diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index ed3e5e949fce30..f35473f8c63057 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -24,8 +24,6 @@ DMA-ISA-LPC.txt - How to do DMA with ISA (and LPC) devices. DMA-attributes.txt - listing of the various possible attributes a DMA region can have -DocBook/ - - directory with DocBook templates etc. for kernel documentation. EDID/ - directory with info on customizing EDID for broken gfx/displays. IPMI.txt @@ -40,8 +38,6 @@ Intel-IOMMU.txt - basic info on the Intel IOMMU virtualization support. Makefile - It's not of interest for those who aren't touching the build system. -Makefile.sphinx - - It's not of interest for those who aren't touching the build system. PCI/ - info related to PCI drivers. RCU/ @@ -264,6 +260,8 @@ logo.gif - full colour GIF image of Linux logo (penguin - Tux). logo.txt - info on creator of above logo & site to get additional images from. +lsm.txt + - Linux Security Modules: General Security Hooks for Linux lzo.txt - kernel LZO decompressor input formats m68k/ diff --git a/Documentation/ABI/stable/sysfs-driver-aspeed-vuart b/Documentation/ABI/stable/sysfs-driver-aspeed-vuart new file mode 100644 index 00000000000000..8062953ce77bae --- /dev/null +++ b/Documentation/ABI/stable/sysfs-driver-aspeed-vuart @@ -0,0 +1,15 @@ +What: /sys/bus/platform/drivers/aspeed-vuart/*/lpc_address +Date: April 2017 +Contact: Jeremy Kerr +Description: Configures which IO port the host side of the UART + will appear on the host <-> BMC LPC bus. +Users: OpenBMC. Proposed changes should be mailed to + openbmc@lists.ozlabs.org + +What: /sys/bus/platform/drivers/aspeed-vuart*/sirq +Date: April 2017 +Contact: Jeremy Kerr +Description: Configures which interrupt number the host side of + the UART will appear on the host <-> BMC LPC bus. +Users: OpenBMC. Proposed changes should be mailed to + openbmc@lists.ozlabs.org diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 8c24d0892f61e3..2db2cdf42d5417 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1425,6 +1425,17 @@ Description: guarantees that the hardware fifo is flushed to the device buffer. +What: /sys/bus/iio/devices/iio:device*/buffer/hwfifo_timeout +KernelVersion: 4.12 +Contact: linux-iio@vger.kernel.org +Description: + A read/write property to provide capability to delay reporting of + samples till a timeout is reached. This allows host processors to + sleep, while the sensor is storing samples in its internal fifo. + The maximum timeout in seconds can be specified by setting + hwfifo_timeout.The current delay can be read by reading + hwfifo_timeout. A value of 0 means that there is no timeout. + What: /sys/bus/iio/devices/iio:deviceX/buffer/hwfifo_watermark KernelVersion: 4.2 Contact: linux-iio@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-bus-iio-meas-spec b/Documentation/ABI/testing/sysfs-bus-iio-meas-spec index 1a6265e92e2faa..6d47e548eee503 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-meas-spec +++ b/Documentation/ABI/testing/sysfs-bus-iio-meas-spec @@ -5,4 +5,3 @@ Description: Reading returns either '1' or '0'. '1' means that the battery level supplied to sensor is below 2.25V. This ABI is available for tsys02d, htu21, ms8607 - This ABI is available for htu21, ms8607 diff --git a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 index 230020e06677d7..deb01593568393 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 +++ b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 @@ -16,6 +16,54 @@ Description: - "OC2REF" : OC2REF signal is used as trigger output. - "OC3REF" : OC3REF signal is used as trigger output. - "OC4REF" : OC4REF signal is used as trigger output. + Additional modes (on TRGO2 only): + - "OC5REF" : OC5REF signal is used as trigger output. + - "OC6REF" : OC6REF signal is used as trigger output. + - "compare_pulse_OC4REF": + OC4REF rising or falling edges generate pulses. + - "compare_pulse_OC6REF": + OC6REF rising or falling edges generate pulses. + - "compare_pulse_OC4REF_r_or_OC6REF_r": + OC4REF or OC6REF rising edges generate pulses. + - "compare_pulse_OC4REF_r_or_OC6REF_f": + OC4REF rising or OC6REF falling edges generate pulses. + - "compare_pulse_OC5REF_r_or_OC6REF_r": + OC5REF or OC6REF rising edges generate pulses. + - "compare_pulse_OC5REF_r_or_OC6REF_f": + OC5REF rising or OC6REF falling edges generate pulses. + + +-----------+ +-------------+ +---------+ + | Prescaler +-> | Counter | +-> | Master | TRGO(2) + +-----------+ +--+--------+-+ |-> | Control +--> + | | || +---------+ + +--v--------+-+ OCxREF || +---------+ + | Chx compare +----------> | Output | ChX + +-----------+-+ | | Control +--> + . | | +---------+ + . | | . + +-----------v-+ OC6REF | . + | Ch6 compare +---------+> + +-------------+ + + Example with: "compare_pulse_OC4REF_r_or_OC6REF_r": + + X + X X + X . . X + X . . X + X . . X + count X . . . . X + . . . . + . . . . + +---------------+ + OC4REF | . . | + +-+ . . +-+ + . +---+ . + OC6REF . | | . + +-------+ +-------+ + +-+ +-+ + TRGO2 | | | | + +-+ +---+ +---------+ What: /sys/bus/iio/devices/triggerX/master_mode KernelVersion: 4.11 diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index 668604fc8e062b..6856da99b6f73b 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -251,3 +251,11 @@ Contact: netdev@vger.kernel.org Description: Indicates the unique physical switch identifier of a switch this port belongs to, as a string. + +What: /sys/class/net//phydev +Date: May 2017 +KernelVersion: 4.13 +Contact: netdev@vger.kernel.org +Description: + Symbolic link to the PHY device this network device is attached + to. diff --git a/Documentation/ABI/testing/sysfs-class-net-phydev b/Documentation/ABI/testing/sysfs-class-net-phydev new file mode 100644 index 00000000000000..c768d5fd849622 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-phydev @@ -0,0 +1,36 @@ +What: /sys/class/mdio_bus///attached_dev +Date: May 2017 +KernelVersion: 4.13 +Contact: netdev@vger.kernel.org +Description: + Symbolic link to the network device this PHY device is + attached to. + +What: /sys/class/mdio_bus///phy_has_fixups +Date: February 2014 +KernelVersion: 3.15 +Contact: netdev@vger.kernel.org +Description: + Boolean value indicating whether the PHY device has + any fixups registered against it (phy_register_fixup) + +What: /sys/class/mdio_bus///phy_id +Date: November 2012 +KernelVersion: 3.8 +Contact: netdev@vger.kernel.org +Description: + 32-bit hexadecimal value corresponding to the PHY device's OUI, + model and revision number. + +What: /sys/class/mdio_bus///phy_interface +Date: February 2014 +KernelVersion: 3.15 +Contact: netdev@vger.kernel.org +Description: + String value indicating the PHY interface, possible + values are:. + (not available), mii, gmii, sgmii, tbi, rev-mii, + rmii, rgmii, rgmii-id, rgmii-rxid, rgmii-txid, rtbi, smii + xgmii, moca, qsgmii, trgmii, 1000base-x, 2500base-x, rxaui, + unknown + diff --git a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop index b31e782bd98506..597a2f3d1efceb 100644 --- a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop +++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop @@ -17,3 +17,11 @@ Description: * 2 -> Dust Cleaning * 4 -> Efficient Thermal Dissipation Mode +What: /sys/devices/platform/ideapad/touchpad +Date: May 2017 +KernelVersion: 4.13 +Contact: "Ritesh Raj Sarraf " +Description: + Control touchpad mode. + * 1 -> Switched On + * 0 -> Switched Off diff --git a/Documentation/ABI/testing/sysfs-uevent b/Documentation/ABI/testing/sysfs-uevent new file mode 100644 index 00000000000000..aa39f8d7bcdff3 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-uevent @@ -0,0 +1,47 @@ +What: /sys/.../uevent +Date: May 2017 +KernelVersion: 4.13 +Contact: Linux kernel mailing list +Description: + Enable passing additional variables for synthetic uevents that + are generated by writing /sys/.../uevent file. + + Recognized extended format is ACTION [UUID [KEY=VALUE ...]. + + The ACTION is compulsory - it is the name of the uevent action + ("add", "change", "remove"). There is no change compared to + previous functionality here. The rest of the extended format + is optional. + + You need to pass UUID first before any KEY=VALUE pairs. + The UUID must be in "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" + format where 'x' is a hex digit. The UUID is considered to be + a transaction identifier so it's possible to use the same UUID + value for one or more synthetic uevents in which case we + logically group these uevents together for any userspace + listeners. The UUID value appears in uevent as + "SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" environment + variable. + + If UUID is not passed in, the generated synthetic uevent gains + "SYNTH_UUID=0" environment variable automatically. + + The KEY=VALUE pairs can contain alphanumeric characters only. + It's possible to define zero or more pairs - each pair is then + delimited by a space character ' '. Each pair appears in + synthetic uevent as "SYNTH_ARG_KEY=VALUE". That means the KEY + name gains "SYNTH_ARG_" prefix to avoid possible collisions + with existing variables. + + Example of valid sequence written to the uevent file: + + add fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed A=1 B=abc + + This generates synthetic uevent including these variables: + + ACTION=add + SYNTH_ARG_A=1 + SYNTH_ARG_B=abc + SYNTH_UUID=fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed +Users: + udev, userspace tools generating synthetic uevents diff --git a/Documentation/DocBook/.gitignore b/Documentation/DocBook/.gitignore deleted file mode 100644 index e05da3f7aa21cb..00000000000000 --- a/Documentation/DocBook/.gitignore +++ /dev/null @@ -1,17 +0,0 @@ -*.xml -*.ps -*.pdf -*.html -*.9.gz -*.9 -*.aux -*.dvi -*.log -*.out -*.png -*.gif -*.svg -*.proc -*.db -media-indices.tmpl -media-entities.tmpl diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile deleted file mode 100644 index 85916f13d330b7..00000000000000 --- a/Documentation/DocBook/Makefile +++ /dev/null @@ -1,282 +0,0 @@ -### -# This makefile is used to generate the kernel documentation, -# primarily based on in-line comments in various source files. -# See Documentation/kernel-doc-nano-HOWTO.txt for instruction in how -# to document the SRC - and how to read it. -# To add a new book the only step required is to add the book to the -# list of DOCBOOKS. - -DOCBOOKS := z8530book.xml \ - kernel-hacking.xml kernel-locking.xml \ - networking.xml \ - filesystems.xml lsm.xml kgdb.xml \ - libata.xml mtdnand.xml librs.xml rapidio.xml \ - s390-drivers.xml scsi.xml \ - sh.xml w1.xml - -ifeq ($(DOCBOOKS),) - -# Skip DocBook build if the user explicitly requested no DOCBOOKS. -.DEFAULT: - @echo " SKIP DocBook $@ target (DOCBOOKS=\"\" specified)." -else -ifneq ($(SPHINXDIRS),) - -# Skip DocBook build if the user explicitly requested a sphinx dir -.DEFAULT: - @echo " SKIP DocBook $@ target (SPHINXDIRS specified)." -else - - -### -# The build process is as follows (targets): -# (xmldocs) [by docproc] -# file.tmpl --> file.xml +--> file.ps (psdocs) [by db2ps or xmlto] -# +--> file.pdf (pdfdocs) [by db2pdf or xmlto] -# +--> DIR=file (htmldocs) [by xmlto] -# +--> man/ (mandocs) [by xmlto] - - -# for PDF and PS output you can choose between xmlto and docbook-utils tools -PDF_METHOD = $(prefer-db2x) -PS_METHOD = $(prefer-db2x) - - -targets += $(DOCBOOKS) -BOOKS := $(addprefix $(obj)/,$(DOCBOOKS)) -xmldocs: $(BOOKS) -sgmldocs: xmldocs - -PS := $(patsubst %.xml, %.ps, $(BOOKS)) -psdocs: $(PS) - -PDF := $(patsubst %.xml, %.pdf, $(BOOKS)) -pdfdocs: $(PDF) - -HTML := $(sort $(patsubst %.xml, %.html, $(BOOKS))) -htmldocs: $(HTML) - $(call cmd,build_main_index) - -MAN := $(patsubst %.xml, %.9, $(BOOKS)) -mandocs: $(MAN) - find $(obj)/man -name '*.9' | xargs gzip -nf - -# Default location for installed man pages -export INSTALL_MAN_PATH = $(objtree)/usr - -installmandocs: mandocs - mkdir -p $(INSTALL_MAN_PATH)/man/man9/ - find $(obj)/man -name '*.9.gz' -printf '%h %f\n' | \ - sort -k 2 -k 1 | uniq -f 1 | sed -e 's: :/:' | \ - xargs install -m 644 -t $(INSTALL_MAN_PATH)/man/man9/ - -# no-op for the DocBook toolchain -epubdocs: -latexdocs: -linkcheckdocs: - -### -#External programs used -KERNELDOCXMLREF = $(srctree)/scripts/kernel-doc-xml-ref -KERNELDOC = $(srctree)/scripts/kernel-doc -DOCPROC = $(objtree)/scripts/docproc -CHECK_LC_CTYPE = $(objtree)/scripts/check-lc_ctype - -# Use a fixed encoding - UTF-8 if the C library has support built-in -# or ASCII if not -LC_CTYPE := $(call try-run, LC_CTYPE=C.UTF-8 $(CHECK_LC_CTYPE),C.UTF-8,C) -export LC_CTYPE - -XMLTOFLAGS = -m $(srctree)/$(src)/stylesheet.xsl -XMLTOFLAGS += --skip-validation - -### -# DOCPROC is used for two purposes: -# 1) To generate a dependency list for a .tmpl file -# 2) To preprocess a .tmpl file and call kernel-doc with -# appropriate parameters. -# The following rules are used to generate the .xml documentation -# required to generate the final targets. (ps, pdf, html). -quiet_cmd_docproc = DOCPROC $@ - cmd_docproc = SRCTREE=$(srctree)/ $(DOCPROC) doc $< >$@ -define rule_docproc - set -e; \ - $(if $($(quiet)cmd_$(1)),echo ' $($(quiet)cmd_$(1))';) \ - $(cmd_$(1)); \ - ( \ - echo 'cmd_$@ := $(cmd_$(1))'; \ - echo $@: `SRCTREE=$(srctree) $(DOCPROC) depend $<`; \ - ) > $(dir $@).$(notdir $@).cmd -endef - -%.xml: %.tmpl $(KERNELDOC) $(DOCPROC) $(KERNELDOCXMLREF) FORCE - $(call if_changed_rule,docproc) - -# Tell kbuild to always build the programs -always := $(hostprogs-y) - -notfoundtemplate = echo "*** You have to install docbook-utils or xmlto ***"; \ - exit 1 -db2xtemplate = db2TYPE -o $(dir $@) $< -xmltotemplate = xmlto TYPE $(XMLTOFLAGS) -o $(dir $@) $< - -# determine which methods are available -ifeq ($(shell which db2ps >/dev/null 2>&1 && echo found),found) - use-db2x = db2x - prefer-db2x = db2x -else - use-db2x = notfound - prefer-db2x = $(use-xmlto) -endif -ifeq ($(shell which xmlto >/dev/null 2>&1 && echo found),found) - use-xmlto = xmlto - prefer-xmlto = xmlto -else - use-xmlto = notfound - prefer-xmlto = $(use-db2x) -endif - -# the commands, generated from the chosen template -quiet_cmd_db2ps = PS $@ - cmd_db2ps = $(subst TYPE,ps, $($(PS_METHOD)template)) -%.ps : %.xml - $(call cmd,db2ps) - -quiet_cmd_db2pdf = PDF $@ - cmd_db2pdf = $(subst TYPE,pdf, $($(PDF_METHOD)template)) -%.pdf : %.xml - $(call cmd,db2pdf) - - -index = index.html -main_idx = $(obj)/$(index) -quiet_cmd_build_main_index = HTML $(main_idx) - cmd_build_main_index = rm -rf $(main_idx); \ - echo '

Linux Kernel HTML Documentation

' >> $(main_idx) && \ - echo '

Kernel Version: $(KERNELVERSION)

' >> $(main_idx) && \ - cat $(HTML) >> $(main_idx) - -quiet_cmd_db2html = HTML $@ - cmd_db2html = xmlto html $(XMLTOFLAGS) -o $(patsubst %.html,%,$@) $< && \ - echo ' \ - $(patsubst %.html,%,$(notdir $@))

' > $@ - -### -# Rules to create an aux XML and .db, and use them to re-process the DocBook XML -# to fill internal hyperlinks - gen_aux_xml = : - quiet_gen_aux_xml = echo ' XMLREF $@' -silent_gen_aux_xml = : -%.aux.xml: %.xml - @$($(quiet)gen_aux_xml) - @rm -rf $@ - @(cat $< | egrep "^ $<.db) - @$(KERNELDOCXMLREF) -db $<.db $< > $@ -.PRECIOUS: %.aux.xml - -%.html: %.aux.xml - @(which xmlto > /dev/null 2>&1) || \ - (echo "*** You need to install xmlto ***"; \ - exit 1) - @rm -rf $@ $(patsubst %.html,%,$@) - $(call cmd,db2html) - @if [ ! -z "$(PNG-$(basename $(notdir $@)))" ]; then \ - cp $(PNG-$(basename $(notdir $@))) $(patsubst %.html,%,$@); fi - -quiet_cmd_db2man = MAN $@ - cmd_db2man = if grep -q refentry $<; then xmlto man $(XMLTOFLAGS) -o $(obj)/man/$(*F) $< ; fi -%.9 : %.xml - @(which xmlto > /dev/null 2>&1) || \ - (echo "*** You need to install xmlto ***"; \ - exit 1) - $(Q)mkdir -p $(obj)/man/$(*F) - $(call cmd,db2man) - @touch $@ - -### -# Rules to generate postscripts and PNG images from .fig format files -quiet_cmd_fig2eps = FIG2EPS $@ - cmd_fig2eps = fig2dev -Leps $< $@ - -%.eps: %.fig - @(which fig2dev > /dev/null 2>&1) || \ - (echo "*** You need to install transfig ***"; \ - exit 1) - $(call cmd,fig2eps) - -quiet_cmd_fig2png = FIG2PNG $@ - cmd_fig2png = fig2dev -Lpng $< $@ - -%.png: %.fig - @(which fig2dev > /dev/null 2>&1) || \ - (echo "*** You need to install transfig ***"; \ - exit 1) - $(call cmd,fig2png) - -### -# Rule to convert a .c file to inline XML documentation - gen_xml = : - quiet_gen_xml = echo ' GEN $@' -silent_gen_xml = : -%.xml: %.c - @$($(quiet)gen_xml) - @( \ - echo ""; \ - expand --tabs=8 < $< | \ - sed -e "s/&/\\&/g" \ - -e "s//\\>/g"; \ - echo "") > $@ - -endif # DOCBOOKS="" -endif # SPHINDIR=... - -### -# Help targets as used by the top-level makefile -dochelp: - @echo ' Linux kernel internal documentation in different formats (DocBook):' - @echo ' htmldocs - HTML' - @echo ' pdfdocs - PDF' - @echo ' psdocs - Postscript' - @echo ' xmldocs - XML DocBook' - @echo ' mandocs - man pages' - @echo ' installmandocs - install man pages generated by mandocs to INSTALL_MAN_PATH'; \ - echo ' (default: $(INSTALL_MAN_PATH))'; \ - echo '' - @echo ' cleandocs - clean all generated DocBook files' - @echo - @echo ' make DOCBOOKS="s1.xml s2.xml" [target] Generate only docs s1.xml s2.xml' - @echo ' valid values for DOCBOOKS are: $(DOCBOOKS)' - @echo - @echo " make DOCBOOKS=\"\" [target] Don't generate docs from Docbook" - @echo ' This is useful to generate only the ReST docs (Sphinx)' - - -### -# Temporary files left by various tools -clean-files := $(DOCBOOKS) \ - $(patsubst %.xml, %.dvi, $(DOCBOOKS)) \ - $(patsubst %.xml, %.aux, $(DOCBOOKS)) \ - $(patsubst %.xml, %.tex, $(DOCBOOKS)) \ - $(patsubst %.xml, %.log, $(DOCBOOKS)) \ - $(patsubst %.xml, %.out, $(DOCBOOKS)) \ - $(patsubst %.xml, %.ps, $(DOCBOOKS)) \ - $(patsubst %.xml, %.pdf, $(DOCBOOKS)) \ - $(patsubst %.xml, %.html, $(DOCBOOKS)) \ - $(patsubst %.xml, %.9, $(DOCBOOKS)) \ - $(patsubst %.xml, %.aux.xml, $(DOCBOOKS)) \ - $(patsubst %.xml, %.xml.db, $(DOCBOOKS)) \ - $(patsubst %.xml, %.xml, $(DOCBOOKS)) \ - $(patsubst %.xml, .%.xml.cmd, $(DOCBOOKS)) \ - $(index) - -clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man - -cleandocs: - $(Q)rm -f $(call objectify, $(clean-files)) - $(Q)rm -rf $(call objectify, $(clean-dirs)) - -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable so we can use it in if_changed and friends. - -.PHONY: $(PHONY) diff --git a/Documentation/DocBook/filesystems.tmpl b/Documentation/DocBook/filesystems.tmpl deleted file mode 100644 index 6006b6358c867f..00000000000000 --- a/Documentation/DocBook/filesystems.tmpl +++ /dev/null @@ -1,381 +0,0 @@ - - - - - - Linux Filesystems API - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - The Linux VFS - The Filesystem types -!Iinclude/linux/fs.h - - The Directory Cache -!Efs/dcache.c -!Iinclude/linux/dcache.h - - Inode Handling -!Efs/inode.c -!Efs/bad_inode.c - - Registration and Superblocks -!Efs/super.c - - File Locks -!Efs/locks.c -!Ifs/locks.c - - Other Functions -!Efs/mpage.c -!Efs/namei.c -!Efs/buffer.c -!Eblock/bio.c -!Efs/seq_file.c -!Efs/filesystems.c -!Efs/fs-writeback.c -!Efs/block_dev.c - - - - - The proc filesystem - - sysctl interface -!Ekernel/sysctl.c - - - proc filesystem interface -!Ifs/proc/base.c - - - - - Events based on file descriptors -!Efs/eventfd.c - - - - The Filesystem for Exporting Kernel Objects -!Efs/sysfs/file.c -!Efs/sysfs/symlink.c - - - - The debugfs filesystem - - debugfs interface -!Efs/debugfs/inode.c -!Efs/debugfs/file.c - - - - - - The Linux Journalling API - - - - Roger - Gammans - -

- rgammans@computer-surgery.co.uk -
- - - - - - - Stephen - Tweedie - -
- sct@redhat.com -
- - - - - - 2002 - Roger Gammans - - - - The Linux Journalling API - - - Overview - - Details - -The journalling layer is easy to use. You need to -first of all create a journal_t data structure. There are -two calls to do this dependent on how you decide to allocate the physical -media on which the journal resides. The jbd2_journal_init_inode() call -is for journals stored in filesystem inodes, or the jbd2_journal_init_dev() -call can be used for journal stored on a raw device (in a continuous range -of blocks). A journal_t is a typedef for a struct pointer, so when -you are finally finished make sure you call jbd2_journal_destroy() on it -to free up any used kernel memory. - - - -Once you have got your journal_t object you need to 'mount' or load the journal -file. The journalling layer expects the space for the journal was already -allocated and initialized properly by the userspace tools. When loading the -journal you must call jbd2_journal_load() to process journal contents. If the -client file system detects the journal contents does not need to be processed -(or even need not have valid contents), it may call jbd2_journal_wipe() to -clear the journal contents before calling jbd2_journal_load(). - - - -Note that jbd2_journal_wipe(..,0) calls jbd2_journal_skip_recovery() for you if -it detects any outstanding transactions in the journal and similarly -jbd2_journal_load() will call jbd2_journal_recover() if necessary. I would -advise reading ext4_load_journal() in fs/ext4/super.c for examples on this -stage. - - - -Now you can go ahead and start modifying the underlying -filesystem. Almost. - - - - -You still need to actually journal your filesystem changes, this -is done by wrapping them into transactions. Additionally you -also need to wrap the modification of each of the buffers -with calls to the journal layer, so it knows what the modifications -you are actually making are. To do this use jbd2_journal_start() which -returns a transaction handle. - - - -jbd2_journal_start() -and its counterpart jbd2_journal_stop(), which indicates the end of a -transaction are nestable calls, so you can reenter a transaction if necessary, -but remember you must call jbd2_journal_stop() the same number of times as -jbd2_journal_start() before the transaction is completed (or more accurately -leaves the update phase). Ext4/VFS makes use of this feature to simplify -handling of inode dirtying, quota support, etc. - - - -Inside each transaction you need to wrap the modifications to the -individual buffers (blocks). Before you start to modify a buffer you -need to call jbd2_journal_get_{create,write,undo}_access() as appropriate, -this allows the journalling layer to copy the unmodified data if it -needs to. After all the buffer may be part of a previously uncommitted -transaction. -At this point you are at last ready to modify a buffer, and once -you are have done so you need to call jbd2_journal_dirty_{meta,}data(). -Or if you've asked for access to a buffer you now know is now longer -required to be pushed back on the device you can call jbd2_journal_forget() -in much the same way as you might have used bforget() in the past. - - - -A jbd2_journal_flush() may be called at any time to commit and checkpoint -all your transactions. - - - -Then at umount time , in your put_super() you can then call jbd2_journal_destroy() -to clean up your in-core journal object. - - - -Unfortunately there a couple of ways the journal layer can cause a deadlock. -The first thing to note is that each task can only have -a single outstanding transaction at any one time, remember nothing -commits until the outermost jbd2_journal_stop(). This means -you must complete the transaction at the end of each file/inode/address -etc. operation you perform, so that the journalling system isn't re-entered -on another journal. Since transactions can't be nested/batched -across differing journals, and another filesystem other than -yours (say ext4) may be modified in a later syscall. - - - -The second case to bear in mind is that jbd2_journal_start() can -block if there isn't enough space in the journal for your transaction -(based on the passed nblocks param) - when it blocks it merely(!) needs to -wait for transactions to complete and be committed from other tasks, -so essentially we are waiting for jbd2_journal_stop(). So to avoid -deadlocks you must treat jbd2_journal_start/stop() as if they -were semaphores and include them in your semaphore ordering rules to prevent -deadlocks. Note that jbd2_journal_extend() has similar blocking behaviour to -jbd2_journal_start() so you can deadlock here just as easily as on -jbd2_journal_start(). - - - -Try to reserve the right number of blocks the first time. ;-). This will -be the maximum number of blocks you are going to touch in this transaction. -I advise having a look at at least ext4_jbd.h to see the basis on which -ext4 uses to make these decisions. - - - -Another wriggle to watch out for is your on-disk block allocation strategy. -Why? Because, if you do a delete, you need to ensure you haven't reused any -of the freed blocks until the transaction freeing these blocks commits. If you -reused these blocks and crash happens, there is no way to restore the contents -of the reallocated blocks at the end of the last fully committed transaction. - -One simple way of doing this is to mark blocks as free in internal in-memory -block allocation structures only after the transaction freeing them commits. -Ext4 uses journal commit callback for this purpose. - - - -With journal commit callbacks you can ask the journalling layer to call a -callback function when the transaction is finally committed to disk, so that -you can do some of your own management. You ask the journalling layer for -calling the callback by simply setting journal->j_commit_callback function -pointer and that function is called after each transaction commit. You can also -use transaction->t_private_list for attaching entries to a transaction that -need processing when the transaction commits. - - - -JBD2 also provides a way to block all transaction updates via -jbd2_journal_{un,}lock_updates(). Ext4 uses this when it wants a window with a -clean and stable fs for a moment. E.g. - - - - - jbd2_journal_lock_updates() //stop new stuff happening.. - jbd2_journal_flush() // checkpoint everything. - ..do stuff on stable fs - jbd2_journal_unlock_updates() // carry on with filesystem use. - - - -The opportunities for abuse and DOS attacks with this should be obvious, -if you allow unprivileged userspace to trigger codepaths containing these -calls. - - - - - - Summary - -Using the journal is a matter of wrapping the different context changes, -being each mount, each modification (transaction) and each changed buffer -to tell the journalling layer about them. - - - - - - - - Data Types - - The journalling layer uses typedefs to 'hide' the concrete definitions - of the structures used. As a client of the JBD2 layer you can - just rely on the using the pointer as a magic cookie of some sort. - - Obviously the hiding is not enforced as this is 'C'. - - Structures -!Iinclude/linux/jbd2.h - - - - - Functions - - The functions here are split into two groups those that - affect a journal as a whole, and those which are used to - manage transactions - - Journal Level -!Efs/jbd2/journal.c -!Ifs/jbd2/recovery.c - - Transasction Level -!Efs/jbd2/transaction.c - - - - See also - - - - Journaling the Linux ext2fs Filesystem, LinuxExpo 98, Stephen Tweedie - - - - - - - Ext3 Journalling FileSystem, OLS 2000, Dr. Stephen Tweedie - - - - - - - - - splice API - - splice is a method for moving blocks of data around inside the - kernel, without continually transferring them between the kernel - and user space. - -!Ffs/splice.c - - - - pipes API - - Pipe interfaces are all for in-kernel (builtin image) use. - They are not exported for use by modules. - -!Iinclude/linux/pipe_fs_i.h -!Ffs/pipe.c - - - diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl deleted file mode 100644 index da5c087462b1df..00000000000000 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ /dev/null @@ -1,1312 +0,0 @@ - - - - - - Unreliable Guide To Hacking The Linux Kernel - - - - Rusty - Russell - -
- rusty@rustcorp.com.au -
- - - - - - 2005 - Rusty Russell - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - This is the first release of this document as part of the kernel tarball. - - - - - - - - Introduction - - Welcome, gentle reader, to Rusty's Remarkably Unreliable Guide to Linux - Kernel Hacking. This document describes the common routines and - general requirements for kernel code: its goal is to serve as a - primer for Linux kernel development for experienced C - programmers. I avoid implementation details: that's what the - code is for, and I ignore whole tracts of useful routines. - - - Before you read this, please understand that I never wanted to - write this document, being grossly under-qualified, but I always - wanted to read it, and this was the only way. I hope it will - grow into a compendium of best practice, common starting points - and random information. - - - - - The Players - - - At any time each of the CPUs in a system can be: - - - - - - not associated with any process, serving a hardware interrupt; - - - - - - not associated with any process, serving a softirq or tasklet; - - - - - - running in kernel space, associated with a process (user context); - - - - - - running a process in user space. - - - - - - There is an ordering between these. The bottom two can preempt - each other, but above that is a strict hierarchy: each can only be - preempted by the ones above it. For example, while a softirq is - running on a CPU, no other softirq will preempt it, but a hardware - interrupt can. However, any other CPUs in the system execute - independently. - - - - We'll see a number of ways that the user context can block - interrupts, to become truly non-preemptable. - - - - User Context - - - User context is when you are coming in from a system call or other - trap: like userspace, you can be preempted by more important tasks - and by interrupts. You can sleep, by calling - schedule(). - - - - - You are always in user context on module load and unload, - and on operations on the block device layer. - - - - - In user context, the current pointer (indicating - the task we are currently executing) is valid, and - in_interrupt() - (include/linux/interrupt.h) is false - . - - - - - Beware that if you have preemption or softirqs disabled - (see below), in_interrupt() will return a - false positive. - - - - - - Hardware Interrupts (Hard IRQs) - - - Timer ticks, network cards and - keyboard are examples of real - hardware which produce interrupts at any time. The kernel runs - interrupt handlers, which services the hardware. The kernel - guarantees that this handler is never re-entered: if the same - interrupt arrives, it is queued (or dropped). Because it - disables interrupts, this handler has to be fast: frequently it - simply acknowledges the interrupt, marks a 'software interrupt' - for execution and exits. - - - - You can tell you are in a hardware interrupt, because - in_irq() returns true. - - - - Beware that this will return a false positive if interrupts are disabled - (see below). - - - - - - Software Interrupt Context: Softirqs and Tasklets - - - Whenever a system call is about to return to userspace, or a - hardware interrupt handler exits, any 'software interrupts' - which are marked pending (usually by hardware interrupts) are - run (kernel/softirq.c). - - - - Much of the real interrupt handling work is done here. Early in - the transition to SMP, there were only 'bottom - halves' (BHs), which didn't take advantage of multiple CPUs. Shortly - after we switched from wind-up computers made of match-sticks and snot, - we abandoned this limitation and switched to 'softirqs'. - - - - include/linux/interrupt.h lists the - different softirqs. A very important softirq is the - timer softirq (include/linux/timer.h): you can - register to have it call functions for you in a given length of - time. - - - - Softirqs are often a pain to deal with, since the same softirq - will run simultaneously on more than one CPU. For this reason, - tasklets (include/linux/interrupt.h) are more - often used: they are dynamically-registrable (meaning you can have - as many as you want), and they also guarantee that any tasklet - will only run on one CPU at any time, although different tasklets - can run simultaneously. - - - - The name 'tasklet' is misleading: they have nothing to do with 'tasks', - and probably more to do with some bad vodka Alexey Kuznetsov had at the - time. - - - - - You can tell you are in a softirq (or tasklet) - using the in_softirq() macro - (include/linux/interrupt.h). - - - - Beware that this will return a false positive if a bh lock (see below) - is held. - - - - - - - Some Basic Rules - - - - No memory protection - - - If you corrupt memory, whether in user context or - interrupt context, the whole machine will crash. Are you - sure you can't do what you want in userspace? - - - - - - No floating point or MMX - - - The FPU context is not saved; even in user - context the FPU state probably won't - correspond with the current process: you would mess with some - user process' FPU state. If you really want - to do this, you would have to explicitly save/restore the full - FPU state (and avoid context switches). It - is generally a bad idea; use fixed point arithmetic first. - - - - - - A rigid stack limit - - - Depending on configuration options the kernel stack is about 3K to 6K for most 32-bit architectures: it's - about 14K on most 64-bit archs, and often shared with interrupts - so you can't use it all. Avoid deep recursion and huge local - arrays on the stack (allocate them dynamically instead). - - - - - - The Linux kernel is portable - - - Let's keep it that way. Your code should be 64-bit clean, - and endian-independent. You should also minimize CPU - specific stuff, e.g. inline assembly should be cleanly - encapsulated and minimized to ease porting. Generally it - should be restricted to the architecture-dependent part of - the kernel tree. - - - - - - - - ioctls: Not writing a new system call - - - A system call generally looks like this - - - -asmlinkage long sys_mycall(int arg) -{ - return 0; -} - - - - First, in most cases you don't want to create a new system call. - You create a character device and implement an appropriate ioctl - for it. This is much more flexible than system calls, doesn't have - to be entered in every architecture's - include/asm/unistd.h and - arch/kernel/entry.S file, and is much more - likely to be accepted by Linus. - - - - If all your routine does is read or write some parameter, consider - implementing a sysfs interface instead. - - - - Inside the ioctl you're in user context to a process. When a - error occurs you return a negated errno (see - include/linux/errno.h), - otherwise you return 0. - - - - After you slept you should check if a signal occurred: the - Unix/Linux way of handling signals is to temporarily exit the - system call with the -ERESTARTSYS error. The - system call entry code will switch back to user context, process - the signal handler and then your system call will be restarted - (unless the user disabled that). So you should be prepared to - process the restart, e.g. if you're in the middle of manipulating - some data structure. - - - -if (signal_pending(current)) - return -ERESTARTSYS; - - - - If you're doing longer computations: first think userspace. If you - really want to do it in kernel you should - regularly check if you need to give up the CPU (remember there is - cooperative multitasking per CPU). Idiom: - - - -cond_resched(); /* Will sleep */ - - - - A short note on interface design: the UNIX system call motto is - "Provide mechanism not policy". - - - - - Recipes for Deadlock - - - You cannot call any routines which may sleep, unless: - - - - - You are in user context. - - - - - - You do not own any spinlocks. - - - - - - You have interrupts enabled (actually, Andi Kleen says - that the scheduling code will enable them for you, but - that's probably not what you wanted). - - - - - - Note that some functions may sleep implicitly: common ones are - the user space access functions (*_user) and memory allocation - functions without GFP_ATOMIC. - - - - You should always compile your kernel - CONFIG_DEBUG_ATOMIC_SLEEP on, and it will warn - you if you break these rules. If you do break - the rules, you will eventually lock up your box. - - - - Really. - - - - - Common Routines - - - - <function>printk()</function> - <filename class="headerfile">include/linux/kernel.h</filename> - - - - printk() feeds kernel messages to the - console, dmesg, and the syslog daemon. It is useful for debugging - and reporting errors, and can be used inside interrupt context, - but use with caution: a machine which has its console flooded with - printk messages is unusable. It uses a format string mostly - compatible with ANSI C printf, and C string concatenation to give - it a first "priority" argument: - - - -printk(KERN_INFO "i = %u\n", i); - - - - See include/linux/kernel.h; - for other KERN_ values; these are interpreted by syslog as the - level. Special case: for printing an IP address use - - - -__be32 ipaddress; -printk(KERN_INFO "my ip: %pI4\n", &ipaddress); - - - - printk() internally uses a 1K buffer and does - not catch overruns. Make sure that will be enough. - - - - - You will know when you are a real kernel hacker - when you start typoing printf as printk in your user programs :) - - - - - - - - Another sidenote: the original Unix Version 6 sources had a - comment on top of its printf function: "Printf should not be - used for chit-chat". You should follow that advice. - - - - - - - <function>copy_[to/from]_user()</function> - / - <function>get_user()</function> - / - <function>put_user()</function> - <filename class="headerfile">include/linux/uaccess.h</filename> - - - - [SLEEPS] - - - - put_user() and get_user() - are used to get and put single values (such as an int, char, or - long) from and to userspace. A pointer into userspace should - never be simply dereferenced: data should be copied using these - routines. Both return -EFAULT or 0. - - - copy_to_user() and - copy_from_user() are more general: they copy - an arbitrary amount of data to and from userspace. - - - Unlike put_user() and - get_user(), they return the amount of - uncopied data (ie. 0 still means - success). - - - [Yes, this moronic interface makes me cringe. The flamewar comes up every year or so. --RR.] - - - The functions may sleep implicitly. This should never be called - outside user context (it makes no sense), with interrupts - disabled, or a spinlock held. - - - - - <function>kmalloc()</function>/<function>kfree()</function> - <filename class="headerfile">include/linux/slab.h</filename> - - - [MAY SLEEP: SEE BELOW] - - - - These routines are used to dynamically request pointer-aligned - chunks of memory, like malloc and free do in userspace, but - kmalloc() takes an extra flag word. - Important values: - - - - - - - GFP_KERNEL - - - - - May sleep and swap to free memory. Only allowed in user - context, but is the most reliable way to allocate memory. - - - - - - - - GFP_ATOMIC - - - - - Don't sleep. Less reliable than GFP_KERNEL, - but may be called from interrupt context. You should - really have a good out-of-memory - error-handling strategy. - - - - - - - - GFP_DMA - - - - - Allocate ISA DMA lower than 16MB. If you don't know what that - is you don't need it. Very unreliable. - - - - - - - If you see a sleeping function called from invalid - context warning message, then maybe you called a - sleeping allocation function from interrupt context without - GFP_ATOMIC. You should really fix that. - Run, don't walk. - - - - If you are allocating at least PAGE_SIZE - (include/asm/page.h) bytes, - consider using __get_free_pages() - - (include/linux/mm.h). It - takes an order argument (0 for page sized, 1 for double page, 2 - for four pages etc.) and the same memory priority flag word as - above. - - - - If you are allocating more than a page worth of bytes you can use - vmalloc(). It'll allocate virtual memory in - the kernel map. This block is not contiguous in physical memory, - but the MMU makes it look like it is for you - (so it'll only look contiguous to the CPUs, not to external device - drivers). If you really need large physically contiguous memory - for some weird device, you have a problem: it is poorly supported - in Linux because after some time memory fragmentation in a running - kernel makes it hard. The best way is to allocate the block early - in the boot process via the alloc_bootmem() - routine. - - - - Before inventing your own cache of often-used objects consider - using a slab cache in - include/linux/slab.h - - - - - <function>current</function> - <filename class="headerfile">include/asm/current.h</filename> - - - This global variable (really a macro) contains a pointer to - the current task structure, so is only valid in user context. - For example, when a process makes a system call, this will - point to the task structure of the calling process. It is - not NULL in interrupt context. - - - - - <function>mdelay()</function>/<function>udelay()</function> - <filename class="headerfile">include/asm/delay.h</filename> - <filename class="headerfile">include/linux/delay.h</filename> - - - - The udelay() and ndelay() functions can be used for small pauses. - Do not use large values with them as you risk - overflow - the helper function mdelay() is useful - here, or consider msleep(). - - - - - <function>cpu_to_be32()</function>/<function>be32_to_cpu()</function>/<function>cpu_to_le32()</function>/<function>le32_to_cpu()</function> - <filename class="headerfile">include/asm/byteorder.h</filename> - - - - The cpu_to_be32() family (where the "32" can - be replaced by 64 or 16, and the "be" can be replaced by "le") are - the general way to do endian conversions in the kernel: they - return the converted value. All variations supply the reverse as - well: be32_to_cpu(), etc. - - - - There are two major variations of these functions: the pointer - variation, such as cpu_to_be32p(), which take - a pointer to the given type, and return the converted value. The - other variation is the "in-situ" family, such as - cpu_to_be32s(), which convert value referred - to by the pointer, and return void. - - - - - <function>local_irq_save()</function>/<function>local_irq_restore()</function> - <filename class="headerfile">include/linux/irqflags.h</filename> - - - - These routines disable hard interrupts on the local CPU, and - restore them. They are reentrant; saving the previous state in - their one unsigned long flags argument. If you - know that interrupts are enabled, you can simply use - local_irq_disable() and - local_irq_enable(). - - - - - <function>local_bh_disable()</function>/<function>local_bh_enable()</function> - <filename class="headerfile">include/linux/interrupt.h</filename> - - - These routines disable soft interrupts on the local CPU, and - restore them. They are reentrant; if soft interrupts were - disabled before, they will still be disabled after this pair - of functions has been called. They prevent softirqs and tasklets - from running on the current CPU. - - - - - <function>smp_processor_id</function>() - <filename class="headerfile">include/asm/smp.h</filename> - - - get_cpu() disables preemption (so you won't - suddenly get moved to another CPU) and returns the current - processor number, between 0 and NR_CPUS. Note - that the CPU numbers are not necessarily continuous. You return - it again with put_cpu() when you are done. - - - If you know you cannot be preempted by another task (ie. you are - in interrupt context, or have preemption disabled) you can use - smp_processor_id(). - - - - - <type>__init</type>/<type>__exit</type>/<type>__initdata</type> - <filename class="headerfile">include/linux/init.h</filename> - - - After boot, the kernel frees up a special section; functions - marked with __init and data structures marked with - __initdata are dropped after boot is complete: similarly - modules discard this memory after initialization. __exit - is used to declare a function which is only required on exit: the - function will be dropped if this file is not compiled as a module. - See the header file for use. Note that it makes no sense for a function - marked with __init to be exported to modules with - EXPORT_SYMBOL() - this will break. - - - - - - <function>__initcall()</function>/<function>module_init()</function> - <filename class="headerfile">include/linux/init.h</filename> - - Many parts of the kernel are well served as a module - (dynamically-loadable parts of the kernel). Using the - module_init() and - module_exit() macros it is easy to write code - without #ifdefs which can operate both as a module or built into - the kernel. - - - - The module_init() macro defines which - function is to be called at module insertion time (if the file is - compiled as a module), or at boot time: if the file is not - compiled as a module the module_init() macro - becomes equivalent to __initcall(), which - through linker magic ensures that the function is called on boot. - - - - The function can return a negative error number to cause - module loading to fail (unfortunately, this has no effect if - the module is compiled into the kernel). This function is - called in user context with interrupts enabled, so it can sleep. - - - - - <function>module_exit()</function> - <filename class="headerfile">include/linux/init.h</filename> - - - This macro defines the function to be called at module removal - time (or never, in the case of the file compiled into the - kernel). It will only be called if the module usage count has - reached zero. This function can also sleep, but cannot fail: - everything must be cleaned up by the time it returns. - - - - Note that this macro is optional: if it is not present, your - module will not be removable (except for 'rmmod -f'). - - - - - <function>try_module_get()</function>/<function>module_put()</function> - <filename class="headerfile">include/linux/module.h</filename> - - - These manipulate the module usage count, to protect against - removal (a module also can't be removed if another module uses one - of its exported symbols: see below). Before calling into module - code, you should call try_module_get() on - that module: if it fails, then the module is being removed and you - should act as if it wasn't there. Otherwise, you can safely enter - the module, and call module_put() when you're - finished. - - - - Most registerable structures have an - owner field, such as in the - file_operations structure. Set this field - to the macro THIS_MODULE. - - - - - - - - Wait Queues - <filename class="headerfile">include/linux/wait.h</filename> - - - [SLEEPS] - - - - A wait queue is used to wait for someone to wake you up when a - certain condition is true. They must be used carefully to ensure - there is no race condition. You declare a - wait_queue_head_t, and then processes which want to - wait for that condition declare a wait_queue_t - referring to themselves, and place that in the queue. - - - - Declaring - - - You declare a wait_queue_head_t using the - DECLARE_WAIT_QUEUE_HEAD() macro, or using the - init_waitqueue_head() routine in your - initialization code. - - - - - Queuing - - - Placing yourself in the waitqueue is fairly complex, because you - must put yourself in the queue before checking the condition. - There is a macro to do this: - wait_event_interruptible() - - include/linux/wait.h The - first argument is the wait queue head, and the second is an - expression which is evaluated; the macro returns - 0 when this expression is true, or - -ERESTARTSYS if a signal is received. - The wait_event() version ignores signals. - - - - - - Waking Up Queued Tasks - - - Call wake_up() - - include/linux/wait.h;, - which will wake up every process in the queue. The exception is - if one has TASK_EXCLUSIVE set, in which case - the remainder of the queue will not be woken. There are other variants - of this basic function available in the same header. - - - - - - Atomic Operations - - - Certain operations are guaranteed atomic on all platforms. The - first class of operations work on atomic_t - - include/asm/atomic.h; this - contains a signed integer (at least 32 bits long), and you must use - these functions to manipulate or read atomic_t variables. - atomic_read() and - atomic_set() get and set the counter, - atomic_add(), - atomic_sub(), - atomic_inc(), - atomic_dec(), and - atomic_dec_and_test() (returns - true if it was decremented to zero). - - - - Yes. It returns true (i.e. != 0) if the - atomic variable is zero. - - - - Note that these functions are slower than normal arithmetic, and - so should not be used unnecessarily. - - - - The second class of atomic operations is atomic bit operations on an - unsigned long, defined in - - include/linux/bitops.h. These - operations generally take a pointer to the bit pattern, and a bit - number: 0 is the least significant bit. - set_bit(), clear_bit() - and change_bit() set, clear, and flip the - given bit. test_and_set_bit(), - test_and_clear_bit() and - test_and_change_bit() do the same thing, - except return true if the bit was previously set; these are - particularly useful for atomically setting flags. - - - - It is possible to call these operations with bit indices greater - than BITS_PER_LONG. The resulting behavior is strange on big-endian - platforms though so it is a good idea not to do this. - - - - - Symbols - - - Within the kernel proper, the normal linking rules apply - (ie. unless a symbol is declared to be file scope with the - static keyword, it can be used anywhere in the - kernel). However, for modules, a special exported symbol table is - kept which limits the entry points to the kernel proper. Modules - can also export symbols. - - - - <function>EXPORT_SYMBOL()</function> - <filename class="headerfile">include/linux/export.h</filename> - - - This is the classic method of exporting a symbol: dynamically - loaded modules will be able to use the symbol as normal. - - - - - <function>EXPORT_SYMBOL_GPL()</function> - <filename class="headerfile">include/linux/export.h</filename> - - - Similar to EXPORT_SYMBOL() except that the - symbols exported by EXPORT_SYMBOL_GPL() can - only be seen by modules with a - MODULE_LICENSE() that specifies a GPL - compatible license. It implies that the function is considered - an internal implementation issue, and not really an interface. - Some maintainers and developers may however - require EXPORT_SYMBOL_GPL() when adding any new APIs or functionality. - - - - - - Routines and Conventions - - - Double-linked lists - <filename class="headerfile">include/linux/list.h</filename> - - - There used to be three sets of linked-list routines in the kernel - headers, but this one is the winner. If you don't have some - particular pressing need for a single list, it's a good choice. - - - - In particular, list_for_each_entry is useful. - - - - - Return Conventions - - - For code called in user context, it's very common to defy C - convention, and return 0 for success, - and a negative error number - (eg. -EFAULT) for failure. This can be - unintuitive at first, but it's fairly widespread in the kernel. - - - - Using ERR_PTR() - - include/linux/err.h; to - encode a negative error number into a pointer, and - IS_ERR() and PTR_ERR() - to get it back out again: avoids a separate pointer parameter for - the error number. Icky, but in a good way. - - - - - Breaking Compilation - - - Linus and the other developers sometimes change function or - structure names in development kernels; this is not done just to - keep everyone on their toes: it reflects a fundamental change - (eg. can no longer be called with interrupts on, or does extra - checks, or doesn't do checks which were caught before). Usually - this is accompanied by a fairly complete note to the linux-kernel - mailing list; search the archive. Simply doing a global replace - on the file usually makes things worse. - - - - - Initializing structure members - - - The preferred method of initializing structures is to use - designated initialisers, as defined by ISO C99, eg: - - -static struct block_device_operations opt_fops = { - .open = opt_open, - .release = opt_release, - .ioctl = opt_ioctl, - .check_media_change = opt_media_change, -}; - - - This makes it easy to grep for, and makes it clear which - structure fields are set. You should do this because it looks - cool. - - - - - GNU Extensions - - - GNU Extensions are explicitly allowed in the Linux kernel. - Note that some of the more complex ones are not very well - supported, due to lack of general use, but the following are - considered standard (see the GCC info page section "C - Extensions" for more details - Yes, really the info page, the - man page is only a short summary of the stuff in info). - - - - - Inline functions - - - - - Statement expressions (ie. the ({ and }) constructs). - - - - - Declaring attributes of a function / variable / type - (__attribute__) - - - - - typeof - - - - - Zero length arrays - - - - - Macro varargs - - - - - Arithmetic on void pointers - - - - - Non-Constant initializers - - - - - Assembler Instructions (not outside arch/ and include/asm/) - - - - - Function names as strings (__func__). - - - - - __builtin_constant_p() - - - - - - Be wary when using long long in the kernel, the code gcc generates for - it is horrible and worse: division and multiplication does not work - on i386 because the GCC runtime functions for it are missing from - the kernel environment. - - - - - - - C++ - - - Using C++ in the kernel is usually a bad idea, because the - kernel does not provide the necessary runtime environment - and the include files are not tested for it. It is still - possible, but not recommended. If you really want to do - this, forget about exceptions at least. - - - - - #if - - - It is generally considered cleaner to use macros in header files - (or at the top of .c files) to abstract away functions rather than - using `#if' pre-processor statements throughout the source code. - - - - - - Putting Your Stuff in the Kernel - - - In order to get your stuff into shape for official inclusion, or - even to make a neat patch, there's administrative work to be - done: - - - - - Figure out whose pond you've been pissing in. Look at the top of - the source files, inside the MAINTAINERS - file, and last of all in the CREDITS file. - You should coordinate with this person to make sure you're not - duplicating effort, or trying something that's already been - rejected. - - - - Make sure you put your name and EMail address at the top of - any files you create or mangle significantly. This is the - first place people will look when they find a bug, or when - they want to make a change. - - - - - - Usually you want a configuration option for your kernel hack. - Edit Kconfig in the appropriate directory. - The Config language is simple to use by cut and paste, and there's - complete documentation in - Documentation/kbuild/kconfig-language.txt. - - - - In your description of the option, make sure you address both the - expert user and the user who knows nothing about your feature. Mention - incompatibilities and issues here. Definitely - end your description with if in doubt, say N - (or, occasionally, `Y'); this is for people who have no - idea what you are talking about. - - - - - - Edit the Makefile: the CONFIG variables are - exported here so you can usually just add a "obj-$(CONFIG_xxx) += - xxx.o" line. The syntax is documented in - Documentation/kbuild/makefiles.txt. - - - - - - Put yourself in CREDITS if you've done - something noteworthy, usually beyond a single file (your name - should be at the top of the source files anyway). - MAINTAINERS means you want to be consulted - when changes are made to a subsystem, and hear about bugs; it - implies a more-than-passing commitment to some part of the code. - - - - - - Finally, don't forget to read Documentation/process/submitting-patches.rst - and possibly Documentation/process/submitting-drivers.rst. - - - - - - - Kernel Cantrips - - - Some favorites from browsing the source. Feel free to add to this - list. - - - - arch/x86/include/asm/delay.h: - - -#define ndelay(n) (__builtin_constant_p(n) ? \ - ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \ - __ndelay(n)) - - - - include/linux/fs.h: - - -/* - * Kernel pointers have redundant information, so we can use a - * scheme where we can return either an error code or a dentry - * pointer with the same return value. - * - * This should be a per-architecture thing, to allow different - * error and pointer decisions. - */ - #define ERR_PTR(err) ((void *)((long)(err))) - #define PTR_ERR(ptr) ((long)(ptr)) - #define IS_ERR(ptr) ((unsigned long)(ptr) > (unsigned long)(-1000)) - - - - arch/x86/include/asm/uaccess_32.h: - - - -#define copy_to_user(to,from,n) \ - (__builtin_constant_p(n) ? \ - __constant_copy_to_user((to),(from),(n)) : \ - __generic_copy_to_user((to),(from),(n))) - - - - arch/sparc/kernel/head.S: - - - -/* - * Sun people can't spell worth damn. "compatability" indeed. - * At least we *know* we can't spell, and use a spell-checker. - */ - -/* Uh, actually Linus it is I who cannot spell. Too much murky - * Sparc assembly will do this to ya. - */ -C_LABEL(cputypvar): - .asciz "compatibility" - -/* Tested on SS-5, SS-10. Probably someone at Sun applied a spell-checker. */ - .align 4 -C_LABEL(cputypvar_sun4m): - .asciz "compatible" - - - - arch/sparc/lib/checksum.S: - - - - /* Sun, you just can't beat me, you just can't. Stop trying, - * give up. I'm serious, I am going to kick the living shit - * out of you, game over, lights out. - */ - - - - - Thanks - - - Thanks to Andi Kleen for the idea, answering my questions, fixing - my mistakes, filling content, etc. Philipp Rumpf for more spelling - and clarity fixes, and some excellent non-obvious points. Werner - Almesberger for giving me a great summary of - disable_irq(), and Jes Sorensen and Andrea - Arcangeli added caveats. Michael Elizabeth Chastain for checking - and adding to the Configure section. Telsa Gwynne for teaching me DocBook. - - - - diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl deleted file mode 100644 index 7c9cc4846cb671..00000000000000 --- a/Documentation/DocBook/kernel-locking.tmpl +++ /dev/null @@ -1,2151 +0,0 @@ - - - - - - Unreliable Guide To Locking - - - - Rusty - Russell - -
- rusty@rustcorp.com.au -
- - - - - - 2003 - Rusty Russell - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - Introduction - - Welcome, to Rusty's Remarkably Unreliable Guide to Kernel - Locking issues. This document describes the locking systems in - the Linux Kernel in 2.6. - - - With the wide availability of HyperThreading, and preemption in the Linux - Kernel, everyone hacking on the kernel needs to know the - fundamentals of concurrency and locking for - SMP. - - - - - The Problem With Concurrency - - (Skip this if you know what a Race Condition is). - - - In a normal program, you can increment a counter like so: - - - very_important_count++; - - - - This is what they would expect to happen: - - - - Expected Results - - - - - - Instance 1 - Instance 2 - - - - - - read very_important_count (5) - - - - add 1 (6) - - - - write very_important_count (6) - - - - - read very_important_count (6) - - - - add 1 (7) - - - - write very_important_count (7) - - - - -
- - - This is what might happen: - - - - Possible Results - - - - - Instance 1 - Instance 2 - - - - - - read very_important_count (5) - - - - - read very_important_count (5) - - - add 1 (6) - - - - - add 1 (6) - - - write very_important_count (6) - - - - - write very_important_count (6) - - - -
- - - Race Conditions and Critical Regions - - This overlap, where the result depends on the - relative timing of multiple tasks, is called a race condition. - The piece of code containing the concurrency issue is called a - critical region. And especially since Linux starting running - on SMP machines, they became one of the major issues in kernel - design and implementation. - - - Preemption can have the same effect, even if there is only one - CPU: by preempting one task during the critical region, we have - exactly the same race condition. In this case the thread which - preempts might run the critical region itself. - - - The solution is to recognize when these simultaneous accesses - occur, and use locks to make sure that only one instance can - enter the critical region at any time. There are many - friendly primitives in the Linux kernel to help you do this. - And then there are the unfriendly primitives, but I'll pretend - they don't exist. - - - - - - Locking in the Linux Kernel - - - If I could give you one piece of advice: never sleep with anyone - crazier than yourself. But if I had to give you advice on - locking: keep it simple. - - - - Be reluctant to introduce new locks. - - - - Strangely enough, this last one is the exact reverse of my advice when - you have slept with someone crazier than yourself. - And you should think about getting a big dog. - - - - Two Main Types of Kernel Locks: Spinlocks and Mutexes - - - There are two main types of kernel locks. The fundamental type - is the spinlock - (include/asm/spinlock.h), - which is a very simple single-holder lock: if you can't get the - spinlock, you keep trying (spinning) until you can. Spinlocks are - very small and fast, and can be used anywhere. - - - The second type is a mutex - (include/linux/mutex.h): it - is like a spinlock, but you may block holding a mutex. - If you can't lock a mutex, your task will suspend itself, and be woken - up when the mutex is released. This means the CPU can do something - else while you are waiting. There are many cases when you simply - can't sleep (see ), and so have to - use a spinlock instead. - - - Neither type of lock is recursive: see - . - - - - - Locks and Uniprocessor Kernels - - - For kernels compiled without CONFIG_SMP, and - without CONFIG_PREEMPT spinlocks do not exist at - all. This is an excellent design decision: when no-one else can - run at the same time, there is no reason to have a lock. - - - - If the kernel is compiled without CONFIG_SMP, - but CONFIG_PREEMPT is set, then spinlocks - simply disable preemption, which is sufficient to prevent any - races. For most purposes, we can think of preemption as - equivalent to SMP, and not worry about it separately. - - - - You should always test your locking code with CONFIG_SMP - and CONFIG_PREEMPT enabled, even if you don't have an SMP test box, because it - will still catch some kinds of locking bugs. - - - - Mutexes still exist, because they are required for - synchronization between user - contexts, as we will see below. - - - - - Locking Only In User Context - - - If you have a data structure which is only ever accessed from - user context, then you can use a simple mutex - (include/linux/mutex.h) to protect it. This - is the most trivial case: you initialize the mutex. Then you can - call mutex_lock_interruptible() to grab the mutex, - and mutex_unlock() to release it. There is also a - mutex_lock(), which should be avoided, because it - will not return if a signal is received. - - - - Example: net/netfilter/nf_sockopt.c allows - registration of new setsockopt() and - getsockopt() calls, with - nf_register_sockopt(). Registration and - de-registration are only done on module load and unload (and boot - time, where there is no concurrency), and the list of registrations - is only consulted for an unknown setsockopt() - or getsockopt() system call. The - nf_sockopt_mutex is perfect to protect this, - especially since the setsockopt and getsockopt calls may well - sleep. - - - - - Locking Between User Context and Softirqs - - - If a softirq shares - data with user context, you have two problems. Firstly, the current - user context can be interrupted by a softirq, and secondly, the - critical region could be entered from another CPU. This is where - spin_lock_bh() - (include/linux/spinlock.h) is - used. It disables softirqs on that CPU, then grabs the lock. - spin_unlock_bh() does the reverse. (The - '_bh' suffix is a historical reference to "Bottom Halves", the - old name for software interrupts. It should really be - called spin_lock_softirq()' in a perfect world). - - - - Note that you can also use spin_lock_irq() - or spin_lock_irqsave() here, which stop - hardware interrupts as well: see . - - - - This works perfectly for UP - as well: the spin lock vanishes, and this macro - simply becomes local_bh_disable() - (include/linux/interrupt.h), which - protects you from the softirq being run. - - - - - Locking Between User Context and Tasklets - - - This is exactly the same as above, because tasklets are actually run - from a softirq. - - - - - Locking Between User Context and Timers - - - This, too, is exactly the same as above, because timers are actually run from - a softirq. From a locking point of view, tasklets and timers - are identical. - - - - - Locking Between Tasklets/Timers - - - Sometimes a tasklet or timer might want to share data with - another tasklet or timer. - - - - The Same Tasklet/Timer - - Since a tasklet is never run on two CPUs at once, you don't - need to worry about your tasklet being reentrant (running - twice at once), even on SMP. - - - - - Different Tasklets/Timers - - If another tasklet/timer wants - to share data with your tasklet or timer , you will both need to use - spin_lock() and - spin_unlock() calls. - spin_lock_bh() is - unnecessary here, as you are already in a tasklet, and - none will be run on the same CPU. - - - - - - Locking Between Softirqs - - - Often a softirq might - want to share data with itself or a tasklet/timer. - - - - The Same Softirq - - - The same softirq can run on the other CPUs: you can use a - per-CPU array (see ) for better - performance. If you're going so far as to use a softirq, - you probably care about scalable performance enough - to justify the extra complexity. - - - - You'll need to use spin_lock() and - spin_unlock() for shared data. - - - - - Different Softirqs - - - You'll need to use spin_lock() and - spin_unlock() for shared data, whether it - be a timer, tasklet, different softirq or the same or another - softirq: any of them could be running on a different CPU. - - - - - - - Hard IRQ Context - - - Hardware interrupts usually communicate with a - tasklet or softirq. Frequently this involves putting work in a - queue, which the softirq will take out. - - - - Locking Between Hard IRQ and Softirqs/Tasklets - - - If a hardware irq handler shares data with a softirq, you have - two concerns. Firstly, the softirq processing can be - interrupted by a hardware interrupt, and secondly, the - critical region could be entered by a hardware interrupt on - another CPU. This is where spin_lock_irq() is - used. It is defined to disable interrupts on that cpu, then grab - the lock. spin_unlock_irq() does the reverse. - - - - The irq handler does not to use - spin_lock_irq(), because the softirq cannot - run while the irq handler is running: it can use - spin_lock(), which is slightly faster. The - only exception would be if a different hardware irq handler uses - the same lock: spin_lock_irq() will stop - that from interrupting us. - - - - This works perfectly for UP as well: the spin lock vanishes, - and this macro simply becomes local_irq_disable() - (include/asm/smp.h), which - protects you from the softirq/tasklet/BH being run. - - - - spin_lock_irqsave() - (include/linux/spinlock.h) is a variant - which saves whether interrupts were on or off in a flags word, - which is passed to spin_unlock_irqrestore(). This - means that the same code can be used inside an hard irq handler (where - interrupts are already off) and in softirqs (where the irq - disabling is required). - - - - Note that softirqs (and hence tasklets and timers) are run on - return from hardware interrupts, so - spin_lock_irq() also stops these. In that - sense, spin_lock_irqsave() is the most - general and powerful locking function. - - - - - Locking Between Two Hard IRQ Handlers - - It is rare to have to share data between two IRQ handlers, but - if you do, spin_lock_irqsave() should be - used: it is architecture-specific whether all interrupts are - disabled inside irq handlers themselves. - - - - - - - Cheat Sheet For Locking - - Pete Zaitcev gives the following summary: - - - - - If you are in a process context (any syscall) and want to - lock other process out, use a mutex. You can take a mutex - and sleep (copy_from_user*( or - kmalloc(x,GFP_KERNEL)). - - - - - Otherwise (== data can be touched in an interrupt), use - spin_lock_irqsave() and - spin_unlock_irqrestore(). - - - - - Avoid holding spinlock for more than 5 lines of code and - across any function call (except accessors like - readb). - - - - - - Table of Minimum Requirements - - The following table lists the minimum - locking requirements between various contexts. In some cases, - the same context can only be running on one CPU at a time, so - no locking is required for that context (eg. a particular - thread can only run on one CPU at a time, but if it needs - shares data with another thread, locking is required). - - - Remember the advice above: you can always use - spin_lock_irqsave(), which is a superset - of all other spinlock primitives. - - - -Table of Locking Requirements - - - - - -IRQ Handler A -IRQ Handler B -Softirq A -Softirq B -Tasklet A -Tasklet B -Timer A -Timer B -User Context A -User Context B - - - -IRQ Handler A -None - - - -IRQ Handler B -SLIS -None - - - -Softirq A -SLI -SLI -SL - - - -Softirq B -SLI -SLI -SL -SL - - - -Tasklet A -SLI -SLI -SL -SL -None - - - -Tasklet B -SLI -SLI -SL -SL -SL -None - - - -Timer A -SLI -SLI -SL -SL -SL -SL -None - - - -Timer B -SLI -SLI -SL -SL -SL -SL -SL -None - - - -User Context A -SLI -SLI -SLBH -SLBH -SLBH -SLBH -SLBH -SLBH -None - - - -User Context B -SLI -SLI -SLBH -SLBH -SLBH -SLBH -SLBH -SLBH -MLI -None - - - - -
- - -Legend for Locking Requirements Table - - - - -SLIS -spin_lock_irqsave - - -SLI -spin_lock_irq - - -SL -spin_lock - - -SLBH -spin_lock_bh - - -MLI -mutex_lock_interruptible - - - - -
- - - - - - The trylock Functions - - There are functions that try to acquire a lock only once and immediately - return a value telling about success or failure to acquire the lock. - They can be used if you need no access to the data protected with the lock - when some other thread is holding the lock. You should acquire the lock - later if you then need access to the data protected with the lock. - - - - spin_trylock() does not spin but returns non-zero if - it acquires the spinlock on the first try or 0 if not. This function can - be used in all contexts like spin_lock: you must have - disabled the contexts that might interrupt you and acquire the spin lock. - - - - mutex_trylock() does not suspend your task - but returns non-zero if it could lock the mutex on the first try - or 0 if not. This function cannot be safely used in hardware or software - interrupt contexts despite not sleeping. - - - - - Common Examples - -Let's step through a simple example: a cache of number to name -mappings. The cache keeps a count of how often each of the objects is -used, and when it gets full, throws out the least used one. - - - - - All In User Context - -For our first example, we assume that all operations are in user -context (ie. from system calls), so we can sleep. This means we can -use a mutex to protect the cache and all the objects within -it. Here's the code: - - - -#include <linux/list.h> -#include <linux/slab.h> -#include <linux/string.h> -#include <linux/mutex.h> -#include <asm/errno.h> - -struct object -{ - struct list_head list; - int id; - char name[32]; - int popularity; -}; - -/* Protects the cache, cache_num, and the objects within it */ -static DEFINE_MUTEX(cache_lock); -static LIST_HEAD(cache); -static unsigned int cache_num = 0; -#define MAX_CACHE_SIZE 10 - -/* Must be holding cache_lock */ -static struct object *__cache_find(int id) -{ - struct object *i; - - list_for_each_entry(i, &cache, list) - if (i->id == id) { - i->popularity++; - return i; - } - return NULL; -} - -/* Must be holding cache_lock */ -static void __cache_delete(struct object *obj) -{ - BUG_ON(!obj); - list_del(&obj->list); - kfree(obj); - cache_num--; -} - -/* Must be holding cache_lock */ -static void __cache_add(struct object *obj) -{ - list_add(&obj->list, &cache); - if (++cache_num > MAX_CACHE_SIZE) { - struct object *i, *outcast = NULL; - list_for_each_entry(i, &cache, list) { - if (!outcast || i->popularity < outcast->popularity) - outcast = i; - } - __cache_delete(outcast); - } -} - -int cache_add(int id, const char *name) -{ - struct object *obj; - - if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL) - return -ENOMEM; - - strlcpy(obj->name, name, sizeof(obj->name)); - obj->id = id; - obj->popularity = 0; - - mutex_lock(&cache_lock); - __cache_add(obj); - mutex_unlock(&cache_lock); - return 0; -} - -void cache_delete(int id) -{ - mutex_lock(&cache_lock); - __cache_delete(__cache_find(id)); - mutex_unlock(&cache_lock); -} - -int cache_find(int id, char *name) -{ - struct object *obj; - int ret = -ENOENT; - - mutex_lock(&cache_lock); - obj = __cache_find(id); - if (obj) { - ret = 0; - strcpy(name, obj->name); - } - mutex_unlock(&cache_lock); - return ret; -} - - - -Note that we always make sure we have the cache_lock when we add, -delete, or look up the cache: both the cache infrastructure itself and -the contents of the objects are protected by the lock. In this case -it's easy, since we copy the data for the user, and never let them -access the objects directly. - - -There is a slight (and common) optimization here: in -cache_add we set up the fields of the object -before grabbing the lock. This is safe, as no-one else can access it -until we put it in cache. - - - - - Accessing From Interrupt Context - -Now consider the case where cache_find can be -called from interrupt context: either a hardware interrupt or a -softirq. An example would be a timer which deletes object from the -cache. - - -The change is shown below, in standard patch format: the -- are lines which are taken away, and the -+ are lines which are added. - - ---- cache.c.usercontext 2003-12-09 13:58:54.000000000 +1100 -+++ cache.c.interrupt 2003-12-09 14:07:49.000000000 +1100 -@@ -12,7 +12,7 @@ - int popularity; - }; - --static DEFINE_MUTEX(cache_lock); -+static DEFINE_SPINLOCK(cache_lock); - static LIST_HEAD(cache); - static unsigned int cache_num = 0; - #define MAX_CACHE_SIZE 10 -@@ -55,6 +55,7 @@ - int cache_add(int id, const char *name) - { - struct object *obj; -+ unsigned long flags; - - if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL) - return -ENOMEM; -@@ -63,30 +64,33 @@ - obj->id = id; - obj->popularity = 0; - -- mutex_lock(&cache_lock); -+ spin_lock_irqsave(&cache_lock, flags); - __cache_add(obj); -- mutex_unlock(&cache_lock); -+ spin_unlock_irqrestore(&cache_lock, flags); - return 0; - } - - void cache_delete(int id) - { -- mutex_lock(&cache_lock); -+ unsigned long flags; -+ -+ spin_lock_irqsave(&cache_lock, flags); - __cache_delete(__cache_find(id)); -- mutex_unlock(&cache_lock); -+ spin_unlock_irqrestore(&cache_lock, flags); - } - - int cache_find(int id, char *name) - { - struct object *obj; - int ret = -ENOENT; -+ unsigned long flags; - -- mutex_lock(&cache_lock); -+ spin_lock_irqsave(&cache_lock, flags); - obj = __cache_find(id); - if (obj) { - ret = 0; - strcpy(name, obj->name); - } -- mutex_unlock(&cache_lock); -+ spin_unlock_irqrestore(&cache_lock, flags); - return ret; - } - - - -Note that the spin_lock_irqsave will turn off -interrupts if they are on, otherwise does nothing (if we are already -in an interrupt handler), hence these functions are safe to call from -any context. - - -Unfortunately, cache_add calls -kmalloc with the GFP_KERNEL -flag, which is only legal in user context. I have assumed that -cache_add is still only called in user context, -otherwise this should become a parameter to -cache_add. - - - - Exposing Objects Outside This File - -If our objects contained more information, it might not be sufficient -to copy the information in and out: other parts of the code might want -to keep pointers to these objects, for example, rather than looking up -the id every time. This produces two problems. - - -The first problem is that we use the cache_lock to -protect objects: we'd need to make this non-static so the rest of the -code can use it. This makes locking trickier, as it is no longer all -in one place. - - -The second problem is the lifetime problem: if another structure keeps -a pointer to an object, it presumably expects that pointer to remain -valid. Unfortunately, this is only guaranteed while you hold the -lock, otherwise someone might call cache_delete -and even worse, add another object, re-using the same address. - - -As there is only one lock, you can't hold it forever: no-one else would -get any work done. - - -The solution to this problem is to use a reference count: everyone who -has a pointer to the object increases it when they first get the -object, and drops the reference count when they're finished with it. -Whoever drops it to zero knows it is unused, and can actually delete it. - - -Here is the code: - - - ---- cache.c.interrupt 2003-12-09 14:25:43.000000000 +1100 -+++ cache.c.refcnt 2003-12-09 14:33:05.000000000 +1100 -@@ -7,6 +7,7 @@ - struct object - { - struct list_head list; -+ unsigned int refcnt; - int id; - char name[32]; - int popularity; -@@ -17,6 +18,35 @@ - static unsigned int cache_num = 0; - #define MAX_CACHE_SIZE 10 - -+static void __object_put(struct object *obj) -+{ -+ if (--obj->refcnt == 0) -+ kfree(obj); -+} -+ -+static void __object_get(struct object *obj) -+{ -+ obj->refcnt++; -+} -+ -+void object_put(struct object *obj) -+{ -+ unsigned long flags; -+ -+ spin_lock_irqsave(&cache_lock, flags); -+ __object_put(obj); -+ spin_unlock_irqrestore(&cache_lock, flags); -+} -+ -+void object_get(struct object *obj) -+{ -+ unsigned long flags; -+ -+ spin_lock_irqsave(&cache_lock, flags); -+ __object_get(obj); -+ spin_unlock_irqrestore(&cache_lock, flags); -+} -+ - /* Must be holding cache_lock */ - static struct object *__cache_find(int id) - { -@@ -35,6 +65,7 @@ - { - BUG_ON(!obj); - list_del(&obj->list); -+ __object_put(obj); - cache_num--; - } - -@@ -63,6 +94,7 @@ - strlcpy(obj->name, name, sizeof(obj->name)); - obj->id = id; - obj->popularity = 0; -+ obj->refcnt = 1; /* The cache holds a reference */ - - spin_lock_irqsave(&cache_lock, flags); - __cache_add(obj); -@@ -79,18 +111,15 @@ - spin_unlock_irqrestore(&cache_lock, flags); - } - --int cache_find(int id, char *name) -+struct object *cache_find(int id) - { - struct object *obj; -- int ret = -ENOENT; - unsigned long flags; - - spin_lock_irqsave(&cache_lock, flags); - obj = __cache_find(id); -- if (obj) { -- ret = 0; -- strcpy(name, obj->name); -- } -+ if (obj) -+ __object_get(obj); - spin_unlock_irqrestore(&cache_lock, flags); -- return ret; -+ return obj; - } - - - -We encapsulate the reference counting in the standard 'get' and 'put' -functions. Now we can return the object itself from -cache_find which has the advantage that the user -can now sleep holding the object (eg. to -copy_to_user to name to userspace). - - -The other point to note is that I said a reference should be held for -every pointer to the object: thus the reference count is 1 when first -inserted into the cache. In some versions the framework does not hold -a reference count, but they are more complicated. - - - - Using Atomic Operations For The Reference Count - -In practice, atomic_t would usually be used for -refcnt. There are a number of atomic -operations defined in - -include/asm/atomic.h: these are -guaranteed to be seen atomically from all CPUs in the system, so no -lock is required. In this case, it is simpler than using spinlocks, -although for anything non-trivial using spinlocks is clearer. The -atomic_inc and -atomic_dec_and_test are used instead of the -standard increment and decrement operators, and the lock is no longer -used to protect the reference count itself. - - - ---- cache.c.refcnt 2003-12-09 15:00:35.000000000 +1100 -+++ cache.c.refcnt-atomic 2003-12-11 15:49:42.000000000 +1100 -@@ -7,7 +7,7 @@ - struct object - { - struct list_head list; -- unsigned int refcnt; -+ atomic_t refcnt; - int id; - char name[32]; - int popularity; -@@ -18,33 +18,15 @@ - static unsigned int cache_num = 0; - #define MAX_CACHE_SIZE 10 - --static void __object_put(struct object *obj) --{ -- if (--obj->refcnt == 0) -- kfree(obj); --} -- --static void __object_get(struct object *obj) --{ -- obj->refcnt++; --} -- - void object_put(struct object *obj) - { -- unsigned long flags; -- -- spin_lock_irqsave(&cache_lock, flags); -- __object_put(obj); -- spin_unlock_irqrestore(&cache_lock, flags); -+ if (atomic_dec_and_test(&obj->refcnt)) -+ kfree(obj); - } - - void object_get(struct object *obj) - { -- unsigned long flags; -- -- spin_lock_irqsave(&cache_lock, flags); -- __object_get(obj); -- spin_unlock_irqrestore(&cache_lock, flags); -+ atomic_inc(&obj->refcnt); - } - - /* Must be holding cache_lock */ -@@ -65,7 +47,7 @@ - { - BUG_ON(!obj); - list_del(&obj->list); -- __object_put(obj); -+ object_put(obj); - cache_num--; - } - -@@ -94,7 +76,7 @@ - strlcpy(obj->name, name, sizeof(obj->name)); - obj->id = id; - obj->popularity = 0; -- obj->refcnt = 1; /* The cache holds a reference */ -+ atomic_set(&obj->refcnt, 1); /* The cache holds a reference */ - - spin_lock_irqsave(&cache_lock, flags); - __cache_add(obj); -@@ -119,7 +101,7 @@ - spin_lock_irqsave(&cache_lock, flags); - obj = __cache_find(id); - if (obj) -- __object_get(obj); -+ object_get(obj); - spin_unlock_irqrestore(&cache_lock, flags); - return obj; - } - - - - - - Protecting The Objects Themselves - -In these examples, we assumed that the objects (except the reference -counts) never changed once they are created. If we wanted to allow -the name to change, there are three possibilities: - - - - -You can make cache_lock non-static, and tell people -to grab that lock before changing the name in any object. - - - - -You can provide a cache_obj_rename which grabs -this lock and changes the name for the caller, and tell everyone to -use that function. - - - - -You can make the cache_lock protect only the cache -itself, and use another lock to protect the name. - - - - - -Theoretically, you can make the locks as fine-grained as one lock for -every field, for every object. In practice, the most common variants -are: - - - - -One lock which protects the infrastructure (the cache -list in this example) and all the objects. This is what we have done -so far. - - - - -One lock which protects the infrastructure (including the list -pointers inside the objects), and one lock inside the object which -protects the rest of that object. - - - - -Multiple locks to protect the infrastructure (eg. one lock per hash -chain), possibly with a separate per-object lock. - - - - - -Here is the "lock-per-object" implementation: - - ---- cache.c.refcnt-atomic 2003-12-11 15:50:54.000000000 +1100 -+++ cache.c.perobjectlock 2003-12-11 17:15:03.000000000 +1100 -@@ -6,11 +6,17 @@ - - struct object - { -+ /* These two protected by cache_lock. */ - struct list_head list; -+ int popularity; -+ - atomic_t refcnt; -+ -+ /* Doesn't change once created. */ - int id; -+ -+ spinlock_t lock; /* Protects the name */ - char name[32]; -- int popularity; - }; - - static DEFINE_SPINLOCK(cache_lock); -@@ -77,6 +84,7 @@ - obj->id = id; - obj->popularity = 0; - atomic_set(&obj->refcnt, 1); /* The cache holds a reference */ -+ spin_lock_init(&obj->lock); - - spin_lock_irqsave(&cache_lock, flags); - __cache_add(obj); - - - -Note that I decide that the popularity -count should be protected by the cache_lock rather -than the per-object lock: this is because it (like the -struct list_head inside the object) is -logically part of the infrastructure. This way, I don't need to grab -the lock of every object in __cache_add when -seeking the least popular. - - - -I also decided that the id member is -unchangeable, so I don't need to grab each object lock in -__cache_find() to examine the -id: the object lock is only used by a -caller who wants to read or write the name -field. - - - -Note also that I added a comment describing what data was protected by -which locks. This is extremely important, as it describes the runtime -behavior of the code, and can be hard to gain from just reading. And -as Alan Cox says, Lock data, not code. - - - - - - Common Problems - - Deadlock: Simple and Advanced - - - There is a coding bug where a piece of code tries to grab a - spinlock twice: it will spin forever, waiting for the lock to - be released (spinlocks, rwlocks and mutexes are not - recursive in Linux). This is trivial to diagnose: not a - stay-up-five-nights-talk-to-fluffy-code-bunnies kind of - problem. - - - - For a slightly more complex case, imagine you have a region - shared by a softirq and user context. If you use a - spin_lock() call to protect it, it is - possible that the user context will be interrupted by the softirq - while it holds the lock, and the softirq will then spin - forever trying to get the same lock. - - - - Both of these are called deadlock, and as shown above, it can - occur even with a single CPU (although not on UP compiles, - since spinlocks vanish on kernel compiles with - CONFIG_SMP=n. You'll still get data corruption - in the second example). - - - - This complete lockup is easy to diagnose: on SMP boxes the - watchdog timer or compiling with DEBUG_SPINLOCK set - (include/linux/spinlock.h) will show this up - immediately when it happens. - - - - A more complex problem is the so-called 'deadly embrace', - involving two or more locks. Say you have a hash table: each - entry in the table is a spinlock, and a chain of hashed - objects. Inside a softirq handler, you sometimes want to - alter an object from one place in the hash to another: you - grab the spinlock of the old hash chain and the spinlock of - the new hash chain, and delete the object from the old one, - and insert it in the new one. - - - - There are two problems here. First, if your code ever - tries to move the object to the same chain, it will deadlock - with itself as it tries to lock it twice. Secondly, if the - same softirq on another CPU is trying to move another object - in the reverse direction, the following could happen: - - - - Consequences - - - - - - CPU 1 - CPU 2 - - - - - - Grab lock A -> OK - Grab lock B -> OK - - - Grab lock B -> spin - Grab lock A -> spin - - - -
- - - The two CPUs will spin forever, waiting for the other to give up - their lock. It will look, smell, and feel like a crash. - - - - - Preventing Deadlock - - - Textbooks will tell you that if you always lock in the same - order, you will never get this kind of deadlock. Practice - will tell you that this approach doesn't scale: when I - create a new lock, I don't understand enough of the kernel - to figure out where in the 5000 lock hierarchy it will fit. - - - - The best locks are encapsulated: they never get exposed in - headers, and are never held around calls to non-trivial - functions outside the same file. You can read through this - code and see that it will never deadlock, because it never - tries to grab another lock while it has that one. People - using your code don't even need to know you are using a - lock. - - - - A classic problem here is when you provide callbacks or - hooks: if you call these with the lock held, you risk simple - deadlock, or a deadly embrace (who knows what the callback - will do?). Remember, the other programmers are out to get - you, so don't do this. - - - - Overzealous Prevention Of Deadlocks - - - Deadlocks are problematic, but not as bad as data - corruption. Code which grabs a read lock, searches a list, - fails to find what it wants, drops the read lock, grabs a - write lock and inserts the object has a race condition. - - - - If you don't see why, please stay the fuck away from my code. - - - - - - Racing Timers: A Kernel Pastime - - - Timers can produce their own special problems with races. - Consider a collection of objects (list, hash, etc) where each - object has a timer which is due to destroy it. - - - - If you want to destroy the entire collection (say on module - removal), you might do the following: - - - - /* THIS CODE BAD BAD BAD BAD: IF IT WAS ANY WORSE IT WOULD USE - HUNGARIAN NOTATION */ - spin_lock_bh(&list_lock); - - while (list) { - struct foo *next = list->next; - del_timer(&list->timer); - kfree(list); - list = next; - } - - spin_unlock_bh(&list_lock); - - - - Sooner or later, this will crash on SMP, because a timer can - have just gone off before the spin_lock_bh(), - and it will only get the lock after we - spin_unlock_bh(), and then try to free - the element (which has already been freed!). - - - - This can be avoided by checking the result of - del_timer(): if it returns - 1, the timer has been deleted. - If 0, it means (in this - case) that it is currently running, so we can do: - - - - retry: - spin_lock_bh(&list_lock); - - while (list) { - struct foo *next = list->next; - if (!del_timer(&list->timer)) { - /* Give timer a chance to delete this */ - spin_unlock_bh(&list_lock); - goto retry; - } - kfree(list); - list = next; - } - - spin_unlock_bh(&list_lock); - - - - Another common problem is deleting timers which restart - themselves (by calling add_timer() at the end - of their timer function). Because this is a fairly common case - which is prone to races, you should use del_timer_sync() - (include/linux/timer.h) - to handle this case. It returns the number of times the timer - had to be deleted before we finally stopped it from adding itself back - in. - - - - - - - Locking Speed - - -There are three main things to worry about when considering speed of -some code which does locking. First is concurrency: how many things -are going to be waiting while someone else is holding a lock. Second -is the time taken to actually acquire and release an uncontended lock. -Third is using fewer, or smarter locks. I'm assuming that the lock is -used fairly often: otherwise, you wouldn't be concerned about -efficiency. - - -Concurrency depends on how long the lock is usually held: you should -hold the lock for as long as needed, but no longer. In the cache -example, we always create the object without the lock held, and then -grab the lock only when we are ready to insert it in the list. - - -Acquisition times depend on how much damage the lock operations do to -the pipeline (pipeline stalls) and how likely it is that this CPU was -the last one to grab the lock (ie. is the lock cache-hot for this -CPU): on a machine with more CPUs, this likelihood drops fast. -Consider a 700MHz Intel Pentium III: an instruction takes about 0.7ns, -an atomic increment takes about 58ns, a lock which is cache-hot on -this CPU takes 160ns, and a cacheline transfer from another CPU takes -an additional 170 to 360ns. (These figures from Paul McKenney's - Linux -Journal RCU article). - - -These two aims conflict: holding a lock for a short time might be done -by splitting locks into parts (such as in our final per-object-lock -example), but this increases the number of lock acquisitions, and the -results are often slower than having a single lock. This is another -reason to advocate locking simplicity. - - -The third concern is addressed below: there are some methods to reduce -the amount of locking which needs to be done. - - - - Read/Write Lock Variants - - - Both spinlocks and mutexes have read/write variants: - rwlock_t and struct rw_semaphore. - These divide users into two classes: the readers and the writers. If - you are only reading the data, you can get a read lock, but to write to - the data you need the write lock. Many people can hold a read lock, - but a writer must be sole holder. - - - - If your code divides neatly along reader/writer lines (as our - cache code does), and the lock is held by readers for - significant lengths of time, using these locks can help. They - are slightly slower than the normal locks though, so in practice - rwlock_t is not usually worthwhile. - - - - - Avoiding Locks: Read Copy Update - - - There is a special method of read/write locking called Read Copy - Update. Using RCU, the readers can avoid taking a lock - altogether: as we expect our cache to be read more often than - updated (otherwise the cache is a waste of time), it is a - candidate for this optimization. - - - - How do we get rid of read locks? Getting rid of read locks - means that writers may be changing the list underneath the - readers. That is actually quite simple: we can read a linked - list while an element is being added if the writer adds the - element very carefully. For example, adding - new to a single linked list called - list: - - - - new->next = list->next; - wmb(); - list->next = new; - - - - The wmb() is a write memory barrier. It - ensures that the first operation (setting the new element's - next pointer) is complete and will be seen by - all CPUs, before the second operation is (putting the new - element into the list). This is important, since modern - compilers and modern CPUs can both reorder instructions unless - told otherwise: we want a reader to either not see the new - element at all, or see the new element with the - next pointer correctly pointing at the rest of - the list. - - - Fortunately, there is a function to do this for standard - struct list_head lists: - list_add_rcu() - (include/linux/list.h). - - - Removing an element from the list is even simpler: we replace - the pointer to the old element with a pointer to its successor, - and readers will either see it, or skip over it. - - - list->next = old->next; - - - There is list_del_rcu() - (include/linux/list.h) which does this (the - normal version poisons the old object, which we don't want). - - - The reader must also be careful: some CPUs can look through the - next pointer to start reading the contents of - the next element early, but don't realize that the pre-fetched - contents is wrong when the next pointer changes - underneath them. Once again, there is a - list_for_each_entry_rcu() - (include/linux/list.h) to help you. Of - course, writers can just use - list_for_each_entry(), since there cannot - be two simultaneous writers. - - - Our final dilemma is this: when can we actually destroy the - removed element? Remember, a reader might be stepping through - this element in the list right now: if we free this element and - the next pointer changes, the reader will jump - off into garbage and crash. We need to wait until we know that - all the readers who were traversing the list when we deleted the - element are finished. We use call_rcu() to - register a callback which will actually destroy the object once - all pre-existing readers are finished. Alternatively, - synchronize_rcu() may be used to block until - all pre-existing are finished. - - - But how does Read Copy Update know when the readers are - finished? The method is this: firstly, the readers always - traverse the list inside - rcu_read_lock()/rcu_read_unlock() - pairs: these simply disable preemption so the reader won't go to - sleep while reading the list. - - - RCU then waits until every other CPU has slept at least once: - since readers cannot sleep, we know that any readers which were - traversing the list during the deletion are finished, and the - callback is triggered. The real Read Copy Update code is a - little more optimized than this, but this is the fundamental - idea. - - - ---- cache.c.perobjectlock 2003-12-11 17:15:03.000000000 +1100 -+++ cache.c.rcupdate 2003-12-11 17:55:14.000000000 +1100 -@@ -1,15 +1,18 @@ - #include <linux/list.h> - #include <linux/slab.h> - #include <linux/string.h> -+#include <linux/rcupdate.h> - #include <linux/mutex.h> - #include <asm/errno.h> - - struct object - { -- /* These two protected by cache_lock. */ -+ /* This is protected by RCU */ - struct list_head list; - int popularity; - -+ struct rcu_head rcu; -+ - atomic_t refcnt; - - /* Doesn't change once created. */ -@@ -40,7 +43,7 @@ - { - struct object *i; - -- list_for_each_entry(i, &cache, list) { -+ list_for_each_entry_rcu(i, &cache, list) { - if (i->id == id) { - i->popularity++; - return i; -@@ -49,19 +52,25 @@ - return NULL; - } - -+/* Final discard done once we know no readers are looking. */ -+static void cache_delete_rcu(void *arg) -+{ -+ object_put(arg); -+} -+ - /* Must be holding cache_lock */ - static void __cache_delete(struct object *obj) - { - BUG_ON(!obj); -- list_del(&obj->list); -- object_put(obj); -+ list_del_rcu(&obj->list); - cache_num--; -+ call_rcu(&obj->rcu, cache_delete_rcu); - } - - /* Must be holding cache_lock */ - static void __cache_add(struct object *obj) - { -- list_add(&obj->list, &cache); -+ list_add_rcu(&obj->list, &cache); - if (++cache_num > MAX_CACHE_SIZE) { - struct object *i, *outcast = NULL; - list_for_each_entry(i, &cache, list) { -@@ -104,12 +114,11 @@ - struct object *cache_find(int id) - { - struct object *obj; -- unsigned long flags; - -- spin_lock_irqsave(&cache_lock, flags); -+ rcu_read_lock(); - obj = __cache_find(id); - if (obj) - object_get(obj); -- spin_unlock_irqrestore(&cache_lock, flags); -+ rcu_read_unlock(); - return obj; - } - - - -Note that the reader will alter the -popularity member in -__cache_find(), and now it doesn't hold a lock. -One solution would be to make it an atomic_t, but for -this usage, we don't really care about races: an approximate result is -good enough, so I didn't change it. - - - -The result is that cache_find() requires no -synchronization with any other functions, so is almost as fast on SMP -as it would be on UP. - - - -There is a further optimization possible here: remember our original -cache code, where there were no reference counts and the caller simply -held the lock whenever using the object? This is still possible: if -you hold the lock, no one can delete the object, so you don't need to -get and put the reference count. - - - -Now, because the 'read lock' in RCU is simply disabling preemption, a -caller which always has preemption disabled between calling -cache_find() and -object_put() does not need to actually get and -put the reference count: we could expose -__cache_find() by making it non-static, and -such callers could simply call that. - - -The benefit here is that the reference count is not written to: the -object is not altered in any way, which is much faster on SMP -machines due to caching. - - - - - Per-CPU Data - - - Another technique for avoiding locking which is used fairly - widely is to duplicate information for each CPU. For example, - if you wanted to keep a count of a common condition, you could - use a spin lock and a single counter. Nice and simple. - - - - If that was too slow (it's usually not, but if you've got a - really big machine to test on and can show that it is), you - could instead use a counter for each CPU, then none of them need - an exclusive lock. See DEFINE_PER_CPU(), - get_cpu_var() and - put_cpu_var() - (include/linux/percpu.h). - - - - Of particular use for simple per-cpu counters is the - local_t type, and the - cpu_local_inc() and related functions, - which are more efficient than simple code on some architectures - (include/asm/local.h). - - - - Note that there is no simple, reliable way of getting an exact - value of such a counter, without introducing more locks. This - is not a problem for some uses. - - - - - Data Which Mostly Used By An IRQ Handler - - - If data is always accessed from within the same IRQ handler, you - don't need a lock at all: the kernel already guarantees that the - irq handler will not run simultaneously on multiple CPUs. - - - Manfred Spraul points out that you can still do this, even if - the data is very occasionally accessed in user context or - softirqs/tasklets. The irq handler doesn't use a lock, and - all other accesses are done as so: - - - - spin_lock(&lock); - disable_irq(irq); - ... - enable_irq(irq); - spin_unlock(&lock); - - - The disable_irq() prevents the irq handler - from running (and waits for it to finish if it's currently - running on other CPUs). The spinlock prevents any other - accesses happening at the same time. Naturally, this is slower - than just a spin_lock_irq() call, so it - only makes sense if this type of access happens extremely - rarely. - - - - - - What Functions Are Safe To Call From Interrupts? - - - Many functions in the kernel sleep (ie. call schedule()) - directly or indirectly: you can never call them while holding a - spinlock, or with preemption disabled. This also means you need - to be in user context: calling them from an interrupt is illegal. - - - - Some Functions Which Sleep - - - The most common ones are listed below, but you usually have to - read the code to find out if other calls are safe. If everyone - else who calls it can sleep, you probably need to be able to - sleep, too. In particular, registration and deregistration - functions usually expect to be called from user context, and can - sleep. - - - - - - Accesses to - userspace: - - - - - copy_from_user() - - - - - copy_to_user() - - - - - get_user() - - - - - put_user() - - - - - - - - kmalloc(GFP_KERNEL) - - - - - - mutex_lock_interruptible() and - mutex_lock() - - - There is a mutex_trylock() which does not - sleep. Still, it must not be used inside interrupt context since - its implementation is not safe for that. - mutex_unlock() will also never sleep. - It cannot be used in interrupt context either since a mutex - must be released by the same task that acquired it. - - - - - - - Some Functions Which Don't Sleep - - - Some functions are safe to call from any context, or holding - almost any lock. - - - - - - printk() - - - - - kfree() - - - - - add_timer() and del_timer() - - - - - - - - Mutex API reference -!Iinclude/linux/mutex.h -!Ekernel/locking/mutex.c - - - - Futex API reference -!Ikernel/futex.c - - - - Further reading - - - - - Documentation/locking/spinlocks.txt: - Linus Torvalds' spinlocking tutorial in the kernel sources. - - - - - - Unix Systems for Modern Architectures: Symmetric - Multiprocessing and Caching for Kernel Programmers: - - - - Curt Schimmel's very good introduction to kernel level - locking (not written for Linux, but nearly everything - applies). The book is expensive, but really worth every - penny to understand SMP locking. [ISBN: 0201633388] - - - - - - - Thanks - - - Thanks to Telsa Gwynne for DocBooking, neatening and adding - style. - - - - Thanks to Martin Pool, Philipp Rumpf, Stephen Rothwell, Paul - Mackerras, Ruedi Aschwanden, Alan Cox, Manfred Spraul, Tim - Waugh, Pete Zaitcev, James Morris, Robert Love, Paul McKenney, - John Ashby for proofreading, correcting, flaming, commenting. - - - - Thanks to the cabal for having no influence on this document. - - - - - Glossary - - - preemption - - - Prior to 2.5, or when CONFIG_PREEMPT is - unset, processes in user context inside the kernel would not - preempt each other (ie. you had that CPU until you gave it up, - except for interrupts). With the addition of - CONFIG_PREEMPT in 2.5.4, this changed: when - in user context, higher priority tasks can "cut in": spinlocks - were changed to disable preemption, even on UP. - - - - - - bh - - - Bottom Half: for historical reasons, functions with - '_bh' in them often now refer to any software interrupt, e.g. - spin_lock_bh() blocks any software interrupt - on the current CPU. Bottom halves are deprecated, and will - eventually be replaced by tasklets. Only one bottom half will be - running at any time. - - - - - - Hardware Interrupt / Hardware IRQ - - - Hardware interrupt request. in_irq() returns - true in a hardware interrupt handler. - - - - - - Interrupt Context - - - Not user context: processing a hardware irq or software irq. - Indicated by the in_interrupt() macro - returning true. - - - - - - SMP - - - Symmetric Multi-Processor: kernels compiled for multiple-CPU - machines. (CONFIG_SMP=y). - - - - - - Software Interrupt / softirq - - - Software interrupt handler. in_irq() returns - false; in_softirq() - returns true. Tasklets and softirqs - both fall into the category of 'software interrupts'. - - - Strictly speaking a softirq is one of up to 32 enumerated software - interrupts which can run on multiple CPUs at once. - Sometimes used to refer to tasklets as - well (ie. all software interrupts). - - - - - - tasklet - - - A dynamically-registrable software interrupt, - which is guaranteed to only run on one CPU at a time. - - - - - - timer - - - A dynamically-registrable software interrupt, which is run at - (or close to) a given time. When running, it is just like a - tasklet (in fact, they are called from the TIMER_SOFTIRQ). - - - - - - UP - - - Uni-Processor: Non-SMP. (CONFIG_SMP=n). - - - - - - User Context - - - The kernel executing on behalf of a particular process (ie. a - system call or trap) or kernel thread. You can tell which - process with the current macro.) Not to - be confused with userspace. Can be interrupted by software or - hardware interrupts. - - - - - - Userspace - - - A process executing its own code outside the kernel. - - - - - - - diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl deleted file mode 100644 index 856ac20bf36782..00000000000000 --- a/Documentation/DocBook/kgdb.tmpl +++ /dev/null @@ -1,918 +0,0 @@ - - - - - - Using kgdb, kdb and the kernel debugger internals - - - - Jason - Wessel - -
- jason.wessel@windriver.com -
- - - - - 2008,2010 - Wind River Systems, Inc. - - - 2004-2005 - MontaVista Software, Inc. - - - 2004 - Amit S. Kale - - - - - This file is licensed under the terms of the GNU General Public License - version 2. This program is licensed "as is" without any warranty of any - kind, whether express or implied. - - - - - - - - Introduction - - The kernel has two different debugger front ends (kdb and kgdb) - which interface to the debug core. It is possible to use either - of the debugger front ends and dynamically transition between them - if you configure the kernel properly at compile and runtime. - - - Kdb is simplistic shell-style interface which you can use on a - system console with a keyboard or serial console. You can use it - to inspect memory, registers, process lists, dmesg, and even set - breakpoints to stop in a certain location. Kdb is not a source - level debugger, although you can set breakpoints and execute some - basic kernel run control. Kdb is mainly aimed at doing some - analysis to aid in development or diagnosing kernel problems. You - can access some symbols by name in kernel built-ins or in kernel - modules if the code was built - with CONFIG_KALLSYMS. - - - Kgdb is intended to be used as a source level debugger for the - Linux kernel. It is used along with gdb to debug a Linux kernel. - The expectation is that gdb can be used to "break in" to the - kernel to inspect memory, variables and look through call stack - information similar to the way an application developer would use - gdb to debug an application. It is possible to place breakpoints - in kernel code and perform some limited execution stepping. - - - Two machines are required for using kgdb. One of these machines is - a development machine and the other is the target machine. The - kernel to be debugged runs on the target machine. The development - machine runs an instance of gdb against the vmlinux file which - contains the symbols (not a boot image such as bzImage, zImage, - uImage...). In gdb the developer specifies the connection - parameters and connects to kgdb. The type of connection a - developer makes with gdb depends on the availability of kgdb I/O - modules compiled as built-ins or loadable kernel modules in the test - machine's kernel. - - - - Compiling a kernel - - - In order to enable compilation of kdb, you must first enable kgdb. - The kgdb test compile options are described in the kgdb test suite chapter. - - - - Kernel config options for kgdb - - To enable CONFIG_KGDB you should look under - "Kernel hacking" / "Kernel debugging" and select "KGDB: kernel debugger". - - - While it is not a hard requirement that you have symbols in your - vmlinux file, gdb tends not to be very useful without the symbolic - data, so you will want to turn - on CONFIG_DEBUG_INFO which is called "Compile the - kernel with debug info" in the config menu. - - - It is advised, but not required, that you turn on the - CONFIG_FRAME_POINTER kernel option which is called "Compile the - kernel with frame pointers" in the config menu. This option - inserts code to into the compiled executable which saves the frame - information in registers or on the stack at different points which - allows a debugger such as gdb to more accurately construct - stack back traces while debugging the kernel. - - - If the architecture that you are using supports the kernel option - CONFIG_STRICT_KERNEL_RWX, you should consider turning it off. This - option will prevent the use of software breakpoints because it - marks certain regions of the kernel's memory space as read-only. - If kgdb supports it for the architecture you are using, you can - use hardware breakpoints if you desire to run with the - CONFIG_STRICT_KERNEL_RWX option turned on, else you need to turn off - this option. - - - Next you should choose one of more I/O drivers to interconnect - debugging host and debugged target. Early boot debugging requires - a KGDB I/O driver that supports early debugging and the driver - must be built into the kernel directly. Kgdb I/O driver - configuration takes place via kernel or module parameters which - you can learn more about in the in the section that describes the - parameter "kgdboc". - - Here is an example set of .config symbols to enable or - disable for kgdb: - - # CONFIG_STRICT_KERNEL_RWX is not set - CONFIG_FRAME_POINTER=y - CONFIG_KGDB=y - CONFIG_KGDB_SERIAL_CONSOLE=y - - - - - Kernel config options for kdb - Kdb is quite a bit more complex than the simple gdbstub - sitting on top of the kernel's debug core. Kdb must implement a - shell, and also adds some helper functions in other parts of the - kernel, responsible for printing out interesting data such as what - you would see if you ran "lsmod", or "ps". In order to build kdb - into the kernel you follow the same steps as you would for kgdb. - - The main config option for kdb - is CONFIG_KGDB_KDB which is called "KGDB_KDB: - include kdb frontend for kgdb" in the config menu. In theory you - would have already also selected an I/O driver such as the - CONFIG_KGDB_SERIAL_CONSOLE interface if you plan on using kdb on a - serial port, when you were configuring kgdb. - - If you want to use a PS/2-style keyboard with kdb, you would - select CONFIG_KDB_KEYBOARD which is called "KGDB_KDB: keyboard as - input device" in the config menu. The CONFIG_KDB_KEYBOARD option - is not used for anything in the gdb interface to kgdb. The - CONFIG_KDB_KEYBOARD option only works with kdb. - - Here is an example set of .config symbols to enable/disable kdb: - - # CONFIG_STRICT_KERNEL_RWX is not set - CONFIG_FRAME_POINTER=y - CONFIG_KGDB=y - CONFIG_KGDB_SERIAL_CONSOLE=y - CONFIG_KGDB_KDB=y - CONFIG_KDB_KEYBOARD=y - - - - - - Kernel Debugger Boot Arguments - This section describes the various runtime kernel - parameters that affect the configuration of the kernel debugger. - The following chapter covers using kdb and kgdb as well as - providing some examples of the configuration parameters. - - Kernel parameter: kgdboc - The kgdboc driver was originally an abbreviation meant to - stand for "kgdb over console". Today it is the primary mechanism - to configure how to communicate from gdb to kgdb as well as the - devices you want to use to interact with the kdb shell. - - For kgdb/gdb, kgdboc is designed to work with a single serial - port. It is intended to cover the circumstance where you want to - use a serial console as your primary console as well as using it to - perform kernel debugging. It is also possible to use kgdb on a - serial port which is not designated as a system console. Kgdboc - may be configured as a kernel built-in or a kernel loadable module. - You can only make use of kgdbwait and early - debugging if you build kgdboc into the kernel as a built-in. - - Optionally you can elect to activate kms (Kernel Mode - Setting) integration. When you use kms with kgdboc and you have a - video driver that has atomic mode setting hooks, it is possible to - enter the debugger on the graphics console. When the kernel - execution is resumed, the previous graphics mode will be restored. - This integration can serve as a useful tool to aid in diagnosing - crashes or doing analysis of memory with kdb while allowing the - full graphics console applications to run. - - - kgdboc arguments - Usage: kgdboc=[kms][[,]kbd][[,]serial_device][,baud] - The order listed above must be observed if you use any of the - optional configurations together. - - Abbreviations: - - kms = Kernel Mode Setting - kbd = Keyboard - - - You can configure kgdboc to use the keyboard, and/or a serial - device depending on if you are using kdb and/or kgdb, in one of the - following scenarios. The order listed above must be observed if - you use any of the optional configurations together. Using kms + - only gdb is generally not a useful combination. - - Using loadable module or built-in - - - As a kernel built-in: - Use the kernel boot argument: kgdboc=<tty-device>,[baud] - - As a kernel loadable module: - Use the command: modprobe kgdboc kgdboc=<tty-device>,[baud] - Here are two examples of how you might format the kgdboc - string. The first is for an x86 target using the first serial port. - The second example is for the ARM Versatile AB using the second - serial port. - - kgdboc=ttyS0,115200 - kgdboc=ttyAMA1,115200 - - - - - - - Configure kgdboc at runtime with sysfs - At run time you can enable or disable kgdboc by echoing a - parameters into the sysfs. Here are two examples: - - Enable kgdboc on ttyS0 - echo ttyS0 > /sys/module/kgdboc/parameters/kgdboc - Disable kgdboc - echo "" > /sys/module/kgdboc/parameters/kgdboc - - NOTE: You do not need to specify the baud if you are - configuring the console on tty which is already configured or - open. - - - More examples - You can configure kgdboc to use the keyboard, and/or a serial device - depending on if you are using kdb and/or kgdb, in one of the - following scenarios. - - kdb and kgdb over only a serial port - kgdboc=<serial_device>[,baud] - Example: kgdboc=ttyS0,115200 - - kdb and kgdb with keyboard and a serial port - kgdboc=kbd,<serial_device>[,baud] - Example: kgdboc=kbd,ttyS0,115200 - - kdb with a keyboard - kgdboc=kbd - - kdb with kernel mode setting - kgdboc=kms,kbd - - kdb with kernel mode setting and kgdb over a serial port - kgdboc=kms,kbd,ttyS0,115200 - - - - NOTE: Kgdboc does not support interrupting the target via the - gdb remote protocol. You must manually send a sysrq-g unless you - have a proxy that splits console output to a terminal program. - A console proxy has a separate TCP port for the debugger and a separate - TCP port for the "human" console. The proxy can take care of sending - the sysrq-g for you. - - When using kgdboc with no debugger proxy, you can end up - connecting the debugger at one of two entry points. If an - exception occurs after you have loaded kgdboc, a message should - print on the console stating it is waiting for the debugger. In - this case you disconnect your terminal program and then connect the - debugger in its place. If you want to interrupt the target system - and forcibly enter a debug session you have to issue a Sysrq - sequence and then type the letter g. Then - you disconnect the terminal session and connect gdb. Your options - if you don't like this are to hack gdb to send the sysrq-g for you - as well as on the initial connect, or to use a debugger proxy that - allows an unmodified gdb to do the debugging. - - - - - - Kernel parameter: kgdbwait - - The Kernel command line option kgdbwait makes - kgdb wait for a debugger connection during booting of a kernel. You - can only use this option if you compiled a kgdb I/O driver into the - kernel and you specified the I/O driver configuration as a kernel - command line option. The kgdbwait parameter should always follow the - configuration parameter for the kgdb I/O driver in the kernel - command line else the I/O driver will not be configured prior to - asking the kernel to use it to wait. - - - The kernel will stop and wait as early as the I/O driver and - architecture allows when you use this option. If you build the - kgdb I/O driver as a loadable kernel module kgdbwait will not do - anything. - - - - Kernel parameter: kgdbcon - The kgdbcon feature allows you to see printk() messages - inside gdb while gdb is connected to the kernel. Kdb does not make - use of the kgdbcon feature. - - Kgdb supports using the gdb serial protocol to send console - messages to the debugger when the debugger is connected and running. - There are two ways to activate this feature. - - Activate with the kernel command line option: - kgdbcon - - Use sysfs before configuring an I/O driver - - echo 1 > /sys/module/kgdb/parameters/kgdb_use_con - - - NOTE: If you do this after you configure the kgdb I/O driver, the - setting will not take effect until the next point the I/O is - reconfigured. - - - - - IMPORTANT NOTE: You cannot use kgdboc + kgdbcon on a tty that is an - active system console. An example of incorrect usage is console=ttyS0,115200 kgdboc=ttyS0 kgdbcon - - It is possible to use this option with kgdboc on a tty that is not a system console. - - - - Run time parameter: kgdbreboot - The kgdbreboot feature allows you to change how the debugger - deals with the reboot notification. You have 3 choices for the - behavior. The default behavior is always set to 0. - - echo -1 > /sys/module/debug_core/parameters/kgdbreboot - Ignore the reboot notification entirely. - - echo 0 > /sys/module/debug_core/parameters/kgdbreboot - Send the detach message to any attached debugger client. - - echo 1 > /sys/module/debug_core/parameters/kgdbreboot - Enter the debugger on reboot notify. - - - - - - Using kdb - - - - Quick start for kdb on a serial port - This is a quick example of how to use kdb. - - Configure kgdboc at boot using kernel parameters: - - console=ttyS0,115200 kgdboc=ttyS0,115200 - - OR - Configure kgdboc after the kernel has booted; assuming you are using a serial port console: - - echo ttyS0 > /sys/module/kgdboc/parameters/kgdboc - - - - Enter the kernel debugger manually or by waiting for an oops or fault. There are several ways you can enter the kernel debugger manually; all involve using the sysrq-g, which means you must have enabled CONFIG_MAGIC_SYSRQ=y in your kernel config. - - When logged in as root or with a super user session you can run: - echo g > /proc/sysrq-trigger - Example using minicom 2.2 - Press: Control-a - Press: f - Press: g - - When you have telneted to a terminal server that supports sending a remote break - Press: Control-] - Type in:send break - Press: Enter - Press: g - - - - From the kdb prompt you can run the "help" command to see a complete list of the commands that are available. - Some useful commands in kdb include: - - lsmod -- Shows where kernel modules are loaded - ps -- Displays only the active processes - ps A -- Shows all the processes - summary -- Shows kernel version info and memory usage - bt -- Get a backtrace of the current process using dump_stack() - dmesg -- View the kernel syslog buffer - go -- Continue the system - - - - - When you are done using kdb you need to consider rebooting the - system or using the "go" command to resuming normal kernel - execution. If you have paused the kernel for a lengthy period of - time, applications that rely on timely networking or anything to do - with real wall clock time could be adversely affected, so you - should take this into consideration when using the kernel - debugger. - - - - - Quick start for kdb using a keyboard connected console - This is a quick example of how to use kdb with a keyboard. - - Configure kgdboc at boot using kernel parameters: - - kgdboc=kbd - - OR - Configure kgdboc after the kernel has booted: - - echo kbd > /sys/module/kgdboc/parameters/kgdboc - - - - Enter the kernel debugger manually or by waiting for an oops or fault. There are several ways you can enter the kernel debugger manually; all involve using the sysrq-g, which means you must have enabled CONFIG_MAGIC_SYSRQ=y in your kernel config. - - When logged in as root or with a super user session you can run: - echo g > /proc/sysrq-trigger - Example using a laptop keyboard - Press and hold down: Alt - Press and hold down: Fn - Press and release the key with the label: SysRq - Release: Fn - Press and release: g - Release: Alt - - Example using a PS/2 101-key keyboard - Press and hold down: Alt - Press and release the key with the label: SysRq - Press and release: g - Release: Alt - - - - - Now type in a kdb command such as "help", "dmesg", "bt" or "go" to continue kernel execution. - - - - - - Using kgdb / gdb - In order to use kgdb you must activate it by passing - configuration information to one of the kgdb I/O drivers. If you - do not pass any configuration information kgdb will not do anything - at all. Kgdb will only actively hook up to the kernel trap hooks - if a kgdb I/O driver is loaded and configured. If you unconfigure - a kgdb I/O driver, kgdb will unregister all the kernel hook points. - - All kgdb I/O drivers can be reconfigured at run time, if - CONFIG_SYSFS and CONFIG_MODULES - are enabled, by echo'ing a new config string to - /sys/module/<driver>/parameter/<option>. - The driver can be unconfigured by passing an empty string. You cannot - change the configuration while the debugger is attached. Make sure - to detach the debugger with the detach command - prior to trying to unconfigure a kgdb I/O driver. - - - Connecting with gdb to a serial port - - Configure kgdboc - Configure kgdboc at boot using kernel parameters: - - kgdboc=ttyS0,115200 - - OR - Configure kgdboc after the kernel has booted: - - echo ttyS0 > /sys/module/kgdboc/parameters/kgdboc - - - - Stop kernel execution (break into the debugger) - In order to connect to gdb via kgdboc, the kernel must - first be stopped. There are several ways to stop the kernel which - include using kgdbwait as a boot argument, via a sysrq-g, or running - the kernel until it takes an exception where it waits for the - debugger to attach. - - When logged in as root or with a super user session you can run: - echo g > /proc/sysrq-trigger - Example using minicom 2.2 - Press: Control-a - Press: f - Press: g - - When you have telneted to a terminal server that supports sending a remote break - Press: Control-] - Type in:send break - Press: Enter - Press: g - - - - - - Connect from gdb - - Example (using a directly connected port): - - - % gdb ./vmlinux - (gdb) set remotebaud 115200 - (gdb) target remote /dev/ttyS0 - - - Example (kgdb to a terminal server on TCP port 2012): - - - % gdb ./vmlinux - (gdb) target remote 192.168.2.2:2012 - - - Once connected, you can debug a kernel the way you would debug an - application program. - - - If you are having problems connecting or something is going - seriously wrong while debugging, it will most often be the case - that you want to enable gdb to be verbose about its target - communications. You do this prior to issuing the target - remote command by typing in: set debug remote 1 - - - - Remember if you continue in gdb, and need to "break in" again, - you need to issue an other sysrq-g. It is easy to create a simple - entry point by putting a breakpoint at sys_sync - and then you can run "sync" from a shell or script to break into the - debugger. - - - - kgdb and kdb interoperability - It is possible to transition between kdb and kgdb dynamically. - The debug core will remember which you used the last time and - automatically start in the same mode. - - Switching between kdb and kgdb - - Switching from kgdb to kdb - - There are two ways to switch from kgdb to kdb: you can use gdb to - issue a maintenance packet, or you can blindly type the command $3#33. - Whenever the kernel debugger stops in kgdb mode it will print the - message KGDB or $3#33 for KDB. It is important - to note that you have to type the sequence correctly in one pass. - You cannot type a backspace or delete because kgdb will interpret - that as part of the debug stream. - - Change from kgdb to kdb by blindly typing: - $3#33 - Change from kgdb to kdb with gdb - maintenance packet 3 - NOTE: Now you must kill gdb. Typically you press control-z and - issue the command: kill -9 % - - - - - Change from kdb to kgdb - There are two ways you can change from kdb to kgdb. You can - manually enter kgdb mode by issuing the kgdb command from the kdb - shell prompt, or you can connect gdb while the kdb shell prompt is - active. The kdb shell looks for the typical first commands that gdb - would issue with the gdb remote protocol and if it sees one of those - commands it automatically changes into kgdb mode. - - From kdb issue the command: - kgdb - Now disconnect your terminal program and connect gdb in its place - At the kdb prompt, disconnect the terminal program and connect gdb in its place. - - - - - Running kdb commands from gdb - It is possible to run a limited set of kdb commands from gdb, - using the gdb monitor command. You don't want to execute any of the - run control or breakpoint operations, because it can disrupt the - state of the kernel debugger. You should be using gdb for - breakpoints and run control operations if you have gdb connected. - The more useful commands to run are things like lsmod, dmesg, ps or - possibly some of the memory information commands. To see all the kdb - commands you can run monitor help. - Example: - -(gdb) monitor ps -1 idle process (state I) and -27 sleeping system daemon (state M) processes suppressed, -use 'ps A' to see all. -Task Addr Pid Parent [*] cpu State Thread Command - -0xc78291d0 1 0 0 0 S 0xc7829404 init -0xc7954150 942 1 0 0 S 0xc7954384 dropbear -0xc78789c0 944 1 0 0 S 0xc7878bf4 sh -(gdb) - - - - - - kgdb Test Suite - - When kgdb is enabled in the kernel config you can also elect to - enable the config parameter KGDB_TESTS. Turning this on will - enable a special kgdb I/O module which is designed to test the - kgdb internal functions. - - - The kgdb tests are mainly intended for developers to test the kgdb - internals as well as a tool for developing a new kgdb architecture - specific implementation. These tests are not really for end users - of the Linux kernel. The primary source of documentation would be - to look in the drivers/misc/kgdbts.c file. - - - The kgdb test suite can also be configured at compile time to run - the core set of tests by setting the kernel config parameter - KGDB_TESTS_ON_BOOT. This particular option is aimed at automated - regression testing and does not require modifying the kernel boot - config arguments. If this is turned on, the kgdb test suite can - be disabled by specifying "kgdbts=" as a kernel boot argument. - - - - Kernel Debugger Internals - - Architecture Specifics - - The kernel debugger is organized into a number of components: - - The debug core - - The debug core is found in kernel/debugger/debug_core.c. It contains: - - A generic OS exception handler which includes - sync'ing the processors into a stopped state on an multi-CPU - system. - The API to talk to the kgdb I/O drivers - The API to make calls to the arch-specific kgdb implementation - The logic to perform safe memory reads and writes to memory while using the debugger - A full implementation for software breakpoints unless overridden by the arch - The API to invoke either the kdb or kgdb frontend to the debug core. - The structures and callback API for atomic kernel mode setting. - NOTE: kgdboc is where the kms callbacks are invoked. - - - - kgdb arch-specific implementation - - This implementation is generally found in arch/*/kernel/kgdb.c. - As an example, arch/x86/kernel/kgdb.c contains the specifics to - implement HW breakpoint as well as the initialization to - dynamically register and unregister for the trap handlers on - this architecture. The arch-specific portion implements: - - contains an arch-specific trap catcher which - invokes kgdb_handle_exception() to start kgdb about doing its - work - translation to and from gdb specific packet format to pt_regs - Registration and unregistration of architecture specific trap hooks - Any special exception handling and cleanup - NMI exception handling and cleanup - (optional) HW breakpoints - - - - gdbstub frontend (aka kgdb) - The gdbstub is located in kernel/debug/gdbstub.c. It contains: - - All the logic to implement the gdb serial protocol - - - kdb frontend - The kdb debugger shell is broken down into a number of - components. The kdb core is located in kernel/debug/kdb. There - are a number of helper functions in some of the other kernel - components to make it possible for kdb to examine and report - information about the kernel without taking locks that could - cause a kernel deadlock. The kdb core contains implements the following functionality. - - A simple shell - The kdb core command set - A registration API to register additional kdb shell commands. - - A good example of a self-contained kdb module - is the "ftdump" command for dumping the ftrace buffer. See: - kernel/trace/trace_kdb.c - For an example of how to dynamically register - a new kdb command you can build the kdb_hello.ko kernel module - from samples/kdb/kdb_hello.c. To build this example you can - set CONFIG_SAMPLES=y and CONFIG_SAMPLE_KDB=m in your kernel - config. Later run "modprobe kdb_hello" and the next time you - enter the kdb shell, you can run the "hello" - command. - - The implementation for kdb_printf() which - emits messages directly to I/O drivers, bypassing the kernel - log. - SW / HW breakpoint management for the kdb shell - - - kgdb I/O driver - - Each kgdb I/O driver has to provide an implementation for the following: - - configuration via built-in or module - dynamic configuration and kgdb hook registration calls - read and write character interface - A cleanup handler for unconfiguring from the kgdb core - (optional) Early debug methodology - - Any given kgdb I/O driver has to operate very closely with the - hardware and must do it in such a way that does not enable - interrupts or change other parts of the system context without - completely restoring them. The kgdb core will repeatedly "poll" - a kgdb I/O driver for characters when it needs input. The I/O - driver is expected to return immediately if there is no data - available. Doing so allows for the future possibility to touch - watchdog hardware in such a way as to have a target system not - reset when these are enabled. - - - - - - If you are intent on adding kgdb architecture specific support - for a new architecture, the architecture should define - HAVE_ARCH_KGDB in the architecture specific - Kconfig file. This will enable kgdb for the architecture, and - at that point you must create an architecture specific kgdb - implementation. - - - There are a few flags which must be set on every architecture in - their <asm/kgdb.h> file. These are: - - - - NUMREGBYTES: The size in bytes of all of the registers, so - that we can ensure they will all fit into a packet. - - - - - BUFMAX: The size in bytes of the buffer GDB will read into. - This must be larger than NUMREGBYTES. - - - - - CACHE_FLUSH_IS_SAFE: Set to 1 if it is always safe to call - flush_cache_range or flush_icache_range. On some architectures, - these functions may not be safe to call on SMP since we keep other - CPUs in a holding pattern. - - - - - - There are also the following functions for the common backend, - found in kernel/kgdb.c, that must be supplied by the - architecture-specific backend unless marked as (optional), in - which case a default function maybe used if the architecture - does not need to provide a specific implementation. - -!Iinclude/linux/kgdb.h - - - kgdboc internals - - kgdboc and uarts - - The kgdboc driver is actually a very thin driver that relies on the - underlying low level to the hardware driver having "polling hooks" - to which the tty driver is attached. In the initial - implementation of kgdboc the serial_core was changed to expose a - low level UART hook for doing polled mode reading and writing of a - single character while in an atomic context. When kgdb makes an I/O - request to the debugger, kgdboc invokes a callback in the serial - core which in turn uses the callback in the UART driver. - - When using kgdboc with a UART, the UART driver must implement two callbacks in the struct uart_ops. Example from drivers/8250.c: -#ifdef CONFIG_CONSOLE_POLL - .poll_get_char = serial8250_get_poll_char, - .poll_put_char = serial8250_put_poll_char, -#endif - - Any implementation specifics around creating a polling driver use the - #ifdef CONFIG_CONSOLE_POLL, as shown above. - Keep in mind that polling hooks have to be implemented in such a way - that they can be called from an atomic context and have to restore - the state of the UART chip on return such that the system can return - to normal when the debugger detaches. You need to be very careful - with any kind of lock you consider, because failing here is most likely - going to mean pressing the reset button. - - - - kgdboc and keyboards - The kgdboc driver contains logic to configure communications - with an attached keyboard. The keyboard infrastructure is only - compiled into the kernel when CONFIG_KDB_KEYBOARD=y is set in the - kernel configuration. - The core polled keyboard driver driver for PS/2 type keyboards - is in drivers/char/kdb_keyboard.c. This driver is hooked into the - debug core when kgdboc populates the callback in the array - called kdb_poll_funcs[]. The - kdb_get_kbd_char() is the top-level function which polls hardware - for single character input. - - - - kgdboc and kms - The kgdboc driver contains logic to request the graphics - display to switch to a text context when you are using - "kgdboc=kms,kbd", provided that you have a video driver which has a - frame buffer console and atomic kernel mode setting support. - - Every time the kernel - debugger is entered it calls kgdboc_pre_exp_handler() which in turn - calls con_debug_enter() in the virtual console layer. On resuming kernel - execution, the kernel debugger calls kgdboc_post_exp_handler() which - in turn calls con_debug_leave(). - Any video driver that wants to be compatible with the kernel - debugger and the atomic kms callbacks must implement the - mode_set_base_atomic, fb_debug_enter and fb_debug_leave operations. - For the fb_debug_enter and fb_debug_leave the option exists to use - the generic drm fb helper functions or implement something custom for - the hardware. The following example shows the initialization of the - .mode_set_base_atomic operation in - drivers/gpu/drm/i915/intel_display.c: - - -static const struct drm_crtc_helper_funcs intel_helper_funcs = { -[...] - .mode_set_base_atomic = intel_pipe_set_base_atomic, -[...] -}; - - - - Here is an example of how the i915 driver initializes the fb_debug_enter and fb_debug_leave functions to use the generic drm helpers in - drivers/gpu/drm/i915/intel_fb.c: - - -static struct fb_ops intelfb_ops = { -[...] - .fb_debug_enter = drm_fb_helper_debug_enter, - .fb_debug_leave = drm_fb_helper_debug_leave, -[...] -}; - - - - - - - - Credits - - The following people have contributed to this document: - - Amit Kaleamitkale@linsyssoft.com - Tom Rinitrini@kernel.crashing.org - - In March 2008 this document was completely rewritten by: - - Jason Wesseljason.wessel@windriver.com - - In Jan 2010 this document was updated to include kdb. - - Jason Wesseljason.wessel@windriver.com - - - - - diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl deleted file mode 100644 index 0320910b866db2..00000000000000 --- a/Documentation/DocBook/libata.tmpl +++ /dev/null @@ -1,1625 +0,0 @@ - - - - - - libATA Developer's Guide - - - - Jeff - Garzik - - - - - 2003-2006 - Jeff Garzik - - - - - The contents of this file are subject to the Open - Software License version 1.1 that can be found at - http://fedoraproject.org/wiki/Licensing:OSL1.1 - and is included herein by reference. - - - - Alternatively, the contents of this file may be used under the terms - of the GNU General Public License version 2 (the "GPL") as distributed - in the kernel source COPYING file, in which case the provisions of - the GPL are applicable instead of the above. If you wish to allow - the use of your version of this file only under the terms of the - GPL and not to allow others to use your version of this file under - the OSL, indicate your decision by deleting the provisions above and - replace them with the notice and other provisions required by the GPL. - If you do not delete the provisions above, a recipient may use your - version of this file under either the OSL or the GPL. - - - - - - - - - Introduction - - libATA is a library used inside the Linux kernel to support ATA host - controllers and devices. libATA provides an ATA driver API, class - transports for ATA and ATAPI devices, and SCSI<->ATA translation - for ATA devices according to the T10 SAT specification. - - - This Guide documents the libATA driver API, library functions, library - internals, and a couple sample ATA low-level drivers. - - - - - libata Driver API - - struct ata_port_operations is defined for every low-level libata - hardware driver, and it controls how the low-level driver - interfaces with the ATA and SCSI layers. - - - FIS-based drivers will hook into the system with ->qc_prep() and - ->qc_issue() high-level hooks. Hardware which behaves in a manner - similar to PCI IDE hardware may utilize several generic helpers, - defining at a bare minimum the bus I/O addresses of the ATA shadow - register blocks. - - - struct ata_port_operations - - Disable ATA port - -void (*port_disable) (struct ata_port *); - - - - Called from ata_bus_probe() error path, as well as when - unregistering from the SCSI module (rmmod, hot unplug). - This function should do whatever needs to be done to take the - port out of use. In most cases, ata_port_disable() can be used - as this hook. - - - Called from ata_bus_probe() on a failed probe. - Called from ata_scsi_release(). - - - - - Post-IDENTIFY device configuration - -void (*dev_config) (struct ata_port *, struct ata_device *); - - - - Called after IDENTIFY [PACKET] DEVICE is issued to each device - found. Typically used to apply device-specific fixups prior to - issue of SET FEATURES - XFER MODE, and prior to operation. - - - This entry may be specified as NULL in ata_port_operations. - - - - - Set PIO/DMA mode - -void (*set_piomode) (struct ata_port *, struct ata_device *); -void (*set_dmamode) (struct ata_port *, struct ata_device *); -void (*post_set_mode) (struct ata_port *); -unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned int); - - - - Hooks called prior to the issue of SET FEATURES - XFER MODE - command. The optional ->mode_filter() hook is called when libata - has built a mask of the possible modes. This is passed to the - ->mode_filter() function which should return a mask of valid modes - after filtering those unsuitable due to hardware limits. It is not - valid to use this interface to add modes. - - - dev->pio_mode and dev->dma_mode are guaranteed to be valid when - ->set_piomode() and when ->set_dmamode() is called. The timings for - any other drive sharing the cable will also be valid at this point. - That is the library records the decisions for the modes of each - drive on a channel before it attempts to set any of them. - - - ->post_set_mode() is - called unconditionally, after the SET FEATURES - XFER MODE - command completes successfully. - - - - ->set_piomode() is always called (if present), but - ->set_dma_mode() is only called if DMA is possible. - - - - - Taskfile read/write - -void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf); -void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf); - - - - ->tf_load() is called to load the given taskfile into hardware - registers / DMA buffers. ->tf_read() is called to read the - hardware registers / DMA buffers, to obtain the current set of - taskfile register values. - Most drivers for taskfile-based hardware (PIO or MMIO) use - ata_sff_tf_load() and ata_sff_tf_read() for these hooks. - - - - - PIO data read/write - -void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); - - - -All bmdma-style drivers must implement this hook. This is the low-level -operation that actually copies the data bytes during a PIO data -transfer. -Typically the driver will choose one of ata_sff_data_xfer_noirq(), -ata_sff_data_xfer(), or ata_sff_data_xfer32(). - - - - - ATA command execute - -void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf); - - - - causes an ATA command, previously loaded with - ->tf_load(), to be initiated in hardware. - Most drivers for taskfile-based hardware use ata_sff_exec_command() - for this hook. - - - - - Per-cmd ATAPI DMA capabilities filter - -int (*check_atapi_dma) (struct ata_queued_cmd *qc); - - - -Allow low-level driver to filter ATA PACKET commands, returning a status -indicating whether or not it is OK to use DMA for the supplied PACKET -command. - - - This hook may be specified as NULL, in which case libata will - assume that atapi dma can be supported. - - - - - Read specific ATA shadow registers - -u8 (*sff_check_status)(struct ata_port *ap); -u8 (*sff_check_altstatus)(struct ata_port *ap); - - - - Reads the Status/AltStatus ATA shadow register from - hardware. On some hardware, reading the Status register has - the side effect of clearing the interrupt condition. - Most drivers for taskfile-based hardware use - ata_sff_check_status() for this hook. - - - - - Write specific ATA shadow register - -void (*sff_set_devctl)(struct ata_port *ap, u8 ctl); - - - - Write the device control ATA shadow register to the hardware. - Most drivers don't need to define this. - - - - - Select ATA device on bus - -void (*sff_dev_select)(struct ata_port *ap, unsigned int device); - - - - Issues the low-level hardware command(s) that causes one of N - hardware devices to be considered 'selected' (active and - available for use) on the ATA bus. This generally has no - meaning on FIS-based devices. - - - Most drivers for taskfile-based hardware use - ata_sff_dev_select() for this hook. - - - - - Private tuning method - -void (*set_mode) (struct ata_port *ap); - - - - By default libata performs drive and controller tuning in - accordance with the ATA timing rules and also applies blacklists - and cable limits. Some controllers need special handling and have - custom tuning rules, typically raid controllers that use ATA - commands but do not actually do drive timing. - - - - - This hook should not be used to replace the standard controller - tuning logic when a controller has quirks. Replacing the default - tuning logic in that case would bypass handling for drive and - bridge quirks that may be important to data reliability. If a - controller needs to filter the mode selection it should use the - mode_filter hook instead. - - - - - - Control PCI IDE BMDMA engine - -void (*bmdma_setup) (struct ata_queued_cmd *qc); -void (*bmdma_start) (struct ata_queued_cmd *qc); -void (*bmdma_stop) (struct ata_port *ap); -u8 (*bmdma_status) (struct ata_port *ap); - - - -When setting up an IDE BMDMA transaction, these hooks arm -(->bmdma_setup), fire (->bmdma_start), and halt (->bmdma_stop) -the hardware's DMA engine. ->bmdma_status is used to read the standard -PCI IDE DMA Status register. - - - -These hooks are typically either no-ops, or simply not implemented, in -FIS-based drivers. - - -Most legacy IDE drivers use ata_bmdma_setup() for the bmdma_setup() -hook. ata_bmdma_setup() will write the pointer to the PRD table to -the IDE PRD Table Address register, enable DMA in the DMA Command -register, and call exec_command() to begin the transfer. - - -Most legacy IDE drivers use ata_bmdma_start() for the bmdma_start() -hook. ata_bmdma_start() will write the ATA_DMA_START flag to the DMA -Command register. - - -Many legacy IDE drivers use ata_bmdma_stop() for the bmdma_stop() -hook. ata_bmdma_stop() clears the ATA_DMA_START flag in the DMA -command register. - - -Many legacy IDE drivers use ata_bmdma_status() as the bmdma_status() hook. - - - - - High-level taskfile hooks - -void (*qc_prep) (struct ata_queued_cmd *qc); -int (*qc_issue) (struct ata_queued_cmd *qc); - - - - Higher-level hooks, these two hooks can potentially supercede - several of the above taskfile/DMA engine hooks. ->qc_prep is - called after the buffers have been DMA-mapped, and is typically - used to populate the hardware's DMA scatter-gather table. - Most drivers use the standard ata_qc_prep() helper function, but - more advanced drivers roll their own. - - - ->qc_issue is used to make a command active, once the hardware - and S/G tables have been prepared. IDE BMDMA drivers use the - helper function ata_qc_issue_prot() for taskfile protocol-based - dispatch. More advanced drivers implement their own ->qc_issue. - - - ata_qc_issue_prot() calls ->tf_load(), ->bmdma_setup(), and - ->bmdma_start() as necessary to initiate a transfer. - - - - - Exception and probe handling (EH) - -void (*eng_timeout) (struct ata_port *ap); -void (*phy_reset) (struct ata_port *ap); - - - -Deprecated. Use ->error_handler() instead. - - - -void (*freeze) (struct ata_port *ap); -void (*thaw) (struct ata_port *ap); - - - -ata_port_freeze() is called when HSM violations or some other -condition disrupts normal operation of the port. A frozen port -is not allowed to perform any operation until the port is -thawed, which usually follows a successful reset. - - - -The optional ->freeze() callback can be used for freezing the port -hardware-wise (e.g. mask interrupt and stop DMA engine). If a -port cannot be frozen hardware-wise, the interrupt handler -must ack and clear interrupts unconditionally while the port -is frozen. - - -The optional ->thaw() callback is called to perform the opposite of ->freeze(): -prepare the port for normal operation once again. Unmask interrupts, -start DMA engine, etc. - - - -void (*error_handler) (struct ata_port *ap); - - - -->error_handler() is a driver's hook into probe, hotplug, and recovery -and other exceptional conditions. The primary responsibility of an -implementation is to call ata_do_eh() or ata_bmdma_drive_eh() with a set -of EH hooks as arguments: - - - -'prereset' hook (may be NULL) is called during an EH reset, before any other actions -are taken. - - - -'postreset' hook (may be NULL) is called after the EH reset is performed. Based on -existing conditions, severity of the problem, and hardware capabilities, - - - -Either 'softreset' (may be NULL) or 'hardreset' (may be NULL) will be -called to perform the low-level EH reset. - - - -void (*post_internal_cmd) (struct ata_queued_cmd *qc); - - - -Perform any hardware-specific actions necessary to finish processing -after executing a probe-time or EH-time command via ata_exec_internal(). - - - - - Hardware interrupt handling - -irqreturn_t (*irq_handler)(int, void *, struct pt_regs *); -void (*irq_clear) (struct ata_port *); - - - - ->irq_handler is the interrupt handling routine registered with - the system, by libata. ->irq_clear is called during probe just - before the interrupt handler is registered, to be sure hardware - is quiet. - - - The second argument, dev_instance, should be cast to a pointer - to struct ata_host_set. - - - Most legacy IDE drivers use ata_sff_interrupt() for the - irq_handler hook, which scans all ports in the host_set, - determines which queued command was active (if any), and calls - ata_sff_host_intr(ap,qc). - - - Most legacy IDE drivers use ata_sff_irq_clear() for the - irq_clear() hook, which simply clears the interrupt and error - flags in the DMA status register. - - - - - SATA phy read/write - -int (*scr_read) (struct ata_port *ap, unsigned int sc_reg, - u32 *val); -int (*scr_write) (struct ata_port *ap, unsigned int sc_reg, - u32 val); - - - - Read and write standard SATA phy registers. Currently only used - if ->phy_reset hook called the sata_phy_reset() helper function. - sc_reg is one of SCR_STATUS, SCR_CONTROL, SCR_ERROR, or SCR_ACTIVE. - - - - - Init and shutdown - -int (*port_start) (struct ata_port *ap); -void (*port_stop) (struct ata_port *ap); -void (*host_stop) (struct ata_host_set *host_set); - - - - ->port_start() is called just after the data structures for each - port are initialized. Typically this is used to alloc per-port - DMA buffers / tables / rings, enable DMA engines, and similar - tasks. Some drivers also use this entry point as a chance to - allocate driver-private memory for ap->private_data. - - - Many drivers use ata_port_start() as this hook or call - it from their own port_start() hooks. ata_port_start() - allocates space for a legacy IDE PRD table and returns. - - - ->port_stop() is called after ->host_stop(). Its sole function - is to release DMA/memory resources, now that they are no longer - actively being used. Many drivers also free driver-private - data from port at this time. - - - ->host_stop() is called after all ->port_stop() calls -have completed. The hook must finalize hardware shutdown, release DMA -and other resources, etc. - This hook may be specified as NULL, in which case it is not called. - - - - - - - - - Error handling - - - This chapter describes how errors are handled under libata. - Readers are advised to read SCSI EH - (Documentation/scsi/scsi_eh.txt) and ATA exceptions doc first. - - - Origins of commands - - In libata, a command is represented with struct ata_queued_cmd - or qc. qc's are preallocated during port initialization and - repetitively used for command executions. Currently only one - qc is allocated per port but yet-to-be-merged NCQ branch - allocates one for each tag and maps each qc to NCQ tag 1-to-1. - - - libata commands can originate from two sources - libata itself - and SCSI midlayer. libata internal commands are used for - initialization and error handling. All normal blk requests - and commands for SCSI emulation are passed as SCSI commands - through queuecommand callback of SCSI host template. - - - - How commands are issued - - - - Internal commands - - - First, qc is allocated and initialized using - ata_qc_new_init(). Although ata_qc_new_init() doesn't - implement any wait or retry mechanism when qc is not - available, internal commands are currently issued only during - initialization and error recovery, so no other command is - active and allocation is guaranteed to succeed. - - - Once allocated qc's taskfile is initialized for the command to - be executed. qc currently has two mechanisms to notify - completion. One is via qc->complete_fn() callback and the - other is completion qc->waiting. qc->complete_fn() callback - is the asynchronous path used by normal SCSI translated - commands and qc->waiting is the synchronous (issuer sleeps in - process context) path used by internal commands. - - - Once initialization is complete, host_set lock is acquired - and the qc is issued. - - - - - SCSI commands - - - All libata drivers use ata_scsi_queuecmd() as - hostt->queuecommand callback. scmds can either be simulated - or translated. No qc is involved in processing a simulated - scmd. The result is computed right away and the scmd is - completed. - - - For a translated scmd, ata_qc_new_init() is invoked to - allocate a qc and the scmd is translated into the qc. SCSI - midlayer's completion notification function pointer is stored - into qc->scsidone. - - - qc->complete_fn() callback is used for completion - notification. ATA commands use ata_scsi_qc_complete() while - ATAPI commands use atapi_qc_complete(). Both functions end up - calling qc->scsidone to notify upper layer when the qc is - finished. After translation is completed, the qc is issued - with ata_qc_issue(). - - - Note that SCSI midlayer invokes hostt->queuecommand while - holding host_set lock, so all above occur while holding - host_set lock. - - - - - - - - How commands are processed - - Depending on which protocol and which controller are used, - commands are processed differently. For the purpose of - discussion, a controller which uses taskfile interface and all - standard callbacks is assumed. - - - Currently 6 ATA command protocols are used. They can be - sorted into the following four categories according to how - they are processed. - - - - ATA NO DATA or DMA - - - ATA_PROT_NODATA and ATA_PROT_DMA fall into this category. - These types of commands don't require any software - intervention once issued. Device will raise interrupt on - completion. - - - - - ATA PIO - - - ATA_PROT_PIO is in this category. libata currently - implements PIO with polling. ATA_NIEN bit is set to turn - off interrupt and pio_task on ata_wq performs polling and - IO. - - - - - ATAPI NODATA or DMA - - - ATA_PROT_ATAPI_NODATA and ATA_PROT_ATAPI_DMA are in this - category. packet_task is used to poll BSY bit after - issuing PACKET command. Once BSY is turned off by the - device, packet_task transfers CDB and hands off processing - to interrupt handler. - - - - - ATAPI PIO - - - ATA_PROT_ATAPI is in this category. ATA_NIEN bit is set - and, as in ATAPI NODATA or DMA, packet_task submits cdb. - However, after submitting cdb, further processing (data - transfer) is handed off to pio_task. - - - - - - - How commands are completed - - Once issued, all qc's are either completed with - ata_qc_complete() or time out. For commands which are handled - by interrupts, ata_host_intr() invokes ata_qc_complete(), and, - for PIO tasks, pio_task invokes ata_qc_complete(). In error - cases, packet_task may also complete commands. - - - ata_qc_complete() does the following. - - - - - - - DMA memory is unmapped. - - - - - - ATA_QCFLAG_ACTIVE is cleared from qc->flags. - - - - - - qc->complete_fn() callback is invoked. If the return value of - the callback is not zero. Completion is short circuited and - ata_qc_complete() returns. - - - - - - __ata_qc_complete() is called, which does - - - - - qc->flags is cleared to zero. - - - - - - ap->active_tag and qc->tag are poisoned. - - - - - - qc->waiting is cleared & completed (in that order). - - - - - - qc is deallocated by clearing appropriate bit in ap->qactive. - - - - - - - - - - - So, it basically notifies upper layer and deallocates qc. One - exception is short-circuit path in #3 which is used by - atapi_qc_complete(). - - - For all non-ATAPI commands, whether it fails or not, almost - the same code path is taken and very little error handling - takes place. A qc is completed with success status if it - succeeded, with failed status otherwise. - - - However, failed ATAPI commands require more handling as - REQUEST SENSE is needed to acquire sense data. If an ATAPI - command fails, ata_qc_complete() is invoked with error status, - which in turn invokes atapi_qc_complete() via - qc->complete_fn() callback. - - - This makes atapi_qc_complete() set scmd->result to - SAM_STAT_CHECK_CONDITION, complete the scmd and return 1. As - the sense data is empty but scmd->result is CHECK CONDITION, - SCSI midlayer will invoke EH for the scmd, and returning 1 - makes ata_qc_complete() to return without deallocating the qc. - This leads us to ata_scsi_error() with partially completed qc. - - - - - ata_scsi_error() - - ata_scsi_error() is the current transportt->eh_strategy_handler() - for libata. As discussed above, this will be entered in two - cases - timeout and ATAPI error completion. This function - calls low level libata driver's eng_timeout() callback, the - standard callback for which is ata_eng_timeout(). It checks - if a qc is active and calls ata_qc_timeout() on the qc if so. - Actual error handling occurs in ata_qc_timeout(). - - - If EH is invoked for timeout, ata_qc_timeout() stops BMDMA and - completes the qc. Note that as we're currently in EH, we - cannot call scsi_done. As described in SCSI EH doc, a - recovered scmd should be either retried with - scsi_queue_insert() or finished with scsi_finish_command(). - Here, we override qc->scsidone with scsi_finish_command() and - calls ata_qc_complete(). - - - If EH is invoked due to a failed ATAPI qc, the qc here is - completed but not deallocated. The purpose of this - half-completion is to use the qc as place holder to make EH - code reach this place. This is a bit hackish, but it works. - - - Once control reaches here, the qc is deallocated by invoking - __ata_qc_complete() explicitly. Then, internal qc for REQUEST - SENSE is issued. Once sense data is acquired, scmd is - finished by directly invoking scsi_finish_command() on the - scmd. Note that as we already have completed and deallocated - the qc which was associated with the scmd, we don't need - to/cannot call ata_qc_complete() again. - - - - - Problems with the current EH - - - - - - Error representation is too crude. Currently any and all - error conditions are represented with ATA STATUS and ERROR - registers. Errors which aren't ATA device errors are treated - as ATA device errors by setting ATA_ERR bit. Better error - descriptor which can properly represent ATA and other - errors/exceptions is needed. - - - - - - When handling timeouts, no action is taken to make device - forget about the timed out command and ready for new commands. - - - - - - EH handling via ata_scsi_error() is not properly protected - from usual command processing. On EH entrance, the device is - not in quiescent state. Timed out commands may succeed or - fail any time. pio_task and atapi_task may still be running. - - - - - - Too weak error recovery. Devices / controllers causing HSM - mismatch errors and other errors quite often require reset to - return to known state. Also, advanced error handling is - necessary to support features like NCQ and hotplug. - - - - - - ATA errors are directly handled in the interrupt handler and - PIO errors in pio_task. This is problematic for advanced - error handling for the following reasons. - - - First, advanced error handling often requires context and - internal qc execution. - - - Second, even a simple failure (say, CRC error) needs - information gathering and could trigger complex error handling - (say, resetting & reconfiguring). Having multiple code - paths to gather information, enter EH and trigger actions - makes life painful. - - - Third, scattered EH code makes implementing low level drivers - difficult. Low level drivers override libata callbacks. If - EH is scattered over several places, each affected callbacks - should perform its part of error handling. This can be error - prone and painful. - - - - - - - - - libata Library -!Edrivers/ata/libata-core.c - - - - libata Core Internals -!Idrivers/ata/libata-core.c - - - - libata SCSI translation/emulation -!Edrivers/ata/libata-scsi.c -!Idrivers/ata/libata-scsi.c - - - - ATA errors and exceptions - - - This chapter tries to identify what error/exception conditions exist - for ATA/ATAPI devices and describe how they should be handled in - implementation-neutral way. - - - - The term 'error' is used to describe conditions where either an - explicit error condition is reported from device or a command has - timed out. - - - - The term 'exception' is either used to describe exceptional - conditions which are not errors (say, power or hotplug events), or - to describe both errors and non-error exceptional conditions. Where - explicit distinction between error and exception is necessary, the - term 'non-error exception' is used. - - - - Exception categories - - Exceptions are described primarily with respect to legacy - taskfile + bus master IDE interface. If a controller provides - other better mechanism for error reporting, mapping those into - categories described below shouldn't be difficult. - - - - In the following sections, two recovery actions - reset and - reconfiguring transport - are mentioned. These are described - further in . - - - - HSM violation - - This error is indicated when STATUS value doesn't match HSM - requirement during issuing or execution any ATA/ATAPI command. - - - - Examples - - - - ATA_STATUS doesn't contain !BSY && DRDY && !DRQ while trying - to issue a command. - - - - - - !BSY && !DRQ during PIO data transfer. - - - - - - DRQ on command completion. - - - - - - !BSY && ERR after CDB transfer starts but before the - last byte of CDB is transferred. ATA/ATAPI standard states - that "The device shall not terminate the PACKET command - with an error before the last byte of the command packet has - been written" in the error outputs description of PACKET - command and the state diagram doesn't include such - transitions. - - - - - - - In these cases, HSM is violated and not much information - regarding the error can be acquired from STATUS or ERROR - register. IOW, this error can be anything - driver bug, - faulty device, controller and/or cable. - - - - As HSM is violated, reset is necessary to restore known state. - Reconfiguring transport for lower speed might be helpful too - as transmission errors sometimes cause this kind of errors. - - - - - ATA/ATAPI device error (non-NCQ / non-CHECK CONDITION) - - - These are errors detected and reported by ATA/ATAPI devices - indicating device problems. For this type of errors, STATUS - and ERROR register values are valid and describe error - condition. Note that some of ATA bus errors are detected by - ATA/ATAPI devices and reported using the same mechanism as - device errors. Those cases are described later in this - section. - - - - For ATA commands, this type of errors are indicated by !BSY - && ERR during command execution and on completion. - - - For ATAPI commands, - - - - - - !BSY && ERR && ABRT right after issuing PACKET - indicates that PACKET command is not supported and falls in - this category. - - - - - - !BSY && ERR(==CHK) && !ABRT after the last - byte of CDB is transferred indicates CHECK CONDITION and - doesn't fall in this category. - - - - - - !BSY && ERR(==CHK) && ABRT after the last byte - of CDB is transferred *probably* indicates CHECK CONDITION and - doesn't fall in this category. - - - - - - - Of errors detected as above, the following are not ATA/ATAPI - device errors but ATA bus errors and should be handled - according to . - - - - - - CRC error during data transfer - - - This is indicated by ICRC bit in the ERROR register and - means that corruption occurred during data transfer. Up to - ATA/ATAPI-7, the standard specifies that this bit is only - applicable to UDMA transfers but ATA/ATAPI-8 draft revision - 1f says that the bit may be applicable to multiword DMA and - PIO. - - - - - - ABRT error during data transfer or on completion - - - Up to ATA/ATAPI-7, the standard specifies that ABRT could be - set on ICRC errors and on cases where a device is not able - to complete a command. Combined with the fact that MWDMA - and PIO transfer errors aren't allowed to use ICRC bit up to - ATA/ATAPI-7, it seems to imply that ABRT bit alone could - indicate transfer errors. - - - However, ATA/ATAPI-8 draft revision 1f removes the part - that ICRC errors can turn on ABRT. So, this is kind of - gray area. Some heuristics are needed here. - - - - - - - - ATA/ATAPI device errors can be further categorized as follows. - - - - - - Media errors - - - This is indicated by UNC bit in the ERROR register. ATA - devices reports UNC error only after certain number of - retries cannot recover the data, so there's nothing much - else to do other than notifying upper layer. - - - READ and WRITE commands report CHS or LBA of the first - failed sector but ATA/ATAPI standard specifies that the - amount of transferred data on error completion is - indeterminate, so we cannot assume that sectors preceding - the failed sector have been transferred and thus cannot - complete those sectors successfully as SCSI does. - - - - - - Media changed / media change requested error - - - <<TODO: fill here>> - - - - - Address error - - - This is indicated by IDNF bit in the ERROR register. - Report to upper layer. - - - - - Other errors - - - This can be invalid command or parameter indicated by ABRT - ERROR bit or some other error condition. Note that ABRT - bit can indicate a lot of things including ICRC and Address - errors. Heuristics needed. - - - - - - - - Depending on commands, not all STATUS/ERROR bits are - applicable. These non-applicable bits are marked with - "na" in the output descriptions but up to ATA/ATAPI-7 - no definition of "na" can be found. However, - ATA/ATAPI-8 draft revision 1f describes "N/A" as - follows. - - -
- - 3.2.3.3a N/A - - - A keyword the indicates a field has no defined value in - this standard and should not be checked by the host or - device. N/A fields should be cleared to zero. - - - - -
- - - So, it seems reasonable to assume that "na" bits are - cleared to zero by devices and thus need no explicit masking. - - - - - - ATAPI device CHECK CONDITION - - - ATAPI device CHECK CONDITION error is indicated by set CHK bit - (ERR bit) in the STATUS register after the last byte of CDB is - transferred for a PACKET command. For this kind of errors, - sense data should be acquired to gather information regarding - the errors. REQUEST SENSE packet command should be used to - acquire sense data. - - - - Once sense data is acquired, this type of errors can be - handled similarly to other SCSI errors. Note that sense data - may indicate ATA bus error (e.g. Sense Key 04h HARDWARE ERROR - && ASC/ASCQ 47h/00h SCSI PARITY ERROR). In such - cases, the error should be considered as an ATA bus error and - handled according to . - - - - - - ATA device error (NCQ) - - - NCQ command error is indicated by cleared BSY and set ERR bit - during NCQ command phase (one or more NCQ commands - outstanding). Although STATUS and ERROR registers will - contain valid values describing the error, READ LOG EXT is - required to clear the error condition, determine which command - has failed and acquire more information. - - - - READ LOG EXT Log Page 10h reports which tag has failed and - taskfile register values describing the error. With this - information the failed command can be handled as a normal ATA - command error as in and all - other in-flight commands must be retried. Note that this - retry should not be counted - it's likely that commands - retried this way would have completed normally if it were not - for the failed command. - - - - Note that ATA bus errors can be reported as ATA device NCQ - errors. This should be handled as described in . - - - - If READ LOG EXT Log Page 10h fails or reports NQ, we're - thoroughly screwed. This condition should be treated - according to . - - - - - - ATA bus error - - - ATA bus error means that data corruption occurred during - transmission over ATA bus (SATA or PATA). This type of errors - can be indicated by - - - - - - - ICRC or ABRT error as described in . - - - - - - Controller-specific error completion with error information - indicating transmission error. - - - - - - On some controllers, command timeout. In this case, there may - be a mechanism to determine that the timeout is due to - transmission error. - - - - - - Unknown/random errors, timeouts and all sorts of weirdities. - - - - - - - As described above, transmission errors can cause wide variety - of symptoms ranging from device ICRC error to random device - lockup, and, for many cases, there is no way to tell if an - error condition is due to transmission error or not; - therefore, it's necessary to employ some kind of heuristic - when dealing with errors and timeouts. For example, - encountering repetitive ABRT errors for known supported - command is likely to indicate ATA bus error. - - - - Once it's determined that ATA bus errors have possibly - occurred, lowering ATA bus transmission speed is one of - actions which may alleviate the problem. See for more information. - - - - - - PCI bus error - - - Data corruption or other failures during transmission over PCI - (or other system bus). For standard BMDMA, this is indicated - by Error bit in the BMDMA Status register. This type of - errors must be logged as it indicates something is very wrong - with the system. Resetting host controller is recommended. - - - - - - Late completion - - - This occurs when timeout occurs and the timeout handler finds - out that the timed out command has completed successfully or - with error. This is usually caused by lost interrupts. This - type of errors must be logged. Resetting host controller is - recommended. - - - - - - Unknown error (timeout) - - - This is when timeout occurs and the command is still - processing or the host and device are in unknown state. When - this occurs, HSM could be in any valid or invalid state. To - bring the device to known state and make it forget about the - timed out command, resetting is necessary. The timed out - command may be retried. - - - - Timeouts can also be caused by transmission errors. Refer to - for more details. - - - - - - Hotplug and power management exceptions - - - <<TODO: fill here>> - - - - - - - - EH recovery actions - - - This section discusses several important recovery actions. - - - - Clearing error condition - - - Many controllers require its error registers to be cleared by - error handler. Different controllers may have different - requirements. - - - - For SATA, it's strongly recommended to clear at least SError - register during error handling. - - - - - Reset - - - During EH, resetting is necessary in the following cases. - - - - - - - HSM is in unknown or invalid state - - - - - - HBA is in unknown or invalid state - - - - - - EH needs to make HBA/device forget about in-flight commands - - - - - - HBA/device behaves weirdly - - - - - - - Resetting during EH might be a good idea regardless of error - condition to improve EH robustness. Whether to reset both or - either one of HBA and device depends on situation but the - following scheme is recommended. - - - - - - - When it's known that HBA is in ready state but ATA/ATAPI - device is in unknown state, reset only device. - - - - - - If HBA is in unknown state, reset both HBA and device. - - - - - - - HBA resetting is implementation specific. For a controller - complying to taskfile/BMDMA PCI IDE, stopping active DMA - transaction may be sufficient iff BMDMA state is the only HBA - context. But even mostly taskfile/BMDMA PCI IDE complying - controllers may have implementation specific requirements and - mechanism to reset themselves. This must be addressed by - specific drivers. - - - - OTOH, ATA/ATAPI standard describes in detail ways to reset - ATA/ATAPI devices. - - - - - PATA hardware reset - - - This is hardware initiated device reset signalled with - asserted PATA RESET- signal. There is no standard way to - initiate hardware reset from software although some - hardware provides registers that allow driver to directly - tweak the RESET- signal. - - - - - Software reset - - - This is achieved by turning CONTROL SRST bit on for at - least 5us. Both PATA and SATA support it but, in case of - SATA, this may require controller-specific support as the - second Register FIS to clear SRST should be transmitted - while BSY bit is still set. Note that on PATA, this resets - both master and slave devices on a channel. - - - - - EXECUTE DEVICE DIAGNOSTIC command - - - Although ATA/ATAPI standard doesn't describe exactly, EDD - implies some level of resetting, possibly similar level - with software reset. Host-side EDD protocol can be handled - with normal command processing and most SATA controllers - should be able to handle EDD's just like other commands. - As in software reset, EDD affects both devices on a PATA - bus. - - - Although EDD does reset devices, this doesn't suit error - handling as EDD cannot be issued while BSY is set and it's - unclear how it will act when device is in unknown/weird - state. - - - - - ATAPI DEVICE RESET command - - - This is very similar to software reset except that reset - can be restricted to the selected device without affecting - the other device sharing the cable. - - - - - SATA phy reset - - - This is the preferred way of resetting a SATA device. In - effect, it's identical to PATA hardware reset. Note that - this can be done with the standard SCR Control register. - As such, it's usually easier to implement than software - reset. - - - - - - - - One more thing to consider when resetting devices is that - resetting clears certain configuration parameters and they - need to be set to their previous or newly adjusted values - after reset. - - - - Parameters affected are. - - - - - - - CHS set up with INITIALIZE DEVICE PARAMETERS (seldom used) - - - - - - Parameters set with SET FEATURES including transfer mode setting - - - - - - Block count set with SET MULTIPLE MODE - - - - - - Other parameters (SET MAX, MEDIA LOCK...) - - - - - - - ATA/ATAPI standard specifies that some parameters must be - maintained across hardware or software reset, but doesn't - strictly specify all of them. Always reconfiguring needed - parameters after reset is required for robustness. Note that - this also applies when resuming from deep sleep (power-off). - - - - Also, ATA/ATAPI standard requires that IDENTIFY DEVICE / - IDENTIFY PACKET DEVICE is issued after any configuration - parameter is updated or a hardware reset and the result used - for further operation. OS driver is required to implement - revalidation mechanism to support this. - - - - - - Reconfigure transport - - - For both PATA and SATA, a lot of corners are cut for cheap - connectors, cables or controllers and it's quite common to see - high transmission error rate. This can be mitigated by - lowering transmission speed. - - - - The following is a possible scheme Jeff Garzik suggested. - - -
- - If more than $N (3?) transmission errors happen in 15 minutes, - - - - - if SATA, decrease SATA PHY speed. if speed cannot be decreased, - - - - - decrease UDMA xfer speed. if at UDMA0, switch to PIO4, - - - - - decrease PIO xfer speed. if at PIO3, complain, but continue - - - -
- - - - - - - - - ata_piix Internals -!Idrivers/ata/ata_piix.c - - - - sata_sil Internals -!Idrivers/ata/sata_sil.c - - - - Thanks - - The bulk of the ATA knowledge comes thanks to long conversations with - Andre Hedrick (www.linux-ide.org), and long hours pondering the ATA - and SCSI specifications. - - - Thanks to Alan Cox for pointing out similarities - between SATA and SCSI, and in general for motivation to hack on - libata. - - - libata's device detection - method, ata_pio_devchk, and in general all the early probing was - based on extensive study of Hale Landis's probe/reset code in his - ATADRVR driver (www.ata-atapi.com). - - - - diff --git a/Documentation/DocBook/librs.tmpl b/Documentation/DocBook/librs.tmpl deleted file mode 100644 index 94f21361e0edaa..00000000000000 --- a/Documentation/DocBook/librs.tmpl +++ /dev/null @@ -1,289 +0,0 @@ - - - - - - Reed-Solomon Library Programming Interface - - - - Thomas - Gleixner - -
- tglx@linutronix.de -
- - - - - - 2004 - Thomas Gleixner - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2 as published by the Free Software Foundation. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - The generic Reed-Solomon Library provides encoding, decoding - and error correction functions. - - - Reed-Solomon codes are used in communication and storage - applications to ensure data integrity. - - - This documentation is provided for developers who want to utilize - the functions provided by the library. - - - - - Known Bugs And Assumptions - - None. - - - - - Usage - - This chapter provides examples of how to use the library. - - - Initializing - - The init function init_rs returns a pointer to an - rs decoder structure, which holds the necessary - information for encoding, decoding and error correction - with the given polynomial. It either uses an existing - matching decoder or creates a new one. On creation all - the lookup tables for fast en/decoding are created. - The function may take a while, so make sure not to - call it in critical code paths. - - -/* the Reed Solomon control structure */ -static struct rs_control *rs_decoder; - -/* Symbolsize is 10 (bits) - * Primitive polynomial is x^10+x^3+1 - * first consecutive root is 0 - * primitive element to generate roots = 1 - * generator polynomial degree (number of roots) = 6 - */ -rs_decoder = init_rs (10, 0x409, 0, 1, 6); - - - - Encoding - - The encoder calculates the Reed-Solomon code over - the given data length and stores the result in - the parity buffer. Note that the parity buffer must - be initialized before calling the encoder. - - - The expanded data can be inverted on the fly by - providing a non-zero inversion mask. The expanded data is - XOR'ed with the mask. This is used e.g. for FLASH - ECC, where the all 0xFF is inverted to an all 0x00. - The Reed-Solomon code for all 0x00 is all 0x00. The - code is inverted before storing to FLASH so it is 0xFF - too. This prevents that reading from an erased FLASH - results in ECC errors. - - - The databytes are expanded to the given symbol size - on the fly. There is no support for encoding continuous - bitstreams with a symbol size != 8 at the moment. If - it is necessary it should be not a big deal to implement - such functionality. - - -/* Parity buffer. Size = number of roots */ -uint16_t par[6]; -/* Initialize the parity buffer */ -memset(par, 0, sizeof(par)); -/* Encode 512 byte in data8. Store parity in buffer par */ -encode_rs8 (rs_decoder, data8, 512, par, 0); - - - - Decoding - - The decoder calculates the syndrome over - the given data length and the received parity symbols - and corrects errors in the data. - - - If a syndrome is available from a hardware decoder - then the syndrome calculation is skipped. - - - The correction of the data buffer can be suppressed - by providing a correction pattern buffer and an error - location buffer to the decoder. The decoder stores the - calculated error location and the correction bitmask - in the given buffers. This is useful for hardware - decoders which use a weird bit ordering scheme. - - - The databytes are expanded to the given symbol size - on the fly. There is no support for decoding continuous - bitstreams with a symbolsize != 8 at the moment. If - it is necessary it should be not a big deal to implement - such functionality. - - - - - Decoding with syndrome calculation, direct data correction - - -/* Parity buffer. Size = number of roots */ -uint16_t par[6]; -uint8_t data[512]; -int numerr; -/* Receive data */ -..... -/* Receive parity */ -..... -/* Decode 512 byte in data8.*/ -numerr = decode_rs8 (rs_decoder, data8, par, 512, NULL, 0, NULL, 0, NULL); - - - - - - Decoding with syndrome given by hardware decoder, direct data correction - - -/* Parity buffer. Size = number of roots */ -uint16_t par[6], syn[6]; -uint8_t data[512]; -int numerr; -/* Receive data */ -..... -/* Receive parity */ -..... -/* Get syndrome from hardware decoder */ -..... -/* Decode 512 byte in data8.*/ -numerr = decode_rs8 (rs_decoder, data8, par, 512, syn, 0, NULL, 0, NULL); - - - - - - Decoding with syndrome given by hardware decoder, no direct data correction. - - - Note: It's not necessary to give data and received parity to the decoder. - - -/* Parity buffer. Size = number of roots */ -uint16_t par[6], syn[6], corr[8]; -uint8_t data[512]; -int numerr, errpos[8]; -/* Receive data */ -..... -/* Receive parity */ -..... -/* Get syndrome from hardware decoder */ -..... -/* Decode 512 byte in data8.*/ -numerr = decode_rs8 (rs_decoder, NULL, NULL, 512, syn, 0, errpos, 0, corr); -for (i = 0; i < numerr; i++) { - do_error_correction_in_your_buffer(errpos[i], corr[i]); -} - - - - - Cleanup - - The function free_rs frees the allocated resources, - if the caller is the last user of the decoder. - - -/* Release resources */ -free_rs(rs_decoder); - - - - - - - Structures - - This chapter contains the autogenerated documentation of the structures which are - used in the Reed-Solomon Library and are relevant for a developer. - -!Iinclude/linux/rslib.h - - - - Public Functions Provided - - This chapter contains the autogenerated documentation of the Reed-Solomon functions - which are exported. - -!Elib/reed_solomon/reed_solomon.c - - - - Credits - - The library code for encoding and decoding was written by Phil Karn. - - - Copyright 2002, Phil Karn, KA9Q - May be used under the terms of the GNU General Public License (GPL) - - - The wrapper functions and interfaces are written by Thomas Gleixner. - - - Many users have provided bugfixes, improvements and helping hands for testing. - Thanks a lot. - - - The following people have contributed to this document: - - - Thomas Gleixnertglx@linutronix.de - - - diff --git a/Documentation/DocBook/lsm.tmpl b/Documentation/DocBook/lsm.tmpl deleted file mode 100644 index fe7664ce966780..00000000000000 --- a/Documentation/DocBook/lsm.tmpl +++ /dev/null @@ -1,265 +0,0 @@ - - - -
- - Linux Security Modules: General Security Hooks for Linux - - - Stephen - Smalley - - NAI Labs -
ssmalley@nai.com
- - - - Timothy - Fraser - - NAI Labs -
tfraser@nai.com
- - - - Chris - Vance - - NAI Labs -
cvance@nai.com
- - - - - -Introduction - - -In March 2001, the National Security Agency (NSA) gave a presentation -about Security-Enhanced Linux (SELinux) at the 2.5 Linux Kernel -Summit. SELinux is an implementation of flexible and fine-grained -nondiscretionary access controls in the Linux kernel, originally -implemented as its own particular kernel patch. Several other -security projects (e.g. RSBAC, Medusa) have also developed flexible -access control architectures for the Linux kernel, and various -projects have developed particular access control models for Linux -(e.g. LIDS, DTE, SubDomain). Each project has developed and -maintained its own kernel patch to support its security needs. - - - -In response to the NSA presentation, Linus Torvalds made a set of -remarks that described a security framework he would be willing to -consider for inclusion in the mainstream Linux kernel. He described a -general framework that would provide a set of security hooks to -control operations on kernel objects and a set of opaque security -fields in kernel data structures for maintaining security attributes. -This framework could then be used by loadable kernel modules to -implement any desired model of security. Linus also suggested the -possibility of migrating the Linux capabilities code into such a -module. - - - -The Linux Security Modules (LSM) project was started by WireX to -develop such a framework. LSM is a joint development effort by -several security projects, including Immunix, SELinux, SGI and Janus, -and several individuals, including Greg Kroah-Hartman and James -Morris, to develop a Linux kernel patch that implements this -framework. The patch is currently tracking the 2.4 series and is -targeted for integration into the 2.5 development series. This -technical report provides an overview of the framework and the example -capabilities security module provided by the LSM kernel patch. - - - - -LSM Framework - - -The LSM kernel patch provides a general kernel framework to support -security modules. In particular, the LSM framework is primarily -focused on supporting access control modules, although future -development is likely to address other security needs such as -auditing. By itself, the framework does not provide any additional -security; it merely provides the infrastructure to support security -modules. The LSM kernel patch also moves most of the capabilities -logic into an optional security module, with the system defaulting -to the traditional superuser logic. This capabilities module -is discussed further in . - - - -The LSM kernel patch adds security fields to kernel data structures -and inserts calls to hook functions at critical points in the kernel -code to manage the security fields and to perform access control. It -also adds functions for registering and unregistering security -modules, and adds a general security system call -to support new system calls for security-aware applications. - - - -The LSM security fields are simply void* pointers. For -process and program execution security information, security fields -were added to struct task_struct and -struct linux_binprm. For filesystem security -information, a security field was added to -struct super_block. For pipe, file, and socket -security information, security fields were added to -struct inode and -struct file. For packet and network device security -information, security fields were added to -struct sk_buff and -struct net_device. For System V IPC security -information, security fields were added to -struct kern_ipc_perm and -struct msg_msg; additionally, the definitions -for struct msg_msg, struct -msg_queue, and struct -shmid_kernel were moved to header files -(include/linux/msg.h and -include/linux/shm.h as appropriate) to allow -the security modules to use these definitions. - - - -Each LSM hook is a function pointer in a global table, -security_ops. This table is a -security_operations structure as defined by -include/linux/security.h. Detailed documentation -for each hook is included in this header file. At present, this -structure consists of a collection of substructures that group related -hooks based on the kernel object (e.g. task, inode, file, sk_buff, -etc) as well as some top-level hook function pointers for system -operations. This structure is likely to be flattened in the future -for performance. The placement of the hook calls in the kernel code -is described by the "called:" lines in the per-hook documentation in -the header file. The hook calls can also be easily found in the -kernel code by looking for the string "security_ops->". - - - - -Linus mentioned per-process security hooks in his original remarks as a -possible alternative to global security hooks. However, if LSM were -to start from the perspective of per-process hooks, then the base -framework would have to deal with how to handle operations that -involve multiple processes (e.g. kill), since each process might have -its own hook for controlling the operation. This would require a -general mechanism for composing hooks in the base framework. -Additionally, LSM would still need global hooks for operations that -have no process context (e.g. network input operations). -Consequently, LSM provides global security hooks, but a security -module is free to implement per-process hooks (where that makes sense) -by storing a security_ops table in each process' security field and -then invoking these per-process hooks from the global hooks. -The problem of composition is thus deferred to the module. - - - -The global security_ops table is initialized to a set of hook -functions provided by a dummy security module that provides -traditional superuser logic. A register_security -function (in security/security.c) is provided to -allow a security module to set security_ops to refer to its own hook -functions, and an unregister_security function is -provided to revert security_ops to the dummy module hooks. This -mechanism is used to set the primary security module, which is -responsible for making the final decision for each hook. - - - -LSM also provides a simple mechanism for stacking additional security -modules with the primary security module. It defines -register_security and -unregister_security hooks in the -security_operations structure and provides -mod_reg_security and -mod_unreg_security functions that invoke these -hooks after performing some sanity checking. A security module can -call these functions in order to stack with other modules. However, -the actual details of how this stacking is handled are deferred to the -module, which can implement these hooks in any way it wishes -(including always returning an error if it does not wish to support -stacking). In this manner, LSM again defers the problem of -composition to the module. - - - -Although the LSM hooks are organized into substructures based on -kernel object, all of the hooks can be viewed as falling into two -major categories: hooks that are used to manage the security fields -and hooks that are used to perform access control. Examples of the -first category of hooks include the -alloc_security and -free_security hooks defined for each kernel data -structure that has a security field. These hooks are used to allocate -and free security structures for kernel objects. The first category -of hooks also includes hooks that set information in the security -field after allocation, such as the post_lookup -hook in struct inode_security_ops. This hook -is used to set security information for inodes after successful lookup -operations. An example of the second category of hooks is the -permission hook in -struct inode_security_ops. This hook checks -permission when accessing an inode. - - - - -LSM Capabilities Module - - -The LSM kernel patch moves most of the existing POSIX.1e capabilities -logic into an optional security module stored in the file -security/capability.c. This change allows -users who do not want to use capabilities to omit this code entirely -from their kernel, instead using the dummy module for traditional -superuser logic or any other module that they desire. This change -also allows the developers of the capabilities logic to maintain and -enhance their code more freely, without needing to integrate patches -back into the base kernel. - - - -In addition to moving the capabilities logic, the LSM kernel patch -could move the capability-related fields from the kernel data -structures into the new security fields managed by the security -modules. However, at present, the LSM kernel patch leaves the -capability fields in the kernel data structures. In his original -remarks, Linus suggested that this might be preferable so that other -security modules can be easily stacked with the capabilities module -without needing to chain multiple security structures on the security field. -It also avoids imposing extra overhead on the capabilities module -to manage the security fields. However, the LSM framework could -certainly support such a move if it is determined to be desirable, -with only a few additional changes described below. - - - -At present, the capabilities logic for computing process capabilities -on execve and set*uid, -checking capabilities for a particular process, saving and checking -capabilities for netlink messages, and handling the -capget and capset system -calls have been moved into the capabilities module. There are still a -few locations in the base kernel where capability-related fields are -directly examined or modified, but the current version of the LSM -patch does allow a security module to completely replace the -assignment and testing of capabilities. These few locations would -need to be changed if the capability-related fields were moved into -the security field. The following is a list of known locations that -still perform such direct examination or modification of -capability-related fields: - -fs/open.c:sys_access -fs/lockd/host.c:nlm_bind_host -fs/nfsd/auth.c:nfsd_setuser -fs/proc/array.c:task_cap - - - - - -
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl deleted file mode 100644 index b442921bca540a..00000000000000 --- a/Documentation/DocBook/mtdnand.tmpl +++ /dev/null @@ -1,1291 +0,0 @@ - - - - - - MTD NAND Driver Programming Interface - - - - Thomas - Gleixner - -
- tglx@linutronix.de -
- - - - - - 2004 - Thomas Gleixner - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2 as published by the Free Software Foundation. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - The generic NAND driver supports almost all NAND and AG-AND based - chips and connects them to the Memory Technology Devices (MTD) - subsystem of the Linux Kernel. - - - This documentation is provided for developers who want to implement - board drivers or filesystem drivers suitable for NAND devices. - - - - - Known Bugs And Assumptions - - None. - - - - - Documentation hints - - The function and structure docs are autogenerated. Each function and - struct member has a short description which is marked with an [XXX] identifier. - The following chapters explain the meaning of those identifiers. - - - Function identifiers [XXX] - - The functions are marked with [XXX] identifiers in the short - comment. The identifiers explain the usage and scope of the - functions. Following identifiers are used: - - - - [MTD Interface] - These functions provide the interface to the MTD kernel API. - They are not replaceable and provide functionality - which is complete hardware independent. - - - [NAND Interface] - These functions are exported and provide the interface to the NAND kernel API. - - - [GENERIC] - Generic functions are not replaceable and provide functionality - which is complete hardware independent. - - - [DEFAULT] - Default functions provide hardware related functionality which is suitable - for most of the implementations. These functions can be replaced by the - board driver if necessary. Those functions are called via pointers in the - NAND chip description structure. The board driver can set the functions which - should be replaced by board dependent functions before calling nand_scan(). - If the function pointer is NULL on entry to nand_scan() then the pointer - is set to the default function which is suitable for the detected chip type. - - - - - Struct member identifiers [XXX] - - The struct members are marked with [XXX] identifiers in the - comment. The identifiers explain the usage and scope of the - members. Following identifiers are used: - - - - [INTERN] - These members are for NAND driver internal use only and must not be - modified. Most of these values are calculated from the chip geometry - information which is evaluated during nand_scan(). - - - [REPLACEABLE] - Replaceable members hold hardware related functions which can be - provided by the board driver. The board driver can set the functions which - should be replaced by board dependent functions before calling nand_scan(). - If the function pointer is NULL on entry to nand_scan() then the pointer - is set to the default function which is suitable for the detected chip type. - - - [BOARDSPECIFIC] - Board specific members hold hardware related information which must - be provided by the board driver. The board driver must set the function - pointers and datafields before calling nand_scan(). - - - [OPTIONAL] - Optional members can hold information relevant for the board driver. The - generic NAND driver code does not use this information. - - - - - - - Basic board driver - - For most boards it will be sufficient to provide just the - basic functions and fill out some really board dependent - members in the nand chip description structure. - - - Basic defines - - At least you have to provide a nand_chip structure - and a storage for the ioremap'ed chip address. - You can allocate the nand_chip structure using - kmalloc or you can allocate it statically. - The NAND chip structure embeds an mtd structure - which will be registered to the MTD subsystem. - You can extract a pointer to the mtd structure - from a nand_chip pointer using the nand_to_mtd() - helper. - - - Kmalloc based example - - -static struct mtd_info *board_mtd; -static void __iomem *baseaddr; - - - Static example - - -static struct nand_chip board_chip; -static void __iomem *baseaddr; - - - - Partition defines - - If you want to divide your device into partitions, then - define a partitioning scheme suitable to your board. - - -#define NUM_PARTITIONS 2 -static struct mtd_partition partition_info[] = { - { .name = "Flash partition 1", - .offset = 0, - .size = 8 * 1024 * 1024 }, - { .name = "Flash partition 2", - .offset = MTDPART_OFS_NEXT, - .size = MTDPART_SIZ_FULL }, -}; - - - - Hardware control function - - The hardware control function provides access to the - control pins of the NAND chip(s). - The access can be done by GPIO pins or by address lines. - If you use address lines, make sure that the timing - requirements are met. - - - GPIO based example - - -static void board_hwcontrol(struct mtd_info *mtd, int cmd) -{ - switch(cmd){ - case NAND_CTL_SETCLE: /* Set CLE pin high */ break; - case NAND_CTL_CLRCLE: /* Set CLE pin low */ break; - case NAND_CTL_SETALE: /* Set ALE pin high */ break; - case NAND_CTL_CLRALE: /* Set ALE pin low */ break; - case NAND_CTL_SETNCE: /* Set nCE pin low */ break; - case NAND_CTL_CLRNCE: /* Set nCE pin high */ break; - } -} - - - Address lines based example. It's assumed that the - nCE pin is driven by a chip select decoder. - - -static void board_hwcontrol(struct mtd_info *mtd, int cmd) -{ - struct nand_chip *this = mtd_to_nand(mtd); - switch(cmd){ - case NAND_CTL_SETCLE: this->IO_ADDR_W |= CLE_ADRR_BIT; break; - case NAND_CTL_CLRCLE: this->IO_ADDR_W &= ~CLE_ADRR_BIT; break; - case NAND_CTL_SETALE: this->IO_ADDR_W |= ALE_ADRR_BIT; break; - case NAND_CTL_CLRALE: this->IO_ADDR_W &= ~ALE_ADRR_BIT; break; - } -} - - - - Device ready function - - If the hardware interface has the ready busy pin of the NAND chip connected to a - GPIO or other accessible I/O pin, this function is used to read back the state of the - pin. The function has no arguments and should return 0, if the device is busy (R/B pin - is low) and 1, if the device is ready (R/B pin is high). - If the hardware interface does not give access to the ready busy pin, then - the function must not be defined and the function pointer this->dev_ready is set to NULL. - - - - Init function - - The init function allocates memory and sets up all the board - specific parameters and function pointers. When everything - is set up nand_scan() is called. This function tries to - detect and identify then chip. If a chip is found all the - internal data fields are initialized accordingly. - The structure(s) have to be zeroed out first and then filled with the necessary - information about the device. - - -static int __init board_init (void) -{ - struct nand_chip *this; - int err = 0; - - /* Allocate memory for MTD device structure and private data */ - this = kzalloc(sizeof(struct nand_chip), GFP_KERNEL); - if (!this) { - printk ("Unable to allocate NAND MTD device structure.\n"); - err = -ENOMEM; - goto out; - } - - board_mtd = nand_to_mtd(this); - - /* map physical address */ - baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024); - if (!baseaddr) { - printk("Ioremap to access NAND chip failed\n"); - err = -EIO; - goto out_mtd; - } - - /* Set address of NAND IO lines */ - this->IO_ADDR_R = baseaddr; - this->IO_ADDR_W = baseaddr; - /* Reference hardware control function */ - this->hwcontrol = board_hwcontrol; - /* Set command delay time, see datasheet for correct value */ - this->chip_delay = CHIP_DEPENDEND_COMMAND_DELAY; - /* Assign the device ready function, if available */ - this->dev_ready = board_dev_ready; - this->eccmode = NAND_ECC_SOFT; - - /* Scan to find existence of the device */ - if (nand_scan (board_mtd, 1)) { - err = -ENXIO; - goto out_ior; - } - - add_mtd_partitions(board_mtd, partition_info, NUM_PARTITIONS); - goto out; - -out_ior: - iounmap(baseaddr); -out_mtd: - kfree (this); -out: - return err; -} -module_init(board_init); - - - - Exit function - - The exit function is only necessary if the driver is - compiled as a module. It releases all resources which - are held by the chip driver and unregisters the partitions - in the MTD layer. - - -#ifdef MODULE -static void __exit board_cleanup (void) -{ - /* Release resources, unregister device */ - nand_release (board_mtd); - - /* unmap physical address */ - iounmap(baseaddr); - - /* Free the MTD device structure */ - kfree (mtd_to_nand(board_mtd)); -} -module_exit(board_cleanup); -#endif - - - - - - Advanced board driver functions - - This chapter describes the advanced functionality of the NAND - driver. For a list of functions which can be overridden by the board - driver see the documentation of the nand_chip structure. - - - Multiple chip control - - The nand driver can control chip arrays. Therefore the - board driver must provide an own select_chip function. This - function must (de)select the requested chip. - The function pointer in the nand_chip structure must - be set before calling nand_scan(). The maxchip parameter - of nand_scan() defines the maximum number of chips to - scan for. Make sure that the select_chip function can - handle the requested number of chips. - - - The nand driver concatenates the chips to one virtual - chip and provides this virtual chip to the MTD layer. - - - Note: The driver can only handle linear chip arrays - of equally sized chips. There is no support for - parallel arrays which extend the buswidth. - - - GPIO based example - - -static void board_select_chip (struct mtd_info *mtd, int chip) -{ - /* Deselect all chips, set all nCE pins high */ - GPIO(BOARD_NAND_NCE) |= 0xff; - if (chip >= 0) - GPIO(BOARD_NAND_NCE) &= ~ (1 << chip); -} - - - Address lines based example. - Its assumed that the nCE pins are connected to an - address decoder. - - -static void board_select_chip (struct mtd_info *mtd, int chip) -{ - struct nand_chip *this = mtd_to_nand(mtd); - - /* Deselect all chips */ - this->IO_ADDR_R &= ~BOARD_NAND_ADDR_MASK; - this->IO_ADDR_W &= ~BOARD_NAND_ADDR_MASK; - switch (chip) { - case 0: - this->IO_ADDR_R |= BOARD_NAND_ADDR_CHIP0; - this->IO_ADDR_W |= BOARD_NAND_ADDR_CHIP0; - break; - .... - case n: - this->IO_ADDR_R |= BOARD_NAND_ADDR_CHIPn; - this->IO_ADDR_W |= BOARD_NAND_ADDR_CHIPn; - break; - } -} - - - - Hardware ECC support - - Functions and constants - - The nand driver supports three different types of - hardware ECC. - - NAND_ECC_HW3_256 - Hardware ECC generator providing 3 bytes ECC per - 256 byte. - - NAND_ECC_HW3_512 - Hardware ECC generator providing 3 bytes ECC per - 512 byte. - - NAND_ECC_HW6_512 - Hardware ECC generator providing 6 bytes ECC per - 512 byte. - - NAND_ECC_HW8_512 - Hardware ECC generator providing 6 bytes ECC per - 512 byte. - - - If your hardware generator has a different functionality - add it at the appropriate place in nand_base.c - - - The board driver must provide following functions: - - enable_hwecc - This function is called before reading / writing to - the chip. Reset or initialize the hardware generator - in this function. The function is called with an - argument which let you distinguish between read - and write operations. - - calculate_ecc - This function is called after read / write from / to - the chip. Transfer the ECC from the hardware to - the buffer. If the option NAND_HWECC_SYNDROME is set - then the function is only called on write. See below. - - correct_data - In case of an ECC error this function is called for - error detection and correction. Return 1 respectively 2 - in case the error can be corrected. If the error is - not correctable return -1. If your hardware generator - matches the default algorithm of the nand_ecc software - generator then use the correction function provided - by nand_ecc instead of implementing duplicated code. - - - - - - Hardware ECC with syndrome calculation - - Many hardware ECC implementations provide Reed-Solomon - codes and calculate an error syndrome on read. The syndrome - must be converted to a standard Reed-Solomon syndrome - before calling the error correction code in the generic - Reed-Solomon library. - - - The ECC bytes must be placed immediately after the data - bytes in order to make the syndrome generator work. This - is contrary to the usual layout used by software ECC. The - separation of data and out of band area is not longer - possible. The nand driver code handles this layout and - the remaining free bytes in the oob area are managed by - the autoplacement code. Provide a matching oob-layout - in this case. See rts_from4.c and diskonchip.c for - implementation reference. In those cases we must also - use bad block tables on FLASH, because the ECC layout is - interfering with the bad block marker positions. - See bad block table support for details. - - - - - Bad block table support - - Most NAND chips mark the bad blocks at a defined - position in the spare area. Those blocks must - not be erased under any circumstances as the bad - block information would be lost. - It is possible to check the bad block mark each - time when the blocks are accessed by reading the - spare area of the first page in the block. This - is time consuming so a bad block table is used. - - - The nand driver supports various types of bad block - tables. - - Per device - The bad block table contains all bad block information - of the device which can consist of multiple chips. - - Per chip - A bad block table is used per chip and contains the - bad block information for this particular chip. - - Fixed offset - The bad block table is located at a fixed offset - in the chip (device). This applies to various - DiskOnChip devices. - - Automatic placed - The bad block table is automatically placed and - detected either at the end or at the beginning - of a chip (device) - - Mirrored tables - The bad block table is mirrored on the chip (device) to - allow updates of the bad block table without data loss. - - - - - nand_scan() calls the function nand_default_bbt(). - nand_default_bbt() selects appropriate default - bad block table descriptors depending on the chip information - which was retrieved by nand_scan(). - - - The standard policy is scanning the device for bad - blocks and build a ram based bad block table which - allows faster access than always checking the - bad block information on the flash chip itself. - - - Flash based tables - - It may be desired or necessary to keep a bad block table in FLASH. - For AG-AND chips this is mandatory, as they have no factory marked - bad blocks. They have factory marked good blocks. The marker pattern - is erased when the block is erased to be reused. So in case of - powerloss before writing the pattern back to the chip this block - would be lost and added to the bad blocks. Therefore we scan the - chip(s) when we detect them the first time for good blocks and - store this information in a bad block table before erasing any - of the blocks. - - - The blocks in which the tables are stored are protected against - accidental access by marking them bad in the memory bad block - table. The bad block table management functions are allowed - to circumvent this protection. - - - The simplest way to activate the FLASH based bad block table support - is to set the option NAND_BBT_USE_FLASH in the bbt_option field of - the nand chip structure before calling nand_scan(). For AG-AND - chips is this done by default. - This activates the default FLASH based bad block table functionality - of the NAND driver. The default bad block table options are - - Store bad block table per chip - Use 2 bits per block - Automatic placement at the end of the chip - Use mirrored tables with version numbers - Reserve 4 blocks at the end of the chip - - - - - User defined tables - - User defined tables are created by filling out a - nand_bbt_descr structure and storing the pointer in the - nand_chip structure member bbt_td before calling nand_scan(). - If a mirror table is necessary a second structure must be - created and a pointer to this structure must be stored - in bbt_md inside the nand_chip structure. If the bbt_md - member is set to NULL then only the main table is used - and no scan for the mirrored table is performed. - - - The most important field in the nand_bbt_descr structure - is the options field. The options define most of the - table properties. Use the predefined constants from - nand.h to define the options. - - Number of bits per block - The supported number of bits is 1, 2, 4, 8. - Table per chip - Setting the constant NAND_BBT_PERCHIP selects that - a bad block table is managed for each chip in a chip array. - If this option is not set then a per device bad block table - is used. - Table location is absolute - Use the option constant NAND_BBT_ABSPAGE and - define the absolute page number where the bad block - table starts in the field pages. If you have selected bad block - tables per chip and you have a multi chip array then the start page - must be given for each chip in the chip array. Note: there is no scan - for a table ident pattern performed, so the fields - pattern, veroffs, offs, len can be left uninitialized - Table location is automatically detected - The table can either be located in the first or the last good - blocks of the chip (device). Set NAND_BBT_LASTBLOCK to place - the bad block table at the end of the chip (device). The - bad block tables are marked and identified by a pattern which - is stored in the spare area of the first page in the block which - holds the bad block table. Store a pointer to the pattern - in the pattern field. Further the length of the pattern has to be - stored in len and the offset in the spare area must be given - in the offs member of the nand_bbt_descr structure. For mirrored - bad block tables different patterns are mandatory. - Table creation - Set the option NAND_BBT_CREATE to enable the table creation - if no table can be found during the scan. Usually this is done only - once if a new chip is found. - Table write support - Set the option NAND_BBT_WRITE to enable the table write support. - This allows the update of the bad block table(s) in case a block has - to be marked bad due to wear. The MTD interface function block_markbad - is calling the update function of the bad block table. If the write - support is enabled then the table is updated on FLASH. - - Note: Write support should only be enabled for mirrored tables with - version control. - - Table version control - Set the option NAND_BBT_VERSION to enable the table version control. - It's highly recommended to enable this for mirrored tables with write - support. It makes sure that the risk of losing the bad block - table information is reduced to the loss of the information about the - one worn out block which should be marked bad. The version is stored in - 4 consecutive bytes in the spare area of the device. The position of - the version number is defined by the member veroffs in the bad block table - descriptor. - Save block contents on write - - In case that the block which holds the bad block table does contain - other useful information, set the option NAND_BBT_SAVECONTENT. When - the bad block table is written then the whole block is read the bad - block table is updated and the block is erased and everything is - written back. If this option is not set only the bad block table - is written and everything else in the block is ignored and erased. - - Number of reserved blocks - - For automatic placement some blocks must be reserved for - bad block table storage. The number of reserved blocks is defined - in the maxblocks member of the bad block table description structure. - Reserving 4 blocks for mirrored tables should be a reasonable number. - This also limits the number of blocks which are scanned for the bad - block table ident pattern. - - - - - - - Spare area (auto)placement - - The nand driver implements different possibilities for - placement of filesystem data in the spare area, - - Placement defined by fs driver - Automatic placement - - The default placement function is automatic placement. The - nand driver has built in default placement schemes for the - various chiptypes. If due to hardware ECC functionality the - default placement does not fit then the board driver can - provide a own placement scheme. - - - File system drivers can provide a own placement scheme which - is used instead of the default placement scheme. - - - Placement schemes are defined by a nand_oobinfo structure - -struct nand_oobinfo { - int useecc; - int eccbytes; - int eccpos[24]; - int oobfree[8][2]; -}; - - - useecc - The useecc member controls the ecc and placement function. The header - file include/mtd/mtd-abi.h contains constants to select ecc and - placement. MTD_NANDECC_OFF switches off the ecc complete. This is - not recommended and available for testing and diagnosis only. - MTD_NANDECC_PLACE selects caller defined placement, MTD_NANDECC_AUTOPLACE - selects automatic placement. - - eccbytes - The eccbytes member defines the number of ecc bytes per page. - - eccpos - The eccpos array holds the byte offsets in the spare area where - the ecc codes are placed. - - oobfree - The oobfree array defines the areas in the spare area which can be - used for automatic placement. The information is given in the format - {offset, size}. offset defines the start of the usable area, size the - length in bytes. More than one area can be defined. The list is terminated - by an {0, 0} entry. - - - - - Placement defined by fs driver - - The calling function provides a pointer to a nand_oobinfo - structure which defines the ecc placement. For writes the - caller must provide a spare area buffer along with the - data buffer. The spare area buffer size is (number of pages) * - (size of spare area). For reads the buffer size is - (number of pages) * ((size of spare area) + (number of ecc - steps per page) * sizeof (int)). The driver stores the - result of the ecc check for each tuple in the spare buffer. - The storage sequence is - - - <spare data page 0><ecc result 0>...<ecc result n> - - - ... - - - <spare data page n><ecc result 0>...<ecc result n> - - - This is a legacy mode used by YAFFS1. - - - If the spare area buffer is NULL then only the ECC placement is - done according to the given scheme in the nand_oobinfo structure. - - - - Automatic placement - - Automatic placement uses the built in defaults to place the - ecc bytes in the spare area. If filesystem data have to be stored / - read into the spare area then the calling function must provide a - buffer. The buffer size per page is determined by the oobfree array in - the nand_oobinfo structure. - - - If the spare area buffer is NULL then only the ECC placement is - done according to the default builtin scheme. - - - - - Spare area autoplacement default schemes - - 256 byte pagesize - - -Offset -Content -Comment - - -0x00 -ECC byte 0 -Error correction code byte 0 - - -0x01 -ECC byte 1 -Error correction code byte 1 - - -0x02 -ECC byte 2 -Error correction code byte 2 - - -0x03 -Autoplace 0 - - - -0x04 -Autoplace 1 - - - -0x05 -Bad block marker -If any bit in this byte is zero, then this block is bad. -This applies only to the first page in a block. In the remaining -pages this byte is reserved - - -0x06 -Autoplace 2 - - - -0x07 -Autoplace 3 - - - - - - 512 byte pagesize - - -Offset -Content -Comment - - -0x00 -ECC byte 0 -Error correction code byte 0 of the lower 256 Byte data in -this page - - -0x01 -ECC byte 1 -Error correction code byte 1 of the lower 256 Bytes of data -in this page - - -0x02 -ECC byte 2 -Error correction code byte 2 of the lower 256 Bytes of data -in this page - - -0x03 -ECC byte 3 -Error correction code byte 0 of the upper 256 Bytes of data -in this page - - -0x04 -reserved -reserved - - -0x05 -Bad block marker -If any bit in this byte is zero, then this block is bad. -This applies only to the first page in a block. In the remaining -pages this byte is reserved - - -0x06 -ECC byte 4 -Error correction code byte 1 of the upper 256 Bytes of data -in this page - - -0x07 -ECC byte 5 -Error correction code byte 2 of the upper 256 Bytes of data -in this page - - -0x08 - 0x0F -Autoplace 0 - 7 - - - - - - 2048 byte pagesize - - -Offset -Content -Comment - - -0x00 -Bad block marker -If any bit in this byte is zero, then this block is bad. -This applies only to the first page in a block. In the remaining -pages this byte is reserved - - -0x01 -Reserved -Reserved - - -0x02-0x27 -Autoplace 0 - 37 - - - -0x28 -ECC byte 0 -Error correction code byte 0 of the first 256 Byte data in -this page - - -0x29 -ECC byte 1 -Error correction code byte 1 of the first 256 Bytes of data -in this page - - -0x2A -ECC byte 2 -Error correction code byte 2 of the first 256 Bytes data in -this page - - -0x2B -ECC byte 3 -Error correction code byte 0 of the second 256 Bytes of data -in this page - - -0x2C -ECC byte 4 -Error correction code byte 1 of the second 256 Bytes of data -in this page - - -0x2D -ECC byte 5 -Error correction code byte 2 of the second 256 Bytes of data -in this page - - -0x2E -ECC byte 6 -Error correction code byte 0 of the third 256 Bytes of data -in this page - - -0x2F -ECC byte 7 -Error correction code byte 1 of the third 256 Bytes of data -in this page - - -0x30 -ECC byte 8 -Error correction code byte 2 of the third 256 Bytes of data -in this page - - -0x31 -ECC byte 9 -Error correction code byte 0 of the fourth 256 Bytes of data -in this page - - -0x32 -ECC byte 10 -Error correction code byte 1 of the fourth 256 Bytes of data -in this page - - -0x33 -ECC byte 11 -Error correction code byte 2 of the fourth 256 Bytes of data -in this page - - -0x34 -ECC byte 12 -Error correction code byte 0 of the fifth 256 Bytes of data -in this page - - -0x35 -ECC byte 13 -Error correction code byte 1 of the fifth 256 Bytes of data -in this page - - -0x36 -ECC byte 14 -Error correction code byte 2 of the fifth 256 Bytes of data -in this page - - -0x37 -ECC byte 15 -Error correction code byte 0 of the sixt 256 Bytes of data -in this page - - -0x38 -ECC byte 16 -Error correction code byte 1 of the sixt 256 Bytes of data -in this page - - -0x39 -ECC byte 17 -Error correction code byte 2 of the sixt 256 Bytes of data -in this page - - -0x3A -ECC byte 18 -Error correction code byte 0 of the seventh 256 Bytes of -data in this page - - -0x3B -ECC byte 19 -Error correction code byte 1 of the seventh 256 Bytes of -data in this page - - -0x3C -ECC byte 20 -Error correction code byte 2 of the seventh 256 Bytes of -data in this page - - -0x3D -ECC byte 21 -Error correction code byte 0 of the eighth 256 Bytes of data -in this page - - -0x3E -ECC byte 22 -Error correction code byte 1 of the eighth 256 Bytes of data -in this page - - -0x3F -ECC byte 23 -Error correction code byte 2 of the eighth 256 Bytes of data -in this page - - - - - - - - Filesystem support - - The NAND driver provides all necessary functions for a - filesystem via the MTD interface. - - - Filesystems must be aware of the NAND peculiarities and - restrictions. One major restrictions of NAND Flash is, that you cannot - write as often as you want to a page. The consecutive writes to a page, - before erasing it again, are restricted to 1-3 writes, depending on the - manufacturers specifications. This applies similar to the spare area. - - - Therefore NAND aware filesystems must either write in page size chunks - or hold a writebuffer to collect smaller writes until they sum up to - pagesize. Available NAND aware filesystems: JFFS2, YAFFS. - - - The spare area usage to store filesystem data is controlled by - the spare area placement functionality which is described in one - of the earlier chapters. - - - - Tools - - The MTD project provides a couple of helpful tools to handle NAND Flash. - - flasherase, flasheraseall: Erase and format FLASH partitions - nandwrite: write filesystem images to NAND FLASH - nanddump: dump the contents of a NAND FLASH partitions - - - - These tools are aware of the NAND restrictions. Please use those tools - instead of complaining about errors which are caused by non NAND aware - access methods. - - - - - Constants - - This chapter describes the constants which might be relevant for a driver developer. - - - Chip option constants - - Constants for chip id table - - These constants are defined in nand.h. They are ored together to describe - the chip functionality. - -/* Buswitdh is 16 bit */ -#define NAND_BUSWIDTH_16 0x00000002 -/* Device supports partial programming without padding */ -#define NAND_NO_PADDING 0x00000004 -/* Chip has cache program function */ -#define NAND_CACHEPRG 0x00000008 -/* Chip has copy back function */ -#define NAND_COPYBACK 0x00000010 -/* AND Chip which has 4 banks and a confusing page / block - * assignment. See Renesas datasheet for further information */ -#define NAND_IS_AND 0x00000020 -/* Chip has a array of 4 pages which can be read without - * additional ready /busy waits */ -#define NAND_4PAGE_ARRAY 0x00000040 - - - - - Constants for runtime options - - These constants are defined in nand.h. They are ored together to describe - the functionality. - -/* The hw ecc generator provides a syndrome instead a ecc value on read - * This can only work if we have the ecc bytes directly behind the - * data bytes. Applies for DOC and AG-AND Renesas HW Reed Solomon generators */ -#define NAND_HWECC_SYNDROME 0x00020000 - - - - - - - ECC selection constants - - Use these constants to select the ECC algorithm. - -/* No ECC. Usage is not recommended ! */ -#define NAND_ECC_NONE 0 -/* Software ECC 3 byte ECC per 256 Byte data */ -#define NAND_ECC_SOFT 1 -/* Hardware ECC 3 byte ECC per 256 Byte data */ -#define NAND_ECC_HW3_256 2 -/* Hardware ECC 3 byte ECC per 512 Byte data */ -#define NAND_ECC_HW3_512 3 -/* Hardware ECC 6 byte ECC per 512 Byte data */ -#define NAND_ECC_HW6_512 4 -/* Hardware ECC 6 byte ECC per 512 Byte data */ -#define NAND_ECC_HW8_512 6 - - - - - - Hardware control related constants - - These constants describe the requested hardware access function when - the boardspecific hardware control function is called - -/* Select the chip by setting nCE to low */ -#define NAND_CTL_SETNCE 1 -/* Deselect the chip by setting nCE to high */ -#define NAND_CTL_CLRNCE 2 -/* Select the command latch by setting CLE to high */ -#define NAND_CTL_SETCLE 3 -/* Deselect the command latch by setting CLE to low */ -#define NAND_CTL_CLRCLE 4 -/* Select the address latch by setting ALE to high */ -#define NAND_CTL_SETALE 5 -/* Deselect the address latch by setting ALE to low */ -#define NAND_CTL_CLRALE 6 -/* Set write protection by setting WP to high. Not used! */ -#define NAND_CTL_SETWP 7 -/* Clear write protection by setting WP to low. Not used! */ -#define NAND_CTL_CLRWP 8 - - - - - - Bad block table related constants - - These constants describe the options used for bad block - table descriptors. - -/* Options for the bad block table descriptors */ - -/* The number of bits used per block in the bbt on the device */ -#define NAND_BBT_NRBITS_MSK 0x0000000F -#define NAND_BBT_1BIT 0x00000001 -#define NAND_BBT_2BIT 0x00000002 -#define NAND_BBT_4BIT 0x00000004 -#define NAND_BBT_8BIT 0x00000008 -/* The bad block table is in the last good block of the device */ -#define NAND_BBT_LASTBLOCK 0x00000010 -/* The bbt is at the given page, else we must scan for the bbt */ -#define NAND_BBT_ABSPAGE 0x00000020 -/* bbt is stored per chip on multichip devices */ -#define NAND_BBT_PERCHIP 0x00000080 -/* bbt has a version counter at offset veroffs */ -#define NAND_BBT_VERSION 0x00000100 -/* Create a bbt if none axists */ -#define NAND_BBT_CREATE 0x00000200 -/* Write bbt if necessary */ -#define NAND_BBT_WRITE 0x00001000 -/* Read and write back block contents when writing bbt */ -#define NAND_BBT_SAVECONTENT 0x00002000 - - - - - - - - Structures - - This chapter contains the autogenerated documentation of the structures which are - used in the NAND driver and might be relevant for a driver developer. Each - struct member has a short description which is marked with an [XXX] identifier. - See the chapter "Documentation hints" for an explanation. - -!Iinclude/linux/mtd/nand.h - - - - Public Functions Provided - - This chapter contains the autogenerated documentation of the NAND kernel API functions - which are exported. Each function has a short description which is marked with an [XXX] identifier. - See the chapter "Documentation hints" for an explanation. - -!Edrivers/mtd/nand/nand_base.c -!Edrivers/mtd/nand/nand_bbt.c -!Edrivers/mtd/nand/nand_ecc.c - - - - Internal Functions Provided - - This chapter contains the autogenerated documentation of the NAND driver internal functions. - Each function has a short description which is marked with an [XXX] identifier. - See the chapter "Documentation hints" for an explanation. - The functions marked with [DEFAULT] might be relevant for a board driver developer. - -!Idrivers/mtd/nand/nand_base.c -!Idrivers/mtd/nand/nand_bbt.c - - - - - Credits - - The following people have contributed to the NAND driver: - - Steven J. Hillsjhill@realitydiluted.com - David Woodhousedwmw2@infradead.org - Thomas Gleixnertglx@linutronix.de - - A lot of users have provided bugfixes, improvements and helping hands for testing. - Thanks a lot. - - - The following people have contributed to this document: - - Thomas Gleixnertglx@linutronix.de - - - - diff --git a/Documentation/DocBook/networking.tmpl b/Documentation/DocBook/networking.tmpl deleted file mode 100644 index 29df25016c7c12..00000000000000 --- a/Documentation/DocBook/networking.tmpl +++ /dev/null @@ -1,111 +0,0 @@ - - - - - - Linux Networking and Network Devices APIs - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Linux Networking - Networking Base Types -!Iinclude/linux/net.h - - Socket Buffer Functions -!Iinclude/linux/skbuff.h -!Iinclude/net/sock.h -!Enet/socket.c -!Enet/core/skbuff.c -!Enet/core/sock.c -!Enet/core/datagram.c -!Enet/core/stream.c - - Socket Filter -!Enet/core/filter.c - - Generic Network Statistics -!Iinclude/uapi/linux/gen_stats.h -!Enet/core/gen_stats.c -!Enet/core/gen_estimator.c - - SUN RPC subsystem - -!Enet/sunrpc/xdr.c -!Enet/sunrpc/svc_xprt.c -!Enet/sunrpc/xprt.c -!Enet/sunrpc/sched.c -!Enet/sunrpc/socklib.c -!Enet/sunrpc/stats.c -!Enet/sunrpc/rpc_pipe.c -!Enet/sunrpc/rpcb_clnt.c -!Enet/sunrpc/clnt.c - - WiMAX -!Enet/wimax/op-msg.c -!Enet/wimax/op-reset.c -!Enet/wimax/op-rfkill.c -!Enet/wimax/stack.c -!Iinclude/net/wimax.h -!Iinclude/uapi/linux/wimax.h - - - - - Network device support - Driver Support -!Enet/core/dev.c -!Enet/ethernet/eth.c -!Enet/sched/sch_generic.c -!Iinclude/linux/etherdevice.h -!Iinclude/linux/netdevice.h - - PHY Support -!Edrivers/net/phy/phy.c -!Idrivers/net/phy/phy.c -!Edrivers/net/phy/phy_device.c -!Idrivers/net/phy/phy_device.c -!Edrivers/net/phy/mdio_bus.c -!Idrivers/net/phy/mdio_bus.c - - - - - diff --git a/Documentation/DocBook/rapidio.tmpl b/Documentation/DocBook/rapidio.tmpl deleted file mode 100644 index ac3cca3399a1e4..00000000000000 --- a/Documentation/DocBook/rapidio.tmpl +++ /dev/null @@ -1,155 +0,0 @@ - - - ]> - - - - RapidIO Subsystem Guide - - - - Matt - Porter - -
- mporter@kernel.crashing.org - mporter@mvista.com -
- - - - - - 2005 - MontaVista Software, Inc. - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2 as published by the Free Software Foundation. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - RapidIO is a high speed switched fabric interconnect with - features aimed at the embedded market. RapidIO provides - support for memory-mapped I/O as well as message-based - transactions over the switched fabric network. RapidIO has - a standardized discovery mechanism not unlike the PCI bus - standard that allows simple detection of devices in a - network. - - - This documentation is provided for developers intending - to support RapidIO on new architectures, write new drivers, - or to understand the subsystem internals. - - - - - Known Bugs and Limitations - - - Bugs - None. ;) - - - Limitations - - - Access/management of RapidIO memory regions is not supported - Multiple host enumeration is not supported - - - - - - - RapidIO driver interface - - Drivers are provided a set of calls in order - to interface with the subsystem to gather info - on devices, request/map memory region resources, - and manage mailboxes/doorbells. - - - Functions -!Iinclude/linux/rio_drv.h -!Edrivers/rapidio/rio-driver.c -!Edrivers/rapidio/rio.c - - - - - Internals - - - This chapter contains the autogenerated documentation of the RapidIO - subsystem. - - - Structures -!Iinclude/linux/rio.h - - Enumeration and Discovery -!Idrivers/rapidio/rio-scan.c - - Driver functionality -!Idrivers/rapidio/rio.c -!Idrivers/rapidio/rio-access.c - - Device model support -!Idrivers/rapidio/rio-driver.c - - PPC32 support -!Iarch/powerpc/sysdev/fsl_rio.c - - - - - Credits - - The following people have contributed to the RapidIO - subsystem directly or indirectly: - - Matt Portermporter@kernel.crashing.org - Randy Vinsonrvinson@mvista.com - Dan Malekdan@embeddedalley.com - - - - The following people have contributed to this document: - - Matt Portermporter@kernel.crashing.org - - - - diff --git a/Documentation/DocBook/s390-drivers.tmpl b/Documentation/DocBook/s390-drivers.tmpl deleted file mode 100644 index 95bfc12e5439d5..00000000000000 --- a/Documentation/DocBook/s390-drivers.tmpl +++ /dev/null @@ -1,161 +0,0 @@ - - - - - - Writing s390 channel device drivers - - - - Cornelia - Huck - -
- cornelia.huck@de.ibm.com -
- - - - - - 2007 - IBM Corp. - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - This document describes the interfaces available for device drivers that - drive s390 based channel attached I/O devices. This includes interfaces for - interaction with the hardware and interfaces for interacting with the - common driver core. Those interfaces are provided by the s390 common I/O - layer. - - - The document assumes a familarity with the technical terms associated - with the s390 channel I/O architecture. For a description of this - architecture, please refer to the "z/Architecture: Principles of - Operation", IBM publication no. SA22-7832. - - - While most I/O devices on a s390 system are typically driven through the - channel I/O mechanism described here, there are various other methods - (like the diag interface). These are out of the scope of this document. - - - Some additional information can also be found in the kernel source - under Documentation/s390/driver-model.txt. - - - - The ccw bus - - The ccw bus typically contains the majority of devices available to - a s390 system. Named after the channel command word (ccw), the basic - command structure used to address its devices, the ccw bus contains - so-called channel attached devices. They are addressed via I/O - subchannels, visible on the css bus. A device driver for - channel-attached devices, however, will never interact with the - subchannel directly, but only via the I/O device on the ccw bus, - the ccw device. - - - I/O functions for channel-attached devices - - Some hardware structures have been translated into C structures for use - by the common I/O layer and device drivers. For more information on - the hardware structures represented here, please consult the Principles - of Operation. - -!Iarch/s390/include/asm/cio.h - - - ccw devices - - Devices that want to initiate channel I/O need to attach to the ccw bus. - Interaction with the driver core is done via the common I/O layer, which - provides the abstractions of ccw devices and ccw device drivers. - - - The functions that initiate or terminate channel I/O all act upon a - ccw device structure. Device drivers must not bypass those functions - or strange side effects may happen. - -!Iarch/s390/include/asm/ccwdev.h -!Edrivers/s390/cio/device.c -!Edrivers/s390/cio/device_ops.c - - - The channel-measurement facility - - The channel-measurement facility provides a means to collect - measurement data which is made available by the channel subsystem - for each channel attached device. - -!Iarch/s390/include/asm/cmb.h -!Edrivers/s390/cio/cmf.c - - - - - The ccwgroup bus - - The ccwgroup bus only contains artificial devices, created by the user. - Many networking devices (e.g. qeth) are in fact composed of several - ccw devices (like read, write and data channel for qeth). The - ccwgroup bus provides a mechanism to create a meta-device which - contains those ccw devices as slave devices and can be associated - with the netdevice. - - - ccw group devices -!Iarch/s390/include/asm/ccwgroup.h -!Edrivers/s390/cio/ccwgroup.c - - - - - Generic interfaces - - Some interfaces are available to other drivers that do not necessarily - have anything to do with the busses described above, but still are - indirectly using basic infrastructure in the common I/O layer. - One example is the support for adapter interrupts. - -!Edrivers/s390/cio/airq.c - - - diff --git a/Documentation/DocBook/scsi.tmpl b/Documentation/DocBook/scsi.tmpl deleted file mode 100644 index 4b9b9b286cea6c..00000000000000 --- a/Documentation/DocBook/scsi.tmpl +++ /dev/null @@ -1,409 +0,0 @@ - - - - - - SCSI Interfaces Guide - - - - James - Bottomley - -
- James.Bottomley@hansenpartnership.com -
- - - - - Rob - Landley - -
- rob@landley.net -
- - - - - - - 2007 - Linux Foundation - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - Protocol vs bus - - Once upon a time, the Small Computer Systems Interface defined both - a parallel I/O bus and a data protocol to connect a wide variety of - peripherals (disk drives, tape drives, modems, printers, scanners, - optical drives, test equipment, and medical devices) to a host - computer. - - - Although the old parallel (fast/wide/ultra) SCSI bus has largely - fallen out of use, the SCSI command set is more widely used than ever - to communicate with devices over a number of different busses. - - - The SCSI protocol - is a big-endian peer-to-peer packet based protocol. SCSI commands - are 6, 10, 12, or 16 bytes long, often followed by an associated data - payload. - - - SCSI commands can be transported over just about any kind of bus, and - are the default protocol for storage devices attached to USB, SATA, - SAS, Fibre Channel, FireWire, and ATAPI devices. SCSI packets are - also commonly exchanged over Infiniband, - I20, TCP/IP - (iSCSI), even - Parallel - ports. - - - - Design of the Linux SCSI subsystem - - The SCSI subsystem uses a three layer design, with upper, mid, and low - layers. Every operation involving the SCSI subsystem (such as reading - a sector from a disk) uses one driver at each of the 3 levels: one - upper layer driver, one lower layer driver, and the SCSI midlayer. - - - The SCSI upper layer provides the interface between userspace and the - kernel, in the form of block and char device nodes for I/O and - ioctl(). The SCSI lower layer contains drivers for specific hardware - devices. - - - In between is the SCSI mid-layer, analogous to a network routing - layer such as the IPv4 stack. The SCSI mid-layer routes a packet - based data protocol between the upper layer's /dev nodes and the - corresponding devices in the lower layer. It manages command queues, - provides error handling and power management functions, and responds - to ioctl() requests. - - - - - - SCSI upper layer - - The upper layer supports the user-kernel interface by providing - device nodes. - - - sd (SCSI Disk) - sd (sd_mod.o) - - - - sr (SCSI CD-ROM) - sr (sr_mod.o) - - - st (SCSI Tape) - st (st.o) - - - sg (SCSI Generic) - sg (sg.o) - - - ch (SCSI Media Changer) - ch (ch.c) - - - - - SCSI mid layer - - - SCSI midlayer implementation - - include/scsi/scsi_device.h - - -!Iinclude/scsi/scsi_device.h - - - - drivers/scsi/scsi.c - Main file for the SCSI midlayer. -!Edrivers/scsi/scsi.c - - - drivers/scsi/scsicam.c - - SCSI - Common Access Method support functions, for use with - HDIO_GETGEO, etc. - -!Edrivers/scsi/scsicam.c - - - drivers/scsi/scsi_error.c - Common SCSI error/timeout handling routines. -!Edrivers/scsi/scsi_error.c - - - drivers/scsi/scsi_devinfo.c - - Manage scsi_dev_info_list, which tracks blacklisted and whitelisted - devices. - -!Idrivers/scsi/scsi_devinfo.c - - - drivers/scsi/scsi_ioctl.c - - Handle ioctl() calls for SCSI devices. - -!Edrivers/scsi/scsi_ioctl.c - - - drivers/scsi/scsi_lib.c - - SCSI queuing library. - -!Edrivers/scsi/scsi_lib.c - - - drivers/scsi/scsi_lib_dma.c - - SCSI library functions depending on DMA - (map and unmap scatter-gather lists). - -!Edrivers/scsi/scsi_lib_dma.c - - - drivers/scsi/scsi_module.c - - The file drivers/scsi/scsi_module.c contains legacy support for - old-style host templates. It should never be used by any new driver. - - - - drivers/scsi/scsi_proc.c - - The functions in this file provide an interface between - the PROC file system and the SCSI device drivers - It is mainly used for debugging, statistics and to pass - information directly to the lowlevel driver. - - I.E. plumbing to manage /proc/scsi/* - -!Idrivers/scsi/scsi_proc.c - - - drivers/scsi/scsi_netlink.c - - Infrastructure to provide async events from transports to userspace - via netlink, using a single NETLINK_SCSITRANSPORT protocol for all - transports. - - See the - original patch submission for more details. - -!Idrivers/scsi/scsi_netlink.c - - - drivers/scsi/scsi_scan.c - - Scan a host to determine which (if any) devices are attached. - - The general scanning/probing algorithm is as follows, exceptions are - made to it depending on device specific flags, compilation options, - and global variable (boot or module load time) settings. - - A specific LUN is scanned via an INQUIRY command; if the LUN has a - device attached, a scsi_device is allocated and setup for it. - - For every id of every channel on the given host, start by scanning - LUN 0. Skip hosts that don't respond at all to a scan of LUN 0. - Otherwise, if LUN 0 has a device attached, allocate and setup a - scsi_device for it. If target is SCSI-3 or up, issue a REPORT LUN, - and scan all of the LUNs returned by the REPORT LUN; else, - sequentially scan LUNs up until some maximum is reached, or a LUN is - seen that cannot have a device attached to it. - -!Idrivers/scsi/scsi_scan.c - - - drivers/scsi/scsi_sysctl.c - - Set up the sysctl entry: "/dev/scsi/logging_level" - (DEV_SCSI_LOGGING_LEVEL) which sets/returns scsi_logging_level. - - - - drivers/scsi/scsi_sysfs.c - - SCSI sysfs interface routines. - -!Edrivers/scsi/scsi_sysfs.c - - - drivers/scsi/hosts.c - - mid to lowlevel SCSI driver interface - -!Edrivers/scsi/hosts.c - - - drivers/scsi/constants.c - - mid to lowlevel SCSI driver interface - -!Edrivers/scsi/constants.c - - - - - Transport classes - - Transport classes are service libraries for drivers in the SCSI - lower layer, which expose transport attributes in sysfs. - - - Fibre Channel transport - - The file drivers/scsi/scsi_transport_fc.c defines transport attributes - for Fibre Channel. - -!Edrivers/scsi/scsi_transport_fc.c - - - iSCSI transport class - - The file drivers/scsi/scsi_transport_iscsi.c defines transport - attributes for the iSCSI class, which sends SCSI packets over TCP/IP - connections. - -!Edrivers/scsi/scsi_transport_iscsi.c - - - Serial Attached SCSI (SAS) transport class - - The file drivers/scsi/scsi_transport_sas.c defines transport - attributes for Serial Attached SCSI, a variant of SATA aimed at - large high-end systems. - - - The SAS transport class contains common code to deal with SAS HBAs, - an aproximated representation of SAS topologies in the driver model, - and various sysfs attributes to expose these topologies and management - interfaces to userspace. - - - In addition to the basic SCSI core objects this transport class - introduces two additional intermediate objects: The SAS PHY - as represented by struct sas_phy defines an "outgoing" PHY on - a SAS HBA or Expander, and the SAS remote PHY represented by - struct sas_rphy defines an "incoming" PHY on a SAS Expander or - end device. Note that this is purely a software concept, the - underlying hardware for a PHY and a remote PHY is the exactly - the same. - - - There is no concept of a SAS port in this code, users can see - what PHYs form a wide port based on the port_identifier attribute, - which is the same for all PHYs in a port. - -!Edrivers/scsi/scsi_transport_sas.c - - - SATA transport class - - The SATA transport is handled by libata, which has its own book of - documentation in this directory. - - - - Parallel SCSI (SPI) transport class - - The file drivers/scsi/scsi_transport_spi.c defines transport - attributes for traditional (fast/wide/ultra) SCSI busses. - -!Edrivers/scsi/scsi_transport_spi.c - - - SCSI RDMA (SRP) transport class - - The file drivers/scsi/scsi_transport_srp.c defines transport - attributes for SCSI over Remote Direct Memory Access. - -!Edrivers/scsi/scsi_transport_srp.c - - - - - - - SCSI lower layer - - Host Bus Adapter transport types - - Many modern device controllers use the SCSI command set as a protocol to - communicate with their devices through many different types of physical - connections. - - - In SCSI language a bus capable of carrying SCSI commands is - called a "transport", and a controller connecting to such a bus is - called a "host bus adapter" (HBA). - - - Debug transport - - The file drivers/scsi/scsi_debug.c simulates a host adapter with a - variable number of disks (or disk like devices) attached, sharing a - common amount of RAM. Does a lot of checking to make sure that we are - not getting blocks mixed up, and panics the kernel if anything out of - the ordinary is seen. - - - To be more realistic, the simulated devices have the transport - attributes of SAS disks. - - - For documentation see - http://sg.danny.cz/sg/sdebug26.html - - - - - todo - Parallel (fast/wide/ultra) SCSI, USB, SATA, - SAS, Fibre Channel, FireWire, ATAPI devices, Infiniband, - I20, iSCSI, Parallel ports, netlink... - - - - - diff --git a/Documentation/DocBook/sh.tmpl b/Documentation/DocBook/sh.tmpl deleted file mode 100644 index 4a38f604fa661f..00000000000000 --- a/Documentation/DocBook/sh.tmpl +++ /dev/null @@ -1,105 +0,0 @@ - - - - - - SuperH Interfaces Guide - - - - Paul - Mundt - -
- lethal@linux-sh.org -
- - - - - - 2008-2010 - Paul Mundt - - - 2008-2010 - Renesas Technology Corp. - - - 2010 - Renesas Electronics Corp. - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2 as published by the Free Software Foundation. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Memory Management - - SH-4 - - Store Queue API -!Earch/sh/kernel/cpu/sh4/sq.c - - - - SH-5 - - TLB Interfaces -!Iarch/sh/mm/tlb-sh5.c -!Iarch/sh/include/asm/tlb_64.h - - - - - Machine Specific Interfaces - - mach-dreamcast -!Iarch/sh/boards/mach-dreamcast/rtc.c - - - mach-x3proto -!Earch/sh/boards/mach-x3proto/ilsel.c - - - - Busses - - SuperHyway -!Edrivers/sh/superhyway/superhyway.c - - - - Maple -!Edrivers/sh/maple/maple.c - - - diff --git a/Documentation/DocBook/stylesheet.xsl b/Documentation/DocBook/stylesheet.xsl deleted file mode 100644 index 3bf4ecf3d760c8..00000000000000 --- a/Documentation/DocBook/stylesheet.xsl +++ /dev/null @@ -1,11 +0,0 @@ - - -1 -ansi -80 -0 - -1 -2 -1 - diff --git a/Documentation/DocBook/w1.tmpl b/Documentation/DocBook/w1.tmpl deleted file mode 100644 index b0228d4c81bb5c..00000000000000 --- a/Documentation/DocBook/w1.tmpl +++ /dev/null @@ -1,101 +0,0 @@ - - - - - - W1: Dallas' 1-wire bus - - - - David - Fries - -
- David@Fries.net -
- - - - - - - 2013 - - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License version 2. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - W1 API internal to the kernel - - - W1 API internal to the kernel - - drivers/w1/w1.h - W1 core functions. -!Idrivers/w1/w1.h - - - - drivers/w1/w1.c - W1 core functions. -!Idrivers/w1/w1.c - - - - drivers/w1/w1_family.h - Allows registering device family operations. -!Idrivers/w1/w1_family.h - - - - drivers/w1/w1_family.c - Allows registering device family operations. -!Edrivers/w1/w1_family.c - - - - drivers/w1/w1_int.c - W1 internal initialization for master devices. -!Edrivers/w1/w1_int.c - - - - drivers/w1/w1_netlink.h - W1 external netlink API structures and commands. -!Idrivers/w1/w1_netlink.h - - - - drivers/w1/w1_io.c - W1 input/output. -!Edrivers/w1/w1_io.c -!Idrivers/w1/w1_io.c - - - - - - - - diff --git a/Documentation/DocBook/z8530book.tmpl b/Documentation/DocBook/z8530book.tmpl deleted file mode 100644 index 6f3883be877e2a..00000000000000 --- a/Documentation/DocBook/z8530book.tmpl +++ /dev/null @@ -1,371 +0,0 @@ - - - - - - Z8530 Programming Guide - - - - Alan - Cox - -
- alan@lxorguk.ukuu.org.uk -
- - - - - - 2000 - Alan Cox - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - The Z85x30 family synchronous/asynchronous controller chips are - used on a large number of cheap network interface cards. The - kernel provides a core interface layer that is designed to make - it easy to provide WAN services using this chip. - - - The current driver only support synchronous operation. Merging the - asynchronous driver support into this code to allow any Z85x30 - device to be used as both a tty interface and as a synchronous - controller is a project for Linux post the 2.4 release - - - - - Driver Modes - - The Z85230 driver layer can drive Z8530, Z85C30 and Z85230 devices - in three different modes. Each mode can be applied to an individual - channel on the chip (each chip has two channels). - - - The PIO synchronous mode supports the most common Z8530 wiring. Here - the chip is interface to the I/O and interrupt facilities of the - host machine but not to the DMA subsystem. When running PIO the - Z8530 has extremely tight timing requirements. Doing high speeds, - even with a Z85230 will be tricky. Typically you should expect to - achieve at best 9600 baud with a Z8C530 and 64Kbits with a Z85230. - - - The DMA mode supports the chip when it is configured to use dual DMA - channels on an ISA bus. The better cards tend to support this mode - of operation for a single channel. With DMA running the Z85230 tops - out when it starts to hit ISA DMA constraints at about 512Kbits. It - is worth noting here that many PC machines hang or crash when the - chip is driven fast enough to hold the ISA bus solid. - - - Transmit DMA mode uses a single DMA channel. The DMA channel is used - for transmission as the transmit FIFO is smaller than the receive - FIFO. it gives better performance than pure PIO mode but is nowhere - near as ideal as pure DMA mode. - - - - - Using the Z85230 driver - - The Z85230 driver provides the back end interface to your board. To - configure a Z8530 interface you need to detect the board and to - identify its ports and interrupt resources. It is also your problem - to verify the resources are available. - - - Having identified the chip you need to fill in a struct z8530_dev, - which describes each chip. This object must exist until you finally - shutdown the board. Firstly zero the active field. This ensures - nothing goes off without you intending it. The irq field should - be set to the interrupt number of the chip. (Each chip has a single - interrupt source rather than each channel). You are responsible - for allocating the interrupt line. The interrupt handler should be - set to z8530_interrupt. The device id should - be set to the z8530_dev structure pointer. Whether the interrupt can - be shared or not is board dependent, and up to you to initialise. - - - The structure holds two channel structures. - Initialise chanA.ctrlio and chanA.dataio with the address of the - control and data ports. You can or this with Z8530_PORT_SLEEP to - indicate your interface needs the 5uS delay for chip settling done - in software. The PORT_SLEEP option is architecture specific. Other - flags may become available on future platforms, eg for MMIO. - Initialise the chanA.irqs to &z8530_nop to start the chip up - as disabled and discarding interrupt events. This ensures that - stray interrupts will be mopped up and not hang the bus. Set - chanA.dev to point to the device structure itself. The - private and name field you may use as you wish. The private field - is unused by the Z85230 layer. The name is used for error reporting - and it may thus make sense to make it match the network name. - - - Repeat the same operation with the B channel if your chip has - both channels wired to something useful. This isn't always the - case. If it is not wired then the I/O values do not matter, but - you must initialise chanB.dev. - - - If your board has DMA facilities then initialise the txdma and - rxdma fields for the relevant channels. You must also allocate the - ISA DMA channels and do any necessary board level initialisation - to configure them. The low level driver will do the Z8530 and - DMA controller programming but not board specific magic. - - - Having initialised the device you can then call - z8530_init. This will probe the chip and - reset it into a known state. An identification sequence is then - run to identify the chip type. If the checks fail to pass the - function returns a non zero error code. Typically this indicates - that the port given is not valid. After this call the - type field of the z8530_dev structure is initialised to either - Z8530, Z85C30 or Z85230 according to the chip found. - - - Once you have called z8530_init you can also make use of the utility - function z8530_describe. This provides a - consistent reporting format for the Z8530 devices, and allows all - the drivers to provide consistent reporting. - - - - - Attaching Network Interfaces - - If you wish to use the network interface facilities of the driver, - then you need to attach a network device to each channel that is - present and in use. In addition to use the generic HDLC - you need to follow some additional plumbing rules. They may seem - complex but a look at the example hostess_sv11 driver should - reassure you. - - - The network device used for each channel should be pointed to by - the netdevice field of each channel. The hdlc-> priv field of the - network device points to your private data - you will need to be - able to find your private data from this. - - - The way most drivers approach this particular problem is to - create a structure holding the Z8530 device definition and - put that into the private field of the network device. The - network device fields of the channels then point back to the - network devices. - - - If you wish to use the generic HDLC then you need to register - the HDLC device. - - - Before you register your network device you will also need to - provide suitable handlers for most of the network device callbacks. - See the network device documentation for more details on this. - - - - - Configuring And Activating The Port - - The Z85230 driver provides helper functions and tables to load the - port registers on the Z8530 chips. When programming the register - settings for a channel be aware that the documentation recommends - initialisation orders. Strange things happen when these are not - followed. - - - z8530_channel_load takes an array of - pairs of initialisation values in an array of u8 type. The first - value is the Z8530 register number. Add 16 to indicate the alternate - register bank on the later chips. The array is terminated by a 255. - - - The driver provides a pair of public tables. The - z8530_hdlc_kilostream table is for the UK 'Kilostream' service and - also happens to cover most other end host configurations. The - z8530_hdlc_kilostream_85230 table is the same configuration using - the enhancements of the 85230 chip. The configuration loaded is - standard NRZ encoded synchronous data with HDLC bitstuffing. All - of the timing is taken from the other end of the link. - - - When writing your own tables be aware that the driver internally - tracks register values. It may need to reload values. You should - therefore be sure to set registers 1-7, 9-11, 14 and 15 in all - configurations. Where the register settings depend on DMA selection - the driver will update the bits itself when you open or close. - Loading a new table with the interface open is not recommended. - - - There are three standard configurations supported by the core - code. In PIO mode the interface is programmed up to use - interrupt driven PIO. This places high demands on the host processor - to avoid latency. The driver is written to take account of latency - issues but it cannot avoid latencies caused by other drivers, - notably IDE in PIO mode. Because the drivers allocate buffers you - must also prevent MTU changes while the port is open. - - - Once the port is open it will call the rx_function of each channel - whenever a completed packet arrived. This is invoked from - interrupt context and passes you the channel and a network - buffer (struct sk_buff) holding the data. The data includes - the CRC bytes so most users will want to trim the last two - bytes before processing the data. This function is very timing - critical. When you wish to simply discard data the support - code provides the function z8530_null_rx - to discard the data. - - - To active PIO mode sending and receiving the - z8530_sync_open is called. This expects to be passed - the network device and the channel. Typically this is called from - your network device open callback. On a failure a non zero error - status is returned. The z8530_sync_close - function shuts down a PIO channel. This must be done before the - channel is opened again and before the driver shuts down - and unloads. - - - The ideal mode of operation is dual channel DMA mode. Here the - kernel driver will configure the board for DMA in both directions. - The driver also handles ISA DMA issues such as controller - programming and the memory range limit for you. This mode is - activated by calling the z8530_sync_dma_open - function. On failure a non zero error value is returned. - Once this mode is activated it can be shut down by calling the - z8530_sync_dma_close. You must call the close - function matching the open mode you used. - - - The final supported mode uses a single DMA channel to drive the - transmit side. As the Z85C30 has a larger FIFO on the receive - channel this tends to increase the maximum speed a little. - This is activated by calling the z8530_sync_txdma_open - . This returns a non zero error code on failure. The - z8530_sync_txdma_close function closes down - the Z8530 interface from this mode. - - - - - Network Layer Functions - - The Z8530 layer provides functions to queue packets for - transmission. The driver internally buffers the frame currently - being transmitted and one further frame (in order to keep back - to back transmission running). Any further buffering is up to - the caller. - - - The function z8530_queue_xmit takes a network - buffer in sk_buff format and queues it for transmission. The - caller must provide the entire packet with the exception of the - bitstuffing and CRC. This is normally done by the caller via - the generic HDLC interface layer. It returns 0 if the buffer has been - queued and non zero values for queue full. If the function accepts - the buffer it becomes property of the Z8530 layer and the caller - should not free it. - - - The function z8530_get_stats returns a pointer - to an internally maintained per interface statistics block. This - provides most of the interface code needed to implement the network - layer get_stats callback. - - - - - Porting The Z8530 Driver - - The Z8530 driver is written to be portable. In DMA mode it makes - assumptions about the use of ISA DMA. These are probably warranted - in most cases as the Z85230 in particular was designed to glue to PC - type machines. The PIO mode makes no real assumptions. - - - Should you need to retarget the Z8530 driver to another architecture - the only code that should need changing are the port I/O functions. - At the moment these assume PC I/O port accesses. This may not be - appropriate for all platforms. Replacing - z8530_read_port and z8530_write_port - is intended to be all that is required to port this - driver layer. - - - - - Known Bugs And Assumptions - - - Interrupt Locking - - - The locking in the driver is done via the global cli/sti lock. This - makes for relatively poor SMP performance. Switching this to use a - per device spin lock would probably materially improve performance. - - - - Occasional Failures - - - We have reports of occasional failures when run for very long - periods of time and the driver starts to receive junk frames. At - the moment the cause of this is not clear. - - - - - - - - - Public Functions Provided -!Edrivers/net/wan/z85230.c - - - - Internal Functions -!Idrivers/net/wan/z85230.c - - - diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt index 82001a25a14bd7..1f246eb25ca546 100644 --- a/Documentation/IRQ-domain.txt +++ b/Documentation/IRQ-domain.txt @@ -231,5 +231,42 @@ needs to: 4) No need to implement irq_domain_ops.map and irq_domain_ops.unmap, they are unused with hierarchy irq_domain. -Hierarchy irq_domain may also be used to support other architectures, -such as ARM, ARM64 etc. +Hierarchy irq_domain is in no way x86 specific, and is heavily used to +support other architectures, such as ARM, ARM64 etc. + +=== Debugging === + +If you switch on CONFIG_IRQ_DOMAIN_DEBUG (which depends on +CONFIG_IRQ_DOMAIN and CONFIG_DEBUG_FS), you will find a new file in +your debugfs mount point, called irq_domain_mapping. This file +contains a live snapshot of all the IRQ domains in the system: + + name mapped linear-max direct-max devtree-node + pl061 8 8 0 /smb/gpio@e0080000 + pl061 8 8 0 /smb/gpio@e1050000 + pMSI 0 0 0 /interrupt-controller@e1101000/v2m@e0080000 + MSI 37 0 0 /interrupt-controller@e1101000/v2m@e0080000 + GICv2m 37 0 0 /interrupt-controller@e1101000/v2m@e0080000 + GICv2 448 448 0 /interrupt-controller@e1101000 + +it also iterates over the interrupts to display their mapping in the +domains, and makes the domain stacking visible: + + +irq hwirq chip name chip data active type domain + 1 0x00019 GICv2 0xffff00000916bfd8 * LINEAR GICv2 + 2 0x0001d GICv2 0xffff00000916bfd8 LINEAR GICv2 + 3 0x0001e GICv2 0xffff00000916bfd8 * LINEAR GICv2 + 4 0x0001b GICv2 0xffff00000916bfd8 * LINEAR GICv2 + 5 0x0001a GICv2 0xffff00000916bfd8 LINEAR GICv2 +[...] + 96 0x81808 MSI 0x (null) RADIX MSI + 96+ 0x00063 GICv2m 0xffff8003ee116980 RADIX GICv2m + 96+ 0x00063 GICv2 0xffff00000916bfd8 LINEAR GICv2 + 97 0x08800 MSI 0x (null) * RADIX MSI + 97+ 0x00064 GICv2m 0xffff8003ee116980 * RADIX GICv2m + 97+ 0x00064 GICv2 0xffff00000916bfd8 * LINEAR GICv2 + +Here, interrupts 1-5 are only using a single domain, while 96 and 97 +are build out of a stack of three domain, each level performing a +particular function. diff --git a/Documentation/Makefile b/Documentation/Makefile index c2a469112c37bb..a42320385df34e 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -1 +1,126 @@ +# -*- makefile -*- +# Makefile for Sphinx documentation +# + subdir-y := + +# You can set these variables from the command line. +SPHINXBUILD = sphinx-build +SPHINXOPTS = +SPHINXDIRS = . +_SPHINXDIRS = $(patsubst $(srctree)/Documentation/%/conf.py,%,$(wildcard $(srctree)/Documentation/*/conf.py)) +SPHINX_CONF = conf.py +PAPER = +BUILDDIR = $(obj)/output +PDFLATEX = xelatex +LATEXOPTS = -interaction=batchmode + +# User-friendly check for sphinx-build +HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi) + +ifeq ($(HAVE_SPHINX),0) + +.DEFAULT: + $(warning The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed and in PATH, or set the SPHINXBUILD make variable to point to the full path of the '$(SPHINXBUILD)' executable.) + @echo " SKIP Sphinx $@ target." + +else # HAVE_SPHINX + +# User-friendly check for pdflatex +HAVE_PDFLATEX := $(shell if which $(PDFLATEX) >/dev/null 2>&1; then echo 1; else echo 0; fi) + +# Internal variables. +PAPEROPT_a4 = -D latex_paper_size=a4 +PAPEROPT_letter = -D latex_paper_size=letter +KERNELDOC = $(srctree)/scripts/kernel-doc +KERNELDOC_CONF = -D kerneldoc_srctree=$(srctree) -D kerneldoc_bin=$(KERNELDOC) +ALLSPHINXOPTS = $(KERNELDOC_CONF) $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) +# the i18n builder cannot share the environment and doctrees with the others +I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . + +# commands; the 'cmd' from scripts/Kbuild.include is not *loopable* +loop_cmd = $(echo-cmd) $(cmd_$(1)) || exit; + +# $2 sphinx builder e.g. "html" +# $3 name of the build subfolder / e.g. "media", used as: +# * dest folder relative to $(BUILDDIR) and +# * cache folder relative to $(BUILDDIR)/.doctrees +# $4 dest subfolder e.g. "man" for man pages at media/man +# $5 reST source folder relative to $(srctree)/$(src), +# e.g. "media" for the linux-tv book-set at ./Documentation/media + +quiet_cmd_sphinx = SPHINX $@ --> file://$(abspath $(BUILDDIR)/$3/$4) + cmd_sphinx = $(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/media $2 && \ + PYTHONDONTWRITEBYTECODE=1 \ + BUILDDIR=$(abspath $(BUILDDIR)) SPHINX_CONF=$(abspath $(srctree)/$(src)/$5/$(SPHINX_CONF)) \ + $(SPHINXBUILD) \ + -b $2 \ + -c $(abspath $(srctree)/$(src)) \ + -d $(abspath $(BUILDDIR)/.doctrees/$3) \ + -D version=$(KERNELVERSION) -D release=$(KERNELRELEASE) \ + $(ALLSPHINXOPTS) \ + $(abspath $(srctree)/$(src)/$5) \ + $(abspath $(BUILDDIR)/$3/$4) + +htmldocs: + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,html,$(var),,$(var))) + +linkcheckdocs: + @$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,linkcheck,$(var),,$(var))) + +latexdocs: + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,latex,$(var),latex,$(var))) + +ifeq ($(HAVE_PDFLATEX),0) + +pdfdocs: + $(warning The '$(PDFLATEX)' command was not found. Make sure you have it installed and in PATH to produce PDF output.) + @echo " SKIP Sphinx $@ target." + +else # HAVE_PDFLATEX + +pdfdocs: latexdocs + $(foreach var,$(SPHINXDIRS), $(MAKE) PDFLATEX=$(PDFLATEX) LATEXOPTS="$(LATEXOPTS)" -C $(BUILDDIR)/$(var)/latex || exit;) + +endif # HAVE_PDFLATEX + +epubdocs: + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,epub,$(var),epub,$(var))) + +xmldocs: + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,xml,$(var),xml,$(var))) + +endif # HAVE_SPHINX + +# The following targets are independent of HAVE_SPHINX, and the rules should +# work or silently pass without Sphinx. + +# no-ops for the Sphinx toolchain +sgmldocs: + @: +psdocs: + @: +mandocs: + @: +installmandocs: + @: + +cleandocs: + $(Q)rm -rf $(BUILDDIR) + $(Q)$(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/media clean + +dochelp: + @echo ' Linux kernel internal documentation in different formats from ReST:' + @echo ' htmldocs - HTML' + @echo ' latexdocs - LaTeX' + @echo ' pdfdocs - PDF' + @echo ' epubdocs - EPUB' + @echo ' xmldocs - XML' + @echo ' linkcheckdocs - check for broken external links (will connect to external hosts)' + @echo ' cleandocs - clean all generated files' + @echo + @echo ' make SPHINXDIRS="s1 s2" [target] Generate only docs of folder s1, s2' + @echo ' valid values for SPHINXDIRS are: $(_SPHINXDIRS)' + @echo + @echo ' make SPHINX_CONF={conf-file} [target] use *additional* sphinx-build' + @echo ' configuration. This is e.g. useful to build with nit-picking config.' diff --git a/Documentation/Makefile.sphinx b/Documentation/Makefile.sphinx deleted file mode 100644 index bcf529f6cf9b25..00000000000000 --- a/Documentation/Makefile.sphinx +++ /dev/null @@ -1,130 +0,0 @@ -# -*- makefile -*- -# Makefile for Sphinx documentation -# - -# You can set these variables from the command line. -SPHINXBUILD = sphinx-build -SPHINXOPTS = -SPHINXDIRS = . -_SPHINXDIRS = $(patsubst $(srctree)/Documentation/%/conf.py,%,$(wildcard $(srctree)/Documentation/*/conf.py)) -SPHINX_CONF = conf.py -PAPER = -BUILDDIR = $(obj)/output -PDFLATEX = xelatex -LATEXOPTS = -interaction=batchmode - -# User-friendly check for sphinx-build -HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi) - -ifeq ($(HAVE_SPHINX),0) - -.DEFAULT: - $(warning The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed and in PATH, or set the SPHINXBUILD make variable to point to the full path of the '$(SPHINXBUILD)' executable.) - @echo " SKIP Sphinx $@ target." - -else ifneq ($(DOCBOOKS),) - -# Skip Sphinx build if the user explicitly requested DOCBOOKS. -.DEFAULT: - @echo " SKIP Sphinx $@ target (DOCBOOKS specified)." - -else # HAVE_SPHINX - -# User-friendly check for pdflatex -HAVE_PDFLATEX := $(shell if which $(PDFLATEX) >/dev/null 2>&1; then echo 1; else echo 0; fi) - -# Internal variables. -PAPEROPT_a4 = -D latex_paper_size=a4 -PAPEROPT_letter = -D latex_paper_size=letter -KERNELDOC = $(srctree)/scripts/kernel-doc -KERNELDOC_CONF = -D kerneldoc_srctree=$(srctree) -D kerneldoc_bin=$(KERNELDOC) -ALLSPHINXOPTS = $(KERNELDOC_CONF) $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) -# the i18n builder cannot share the environment and doctrees with the others -I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . - -# commands; the 'cmd' from scripts/Kbuild.include is not *loopable* -loop_cmd = $(echo-cmd) $(cmd_$(1)) || exit; - -# $2 sphinx builder e.g. "html" -# $3 name of the build subfolder / e.g. "media", used as: -# * dest folder relative to $(BUILDDIR) and -# * cache folder relative to $(BUILDDIR)/.doctrees -# $4 dest subfolder e.g. "man" for man pages at media/man -# $5 reST source folder relative to $(srctree)/$(src), -# e.g. "media" for the linux-tv book-set at ./Documentation/media - -quiet_cmd_sphinx = SPHINX $@ --> file://$(abspath $(BUILDDIR)/$3/$4) - cmd_sphinx = $(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/media $2 && \ - PYTHONDONTWRITEBYTECODE=1 \ - BUILDDIR=$(abspath $(BUILDDIR)) SPHINX_CONF=$(abspath $(srctree)/$(src)/$5/$(SPHINX_CONF)) \ - $(SPHINXBUILD) \ - -b $2 \ - -c $(abspath $(srctree)/$(src)) \ - -d $(abspath $(BUILDDIR)/.doctrees/$3) \ - -D version=$(KERNELVERSION) -D release=$(KERNELRELEASE) \ - $(ALLSPHINXOPTS) \ - $(abspath $(srctree)/$(src)/$5) \ - $(abspath $(BUILDDIR)/$3/$4) - -htmldocs: - @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,html,$(var),,$(var))) - -linkcheckdocs: - @$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,linkcheck,$(var),,$(var))) - -latexdocs: - @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,latex,$(var),latex,$(var))) - -ifeq ($(HAVE_PDFLATEX),0) - -pdfdocs: - $(warning The '$(PDFLATEX)' command was not found. Make sure you have it installed and in PATH to produce PDF output.) - @echo " SKIP Sphinx $@ target." - -else # HAVE_PDFLATEX - -pdfdocs: latexdocs - $(foreach var,$(SPHINXDIRS), $(MAKE) PDFLATEX=$(PDFLATEX) LATEXOPTS="$(LATEXOPTS)" -C $(BUILDDIR)/$(var)/latex || exit;) - -endif # HAVE_PDFLATEX - -epubdocs: - @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,epub,$(var),epub,$(var))) - -xmldocs: - @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,xml,$(var),xml,$(var))) - -endif # HAVE_SPHINX - -# The following targets are independent of HAVE_SPHINX, and the rules should -# work or silently pass without Sphinx. - -# no-ops for the Sphinx toolchain -sgmldocs: - @: -psdocs: - @: -mandocs: - @: -installmandocs: - @: - -cleandocs: - $(Q)rm -rf $(BUILDDIR) - $(Q)$(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/media clean - -dochelp: - @echo ' Linux kernel internal documentation in different formats (Sphinx):' - @echo ' htmldocs - HTML' - @echo ' latexdocs - LaTeX' - @echo ' pdfdocs - PDF' - @echo ' epubdocs - EPUB' - @echo ' xmldocs - XML' - @echo ' linkcheckdocs - check for broken external links (will connect to external hosts)' - @echo ' cleandocs - clean all generated files' - @echo - @echo ' make SPHINXDIRS="s1 s2" [target] Generate only docs of folder s1, s2' - @echo ' valid values for SPHINXDIRS are: $(_SPHINXDIRS)' - @echo - @echo ' make SPHINX_CONF={conf-file} [target] use *additional* sphinx-build' - @echo ' configuration. This is e.g. useful to build with nit-picking config.' diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 1e37138027a3c8..618e13d5e27632 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -186,7 +186,7 @@ must disable interrupts while the lock is held. If the device sends a different interrupt, the driver will deadlock trying to recursively acquire the spinlock. Such deadlocks can be avoided by using spin_lock_irqsave() or spin_lock_irq() which disable local interrupts -and acquire the lock (see Documentation/DocBook/kernel-locking). +and acquire the lock (see Documentation/kernel-hacking/locking.rst). 4.5 How to tell whether MSI/MSI-X is enabled on a device diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 1672573b037a73..f46980c060aad9 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -28,8 +28,6 @@ stallwarn.txt - RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress) torture.txt - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST) -trace.txt - - CONFIG_RCU_TRACE debugfs files and formats UP.txt - RCU on Uniprocessor Systems whatisRCU.txt diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html index f60adf112663aa..95b30fa25d56ae 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.html +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -559,9 +559,7 @@

Publish/Subscribe Guarantee

For remove_gp_synchronous(), as long as all modifications to gp are carried out while holding gp_lock, the above optimizations are harmless. - However, - with CONFIG_SPARSE_RCU_POINTER=y, - sparse will complain if you + However, sparse will complain if you define gp with __rcu and then access it without using either rcu_access_pointer() or rcu_dereference(). @@ -1849,7 +1847,8 @@

Composability

If the nesting is not visible to the compiler, as is the case with mutually recursive functions each in its own translation unit, stack overflow will result. -If the nesting takes the form of loops, either the control variable +If the nesting takes the form of loops, perhaps in the guise of tail +recursion, either the control variable will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. Nevertheless, this class of RCU implementations is one of the most composable constructs in existence. @@ -1977,9 +1976,8 @@

and rcu_dereference(), perhaps (incorrectly) substituting a simple assignment. To catch this sort of error, a given RCU-protected pointer may be - tagged with __rcu, after which running sparse - with CONFIG_SPARSE_RCU_POINTER=y will complain - about simple-assignment accesses to that pointer. + tagged with __rcu, after which sparse + will complain about simple-assignment accesses to that pointer. Arnd Bergmann made me aware of this requirement, and also supplied the needed patch series. @@ -2036,7 +2034,7 @@

some other synchronization mechanism, for example, reference counting.
  • In kernels built with CONFIG_RCU_TRACE=y, RCU-related - information is provided via both debugfs and event tracing. + information is provided via event tracing.
  • Open-coded use of rcu_assign_pointer() and rcu_dereference() to create typical linked data structures can be surprisingly error-prone. @@ -2519,11 +2517,7 @@

    Energy Efficiency

    nohz_full CPU running in userspace. RCU must therefore track nohz_full userspace execution. -And in -CONFIG_NO_HZ_FULL_SYSIDLE=y -kernels, RCU must separately track idle CPUs on the one hand and -CPUs that are either idle or executing in userspace on the other. -In both cases, RCU must be able to sample state at two points in +RCU must therefore be able to sample state at two points in time, and be able to determine whether or not some other CPU spent any time idle and/or executing in userspace. @@ -2935,6 +2929,20 @@

    Sleepable RCU

    to whether or not a CPU is online, which means that srcu_barrier() need not exclude CPU-hotplug operations. +

    +SRCU also differs from other RCU flavors in that SRCU's expedited and +non-expedited grace periods are implemented by the same mechanism. +This means that in the current SRCU implementation, expediting a +future grace period has the side effect of expediting all prior +grace periods that have not yet completed. +(But please note that this is a property of the current implementation, +not necessarily of future implementations.) +In addition, if SRCU has been idle for longer than the interval +specified by the srcutree.exp_holdoff kernel boot parameter +(25 microseconds by default), +and if a synchronize_srcu() invocation ends this idle period, +that invocation will be automatically expedited. +

    As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating a locking bottleneck present in prior kernel versions. diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 877947130ebe63..6beda556faf32a 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -413,11 +413,11 @@ over a rather long period of time, but improvements are always welcome! read-side critical sections. It is the responsibility of the RCU update-side primitives to deal with this. -17. Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the - __rcu sparse checks (enabled by CONFIG_SPARSE_RCU_POINTER) to - validate your RCU code. These can help find problems as follows: +17. Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the + __rcu sparse checks to validate your RCU code. These can help + find problems as follows: - CONFIG_PROVE_RCU: check that accesses to RCU-protected data + CONFIG_PROVE_LOCKING: check that accesses to RCU-protected data structures are carried out under the proper RCU read-side critical section, while holding the right combination of locks, or whatever other conditions diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt deleted file mode 100644 index 6549012033f9d3..00000000000000 --- a/Documentation/RCU/trace.txt +++ /dev/null @@ -1,535 +0,0 @@ -CONFIG_RCU_TRACE debugfs Files and Formats - - -The rcutree and rcutiny implementations of RCU provide debugfs trace -output that summarizes counters and state. This information is useful for -debugging RCU itself, and can sometimes also help to debug abuses of RCU. -The following sections describe the debugfs files and formats, first -for rcutree and next for rcutiny. - - -CONFIG_TREE_RCU and CONFIG_PREEMPT_RCU debugfs Files and Formats - -These implementations of RCU provide several debugfs directories under the -top-level directory "rcu": - -rcu/rcu_bh -rcu/rcu_preempt -rcu/rcu_sched - -Each directory contains files for the corresponding flavor of RCU. -Note that rcu/rcu_preempt is only present for CONFIG_PREEMPT_RCU. -For CONFIG_TREE_RCU, the RCU flavor maps onto the RCU-sched flavor, -so that activity for both appears in rcu/rcu_sched. - -In addition, the following file appears in the top-level directory: -rcu/rcutorture. This file displays rcutorture test progress. The output -of "cat rcu/rcutorture" looks as follows: - -rcutorture test sequence: 0 (test in progress) -rcutorture update version number: 615 - -The first line shows the number of rcutorture tests that have completed -since boot. If a test is currently running, the "(test in progress)" -string will appear as shown above. The second line shows the number of -update cycles that the current test has started, or zero if there is -no test in progress. - - -Within each flavor directory (rcu/rcu_bh, rcu/rcu_sched, and possibly -also rcu/rcu_preempt) the following files will be present: - -rcudata: - Displays fields in struct rcu_data. -rcuexp: - Displays statistics for expedited grace periods. -rcugp: - Displays grace-period counters. -rcuhier: - Displays the struct rcu_node hierarchy. -rcu_pending: - Displays counts of the reasons rcu_pending() decided that RCU had - work to do. -rcuboost: - Displays RCU boosting statistics. Only present if - CONFIG_RCU_BOOST=y. - -The output of "cat rcu/rcu_preempt/rcudata" looks as follows: - - 0!c=30455 g=30456 cnq=1/0:1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 - 1!c=30719 g=30720 cnq=1/0:0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 - 2!c=30150 g=30151 cnq=1/1:1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 - 3 c=31249 g=31250 cnq=1/1:0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 - 4!c=29502 g=29503 cnq=1/0:1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 - 5 c=31201 g=31202 cnq=1/0:1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 - 6!c=30253 g=30254 cnq=1/0:1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 - 7 c=31178 g=31178 cnq=1/0:0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 - -This file has one line per CPU, or eight for this 8-CPU system. -The fields are as follows: - -o The number at the beginning of each line is the CPU number. - CPUs numbers followed by an exclamation mark are offline, - but have been online at least once since boot. There will be - no output for CPUs that have never been online, which can be - a good thing in the surprisingly common case where NR_CPUS is - substantially larger than the number of actual CPUs. - -o "c" is the count of grace periods that this CPU believes have - completed. Offlined CPUs and CPUs in dynticks idle mode may lag - quite a ways behind, for example, CPU 4 under "rcu_sched" above, - which has been offline through 16 RCU grace periods. It is not - unusual to see offline CPUs lagging by thousands of grace periods. - Note that although the grace-period number is an unsigned long, - it is printed out as a signed long to allow more human-friendly - representation near boot time. - -o "g" is the count of grace periods that this CPU believes have - started. Again, offlined CPUs and CPUs in dynticks idle mode - may lag behind. If the "c" and "g" values are equal, this CPU - has already reported a quiescent state for the last RCU grace - period that it is aware of, otherwise, the CPU believes that it - owes RCU a quiescent state. - -o "pq" indicates that this CPU has passed through a quiescent state - for the current grace period. It is possible for "pq" to be - "1" and "c" different than "g", which indicates that although - the CPU has passed through a quiescent state, either (1) this - CPU has not yet reported that fact, (2) some other CPU has not - yet reported for this grace period, or (3) both. - -o "qp" indicates that RCU still expects a quiescent state from - this CPU. Offlined CPUs and CPUs in dyntick idle mode might - well have qp=1, which is OK: RCU is still ignoring them. - -o "dt" is the current value of the dyntick counter that is incremented - when entering or leaving idle, either due to a context switch or - due to an interrupt. This number is even if the CPU is in idle - from RCU's viewpoint and odd otherwise. The number after the - first "/" is the interrupt nesting depth when in idle state, - or a large number added to the interrupt-nesting depth when - running a non-idle task. Some architectures do not accurately - count interrupt nesting when running in non-idle kernel context, - which can result in interesting anomalies such as negative - interrupt-nesting levels. The number after the second "/" - is the NMI nesting depth. - -o "df" is the number of times that some other CPU has forced a - quiescent state on behalf of this CPU due to this CPU being in - idle state. - -o "of" is the number of times that some other CPU has forced a - quiescent state on behalf of this CPU due to this CPU being - offline. In a perfect world, this might never happen, but it - turns out that offlining and onlining a CPU can take several grace - periods, and so there is likely to be an extended period of time - when RCU believes that the CPU is online when it really is not. - Please note that erring in the other direction (RCU believing a - CPU is offline when it is really alive and kicking) is a fatal - error, so it makes sense to err conservatively. - -o "ql" is the number of RCU callbacks currently residing on - this CPU. The first number is the number of "lazy" callbacks - that are known to RCU to only be freeing memory, and the number - after the "/" is the total number of callbacks, lazy or not. - These counters count callbacks regardless of what phase of - grace-period processing that they are in (new, waiting for - grace period to start, waiting for grace period to end, ready - to invoke). - -o "qs" gives an indication of the state of the callback queue - with four characters: - - "N" Indicates that there are callbacks queued that are not - ready to be handled by the next grace period, and thus - will be handled by the grace period following the next - one. - - "R" Indicates that there are callbacks queued that are - ready to be handled by the next grace period. - - "W" Indicates that there are callbacks queued that are - waiting on the current grace period. - - "D" Indicates that there are callbacks queued that have - already been handled by a prior grace period, and are - thus waiting to be invoked. Note that callbacks in - the process of being invoked are not counted here. - Callbacks in the process of being invoked are those - that have been removed from the rcu_data structures - queues by rcu_do_batch(), but which have not yet been - invoked. - - If there are no callbacks in a given one of the above states, - the corresponding character is replaced by ".". - -o "b" is the batch limit for this CPU. If more than this number - of RCU callbacks is ready to invoke, then the remainder will - be deferred. - -o "ci" is the number of RCU callbacks that have been invoked for - this CPU. Note that ci+nci+ql is the number of callbacks that have - been registered in absence of CPU-hotplug activity. - -o "nci" is the number of RCU callbacks that have been offloaded from - this CPU. This will always be zero unless the kernel was built - with CONFIG_RCU_NOCB_CPU=y and the "rcu_nocbs=" kernel boot - parameter was specified. - -o "co" is the number of RCU callbacks that have been orphaned due to - this CPU going offline. These orphaned callbacks have been moved - to an arbitrarily chosen online CPU. - -o "ca" is the number of RCU callbacks that have been adopted by this - CPU due to other CPUs going offline. Note that ci+co-ca+ql is - the number of RCU callbacks registered on this CPU. - - -Kernels compiled with CONFIG_RCU_BOOST=y display the following from -/debug/rcu/rcu_preempt/rcudata: - - 0!c=12865 g=12866 cnq=1/0:1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 - 1 c=14407 g=14408 cnq=1/0:0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 - 2 c=14407 g=14408 cnq=1/0:0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 - 3 c=14407 g=14408 cnq=1/0:0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 - 4 c=14405 g=14406 cnq=1/0:1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 - 5!c=14168 g=14169 cnq=1/0:0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 - 6 c=14404 g=14405 cnq=1/0:0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 - 7 c=14407 g=14408 cnq=1/0:1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 - -This is similar to the output discussed above, but contains the following -additional fields: - -o "kt" is the per-CPU kernel-thread state. The digit preceding - the first slash is zero if there is no work pending and 1 - otherwise. The character between the first pair of slashes is - as follows: - - "S" The kernel thread is stopped, in other words, all - CPUs corresponding to this rcu_node structure are - offline. - - "R" The kernel thread is running. - - "W" The kernel thread is waiting because there is no work - for it to do. - - "O" The kernel thread is waiting because it has been - forced off of its designated CPU or because its - ->cpus_allowed mask permits it to run on other than - its designated CPU. - - "Y" The kernel thread is yielding to avoid hogging CPU. - - "?" Unknown value, indicates a bug. - - The number after the final slash is the CPU that the kthread - is actually running on. - - This field is displayed only for CONFIG_RCU_BOOST kernels. - -o "ktl" is the low-order 16 bits (in hexadecimal) of the count of - the number of times that this CPU's per-CPU kthread has gone - through its loop servicing invoke_rcu_cpu_kthread() requests. - - This field is displayed only for CONFIG_RCU_BOOST kernels. - - -The output of "cat rcu/rcu_preempt/rcuexp" looks as follows: - -s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872 - -These fields are as follows: - -o "s" is the sequence number, with an odd number indicating that - an expedited grace period is in progress. - -o "wd1", "wd2", and "wd3" are the number of times that an attempt - to start an expedited grace period found that someone else had - completed an expedited grace period that satisfies the attempted - request. "Our work is done." - -o "enq" is the number of quiescent states still outstanding. - -o "sc" is the number of times that the attempt to start a - new expedited grace period succeeded. - - -The output of "cat rcu/rcu_preempt/rcugp" looks as follows: - -completed=31249 gpnum=31250 age=1 max=18 - -These fields are taken from the rcu_state structure, and are as follows: - -o "completed" is the number of grace periods that have completed. - It is comparable to the "c" field from rcu/rcudata in that a - CPU whose "c" field matches the value of "completed" is aware - that the corresponding RCU grace period has completed. - -o "gpnum" is the number of grace periods that have started. It is - similarly comparable to the "g" field from rcu/rcudata in that - a CPU whose "g" field matches the value of "gpnum" is aware that - the corresponding RCU grace period has started. - - If these two fields are equal, then there is no grace period - in progress, in other words, RCU is idle. On the other hand, - if the two fields differ (as they are above), then an RCU grace - period is in progress. - -o "age" is the number of jiffies that the current grace period - has extended for, or zero if there is no grace period currently - in effect. - -o "max" is the age in jiffies of the longest-duration grace period - thus far. - -The output of "cat rcu/rcu_preempt/rcuhier" looks as follows: - -c=14407 g=14408 s=0 jfq=2 j=c863 nfqs=12040/nfqsng=0(12040) fqlh=1051 oqlen=0/0 -3/3 ..>. 0:7 ^0 -e/e ..>. 0:3 ^0 d/d ..>. 4:7 ^1 - -The fields are as follows: - -o "c" is exactly the same as "completed" under rcu/rcu_preempt/rcugp. - -o "g" is exactly the same as "gpnum" under rcu/rcu_preempt/rcugp. - -o "s" is the current state of the force_quiescent_state() - state machine. - -o "jfq" is the number of jiffies remaining for this grace period - before force_quiescent_state() is invoked to help push things - along. Note that CPUs in idle mode throughout the grace period - will not report on their own, but rather must be check by some - other CPU via force_quiescent_state(). - -o "j" is the low-order four hex digits of the jiffies counter. - Yes, Paul did run into a number of problems that turned out to - be due to the jiffies counter no longer counting. Why do you ask? - -o "nfqs" is the number of calls to force_quiescent_state() since - boot. - -o "nfqsng" is the number of useless calls to force_quiescent_state(), - where there wasn't actually a grace period active. This can - no longer happen due to grace-period processing being pushed - into a kthread. The number in parentheses is the difference - between "nfqs" and "nfqsng", or the number of times that - force_quiescent_state() actually did some real work. - -o "fqlh" is the number of calls to force_quiescent_state() that - exited immediately (without even being counted in nfqs above) - due to contention on ->fqslock. - -o Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node - structure. Each line represents one level of the hierarchy, - from root to leaves. It is best to think of the rcu_data - structures as forming yet another level after the leaves. - Note that there might be either one, two, three, or even four - levels of rcu_node structures, depending on the relationship - between CONFIG_RCU_FANOUT, CONFIG_RCU_FANOUT_LEAF (possibly - adjusted using the rcu_fanout_leaf kernel boot parameter), and - CONFIG_NR_CPUS (possibly adjusted using the nr_cpu_ids count of - possible CPUs for the booting hardware). - - o The numbers separated by the "/" are the qsmask followed - by the qsmaskinit. The qsmask will have one bit - set for each entity in the next lower level that has - not yet checked in for the current grace period ("e" - indicating CPUs 5, 6, and 7 in the example above). - The qsmaskinit will have one bit for each entity that is - currently expected to check in during each grace period. - The value of qsmaskinit is assigned to that of qsmask - at the beginning of each grace period. - - o The characters separated by the ">" indicate the state - of the blocked-tasks lists. A "G" preceding the ">" - indicates that at least one task blocked in an RCU - read-side critical section blocks the current grace - period, while a "E" preceding the ">" indicates that - at least one task blocked in an RCU read-side critical - section blocks the current expedited grace period. - A "T" character following the ">" indicates that at - least one task is blocked within an RCU read-side - critical section, regardless of whether any current - grace period (expedited or normal) is inconvenienced. - A "." character appears if the corresponding condition - does not hold, so that "..>." indicates that no tasks - are blocked. In contrast, "GE>T" indicates maximal - inconvenience from blocked tasks. CONFIG_TREE_RCU - builds of the kernel will always show "..>.". - - o The numbers separated by the ":" are the range of CPUs - served by this struct rcu_node. This can be helpful - in working out how the hierarchy is wired together. - - For example, the example rcu_node structure shown above - has "0:7", indicating that it covers CPUs 0 through 7. - - o The number after the "^" indicates the bit in the - next higher level rcu_node structure that this rcu_node - structure corresponds to. For example, the "d/d ..>. 4:7 - ^1" has a "1" in this position, indicating that it - corresponds to the "1" bit in the "3" shown in the - "3/3 ..>. 0:7 ^0" entry on the next level up. - - -The output of "cat rcu/rcu_sched/rcu_pending" looks as follows: - - 0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0 - 1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0 - 2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0 - 3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0 - 4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0 - 5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0 - 6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0 - 7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0 - -The fields are as follows: - -o The leading number is the CPU number, with "!" indicating - an offline CPU. - -o "np" is the number of times that __rcu_pending() has been invoked - for the corresponding flavor of RCU. - -o "qsp" is the number of times that the RCU was waiting for a - quiescent state from this CPU. - -o "rpq" is the number of times that the CPU had passed through - a quiescent state, but not yet reported it to RCU. - -o "cbr" is the number of times that this CPU had RCU callbacks - that had passed through a grace period, and were thus ready - to be invoked. - -o "cng" is the number of times that this CPU needed another - grace period while RCU was idle. - -o "gpc" is the number of times that an old grace period had - completed, but this CPU was not yet aware of it. - -o "gps" is the number of times that a new grace period had started, - but this CPU was not yet aware of it. - -o "ndw" is the number of times that a wakeup of an rcuo - callback-offload kthread had to be deferred in order to avoid - deadlock. - -o "nn" is the number of times that this CPU needed nothing. - - -The output of "cat rcu/rcuboost" looks as follows: - -0:3 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=c864 bt=c894 - balk: nt=0 egt=4695 bt=0 nb=0 ny=56 nos=0 -4:7 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=c864 bt=c894 - balk: nt=0 egt=6541 bt=0 nb=0 ny=126 nos=0 - -This information is output only for rcu_preempt. Each two-line entry -corresponds to a leaf rcu_node structure. The fields are as follows: - -o "n:m" is the CPU-number range for the corresponding two-line - entry. In the sample output above, the first entry covers - CPUs zero through three and the second entry covers CPUs four - through seven. - -o "tasks=TNEB" gives the state of the various segments of the - rnp->blocked_tasks list: - - "T" This indicates that there are some tasks that blocked - while running on one of the corresponding CPUs while - in an RCU read-side critical section. - - "N" This indicates that some of the blocked tasks are preventing - the current normal (non-expedited) grace period from - completing. - - "E" This indicates that some of the blocked tasks are preventing - the current expedited grace period from completing. - - "B" This indicates that some of the blocked tasks are in - need of RCU priority boosting. - - Each character is replaced with "." if the corresponding - condition does not hold. - -o "kt" is the state of the RCU priority-boosting kernel - thread associated with the corresponding rcu_node structure. - The state can be one of the following: - - "S" The kernel thread is stopped, in other words, all - CPUs corresponding to this rcu_node structure are - offline. - - "R" The kernel thread is running. - - "W" The kernel thread is waiting because there is no work - for it to do. - - "Y" The kernel thread is yielding to avoid hogging CPU. - - "?" Unknown value, indicates a bug. - -o "ntb" is the number of tasks boosted. - -o "neb" is the number of tasks boosted in order to complete an - expedited grace period. - -o "nnb" is the number of tasks boosted in order to complete a - normal (non-expedited) grace period. When boosting a task - that was blocking both an expedited and a normal grace period, - it is counted against the expedited total above. - -o "j" is the low-order 16 bits of the jiffies counter in - hexadecimal. - -o "bt" is the low-order 16 bits of the value that the jiffies - counter will have when we next start boosting, assuming that - the current grace period does not end beforehand. This is - also in hexadecimal. - -o "balk: nt" counts the number of times we didn't boost (in - other words, we balked) even though it was time to boost because - there were no blocked tasks to boost. This situation occurs - when there is one blocked task on one rcu_node structure and - none on some other rcu_node structure. - -o "egt" counts the number of times we balked because although - there were blocked tasks, none of them were blocking the - current grace period, whether expedited or otherwise. - -o "bt" counts the number of times we balked because boosting - had already been initiated for the current grace period. - -o "nb" counts the number of times we balked because there - was at least one task blocking the current non-expedited grace - period that never had blocked. If it is already running, it - just won't help to boost its priority! - -o "ny" counts the number of times we balked because it was - not yet time to start boosting. - -o "nos" counts the number of times we balked for other - reasons, e.g., the grace period ended first. - - -CONFIG_TINY_RCU debugfs Files and Formats - -These implementations of RCU provides a single debugfs file under the -top-level directory RCU, namely rcu/rcudata, which displays fields in -rcu_bh_ctrlblk and rcu_sched_ctrlblk. - -The output of "cat rcu/rcudata" is as follows: - -rcu_sched: qlen: 0 -rcu_bh: qlen: 0 - -This is split into rcu_sched and rcu_bh sections. The field is as -follows: - -o "qlen" is the number of RCU callbacks currently waiting either - for an RCU grace period or waiting to be invoked. This is the - only field present for rcu_sched and rcu_bh, due to the - short-circuiting of grace period in those two cases. diff --git a/Documentation/acpi/gpio-properties.txt b/Documentation/acpi/gpio-properties.txt index 2aff0349facd6e..88c65cb5bf0a70 100644 --- a/Documentation/acpi/gpio-properties.txt +++ b/Documentation/acpi/gpio-properties.txt @@ -156,3 +156,68 @@ pointed to by its first argument. That should be done in the driver's .probe() routine. On removal, the driver should unregister its GPIO mapping table by calling acpi_dev_remove_driver_gpios() on the ACPI device object where that table was previously registered. + +Using the _CRS fallback +----------------------- + +If a device does not have _DSD or the driver does not create ACPI GPIO +mapping, the Linux GPIO framework refuses to return any GPIOs. This is +because the driver does not know what it actually gets. For example if we +have a device like below: + + Device (BTH) + { + Name (_HID, ...) + + Name (_CRS, ResourceTemplate () { + GpioIo (Exclusive, PullNone, 0, 0, IoRestrictionNone, + "\\_SB.GPO0", 0, ResourceConsumer) {15} + GpioIo (Exclusive, PullNone, 0, 0, IoRestrictionNone, + "\\_SB.GPO0", 0, ResourceConsumer) {27} + }) + } + +The driver might expect to get the right GPIO when it does: + + desc = gpiod_get(dev, "reset", GPIOD_OUT_LOW); + +but since there is no way to know the mapping between "reset" and +the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT). + +The driver author can solve this by passing the mapping explictly +(the recommended way and documented in the above chapter). + +The ACPI GPIO mapping tables should not contaminate drivers that are not +knowing about which exact device they are servicing on. It implies that +the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain +objects, as listed in the above chapter, of the device in question. + +Getting GPIO descriptor +----------------------- + +There are two main approaches to get GPIO resource from ACPI: + desc = gpiod_get(dev, connection_id, flags); + desc = gpiod_get_index(dev, connection_id, index, flags); + +We may consider two different cases here, i.e. when connection ID is +provided and otherwise. + +Case 1: + desc = gpiod_get(dev, "non-null-connection-id", flags); + desc = gpiod_get_index(dev, "non-null-connection-id", index, flags); + +Case 2: + desc = gpiod_get(dev, NULL, flags); + desc = gpiod_get_index(dev, NULL, index, flags); + +Case 1 assumes that corresponding ACPI device description must have +defined device properties and will prevent to getting any GPIO resources +otherwise. + +Case 2 explicitly tells GPIO core to look for resources in _CRS. + +Be aware that gpiod_get_index() in cases 1 and 2, assuming that there +are two versions of ACPI device description provided and no mapping is +present in the driver, will return different resources. That's why a +certain driver has to handle them carefully as explained in previous +chapter. diff --git a/Documentation/security/LoadPin.txt b/Documentation/admin-guide/LSM/LoadPin.rst similarity index 73% rename from Documentation/security/LoadPin.txt rename to Documentation/admin-guide/LSM/LoadPin.rst index e11877f5d3d4b5..32070762d24c44 100644 --- a/Documentation/security/LoadPin.txt +++ b/Documentation/admin-guide/LSM/LoadPin.rst @@ -1,3 +1,7 @@ +======= +LoadPin +======= + LoadPin is a Linux Security Module that ensures all kernel-loaded files (modules, firmware, etc) all originate from the same filesystem, with the expectation that such a filesystem is backed by a read-only device @@ -5,13 +9,13 @@ such as dm-verity or CDROM. This allows systems that have a verified and/or unchangeable filesystem to enforce module and firmware loading restrictions without needing to sign the files individually. -The LSM is selectable at build-time with CONFIG_SECURITY_LOADPIN, and +The LSM is selectable at build-time with ``CONFIG_SECURITY_LOADPIN``, and can be controlled at boot-time with the kernel command line option -"loadpin.enabled". By default, it is enabled, but can be disabled at -boot ("loadpin.enabled=0"). +"``loadpin.enabled``". By default, it is enabled, but can be disabled at +boot ("``loadpin.enabled=0``"). LoadPin starts pinning when it sees the first file loaded. If the block device backing the filesystem is not read-only, a sysctl is -created to toggle pinning: /proc/sys/kernel/loadpin/enabled. (Having +created to toggle pinning: ``/proc/sys/kernel/loadpin/enabled``. (Having a mutable filesystem means pinning is mutable too, but having the sysctl allows for easy testing on systems with a mutable filesystem.) diff --git a/Documentation/security/SELinux.txt b/Documentation/admin-guide/LSM/SELinux.rst similarity index 71% rename from Documentation/security/SELinux.txt rename to Documentation/admin-guide/LSM/SELinux.rst index 07eae00f3314a2..f722c9b4173a82 100644 --- a/Documentation/security/SELinux.txt +++ b/Documentation/admin-guide/LSM/SELinux.rst @@ -1,27 +1,33 @@ +======= +SELinux +======= + If you want to use SELinux, chances are you will want to use the distro-provided policies, or install the latest reference policy release from + http://oss.tresys.com/projects/refpolicy However, if you want to install a dummy policy for -testing, you can do using 'mdp' provided under +testing, you can do using ``mdp`` provided under scripts/selinux. Note that this requires the selinux userspace to be installed - in particular you will need checkpolicy to compile a kernel, and setfiles and fixfiles to label the filesystem. 1. Compile the kernel with selinux enabled. - 2. Type 'make' to compile mdp. + 2. Type ``make`` to compile ``mdp``. 3. Make sure that you are not running with SELinux enabled and a real policy. If you are, reboot with selinux disabled before continuing. - 4. Run install_policy.sh: + 4. Run install_policy.sh:: + cd scripts/selinux sh install_policy.sh Step 4 will create a new dummy policy valid for your kernel, with a single selinux user, role, and type. -It will compile the policy, will set your SELINUXTYPE to -dummy in /etc/selinux/config, install the compiled policy -as 'dummy', and relabel your filesystem. +It will compile the policy, will set your ``SELINUXTYPE`` to +``dummy`` in ``/etc/selinux/config``, install the compiled policy +as ``dummy``, and relabel your filesystem. diff --git a/Documentation/security/Smack.txt b/Documentation/admin-guide/LSM/Smack.rst similarity index 85% rename from Documentation/security/Smack.txt rename to Documentation/admin-guide/LSM/Smack.rst index 945cc633d883de..6a5826a13aea8c 100644 --- a/Documentation/security/Smack.txt +++ b/Documentation/admin-guide/LSM/Smack.rst @@ -1,3 +1,6 @@ +===== +Smack +===== "Good for you, you've decided to clean the elevator!" @@ -14,6 +17,7 @@ available to determine which is best suited to the problem at hand. Smack consists of three major components: + - The kernel - Basic utilities, which are helpful but not required - Configuration data @@ -39,16 +43,24 @@ The current git repository for Smack user space is: This should make and install on most modern distributions. There are five commands included in smackutil: -chsmack - display or set Smack extended attribute values -smackctl - load the Smack access rules -smackaccess - report if a process with one label has access - to an object with another +chsmack: + display or set Smack extended attribute values + +smackctl: + load the Smack access rules + +smackaccess: + report if a process with one label has access + to an object with another These two commands are obsolete with the introduction of the smackfs/load2 and smackfs/cipso2 interfaces. -smackload - properly formats data for writing to smackfs/load -smackcipso - properly formats data for writing to smackfs/cipso +smackload: + properly formats data for writing to smackfs/load + +smackcipso: + properly formats data for writing to smackfs/cipso In keeping with the intent of Smack, configuration data is minimal and not strictly required. The most important @@ -56,15 +68,15 @@ configuration step is mounting the smackfs pseudo filesystem. If smackutil is installed the startup script will take care of this, but it can be manually as well. -Add this line to /etc/fstab: +Add this line to ``/etc/fstab``:: smackfs /sys/fs/smackfs smackfs defaults 0 0 -The /sys/fs/smackfs directory is created by the kernel. +The ``/sys/fs/smackfs`` directory is created by the kernel. Smack uses extended attributes (xattrs) to store labels on filesystem objects. The attributes are stored in the extended attribute security -name space. A process must have CAP_MAC_ADMIN to change any of these +name space. A process must have ``CAP_MAC_ADMIN`` to change any of these attributes. The extended attributes that Smack uses are: @@ -73,14 +85,17 @@ SMACK64 Used to make access control decisions. In almost all cases the label given to a new filesystem object will be the label of the process that created it. + SMACK64EXEC The Smack label of a process that execs a program file with this attribute set will run with this attribute's value. + SMACK64MMAP Don't allow the file to be mmapped by a process whose Smack label does not allow all of the access permitted to a process with the label contained in this attribute. This is a very specific use case for shared libraries. + SMACK64TRANSMUTE Can only have the value "TRUE". If this attribute is present on a directory when an object is created in the directory and @@ -89,27 +104,29 @@ SMACK64TRANSMUTE gets the label of the directory instead of the label of the creating process. If the object being created is a directory the SMACK64TRANSMUTE attribute is set as well. + SMACK64IPIN This attribute is only available on file descriptors for sockets. Use the Smack label in this attribute for access control decisions on packets being delivered to this socket. + SMACK64IPOUT This attribute is only available on file descriptors for sockets. Use the Smack label in this attribute for access control decisions on packets coming from this socket. -There are multiple ways to set a Smack label on a file: +There are multiple ways to set a Smack label on a file:: # attr -S -s SMACK64 -V "value" path # chsmack -a value path A process can see the Smack label it is running with by -reading /proc/self/attr/current. A process with CAP_MAC_ADMIN +reading ``/proc/self/attr/current``. A process with ``CAP_MAC_ADMIN`` can set the process Smack by writing there. Most Smack configuration is accomplished by writing to files in the smackfs filesystem. This pseudo-filesystem is mounted -on /sys/fs/smackfs. +on ``/sys/fs/smackfs``. access Provided for backward compatibility. The access2 interface @@ -120,6 +137,7 @@ access this file. The next read will indicate whether the access would be permitted. The text will be either "1" indicating access, or "0" indicating denial. + access2 This interface reports whether a subject with the specified Smack label has a particular access to an object with a @@ -127,13 +145,17 @@ access2 this file. The next read will indicate whether the access would be permitted. The text will be either "1" indicating access, or "0" indicating denial. + ambient This contains the Smack label applied to unlabeled network packets. + change-rule This interface allows modification of existing access control rules. - The format accepted on write is: + The format accepted on write is:: + "%s %s %s %s" + where the first string is the subject label, the second the object label, the third the access to allow and the fourth the access to deny. The access strings may contain only the characters @@ -141,47 +163,63 @@ change-rule modified by enabling the permissions in the third string and disabling those in the fourth string. If there is no such rule it will be created using the access specified in the third and the fourth strings. + cipso Provided for backward compatibility. The cipso2 interface is preferred and should be used instead. This interface allows a specific CIPSO header to be assigned - to a Smack label. The format accepted on write is: + to a Smack label. The format accepted on write is:: + "%24s%4d%4d"["%4d"]... + The first string is a fixed Smack label. The first number is the level to use. The second number is the number of categories. - The following numbers are the categories. - "level-3-cats-5-19 3 2 5 19" + The following numbers are the categories:: + + "level-3-cats-5-19 3 2 5 19" + cipso2 This interface allows a specific CIPSO header to be assigned - to a Smack label. The format accepted on write is: - "%s%4d%4d"["%4d"]... + to a Smack label. The format accepted on write is:: + + "%s%4d%4d"["%4d"]... + The first string is a long Smack label. The first number is the level to use. The second number is the number of categories. - The following numbers are the categories. - "level-3-cats-5-19 3 2 5 19" + The following numbers are the categories:: + + "level-3-cats-5-19 3 2 5 19" + direct This contains the CIPSO level used for Smack direct label representation in network packets. + doi This contains the CIPSO domain of interpretation used in network packets. + ipv6host This interface allows specific IPv6 internet addresses to be treated as single label hosts. Packets are sent to single label hosts only from processes that have Smack write access to the host label. All packets received from single label hosts - are given the specified label. The format accepted on write is: + are given the specified label. The format accepted on write is:: + "%h:%h:%h:%h:%h:%h:%h:%h label" or "%h:%h:%h:%h:%h:%h:%h:%h/%d label". + The "::" address shortcut is not supported. If label is "-DELETE" a matched entry will be deleted. + load Provided for backward compatibility. The load2 interface is preferred and should be used instead. This interface allows access control rules in addition to the system defined rules to be specified. The format accepted - on write is: + on write is:: + "%24s%24s%5s" + where the first string is the subject label, the second the object label, and the third the requested access. The access string may contain only the characters "rwxat-", and specifies @@ -189,17 +227,21 @@ load permissions that are not allowed. The string "r-x--" would specify read and execute access. Labels are limited to 23 characters in length. + load2 This interface allows access control rules in addition to the system defined rules to be specified. The format accepted - on write is: + on write is:: + "%s %s %s" + where the first string is the subject label, the second the object label, and the third the requested access. The access string may contain only the characters "rwxat-", and specifies which sort of access is allowed. The "-" is a placeholder for permissions that are not allowed. The string "r-x--" would specify read and execute access. + load-self Provided for backward compatibility. The load-self2 interface is preferred and should be used instead. @@ -208,66 +250,83 @@ load-self otherwise be permitted, and are intended to provide additional restrictions on the process. The format is the same as for the load interface. + load-self2 This interface allows process specific access rules to be defined. These rules are only consulted if access would otherwise be permitted, and are intended to provide additional restrictions on the process. The format is the same as for the load2 interface. + logging This contains the Smack logging state. + mapped This contains the CIPSO level used for Smack mapped label representation in network packets. + netlabel This interface allows specific internet addresses to be treated as single label hosts. Packets are sent to single label hosts without CIPSO headers, but only from processes that have Smack write access to the host label. All packets received from single label hosts are given the specified - label. The format accepted on write is: + label. The format accepted on write is:: + "%d.%d.%d.%d label" or "%d.%d.%d.%d/%d label". + If the label specified is "-CIPSO" the address is treated as a host that supports CIPSO headers. + onlycap This contains labels processes must have for CAP_MAC_ADMIN - and CAP_MAC_OVERRIDE to be effective. If this file is empty + and ``CAP_MAC_OVERRIDE`` to be effective. If this file is empty these capabilities are effective at for processes with any label. The values are set by writing the desired labels, separated by spaces, to the file or cleared by writing "-" to the file. + ptrace This is used to define the current ptrace policy - 0 - default: this is the policy that relies on Smack access rules. - For the PTRACE_READ a subject needs to have a read access on - object. For the PTRACE_ATTACH a read-write access is required. - 1 - exact: this is the policy that limits PTRACE_ATTACH. Attach is + + 0 - default: + this is the policy that relies on Smack access rules. + For the ``PTRACE_READ`` a subject needs to have a read access on + object. For the ``PTRACE_ATTACH`` a read-write access is required. + + 1 - exact: + this is the policy that limits ``PTRACE_ATTACH``. Attach is only allowed when subject's and object's labels are equal. - PTRACE_READ is not affected. Can be overridden with CAP_SYS_PTRACE. - 2 - draconian: this policy behaves like the 'exact' above with an - exception that it can't be overridden with CAP_SYS_PTRACE. + ``PTRACE_READ`` is not affected. Can be overridden with ``CAP_SYS_PTRACE``. + + 2 - draconian: + this policy behaves like the 'exact' above with an + exception that it can't be overridden with ``CAP_SYS_PTRACE``. + revoke-subject Writing a Smack label here sets the access to '-' for all access rules with that subject label. + unconfined - If the kernel is configured with CONFIG_SECURITY_SMACK_BRINGUP - a process with CAP_MAC_ADMIN can write a label into this interface. + If the kernel is configured with ``CONFIG_SECURITY_SMACK_BRINGUP`` + a process with ``CAP_MAC_ADMIN`` can write a label into this interface. Thereafter, accesses that involve that label will be logged and the access permitted if it wouldn't be otherwise. Note that this is dangerous and can ruin the proper labeling of your system. It should never be used in production. + relabel-self This interface contains a list of labels to which the process can - transition to, by writing to /proc/self/attr/current. + transition to, by writing to ``/proc/self/attr/current``. Normally a process can change its own label to any legal value, but only - if it has CAP_MAC_ADMIN. This interface allows a process without - CAP_MAC_ADMIN to relabel itself to one of labels from predefined list. - A process without CAP_MAC_ADMIN can change its label only once. When it + if it has ``CAP_MAC_ADMIN``. This interface allows a process without + ``CAP_MAC_ADMIN`` to relabel itself to one of labels from predefined list. + A process without ``CAP_MAC_ADMIN`` can change its label only once. When it does, this list will be cleared. The values are set by writing the desired labels, separated by spaces, to the file or cleared by writing "-" to the file. If you are using the smackload utility -you can add access rules in /etc/smack/accesses. They take the form: +you can add access rules in ``/etc/smack/accesses``. They take the form:: subjectlabel objectlabel access @@ -277,14 +336,14 @@ object with objectlabel. If there is no rule no access is allowed. Look for additional programs on http://schaufler-ca.com -From the Smack Whitepaper: - -The Simplified Mandatory Access Control Kernel +The Simplified Mandatory Access Control Kernel (Whitepaper) +=========================================================== Casey Schaufler casey@schaufler-ca.com Mandatory Access Control +------------------------ Computer systems employ a variety of schemes to constrain how information is shared among the people and services using the machine. Some of these schemes @@ -297,6 +356,7 @@ access control mechanisms because you don't have a choice regarding the users or programs that have access to pieces of data. Bell & LaPadula +--------------- From the middle of the 1980's until the turn of the century Mandatory Access Control (MAC) was very closely associated with the Bell & LaPadula security @@ -306,6 +366,7 @@ within the Capital Beltway and Scandinavian supercomputer centers but was often sited as failing to address general needs. Domain Type Enforcement +----------------------- Around the turn of the century Domain Type Enforcement (DTE) became popular. This scheme organizes users, programs, and data into domains that are @@ -316,6 +377,7 @@ necessary to provide a secure domain mapping leads to the scheme being disabled or used in limited ways in the majority of cases. Smack +----- Smack is a Mandatory Access Control mechanism designed to provide useful MAC while avoiding the pitfalls of its predecessors. The limitations of Bell & @@ -326,46 +388,55 @@ Enforcement and avoided by defining access controls in terms of the access modes already in use. Smack Terminology +----------------- The jargon used to talk about Smack will be familiar to those who have dealt with other MAC systems and shouldn't be too difficult for the uninitiated to pick up. There are four terms that are used in a specific way and that are especially important: - Subject: A subject is an active entity on the computer system. + Subject: + A subject is an active entity on the computer system. On Smack a subject is a task, which is in turn the basic unit of execution. - Object: An object is a passive entity on the computer system. + Object: + An object is a passive entity on the computer system. On Smack files of all types, IPC, and tasks can be objects. - Access: Any attempt by a subject to put information into or get + Access: + Any attempt by a subject to put information into or get information from an object is an access. - Label: Data that identifies the Mandatory Access Control + Label: + Data that identifies the Mandatory Access Control characteristics of a subject or an object. These definitions are consistent with the traditional use in the security community. There are also some terms from Linux that are likely to crop up: - Capability: A task that possesses a capability has permission to + Capability: + A task that possesses a capability has permission to violate an aspect of the system security policy, as identified by the specific capability. A task that possesses one or more capabilities is a privileged task, whereas a task with no capabilities is an unprivileged task. - Privilege: A task that is allowed to violate the system security + Privilege: + A task that is allowed to violate the system security policy is said to have privilege. As of this writing a task can have privilege either by possessing capabilities or by having an effective user of root. Smack Basics +------------ Smack is an extension to a Linux system. It enforces additional restrictions on what subjects can access which objects, based on the labels attached to each of the subject and the object. Labels +~~~~~~ Smack labels are ASCII character strings. They can be up to 255 characters long, but keeping them to twenty-three characters is recommended. @@ -377,7 +448,7 @@ contain unprintable characters, the "/" (slash), the "\" (backslash), the "'" (quote) and '"' (double-quote) characters. Smack labels cannot begin with a '-'. This is reserved for special options. -There are some predefined labels: +There are some predefined labels:: _ Pronounced "floor", a single underscore character. ^ Pronounced "hat", a single circumflex character. @@ -390,14 +461,18 @@ of a process will usually be assigned by the system initialization mechanism. Access Rules +~~~~~~~~~~~~ Smack uses the traditional access modes of Linux. These modes are read, execute, write, and occasionally append. There are a few cases where the access mode may not be obvious. These include: - Signals: A signal is a write operation from the subject task to + Signals: + A signal is a write operation from the subject task to the object task. - Internet Domain IPC: Transmission of a packet is considered a + + Internet Domain IPC: + Transmission of a packet is considered a write operation from the source task to the destination task. Smack restricts access based on the label attached to a subject and the label @@ -417,6 +492,7 @@ order: 7. Any other access is denied. Smack Access Rules +~~~~~~~~~~~~~~~~~~ With the isolation provided by Smack access separation is simple. There are many interesting cases where limited access by subjects to objects with @@ -427,8 +503,9 @@ be "born" highly classified. To accommodate such schemes Smack includes a mechanism for specifying rules allowing access between labels. Access Rule Format +~~~~~~~~~~~~~~~~~~ -The format of an access rule is: +The format of an access rule is:: subject-label object-label access @@ -446,7 +523,7 @@ describe access modes: Uppercase values for the specification letters are allowed as well. Access mode specifications can be in any order. Examples of acceptable rules -are: +are:: TopSecret Secret rx Secret Unclass R @@ -456,7 +533,7 @@ are: New Old rRrRr Closed Off - -Examples of unacceptable rules are: +Examples of unacceptable rules are:: Top Secret Secret rx Ace Ace r @@ -469,6 +546,7 @@ access specifications. The dash is a placeholder, so "a-r" is the same as "ar". A lone dash is used to specify that no access should be allowed. Applying Access Rules +~~~~~~~~~~~~~~~~~~~~~ The developers of Linux rarely define new sorts of things, usually importing schemes and concepts from other systems. Most often, the other systems are @@ -511,6 +589,7 @@ one process to another requires that the sender have write access to the receiver. The receiver is not required to have read access to the sender. Setting Access Rules +~~~~~~~~~~~~~~~~~~~~ The configuration file /etc/smack/accesses contains the rules to be set at system startup. The contents are written to the special file @@ -520,6 +599,7 @@ one rule, with the most recently specified overriding any earlier specification. Task Attribute +~~~~~~~~~~~~~~ The Smack label of a process can be read from /proc//attr/current. A process can read its own Smack label from /proc/self/attr/current. A @@ -527,12 +607,14 @@ privileged process can change its own Smack label by writing to /proc/self/attr/current but not the label of another process. File Attribute +~~~~~~~~~~~~~~ The Smack label of a filesystem object is stored as an extended attribute named SMACK64 on the file. This attribute is in the security namespace. It can only be changed by a process with privilege. Privilege +~~~~~~~~~ A process with CAP_MAC_OVERRIDE or CAP_MAC_ADMIN is privileged. CAP_MAC_OVERRIDE allows the process access to objects it would @@ -540,6 +622,7 @@ be denied otherwise. CAP_MAC_ADMIN allows a process to change Smack data, including rules and attributes. Smack Networking +~~~~~~~~~~~~~~~~ As mentioned before, Smack enforces access control on network protocol transmissions. Every packet sent by a Smack process is tagged with its Smack @@ -551,6 +634,7 @@ packet has write access to the receiving process and if that is not the case the packet is dropped. CIPSO Configuration +~~~~~~~~~~~~~~~~~~~ It is normally unnecessary to specify the CIPSO configuration. The default values used by the system handle all internal cases. Smack will compose CIPSO @@ -571,13 +655,13 @@ discarded. The DOI is 3 by default. The value can be read from The label and category set are mapped to a Smack label as defined in /etc/smack/cipso. -A Smack/CIPSO mapping has the form: +A Smack/CIPSO mapping has the form:: smack level [category [category]*] Smack does not expect the level or category sets to be related in any particular way and does not assume or assign accesses based on them. Some -examples of mappings: +examples of mappings:: TopSecret 7 TS:A,B 7 1 2 @@ -597,25 +681,30 @@ value can be read from /sys/fs/smackfs/direct and changed by writing to /sys/fs/smackfs/direct. Socket Attributes +~~~~~~~~~~~~~~~~~ There are two attributes that are associated with sockets. These attributes can only be set by privileged tasks, but any task can read them for their own sockets. - SMACK64IPIN: The Smack label of the task object. A privileged + SMACK64IPIN: + The Smack label of the task object. A privileged program that will enforce policy may set this to the star label. - SMACK64IPOUT: The Smack label transmitted with outgoing packets. + SMACK64IPOUT: + The Smack label transmitted with outgoing packets. A privileged program may set this to match the label of another task with which it hopes to communicate. Smack Netlabel Exceptions +~~~~~~~~~~~~~~~~~~~~~~~~~ You will often find that your labeled application has to talk to the outside, unlabeled world. To do this there's a special file /sys/fs/smackfs/netlabel -where you can add some exceptions in the form of : -@IP1 LABEL1 or -@IP2/MASK LABEL2 +where you can add some exceptions in the form of:: + + @IP1 LABEL1 or + @IP2/MASK LABEL2 It means that your application will have unlabeled access to @IP1 if it has write access on LABEL1, and access to the subnet @IP2/MASK if it has write @@ -624,28 +713,32 @@ access on LABEL2. Entries in the /sys/fs/smackfs/netlabel file are matched by longest mask first, like in classless IPv4 routing. -A special label '@' and an option '-CIPSO' can be used there : -@ means Internet, any application with any label has access to it --CIPSO means standard CIPSO networking +A special label '@' and an option '-CIPSO' can be used there:: -If you don't know what CIPSO is and don't plan to use it, you can just do : -echo 127.0.0.1 -CIPSO > /sys/fs/smackfs/netlabel -echo 0.0.0.0/0 @ > /sys/fs/smackfs/netlabel + @ means Internet, any application with any label has access to it + -CIPSO means standard CIPSO networking + +If you don't know what CIPSO is and don't plan to use it, you can just do:: + + echo 127.0.0.1 -CIPSO > /sys/fs/smackfs/netlabel + echo 0.0.0.0/0 @ > /sys/fs/smackfs/netlabel If you use CIPSO on your 192.168.0.0/16 local network and need also unlabeled -Internet access, you can have : -echo 127.0.0.1 -CIPSO > /sys/fs/smackfs/netlabel -echo 192.168.0.0/16 -CIPSO > /sys/fs/smackfs/netlabel -echo 0.0.0.0/0 @ > /sys/fs/smackfs/netlabel +Internet access, you can have:: + echo 127.0.0.1 -CIPSO > /sys/fs/smackfs/netlabel + echo 192.168.0.0/16 -CIPSO > /sys/fs/smackfs/netlabel + echo 0.0.0.0/0 @ > /sys/fs/smackfs/netlabel Writing Applications for Smack +------------------------------ There are three sorts of applications that will run on a Smack system. How an application interacts with Smack will determine what it will have to do to work properly under Smack. Smack Ignorant Applications +--------------------------- By far the majority of applications have no reason whatever to care about the unique properties of Smack. Since invoking a program has no impact on the @@ -653,12 +746,14 @@ Smack label associated with the process the only concern likely to arise is whether the process has execute access to the program. Smack Relevant Applications +--------------------------- Some programs can be improved by teaching them about Smack, but do not make any security decisions themselves. The utility ls(1) is one example of such a program. Smack Enforcing Applications +---------------------------- These are special programs that not only know about Smack, but participate in the enforcement of system policy. In most cases these are the programs that @@ -666,15 +761,16 @@ set up user sessions. There are also network services that provide information to processes running with various labels. File System Interfaces +---------------------- Smack maintains labels on file system objects using extended attributes. The Smack label of a file, directory, or other file system object can be obtained -using getxattr(2). +using getxattr(2):: len = getxattr("/", "security.SMACK64", value, sizeof (value)); will put the Smack label of the root directory into value. A privileged -process can set the Smack label of a file system object with setxattr(2). +process can set the Smack label of a file system object with setxattr(2):: len = strlen("Rubble"); rc = setxattr("/foo", "security.SMACK64", "Rubble", len, 0); @@ -683,17 +779,18 @@ will set the Smack label of /foo to "Rubble" if the program has appropriate privilege. Socket Interfaces +----------------- The socket attributes can be read using fgetxattr(2). A privileged process can set the Smack label of outgoing packets with -fsetxattr(2). +fsetxattr(2):: len = strlen("Rubble"); rc = fsetxattr(fd, "security.SMACK64IPOUT", "Rubble", len, 0); will set the Smack label "Rubble" on packets going out from the socket if the -program has appropriate privilege. +program has appropriate privilege:: rc = fsetxattr(fd, "security.SMACK64IPIN, "*", strlen("*"), 0); @@ -701,33 +798,40 @@ will set the Smack label "*" as the object label against which incoming packets will be checked if the program has appropriate privilege. Administration +-------------- Smack supports some mount options: - smackfsdef=label: specifies the label to give files that lack + smackfsdef=label: + specifies the label to give files that lack the Smack label extended attribute. - smackfsroot=label: specifies the label to assign the root of the + smackfsroot=label: + specifies the label to assign the root of the file system if it lacks the Smack extended attribute. - smackfshat=label: specifies a label that must have read access to + smackfshat=label: + specifies a label that must have read access to all labels set on the filesystem. Not yet enforced. - smackfsfloor=label: specifies a label to which all labels set on the + smackfsfloor=label: + specifies a label to which all labels set on the filesystem must have read access. Not yet enforced. These mount options apply to all file system types. Smack auditing +-------------- If you want Smack auditing of security events, you need to set CONFIG_AUDIT in your kernel configuration. By default, all denied events will be audited. You can change this behavior by -writing a single character to the /sys/fs/smackfs/logging file : -0 : no logging -1 : log denied (default) -2 : log accepted -3 : log denied & accepted +writing a single character to the /sys/fs/smackfs/logging file:: + + 0 : no logging + 1 : log denied (default) + 2 : log accepted + 3 : log denied & accepted Events are logged as 'key=value' pairs, for each event you at least will get the subject, the object, the rights requested, the action, the kernel function @@ -735,6 +839,7 @@ that triggered the event, plus other pairs depending on the type of event audited. Bringup Mode +------------ Bringup mode provides logging features that can make application configuration and system bringup easier. Configure the kernel with diff --git a/Documentation/security/Yama.txt b/Documentation/admin-guide/LSM/Yama.rst similarity index 60% rename from Documentation/security/Yama.txt rename to Documentation/admin-guide/LSM/Yama.rst index d9ee7d7a6c7fda..13468ea696b716 100644 --- a/Documentation/security/Yama.txt +++ b/Documentation/admin-guide/LSM/Yama.rst @@ -1,13 +1,14 @@ +==== +Yama +==== + Yama is a Linux Security Module that collects system-wide DAC security protections that are not handled by the core kernel itself. This is -selectable at build-time with CONFIG_SECURITY_YAMA, and can be controlled -at run-time through sysctls in /proc/sys/kernel/yama: - -- ptrace_scope +selectable at build-time with ``CONFIG_SECURITY_YAMA``, and can be controlled +at run-time through sysctls in ``/proc/sys/kernel/yama``: -============================================================== - -ptrace_scope: +ptrace_scope +============ As Linux grows in popularity, it will become a larger target for malware. One particularly troubling weakness of the Linux process @@ -25,47 +26,49 @@ exist and remain possible if ptrace is allowed to operate as before. Since ptrace is not commonly used by non-developers and non-admins, system builders should be allowed the option to disable this debugging system. -For a solution, some applications use prctl(PR_SET_DUMPABLE, ...) to +For a solution, some applications use ``prctl(PR_SET_DUMPABLE, ...)`` to specifically disallow such ptrace attachment (e.g. ssh-agent), but many do not. A more general solution is to only allow ptrace directly from a parent to a child process (i.e. direct "gdb EXE" and "strace EXE" still -work), or with CAP_SYS_PTRACE (i.e. "gdb --pid=PID", and "strace -p PID" +work), or with ``CAP_SYS_PTRACE`` (i.e. "gdb --pid=PID", and "strace -p PID" still work as root). In mode 1, software that has defined application-specific relationships between a debugging process and its inferior (crash handlers, etc), -prctl(PR_SET_PTRACER, pid, ...) can be used. An inferior can declare which -other process (and its descendants) are allowed to call PTRACE_ATTACH +``prctl(PR_SET_PTRACER, pid, ...)`` can be used. An inferior can declare which +other process (and its descendants) are allowed to call ``PTRACE_ATTACH`` against it. Only one such declared debugging process can exists for each inferior at a time. For example, this is used by KDE, Chromium, and Firefox's crash handlers, and by Wine for allowing only Wine processes to ptrace each other. If a process wishes to entirely disable these ptrace -restrictions, it can call prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, ...) +restrictions, it can call ``prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, ...)`` so that any otherwise allowed process (even those in external pid namespaces) may attach. -The sysctl settings (writable only with CAP_SYS_PTRACE) are: +The sysctl settings (writable only with ``CAP_SYS_PTRACE``) are: -0 - classic ptrace permissions: a process can PTRACE_ATTACH to any other +0 - classic ptrace permissions: + a process can ``PTRACE_ATTACH`` to any other process running under the same uid, as long as it is dumpable (i.e. did not transition uids, start privileged, or have called - prctl(PR_SET_DUMPABLE...) already). Similarly, PTRACE_TRACEME is + ``prctl(PR_SET_DUMPABLE...)`` already). Similarly, ``PTRACE_TRACEME`` is unchanged. -1 - restricted ptrace: a process must have a predefined relationship - with the inferior it wants to call PTRACE_ATTACH on. By default, +1 - restricted ptrace: + a process must have a predefined relationship + with the inferior it wants to call ``PTRACE_ATTACH`` on. By default, this relationship is that of only its descendants when the above classic criteria is also met. To change the relationship, an - inferior can call prctl(PR_SET_PTRACER, debugger, ...) to declare - an allowed debugger PID to call PTRACE_ATTACH on the inferior. - Using PTRACE_TRACEME is unchanged. + inferior can call ``prctl(PR_SET_PTRACER, debugger, ...)`` to declare + an allowed debugger PID to call ``PTRACE_ATTACH`` on the inferior. + Using ``PTRACE_TRACEME`` is unchanged. -2 - admin-only attach: only processes with CAP_SYS_PTRACE may use ptrace - with PTRACE_ATTACH, or through children calling PTRACE_TRACEME. +2 - admin-only attach: + only processes with ``CAP_SYS_PTRACE`` may use ptrace + with ``PTRACE_ATTACH``, or through children calling ``PTRACE_TRACEME``. -3 - no attach: no processes may use ptrace with PTRACE_ATTACH nor via - PTRACE_TRACEME. Once set, this sysctl value cannot be changed. +3 - no attach: + no processes may use ptrace with ``PTRACE_ATTACH`` nor via + ``PTRACE_TRACEME``. Once set, this sysctl value cannot be changed. The original children-only logic was based on the restrictions in grsecurity. - -============================================================== diff --git a/Documentation/security/apparmor.txt b/Documentation/admin-guide/LSM/apparmor.rst similarity index 65% rename from Documentation/security/apparmor.txt rename to Documentation/admin-guide/LSM/apparmor.rst index 93c1fd7d063506..3e9734bd0e0586 100644 --- a/Documentation/security/apparmor.txt +++ b/Documentation/admin-guide/LSM/apparmor.rst @@ -1,4 +1,9 @@ ---- What is AppArmor? --- +======== +AppArmor +======== + +What is AppArmor? +================= AppArmor is MAC style security extension for the Linux kernel. It implements a task centered policy, with task "profiles" being created and loaded @@ -6,34 +11,41 @@ from user space. Tasks on the system that do not have a profile defined for them run in an unconfined state which is equivalent to standard Linux DAC permissions. ---- How to enable/disable --- +How to enable/disable +===================== + +set ``CONFIG_SECURITY_APPARMOR=y`` -set CONFIG_SECURITY_APPARMOR=y +If AppArmor should be selected as the default security module then set:: -If AppArmor should be selected as the default security module then - set CONFIG_DEFAULT_SECURITY="apparmor" - and CONFIG_SECURITY_APPARMOR_BOOTPARAM_VALUE=1 + CONFIG_DEFAULT_SECURITY="apparmor" + CONFIG_SECURITY_APPARMOR_BOOTPARAM_VALUE=1 Build the kernel If AppArmor is not the default security module it can be enabled by passing -security=apparmor on the kernel's command line. +``security=apparmor`` on the kernel's command line. If AppArmor is the default security module it can be disabled by passing -apparmor=0, security=XXXX (where XXX is valid security module), on the -kernel's command line +``apparmor=0, security=XXXX`` (where ``XXXX`` is valid security module), on the +kernel's command line. For AppArmor to enforce any restrictions beyond standard Linux DAC permissions policy must be loaded into the kernel from user space (see the Documentation and tools links). ---- Documentation --- +Documentation +============= -Documentation can be found on the wiki. +Documentation can be found on the wiki, linked below. ---- Links --- +Links +===== Mailing List - apparmor@lists.ubuntu.com + Wiki - http://apparmor.wiki.kernel.org/ + User space tools - https://launchpad.net/apparmor + Kernel module - git://git.kernel.org/pub/scm/linux/kernel/git/jj/apparmor-dev.git diff --git a/Documentation/security/LSM.txt b/Documentation/admin-guide/LSM/index.rst similarity index 62% rename from Documentation/security/LSM.txt rename to Documentation/admin-guide/LSM/index.rst index c2683f28ed367b..c980dfe9abf17a 100644 --- a/Documentation/security/LSM.txt +++ b/Documentation/admin-guide/LSM/index.rst @@ -1,12 +1,13 @@ -Linux Security Module framework -------------------------------- +=========================== +Linux Security Module Usage +=========================== The Linux Security Module (LSM) framework provides a mechanism for various security checks to be hooked by new kernel extensions. The name "module" is a bit of a misnomer since these extensions are not actually loadable kernel modules. Instead, they are selectable at build-time via CONFIG_DEFAULT_SECURITY and can be overridden at boot-time via the -"security=..." kernel command line argument, in the case where multiple +``"security=..."`` kernel command line argument, in the case where multiple LSMs were built into a given kernel. The primary users of the LSM interface are Mandatory Access Control @@ -19,23 +20,22 @@ in the core functionality of Linux itself. Without a specific LSM built into the kernel, the default LSM will be the Linux capabilities system. Most LSMs choose to extend the capabilities system, building their checks on top of the defined capability hooks. -For more details on capabilities, see capabilities(7) in the Linux +For more details on capabilities, see ``capabilities(7)`` in the Linux man-pages project. A list of the active security modules can be found by reading -/sys/kernel/security/lsm. This is a comma separated list, and +``/sys/kernel/security/lsm``. This is a comma separated list, and will always include the capability module. The list reflects the order in which checks are made. The capability module will always be first, followed by any "minor" modules (e.g. Yama) and then the one "major" module (e.g. SELinux) if there is one configured. -Based on https://lkml.org/lkml/2007/10/26/215, -a new LSM is accepted into the kernel when its intent (a description of -what it tries to protect against and in what cases one would expect to -use it) has been appropriately documented in Documentation/security/. -This allows an LSM's code to be easily compared to its goals, and so -that end users and distros can make a more informed decision about which -LSMs suit their requirements. +.. toctree:: + :maxdepth: 1 -For extensive documentation on the available LSM hook interfaces, please -see include/linux/security.h. + apparmor + LoadPin + SELinux + Smack + tomoyo + Yama diff --git a/Documentation/security/tomoyo.txt b/Documentation/admin-guide/LSM/tomoyo.rst similarity index 85% rename from Documentation/security/tomoyo.txt rename to Documentation/admin-guide/LSM/tomoyo.rst index 200a2d37cbc897..a5947218fa647f 100644 --- a/Documentation/security/tomoyo.txt +++ b/Documentation/admin-guide/LSM/tomoyo.rst @@ -1,21 +1,30 @@ ---- What is TOMOYO? --- +====== +TOMOYO +====== + +What is TOMOYO? +=============== TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel. LiveCD-based tutorials are available at + http://tomoyo.sourceforge.jp/1.7/1st-step/ubuntu10.04-live/ -http://tomoyo.sourceforge.jp/1.7/1st-step/centos5-live/ . +http://tomoyo.sourceforge.jp/1.7/1st-step/centos5-live/ + Though these tutorials use non-LSM version of TOMOYO, they are useful for you to know what TOMOYO is. ---- How to enable TOMOYO? --- +How to enable TOMOYO? +===================== -Build the kernel with CONFIG_SECURITY_TOMOYO=y and pass "security=tomoyo" on +Build the kernel with ``CONFIG_SECURITY_TOMOYO=y`` and pass ``security=tomoyo`` on kernel's command line. Please see http://tomoyo.sourceforge.jp/2.3/ for details. ---- Where is documentation? --- +Where is documentation? +======================= User <-> Kernel interface documentation is available at http://tomoyo.sourceforge.jp/2.3/policy-reference.html . @@ -42,7 +51,8 @@ History of TOMOYO? Realities of Mainlining http://sourceforge.jp/projects/tomoyo/docs/lfj2008.pdf ---- What is future plan? --- +What is future plan? +==================== We believe that inode based security and name based security are complementary and both should be used together. But unfortunately, so far, we cannot enable diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index b96e80f79e8531..b5343c5aa224ce 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -55,12 +55,6 @@ Documentation contains information about the problems, which may result by upgrading your kernel. - - The Documentation/DocBook/ subdirectory contains several guides for - kernel developers and users. These guides can be rendered in a - number of formats: PostScript (.ps), PDF, HTML, & man-pages, among others. - After installation, ``make psdocs``, ``make pdfdocs``, ``make htmldocs``, - or ``make mandocs`` will render the documentation in the requested format. - Installing the kernel source ---------------------------- diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt index c9cea2e39c2188..6b71852dadc277 100644 --- a/Documentation/admin-guide/devices.txt +++ b/Documentation/admin-guide/devices.txt @@ -369,8 +369,10 @@ 237 = /dev/loop-control Loopback control device 238 = /dev/vhost-net Host kernel accelerator for virtio net 239 = /dev/uhid User-space I/O driver support for HID subsystem + 240 = /dev/userio Serio driver testing device + 241 = /dev/vhost-vsock Host kernel driver for virtio vsock - 240-254 Reserved for local use + 242-254 Reserved for local use 255 Reserved for MISC_DYNAMIC_MINOR 11 char Raw keyboard device (Linux/SPARC only) diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index 8c60a8a32a1a1c..e14c374aaf60be 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -61,6 +61,7 @@ configure specific aspects of kernel behavior to your liking. java ras pm/index + LSM/index .. only:: subproject and html diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3650c39f396dee..9b852eb3b62038 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -649,6 +649,13 @@ /proc//coredump_filter. See also Documentation/filesystems/proc.txt. + coresight_cpu_debug.enable + [ARM,ARM64] + Format: + Enable/disable the CPU sampling based debugging. + 0: default value, disable debugging + 1: enable debugging at boot time + cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system @@ -866,6 +873,15 @@ dscc4.setup= [NET] + dt_cpu_ftrs= [PPC] + Format: {"off" | "known"} + Control how the dt_cpu_ftrs device-tree binding is + used for CPU feature discovery and setup (if it + exists). + off: Do not use it, fall back to legacy cpu table. + known: Do not pass through unknown features to guests + or userspace, only those that the kernel is aware of. + dump_apple_properties [X86] Dump name and content of EFI device properties on x86 Macs. Useful for driver authors to determine @@ -2127,6 +2143,12 @@ memmap=nn[KMG]@ss[KMG] [KNL] Force usage of a specific region of memory. Region of memory to be used is from ss to ss+nn. + If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], + which limits max address to nn[KMG]. + Multiple different regions can be specified, + comma delimited. + Example: + memmap=100M@2G,100M#3G,1G!1024G memmap=nn[KMG]#ss[KMG] [KNL,ACPI] Mark specific memory as ACPI data. @@ -2139,6 +2161,9 @@ memmap=64K$0x18690000 or memmap=0x10000$0x18690000 + Some bootloaders may need an escape character before '$', + like Grub2, otherwise '$' and the following number + will be eaten. memmap=nn[KMG]!ss[KMG] [KNL,X86] Mark specific memory as protected. @@ -3232,21 +3257,17 @@ rcutree.gp_cleanup_delay= [KNL] Set the number of jiffies to delay each step of - RCU grace-period cleanup. This only has effect - when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set. + RCU grace-period cleanup. rcutree.gp_init_delay= [KNL] Set the number of jiffies to delay each step of - RCU grace-period initialization. This only has - effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT - is set. + RCU grace-period initialization. rcutree.gp_preinit_delay= [KNL] Set the number of jiffies to delay each step of RCU grace-period pre-initialization, that is, the propagation of recent CPU-hotplug changes up - the rcu_node combining tree. This only has effect - when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set. + the rcu_node combining tree. rcutree.rcu_fanout_exact= [KNL] Disable autobalancing of the rcu_node combining @@ -3322,6 +3343,17 @@ This wake_up() will be accompanied by a WARN_ONCE() splat and an ftrace_dump(). + rcuperf.gp_async= [KNL] + Measure performance of asynchronous + grace-period primitives such as call_rcu(). + + rcuperf.gp_async_max= [KNL] + Specify the maximum number of outstanding + callbacks per writer thread. When a writer + thread exceeds this limit, it invokes the + corresponding flavor of rcu_barrier() to allow + previously posted callbacks to drain. + rcuperf.gp_exp= [KNL] Measure performance of expedited synchronous grace-period primitives. @@ -3349,17 +3381,22 @@ rcuperf.perf_runnable= [BOOT] Start rcuperf running at boot time. + rcuperf.perf_type= [KNL] + Specify the RCU implementation to test. + rcuperf.shutdown= [KNL] Shut the system down after performance tests complete. This is useful for hands-off automated testing. - rcuperf.perf_type= [KNL] - Specify the RCU implementation to test. - rcuperf.verbose= [KNL] Enable additional printk() statements. + rcuperf.writer_holdoff= [KNL] + Write-side holdoff between grace periods, + in microseconds. The default of zero says + no holdoff. + rcutorture.cbflood_inter_holdoff= [KNL] Set holdoff time (jiffies) between successive callback-flood tests. @@ -3797,6 +3834,15 @@ spia_pedr= spia_peddr= + srcutree.counter_wrap_check [KNL] + Specifies how frequently to check for + grace-period sequence counter wrap for the + srcu_data structure's ->srcu_gp_seq_needed field. + The greater the number of bits set in this kernel + parameter, the less frequently counter wrap will + be checked for. Note that the bottom two bits + are ignored. + srcutree.exp_holdoff [KNL] Specifies how many nanoseconds must elapse since the end of the last SRCU grace period for diff --git a/Documentation/conf.py b/Documentation/conf.py index bacf9d337c89a0..77d47bb1df1d5b 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -281,6 +281,7 @@ \\definecolor{NoteColor}{RGB}{204,255,255} \\definecolor{WarningColor}{RGB}{255,204,204} \\definecolor{AttentionColor}{RGB}{255,255,204} + \\definecolor{ImportantColor}{RGB}{192,255,204} \\definecolor{OtherColor}{RGB}{204,204,204} \\newlength{\\mynoticelength} \\makeatletter\\newenvironment{coloredbox}[1]{% @@ -301,7 +302,12 @@ \\ifthenelse% {\\equal{\\py@noticetype}{attention}}% {\\colorbox{AttentionColor}{\\usebox{\\@tempboxa}}}% - {\\colorbox{OtherColor}{\\usebox{\\@tempboxa}}}% + {% + \\ifthenelse% + {\\equal{\\py@noticetype}{important}}% + {\\colorbox{ImportantColor}{\\usebox{\\@tempboxa}}}% + {\\colorbox{OtherColor}{\\usebox{\\@tempboxa}}}% + }% }% }% }\\makeatother @@ -339,27 +345,42 @@ # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, # author, documentclass [howto, manual, or own class]). +# Sorted in alphabetical order latex_documents = [ - ('doc-guide/index', 'kernel-doc-guide.tex', 'Linux Kernel Documentation Guide', - 'The kernel development community', 'manual'), ('admin-guide/index', 'linux-user.tex', 'Linux Kernel User Documentation', 'The kernel development community', 'manual'), ('core-api/index', 'core-api.tex', 'The kernel core API manual', 'The kernel development community', 'manual'), - ('driver-api/index', 'driver-api.tex', 'The kernel driver API manual', + ('crypto/index', 'crypto-api.tex', 'Linux Kernel Crypto API manual', 'The kernel development community', 'manual'), - ('input/index', 'linux-input.tex', 'The Linux input driver subsystem', + ('dev-tools/index', 'dev-tools.tex', 'Development tools for the Kernel', 'The kernel development community', 'manual'), - ('kernel-documentation', 'kernel-documentation.tex', 'The Linux Kernel Documentation', + ('doc-guide/index', 'kernel-doc-guide.tex', 'Linux Kernel Documentation Guide', 'The kernel development community', 'manual'), - ('process/index', 'development-process.tex', 'Linux Kernel Development Documentation', + ('driver-api/index', 'driver-api.tex', 'The kernel driver API manual', + 'The kernel development community', 'manual'), + ('filesystems/index', 'filesystems.tex', 'Linux Filesystems API', 'The kernel development community', 'manual'), ('gpu/index', 'gpu.tex', 'Linux GPU Driver Developer\'s Guide', 'The kernel development community', 'manual'), + ('input/index', 'linux-input.tex', 'The Linux input driver subsystem', + 'The kernel development community', 'manual'), + ('kernel-hacking/index', 'kernel-hacking.tex', 'Unreliable Guide To Hacking The Linux Kernel', + 'The kernel development community', 'manual'), ('media/index', 'media.tex', 'Linux Media Subsystem Documentation', 'The kernel development community', 'manual'), + ('networking/index', 'networking.tex', 'Linux Networking Documentation', + 'The kernel development community', 'manual'), + ('process/index', 'development-process.tex', 'Linux Kernel Development Documentation', + 'The kernel development community', 'manual'), ('security/index', 'security.tex', 'The kernel security subsystem manual', 'The kernel development community', 'manual'), + ('sh/index', 'sh.tex', 'SuperH architecture implementation manual', + 'The kernel development community', 'manual'), + ('sound/index', 'sound.tex', 'Linux Sound Subsystem Documentation', + 'The kernel development community', 'manual'), + ('userspace-api/index', 'userspace-api.tex', 'The Linux kernel user-space API guide', + 'The kernel development community', 'manual'), ] # The name of an image file (relative to this directory) to place at the top of diff --git a/Documentation/core-api/assoc_array.rst b/Documentation/core-api/assoc_array.rst index d83cfff9ea43a9..8231b915c939d5 100644 --- a/Documentation/core-api/assoc_array.rst +++ b/Documentation/core-api/assoc_array.rst @@ -10,7 +10,10 @@ properties: 1. Objects are opaque pointers. The implementation does not care where they point (if anywhere) or what they point to (if anything). -.. note:: Pointers to objects _must_ be zero in the least significant bit. + + .. note:: + + Pointers to objects _must_ be zero in the least significant bit. 2. Objects do not need to contain linkage blocks for use by the array. This permits an object to be located in multiple arrays simultaneously. diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst index 55e43f1c80def8..fce929144ccdc3 100644 --- a/Documentation/core-api/atomic_ops.rst +++ b/Documentation/core-api/atomic_ops.rst @@ -303,6 +303,11 @@ defined which accomplish this:: void smp_mb__before_atomic(void); void smp_mb__after_atomic(void); +Preceding a non-value-returning read-modify-write atomic operation with +smp_mb__before_atomic() and following it with smp_mb__after_atomic() +provides the same full ordering that is provided by value-returning +read-modify-write atomic operations. + For example, smp_mb__before_atomic() can be used like so:: obj->dead = 1; diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 62abd36bfffbc1..0606be3a311181 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -19,6 +19,7 @@ Core utilities workqueue genericirq flexible-arrays + librs Interfaces for kernel debugging =============================== diff --git a/Documentation/core-api/librs.rst b/Documentation/core-api/librs.rst new file mode 100644 index 00000000000000..6010f5bc5bf91d --- /dev/null +++ b/Documentation/core-api/librs.rst @@ -0,0 +1,212 @@ +========================================== +Reed-Solomon Library Programming Interface +========================================== + +:Author: Thomas Gleixner + +Introduction +============ + +The generic Reed-Solomon Library provides encoding, decoding and error +correction functions. + +Reed-Solomon codes are used in communication and storage applications to +ensure data integrity. + +This documentation is provided for developers who want to utilize the +functions provided by the library. + +Known Bugs And Assumptions +========================== + +None. + +Usage +===== + +This chapter provides examples of how to use the library. + +Initializing +------------ + +The init function init_rs returns a pointer to an rs decoder structure, +which holds the necessary information for encoding, decoding and error +correction with the given polynomial. It either uses an existing +matching decoder or creates a new one. On creation all the lookup tables +for fast en/decoding are created. The function may take a while, so make +sure not to call it in critical code paths. + +:: + + /* the Reed Solomon control structure */ + static struct rs_control *rs_decoder; + + /* Symbolsize is 10 (bits) + * Primitive polynomial is x^10+x^3+1 + * first consecutive root is 0 + * primitive element to generate roots = 1 + * generator polynomial degree (number of roots) = 6 + */ + rs_decoder = init_rs (10, 0x409, 0, 1, 6); + + +Encoding +-------- + +The encoder calculates the Reed-Solomon code over the given data length +and stores the result in the parity buffer. Note that the parity buffer +must be initialized before calling the encoder. + +The expanded data can be inverted on the fly by providing a non-zero +inversion mask. The expanded data is XOR'ed with the mask. This is used +e.g. for FLASH ECC, where the all 0xFF is inverted to an all 0x00. The +Reed-Solomon code for all 0x00 is all 0x00. The code is inverted before +storing to FLASH so it is 0xFF too. This prevents that reading from an +erased FLASH results in ECC errors. + +The databytes are expanded to the given symbol size on the fly. There is +no support for encoding continuous bitstreams with a symbol size != 8 at +the moment. If it is necessary it should be not a big deal to implement +such functionality. + +:: + + /* Parity buffer. Size = number of roots */ + uint16_t par[6]; + /* Initialize the parity buffer */ + memset(par, 0, sizeof(par)); + /* Encode 512 byte in data8. Store parity in buffer par */ + encode_rs8 (rs_decoder, data8, 512, par, 0); + + +Decoding +-------- + +The decoder calculates the syndrome over the given data length and the +received parity symbols and corrects errors in the data. + +If a syndrome is available from a hardware decoder then the syndrome +calculation is skipped. + +The correction of the data buffer can be suppressed by providing a +correction pattern buffer and an error location buffer to the decoder. +The decoder stores the calculated error location and the correction +bitmask in the given buffers. This is useful for hardware decoders which +use a weird bit ordering scheme. + +The databytes are expanded to the given symbol size on the fly. There is +no support for decoding continuous bitstreams with a symbolsize != 8 at +the moment. If it is necessary it should be not a big deal to implement +such functionality. + +Decoding with syndrome calculation, direct data correction +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + /* Parity buffer. Size = number of roots */ + uint16_t par[6]; + uint8_t data[512]; + int numerr; + /* Receive data */ + ..... + /* Receive parity */ + ..... + /* Decode 512 byte in data8.*/ + numerr = decode_rs8 (rs_decoder, data8, par, 512, NULL, 0, NULL, 0, NULL); + + +Decoding with syndrome given by hardware decoder, direct data correction +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + /* Parity buffer. Size = number of roots */ + uint16_t par[6], syn[6]; + uint8_t data[512]; + int numerr; + /* Receive data */ + ..... + /* Receive parity */ + ..... + /* Get syndrome from hardware decoder */ + ..... + /* Decode 512 byte in data8.*/ + numerr = decode_rs8 (rs_decoder, data8, par, 512, syn, 0, NULL, 0, NULL); + + +Decoding with syndrome given by hardware decoder, no direct data correction. +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Note: It's not necessary to give data and received parity to the +decoder. + +:: + + /* Parity buffer. Size = number of roots */ + uint16_t par[6], syn[6], corr[8]; + uint8_t data[512]; + int numerr, errpos[8]; + /* Receive data */ + ..... + /* Receive parity */ + ..... + /* Get syndrome from hardware decoder */ + ..... + /* Decode 512 byte in data8.*/ + numerr = decode_rs8 (rs_decoder, NULL, NULL, 512, syn, 0, errpos, 0, corr); + for (i = 0; i < numerr; i++) { + do_error_correction_in_your_buffer(errpos[i], corr[i]); + } + + +Cleanup +------- + +The function free_rs frees the allocated resources, if the caller is +the last user of the decoder. + +:: + + /* Release resources */ + free_rs(rs_decoder); + + +Structures +========== + +This chapter contains the autogenerated documentation of the structures +which are used in the Reed-Solomon Library and are relevant for a +developer. + +.. kernel-doc:: include/linux/rslib.h + :internal: + +Public Functions Provided +========================= + +This chapter contains the autogenerated documentation of the +Reed-Solomon functions which are exported. + +.. kernel-doc:: lib/reed_solomon/reed_solomon.c + :export: + +Credits +======= + +The library code for encoding and decoding was written by Phil Karn. + +:: + + Copyright 2002, Phil Karn, KA9Q + May be used under the terms of the GNU General Public License (GPL) + + +The wrapper functions and interfaces are written by Thomas Gleixner. + +Many users have provided bugfixes, improvements and helping hands for +testing. Thanks a lot. + +The following people have contributed to this document: + +Thomas Gleixner\ tglx@linutronix.de diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt index 5ad6480e3fb963..b82b6ad4848873 100644 --- a/Documentation/crypto/asymmetric-keys.txt +++ b/Documentation/crypto/asymmetric-keys.txt @@ -265,7 +265,7 @@ mandatory: The caller passes a pointer to the following struct with all of the fields cleared, except for data, datalen and quotalen [see - Documentation/security/keys.txt]. + Documentation/security/keys/core.rst]. struct key_preparsed_payload { char *description; diff --git a/Documentation/crypto/conf.py b/Documentation/crypto/conf.py new file mode 100644 index 00000000000000..4335d251ddf339 --- /dev/null +++ b/Documentation/crypto/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = 'Linux Kernel Crypto API' + +tags.add("subproject") + +latex_documents = [ + ('index', 'crypto-api.tex', 'Linux Kernel Crypto API manual', + 'The kernel development community', 'manual'), +] diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index 07d881147ef3c1..4ac991dbddb714 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -23,6 +23,7 @@ whole; patches welcome! kmemleak kmemcheck gdb-kernel-debugging + kgdb .. only:: subproject and html diff --git a/Documentation/dev-tools/kgdb.rst b/Documentation/dev-tools/kgdb.rst new file mode 100644 index 00000000000000..75273203a35a25 --- /dev/null +++ b/Documentation/dev-tools/kgdb.rst @@ -0,0 +1,907 @@ +================================================= +Using kgdb, kdb and the kernel debugger internals +================================================= + +:Author: Jason Wessel + +Introduction +============ + +The kernel has two different debugger front ends (kdb and kgdb) which +interface to the debug core. It is possible to use either of the +debugger front ends and dynamically transition between them if you +configure the kernel properly at compile and runtime. + +Kdb is simplistic shell-style interface which you can use on a system +console with a keyboard or serial console. You can use it to inspect +memory, registers, process lists, dmesg, and even set breakpoints to +stop in a certain location. Kdb is not a source level debugger, although +you can set breakpoints and execute some basic kernel run control. Kdb +is mainly aimed at doing some analysis to aid in development or +diagnosing kernel problems. You can access some symbols by name in +kernel built-ins or in kernel modules if the code was built with +``CONFIG_KALLSYMS``. + +Kgdb is intended to be used as a source level debugger for the Linux +kernel. It is used along with gdb to debug a Linux kernel. The +expectation is that gdb can be used to "break in" to the kernel to +inspect memory, variables and look through call stack information +similar to the way an application developer would use gdb to debug an +application. It is possible to place breakpoints in kernel code and +perform some limited execution stepping. + +Two machines are required for using kgdb. One of these machines is a +development machine and the other is the target machine. The kernel to +be debugged runs on the target machine. The development machine runs an +instance of gdb against the vmlinux file which contains the symbols (not +a boot image such as bzImage, zImage, uImage...). In gdb the developer +specifies the connection parameters and connects to kgdb. The type of +connection a developer makes with gdb depends on the availability of +kgdb I/O modules compiled as built-ins or loadable kernel modules in the +test machine's kernel. + +Compiling a kernel +================== + +- In order to enable compilation of kdb, you must first enable kgdb. + +- The kgdb test compile options are described in the kgdb test suite + chapter. + +Kernel config options for kgdb +------------------------------ + +To enable ``CONFIG_KGDB`` you should look under +:menuselection:`Kernel hacking --> Kernel debugging` and select +:menuselection:`KGDB: kernel debugger`. + +While it is not a hard requirement that you have symbols in your vmlinux +file, gdb tends not to be very useful without the symbolic data, so you +will want to turn on ``CONFIG_DEBUG_INFO`` which is called +:menuselection:`Compile the kernel with debug info` in the config menu. + +It is advised, but not required, that you turn on the +``CONFIG_FRAME_POINTER`` kernel option which is called :menuselection:`Compile +the kernel with frame pointers` in the config menu. This option inserts code +to into the compiled executable which saves the frame information in +registers or on the stack at different points which allows a debugger +such as gdb to more accurately construct stack back traces while +debugging the kernel. + +If the architecture that you are using supports the kernel option +``CONFIG_STRICT_KERNEL_RWX``, you should consider turning it off. This +option will prevent the use of software breakpoints because it marks +certain regions of the kernel's memory space as read-only. If kgdb +supports it for the architecture you are using, you can use hardware +breakpoints if you desire to run with the ``CONFIG_STRICT_KERNEL_RWX`` +option turned on, else you need to turn off this option. + +Next you should choose one of more I/O drivers to interconnect debugging +host and debugged target. Early boot debugging requires a KGDB I/O +driver that supports early debugging and the driver must be built into +the kernel directly. Kgdb I/O driver configuration takes place via +kernel or module parameters which you can learn more about in the in the +section that describes the parameter kgdboc. + +Here is an example set of ``.config`` symbols to enable or disable for kgdb:: + + # CONFIG_STRICT_KERNEL_RWX is not set + CONFIG_FRAME_POINTER=y + CONFIG_KGDB=y + CONFIG_KGDB_SERIAL_CONSOLE=y + +Kernel config options for kdb +----------------------------- + +Kdb is quite a bit more complex than the simple gdbstub sitting on top +of the kernel's debug core. Kdb must implement a shell, and also adds +some helper functions in other parts of the kernel, responsible for +printing out interesting data such as what you would see if you ran +``lsmod``, or ``ps``. In order to build kdb into the kernel you follow the +same steps as you would for kgdb. + +The main config option for kdb is ``CONFIG_KGDB_KDB`` which is called +:menuselection:`KGDB_KDB: include kdb frontend for kgdb` in the config menu. +In theory you would have already also selected an I/O driver such as the +``CONFIG_KGDB_SERIAL_CONSOLE`` interface if you plan on using kdb on a +serial port, when you were configuring kgdb. + +If you want to use a PS/2-style keyboard with kdb, you would select +``CONFIG_KDB_KEYBOARD`` which is called :menuselection:`KGDB_KDB: keyboard as +input device` in the config menu. The ``CONFIG_KDB_KEYBOARD`` option is not +used for anything in the gdb interface to kgdb. The ``CONFIG_KDB_KEYBOARD`` +option only works with kdb. + +Here is an example set of ``.config`` symbols to enable/disable kdb:: + + # CONFIG_STRICT_KERNEL_RWX is not set + CONFIG_FRAME_POINTER=y + CONFIG_KGDB=y + CONFIG_KGDB_SERIAL_CONSOLE=y + CONFIG_KGDB_KDB=y + CONFIG_KDB_KEYBOARD=y + +Kernel Debugger Boot Arguments +============================== + +This section describes the various runtime kernel parameters that affect +the configuration of the kernel debugger. The following chapter covers +using kdb and kgdb as well as providing some examples of the +configuration parameters. + +Kernel parameter: kgdboc +------------------------ + +The kgdboc driver was originally an abbreviation meant to stand for +"kgdb over console". Today it is the primary mechanism to configure how +to communicate from gdb to kgdb as well as the devices you want to use +to interact with the kdb shell. + +For kgdb/gdb, kgdboc is designed to work with a single serial port. It +is intended to cover the circumstance where you want to use a serial +console as your primary console as well as using it to perform kernel +debugging. It is also possible to use kgdb on a serial port which is not +designated as a system console. Kgdboc may be configured as a kernel +built-in or a kernel loadable module. You can only make use of +``kgdbwait`` and early debugging if you build kgdboc into the kernel as +a built-in. + +Optionally you can elect to activate kms (Kernel Mode Setting) +integration. When you use kms with kgdboc and you have a video driver +that has atomic mode setting hooks, it is possible to enter the debugger +on the graphics console. When the kernel execution is resumed, the +previous graphics mode will be restored. This integration can serve as a +useful tool to aid in diagnosing crashes or doing analysis of memory +with kdb while allowing the full graphics console applications to run. + +kgdboc arguments +~~~~~~~~~~~~~~~~ + +Usage:: + + kgdboc=[kms][[,]kbd][[,]serial_device][,baud] + +The order listed above must be observed if you use any of the optional +configurations together. + +Abbreviations: + +- kms = Kernel Mode Setting + +- kbd = Keyboard + +You can configure kgdboc to use the keyboard, and/or a serial device +depending on if you are using kdb and/or kgdb, in one of the following +scenarios. The order listed above must be observed if you use any of the +optional configurations together. Using kms + only gdb is generally not +a useful combination. + +Using loadable module or built-in +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +1. As a kernel built-in: + + Use the kernel boot argument:: + + kgdboc=,[baud] + +2. As a kernel loadable module: + + Use the command:: + + modprobe kgdboc kgdboc=,[baud] + + Here are two examples of how you might format the kgdboc string. The + first is for an x86 target using the first serial port. The second + example is for the ARM Versatile AB using the second serial port. + + 1. ``kgdboc=ttyS0,115200`` + + 2. ``kgdboc=ttyAMA1,115200`` + +Configure kgdboc at runtime with sysfs +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +At run time you can enable or disable kgdboc by echoing a parameters +into the sysfs. Here are two examples: + +1. Enable kgdboc on ttyS0:: + + echo ttyS0 > /sys/module/kgdboc/parameters/kgdboc + +2. Disable kgdboc:: + + echo "" > /sys/module/kgdboc/parameters/kgdboc + +.. note:: + + You do not need to specify the baud if you are configuring the + console on tty which is already configured or open. + +More examples +^^^^^^^^^^^^^ + +You can configure kgdboc to use the keyboard, and/or a serial device +depending on if you are using kdb and/or kgdb, in one of the following +scenarios. + +1. kdb and kgdb over only a serial port:: + + kgdboc=[,baud] + + Example:: + + kgdboc=ttyS0,115200 + +2. kdb and kgdb with keyboard and a serial port:: + + kgdboc=kbd,[,baud] + + Example:: + + kgdboc=kbd,ttyS0,115200 + +3. kdb with a keyboard:: + + kgdboc=kbd + +4. kdb with kernel mode setting:: + + kgdboc=kms,kbd + +5. kdb with kernel mode setting and kgdb over a serial port:: + + kgdboc=kms,kbd,ttyS0,115200 + +.. note:: + + Kgdboc does not support interrupting the target via the gdb remote + protocol. You must manually send a :kbd:`SysRq-G` unless you have a proxy + that splits console output to a terminal program. A console proxy has a + separate TCP port for the debugger and a separate TCP port for the + "human" console. The proxy can take care of sending the :kbd:`SysRq-G` + for you. + +When using kgdboc with no debugger proxy, you can end up connecting the +debugger at one of two entry points. If an exception occurs after you +have loaded kgdboc, a message should print on the console stating it is +waiting for the debugger. In this case you disconnect your terminal +program and then connect the debugger in its place. If you want to +interrupt the target system and forcibly enter a debug session you have +to issue a :kbd:`Sysrq` sequence and then type the letter :kbd:`g`. Then you +disconnect the terminal session and connect gdb. Your options if you +don't like this are to hack gdb to send the :kbd:`SysRq-G` for you as well as +on the initial connect, or to use a debugger proxy that allows an +unmodified gdb to do the debugging. + +Kernel parameter: ``kgdbwait`` +------------------------------ + +The Kernel command line option ``kgdbwait`` makes kgdb wait for a +debugger connection during booting of a kernel. You can only use this +option if you compiled a kgdb I/O driver into the kernel and you +specified the I/O driver configuration as a kernel command line option. +The kgdbwait parameter should always follow the configuration parameter +for the kgdb I/O driver in the kernel command line else the I/O driver +will not be configured prior to asking the kernel to use it to wait. + +The kernel will stop and wait as early as the I/O driver and +architecture allows when you use this option. If you build the kgdb I/O +driver as a loadable kernel module kgdbwait will not do anything. + +Kernel parameter: ``kgdbcon`` +----------------------------- + +The ``kgdbcon`` feature allows you to see :c:func:`printk` messages inside gdb +while gdb is connected to the kernel. Kdb does not make use of the kgdbcon +feature. + +Kgdb supports using the gdb serial protocol to send console messages to +the debugger when the debugger is connected and running. There are two +ways to activate this feature. + +1. Activate with the kernel command line option:: + + kgdbcon + +2. Use sysfs before configuring an I/O driver:: + + echo 1 > /sys/module/kgdb/parameters/kgdb_use_con + +.. note:: + + If you do this after you configure the kgdb I/O driver, the + setting will not take effect until the next point the I/O is + reconfigured. + +.. important:: + + You cannot use kgdboc + kgdbcon on a tty that is an + active system console. An example of incorrect usage is:: + + console=ttyS0,115200 kgdboc=ttyS0 kgdbcon + +It is possible to use this option with kgdboc on a tty that is not a +system console. + +Run time parameter: ``kgdbreboot`` +---------------------------------- + +The kgdbreboot feature allows you to change how the debugger deals with +the reboot notification. You have 3 choices for the behavior. The +default behavior is always set to 0. + +.. tabularcolumns:: |p{0.4cm}|p{11.5cm}|p{5.6cm}| + +.. flat-table:: + :widths: 1 10 8 + + * - 1 + - ``echo -1 > /sys/module/debug_core/parameters/kgdbreboot`` + - Ignore the reboot notification entirely. + + * - 2 + - ``echo 0 > /sys/module/debug_core/parameters/kgdbreboot`` + - Send the detach message to any attached debugger client. + + * - 3 + - ``echo 1 > /sys/module/debug_core/parameters/kgdbreboot`` + - Enter the debugger on reboot notify. + +Using kdb +========= + +Quick start for kdb on a serial port +------------------------------------ + +This is a quick example of how to use kdb. + +1. Configure kgdboc at boot using kernel parameters:: + + console=ttyS0,115200 kgdboc=ttyS0,115200 + + OR + + Configure kgdboc after the kernel has booted; assuming you are using + a serial port console:: + + echo ttyS0 > /sys/module/kgdboc/parameters/kgdboc + +2. Enter the kernel debugger manually or by waiting for an oops or + fault. There are several ways you can enter the kernel debugger + manually; all involve using the :kbd:`SysRq-G`, which means you must have + enabled ``CONFIG_MAGIC_SysRq=y`` in your kernel config. + + - When logged in as root or with a super user session you can run:: + + echo g > /proc/sysrq-trigger + + - Example using minicom 2.2 + + Press: :kbd:`CTRL-A` :kbd:`f` :kbd:`g` + + - When you have telneted to a terminal server that supports sending + a remote break + + Press: :kbd:`CTRL-]` + + Type in: ``send break`` + + Press: :kbd:`Enter` :kbd:`g` + +3. From the kdb prompt you can run the ``help`` command to see a complete + list of the commands that are available. + + Some useful commands in kdb include: + + =========== ================================================================= + ``lsmod`` Shows where kernel modules are loaded + ``ps`` Displays only the active processes + ``ps A`` Shows all the processes + ``summary`` Shows kernel version info and memory usage + ``bt`` Get a backtrace of the current process using :c:func:`dump_stack` + ``dmesg`` View the kernel syslog buffer + ``go`` Continue the system + =========== ================================================================= + +4. When you are done using kdb you need to consider rebooting the system + or using the ``go`` command to resuming normal kernel execution. If you + have paused the kernel for a lengthy period of time, applications + that rely on timely networking or anything to do with real wall clock + time could be adversely affected, so you should take this into + consideration when using the kernel debugger. + +Quick start for kdb using a keyboard connected console +------------------------------------------------------ + +This is a quick example of how to use kdb with a keyboard. + +1. Configure kgdboc at boot using kernel parameters:: + + kgdboc=kbd + + OR + + Configure kgdboc after the kernel has booted:: + + echo kbd > /sys/module/kgdboc/parameters/kgdboc + +2. Enter the kernel debugger manually or by waiting for an oops or + fault. There are several ways you can enter the kernel debugger + manually; all involve using the :kbd:`SysRq-G`, which means you must have + enabled ``CONFIG_MAGIC_SysRq=y`` in your kernel config. + + - When logged in as root or with a super user session you can run:: + + echo g > /proc/sysrq-trigger + + - Example using a laptop keyboard: + + Press and hold down: :kbd:`Alt` + + Press and hold down: :kbd:`Fn` + + Press and release the key with the label: :kbd:`SysRq` + + Release: :kbd:`Fn` + + Press and release: :kbd:`g` + + Release: :kbd:`Alt` + + - Example using a PS/2 101-key keyboard + + Press and hold down: :kbd:`Alt` + + Press and release the key with the label: :kbd:`SysRq` + + Press and release: :kbd:`g` + + Release: :kbd:`Alt` + +3. Now type in a kdb command such as ``help``, ``dmesg``, ``bt`` or ``go`` to + continue kernel execution. + +Using kgdb / gdb +================ + +In order to use kgdb you must activate it by passing configuration +information to one of the kgdb I/O drivers. If you do not pass any +configuration information kgdb will not do anything at all. Kgdb will +only actively hook up to the kernel trap hooks if a kgdb I/O driver is +loaded and configured. If you unconfigure a kgdb I/O driver, kgdb will +unregister all the kernel hook points. + +All kgdb I/O drivers can be reconfigured at run time, if +``CONFIG_SYSFS`` and ``CONFIG_MODULES`` are enabled, by echo'ing a new +config string to ``/sys/module//parameter/

    `` is replaced by the contents of the ``DOC:`` -section titled ``
    `` from ````. Spaces are allowed in -``
    ``; do not quote the ``
    ``. - -``!C`` is replaced by nothing, but makes the tools check that all DOC: -sections and documented functions, symbols, etc. are used. This makes sense to -use when you use ``!F`` or ``!P`` only and want to verify that all documentation -is included. diff --git a/Documentation/doc-guide/index.rst b/Documentation/doc-guide/index.rst index 6fff4024606e33..a7f95d7d3a6355 100644 --- a/Documentation/doc-guide/index.rst +++ b/Documentation/doc-guide/index.rst @@ -10,7 +10,6 @@ How to write kernel documentation sphinx.rst kernel-doc.rst parse-headers.rst - docbook.rst .. only:: subproject and html diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst index b32e4813ff6fdd..b24854b5d6beb2 100644 --- a/Documentation/doc-guide/kernel-doc.rst +++ b/Documentation/doc-guide/kernel-doc.rst @@ -149,6 +149,16 @@ Domain`_ references. ``%CONST`` Name of a constant. (No cross-referencing, just formatting.) +````literal```` + A literal block that should be handled as-is. The output will use a + ``monospaced font``. + + Useful if you need to use special characters that would otherwise have some + meaning either by kernel-doc script of by reStructuredText. + + This is particularly useful if you need to use things like ``%ph`` inside + a function description. + ``$ENVVAR`` Name of an environment variable. (No cross-referencing, just formatting.) diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst index 731334de3efdd5..84e8e8a9cbdb04 100644 --- a/Documentation/doc-guide/sphinx.rst +++ b/Documentation/doc-guide/sphinx.rst @@ -15,11 +15,6 @@ are used to describe the functions and types and design of the code. The kernel-doc comments have some special structure and formatting, but beyond that they are also treated as reStructuredText. -There is also the deprecated DocBook toolchain to generate documentation from -DocBook XML template files under ``Documentation/DocBook``. The DocBook files -are to be converted to reStructuredText, and the toolchain is slated to be -removed. - Finally, there are thousands of plain text documentation files scattered around ``Documentation``. Some of these will likely be converted to reStructuredText over time, but the bulk of them will remain in plain text. diff --git a/Documentation/dontdiff b/Documentation/dontdiff index 77b92221f95127..e10a484629e4e0 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -207,6 +207,8 @@ r200_reg_safe.h r300_reg_safe.h r420_reg_safe.h r600_reg_safe.h +randomize_layout_hash.h +randomize_layout_seed.h recordmcount relocs rlim_names.h diff --git a/Documentation/driver-api/i2c.rst b/Documentation/driver-api/i2c.rst index f3939f7852bd59..c215503801f0fd 100644 --- a/Documentation/driver-api/i2c.rst +++ b/Documentation/driver-api/i2c.rst @@ -42,5 +42,8 @@ i2c_adapter devices which don't support those I2C operations. .. kernel-doc:: drivers/i2c/i2c-boardinfo.c :functions: i2c_register_board_info -.. kernel-doc:: drivers/i2c/i2c-core.c +.. kernel-doc:: drivers/i2c/i2c-core-base.c + :export: + +.. kernel-doc:: drivers/i2c/i2c-core-smbus.c :export: diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 8058a87c1c74e1..3cf1acebc4eeb4 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -32,7 +32,13 @@ available subsections can be seen below. i2c hsi edac + scsi + libata + mtdnand miscellaneous + w1 + rapidio + s390-drivers vme 80211/index uio-howto diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst new file mode 100644 index 00000000000000..4adc056f763565 --- /dev/null +++ b/Documentation/driver-api/libata.rst @@ -0,0 +1,1031 @@ +======================== +libATA Developer's Guide +======================== + +:Author: Jeff Garzik + +Introduction +============ + +libATA is a library used inside the Linux kernel to support ATA host +controllers and devices. libATA provides an ATA driver API, class +transports for ATA and ATAPI devices, and SCSI<->ATA translation for ATA +devices according to the T10 SAT specification. + +This Guide documents the libATA driver API, library functions, library +internals, and a couple sample ATA low-level drivers. + +libata Driver API +================= + +:c:type:`struct ata_port_operations ` +is defined for every low-level libata +hardware driver, and it controls how the low-level driver interfaces +with the ATA and SCSI layers. + +FIS-based drivers will hook into the system with ``->qc_prep()`` and +``->qc_issue()`` high-level hooks. Hardware which behaves in a manner +similar to PCI IDE hardware may utilize several generic helpers, +defining at a bare minimum the bus I/O addresses of the ATA shadow +register blocks. + +:c:type:`struct ata_port_operations ` +---------------------------------------------------------- + +Disable ATA port +~~~~~~~~~~~~~~~~ + +:: + + void (*port_disable) (struct ata_port *); + + +Called from :c:func:`ata_bus_probe` error path, as well as when unregistering +from the SCSI module (rmmod, hot unplug). This function should do +whatever needs to be done to take the port out of use. In most cases, +:c:func:`ata_port_disable` can be used as this hook. + +Called from :c:func:`ata_bus_probe` on a failed probe. Called from +:c:func:`ata_scsi_release`. + +Post-IDENTIFY device configuration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*dev_config) (struct ata_port *, struct ata_device *); + + +Called after IDENTIFY [PACKET] DEVICE is issued to each device found. +Typically used to apply device-specific fixups prior to issue of SET +FEATURES - XFER MODE, and prior to operation. + +This entry may be specified as NULL in ata_port_operations. + +Set PIO/DMA mode +~~~~~~~~~~~~~~~~ + +:: + + void (*set_piomode) (struct ata_port *, struct ata_device *); + void (*set_dmamode) (struct ata_port *, struct ata_device *); + void (*post_set_mode) (struct ata_port *); + unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned int); + + +Hooks called prior to the issue of SET FEATURES - XFER MODE command. The +optional ``->mode_filter()`` hook is called when libata has built a mask of +the possible modes. This is passed to the ``->mode_filter()`` function +which should return a mask of valid modes after filtering those +unsuitable due to hardware limits. It is not valid to use this interface +to add modes. + +``dev->pio_mode`` and ``dev->dma_mode`` are guaranteed to be valid when +``->set_piomode()`` and when ``->set_dmamode()`` is called. The timings for +any other drive sharing the cable will also be valid at this point. That +is the library records the decisions for the modes of each drive on a +channel before it attempts to set any of them. + +``->post_set_mode()`` is called unconditionally, after the SET FEATURES - +XFER MODE command completes successfully. + +``->set_piomode()`` is always called (if present), but ``->set_dma_mode()`` +is only called if DMA is possible. + +Taskfile read/write +~~~~~~~~~~~~~~~~~~~ + +:: + + void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf); + void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf); + + +``->tf_load()`` is called to load the given taskfile into hardware +registers / DMA buffers. ``->tf_read()`` is called to read the hardware +registers / DMA buffers, to obtain the current set of taskfile register +values. Most drivers for taskfile-based hardware (PIO or MMIO) use +:c:func:`ata_sff_tf_load` and :c:func:`ata_sff_tf_read` for these hooks. + +PIO data read/write +~~~~~~~~~~~~~~~~~~~ + +:: + + void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); + + +All bmdma-style drivers must implement this hook. This is the low-level +operation that actually copies the data bytes during a PIO data +transfer. Typically the driver will choose one of +:c:func:`ata_sff_data_xfer_noirq`, :c:func:`ata_sff_data_xfer`, or +:c:func:`ata_sff_data_xfer32`. + +ATA command execute +~~~~~~~~~~~~~~~~~~~ + +:: + + void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf); + + +causes an ATA command, previously loaded with ``->tf_load()``, to be +initiated in hardware. Most drivers for taskfile-based hardware use +:c:func:`ata_sff_exec_command` for this hook. + +Per-cmd ATAPI DMA capabilities filter +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + int (*check_atapi_dma) (struct ata_queued_cmd *qc); + + +Allow low-level driver to filter ATA PACKET commands, returning a status +indicating whether or not it is OK to use DMA for the supplied PACKET +command. + +This hook may be specified as NULL, in which case libata will assume +that atapi dma can be supported. + +Read specific ATA shadow registers +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + u8 (*sff_check_status)(struct ata_port *ap); + u8 (*sff_check_altstatus)(struct ata_port *ap); + + +Reads the Status/AltStatus ATA shadow register from hardware. On some +hardware, reading the Status register has the side effect of clearing +the interrupt condition. Most drivers for taskfile-based hardware use +:c:func:`ata_sff_check_status` for this hook. + +Write specific ATA shadow register +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*sff_set_devctl)(struct ata_port *ap, u8 ctl); + + +Write the device control ATA shadow register to the hardware. Most +drivers don't need to define this. + +Select ATA device on bus +~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*sff_dev_select)(struct ata_port *ap, unsigned int device); + + +Issues the low-level hardware command(s) that causes one of N hardware +devices to be considered 'selected' (active and available for use) on +the ATA bus. This generally has no meaning on FIS-based devices. + +Most drivers for taskfile-based hardware use :c:func:`ata_sff_dev_select` for +this hook. + +Private tuning method +~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*set_mode) (struct ata_port *ap); + + +By default libata performs drive and controller tuning in accordance +with the ATA timing rules and also applies blacklists and cable limits. +Some controllers need special handling and have custom tuning rules, +typically raid controllers that use ATA commands but do not actually do +drive timing. + + **Warning** + + This hook should not be used to replace the standard controller + tuning logic when a controller has quirks. Replacing the default + tuning logic in that case would bypass handling for drive and bridge + quirks that may be important to data reliability. If a controller + needs to filter the mode selection it should use the mode_filter + hook instead. + +Control PCI IDE BMDMA engine +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*bmdma_setup) (struct ata_queued_cmd *qc); + void (*bmdma_start) (struct ata_queued_cmd *qc); + void (*bmdma_stop) (struct ata_port *ap); + u8 (*bmdma_status) (struct ata_port *ap); + + +When setting up an IDE BMDMA transaction, these hooks arm +(``->bmdma_setup``), fire (``->bmdma_start``), and halt (``->bmdma_stop``) the +hardware's DMA engine. ``->bmdma_status`` is used to read the standard PCI +IDE DMA Status register. + +These hooks are typically either no-ops, or simply not implemented, in +FIS-based drivers. + +Most legacy IDE drivers use :c:func:`ata_bmdma_setup` for the +:c:func:`bmdma_setup` hook. :c:func:`ata_bmdma_setup` will write the pointer +to the PRD table to the IDE PRD Table Address register, enable DMA in the DMA +Command register, and call :c:func:`exec_command` to begin the transfer. + +Most legacy IDE drivers use :c:func:`ata_bmdma_start` for the +:c:func:`bmdma_start` hook. :c:func:`ata_bmdma_start` will write the +ATA_DMA_START flag to the DMA Command register. + +Many legacy IDE drivers use :c:func:`ata_bmdma_stop` for the +:c:func:`bmdma_stop` hook. :c:func:`ata_bmdma_stop` clears the ATA_DMA_START +flag in the DMA command register. + +Many legacy IDE drivers use :c:func:`ata_bmdma_status` as the +:c:func:`bmdma_status` hook. + +High-level taskfile hooks +~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*qc_prep) (struct ata_queued_cmd *qc); + int (*qc_issue) (struct ata_queued_cmd *qc); + + +Higher-level hooks, these two hooks can potentially supercede several of +the above taskfile/DMA engine hooks. ``->qc_prep`` is called after the +buffers have been DMA-mapped, and is typically used to populate the +hardware's DMA scatter-gather table. Most drivers use the standard +:c:func:`ata_qc_prep` helper function, but more advanced drivers roll their +own. + +``->qc_issue`` is used to make a command active, once the hardware and S/G +tables have been prepared. IDE BMDMA drivers use the helper function +:c:func:`ata_qc_issue_prot` for taskfile protocol-based dispatch. More +advanced drivers implement their own ``->qc_issue``. + +:c:func:`ata_qc_issue_prot` calls ``->tf_load()``, ``->bmdma_setup()``, and +``->bmdma_start()`` as necessary to initiate a transfer. + +Exception and probe handling (EH) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + void (*eng_timeout) (struct ata_port *ap); + void (*phy_reset) (struct ata_port *ap); + + +Deprecated. Use ``->error_handler()`` instead. + +:: + + void (*freeze) (struct ata_port *ap); + void (*thaw) (struct ata_port *ap); + + +:c:func:`ata_port_freeze` is called when HSM violations or some other +condition disrupts normal operation of the port. A frozen port is not +allowed to perform any operation until the port is thawed, which usually +follows a successful reset. + +The optional ``->freeze()`` callback can be used for freezing the port +hardware-wise (e.g. mask interrupt and stop DMA engine). If a port +cannot be frozen hardware-wise, the interrupt handler must ack and clear +interrupts unconditionally while the port is frozen. + +The optional ``->thaw()`` callback is called to perform the opposite of +``->freeze()``: prepare the port for normal operation once again. Unmask +interrupts, start DMA engine, etc. + +:: + + void (*error_handler) (struct ata_port *ap); + + +``->error_handler()`` is a driver's hook into probe, hotplug, and recovery +and other exceptional conditions. The primary responsibility of an +implementation is to call :c:func:`ata_do_eh` or :c:func:`ata_bmdma_drive_eh` +with a set of EH hooks as arguments: + +'prereset' hook (may be NULL) is called during an EH reset, before any +other actions are taken. + +'postreset' hook (may be NULL) is called after the EH reset is +performed. Based on existing conditions, severity of the problem, and +hardware capabilities, + +Either 'softreset' (may be NULL) or 'hardreset' (may be NULL) will be +called to perform the low-level EH reset. + +:: + + void (*post_internal_cmd) (struct ata_queued_cmd *qc); + + +Perform any hardware-specific actions necessary to finish processing +after executing a probe-time or EH-time command via +:c:func:`ata_exec_internal`. + +Hardware interrupt handling +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +:: + + irqreturn_t (*irq_handler)(int, void *, struct pt_regs *); + void (*irq_clear) (struct ata_port *); + + +``->irq_handler`` is the interrupt handling routine registered with the +system, by libata. ``->irq_clear`` is called during probe just before the +interrupt handler is registered, to be sure hardware is quiet. + +The second argument, dev_instance, should be cast to a pointer to +:c:type:`struct ata_host_set `. + +Most legacy IDE drivers use :c:func:`ata_sff_interrupt` for the irq_handler +hook, which scans all ports in the host_set, determines which queued +command was active (if any), and calls ata_sff_host_intr(ap,qc). + +Most legacy IDE drivers use :c:func:`ata_sff_irq_clear` for the +:c:func:`irq_clear` hook, which simply clears the interrupt and error flags +in the DMA status register. + +SATA phy read/write +~~~~~~~~~~~~~~~~~~~ + +:: + + int (*scr_read) (struct ata_port *ap, unsigned int sc_reg, + u32 *val); + int (*scr_write) (struct ata_port *ap, unsigned int sc_reg, + u32 val); + + +Read and write standard SATA phy registers. Currently only used if +``->phy_reset`` hook called the :c:func:`sata_phy_reset` helper function. +sc_reg is one of SCR_STATUS, SCR_CONTROL, SCR_ERROR, or SCR_ACTIVE. + +Init and shutdown +~~~~~~~~~~~~~~~~~ + +:: + + int (*port_start) (struct ata_port *ap); + void (*port_stop) (struct ata_port *ap); + void (*host_stop) (struct ata_host_set *host_set); + + +``->port_start()`` is called just after the data structures for each port +are initialized. Typically this is used to alloc per-port DMA buffers / +tables / rings, enable DMA engines, and similar tasks. Some drivers also +use this entry point as a chance to allocate driver-private memory for +``ap->private_data``. + +Many drivers use :c:func:`ata_port_start` as this hook or call it from their +own :c:func:`port_start` hooks. :c:func:`ata_port_start` allocates space for +a legacy IDE PRD table and returns. + +``->port_stop()`` is called after ``->host_stop()``. Its sole function is to +release DMA/memory resources, now that they are no longer actively being +used. Many drivers also free driver-private data from port at this time. + +``->host_stop()`` is called after all ``->port_stop()`` calls have completed. +The hook must finalize hardware shutdown, release DMA and other +resources, etc. This hook may be specified as NULL, in which case it is +not called. + +Error handling +============== + +This chapter describes how errors are handled under libata. Readers are +advised to read SCSI EH (Documentation/scsi/scsi_eh.txt) and ATA +exceptions doc first. + +Origins of commands +------------------- + +In libata, a command is represented with +:c:type:`struct ata_queued_cmd ` or qc. +qc's are preallocated during port initialization and repetitively used +for command executions. Currently only one qc is allocated per port but +yet-to-be-merged NCQ branch allocates one for each tag and maps each qc +to NCQ tag 1-to-1. + +libata commands can originate from two sources - libata itself and SCSI +midlayer. libata internal commands are used for initialization and error +handling. All normal blk requests and commands for SCSI emulation are +passed as SCSI commands through queuecommand callback of SCSI host +template. + +How commands are issued +----------------------- + +Internal commands + First, qc is allocated and initialized using :c:func:`ata_qc_new_init`. + Although :c:func:`ata_qc_new_init` doesn't implement any wait or retry + mechanism when qc is not available, internal commands are currently + issued only during initialization and error recovery, so no other + command is active and allocation is guaranteed to succeed. + + Once allocated qc's taskfile is initialized for the command to be + executed. qc currently has two mechanisms to notify completion. One + is via ``qc->complete_fn()`` callback and the other is completion + ``qc->waiting``. ``qc->complete_fn()`` callback is the asynchronous path + used by normal SCSI translated commands and ``qc->waiting`` is the + synchronous (issuer sleeps in process context) path used by internal + commands. + + Once initialization is complete, host_set lock is acquired and the + qc is issued. + +SCSI commands + All libata drivers use :c:func:`ata_scsi_queuecmd` as + ``hostt->queuecommand`` callback. scmds can either be simulated or + translated. No qc is involved in processing a simulated scmd. The + result is computed right away and the scmd is completed. + + For a translated scmd, :c:func:`ata_qc_new_init` is invoked to allocate a + qc and the scmd is translated into the qc. SCSI midlayer's + completion notification function pointer is stored into + ``qc->scsidone``. + + ``qc->complete_fn()`` callback is used for completion notification. ATA + commands use :c:func:`ata_scsi_qc_complete` while ATAPI commands use + :c:func:`atapi_qc_complete`. Both functions end up calling ``qc->scsidone`` + to notify upper layer when the qc is finished. After translation is + completed, the qc is issued with :c:func:`ata_qc_issue`. + + Note that SCSI midlayer invokes hostt->queuecommand while holding + host_set lock, so all above occur while holding host_set lock. + +How commands are processed +-------------------------- + +Depending on which protocol and which controller are used, commands are +processed differently. For the purpose of discussion, a controller which +uses taskfile interface and all standard callbacks is assumed. + +Currently 6 ATA command protocols are used. They can be sorted into the +following four categories according to how they are processed. + +ATA NO DATA or DMA + ATA_PROT_NODATA and ATA_PROT_DMA fall into this category. These + types of commands don't require any software intervention once + issued. Device will raise interrupt on completion. + +ATA PIO + ATA_PROT_PIO is in this category. libata currently implements PIO + with polling. ATA_NIEN bit is set to turn off interrupt and + pio_task on ata_wq performs polling and IO. + +ATAPI NODATA or DMA + ATA_PROT_ATAPI_NODATA and ATA_PROT_ATAPI_DMA are in this + category. packet_task is used to poll BSY bit after issuing PACKET + command. Once BSY is turned off by the device, packet_task + transfers CDB and hands off processing to interrupt handler. + +ATAPI PIO + ATA_PROT_ATAPI is in this category. ATA_NIEN bit is set and, as + in ATAPI NODATA or DMA, packet_task submits cdb. However, after + submitting cdb, further processing (data transfer) is handed off to + pio_task. + +How commands are completed +-------------------------- + +Once issued, all qc's are either completed with :c:func:`ata_qc_complete` or +time out. For commands which are handled by interrupts, +:c:func:`ata_host_intr` invokes :c:func:`ata_qc_complete`, and, for PIO tasks, +pio_task invokes :c:func:`ata_qc_complete`. In error cases, packet_task may +also complete commands. + +:c:func:`ata_qc_complete` does the following. + +1. DMA memory is unmapped. + +2. ATA_QCFLAG_ACTIVE is cleared from qc->flags. + +3. :c:func:`qc->complete_fn` callback is invoked. If the return value of the + callback is not zero. Completion is short circuited and + :c:func:`ata_qc_complete` returns. + +4. :c:func:`__ata_qc_complete` is called, which does + + 1. ``qc->flags`` is cleared to zero. + + 2. ``ap->active_tag`` and ``qc->tag`` are poisoned. + + 3. ``qc->waiting`` is cleared & completed (in that order). + + 4. qc is deallocated by clearing appropriate bit in ``ap->qactive``. + +So, it basically notifies upper layer and deallocates qc. One exception +is short-circuit path in #3 which is used by :c:func:`atapi_qc_complete`. + +For all non-ATAPI commands, whether it fails or not, almost the same +code path is taken and very little error handling takes place. A qc is +completed with success status if it succeeded, with failed status +otherwise. + +However, failed ATAPI commands require more handling as REQUEST SENSE is +needed to acquire sense data. If an ATAPI command fails, +:c:func:`ata_qc_complete` is invoked with error status, which in turn invokes +:c:func:`atapi_qc_complete` via ``qc->complete_fn()`` callback. + +This makes :c:func:`atapi_qc_complete` set ``scmd->result`` to +SAM_STAT_CHECK_CONDITION, complete the scmd and return 1. As the +sense data is empty but ``scmd->result`` is CHECK CONDITION, SCSI midlayer +will invoke EH for the scmd, and returning 1 makes :c:func:`ata_qc_complete` +to return without deallocating the qc. This leads us to +:c:func:`ata_scsi_error` with partially completed qc. + +:c:func:`ata_scsi_error` +------------------------ + +:c:func:`ata_scsi_error` is the current ``transportt->eh_strategy_handler()`` +for libata. As discussed above, this will be entered in two cases - +timeout and ATAPI error completion. This function calls low level libata +driver's :c:func:`eng_timeout` callback, the standard callback for which is +:c:func:`ata_eng_timeout`. It checks if a qc is active and calls +:c:func:`ata_qc_timeout` on the qc if so. Actual error handling occurs in +:c:func:`ata_qc_timeout`. + +If EH is invoked for timeout, :c:func:`ata_qc_timeout` stops BMDMA and +completes the qc. Note that as we're currently in EH, we cannot call +scsi_done. As described in SCSI EH doc, a recovered scmd should be +either retried with :c:func:`scsi_queue_insert` or finished with +:c:func:`scsi_finish_command`. Here, we override ``qc->scsidone`` with +:c:func:`scsi_finish_command` and calls :c:func:`ata_qc_complete`. + +If EH is invoked due to a failed ATAPI qc, the qc here is completed but +not deallocated. The purpose of this half-completion is to use the qc as +place holder to make EH code reach this place. This is a bit hackish, +but it works. + +Once control reaches here, the qc is deallocated by invoking +:c:func:`__ata_qc_complete` explicitly. Then, internal qc for REQUEST SENSE +is issued. Once sense data is acquired, scmd is finished by directly +invoking :c:func:`scsi_finish_command` on the scmd. Note that as we already +have completed and deallocated the qc which was associated with the +scmd, we don't need to/cannot call :c:func:`ata_qc_complete` again. + +Problems with the current EH +---------------------------- + +- Error representation is too crude. Currently any and all error + conditions are represented with ATA STATUS and ERROR registers. + Errors which aren't ATA device errors are treated as ATA device + errors by setting ATA_ERR bit. Better error descriptor which can + properly represent ATA and other errors/exceptions is needed. + +- When handling timeouts, no action is taken to make device forget + about the timed out command and ready for new commands. + +- EH handling via :c:func:`ata_scsi_error` is not properly protected from + usual command processing. On EH entrance, the device is not in + quiescent state. Timed out commands may succeed or fail any time. + pio_task and atapi_task may still be running. + +- Too weak error recovery. Devices / controllers causing HSM mismatch + errors and other errors quite often require reset to return to known + state. Also, advanced error handling is necessary to support features + like NCQ and hotplug. + +- ATA errors are directly handled in the interrupt handler and PIO + errors in pio_task. This is problematic for advanced error handling + for the following reasons. + + First, advanced error handling often requires context and internal qc + execution. + + Second, even a simple failure (say, CRC error) needs information + gathering and could trigger complex error handling (say, resetting & + reconfiguring). Having multiple code paths to gather information, + enter EH and trigger actions makes life painful. + + Third, scattered EH code makes implementing low level drivers + difficult. Low level drivers override libata callbacks. If EH is + scattered over several places, each affected callbacks should perform + its part of error handling. This can be error prone and painful. + +libata Library +============== + +.. kernel-doc:: drivers/ata/libata-core.c + :export: + +libata Core Internals +===================== + +.. kernel-doc:: drivers/ata/libata-core.c + :internal: + +.. kernel-doc:: drivers/ata/libata-eh.c + +libata SCSI translation/emulation +================================= + +.. kernel-doc:: drivers/ata/libata-scsi.c + :export: + +.. kernel-doc:: drivers/ata/libata-scsi.c + :internal: + +ATA errors and exceptions +========================= + +This chapter tries to identify what error/exception conditions exist for +ATA/ATAPI devices and describe how they should be handled in +implementation-neutral way. + +The term 'error' is used to describe conditions where either an explicit +error condition is reported from device or a command has timed out. + +The term 'exception' is either used to describe exceptional conditions +which are not errors (say, power or hotplug events), or to describe both +errors and non-error exceptional conditions. Where explicit distinction +between error and exception is necessary, the term 'non-error exception' +is used. + +Exception categories +-------------------- + +Exceptions are described primarily with respect to legacy taskfile + bus +master IDE interface. If a controller provides other better mechanism +for error reporting, mapping those into categories described below +shouldn't be difficult. + +In the following sections, two recovery actions - reset and +reconfiguring transport - are mentioned. These are described further in +`EH recovery actions <#exrec>`__. + +HSM violation +~~~~~~~~~~~~~ + +This error is indicated when STATUS value doesn't match HSM requirement +during issuing or execution any ATA/ATAPI command. + +- ATA_STATUS doesn't contain !BSY && DRDY && !DRQ while trying to + issue a command. + +- !BSY && !DRQ during PIO data transfer. + +- DRQ on command completion. + +- !BSY && ERR after CDB transfer starts but before the last byte of CDB + is transferred. ATA/ATAPI standard states that "The device shall not + terminate the PACKET command with an error before the last byte of + the command packet has been written" in the error outputs description + of PACKET command and the state diagram doesn't include such + transitions. + +In these cases, HSM is violated and not much information regarding the +error can be acquired from STATUS or ERROR register. IOW, this error can +be anything - driver bug, faulty device, controller and/or cable. + +As HSM is violated, reset is necessary to restore known state. +Reconfiguring transport for lower speed might be helpful too as +transmission errors sometimes cause this kind of errors. + +ATA/ATAPI device error (non-NCQ / non-CHECK CONDITION) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +These are errors detected and reported by ATA/ATAPI devices indicating +device problems. For this type of errors, STATUS and ERROR register +values are valid and describe error condition. Note that some of ATA bus +errors are detected by ATA/ATAPI devices and reported using the same +mechanism as device errors. Those cases are described later in this +section. + +For ATA commands, this type of errors are indicated by !BSY && ERR +during command execution and on completion. + +For ATAPI commands, + +- !BSY && ERR && ABRT right after issuing PACKET indicates that PACKET + command is not supported and falls in this category. + +- !BSY && ERR(==CHK) && !ABRT after the last byte of CDB is transferred + indicates CHECK CONDITION and doesn't fall in this category. + +- !BSY && ERR(==CHK) && ABRT after the last byte of CDB is transferred + \*probably\* indicates CHECK CONDITION and doesn't fall in this + category. + +Of errors detected as above, the following are not ATA/ATAPI device +errors but ATA bus errors and should be handled according to +`ATA bus error <#excatATAbusErr>`__. + +CRC error during data transfer + This is indicated by ICRC bit in the ERROR register and means that + corruption occurred during data transfer. Up to ATA/ATAPI-7, the + standard specifies that this bit is only applicable to UDMA + transfers but ATA/ATAPI-8 draft revision 1f says that the bit may be + applicable to multiword DMA and PIO. + +ABRT error during data transfer or on completion + Up to ATA/ATAPI-7, the standard specifies that ABRT could be set on + ICRC errors and on cases where a device is not able to complete a + command. Combined with the fact that MWDMA and PIO transfer errors + aren't allowed to use ICRC bit up to ATA/ATAPI-7, it seems to imply + that ABRT bit alone could indicate transfer errors. + + However, ATA/ATAPI-8 draft revision 1f removes the part that ICRC + errors can turn on ABRT. So, this is kind of gray area. Some + heuristics are needed here. + +ATA/ATAPI device errors can be further categorized as follows. + +Media errors + This is indicated by UNC bit in the ERROR register. ATA devices + reports UNC error only after certain number of retries cannot + recover the data, so there's nothing much else to do other than + notifying upper layer. + + READ and WRITE commands report CHS or LBA of the first failed sector + but ATA/ATAPI standard specifies that the amount of transferred data + on error completion is indeterminate, so we cannot assume that + sectors preceding the failed sector have been transferred and thus + cannot complete those sectors successfully as SCSI does. + +Media changed / media change requested error + <> + +Address error + This is indicated by IDNF bit in the ERROR register. Report to upper + layer. + +Other errors + This can be invalid command or parameter indicated by ABRT ERROR bit + or some other error condition. Note that ABRT bit can indicate a lot + of things including ICRC and Address errors. Heuristics needed. + +Depending on commands, not all STATUS/ERROR bits are applicable. These +non-applicable bits are marked with "na" in the output descriptions but +up to ATA/ATAPI-7 no definition of "na" can be found. However, +ATA/ATAPI-8 draft revision 1f describes "N/A" as follows. + + 3.2.3.3a N/A + A keyword the indicates a field has no defined value in this + standard and should not be checked by the host or device. N/A + fields should be cleared to zero. + +So, it seems reasonable to assume that "na" bits are cleared to zero by +devices and thus need no explicit masking. + +ATAPI device CHECK CONDITION +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +ATAPI device CHECK CONDITION error is indicated by set CHK bit (ERR bit) +in the STATUS register after the last byte of CDB is transferred for a +PACKET command. For this kind of errors, sense data should be acquired +to gather information regarding the errors. REQUEST SENSE packet command +should be used to acquire sense data. + +Once sense data is acquired, this type of errors can be handled +similarly to other SCSI errors. Note that sense data may indicate ATA +bus error (e.g. Sense Key 04h HARDWARE ERROR && ASC/ASCQ 47h/00h SCSI +PARITY ERROR). In such cases, the error should be considered as an ATA +bus error and handled according to `ATA bus error <#excatATAbusErr>`__. + +ATA device error (NCQ) +~~~~~~~~~~~~~~~~~~~~~~ + +NCQ command error is indicated by cleared BSY and set ERR bit during NCQ +command phase (one or more NCQ commands outstanding). Although STATUS +and ERROR registers will contain valid values describing the error, READ +LOG EXT is required to clear the error condition, determine which +command has failed and acquire more information. + +READ LOG EXT Log Page 10h reports which tag has failed and taskfile +register values describing the error. With this information the failed +command can be handled as a normal ATA command error as in +`ATA/ATAPI device error (non-NCQ / non-CHECK CONDITION) <#excatDevErr>`__ +and all other in-flight commands must be retried. Note that this retry +should not be counted - it's likely that commands retried this way would +have completed normally if it were not for the failed command. + +Note that ATA bus errors can be reported as ATA device NCQ errors. This +should be handled as described in `ATA bus error <#excatATAbusErr>`__. + +If READ LOG EXT Log Page 10h fails or reports NQ, we're thoroughly +screwed. This condition should be treated according to +`HSM violation <#excatHSMviolation>`__. + +ATA bus error +~~~~~~~~~~~~~ + +ATA bus error means that data corruption occurred during transmission +over ATA bus (SATA or PATA). This type of errors can be indicated by + +- ICRC or ABRT error as described in + `ATA/ATAPI device error (non-NCQ / non-CHECK CONDITION) <#excatDevErr>`__. + +- Controller-specific error completion with error information + indicating transmission error. + +- On some controllers, command timeout. In this case, there may be a + mechanism to determine that the timeout is due to transmission error. + +- Unknown/random errors, timeouts and all sorts of weirdities. + +As described above, transmission errors can cause wide variety of +symptoms ranging from device ICRC error to random device lockup, and, +for many cases, there is no way to tell if an error condition is due to +transmission error or not; therefore, it's necessary to employ some kind +of heuristic when dealing with errors and timeouts. For example, +encountering repetitive ABRT errors for known supported command is +likely to indicate ATA bus error. + +Once it's determined that ATA bus errors have possibly occurred, +lowering ATA bus transmission speed is one of actions which may +alleviate the problem. See `Reconfigure transport <#exrecReconf>`__ for +more information. + +PCI bus error +~~~~~~~~~~~~~ + +Data corruption or other failures during transmission over PCI (or other +system bus). For standard BMDMA, this is indicated by Error bit in the +BMDMA Status register. This type of errors must be logged as it +indicates something is very wrong with the system. Resetting host +controller is recommended. + +Late completion +~~~~~~~~~~~~~~~ + +This occurs when timeout occurs and the timeout handler finds out that +the timed out command has completed successfully or with error. This is +usually caused by lost interrupts. This type of errors must be logged. +Resetting host controller is recommended. + +Unknown error (timeout) +~~~~~~~~~~~~~~~~~~~~~~~ + +This is when timeout occurs and the command is still processing or the +host and device are in unknown state. When this occurs, HSM could be in +any valid or invalid state. To bring the device to known state and make +it forget about the timed out command, resetting is necessary. The timed +out command may be retried. + +Timeouts can also be caused by transmission errors. Refer to +`ATA bus error <#excatATAbusErr>`__ for more details. + +Hotplug and power management exceptions +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +<> + +EH recovery actions +------------------- + +This section discusses several important recovery actions. + +Clearing error condition +~~~~~~~~~~~~~~~~~~~~~~~~ + +Many controllers require its error registers to be cleared by error +handler. Different controllers may have different requirements. + +For SATA, it's strongly recommended to clear at least SError register +during error handling. + +Reset +~~~~~ + +During EH, resetting is necessary in the following cases. + +- HSM is in unknown or invalid state + +- HBA is in unknown or invalid state + +- EH needs to make HBA/device forget about in-flight commands + +- HBA/device behaves weirdly + +Resetting during EH might be a good idea regardless of error condition +to improve EH robustness. Whether to reset both or either one of HBA and +device depends on situation but the following scheme is recommended. + +- When it's known that HBA is in ready state but ATA/ATAPI device is in + unknown state, reset only device. + +- If HBA is in unknown state, reset both HBA and device. + +HBA resetting is implementation specific. For a controller complying to +taskfile/BMDMA PCI IDE, stopping active DMA transaction may be +sufficient iff BMDMA state is the only HBA context. But even mostly +taskfile/BMDMA PCI IDE complying controllers may have implementation +specific requirements and mechanism to reset themselves. This must be +addressed by specific drivers. + +OTOH, ATA/ATAPI standard describes in detail ways to reset ATA/ATAPI +devices. + +PATA hardware reset + This is hardware initiated device reset signalled with asserted PATA + RESET- signal. There is no standard way to initiate hardware reset + from software although some hardware provides registers that allow + driver to directly tweak the RESET- signal. + +Software reset + This is achieved by turning CONTROL SRST bit on for at least 5us. + Both PATA and SATA support it but, in case of SATA, this may require + controller-specific support as the second Register FIS to clear SRST + should be transmitted while BSY bit is still set. Note that on PATA, + this resets both master and slave devices on a channel. + +EXECUTE DEVICE DIAGNOSTIC command + Although ATA/ATAPI standard doesn't describe exactly, EDD implies + some level of resetting, possibly similar level with software reset. + Host-side EDD protocol can be handled with normal command processing + and most SATA controllers should be able to handle EDD's just like + other commands. As in software reset, EDD affects both devices on a + PATA bus. + + Although EDD does reset devices, this doesn't suit error handling as + EDD cannot be issued while BSY is set and it's unclear how it will + act when device is in unknown/weird state. + +ATAPI DEVICE RESET command + This is very similar to software reset except that reset can be + restricted to the selected device without affecting the other device + sharing the cable. + +SATA phy reset + This is the preferred way of resetting a SATA device. In effect, + it's identical to PATA hardware reset. Note that this can be done + with the standard SCR Control register. As such, it's usually easier + to implement than software reset. + +One more thing to consider when resetting devices is that resetting +clears certain configuration parameters and they need to be set to their +previous or newly adjusted values after reset. + +Parameters affected are. + +- CHS set up with INITIALIZE DEVICE PARAMETERS (seldom used) + +- Parameters set with SET FEATURES including transfer mode setting + +- Block count set with SET MULTIPLE MODE + +- Other parameters (SET MAX, MEDIA LOCK...) + +ATA/ATAPI standard specifies that some parameters must be maintained +across hardware or software reset, but doesn't strictly specify all of +them. Always reconfiguring needed parameters after reset is required for +robustness. Note that this also applies when resuming from deep sleep +(power-off). + +Also, ATA/ATAPI standard requires that IDENTIFY DEVICE / IDENTIFY PACKET +DEVICE is issued after any configuration parameter is updated or a +hardware reset and the result used for further operation. OS driver is +required to implement revalidation mechanism to support this. + +Reconfigure transport +~~~~~~~~~~~~~~~~~~~~~ + +For both PATA and SATA, a lot of corners are cut for cheap connectors, +cables or controllers and it's quite common to see high transmission +error rate. This can be mitigated by lowering transmission speed. + +The following is a possible scheme Jeff Garzik suggested. + + If more than $N (3?) transmission errors happen in 15 minutes, + + - if SATA, decrease SATA PHY speed. if speed cannot be decreased, + + - decrease UDMA xfer speed. if at UDMA0, switch to PIO4, + + - decrease PIO xfer speed. if at PIO3, complain, but continue + +ata_piix Internals +=================== + +.. kernel-doc:: drivers/ata/ata_piix.c + :internal: + +sata_sil Internals +=================== + +.. kernel-doc:: drivers/ata/sata_sil.c + :internal: + +Thanks +====== + +The bulk of the ATA knowledge comes thanks to long conversations with +Andre Hedrick (www.linux-ide.org), and long hours pondering the ATA and +SCSI specifications. + +Thanks to Alan Cox for pointing out similarities between SATA and SCSI, +and in general for motivation to hack on libata. + +libata's device detection method, ata_pio_devchk, and in general all +the early probing was based on extensive study of Hale Landis's +probe/reset code in his ATADRVR driver (www.ata-atapi.com). diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst new file mode 100644 index 00000000000000..e9afa586d15ea9 --- /dev/null +++ b/Documentation/driver-api/mtdnand.rst @@ -0,0 +1,1007 @@ +===================================== +MTD NAND Driver Programming Interface +===================================== + +:Author: Thomas Gleixner + +Introduction +============ + +The generic NAND driver supports almost all NAND and AG-AND based chips +and connects them to the Memory Technology Devices (MTD) subsystem of +the Linux Kernel. + +This documentation is provided for developers who want to implement +board drivers or filesystem drivers suitable for NAND devices. + +Known Bugs And Assumptions +========================== + +None. + +Documentation hints +=================== + +The function and structure docs are autogenerated. Each function and +struct member has a short description which is marked with an [XXX] +identifier. The following chapters explain the meaning of those +identifiers. + +Function identifiers [XXX] +-------------------------- + +The functions are marked with [XXX] identifiers in the short comment. +The identifiers explain the usage and scope of the functions. Following +identifiers are used: + +- [MTD Interface] + + These functions provide the interface to the MTD kernel API. They are + not replaceable and provide functionality which is complete hardware + independent. + +- [NAND Interface] + + These functions are exported and provide the interface to the NAND + kernel API. + +- [GENERIC] + + Generic functions are not replaceable and provide functionality which + is complete hardware independent. + +- [DEFAULT] + + Default functions provide hardware related functionality which is + suitable for most of the implementations. These functions can be + replaced by the board driver if necessary. Those functions are called + via pointers in the NAND chip description structure. The board driver + can set the functions which should be replaced by board dependent + functions before calling nand_scan(). If the function pointer is + NULL on entry to nand_scan() then the pointer is set to the default + function which is suitable for the detected chip type. + +Struct member identifiers [XXX] +------------------------------- + +The struct members are marked with [XXX] identifiers in the comment. The +identifiers explain the usage and scope of the members. Following +identifiers are used: + +- [INTERN] + + These members are for NAND driver internal use only and must not be + modified. Most of these values are calculated from the chip geometry + information which is evaluated during nand_scan(). + +- [REPLACEABLE] + + Replaceable members hold hardware related functions which can be + provided by the board driver. The board driver can set the functions + which should be replaced by board dependent functions before calling + nand_scan(). If the function pointer is NULL on entry to + nand_scan() then the pointer is set to the default function which is + suitable for the detected chip type. + +- [BOARDSPECIFIC] + + Board specific members hold hardware related information which must + be provided by the board driver. The board driver must set the + function pointers and datafields before calling nand_scan(). + +- [OPTIONAL] + + Optional members can hold information relevant for the board driver. + The generic NAND driver code does not use this information. + +Basic board driver +================== + +For most boards it will be sufficient to provide just the basic +functions and fill out some really board dependent members in the nand +chip description structure. + +Basic defines +------------- + +At least you have to provide a nand_chip structure and a storage for +the ioremap'ed chip address. You can allocate the nand_chip structure +using kmalloc or you can allocate it statically. The NAND chip structure +embeds an mtd structure which will be registered to the MTD subsystem. +You can extract a pointer to the mtd structure from a nand_chip pointer +using the nand_to_mtd() helper. + +Kmalloc based example + +:: + + static struct mtd_info *board_mtd; + static void __iomem *baseaddr; + + +Static example + +:: + + static struct nand_chip board_chip; + static void __iomem *baseaddr; + + +Partition defines +----------------- + +If you want to divide your device into partitions, then define a +partitioning scheme suitable to your board. + +:: + + #define NUM_PARTITIONS 2 + static struct mtd_partition partition_info[] = { + { .name = "Flash partition 1", + .offset = 0, + .size = 8 * 1024 * 1024 }, + { .name = "Flash partition 2", + .offset = MTDPART_OFS_NEXT, + .size = MTDPART_SIZ_FULL }, + }; + + +Hardware control function +------------------------- + +The hardware control function provides access to the control pins of the +NAND chip(s). The access can be done by GPIO pins or by address lines. +If you use address lines, make sure that the timing requirements are +met. + +*GPIO based example* + +:: + + static void board_hwcontrol(struct mtd_info *mtd, int cmd) + { + switch(cmd){ + case NAND_CTL_SETCLE: /* Set CLE pin high */ break; + case NAND_CTL_CLRCLE: /* Set CLE pin low */ break; + case NAND_CTL_SETALE: /* Set ALE pin high */ break; + case NAND_CTL_CLRALE: /* Set ALE pin low */ break; + case NAND_CTL_SETNCE: /* Set nCE pin low */ break; + case NAND_CTL_CLRNCE: /* Set nCE pin high */ break; + } + } + + +*Address lines based example.* It's assumed that the nCE pin is driven +by a chip select decoder. + +:: + + static void board_hwcontrol(struct mtd_info *mtd, int cmd) + { + struct nand_chip *this = mtd_to_nand(mtd); + switch(cmd){ + case NAND_CTL_SETCLE: this->IO_ADDR_W |= CLE_ADRR_BIT; break; + case NAND_CTL_CLRCLE: this->IO_ADDR_W &= ~CLE_ADRR_BIT; break; + case NAND_CTL_SETALE: this->IO_ADDR_W |= ALE_ADRR_BIT; break; + case NAND_CTL_CLRALE: this->IO_ADDR_W &= ~ALE_ADRR_BIT; break; + } + } + + +Device ready function +--------------------- + +If the hardware interface has the ready busy pin of the NAND chip +connected to a GPIO or other accessible I/O pin, this function is used +to read back the state of the pin. The function has no arguments and +should return 0, if the device is busy (R/B pin is low) and 1, if the +device is ready (R/B pin is high). If the hardware interface does not +give access to the ready busy pin, then the function must not be defined +and the function pointer this->dev_ready is set to NULL. + +Init function +------------- + +The init function allocates memory and sets up all the board specific +parameters and function pointers. When everything is set up nand_scan() +is called. This function tries to detect and identify then chip. If a +chip is found all the internal data fields are initialized accordingly. +The structure(s) have to be zeroed out first and then filled with the +necessary information about the device. + +:: + + static int __init board_init (void) + { + struct nand_chip *this; + int err = 0; + + /* Allocate memory for MTD device structure and private data */ + this = kzalloc(sizeof(struct nand_chip), GFP_KERNEL); + if (!this) { + printk ("Unable to allocate NAND MTD device structure.\n"); + err = -ENOMEM; + goto out; + } + + board_mtd = nand_to_mtd(this); + + /* map physical address */ + baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024); + if (!baseaddr) { + printk("Ioremap to access NAND chip failed\n"); + err = -EIO; + goto out_mtd; + } + + /* Set address of NAND IO lines */ + this->IO_ADDR_R = baseaddr; + this->IO_ADDR_W = baseaddr; + /* Reference hardware control function */ + this->hwcontrol = board_hwcontrol; + /* Set command delay time, see datasheet for correct value */ + this->chip_delay = CHIP_DEPENDEND_COMMAND_DELAY; + /* Assign the device ready function, if available */ + this->dev_ready = board_dev_ready; + this->eccmode = NAND_ECC_SOFT; + + /* Scan to find existence of the device */ + if (nand_scan (board_mtd, 1)) { + err = -ENXIO; + goto out_ior; + } + + add_mtd_partitions(board_mtd, partition_info, NUM_PARTITIONS); + goto out; + + out_ior: + iounmap(baseaddr); + out_mtd: + kfree (this); + out: + return err; + } + module_init(board_init); + + +Exit function +------------- + +The exit function is only necessary if the driver is compiled as a +module. It releases all resources which are held by the chip driver and +unregisters the partitions in the MTD layer. + +:: + + #ifdef MODULE + static void __exit board_cleanup (void) + { + /* Release resources, unregister device */ + nand_release (board_mtd); + + /* unmap physical address */ + iounmap(baseaddr); + + /* Free the MTD device structure */ + kfree (mtd_to_nand(board_mtd)); + } + module_exit(board_cleanup); + #endif + + +Advanced board driver functions +=============================== + +This chapter describes the advanced functionality of the NAND driver. +For a list of functions which can be overridden by the board driver see +the documentation of the nand_chip structure. + +Multiple chip control +--------------------- + +The nand driver can control chip arrays. Therefore the board driver must +provide an own select_chip function. This function must (de)select the +requested chip. The function pointer in the nand_chip structure must be +set before calling nand_scan(). The maxchip parameter of nand_scan() +defines the maximum number of chips to scan for. Make sure that the +select_chip function can handle the requested number of chips. + +The nand driver concatenates the chips to one virtual chip and provides +this virtual chip to the MTD layer. + +*Note: The driver can only handle linear chip arrays of equally sized +chips. There is no support for parallel arrays which extend the +buswidth.* + +*GPIO based example* + +:: + + static void board_select_chip (struct mtd_info *mtd, int chip) + { + /* Deselect all chips, set all nCE pins high */ + GPIO(BOARD_NAND_NCE) |= 0xff; + if (chip >= 0) + GPIO(BOARD_NAND_NCE) &= ~ (1 << chip); + } + + +*Address lines based example.* Its assumed that the nCE pins are +connected to an address decoder. + +:: + + static void board_select_chip (struct mtd_info *mtd, int chip) + { + struct nand_chip *this = mtd_to_nand(mtd); + + /* Deselect all chips */ + this->IO_ADDR_R &= ~BOARD_NAND_ADDR_MASK; + this->IO_ADDR_W &= ~BOARD_NAND_ADDR_MASK; + switch (chip) { + case 0: + this->IO_ADDR_R |= BOARD_NAND_ADDR_CHIP0; + this->IO_ADDR_W |= BOARD_NAND_ADDR_CHIP0; + break; + .... + case n: + this->IO_ADDR_R |= BOARD_NAND_ADDR_CHIPn; + this->IO_ADDR_W |= BOARD_NAND_ADDR_CHIPn; + break; + } + } + + +Hardware ECC support +-------------------- + +Functions and constants +~~~~~~~~~~~~~~~~~~~~~~~ + +The nand driver supports three different types of hardware ECC. + +- NAND_ECC_HW3_256 + + Hardware ECC generator providing 3 bytes ECC per 256 byte. + +- NAND_ECC_HW3_512 + + Hardware ECC generator providing 3 bytes ECC per 512 byte. + +- NAND_ECC_HW6_512 + + Hardware ECC generator providing 6 bytes ECC per 512 byte. + +- NAND_ECC_HW8_512 + + Hardware ECC generator providing 6 bytes ECC per 512 byte. + +If your hardware generator has a different functionality add it at the +appropriate place in nand_base.c + +The board driver must provide following functions: + +- enable_hwecc + + This function is called before reading / writing to the chip. Reset + or initialize the hardware generator in this function. The function + is called with an argument which let you distinguish between read and + write operations. + +- calculate_ecc + + This function is called after read / write from / to the chip. + Transfer the ECC from the hardware to the buffer. If the option + NAND_HWECC_SYNDROME is set then the function is only called on + write. See below. + +- correct_data + + In case of an ECC error this function is called for error detection + and correction. Return 1 respectively 2 in case the error can be + corrected. If the error is not correctable return -1. If your + hardware generator matches the default algorithm of the nand_ecc + software generator then use the correction function provided by + nand_ecc instead of implementing duplicated code. + +Hardware ECC with syndrome calculation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Many hardware ECC implementations provide Reed-Solomon codes and +calculate an error syndrome on read. The syndrome must be converted to a +standard Reed-Solomon syndrome before calling the error correction code +in the generic Reed-Solomon library. + +The ECC bytes must be placed immediately after the data bytes in order +to make the syndrome generator work. This is contrary to the usual +layout used by software ECC. The separation of data and out of band area +is not longer possible. The nand driver code handles this layout and the +remaining free bytes in the oob area are managed by the autoplacement +code. Provide a matching oob-layout in this case. See rts_from4.c and +diskonchip.c for implementation reference. In those cases we must also +use bad block tables on FLASH, because the ECC layout is interfering +with the bad block marker positions. See bad block table support for +details. + +Bad block table support +----------------------- + +Most NAND chips mark the bad blocks at a defined position in the spare +area. Those blocks must not be erased under any circumstances as the bad +block information would be lost. It is possible to check the bad block +mark each time when the blocks are accessed by reading the spare area of +the first page in the block. This is time consuming so a bad block table +is used. + +The nand driver supports various types of bad block tables. + +- Per device + + The bad block table contains all bad block information of the device + which can consist of multiple chips. + +- Per chip + + A bad block table is used per chip and contains the bad block + information for this particular chip. + +- Fixed offset + + The bad block table is located at a fixed offset in the chip + (device). This applies to various DiskOnChip devices. + +- Automatic placed + + The bad block table is automatically placed and detected either at + the end or at the beginning of a chip (device) + +- Mirrored tables + + The bad block table is mirrored on the chip (device) to allow updates + of the bad block table without data loss. + +nand_scan() calls the function nand_default_bbt(). +nand_default_bbt() selects appropriate default bad block table +descriptors depending on the chip information which was retrieved by +nand_scan(). + +The standard policy is scanning the device for bad blocks and build a +ram based bad block table which allows faster access than always +checking the bad block information on the flash chip itself. + +Flash based tables +~~~~~~~~~~~~~~~~~~ + +It may be desired or necessary to keep a bad block table in FLASH. For +AG-AND chips this is mandatory, as they have no factory marked bad +blocks. They have factory marked good blocks. The marker pattern is +erased when the block is erased to be reused. So in case of powerloss +before writing the pattern back to the chip this block would be lost and +added to the bad blocks. Therefore we scan the chip(s) when we detect +them the first time for good blocks and store this information in a bad +block table before erasing any of the blocks. + +The blocks in which the tables are stored are protected against +accidental access by marking them bad in the memory bad block table. The +bad block table management functions are allowed to circumvent this +protection. + +The simplest way to activate the FLASH based bad block table support is +to set the option NAND_BBT_USE_FLASH in the bbt_option field of the +nand chip structure before calling nand_scan(). For AG-AND chips is +this done by default. This activates the default FLASH based bad block +table functionality of the NAND driver. The default bad block table +options are + +- Store bad block table per chip + +- Use 2 bits per block + +- Automatic placement at the end of the chip + +- Use mirrored tables with version numbers + +- Reserve 4 blocks at the end of the chip + +User defined tables +~~~~~~~~~~~~~~~~~~~ + +User defined tables are created by filling out a nand_bbt_descr +structure and storing the pointer in the nand_chip structure member +bbt_td before calling nand_scan(). If a mirror table is necessary a +second structure must be created and a pointer to this structure must be +stored in bbt_md inside the nand_chip structure. If the bbt_md member +is set to NULL then only the main table is used and no scan for the +mirrored table is performed. + +The most important field in the nand_bbt_descr structure is the +options field. The options define most of the table properties. Use the +predefined constants from nand.h to define the options. + +- Number of bits per block + + The supported number of bits is 1, 2, 4, 8. + +- Table per chip + + Setting the constant NAND_BBT_PERCHIP selects that a bad block + table is managed for each chip in a chip array. If this option is not + set then a per device bad block table is used. + +- Table location is absolute + + Use the option constant NAND_BBT_ABSPAGE and define the absolute + page number where the bad block table starts in the field pages. If + you have selected bad block tables per chip and you have a multi chip + array then the start page must be given for each chip in the chip + array. Note: there is no scan for a table ident pattern performed, so + the fields pattern, veroffs, offs, len can be left uninitialized + +- Table location is automatically detected + + The table can either be located in the first or the last good blocks + of the chip (device). Set NAND_BBT_LASTBLOCK to place the bad block + table at the end of the chip (device). The bad block tables are + marked and identified by a pattern which is stored in the spare area + of the first page in the block which holds the bad block table. Store + a pointer to the pattern in the pattern field. Further the length of + the pattern has to be stored in len and the offset in the spare area + must be given in the offs member of the nand_bbt_descr structure. + For mirrored bad block tables different patterns are mandatory. + +- Table creation + + Set the option NAND_BBT_CREATE to enable the table creation if no + table can be found during the scan. Usually this is done only once if + a new chip is found. + +- Table write support + + Set the option NAND_BBT_WRITE to enable the table write support. + This allows the update of the bad block table(s) in case a block has + to be marked bad due to wear. The MTD interface function + block_markbad is calling the update function of the bad block table. + If the write support is enabled then the table is updated on FLASH. + + Note: Write support should only be enabled for mirrored tables with + version control. + +- Table version control + + Set the option NAND_BBT_VERSION to enable the table version + control. It's highly recommended to enable this for mirrored tables + with write support. It makes sure that the risk of losing the bad + block table information is reduced to the loss of the information + about the one worn out block which should be marked bad. The version + is stored in 4 consecutive bytes in the spare area of the device. The + position of the version number is defined by the member veroffs in + the bad block table descriptor. + +- Save block contents on write + + In case that the block which holds the bad block table does contain + other useful information, set the option NAND_BBT_SAVECONTENT. When + the bad block table is written then the whole block is read the bad + block table is updated and the block is erased and everything is + written back. If this option is not set only the bad block table is + written and everything else in the block is ignored and erased. + +- Number of reserved blocks + + For automatic placement some blocks must be reserved for bad block + table storage. The number of reserved blocks is defined in the + maxblocks member of the bad block table description structure. + Reserving 4 blocks for mirrored tables should be a reasonable number. + This also limits the number of blocks which are scanned for the bad + block table ident pattern. + +Spare area (auto)placement +-------------------------- + +The nand driver implements different possibilities for placement of +filesystem data in the spare area, + +- Placement defined by fs driver + +- Automatic placement + +The default placement function is automatic placement. The nand driver +has built in default placement schemes for the various chiptypes. If due +to hardware ECC functionality the default placement does not fit then +the board driver can provide a own placement scheme. + +File system drivers can provide a own placement scheme which is used +instead of the default placement scheme. + +Placement schemes are defined by a nand_oobinfo structure + +:: + + struct nand_oobinfo { + int useecc; + int eccbytes; + int eccpos[24]; + int oobfree[8][2]; + }; + + +- useecc + + The useecc member controls the ecc and placement function. The header + file include/mtd/mtd-abi.h contains constants to select ecc and + placement. MTD_NANDECC_OFF switches off the ecc complete. This is + not recommended and available for testing and diagnosis only. + MTD_NANDECC_PLACE selects caller defined placement, + MTD_NANDECC_AUTOPLACE selects automatic placement. + +- eccbytes + + The eccbytes member defines the number of ecc bytes per page. + +- eccpos + + The eccpos array holds the byte offsets in the spare area where the + ecc codes are placed. + +- oobfree + + The oobfree array defines the areas in the spare area which can be + used for automatic placement. The information is given in the format + {offset, size}. offset defines the start of the usable area, size the + length in bytes. More than one area can be defined. The list is + terminated by an {0, 0} entry. + +Placement defined by fs driver +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The calling function provides a pointer to a nand_oobinfo structure +which defines the ecc placement. For writes the caller must provide a +spare area buffer along with the data buffer. The spare area buffer size +is (number of pages) \* (size of spare area). For reads the buffer size +is (number of pages) \* ((size of spare area) + (number of ecc steps per +page) \* sizeof (int)). The driver stores the result of the ecc check +for each tuple in the spare buffer. The storage sequence is:: + + ... + + ... + + ... + +This is a legacy mode used by YAFFS1. + +If the spare area buffer is NULL then only the ECC placement is done +according to the given scheme in the nand_oobinfo structure. + +Automatic placement +~~~~~~~~~~~~~~~~~~~ + +Automatic placement uses the built in defaults to place the ecc bytes in +the spare area. If filesystem data have to be stored / read into the +spare area then the calling function must provide a buffer. The buffer +size per page is determined by the oobfree array in the nand_oobinfo +structure. + +If the spare area buffer is NULL then only the ECC placement is done +according to the default builtin scheme. + +Spare area autoplacement default schemes +---------------------------------------- + +256 byte pagesize +~~~~~~~~~~~~~~~~~ + +======== ================== =================================================== +Offset Content Comment +======== ================== =================================================== +0x00 ECC byte 0 Error correction code byte 0 +0x01 ECC byte 1 Error correction code byte 1 +0x02 ECC byte 2 Error correction code byte 2 +0x03 Autoplace 0 +0x04 Autoplace 1 +0x05 Bad block marker If any bit in this byte is zero, then this + block is bad. This applies only to the first + page in a block. In the remaining pages this + byte is reserved +0x06 Autoplace 2 +0x07 Autoplace 3 +======== ================== =================================================== + +512 byte pagesize +~~~~~~~~~~~~~~~~~ + + +============= ================== ============================================== +Offset Content Comment +============= ================== ============================================== +0x00 ECC byte 0 Error correction code byte 0 of the lower + 256 Byte data in this page +0x01 ECC byte 1 Error correction code byte 1 of the lower + 256 Bytes of data in this page +0x02 ECC byte 2 Error correction code byte 2 of the lower + 256 Bytes of data in this page +0x03 ECC byte 3 Error correction code byte 0 of the upper + 256 Bytes of data in this page +0x04 reserved reserved +0x05 Bad block marker If any bit in this byte is zero, then this + block is bad. This applies only to the first + page in a block. In the remaining pages this + byte is reserved +0x06 ECC byte 4 Error correction code byte 1 of the upper + 256 Bytes of data in this page +0x07 ECC byte 5 Error correction code byte 2 of the upper + 256 Bytes of data in this page +0x08 - 0x0F Autoplace 0 - 7 +============= ================== ============================================== + +2048 byte pagesize +~~~~~~~~~~~~~~~~~~ + +=========== ================== ================================================ +Offset Content Comment +=========== ================== ================================================ +0x00 Bad block marker If any bit in this byte is zero, then this block + is bad. This applies only to the first page in a + block. In the remaining pages this byte is + reserved +0x01 Reserved Reserved +0x02-0x27 Autoplace 0 - 37 +0x28 ECC byte 0 Error correction code byte 0 of the first + 256 Byte data in this page +0x29 ECC byte 1 Error correction code byte 1 of the first + 256 Bytes of data in this page +0x2A ECC byte 2 Error correction code byte 2 of the first + 256 Bytes data in this page +0x2B ECC byte 3 Error correction code byte 0 of the second + 256 Bytes of data in this page +0x2C ECC byte 4 Error correction code byte 1 of the second + 256 Bytes of data in this page +0x2D ECC byte 5 Error correction code byte 2 of the second + 256 Bytes of data in this page +0x2E ECC byte 6 Error correction code byte 0 of the third + 256 Bytes of data in this page +0x2F ECC byte 7 Error correction code byte 1 of the third + 256 Bytes of data in this page +0x30 ECC byte 8 Error correction code byte 2 of the third + 256 Bytes of data in this page +0x31 ECC byte 9 Error correction code byte 0 of the fourth + 256 Bytes of data in this page +0x32 ECC byte 10 Error correction code byte 1 of the fourth + 256 Bytes of data in this page +0x33 ECC byte 11 Error correction code byte 2 of the fourth + 256 Bytes of data in this page +0x34 ECC byte 12 Error correction code byte 0 of the fifth + 256 Bytes of data in this page +0x35 ECC byte 13 Error correction code byte 1 of the fifth + 256 Bytes of data in this page +0x36 ECC byte 14 Error correction code byte 2 of the fifth + 256 Bytes of data in this page +0x37 ECC byte 15 Error correction code byte 0 of the sixth + 256 Bytes of data in this page +0x38 ECC byte 16 Error correction code byte 1 of the sixth + 256 Bytes of data in this page +0x39 ECC byte 17 Error correction code byte 2 of the sixth + 256 Bytes of data in this page +0x3A ECC byte 18 Error correction code byte 0 of the seventh + 256 Bytes of data in this page +0x3B ECC byte 19 Error correction code byte 1 of the seventh + 256 Bytes of data in this page +0x3C ECC byte 20 Error correction code byte 2 of the seventh + 256 Bytes of data in this page +0x3D ECC byte 21 Error correction code byte 0 of the eighth + 256 Bytes of data in this page +0x3E ECC byte 22 Error correction code byte 1 of the eighth + 256 Bytes of data in this page +0x3F ECC byte 23 Error correction code byte 2 of the eighth + 256 Bytes of data in this page +=========== ================== ================================================ + +Filesystem support +================== + +The NAND driver provides all necessary functions for a filesystem via +the MTD interface. + +Filesystems must be aware of the NAND peculiarities and restrictions. +One major restrictions of NAND Flash is, that you cannot write as often +as you want to a page. The consecutive writes to a page, before erasing +it again, are restricted to 1-3 writes, depending on the manufacturers +specifications. This applies similar to the spare area. + +Therefore NAND aware filesystems must either write in page size chunks +or hold a writebuffer to collect smaller writes until they sum up to +pagesize. Available NAND aware filesystems: JFFS2, YAFFS. + +The spare area usage to store filesystem data is controlled by the spare +area placement functionality which is described in one of the earlier +chapters. + +Tools +===== + +The MTD project provides a couple of helpful tools to handle NAND Flash. + +- flasherase, flasheraseall: Erase and format FLASH partitions + +- nandwrite: write filesystem images to NAND FLASH + +- nanddump: dump the contents of a NAND FLASH partitions + +These tools are aware of the NAND restrictions. Please use those tools +instead of complaining about errors which are caused by non NAND aware +access methods. + +Constants +========= + +This chapter describes the constants which might be relevant for a +driver developer. + +Chip option constants +--------------------- + +Constants for chip id table +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +These constants are defined in nand.h. They are OR-ed together to +describe the chip functionality:: + + /* Buswitdh is 16 bit */ + #define NAND_BUSWIDTH_16 0x00000002 + /* Device supports partial programming without padding */ + #define NAND_NO_PADDING 0x00000004 + /* Chip has cache program function */ + #define NAND_CACHEPRG 0x00000008 + /* Chip has copy back function */ + #define NAND_COPYBACK 0x00000010 + /* AND Chip which has 4 banks and a confusing page / block + * assignment. See Renesas datasheet for further information */ + #define NAND_IS_AND 0x00000020 + /* Chip has a array of 4 pages which can be read without + * additional ready /busy waits */ + #define NAND_4PAGE_ARRAY 0x00000040 + + +Constants for runtime options +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +These constants are defined in nand.h. They are OR-ed together to +describe the functionality:: + + /* The hw ecc generator provides a syndrome instead a ecc value on read + * This can only work if we have the ecc bytes directly behind the + * data bytes. Applies for DOC and AG-AND Renesas HW Reed Solomon generators */ + #define NAND_HWECC_SYNDROME 0x00020000 + + +ECC selection constants +----------------------- + +Use these constants to select the ECC algorithm:: + + /* No ECC. Usage is not recommended ! */ + #define NAND_ECC_NONE 0 + /* Software ECC 3 byte ECC per 256 Byte data */ + #define NAND_ECC_SOFT 1 + /* Hardware ECC 3 byte ECC per 256 Byte data */ + #define NAND_ECC_HW3_256 2 + /* Hardware ECC 3 byte ECC per 512 Byte data */ + #define NAND_ECC_HW3_512 3 + /* Hardware ECC 6 byte ECC per 512 Byte data */ + #define NAND_ECC_HW6_512 4 + /* Hardware ECC 6 byte ECC per 512 Byte data */ + #define NAND_ECC_HW8_512 6 + + +Hardware control related constants +---------------------------------- + +These constants describe the requested hardware access function when the +boardspecific hardware control function is called:: + + /* Select the chip by setting nCE to low */ + #define NAND_CTL_SETNCE 1 + /* Deselect the chip by setting nCE to high */ + #define NAND_CTL_CLRNCE 2 + /* Select the command latch by setting CLE to high */ + #define NAND_CTL_SETCLE 3 + /* Deselect the command latch by setting CLE to low */ + #define NAND_CTL_CLRCLE 4 + /* Select the address latch by setting ALE to high */ + #define NAND_CTL_SETALE 5 + /* Deselect the address latch by setting ALE to low */ + #define NAND_CTL_CLRALE 6 + /* Set write protection by setting WP to high. Not used! */ + #define NAND_CTL_SETWP 7 + /* Clear write protection by setting WP to low. Not used! */ + #define NAND_CTL_CLRWP 8 + + +Bad block table related constants +--------------------------------- + +These constants describe the options used for bad block table +descriptors:: + + /* Options for the bad block table descriptors */ + + /* The number of bits used per block in the bbt on the device */ + #define NAND_BBT_NRBITS_MSK 0x0000000F + #define NAND_BBT_1BIT 0x00000001 + #define NAND_BBT_2BIT 0x00000002 + #define NAND_BBT_4BIT 0x00000004 + #define NAND_BBT_8BIT 0x00000008 + /* The bad block table is in the last good block of the device */ + #define NAND_BBT_LASTBLOCK 0x00000010 + /* The bbt is at the given page, else we must scan for the bbt */ + #define NAND_BBT_ABSPAGE 0x00000020 + /* bbt is stored per chip on multichip devices */ + #define NAND_BBT_PERCHIP 0x00000080 + /* bbt has a version counter at offset veroffs */ + #define NAND_BBT_VERSION 0x00000100 + /* Create a bbt if none axists */ + #define NAND_BBT_CREATE 0x00000200 + /* Write bbt if necessary */ + #define NAND_BBT_WRITE 0x00001000 + /* Read and write back block contents when writing bbt */ + #define NAND_BBT_SAVECONTENT 0x00002000 + + +Structures +========== + +This chapter contains the autogenerated documentation of the structures +which are used in the NAND driver and might be relevant for a driver +developer. Each struct member has a short description which is marked +with an [XXX] identifier. See the chapter "Documentation hints" for an +explanation. + +.. kernel-doc:: include/linux/mtd/nand.h + :internal: + +Public Functions Provided +========================= + +This chapter contains the autogenerated documentation of the NAND kernel +API functions which are exported. Each function has a short description +which is marked with an [XXX] identifier. See the chapter "Documentation +hints" for an explanation. + +.. kernel-doc:: drivers/mtd/nand/nand_base.c + :export: + +.. kernel-doc:: drivers/mtd/nand/nand_ecc.c + :export: + +Internal Functions Provided +=========================== + +This chapter contains the autogenerated documentation of the NAND driver +internal functions. Each function has a short description which is +marked with an [XXX] identifier. See the chapter "Documentation hints" +for an explanation. The functions marked with [DEFAULT] might be +relevant for a board driver developer. + +.. kernel-doc:: drivers/mtd/nand/nand_base.c + :internal: + +.. kernel-doc:: drivers/mtd/nand/nand_bbt.c + :internal: + +Credits +======= + +The following people have contributed to the NAND driver: + +1. Steven J. Hill\ sjhill@realitydiluted.com + +2. David Woodhouse\ dwmw2@infradead.org + +3. Thomas Gleixner\ tglx@linutronix.de + +A lot of users have provided bugfixes, improvements and helping hands +for testing. Thanks a lot. + +The following people have contributed to this document: + +1. Thomas Gleixner\ tglx@linutronix.de diff --git a/Documentation/driver-api/rapidio.rst b/Documentation/driver-api/rapidio.rst new file mode 100644 index 00000000000000..71ff658ab78e89 --- /dev/null +++ b/Documentation/driver-api/rapidio.rst @@ -0,0 +1,107 @@ +======================= +RapidIO Subsystem Guide +======================= + +:Author: Matt Porter + +Introduction +============ + +RapidIO is a high speed switched fabric interconnect with features aimed +at the embedded market. RapidIO provides support for memory-mapped I/O +as well as message-based transactions over the switched fabric network. +RapidIO has a standardized discovery mechanism not unlike the PCI bus +standard that allows simple detection of devices in a network. + +This documentation is provided for developers intending to support +RapidIO on new architectures, write new drivers, or to understand the +subsystem internals. + +Known Bugs and Limitations +========================== + +Bugs +---- + +None. ;) + +Limitations +----------- + +1. Access/management of RapidIO memory regions is not supported + +2. Multiple host enumeration is not supported + +RapidIO driver interface +======================== + +Drivers are provided a set of calls in order to interface with the +subsystem to gather info on devices, request/map memory region +resources, and manage mailboxes/doorbells. + +Functions +--------- + +.. kernel-doc:: include/linux/rio_drv.h + :internal: + +.. kernel-doc:: drivers/rapidio/rio-driver.c + :export: + +.. kernel-doc:: drivers/rapidio/rio.c + :export: + +Internals +========= + +This chapter contains the autogenerated documentation of the RapidIO +subsystem. + +Structures +---------- + +.. kernel-doc:: include/linux/rio.h + :internal: + +Enumeration and Discovery +------------------------- + +.. kernel-doc:: drivers/rapidio/rio-scan.c + :internal: + +Driver functionality +-------------------- + +.. kernel-doc:: drivers/rapidio/rio.c + :internal: + +.. kernel-doc:: drivers/rapidio/rio-access.c + :internal: + +Device model support +-------------------- + +.. kernel-doc:: drivers/rapidio/rio-driver.c + :internal: + +PPC32 support +------------- + +.. kernel-doc:: arch/powerpc/sysdev/fsl_rio.c + :internal: + +Credits +======= + +The following people have contributed to the RapidIO subsystem directly +or indirectly: + +1. Matt Porter\ mporter@kernel.crashing.org + +2. Randy Vinson\ rvinson@mvista.com + +3. Dan Malek\ dan@embeddedalley.com + +The following people have contributed to this document: + +1. Matt Porter\ mporter@kernel.crashing.org diff --git a/Documentation/driver-api/s390-drivers.rst b/Documentation/driver-api/s390-drivers.rst new file mode 100644 index 00000000000000..7060da1360951b --- /dev/null +++ b/Documentation/driver-api/s390-drivers.rst @@ -0,0 +1,111 @@ +=================================== +Writing s390 channel device drivers +=================================== + +:Author: Cornelia Huck + +Introduction +============ + +This document describes the interfaces available for device drivers that +drive s390 based channel attached I/O devices. This includes interfaces +for interaction with the hardware and interfaces for interacting with +the common driver core. Those interfaces are provided by the s390 common +I/O layer. + +The document assumes a familarity with the technical terms associated +with the s390 channel I/O architecture. For a description of this +architecture, please refer to the "z/Architecture: Principles of +Operation", IBM publication no. SA22-7832. + +While most I/O devices on a s390 system are typically driven through the +channel I/O mechanism described here, there are various other methods +(like the diag interface). These are out of the scope of this document. + +Some additional information can also be found in the kernel source under +Documentation/s390/driver-model.txt. + +The ccw bus +=========== + +The ccw bus typically contains the majority of devices available to a +s390 system. Named after the channel command word (ccw), the basic +command structure used to address its devices, the ccw bus contains +so-called channel attached devices. They are addressed via I/O +subchannels, visible on the css bus. A device driver for +channel-attached devices, however, will never interact with the +subchannel directly, but only via the I/O device on the ccw bus, the ccw +device. + +I/O functions for channel-attached devices +------------------------------------------ + +Some hardware structures have been translated into C structures for use +by the common I/O layer and device drivers. For more information on the +hardware structures represented here, please consult the Principles of +Operation. + +.. kernel-doc:: arch/s390/include/asm/cio.h + :internal: + +ccw devices +----------- + +Devices that want to initiate channel I/O need to attach to the ccw bus. +Interaction with the driver core is done via the common I/O layer, which +provides the abstractions of ccw devices and ccw device drivers. + +The functions that initiate or terminate channel I/O all act upon a ccw +device structure. Device drivers must not bypass those functions or +strange side effects may happen. + +.. kernel-doc:: arch/s390/include/asm/ccwdev.h + :internal: + +.. kernel-doc:: drivers/s390/cio/device.c + :export: + +.. kernel-doc:: drivers/s390/cio/device_ops.c + :export: + +The channel-measurement facility +-------------------------------- + +The channel-measurement facility provides a means to collect measurement +data which is made available by the channel subsystem for each channel +attached device. + +.. kernel-doc:: arch/s390/include/asm/cmb.h + :internal: + +.. kernel-doc:: drivers/s390/cio/cmf.c + :export: + +The ccwgroup bus +================ + +The ccwgroup bus only contains artificial devices, created by the user. +Many networking devices (e.g. qeth) are in fact composed of several ccw +devices (like read, write and data channel for qeth). The ccwgroup bus +provides a mechanism to create a meta-device which contains those ccw +devices as slave devices and can be associated with the netdevice. + +ccw group devices +----------------- + +.. kernel-doc:: arch/s390/include/asm/ccwgroup.h + :internal: + +.. kernel-doc:: drivers/s390/cio/ccwgroup.c + :export: + +Generic interfaces +================== + +Some interfaces are available to other drivers that do not necessarily +have anything to do with the busses described above, but still are +indirectly using basic infrastructure in the common I/O layer. One +example is the support for adapter interrupts. + +.. kernel-doc:: drivers/s390/cio/airq.c + :export: diff --git a/Documentation/driver-api/scsi.rst b/Documentation/driver-api/scsi.rst new file mode 100644 index 00000000000000..859fb672319f9c --- /dev/null +++ b/Documentation/driver-api/scsi.rst @@ -0,0 +1,344 @@ +===================== +SCSI Interfaces Guide +===================== + +:Author: James Bottomley +:Author: Rob Landley + +Introduction +============ + +Protocol vs bus +--------------- + +Once upon a time, the Small Computer Systems Interface defined both a +parallel I/O bus and a data protocol to connect a wide variety of +peripherals (disk drives, tape drives, modems, printers, scanners, +optical drives, test equipment, and medical devices) to a host computer. + +Although the old parallel (fast/wide/ultra) SCSI bus has largely fallen +out of use, the SCSI command set is more widely used than ever to +communicate with devices over a number of different busses. + +The `SCSI protocol `__ is a big-endian +peer-to-peer packet based protocol. SCSI commands are 6, 10, 12, or 16 +bytes long, often followed by an associated data payload. + +SCSI commands can be transported over just about any kind of bus, and +are the default protocol for storage devices attached to USB, SATA, SAS, +Fibre Channel, FireWire, and ATAPI devices. SCSI packets are also +commonly exchanged over Infiniband, +`I20 `__, TCP/IP +(`iSCSI `__), even `Parallel +ports `__. + +Design of the Linux SCSI subsystem +---------------------------------- + +The SCSI subsystem uses a three layer design, with upper, mid, and low +layers. Every operation involving the SCSI subsystem (such as reading a +sector from a disk) uses one driver at each of the 3 levels: one upper +layer driver, one lower layer driver, and the SCSI midlayer. + +The SCSI upper layer provides the interface between userspace and the +kernel, in the form of block and char device nodes for I/O and ioctl(). +The SCSI lower layer contains drivers for specific hardware devices. + +In between is the SCSI mid-layer, analogous to a network routing layer +such as the IPv4 stack. The SCSI mid-layer routes a packet based data +protocol between the upper layer's /dev nodes and the corresponding +devices in the lower layer. It manages command queues, provides error +handling and power management functions, and responds to ioctl() +requests. + +SCSI upper layer +================ + +The upper layer supports the user-kernel interface by providing device +nodes. + +sd (SCSI Disk) +-------------- + +sd (sd_mod.o) + +sr (SCSI CD-ROM) +---------------- + +sr (sr_mod.o) + +st (SCSI Tape) +-------------- + +st (st.o) + +sg (SCSI Generic) +----------------- + +sg (sg.o) + +ch (SCSI Media Changer) +----------------------- + +ch (ch.c) + +SCSI mid layer +============== + +SCSI midlayer implementation +---------------------------- + +include/scsi/scsi_device.h +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/scsi/scsi_device.h + :internal: + +drivers/scsi/scsi.c +~~~~~~~~~~~~~~~~~~~ + +Main file for the SCSI midlayer. + +.. kernel-doc:: drivers/scsi/scsi.c + :export: + +drivers/scsi/scsicam.c +~~~~~~~~~~~~~~~~~~~~~~ + +`SCSI Common Access +Method `__ support +functions, for use with HDIO_GETGEO, etc. + +.. kernel-doc:: drivers/scsi/scsicam.c + :export: + +drivers/scsi/scsi_error.c +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Common SCSI error/timeout handling routines. + +.. kernel-doc:: drivers/scsi/scsi_error.c + :export: + +drivers/scsi/scsi_devinfo.c +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Manage scsi_dev_info_list, which tracks blacklisted and whitelisted +devices. + +.. kernel-doc:: drivers/scsi/scsi_devinfo.c + :internal: + +drivers/scsi/scsi_ioctl.c +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Handle ioctl() calls for SCSI devices. + +.. kernel-doc:: drivers/scsi/scsi_ioctl.c + :export: + +drivers/scsi/scsi_lib.c +~~~~~~~~~~~~~~~~~~~~~~~~ + +SCSI queuing library. + +.. kernel-doc:: drivers/scsi/scsi_lib.c + :export: + +drivers/scsi/scsi_lib_dma.c +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +SCSI library functions depending on DMA (map and unmap scatter-gather +lists). + +.. kernel-doc:: drivers/scsi/scsi_lib_dma.c + :export: + +drivers/scsi/scsi_module.c +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_module.c contains legacy support for +old-style host templates. It should never be used by any new driver. + +drivers/scsi/scsi_proc.c +~~~~~~~~~~~~~~~~~~~~~~~~~ + +The functions in this file provide an interface between the PROC file +system and the SCSI device drivers It is mainly used for debugging, +statistics and to pass information directly to the lowlevel driver. I.E. +plumbing to manage /proc/scsi/\* + +.. kernel-doc:: drivers/scsi/scsi_proc.c + :internal: + +drivers/scsi/scsi_netlink.c +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Infrastructure to provide async events from transports to userspace via +netlink, using a single NETLINK_SCSITRANSPORT protocol for all +transports. See `the original patch +submission `__ for +more details. + +.. kernel-doc:: drivers/scsi/scsi_netlink.c + :internal: + +drivers/scsi/scsi_scan.c +~~~~~~~~~~~~~~~~~~~~~~~~~ + +Scan a host to determine which (if any) devices are attached. The +general scanning/probing algorithm is as follows, exceptions are made to +it depending on device specific flags, compilation options, and global +variable (boot or module load time) settings. A specific LUN is scanned +via an INQUIRY command; if the LUN has a device attached, a scsi_device +is allocated and setup for it. For every id of every channel on the +given host, start by scanning LUN 0. Skip hosts that don't respond at +all to a scan of LUN 0. Otherwise, if LUN 0 has a device attached, +allocate and setup a scsi_device for it. If target is SCSI-3 or up, +issue a REPORT LUN, and scan all of the LUNs returned by the REPORT LUN; +else, sequentially scan LUNs up until some maximum is reached, or a LUN +is seen that cannot have a device attached to it. + +.. kernel-doc:: drivers/scsi/scsi_scan.c + :internal: + +drivers/scsi/scsi_sysctl.c +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Set up the sysctl entry: "/dev/scsi/logging_level" +(DEV_SCSI_LOGGING_LEVEL) which sets/returns scsi_logging_level. + +drivers/scsi/scsi_sysfs.c +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +SCSI sysfs interface routines. + +.. kernel-doc:: drivers/scsi/scsi_sysfs.c + :export: + +drivers/scsi/hosts.c +~~~~~~~~~~~~~~~~~~~~ + +mid to lowlevel SCSI driver interface + +.. kernel-doc:: drivers/scsi/hosts.c + :export: + +drivers/scsi/constants.c +~~~~~~~~~~~~~~~~~~~~~~~~ + +mid to lowlevel SCSI driver interface + +.. kernel-doc:: drivers/scsi/constants.c + :export: + +Transport classes +----------------- + +Transport classes are service libraries for drivers in the SCSI lower +layer, which expose transport attributes in sysfs. + +Fibre Channel transport +~~~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_transport_fc.c defines transport attributes +for Fibre Channel. + +.. kernel-doc:: drivers/scsi/scsi_transport_fc.c + :export: + +iSCSI transport class +~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_transport_iscsi.c defines transport +attributes for the iSCSI class, which sends SCSI packets over TCP/IP +connections. + +.. kernel-doc:: drivers/scsi/scsi_transport_iscsi.c + :export: + +Serial Attached SCSI (SAS) transport class +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_transport_sas.c defines transport +attributes for Serial Attached SCSI, a variant of SATA aimed at large +high-end systems. + +The SAS transport class contains common code to deal with SAS HBAs, an +aproximated representation of SAS topologies in the driver model, and +various sysfs attributes to expose these topologies and management +interfaces to userspace. + +In addition to the basic SCSI core objects this transport class +introduces two additional intermediate objects: The SAS PHY as +represented by struct sas_phy defines an "outgoing" PHY on a SAS HBA or +Expander, and the SAS remote PHY represented by struct sas_rphy defines +an "incoming" PHY on a SAS Expander or end device. Note that this is +purely a software concept, the underlying hardware for a PHY and a +remote PHY is the exactly the same. + +There is no concept of a SAS port in this code, users can see what PHYs +form a wide port based on the port_identifier attribute, which is the +same for all PHYs in a port. + +.. kernel-doc:: drivers/scsi/scsi_transport_sas.c + :export: + +SATA transport class +~~~~~~~~~~~~~~~~~~~~ + +The SATA transport is handled by libata, which has its own book of +documentation in this directory. + +Parallel SCSI (SPI) transport class +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_transport_spi.c defines transport +attributes for traditional (fast/wide/ultra) SCSI busses. + +.. kernel-doc:: drivers/scsi/scsi_transport_spi.c + :export: + +SCSI RDMA (SRP) transport class +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_transport_srp.c defines transport +attributes for SCSI over Remote Direct Memory Access. + +.. kernel-doc:: drivers/scsi/scsi_transport_srp.c + :export: + +SCSI lower layer +================ + +Host Bus Adapter transport types +-------------------------------- + +Many modern device controllers use the SCSI command set as a protocol to +communicate with their devices through many different types of physical +connections. + +In SCSI language a bus capable of carrying SCSI commands is called a +"transport", and a controller connecting to such a bus is called a "host +bus adapter" (HBA). + +Debug transport +~~~~~~~~~~~~~~~ + +The file drivers/scsi/scsi_debug.c simulates a host adapter with a +variable number of disks (or disk like devices) attached, sharing a +common amount of RAM. Does a lot of checking to make sure that we are +not getting blocks mixed up, and panics the kernel if anything out of +the ordinary is seen. + +To be more realistic, the simulated devices have the transport +attributes of SAS disks. + +For documentation see http://sg.danny.cz/sg/sdebug26.html + +todo +~~~~ + +Parallel (fast/wide/ultra) SCSI, USB, SATA, SAS, Fibre Channel, +FireWire, ATAPI devices, Infiniband, I20, iSCSI, Parallel ports, +netlink... diff --git a/Documentation/driver-api/w1.rst b/Documentation/driver-api/w1.rst new file mode 100644 index 00000000000000..c1da8f0cb476b2 --- /dev/null +++ b/Documentation/driver-api/w1.rst @@ -0,0 +1,70 @@ +====================== +W1: Dallas' 1-wire bus +====================== + +:Author: David Fries + +W1 API internal to the kernel +============================= + +W1 API internal to the kernel +----------------------------- + +drivers/w1/w1.h +~~~~~~~~~~~~~~~ + +W1 core functions. + +.. kernel-doc:: drivers/w1/w1.h + :internal: + +drivers/w1/w1.c +~~~~~~~~~~~~~~~ + +W1 core functions. + +.. kernel-doc:: drivers/w1/w1.c + :internal: + +drivers/w1/w1_family.h +~~~~~~~~~~~~~~~~~~~~~~~ + +Allows registering device family operations. + +.. kernel-doc:: drivers/w1/w1_family.h + :internal: + +drivers/w1/w1_family.c +~~~~~~~~~~~~~~~~~~~~~~~ + +Allows registering device family operations. + +.. kernel-doc:: drivers/w1/w1_family.c + :export: + +drivers/w1/w1_int.c +~~~~~~~~~~~~~~~~~~~~ + +W1 internal initialization for master devices. + +.. kernel-doc:: drivers/w1/w1_int.c + :export: + +drivers/w1/w1_netlink.h +~~~~~~~~~~~~~~~~~~~~~~~~ + +W1 external netlink API structures and commands. + +.. kernel-doc:: drivers/w1/w1_netlink.h + :internal: + +drivers/w1/w1_io.c +~~~~~~~~~~~~~~~~~~~ + +W1 input/output. + +.. kernel-doc:: drivers/w1/w1_io.c + :export: + +.. kernel-doc:: drivers/w1/w1_io.c + :internal: diff --git a/Documentation/fb/api.txt b/Documentation/fb/api.txt index d4ff7de8570082..d52cf1e3b975a9 100644 --- a/Documentation/fb/api.txt +++ b/Documentation/fb/api.txt @@ -289,12 +289,12 @@ the FB_CAP_FOURCC bit in the fb_fix_screeninfo capabilities field. FOURCC definitions are located in the linux/videodev2.h header. However, and despite starting with the V4L2_PIX_FMT_prefix, they are not restricted to V4L2 and don't require usage of the V4L2 subsystem. FOURCC documentation is -available in Documentation/DocBook/v4l/pixfmt.xml. +available in Documentation/media/uapi/v4l/pixfmt.rst. To select a format, applications set the grayscale field to the desired FOURCC. For YUV formats, they should also select the appropriate colorspace by setting the colorspace field to one of the colorspaces listed in linux/videodev2.h and -documented in Documentation/DocBook/v4l/colorspaces.xml. +documented in Documentation/media/uapi/v4l/colorspaces.rst. The red, green, blue and transp fields are not used with the FOURCC-based API. For forward compatibility reasons applications must zero those fields, and diff --git a/Documentation/filesystems/conf.py b/Documentation/filesystems/conf.py new file mode 100644 index 00000000000000..ea44172af5c493 --- /dev/null +++ b/Documentation/filesystems/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "Linux Filesystems API" + +tags.add("subproject") + +latex_documents = [ + ('index', 'filesystems.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst new file mode 100644 index 00000000000000..256e10eedba4e4 --- /dev/null +++ b/Documentation/filesystems/index.rst @@ -0,0 +1,317 @@ +===================== +Linux Filesystems API +===================== + +The Linux VFS +============= + +The Filesystem types +-------------------- + +.. kernel-doc:: include/linux/fs.h + :internal: + +The Directory Cache +------------------- + +.. kernel-doc:: fs/dcache.c + :export: + +.. kernel-doc:: include/linux/dcache.h + :internal: + +Inode Handling +-------------- + +.. kernel-doc:: fs/inode.c + :export: + +.. kernel-doc:: fs/bad_inode.c + :export: + +Registration and Superblocks +---------------------------- + +.. kernel-doc:: fs/super.c + :export: + +File Locks +---------- + +.. kernel-doc:: fs/locks.c + :export: + +.. kernel-doc:: fs/locks.c + :internal: + +Other Functions +--------------- + +.. kernel-doc:: fs/mpage.c + :export: + +.. kernel-doc:: fs/namei.c + :export: + +.. kernel-doc:: fs/buffer.c + :export: + +.. kernel-doc:: block/bio.c + :export: + +.. kernel-doc:: fs/seq_file.c + :export: + +.. kernel-doc:: fs/filesystems.c + :export: + +.. kernel-doc:: fs/fs-writeback.c + :export: + +.. kernel-doc:: fs/block_dev.c + :export: + +The proc filesystem +=================== + +sysctl interface +---------------- + +.. kernel-doc:: kernel/sysctl.c + :export: + +proc filesystem interface +------------------------- + +.. kernel-doc:: fs/proc/base.c + :internal: + +Events based on file descriptors +================================ + +.. kernel-doc:: fs/eventfd.c + :export: + +The Filesystem for Exporting Kernel Objects +=========================================== + +.. kernel-doc:: fs/sysfs/file.c + :export: + +.. kernel-doc:: fs/sysfs/symlink.c + :export: + +The debugfs filesystem +====================== + +debugfs interface +----------------- + +.. kernel-doc:: fs/debugfs/inode.c + :export: + +.. kernel-doc:: fs/debugfs/file.c + :export: + +The Linux Journalling API +========================= + +Overview +-------- + +Details +~~~~~~~ + +The journalling layer is easy to use. You need to first of all create a +journal_t data structure. There are two calls to do this dependent on +how you decide to allocate the physical media on which the journal +resides. The :c:func:`jbd2_journal_init_inode` call is for journals stored in +filesystem inodes, or the :c:func:`jbd2_journal_init_dev` call can be used +for journal stored on a raw device (in a continuous range of blocks). A +journal_t is a typedef for a struct pointer, so when you are finally +finished make sure you call :c:func:`jbd2_journal_destroy` on it to free up +any used kernel memory. + +Once you have got your journal_t object you need to 'mount' or load the +journal file. The journalling layer expects the space for the journal +was already allocated and initialized properly by the userspace tools. +When loading the journal you must call :c:func:`jbd2_journal_load` to process +journal contents. If the client file system detects the journal contents +does not need to be processed (or even need not have valid contents), it +may call :c:func:`jbd2_journal_wipe` to clear the journal contents before +calling :c:func:`jbd2_journal_load`. + +Note that jbd2_journal_wipe(..,0) calls +:c:func:`jbd2_journal_skip_recovery` for you if it detects any outstanding +transactions in the journal and similarly :c:func:`jbd2_journal_load` will +call :c:func:`jbd2_journal_recover` if necessary. I would advise reading +:c:func:`ext4_load_journal` in fs/ext4/super.c for examples on this stage. + +Now you can go ahead and start modifying the underlying filesystem. +Almost. + +You still need to actually journal your filesystem changes, this is done +by wrapping them into transactions. Additionally you also need to wrap +the modification of each of the buffers with calls to the journal layer, +so it knows what the modifications you are actually making are. To do +this use :c:func:`jbd2_journal_start` which returns a transaction handle. + +:c:func:`jbd2_journal_start` and its counterpart :c:func:`jbd2_journal_stop`, +which indicates the end of a transaction are nestable calls, so you can +reenter a transaction if necessary, but remember you must call +:c:func:`jbd2_journal_stop` the same number of times as +:c:func:`jbd2_journal_start` before the transaction is completed (or more +accurately leaves the update phase). Ext4/VFS makes use of this feature to +simplify handling of inode dirtying, quota support, etc. + +Inside each transaction you need to wrap the modifications to the +individual buffers (blocks). Before you start to modify a buffer you +need to call :c:func:`jbd2_journal_get_create_access()` / +:c:func:`jbd2_journal_get_write_access()` / +:c:func:`jbd2_journal_get_undo_access()` as appropriate, this allows the +journalling layer to copy the unmodified +data if it needs to. After all the buffer may be part of a previously +uncommitted transaction. At this point you are at last ready to modify a +buffer, and once you are have done so you need to call +:c:func:`jbd2_journal_dirty_metadata`. Or if you've asked for access to a +buffer you now know is now longer required to be pushed back on the +device you can call :c:func:`jbd2_journal_forget` in much the same way as you +might have used :c:func:`bforget` in the past. + +A :c:func:`jbd2_journal_flush` may be called at any time to commit and +checkpoint all your transactions. + +Then at umount time , in your :c:func:`put_super` you can then call +:c:func:`jbd2_journal_destroy` to clean up your in-core journal object. + +Unfortunately there a couple of ways the journal layer can cause a +deadlock. The first thing to note is that each task can only have a +single outstanding transaction at any one time, remember nothing commits +until the outermost :c:func:`jbd2_journal_stop`. This means you must complete +the transaction at the end of each file/inode/address etc. operation you +perform, so that the journalling system isn't re-entered on another +journal. Since transactions can't be nested/batched across differing +journals, and another filesystem other than yours (say ext4) may be +modified in a later syscall. + +The second case to bear in mind is that :c:func:`jbd2_journal_start` can block +if there isn't enough space in the journal for your transaction (based +on the passed nblocks param) - when it blocks it merely(!) needs to wait +for transactions to complete and be committed from other tasks, so +essentially we are waiting for :c:func:`jbd2_journal_stop`. So to avoid +deadlocks you must treat :c:func:`jbd2_journal_start` / +:c:func:`jbd2_journal_stop` as if they were semaphores and include them in +your semaphore ordering rules to prevent +deadlocks. Note that :c:func:`jbd2_journal_extend` has similar blocking +behaviour to :c:func:`jbd2_journal_start` so you can deadlock here just as +easily as on :c:func:`jbd2_journal_start`. + +Try to reserve the right number of blocks the first time. ;-). This will +be the maximum number of blocks you are going to touch in this +transaction. I advise having a look at at least ext4_jbd.h to see the +basis on which ext4 uses to make these decisions. + +Another wriggle to watch out for is your on-disk block allocation +strategy. Why? Because, if you do a delete, you need to ensure you +haven't reused any of the freed blocks until the transaction freeing +these blocks commits. If you reused these blocks and crash happens, +there is no way to restore the contents of the reallocated blocks at the +end of the last fully committed transaction. One simple way of doing +this is to mark blocks as free in internal in-memory block allocation +structures only after the transaction freeing them commits. Ext4 uses +journal commit callback for this purpose. + +With journal commit callbacks you can ask the journalling layer to call +a callback function when the transaction is finally committed to disk, +so that you can do some of your own management. You ask the journalling +layer for calling the callback by simply setting +``journal->j_commit_callback`` function pointer and that function is +called after each transaction commit. You can also use +``transaction->t_private_list`` for attaching entries to a transaction +that need processing when the transaction commits. + +JBD2 also provides a way to block all transaction updates via +:c:func:`jbd2_journal_lock_updates()` / +:c:func:`jbd2_journal_unlock_updates()`. Ext4 uses this when it wants a +window with a clean and stable fs for a moment. E.g. + +:: + + + jbd2_journal_lock_updates() //stop new stuff happening.. + jbd2_journal_flush() // checkpoint everything. + ..do stuff on stable fs + jbd2_journal_unlock_updates() // carry on with filesystem use. + +The opportunities for abuse and DOS attacks with this should be obvious, +if you allow unprivileged userspace to trigger codepaths containing +these calls. + +Summary +~~~~~~~ + +Using the journal is a matter of wrapping the different context changes, +being each mount, each modification (transaction) and each changed +buffer to tell the journalling layer about them. + +Data Types +---------- + +The journalling layer uses typedefs to 'hide' the concrete definitions +of the structures used. As a client of the JBD2 layer you can just rely +on the using the pointer as a magic cookie of some sort. Obviously the +hiding is not enforced as this is 'C'. + +Structures +~~~~~~~~~~ + +.. kernel-doc:: include/linux/jbd2.h + :internal: + +Functions +--------- + +The functions here are split into two groups those that affect a journal +as a whole, and those which are used to manage transactions + +Journal Level +~~~~~~~~~~~~~ + +.. kernel-doc:: fs/jbd2/journal.c + :export: + +.. kernel-doc:: fs/jbd2/recovery.c + :internal: + +Transasction Level +~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: fs/jbd2/transaction.c + +See also +-------- + +`Journaling the Linux ext2fs Filesystem, LinuxExpo 98, Stephen +Tweedie `__ + +`Ext3 Journalling FileSystem, OLS 2000, Dr. Stephen +Tweedie `__ + +splice API +========== + +splice is a method for moving blocks of data around inside the kernel, +without continually transferring them between the kernel and user space. + +.. kernel-doc:: fs/splice.c + +pipes API +========= + +Pipe interfaces are all for in-kernel (builtin image) use. They are not +exported for use by modules. + +.. kernel-doc:: include/linux/pipe_fs_i.h + :internal: + +.. kernel-doc:: fs/pipe.c diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt index fe03d10bb79a36..b86831acd5834e 100644 --- a/Documentation/filesystems/nfs/idmapper.txt +++ b/Documentation/filesystems/nfs/idmapper.txt @@ -55,7 +55,7 @@ request-key will find the first matching line and corresponding program. In this case, /some/other/program will handle all uid lookups and /usr/sbin/nfs.idmap will handle gid, user, and group lookups. -See for more information +See for more information about the request-key function. diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index c572f092739e04..037a39ac180763 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -12,6 +12,7 @@ Linux GPU Driver Developer's Guide drm-uapi i915 meson + pl111 tinydrm vc4 vga-switcheroo diff --git a/Documentation/gpu/pl111.rst b/Documentation/gpu/pl111.rst new file mode 100644 index 00000000000000..9b03736d33dd73 --- /dev/null +++ b/Documentation/gpu/pl111.rst @@ -0,0 +1,6 @@ +========================================== + drm/pl111 ARM PrimeCell PL111 CLCD Driver +========================================== + +.. kernel-doc:: drivers/gpu/drm/pl111/pl111_drv.c + :doc: ARM PrimeCell PL111 CLCD Driver diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 1bdb7356a31028..6162d0e9dc28f3 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -228,7 +228,7 @@ The DRM reference documentation is still lacking kerneldoc in a few areas. The task would be to clean up interfaces like moving functions around between files to better group them and improving the interfaces like dropping return values for functions that never fail. Then write kerneldoc for all exported -functions and an overview section and integrate it all into the drm DocBook. +functions and an overview section and integrate it all into the drm book. See https://dri.freedesktop.org/docs/drm/ for what's there already. diff --git a/Documentation/hwmon/ads1015 b/Documentation/hwmon/ads1015 index 063b80d857b1f8..02d2a459385f39 100644 --- a/Documentation/hwmon/ads1015 +++ b/Documentation/hwmon/ads1015 @@ -40,7 +40,7 @@ By default all inputs are exported. Platform Data ------------- -In linux/i2c/ads1015.h platform data is defined, channel_data contains +In linux/platform_data/ads1015.h platform data is defined, channel_data contains configuration data for the used input combinations: - pga is the programmable gain amplifier (values are full scale) 0: +/- 6.144 V diff --git a/Documentation/hwmon/adt7475 b/Documentation/hwmon/adt7475 index 0502f2b464e1c0..09d73a10644c4e 100644 --- a/Documentation/hwmon/adt7475 +++ b/Documentation/hwmon/adt7475 @@ -109,6 +109,15 @@ fan speed) is applied. PWM values range from 0 (off) to 255 (full speed). Fan speed may be set to maximum when the temperature sensor associated with the PWM control exceeds temp#_max. +At Tmin - hysteresis the PWM output can either be off (0% duty cycle) or at the +minimum (i.e. auto_point1_pwm). This behaviour can be configured using the +pwm[1-*]_stall_disable sysfs attribute. A value of 0 means the fans will shut +off. A value of 1 means the fans will run at auto_point1_pwm. + +The responsiveness of the ADT747x to temperature changes can be configured. +This allows smoothing of the fan speed transition. To set the transition time +set the value in ms in the temp[1-*]_smoothing sysfs attribute. + Notes ----- diff --git a/Documentation/hwmon/ir35221 b/Documentation/hwmon/ir35221 new file mode 100644 index 00000000000000..f7e112752c0467 --- /dev/null +++ b/Documentation/hwmon/ir35221 @@ -0,0 +1,87 @@ +Kernel driver ir35221 +===================== + +Supported chips: + * Infinion IR35221 + Prefix: 'ir35221' + Addresses scanned: - + Datasheet: Datasheet is not publicly available. + +Author: Samuel Mendoza-Jonas + + +Description +----------- + +IR35221 is a Digital DC-DC Multiphase Converter + + +Usage Notes +----------- + +This driver does not probe for PMBus devices. You will have to instantiate +devices explicitly. + +Example: the following commands will load the driver for an IR35221 +at address 0x70 on I2C bus #4: + +# modprobe ir35221 +# echo ir35221 0x70 > /sys/bus/i2c/devices/i2c-4/new_device + + +Sysfs attributes +---------------- + +curr1_label "iin" +curr1_input Measured input current +curr1_max Maximum current +curr1_max_alarm Current high alarm + +curr[2-3]_label "iout[1-2]" +curr[2-3]_input Measured output current +curr[2-3]_crit Critical maximum current +curr[2-3]_crit_alarm Current critical high alarm +curr[2-3]_highest Highest output current +curr[2-3]_lowest Lowest output current +curr[2-3]_max Maximum current +curr[2-3]_max_alarm Current high alarm + +in1_label "vin" +in1_input Measured input voltage +in1_crit Critical maximum input voltage +in1_crit_alarm Input voltage critical high alarm +in1_highest Highest input voltage +in1_lowest Lowest input voltage +in1_min Minimum input voltage +in1_min_alarm Input voltage low alarm + +in[2-3]_label "vout[1-2]" +in[2-3]_input Measured output voltage +in[2-3]_lcrit Critical minimum output voltage +in[2-3]_lcrit_alarm Output voltage critical low alarm +in[2-3]_crit Critical maximum output voltage +in[2-3]_crit_alarm Output voltage critical high alarm +in[2-3]_highest Highest output voltage +in[2-3]_lowest Lowest output voltage +in[2-3]_max Maximum output voltage +in[2-3]_max_alarm Output voltage high alarm +in[2-3]_min Minimum output voltage +in[2-3]_min_alarm Output voltage low alarm + +power1_label "pin" +power1_input Measured input power +power1_alarm Input power high alarm +power1_max Input power limit + +power[2-3]_label "pout[1-2]" +power[2-3]_input Measured output power +power[2-3]_max Output power limit +power[2-3]_max_alarm Output power high alarm + +temp[1-2]_input Measured temperature +temp[1-2]_crit Critical high temperature +temp[1-2]_crit_alarm Chip temperature critical high alarm +temp[1-2]_highest Highest temperature +temp[1-2]_lowest Lowest temperature +temp[1-2]_max Maximum temperature +temp[1-2]_max_alarm Chip temperature high alarm diff --git a/Documentation/hwmon/ltc4245 b/Documentation/hwmon/ltc4245 index b478b086496586..4ca7a9da09f918 100644 --- a/Documentation/hwmon/ltc4245 +++ b/Documentation/hwmon/ltc4245 @@ -96,7 +96,7 @@ slowly, -EAGAIN will be returned when you read the sysfs attribute containing the sensor reading. The LTC4245 chip can be configured to sample all GPIO pins with two methods: -1) platform data -- see include/linux/i2c/ltc4245.h +1) platform data -- see include/linux/platform_data/ltc4245.h 2) OF device tree -- add the "ltc4245,use-extra-gpios" property to each chip The default mode of operation is to sample a single GPIO pin. diff --git a/Documentation/hwmon/pmbus-core b/Documentation/hwmon/pmbus-core index 31e4720fed18c7..8ed10e9ddfb589 100644 --- a/Documentation/hwmon/pmbus-core +++ b/Documentation/hwmon/pmbus-core @@ -253,7 +253,7 @@ Specifically, it provides the following information. PMBus driver platform data ========================== -PMBus platform data is defined in include/linux/i2c/pmbus.h. Platform data +PMBus platform data is defined in include/linux/pmbus.h. Platform data currently only provides a flag field with a single bit used. #define PMBUS_SKIP_STATUS_CHECK (1 << 0) diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface index bcf919d8625ceb..5ff19447ac4420 100644 --- a/Documentation/i2c/dev-interface +++ b/Documentation/i2c/dev-interface @@ -191,7 +191,7 @@ checking on future transactions.) 4* Other ioctl() calls are converted to in-kernel function calls by i2c-dev. Examples include I2C_FUNCS, which queries the I2C adapter functionality using i2c.h:i2c_get_functionality(), and I2C_SMBUS, which -performs an SMBus transaction using i2c-core.c:i2c_smbus_xfer(). +performs an SMBus transaction using i2c-core-smbus.c:i2c_smbus_xfer(). The i2c-dev driver is responsible for checking all the parameters that come from user-space for validity. After this point, there is no @@ -200,13 +200,13 @@ and calls that would have been performed by kernel I2C chip drivers directly. This means that I2C bus drivers don't need to implement anything special to support access from user-space. -5* These i2c-core.c/i2c.h functions are wrappers to the actual -implementation of your I2C bus driver. Each adapter must declare -callback functions implementing these standard calls. -i2c.h:i2c_get_functionality() calls i2c_adapter.algo->functionality(), -while i2c-core.c:i2c_smbus_xfer() calls either +5* These i2c.h functions are wrappers to the actual implementation of +your I2C bus driver. Each adapter must declare callback functions +implementing these standard calls. i2c.h:i2c_get_functionality() calls +i2c_adapter.algo->functionality(), while +i2c-core-smbus.c:i2c_smbus_xfer() calls either adapter.algo->smbus_xfer() if it is implemented, or if not, -i2c-core.c:i2c_smbus_xfer_emulated() which in turn calls +i2c-core-smbus.c:i2c_smbus_xfer_emulated() which in turn calls i2c_adapter.algo->master_xfer(). After your I2C bus driver has processed these requests, execution runs diff --git a/Documentation/index.rst b/Documentation/index.rst index bc67dbf76eb041..e9017bb3a6ce06 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -51,6 +51,7 @@ merged much easier. process/index dev-tools/index doc-guide/index + kernel-hacking/index Kernel API documentation ------------------------ @@ -67,11 +68,24 @@ needed). driver-api/index core-api/index media/index + networking/index input/index gpu/index security/index sound/index crypto/index + filesystems/index + +Architecture-specific documentation +----------------------------------- + +These books provide programming details about architecture-specific +implementation. + +.. toctree:: + :maxdepth: 2 + + sh/index Korean translations ------------------- diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index e18daca65ccd2a..659afd56ecdb3e 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -1331,7 +1331,7 @@ See subsequent chapter for the syntax of the Kbuild file. --- 7.5 mandatory-y mandatory-y is essentially used by include/uapi/asm-generic/Kbuild.asm - to define the minimun set of headers that must be exported in + to define the minimum set of headers that must be exported in include/asm. The convention is to list one subdir per line and diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index 104740ea004126..c23e2c5ab80da3 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -17,8 +17,8 @@ The format for this documentation is called the kernel-doc format. It is documented in this Documentation/kernel-doc-nano-HOWTO.txt file. This style embeds the documentation within the source files, using -a few simple conventions. The scripts/kernel-doc perl script, some -SGML templates in Documentation/DocBook, and other tools understand +a few simple conventions. The scripts/kernel-doc perl script, the +Documentation/sphinx/kerneldoc.py Sphinx extension and other tools understand these conventions, and are used to extract this embedded documentation into various documents. @@ -122,15 +122,9 @@ are: - scripts/kernel-doc This is a perl script that hunts for the block comments and can mark - them up directly into DocBook, man, text, and HTML. (No, not + them up directly into DocBook, ReST, man, text, and HTML. (No, not texinfo.) -- Documentation/DocBook/*.tmpl - - These are SGML template files, which are normal SGML files with - special place-holders for where the extracted documentation should - go. - - scripts/docproc.c This is a program for converting SGML template files into SGML @@ -145,25 +139,18 @@ are: - Makefile - The targets 'xmldocs', 'psdocs', 'pdfdocs', and 'htmldocs' are used - to build XML DocBook files, PostScript files, PDF files, and html files - in Documentation/DocBook. The older target 'sgmldocs' is equivalent - to 'xmldocs'. - -- Documentation/DocBook/Makefile - - This is where C files are associated with SGML templates. - + The targets 'xmldocs', 'latexdocs', 'pdfdocs', 'epubdocs'and 'htmldocs' + are used to build XML DocBook files, LaTeX files, PDF files, + ePub files and html files in Documentation/. How to extract the documentation -------------------------------- If you just want to read the ready-made books on the various -subsystems (see Documentation/DocBook/*.tmpl), just type 'make -psdocs', or 'make pdfdocs', or 'make htmldocs', depending on your -preference. If you would rather read a different format, you can type -'make xmldocs' and then use DocBook tools to convert -Documentation/DocBook/*.xml to a format of your choice (for example, +subsystems, just type 'make epubdocs', or 'make pdfdocs', or 'make htmldocs', +depending on your preference. If you would rather read a different format, +you can type 'make xmldocs' and then use DocBook tools to convert +Documentation/output/*.xml to a format of your choice (for example, 'db2html ...' if 'make htmldocs' was not defined). If you want to see man pages instead, you can do this: @@ -329,37 +316,7 @@ This is done by using a DOC: section keyword with a section title. E.g.: * hardware, software, or its subject(s). */ -DOC: sections are used in SGML templates files as indicated below. - - -How to make new SGML template files ------------------------------------ - -SGML template files (*.tmpl) are like normal SGML files, except that -they can contain escape sequences where extracted documentation should -be inserted. - -!E is replaced by the documentation, in , for -functions that are exported using EXPORT_SYMBOL: the function list is -collected from files listed in Documentation/DocBook/Makefile. - -!I is replaced by the documentation for functions that are -_not_ exported using EXPORT_SYMBOL. - -!D is used to name additional files to search for functions -exported using EXPORT_SYMBOL. - -!F is replaced by the -documentation, in , for the functions listed. - -!P
    is replaced by the contents of the DOC: -section titled
    from . -Spaces are allowed in
    ; do not quote the
    . - -!C is replaced by nothing, but makes the tools check that -all DOC: sections and documented functions, symbols, etc. are used. -This makes sense to use when you use !F/!P only and want to verify -that all documentation is included. +DOC: sections are used in ReST files. Tim. */ diff --git a/Documentation/kernel-hacking/conf.py b/Documentation/kernel-hacking/conf.py new file mode 100644 index 00000000000000..3d8acf0f33adaf --- /dev/null +++ b/Documentation/kernel-hacking/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "Kernel Hacking Guides" + +tags.add("subproject") + +latex_documents = [ + ('index', 'kernel-hacking.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst new file mode 100644 index 00000000000000..1a456b60a7cfd0 --- /dev/null +++ b/Documentation/kernel-hacking/hacking.rst @@ -0,0 +1,811 @@ +============================================ +Unreliable Guide To Hacking The Linux Kernel +============================================ + +:Author: Rusty Russell + +Introduction +============ + +Welcome, gentle reader, to Rusty's Remarkably Unreliable Guide to Linux +Kernel Hacking. This document describes the common routines and general +requirements for kernel code: its goal is to serve as a primer for Linux +kernel development for experienced C programmers. I avoid implementation +details: that's what the code is for, and I ignore whole tracts of +useful routines. + +Before you read this, please understand that I never wanted to write +this document, being grossly under-qualified, but I always wanted to +read it, and this was the only way. I hope it will grow into a +compendium of best practice, common starting points and random +information. + +The Players +=========== + +At any time each of the CPUs in a system can be: + +- not associated with any process, serving a hardware interrupt; + +- not associated with any process, serving a softirq or tasklet; + +- running in kernel space, associated with a process (user context); + +- running a process in user space. + +There is an ordering between these. The bottom two can preempt each +other, but above that is a strict hierarchy: each can only be preempted +by the ones above it. For example, while a softirq is running on a CPU, +no other softirq will preempt it, but a hardware interrupt can. However, +any other CPUs in the system execute independently. + +We'll see a number of ways that the user context can block interrupts, +to become truly non-preemptable. + +User Context +------------ + +User context is when you are coming in from a system call or other trap: +like userspace, you can be preempted by more important tasks and by +interrupts. You can sleep, by calling :c:func:`schedule()`. + +.. note:: + + You are always in user context on module load and unload, and on + operations on the block device layer. + +In user context, the ``current`` pointer (indicating the task we are +currently executing) is valid, and :c:func:`in_interrupt()` +(``include/linux/preempt.h``) is false. + +.. warning:: + + Beware that if you have preemption or softirqs disabled (see below), + :c:func:`in_interrupt()` will return a false positive. + +Hardware Interrupts (Hard IRQs) +------------------------------- + +Timer ticks, network cards and keyboard are examples of real hardware +which produce interrupts at any time. The kernel runs interrupt +handlers, which services the hardware. The kernel guarantees that this +handler is never re-entered: if the same interrupt arrives, it is queued +(or dropped). Because it disables interrupts, this handler has to be +fast: frequently it simply acknowledges the interrupt, marks a 'software +interrupt' for execution and exits. + +You can tell you are in a hardware interrupt, because +:c:func:`in_irq()` returns true. + +.. warning:: + + Beware that this will return a false positive if interrupts are + disabled (see below). + +Software Interrupt Context: Softirqs and Tasklets +------------------------------------------------- + +Whenever a system call is about to return to userspace, or a hardware +interrupt handler exits, any 'software interrupts' which are marked +pending (usually by hardware interrupts) are run (``kernel/softirq.c``). + +Much of the real interrupt handling work is done here. Early in the +transition to SMP, there were only 'bottom halves' (BHs), which didn't +take advantage of multiple CPUs. Shortly after we switched from wind-up +computers made of match-sticks and snot, we abandoned this limitation +and switched to 'softirqs'. + +``include/linux/interrupt.h`` lists the different softirqs. A very +important softirq is the timer softirq (``include/linux/timer.h``): you +can register to have it call functions for you in a given length of +time. + +Softirqs are often a pain to deal with, since the same softirq will run +simultaneously on more than one CPU. For this reason, tasklets +(``include/linux/interrupt.h``) are more often used: they are +dynamically-registrable (meaning you can have as many as you want), and +they also guarantee that any tasklet will only run on one CPU at any +time, although different tasklets can run simultaneously. + +.. warning:: + + The name 'tasklet' is misleading: they have nothing to do with + 'tasks', and probably more to do with some bad vodka Alexey + Kuznetsov had at the time. + +You can tell you are in a softirq (or tasklet) using the +:c:func:`in_softirq()` macro (``include/linux/preempt.h``). + +.. warning:: + + Beware that this will return a false positive if a + :ref:`botton half lock ` is held. + +Some Basic Rules +================ + +No memory protection + If you corrupt memory, whether in user context or interrupt context, + the whole machine will crash. Are you sure you can't do what you + want in userspace? + +No floating point or MMX + The FPU context is not saved; even in user context the FPU state + probably won't correspond with the current process: you would mess + with some user process' FPU state. If you really want to do this, + you would have to explicitly save/restore the full FPU state (and + avoid context switches). It is generally a bad idea; use fixed point + arithmetic first. + +A rigid stack limit + Depending on configuration options the kernel stack is about 3K to + 6K for most 32-bit architectures: it's about 14K on most 64-bit + archs, and often shared with interrupts so you can't use it all. + Avoid deep recursion and huge local arrays on the stack (allocate + them dynamically instead). + +The Linux kernel is portable + Let's keep it that way. Your code should be 64-bit clean, and + endian-independent. You should also minimize CPU specific stuff, + e.g. inline assembly should be cleanly encapsulated and minimized to + ease porting. Generally it should be restricted to the + architecture-dependent part of the kernel tree. + +ioctls: Not writing a new system call +===================================== + +A system call generally looks like this:: + + asmlinkage long sys_mycall(int arg) + { + return 0; + } + + +First, in most cases you don't want to create a new system call. You +create a character device and implement an appropriate ioctl for it. +This is much more flexible than system calls, doesn't have to be entered +in every architecture's ``include/asm/unistd.h`` and +``arch/kernel/entry.S`` file, and is much more likely to be accepted by +Linus. + +If all your routine does is read or write some parameter, consider +implementing a :c:func:`sysfs()` interface instead. + +Inside the ioctl you're in user context to a process. When a error +occurs you return a negated errno (see +``include/uapi/asm-generic/errno-base.h``, +``include/uapi/asm-generic/errno.h`` and ``include/linux/errno.h``), +otherwise you return 0. + +After you slept you should check if a signal occurred: the Unix/Linux +way of handling signals is to temporarily exit the system call with the +``-ERESTARTSYS`` error. The system call entry code will switch back to +user context, process the signal handler and then your system call will +be restarted (unless the user disabled that). So you should be prepared +to process the restart, e.g. if you're in the middle of manipulating +some data structure. + +:: + + if (signal_pending(current)) + return -ERESTARTSYS; + + +If you're doing longer computations: first think userspace. If you +**really** want to do it in kernel you should regularly check if you need +to give up the CPU (remember there is cooperative multitasking per CPU). +Idiom:: + + cond_resched(); /* Will sleep */ + + +A short note on interface design: the UNIX system call motto is "Provide +mechanism not policy". + +Recipes for Deadlock +==================== + +You cannot call any routines which may sleep, unless: + +- You are in user context. + +- You do not own any spinlocks. + +- You have interrupts enabled (actually, Andi Kleen says that the + scheduling code will enable them for you, but that's probably not + what you wanted). + +Note that some functions may sleep implicitly: common ones are the user +space access functions (\*_user) and memory allocation functions +without ``GFP_ATOMIC``. + +You should always compile your kernel ``CONFIG_DEBUG_ATOMIC_SLEEP`` on, +and it will warn you if you break these rules. If you **do** break the +rules, you will eventually lock up your box. + +Really. + +Common Routines +=============== + +:c:func:`printk()` +------------------ + +Defined in ``include/linux/printk.h`` + +:c:func:`printk()` feeds kernel messages to the console, dmesg, and +the syslog daemon. It is useful for debugging and reporting errors, and +can be used inside interrupt context, but use with caution: a machine +which has its console flooded with printk messages is unusable. It uses +a format string mostly compatible with ANSI C printf, and C string +concatenation to give it a first "priority" argument:: + + printk(KERN_INFO "i = %u\n", i); + + +See ``include/linux/kern_levels.h``; for other ``KERN_`` values; these are +interpreted by syslog as the level. Special case: for printing an IP +address use:: + + __be32 ipaddress; + printk(KERN_INFO "my ip: %pI4\n", &ipaddress); + + +:c:func:`printk()` internally uses a 1K buffer and does not catch +overruns. Make sure that will be enough. + +.. note:: + + You will know when you are a real kernel hacker when you start + typoing printf as printk in your user programs :) + +.. note:: + + Another sidenote: the original Unix Version 6 sources had a comment + on top of its printf function: "Printf should not be used for + chit-chat". You should follow that advice. + +:c:func:`copy_to_user()` / :c:func:`copy_from_user()` / :c:func:`get_user()` / :c:func:`put_user()` +--------------------------------------------------------------------------------------------------- + +Defined in ``include/linux/uaccess.h`` / ``asm/uaccess.h`` + +**[SLEEPS]** + +:c:func:`put_user()` and :c:func:`get_user()` are used to get +and put single values (such as an int, char, or long) from and to +userspace. A pointer into userspace should never be simply dereferenced: +data should be copied using these routines. Both return ``-EFAULT`` or +0. + +:c:func:`copy_to_user()` and :c:func:`copy_from_user()` are +more general: they copy an arbitrary amount of data to and from +userspace. + +.. warning:: + + Unlike :c:func:`put_user()` and :c:func:`get_user()`, they + return the amount of uncopied data (ie. 0 still means success). + +[Yes, this moronic interface makes me cringe. The flamewar comes up +every year or so. --RR.] + +The functions may sleep implicitly. This should never be called outside +user context (it makes no sense), with interrupts disabled, or a +spinlock held. + +:c:func:`kmalloc()`/:c:func:`kfree()` +------------------------------------- + +Defined in ``include/linux/slab.h`` + +**[MAY SLEEP: SEE BELOW]** + +These routines are used to dynamically request pointer-aligned chunks of +memory, like malloc and free do in userspace, but +:c:func:`kmalloc()` takes an extra flag word. Important values: + +``GFP_KERNEL`` + May sleep and swap to free memory. Only allowed in user context, but + is the most reliable way to allocate memory. + +``GFP_ATOMIC`` + Don't sleep. Less reliable than ``GFP_KERNEL``, but may be called + from interrupt context. You should **really** have a good + out-of-memory error-handling strategy. + +``GFP_DMA`` + Allocate ISA DMA lower than 16MB. If you don't know what that is you + don't need it. Very unreliable. + +If you see a sleeping function called from invalid context warning +message, then maybe you called a sleeping allocation function from +interrupt context without ``GFP_ATOMIC``. You should really fix that. +Run, don't walk. + +If you are allocating at least ``PAGE_SIZE`` (``asm/page.h`` or +``asm/page_types.h``) bytes, consider using :c:func:`__get_free_pages()` +(``include/linux/gfp.h``). It takes an order argument (0 for page sized, +1 for double page, 2 for four pages etc.) and the same memory priority +flag word as above. + +If you are allocating more than a page worth of bytes you can use +:c:func:`vmalloc()`. It'll allocate virtual memory in the kernel +map. This block is not contiguous in physical memory, but the MMU makes +it look like it is for you (so it'll only look contiguous to the CPUs, +not to external device drivers). If you really need large physically +contiguous memory for some weird device, you have a problem: it is +poorly supported in Linux because after some time memory fragmentation +in a running kernel makes it hard. The best way is to allocate the block +early in the boot process via the :c:func:`alloc_bootmem()` +routine. + +Before inventing your own cache of often-used objects consider using a +slab cache in ``include/linux/slab.h`` + +:c:func:`current()` +------------------- + +Defined in ``include/asm/current.h`` + +This global variable (really a macro) contains a pointer to the current +task structure, so is only valid in user context. For example, when a +process makes a system call, this will point to the task structure of +the calling process. It is **not NULL** in interrupt context. + +:c:func:`mdelay()`/:c:func:`udelay()` +------------------------------------- + +Defined in ``include/asm/delay.h`` / ``include/linux/delay.h`` + +The :c:func:`udelay()` and :c:func:`ndelay()` functions can be +used for small pauses. Do not use large values with them as you risk +overflow - the helper function :c:func:`mdelay()` is useful here, or +consider :c:func:`msleep()`. + +:c:func:`cpu_to_be32()`/:c:func:`be32_to_cpu()`/:c:func:`cpu_to_le32()`/:c:func:`le32_to_cpu()` +----------------------------------------------------------------------------------------------- + +Defined in ``include/asm/byteorder.h`` + +The :c:func:`cpu_to_be32()` family (where the "32" can be replaced +by 64 or 16, and the "be" can be replaced by "le") are the general way +to do endian conversions in the kernel: they return the converted value. +All variations supply the reverse as well: +:c:func:`be32_to_cpu()`, etc. + +There are two major variations of these functions: the pointer +variation, such as :c:func:`cpu_to_be32p()`, which take a pointer +to the given type, and return the converted value. The other variation +is the "in-situ" family, such as :c:func:`cpu_to_be32s()`, which +convert value referred to by the pointer, and return void. + +:c:func:`local_irq_save()`/:c:func:`local_irq_restore()` +-------------------------------------------------------- + +Defined in ``include/linux/irqflags.h`` + +These routines disable hard interrupts on the local CPU, and restore +them. They are reentrant; saving the previous state in their one +``unsigned long flags`` argument. If you know that interrupts are +enabled, you can simply use :c:func:`local_irq_disable()` and +:c:func:`local_irq_enable()`. + +.. _local_bh_disable: + +:c:func:`local_bh_disable()`/:c:func:`local_bh_enable()` +-------------------------------------------------------- + +Defined in ``include/linux/bottom_half.h`` + + +These routines disable soft interrupts on the local CPU, and restore +them. They are reentrant; if soft interrupts were disabled before, they +will still be disabled after this pair of functions has been called. +They prevent softirqs and tasklets from running on the current CPU. + +:c:func:`smp_processor_id()` +---------------------------- + +Defined in ``include/linux/smp.h`` + +:c:func:`get_cpu()` disables preemption (so you won't suddenly get +moved to another CPU) and returns the current processor number, between +0 and ``NR_CPUS``. Note that the CPU numbers are not necessarily +continuous. You return it again with :c:func:`put_cpu()` when you +are done. + +If you know you cannot be preempted by another task (ie. you are in +interrupt context, or have preemption disabled) you can use +smp_processor_id(). + +``__init``/``__exit``/``__initdata`` +------------------------------------ + +Defined in ``include/linux/init.h`` + +After boot, the kernel frees up a special section; functions marked with +``__init`` and data structures marked with ``__initdata`` are dropped +after boot is complete: similarly modules discard this memory after +initialization. ``__exit`` is used to declare a function which is only +required on exit: the function will be dropped if this file is not +compiled as a module. See the header file for use. Note that it makes no +sense for a function marked with ``__init`` to be exported to modules +with :c:func:`EXPORT_SYMBOL()` or :c:func:`EXPORT_SYMBOL_GPL()`- this +will break. + +:c:func:`__initcall()`/:c:func:`module_init()` +---------------------------------------------- + +Defined in ``include/linux/init.h`` / ``include/linux/module.h`` + +Many parts of the kernel are well served as a module +(dynamically-loadable parts of the kernel). Using the +:c:func:`module_init()` and :c:func:`module_exit()` macros it +is easy to write code without #ifdefs which can operate both as a module +or built into the kernel. + +The :c:func:`module_init()` macro defines which function is to be +called at module insertion time (if the file is compiled as a module), +or at boot time: if the file is not compiled as a module the +:c:func:`module_init()` macro becomes equivalent to +:c:func:`__initcall()`, which through linker magic ensures that +the function is called on boot. + +The function can return a negative error number to cause module loading +to fail (unfortunately, this has no effect if the module is compiled +into the kernel). This function is called in user context with +interrupts enabled, so it can sleep. + +:c:func:`module_exit()` +----------------------- + + +Defined in ``include/linux/module.h`` + +This macro defines the function to be called at module removal time (or +never, in the case of the file compiled into the kernel). It will only +be called if the module usage count has reached zero. This function can +also sleep, but cannot fail: everything must be cleaned up by the time +it returns. + +Note that this macro is optional: if it is not present, your module will +not be removable (except for 'rmmod -f'). + +:c:func:`try_module_get()`/:c:func:`module_put()` +------------------------------------------------- + +Defined in ``include/linux/module.h`` + +These manipulate the module usage count, to protect against removal (a +module also can't be removed if another module uses one of its exported +symbols: see below). Before calling into module code, you should call +:c:func:`try_module_get()` on that module: if it fails, then the +module is being removed and you should act as if it wasn't there. +Otherwise, you can safely enter the module, and call +:c:func:`module_put()` when you're finished. + +Most registerable structures have an owner field, such as in the +:c:type:`struct file_operations ` structure. +Set this field to the macro ``THIS_MODULE``. + +Wait Queues ``include/linux/wait.h`` +==================================== + +**[SLEEPS]** + +A wait queue is used to wait for someone to wake you up when a certain +condition is true. They must be used carefully to ensure there is no +race condition. You declare a :c:type:`wait_queue_head_t`, and then processes +which want to wait for that condition declare a :c:type:`wait_queue_t` +referring to themselves, and place that in the queue. + +Declaring +--------- + +You declare a ``wait_queue_head_t`` using the +:c:func:`DECLARE_WAIT_QUEUE_HEAD()` macro, or using the +:c:func:`init_waitqueue_head()` routine in your initialization +code. + +Queuing +------- + +Placing yourself in the waitqueue is fairly complex, because you must +put yourself in the queue before checking the condition. There is a +macro to do this: :c:func:`wait_event_interruptible()` +(``include/linux/wait.h``) The first argument is the wait queue head, and +the second is an expression which is evaluated; the macro returns 0 when +this expression is true, or ``-ERESTARTSYS`` if a signal is received. The +:c:func:`wait_event()` version ignores signals. + +Waking Up Queued Tasks +---------------------- + +Call :c:func:`wake_up()` (``include/linux/wait.h``);, which will wake +up every process in the queue. The exception is if one has +``TASK_EXCLUSIVE`` set, in which case the remainder of the queue will +not be woken. There are other variants of this basic function available +in the same header. + +Atomic Operations +================= + +Certain operations are guaranteed atomic on all platforms. The first +class of operations work on :c:type:`atomic_t` (``include/asm/atomic.h``); +this contains a signed integer (at least 32 bits long), and you must use +these functions to manipulate or read :c:type:`atomic_t` variables. +:c:func:`atomic_read()` and :c:func:`atomic_set()` get and set +the counter, :c:func:`atomic_add()`, :c:func:`atomic_sub()`, +:c:func:`atomic_inc()`, :c:func:`atomic_dec()`, and +:c:func:`atomic_dec_and_test()` (returns true if it was +decremented to zero). + +Yes. It returns true (i.e. != 0) if the atomic variable is zero. + +Note that these functions are slower than normal arithmetic, and so +should not be used unnecessarily. + +The second class of atomic operations is atomic bit operations on an +``unsigned long``, defined in ``include/linux/bitops.h``. These +operations generally take a pointer to the bit pattern, and a bit +number: 0 is the least significant bit. :c:func:`set_bit()`, +:c:func:`clear_bit()` and :c:func:`change_bit()` set, clear, +and flip the given bit. :c:func:`test_and_set_bit()`, +:c:func:`test_and_clear_bit()` and +:c:func:`test_and_change_bit()` do the same thing, except return +true if the bit was previously set; these are particularly useful for +atomically setting flags. + +It is possible to call these operations with bit indices greater than +``BITS_PER_LONG``. The resulting behavior is strange on big-endian +platforms though so it is a good idea not to do this. + +Symbols +======= + +Within the kernel proper, the normal linking rules apply (ie. unless a +symbol is declared to be file scope with the ``static`` keyword, it can +be used anywhere in the kernel). However, for modules, a special +exported symbol table is kept which limits the entry points to the +kernel proper. Modules can also export symbols. + +:c:func:`EXPORT_SYMBOL()` +------------------------- + +Defined in ``include/linux/export.h`` + +This is the classic method of exporting a symbol: dynamically loaded +modules will be able to use the symbol as normal. + +:c:func:`EXPORT_SYMBOL_GPL()` +----------------------------- + +Defined in ``include/linux/export.h`` + +Similar to :c:func:`EXPORT_SYMBOL()` except that the symbols +exported by :c:func:`EXPORT_SYMBOL_GPL()` can only be seen by +modules with a :c:func:`MODULE_LICENSE()` that specifies a GPL +compatible license. It implies that the function is considered an +internal implementation issue, and not really an interface. Some +maintainers and developers may however require EXPORT_SYMBOL_GPL() +when adding any new APIs or functionality. + +Routines and Conventions +======================== + +Double-linked lists ``include/linux/list.h`` +-------------------------------------------- + +There used to be three sets of linked-list routines in the kernel +headers, but this one is the winner. If you don't have some particular +pressing need for a single list, it's a good choice. + +In particular, :c:func:`list_for_each_entry()` is useful. + +Return Conventions +------------------ + +For code called in user context, it's very common to defy C convention, +and return 0 for success, and a negative error number (eg. ``-EFAULT``) for +failure. This can be unintuitive at first, but it's fairly widespread in +the kernel. + +Using :c:func:`ERR_PTR()` (``include/linux/err.h``) to encode a +negative error number into a pointer, and :c:func:`IS_ERR()` and +:c:func:`PTR_ERR()` to get it back out again: avoids a separate +pointer parameter for the error number. Icky, but in a good way. + +Breaking Compilation +-------------------- + +Linus and the other developers sometimes change function or structure +names in development kernels; this is not done just to keep everyone on +their toes: it reflects a fundamental change (eg. can no longer be +called with interrupts on, or does extra checks, or doesn't do checks +which were caught before). Usually this is accompanied by a fairly +complete note to the linux-kernel mailing list; search the archive. +Simply doing a global replace on the file usually makes things **worse**. + +Initializing structure members +------------------------------ + +The preferred method of initializing structures is to use designated +initialisers, as defined by ISO C99, eg:: + + static struct block_device_operations opt_fops = { + .open = opt_open, + .release = opt_release, + .ioctl = opt_ioctl, + .check_media_change = opt_media_change, + }; + + +This makes it easy to grep for, and makes it clear which structure +fields are set. You should do this because it looks cool. + +GNU Extensions +-------------- + +GNU Extensions are explicitly allowed in the Linux kernel. Note that +some of the more complex ones are not very well supported, due to lack +of general use, but the following are considered standard (see the GCC +info page section "C Extensions" for more details - Yes, really the info +page, the man page is only a short summary of the stuff in info). + +- Inline functions + +- Statement expressions (ie. the ({ and }) constructs). + +- Declaring attributes of a function / variable / type + (__attribute__) + +- typeof + +- Zero length arrays + +- Macro varargs + +- Arithmetic on void pointers + +- Non-Constant initializers + +- Assembler Instructions (not outside arch/ and include/asm/) + +- Function names as strings (__func__). + +- __builtin_constant_p() + +Be wary when using long long in the kernel, the code gcc generates for +it is horrible and worse: division and multiplication does not work on +i386 because the GCC runtime functions for it are missing from the +kernel environment. + +C++ +--- + +Using C++ in the kernel is usually a bad idea, because the kernel does +not provide the necessary runtime environment and the include files are +not tested for it. It is still possible, but not recommended. If you +really want to do this, forget about exceptions at least. + +NUMif +----- + +It is generally considered cleaner to use macros in header files (or at +the top of .c files) to abstract away functions rather than using \`#if' +pre-processor statements throughout the source code. + +Putting Your Stuff in the Kernel +================================ + +In order to get your stuff into shape for official inclusion, or even to +make a neat patch, there's administrative work to be done: + +- Figure out whose pond you've been pissing in. Look at the top of the + source files, inside the ``MAINTAINERS`` file, and last of all in the + ``CREDITS`` file. You should coordinate with this person to make sure + you're not duplicating effort, or trying something that's already + been rejected. + + Make sure you put your name and EMail address at the top of any files + you create or mangle significantly. This is the first place people + will look when they find a bug, or when **they** want to make a change. + +- Usually you want a configuration option for your kernel hack. Edit + ``Kconfig`` in the appropriate directory. The Config language is + simple to use by cut and paste, and there's complete documentation in + ``Documentation/kbuild/kconfig-language.txt``. + + In your description of the option, make sure you address both the + expert user and the user who knows nothing about your feature. + Mention incompatibilities and issues here. **Definitely** end your + description with “if in doubt, say N” (or, occasionally, \`Y'); this + is for people who have no idea what you are talking about. + +- Edit the ``Makefile``: the CONFIG variables are exported here so you + can usually just add a "obj-$(CONFIG_xxx) += xxx.o" line. The syntax + is documented in ``Documentation/kbuild/makefiles.txt``. + +- Put yourself in ``CREDITS`` if you've done something noteworthy, + usually beyond a single file (your name should be at the top of the + source files anyway). ``MAINTAINERS`` means you want to be consulted + when changes are made to a subsystem, and hear about bugs; it implies + a more-than-passing commitment to some part of the code. + +- Finally, don't forget to read + ``Documentation/process/submitting-patches.rst`` and possibly + ``Documentation/process/submitting-drivers.rst``. + +Kernel Cantrips +=============== + +Some favorites from browsing the source. Feel free to add to this list. + +``arch/x86/include/asm/delay.h``:: + + #define ndelay(n) (__builtin_constant_p(n) ? \ + ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \ + __ndelay(n)) + + +``include/linux/fs.h``:: + + /* + * Kernel pointers have redundant information, so we can use a + * scheme where we can return either an error code or a dentry + * pointer with the same return value. + * + * This should be a per-architecture thing, to allow different + * error and pointer decisions. + */ + #define ERR_PTR(err) ((void *)((long)(err))) + #define PTR_ERR(ptr) ((long)(ptr)) + #define IS_ERR(ptr) ((unsigned long)(ptr) > (unsigned long)(-1000)) + +``arch/x86/include/asm/uaccess_32.h:``:: + + #define copy_to_user(to,from,n) \ + (__builtin_constant_p(n) ? \ + __constant_copy_to_user((to),(from),(n)) : \ + __generic_copy_to_user((to),(from),(n))) + + +``arch/sparc/kernel/head.S:``:: + + /* + * Sun people can't spell worth damn. "compatability" indeed. + * At least we *know* we can't spell, and use a spell-checker. + */ + + /* Uh, actually Linus it is I who cannot spell. Too much murky + * Sparc assembly will do this to ya. + */ + C_LABEL(cputypvar): + .asciz "compatibility" + + /* Tested on SS-5, SS-10. Probably someone at Sun applied a spell-checker. */ + .align 4 + C_LABEL(cputypvar_sun4m): + .asciz "compatible" + + +``arch/sparc/lib/checksum.S:``:: + + /* Sun, you just can't beat me, you just can't. Stop trying, + * give up. I'm serious, I am going to kick the living shit + * out of you, game over, lights out. + */ + + +Thanks +====== + +Thanks to Andi Kleen for the idea, answering my questions, fixing my +mistakes, filling content, etc. Philipp Rumpf for more spelling and +clarity fixes, and some excellent non-obvious points. Werner Almesberger +for giving me a great summary of :c:func:`disable_irq()`, and Jes +Sorensen and Andrea Arcangeli added caveats. Michael Elizabeth Chastain +for checking and adding to the Configure section. Telsa Gwynne for +teaching me DocBook. diff --git a/Documentation/kernel-hacking/index.rst b/Documentation/kernel-hacking/index.rst new file mode 100644 index 00000000000000..fcb0eda3cca36a --- /dev/null +++ b/Documentation/kernel-hacking/index.rst @@ -0,0 +1,9 @@ +===================== +Kernel Hacking Guides +===================== + +.. toctree:: + :maxdepth: 2 + + hacking + locking diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst new file mode 100644 index 00000000000000..f937c0fd11aaa5 --- /dev/null +++ b/Documentation/kernel-hacking/locking.rst @@ -0,0 +1,1446 @@ +=========================== +Unreliable Guide To Locking +=========================== + +:Author: Rusty Russell + +Introduction +============ + +Welcome, to Rusty's Remarkably Unreliable Guide to Kernel Locking +issues. This document describes the locking systems in the Linux Kernel +in 2.6. + +With the wide availability of HyperThreading, and preemption in the +Linux Kernel, everyone hacking on the kernel needs to know the +fundamentals of concurrency and locking for SMP. + +The Problem With Concurrency +============================ + +(Skip this if you know what a Race Condition is). + +In a normal program, you can increment a counter like so: + +:: + + very_important_count++; + + +This is what they would expect to happen: + + +.. table:: Expected Results + + +------------------------------------+------------------------------------+ + | Instance 1 | Instance 2 | + +====================================+====================================+ + | read very_important_count (5) | | + +------------------------------------+------------------------------------+ + | add 1 (6) | | + +------------------------------------+------------------------------------+ + | write very_important_count (6) | | + +------------------------------------+------------------------------------+ + | | read very_important_count (6) | + +------------------------------------+------------------------------------+ + | | add 1 (7) | + +------------------------------------+------------------------------------+ + | | write very_important_count (7) | + +------------------------------------+------------------------------------+ + +This is what might happen: + +.. table:: Possible Results + + +------------------------------------+------------------------------------+ + | Instance 1 | Instance 2 | + +====================================+====================================+ + | read very_important_count (5) | | + +------------------------------------+------------------------------------+ + | | read very_important_count (5) | + +------------------------------------+------------------------------------+ + | add 1 (6) | | + +------------------------------------+------------------------------------+ + | | add 1 (6) | + +------------------------------------+------------------------------------+ + | write very_important_count (6) | | + +------------------------------------+------------------------------------+ + | | write very_important_count (6) | + +------------------------------------+------------------------------------+ + + +Race Conditions and Critical Regions +------------------------------------ + +This overlap, where the result depends on the relative timing of +multiple tasks, is called a race condition. The piece of code containing +the concurrency issue is called a critical region. And especially since +Linux starting running on SMP machines, they became one of the major +issues in kernel design and implementation. + +Preemption can have the same effect, even if there is only one CPU: by +preempting one task during the critical region, we have exactly the same +race condition. In this case the thread which preempts might run the +critical region itself. + +The solution is to recognize when these simultaneous accesses occur, and +use locks to make sure that only one instance can enter the critical +region at any time. There are many friendly primitives in the Linux +kernel to help you do this. And then there are the unfriendly +primitives, but I'll pretend they don't exist. + +Locking in the Linux Kernel +=========================== + +If I could give you one piece of advice: never sleep with anyone crazier +than yourself. But if I had to give you advice on locking: **keep it +simple**. + +Be reluctant to introduce new locks. + +Strangely enough, this last one is the exact reverse of my advice when +you **have** slept with someone crazier than yourself. And you should +think about getting a big dog. + +Two Main Types of Kernel Locks: Spinlocks and Mutexes +----------------------------------------------------- + +There are two main types of kernel locks. The fundamental type is the +spinlock (``include/asm/spinlock.h``), which is a very simple +single-holder lock: if you can't get the spinlock, you keep trying +(spinning) until you can. Spinlocks are very small and fast, and can be +used anywhere. + +The second type is a mutex (``include/linux/mutex.h``): it is like a +spinlock, but you may block holding a mutex. If you can't lock a mutex, +your task will suspend itself, and be woken up when the mutex is +released. This means the CPU can do something else while you are +waiting. There are many cases when you simply can't sleep (see +`What Functions Are Safe To Call From Interrupts? <#sleeping-things>`__), +and so have to use a spinlock instead. + +Neither type of lock is recursive: see +`Deadlock: Simple and Advanced <#deadlock>`__. + +Locks and Uniprocessor Kernels +------------------------------ + +For kernels compiled without ``CONFIG_SMP``, and without +``CONFIG_PREEMPT`` spinlocks do not exist at all. This is an excellent +design decision: when no-one else can run at the same time, there is no +reason to have a lock. + +If the kernel is compiled without ``CONFIG_SMP``, but ``CONFIG_PREEMPT`` +is set, then spinlocks simply disable preemption, which is sufficient to +prevent any races. For most purposes, we can think of preemption as +equivalent to SMP, and not worry about it separately. + +You should always test your locking code with ``CONFIG_SMP`` and +``CONFIG_PREEMPT`` enabled, even if you don't have an SMP test box, +because it will still catch some kinds of locking bugs. + +Mutexes still exist, because they are required for synchronization +between user contexts, as we will see below. + +Locking Only In User Context +---------------------------- + +If you have a data structure which is only ever accessed from user +context, then you can use a simple mutex (``include/linux/mutex.h``) to +protect it. This is the most trivial case: you initialize the mutex. +Then you can call :c:func:`mutex_lock_interruptible()` to grab the +mutex, and :c:func:`mutex_unlock()` to release it. There is also a +:c:func:`mutex_lock()`, which should be avoided, because it will +not return if a signal is received. + +Example: ``net/netfilter/nf_sockopt.c`` allows registration of new +:c:func:`setsockopt()` and :c:func:`getsockopt()` calls, with +:c:func:`nf_register_sockopt()`. Registration and de-registration +are only done on module load and unload (and boot time, where there is +no concurrency), and the list of registrations is only consulted for an +unknown :c:func:`setsockopt()` or :c:func:`getsockopt()` system +call. The ``nf_sockopt_mutex`` is perfect to protect this, especially +since the setsockopt and getsockopt calls may well sleep. + +Locking Between User Context and Softirqs +----------------------------------------- + +If a softirq shares data with user context, you have two problems. +Firstly, the current user context can be interrupted by a softirq, and +secondly, the critical region could be entered from another CPU. This is +where :c:func:`spin_lock_bh()` (``include/linux/spinlock.h``) is +used. It disables softirqs on that CPU, then grabs the lock. +:c:func:`spin_unlock_bh()` does the reverse. (The '_bh' suffix is +a historical reference to "Bottom Halves", the old name for software +interrupts. It should really be called spin_lock_softirq()' in a +perfect world). + +Note that you can also use :c:func:`spin_lock_irq()` or +:c:func:`spin_lock_irqsave()` here, which stop hardware interrupts +as well: see `Hard IRQ Context <#hardirq-context>`__. + +This works perfectly for UP as well: the spin lock vanishes, and this +macro simply becomes :c:func:`local_bh_disable()` +(``include/linux/interrupt.h``), which protects you from the softirq +being run. + +Locking Between User Context and Tasklets +----------------------------------------- + +This is exactly the same as above, because tasklets are actually run +from a softirq. + +Locking Between User Context and Timers +--------------------------------------- + +This, too, is exactly the same as above, because timers are actually run +from a softirq. From a locking point of view, tasklets and timers are +identical. + +Locking Between Tasklets/Timers +------------------------------- + +Sometimes a tasklet or timer might want to share data with another +tasklet or timer. + +The Same Tasklet/Timer +~~~~~~~~~~~~~~~~~~~~~~ + +Since a tasklet is never run on two CPUs at once, you don't need to +worry about your tasklet being reentrant (running twice at once), even +on SMP. + +Different Tasklets/Timers +~~~~~~~~~~~~~~~~~~~~~~~~~ + +If another tasklet/timer wants to share data with your tasklet or timer +, you will both need to use :c:func:`spin_lock()` and +:c:func:`spin_unlock()` calls. :c:func:`spin_lock_bh()` is +unnecessary here, as you are already in a tasklet, and none will be run +on the same CPU. + +Locking Between Softirqs +------------------------ + +Often a softirq might want to share data with itself or a tasklet/timer. + +The Same Softirq +~~~~~~~~~~~~~~~~ + +The same softirq can run on the other CPUs: you can use a per-CPU array +(see `Per-CPU Data <#per-cpu>`__) for better performance. If you're +going so far as to use a softirq, you probably care about scalable +performance enough to justify the extra complexity. + +You'll need to use :c:func:`spin_lock()` and +:c:func:`spin_unlock()` for shared data. + +Different Softirqs +~~~~~~~~~~~~~~~~~~ + +You'll need to use :c:func:`spin_lock()` and +:c:func:`spin_unlock()` for shared data, whether it be a timer, +tasklet, different softirq or the same or another softirq: any of them +could be running on a different CPU. + +Hard IRQ Context +================ + +Hardware interrupts usually communicate with a tasklet or softirq. +Frequently this involves putting work in a queue, which the softirq will +take out. + +Locking Between Hard IRQ and Softirqs/Tasklets +---------------------------------------------- + +If a hardware irq handler shares data with a softirq, you have two +concerns. Firstly, the softirq processing can be interrupted by a +hardware interrupt, and secondly, the critical region could be entered +by a hardware interrupt on another CPU. This is where +:c:func:`spin_lock_irq()` is used. It is defined to disable +interrupts on that cpu, then grab the lock. +:c:func:`spin_unlock_irq()` does the reverse. + +The irq handler does not to use :c:func:`spin_lock_irq()`, because +the softirq cannot run while the irq handler is running: it can use +:c:func:`spin_lock()`, which is slightly faster. The only exception +would be if a different hardware irq handler uses the same lock: +:c:func:`spin_lock_irq()` will stop that from interrupting us. + +This works perfectly for UP as well: the spin lock vanishes, and this +macro simply becomes :c:func:`local_irq_disable()` +(``include/asm/smp.h``), which protects you from the softirq/tasklet/BH +being run. + +:c:func:`spin_lock_irqsave()` (``include/linux/spinlock.h``) is a +variant which saves whether interrupts were on or off in a flags word, +which is passed to :c:func:`spin_unlock_irqrestore()`. This means +that the same code can be used inside an hard irq handler (where +interrupts are already off) and in softirqs (where the irq disabling is +required). + +Note that softirqs (and hence tasklets and timers) are run on return +from hardware interrupts, so :c:func:`spin_lock_irq()` also stops +these. In that sense, :c:func:`spin_lock_irqsave()` is the most +general and powerful locking function. + +Locking Between Two Hard IRQ Handlers +------------------------------------- + +It is rare to have to share data between two IRQ handlers, but if you +do, :c:func:`spin_lock_irqsave()` should be used: it is +architecture-specific whether all interrupts are disabled inside irq +handlers themselves. + +Cheat Sheet For Locking +======================= + +Pete Zaitcev gives the following summary: + +- If you are in a process context (any syscall) and want to lock other + process out, use a mutex. You can take a mutex and sleep + (``copy_from_user*(`` or ``kmalloc(x,GFP_KERNEL)``). + +- Otherwise (== data can be touched in an interrupt), use + :c:func:`spin_lock_irqsave()` and + :c:func:`spin_unlock_irqrestore()`. + +- Avoid holding spinlock for more than 5 lines of code and across any + function call (except accessors like :c:func:`readb()`). + +Table of Minimum Requirements +----------------------------- + +The following table lists the **minimum** locking requirements between +various contexts. In some cases, the same context can only be running on +one CPU at a time, so no locking is required for that context (eg. a +particular thread can only run on one CPU at a time, but if it needs +shares data with another thread, locking is required). + +Remember the advice above: you can always use +:c:func:`spin_lock_irqsave()`, which is a superset of all other +spinlock primitives. + +============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ============== +. IRQ Handler A IRQ Handler B Softirq A Softirq B Tasklet A Tasklet B Timer A Timer B User Context A User Context B +============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ============== +IRQ Handler A None +IRQ Handler B SLIS None +Softirq A SLI SLI SL +Softirq B SLI SLI SL SL +Tasklet A SLI SLI SL SL None +Tasklet B SLI SLI SL SL SL None +Timer A SLI SLI SL SL SL SL None +Timer B SLI SLI SL SL SL SL SL None +User Context A SLI SLI SLBH SLBH SLBH SLBH SLBH SLBH None +User Context B SLI SLI SLBH SLBH SLBH SLBH SLBH SLBH MLI None +============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ============== + +Table: Table of Locking Requirements + ++--------+----------------------------+ +| SLIS | spin_lock_irqsave | ++--------+----------------------------+ +| SLI | spin_lock_irq | ++--------+----------------------------+ +| SL | spin_lock | ++--------+----------------------------+ +| SLBH | spin_lock_bh | ++--------+----------------------------+ +| MLI | mutex_lock_interruptible | ++--------+----------------------------+ + +Table: Legend for Locking Requirements Table + +The trylock Functions +===================== + +There are functions that try to acquire a lock only once and immediately +return a value telling about success or failure to acquire the lock. +They can be used if you need no access to the data protected with the +lock when some other thread is holding the lock. You should acquire the +lock later if you then need access to the data protected with the lock. + +:c:func:`spin_trylock()` does not spin but returns non-zero if it +acquires the spinlock on the first try or 0 if not. This function can be +used in all contexts like :c:func:`spin_lock()`: you must have +disabled the contexts that might interrupt you and acquire the spin +lock. + +:c:func:`mutex_trylock()` does not suspend your task but returns +non-zero if it could lock the mutex on the first try or 0 if not. This +function cannot be safely used in hardware or software interrupt +contexts despite not sleeping. + +Common Examples +=============== + +Let's step through a simple example: a cache of number to name mappings. +The cache keeps a count of how often each of the objects is used, and +when it gets full, throws out the least used one. + +All In User Context +------------------- + +For our first example, we assume that all operations are in user context +(ie. from system calls), so we can sleep. This means we can use a mutex +to protect the cache and all the objects within it. Here's the code:: + + #include + #include + #include + #include + #include + + struct object + { + struct list_head list; + int id; + char name[32]; + int popularity; + }; + + /* Protects the cache, cache_num, and the objects within it */ + static DEFINE_MUTEX(cache_lock); + static LIST_HEAD(cache); + static unsigned int cache_num = 0; + #define MAX_CACHE_SIZE 10 + + /* Must be holding cache_lock */ + static struct object *__cache_find(int id) + { + struct object *i; + + list_for_each_entry(i, &cache, list) + if (i->id == id) { + i->popularity++; + return i; + } + return NULL; + } + + /* Must be holding cache_lock */ + static void __cache_delete(struct object *obj) + { + BUG_ON(!obj); + list_del(&obj->list); + kfree(obj); + cache_num--; + } + + /* Must be holding cache_lock */ + static void __cache_add(struct object *obj) + { + list_add(&obj->list, &cache); + if (++cache_num > MAX_CACHE_SIZE) { + struct object *i, *outcast = NULL; + list_for_each_entry(i, &cache, list) { + if (!outcast || i->popularity < outcast->popularity) + outcast = i; + } + __cache_delete(outcast); + } + } + + int cache_add(int id, const char *name) + { + struct object *obj; + + if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL) + return -ENOMEM; + + strlcpy(obj->name, name, sizeof(obj->name)); + obj->id = id; + obj->popularity = 0; + + mutex_lock(&cache_lock); + __cache_add(obj); + mutex_unlock(&cache_lock); + return 0; + } + + void cache_delete(int id) + { + mutex_lock(&cache_lock); + __cache_delete(__cache_find(id)); + mutex_unlock(&cache_lock); + } + + int cache_find(int id, char *name) + { + struct object *obj; + int ret = -ENOENT; + + mutex_lock(&cache_lock); + obj = __cache_find(id); + if (obj) { + ret = 0; + strcpy(name, obj->name); + } + mutex_unlock(&cache_lock); + return ret; + } + +Note that we always make sure we have the cache_lock when we add, +delete, or look up the cache: both the cache infrastructure itself and +the contents of the objects are protected by the lock. In this case it's +easy, since we copy the data for the user, and never let them access the +objects directly. + +There is a slight (and common) optimization here: in +:c:func:`cache_add()` we set up the fields of the object before +grabbing the lock. This is safe, as no-one else can access it until we +put it in cache. + +Accessing From Interrupt Context +-------------------------------- + +Now consider the case where :c:func:`cache_find()` can be called +from interrupt context: either a hardware interrupt or a softirq. An +example would be a timer which deletes object from the cache. + +The change is shown below, in standard patch format: the ``-`` are lines +which are taken away, and the ``+`` are lines which are added. + +:: + + --- cache.c.usercontext 2003-12-09 13:58:54.000000000 +1100 + +++ cache.c.interrupt 2003-12-09 14:07:49.000000000 +1100 + @@ -12,7 +12,7 @@ + int popularity; + }; + + -static DEFINE_MUTEX(cache_lock); + +static DEFINE_SPINLOCK(cache_lock); + static LIST_HEAD(cache); + static unsigned int cache_num = 0; + #define MAX_CACHE_SIZE 10 + @@ -55,6 +55,7 @@ + int cache_add(int id, const char *name) + { + struct object *obj; + + unsigned long flags; + + if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL) + return -ENOMEM; + @@ -63,30 +64,33 @@ + obj->id = id; + obj->popularity = 0; + + - mutex_lock(&cache_lock); + + spin_lock_irqsave(&cache_lock, flags); + __cache_add(obj); + - mutex_unlock(&cache_lock); + + spin_unlock_irqrestore(&cache_lock, flags); + return 0; + } + + void cache_delete(int id) + { + - mutex_lock(&cache_lock); + + unsigned long flags; + + + + spin_lock_irqsave(&cache_lock, flags); + __cache_delete(__cache_find(id)); + - mutex_unlock(&cache_lock); + + spin_unlock_irqrestore(&cache_lock, flags); + } + + int cache_find(int id, char *name) + { + struct object *obj; + int ret = -ENOENT; + + unsigned long flags; + + - mutex_lock(&cache_lock); + + spin_lock_irqsave(&cache_lock, flags); + obj = __cache_find(id); + if (obj) { + ret = 0; + strcpy(name, obj->name); + } + - mutex_unlock(&cache_lock); + + spin_unlock_irqrestore(&cache_lock, flags); + return ret; + } + +Note that the :c:func:`spin_lock_irqsave()` will turn off +interrupts if they are on, otherwise does nothing (if we are already in +an interrupt handler), hence these functions are safe to call from any +context. + +Unfortunately, :c:func:`cache_add()` calls :c:func:`kmalloc()` +with the ``GFP_KERNEL`` flag, which is only legal in user context. I +have assumed that :c:func:`cache_add()` is still only called in +user context, otherwise this should become a parameter to +:c:func:`cache_add()`. + +Exposing Objects Outside This File +---------------------------------- + +If our objects contained more information, it might not be sufficient to +copy the information in and out: other parts of the code might want to +keep pointers to these objects, for example, rather than looking up the +id every time. This produces two problems. + +The first problem is that we use the ``cache_lock`` to protect objects: +we'd need to make this non-static so the rest of the code can use it. +This makes locking trickier, as it is no longer all in one place. + +The second problem is the lifetime problem: if another structure keeps a +pointer to an object, it presumably expects that pointer to remain +valid. Unfortunately, this is only guaranteed while you hold the lock, +otherwise someone might call :c:func:`cache_delete()` and even +worse, add another object, re-using the same address. + +As there is only one lock, you can't hold it forever: no-one else would +get any work done. + +The solution to this problem is to use a reference count: everyone who +has a pointer to the object increases it when they first get the object, +and drops the reference count when they're finished with it. Whoever +drops it to zero knows it is unused, and can actually delete it. + +Here is the code:: + + --- cache.c.interrupt 2003-12-09 14:25:43.000000000 +1100 + +++ cache.c.refcnt 2003-12-09 14:33:05.000000000 +1100 + @@ -7,6 +7,7 @@ + struct object + { + struct list_head list; + + unsigned int refcnt; + int id; + char name[32]; + int popularity; + @@ -17,6 +18,35 @@ + static unsigned int cache_num = 0; + #define MAX_CACHE_SIZE 10 + + +static void __object_put(struct object *obj) + +{ + + if (--obj->refcnt == 0) + + kfree(obj); + +} + + + +static void __object_get(struct object *obj) + +{ + + obj->refcnt++; + +} + + + +void object_put(struct object *obj) + +{ + + unsigned long flags; + + + + spin_lock_irqsave(&cache_lock, flags); + + __object_put(obj); + + spin_unlock_irqrestore(&cache_lock, flags); + +} + + + +void object_get(struct object *obj) + +{ + + unsigned long flags; + + + + spin_lock_irqsave(&cache_lock, flags); + + __object_get(obj); + + spin_unlock_irqrestore(&cache_lock, flags); + +} + + + /* Must be holding cache_lock */ + static struct object *__cache_find(int id) + { + @@ -35,6 +65,7 @@ + { + BUG_ON(!obj); + list_del(&obj->list); + + __object_put(obj); + cache_num--; + } + + @@ -63,6 +94,7 @@ + strlcpy(obj->name, name, sizeof(obj->name)); + obj->id = id; + obj->popularity = 0; + + obj->refcnt = 1; /* The cache holds a reference */ + + spin_lock_irqsave(&cache_lock, flags); + __cache_add(obj); + @@ -79,18 +111,15 @@ + spin_unlock_irqrestore(&cache_lock, flags); + } + + -int cache_find(int id, char *name) + +struct object *cache_find(int id) + { + struct object *obj; + - int ret = -ENOENT; + unsigned long flags; + + spin_lock_irqsave(&cache_lock, flags); + obj = __cache_find(id); + - if (obj) { + - ret = 0; + - strcpy(name, obj->name); + - } + + if (obj) + + __object_get(obj); + spin_unlock_irqrestore(&cache_lock, flags); + - return ret; + + return obj; + } + +We encapsulate the reference counting in the standard 'get' and 'put' +functions. Now we can return the object itself from +:c:func:`cache_find()` which has the advantage that the user can +now sleep holding the object (eg. to :c:func:`copy_to_user()` to +name to userspace). + +The other point to note is that I said a reference should be held for +every pointer to the object: thus the reference count is 1 when first +inserted into the cache. In some versions the framework does not hold a +reference count, but they are more complicated. + +Using Atomic Operations For The Reference Count +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +In practice, :c:type:`atomic_t` would usually be used for refcnt. There are a +number of atomic operations defined in ``include/asm/atomic.h``: these +are guaranteed to be seen atomically from all CPUs in the system, so no +lock is required. In this case, it is simpler than using spinlocks, +although for anything non-trivial using spinlocks is clearer. The +:c:func:`atomic_inc()` and :c:func:`atomic_dec_and_test()` +are used instead of the standard increment and decrement operators, and +the lock is no longer used to protect the reference count itself. + +:: + + --- cache.c.refcnt 2003-12-09 15:00:35.000000000 +1100 + +++ cache.c.refcnt-atomic 2003-12-11 15:49:42.000000000 +1100 + @@ -7,7 +7,7 @@ + struct object + { + struct list_head list; + - unsigned int refcnt; + + atomic_t refcnt; + int id; + char name[32]; + int popularity; + @@ -18,33 +18,15 @@ + static unsigned int cache_num = 0; + #define MAX_CACHE_SIZE 10 + + -static void __object_put(struct object *obj) + -{ + - if (--obj->refcnt == 0) + - kfree(obj); + -} + - + -static void __object_get(struct object *obj) + -{ + - obj->refcnt++; + -} + - + void object_put(struct object *obj) + { + - unsigned long flags; + - + - spin_lock_irqsave(&cache_lock, flags); + - __object_put(obj); + - spin_unlock_irqrestore(&cache_lock, flags); + + if (atomic_dec_and_test(&obj->refcnt)) + + kfree(obj); + } + + void object_get(struct object *obj) + { + - unsigned long flags; + - + - spin_lock_irqsave(&cache_lock, flags); + - __object_get(obj); + - spin_unlock_irqrestore(&cache_lock, flags); + + atomic_inc(&obj->refcnt); + } + + /* Must be holding cache_lock */ + @@ -65,7 +47,7 @@ + { + BUG_ON(!obj); + list_del(&obj->list); + - __object_put(obj); + + object_put(obj); + cache_num--; + } + + @@ -94,7 +76,7 @@ + strlcpy(obj->name, name, sizeof(obj->name)); + obj->id = id; + obj->popularity = 0; + - obj->refcnt = 1; /* The cache holds a reference */ + + atomic_set(&obj->refcnt, 1); /* The cache holds a reference */ + + spin_lock_irqsave(&cache_lock, flags); + __cache_add(obj); + @@ -119,7 +101,7 @@ + spin_lock_irqsave(&cache_lock, flags); + obj = __cache_find(id); + if (obj) + - __object_get(obj); + + object_get(obj); + spin_unlock_irqrestore(&cache_lock, flags); + return obj; + } + +Protecting The Objects Themselves +--------------------------------- + +In these examples, we assumed that the objects (except the reference +counts) never changed once they are created. If we wanted to allow the +name to change, there are three possibilities: + +- You can make ``cache_lock`` non-static, and tell people to grab that + lock before changing the name in any object. + +- You can provide a :c:func:`cache_obj_rename()` which grabs this + lock and changes the name for the caller, and tell everyone to use + that function. + +- You can make the ``cache_lock`` protect only the cache itself, and + use another lock to protect the name. + +Theoretically, you can make the locks as fine-grained as one lock for +every field, for every object. In practice, the most common variants +are: + +- One lock which protects the infrastructure (the ``cache`` list in + this example) and all the objects. This is what we have done so far. + +- One lock which protects the infrastructure (including the list + pointers inside the objects), and one lock inside the object which + protects the rest of that object. + +- Multiple locks to protect the infrastructure (eg. one lock per hash + chain), possibly with a separate per-object lock. + +Here is the "lock-per-object" implementation: + +:: + + --- cache.c.refcnt-atomic 2003-12-11 15:50:54.000000000 +1100 + +++ cache.c.perobjectlock 2003-12-11 17:15:03.000000000 +1100 + @@ -6,11 +6,17 @@ + + struct object + { + + /* These two protected by cache_lock. */ + struct list_head list; + + int popularity; + + + atomic_t refcnt; + + + + /* Doesn't change once created. */ + int id; + + + + spinlock_t lock; /* Protects the name */ + char name[32]; + - int popularity; + }; + + static DEFINE_SPINLOCK(cache_lock); + @@ -77,6 +84,7 @@ + obj->id = id; + obj->popularity = 0; + atomic_set(&obj->refcnt, 1); /* The cache holds a reference */ + + spin_lock_init(&obj->lock); + + spin_lock_irqsave(&cache_lock, flags); + __cache_add(obj); + +Note that I decide that the popularity count should be protected by the +``cache_lock`` rather than the per-object lock: this is because it (like +the :c:type:`struct list_head ` inside the object) +is logically part of the infrastructure. This way, I don't need to grab +the lock of every object in :c:func:`__cache_add()` when seeking +the least popular. + +I also decided that the id member is unchangeable, so I don't need to +grab each object lock in :c:func:`__cache_find()` to examine the +id: the object lock is only used by a caller who wants to read or write +the name field. + +Note also that I added a comment describing what data was protected by +which locks. This is extremely important, as it describes the runtime +behavior of the code, and can be hard to gain from just reading. And as +Alan Cox says, “Lock data, not code”. + +Common Problems +=============== + +Deadlock: Simple and Advanced +----------------------------- + +There is a coding bug where a piece of code tries to grab a spinlock +twice: it will spin forever, waiting for the lock to be released +(spinlocks, rwlocks and mutexes are not recursive in Linux). This is +trivial to diagnose: not a +stay-up-five-nights-talk-to-fluffy-code-bunnies kind of problem. + +For a slightly more complex case, imagine you have a region shared by a +softirq and user context. If you use a :c:func:`spin_lock()` call +to protect it, it is possible that the user context will be interrupted +by the softirq while it holds the lock, and the softirq will then spin +forever trying to get the same lock. + +Both of these are called deadlock, and as shown above, it can occur even +with a single CPU (although not on UP compiles, since spinlocks vanish +on kernel compiles with ``CONFIG_SMP``\ =n. You'll still get data +corruption in the second example). + +This complete lockup is easy to diagnose: on SMP boxes the watchdog +timer or compiling with ``DEBUG_SPINLOCK`` set +(``include/linux/spinlock.h``) will show this up immediately when it +happens. + +A more complex problem is the so-called 'deadly embrace', involving two +or more locks. Say you have a hash table: each entry in the table is a +spinlock, and a chain of hashed objects. Inside a softirq handler, you +sometimes want to alter an object from one place in the hash to another: +you grab the spinlock of the old hash chain and the spinlock of the new +hash chain, and delete the object from the old one, and insert it in the +new one. + +There are two problems here. First, if your code ever tries to move the +object to the same chain, it will deadlock with itself as it tries to +lock it twice. Secondly, if the same softirq on another CPU is trying to +move another object in the reverse direction, the following could +happen: + ++-----------------------+-----------------------+ +| CPU 1 | CPU 2 | ++=======================+=======================+ +| Grab lock A -> OK | Grab lock B -> OK | ++-----------------------+-----------------------+ +| Grab lock B -> spin | Grab lock A -> spin | ++-----------------------+-----------------------+ + +Table: Consequences + +The two CPUs will spin forever, waiting for the other to give up their +lock. It will look, smell, and feel like a crash. + +Preventing Deadlock +------------------- + +Textbooks will tell you that if you always lock in the same order, you +will never get this kind of deadlock. Practice will tell you that this +approach doesn't scale: when I create a new lock, I don't understand +enough of the kernel to figure out where in the 5000 lock hierarchy it +will fit. + +The best locks are encapsulated: they never get exposed in headers, and +are never held around calls to non-trivial functions outside the same +file. You can read through this code and see that it will never +deadlock, because it never tries to grab another lock while it has that +one. People using your code don't even need to know you are using a +lock. + +A classic problem here is when you provide callbacks or hooks: if you +call these with the lock held, you risk simple deadlock, or a deadly +embrace (who knows what the callback will do?). Remember, the other +programmers are out to get you, so don't do this. + +Overzealous Prevention Of Deadlocks +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Deadlocks are problematic, but not as bad as data corruption. Code which +grabs a read lock, searches a list, fails to find what it wants, drops +the read lock, grabs a write lock and inserts the object has a race +condition. + +If you don't see why, please stay the fuck away from my code. + +Racing Timers: A Kernel Pastime +------------------------------- + +Timers can produce their own special problems with races. Consider a +collection of objects (list, hash, etc) where each object has a timer +which is due to destroy it. + +If you want to destroy the entire collection (say on module removal), +you might do the following:: + + /* THIS CODE BAD BAD BAD BAD: IF IT WAS ANY WORSE IT WOULD USE + HUNGARIAN NOTATION */ + spin_lock_bh(&list_lock); + + while (list) { + struct foo *next = list->next; + del_timer(&list->timer); + kfree(list); + list = next; + } + + spin_unlock_bh(&list_lock); + + +Sooner or later, this will crash on SMP, because a timer can have just +gone off before the :c:func:`spin_lock_bh()`, and it will only get +the lock after we :c:func:`spin_unlock_bh()`, and then try to free +the element (which has already been freed!). + +This can be avoided by checking the result of +:c:func:`del_timer()`: if it returns 1, the timer has been deleted. +If 0, it means (in this case) that it is currently running, so we can +do:: + + retry: + spin_lock_bh(&list_lock); + + while (list) { + struct foo *next = list->next; + if (!del_timer(&list->timer)) { + /* Give timer a chance to delete this */ + spin_unlock_bh(&list_lock); + goto retry; + } + kfree(list); + list = next; + } + + spin_unlock_bh(&list_lock); + + +Another common problem is deleting timers which restart themselves (by +calling :c:func:`add_timer()` at the end of their timer function). +Because this is a fairly common case which is prone to races, you should +use :c:func:`del_timer_sync()` (``include/linux/timer.h``) to +handle this case. It returns the number of times the timer had to be +deleted before we finally stopped it from adding itself back in. + +Locking Speed +============= + +There are three main things to worry about when considering speed of +some code which does locking. First is concurrency: how many things are +going to be waiting while someone else is holding a lock. Second is the +time taken to actually acquire and release an uncontended lock. Third is +using fewer, or smarter locks. I'm assuming that the lock is used fairly +often: otherwise, you wouldn't be concerned about efficiency. + +Concurrency depends on how long the lock is usually held: you should +hold the lock for as long as needed, but no longer. In the cache +example, we always create the object without the lock held, and then +grab the lock only when we are ready to insert it in the list. + +Acquisition times depend on how much damage the lock operations do to +the pipeline (pipeline stalls) and how likely it is that this CPU was +the last one to grab the lock (ie. is the lock cache-hot for this CPU): +on a machine with more CPUs, this likelihood drops fast. Consider a +700MHz Intel Pentium III: an instruction takes about 0.7ns, an atomic +increment takes about 58ns, a lock which is cache-hot on this CPU takes +160ns, and a cacheline transfer from another CPU takes an additional 170 +to 360ns. (These figures from Paul McKenney's `Linux Journal RCU +article `__). + +These two aims conflict: holding a lock for a short time might be done +by splitting locks into parts (such as in our final per-object-lock +example), but this increases the number of lock acquisitions, and the +results are often slower than having a single lock. This is another +reason to advocate locking simplicity. + +The third concern is addressed below: there are some methods to reduce +the amount of locking which needs to be done. + +Read/Write Lock Variants +------------------------ + +Both spinlocks and mutexes have read/write variants: ``rwlock_t`` and +:c:type:`struct rw_semaphore `. These divide +users into two classes: the readers and the writers. If you are only +reading the data, you can get a read lock, but to write to the data you +need the write lock. Many people can hold a read lock, but a writer must +be sole holder. + +If your code divides neatly along reader/writer lines (as our cache code +does), and the lock is held by readers for significant lengths of time, +using these locks can help. They are slightly slower than the normal +locks though, so in practice ``rwlock_t`` is not usually worthwhile. + +Avoiding Locks: Read Copy Update +-------------------------------- + +There is a special method of read/write locking called Read Copy Update. +Using RCU, the readers can avoid taking a lock altogether: as we expect +our cache to be read more often than updated (otherwise the cache is a +waste of time), it is a candidate for this optimization. + +How do we get rid of read locks? Getting rid of read locks means that +writers may be changing the list underneath the readers. That is +actually quite simple: we can read a linked list while an element is +being added if the writer adds the element very carefully. For example, +adding ``new`` to a single linked list called ``list``:: + + new->next = list->next; + wmb(); + list->next = new; + + +The :c:func:`wmb()` is a write memory barrier. It ensures that the +first operation (setting the new element's ``next`` pointer) is complete +and will be seen by all CPUs, before the second operation is (putting +the new element into the list). This is important, since modern +compilers and modern CPUs can both reorder instructions unless told +otherwise: we want a reader to either not see the new element at all, or +see the new element with the ``next`` pointer correctly pointing at the +rest of the list. + +Fortunately, there is a function to do this for standard +:c:type:`struct list_head ` lists: +:c:func:`list_add_rcu()` (``include/linux/list.h``). + +Removing an element from the list is even simpler: we replace the +pointer to the old element with a pointer to its successor, and readers +will either see it, or skip over it. + +:: + + list->next = old->next; + + +There is :c:func:`list_del_rcu()` (``include/linux/list.h``) which +does this (the normal version poisons the old object, which we don't +want). + +The reader must also be careful: some CPUs can look through the ``next`` +pointer to start reading the contents of the next element early, but +don't realize that the pre-fetched contents is wrong when the ``next`` +pointer changes underneath them. Once again, there is a +:c:func:`list_for_each_entry_rcu()` (``include/linux/list.h``) +to help you. Of course, writers can just use +:c:func:`list_for_each_entry()`, since there cannot be two +simultaneous writers. + +Our final dilemma is this: when can we actually destroy the removed +element? Remember, a reader might be stepping through this element in +the list right now: if we free this element and the ``next`` pointer +changes, the reader will jump off into garbage and crash. We need to +wait until we know that all the readers who were traversing the list +when we deleted the element are finished. We use +:c:func:`call_rcu()` to register a callback which will actually +destroy the object once all pre-existing readers are finished. +Alternatively, :c:func:`synchronize_rcu()` may be used to block +until all pre-existing are finished. + +But how does Read Copy Update know when the readers are finished? The +method is this: firstly, the readers always traverse the list inside +:c:func:`rcu_read_lock()`/:c:func:`rcu_read_unlock()` pairs: +these simply disable preemption so the reader won't go to sleep while +reading the list. + +RCU then waits until every other CPU has slept at least once: since +readers cannot sleep, we know that any readers which were traversing the +list during the deletion are finished, and the callback is triggered. +The real Read Copy Update code is a little more optimized than this, but +this is the fundamental idea. + +:: + + --- cache.c.perobjectlock 2003-12-11 17:15:03.000000000 +1100 + +++ cache.c.rcupdate 2003-12-11 17:55:14.000000000 +1100 + @@ -1,15 +1,18 @@ + #include + #include + #include + +#include + #include + #include + + struct object + { + - /* These two protected by cache_lock. */ + + /* This is protected by RCU */ + struct list_head list; + int popularity; + + + struct rcu_head rcu; + + + atomic_t refcnt; + + /* Doesn't change once created. */ + @@ -40,7 +43,7 @@ + { + struct object *i; + + - list_for_each_entry(i, &cache, list) { + + list_for_each_entry_rcu(i, &cache, list) { + if (i->id == id) { + i->popularity++; + return i; + @@ -49,19 +52,25 @@ + return NULL; + } + + +/* Final discard done once we know no readers are looking. */ + +static void cache_delete_rcu(void *arg) + +{ + + object_put(arg); + +} + + + /* Must be holding cache_lock */ + static void __cache_delete(struct object *obj) + { + BUG_ON(!obj); + - list_del(&obj->list); + - object_put(obj); + + list_del_rcu(&obj->list); + cache_num--; + + call_rcu(&obj->rcu, cache_delete_rcu); + } + + /* Must be holding cache_lock */ + static void __cache_add(struct object *obj) + { + - list_add(&obj->list, &cache); + + list_add_rcu(&obj->list, &cache); + if (++cache_num > MAX_CACHE_SIZE) { + struct object *i, *outcast = NULL; + list_for_each_entry(i, &cache, list) { + @@ -104,12 +114,11 @@ + struct object *cache_find(int id) + { + struct object *obj; + - unsigned long flags; + + - spin_lock_irqsave(&cache_lock, flags); + + rcu_read_lock(); + obj = __cache_find(id); + if (obj) + object_get(obj); + - spin_unlock_irqrestore(&cache_lock, flags); + + rcu_read_unlock(); + return obj; + } + +Note that the reader will alter the popularity member in +:c:func:`__cache_find()`, and now it doesn't hold a lock. One +solution would be to make it an ``atomic_t``, but for this usage, we +don't really care about races: an approximate result is good enough, so +I didn't change it. + +The result is that :c:func:`cache_find()` requires no +synchronization with any other functions, so is almost as fast on SMP as +it would be on UP. + +There is a further optimization possible here: remember our original +cache code, where there were no reference counts and the caller simply +held the lock whenever using the object? This is still possible: if you +hold the lock, no one can delete the object, so you don't need to get +and put the reference count. + +Now, because the 'read lock' in RCU is simply disabling preemption, a +caller which always has preemption disabled between calling +:c:func:`cache_find()` and :c:func:`object_put()` does not +need to actually get and put the reference count: we could expose +:c:func:`__cache_find()` by making it non-static, and such +callers could simply call that. + +The benefit here is that the reference count is not written to: the +object is not altered in any way, which is much faster on SMP machines +due to caching. + +Per-CPU Data +------------ + +Another technique for avoiding locking which is used fairly widely is to +duplicate information for each CPU. For example, if you wanted to keep a +count of a common condition, you could use a spin lock and a single +counter. Nice and simple. + +If that was too slow (it's usually not, but if you've got a really big +machine to test on and can show that it is), you could instead use a +counter for each CPU, then none of them need an exclusive lock. See +:c:func:`DEFINE_PER_CPU()`, :c:func:`get_cpu_var()` and +:c:func:`put_cpu_var()` (``include/linux/percpu.h``). + +Of particular use for simple per-cpu counters is the ``local_t`` type, +and the :c:func:`cpu_local_inc()` and related functions, which are +more efficient than simple code on some architectures +(``include/asm/local.h``). + +Note that there is no simple, reliable way of getting an exact value of +such a counter, without introducing more locks. This is not a problem +for some uses. + +Data Which Mostly Used By An IRQ Handler +---------------------------------------- + +If data is always accessed from within the same IRQ handler, you don't +need a lock at all: the kernel already guarantees that the irq handler +will not run simultaneously on multiple CPUs. + +Manfred Spraul points out that you can still do this, even if the data +is very occasionally accessed in user context or softirqs/tasklets. The +irq handler doesn't use a lock, and all other accesses are done as so:: + + spin_lock(&lock); + disable_irq(irq); + ... + enable_irq(irq); + spin_unlock(&lock); + +The :c:func:`disable_irq()` prevents the irq handler from running +(and waits for it to finish if it's currently running on other CPUs). +The spinlock prevents any other accesses happening at the same time. +Naturally, this is slower than just a :c:func:`spin_lock_irq()` +call, so it only makes sense if this type of access happens extremely +rarely. + +What Functions Are Safe To Call From Interrupts? +================================================ + +Many functions in the kernel sleep (ie. call schedule()) directly or +indirectly: you can never call them while holding a spinlock, or with +preemption disabled. This also means you need to be in user context: +calling them from an interrupt is illegal. + +Some Functions Which Sleep +-------------------------- + +The most common ones are listed below, but you usually have to read the +code to find out if other calls are safe. If everyone else who calls it +can sleep, you probably need to be able to sleep, too. In particular, +registration and deregistration functions usually expect to be called +from user context, and can sleep. + +- Accesses to userspace: + + - :c:func:`copy_from_user()` + + - :c:func:`copy_to_user()` + + - :c:func:`get_user()` + + - :c:func:`put_user()` + +- :c:func:`kmalloc(GFP_KERNEL) ` + +- :c:func:`mutex_lock_interruptible()` and + :c:func:`mutex_lock()` + + There is a :c:func:`mutex_trylock()` which does not sleep. + Still, it must not be used inside interrupt context since its + implementation is not safe for that. :c:func:`mutex_unlock()` + will also never sleep. It cannot be used in interrupt context either + since a mutex must be released by the same task that acquired it. + +Some Functions Which Don't Sleep +-------------------------------- + +Some functions are safe to call from any context, or holding almost any +lock. + +- :c:func:`printk()` + +- :c:func:`kfree()` + +- :c:func:`add_timer()` and :c:func:`del_timer()` + +Mutex API reference +=================== + +.. kernel-doc:: include/linux/mutex.h + :internal: + +.. kernel-doc:: kernel/locking/mutex.c + :export: + +Futex API reference +=================== + +.. kernel-doc:: kernel/futex.c + :internal: + +Further reading +=============== + +- ``Documentation/locking/spinlocks.txt``: Linus Torvalds' spinlocking + tutorial in the kernel sources. + +- Unix Systems for Modern Architectures: Symmetric Multiprocessing and + Caching for Kernel Programmers: + + Curt Schimmel's very good introduction to kernel level locking (not + written for Linux, but nearly everything applies). The book is + expensive, but really worth every penny to understand SMP locking. + [ISBN: 0201633388] + +Thanks +====== + +Thanks to Telsa Gwynne for DocBooking, neatening and adding style. + +Thanks to Martin Pool, Philipp Rumpf, Stephen Rothwell, Paul Mackerras, +Ruedi Aschwanden, Alan Cox, Manfred Spraul, Tim Waugh, Pete Zaitcev, +James Morris, Robert Love, Paul McKenney, John Ashby for proofreading, +correcting, flaming, commenting. + +Thanks to the cabal for having no influence on this document. + +Glossary +======== + +preemption + Prior to 2.5, or when ``CONFIG_PREEMPT`` is unset, processes in user + context inside the kernel would not preempt each other (ie. you had that + CPU until you gave it up, except for interrupts). With the addition of + ``CONFIG_PREEMPT`` in 2.5.4, this changed: when in user context, higher + priority tasks can "cut in": spinlocks were changed to disable + preemption, even on UP. + +bh + Bottom Half: for historical reasons, functions with '_bh' in them often + now refer to any software interrupt, e.g. :c:func:`spin_lock_bh()` + blocks any software interrupt on the current CPU. Bottom halves are + deprecated, and will eventually be replaced by tasklets. Only one bottom + half will be running at any time. + +Hardware Interrupt / Hardware IRQ + Hardware interrupt request. :c:func:`in_irq()` returns true in a + hardware interrupt handler. + +Interrupt Context + Not user context: processing a hardware irq or software irq. Indicated + by the :c:func:`in_interrupt()` macro returning true. + +SMP + Symmetric Multi-Processor: kernels compiled for multiple-CPU machines. + (``CONFIG_SMP=y``). + +Software Interrupt / softirq + Software interrupt handler. :c:func:`in_irq()` returns false; + :c:func:`in_softirq()` returns true. Tasklets and softirqs both + fall into the category of 'software interrupts'. + + Strictly speaking a softirq is one of up to 32 enumerated software + interrupts which can run on multiple CPUs at once. Sometimes used to + refer to tasklets as well (ie. all software interrupts). + +tasklet + A dynamically-registrable software interrupt, which is guaranteed to + only run on one CPU at a time. + +timer + A dynamically-registrable software interrupt, which is run at (or close + to) a given time. When running, it is just like a tasklet (in fact, they + are called from the ``TIMER_SOFTIRQ``). + +UP + Uni-Processor: Non-SMP. (``CONFIG_SMP=n``). + +User Context + The kernel executing on behalf of a particular process (ie. a system + call or trap) or kernel thread. You can tell which process with the + ``current`` macro.) Not to be confused with userspace. Can be + interrupted by software or hardware interrupts. + +Userspace + A process executing its own code outside the kernel. diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt index df31e30b6a0259..2cb7dc5c0e0db3 100644 --- a/Documentation/kernel-per-CPU-kthreads.txt +++ b/Documentation/kernel-per-CPU-kthreads.txt @@ -109,13 +109,12 @@ SCHED_SOFTIRQ: Do all of the following: on that CPU. If a thread that expects to run on the de-jittered CPU awakens, the scheduler will send an IPI that can result in a subsequent SCHED_SOFTIRQ. -2. Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y, - CONFIG_NO_HZ_FULL=y, and, in addition, ensure that the CPU - to be de-jittered is marked as an adaptive-ticks CPU using the - "nohz_full=" boot parameter. This reduces the number of - scheduler-clock interrupts that the de-jittered CPU receives, - minimizing its chances of being selected to do the load balancing - work that runs in SCHED_SOFTIRQ context. +2. CONFIG_NO_HZ_FULL=y and ensure that the CPU to be de-jittered + is marked as an adaptive-ticks CPU using the "nohz_full=" + boot parameter. This reduces the number of scheduler-clock + interrupts that the de-jittered CPU receives, minimizing its + chances of being selected to do the load balancing work that + runs in SCHED_SOFTIRQ context. 3. To the extent possible, keep the CPU out of the kernel when it is non-idle, for example, by avoiding system calls and by forcing both kernel threads and interrupts to execute elsewhere. @@ -135,11 +134,10 @@ HRTIMER_SOFTIRQ: Do all of the following: RCU_SOFTIRQ: Do at least one of the following: 1. Offload callbacks and keep the CPU in either dyntick-idle or adaptive-ticks state by doing all of the following: - a. Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y, - CONFIG_NO_HZ_FULL=y, and, in addition ensure that the CPU - to be de-jittered is marked as an adaptive-ticks CPU using - the "nohz_full=" boot parameter. Bind the rcuo kthreads - to housekeeping CPUs, which can tolerate OS jitter. + a. CONFIG_NO_HZ_FULL=y and ensure that the CPU to be + de-jittered is marked as an adaptive-ticks CPU using the + "nohz_full=" boot parameter. Bind the rcuo kthreads to + housekeeping CPUs, which can tolerate OS jitter. b. To the extent possible, keep the CPU out of the kernel when it is non-idle, for example, by avoiding system calls and by forcing both kernel threads and interrupts @@ -236,11 +234,10 @@ To reduce its OS jitter, do at least one of the following: is feasible only if your workload never requires RCU priority boosting, for example, if you ensure frequent idle time on all CPUs that might execute within the kernel. -3. Build with CONFIG_RCU_NOCB_CPU=y and CONFIG_RCU_NOCB_CPU_ALL=y, - which offloads all RCU callbacks to kthreads that can be moved - off of CPUs susceptible to OS jitter. This approach prevents the - rcuc/%u kthreads from having any work to do, so that they are - never awakened. +3. Build with CONFIG_RCU_NOCB_CPU=y and boot with the rcu_nocbs= + boot parameter offloading RCU callbacks from all CPUs susceptible + to OS jitter. This approach prevents the rcuc/%u kthreads from + having any work to do, so that they are never awakened. 4. Ensure that the CPU never enters the kernel, and, in particular, avoid initiating any CPU hotplug operations on this CPU. This is another way of preventing any callbacks from being queued on the diff --git a/Documentation/lsm.txt b/Documentation/lsm.txt new file mode 100644 index 00000000000000..ad4dfd020e0d52 --- /dev/null +++ b/Documentation/lsm.txt @@ -0,0 +1,201 @@ +======================================================== +Linux Security Modules: General Security Hooks for Linux +======================================================== + +:Author: Stephen Smalley +:Author: Timothy Fraser +:Author: Chris Vance + +.. note:: + + The APIs described in this book are outdated. + +Introduction +============ + +In March 2001, the National Security Agency (NSA) gave a presentation +about Security-Enhanced Linux (SELinux) at the 2.5 Linux Kernel Summit. +SELinux is an implementation of flexible and fine-grained +nondiscretionary access controls in the Linux kernel, originally +implemented as its own particular kernel patch. Several other security +projects (e.g. RSBAC, Medusa) have also developed flexible access +control architectures for the Linux kernel, and various projects have +developed particular access control models for Linux (e.g. LIDS, DTE, +SubDomain). Each project has developed and maintained its own kernel +patch to support its security needs. + +In response to the NSA presentation, Linus Torvalds made a set of +remarks that described a security framework he would be willing to +consider for inclusion in the mainstream Linux kernel. He described a +general framework that would provide a set of security hooks to control +operations on kernel objects and a set of opaque security fields in +kernel data structures for maintaining security attributes. This +framework could then be used by loadable kernel modules to implement any +desired model of security. Linus also suggested the possibility of +migrating the Linux capabilities code into such a module. + +The Linux Security Modules (LSM) project was started by WireX to develop +such a framework. LSM is a joint development effort by several security +projects, including Immunix, SELinux, SGI and Janus, and several +individuals, including Greg Kroah-Hartman and James Morris, to develop a +Linux kernel patch that implements this framework. The patch is +currently tracking the 2.4 series and is targeted for integration into +the 2.5 development series. This technical report provides an overview +of the framework and the example capabilities security module provided +by the LSM kernel patch. + +LSM Framework +============= + +The LSM kernel patch provides a general kernel framework to support +security modules. In particular, the LSM framework is primarily focused +on supporting access control modules, although future development is +likely to address other security needs such as auditing. By itself, the +framework does not provide any additional security; it merely provides +the infrastructure to support security modules. The LSM kernel patch +also moves most of the capabilities logic into an optional security +module, with the system defaulting to the traditional superuser logic. +This capabilities module is discussed further in +`LSM Capabilities Module <#cap>`__. + +The LSM kernel patch adds security fields to kernel data structures and +inserts calls to hook functions at critical points in the kernel code to +manage the security fields and to perform access control. It also adds +functions for registering and unregistering security modules, and adds a +general :c:func:`security()` system call to support new system calls +for security-aware applications. + +The LSM security fields are simply ``void*`` pointers. For process and +program execution security information, security fields were added to +:c:type:`struct task_struct ` and +:c:type:`struct linux_binprm `. For filesystem +security information, a security field was added to :c:type:`struct +super_block `. For pipe, file, and socket security +information, security fields were added to :c:type:`struct inode +` and :c:type:`struct file `. For packet and +network device security information, security fields were added to +:c:type:`struct sk_buff ` and :c:type:`struct +net_device `. For System V IPC security information, +security fields were added to :c:type:`struct kern_ipc_perm +` and :c:type:`struct msg_msg +`; additionally, the definitions for :c:type:`struct +msg_msg `, struct msg_queue, and struct shmid_kernel +were moved to header files (``include/linux/msg.h`` and +``include/linux/shm.h`` as appropriate) to allow the security modules to +use these definitions. + +Each LSM hook is a function pointer in a global table, security_ops. +This table is a :c:type:`struct security_operations +` structure as defined by +``include/linux/security.h``. Detailed documentation for each hook is +included in this header file. At present, this structure consists of a +collection of substructures that group related hooks based on the kernel +object (e.g. task, inode, file, sk_buff, etc) as well as some top-level +hook function pointers for system operations. This structure is likely +to be flattened in the future for performance. The placement of the hook +calls in the kernel code is described by the "called:" lines in the +per-hook documentation in the header file. The hook calls can also be +easily found in the kernel code by looking for the string +"security_ops->". + +Linus mentioned per-process security hooks in his original remarks as a +possible alternative to global security hooks. However, if LSM were to +start from the perspective of per-process hooks, then the base framework +would have to deal with how to handle operations that involve multiple +processes (e.g. kill), since each process might have its own hook for +controlling the operation. This would require a general mechanism for +composing hooks in the base framework. Additionally, LSM would still +need global hooks for operations that have no process context (e.g. +network input operations). Consequently, LSM provides global security +hooks, but a security module is free to implement per-process hooks +(where that makes sense) by storing a security_ops table in each +process' security field and then invoking these per-process hooks from +the global hooks. The problem of composition is thus deferred to the +module. + +The global security_ops table is initialized to a set of hook functions +provided by a dummy security module that provides traditional superuser +logic. A :c:func:`register_security()` function (in +``security/security.c``) is provided to allow a security module to set +security_ops to refer to its own hook functions, and an +:c:func:`unregister_security()` function is provided to revert +security_ops to the dummy module hooks. This mechanism is used to set +the primary security module, which is responsible for making the final +decision for each hook. + +LSM also provides a simple mechanism for stacking additional security +modules with the primary security module. It defines +:c:func:`register_security()` and +:c:func:`unregister_security()` hooks in the :c:type:`struct +security_operations ` structure and +provides :c:func:`mod_reg_security()` and +:c:func:`mod_unreg_security()` functions that invoke these hooks +after performing some sanity checking. A security module can call these +functions in order to stack with other modules. However, the actual +details of how this stacking is handled are deferred to the module, +which can implement these hooks in any way it wishes (including always +returning an error if it does not wish to support stacking). In this +manner, LSM again defers the problem of composition to the module. + +Although the LSM hooks are organized into substructures based on kernel +object, all of the hooks can be viewed as falling into two major +categories: hooks that are used to manage the security fields and hooks +that are used to perform access control. Examples of the first category +of hooks include the :c:func:`alloc_security()` and +:c:func:`free_security()` hooks defined for each kernel data +structure that has a security field. These hooks are used to allocate +and free security structures for kernel objects. The first category of +hooks also includes hooks that set information in the security field +after allocation, such as the :c:func:`post_lookup()` hook in +:c:type:`struct inode_security_ops `. +This hook is used to set security information for inodes after +successful lookup operations. An example of the second category of hooks +is the :c:func:`permission()` hook in :c:type:`struct +inode_security_ops `. This hook checks +permission when accessing an inode. + +LSM Capabilities Module +======================= + +The LSM kernel patch moves most of the existing POSIX.1e capabilities +logic into an optional security module stored in the file +``security/capability.c``. This change allows users who do not want to +use capabilities to omit this code entirely from their kernel, instead +using the dummy module for traditional superuser logic or any other +module that they desire. This change also allows the developers of the +capabilities logic to maintain and enhance their code more freely, +without needing to integrate patches back into the base kernel. + +In addition to moving the capabilities logic, the LSM kernel patch could +move the capability-related fields from the kernel data structures into +the new security fields managed by the security modules. However, at +present, the LSM kernel patch leaves the capability fields in the kernel +data structures. In his original remarks, Linus suggested that this +might be preferable so that other security modules can be easily stacked +with the capabilities module without needing to chain multiple security +structures on the security field. It also avoids imposing extra overhead +on the capabilities module to manage the security fields. However, the +LSM framework could certainly support such a move if it is determined to +be desirable, with only a few additional changes described below. + +At present, the capabilities logic for computing process capabilities on +:c:func:`execve()` and :c:func:`set\*uid()`, checking +capabilities for a particular process, saving and checking capabilities +for netlink messages, and handling the :c:func:`capget()` and +:c:func:`capset()` system calls have been moved into the +capabilities module. There are still a few locations in the base kernel +where capability-related fields are directly examined or modified, but +the current version of the LSM patch does allow a security module to +completely replace the assignment and testing of capabilities. These few +locations would need to be changed if the capability-related fields were +moved into the security field. The following is a list of known +locations that still perform such direct examination or modification of +capability-related fields: + +- ``fs/open.c``::c:func:`sys_access()` + +- ``fs/lockd/host.c``::c:func:`nlm_bind_host()` + +- ``fs/nfsd/auth.c``::c:func:`nfsd_setuser()` + +- ``fs/proc/array.c``::c:func:`task_cap()` diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 732f10ea382e8e..9d5e0f853f087c 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -27,7 +27,7 @@ The purpose of this document is twofold: (2) to provide a guide as to how to use the barriers that are available. Note that an architecture can provide more than the minimum requirement -for any particular barrier, but if the architecure provides less than +for any particular barrier, but if the architecture provides less than that, that architecture is incorrect. Note also that it is possible that a barrier may be a no-op for an diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt index 56e36861245f10..d52d191bbb0c4c 100644 --- a/Documentation/networking/checksum-offloads.txt +++ b/Documentation/networking/checksum-offloads.txt @@ -35,6 +35,9 @@ This interface only allows a single checksum to be offloaded. Where encapsulation is used, the packet may have multiple checksum fields in different header layers, and the rest will have to be handled by another mechanism such as LCO or RCO. +CRC32c can also be offloaded using this interface, by means of filling + skb->csum_start and skb->csum_offset as described above, and setting + skb->csum_not_inet: see skbuff.h comment (section 'D') for more details. No offloading of the IP header checksum is performed; it is always done in software. This is OK because when we build the IP header, we obviously have it in cache, so summing it isn't expensive. It's also rather short. @@ -49,9 +52,9 @@ A driver declares its offload capabilities in netdev->hw_features; see and csum_offset given in the SKB; if it tries to deduce these itself in hardware (as some NICs do) the driver should check that the values in the SKB match those which the hardware will deduce, and if not, fall back to - checksumming in software instead (with skb_checksum_help or one of the - skb_csum_off_chk* functions as mentioned in include/linux/skbuff.h). This - is a pain, but that's what you get when hardware tries to be clever. + checksumming in software instead (with skb_csum_hwoffload_help() or one of + the skb_checksum_help() / skb_crc32c_csum_help functions, as mentioned in + include/linux/skbuff.h). The stack should, for the most part, assume that checksum offload is supported by the underlying device. The only place that should check is @@ -60,7 +63,7 @@ The stack should, for the most part, assume that checksum offload is may include other offloads besides TX Checksum Offload) and, if they are not supported or enabled on the device (determined by netdev->features), performs the corresponding offload in software. In the case of TX - Checksum Offload, that means calling skb_checksum_help(skb). + Checksum Offload, that means calling skb_csum_hwoffload_help(skb, features). LCO: Local Checksum Offload diff --git a/Documentation/networking/conf.py b/Documentation/networking/conf.py new file mode 100644 index 00000000000000..40f69e67a88315 --- /dev/null +++ b/Documentation/networking/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "Linux Networking Documentation" + +tags.add("subproject") + +latex_documents = [ + ('index', 'networking.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/networking/dns_resolver.txt b/Documentation/networking/dns_resolver.txt index d86adcdae4202a..eaa8f9a6fd5d2d 100644 --- a/Documentation/networking/dns_resolver.txt +++ b/Documentation/networking/dns_resolver.txt @@ -143,7 +143,7 @@ the key will be discarded and recreated when the data it holds has expired. dns_query() returns a copy of the value attached to the key, or an error if that is indicated instead. -See for further +See for further information about request-key function. diff --git a/Documentation/networking/dpaa.txt b/Documentation/networking/dpaa.txt new file mode 100644 index 00000000000000..76e016d4d34496 --- /dev/null +++ b/Documentation/networking/dpaa.txt @@ -0,0 +1,194 @@ +The QorIQ DPAA Ethernet Driver +============================== + +Authors: +Madalin Bucur +Camelia Groza + +Contents +======== + + - DPAA Ethernet Overview + - DPAA Ethernet Supported SoCs + - Configuring DPAA Ethernet in your kernel + - DPAA Ethernet Frame Processing + - DPAA Ethernet Features + - Debugging + +DPAA Ethernet Overview +====================== + +DPAA stands for Data Path Acceleration Architecture and it is a +set of networking acceleration IPs that are available on several +generations of SoCs, both on PowerPC and ARM64. + +The Freescale DPAA architecture consists of a series of hardware blocks +that support Ethernet connectivity. The Ethernet driver depends upon the +following drivers in the Linux kernel: + + - Peripheral Access Memory Unit (PAMU) (* needed only for PPC platforms) + drivers/iommu/fsl_* + - Frame Manager (FMan) + drivers/net/ethernet/freescale/fman + - Queue Manager (QMan), Buffer Manager (BMan) + drivers/soc/fsl/qbman + +A simplified view of the dpaa_eth interfaces mapped to FMan MACs: + + dpaa_eth /eth0\ ... /ethN\ + driver | | | | + ------------- ---- ----------- ---- ------------- + -Ports / Tx Rx \ ... / Tx Rx \ + FMan | | | | + -MACs | MAC0 | | MACN | + / dtsec0 \ ... / dtsecN \ (or tgec) + / \ / \(or memac) + --------- -------------- --- -------------- --------- + FMan, FMan Port, FMan SP, FMan MURAM drivers + --------------------------------------------------------- + FMan HW blocks: MURAM, MACs, Ports, SP + --------------------------------------------------------- + +The dpaa_eth relation to the QMan, BMan and FMan: + ________________________________ + dpaa_eth / eth0 \ + driver / \ + --------- -^- -^- -^- --- --------- + QMan driver / \ / \ / \ \ / | BMan | + |Rx | |Rx | |Tx | |Tx | | driver | + --------- |Dfl| |Err| |Cnf| |FQs| | | + QMan HW |FQ | |FQ | |FQs| | | | | + / \ / \ / \ \ / | | + --------- --- --- --- -v- --------- + | FMan QMI | | + | FMan HW FMan BMI | BMan HW | + ----------------------- -------- + +where the acronyms used above (and in the code) are: +DPAA = Data Path Acceleration Architecture +FMan = DPAA Frame Manager +QMan = DPAA Queue Manager +BMan = DPAA Buffers Manager +QMI = QMan interface in FMan +BMI = BMan interface in FMan +FMan SP = FMan Storage Profiles +MURAM = Multi-user RAM in FMan +FQ = QMan Frame Queue +Rx Dfl FQ = default reception FQ +Rx Err FQ = Rx error frames FQ +Tx Cnf FQ = Tx confirmation FQs +Tx FQs = transmission frame queues +dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps) +tgec = ten gigabit Ethernet controller (10 Gbps) +memac = multirate Ethernet MAC (10/100/1000/10000) + +DPAA Ethernet Supported SoCs +============================ + +The DPAA drivers enable the Ethernet controllers present on the following SoCs: + +# PPC +P1023 +P2041 +P3041 +P4080 +P5020 +P5040 +T1023 +T1024 +T1040 +T1042 +T2080 +T4240 +B4860 + +# ARM +LS1043A +LS1046A + +Configuring DPAA Ethernet in your kernel +======================================== + +To enable the DPAA Ethernet driver, the following Kconfig options are required: + +# common for arch/arm64 and arch/powerpc platforms +CONFIG_FSL_DPAA=y +CONFIG_FSL_FMAN=y +CONFIG_FSL_DPAA_ETH=y +CONFIG_FSL_XGMAC_MDIO=y + +# for arch/powerpc only +CONFIG_FSL_PAMU=y + +# common options needed for the PHYs used on the RDBs +CONFIG_VITESSE_PHY=y +CONFIG_REALTEK_PHY=y +CONFIG_AQUANTIA_PHY=y + +DPAA Ethernet Frame Processing +============================== + +On Rx, buffers for the incoming frames are retrieved from one of the three +existing buffers pools. The driver initializes and seeds these, each with +buffers of different sizes: 1KB, 2KB and 4KB. + +On Tx, all transmitted frames are returned to the driver through Tx +confirmation frame queues. The driver is then responsible for freeing the +buffers. In order to do this properly, a backpointer is added to the buffer +before transmission that points to the skb. When the buffer returns to the +driver on a confirmation FQ, the skb can be correctly consumed. + +DPAA Ethernet Features +====================== + +Currently the DPAA Ethernet driver enables the basic features required for +a Linux Ethernet driver. The support for advanced features will be added +gradually. + +The driver has Rx and Tx checksum offloading for UDP and TCP. Currently the Rx +checksum offload feature is enabled by default and cannot be controlled through +ethtool. + +The driver has support for multiple prioritized Tx traffic classes. Priorities +range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with +strict priority levels. Each traffic class contains NR_CPU TX queues. By +default, only one traffic class is enabled and the lowest priority Tx queues +are used. Higher priority traffic classes can be enabled with the mqprio +qdisc. For example, all four traffic classes are enabled on an interface with +the following command. Furthermore, skb priority levels are mapped to traffic +classes as follows: + + * priorities 0 to 3 - traffic class 0 (low priority) + * priorities 4 to 7 - traffic class 1 (medium-low priority) + * priorities 8 to 11 - traffic class 2 (medium-high priority) + * priorities 12 to 15 - traffic class 3 (high priority) + +tc qdisc add dev root handle 1: \ + mqprio num_tc 4 map 0 0 0 0 1 1 1 1 2 2 2 2 3 3 3 3 hw 1 + +Debugging +========= + +The following statistics are exported for each interface through ethtool: + + - interrupt count per CPU + - Rx packets count per CPU + - Tx packets count per CPU + - Tx confirmed packets count per CPU + - Tx S/G frames count per CPU + - Tx error count per CPU + - Rx error count per CPU + - Rx error count per type + - congestion related statistics: + - congestion status + - time spent in congestion + - number of time the device entered congestion + - dropped packets count per cause + +The driver also exports the following information in sysfs: + + - the FQ IDs for each FQ type + /sys/devices/platform/dpaa-ethernet.0/net//fqids + + - the IDs of the buffer pools in use + /sys/devices/platform/dpaa-ethernet.0/net//bpids diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst new file mode 100644 index 00000000000000..b5bd87e01f52e3 --- /dev/null +++ b/Documentation/networking/index.rst @@ -0,0 +1,18 @@ +Linux Networking Documentation +============================== + +Contents: + +.. toctree:: + :maxdepth: 2 + + kapi + z8530book + +.. only:: subproject + + Indices + ======= + + * :ref:`genindex` + diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst new file mode 100644 index 00000000000000..580289f345daa3 --- /dev/null +++ b/Documentation/networking/kapi.rst @@ -0,0 +1,147 @@ +========================================= +Linux Networking and Network Devices APIs +========================================= + +Linux Networking +================ + +Networking Base Types +--------------------- + +.. kernel-doc:: include/linux/net.h + :internal: + +Socket Buffer Functions +----------------------- + +.. kernel-doc:: include/linux/skbuff.h + :internal: + +.. kernel-doc:: include/net/sock.h + :internal: + +.. kernel-doc:: net/socket.c + :export: + +.. kernel-doc:: net/core/skbuff.c + :export: + +.. kernel-doc:: net/core/sock.c + :export: + +.. kernel-doc:: net/core/datagram.c + :export: + +.. kernel-doc:: net/core/stream.c + :export: + +Socket Filter +------------- + +.. kernel-doc:: net/core/filter.c + :export: + +Generic Network Statistics +-------------------------- + +.. kernel-doc:: include/uapi/linux/gen_stats.h + :internal: + +.. kernel-doc:: net/core/gen_stats.c + :export: + +.. kernel-doc:: net/core/gen_estimator.c + :export: + +SUN RPC subsystem +----------------- + +.. kernel-doc:: net/sunrpc/xdr.c + :export: + +.. kernel-doc:: net/sunrpc/svc_xprt.c + :export: + +.. kernel-doc:: net/sunrpc/xprt.c + :export: + +.. kernel-doc:: net/sunrpc/sched.c + :export: + +.. kernel-doc:: net/sunrpc/socklib.c + :export: + +.. kernel-doc:: net/sunrpc/stats.c + :export: + +.. kernel-doc:: net/sunrpc/rpc_pipe.c + :export: + +.. kernel-doc:: net/sunrpc/rpcb_clnt.c + :export: + +.. kernel-doc:: net/sunrpc/clnt.c + :export: + +WiMAX +----- + +.. kernel-doc:: net/wimax/op-msg.c + :export: + +.. kernel-doc:: net/wimax/op-reset.c + :export: + +.. kernel-doc:: net/wimax/op-rfkill.c + :export: + +.. kernel-doc:: net/wimax/stack.c + :export: + +.. kernel-doc:: include/net/wimax.h + :internal: + +.. kernel-doc:: include/uapi/linux/wimax.h + :internal: + +Network device support +====================== + +Driver Support +-------------- + +.. kernel-doc:: net/core/dev.c + :export: + +.. kernel-doc:: net/ethernet/eth.c + :export: + +.. kernel-doc:: net/sched/sch_generic.c + :export: + +.. kernel-doc:: include/linux/etherdevice.h + :internal: + +.. kernel-doc:: include/linux/netdevice.h + :internal: + +PHY Support +----------- + +.. kernel-doc:: drivers/net/phy/phy.c + :export: + +.. kernel-doc:: drivers/net/phy/phy.c + :internal: + +.. kernel-doc:: drivers/net/phy/phy_device.c + :export: + +.. kernel-doc:: drivers/net/phy/phy_device.c + :internal: + +.. kernel-doc:: drivers/net/phy/mdio_bus.c + :export: + +.. kernel-doc:: drivers/net/phy/mdio_bus.c + :internal: diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 96f50694a74837..196ba17cc344f6 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -193,6 +193,24 @@ SOF_TIMESTAMPING_OPT_STATS: the transmit timestamps, such as how long a certain block of data was limited by peer's receiver window. +SOF_TIMESTAMPING_OPT_PKTINFO: + + Enable the SCM_TIMESTAMPING_PKTINFO control message for incoming + packets with hardware timestamps. The message contains struct + scm_ts_pktinfo, which supplies the index of the real interface which + received the packet and its length at layer 2. A valid (non-zero) + interface index will be returned only if CONFIG_NET_RX_BUSY_POLL is + enabled and the driver is using NAPI. The struct contains also two + other fields, but they are reserved and undefined. + +SOF_TIMESTAMPING_OPT_TX_SWHW: + + Request both hardware and software timestamps for outgoing packets + when SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE + are enabled at the same time. If both timestamps are generated, + two separate messages will be looped to the socket's error queue, + each containing just one timestamp. + New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate regardless of the setting of sysctl net.core.tstamp_allow_data. @@ -312,7 +330,7 @@ struct scm_timestamping { }; The structure can return up to three timestamps. This is a legacy -feature. Only one field is non-zero at any time. Most timestamps +feature. At least one field is non-zero at any time. Most timestamps are passed in ts[0]. Hardware timestamps are passed in ts[2]. ts[1] used to hold hardware timestamps converted to system time. @@ -321,6 +339,12 @@ a HW PTP clock source, to allow time conversion in userspace and optionally synchronize system time with a userspace PTP stack such as linuxptp. For the PTP clock API, see Documentation/ptp/ptp.txt. +Note that if the SO_TIMESTAMP or SO_TIMESTAMPNS option is enabled +together with SO_TIMESTAMPING using SOF_TIMESTAMPING_SOFTWARE, a false +software timestamp will be generated in the recvmsg() call and passed +in ts[0] when a real software timestamp is missing. This happens also +on hardware transmit timestamps. + 2.1.1 Transmit timestamps with MSG_ERRQUEUE For transmit timestamps the outgoing packet is looped back to the diff --git a/Documentation/networking/z8530book.rst b/Documentation/networking/z8530book.rst new file mode 100644 index 00000000000000..fea2c40e797302 --- /dev/null +++ b/Documentation/networking/z8530book.rst @@ -0,0 +1,256 @@ +======================= +Z8530 Programming Guide +======================= + +:Author: Alan Cox + +Introduction +============ + +The Z85x30 family synchronous/asynchronous controller chips are used on +a large number of cheap network interface cards. The kernel provides a +core interface layer that is designed to make it easy to provide WAN +services using this chip. + +The current driver only support synchronous operation. Merging the +asynchronous driver support into this code to allow any Z85x30 device to +be used as both a tty interface and as a synchronous controller is a +project for Linux post the 2.4 release + +Driver Modes +============ + +The Z85230 driver layer can drive Z8530, Z85C30 and Z85230 devices in +three different modes. Each mode can be applied to an individual channel +on the chip (each chip has two channels). + +The PIO synchronous mode supports the most common Z8530 wiring. Here the +chip is interface to the I/O and interrupt facilities of the host +machine but not to the DMA subsystem. When running PIO the Z8530 has +extremely tight timing requirements. Doing high speeds, even with a +Z85230 will be tricky. Typically you should expect to achieve at best +9600 baud with a Z8C530 and 64Kbits with a Z85230. + +The DMA mode supports the chip when it is configured to use dual DMA +channels on an ISA bus. The better cards tend to support this mode of +operation for a single channel. With DMA running the Z85230 tops out +when it starts to hit ISA DMA constraints at about 512Kbits. It is worth +noting here that many PC machines hang or crash when the chip is driven +fast enough to hold the ISA bus solid. + +Transmit DMA mode uses a single DMA channel. The DMA channel is used for +transmission as the transmit FIFO is smaller than the receive FIFO. it +gives better performance than pure PIO mode but is nowhere near as ideal +as pure DMA mode. + +Using the Z85230 driver +======================= + +The Z85230 driver provides the back end interface to your board. To +configure a Z8530 interface you need to detect the board and to identify +its ports and interrupt resources. It is also your problem to verify the +resources are available. + +Having identified the chip you need to fill in a struct z8530_dev, +which describes each chip. This object must exist until you finally +shutdown the board. Firstly zero the active field. This ensures nothing +goes off without you intending it. The irq field should be set to the +interrupt number of the chip. (Each chip has a single interrupt source +rather than each channel). You are responsible for allocating the +interrupt line. The interrupt handler should be set to +:c:func:`z8530_interrupt()`. The device id should be set to the +z8530_dev structure pointer. Whether the interrupt can be shared or not +is board dependent, and up to you to initialise. + +The structure holds two channel structures. Initialise chanA.ctrlio and +chanA.dataio with the address of the control and data ports. You can or +this with Z8530_PORT_SLEEP to indicate your interface needs the 5uS +delay for chip settling done in software. The PORT_SLEEP option is +architecture specific. Other flags may become available on future +platforms, eg for MMIO. Initialise the chanA.irqs to &z8530_nop to +start the chip up as disabled and discarding interrupt events. This +ensures that stray interrupts will be mopped up and not hang the bus. +Set chanA.dev to point to the device structure itself. The private and +name field you may use as you wish. The private field is unused by the +Z85230 layer. The name is used for error reporting and it may thus make +sense to make it match the network name. + +Repeat the same operation with the B channel if your chip has both +channels wired to something useful. This isn't always the case. If it is +not wired then the I/O values do not matter, but you must initialise +chanB.dev. + +If your board has DMA facilities then initialise the txdma and rxdma +fields for the relevant channels. You must also allocate the ISA DMA +channels and do any necessary board level initialisation to configure +them. The low level driver will do the Z8530 and DMA controller +programming but not board specific magic. + +Having initialised the device you can then call +:c:func:`z8530_init()`. This will probe the chip and reset it into +a known state. An identification sequence is then run to identify the +chip type. If the checks fail to pass the function returns a non zero +error code. Typically this indicates that the port given is not valid. +After this call the type field of the z8530_dev structure is +initialised to either Z8530, Z85C30 or Z85230 according to the chip +found. + +Once you have called z8530_init you can also make use of the utility +function :c:func:`z8530_describe()`. This provides a consistent +reporting format for the Z8530 devices, and allows all the drivers to +provide consistent reporting. + +Attaching Network Interfaces +============================ + +If you wish to use the network interface facilities of the driver, then +you need to attach a network device to each channel that is present and +in use. In addition to use the generic HDLC you need to follow some +additional plumbing rules. They may seem complex but a look at the +example hostess_sv11 driver should reassure you. + +The network device used for each channel should be pointed to by the +netdevice field of each channel. The hdlc-> priv field of the network +device points to your private data - you will need to be able to find +your private data from this. + +The way most drivers approach this particular problem is to create a +structure holding the Z8530 device definition and put that into the +private field of the network device. The network device fields of the +channels then point back to the network devices. + +If you wish to use the generic HDLC then you need to register the HDLC +device. + +Before you register your network device you will also need to provide +suitable handlers for most of the network device callbacks. See the +network device documentation for more details on this. + +Configuring And Activating The Port +=================================== + +The Z85230 driver provides helper functions and tables to load the port +registers on the Z8530 chips. When programming the register settings for +a channel be aware that the documentation recommends initialisation +orders. Strange things happen when these are not followed. + +:c:func:`z8530_channel_load()` takes an array of pairs of +initialisation values in an array of u8 type. The first value is the +Z8530 register number. Add 16 to indicate the alternate register bank on +the later chips. The array is terminated by a 255. + +The driver provides a pair of public tables. The z8530_hdlc_kilostream +table is for the UK 'Kilostream' service and also happens to cover most +other end host configurations. The z8530_hdlc_kilostream_85230 table +is the same configuration using the enhancements of the 85230 chip. The +configuration loaded is standard NRZ encoded synchronous data with HDLC +bitstuffing. All of the timing is taken from the other end of the link. + +When writing your own tables be aware that the driver internally tracks +register values. It may need to reload values. You should therefore be +sure to set registers 1-7, 9-11, 14 and 15 in all configurations. Where +the register settings depend on DMA selection the driver will update the +bits itself when you open or close. Loading a new table with the +interface open is not recommended. + +There are three standard configurations supported by the core code. In +PIO mode the interface is programmed up to use interrupt driven PIO. +This places high demands on the host processor to avoid latency. The +driver is written to take account of latency issues but it cannot avoid +latencies caused by other drivers, notably IDE in PIO mode. Because the +drivers allocate buffers you must also prevent MTU changes while the +port is open. + +Once the port is open it will call the rx_function of each channel +whenever a completed packet arrived. This is invoked from interrupt +context and passes you the channel and a network buffer (struct +sk_buff) holding the data. The data includes the CRC bytes so most +users will want to trim the last two bytes before processing the data. +This function is very timing critical. When you wish to simply discard +data the support code provides the function +:c:func:`z8530_null_rx()` to discard the data. + +To active PIO mode sending and receiving the ``z8530_sync_open`` is called. +This expects to be passed the network device and the channel. Typically +this is called from your network device open callback. On a failure a +non zero error status is returned. +The :c:func:`z8530_sync_close()` function shuts down a PIO +channel. This must be done before the channel is opened again and before +the driver shuts down and unloads. + +The ideal mode of operation is dual channel DMA mode. Here the kernel +driver will configure the board for DMA in both directions. The driver +also handles ISA DMA issues such as controller programming and the +memory range limit for you. This mode is activated by calling the +:c:func:`z8530_sync_dma_open()` function. On failure a non zero +error value is returned. Once this mode is activated it can be shut down +by calling the :c:func:`z8530_sync_dma_close()`. You must call +the close function matching the open mode you used. + +The final supported mode uses a single DMA channel to drive the transmit +side. As the Z85C30 has a larger FIFO on the receive channel this tends +to increase the maximum speed a little. This is activated by calling the +``z8530_sync_txdma_open``. This returns a non zero error code on failure. The +:c:func:`z8530_sync_txdma_close()` function closes down the Z8530 +interface from this mode. + +Network Layer Functions +======================= + +The Z8530 layer provides functions to queue packets for transmission. +The driver internally buffers the frame currently being transmitted and +one further frame (in order to keep back to back transmission running). +Any further buffering is up to the caller. + +The function :c:func:`z8530_queue_xmit()` takes a network buffer +in sk_buff format and queues it for transmission. The caller must +provide the entire packet with the exception of the bitstuffing and CRC. +This is normally done by the caller via the generic HDLC interface +layer. It returns 0 if the buffer has been queued and non zero values +for queue full. If the function accepts the buffer it becomes property +of the Z8530 layer and the caller should not free it. + +The function :c:func:`z8530_get_stats()` returns a pointer to an +internally maintained per interface statistics block. This provides most +of the interface code needed to implement the network layer get_stats +callback. + +Porting The Z8530 Driver +======================== + +The Z8530 driver is written to be portable. In DMA mode it makes +assumptions about the use of ISA DMA. These are probably warranted in +most cases as the Z85230 in particular was designed to glue to PC type +machines. The PIO mode makes no real assumptions. + +Should you need to retarget the Z8530 driver to another architecture the +only code that should need changing are the port I/O functions. At the +moment these assume PC I/O port accesses. This may not be appropriate +for all platforms. Replacing :c:func:`z8530_read_port()` and +``z8530_write_port`` is intended to be all that is required to port +this driver layer. + +Known Bugs And Assumptions +========================== + +Interrupt Locking + The locking in the driver is done via the global cli/sti lock. This + makes for relatively poor SMP performance. Switching this to use a + per device spin lock would probably materially improve performance. + +Occasional Failures + We have reports of occasional failures when run for very long + periods of time and the driver starts to receive junk frames. At the + moment the cause of this is not clear. + +Public Functions Provided +========================= + +.. kernel-doc:: drivers/net/wan/z85230.c + :export: + +Internal Functions +================== + +.. kernel-doc:: drivers/net/wan/z85230.c + :internal: diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt index f2af35f6d6b2bc..48f15b4f9d3e44 100644 --- a/Documentation/pinctrl.txt +++ b/Documentation/pinctrl.txt @@ -1,4 +1,7 @@ +=============================== PINCTRL (PIN CONTROL) subsystem +=============================== + This document outlines the pin control subsystem in Linux This subsystem deals with: @@ -33,7 +36,7 @@ When a PIN CONTROLLER is instantiated, it will register a descriptor to the pin control framework, and this descriptor contains an array of pin descriptors describing the pins handled by this specific pin controller. -Here is an example of a PGA (Pin Grid Array) chip seen from underneath: +Here is an example of a PGA (Pin Grid Array) chip seen from underneath:: A B C D E F G H @@ -54,39 +57,40 @@ Here is an example of a PGA (Pin Grid Array) chip seen from underneath: 1 o o o o o o o o To register a pin controller and name all the pins on this package we can do -this in our driver: - -#include - -const struct pinctrl_pin_desc foo_pins[] = { - PINCTRL_PIN(0, "A8"), - PINCTRL_PIN(1, "B8"), - PINCTRL_PIN(2, "C8"), - ... - PINCTRL_PIN(61, "F1"), - PINCTRL_PIN(62, "G1"), - PINCTRL_PIN(63, "H1"), -}; +this in our driver:: -static struct pinctrl_desc foo_desc = { - .name = "foo", - .pins = foo_pins, - .npins = ARRAY_SIZE(foo_pins), - .owner = THIS_MODULE, -}; + #include -int __init foo_probe(void) -{ - int error; + const struct pinctrl_pin_desc foo_pins[] = { + PINCTRL_PIN(0, "A8"), + PINCTRL_PIN(1, "B8"), + PINCTRL_PIN(2, "C8"), + ... + PINCTRL_PIN(61, "F1"), + PINCTRL_PIN(62, "G1"), + PINCTRL_PIN(63, "H1"), + }; + + static struct pinctrl_desc foo_desc = { + .name = "foo", + .pins = foo_pins, + .npins = ARRAY_SIZE(foo_pins), + .owner = THIS_MODULE, + }; + + int __init foo_probe(void) + { + int error; - struct pinctrl_dev *pctl; + struct pinctrl_dev *pctl; - error = pinctrl_register_and_init(&foo_desc, , NULL, &pctl); - if (error) - return error; + error = pinctrl_register_and_init(&foo_desc, , + NULL, &pctl); + if (error) + return error; - return pinctrl_enable(pctl); -} + return pinctrl_enable(pctl); + } To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and selected drivers, you need to select them from your machine's Kconfig entry, @@ -105,7 +109,7 @@ the pin controller. For a padring with 467 pads, as opposed to actual pins, I used an enumeration like this, walking around the edge of the chip, which seems to be industry -standard too (all these pads had names, too): +standard too (all these pads had names, too):: 0 ..... 104 @@ -128,64 +132,64 @@ on { 0, 8, 16, 24 }, and a group of pins dealing with an I2C interface on pins on { 24, 25 }. These two groups are presented to the pin control subsystem by implementing -some generic pinctrl_ops like this: - -#include - -struct foo_group { - const char *name; - const unsigned int *pins; - const unsigned num_pins; -}; - -static const unsigned int spi0_pins[] = { 0, 8, 16, 24 }; -static const unsigned int i2c0_pins[] = { 24, 25 }; - -static const struct foo_group foo_groups[] = { - { - .name = "spi0_grp", - .pins = spi0_pins, - .num_pins = ARRAY_SIZE(spi0_pins), - }, +some generic pinctrl_ops like this:: + + #include + + struct foo_group { + const char *name; + const unsigned int *pins; + const unsigned num_pins; + }; + + static const unsigned int spi0_pins[] = { 0, 8, 16, 24 }; + static const unsigned int i2c0_pins[] = { 24, 25 }; + + static const struct foo_group foo_groups[] = { + { + .name = "spi0_grp", + .pins = spi0_pins, + .num_pins = ARRAY_SIZE(spi0_pins), + }, + { + .name = "i2c0_grp", + .pins = i2c0_pins, + .num_pins = ARRAY_SIZE(i2c0_pins), + }, + }; + + + static int foo_get_groups_count(struct pinctrl_dev *pctldev) { - .name = "i2c0_grp", - .pins = i2c0_pins, - .num_pins = ARRAY_SIZE(i2c0_pins), - }, -}; - - -static int foo_get_groups_count(struct pinctrl_dev *pctldev) -{ - return ARRAY_SIZE(foo_groups); -} + return ARRAY_SIZE(foo_groups); + } -static const char *foo_get_group_name(struct pinctrl_dev *pctldev, - unsigned selector) -{ - return foo_groups[selector].name; -} + static const char *foo_get_group_name(struct pinctrl_dev *pctldev, + unsigned selector) + { + return foo_groups[selector].name; + } -static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector, - const unsigned **pins, - unsigned *num_pins) -{ - *pins = (unsigned *) foo_groups[selector].pins; - *num_pins = foo_groups[selector].num_pins; - return 0; -} + static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector, + const unsigned **pins, + unsigned *num_pins) + { + *pins = (unsigned *) foo_groups[selector].pins; + *num_pins = foo_groups[selector].num_pins; + return 0; + } -static struct pinctrl_ops foo_pctrl_ops = { - .get_groups_count = foo_get_groups_count, - .get_group_name = foo_get_group_name, - .get_group_pins = foo_get_group_pins, -}; + static struct pinctrl_ops foo_pctrl_ops = { + .get_groups_count = foo_get_groups_count, + .get_group_name = foo_get_group_name, + .get_group_pins = foo_get_group_pins, + }; -static struct pinctrl_desc foo_desc = { - ... - .pctlops = &foo_pctrl_ops, -}; + static struct pinctrl_desc foo_desc = { + ... + .pctlops = &foo_pctrl_ops, + }; The pin control subsystem will call the .get_groups_count() function to determine the total number of legal selectors, then it will call the other functions @@ -213,62 +217,62 @@ The format and meaning of the configuration parameter, PLATFORM_X_PULL_UP above, is entirely defined by the pin controller driver. The pin configuration driver implements callbacks for changing pin -configuration in the pin controller ops like this: +configuration in the pin controller ops like this:: -#include -#include -#include "platform_x_pindefs.h" + #include + #include + #include "platform_x_pindefs.h" -static int foo_pin_config_get(struct pinctrl_dev *pctldev, - unsigned offset, - unsigned long *config) -{ - struct my_conftype conf; + static int foo_pin_config_get(struct pinctrl_dev *pctldev, + unsigned offset, + unsigned long *config) + { + struct my_conftype conf; - ... Find setting for pin @ offset ... + ... Find setting for pin @ offset ... - *config = (unsigned long) conf; -} + *config = (unsigned long) conf; + } -static int foo_pin_config_set(struct pinctrl_dev *pctldev, - unsigned offset, - unsigned long config) -{ - struct my_conftype *conf = (struct my_conftype *) config; + static int foo_pin_config_set(struct pinctrl_dev *pctldev, + unsigned offset, + unsigned long config) + { + struct my_conftype *conf = (struct my_conftype *) config; - switch (conf) { - case PLATFORM_X_PULL_UP: - ... + switch (conf) { + case PLATFORM_X_PULL_UP: + ... + } } } -} -static int foo_pin_config_group_get (struct pinctrl_dev *pctldev, - unsigned selector, - unsigned long *config) -{ - ... -} + static int foo_pin_config_group_get (struct pinctrl_dev *pctldev, + unsigned selector, + unsigned long *config) + { + ... + } -static int foo_pin_config_group_set (struct pinctrl_dev *pctldev, - unsigned selector, - unsigned long config) -{ - ... -} + static int foo_pin_config_group_set (struct pinctrl_dev *pctldev, + unsigned selector, + unsigned long config) + { + ... + } -static struct pinconf_ops foo_pconf_ops = { - .pin_config_get = foo_pin_config_get, - .pin_config_set = foo_pin_config_set, - .pin_config_group_get = foo_pin_config_group_get, - .pin_config_group_set = foo_pin_config_group_set, -}; + static struct pinconf_ops foo_pconf_ops = { + .pin_config_get = foo_pin_config_get, + .pin_config_set = foo_pin_config_set, + .pin_config_group_get = foo_pin_config_group_get, + .pin_config_group_set = foo_pin_config_group_set, + }; -/* Pin config operations are handled by some pin controller */ -static struct pinctrl_desc foo_desc = { - ... - .confops = &foo_pconf_ops, -}; + /* Pin config operations are handled by some pin controller */ + static struct pinctrl_desc foo_desc = { + ... + .confops = &foo_pconf_ops, + }; Since some controllers have special logic for handling entire groups of pins they can exploit the special whole-group pin control function. The @@ -296,35 +300,35 @@ controller handles control of a certain GPIO pin. Since a single pin controller may be muxing several GPIO ranges (typically SoCs that have one set of pins, but internally several GPIO silicon blocks, each modelled as a struct gpio_chip) any number of GPIO ranges can be added to a pin controller instance -like this: - -struct gpio_chip chip_a; -struct gpio_chip chip_b; - -static struct pinctrl_gpio_range gpio_range_a = { - .name = "chip a", - .id = 0, - .base = 32, - .pin_base = 32, - .npins = 16, - .gc = &chip_a; -}; - -static struct pinctrl_gpio_range gpio_range_b = { - .name = "chip b", - .id = 0, - .base = 48, - .pin_base = 64, - .npins = 8, - .gc = &chip_b; -}; - -{ - struct pinctrl_dev *pctl; - ... - pinctrl_add_gpio_range(pctl, &gpio_range_a); - pinctrl_add_gpio_range(pctl, &gpio_range_b); -} +like this:: + + struct gpio_chip chip_a; + struct gpio_chip chip_b; + + static struct pinctrl_gpio_range gpio_range_a = { + .name = "chip a", + .id = 0, + .base = 32, + .pin_base = 32, + .npins = 16, + .gc = &chip_a; + }; + + static struct pinctrl_gpio_range gpio_range_b = { + .name = "chip b", + .id = 0, + .base = 48, + .pin_base = 64, + .npins = 8, + .gc = &chip_b; + }; + + { + struct pinctrl_dev *pctl; + ... + pinctrl_add_gpio_range(pctl, &gpio_range_a); + pinctrl_add_gpio_range(pctl, &gpio_range_b); + } So this complex system has one pin controller handling two different GPIO chips. "chip a" has 16 pins and "chip b" has 8 pins. The "chip a" and @@ -348,25 +352,26 @@ chip b: The above examples assume the mapping between the GPIOs and pins is linear. If the mapping is sparse or haphazard, an array of arbitrary pin -numbers can be encoded in the range like this: +numbers can be encoded in the range like this:: -static const unsigned range_pins[] = { 14, 1, 22, 17, 10, 8, 6, 2 }; + static const unsigned range_pins[] = { 14, 1, 22, 17, 10, 8, 6, 2 }; -static struct pinctrl_gpio_range gpio_range = { - .name = "chip", - .id = 0, - .base = 32, - .pins = &range_pins, - .npins = ARRAY_SIZE(range_pins), - .gc = &chip; -}; + static struct pinctrl_gpio_range gpio_range = { + .name = "chip", + .id = 0, + .base = 32, + .pins = &range_pins, + .npins = ARRAY_SIZE(range_pins), + .gc = &chip; + }; In this case the pin_base property will be ignored. If the name of a pin group is known, the pins and npins elements of the above structure can be initialised using the function pinctrl_get_group_pins(), e.g. for pin -group "foo": +group "foo":: -pinctrl_get_group_pins(pctl, "foo", &gpio_range.pins, &gpio_range.npins); + pinctrl_get_group_pins(pctl, "foo", &gpio_range.pins, + &gpio_range.npins); When GPIO-specific functions in the pin control subsystem are called, these ranges will be used to look up the appropriate pin controller by inspecting @@ -405,7 +410,7 @@ we usually mean a way of soldering or wiring the package into an electronic system, even though the framework makes it possible to also change the function at runtime. -Here is an example of a PGA (Pin Grid Array) chip seen from underneath: +Here is an example of a PGA (Pin Grid Array) chip seen from underneath:: A B C D E F G H +---+ @@ -519,12 +524,12 @@ Definitions: In the example case we can define that this particular machine shall use device spi0 with pinmux function fspi0 group gspi0 and i2c0 on function fi2c0 group gi2c0, on the primary pin controller, we get mappings - like these: + like these:: - { - {"map-spi0", spi0, pinctrl0, fspi0, gspi0}, - {"map-i2c0", i2c0, pinctrl0, fi2c0, gi2c0} - } + { + {"map-spi0", spi0, pinctrl0, fspi0, gspi0}, + {"map-i2c0", i2c0, pinctrl0, fi2c0, gi2c0} + } Every map must be assigned a state name, pin controller, device and function. The group is not compulsory - if it is omitted the first group @@ -578,155 +583,155 @@ some certain registers to activate a certain mux setting for a certain pin. A simple driver for the above example will work by setting bits 0, 1, 2, 3 or 4 into some register named MUX to select a certain function with a certain -group of pins would work something like this: - -#include -#include - -struct foo_group { - const char *name; - const unsigned int *pins; - const unsigned num_pins; -}; - -static const unsigned spi0_0_pins[] = { 0, 8, 16, 24 }; -static const unsigned spi0_1_pins[] = { 38, 46, 54, 62 }; -static const unsigned i2c0_pins[] = { 24, 25 }; -static const unsigned mmc0_1_pins[] = { 56, 57 }; -static const unsigned mmc0_2_pins[] = { 58, 59 }; -static const unsigned mmc0_3_pins[] = { 60, 61, 62, 63 }; - -static const struct foo_group foo_groups[] = { - { - .name = "spi0_0_grp", - .pins = spi0_0_pins, - .num_pins = ARRAY_SIZE(spi0_0_pins), - }, +group of pins would work something like this:: + + #include + #include + + struct foo_group { + const char *name; + const unsigned int *pins; + const unsigned num_pins; + }; + + static const unsigned spi0_0_pins[] = { 0, 8, 16, 24 }; + static const unsigned spi0_1_pins[] = { 38, 46, 54, 62 }; + static const unsigned i2c0_pins[] = { 24, 25 }; + static const unsigned mmc0_1_pins[] = { 56, 57 }; + static const unsigned mmc0_2_pins[] = { 58, 59 }; + static const unsigned mmc0_3_pins[] = { 60, 61, 62, 63 }; + + static const struct foo_group foo_groups[] = { + { + .name = "spi0_0_grp", + .pins = spi0_0_pins, + .num_pins = ARRAY_SIZE(spi0_0_pins), + }, + { + .name = "spi0_1_grp", + .pins = spi0_1_pins, + .num_pins = ARRAY_SIZE(spi0_1_pins), + }, + { + .name = "i2c0_grp", + .pins = i2c0_pins, + .num_pins = ARRAY_SIZE(i2c0_pins), + }, + { + .name = "mmc0_1_grp", + .pins = mmc0_1_pins, + .num_pins = ARRAY_SIZE(mmc0_1_pins), + }, + { + .name = "mmc0_2_grp", + .pins = mmc0_2_pins, + .num_pins = ARRAY_SIZE(mmc0_2_pins), + }, + { + .name = "mmc0_3_grp", + .pins = mmc0_3_pins, + .num_pins = ARRAY_SIZE(mmc0_3_pins), + }, + }; + + + static int foo_get_groups_count(struct pinctrl_dev *pctldev) { - .name = "spi0_1_grp", - .pins = spi0_1_pins, - .num_pins = ARRAY_SIZE(spi0_1_pins), - }, - { - .name = "i2c0_grp", - .pins = i2c0_pins, - .num_pins = ARRAY_SIZE(i2c0_pins), - }, + return ARRAY_SIZE(foo_groups); + } + + static const char *foo_get_group_name(struct pinctrl_dev *pctldev, + unsigned selector) { - .name = "mmc0_1_grp", - .pins = mmc0_1_pins, - .num_pins = ARRAY_SIZE(mmc0_1_pins), - }, + return foo_groups[selector].name; + } + + static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector, + unsigned ** const pins, + unsigned * const num_pins) { - .name = "mmc0_2_grp", - .pins = mmc0_2_pins, - .num_pins = ARRAY_SIZE(mmc0_2_pins), - }, + *pins = (unsigned *) foo_groups[selector].pins; + *num_pins = foo_groups[selector].num_pins; + return 0; + } + + static struct pinctrl_ops foo_pctrl_ops = { + .get_groups_count = foo_get_groups_count, + .get_group_name = foo_get_group_name, + .get_group_pins = foo_get_group_pins, + }; + + struct foo_pmx_func { + const char *name; + const char * const *groups; + const unsigned num_groups; + }; + + static const char * const spi0_groups[] = { "spi0_0_grp", "spi0_1_grp" }; + static const char * const i2c0_groups[] = { "i2c0_grp" }; + static const char * const mmc0_groups[] = { "mmc0_1_grp", "mmc0_2_grp", + "mmc0_3_grp" }; + + static const struct foo_pmx_func foo_functions[] = { + { + .name = "spi0", + .groups = spi0_groups, + .num_groups = ARRAY_SIZE(spi0_groups), + }, + { + .name = "i2c0", + .groups = i2c0_groups, + .num_groups = ARRAY_SIZE(i2c0_groups), + }, + { + .name = "mmc0", + .groups = mmc0_groups, + .num_groups = ARRAY_SIZE(mmc0_groups), + }, + }; + + static int foo_get_functions_count(struct pinctrl_dev *pctldev) { - .name = "mmc0_3_grp", - .pins = mmc0_3_pins, - .num_pins = ARRAY_SIZE(mmc0_3_pins), - }, -}; - - -static int foo_get_groups_count(struct pinctrl_dev *pctldev) -{ - return ARRAY_SIZE(foo_groups); -} - -static const char *foo_get_group_name(struct pinctrl_dev *pctldev, - unsigned selector) -{ - return foo_groups[selector].name; -} - -static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector, - unsigned ** const pins, - unsigned * const num_pins) -{ - *pins = (unsigned *) foo_groups[selector].pins; - *num_pins = foo_groups[selector].num_pins; - return 0; -} - -static struct pinctrl_ops foo_pctrl_ops = { - .get_groups_count = foo_get_groups_count, - .get_group_name = foo_get_group_name, - .get_group_pins = foo_get_group_pins, -}; - -struct foo_pmx_func { - const char *name; - const char * const *groups; - const unsigned num_groups; -}; - -static const char * const spi0_groups[] = { "spi0_0_grp", "spi0_1_grp" }; -static const char * const i2c0_groups[] = { "i2c0_grp" }; -static const char * const mmc0_groups[] = { "mmc0_1_grp", "mmc0_2_grp", - "mmc0_3_grp" }; - -static const struct foo_pmx_func foo_functions[] = { + return ARRAY_SIZE(foo_functions); + } + + static const char *foo_get_fname(struct pinctrl_dev *pctldev, unsigned selector) { - .name = "spi0", - .groups = spi0_groups, - .num_groups = ARRAY_SIZE(spi0_groups), - }, + return foo_functions[selector].name; + } + + static int foo_get_groups(struct pinctrl_dev *pctldev, unsigned selector, + const char * const **groups, + unsigned * const num_groups) { - .name = "i2c0", - .groups = i2c0_groups, - .num_groups = ARRAY_SIZE(i2c0_groups), - }, + *groups = foo_functions[selector].groups; + *num_groups = foo_functions[selector].num_groups; + return 0; + } + + static int foo_set_mux(struct pinctrl_dev *pctldev, unsigned selector, + unsigned group) { - .name = "mmc0", - .groups = mmc0_groups, - .num_groups = ARRAY_SIZE(mmc0_groups), - }, -}; - -static int foo_get_functions_count(struct pinctrl_dev *pctldev) -{ - return ARRAY_SIZE(foo_functions); -} - -static const char *foo_get_fname(struct pinctrl_dev *pctldev, unsigned selector) -{ - return foo_functions[selector].name; -} - -static int foo_get_groups(struct pinctrl_dev *pctldev, unsigned selector, - const char * const **groups, - unsigned * const num_groups) -{ - *groups = foo_functions[selector].groups; - *num_groups = foo_functions[selector].num_groups; - return 0; -} - -static int foo_set_mux(struct pinctrl_dev *pctldev, unsigned selector, - unsigned group) -{ - u8 regbit = (1 << selector + group); - - writeb((readb(MUX)|regbit), MUX) - return 0; -} - -static struct pinmux_ops foo_pmxops = { - .get_functions_count = foo_get_functions_count, - .get_function_name = foo_get_fname, - .get_function_groups = foo_get_groups, - .set_mux = foo_set_mux, - .strict = true, -}; - -/* Pinmux operations are handled by some pin controller */ -static struct pinctrl_desc foo_desc = { - ... - .pctlops = &foo_pctrl_ops, - .pmxops = &foo_pmxops, -}; + u8 regbit = (1 << selector + group); + + writeb((readb(MUX)|regbit), MUX) + return 0; + } + + static struct pinmux_ops foo_pmxops = { + .get_functions_count = foo_get_functions_count, + .get_function_name = foo_get_fname, + .get_function_groups = foo_get_groups, + .set_mux = foo_set_mux, + .strict = true, + }; + + /* Pinmux operations are handled by some pin controller */ + static struct pinctrl_desc foo_desc = { + ... + .pctlops = &foo_pctrl_ops, + .pmxops = &foo_pmxops, + }; In the example activating muxing 0 and 1 at the same time setting bits 0 and 1, uses one pin in common so they would collide. @@ -809,9 +814,9 @@ for a device. The GPIO portions of a pin and its relation to a certain pin controller configuration and muxing logic can be constructed in several ways. Here -are two examples: +are two examples:: -(A) + (A) pin config logic regs | +- SPI @@ -840,7 +845,9 @@ simultaneous access to the same pin from GPIO and pin multiplexing consumers on hardware of this type. The pinctrl driver should set this flag accordingly. -(B) +:: + + (B) pin config logic regs @@ -911,52 +918,55 @@ has to be handled by the interface. Instead view this as a certain pin config setting. Look in e.g. and you find this in the documentation: - PIN_CONFIG_OUTPUT: this will configure the pin in output, use argument + PIN_CONFIG_OUTPUT: + this will configure the pin in output, use argument 1 to indicate high level, argument 0 to indicate low level. So it is perfectly possible to push a pin into "GPIO mode" and drive the line low as part of the usual pin control map. So for example your UART -driver may look like this: +driver may look like this:: -#include + #include -struct pinctrl *pinctrl; -struct pinctrl_state *pins_default; -struct pinctrl_state *pins_sleep; + struct pinctrl *pinctrl; + struct pinctrl_state *pins_default; + struct pinctrl_state *pins_sleep; -pins_default = pinctrl_lookup_state(uap->pinctrl, PINCTRL_STATE_DEFAULT); -pins_sleep = pinctrl_lookup_state(uap->pinctrl, PINCTRL_STATE_SLEEP); + pins_default = pinctrl_lookup_state(uap->pinctrl, PINCTRL_STATE_DEFAULT); + pins_sleep = pinctrl_lookup_state(uap->pinctrl, PINCTRL_STATE_SLEEP); -/* Normal mode */ -retval = pinctrl_select_state(pinctrl, pins_default); -/* Sleep mode */ -retval = pinctrl_select_state(pinctrl, pins_sleep); + /* Normal mode */ + retval = pinctrl_select_state(pinctrl, pins_default); + /* Sleep mode */ + retval = pinctrl_select_state(pinctrl, pins_sleep); And your machine configuration may look like this: -------------------------------------------------- -static unsigned long uart_default_mode[] = { - PIN_CONF_PACKED(PIN_CONFIG_DRIVE_PUSH_PULL, 0), -}; - -static unsigned long uart_sleep_mode[] = { - PIN_CONF_PACKED(PIN_CONFIG_OUTPUT, 0), -}; - -static struct pinctrl_map pinmap[] __initdata = { - PIN_MAP_MUX_GROUP("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo", - "u0_group", "u0"), - PIN_MAP_CONFIGS_PIN("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo", - "UART_TX_PIN", uart_default_mode), - PIN_MAP_MUX_GROUP("uart", PINCTRL_STATE_SLEEP, "pinctrl-foo", - "u0_group", "gpio-mode"), - PIN_MAP_CONFIGS_PIN("uart", PINCTRL_STATE_SLEEP, "pinctrl-foo", - "UART_TX_PIN", uart_sleep_mode), -}; - -foo_init(void) { - pinctrl_register_mappings(pinmap, ARRAY_SIZE(pinmap)); -} +:: + + static unsigned long uart_default_mode[] = { + PIN_CONF_PACKED(PIN_CONFIG_DRIVE_PUSH_PULL, 0), + }; + + static unsigned long uart_sleep_mode[] = { + PIN_CONF_PACKED(PIN_CONFIG_OUTPUT, 0), + }; + + static struct pinctrl_map pinmap[] __initdata = { + PIN_MAP_MUX_GROUP("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo", + "u0_group", "u0"), + PIN_MAP_CONFIGS_PIN("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo", + "UART_TX_PIN", uart_default_mode), + PIN_MAP_MUX_GROUP("uart", PINCTRL_STATE_SLEEP, "pinctrl-foo", + "u0_group", "gpio-mode"), + PIN_MAP_CONFIGS_PIN("uart", PINCTRL_STATE_SLEEP, "pinctrl-foo", + "UART_TX_PIN", uart_sleep_mode), + }; + + foo_init(void) { + pinctrl_register_mappings(pinmap, ARRAY_SIZE(pinmap)); + } Here the pins we want to control are in the "u0_group" and there is some function called "u0" that can be enabled on this group of pins, and then @@ -985,7 +995,7 @@ API. Board/machine configuration -================================== +=========================== Boards and machines define how a certain complete running system is put together, including how GPIOs and devices are muxed, how regulators are @@ -994,33 +1004,33 @@ part of this. A pin controller configuration for a machine looks pretty much like a simple regulator configuration, so for the example array above we want to enable i2c -and spi on the second function mapping: - -#include - -static const struct pinctrl_map mapping[] __initconst = { - { - .dev_name = "foo-spi.0", - .name = PINCTRL_STATE_DEFAULT, - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .data.mux.function = "spi0", - }, - { - .dev_name = "foo-i2c.0", - .name = PINCTRL_STATE_DEFAULT, - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .data.mux.function = "i2c0", - }, - { - .dev_name = "foo-mmc.0", - .name = PINCTRL_STATE_DEFAULT, - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .data.mux.function = "mmc0", - }, -}; +and spi on the second function mapping:: + + #include + + static const struct pinctrl_map mapping[] __initconst = { + { + .dev_name = "foo-spi.0", + .name = PINCTRL_STATE_DEFAULT, + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .data.mux.function = "spi0", + }, + { + .dev_name = "foo-i2c.0", + .name = PINCTRL_STATE_DEFAULT, + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .data.mux.function = "i2c0", + }, + { + .dev_name = "foo-mmc.0", + .name = PINCTRL_STATE_DEFAULT, + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .data.mux.function = "mmc0", + }, + }; The dev_name here matches to the unique device name that can be used to look up the device struct (just like with clockdev or regulators). The function name @@ -1029,76 +1039,81 @@ must match a function provided by the pinmux driver handling this pin range. As you can see we may have several pin controllers on the system and thus we need to specify which one of them contains the functions we wish to map. -You register this pinmux mapping to the pinmux subsystem by simply: +You register this pinmux mapping to the pinmux subsystem by simply:: ret = pinctrl_register_mappings(mapping, ARRAY_SIZE(mapping)); Since the above construct is pretty common there is a helper macro to make it even more compact which assumes you want to use pinctrl-foo and position -0 for mapping, for example: +0 for mapping, for example:: -static struct pinctrl_map mapping[] __initdata = { - PIN_MAP_MUX_GROUP("foo-i2c.o", PINCTRL_STATE_DEFAULT, "pinctrl-foo", NULL, "i2c0"), -}; + static struct pinctrl_map mapping[] __initdata = { + PIN_MAP_MUX_GROUP("foo-i2c.o", PINCTRL_STATE_DEFAULT, + "pinctrl-foo", NULL, "i2c0"), + }; The mapping table may also contain pin configuration entries. It's common for each pin/group to have a number of configuration entries that affect it, so the table entries for configuration reference an array of config parameters -and values. An example using the convenience macros is shown below: - -static unsigned long i2c_grp_configs[] = { - FOO_PIN_DRIVEN, - FOO_PIN_PULLUP, -}; - -static unsigned long i2c_pin_configs[] = { - FOO_OPEN_COLLECTOR, - FOO_SLEW_RATE_SLOW, -}; - -static struct pinctrl_map mapping[] __initdata = { - PIN_MAP_MUX_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", "i2c0"), - PIN_MAP_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs), - PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs), - PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0sda", i2c_pin_configs), -}; +and values. An example using the convenience macros is shown below:: + + static unsigned long i2c_grp_configs[] = { + FOO_PIN_DRIVEN, + FOO_PIN_PULLUP, + }; + + static unsigned long i2c_pin_configs[] = { + FOO_OPEN_COLLECTOR, + FOO_SLEW_RATE_SLOW, + }; + + static struct pinctrl_map mapping[] __initdata = { + PIN_MAP_MUX_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, + "pinctrl-foo", "i2c0", "i2c0"), + PIN_MAP_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, + "pinctrl-foo", "i2c0", i2c_grp_configs), + PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, + "pinctrl-foo", "i2c0scl", i2c_pin_configs), + PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, + "pinctrl-foo", "i2c0sda", i2c_pin_configs), + }; Finally, some devices expect the mapping table to contain certain specific named states. When running on hardware that doesn't need any pin controller configuration, the mapping table must still contain those named states, in order to explicitly indicate that the states were provided and intended to be empty. Table entry macro PIN_MAP_DUMMY_STATE serves the purpose of defining -a named state without causing any pin controller to be programmed: +a named state without causing any pin controller to be programmed:: -static struct pinctrl_map mapping[] __initdata = { - PIN_MAP_DUMMY_STATE("foo-i2c.0", PINCTRL_STATE_DEFAULT), -}; + static struct pinctrl_map mapping[] __initdata = { + PIN_MAP_DUMMY_STATE("foo-i2c.0", PINCTRL_STATE_DEFAULT), + }; Complex mappings ================ As it is possible to map a function to different groups of pins an optional -.group can be specified like this: - -... -{ - .dev_name = "foo-spi.0", - .name = "spi0-pos-A", - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "spi0", - .group = "spi0_0_grp", -}, -{ - .dev_name = "foo-spi.0", - .name = "spi0-pos-B", - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "spi0", - .group = "spi0_1_grp", -}, -... +.group can be specified like this:: + + ... + { + .dev_name = "foo-spi.0", + .name = "spi0-pos-A", + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "spi0", + .group = "spi0_0_grp", + }, + { + .dev_name = "foo-spi.0", + .name = "spi0-pos-B", + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "spi0", + .group = "spi0_1_grp", + }, + ... This example mapping is used to switch between two positions for spi0 at runtime, as described further below under the heading "Runtime pinmuxing". @@ -1107,67 +1122,67 @@ Further it is possible for one named state to affect the muxing of several groups of pins, say for example in the mmc0 example above, where you can additively expand the mmc0 bus from 2 to 4 to 8 pins. If we want to use all three groups for a total of 2+2+4 = 8 pins (for an 8-bit MMC bus as is the -case), we define a mapping like this: - -... -{ - .dev_name = "foo-mmc.0", - .name = "2bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_1_grp", -}, -{ - .dev_name = "foo-mmc.0", - .name = "4bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_1_grp", -}, -{ - .dev_name = "foo-mmc.0", - .name = "4bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_2_grp", -}, -{ - .dev_name = "foo-mmc.0", - .name = "8bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_1_grp", -}, -{ - .dev_name = "foo-mmc.0", - .name = "8bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_2_grp", -}, -{ - .dev_name = "foo-mmc.0", - .name = "8bit" - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "mmc0", - .group = "mmc0_3_grp", -}, -... +case), we define a mapping like this:: + + ... + { + .dev_name = "foo-mmc.0", + .name = "2bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_1_grp", + }, + { + .dev_name = "foo-mmc.0", + .name = "4bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_1_grp", + }, + { + .dev_name = "foo-mmc.0", + .name = "4bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_2_grp", + }, + { + .dev_name = "foo-mmc.0", + .name = "8bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_1_grp", + }, + { + .dev_name = "foo-mmc.0", + .name = "8bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_2_grp", + }, + { + .dev_name = "foo-mmc.0", + .name = "8bit" + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "mmc0", + .group = "mmc0_3_grp", + }, + ... The result of grabbing this mapping from the device with something like -this (see next paragraph): +this (see next paragraph):: p = devm_pinctrl_get(dev); s = pinctrl_lookup_state(p, "8bit"); ret = pinctrl_select_state(p, s); -or more simply: +or more simply:: p = devm_pinctrl_get_select(dev, "8bit"); @@ -1205,39 +1220,39 @@ PINCTRL_STATE_SLEEP at runtime, re-biasing or even re-muxing pins to save current in sleep mode. A driver may request a certain control state to be activated, usually just the -default state like this: +default state like this:: -#include + #include -struct foo_state { - struct pinctrl *p; - struct pinctrl_state *s; - ... -}; + struct foo_state { + struct pinctrl *p; + struct pinctrl_state *s; + ... + }; -foo_probe() -{ - /* Allocate a state holder named "foo" etc */ - struct foo_state *foo = ...; + foo_probe() + { + /* Allocate a state holder named "foo" etc */ + struct foo_state *foo = ...; - foo->p = devm_pinctrl_get(&device); - if (IS_ERR(foo->p)) { - /* FIXME: clean up "foo" here */ - return PTR_ERR(foo->p); - } + foo->p = devm_pinctrl_get(&device); + if (IS_ERR(foo->p)) { + /* FIXME: clean up "foo" here */ + return PTR_ERR(foo->p); + } - foo->s = pinctrl_lookup_state(foo->p, PINCTRL_STATE_DEFAULT); - if (IS_ERR(foo->s)) { - /* FIXME: clean up "foo" here */ - return PTR_ERR(s); - } + foo->s = pinctrl_lookup_state(foo->p, PINCTRL_STATE_DEFAULT); + if (IS_ERR(foo->s)) { + /* FIXME: clean up "foo" here */ + return PTR_ERR(s); + } - ret = pinctrl_select_state(foo->s); - if (ret < 0) { - /* FIXME: clean up "foo" here */ - return ret; + ret = pinctrl_select_state(foo->s); + if (ret < 0) { + /* FIXME: clean up "foo" here */ + return ret; + } } -} This get/lookup/select/put sequence can just as well be handled by bus drivers if you don't want each and every driver to handle it and you know the @@ -1299,16 +1314,16 @@ Drivers needing both pin control and GPIOs Again, it is discouraged to let drivers lookup and select pin control states themselves, but again sometimes this is unavoidable. -So say that your driver is fetching its resources like this: +So say that your driver is fetching its resources like this:: -#include -#include + #include + #include -struct pinctrl *pinctrl; -int gpio; + struct pinctrl *pinctrl; + int gpio; -pinctrl = devm_pinctrl_get_select_default(&dev); -gpio = devm_gpio_request(&dev, 14, "foo"); + pinctrl = devm_pinctrl_get_select_default(&dev); + gpio = devm_gpio_request(&dev, 14, "foo"); Here we first request a certain pin state and then request GPIO 14 to be used. If you're using the subsystems orthogonally like this, you should @@ -1347,21 +1362,22 @@ lookup_state() and select_state() on it immediately after the pin control device has been registered. This occurs for mapping table entries where the client device name is equal -to the pin controller device name, and the state name is PINCTRL_STATE_DEFAULT. +to the pin controller device name, and the state name is PINCTRL_STATE_DEFAULT:: -{ - .dev_name = "pinctrl-foo", - .name = PINCTRL_STATE_DEFAULT, - .type = PIN_MAP_TYPE_MUX_GROUP, - .ctrl_dev_name = "pinctrl-foo", - .function = "power_func", -}, + { + .dev_name = "pinctrl-foo", + .name = PINCTRL_STATE_DEFAULT, + .type = PIN_MAP_TYPE_MUX_GROUP, + .ctrl_dev_name = "pinctrl-foo", + .function = "power_func", + }, Since it may be common to request the core to hog a few always-applicable mux settings on the primary pin controller, there is a convenience macro for -this: +this:: -PIN_MAP_MUX_GROUP_HOG_DEFAULT("pinctrl-foo", NULL /* group */, "power_func") + PIN_MAP_MUX_GROUP_HOG_DEFAULT("pinctrl-foo", NULL /* group */, + "power_func") This gives the exact same result as the above construction. @@ -1378,45 +1394,45 @@ function, but with different named in the mapping as described under This snippet first initializes a state object for both groups (in foo_probe()), then muxes the function in the pins defined by group A, and finally muxes it in -on the pins defined by group B: +on the pins defined by group B:: -#include + #include -struct pinctrl *p; -struct pinctrl_state *s1, *s2; + struct pinctrl *p; + struct pinctrl_state *s1, *s2; -foo_probe() -{ - /* Setup */ - p = devm_pinctrl_get(&device); - if (IS_ERR(p)) - ... + foo_probe() + { + /* Setup */ + p = devm_pinctrl_get(&device); + if (IS_ERR(p)) + ... + + s1 = pinctrl_lookup_state(foo->p, "pos-A"); + if (IS_ERR(s1)) + ... + + s2 = pinctrl_lookup_state(foo->p, "pos-B"); + if (IS_ERR(s2)) + ... + } - s1 = pinctrl_lookup_state(foo->p, "pos-A"); - if (IS_ERR(s1)) + foo_switch() + { + /* Enable on position A */ + ret = pinctrl_select_state(s1); + if (ret < 0) ... - s2 = pinctrl_lookup_state(foo->p, "pos-B"); - if (IS_ERR(s2)) ... -} - -foo_switch() -{ - /* Enable on position A */ - ret = pinctrl_select_state(s1); - if (ret < 0) - ... - - ... - /* Enable on position B */ - ret = pinctrl_select_state(s2); - if (ret < 0) - ... + /* Enable on position B */ + ret = pinctrl_select_state(s2); + if (ret < 0) + ... - ... -} + ... + } The above has to be done from process context. The reservation of the pins will be done when the state is activated, so in effect one specific pin diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index e25d63f8c0da1e..3aed751e0cb599 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -116,12 +116,11 @@ DevFS has been obsoleted in favour of udev Linux documentation for functions is transitioning to inline documentation via specially-formatted comments near their -definitions in the source. These comments can be combined with the -SGML templates in the Documentation/DocBook directory to make DocBook -files, which can then be converted by DocBook stylesheets to PostScript, -HTML, PDF files, and several other formats. In order to convert from -DocBook format to a format of your choice, you'll need to install Jade as -well as the desired DocBook stylesheets. +definitions in the source. These comments can be combined with ReST +files the Documentation/ directory to make enriched documentation, which can +then be converted to PostScript, HTML, LaTex, ePUB and PDF files. +In order to convert from ReST format to a format of your choice, you'll need +Sphinx. Util-linux ---------- @@ -323,12 +322,6 @@ PDF outputs, it is recommended to use version 1.4.6. functionalities required for ``XeLaTex`` to work. For PDF output you'll also need ``convert(1)`` from ImageMagick (https://www.imagemagick.org). -Other tools ------------ - -In order to produce documentation from DocBook, you'll also need ``xmlto``. -Please notice, however, that we're currently migrating all documents to use -``Sphinx``. Getting updated software ======================== @@ -409,15 +402,6 @@ Quota-tools - -DocBook Stylesheets -------------------- - -- - -XMLTO XSLT Frontend -------------------- - -- Intel P6 microcode ------------------ diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst index 1260f60d4cb99f..c6875b1db56f3c 100644 --- a/Documentation/process/howto.rst +++ b/Documentation/process/howto.rst @@ -180,14 +180,6 @@ They can also be generated on LaTeX and ePub formats with:: make latexdocs make epubdocs -Currently, there are some documents written on DocBook that are in -the process of conversion to ReST. Such documents will be created in the -Documentation/DocBook/ directory and can be generated also as -Postscript or man pages by running:: - - make psdocs - make mandocs - Becoming A Kernel Developer --------------------------- diff --git a/Documentation/process/kernel-docs.rst b/Documentation/process/kernel-docs.rst index 05a7857a4a838b..b8cac85a40011c 100644 --- a/Documentation/process/kernel-docs.rst +++ b/Documentation/process/kernel-docs.rst @@ -40,50 +40,18 @@ Enjoy! Docs at the Linux Kernel tree ----------------------------- -The DocBook books should be built with ``make {htmldocs | psdocs | pdfdocs}``. The Sphinx books should be built with ``make {htmldocs | pdfdocs | epubdocs}``. * Name: **linux/Documentation** :Author: Many. :Location: Documentation/ - :Keywords: text files, Sphinx, DocBook. + :Keywords: text files, Sphinx. :Description: Documentation that comes with the kernel sources, inside the Documentation directory. Some pages from this document (including this document itself) have been moved there, and might be more up to date than the web version. - * Title: **The Kernel Hacking HOWTO** - - :Author: Various Talented People, and Rusty. - :Location: Documentation/DocBook/kernel-hacking.tmpl - :Keywords: HOWTO, kernel contexts, deadlock, locking, modules, - symbols, return conventions. - :Description: From the Introduction: "Please understand that I - never wanted to write this document, being grossly underqualified, - but I always wanted to read it, and this was the only way. I - simply explain some best practices, and give reading entry-points - into the kernel sources. I avoid implementation details: that's - what the code is for, and I ignore whole tracts of useful - routines. This document assumes familiarity with C, and an - understanding of what the kernel is, and how it is used. It was - originally written for the 2.3 kernels, but nearly all of it - applies to 2.2 too; 2.0 is slightly different". - - * Title: **Linux Kernel Locking HOWTO** - - :Author: Various Talented People, and Rusty. - :Location: Documentation/DocBook/kernel-locking.tmpl - :Keywords: locks, locking, spinlock, semaphore, atomic, race - condition, bottom halves, tasklets, softirqs. - :Description: The title says it all: document describing the - locking system in the Linux Kernel either in uniprocessor or SMP - systems. - :Notes: "It was originally written for the later (>2.3.47) 2.3 - kernels, but most of it applies to 2.2 too; 2.0 is slightly - different". Freely redistributable under the conditions of the GNU - General Public License. - On-line docs ------------ diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt index ddc366026e00f6..47feb4414b7e1f 100644 --- a/Documentation/rtc.txt +++ b/Documentation/rtc.txt @@ -1,6 +1,6 @@ - - Real Time Clock (RTC) Drivers for Linux - ======================================= +======================================= +Real Time Clock (RTC) Drivers for Linux +======================================= When Linux developers talk about a "Real Time Clock", they usually mean something that tracks wall clock time and is battery backed so that it @@ -32,8 +32,8 @@ only issue an alarm up to 24 hours in the future, other hardware may be able to schedule one any time in the upcoming century. - Old PC/AT-Compatible driver: /dev/rtc - -------------------------------------- +Old PC/AT-Compatible driver: /dev/rtc +-------------------------------------- All PCs (even Alpha machines) have a Real Time Clock built into them. Usually they are built into the chipset of the computer, but some may @@ -105,8 +105,8 @@ that will be using this driver. See the code at the end of this document. (The original /dev/rtc driver was written by Paul Gortmaker.) - New portable "RTC Class" drivers: /dev/rtcN - -------------------------------------------- +New portable "RTC Class" drivers: /dev/rtcN +-------------------------------------------- Because Linux supports many non-ACPI and non-PC platforms, some of which have more than one RTC style clock, it needed a more portable solution @@ -136,35 +136,37 @@ a high functionality RTC is integrated into the SOC. That system might read the system clock from the discrete RTC, but use the integrated one for all other tasks, because of its greater functionality. -SYSFS INTERFACE +SYSFS interface --------------- The sysfs interface under /sys/class/rtc/rtcN provides access to various rtc attributes without requiring the use of ioctls. All dates and times are in the RTC's timezone, rather than in system time. -date: RTC-provided date -hctosys: 1 if the RTC provided the system time at boot via the +================ ============================================================== +date RTC-provided date +hctosys 1 if the RTC provided the system time at boot via the CONFIG_RTC_HCTOSYS kernel option, 0 otherwise -max_user_freq: The maximum interrupt rate an unprivileged user may request +max_user_freq The maximum interrupt rate an unprivileged user may request from this RTC. -name: The name of the RTC corresponding to this sysfs directory -since_epoch: The number of seconds since the epoch according to the RTC -time: RTC-provided time -wakealarm: The time at which the clock will generate a system wakeup +name The name of the RTC corresponding to this sysfs directory +since_epoch The number of seconds since the epoch according to the RTC +time RTC-provided time +wakealarm The time at which the clock will generate a system wakeup event. This is a one shot wakeup event, so must be reset - after wake if a daily wakeup is required. Format is seconds since - the epoch by default, or if there's a leading +, seconds in the - future, or if there is a leading +=, seconds ahead of the current - alarm. -offset: The amount which the rtc clock has been adjusted in firmware. + after wake if a daily wakeup is required. Format is seconds + since the epoch by default, or if there's a leading +, seconds + in the future, or if there is a leading +=, seconds ahead of + the current alarm. +offset The amount which the rtc clock has been adjusted in firmware. Visible only if the driver supports clock offset adjustment. The unit is parts per billion, i.e. The number of clock ticks which are added to or removed from the rtc's base clock per billion ticks. A positive value makes a day pass more slowly, longer, and a negative value makes a day pass more quickly. +================ ============================================================== -IOCTL INTERFACE +IOCTL interface --------------- The ioctl() calls supported by /dev/rtc are also supported by the RTC class diff --git a/Documentation/security/00-INDEX b/Documentation/security/00-INDEX deleted file mode 100644 index 45c82fd3e9d39b..00000000000000 --- a/Documentation/security/00-INDEX +++ /dev/null @@ -1,26 +0,0 @@ -00-INDEX - - this file. -LSM.txt - - description of the Linux Security Module framework. -SELinux.txt - - how to get started with the SELinux security enhancement. -Smack.txt - - documentation on the Smack Linux Security Module. -Yama.txt - - documentation on the Yama Linux Security Module. -apparmor.txt - - documentation on the AppArmor security extension. -credentials.txt - - documentation about credentials in Linux. -keys-ecryptfs.txt - - description of the encryption keys for the ecryptfs filesystem. -keys-request-key.txt - - description of the kernel key request service. -keys-trusted-encrypted.txt - - info on the Trusted and Encrypted keys in the kernel key ring service. -keys.txt - - description of the kernel key retention service. -tomoyo.txt - - documentation on the TOMOYO Linux Security Module. -IMA-templates.txt - - documentation on the template management mechanism for IMA. diff --git a/Documentation/security/IMA-templates.txt b/Documentation/security/IMA-templates.rst similarity index 72% rename from Documentation/security/IMA-templates.txt rename to Documentation/security/IMA-templates.rst index 839b5dad922663..2cd0e273cc9aa0 100644 --- a/Documentation/security/IMA-templates.txt +++ b/Documentation/security/IMA-templates.rst @@ -1,9 +1,12 @@ - IMA Template Management Mechanism +================================= +IMA Template Management Mechanism +================================= -==== INTRODUCTION ==== +Introduction +============ -The original 'ima' template is fixed length, containing the filedata hash +The original ``ima`` template is fixed length, containing the filedata hash and pathname. The filedata hash is limited to 20 bytes (md5/sha1). The pathname is a null terminated string, limited to 255 characters. To overcome these limitations and to add additional file metadata, it is @@ -28,61 +31,64 @@ a new data type, developers define the field identifier and implement two functions, init() and show(), respectively to generate and display measurement entries. Defining a new template descriptor requires specifying the template format (a string of field identifiers separated -by the '|' character) through the 'ima_template_fmt' kernel command line +by the ``|`` character) through the ``ima_template_fmt`` kernel command line parameter. At boot time, IMA initializes the chosen template descriptor by translating the format into an array of template fields structures taken from the set of the supported ones. -After the initialization step, IMA will call ima_alloc_init_template() +After the initialization step, IMA will call ``ima_alloc_init_template()`` (new function defined within the patches for the new template management mechanism) to generate a new measurement entry by using the template descriptor chosen through the kernel configuration or through the newly -introduced 'ima_template' and 'ima_template_fmt' kernel command line parameters. +introduced ``ima_template`` and ``ima_template_fmt`` kernel command line parameters. It is during this phase that the advantages of the new architecture are clearly shown: the latter function will not contain specific code to handle -a given template but, instead, it simply calls the init() method of the template +a given template but, instead, it simply calls the ``init()`` method of the template fields associated to the chosen template descriptor and store the result (pointer to allocated data and data length) in the measurement entry structure. The same mechanism is employed to display measurements entries. -The functions ima[_ascii]_measurements_show() retrieve, for each entry, +The functions ``ima[_ascii]_measurements_show()`` retrieve, for each entry, the template descriptor used to produce that entry and call the show() method for each item of the array of template fields structures. -==== SUPPORTED TEMPLATE FIELDS AND DESCRIPTORS ==== +Supported Template Fields and Descriptors +========================================= In the following, there is the list of supported template fields -('': description), that can be used to define new template +``('': description)``, that can be used to define new template descriptors by adding their identifier to the format string (support for more data types will be added later): - 'd': the digest of the event (i.e. the digest of a measured file), - calculated with the SHA1 or MD5 hash algorithm; + calculated with the SHA1 or MD5 hash algorithm; - 'n': the name of the event (i.e. the file name), with size up to 255 bytes; - 'd-ng': the digest of the event, calculated with an arbitrary hash - algorithm (field format: [:]digest, where the digest - prefix is shown only if the hash algorithm is not SHA1 or MD5); + algorithm (field format: [:]digest, where the digest + prefix is shown only if the hash algorithm is not SHA1 or MD5); - 'n-ng': the name of the event, without size limitations; - 'sig': the file signature. Below, there is the list of defined template descriptors: - - "ima": its format is 'd|n'; - - "ima-ng" (default): its format is 'd-ng|n-ng'; - - "ima-sig": its format is 'd-ng|n-ng|sig'. + - "ima": its format is ``d|n``; + - "ima-ng" (default): its format is ``d-ng|n-ng``; + - "ima-sig": its format is ``d-ng|n-ng|sig``. -==== USE ==== + +Use +=== To specify the template descriptor to be used to generate measurement entries, currently the following methods are supported: - select a template descriptor among those supported in the kernel - configuration ('ima-ng' is the default choice); + configuration (``ima-ng`` is the default choice); - specify a template descriptor name from the kernel command line through - the 'ima_template=' parameter; + the ``ima_template=`` parameter; - register a new template descriptor with custom format through the kernel - command line parameter 'ima_template_fmt='. + command line parameter ``ima_template_fmt=``. diff --git a/Documentation/security/LSM.rst b/Documentation/security/LSM.rst new file mode 100644 index 00000000000000..d75778b0fa1000 --- /dev/null +++ b/Documentation/security/LSM.rst @@ -0,0 +1,14 @@ +================================= +Linux Security Module Development +================================= + +Based on https://lkml.org/lkml/2007/10/26/215, +a new LSM is accepted into the kernel when its intent (a description of +what it tries to protect against and in what cases one would expect to +use it) has been appropriately documented in ``Documentation/security/LSM``. +This allows an LSM's code to be easily compared to its goals, and so +that end users and distros can make a more informed decision about which +LSMs suit their requirements. + +For extensive documentation on the available LSM hook interfaces, please +see ``include/linux/lsm_hooks.h``. diff --git a/Documentation/security/conf.py b/Documentation/security/conf.py deleted file mode 100644 index 472fc9a8eb6701..00000000000000 --- a/Documentation/security/conf.py +++ /dev/null @@ -1,8 +0,0 @@ -project = "The kernel security subsystem manual" - -tags.add("subproject") - -latex_documents = [ - ('index', 'security.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/security/credentials.txt b/Documentation/security/credentials.rst similarity index 72% rename from Documentation/security/credentials.txt rename to Documentation/security/credentials.rst index 86257052e31ad7..038a7e19eff9ae 100644 --- a/Documentation/security/credentials.txt +++ b/Documentation/security/credentials.rst @@ -1,38 +1,18 @@ - ==================== - CREDENTIALS IN LINUX - ==================== +==================== +Credentials in Linux +==================== By: David Howells -Contents: - - (*) Overview. - - (*) Types of credentials. - - (*) File markings. - - (*) Task credentials. +.. contents:: :local: - - Immutable credentials. - - Accessing task credentials. - - Accessing another task's credentials. - - Altering credentials. - - Managing credentials. - - (*) Open file credentials. - - (*) Overriding the VFS's use of credentials. - - -======== -OVERVIEW +Overview ======== There are several parts to the security check performed by Linux when one object acts upon another: - (1) Objects. + 1. Objects. Objects are things in the system that may be acted upon directly by userspace programs. Linux has a variety of actionable objects, including: @@ -48,7 +28,7 @@ object acts upon another: As a part of the description of all these objects there is a set of credentials. What's in the set depends on the type of object. - (2) Object ownership. + 2. Object ownership. Amongst the credentials of most objects, there will be a subset that indicates the ownership of that object. This is used for resource @@ -57,7 +37,7 @@ object acts upon another: In a standard UNIX filesystem, for instance, this will be defined by the UID marked on the inode. - (3) The objective context. + 3. The objective context. Also amongst the credentials of those objects, there will be a subset that indicates the 'objective context' of that object. This may or may not be @@ -67,7 +47,7 @@ object acts upon another: The objective context is used as part of the security calculation that is carried out when an object is acted upon. - (4) Subjects. + 4. Subjects. A subject is an object that is acting upon another object. @@ -77,10 +57,10 @@ object acts upon another: Objects other than tasks may under some circumstances also be subjects. For instance an open file may send SIGIO to a task using the UID and EUID - given to it by a task that called fcntl(F_SETOWN) upon it. In this case, + given to it by a task that called ``fcntl(F_SETOWN)`` upon it. In this case, the file struct will have a subjective context too. - (5) The subjective context. + 5. The subjective context. A subject has an additional interpretation of its credentials. A subset of its credentials forms the 'subjective context'. The subjective context @@ -92,7 +72,7 @@ object acts upon another: from the real UID and GID that normally form the objective context of the task. - (6) Actions. + 6. Actions. Linux has a number of actions available that a subject may perform upon an object. The set of actions available depends on the nature of the subject @@ -101,7 +81,7 @@ object acts upon another: Actions include reading, writing, creating and deleting files; forking or signalling and tracing tasks. - (7) Rules, access control lists and security calculations. + 7. Rules, access control lists and security calculations. When a subject acts upon an object, a security calculation is made. This involves taking the subjective context, the objective context and the @@ -111,7 +91,7 @@ object acts upon another: There are two main sources of rules: - (a) Discretionary access control (DAC): + a. Discretionary access control (DAC): Sometimes the object will include sets of rules as part of its description. This is an 'Access Control List' or 'ACL'. A Linux @@ -127,7 +107,7 @@ object acts upon another: A Linux file might also sport a POSIX ACL. This is a list of rules that grants various permissions to arbitrary subjects. - (b) Mandatory access control (MAC): + b. Mandatory access control (MAC): The system as a whole may have one or more sets of rules that get applied to all subjects and objects, regardless of their source. @@ -139,65 +119,65 @@ object acts upon another: that says that this action is either granted or denied. -==================== -TYPES OF CREDENTIALS +Types of Credentials ==================== The Linux kernel supports the following types of credentials: - (1) Traditional UNIX credentials. + 1. Traditional UNIX credentials. - Real User ID - Real Group ID + - Real User ID + - Real Group ID The UID and GID are carried by most, if not all, Linux objects, even if in some cases it has to be invented (FAT or CIFS files for example, which are derived from Windows). These (mostly) define the objective context of that object, with tasks being slightly different in some cases. - Effective, Saved and FS User ID - Effective, Saved and FS Group ID - Supplementary groups + - Effective, Saved and FS User ID + - Effective, Saved and FS Group ID + - Supplementary groups These are additional credentials used by tasks only. Usually, an EUID/EGID/GROUPS will be used as the subjective context, and real UID/GID will be used as the objective. For tasks, it should be noted that this is not always true. - (2) Capabilities. + 2. Capabilities. - Set of permitted capabilities - Set of inheritable capabilities - Set of effective capabilities - Capability bounding set + - Set of permitted capabilities + - Set of inheritable capabilities + - Set of effective capabilities + - Capability bounding set These are only carried by tasks. They indicate superior capabilities granted piecemeal to a task that an ordinary task wouldn't otherwise have. These are manipulated implicitly by changes to the traditional UNIX - credentials, but can also be manipulated directly by the capset() system - call. + credentials, but can also be manipulated directly by the ``capset()`` + system call. The permitted capabilities are those caps that the process might grant - itself to its effective or permitted sets through capset(). This + itself to its effective or permitted sets through ``capset()``. This inheritable set might also be so constrained. The effective capabilities are the ones that a task is actually allowed to make use of itself. The inheritable capabilities are the ones that may get passed across - execve(). + ``execve()``. The bounding set limits the capabilities that may be inherited across - execve(), especially when a binary is executed that will execute as UID 0. + ``execve()``, especially when a binary is executed that will execute as + UID 0. - (3) Secure management flags (securebits). + 3. Secure management flags (securebits). These are only carried by tasks. These govern the way the above credentials are manipulated and inherited over certain operations such as execve(). They aren't used directly as objective or subjective credentials. - (4) Keys and keyrings. + 4. Keys and keyrings. These are only carried by tasks. They carry and cache security tokens that don't fit into the other standard UNIX credentials. They are for @@ -218,7 +198,7 @@ The Linux kernel supports the following types of credentials: For more information on using keys, see Documentation/security/keys.txt. - (5) LSM + 5. LSM The Linux Security Module allows extra controls to be placed over the operations that a task may do. Currently Linux supports several LSM @@ -228,7 +208,7 @@ The Linux kernel supports the following types of credentials: rules (policies) that say what operations a task with one label may do to an object with another label. - (6) AF_KEY + 6. AF_KEY This is a socket-based approach to credential management for networking stacks [RFC 2367]. It isn't discussed by this document as it doesn't @@ -244,25 +224,19 @@ network filesystem where the credentials of the opened file should be presented to the server, regardless of who is actually doing a read or a write upon it. -============= -FILE MARKINGS +File Markings ============= Files on disk or obtained over the network may have annotations that form the objective security context of that file. Depending on the type of filesystem, this may include one or more of the following: - (*) UNIX UID, GID, mode; - - (*) Windows user ID; - - (*) Access control list; - - (*) LSM security label; - - (*) UNIX exec privilege escalation bits (SUID/SGID); - - (*) File capabilities exec privilege escalation bits. + * UNIX UID, GID, mode; + * Windows user ID; + * Access control list; + * LSM security label; + * UNIX exec privilege escalation bits (SUID/SGID); + * File capabilities exec privilege escalation bits. These are compared to the task's subjective security context, and certain operations allowed or disallowed as a result. In the case of execve(), the @@ -270,8 +244,7 @@ privilege escalation bits come into play, and may allow the resulting process extra privileges, based on the annotations on the executable file. -================ -TASK CREDENTIALS +Task Credentials ================ In Linux, all of a task's credentials are held in (uid, gid) or through @@ -282,20 +255,20 @@ task_struct. Once a set of credentials has been prepared and committed, it may not be changed, barring the following exceptions: - (1) its reference count may be changed; + 1. its reference count may be changed; - (2) the reference count on the group_info struct it points to may be changed; + 2. the reference count on the group_info struct it points to may be changed; - (3) the reference count on the security data it points to may be changed; + 3. the reference count on the security data it points to may be changed; - (4) the reference count on any keyrings it points to may be changed; + 4. the reference count on any keyrings it points to may be changed; - (5) any keyrings it points to may be revoked, expired or have their security - attributes changed; and + 5. any keyrings it points to may be revoked, expired or have their security + attributes changed; and - (6) the contents of any keyrings to which it points may be changed (the whole - point of keyrings being a shared set of credentials, modifiable by anyone - with appropriate access). + 6. the contents of any keyrings to which it points may be changed (the whole + point of keyrings being a shared set of credentials, modifiable by anyone + with appropriate access). To alter anything in the cred struct, the copy-and-replace principle must be adhered to. First take a copy, then alter the copy and then use RCU to change @@ -303,37 +276,37 @@ the task pointer to make it point to the new copy. There are wrappers to aid with this (see below). A task may only alter its _own_ credentials; it is no longer permitted for a -task to alter another's credentials. This means the capset() system call is no -longer permitted to take any PID other than the one of the current process. -Also keyctl_instantiate() and keyctl_negate() functions no longer permit -attachment to process-specific keyrings in the requesting process as the -instantiating process may need to create them. +task to alter another's credentials. This means the ``capset()`` system call +is no longer permitted to take any PID other than the one of the current +process. Also ``keyctl_instantiate()`` and ``keyctl_negate()`` functions no +longer permit attachment to process-specific keyrings in the requesting +process as the instantiating process may need to create them. -IMMUTABLE CREDENTIALS +Immutable Credentials --------------------- -Once a set of credentials has been made public (by calling commit_creds() for -example), it must be considered immutable, barring two exceptions: +Once a set of credentials has been made public (by calling ``commit_creds()`` +for example), it must be considered immutable, barring two exceptions: - (1) The reference count may be altered. + 1. The reference count may be altered. - (2) Whilst the keyring subscriptions of a set of credentials may not be - changed, the keyrings subscribed to may have their contents altered. + 2. Whilst the keyring subscriptions of a set of credentials may not be + changed, the keyrings subscribed to may have their contents altered. To catch accidental credential alteration at compile time, struct task_struct has _const_ pointers to its credential sets, as does struct file. Furthermore, -certain functions such as get_cred() and put_cred() operate on const pointers, -thus rendering casts unnecessary, but require to temporarily ditch the const -qualification to be able to alter the reference count. +certain functions such as ``get_cred()`` and ``put_cred()`` operate on const +pointers, thus rendering casts unnecessary, but require to temporarily ditch +the const qualification to be able to alter the reference count. -ACCESSING TASK CREDENTIALS +Accessing Task Credentials -------------------------- A task being able to alter only its own credentials permits the current process to read or replace its own credentials without the need for any form of locking -- which simplifies things greatly. It can just call: +-- which simplifies things greatly. It can just call:: const struct cred *current_cred() @@ -341,7 +314,7 @@ to get a pointer to its credentials structure, and it doesn't have to release it afterwards. There are convenience wrappers for retrieving specific aspects of a task's -credentials (the value is simply returned in each case): +credentials (the value is simply returned in each case):: uid_t current_uid(void) Current's real UID gid_t current_gid(void) Current's real GID @@ -354,7 +327,7 @@ credentials (the value is simply returned in each case): struct user_struct *current_user(void) Current's user account There are also convenience wrappers for retrieving specific associated pairs of -a task's credentials: +a task's credentials:: void current_uid_gid(uid_t *, gid_t *); void current_euid_egid(uid_t *, gid_t *); @@ -365,12 +338,12 @@ them from the current task's credentials. In addition, there is a function for obtaining a reference on the current -process's current set of credentials: +process's current set of credentials:: const struct cred *get_current_cred(void); and functions for getting references to one of the credentials that don't -actually live in struct cred: +actually live in struct cred:: struct user_struct *get_current_user(void); struct group_info *get_current_groups(void); @@ -378,22 +351,22 @@ actually live in struct cred: which get references to the current process's user accounting structure and supplementary groups list respectively. -Once a reference has been obtained, it must be released with put_cred(), -free_uid() or put_group_info() as appropriate. +Once a reference has been obtained, it must be released with ``put_cred()``, +``free_uid()`` or ``put_group_info()`` as appropriate. -ACCESSING ANOTHER TASK'S CREDENTIALS +Accessing Another Task's Credentials ------------------------------------ Whilst a task may access its own credentials without the need for locking, the same is not true of a task wanting to access another task's credentials. It -must use the RCU read lock and rcu_dereference(). +must use the RCU read lock and ``rcu_dereference()``. -The rcu_dereference() is wrapped by: +The ``rcu_dereference()`` is wrapped by:: const struct cred *__task_cred(struct task_struct *task); -This should be used inside the RCU read lock, as in the following example: +This should be used inside the RCU read lock, as in the following example:: void foo(struct task_struct *t, struct foo_data *f) { @@ -410,39 +383,40 @@ This should be used inside the RCU read lock, as in the following example: Should it be necessary to hold another task's credentials for a long period of time, and possibly to sleep whilst doing so, then the caller should get a -reference on them using: +reference on them using:: const struct cred *get_task_cred(struct task_struct *task); This does all the RCU magic inside of it. The caller must call put_cred() on the credentials so obtained when they're finished with. - [*] Note: The result of __task_cred() should not be passed directly to - get_cred() as this may race with commit_cred(). +.. note:: + The result of ``__task_cred()`` should not be passed directly to + ``get_cred()`` as this may race with ``commit_cred()``. There are a couple of convenience functions to access bits of another task's -credentials, hiding the RCU magic from the caller: +credentials, hiding the RCU magic from the caller:: uid_t task_uid(task) Task's real UID uid_t task_euid(task) Task's effective UID -If the caller is holding the RCU read lock at the time anyway, then: +If the caller is holding the RCU read lock at the time anyway, then:: __task_cred(task)->uid __task_cred(task)->euid should be used instead. Similarly, if multiple aspects of a task's credentials -need to be accessed, RCU read lock should be used, __task_cred() called, the -result stored in a temporary pointer and then the credential aspects called +need to be accessed, RCU read lock should be used, ``__task_cred()`` called, +the result stored in a temporary pointer and then the credential aspects called from that before dropping the lock. This prevents the potentially expensive RCU magic from being invoked multiple times. Should some other single aspect of another task's credentials need to be -accessed, then this can be used: +accessed, then this can be used:: task_cred_xxx(task, member) -where 'member' is a non-pointer member of the cred struct. For instance: +where 'member' is a non-pointer member of the cred struct. For instance:: uid_t task_cred_xxx(task, suid); @@ -451,7 +425,7 @@ magic. This may not be used for pointer members as what they point to may disappear the moment the RCU read lock is dropped. -ALTERING CREDENTIALS +Altering Credentials -------------------- As previously mentioned, a task may only alter its own credentials, and may not @@ -459,7 +433,7 @@ alter those of another task. This means that it doesn't need to use any locking to alter its own credentials. To alter the current process's credentials, a function should first prepare a -new set of credentials by calling: +new set of credentials by calling:: struct cred *prepare_creds(void); @@ -467,9 +441,10 @@ this locks current->cred_replace_mutex and then allocates and constructs a duplicate of the current process's credentials, returning with the mutex still held if successful. It returns NULL if not successful (out of memory). -The mutex prevents ptrace() from altering the ptrace state of a process whilst -security checks on credentials construction and changing is taking place as -the ptrace state may alter the outcome, particularly in the case of execve(). +The mutex prevents ``ptrace()`` from altering the ptrace state of a process +whilst security checks on credentials construction and changing is taking place +as the ptrace state may alter the outcome, particularly in the case of +``execve()``. The new credentials set should be altered appropriately, and any security checks and hooks done. Both the current and the proposed sets of credentials @@ -478,36 +453,37 @@ still at this point. When the credential set is ready, it should be committed to the current process -by calling: +by calling:: int commit_creds(struct cred *new); This will alter various aspects of the credentials and the process, giving the -LSM a chance to do likewise, then it will use rcu_assign_pointer() to actually -commit the new credentials to current->cred, it will release -current->cred_replace_mutex to allow ptrace() to take place, and it will notify -the scheduler and others of the changes. +LSM a chance to do likewise, then it will use ``rcu_assign_pointer()`` to +actually commit the new credentials to ``current->cred``, it will release +``current->cred_replace_mutex`` to allow ``ptrace()`` to take place, and it +will notify the scheduler and others of the changes. This function is guaranteed to return 0, so that it can be tail-called at the -end of such functions as sys_setresuid(). +end of such functions as ``sys_setresuid()``. Note that this function consumes the caller's reference to the new credentials. -The caller should _not_ call put_cred() on the new credentials afterwards. +The caller should _not_ call ``put_cred()`` on the new credentials afterwards. Furthermore, once this function has been called on a new set of credentials, those credentials may _not_ be changed further. -Should the security checks fail or some other error occur after prepare_creds() -has been called, then the following function should be invoked: +Should the security checks fail or some other error occur after +``prepare_creds()`` has been called, then the following function should be +invoked:: void abort_creds(struct cred *new); -This releases the lock on current->cred_replace_mutex that prepare_creds() got -and then releases the new credentials. +This releases the lock on ``current->cred_replace_mutex`` that +``prepare_creds()`` got and then releases the new credentials. -A typical credentials alteration function would look something like this: +A typical credentials alteration function would look something like this:: int alter_suid(uid_t suid) { @@ -529,53 +505,50 @@ A typical credentials alteration function would look something like this: } -MANAGING CREDENTIALS +Managing Credentials -------------------- There are some functions to help manage credentials: - (*) void put_cred(const struct cred *cred); + - ``void put_cred(const struct cred *cred);`` This releases a reference to the given set of credentials. If the reference count reaches zero, the credentials will be scheduled for destruction by the RCU system. - (*) const struct cred *get_cred(const struct cred *cred); + - ``const struct cred *get_cred(const struct cred *cred);`` This gets a reference on a live set of credentials, returning a pointer to that set of credentials. - (*) struct cred *get_new_cred(struct cred *cred); + - ``struct cred *get_new_cred(struct cred *cred);`` This gets a reference on a set of credentials that is under construction and is thus still mutable, returning a pointer to that set of credentials. -===================== -OPEN FILE CREDENTIALS +Open File Credentials ===================== When a new file is opened, a reference is obtained on the opening task's -credentials and this is attached to the file struct as 'f_cred' in place of -'f_uid' and 'f_gid'. Code that used to access file->f_uid and file->f_gid -should now access file->f_cred->fsuid and file->f_cred->fsgid. +credentials and this is attached to the file struct as ``f_cred`` in place of +``f_uid`` and ``f_gid``. Code that used to access ``file->f_uid`` and +``file->f_gid`` should now access ``file->f_cred->fsuid`` and +``file->f_cred->fsgid``. -It is safe to access f_cred without the use of RCU or locking because the +It is safe to access ``f_cred`` without the use of RCU or locking because the pointer will not change over the lifetime of the file struct, and nor will the contents of the cred struct pointed to, barring the exceptions listed above (see the Task Credentials section). -======================================= -OVERRIDING THE VFS'S USE OF CREDENTIALS +Overriding the VFS's Use of Credentials ======================================= Under some circumstances it is desirable to override the credentials used by -the VFS, and that can be done by calling into such as vfs_mkdir() with a +the VFS, and that can be done by calling into such as ``vfs_mkdir()`` with a different set of credentials. This is done in the following places: - (*) sys_faccessat(). - - (*) do_coredump(). - - (*) nfs4recover.c. + * ``sys_faccessat()``. + * ``do_coredump()``. + * nfs4recover.c. diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst index 9bae6bb20e7fd5..298a94a33f053a 100644 --- a/Documentation/security/index.rst +++ b/Documentation/security/index.rst @@ -1,7 +1,13 @@ ====================== -Security documentation +Security Documentation ====================== .. toctree:: + :maxdepth: 1 + credentials + IMA-templates + keys/index + LSM + self-protection tpm/index diff --git a/Documentation/security/keys.txt b/Documentation/security/keys/core.rst similarity index 89% rename from Documentation/security/keys.txt rename to Documentation/security/keys/core.rst index cd5019934d7fb6..0d831a7afe4fe8 100644 --- a/Documentation/security/keys.txt +++ b/Documentation/security/keys/core.rst @@ -1,6 +1,6 @@ - ============================ - KERNEL KEY RETENTION SERVICE - ============================ +============================ +Kernel Key Retention Service +============================ This service allows cryptographic keys, authentication tokens, cross-domain user mappings, and similar to be cached in the kernel for the use of @@ -29,8 +29,7 @@ This document has the following sections: - Garbage collection -============ -KEY OVERVIEW +Key Overview ============ In this context, keys represent units of cryptographic data, authentication @@ -47,14 +46,14 @@ Each key has a number of attributes: - State. - (*) Each key is issued a serial number of type key_serial_t that is unique for + * Each key is issued a serial number of type key_serial_t that is unique for the lifetime of that key. All serial numbers are positive non-zero 32-bit integers. Userspace programs can use a key's serial numbers as a way to gain access to it, subject to permission checking. - (*) Each key is of a defined "type". Types must be registered inside the + * Each key is of a defined "type". Types must be registered inside the kernel by a kernel service (such as a filesystem) before keys of that type can be added or used. Userspace programs cannot define new types directly. @@ -64,18 +63,18 @@ Each key has a number of attributes: Should a type be removed from the system, all the keys of that type will be invalidated. - (*) Each key has a description. This should be a printable string. The key + * Each key has a description. This should be a printable string. The key type provides an operation to perform a match between the description on a key and a criterion string. - (*) Each key has an owner user ID, a group ID and a permissions mask. These + * Each key has an owner user ID, a group ID and a permissions mask. These are used to control what a process may do to a key from userspace, and whether a kernel service will be able to find the key. - (*) Each key can be set to expire at a specific time by the key type's + * Each key can be set to expire at a specific time by the key type's instantiation function. Keys can also be immortal. - (*) Each key can have a payload. This is a quantity of data that represent the + * Each key can have a payload. This is a quantity of data that represent the actual "key". In the case of a keyring, this is a list of keys to which the keyring links; in the case of a user-defined key, it's an arbitrary blob of data. @@ -91,39 +90,38 @@ Each key has a number of attributes: permitted, another key type operation will be called to convert the key's attached payload back into a blob of data. - (*) Each key can be in one of a number of basic states: + * Each key can be in one of a number of basic states: - (*) Uninstantiated. The key exists, but does not have any data attached. + * Uninstantiated. The key exists, but does not have any data attached. Keys being requested from userspace will be in this state. - (*) Instantiated. This is the normal state. The key is fully formed, and + * Instantiated. This is the normal state. The key is fully formed, and has data attached. - (*) Negative. This is a relatively short-lived state. The key acts as a + * Negative. This is a relatively short-lived state. The key acts as a note saying that a previous call out to userspace failed, and acts as a throttle on key lookups. A negative key can be updated to a normal state. - (*) Expired. Keys can have lifetimes set. If their lifetime is exceeded, + * Expired. Keys can have lifetimes set. If their lifetime is exceeded, they traverse to this state. An expired key can be updated back to a normal state. - (*) Revoked. A key is put in this state by userspace action. It can't be + * Revoked. A key is put in this state by userspace action. It can't be found or operated upon (apart from by unlinking it). - (*) Dead. The key's type was unregistered, and so the key is now useless. + * Dead. The key's type was unregistered, and so the key is now useless. Keys in the last three states are subject to garbage collection. See the section on "Garbage collection". -==================== -KEY SERVICE OVERVIEW +Key Service Overview ==================== The key service provides a number of features besides keys: - (*) The key service defines three special key types: + * The key service defines three special key types: (+) "keyring" @@ -149,7 +147,7 @@ The key service provides a number of features besides keys: be created and updated from userspace, but the payload is only readable from kernel space. - (*) Each process subscribes to three keyrings: a thread-specific keyring, a + * Each process subscribes to three keyrings: a thread-specific keyring, a process-specific keyring, and a session-specific keyring. The thread-specific keyring is discarded from the child when any sort of @@ -170,7 +168,7 @@ The key service provides a number of features besides keys: The ownership of the thread keyring changes when the real UID and GID of the thread changes. - (*) Each user ID resident in the system holds two special keyrings: a user + * Each user ID resident in the system holds two special keyrings: a user specific keyring and a default user session keyring. The default session keyring is initialised with a link to the user-specific keyring. @@ -180,7 +178,7 @@ The key service provides a number of features besides keys: If a process attempts to access its session key when it doesn't have one, it will be subscribed to the default for its current UID. - (*) Each user has two quotas against which the keys they own are tracked. One + * Each user has two quotas against which the keys they own are tracked. One limits the total number of keys and keyrings, the other limits the total amount of description and payload space that can be consumed. @@ -194,54 +192,53 @@ The key service provides a number of features besides keys: If a system call that modifies a key or keyring in some way would put the user over quota, the operation is refused and error EDQUOT is returned. - (*) There's a system call interface by which userspace programs can create and + * There's a system call interface by which userspace programs can create and manipulate keys and keyrings. - (*) There's a kernel interface by which services can register types and search + * There's a kernel interface by which services can register types and search for keys. - (*) There's a way for the a search done from the kernel to call back to + * There's a way for the a search done from the kernel to call back to userspace to request a key that can't be found in a process's keyrings. - (*) An optional filesystem is available through which the key database can be + * An optional filesystem is available through which the key database can be viewed and manipulated. -====================== -KEY ACCESS PERMISSIONS +Key Access Permissions ====================== Keys have an owner user ID, a group access ID, and a permissions mask. The mask has up to eight bits each for possessor, user, group and other access. Only six of each set of eight bits are defined. These permissions granted are: - (*) View + * View This permits a key or keyring's attributes to be viewed - including key type and description. - (*) Read + * Read This permits a key's payload to be viewed or a keyring's list of linked keys. - (*) Write + * Write This permits a key's payload to be instantiated or updated, or it allows a link to be added to or removed from a keyring. - (*) Search + * Search This permits keyrings to be searched and keys to be found. Searches can only recurse into nested keyrings that have search permission set. - (*) Link + * Link This permits a key or keyring to be linked to. To create a link from a keyring to a key, a process must have Write permission on the keyring and Link permission on the key. - (*) Set Attribute + * Set Attribute This permits a key's UID, GID and permissions mask to be changed. @@ -249,8 +246,7 @@ For changing the ownership, group ID or permissions mask, being the owner of the key or having the sysadmin capability is sufficient. -=============== -SELINUX SUPPORT +SELinux Support =============== The security class "key" has been added to SELinux so that mandatory access @@ -282,14 +278,13 @@ their associated thread, and both session and process keyrings are handled similarly. -================ -NEW PROCFS FILES +New ProcFS Files ================ Two files have been added to procfs by which an administrator can find out about the status of the key service: - (*) /proc/keys + * /proc/keys This lists the keys that are currently viewable by the task reading the file, giving information about their type, description and permissions. @@ -301,7 +296,7 @@ about the status of the key service: security checks are still performed, and may further filter out keys that the current process is not authorised to view. - The contents of the file look like this: + The contents of the file look like this:: SERIAL FLAGS USAGE EXPY PERM UID GID TYPE DESCRIPTION: SUMMARY 00000001 I----- 39 perm 1f3f0000 0 0 keyring _uid_ses.0: 1/4 @@ -314,7 +309,7 @@ about the status of the key service: 00000893 I--Q-N 1 35s 1f3f0000 0 0 user metal:silver: 0 00000894 I--Q-- 1 10h 003f0000 0 0 user metal:gold: 0 - The flags are: + The flags are:: I Instantiated R Revoked @@ -324,10 +319,10 @@ about the status of the key service: N Negative key - (*) /proc/key-users + * /proc/key-users This file lists the tracking data for each user that has at least one key - on the system. Such data includes quota information and statistics: + on the system. Such data includes quota information and statistics:: [root@andromeda root]# cat /proc/key-users 0: 46 45/45 1/100 13/10000 @@ -335,7 +330,8 @@ about the status of the key service: 32: 2 2/2 2/100 40/10000 38: 2 2/2 2/100 40/10000 - The format of each line is + The format of each line is:: + : User ID to which this applies Structure refcount / Total number of keys and number instantiated @@ -346,14 +342,14 @@ about the status of the key service: Four new sysctl files have been added also for the purpose of controlling the quota limits on keys: - (*) /proc/sys/kernel/keys/root_maxkeys + * /proc/sys/kernel/keys/root_maxkeys /proc/sys/kernel/keys/root_maxbytes These files hold the maximum number of keys that root may have and the maximum total number of bytes of data that root may have stored in those keys. - (*) /proc/sys/kernel/keys/maxkeys + * /proc/sys/kernel/keys/maxkeys /proc/sys/kernel/keys/maxbytes These files hold the maximum number of keys that each non-root user may @@ -364,8 +360,7 @@ Root may alter these by writing each new limit as a decimal number string to the appropriate file. -=============================== -USERSPACE SYSTEM CALL INTERFACE +Userspace System Call Interface =============================== Userspace can manipulate keys directly through three new syscalls: add_key, @@ -375,7 +370,7 @@ manipulating keys. When referring to a key directly, userspace programs should use the key's serial number (a positive 32-bit integer). However, there are some special values available for referring to special keys and keyrings that relate to the -process making the call: +process making the call:: CONSTANT VALUE KEY REFERENCED ============================== ====== =========================== @@ -391,8 +386,8 @@ process making the call: The main syscalls are: - (*) Create a new key of given type, description and payload and add it to the - nominated keyring: + * Create a new key of given type, description and payload and add it to the + nominated keyring:: key_serial_t add_key(const char *type, const char *desc, const void *payload, size_t plen, @@ -432,8 +427,8 @@ The main syscalls are: The ID of the new or updated key is returned if successful. - (*) Search the process's keyrings for a key, potentially calling out to - userspace to create it. + * Search the process's keyrings for a key, potentially calling out to + userspace to create it:: key_serial_t request_key(const char *type, const char *description, const char *callout_info, @@ -453,7 +448,7 @@ The main syscalls are: The keyctl syscall functions are: - (*) Map a special key ID to a real key ID for this process: + * Map a special key ID to a real key ID for this process:: key_serial_t keyctl(KEYCTL_GET_KEYRING_ID, key_serial_t id, int create); @@ -466,7 +461,7 @@ The keyctl syscall functions are: non-zero; and the error ENOKEY will be returned if "create" is zero. - (*) Replace the session keyring this process subscribes to with a new one: + * Replace the session keyring this process subscribes to with a new one:: key_serial_t keyctl(KEYCTL_JOIN_SESSION_KEYRING, const char *name); @@ -484,7 +479,7 @@ The keyctl syscall functions are: The ID of the new session keyring is returned if successful. - (*) Update the specified key: + * Update the specified key:: long keyctl(KEYCTL_UPDATE, key_serial_t key, const void *payload, size_t plen); @@ -498,7 +493,7 @@ The keyctl syscall functions are: add_key(). - (*) Revoke a key: + * Revoke a key:: long keyctl(KEYCTL_REVOKE, key_serial_t key); @@ -507,7 +502,7 @@ The keyctl syscall functions are: be findable. - (*) Change the ownership of a key: + * Change the ownership of a key:: long keyctl(KEYCTL_CHOWN, key_serial_t key, uid_t uid, gid_t gid); @@ -520,7 +515,7 @@ The keyctl syscall functions are: its group list members. - (*) Change the permissions mask on a key: + * Change the permissions mask on a key:: long keyctl(KEYCTL_SETPERM, key_serial_t key, key_perm_t perm); @@ -531,7 +526,7 @@ The keyctl syscall functions are: error EINVAL will be returned. - (*) Describe a key: + * Describe a key:: long keyctl(KEYCTL_DESCRIBE, key_serial_t key, char *buffer, size_t buflen); @@ -547,7 +542,7 @@ The keyctl syscall functions are: A process must have view permission on the key for this function to be successful. - If successful, a string is placed in the buffer in the following format: + If successful, a string is placed in the buffer in the following format:: ;;;; @@ -555,12 +550,12 @@ The keyctl syscall functions are: is hexadecimal. A NUL character is included at the end of the string if the buffer is sufficiently big. - This can be parsed with + This can be parsed with:: sscanf(buffer, "%[^;];%d;%d;%o;%s", type, &uid, &gid, &mode, desc); - (*) Clear out a keyring: + * Clear out a keyring:: long keyctl(KEYCTL_CLEAR, key_serial_t keyring); @@ -573,7 +568,7 @@ The keyctl syscall functions are: DNS resolver cache keyring is an example of this. - (*) Link a key into a keyring: + * Link a key into a keyring:: long keyctl(KEYCTL_LINK, key_serial_t keyring, key_serial_t key); @@ -592,7 +587,7 @@ The keyctl syscall functions are: added. - (*) Unlink a key or keyring from another keyring: + * Unlink a key or keyring from another keyring:: long keyctl(KEYCTL_UNLINK, key_serial_t keyring, key_serial_t key); @@ -604,7 +599,7 @@ The keyctl syscall functions are: is not present, error ENOENT will be the result. - (*) Search a keyring tree for a key: + * Search a keyring tree for a key:: key_serial_t keyctl(KEYCTL_SEARCH, key_serial_t keyring, const char *type, const char *description, @@ -628,7 +623,7 @@ The keyctl syscall functions are: fails. On success, the resulting key ID will be returned. - (*) Read the payload data from a key: + * Read the payload data from a key:: long keyctl(KEYCTL_READ, key_serial_t keyring, char *buffer, size_t buflen); @@ -650,7 +645,7 @@ The keyctl syscall functions are: available rather than the amount copied. - (*) Instantiate a partially constructed key. + * Instantiate a partially constructed key:: long keyctl(KEYCTL_INSTANTIATE, key_serial_t key, const void *payload, size_t plen, @@ -677,7 +672,7 @@ The keyctl syscall functions are: array instead of a single buffer. - (*) Negatively instantiate a partially constructed key. + * Negatively instantiate a partially constructed key:: long keyctl(KEYCTL_NEGATE, key_serial_t key, unsigned timeout, key_serial_t keyring); @@ -700,12 +695,12 @@ The keyctl syscall functions are: as rejecting the key with ENOKEY as the error code. - (*) Set the default request-key destination keyring. + * Set the default request-key destination keyring:: long keyctl(KEYCTL_SET_REQKEY_KEYRING, int reqkey_defl); This sets the default keyring to which implicitly requested keys will be - attached for this thread. reqkey_defl should be one of these constants: + attached for this thread. reqkey_defl should be one of these constants:: CONSTANT VALUE NEW DEFAULT KEYRING ====================================== ====== ======================= @@ -731,7 +726,7 @@ The keyctl syscall functions are: there is one, otherwise the user default session keyring. - (*) Set the timeout on a key. + * Set the timeout on a key:: long keyctl(KEYCTL_SET_TIMEOUT, key_serial_t key, unsigned timeout); @@ -744,7 +739,7 @@ The keyctl syscall functions are: or expired keys. - (*) Assume the authority granted to instantiate a key + * Assume the authority granted to instantiate a key:: long keyctl(KEYCTL_ASSUME_AUTHORITY, key_serial_t key); @@ -766,7 +761,7 @@ The keyctl syscall functions are: The assumed authoritative key is inherited across fork and exec. - (*) Get the LSM security context attached to a key. + * Get the LSM security context attached to a key:: long keyctl(KEYCTL_GET_SECURITY, key_serial_t key, char *buffer, size_t buflen) @@ -787,7 +782,7 @@ The keyctl syscall functions are: successful. - (*) Install the calling process's session keyring on its parent. + * Install the calling process's session keyring on its parent:: long keyctl(KEYCTL_SESSION_TO_PARENT); @@ -807,7 +802,7 @@ The keyctl syscall functions are: kernel and resumes executing userspace. - (*) Invalidate a key. + * Invalidate a key:: long keyctl(KEYCTL_INVALIDATE, key_serial_t key); @@ -823,20 +818,19 @@ The keyctl syscall functions are: A process must have search permission on the key for this function to be successful. - (*) Compute a Diffie-Hellman shared secret or public key + * Compute a Diffie-Hellman shared secret or public key:: - long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params, - char *buffer, size_t buflen, - struct keyctl_kdf_params *kdf); + long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params, + char *buffer, size_t buflen, struct keyctl_kdf_params *kdf); - The params struct contains serial numbers for three keys: + The params struct contains serial numbers for three keys:: - The prime, p, known to both parties - The local private key - The base integer, which is either a shared generator or the remote public key - The value computed is: + The value computed is:: result = base ^ private (mod prime) @@ -858,12 +852,12 @@ The keyctl syscall functions are: of the KDF is returned to the caller. The KDF is characterized with struct keyctl_kdf_params as follows: - - char *hashname specifies the NUL terminated string identifying + - ``char *hashname`` specifies the NUL terminated string identifying the hash used from the kernel crypto API and applied for the KDF operation. The KDF implemenation complies with SP800-56A as well as with SP800-108 (the counter KDF). - - char *otherinfo specifies the OtherInfo data as documented in + - ``char *otherinfo`` specifies the OtherInfo data as documented in SP800-56A section 5.8.1.2. The length of the buffer is given with otherinfolen. The format of OtherInfo is defined by the caller. The otherinfo pointer may be NULL if no OtherInfo shall be used. @@ -875,10 +869,10 @@ The keyctl syscall functions are: and either the buffer length or the OtherInfo length exceeds the allowed length. - (*) Restrict keyring linkage + * Restrict keyring linkage:: - long keyctl(KEYCTL_RESTRICT_KEYRING, key_serial_t keyring, - const char *type, const char *restriction); + long keyctl(KEYCTL_RESTRICT_KEYRING, key_serial_t keyring, + const char *type, const char *restriction); An existing keyring can restrict linkage of additional keys by evaluating the contents of the key according to a restriction scheme. @@ -900,8 +894,7 @@ The keyctl syscall functions are: To apply a keyring restriction the process must have Set Attribute permission and the keyring must not be previously restricted. -=============== -KERNEL SERVICES +Kernel Services =============== The kernel services for key management are fairly simple to deal with. They can @@ -915,29 +908,29 @@ call, and the key released upon close. How to deal with conflicting keys due to two different users opening the same file is left to the filesystem author to solve. -To access the key manager, the following header must be #included: +To access the key manager, the following header must be #included:: Specific key types should have a header file under include/keys/ that should be -used to access that type. For keys of type "user", for example, that would be: +used to access that type. For keys of type "user", for example, that would be:: Note that there are two different types of pointers to keys that may be encountered: - (*) struct key * + * struct key * This simply points to the key structure itself. Key structures will be at least four-byte aligned. - (*) key_ref_t + * key_ref_t - This is equivalent to a struct key *, but the least significant bit is set + This is equivalent to a ``struct key *``, but the least significant bit is set if the caller "possesses" the key. By "possession" it is meant that the calling processes has a searchable link to the key from one of its - keyrings. There are three functions for dealing with these: + keyrings. There are three functions for dealing with these:: key_ref_t make_key_ref(const struct key *key, bool possession); @@ -955,7 +948,7 @@ When accessing a key's payload contents, certain precautions must be taken to prevent access vs modification races. See the section "Notes on accessing payload contents" for more information. -(*) To search for a key, call: + * To search for a key, call:: struct key *request_key(const struct key_type *type, const char *description, @@ -977,7 +970,7 @@ payload contents" for more information. See also Documentation/security/keys-request-key.txt. -(*) To search for a key, passing auxiliary data to the upcaller, call: + * To search for a key, passing auxiliary data to the upcaller, call:: struct key *request_key_with_auxdata(const struct key_type *type, const char *description, @@ -990,14 +983,14 @@ payload contents" for more information. is a blob of length callout_len, if given (the length may be 0). -(*) A key can be requested asynchronously by calling one of: + * A key can be requested asynchronously by calling one of:: struct key *request_key_async(const struct key_type *type, const char *description, const void *callout_info, size_t callout_len); - or: + or:: struct key *request_key_async_with_auxdata(const struct key_type *type, const char *description, @@ -1010,7 +1003,7 @@ payload contents" for more information. These two functions return with the key potentially still under construction. To wait for construction completion, the following should be - called: + called:: int wait_for_key_construction(struct key *key, bool intr); @@ -1022,11 +1015,11 @@ payload contents" for more information. case error ERESTARTSYS will be returned. -(*) When it is no longer required, the key should be released using: + * When it is no longer required, the key should be released using:: void key_put(struct key *key); - Or: + Or:: void key_ref_put(key_ref_t key_ref); @@ -1034,8 +1027,8 @@ payload contents" for more information. the argument will not be parsed. -(*) Extra references can be made to a key by calling one of the following - functions: + * Extra references can be made to a key by calling one of the following + functions:: struct key *__key_get(struct key *key); struct key *key_get(struct key *key); @@ -1047,7 +1040,7 @@ payload contents" for more information. then the key will not be dereferenced and no increment will take place. -(*) A key's serial number can be obtained by calling: + * A key's serial number can be obtained by calling:: key_serial_t key_serial(struct key *key); @@ -1055,7 +1048,7 @@ payload contents" for more information. latter case without parsing the argument). -(*) If a keyring was found in the search, this can be further searched by: + * If a keyring was found in the search, this can be further searched by:: key_ref_t keyring_search(key_ref_t keyring_ref, const struct key_type *type, @@ -1070,7 +1063,7 @@ payload contents" for more information. reference pointer if successful. -(*) A keyring can be created by: + * A keyring can be created by:: struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, const struct cred *cred, @@ -1109,7 +1102,7 @@ payload contents" for more information. -EPERM to in this case. -(*) To check the validity of a key, this function can be called: + * To check the validity of a key, this function can be called:: int validate_key(struct key *key); @@ -1119,7 +1112,7 @@ payload contents" for more information. returned (in the latter case without parsing the argument). -(*) To register a key type, the following function should be called: + * To register a key type, the following function should be called:: int register_key_type(struct key_type *type); @@ -1127,13 +1120,13 @@ payload contents" for more information. present. -(*) To unregister a key type, call: + * To unregister a key type, call:: void unregister_key_type(struct key_type *type); Under some circumstances, it may be desirable to deal with a bundle of keys. -The facility provides access to the keyring type for managing such a bundle: +The facility provides access to the keyring type for managing such a bundle:: struct key_type key_type_keyring; @@ -1143,8 +1136,7 @@ with keyring_search(). Note that it is not possible to use request_key() to search a specific keyring, so using keyrings in this way is of limited utility. -=================================== -NOTES ON ACCESSING PAYLOAD CONTENTS +Notes On Accessing Payload Contents =================================== The simplest payload is just data stored in key->payload directly. In this @@ -1154,31 +1146,31 @@ More complex payload contents must be allocated and pointers to them set in the key->payload.data[] array. One of the following ways must be selected to access the data: - (1) Unmodifiable key type. + 1) Unmodifiable key type. If the key type does not have a modify method, then the key's payload can be accessed without any form of locking, provided that it's known to be instantiated (uninstantiated keys cannot be "found"). - (2) The key's semaphore. + 2) The key's semaphore. The semaphore could be used to govern access to the payload and to control the payload pointer. It must be write-locked for modifications and would have to be read-locked for general access. The disadvantage of doing this is that the accessor may be required to sleep. - (3) RCU. + 3) RCU. RCU must be used when the semaphore isn't already held; if the semaphore is held then the contents can't change under you unexpectedly as the semaphore must still be used to serialise modifications to the key. The key management code takes care of this for the key type. - However, this means using: + However, this means using:: rcu_read_lock() ... rcu_dereference() ... rcu_read_unlock() - to read the pointer, and: + to read the pointer, and:: rcu_dereference() ... rcu_assign_pointer() ... call_rcu() @@ -1194,11 +1186,11 @@ access the data: usage. This is called key->payload.rcu_data0. The following accessors wrap the RCU calls to this element: - (a) Set or change the first payload pointer: + a) Set or change the first payload pointer:: rcu_assign_keypointer(struct key *key, void *data); - (b) Read the first payload pointer with the key semaphore held: + b) Read the first payload pointer with the key semaphore held:: [const] void *dereference_key_locked([const] struct key *key); @@ -1206,39 +1198,38 @@ access the data: parameter. Static analysis will give an error if it things the lock isn't held. - (c) Read the first payload pointer with the RCU read lock held: + c) Read the first payload pointer with the RCU read lock held:: const void *dereference_key_rcu(const struct key *key); -=================== -DEFINING A KEY TYPE +Defining a Key Type =================== A kernel service may want to define its own key type. For instance, an AFS filesystem might want to define a Kerberos 5 ticket key type. To do this, it author fills in a key_type struct and registers it with the system. -Source files that implement key types should include the following header file: +Source files that implement key types should include the following header file:: The structure has a number of fields, some of which are mandatory: - (*) const char *name + * ``const char *name`` The name of the key type. This is used to translate a key type name supplied by userspace into a pointer to the structure. - (*) size_t def_datalen + * ``size_t def_datalen`` This is optional - it supplies the default payload data length as contributed to the quota. If the key type's payload is always or almost always the same size, then this is a more efficient way to do things. The data length (and quota) on a particular key can always be changed - during instantiation or update by calling: + during instantiation or update by calling:: int key_payload_reserve(struct key *key, size_t datalen); @@ -1246,18 +1237,18 @@ The structure has a number of fields, some of which are mandatory: viable. - (*) int (*vet_description)(const char *description); + * ``int (*vet_description)(const char *description);`` This optional method is called to vet a key description. If the key type doesn't approve of the key description, it may return an error, otherwise it should return 0. - (*) int (*preparse)(struct key_preparsed_payload *prep); + * ``int (*preparse)(struct key_preparsed_payload *prep);`` This optional method permits the key type to attempt to parse payload before a key is created (add key) or the key semaphore is taken (update or - instantiate key). The structure pointed to by prep looks like: + instantiate key). The structure pointed to by prep looks like:: struct key_preparsed_payload { char *description; @@ -1285,7 +1276,7 @@ The structure has a number of fields, some of which are mandatory: otherwise. - (*) void (*free_preparse)(struct key_preparsed_payload *prep); + * ``void (*free_preparse)(struct key_preparsed_payload *prep);`` This method is only required if the preparse() method is provided, otherwise it is unused. It cleans up anything attached to the description @@ -1294,7 +1285,7 @@ The structure has a number of fields, some of which are mandatory: successfully, even if instantiate() or update() succeed. - (*) int (*instantiate)(struct key *key, struct key_preparsed_payload *prep); + * ``int (*instantiate)(struct key *key, struct key_preparsed_payload *prep);`` This method is called to attach a payload to a key during construction. The payload attached need not bear any relation to the data passed to this @@ -1318,7 +1309,7 @@ The structure has a number of fields, some of which are mandatory: free_preparse method doesn't release the data. - (*) int (*update)(struct key *key, const void *data, size_t datalen); + * ``int (*update)(struct key *key, const void *data, size_t datalen);`` If this type of key can be updated, then this method should be provided. It is called to update a key's payload from the blob of data provided. @@ -1343,10 +1334,10 @@ The structure has a number of fields, some of which are mandatory: It is safe to sleep in this method. - (*) int (*match_preparse)(struct key_match_data *match_data); + * ``int (*match_preparse)(struct key_match_data *match_data);`` This method is optional. It is called when a key search is about to be - performed. It is given the following structure: + performed. It is given the following structure:: struct key_match_data { bool (*cmp)(const struct key *key, @@ -1357,23 +1348,23 @@ The structure has a number of fields, some of which are mandatory: }; On entry, raw_data will be pointing to the criteria to be used in matching - a key by the caller and should not be modified. (*cmp)() will be pointing + a key by the caller and should not be modified. ``(*cmp)()`` will be pointing to the default matcher function (which does an exact description match against raw_data) and lookup_type will be set to indicate a direct lookup. The following lookup_type values are available: - [*] KEYRING_SEARCH_LOOKUP_DIRECT - A direct lookup hashes the type and + * KEYRING_SEARCH_LOOKUP_DIRECT - A direct lookup hashes the type and description to narrow down the search to a small number of keys. - [*] KEYRING_SEARCH_LOOKUP_ITERATE - An iterative lookup walks all the + * KEYRING_SEARCH_LOOKUP_ITERATE - An iterative lookup walks all the keys in the keyring until one is matched. This must be used for any search that's not doing a simple direct match on the key description. The method may set cmp to point to a function of its choice that does some other form of match, may set lookup_type to KEYRING_SEARCH_LOOKUP_ITERATE - and may attach something to the preparsed pointer for use by (*cmp)(). - (*cmp)() should return true if a key matches and false otherwise. + and may attach something to the preparsed pointer for use by ``(*cmp)()``. + ``(*cmp)()`` should return true if a key matches and false otherwise. If preparsed is set, it may be necessary to use the match_free() method to clean it up. @@ -1381,20 +1372,20 @@ The structure has a number of fields, some of which are mandatory: The method should return 0 if successful or a negative error code otherwise. - It is permitted to sleep in this method, but (*cmp)() may not sleep as + It is permitted to sleep in this method, but ``(*cmp)()`` may not sleep as locks will be held over it. If match_preparse() is not provided, keys of this type will be matched exactly by their description. - (*) void (*match_free)(struct key_match_data *match_data); + * ``void (*match_free)(struct key_match_data *match_data);`` This method is optional. If given, it called to clean up match_data->preparsed after a successful call to match_preparse(). - (*) void (*revoke)(struct key *key); + * ``void (*revoke)(struct key *key);`` This method is optional. It is called to discard part of the payload data upon a key being revoked. The caller will have the key semaphore @@ -1404,7 +1395,7 @@ The structure has a number of fields, some of which are mandatory: a deadlock against the key semaphore. - (*) void (*destroy)(struct key *key); + * ``void (*destroy)(struct key *key);`` This method is optional. It is called to discard the payload data on a key when it is being destroyed. @@ -1416,7 +1407,7 @@ The structure has a number of fields, some of which are mandatory: It is not safe to sleep in this method; the caller may hold spinlocks. - (*) void (*describe)(const struct key *key, struct seq_file *p); + * ``void (*describe)(const struct key *key, struct seq_file *p);`` This method is optional. It is called during /proc/keys reading to summarise a key's description and payload in text form. @@ -1432,7 +1423,7 @@ The structure has a number of fields, some of which are mandatory: caller. - (*) long (*read)(const struct key *key, char __user *buffer, size_t buflen); + * ``long (*read)(const struct key *key, char __user *buffer, size_t buflen);`` This method is optional. It is called by KEYCTL_READ to translate the key's payload into something a blob of data for userspace to deal with. @@ -1448,8 +1439,7 @@ The structure has a number of fields, some of which are mandatory: as might happen when the userspace buffer is accessed. - (*) int (*request_key)(struct key_construction *cons, const char *op, - void *aux); + * ``int (*request_key)(struct key_construction *cons, const char *op, void *aux);`` This method is optional. If provided, request_key() and friends will invoke this function rather than upcalling to /sbin/request-key to operate @@ -1463,7 +1453,7 @@ The structure has a number of fields, some of which are mandatory: This method is permitted to return before the upcall is complete, but the following function must be called under all circumstances to complete the instantiation process, whether or not it succeeds, whether or not there's - an error: + an error:: void complete_request_key(struct key_construction *cons, int error); @@ -1479,16 +1469,16 @@ The structure has a number of fields, some of which are mandatory: The key under construction and the authorisation key can be found in the key_construction struct pointed to by cons: - (*) struct key *key; + * ``struct key *key;`` The key under construction. - (*) struct key *authkey; + * ``struct key *authkey;`` The authorisation key. - (*) struct key_restriction *(*lookup_restriction)(const char *params); + * ``struct key_restriction *(*lookup_restriction)(const char *params);`` This optional method is used to enable userspace configuration of keyring restrictions. The restriction parameter string (not including the key type @@ -1497,12 +1487,11 @@ The structure has a number of fields, some of which are mandatory: attempted key link operation. If there is no match, -EINVAL is returned. -============================ -REQUEST-KEY CALLBACK SERVICE +Request-Key Callback Service ============================ To create a new key, the kernel will attempt to execute the following command -line: +line:: /sbin/request-key create \ @@ -1511,10 +1500,10 @@ line: keyrings from the process that caused the search to be issued. These are included for two reasons: - (1) There may be an authentication token in one of the keyrings that is + 1 There may be an authentication token in one of the keyrings that is required to obtain the key, eg: a Kerberos Ticket-Granting Ticket. - (2) The new key should probably be cached in one of these rings. + 2 The new key should probably be cached in one of these rings. This program should set it UID and GID to those specified before attempting to access any more keys. It may then look around for a user specific process to @@ -1539,7 +1528,7 @@ instead. Similarly, the kernel may attempt to update an expired or a soon to expire key -by executing: +by executing:: /sbin/request-key update \ @@ -1548,8 +1537,7 @@ In this case, the program isn't required to actually attach the key to a ring; the rings are provided for reference. -================== -GARBAGE COLLECTION +Garbage Collection ================== Dead keys (for which the type has been removed) will be automatically unlinked @@ -1557,6 +1545,6 @@ from those keyrings that point to them and deleted as soon as possible by a background garbage collector. Similarly, revoked and expired keys will be garbage collected, but only after a -certain amount of time has passed. This time is set as a number of seconds in: +certain amount of time has passed. This time is set as a number of seconds in:: /proc/sys/kernel/keys/gc_delay diff --git a/Documentation/security/keys-ecryptfs.txt b/Documentation/security/keys/ecryptfs.rst similarity index 91% rename from Documentation/security/keys-ecryptfs.txt rename to Documentation/security/keys/ecryptfs.rst index c3bbeba63562ff..4920f3a8ea7571 100644 --- a/Documentation/security/keys-ecryptfs.txt +++ b/Documentation/security/keys/ecryptfs.rst @@ -1,4 +1,6 @@ - Encrypted keys for the eCryptfs filesystem +========================================== +Encrypted keys for the eCryptfs filesystem +========================================== ECryptfs is a stacked filesystem which transparently encrypts and decrypts each file using a randomly generated File Encryption Key (FEK). @@ -35,20 +37,23 @@ controlled environment. Another advantage is that the key is not exposed to threats of malicious software, because it is available in clear form only at kernel level. -Usage: +Usage:: + keyctl add encrypted name "new ecryptfs key-type:master-key-name keylen" ring keyctl add encrypted name "load hex_blob" ring keyctl update keyid "update key-type:master-key-name" -name:= '<16 hexadecimal characters>' -key-type:= 'trusted' | 'user' -keylen:= 64 +Where:: + + name:= '<16 hexadecimal characters>' + key-type:= 'trusted' | 'user' + keylen:= 64 Example of encrypted key usage with the eCryptfs filesystem: Create an encrypted key "1000100010001000" of length 64 bytes with format -'ecryptfs' and save it using a previously loaded user key "test": +'ecryptfs' and save it using a previously loaded user key "test":: $ keyctl add encrypted 1000100010001000 "new ecryptfs user:test 64" @u 19184530 @@ -62,7 +67,7 @@ Create an encrypted key "1000100010001000" of length 64 bytes with format $ keyctl pipe 19184530 > ecryptfs.blob Mount an eCryptfs filesystem using the created encrypted key "1000100010001000" -into the '/secret' directory: +into the '/secret' directory:: $ mount -i -t ecryptfs -oecryptfs_sig=1000100010001000,\ ecryptfs_cipher=aes,ecryptfs_key_bytes=32 /secret /secret diff --git a/Documentation/security/keys/index.rst b/Documentation/security/keys/index.rst new file mode 100644 index 00000000000000..647d58f2588e45 --- /dev/null +++ b/Documentation/security/keys/index.rst @@ -0,0 +1,11 @@ +=========== +Kernel Keys +=========== + +.. toctree:: + :maxdepth: 1 + + core + ecryptfs + request-key + trusted-encrypted diff --git a/Documentation/security/keys-request-key.txt b/Documentation/security/keys/request-key.rst similarity index 77% rename from Documentation/security/keys-request-key.txt rename to Documentation/security/keys/request-key.rst index 51987bfecfedff..aba32784174c4e 100644 --- a/Documentation/security/keys-request-key.txt +++ b/Documentation/security/keys/request-key.rst @@ -1,19 +1,19 @@ - =================== - KEY REQUEST SERVICE - =================== +=================== +Key Request Service +=================== The key request service is part of the key retention service (refer to Documentation/security/keys.txt). This document explains more fully how the requesting algorithm works. The process starts by either the kernel requesting a service by calling -request_key*(): +``request_key*()``:: struct key *request_key(const struct key_type *type, const char *description, const char *callout_info); -or: +or:: struct key *request_key_with_auxdata(const struct key_type *type, const char *description, @@ -21,14 +21,14 @@ or: size_t callout_len, void *aux); -or: +or:: struct key *request_key_async(const struct key_type *type, const char *description, const char *callout_info, size_t callout_len); -or: +or:: struct key *request_key_async_with_auxdata(const struct key_type *type, const char *description, @@ -36,7 +36,7 @@ or: size_t callout_len, void *aux); -Or by userspace invoking the request_key system call: +Or by userspace invoking the request_key system call:: key_serial_t request_key(const char *type, const char *description, @@ -67,38 +67,37 @@ own upcall mechanisms. If they do, then those should be substituted for the forking and execution of /sbin/request-key. -=========== -THE PROCESS +The Process =========== A request proceeds in the following manner: - (1) Process A calls request_key() [the userspace syscall calls the kernel + 1) Process A calls request_key() [the userspace syscall calls the kernel interface]. - (2) request_key() searches the process's subscribed keyrings to see if there's + 2) request_key() searches the process's subscribed keyrings to see if there's a suitable key there. If there is, it returns the key. If there isn't, and callout_info is not set, an error is returned. Otherwise the process proceeds to the next step. - (3) request_key() sees that A doesn't have the desired key yet, so it creates + 3) request_key() sees that A doesn't have the desired key yet, so it creates two things: - (a) An uninstantiated key U of requested type and description. + a) An uninstantiated key U of requested type and description. - (b) An authorisation key V that refers to key U and notes that process A + b) An authorisation key V that refers to key U and notes that process A is the context in which key U should be instantiated and secured, and from which associated key requests may be satisfied. - (4) request_key() then forks and executes /sbin/request-key with a new session + 4) request_key() then forks and executes /sbin/request-key with a new session keyring that contains a link to auth key V. - (5) /sbin/request-key assumes the authority associated with key U. + 5) /sbin/request-key assumes the authority associated with key U. - (6) /sbin/request-key execs an appropriate program to perform the actual + 6) /sbin/request-key execs an appropriate program to perform the actual instantiation. - (7) The program may want to access another key from A's context (say a + 7) The program may want to access another key from A's context (say a Kerberos TGT key). It just requests the appropriate key, and the keyring search notes that the session keyring has auth key V in its bottom level. @@ -106,15 +105,15 @@ A request proceeds in the following manner: UID, GID, groups and security info of process A as if it was process A, and come up with key W. - (8) The program then does what it must to get the data with which to + 8) The program then does what it must to get the data with which to instantiate key U, using key W as a reference (perhaps it contacts a Kerberos server using the TGT) and then instantiates key U. - (9) Upon instantiating key U, auth key V is automatically revoked so that it + 9) Upon instantiating key U, auth key V is automatically revoked so that it may not be used again. -(10) The program then exits 0 and request_key() deletes key V and returns key - U to the caller. + 10) The program then exits 0 and request_key() deletes key V and returns key + U to the caller. This also extends further. If key W (step 7 above) didn't exist, key W would be created uninstantiated, another auth key (X) would be created (as per step @@ -127,8 +126,7 @@ This is because process A's keyrings can't simply be attached to of them, and (b) it requires the same UID/GID/Groups all the way through. -==================================== -NEGATIVE INSTANTIATION AND REJECTION +Negative Instantiation And Rejection ==================================== Rather than instantiating a key, it is possible for the possessor of an @@ -145,23 +143,22 @@ signal, the key under construction will be automatically negatively instantiated for a short amount of time. -==================== -THE SEARCH ALGORITHM +The Search Algorithm ==================== A search of any particular keyring proceeds in the following fashion: - (1) When the key management code searches for a key (keyring_search_aux) it + 1) When the key management code searches for a key (keyring_search_aux) it firstly calls key_permission(SEARCH) on the keyring it's starting with, if this denies permission, it doesn't search further. - (2) It considers all the non-keyring keys within that keyring and, if any key + 2) It considers all the non-keyring keys within that keyring and, if any key matches the criteria specified, calls key_permission(SEARCH) on it to see if the key is allowed to be found. If it is, that key is returned; if not, the search continues, and the error code is retained if of higher priority than the one currently set. - (3) It then considers all the keyring-type keys in the keyring it's currently + 3) It then considers all the keyring-type keys in the keyring it's currently searching. It calls key_permission(SEARCH) on each keyring, and if this grants permission, it recurses, executing steps (2) and (3) on that keyring. @@ -173,20 +170,20 @@ returned. When search_process_keyrings() is invoked, it performs the following searches until one succeeds: - (1) If extant, the process's thread keyring is searched. + 1) If extant, the process's thread keyring is searched. - (2) If extant, the process's process keyring is searched. + 2) If extant, the process's process keyring is searched. - (3) The process's session keyring is searched. + 3) The process's session keyring is searched. - (4) If the process has assumed the authority associated with a request_key() + 4) If the process has assumed the authority associated with a request_key() authorisation key then: - (a) If extant, the calling process's thread keyring is searched. + a) If extant, the calling process's thread keyring is searched. - (b) If extant, the calling process's process keyring is searched. + b) If extant, the calling process's process keyring is searched. - (c) The calling process's session keyring is searched. + c) The calling process's session keyring is searched. The moment one succeeds, all pending errors are discarded and the found key is returned. @@ -194,7 +191,7 @@ returned. Only if all these fail does the whole thing fail with the highest priority error. Note that several errors may have come from LSM. -The error priority is: +The error priority is:: EKEYREVOKED > EKEYEXPIRED > ENOKEY diff --git a/Documentation/security/keys-trusted-encrypted.txt b/Documentation/security/keys/trusted-encrypted.rst similarity index 93% rename from Documentation/security/keys-trusted-encrypted.txt rename to Documentation/security/keys/trusted-encrypted.rst index b20a993a32afde..7b503831bdeaf0 100644 --- a/Documentation/security/keys-trusted-encrypted.txt +++ b/Documentation/security/keys/trusted-encrypted.rst @@ -1,4 +1,6 @@ - Trusted and Encrypted Keys +========================== +Trusted and Encrypted Keys +========================== Trusted and Encrypted Keys are two new key types added to the existing kernel key ring service. Both of these new types are variable length symmetric keys, @@ -20,7 +22,8 @@ By default, trusted keys are sealed under the SRK, which has the default authorization value (20 zeros). This can be set at takeownership time with the trouser's utility: "tpm_takeownership -u -z". -Usage: +Usage:: + keyctl add trusted name "new keylen [options]" ring keyctl add trusted name "load hex_blob [pcrlock=pcrnum]" ring keyctl update key "update [options]" @@ -64,19 +67,22 @@ The decrypted portion of encrypted keys can contain either a simple symmetric key or a more complex structure. The format of the more complex structure is application specific, which is identified by 'format'. -Usage: +Usage:: + keyctl add encrypted name "new [format] key-type:master-key-name keylen" ring keyctl add encrypted name "load hex_blob" ring keyctl update keyid "update key-type:master-key-name" -format:= 'default | ecryptfs' -key-type:= 'trusted' | 'user' +Where:: + + format:= 'default | ecryptfs' + key-type:= 'trusted' | 'user' Examples of trusted and encrypted key usage: -Create and save a trusted key named "kmk" of length 32 bytes: +Create and save a trusted key named "kmk" of length 32 bytes:: $ keyctl add trusted kmk "new 32" @u 440502848 @@ -99,7 +105,7 @@ Create and save a trusted key named "kmk" of length 32 bytes: $ keyctl pipe 440502848 > kmk.blob -Load a trusted key from the saved blob: +Load a trusted key from the saved blob:: $ keyctl add trusted kmk "load `cat kmk.blob`" @u 268728824 @@ -114,7 +120,7 @@ Load a trusted key from the saved blob: f1f8fff03ad0acb083725535636addb08d73dedb9832da198081e5deae84bfaf0409c22b e4a8aea2b607ec96931e6f4d4fe563ba -Reseal a trusted key under new pcr values: +Reseal a trusted key under new pcr values:: $ keyctl update 268728824 "update pcrinfo=`cat pcr.blob`" $ keyctl print 268728824 @@ -135,11 +141,13 @@ compromised by a user level problem, and when sealed to specific boot PCR values, protects against boot and offline attacks. Create and save an encrypted key "evm" using the above trusted key "kmk": -option 1: omitting 'format' +option 1: omitting 'format':: + $ keyctl add encrypted evm "new trusted:kmk 32" @u 159771175 -option 2: explicitly defining 'format' as 'default' +option 2: explicitly defining 'format' as 'default':: + $ keyctl add encrypted evm "new default trusted:kmk 32" @u 159771175 @@ -150,7 +158,7 @@ option 2: explicitly defining 'format' as 'default' $ keyctl pipe 159771175 > evm.blob -Load an encrypted key "evm" from saved blob: +Load an encrypted key "evm" from saved blob:: $ keyctl add encrypted evm "load `cat evm.blob`" @u 831684262 @@ -164,4 +172,4 @@ Other uses for trusted and encrypted keys, such as for disk and file encryption are anticipated. In particular the new format 'ecryptfs' has been defined in in order to use encrypted keys to mount an eCryptfs filesystem. More details about the usage can be found in the file -'Documentation/security/keys-ecryptfs.txt'. +``Documentation/security/keys-ecryptfs.txt``. diff --git a/Documentation/security/self-protection.txt b/Documentation/security/self-protection.rst similarity index 83% rename from Documentation/security/self-protection.txt rename to Documentation/security/self-protection.rst index 141acfebe6ef16..60c8bd8b77bf2f 100644 --- a/Documentation/security/self-protection.txt +++ b/Documentation/security/self-protection.rst @@ -1,4 +1,6 @@ -# Kernel Self-Protection +====================== +Kernel Self-Protection +====================== Kernel self-protection is the design and implementation of systems and structures within the Linux kernel to protect against security flaws in @@ -26,7 +28,8 @@ mentioning them, since these aspects need to be explored, dealt with, and/or accepted. -## Attack Surface Reduction +Attack Surface Reduction +======================== The most fundamental defense against security exploits is to reduce the areas of the kernel that can be used to redirect execution. This ranges @@ -34,13 +37,15 @@ from limiting the exposed APIs available to userspace, making in-kernel APIs hard to use incorrectly, minimizing the areas of writable kernel memory, etc. -### Strict kernel memory permissions +Strict kernel memory permissions +-------------------------------- When all of kernel memory is writable, it becomes trivial for attacks to redirect execution flow. To reduce the availability of these targets the kernel needs to protect its memory with a tight set of permissions. -#### Executable code and read-only data must not be writable +Executable code and read-only data must not be writable +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Any areas of the kernel with executable memory must not be writable. While this obviously includes the kernel text itself, we must consider @@ -51,18 +56,19 @@ kernel, they are implemented in a way where the memory is temporarily made writable during the update, and then returned to the original permissions.) -In support of this are CONFIG_STRICT_KERNEL_RWX and -CONFIG_STRICT_MODULE_RWX, which seek to make sure that code is not +In support of this are ``CONFIG_STRICT_KERNEL_RWX`` and +``CONFIG_STRICT_MODULE_RWX``, which seek to make sure that code is not writable, data is not executable, and read-only data is neither writable nor executable. Most architectures have these options on by default and not user selectable. For some architectures like arm that wish to have these be selectable, the architecture Kconfig can select ARCH_OPTIONAL_KERNEL_RWX to enable -a Kconfig prompt. CONFIG_ARCH_OPTIONAL_KERNEL_RWX_DEFAULT determines +a Kconfig prompt. ``CONFIG_ARCH_OPTIONAL_KERNEL_RWX_DEFAULT`` determines the default setting when ARCH_OPTIONAL_KERNEL_RWX is enabled. -#### Function pointers and sensitive variables must not be writable +Function pointers and sensitive variables must not be writable +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Vast areas of kernel memory contain function pointers that are looked up by the kernel and used to continue execution (e.g. descriptor/vector @@ -74,8 +80,8 @@ so that they live in the .rodata section instead of the .data section of the kernel, gaining the protection of the kernel's strict memory permissions as described above. -For variables that are initialized once at __init time, these can -be marked with the (new and under development) __ro_after_init +For variables that are initialized once at ``__init`` time, these can +be marked with the (new and under development) ``__ro_after_init`` attribute. What remains are variables that are updated rarely (e.g. GDT). These @@ -85,7 +91,8 @@ of their lifetime read-only. (For example, when being updated, only the CPU thread performing the update would be given uninterruptible write access to the memory.) -#### Segregation of kernel memory from userspace memory +Segregation of kernel memory from userspace memory +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The kernel must never execute userspace memory. The kernel must also never access userspace memory without explicit expectation to do so. These @@ -95,10 +102,11 @@ By blocking userspace memory in this way, execution and data parsing cannot be passed to trivially-controlled userspace memory, forcing attacks to operate entirely in kernel memory. -### Reduced access to syscalls +Reduced access to syscalls +-------------------------- One trivial way to eliminate many syscalls for 64-bit systems is building -without CONFIG_COMPAT. However, this is rarely a feasible scenario. +without ``CONFIG_COMPAT``. However, this is rarely a feasible scenario. The "seccomp" system provides an opt-in feature made available to userspace, which provides a way to reduce the number of kernel entry @@ -112,7 +120,8 @@ to trusted processes. This would keep the scope of kernel entry points restricted to the more regular set of normally available to unprivileged userspace. -### Restricting access to kernel modules +Restricting access to kernel modules +------------------------------------ The kernel should never allow an unprivileged user the ability to load specific kernel modules, since that would provide a facility to @@ -127,11 +136,12 @@ for debate in some scenarios.) To protect against even privileged users, systems may need to either disable module loading entirely (e.g. monolithic kernel builds or modules_disabled sysctl), or provide signed modules (e.g. -CONFIG_MODULE_SIG_FORCE, or dm-crypt with LoadPin), to keep from having +``CONFIG_MODULE_SIG_FORCE``, or dm-crypt with LoadPin), to keep from having root load arbitrary kernel code via the module loader interface. -## Memory integrity +Memory integrity +================ There are many memory structures in the kernel that are regularly abused to gain execution control during an attack, By far the most commonly @@ -139,16 +149,18 @@ understood is that of the stack buffer overflow in which the return address stored on the stack is overwritten. Many other examples of this kind of attack exist, and protections exist to defend against them. -### Stack buffer overflow +Stack buffer overflow +--------------------- The classic stack buffer overflow involves writing past the expected end of a variable stored on the stack, ultimately writing a controlled value to the stack frame's stored return address. The most widely used defense is the presence of a stack canary between the stack variables and the -return address (CONFIG_CC_STACKPROTECTOR), which is verified just before +return address (``CONFIG_CC_STACKPROTECTOR``), which is verified just before the function returns. Other defenses include things like shadow stacks. -### Stack depth overflow +Stack depth overflow +-------------------- A less well understood attack is using a bug that triggers the kernel to consume stack memory with deep function calls or large stack @@ -158,27 +170,31 @@ important changes need to be made for better protections: moving the sensitive thread_info structure elsewhere, and adding a faulting memory hole at the bottom of the stack to catch these overflows. -### Heap memory integrity +Heap memory integrity +--------------------- The structures used to track heap free lists can be sanity-checked during allocation and freeing to make sure they aren't being used to manipulate other memory areas. -### Counter integrity +Counter integrity +----------------- Many places in the kernel use atomic counters to track object references or perform similar lifetime management. When these counters can be made to wrap (over or under) this traditionally exposes a use-after-free flaw. By trapping atomic wrapping, this class of bug vanishes. -### Size calculation overflow detection +Size calculation overflow detection +----------------------------------- Similar to counter overflow, integer overflows (usually size calculations) need to be detected at runtime to kill this class of bug, which traditionally leads to being able to write past the end of kernel buffers. -## Statistical defenses +Probabilistic defenses +====================== While many protections can be considered deterministic (e.g. read-only memory cannot be written to), some protections provide only statistical @@ -186,7 +202,8 @@ defense, in that an attack must gather enough information about a running system to overcome the defense. While not perfect, these do provide meaningful defenses. -### Canaries, blinding, and other secrets +Canaries, blinding, and other secrets +------------------------------------- It should be noted that things like the stack canary discussed earlier are technically statistical defenses, since they rely on a secret value, @@ -201,7 +218,8 @@ It is critical that the secret values used must be separate (e.g. different canary per stack) and high entropy (e.g. is the RNG actually working?) in order to maximize their success. -### Kernel Address Space Layout Randomization (KASLR) +Kernel Address Space Layout Randomization (KASLR) +------------------------------------------------- Since the location of kernel memory is almost always instrumental in mounting a successful attack, making the location non-deterministic @@ -209,22 +227,25 @@ raises the difficulty of an exploit. (Note that this in turn makes the value of information exposures higher, since they may be used to discover desired memory locations.) -#### Text and module base +Text and module base +~~~~~~~~~~~~~~~~~~~~ By relocating the physical and virtual base address of the kernel at -boot-time (CONFIG_RANDOMIZE_BASE), attacks needing kernel code will be +boot-time (``CONFIG_RANDOMIZE_BASE``), attacks needing kernel code will be frustrated. Additionally, offsetting the module loading base address means that even systems that load the same set of modules in the same order every boot will not share a common base address with the rest of the kernel text. -#### Stack base +Stack base +~~~~~~~~~~ If the base address of the kernel stack is not the same between processes, or even not the same between syscalls, targets on or beyond the stack become more difficult to locate. -#### Dynamic memory base +Dynamic memory base +~~~~~~~~~~~~~~~~~~~ Much of the kernel's dynamic memory (e.g. kmalloc, vmalloc, etc) ends up being relatively deterministic in layout due to the order of early-boot @@ -232,7 +253,8 @@ initializations. If the base address of these areas is not the same between boots, targeting them is frustrated, requiring an information exposure specific to the region. -#### Structure layout +Structure layout +~~~~~~~~~~~~~~~~ By performing a per-build randomization of the layout of sensitive structures, attacks must either be tuned to known kernel builds or expose @@ -240,26 +262,30 @@ enough kernel memory to determine structure layouts before manipulating them. -## Preventing Information Exposures +Preventing Information Exposures +================================ Since the locations of sensitive structures are the primary target for attacks, it is important to defend against exposure of both kernel memory addresses and kernel memory contents (since they may contain kernel addresses or other sensitive things like canary values). -### Unique identifiers +Unique identifiers +------------------ Kernel memory addresses must never be used as identifiers exposed to userspace. Instead, use an atomic counter, an idr, or similar unique identifier. -### Memory initialization +Memory initialization +--------------------- Memory copied to userspace must always be fully initialized. If not explicitly memset(), this will require changes to the compiler to make sure structure holes are cleared. -### Memory poisoning +Memory poisoning +---------------- When releasing memory, it is best to poison the contents (clear stack on syscall return, wipe heap memory on a free), to avoid reuse attacks that @@ -267,9 +293,10 @@ rely on the old contents of memory. This frustrates many uninitialized variable attacks, stack content exposures, heap content exposures, and use-after-free attacks. -### Destination tracking +Destination tracking +-------------------- To help kill classes of bugs that result in kernel addresses being written to userspace, the destination of writes needs to be tracked. If -the buffer is destined for userspace (e.g. seq_file backed /proc files), +the buffer is destined for userspace (e.g. seq_file backed ``/proc`` files), it should automatically censor sensitive values. diff --git a/Documentation/sh/conf.py b/Documentation/sh/conf.py new file mode 100644 index 00000000000000..1eb684a13ac8ac --- /dev/null +++ b/Documentation/sh/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "SuperH architecture implementation manual" + +tags.add("subproject") + +latex_documents = [ + ('index', 'sh.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/sh/index.rst b/Documentation/sh/index.rst new file mode 100644 index 00000000000000..bc8db7ba894aea --- /dev/null +++ b/Documentation/sh/index.rst @@ -0,0 +1,59 @@ +======================= +SuperH Interfaces Guide +======================= + +:Author: Paul Mundt + +Memory Management +================= + +SH-4 +---- + +Store Queue API +~~~~~~~~~~~~~~~ + +.. kernel-doc:: arch/sh/kernel/cpu/sh4/sq.c + :export: + +SH-5 +---- + +TLB Interfaces +~~~~~~~~~~~~~~ + +.. kernel-doc:: arch/sh/mm/tlb-sh5.c + :internal: + +.. kernel-doc:: arch/sh/include/asm/tlb_64.h + :internal: + +Machine Specific Interfaces +=========================== + +mach-dreamcast +-------------- + +.. kernel-doc:: arch/sh/boards/mach-dreamcast/rtc.c + :internal: + +mach-x3proto +------------ + +.. kernel-doc:: arch/sh/boards/mach-x3proto/ilsel.c + :export: + +Busses +====== + +SuperHyway +---------- + +.. kernel-doc:: drivers/sh/superhyway/superhyway.c + :export: + +Maple +----- + +.. kernel-doc:: drivers/sh/maple/maple.c + :export: diff --git a/Documentation/sound/conf.py b/Documentation/sound/conf.py new file mode 100644 index 00000000000000..3f1fc5e74e7b23 --- /dev/null +++ b/Documentation/sound/conf.py @@ -0,0 +1,10 @@ +# -*- coding: utf-8; mode: python -*- + +project = "Linux Sound Subsystem Documentation" + +tags.add("subproject") + +latex_documents = [ + ('index', 'sound.tex', project, + 'The kernel development community', 'manual'), +] diff --git a/Documentation/sphinx/tmplcvt b/Documentation/sphinx/tmplcvt deleted file mode 100755 index 6848f0a26fa543..00000000000000 --- a/Documentation/sphinx/tmplcvt +++ /dev/null @@ -1,28 +0,0 @@ -#!/bin/bash -# -# Convert a template file into something like RST -# -# fix -# feed to pandoc -# fix \_ -# title line? -# -set -eu - -if [ "$#" != "2" ]; then - echo "$0 " - exit -fi - -DIR=$(dirname $0) - -in=$1 -rst=$2 -tmp=$rst.tmp - -cp $in $tmp -sed --in-place -f $DIR/convert_template.sed $tmp -pandoc -s -S -f docbook -t rst -o $rst $tmp -sed --in-place -f $DIR/post_convert.sed $rst -rm $tmp -echo "book writen to $rst" diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary index d1824b399b2d1d..1721c1b570c324 100644 --- a/Documentation/spi/spi-summary +++ b/Documentation/spi/spi-summary @@ -62,8 +62,8 @@ chips described as using "three wire" signaling: SCK, data, nCSx. (That data line is sometimes called MOMI or SISO.) Microcontrollers often support both master and slave sides of the SPI -protocol. This document (and Linux) currently only supports the master -side of SPI interactions. +protocol. This document (and Linux) supports both the master and slave +sides of SPI interactions. Who uses it? On what kinds of systems? @@ -154,9 +154,8 @@ control audio interfaces, present touchscreen sensors as input interfaces, or monitor temperature and voltage levels during industrial processing. And those might all be sharing the same controller driver. -A "struct spi_device" encapsulates the master-side interface between -those two types of driver. At this writing, Linux has no slave side -programming interface. +A "struct spi_device" encapsulates the controller-side interface between +those two types of drivers. There is a minimal core of SPI programming interfaces, focussing on using the driver model to connect controller and protocol drivers using @@ -177,10 +176,24 @@ shows up in sysfs in several locations: /sys/bus/spi/drivers/D ... driver for one or more spi*.* devices /sys/class/spi_master/spiB ... symlink (or actual device node) to - a logical node which could hold class related state for the - controller managing bus "B". All spiB.* devices share one + a logical node which could hold class related state for the SPI + master controller managing bus "B". All spiB.* devices share one physical SPI bus segment, with SCLK, MOSI, and MISO. + /sys/devices/.../CTLR/slave ... virtual file for (un)registering the + slave device for an SPI slave controller. + Writing the driver name of an SPI slave handler to this file + registers the slave device; writing "(null)" unregisters the slave + device. + Reading from this file shows the name of the slave device ("(null)" + if not registered). + + /sys/class/spi_slave/spiB ... symlink (or actual device node) to + a logical node which could hold class related state for the SPI + slave controller on bus "B". When registered, a single spiB.* + device is present here, possible sharing the physical SPI bus + segment with other SPI slave devices. + Note that the actual location of the controller's class state depends on whether you enabled CONFIG_SYSFS_DEPRECATED or not. At this time, the only class-specific state is the bus number ("B" in "spiB"), so diff --git a/Documentation/sync_file.txt b/Documentation/sync_file.txt index c3d033a06e8d2d..496fb2c3b3e6a7 100644 --- a/Documentation/sync_file.txt +++ b/Documentation/sync_file.txt @@ -1,8 +1,8 @@ - Sync File API Guide - ~~~~~~~~~~~~~~~~~~~ +=================== +Sync File API Guide +=================== - Gustavo Padovan - +:Author: Gustavo Padovan This document serves as a guide for device drivers writers on what the sync_file API is, and how drivers can support it. Sync file is the carrier of @@ -46,16 +46,17 @@ Creating Sync Files When a driver needs to send an out-fence userspace it creates a sync_file. -Interface: +Interface:: + struct sync_file *sync_file_create(struct dma_fence *fence); The caller pass the out-fence and gets back the sync_file. That is just the first step, next it needs to install an fd on sync_file->file. So it gets an -fd: +fd:: fd = get_unused_fd_flags(O_CLOEXEC); -and installs it on sync_file->file: +and installs it on sync_file->file:: fd_install(fd, sync_file->file); @@ -71,7 +72,8 @@ When userspace needs to send an in-fence to the driver it passes file descriptor of the Sync File to the kernel. The kernel can then retrieve the fences from it. -Interface: +Interface:: + struct dma_fence *sync_file_get_fence(int fd); @@ -79,5 +81,6 @@ The returned reference is owned by the caller and must be disposed of afterwards using dma_fence_put(). In case of error, a NULL is returned instead. References: -[1] struct sync_file in include/linux/sync_file.h -[2] All interfaces mentioned above defined in include/linux/sync_file.h + +1. struct sync_file in include/linux/sync_file.h +2. All interfaces mentioned above defined in include/linux/sync_file.h diff --git a/Documentation/timers/NO_HZ.txt b/Documentation/timers/NO_HZ.txt index 6eaf576294f3bb..2dcaf9adb7a75d 100644 --- a/Documentation/timers/NO_HZ.txt +++ b/Documentation/timers/NO_HZ.txt @@ -194,32 +194,9 @@ that the RCU callbacks are processed in a timely fashion. Another approach is to offload RCU callback processing to "rcuo" kthreads using the CONFIG_RCU_NOCB_CPU=y Kconfig option. The specific CPUs to -offload may be selected via several methods: - -1. One of three mutually exclusive Kconfig options specify a - build-time default for the CPUs to offload: - - a. The CONFIG_RCU_NOCB_CPU_NONE=y Kconfig option results in - no CPUs being offloaded. - - b. The CONFIG_RCU_NOCB_CPU_ZERO=y Kconfig option causes - CPU 0 to be offloaded. - - c. The CONFIG_RCU_NOCB_CPU_ALL=y Kconfig option causes all - CPUs to be offloaded. Note that the callbacks will be - offloaded to "rcuo" kthreads, and that those kthreads - will in fact run on some CPU. However, this approach - gives fine-grained control on exactly which CPUs the - callbacks run on, along with their scheduling priority - (including the default of SCHED_OTHER), and it further - allows this control to be varied dynamically at runtime. - -2. The "rcu_nocbs=" kernel boot parameter, which takes a comma-separated - list of CPUs and CPU ranges, for example, "1,3-5" selects CPUs 1, - 3, 4, and 5. The specified CPUs will be offloaded in addition to - any CPUs specified as offloaded by CONFIG_RCU_NOCB_CPU_ZERO=y or - CONFIG_RCU_NOCB_CPU_ALL=y. This means that the "rcu_nocbs=" boot - parameter has no effect for kernels built with RCU_NOCB_CPU_ALL=y. +offload may be selected using The "rcu_nocbs=" kernel boot parameter, +which takes a comma-separated list of CPUs and CPU ranges, for example, +"1,3-5" selects CPUs 1, 3, 4, and 5. The offloaded CPUs will never queue RCU callbacks, and therefore RCU never prevents offloaded CPUs from entering either dyntick-idle mode diff --git a/Documentation/trace/coresight-cpu-debug.txt b/Documentation/trace/coresight-cpu-debug.txt new file mode 100644 index 00000000000000..b3da1f90b8618e --- /dev/null +++ b/Documentation/trace/coresight-cpu-debug.txt @@ -0,0 +1,175 @@ + Coresight CPU Debug Module + ========================== + + Author: Leo Yan + Date: April 5th, 2017 + +Introduction +------------ + +Coresight CPU debug module is defined in ARMv8-a architecture reference manual +(ARM DDI 0487A.k) Chapter 'Part H: External debug', the CPU can integrate +debug module and it is mainly used for two modes: self-hosted debug and +external debug. Usually the external debug mode is well known as the external +debugger connects with SoC from JTAG port; on the other hand the program can +explore debugging method which rely on self-hosted debug mode, this document +is to focus on this part. + +The debug module provides sample-based profiling extension, which can be used +to sample CPU program counter, secure state and exception level, etc; usually +every CPU has one dedicated debug module to be connected. Based on self-hosted +debug mechanism, Linux kernel can access these related registers from mmio +region when the kernel panic happens. The callback notifier for kernel panic +will dump related registers for every CPU; finally this is good for assistant +analysis for panic. + + +Implementation +-------------- + +- During driver registration, it uses EDDEVID and EDDEVID1 - two device ID + registers to decide if sample-based profiling is implemented or not. On some + platforms this hardware feature is fully or partially implemented; and if + this feature is not supported then registration will fail. + +- At the time this documentation was written, the debug driver mainly relies on + information gathered by the kernel panic callback notifier from three + sampling registers: EDPCSR, EDVIDSR and EDCIDSR: from EDPCSR we can get + program counter; EDVIDSR has information for secure state, exception level, + bit width, etc; EDCIDSR is context ID value which contains the sampled value + of CONTEXTIDR_EL1. + +- The driver supports a CPU running in either AArch64 or AArch32 mode. The + registers naming convention is a bit different between them, AArch64 uses + 'ED' for register prefix (ARM DDI 0487A.k, chapter H9.1) and AArch32 uses + 'DBG' as prefix (ARM DDI 0487A.k, chapter G5.1). The driver is unified to + use AArch64 naming convention. + +- ARMv8-a (ARM DDI 0487A.k) and ARMv7-a (ARM DDI 0406C.b) have different + register bits definition. So the driver consolidates two difference: + + If PCSROffset=0b0000, on ARMv8-a the feature of EDPCSR is not implemented; + but ARMv7-a defines "PCSR samples are offset by a value that depends on the + instruction set state". For ARMv7-a, the driver checks furthermore if CPU + runs with ARM or thumb instruction set and calibrate PCSR value, the + detailed description for offset is in ARMv7-a ARM (ARM DDI 0406C.b) chapter + C11.11.34 "DBGPCSR, Program Counter Sampling Register". + + If PCSROffset=0b0010, ARMv8-a defines "EDPCSR implemented, and samples have + no offset applied and do not sample the instruction set state in AArch32 + state". So on ARMv8 if EDDEVID1.PCSROffset is 0b0010 and the CPU operates + in AArch32 state, EDPCSR is not sampled; when the CPU operates in AArch64 + state EDPCSR is sampled and no offset are applied. + + +Clock and power domain +---------------------- + +Before accessing debug registers, we should ensure the clock and power domain +have been enabled properly. In ARMv8-a ARM (ARM DDI 0487A.k) chapter 'H9.1 +Debug registers', the debug registers are spread into two domains: the debug +domain and the CPU domain. + + +---------------+ + | | + | | + +----------+--+ | + dbg_clock -->| |**| |<-- cpu_clock + | Debug |**| CPU | + dbg_power_domain -->| |**| |<-- cpu_power_domain + +----------+--+ | + | | + | | + +---------------+ + +For debug domain, the user uses DT binding "clocks" and "power-domains" to +specify the corresponding clock source and power supply for the debug logic. +The driver calls the pm_runtime_{put|get} operations as needed to handle the +debug power domain. + +For CPU domain, the different SoC designs have different power management +schemes and finally this heavily impacts external debug module. So we can +divide into below cases: + +- On systems with a sane power controller which can behave correctly with + respect to CPU power domain, the CPU power domain can be controlled by + register EDPRCR in driver. The driver firstly writes bit EDPRCR.COREPURQ + to power up the CPU, and then writes bit EDPRCR.CORENPDRQ for emulation + of CPU power down. As result, this can ensure the CPU power domain is + powered on properly during the period when access debug related registers; + +- Some designs will power down an entire cluster if all CPUs on the cluster + are powered down - including the parts of the debug registers that should + remain powered in the debug power domain. The bits in EDPRCR are not + respected in these cases, so these designs do not support debug over + power down in the way that the CoreSight / Debug designers anticipated. + This means that even checking EDPRSR has the potential to cause a bus hang + if the target register is unpowered. + + In this case, accessing to the debug registers while they are not powered + is a recipe for disaster; so we need preventing CPU low power states at boot + time or when user enable module at the run time. Please see chapter + "How to use the module" for detailed usage info for this. + + +Device Tree Bindings +-------------------- + +See Documentation/devicetree/bindings/arm/coresight-cpu-debug.txt for details. + + +How to use the module +--------------------- + +If you want to enable debugging functionality at boot time, you can add +"coresight_cpu_debug.enable=1" to the kernel command line parameter. + +The driver also can work as module, so can enable the debugging when insmod +module: +# insmod coresight_cpu_debug.ko debug=1 + +When boot time or insmod module you have not enabled the debugging, the driver +uses the debugfs file system to provide a knob to dynamically enable or disable +debugging: + +To enable it, write a '1' into /sys/kernel/debug/coresight_cpu_debug/enable: +# echo 1 > /sys/kernel/debug/coresight_cpu_debug/enable + +To disable it, write a '0' into /sys/kernel/debug/coresight_cpu_debug/enable: +# echo 0 > /sys/kernel/debug/coresight_cpu_debug/enable + +As explained in chapter "Clock and power domain", if you are working on one +platform which has idle states to power off debug logic and the power +controller cannot work well for the request from EDPRCR, then you should +firstly constraint CPU idle states before enable CPU debugging feature; so can +ensure the accessing to debug logic. + +If you want to limit idle states at boot time, you can use "nohlt" or +"cpuidle.off=1" in the kernel command line. + +At the runtime you can disable idle states with below methods: + +Set latency request to /dev/cpu_dma_latency to disable all CPUs specific idle +states (if latency = 0uS then disable all idle states): +# echo "what_ever_latency_you_need_in_uS" > /dev/cpu_dma_latency + +Disable specific CPU's specific idle state: +# echo 1 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$state/disable + + +Output format +------------- + +Here is an example of the debugging output format: + +ARM external debug module: +coresight-cpu-debug 850000.debug: CPU[0]: +coresight-cpu-debug 850000.debug: EDPRSR: 00000001 (Power:On DLK:Unlock) +coresight-cpu-debug 850000.debug: EDPCSR: [] handle_IPI+0x174/0x1d8 +coresight-cpu-debug 850000.debug: EDCIDSR: 00000000 +coresight-cpu-debug 850000.debug: EDVIDSR: 90000000 (State:Non-secure Mode:EL1/0 Width:64bits VMID:0) +coresight-cpu-debug 852000.debug: CPU[1]: +coresight-cpu-debug 852000.debug: EDPRSR: 00000001 (Power:On DLK:Unlock) +coresight-cpu-debug 852000.debug: EDPCSR: [] debug_notifier_call+0x23c/0x358 +coresight-cpu-debug 852000.debug: EDCIDSR: 00000000 +coresight-cpu-debug 852000.debug: EDVIDSR: 90000000 (State:Non-secure Mode:EL1/0 Width:64bits VMID:0) diff --git a/Documentation/translations/ja_JP/howto.rst b/Documentation/translations/ja_JP/howto.rst index 4511eed0fabb5f..8d7ed0cbbf5fb7 100644 --- a/Documentation/translations/ja_JP/howto.rst +++ b/Documentation/translations/ja_JP/howto.rst @@ -197,13 +197,6 @@ ReSTマークアップを使ったドキュメントは Documentation/outputに make latexdocs make epubdocs -現在、幾つかの DocBook形式で書かれたドキュメントは ReST形式に転換中で -す。それらのドキュメントはDocumentation/DocBook ディレクトリに生成され、 -Postscript または man ページの形式を生成するには以下のようにします - :: - - make psdocs - make mandocs - カーネル開発者になるには ------------------------ diff --git a/Documentation/translations/ko_KR/howto.rst b/Documentation/translations/ko_KR/howto.rst index 2333697251ddeb..f06de9ca41a40a 100644 --- a/Documentation/translations/ko_KR/howto.rst +++ b/Documentation/translations/ko_KR/howto.rst @@ -191,13 +191,6 @@ ReST 마크업을 사용하는 문서들은 Documentation/output 에 생성된 make latexdocs make epubdocs -현재, ReST 로의 변환이 진행중인, DocBook 으로 쓰인 문서들이 존재한다. 그런 -문서들은 Documentation/DocBook/ 디렉토리 안에 생성될 것이고 다음 커맨드를 통해 -Postscript 나 man page 로도 만들어질 수 있다:: - - make psdocs - make mandocs - 커널 개발자가 되는 것 --------------------- diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index a9d01b44a6594e..7b2eb1b7d4cab3 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -16,6 +16,8 @@ place where this information is gathered. .. toctree:: :maxdepth: 2 + no_new_privs + seccomp_filter unshare .. only:: subproject and html diff --git a/Documentation/prctl/no_new_privs.txt b/Documentation/userspace-api/no_new_privs.rst similarity index 54% rename from Documentation/prctl/no_new_privs.txt rename to Documentation/userspace-api/no_new_privs.rst index f7be84fba9105c..d060ea217ea1cc 100644 --- a/Documentation/prctl/no_new_privs.txt +++ b/Documentation/userspace-api/no_new_privs.rst @@ -1,3 +1,7 @@ +====================== +No New Privileges Flag +====================== + The execve system call can grant a newly-started program privileges that its parent did not have. The most obvious examples are setuid/setgid programs and file capabilities. To prevent the parent program from @@ -5,53 +9,55 @@ gaining these privileges as well, the kernel and user code must be careful to prevent the parent from doing anything that could subvert the child. For example: - - The dynamic loader handles LD_* environment variables differently if + - The dynamic loader handles ``LD_*`` environment variables differently if a program is setuid. - chroot is disallowed to unprivileged processes, since it would allow - /etc/passwd to be replaced from the point of view of a process that + ``/etc/passwd`` to be replaced from the point of view of a process that inherited chroot. - The exec code has special handling for ptrace. -These are all ad-hoc fixes. The no_new_privs bit (since Linux 3.5) is a +These are all ad-hoc fixes. The ``no_new_privs`` bit (since Linux 3.5) is a new, generic mechanism to make it safe for a process to modify its execution environment in a manner that persists across execve. Any task -can set no_new_privs. Once the bit is set, it is inherited across fork, -clone, and execve and cannot be unset. With no_new_privs set, execve +can set ``no_new_privs``. Once the bit is set, it is inherited across fork, +clone, and execve and cannot be unset. With ``no_new_privs`` set, ``execve()`` promises not to grant the privilege to do anything that could not have been done without the execve call. For example, the setuid and setgid bits will no longer change the uid or gid; file capabilities will not add to the permitted set, and LSMs will not relax constraints after execve. -To set no_new_privs, use prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0). +To set ``no_new_privs``, use:: + + prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); Be careful, though: LSMs might also not tighten constraints on exec -in no_new_privs mode. (This means that setting up a general-purpose -service launcher to set no_new_privs before execing daemons may +in ``no_new_privs`` mode. (This means that setting up a general-purpose +service launcher to set ``no_new_privs`` before execing daemons may interfere with LSM-based sandboxing.) -Note that no_new_privs does not prevent privilege changes that do not -involve execve. An appropriately privileged task can still call -setuid(2) and receive SCM_RIGHTS datagrams. +Note that ``no_new_privs`` does not prevent privilege changes that do not +involve ``execve()``. An appropriately privileged task can still call +``setuid(2)`` and receive SCM_RIGHTS datagrams. -There are two main use cases for no_new_privs so far: +There are two main use cases for ``no_new_privs`` so far: - Filters installed for the seccomp mode 2 sandbox persist across execve and can change the behavior of newly-executed programs. Unprivileged users are therefore only allowed to install such filters - if no_new_privs is set. + if ``no_new_privs`` is set. - - By itself, no_new_privs can be used to reduce the attack surface + - By itself, ``no_new_privs`` can be used to reduce the attack surface available to an unprivileged user. If everything running with a - given uid has no_new_privs set, then that uid will be unable to + given uid has ``no_new_privs`` set, then that uid will be unable to escalate its privileges by directly attacking setuid, setgid, and fcap-using binaries; it will need to compromise something without the - no_new_privs bit set first. + ``no_new_privs`` bit set first. In the future, other potentially dangerous kernel features could become -available to unprivileged tasks if no_new_privs is set. In principle, -several options to unshare(2) and clone(2) would be safe when -no_new_privs is set, and no_new_privs + chroot is considerable less +available to unprivileged tasks if ``no_new_privs`` is set. In principle, +several options to ``unshare(2)`` and ``clone(2)`` would be safe when +``no_new_privs`` is set, and ``no_new_privs`` + ``chroot`` is considerable less dangerous than chroot by itself. diff --git a/Documentation/prctl/seccomp_filter.txt b/Documentation/userspace-api/seccomp_filter.rst similarity index 71% rename from Documentation/prctl/seccomp_filter.txt rename to Documentation/userspace-api/seccomp_filter.rst index 1e469ef7577835..f71eb5ef1f2df4 100644 --- a/Documentation/prctl/seccomp_filter.txt +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -1,8 +1,9 @@ - SECure COMPuting with filters - ============================= +=========================================== +Seccomp BPF (SECure COMPuting with filters) +=========================================== Introduction ------------- +============ A large number of system calls are exposed to every userland process with many of them going unused for the entire lifetime of the process. @@ -27,7 +28,7 @@ pointers which constrains all filters to solely evaluating the system call arguments directly. What it isn't -------------- +============= System call filtering isn't a sandbox. It provides a clearly defined mechanism for minimizing the exposed kernel surface. It is meant to be @@ -40,13 +41,13 @@ system calls in socketcall() is allowed, for instance) which could be construed, incorrectly, as a more complete sandboxing solution. Usage ------ +===== An additional seccomp mode is added and is enabled using the same prctl(2) call as the strict seccomp. If the architecture has -CONFIG_HAVE_ARCH_SECCOMP_FILTER, then filters may be added as below: +``CONFIG_HAVE_ARCH_SECCOMP_FILTER``, then filters may be added as below: -PR_SET_SECCOMP: +``PR_SET_SECCOMP``: Now takes an additional argument which specifies a new filter using a BPF program. The BPF program will be executed over struct seccomp_data @@ -55,24 +56,25 @@ PR_SET_SECCOMP: acceptable values to inform the kernel which action should be taken. - Usage: + Usage:: + prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, prog); The 'prog' argument is a pointer to a struct sock_fprog which will contain the filter program. If the program is invalid, the - call will return -1 and set errno to EINVAL. + call will return -1 and set errno to ``EINVAL``. - If fork/clone and execve are allowed by @prog, any child + If ``fork``/``clone`` and ``execve`` are allowed by @prog, any child processes will be constrained to the same filters and system call ABI as the parent. - Prior to use, the task must call prctl(PR_SET_NO_NEW_PRIVS, 1) or - run with CAP_SYS_ADMIN privileges in its namespace. If these are not - true, -EACCES will be returned. This requirement ensures that filter + Prior to use, the task must call ``prctl(PR_SET_NO_NEW_PRIVS, 1)`` or + run with ``CAP_SYS_ADMIN`` privileges in its namespace. If these are not + true, ``-EACCES`` will be returned. This requirement ensures that filter programs cannot be applied to child processes with greater privileges than the task that installed them. - Additionally, if prctl(2) is allowed by the attached filter, + Additionally, if ``prctl(2)`` is allowed by the attached filter, additional filters may be layered on which will increase evaluation time, but allow for further decreasing the attack surface during execution of a process. @@ -80,51 +82,52 @@ PR_SET_SECCOMP: The above call returns 0 on success and non-zero on error. Return values -------------- +============= + A seccomp filter may return any of the following values. If multiple filters exist, the return value for the evaluation of a given system call will always use the highest precedent value. (For example, -SECCOMP_RET_KILL will always take precedence.) +``SECCOMP_RET_KILL`` will always take precedence.) In precedence order, they are: -SECCOMP_RET_KILL: +``SECCOMP_RET_KILL``: Results in the task exiting immediately without executing the - system call. The exit status of the task (status & 0x7f) will - be SIGSYS, not SIGKILL. + system call. The exit status of the task (``status & 0x7f``) will + be ``SIGSYS``, not ``SIGKILL``. -SECCOMP_RET_TRAP: - Results in the kernel sending a SIGSYS signal to the triggering - task without executing the system call. siginfo->si_call_addr +``SECCOMP_RET_TRAP``: + Results in the kernel sending a ``SIGSYS`` signal to the triggering + task without executing the system call. ``siginfo->si_call_addr`` will show the address of the system call instruction, and - siginfo->si_syscall and siginfo->si_arch will indicate which + ``siginfo->si_syscall`` and ``siginfo->si_arch`` will indicate which syscall was attempted. The program counter will be as though the syscall happened (i.e. it will not point to the syscall instruction). The return value register will contain an arch- dependent value -- if resuming execution, set it to something sensible. (The architecture dependency is because replacing - it with -ENOSYS could overwrite some useful information.) + it with ``-ENOSYS`` could overwrite some useful information.) - The SECCOMP_RET_DATA portion of the return value will be passed - as si_errno. + The ``SECCOMP_RET_DATA`` portion of the return value will be passed + as ``si_errno``. - SIGSYS triggered by seccomp will have a si_code of SYS_SECCOMP. + ``SIGSYS`` triggered by seccomp will have a si_code of ``SYS_SECCOMP``. -SECCOMP_RET_ERRNO: +``SECCOMP_RET_ERRNO``: Results in the lower 16-bits of the return value being passed to userland as the errno without executing the system call. -SECCOMP_RET_TRACE: +``SECCOMP_RET_TRACE``: When returned, this value will cause the kernel to attempt to - notify a ptrace()-based tracer prior to executing the system - call. If there is no tracer present, -ENOSYS is returned to + notify a ``ptrace()``-based tracer prior to executing the system + call. If there is no tracer present, ``-ENOSYS`` is returned to userland and the system call is not executed. - A tracer will be notified if it requests PTRACE_O_TRACESECCOMP - using ptrace(PTRACE_SETOPTIONS). The tracer will be notified - of a PTRACE_EVENT_SECCOMP and the SECCOMP_RET_DATA portion of + A tracer will be notified if it requests ``PTRACE_O_TRACESECCOM``P + using ``ptrace(PTRACE_SETOPTIONS)``. The tracer will be notified + of a ``PTRACE_EVENT_SECCOMP`` and the ``SECCOMP_RET_DATA`` portion of the BPF program return value will be available to the tracer - via PTRACE_GETEVENTMSG. + via ``PTRACE_GETEVENTMSG``. The tracer can skip the system call by changing the syscall number to -1. Alternatively, the tracer can change the system call @@ -138,19 +141,19 @@ SECCOMP_RET_TRACE: allow use of ptrace, even of other sandboxed processes, without extreme care; ptracers can use this mechanism to escape.) -SECCOMP_RET_ALLOW: +``SECCOMP_RET_ALLOW``: Results in the system call being executed. If multiple filters exist, the return value for the evaluation of a given system call will always use the highest precedent value. -Precedence is only determined using the SECCOMP_RET_ACTION mask. When +Precedence is only determined using the ``SECCOMP_RET_ACTION`` mask. When multiple filters return values of the same precedence, only the -SECCOMP_RET_DATA from the most recently installed filter will be +``SECCOMP_RET_DATA`` from the most recently installed filter will be returned. Pitfalls --------- +======== The biggest pitfall to avoid during use is filtering on system call number without checking the architecture value. Why? On any @@ -160,39 +163,40 @@ the numbers in the different calling conventions overlap, then checks in the filters may be abused. Always check the arch value! Example -------- +======= -The samples/seccomp/ directory contains both an x86-specific example +The ``samples/seccomp/`` directory contains both an x86-specific example and a more generic example of a higher level macro interface for BPF program generation. Adding architecture support ------------------------ +=========================== -See arch/Kconfig for the authoritative requirements. In general, if an +See ``arch/Kconfig`` for the authoritative requirements. In general, if an architecture supports both ptrace_event and seccomp, it will be able to -support seccomp filter with minor fixup: SIGSYS support and seccomp return -value checking. Then it must just add CONFIG_HAVE_ARCH_SECCOMP_FILTER +support seccomp filter with minor fixup: ``SIGSYS`` support and seccomp return +value checking. Then it must just add ``CONFIG_HAVE_ARCH_SECCOMP_FILTER`` to its arch-specific Kconfig. Caveats -------- +======= The vDSO can cause some system calls to run entirely in userspace, leading to surprises when you run programs on different machines that fall back to real syscalls. To minimize these surprises on x86, make sure you test with -/sys/devices/system/clocksource/clocksource0/current_clocksource set to -something like acpi_pm. +``/sys/devices/system/clocksource/clocksource0/current_clocksource`` set to +something like ``acpi_pm``. On x86-64, vsyscall emulation is enabled by default. (vsyscalls are -legacy variants on vDSO calls.) Currently, emulated vsyscalls will honor seccomp, with a few oddities: +legacy variants on vDSO calls.) Currently, emulated vsyscalls will +honor seccomp, with a few oddities: -- A return value of SECCOMP_RET_TRAP will set a si_call_addr pointing to +- A return value of ``SECCOMP_RET_TRAP`` will set a ``si_call_addr`` pointing to the vsyscall entry for the given call and not the address after the 'syscall' instruction. Any code which wants to restart the call should be aware that (a) a ret instruction has been emulated and (b) @@ -200,7 +204,7 @@ legacy variants on vDSO calls.) Currently, emulated vsyscalls will honor seccom emulation security checks, making resuming the syscall mostly pointless. -- A return value of SECCOMP_RET_TRACE will signal the tracer as usual, +- A return value of ``SECCOMP_RET_TRACE`` will signal the tracer as usual, but the syscall may not be changed to another system call using the orig_rax register. It may only be changed to -1 order to skip the currently emulated call. Any other change MAY terminate the process. @@ -209,14 +213,14 @@ legacy variants on vDSO calls.) Currently, emulated vsyscalls will honor seccom rip or rsp. (Do not rely on other changes terminating the process. They might work. For example, on some kernels, choosing a syscall that only exists in future kernels will be correctly emulated (by - returning -ENOSYS). + returning ``-ENOSYS``). -To detect this quirky behavior, check for addr & ~0x0C00 == -0xFFFFFFFFFF600000. (For SECCOMP_RET_TRACE, use rip. For -SECCOMP_RET_TRAP, use siginfo->si_call_addr.) Do not check any other +To detect this quirky behavior, check for ``addr & ~0x0C00 == +0xFFFFFFFFFF600000``. (For ``SECCOMP_RET_TRACE``, use rip. For +``SECCOMP_RET_TRAP``, use ``siginfo->si_call_addr``.) Do not check any other condition: future kernels may improve vsyscall emulation and current kernels in vsyscall=native mode will behave differently, but the -instructions at 0xF...F600{0,4,8,C}00 will not be system calls in these +instructions at ``0xF...F600{0,4,8,C}00`` will not be system calls in these cases. Note that modern systems are unlikely to use vsyscalls at all -- they diff --git a/Documentation/userspace-api/unshare.rst b/Documentation/userspace-api/unshare.rst index 737c192cf4e7bd..877e90a3523896 100644 --- a/Documentation/userspace-api/unshare.rst +++ b/Documentation/userspace-api/unshare.rst @@ -107,7 +107,7 @@ the benefits of this new feature can exceed its cost. unshare() reverses sharing that was done using clone(2) system call, so unshare() should have a similar interface as clone(2). That is, -since flags in clone(int flags, void *stack) specifies what should +since flags in clone(int flags, void \*stack) specifies what should be shared, similar flags in unshare(int flags) should specify what should be unshared. Unfortunately, this may appear to invert the meaning of the flags from the way they are used in clone(2). diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 4029943887a30b..912b7df8215aaf 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3255,6 +3255,141 @@ Otherwise, if the MCE is a corrected error, KVM will just store it in the corresponding bank (provided this bank is not holding a previously reported uncorrected error). +4.107 KVM_S390_GET_CMMA_BITS + +Capability: KVM_CAP_S390_CMMA_MIGRATION +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_cmma_log (in, out) +Returns: 0 on success, a negative value on error + +This ioctl is used to get the values of the CMMA bits on the s390 +architecture. It is meant to be used in two scenarios: +- During live migration to save the CMMA values. Live migration needs + to be enabled via the KVM_REQ_START_MIGRATION VM property. +- To non-destructively peek at the CMMA values, with the flag + KVM_S390_CMMA_PEEK set. + +The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired +values are written to a buffer whose location is indicated via the "values" +member in the kvm_s390_cmma_log struct. The values in the input struct are +also updated as needed. +Each CMMA value takes up one byte. + +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +start_gfn is the number of the first guest frame whose CMMA values are +to be retrieved, + +count is the length of the buffer in bytes, + +values points to the buffer where the result will be written to. + +If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be +KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with +other ioctls. + +The result is written in the buffer pointed to by the field values, and +the values of the input parameter are updated as follows. + +Depending on the flags, different actions are performed. The only +supported flag so far is KVM_S390_CMMA_PEEK. + +The default behaviour if KVM_S390_CMMA_PEEK is not set is: +start_gfn will indicate the first page frame whose CMMA bits were dirty. +It is not necessarily the same as the one passed as input, as clean pages +are skipped. + +count will indicate the number of bytes actually written in the buffer. +It can (and very often will) be smaller than the input value, since the +buffer is only filled until 16 bytes of clean values are found (which +are then not copied in the buffer). Since a CMMA migration block needs +the base address and the length, for a total of 16 bytes, we will send +back some clean data if there is some dirty data afterwards, as long as +the size of the clean data does not exceed the size of the header. This +allows to minimize the amount of data to be saved or transferred over +the network at the expense of more roundtrips to userspace. The next +invocation of the ioctl will skip over all the clean values, saving +potentially more than just the 16 bytes we found. + +If KVM_S390_CMMA_PEEK is set: +the existing storage attributes are read even when not in migration +mode, and no other action is performed; + +the output start_gfn will be equal to the input start_gfn, + +the output count will be equal to the input count, except if the end of +memory has been reached. + +In both cases: +the field "remaining" will indicate the total number of dirty CMMA values +still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is +not enabled. + +mask is unused. + +values points to the userspace buffer where the result will be stored. + +This ioctl can fail with -ENOMEM if not enough memory can be allocated to +complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if +KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with +-EFAULT if the userspace address is invalid or if no page table is +present for the addresses (e.g. when using hugepages). + +4.108 KVM_S390_SET_CMMA_BITS + +Capability: KVM_CAP_S390_CMMA_MIGRATION +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_cmma_log (in) +Returns: 0 on success, a negative value on error + +This ioctl is used to set the values of the CMMA bits on the s390 +architecture. It is meant to be used during live migration to restore +the CMMA values, but there are no restrictions on its use. +The ioctl takes parameters via the kvm_s390_cmma_values struct. +Each CMMA value takes up one byte. + +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +start_gfn indicates the starting guest frame number, + +count indicates how many values are to be considered in the buffer, + +flags is not used and must be 0. + +mask indicates which PGSTE bits are to be considered. + +remaining is not used. + +values points to the buffer in userspace where to store the values. + +This ioctl can fail with -ENOMEM if not enough memory can be allocated to +complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if +the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or +if the flags field was not 0, with -EFAULT if the userspace address is +invalid, if invalid pages are written to (e.g. after the end of memory) +or if no page table is present for the addresses (e.g. when using +hugepages). + 5. The kvm_run structure ------------------------ diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt index 575ccb022aacd9..903fc926860b52 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virtual/kvm/devices/vm.txt @@ -222,3 +222,36 @@ Allows user space to disable dea key wrapping, clearing the wrapping key. Parameters: none Returns: 0 + +5. GROUP: KVM_S390_VM_MIGRATION +Architectures: s390 + +5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o) + +Allows userspace to stop migration mode, needed for PGSTE migration. +Setting this attribute when migration mode is not active will have no +effects. + +Parameters: none +Returns: 0 + +5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o) + +Allows userspace to start migration mode, needed for PGSTE migration. +Setting this attribute when migration mode is already active will have +no effects. + +Parameters: none +Returns: -ENOMEM if there is not enough free memory to start migration mode + -EINVAL if the state of the VM is invalid (e.g. no memory defined) + 0 in case of success. + +5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o) + +Allows userspace to query the status of migration mode. + +Parameters: address of a buffer in user space to store the data (u64) to; + the data itself is either 0 if migration mode is disabled or 1 + if it is enabled +Returns: -EFAULT if the given address is not accessible from kernel space + 0 in case of success. diff --git a/MAINTAINERS b/MAINTAINERS index acd835726d1fdd..9609ca6fc77b0c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -155,7 +155,7 @@ S: Maintained F: drivers/scsi/53c700* 6LOWPAN GENERIC (BTLE/IEEE 802.15.4) -M: Alexander Aring +M: Alexander Aring M: Jukka Rissanen L: linux-bluetooth@vger.kernel.org L: linux-wpan@vger.kernel.org @@ -478,7 +478,7 @@ L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ads1015 F: drivers/hwmon/ads1015.c -F: include/linux/i2c/ads1015.h +F: include/linux/platform_data/ads1015.h ADT746X FAN DRIVER M: Colin Leroy @@ -1207,7 +1207,9 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/hwtracing/coresight/* F: Documentation/trace/coresight.txt +F: Documentation/trace/coresight-cpu-debug.txt F: Documentation/devicetree/bindings/arm/coresight.txt +F: Documentation/devicetree/bindings/arm/coresight-cpu-debug.txt F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* F: tools/perf/arch/arm/util/pmu.c F: tools/perf/arch/arm/util/auxtrace.c @@ -1489,13 +1491,16 @@ M: Gregory Clement M: Sebastian Hesselbarth L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -F: arch/arm/mach-mvebu/ -F: drivers/rtc/rtc-armada38x.c F: arch/arm/boot/dts/armada* F: arch/arm/boot/dts/kirkwood* +F: arch/arm/configs/mvebu_*_defconfig +F: arch/arm/mach-mvebu/ F: arch/arm64/boot/dts/marvell/armada* F: drivers/cpufreq/mvebu-cpufreq.c -F: arch/arm/configs/mvebu_*_defconfig +F: drivers/irqchip/irq-armada-370-xp.c +F: drivers/irqchip/irq-mvebu-* +F: drivers/pinctrl/mvebu/ +F: drivers/rtc/rtc-armada38x.c ARM/Marvell Berlin SoC support M: Jisheng Zhang @@ -1677,6 +1682,13 @@ M: Lennert Buytenhek L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained +ARM/REALTEK ARCHITECTURE +M: Andreas Färber +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm64/boot/dts/realtek/ +F: Documentation/devicetree/bindings/arm/realtek.txt + ARM/RENESAS ARM64 ARCHITECTURE M: Simon Horman M: Magnus Damm @@ -1721,7 +1733,6 @@ N: rockchip ARM/SAMSUNG EXYNOS ARM ARCHITECTURES M: Kukjin Kim M: Krzysztof Kozlowski -R: Javier Martinez Canillas L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ @@ -1843,8 +1854,8 @@ F: drivers/i2c/busses/i2c-st.c F: drivers/media/rc/st_rc.c F: drivers/media/platform/sti/c8sectpfe/ F: drivers/mmc/host/sdhci-st.c -F: drivers/phy/phy-miphy28lp.c -F: drivers/phy/phy-stih407-usb.c +F: drivers/phy/st/phy-miphy28lp.c +F: drivers/phy/st/phy-stih407-usb.c F: drivers/pinctrl/pinctrl-st.c F: drivers/remoteproc/st_remoteproc.c F: drivers/remoteproc/st_slim_rproc.c @@ -2685,7 +2696,6 @@ N: kona F: arch/arm/mach-bcm/ BROADCOM BCM2835 ARM ARCHITECTURE -M: Lee Jones M: Eric Anholt M: Stefan Wahren L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) @@ -3586,7 +3596,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6.git S: Maintained F: Documentation/crypto/ F: Documentation/devicetree/bindings/crypto/ -F: Documentation/DocBook/crypto-API.tmpl F: arch/*/crypto/ F: crypto/ F: drivers/crypto/ @@ -4111,6 +4120,17 @@ F: include/uapi/linux/sync_file.h F: Documentation/sync_file.txt T: git git://anongit.freedesktop.org/drm/drm-misc +SYNC FILE FRAMEWORK +M: Sumit Semwal +R: Gustavo Padovan +S: Maintained +L: linux-media@vger.kernel.org +L: dri-devel@lists.freedesktop.org +F: drivers/dma-buf/sync_file.c +F: include/linux/sync_file.h +F: Documentation/sync_file.txt +T: git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git + DMA GENERIC OFFLOAD ENGINE SUBSYSTEM M: Vinod Koul L: dmaengine@vger.kernel.org @@ -4235,6 +4255,12 @@ F: include/drm/drm* F: include/uapi/drm/drm* F: include/linux/vga* +DRM DRIVER FOR ARM PL111 CLCD +M: Eric Anholt +T: git git://anongit.freedesktop.org/drm/drm-misc +S: Supported +F: drivers/gpu/drm/pl111/ + DRM DRIVER FOR AST SERVER GRAPHICS CHIPS M: Dave Airlie S: Odd Fixes @@ -4242,6 +4268,8 @@ F: drivers/gpu/drm/ast/ DRM DRIVERS FOR BRIDGE CHIPS M: Archit Taneja +M: Andrzej Hajda +R: Laurent Pinchart S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/bridge/ @@ -4498,6 +4526,17 @@ S: Maintained F: drivers/gpu/drm/sti F: Documentation/devicetree/bindings/display/st,stih4xx.txt +DRM DRIVERS FOR STM +M: Yannick Fertre +M: Philippe Cornu +M: Benjamin Gaignard +M: Vincent Abriou +L: dri-devel@lists.freedesktop.org +T: git git://anongit.freedesktop.org/drm/drm-misc +S: Maintained +F: drivers/gpu/drm/stm +F: Documentation/devicetree/bindings/display/st,stm32-ltdc.txt + DRM DRIVER FOR TDFX VIDEO CARDS S: Orphan / Obsolete F: drivers/gpu/drm/tdfx/ @@ -5622,7 +5661,7 @@ F: scripts/get_maintainer.pl GENWQE (IBM Generic Workqueue Card) M: Frank Haverkamp -M: Gabriel Krisman Bertazi +M: Guilherme G. Piccoli S: Supported F: drivers/misc/genwqe/ @@ -5667,7 +5706,6 @@ F: tools/testing/selftests/gpio/ GPIO SUBSYSTEM M: Linus Walleij -M: Alexandre Courbot L: linux-gpio@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git S: Maintained @@ -6273,6 +6311,7 @@ M: Mika Westerberg L: linux-i2c@vger.kernel.org L: linux-acpi@vger.kernel.org S: Maintained +F: drivers/i2c/i2c-core-acpi.c I2C-TAOS-EVM DRIVER M: Jean Delvare @@ -6427,7 +6466,7 @@ F: Documentation/cdrom/ide-cd F: drivers/ide/ide-cd* IEEE 802.15.4 SUBSYSTEM -M: Alexander Aring +M: Alexander Aring M: Stefan Schmidt L: linux-wpan@vger.kernel.org W: http://wpan.cakelab.org/ @@ -7349,7 +7388,7 @@ KEYS/KEYRINGS: M: David Howells L: keyrings@vger.kernel.org S: Maintained -F: Documentation/security/keys.txt +F: Documentation/security/keys/core.rst F: include/linux/key.h F: include/linux/key-type.h F: include/linux/keyctl.h @@ -7363,7 +7402,7 @@ M: Mimi Zohar L: linux-security-module@vger.kernel.org L: keyrings@vger.kernel.org S: Supported -F: Documentation/security/keys-trusted-encrypted.txt +F: Documentation/security/keys/trusted-encrypted.rst F: include/keys/trusted-type.h F: security/keys/trusted.c F: security/keys/trusted.h @@ -7374,7 +7413,7 @@ M: David Safford L: linux-security-module@vger.kernel.org L: keyrings@vger.kernel.org S: Supported -F: Documentation/security/keys-trusted-encrypted.txt +F: Documentation/security/keys/trusted-encrypted.rst F: include/keys/encrypted-type.h F: security/keys/encrypted-keys/ @@ -7384,7 +7423,7 @@ W: http://kgdb.wiki.kernel.org/ L: kgdb-bugreport@lists.sourceforge.net T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git S: Maintained -F: Documentation/DocBook/kgdb.tmpl +F: Documentation/dev-tools/kgdb.rst F: drivers/misc/kgdbts.c F: drivers/tty/serial/kgdboc.c F: include/linux/kdb.h @@ -8061,11 +8100,11 @@ S: Supported F: drivers/power/supply/max14577_charger.c F: drivers/power/supply/max77693_charger.c -MAXIM MAX77802 MULTIFUNCTION PMIC DEVICE DRIVERS -M: Javier Martinez Canillas +MAXIM MAX77802 PMIC REGULATOR DEVICE DRIVER +M: Javier Martinez Canillas L: linux-kernel@vger.kernel.org S: Supported -F: drivers/*/*max77802*.c +F: drivers/regulator/max77802-regulator.c F: Documentation/devicetree/bindings/*/*max77802.txt F: include/dt-bindings/*/*max77802.h @@ -8311,6 +8350,16 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* +MELLANOX ETHERNET INNOVA DRIVER +M: Ilan Tayari +R: Boris Pismenny +L: netdev@vger.kernel.org +S: Supported +W: http://www.mellanox.com +Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* +F: include/linux/mlx5/mlx5_ifc_fpga.h + MELLANOX ETHERNET SWITCH DRIVERS M: Jiri Pirko M: Ido Schimmel @@ -8320,6 +8369,14 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlxsw/ +MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) +M: Yotam Gigi +L: netdev@vger.kernel.org +S: Supported +W: http://www.mellanox.com +Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlxfw/ + MELLANOX MLXCPLD I2C AND MUX DRIVER M: Vadim Pasternak M: Michael Shych @@ -8461,6 +8518,16 @@ F: drivers/media/platform/atmel/atmel-isc.c F: drivers/media/platform/atmel/atmel-isc-regs.h F: devicetree/bindings/media/atmel-isc.txt +MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER +M: Woojung Huh +M: Microchip Linux Driver Support +L: netdev@vger.kernel.org +S: Maintained +F: net/dsa/tag_ksz.c +F: drivers/net/dsa/microchip/* +F: include/linux/platform_data/microchip-ksz.h +F: Documentation/devicetree/bindings/net/dsa/ksz.txt + MICROCHIP USB251XB DRIVER M: Richard Leitner L: linux-usb@vger.kernel.org @@ -8508,7 +8575,7 @@ S: Odd Fixes F: drivers/media/radio/radio-miropcm20* MELLANOX MLX4 core VPI driver -M: Yishai Hadas +M: Tariq Toukan L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org W: http://www.mellanox.com @@ -8516,7 +8583,6 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ S: Supported F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ -F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX4 IB driver M: Yishai Hadas @@ -8526,6 +8592,7 @@ Q: http://patchwork.kernel.org/project/linux-rdma/list/ S: Supported F: drivers/infiniband/hw/mlx4/ F: include/linux/mlx4/ +F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX5 core VPI driver M: Saeed Mahameed @@ -8538,7 +8605,6 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ S: Supported F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ -F: include/uapi/rdma/mlx5-abi.h MELLANOX MLX5 IB driver M: Matan Barak @@ -8549,6 +8615,7 @@ Q: http://patchwork.kernel.org/project/linux-rdma/list/ S: Supported F: drivers/infiniband/hw/mlx5/ F: include/linux/mlx5/ +F: include/uapi/rdma/mlx5-abi.h MELEXIS MLX90614 DRIVER M: Crt Mori @@ -10155,7 +10222,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained F: Documentation/hwmon/pmbus F: drivers/hwmon/pmbus/ -F: include/linux/i2c/pmbus.h +F: include/linux/pmbus.h PMC SIERRA MaxRAID DRIVER L: linux-scsi@vger.kernel.org @@ -10610,6 +10677,14 @@ L: qemu-devel@nongnu.org S: Maintained F: drivers/firmware/qemu_fw_cfg.c +QUANTENNA QTNFMAC WIRELESS DRIVER +M: Igor Mitsyanko +M: Avinash Patil +M: Sergey Matyukevich +L: linux-wireless@vger.kernel.org +S: Maintained +F: drivers/net/wireless/quantenna + RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov M: Sage Weil @@ -10847,7 +10922,7 @@ RENESAS USB2 PHY DRIVER M: Yoshihiro Shimoda L: linux-renesas-soc@vger.kernel.org S: Maintained -F: drivers/phy/phy-rcar-gen3-usb2.c +F: drivers/phy/renesas/phy-rcar-gen3-usb2.c RESET CONTROLLER FRAMEWORK M: Philipp Zabel @@ -11004,7 +11079,7 @@ S: Supported F: arch/s390/ F: drivers/s390/ F: Documentation/s390/ -F: Documentation/DocBook/s390* +F: Documentation/driver-api/s390-drivers.rst S390 COMMON I/O LAYER M: Sebastian Ott @@ -11249,12 +11324,12 @@ L: linux-kernel@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/phy/samsung-phy.txt F: Documentation/phy/samsung-usb2.txt -F: drivers/phy/phy-exynos4210-usb2.c -F: drivers/phy/phy-exynos4x12-usb2.c -F: drivers/phy/phy-exynos5250-usb2.c -F: drivers/phy/phy-s5pv210-usb2.c -F: drivers/phy/phy-samsung-usb2.c -F: drivers/phy/phy-samsung-usb2.h +F: drivers/phy/samsung/phy-exynos4210-usb2.c +F: drivers/phy/samsung/phy-exynos4x12-usb2.c +F: drivers/phy/samsung/phy-exynos5250-usb2.c +F: drivers/phy/samsung/phy-s5pv210-usb2.c +F: drivers/phy/samsung/phy-samsung-usb2.c +F: drivers/phy/samsung/phy-samsung-usb2.h SERIAL DRIVERS M: Greg Kroah-Hartman @@ -11506,6 +11581,7 @@ F: kernel/seccomp.c F: include/uapi/linux/seccomp.h F: include/linux/seccomp.h F: tools/testing/selftests/seccomp/* +F: Documentation/userspace-api/seccomp_filter.rst K: \bsecure_computing K: \bTIF_SECCOMP\b @@ -11564,6 +11640,7 @@ S: Supported F: include/linux/selinux* F: security/selinux/ F: scripts/selinux/ +F: Documentation/admin-guide/LSM/SELinux.rst APPARMOR SECURITY MODULE M: John Johansen @@ -11572,18 +11649,21 @@ W: apparmor.wiki.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jj/apparmor-dev.git S: Supported F: security/apparmor/ +F: Documentation/admin-guide/LSM/apparmor.rst LOADPIN SECURITY MODULE M: Kees Cook T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git lsm/loadpin S: Supported F: security/loadpin/ +F: Documentation/admin-guide/LSM/LoadPin.rst YAMA SECURITY MODULE M: Kees Cook T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git yama/tip S: Supported F: security/yama/ +F: Documentation/admin-guide/LSM/Yama.rst SENSABLE PHANTOM M: Jiri Slaby @@ -11885,7 +11965,7 @@ L: linux-security-module@vger.kernel.org W: http://schaufler-ca.com T: git git://github.com/cschaufler/smack-next S: Maintained -F: Documentation/security/Smack.txt +F: Documentation/admin-guide/LSM/Smack.rst F: security/smack/ DRIVERS FOR ADAPTIVE VOLTAGE SCALING (AVS) @@ -13872,7 +13952,7 @@ S: Odd fixes F: drivers/net/wireless/wl3501* WOLFSON MICROELECTRONICS DRIVERS -L: patches@opensource.wolfsonmicro.com +L: patches@opensource.cirrus.com T: git https://github.com/CirrusLogic/linux-drivers.git W: https://github.com/CirrusLogic/linux-drivers/wiki S: Supported @@ -14086,6 +14166,14 @@ L: linux-kernel@vger.kernel.org S: Supported F: drivers/char/xillybus/ +XRA1403 GPIO EXPANDER +M: Nandor Han +M: Semi Malinen +L: linux-gpio@vger.kernel.org +S: Maintained +F: drivers/gpio/gpio-xra1403.c +F: Documentation/devicetree/bindings/gpio/gpio-xra1403.txt + XTENSA XTFPGA PLATFORM SUPPORT M: Max Filippov L: linux-xtensa@linux-xtensa.org diff --git a/Makefile b/Makefile index 0fd20781d79c50..5257bb62512a27 100644 --- a/Makefile +++ b/Makefile @@ -1312,7 +1312,7 @@ clean: archclean vmlinuxclean # mrproper: rm-dirs := $(wildcard $(MRPROPER_DIRS)) mrproper: rm-files := $(wildcard $(MRPROPER_FILES)) -mrproper-dirs := $(addprefix _mrproper_,Documentation/DocBook scripts) +mrproper-dirs := $(addprefix _mrproper_,scripts) PHONY += $(mrproper-dirs) mrproper archmrproper $(mrproper-dirs): @@ -1416,9 +1416,7 @@ help: @$(MAKE) $(build)=$(package-dir) help @echo '' @echo 'Documentation targets:' - @$(MAKE) -f $(srctree)/Documentation/Makefile.sphinx dochelp - @echo '' - @$(MAKE) -f $(srctree)/Documentation/DocBook/Makefile dochelp + @$(MAKE) -f $(srctree)/Documentation/Makefile dochelp @echo '' @echo 'Architecture specific targets ($(SRCARCH)):' @$(if $(archhelp),$(archhelp),\ @@ -1469,9 +1467,8 @@ $(help-board-dirs): help-%: DOC_TARGETS := xmldocs sgmldocs psdocs latexdocs pdfdocs htmldocs mandocs installmandocs epubdocs cleandocs linkcheckdocs PHONY += $(DOC_TARGETS) $(DOC_TARGETS): scripts_basic FORCE - $(Q)$(MAKE) $(build)=scripts build_docproc build_check-lc_ctype - $(Q)$(MAKE) $(build)=Documentation -f $(srctree)/Documentation/Makefile.sphinx $@ - $(Q)$(MAKE) $(build)=Documentation/DocBook $@ + $(Q)$(MAKE) $(build)=scripts build_docproc + $(Q)$(MAKE) $(build)=Documentation $@ else # KBUILD_EXTMOD diff --git a/arch/Kconfig b/arch/Kconfig index 6c00e5b00f8bd6..3eac97a4c7b340 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -425,7 +425,7 @@ config GCC_PLUGIN_STRUCTLEAK bool "Force initialization of variables containing userspace addresses" depends on GCC_PLUGINS help - This plugin zero-initializes any structures that containing a + This plugin zero-initializes any structures containing a __user attribute. This can prevent some classes of information exposures. @@ -443,6 +443,45 @@ config GCC_PLUGIN_STRUCTLEAK_VERBOSE initialized. Since not all existing initializers are detected by the plugin, this can produce false positive warnings. +config GCC_PLUGIN_RANDSTRUCT + bool "Randomize layout of sensitive kernel structures" + depends on GCC_PLUGINS + select MODVERSIONS if MODULES + help + If you say Y here, the layouts of structures explicitly + marked by __randomize_layout will be randomized at + compile-time. This can introduce the requirement of an + additional information exposure vulnerability for exploits + targeting these structure types. + + Enabling this feature will introduce some performance impact, + slightly increase memory usage, and prevent the use of forensic + tools like Volatility against the system (unless the kernel + source tree isn't cleaned after kernel installation). + + The seed used for compilation is located at + scripts/gcc-plgins/randomize_layout_seed.h. It remains after + a make clean to allow for external modules to be compiled with + the existing seed and will be removed by a make mrproper or + make distclean. + + Note that the implementation requires gcc 4.7 or newer. + + This plugin was ported from grsecurity/PaX. More information at: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + +config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE + bool "Use cacheline-aware structure randomization" + depends on GCC_PLUGIN_RANDSTRUCT + depends on !COMPILE_TEST + help + If you say Y here, the RANDSTRUCT randomization will make a + best effort at restricting randomization to cacheline-sized + groups of elements. It will further not randomize bitfields + in structures. This reduces the performance hit of RANDSTRUCT + at the cost of weakened randomization. + config HAVE_CC_STACKPROTECTOR bool help diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 148d7a32754e34..0926de63a62b3a 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -105,4 +105,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index a867575a758b98..3329d0dd171ba7 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1092,8 +1092,8 @@ noinline void __init arc_ioc_setup(void) if (read_aux_reg(ARC_REG_SLC_BCR)) slc_entire_op(OP_FLUSH_N_INV); - /* IOC Aperture start: TDB: handle non default CONFIG_LINUX_LINK_BASE */ - write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000); + /* IOC Aperture start */ + write_aux_reg(ARC_REG_IO_COH_AP0_BASE, CONFIG_LINUX_LINK_BASE >> 12); /* * IOC Aperture size: diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 426d2716f55d37..b3677d1d07fcbf 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -776,6 +776,30 @@ choice their output to the standard serial port on the RealView PB1176 platform. + config DEBUG_RV1108_UART0 + bool "Kernel low-level debugging messages via Rockchip RV1108 UART0" + depends on ARCH_ROCKCHIP + select DEBUG_UART_8250 + help + Say Y here if you want kernel low-level debugging support + on Rockchip RV1108 based platforms. + + config DEBUG_RV1108_UART1 + bool "Kernel low-level debugging messages via Rockchip RV1108 UART1" + depends on ARCH_ROCKCHIP + select DEBUG_UART_8250 + help + Say Y here if you want kernel low-level debugging support + on Rockchip RV1108 based platforms. + + config DEBUG_RV1108_UART2 + bool "Kernel low-level debugging messages via Rockchip RV1108 UART2" + depends on ARCH_ROCKCHIP + select DEBUG_UART_8250 + help + Say Y here if you want kernel low-level debugging support + on Rockchip RV1108 based platforms. + config DEBUG_RK29_UART0 bool "Kernel low-level debugging messages via Rockchip RK29 UART0" depends on ARCH_ROCKCHIP @@ -1465,6 +1489,9 @@ config DEBUG_UART_PHYS default 0x10126000 if DEBUG_RK3X_UART1 default 0x101f1000 if DEBUG_VERSATILE default 0x101fb000 if DEBUG_NOMADIK_UART + default 0x10210000 if DEBUG_RV1108_UART2 + default 0x10220000 if DEBUG_RV1108_UART1 + default 0x10230000 if DEBUG_RV1108_UART0 default 0x11002000 if DEBUG_MT8127_UART0 default 0x11006000 if DEBUG_MT6589_UART0 default 0x11009000 if DEBUG_MT8135_UART3 @@ -1563,6 +1590,9 @@ config DEBUG_UART_PHYS config DEBUG_UART_VIRT hex "Virtual base address of debug UART" + default 0xc881f000 if DEBUG_RV1108_UART2 + default 0xc8821000 if DEBUG_RV1108_UART1 + default 0xc8912000 if DEBUG_RV1108_UART0 default 0xe0000a00 if DEBUG_NETX_UART default 0xe0010fe0 if ARCH_RPC default 0xf0000be0 if ARCH_EBSA110 diff --git a/arch/arm/arm-soc-for-next-contents.txt b/arch/arm/arm-soc-for-next-contents.txt new file mode 100644 index 00000000000000..239a650bd52fd0 --- /dev/null +++ b/arch/arm/arm-soc-for-next-contents.txt @@ -0,0 +1,36 @@ +fixes + patch + ARM: omap2+: make omap4_get_cpu1_ns_pa_addr declaration usable + (1c0803652d82b9a62980886e019c9f70576028a5) + https://github.com/mbgg/linux-mediatek tags/v4.11-next-fixes + (7b4ccb3c466f62bbf2f4dd5d6a143d945a6f3051) + https://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas tags/renesas-fixes-for-v4.12 + (6a680783aaadd168557eec695374929ac066536f) + git://git.infradead.org/linux-mvebu tags/mvebu-dt64-4.12-3 + (d2718d1365f7fce624fd7ed163f60532f92ed016) + git://git.infradead.org/linux-mvebu tags/mvebu-arm64-4.12-1 + tee/initial-merge + Merge branch 'tee/initial-merge' into fixes + patch + tee: add ARM_SMCCC dependency + (2ea659a9ef488125eb46da6eb571de5eae5c43f6) + Merge tag 'v4.12-rc1' into fixes + contains next/tee + patch + devicetree: Move include prefixes from arch to separate directory + (b155f05dc578299557447a6fd6545ebc72c1d19b) + http://github.com/Broadcom/stblinux tags/arm-soc/for-4.12/devicetree-fixes + (31d848aa1d85530770f0bdf1b61a042335d340ad) + http://github.com/Broadcom/stblinux tags/arm-soc/for-4.12/drivers-fixes + patch + ARM: configs: add a gemini defconfig + arm64: defconfig: sync with savedefconfig + arm64: defconfig: enable options needed for QCom DB410c board + (e23c7f7d57831fdae444be9d507e67716ab601d4) + git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux tags/imx-fixes-4.12 + (bca5238816939436d72ae6bab124c4b0641a3a99) + git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap tags/omap-for-v4.12/fixes-v2-signed + patch + ARM: remove duplicate 'const' annotations' + firmware: ti_sci: fix strncat length check + ARM: dts: keystone-k2l: fix broken Ethernet due to disabled OSR diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S index 9d5dc4fda3c167..3f7d1b74c5e02b 100644 --- a/arch/arm/boot/compressed/efi-header.S +++ b/arch/arm/boot/compressed/efi-header.S @@ -17,14 +17,12 @@ @ there. .inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000 #else - mov r0, r0 + W(mov) r0, r0 #endif .endm .macro __EFI_HEADER #ifdef CONFIG_EFI_STUB - b __efi_start - .set start_offset, __efi_start - start .org start + 0x3c @ diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 7c711ba614173d..8a756870c23843 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -130,19 +130,22 @@ start: .rept 7 __nop .endr - ARM( mov r0, r0 ) - ARM( b 1f ) - THUMB( badr r12, 1f ) - THUMB( bx r12 ) +#ifndef CONFIG_THUMB2_KERNEL + mov r0, r0 +#else + AR_CLASS( sub pc, pc, #3 ) @ A/R: switch to Thumb2 mode + M_CLASS( nop.w ) @ M: already in Thumb2 mode + .thumb +#endif + W(b) 1f .word _magic_sig @ Magic numbers to help the loader .word _magic_start @ absolute load/run zImage address .word _magic_end @ zImage end address .word 0x04030201 @ endianness flag - THUMB( .thumb ) -1: __EFI_HEADER - + __EFI_HEADER +1: ARM_BE8( setend be ) @ go BE8 if compiled for BE8 AR_CLASS( mrs r9, cpsr ) #ifdef CONFIG_ARM_VIRT_EXT diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 9c5e1d944d1c71..3bd29feb829804 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -72,6 +72,7 @@ dtb-$(CONFIG_ARCH_BCM2835) += \ bcm2835-rpi-b-plus.dtb \ bcm2835-rpi-a-plus.dtb \ bcm2836-rpi-2-b.dtb \ + bcm2837-rpi-3-b.dtb \ bcm2835-rpi-zero.dtb dtb-$(CONFIG_ARCH_BCM_5301X) += \ bcm4708-asus-rt-ac56u.dtb \ @@ -204,7 +205,8 @@ dtb-$(CONFIG_ARCH_KEYSTONE) += \ keystone-k2hk-evm.dtb \ keystone-k2l-evm.dtb \ keystone-k2e-evm.dtb \ - keystone-k2g-evm.dtb + keystone-k2g-evm.dtb \ + keystone-k2g-ice.dtb dtb-$(CONFIG_MACH_KIRKWOOD) += \ kirkwood-b3.dtb \ kirkwood-blackarmor-nas220.dtb \ @@ -363,6 +365,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \ imx6dl-gw551x.dtb \ imx6dl-gw552x.dtb \ imx6dl-gw553x.dtb \ + imx6dl-gw560x.dtb \ imx6dl-gw5903.dtb \ imx6dl-gw5904.dtb \ imx6dl-hummingboard.dtb \ @@ -408,6 +411,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \ imx6q-gw551x.dtb \ imx6q-gw552x.dtb \ imx6q-gw553x.dtb \ + imx6q-gw560x.dtb \ imx6q-gw5903.dtb \ imx6q-gw5904.dtb \ imx6q-h100.dtb \ @@ -476,6 +480,7 @@ dtb-$(CONFIG_SOC_IMX7D) += \ imx7d-cl-som-imx7.dtb \ imx7d-colibri-eval-v3.dtb \ imx7d-nitrogen7.dtb \ + imx7d-pico.dtb \ imx7d-sbc-imx7.dtb \ imx7d-sdb.dtb \ imx7d-sdb-sht11.dtb \ @@ -701,6 +706,7 @@ dtb-$(CONFIG_ARCH_REALVIEW) += \ dtb-$(CONFIG_ARCH_RENESAS) += \ emev2-kzm9d.dtb \ r7s72100-genmai.dtb \ + r7s72100-gr-peach.dtb \ r7s72100-rskrza1.dtb \ r8a73a4-ape6evm.dtb \ r8a7740-armadillo800eva.dtb \ @@ -718,7 +724,7 @@ dtb-$(CONFIG_ARCH_RENESAS) += \ r8a7794-silk.dtb \ sh73a0-kzm9g.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += \ - rk1108-evb.dtb \ + rv1108-evb.dtb \ rk3036-evb.dtb \ rk3036-kylin.dtb \ rk3066a-bqcurie2.dtb \ @@ -905,7 +911,8 @@ dtb-$(CONFIG_MACH_SUN8I) += \ sun8i-h3-orangepi-plus.dtb \ sun8i-h3-orangepi-plus2e.dtb \ sun8i-r16-parrot.dtb \ - sun8i-v3s-licheepi-zero.dtb + sun8i-v3s-licheepi-zero.dtb \ + sun8i-v3s-licheepi-zero-dock.dtb dtb-$(CONFIG_MACH_SUN9I) += \ sun9i-a80-optimus.dtb \ sun9i-a80-cubieboard4.dtb @@ -999,6 +1006,7 @@ dtb-$(CONFIG_MACH_ARMADA_38X) += \ armada-385-db-ap.dtb \ armada-385-linksys-caiman.dtb \ armada-385-linksys-cobra.dtb \ + armada-385-linksys-rango.dtb \ armada-385-linksys-shelby.dtb \ armada-385-synology-ds116.dtb \ armada-385-turris-omnia.dtb \ diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi index d42b98f15e8b97..ec6052c521ef33 100644 --- a/arch/arm/boot/dts/am335x-baltos.dtsi +++ b/arch/arm/boot/dts/am335x-baltos.dtsi @@ -255,7 +255,7 @@ }; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c02"; pagesize = <8>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am335x-base0033.dts b/arch/arm/boot/dts/am335x-base0033.dts index c2bee452dab820..29782be0760579 100644 --- a/arch/arm/boot/dts/am335x-base0033.dts +++ b/arch/arm/boot/dts/am335x-base0033.dts @@ -89,7 +89,7 @@ &i2c0 { eeprom: eeprom@50 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x50>; }; }; diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index bf6b26abe35b5d..1d154444dfef24 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -232,7 +232,7 @@ }; baseboard_eeprom: baseboard_eeprom@50 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x50>; #address-cells = <1>; @@ -251,7 +251,7 @@ clock-frequency = <100000>; cape_eeprom0: cape_eeprom0@54 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x54>; #address-cells = <1>; #size-cells = <1>; @@ -261,7 +261,7 @@ }; cape_eeprom1: cape_eeprom1@55 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x55>; #address-cells = <1>; #size-cells = <1>; @@ -271,7 +271,7 @@ }; cape_eeprom2: cape_eeprom2@56 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x56>; #address-cells = <1>; #size-cells = <1>; @@ -281,7 +281,7 @@ }; cape_eeprom3: cape_eeprom3@57 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x57>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/am335x-boneblack-wireless.dts b/arch/arm/boot/dts/am335x-boneblack-wireless.dts index 105bd10655f7d1..83f49f616b19c0 100644 --- a/arch/arm/boot/dts/am335x-boneblack-wireless.dts +++ b/arch/arm/boot/dts/am335x-boneblack-wireless.dts @@ -97,6 +97,11 @@ pinctrl-names = "default"; pinctrl-0 = <&uart3_pins &bt_pins>; status = "okay"; + + bluetooth { + compatible = "ti,wl1835-st"; + enable-gpios = <&gpio0 28 GPIO_ACTIVE_HIGH>; + }; }; &gpio3 { diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts index 935ed17d22e462..d154d3133c162a 100644 --- a/arch/arm/boot/dts/am335x-boneblack.dts +++ b/arch/arm/boot/dts/am335x-boneblack.dts @@ -22,7 +22,7 @@ * BeagleBone Blacks have PG 2.0 silicon which is guaranteed * to support 1GHz OPP so enable it for PG 2.0 on this board. */ - oppnitro@1000000000 { + oppnitro-1000000000 { opp-supported-hw = <0x06 0x0100>; }; }; diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts index 807494bc722ba3..946d7069f41711 100644 --- a/arch/arm/boot/dts/am335x-nano.dts +++ b/arch/arm/boot/dts/am335x-nano.dts @@ -224,7 +224,7 @@ }; eeprom@53 { - compatible = "microchip,24c02"; + compatible = "microchip,24c02", "atmel,24c02"; reg = <0x53>; pagesize = <8>; }; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 30e2f8770aaf84..03c7d77023c6a3 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -67,7 +67,7 @@ }; eeprom: eeprom@50 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi index 14533ff6d0add3..428a25e952b0c4 100644 --- a/arch/arm/boot/dts/am335x-phycore-som.dtsi +++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi @@ -138,7 +138,7 @@ }; i2c_rtc: rtc@68 { - compatible = "rv4162"; + compatible = "microcrystal,rv4162"; reg = <0x68>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index bf8727a19ece55..4f6a286ea293fa 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -188,7 +188,7 @@ }; at24@50 { - compatible = "at24,24c32"; + compatible = "atmel,24c32"; pagesize = <32>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts index c5d2589c55fc3d..1bcc60424ecd1e 100644 --- a/arch/arm/boot/dts/am335x-sl50.dts +++ b/arch/arm/boot/dts/am335x-sl50.dts @@ -220,7 +220,7 @@ mmc1_pins: pinmux_mmc1_pins { pinctrl-single,pins = < - AM33XX_IOPAD(0x960, PIN_INPUT | MUX_MODE7) /* spi0_cs1.gpio0_6 */ + AM33XX_IOPAD(0x96c, PIN_INPUT | MUX_MODE7) /* uart0_rtsn.gpio1_9 */ >; }; @@ -280,10 +280,6 @@ AM33XX_IOPAD(0x834, PIN_INPUT_PULLUP | MUX_MODE7) /* nKbdReset - gpmc_ad13.gpio1_13 */ AM33XX_IOPAD(0x838, PIN_INPUT_PULLUP | MUX_MODE7) /* nDispReset - gpmc_ad14.gpio1_14 */ AM33XX_IOPAD(0x844, PIN_INPUT_PULLUP | MUX_MODE7) /* USB1_enPower - gpmc_a1.gpio1_17 */ - /* AVR Programming - SPI Bus (bit bang) - Screen and Keyboard */ - AM33XX_IOPAD(0x954, PIN_INPUT_PULLUP | MUX_MODE7) /* Kbd/Disp/BattMOSI spi0_d0.gpio0_3 */ - AM33XX_IOPAD(0x958, PIN_INPUT_PULLUP | MUX_MODE7) /* Kbd/Disp/BattMISO spi0_d1.gpio0_4 */ - AM33XX_IOPAD(0x950, PIN_INPUT_PULLUP | MUX_MODE7) /* Kbd/Disp/BattSCLK spi0_clk.gpio0_2 */ /* PDI Bus - Battery system */ AM33XX_IOPAD(0x840, PIN_INPUT_PULLUP | MUX_MODE7) /* nBattReset gpmc_a0.gpio1_16 */ AM33XX_IOPAD(0x83c, PIN_INPUT_PULLUP | MUX_MODE7) /* BattPDIData gpmc_ad15.gpio1_15 */ @@ -309,7 +305,7 @@ }; eeprom: eeprom@50 { - compatible = "at,24c256"; + compatible = "atmel,24c256"; reg = <0x50>; }; @@ -384,7 +380,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; bus-width = <4>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; + cd-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; vmmc-supply = <&vmmcsd_fixed>; }; diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 9e242943dcecf1..bdacb3dd689c10 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -64,64 +64,64 @@ * because the can not be enabled simultaneously on a * single SoC. */ - opp50@300000000 { + opp50-300000000 { opp-hz = /bits/ 64 <300000000>; opp-microvolt = <950000 931000 969000>; opp-supported-hw = <0x06 0x0010>; opp-suspend; }; - opp100@275000000 { + opp100-275000000 { opp-hz = /bits/ 64 <275000000>; opp-microvolt = <1100000 1078000 1122000>; opp-supported-hw = <0x01 0x00FF>; opp-suspend; }; - opp100@300000000 { + opp100-300000000 { opp-hz = /bits/ 64 <300000000>; opp-microvolt = <1100000 1078000 1122000>; opp-supported-hw = <0x06 0x0020>; opp-suspend; }; - opp100@500000000 { + opp100-500000000 { opp-hz = /bits/ 64 <500000000>; opp-microvolt = <1100000 1078000 1122000>; opp-supported-hw = <0x01 0xFFFF>; }; - opp100@600000000 { + opp100-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1100000 1078000 1122000>; opp-supported-hw = <0x06 0x0040>; }; - opp120@600000000 { + opp120-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1200000 1176000 1224000>; opp-supported-hw = <0x01 0xFFFF>; }; - opp120@720000000 { + opp120-720000000 { opp-hz = /bits/ 64 <720000000>; opp-microvolt = <1200000 1176000 1224000>; opp-supported-hw = <0x06 0x0080>; }; - oppturbo@720000000 { + oppturbo-720000000 { opp-hz = /bits/ 64 <720000000>; opp-microvolt = <1260000 1234800 1285200>; opp-supported-hw = <0x01 0xFFFF>; }; - oppturbo@800000000 { + oppturbo-800000000 { opp-hz = /bits/ 64 <800000000>; opp-microvolt = <1260000 1234800 1285200>; opp-supported-hw = <0x06 0x0100>; }; - oppnitro@1000000000 { + oppnitro-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <1325000 1298500 1351500>; opp-supported-hw = <0x04 0x0200>; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 176e09e9a45eef..e5b061469bf88a 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -59,32 +59,32 @@ compatible = "operating-points-v2-ti-cpu"; syscon = <&scm_conf>; - opp50@300000000 { + opp50-300000000 { opp-hz = /bits/ 64 <300000000>; opp-microvolt = <950000 931000 969000>; opp-supported-hw = <0xFF 0x01>; opp-suspend; }; - opp100@600000000 { + opp100-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1100000 1078000 1122000>; opp-supported-hw = <0xFF 0x04>; }; - opp120@720000000 { + opp120-720000000 { opp-hz = /bits/ 64 <720000000>; opp-microvolt = <1200000 1176000 1224000>; opp-supported-hw = <0xFF 0x08>; }; - oppturbo@800000000 { + oppturbo-800000000 { opp-hz = /bits/ 64 <800000000>; opp-microvolt = <1260000 1234800 1285200>; opp-supported-hw = <0xFF 0x10>; }; - oppnitro@1000000000 { + oppnitro-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <1325000 1298500 1351500>; opp-supported-hw = <0xFF 0x20>; diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts index c1f7f9336e6449..5e364473067fad 100644 --- a/arch/arm/boot/dts/am437x-idk-evm.dts +++ b/arch/arm/boot/dts/am437x-idk-evm.dts @@ -339,7 +339,7 @@ clock-frequency = <400000>; at24@50 { - compatible = "at24,24c256"; + compatible = "atmel,24c256"; pagesize = <64>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 4dc54bee2f3631..a62e1583da0418 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -511,7 +511,7 @@ }; at24@50 { - compatible = "at24,24c256"; + compatible = "atmel,24c256"; pagesize = <64>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 9acd4ccdec4e24..f6648ab10d29ee 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -477,7 +477,7 @@ }; at24@50 { - compatible = "at24,24c256"; + compatible = "atmel,24c256"; pagesize = <64>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi index d1d73b725f4769..430be5829f8fe0 100644 --- a/arch/arm/boot/dts/am43xx-clocks.dtsi +++ b/arch/arm/boot/dts/am43xx-clocks.dtsi @@ -833,4 +833,40 @@ ti,bit-shift = <23>; reg = <0x4100>; }; + + clkout2_src_mux_ck: clkout2_src_mux_ck { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&clk_rc32k_ck>, <&sysclk_div>, <&dpll_ddr_m2_ck>, + <&dpll_per_m2_ck>, <&dpll_disp_m2_ck>, + <&dpll_mpu_m2_ck>, <&dpll_extdev_ck>; + reg = <0x4108>; + }; + + clkout2_pre_div_ck: clkout2_pre_div_ck { + #clock-cells = <0>; + compatible = "ti,divider-clock"; + clocks = <&clkout2_src_mux_ck>; + ti,bit-shift = <4>; + ti,max-div = <8>; + reg = <0x4108>; + }; + + clkout2_post_div_ck: clkout2_post_div_ck { + #clock-cells = <0>; + compatible = "ti,divider-clock"; + clocks = <&clkout2_pre_div_ck>; + ti,bit-shift = <8>; + ti,max-div = <32>; + ti,index-power-of-two; + reg = <0x4108>; + }; + + clkout2_ck: clkout2_ck { + #clock-cells = <0>; + compatible = "ti,gate-clock"; + clocks = <&clkout2_post_div_ck>; + ti,bit-shift = <16>; + reg = <0x4108>; + }; }; diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts index ad68d1eb3bc3d2..7b207835b2d161 100644 --- a/arch/arm/boot/dts/am571x-idk.dts +++ b/arch/arm/boot/dts/am571x-idk.dts @@ -79,3 +79,20 @@ id-gpio = <&gpio5 7 GPIO_ACTIVE_HIGH>; vbus-gpio = <&gpio7 22 GPIO_ACTIVE_HIGH>; }; + +&mailbox5 { + status = "okay"; + mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { + status = "okay"; + }; + mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { + status = "okay"; + }; +}; + +&mailbox6 { + status = "okay"; + mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { + status = "okay"; + }; +}; diff --git a/arch/arm/boot/dts/am572x-idk.dts b/arch/arm/boot/dts/am572x-idk.dts index 8350b4b34b0852..9da6d83ca185e5 100644 --- a/arch/arm/boot/dts/am572x-idk.dts +++ b/arch/arm/boot/dts/am572x-idk.dts @@ -91,3 +91,23 @@ &pcie1 { gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; }; + +&mailbox5 { + status = "okay"; + mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { + status = "okay"; + }; + mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { + status = "okay"; + }; +}; + +&mailbox6 { + status = "okay"; + mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { + status = "okay"; + }; + mbox_dsp2_ipc3x: mbox_dsp2_ipc3x { + status = "okay"; + }; +}; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi index 585d792a8fdd12..fdfe5b16b80629 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi +++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi @@ -388,7 +388,7 @@ }; eeprom: eeprom@50 { - compatible = "at,24c32"; + compatible = "atmel,24c32"; reg = <0x50>; }; }; diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index cc011c8bc36bf4..5e815ccf72e141 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -137,29 +137,38 @@ }; gpio0: gpio@18100 { - compatible = "marvell,orion-gpio"; - reg = <0x18100 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18100 0x40>, <0x181c0 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <82>, <83>, <84>, <85>; + clocks = <&coreclk 0>; }; gpio1: gpio@18140 { - compatible = "marvell,orion-gpio"; - reg = <0x18140 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18140 0x40>, <0x181c8 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <87>, <88>, <89>, <90>; + clocks = <&coreclk 0>; }; gpio2: gpio@18180 { - compatible = "marvell,orion-gpio"; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; reg = <0x18180 0x40>; ngpios = <2>; gpio-controller; diff --git a/arch/arm/boot/dts/armada-385-linksys-caiman.dts b/arch/arm/boot/dts/armada-385-linksys-caiman.dts index f3cee918d28500..ee669ae61011f9 100644 --- a/arch/arm/boot/dts/armada-385-linksys-caiman.dts +++ b/arch/arm/boot/dts/armada-385-linksys-caiman.dts @@ -44,71 +44,128 @@ model = "Linksys WRT1200AC"; compatible = "linksys,caiman", "linksys,armada385", "marvell,armada385", "marvell,armada380"; +}; + +&expander0 { + wan_amber@0 { + label = "caiman:amber:wan"; + reg = <0x0>; + }; + + wan_white@1 { + label = "caiman:white:wan"; + reg = <0x1>; + }; + + wlan_2g@2 { + label = "caiman:white:wlan_2g"; + reg = <0x2>; + }; + + wlan_5g@3 { + label = "caiman:white:wlan_5g"; + reg = <0x3>; + }; + + usb2@5 { + label = "caiman:white:usb2"; + reg = <0x5>; + }; + + usb3_1@6 { + label = "caiman:white:usb3_1"; + reg = <0x6>; + }; + + usb3_2@7 { + label = "caiman:white:usb3_2"; + reg = <0x7>; + }; + + wps_white@8 { + label = "caiman:white:wps"; + reg = <0x8>; + }; + + wps_amber@9 { + label = "caiman:amber:wps"; + reg = <0x9>; + }; +}; + +&gpio_leds { + power { + label = "caiman:white:power"; + }; + + sata { + label = "caiman:white:sata"; + }; +}; + +&nand { + /* 128MiB */ + + partition@0 { + label = "u-boot"; + reg = <0x0000000 0x200000>; /* 2MiB */ + read-only; + }; + + partition@100000 { + label = "u_env"; + reg = <0x200000 0x40000>; /* 256KiB */ + }; + + partition@140000 { + label = "s_env"; + reg = <0x240000 0x40000>; /* 256KiB */ + }; + + partition@900000 { + label = "devinfo"; + reg = <0x900000 0x100000>; /* 1MiB */ + read-only; + }; + + /* kernel1 overlaps with rootfs1 by design */ + partition@a00000 { + label = "kernel1"; + reg = <0xa00000 0x2800000>; /* 40MiB */ + }; + + partition@1000000 { + label = "rootfs1"; + reg = <0x1000000 0x2200000>; /* 34MiB */ + }; + + /* kernel2 overlaps with rootfs2 by design */ + partition@3200000 { + label = "kernel2"; + reg = <0x3200000 0x2800000>; /* 40MiB */ + }; + + partition@3800000 { + label = "rootfs2"; + reg = <0x3800000 0x2200000>; /* 34MiB */ + }; + + /* + * 38MiB, last MiB is for the BBT, not writable + */ + partition@5a00000 { + label = "syscfg"; + reg = <0x5a00000 0x2600000>; + }; - soc { - internal-regs{ - i2c@11000 { - - pca9635@68 { - #address-cells = <1>; - #size-cells = <0>; - - wan_amber@0 { - label = "caiman:amber:wan"; - reg = <0x0>; - }; - - wan_white@1 { - label = "caiman:white:wan"; - reg = <0x1>; - }; - - wlan_2g@2 { - label = "caiman:white:wlan_2g"; - reg = <0x2>; - }; - - wlan_5g@3 { - label = "caiman:white:wlan_5g"; - reg = <0x3>; - }; - - usb2@5 { - label = "caiman:white:usb2"; - reg = <0x5>; - }; - - usb3_1@6 { - label = "caiman:white:usb3_1"; - reg = <0x6>; - }; - - usb3_2@7 { - label = "caiman:white:usb3_2"; - reg = <0x7>; - }; - - wps_white@8 { - label = "caiman:white:wps"; - reg = <0x8>; - }; - - wps_amber@9 { - label = "caiman:amber:wps"; - reg = <0x9>; - }; - }; - }; - }; - }; - - gpio-leds { - power { - label = "caiman:white:power"; - }; - - sata { - label = "caiman:white:sata"; - }; + /* + * Unused area between "s_env" and "devinfo". + * Moved here because otherwise the renumbered + * partitions would break the bootloader + * supplied bootargs + */ + partition@180000 { + label = "unused_area"; + reg = <0x280000 0x680000>; /* 6.5MiB */ }; }; diff --git a/arch/arm/boot/dts/armada-385-linksys-cobra.dts b/arch/arm/boot/dts/armada-385-linksys-cobra.dts index 11107186055980..5169ca89c55ac1 100644 --- a/arch/arm/boot/dts/armada-385-linksys-cobra.dts +++ b/arch/arm/boot/dts/armada-385-linksys-cobra.dts @@ -44,71 +44,128 @@ model = "Linksys WRT1900ACv2"; compatible = "linksys,cobra", "linksys,armada385", "marvell,armada385", "marvell,armada380"; +}; + +&expander0 { + wan_amber@0 { + label = "cobra:amber:wan"; + reg = <0x0>; + }; + + wan_white@1 { + label = "cobra:white:wan"; + reg = <0x1>; + }; + + wlan_2g@2 { + label = "cobra:white:wlan_2g"; + reg = <0x2>; + }; + + wlan_5g@3 { + label = "cobra:white:wlan_5g"; + reg = <0x3>; + }; + + usb2@5 { + label = "cobra:white:usb2"; + reg = <0x5>; + }; + + usb3_1@6 { + label = "cobra:white:usb3_1"; + reg = <0x6>; + }; + + usb3_2@7 { + label = "cobra:white:usb3_2"; + reg = <0x7>; + }; + + wps_white@8 { + label = "cobra:white:wps"; + reg = <0x8>; + }; + + wps_amber@9 { + label = "cobra:amber:wps"; + reg = <0x9>; + }; +}; + +&gpio_leds { + power { + label = "cobra:white:power"; + }; + + sata { + label = "cobra:white:sata"; + }; +}; + +&nand { + /* 128MiB */ + + partition@0 { + label = "u-boot"; + reg = <0x0000000 0x200000>; /* 2MiB */ + read-only; + }; + + partition@100000 { + label = "u_env"; + reg = <0x200000 0x40000>; /* 256KiB */ + }; + + partition@140000 { + label = "s_env"; + reg = <0x240000 0x40000>; /* 256KiB */ + }; + + partition@900000 { + label = "devinfo"; + reg = <0x900000 0x100000>; /* 1MiB */ + read-only; + }; + + /* kernel1 overlaps with rootfs1 by design */ + partition@a00000 { + label = "kernel1"; + reg = <0xa00000 0x2800000>; /* 40MiB */ + }; + + partition@1000000 { + label = "rootfs1"; + reg = <0x1000000 0x2200000>; /* 34MiB */ + }; + + /* kernel2 overlaps with rootfs2 by design */ + partition@3200000 { + label = "kernel2"; + reg = <0x3200000 0x2800000>; /* 40MiB */ + }; + + partition@3800000 { + label = "rootfs2"; + reg = <0x3800000 0x2200000>; /* 34MiB */ + }; + + /* + * 38MiB, last MiB is for the BBT, not writable + */ + partition@5a00000 { + label = "syscfg"; + reg = <0x5a00000 0x2600000>; + }; - soc { - internal-regs{ - i2c@11000 { - - pca9635@68 { - #address-cells = <1>; - #size-cells = <0>; - - wan_amber@0 { - label = "cobra:amber:wan"; - reg = <0x0>; - }; - - wan_white@1 { - label = "cobra:white:wan"; - reg = <0x1>; - }; - - wlan_2g@2 { - label = "cobra:white:wlan_2g"; - reg = <0x2>; - }; - - wlan_5g@3 { - label = "cobra:white:wlan_5g"; - reg = <0x3>; - }; - - usb2@5 { - label = "cobra:white:usb2"; - reg = <0x5>; - }; - - usb3_1@6 { - label = "cobra:white:usb3_1"; - reg = <0x6>; - }; - - usb3_2@7 { - label = "cobra:white:usb3_2"; - reg = <0x7>; - }; - - wps_white@8 { - label = "cobra:white:wps"; - reg = <0x8>; - }; - - wps_amber@9 { - label = "cobra:amber:wps"; - reg = <0x9>; - }; - }; - }; - }; - }; - - gpio-leds { - power { - label = "cobra:white:power"; - }; - - sata { - label = "cobra:white:sata"; - }; + /* + * Unused area between "s_env" and "devinfo". + * Moved here because otherwise the renumbered + * partitions would break the bootloader + * supplied bootargs + */ + partition@180000 { + label = "unused_area"; + reg = <0x280000 0x680000>; /* 6.5MiB */ }; }; diff --git a/arch/arm/boot/dts/armada-385-linksys-rango.dts b/arch/arm/boot/dts/armada-385-linksys-rango.dts new file mode 100644 index 00000000000000..da8a0f3d432bec --- /dev/null +++ b/arch/arm/boot/dts/armada-385-linksys-rango.dts @@ -0,0 +1,203 @@ +/* + * Device Tree file for the Linksys WRT3200ACM (Rango) + * + * Copyright (C) 2016 Imre Kaloz + * + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without + * any warranty of any kind, whether express or implied. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include +#include +#include "armada-385-linksys.dtsi" + +/ { + model = "Linksys WRT3200ACM"; + compatible = "linksys,rango", "linksys,armada385", "marvell,armada385", + "marvell,armada380"; +}; + +&expander0 { + wan_amber@0 { + label = "rango:amber:wan"; + reg = <0x0>; + }; + + wan_white@1 { + label = "rango:white:wan"; + reg = <0x1>; + }; + + usb2@5 { + label = "rango:white:usb2"; + reg = <0x5>; + }; + + usb3_1@6 { + label = "rango:white:usb3_1"; + reg = <0x6>; + }; + + usb3_2@7 { + label = "rango:white:usb3_2"; + reg = <0x7>; + }; + + wps_white@8 { + label = "rango:white:wps"; + reg = <0x8>; + }; + + wps_amber@9 { + label = "rango:amber:wps"; + reg = <0x9>; + }; +}; + +&gpio_leds { + power { + gpios = <&gpio1 24 GPIO_ACTIVE_HIGH>; + label = "rango:white:power"; + }; + + sata { + gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + label = "rango:white:sata"; + }; + + wlan_2g { + gpios = <&gpio1 13 GPIO_ACTIVE_LOW>; + label = "rango:white:wlan_2g"; + }; + + wlan_5g { + gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; + label = "rango:white:wlan_5g"; + }; +}; + +&gpio_leds_pins { + marvell,pins = "mpp21", "mpp45", "mpp46", "mpp56"; +}; + +&nand { + /* AMD/Spansion S34ML02G2 256MiB, OEM Layout */ + + partition@0 { + label = "u-boot"; + reg = <0x0000000 0x200000>; /* 2MiB */ + read-only; + }; + + partition@200000 { + label = "u_env"; + reg = <0x200000 0x20000>; /* 128KiB */ + }; + + partition@220000 { + label = "s_env"; + reg = <0x220000 0x40000>; /* 256KiB */ + }; + + partition@7e0000 { + label = "devinfo"; + reg = <0x7e0000 0x40000>; /* 256KiB */ + read-only; + }; + + partition@820000 { + label = "sysdiag"; + reg = <0x820000 0x1e0000>; /* 1920KiB */ + read-only; + }; + + /* kernel1 overlaps with rootfs1 by design */ + partition@a00000 { + label = "kernel1"; + reg = <0xa00000 0x5000000>; /* 80MiB */ + }; + + partition@1000000 { + label = "rootfs1"; + reg = <0x1000000 0x4a00000>; /* 74MiB */ + }; + + /* kernel2 overlaps with rootfs2 by design */ + partition@5a00000 { + label = "kernel2"; + reg = <0x5a00000 0x5000000>; /* 80MiB */ + }; + + partition@6000000 { + label = "rootfs2"; + reg = <0x6000000 0x4a00000>; /* 74MiB */ + }; + + /* + * 86MiB, last MiB is for the BBT, not writable + */ + partition@aa00000 { + label = "syscfg"; + reg = <0xaa00000 0x5600000>; + }; + + /* + * Unused area between "s_env" and "devinfo". + * Moved here because otherwise the renumbered + * partitions would break the bootloader + * supplied bootargs + */ + partition@180000 { + label = "unused_area"; + reg = <0x260000 0x5c0000>; /* 5.75MiB */ + }; +}; + +&sdhci { + pinctrl-names = "default"; + pinctrl-0 = <&sdhci_pins>; + no-1-8-v; + non-removable; + wp-inverted; + bus-width = <8>; + status = "okay"; +}; + +&usb3_1_vbus { + gpio = <&gpio1 12 GPIO_ACTIVE_HIGH>; +}; + +&usb3_1_vbus_pins { + marvell,pins = "mpp44"; +}; diff --git a/arch/arm/boot/dts/armada-385-linksys-shelby.dts b/arch/arm/boot/dts/armada-385-linksys-shelby.dts index c7a8ddd7f9a554..94aa35bc0bffd0 100644 --- a/arch/arm/boot/dts/armada-385-linksys-shelby.dts +++ b/arch/arm/boot/dts/armada-385-linksys-shelby.dts @@ -44,71 +44,128 @@ model = "Linksys WRT1900ACS"; compatible = "linksys,shelby", "linksys,armada385", "marvell,armada385", "marvell,armada380"; +}; + +&expander0 { + wan_amber@0 { + label = "shelby:amber:wan"; + reg = <0x0>; + }; + + wan_white@1 { + label = "shelby:white:wan"; + reg = <0x1>; + }; + + wlan_2g@2 { + label = "shelby:white:wlan_2g"; + reg = <0x2>; + }; + + wlan_5g@3 { + label = "shelby:white:wlan_5g"; + reg = <0x3>; + }; + + usb2@5 { + label = "shelby:white:usb2"; + reg = <0x5>; + }; + + usb3_1@6 { + label = "shelby:white:usb3_1"; + reg = <0x6>; + }; + + usb3_2@7 { + label = "shelby:white:usb3_2"; + reg = <0x7>; + }; + + wps_white@8 { + label = "shelby:white:wps"; + reg = <0x8>; + }; + + wps_amber@9 { + label = "shelby:amber:wps"; + reg = <0x9>; + }; +}; + +&gpio_leds { + power { + label = "shelby:white:power"; + }; + + sata { + label = "shelby:white:sata"; + }; +}; + +&nand { + /* 128MiB */ + + partition@0 { + label = "u-boot"; + reg = <0x0000000 0x200000>; /* 2MiB */ + read-only; + }; + + partition@100000 { + label = "u_env"; + reg = <0x200000 0x40000>; /* 256KiB */ + }; + + partition@140000 { + label = "s_env"; + reg = <0x240000 0x40000>; /* 256KiB */ + }; + + partition@900000 { + label = "devinfo"; + reg = <0x900000 0x100000>; /* 1MiB */ + read-only; + }; + + /* kernel1 overlaps with rootfs1 by design */ + partition@a00000 { + label = "kernel1"; + reg = <0xa00000 0x2800000>; /* 40MiB */ + }; + + partition@1000000 { + label = "rootfs1"; + reg = <0x1000000 0x2200000>; /* 34MiB */ + }; + + /* kernel2 overlaps with rootfs2 by design */ + partition@3200000 { + label = "kernel2"; + reg = <0x3200000 0x2800000>; /* 40MiB */ + }; + + partition@3800000 { + label = "rootfs2"; + reg = <0x3800000 0x2200000>; /* 34MiB */ + }; + + /* + * 38MiB, last MiB is for the BBT, not writable + */ + partition@5a00000 { + label = "syscfg"; + reg = <0x5a00000 0x2600000>; + }; - soc { - internal-regs{ - i2c@11000 { - - pca9635@68 { - #address-cells = <1>; - #size-cells = <0>; - - wan_amber@0 { - label = "shelby:amber:wan"; - reg = <0x0>; - }; - - wan_white@1 { - label = "shelby:white:wan"; - reg = <0x1>; - }; - - wlan_2g@2 { - label = "shelby:white:wlan_2g"; - reg = <0x2>; - }; - - wlan_5g@3 { - label = "shelby:white:wlan_5g"; - reg = <0x3>; - }; - - usb2@5 { - label = "shelby:white:usb2"; - reg = <0x5>; - }; - - usb3_1@6 { - label = "shelby:white:usb3_1"; - reg = <0x6>; - }; - - usb3_2@7 { - label = "shelby:white:usb3_2"; - reg = <0x7>; - }; - - wps_white@8 { - label = "shelby:white:wps"; - reg = <0x8>; - }; - - wps_amber@9 { - label = "shelby:amber:wps"; - reg = <0x9>; - }; - }; - }; - }; - }; - - gpio-leds { - power { - label = "shelby:white:power"; - }; - - sata { - label = "shelby:white:sata"; - }; + /* + * Unused area between "s_env" and "devinfo". + * Moved here because otherwise the renumbered + * partitions would break the bootloader + * supplied bootargs + */ + partition@180000 { + label = "unused_area"; + reg = <0x280000 0x680000>; /* 6.5MiB */ }; }; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 2306c45685b1f1..e1f355ffc8f7e0 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -52,7 +52,7 @@ memory { device_type = "memory"; - reg = <0x00000000 0x20000000>; /* 512 MB */ + reg = <0x00000000 0x20000000>; /* 512 MiB */ }; soc { @@ -61,255 +61,45 @@ MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000 MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>; - - internal-regs { - i2c@11000 { - pinctrl-names = "default"; - pinctrl-0 = <&i2c0_pins>; - status = "okay"; - - tmp421@4c { - compatible = "ti,tmp421"; - reg = <0x4c>; - }; - - pca9635@68 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "nxp,pca9635"; - reg = <0x68>; - }; - }; - - /* J10: VCC, NC, RX, NC, TX, GND */ - serial@12000 { - status = "okay"; - }; - - ethernet@70000 { - status = "okay"; - phy-mode = "rgmii-id"; - buffer-manager = <&bm>; - bm,pool-long = <2>; - bm,pool-short = <3>; - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - - ethernet@34000 { - status = "okay"; - phy-mode = "sgmii"; - buffer-manager = <&bm>; - bm,pool-long = <0>; - bm,pool-short = <1>; - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - - mdio@72004 { - status = "okay"; - - switch@0 { - compatible = "marvell,mv88e6085"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "lan4"; - }; - - port@1 { - reg = <1>; - label = "lan3"; - }; - - port@2 { - reg = <2>; - label = "lan2"; - }; - - port@3 { - reg = <3>; - label = "lan1"; - }; - - port@4 { - reg = <4>; - label = "wan"; - }; - - port@5 { - reg = <5>; - label = "cpu"; - ethernet = <ð2>; - - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - }; - }; - }; - - sata@a8000 { - status = "okay"; - }; - - bm@c8000 { - status = "okay"; - }; - - /* USB part of the eSATA/USB 2.0 port */ - usb@58000 { - status = "okay"; - }; - - usb3@f8000 { - status = "okay"; - usb-phy = <&usb3_phy>; - }; - - flash@d0000 { - status = "okay"; - num-cs = <1>; - marvell,nand-keep-config; - marvell,nand-enable-arbiter; - nand-on-flash-bbt; - - partition@0 { - label = "u-boot"; - reg = <0x0000000 0x200000>; /* 2MB */ - read-only; - }; - - partition@100000 { - label = "u_env"; - reg = <0x200000 0x40000>; /* 256KB */ - }; - - partition@140000 { - label = "s_env"; - reg = <0x240000 0x40000>; /* 256KB */ - }; - - partition@900000 { - label = "devinfo"; - reg = <0x900000 0x100000>; /* 1MB */ - read-only; - }; - - /* kernel1 overlaps with rootfs1 by design */ - partition@a00000 { - label = "kernel1"; - reg = <0xa00000 0x2800000>; /* 40MB */ - }; - - partition@1000000 { - label = "rootfs1"; - reg = <0x1000000 0x2200000>; /* 34MB */ - }; - - /* kernel2 overlaps with rootfs2 by design */ - partition@3200000 { - label = "kernel2"; - reg = <0x3200000 0x2800000>; /* 40MB */ - }; - - partition@3800000 { - label = "rootfs2"; - reg = <0x3800000 0x2200000>; /* 34MB */ - }; - - /* - * 38MB, last MB is for the BBT, not writable - */ - partition@5a00000 { - label = "syscfg"; - reg = <0x5a00000 0x2600000>; - }; - - /* - * Unused area between "s_env" and "devinfo". - * Moved here because otherwise the renumbered - * partitions would break the bootloader - * supplied bootargs - */ - partition@180000 { - label = "unused_area"; - reg = <0x280000 0x680000>; /* 6.5MB */ - }; - }; - }; - - bm-bppi { - status = "okay"; - }; - - pcie-controller { - status = "okay"; - - pcie@1,0 { - /* Marvell 88W8864, 5GHz-only */ - status = "okay"; - }; - - pcie@2,0 { - /* Marvell 88W8864, 2GHz-only */ - status = "okay"; - }; - }; }; - usb3_phy: usb3_phy { + usb3_1_phy: usb3_1-phy { compatible = "usb-nop-xceiv"; - vcc-supply = <®_xhci0_vbus>; + vcc-supply = <&usb3_1_vbus>; }; - reg_xhci0_vbus: xhci0-vbus { + usb3_1_vbus: usb3_1-vbus { compatible = "regulator-fixed"; pinctrl-names = "default"; - pinctrl-0 = <&xhci0_vbus_pins>; - regulator-name = "xhci0-vbus"; + pinctrl-0 = <&usb3_1_vbus_pins>; + regulator-name = "usb3_1-vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&gpio1 18 GPIO_ACTIVE_HIGH>; }; - gpio_keys { + gpio_keys: gpio-keys { compatible = "gpio-keys"; - #address-cells = <1>; - #size-cells = <0>; - pinctrl-0 = <&keys_pin>; + pinctrl-0 = <&gpio_keys_pins>; pinctrl-names = "default"; - button@1 { + wps { label = "WPS"; linux,code = ; gpios = <&gpio0 24 GPIO_ACTIVE_LOW>; }; - button@2 { + reset { label = "Factory Reset Button"; linux,code = ; gpios = <&gpio0 29 GPIO_ACTIVE_LOW>; }; }; - gpio-leds { + gpio_leds: gpio-leds { compatible = "gpio-leds"; - pinctrl-0 = <&power_led_pin &sata_led_pin>; + pinctrl-0 = <&gpio_leds_pins>; pinctrl-names = "default"; power { @@ -323,21 +113,83 @@ linux,default-trigger = "disk-activity"; }; }; +}; - dsa@0 { - status = "disabled"; +&ahci0 { + status = "okay"; +}; + +&bm { + status = "okay"; +}; - compatible = "marvell,dsa"; - #address-cells = <2>; +&bm_bppi { + status = "okay"; +}; + +ð0 { + status = "okay"; + phy-mode = "rgmii-id"; + buffer-manager = <&bm>; + bm,pool-long = <0>; + bm,pool-short = <1>; + fixed-link { + speed = <1000>; + full-duplex; + }; +}; + +ð2 { + status = "okay"; + phy-mode = "sgmii"; + buffer-manager = <&bm>; + bm,pool-long = <2>; + bm,pool-short = <3>; + fixed-link { + speed = <1000>; + full-duplex; + }; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; + status = "okay"; + + tmp421@4c { + compatible = "ti,tmp421"; + reg = <0x4c>; + }; + + expander0: pca9635@68 { + #address-cells = <1>; #size-cells = <0>; + compatible = "nxp,pca9635"; + reg = <0x68>; + }; +}; + +&nand { + /* 128MiB or 256MiB */ + status = "okay"; + num-cs = <1>; + marvell,nand-keep-config; + marvell,nand-enable-arbiter; + nand-on-flash-bbt; +}; - dsa,ethernet = <ð2>; - dsa,mii-bus = <&mdio>; +&mdio { + status = "okay"; - switch@0 { + switch@0 { + compatible = "marvell,mv88e6085"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + ports { #address-cells = <1>; #size-cells = <0>; - reg = <0x0 0>; /* MDIO address 0, switch 0 in tree */ port@0 { reg = <0>; @@ -367,28 +219,45 @@ port@5 { reg = <5>; label = "cpu"; + ethernet = <ð2>; + + fixed-link { + speed = <1000>; + full-duplex; + }; }; }; }; }; +&pciec { + status = "okay"; +}; + +&pcie1 { + /* Marvell 88W8864, 5GHz-only */ + status = "okay"; +}; + +&pcie2 { + /* Marvell 88W8864, 2GHz-only */ + status = "okay"; +}; + &pinctrl { - keys_pin: keys-pin { + gpio_keys_pins: gpio-keys-pins { + /* mpp24: wps, mpp29: reset */ marvell,pins = "mpp24", "mpp29"; marvell,function = "gpio"; }; - power_led_pin: power-led-pin { - marvell,pins = "mpp55"; - marvell,function = "gpio"; - }; - - sata_led_pin: sata-led-pin { - marvell,pins = "mpp54"; + gpio_leds_pins: gpio-leds-pins { + /* mpp54: sata, mpp55: power */ + marvell,pins = "mpp54", "mpp55"; marvell,function = "gpio"; }; - xhci0_vbus_pins: xhci0-vbus-pins { + usb3_1_vbus_pins: usb3_1-vbus-pins { marvell,pins = "mpp50"; marvell,function = "gpio"; }; @@ -397,3 +266,18 @@ &spi0 { status = "disabled"; }; + +&uart0 { + /* J10: VCC, NC, RX, NC, TX, GND */ + status = "okay"; +}; + +&usb0 { + /* USB part of the eSATA/USB 2.0 port */ + status = "okay"; +}; + +&usb3_1 { + status = "okay"; + usb-phy = <&usb3_1_phy>; +}; diff --git a/arch/arm/boot/dts/armada-xp-98dx3236.dtsi b/arch/arm/boot/dts/armada-xp-98dx3236.dtsi index 84cc232a29e9e3..be22ec5236acfe 100644 --- a/arch/arm/boot/dts/armada-xp-98dx3236.dtsi +++ b/arch/arm/boot/dts/armada-xp-98dx3236.dtsi @@ -311,6 +311,10 @@ reg = <0x20a00 0x2d0>, <0x21070 0x58>; }; +&rtc { + status = "disabled"; +}; + &timer { compatible = "marvell,armada-xp-timer"; clocks = <&coreclk 2>, <&refclk>; diff --git a/arch/arm/boot/dts/armada-xp-98dx4251.dtsi b/arch/arm/boot/dts/armada-xp-98dx4251.dtsi index 51de91b31a9d22..bc9f824020ebee 100644 --- a/arch/arm/boot/dts/armada-xp-98dx4251.dtsi +++ b/arch/arm/boot/dts/armada-xp-98dx4251.dtsi @@ -87,4 +87,5 @@ &pp0 { compatible = "marvell,prestera-98dx4251"; + interrupts = <33>, <34>, <35>, <36>; }; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 9efcf59c9b442e..6d705f5182548a 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -308,13 +308,11 @@ }; }; - gpio_fan { + pwm_fan { /* SUNON HA4010V4-0000-C99 */ - compatible = "gpio-fan"; - gpios = <&gpio0 24 0>; - gpio-fan,speed-map = <0 0 - 4500 1>; + compatible = "pwm-fan"; + pwms = <&gpio0 24 4000>; }; dsa { diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi index 07c5090ecd29e7..f77168c9add443 100644 --- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi @@ -202,25 +202,33 @@ internal-regs { gpio0: gpio@18100 { - compatible = "marvell,orion-gpio"; - reg = <0x18100 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18100 0x40>, <0x181c0 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <82>, <83>, <84>, <85>; + clocks = <&coreclk 0>; }; gpio1: gpio@18140 { - compatible = "marvell,orion-gpio"; - reg = <0x18140 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18140 0x40>, <0x181c8 0x08>; + reg-names = "gpio", "pwm"; ngpios = <17>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <87>, <88>, <89>; + clocks = <&coreclk 0>; }; }; }; diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi index 64e936ae7b22d6..0ecfaf49d23985 100644 --- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi @@ -285,29 +285,38 @@ internal-regs { gpio0: gpio@18100 { - compatible = "marvell,orion-gpio"; - reg = <0x18100 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18100 0x40>, <0x181c0 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <82>, <83>, <84>, <85>; + clocks = <&coreclk 0>; }; gpio1: gpio@18140 { - compatible = "marvell,orion-gpio"; - reg = <0x18140 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18140 0x40>, <0x181c8 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <87>, <88>, <89>, <90>; + clocks = <&coreclk 0>; }; gpio2: gpio@18180 { - compatible = "marvell,orion-gpio"; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; reg = <0x18180 0x40>; ngpios = <3>; gpio-controller; diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi index d1383dde43eb91..670ece4c6fa704 100644 --- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi @@ -323,29 +323,38 @@ internal-regs { gpio0: gpio@18100 { - compatible = "marvell,orion-gpio"; - reg = <0x18100 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18100 0x40>, <0x181c0 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <82>, <83>, <84>, <85>; + clocks = <&coreclk 0>; }; gpio1: gpio@18140 { - compatible = "marvell,orion-gpio"; - reg = <0x18140 0x40>; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; + reg = <0x18140 0x40>, <0x181c8 0x08>; + reg-names = "gpio", "pwm"; ngpios = <32>; gpio-controller; #gpio-cells = <2>; + #pwm-cells = <2>; interrupt-controller; #interrupt-cells = <2>; interrupts = <87>, <88>, <89>, <90>; + clocks = <&coreclk 0>; }; gpio2: gpio@18180 { - compatible = "marvell,orion-gpio"; + compatible = "marvell,armada-370-xp-gpio", + "marvell,orion-gpio"; reg = <0x18180 0x40>; ngpios = <3>; gpio-controller; diff --git a/arch/arm/boot/dts/at91-linea.dtsi b/arch/arm/boot/dts/at91-linea.dtsi index 0721c84725099f..9bf9aaeff3e8f0 100644 --- a/arch/arm/boot/dts/at91-linea.dtsi +++ b/arch/arm/boot/dts/at91-linea.dtsi @@ -31,7 +31,7 @@ status = "okay"; eeprom@51 { - compatible = "st,24c64"; + compatible = "st,24c64", "atmel,24c64"; reg = <0x51>; pagesize = <32>; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index 0bef9e0b89c608..37de94fc9b5ad4 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -258,6 +258,12 @@ status = "okay"; }; + can0: can@f8054000 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_can0_default>; + status = "okay"; + }; + uart3: serial@fc008000 { atmel,use-dma-rx; atmel,use-dma-tx; @@ -322,6 +328,18 @@ bias-disable; }; + pinctrl_can0_default: can0_default { + pinmux = , + ; + bias-disable; + }; + + pinctrl_can1_default: can1_default { + pinmux = , + ; + bias-disable; + }; + pinctrl_charger_chglev: charger_chglev { pinmux = ; bias-disable; @@ -469,6 +487,12 @@ }; }; + + can1: can@fc050000 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_can1_default>; + status = "okay"; + }; }; }; diff --git a/arch/arm/boot/dts/at91-tse850-3.dts b/arch/arm/boot/dts/at91-tse850-3.dts index 498fba3e52b58b..a5c0dd63025382 100644 --- a/arch/arm/boot/dts/at91-tse850-3.dts +++ b/arch/arm/boot/dts/at91-tse850-3.dts @@ -239,7 +239,7 @@ }; eeprom@50 { - compatible = "nxp,24c02"; + compatible = "nxp,24c02", "atmel,24c02"; reg = <0x50>; pagesize = <16>; }; diff --git a/arch/arm/boot/dts/axp209.dtsi b/arch/arm/boot/dts/axp209.dtsi index 9677dd5cf6b659..3c8fa26e87b70c 100644 --- a/arch/arm/boot/dts/axp209.dtsi +++ b/arch/arm/boot/dts/axp209.dtsi @@ -64,6 +64,11 @@ #gpio-cells = <2>; }; + battery_power_supply: battery-power-supply { + compatible = "x-powers,axp209-battery-power-supply"; + status = "disabled"; + }; + regulators { /* Default work frequency for buck regulators */ x-powers,dcdc-freq = <1500>; diff --git a/arch/arm/boot/dts/axp22x.dtsi b/arch/arm/boot/dts/axp22x.dtsi index 67331c5f171478..87fb08e812eccc 100644 --- a/arch/arm/boot/dts/axp22x.dtsi +++ b/arch/arm/boot/dts/axp22x.dtsi @@ -57,6 +57,11 @@ status = "disabled"; }; + battery_power_supply: battery-power-supply { + compatible = "x-powers,axp221-battery-power-supply"; + status = "disabled"; + }; + regulators { /* Default work frequency for buck regulators */ x-powers,dcdc-freq = <3000>; diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index a7b5ce133784f1..e55b362b9d6e92 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -65,13 +65,13 @@ &sdhci { pinctrl-names = "default"; pinctrl-0 = <&emmc_gpio48>; - status = "okay"; bus-width = <4>; }; &sdhost { pinctrl-names = "default"; pinctrl-0 = <&sdhost_gpio48>; + status = "okay"; bus-width = <4>; }; diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi index 0890d97e674d4b..659b6e9513b1d2 100644 --- a/arch/arm/boot/dts/bcm2835.dtsi +++ b/arch/arm/boot/dts/bcm2835.dtsi @@ -24,6 +24,10 @@ }; }; +&cpu_thermal { + coefficients = <(-538) 407000>; +}; + /* enable thermal sensor with the correct compatible property set */ &thermal { compatible = "brcm,bcm2835-thermal"; diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi index 519a44f5d25a6a..da3deeb4259292 100644 --- a/arch/arm/boot/dts/bcm2836.dtsi +++ b/arch/arm/boot/dts/bcm2836.dtsi @@ -77,6 +77,10 @@ interrupts = <8>; }; +&cpu_thermal { + coefficients = <(-538) 407000>; +}; + /* enable thermal sensor with the correct compatible property set */ &thermal { compatible = "brcm,bcm2836-thermal"; diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts new file mode 100644 index 00000000000000..c72a27d908b6f1 --- /dev/null +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts @@ -0,0 +1 @@ +#include "arm64/broadcom/bcm2837-rpi-3-b.dts" diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 561f27d8d92224..cc721a4e02dbdd 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -3,6 +3,11 @@ #include #include +/* firmware-provided startup stubs live here, where the secondary CPUs are + * spinning. + */ +/memreserve/ 0x00000000 0x00001000; + /* This include file covers the common peripherals and configuration between * bcm2835 and bcm2836 implementations, leaving the CPU configuration to * bcm2835.dtsi and bcm2836.dtsi. @@ -19,6 +24,26 @@ bootargs = "earlyprintk console=ttyAMA0"; }; + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <0>; + polling-delay = <1000>; + + thermal-sensors = <&thermal>; + + trips { + cpu-crit { + temperature = <80000>; + hysteresis = <0>; + type = "critical"; + }; + }; + + cooling-maps { + }; + }; + }; + soc { compatible = "simple-bus"; #address-cells = <1>; @@ -430,6 +455,7 @@ compatible = "brcm,bcm2835-thermal"; reg = <0x7e212000 0x8>; clocks = <&clocks BCM2835_CLOCK_TSENS>; + #thermal-sensor-cells = <0>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 31a9e061ddd0d0..f47fc4daf0628a 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -529,7 +529,8 @@ }; &usb1 { - dr_mode = "peripheral"; + dr_mode = "otg"; + extcon = <&extcon_usb1>; }; &usb2 { diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index e7144662af45cc..0f0f6f58bd187d 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -99,14 +99,14 @@ compatible = "operating-points-v2-ti-cpu"; syscon = <&scm_wkup>; - opp_nom@1000000000 { + opp_nom-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <1060000 850000 1150000>; opp-supported-hw = <0xFF 0x01>; opp-suspend; }; - opp_od@1176000000 { + opp_od-1176000000 { opp-hz = /bits/ 64 <1176000000>; opp-microvolt = <1160000 885000 1160000>; opp-supported-hw = <0xFF 0x02>; diff --git a/arch/arm/boot/dts/dra72-evm-common.dtsi b/arch/arm/boot/dts/dra72-evm-common.dtsi index ad24544adf0f10..85780549bc2635 100644 --- a/arch/arm/boot/dts/dra72-evm-common.dtsi +++ b/arch/arm/boot/dts/dra72-evm-common.dtsi @@ -392,7 +392,8 @@ }; &usb1 { - dr_mode = "peripheral"; + dr_mode = "otg"; + extcon = <&extcon_usb1>; }; &usb2 { diff --git a/arch/arm/boot/dts/emev2.dtsi b/arch/arm/boot/dts/emev2.dtsi index 0124faf175c861..42ea246e71cb4e 100644 --- a/arch/arm/boot/dts/emev2.dtsi +++ b/arch/arm/boot/dts/emev2.dtsi @@ -197,7 +197,7 @@ clock-names = "sclk"; }; - pfc: pfc@e0140200 { + pfc: pin-controller@e0140200 { compatible = "renesas,pfc-emev2"; reg = <0xe0140200 0x100>; }; diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts index 6098dacd09f11c..6a432460eb77b9 100644 --- a/arch/arm/boot/dts/exynos5250-arndale.dts +++ b/arch/arm/boot/dts/exynos5250-arndale.dts @@ -14,7 +14,6 @@ #include #include #include "exynos5250.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Insignal Arndale evaluation board based on EXYNOS5250"; diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts index a97a785ccc6ba8..6632f657394e6d 100644 --- a/arch/arm/boot/dts/exynos5250-smdk5250.dts +++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts @@ -13,7 +13,6 @@ #include #include #include "exynos5250.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { model = "SAMSUNG SMDK5250 board based on EXYNOS5250"; diff --git a/arch/arm/boot/dts/exynos5250-spring.dts b/arch/arm/boot/dts/exynos5250-spring.dts index 4d7bdb735ed3b6..95c3bcace9dcbe 100644 --- a/arch/arm/boot/dts/exynos5250-spring.dts +++ b/arch/arm/boot/dts/exynos5250-spring.dts @@ -14,7 +14,6 @@ #include #include #include "exynos5250.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Google Spring"; diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts index 9cc83c51c92523..ee1bb9b8b36681 100644 --- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts +++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts @@ -16,7 +16,6 @@ #include #include #include -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Insignal Arndale Octa evaluation board based on EXYNOS5420"; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index 1f964ec35c5ec8..2cd65699a29cb3 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -16,7 +16,6 @@ #include #include "exynos5420.dtsi" #include "exynos5420-cpus.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Google Peach Pit Rev 6+"; diff --git a/arch/arm/boot/dts/exynos5420-smdk5420.dts b/arch/arm/boot/dts/exynos5420-smdk5420.dts index aaccd0da41e545..08c8ab173e871f 100644 --- a/arch/arm/boot/dts/exynos5420-smdk5420.dts +++ b/arch/arm/boot/dts/exynos5420-smdk5420.dts @@ -13,7 +13,6 @@ #include "exynos5420.dtsi" #include "exynos5420-cpus.dtsi" #include -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Samsung SMDK5420 board based on EXYNOS5420"; diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi index 05b9afdd67577e..657535e2e3cc80 100644 --- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi +++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi @@ -18,7 +18,6 @@ #include #include "exynos5800.dtsi" #include "exynos5422-cpus.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { memory@40000000 { diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts index f9ff7f07ae0c4c..ecf1c916e8fc34 100644 --- a/arch/arm/boot/dts/exynos5800-peach-pi.dts +++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts @@ -16,7 +16,6 @@ #include #include "exynos5800.dtsi" #include "exynos5420-cpus.dtsi" -#include "exynos-mfc-reserved-memory.dtsi" / { model = "Google Peach Pi Rev 10+"; diff --git a/arch/arm/boot/dts/imx6dl-gw560x.dts b/arch/arm/boot/dts/imx6dl-gw560x.dts new file mode 100644 index 00000000000000..21bdfaf8df53d3 --- /dev/null +++ b/arch/arm/boot/dts/imx6dl-gw560x.dts @@ -0,0 +1,55 @@ +/* + * Copyright 2017 Gateworks Corporation + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this file; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, + * MA 02110-1301 USA + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include "imx6dl.dtsi" +#include "imx6qdl-gw560x.dtsi" + +/ { + model = "Gateworks Ventana i.MX6 DualLite/Solo GW560X"; + compatible = "gw,imx6dl-gw560x", "gw,ventana", "fsl,imx6dl"; +}; diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index 8e84713f42c069..687ab911c13f99 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -19,7 +19,6 @@ /* these are used by bootloader for disabling nodes */ aliases { - ethernet1 = ð1; i2c0 = &i2c1; i2c1 = &i2c2; i2c2 = &i2c3; @@ -347,10 +346,6 @@ &pcie { reset-gpio = <&gpio1 29 GPIO_ACTIVE_LOW>; status = "okay"; - - eth1: sky2@8 { /* MAC/PHY on bus 8 */ - compatible = "marvell,sky2"; - }; }; &ssi1 { diff --git a/arch/arm/boot/dts/imx6q-gw560x.dts b/arch/arm/boot/dts/imx6q-gw560x.dts new file mode 100644 index 00000000000000..735f2bbf143970 --- /dev/null +++ b/arch/arm/boot/dts/imx6q-gw560x.dts @@ -0,0 +1,59 @@ +/* + * Copyright 2017 Gateworks Corporation + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this file; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, + * MA 02110-1301 USA + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include "imx6q.dtsi" +#include "imx6qdl-gw560x.dtsi" + +/ { + model = "Gateworks Ventana i.MX6 Dual/Quad GW560X"; + compatible = "gw,imx6q-gw560x", "gw,ventana", "fsl,imx6q"; +}; + +&sata { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi index e9a5d0b8c7b059..dd33849335b217 100644 --- a/arch/arm/boot/dts/imx6q.dtsi +++ b/arch/arm/boot/dts/imx6q.dtsi @@ -125,7 +125,7 @@ clocks = <&clks IMX6QDL_CLK_OPENVG_AXI>, <&clks IMX6QDL_CLK_GPU2D_CORE>; clock-names = "bus", "core"; - power-domains = <&gpc 1>; + power-domains = <&pd_pu>; }; ipu2: ipu@02800000 { diff --git a/arch/arm/boot/dts/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/imx6qdl-colibri.dtsi index e8078758f26cfd..ad84eddb6836f0 100644 --- a/arch/arm/boot/dts/imx6qdl-colibri.dtsi +++ b/arch/arm/boot/dts/imx6qdl-colibri.dtsi @@ -254,6 +254,7 @@ clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_2p5v>; VDDIO-supply = <®_3p3v>; + lrclk-strength = <3>; }; /* STMPE811 touch screen controller */ diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index a208e7e0dc6e2c..5bc6ed1a5b35ad 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -14,7 +14,6 @@ / { /* these are used by bootloader for disabling nodes */ aliases { - ethernet1 = ð1; led0 = &led0; led1 = &led1; led2 = &led2; @@ -342,10 +341,6 @@ pinctrl-0 = <&pinctrl_pcie>; reset-gpio = <&gpio1 29 GPIO_ACTIVE_LOW>; status = "okay"; - - eth1: sky2@8 { /* MAC/PHY on bus 8 */ - compatible = "marvell,sky2"; - }; }; &pwm2 { diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index 968fda94d14bfb..66fcf838e96450 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -14,7 +14,6 @@ / { /* these are used by bootloader for disabling nodes */ aliases { - ethernet1 = ð1; led0 = &led0; led1 = &led1; led2 = &led2; @@ -379,10 +378,6 @@ pinctrl-0 = <&pinctrl_pcie>; reset-gpio = <&gpio1 29 GPIO_ACTIVE_LOW>; status = "okay"; - - eth1: sky2@8 { /* MAC/PHY on bus 8 */ - compatible = "marvell,sky2"; - }; }; &pwm1 { diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi new file mode 100644 index 00000000000000..d894dde6e85d37 --- /dev/null +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -0,0 +1,749 @@ +/* + * Copyright 2017 Gateworks Corporation + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this file; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, + * MA 02110-1301 USA + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include +#include + +/ { + /* these are used by bootloader for disabling nodes */ + aliases { + led0 = &led0; + led1 = &led1; + led2 = &led2; + ssi0 = &ssi1; + usb0 = &usbh1; + usb1 = &usbotg; + }; + + chosen { + stdout-path = &uart2; + }; + + backlight-display { + compatible = "pwm-backlight"; + pwms = <&pwm4 0 5000000>; + brightness-levels = < + 0 1 2 3 4 5 6 7 8 9 + 10 11 12 13 14 15 16 17 18 19 + 20 21 22 23 24 25 26 27 28 29 + 30 31 32 33 34 35 36 37 38 39 + 40 41 42 43 44 45 46 47 48 49 + 50 51 52 53 54 55 56 57 58 59 + 60 61 62 63 64 65 66 67 68 69 + 70 71 72 73 74 75 76 77 78 79 + 80 81 82 83 84 85 86 87 88 89 + 90 91 92 93 94 95 96 97 98 99 + 100 + >; + default-brightness-level = <100>; + }; + + backlight-keypad { + compatible = "gpio-backlight"; + gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>; + default-on; + }; + + leds { + compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_gpio_leds>; + + led0: user1 { + label = "user1"; + gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ + default-state = "on"; + linux,default-trigger = "heartbeat"; + }; + + led1: user2 { + label = "user2"; + gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ + default-state = "off"; + }; + + led2: user3 { + label = "user3"; + gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ + default-state = "off"; + }; + }; + + memory@10000000 { + reg = <0x10000000 0x40000000>; + }; + + pps { + compatible = "pps-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pps>; + gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>; + }; + + reg_2p5v: regulator-2p5v { + compatible = "regulator-fixed"; + regulator-name = "2P5V"; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + + reg_3p3v: regulator-3p3v { + compatible = "regulator-fixed"; + regulator-name = "3P3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_5p0v: regulator-5p0v { + compatible = "regulator-fixed"; + regulator-name = "5P0V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; + + reg_12p0v: regulator-12p0v { + compatible = "regulator-fixed"; + regulator-name = "12P0V"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + gpio = <&gpio4 25 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + reg_1p4v: regulator-vddsoc { + compatible = "regulator-fixed"; + regulator-name = "vdd_soc"; + regulator-min-microvolt = <1400000>; + regulator-max-microvolt = <1400000>; + regulator-always-on; + }; + + reg_usb_h1_vbus: regulator-usb-h1-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb_h1_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; + + reg_usb_otg_vbus: regulator-usb-otg-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb_otg_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + sound { + compatible = "fsl,imx6q-ventana-sgtl5000", + "fsl,imx-audio-sgtl5000"; + model = "sgtl5000-audio"; + ssi-controller = <&ssi1>; + audio-codec = <&sgtl5000>; + audio-routing = + "MIC_IN", "Mic Jack", + "Mic Jack", "Mic Bias", + "Headphone Jack", "HP_OUT"; + mux-int-port = <1>; + mux-ext-port = <4>; + }; +}; + +&audmux { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_audmux>; + status = "okay"; +}; + +&ecspi3 { + cs-gpios = <&gpio4 24 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ecspi3>; + status = "okay"; +}; + +&can1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flexcan>; + status = "okay"; +}; + +&clks { + assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, + <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>, + <&clks IMX6QDL_CLK_PLL3_USB_OTG>; +}; + +&fec { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_enet>; + phy-mode = "rgmii-id"; + phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +&hdmi { + ddc-i2c-bus = <&i2c3>; + status = "okay"; +}; + +&i2c1 { + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c1>; + status = "okay"; + + eeprom1: eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + pagesize = <16>; + }; + + eeprom2: eeprom@51 { + compatible = "atmel,24c02"; + reg = <0x51>; + pagesize = <16>; + }; + + eeprom3: eeprom@52 { + compatible = "atmel,24c02"; + reg = <0x52>; + pagesize = <16>; + }; + + eeprom4: eeprom@53 { + compatible = "atmel,24c02"; + reg = <0x53>; + pagesize = <16>; + }; + + pca9555: gpio@23 { + compatible = "nxp,pca9555"; + reg = <0x23>; + gpio-controller; + #gpio-cells = <2>; + }; + + ds1672: rtc@68 { + compatible = "dallas,ds1672"; + reg = <0x68>; + }; +}; + +&i2c2 { + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c2>; + status = "okay"; + + sgtl5000: codec@a { + compatible = "fsl,sgtl5000"; + reg = <0x0a>; + clocks = <&clks IMX6QDL_CLK_CKO>; + VDDA-supply = <®_1p8v>; + VDDIO-supply = <®_3p3v>; + }; + + tca8418: keypad@34 { + compatible = "ti,tca8418"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_keypad>; + reg = <0x34>; + interrupt-parent = <&gpio5>; + interrupts = <11 IRQ_TYPE_EDGE_FALLING>; + linux,keymap = < MATRIX_KEY(0x00, 0x01, BTN_0) + MATRIX_KEY(0x00, 0x00, BTN_1) + MATRIX_KEY(0x01, 0x01, BTN_2) + MATRIX_KEY(0x01, 0x00, BTN_3) + MATRIX_KEY(0x02, 0x00, BTN_4) + MATRIX_KEY(0x00, 0x03, BTN_5) + MATRIX_KEY(0x00, 0x02, BTN_6) + MATRIX_KEY(0x01, 0x03, BTN_7) + MATRIX_KEY(0x01, 0x02, BTN_8) + MATRIX_KEY(0x02, 0x02, BTN_9) + >; + keypad,num-rows = <4>; + keypad,num-columns = <4>; + }; + + ltc3676: pmic@3c { + compatible = "lltc,ltc3676"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pmic>; + reg = <0x3c>; + interrupt-parent = <&gpio1>; + interrupts = <8 IRQ_TYPE_EDGE_FALLING>; + + regulators { + /* VDD_DDR (1+R1/R2 = 2.105) */ + reg_vdd_ddr: sw2 { + regulator-name = "vddddr"; + regulator-min-microvolt = <868310>; + regulator-max-microvolt = <1684000>; + lltc,fb-voltage-divider = <221000 200000>; + regulator-ramp-delay = <7000>; + regulator-boot-on; + regulator-always-on; + }; + + /* VDD_ARM (1+R1/R2 = 1.931) */ + reg_vdd_arm: sw3 { + regulator-name = "vddarm"; + regulator-min-microvolt = <796551>; + regulator-max-microvolt = <1544827>; + lltc,fb-voltage-divider = <243000 261000>; + regulator-ramp-delay = <7000>; + regulator-boot-on; + regulator-always-on; + linux,phandle = <®_vdd_arm>; + }; + + /* VDD_1P8 (1+R1/R2 = 2.505): GPS/VideoIn/ENET-PHY */ + reg_1p8v: sw4 { + regulator-name = "vdd1p8"; + regulator-min-microvolt = <1033310>; + regulator-max-microvolt = <2004000>; + lltc,fb-voltage-divider = <301000 200000>; + regulator-ramp-delay = <7000>; + regulator-boot-on; + regulator-always-on; + }; + + /* VDD_1P0 (1+R1/R2 = 1.39): PCIe/ENET-PHY */ + reg_1p0v: ldo2 { + regulator-name = "vdd1p0"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1050000>; + lltc,fb-voltage-divider = <78700 200000>; + regulator-boot-on; + regulator-always-on; + }; + + /* VDD_AUD_1P8: Audio codec */ + reg_aud_1p8v: ldo3 { + regulator-name = "vdd1p8a"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + }; + + /* VDD_HIGH (1+R1/R2 = 4.17) */ + reg_3p0v: ldo4 { + regulator-name = "vdd3p0"; + regulator-min-microvolt = <3023250>; + regulator-max-microvolt = <3023250>; + lltc,fb-voltage-divider = <634000 200000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; +}; + +&i2c3 { + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c3>; + status = "okay"; + + egalax_ts: touchscreen@4 { + compatible = "eeti,egalax_ts"; + reg = <0x04>; + interrupt-parent = <&gpio5>; + interrupts = <12 IRQ_TYPE_EDGE_FALLING>; + wakeup-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>; + }; +}; + +&ldb { + fsl,dual-channel; + status = "okay"; + + lvds-channel@0 { + fsl,data-mapping = "spwg"; + fsl,data-width = <18>; + status = "okay"; + + display-timings { + native-mode = <&timing0>; + timing0: hsd100pxn1 { + clock-frequency = <65000000>; + hactive = <1024>; + vactive = <768>; + hback-porch = <220>; + hfront-porch = <40>; + vback-porch = <21>; + vfront-porch = <7>; + hsync-len = <60>; + vsync-len = <10>; + }; + }; + }; +}; + +&pcie { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pcie>; + reset-gpio = <&gpio4 31 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + +&pwm2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pwm2>; /* MX6_DIO1 */ + status = "disabled"; +}; + +&pwm3 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pwm3>; /* MX6_DIO2 */ + status = "disabled"; +}; + +&pwm4 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pwm4>; + status = "okay"; +}; + +&ssi1 { + status = "okay"; +}; + +&uart1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart1>; + uart-has-rtscts; + rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>; + status = "okay"; +}; + +&uart2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart2>; + status = "okay"; +}; + +&uart5 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart5>; + status = "okay"; +}; + +&usbotg { + vbus-supply = <®_usb_otg_vbus>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg>; + disable-over-current; + status = "okay"; +}; + +&usbh1 { + vbus-supply = <®_usb_h1_vbus>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbh1>; + status = "okay"; +}; + +&usdhc2 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usdhc2>; + bus-width = <8>; + vmmc-supply = <®_3p3v>; + non-removable; + status = "okay"; +}; + +&usdhc3 { + pinctrl-names = "default", "state_100mhz", "state_200mhz"; + pinctrl-0 = <&pinctrl_usdhc3>; + pinctrl-1 = <&pinctrl_usdhc3_100mhz>; + pinctrl-2 = <&pinctrl_usdhc3_200mhz>; + cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>; + vmmc-supply = <®_3p3v>; + status = "okay"; +}; + +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; +}; + +&iomuxc { + pinctrl_audmux: audmuxgrp { + fsl,pins = < + /* AUD4 */ + MX6QDL_PAD_DISP0_DAT20__AUD4_TXC 0x130b0 + MX6QDL_PAD_DISP0_DAT21__AUD4_TXD 0x110b0 + MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS 0x130b0 + MX6QDL_PAD_DISP0_DAT23__AUD4_RXD 0x130b0 + MX6QDL_PAD_GPIO_0__CCM_CLKO1 0x130b0 /* AUD4_MCK */ + /* AUD6 */ + MX6QDL_PAD_DI0_PIN2__AUD6_TXD 0x130b0 + MX6QDL_PAD_DI0_PIN3__AUD6_TXFS 0x130b0 + MX6QDL_PAD_DI0_PIN4__AUD6_RXD 0x130b0 + MX6QDL_PAD_DI0_PIN15__AUD6_TXC 0x130b0 + >; + }; + + pinctrl_ecspi3: escpi3grp { + fsl,pins = < + MX6QDL_PAD_DISP0_DAT0__ECSPI3_SCLK 0x100b1 + MX6QDL_PAD_DISP0_DAT1__ECSPI3_MOSI 0x100b1 + MX6QDL_PAD_DISP0_DAT2__ECSPI3_MISO 0x100b1 + MX6QDL_PAD_DISP0_DAT3__GPIO4_IO24 0x100b1 + >; + }; + + pinctrl_enet: enetgrp { + fsl,pins = < + MX6QDL_PAD_RGMII_RXC__RGMII_RXC 0x1b030 + MX6QDL_PAD_RGMII_RD0__RGMII_RD0 0x1b030 + MX6QDL_PAD_RGMII_RD1__RGMII_RD1 0x1b030 + MX6QDL_PAD_RGMII_RD2__RGMII_RD2 0x1b030 + MX6QDL_PAD_RGMII_RD3__RGMII_RD3 0x1b030 + MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b030 + MX6QDL_PAD_RGMII_TXC__RGMII_TXC 0x1b030 + MX6QDL_PAD_RGMII_TD0__RGMII_TD0 0x1b030 + MX6QDL_PAD_RGMII_TD1__RGMII_TD1 0x1b030 + MX6QDL_PAD_RGMII_TD2__RGMII_TD2 0x1b030 + MX6QDL_PAD_RGMII_TD3__RGMII_TD3 0x1b030 + MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b030 + MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK 0x1b0b0 + MX6QDL_PAD_ENET_MDIO__ENET_MDIO 0x1b0b0 + MX6QDL_PAD_ENET_MDC__ENET_MDC 0x1b0b0 + MX6QDL_PAD_GPIO_16__ENET_REF_CLK 0x4001b0a8 + MX6QDL_PAD_ENET_TXD0__GPIO1_IO30 0x4001b0b0 /* PHY_RST# */ + >; + }; + + pinctrl_flexcan: flexcangrp { + fsl,pins = < + MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX 0x1b0b1 + MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX 0x1b0b1 + MX6QDL_PAD_GPIO_2__GPIO1_IO02 0x4001b0b0 /* CAN_STBY */ + >; + }; + + pinctrl_gpio_leds: gpioledsgrp { + fsl,pins = < + MX6QDL_PAD_KEY_COL0__GPIO4_IO06 0x1b0b0 + MX6QDL_PAD_KEY_ROW0__GPIO4_IO07 0x1b0b0 + MX6QDL_PAD_KEY_ROW4__GPIO4_IO15 0x1b0b0 + >; + }; + + pinctrl_i2c1: i2c1grp { + fsl,pins = < + MX6QDL_PAD_EIM_D21__I2C1_SCL 0x4001b8b1 + MX6QDL_PAD_EIM_D28__I2C1_SDA 0x4001b8b1 + >; + }; + + pinctrl_i2c2: i2c2grp { + fsl,pins = < + MX6QDL_PAD_KEY_COL3__I2C2_SCL 0x4001b8b1 + MX6QDL_PAD_KEY_ROW3__I2C2_SDA 0x4001b8b1 + >; + }; + + pinctrl_i2c3: i2c3grp { + fsl,pins = < + MX6QDL_PAD_GPIO_3__I2C3_SCL 0x4001b8b1 + MX6QDL_PAD_GPIO_6__I2C3_SDA 0x4001b8b1 + MX6QDL_PAD_GPIO_19__GPIO4_IO05 0x4001b0b0 /* DIOI2C_DIS# */ + MX6QDL_PAD_DISP0_DAT18__GPIO5_IO12 0x0001b0b0 /* LVDS_TOUCH_IRQ# */ + MX6QDL_PAD_DISP0_DAT19__GPIO5_IO13 0x0001b0b0 /* LVDS_BACKEN */ + >; + }; + + pinctrl_keypad: keypadgrp { + fsl,pins = < + MX6QDL_PAD_DISP0_DAT17__GPIO5_IO11 0x0001b0b0 /* KEYPAD_IRQ# */ + MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30 0x0001b0b0 /* KEYPAD_LED_EN */ + >; + }; + + pinctrl_pcie: pciegrp { + fsl,pins = < + MX6QDL_PAD_DISP0_DAT10__GPIO4_IO31 0x1b0b0 /* PCI_RST# */ + MX6QDL_PAD_GPIO_17__GPIO7_IO12 0x4001b0b0 /* PCIESKT_WDIS# */ + >; + }; + + pinctrl_pmic: pmicgrp { + fsl,pins = < + MX6QDL_PAD_GPIO_8__GPIO1_IO08 0x0001b0b0 /* PMIC_IRQ# */ + >; + }; + + pinctrl_pps: ppsgrp { + fsl,pins = < + MX6QDL_PAD_ENET_RXD1__GPIO1_IO26 0x1b0b1 + >; + }; + + pinctrl_pwm2: pwm2grp { + fsl,pins = < + MX6QDL_PAD_SD1_DAT2__PWM2_OUT 0x1b0b1 + >; + }; + + pinctrl_pwm3: pwm3grp { + fsl,pins = < + MX6QDL_PAD_SD1_DAT1__PWM3_OUT 0x1b0b1 + >; + }; + + pinctrl_pwm4: pwm4grp { + fsl,pins = < + MX6QDL_PAD_SD1_CMD__PWM4_OUT 0x1b0b1 + >; + }; + + pinctrl_uart1: uart1grp { + fsl,pins = < + MX6QDL_PAD_SD3_DAT7__UART1_TX_DATA 0x1b0b1 + MX6QDL_PAD_SD3_DAT6__UART1_RX_DATA 0x1b0b1 + MX6QDL_PAD_SD3_DAT4__GPIO7_IO01 0x4001b0b1 /* TEN */ + >; + }; + + pinctrl_uart2: uart2grp { + fsl,pins = < + MX6QDL_PAD_SD4_DAT7__UART2_TX_DATA 0x1b0b1 + MX6QDL_PAD_SD4_DAT4__UART2_RX_DATA 0x1b0b1 + >; + }; + + pinctrl_uart5: uart5grp { + fsl,pins = < + MX6QDL_PAD_KEY_COL1__UART5_TX_DATA 0x1b0b1 + MX6QDL_PAD_KEY_ROW1__UART5_RX_DATA 0x1b0b1 + >; + }; + + pinctrl_usbh1: usbh1grp { + fsl,pins = < + MX6QDL_PAD_GPIO_9__GPIO1_IO09 0x4001b0b0 /* USBHUB_RST# */ + >; + }; + + pinctrl_usbotg: usbotggrp { + fsl,pins = < + MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059 + MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x1b0b0 /* PWR_EN */ + MX6QDL_PAD_KEY_COL4__GPIO4_IO14 0x1b0b0 /* OC */ + >; + }; + + pinctrl_usdhc2: usdhc2grp { + fsl,pins = < + MX6QDL_PAD_SD2_CMD__SD2_CMD 0x170f9 + MX6QDL_PAD_SD2_CLK__SD2_CLK 0x100f9 + MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x170f9 + MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x170f9 + MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x170f9 + MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x170f9 + MX6QDL_PAD_NANDF_D4__SD2_DATA4 0x170f9 + MX6QDL_PAD_NANDF_D5__SD2_DATA5 0x170f9 + MX6QDL_PAD_NANDF_D6__SD2_DATA6 0x170f9 + MX6QDL_PAD_NANDF_D7__SD2_DATA7 0x170f9 + >; + }; + + pinctrl_usdhc3: usdhc3grp { + fsl,pins = < + MX6QDL_PAD_SD3_CMD__SD3_CMD 0x17059 + MX6QDL_PAD_SD3_CLK__SD3_CLK 0x10059 + MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x17059 + MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059 + MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059 + MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059 + MX6QDL_PAD_SD3_DAT5__GPIO7_IO00 0x17059 /* CD */ + MX6QDL_PAD_NANDF_CS1__SD3_VSELECT 0x17059 + >; + }; + + pinctrl_usdhc3_100mhz: usdhc3grp100mhz { + fsl,pins = < + MX6QDL_PAD_SD3_CMD__SD3_CMD 0x170b9 + MX6QDL_PAD_SD3_CLK__SD3_CLK 0x100b9 + MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x170b9 + MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x170b9 + MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x170b9 + MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x170b9 + MX6QDL_PAD_SD3_DAT5__GPIO7_IO00 0x170b9 /* CD */ + MX6QDL_PAD_NANDF_CS1__SD3_VSELECT 0x170b9 + >; + }; + + pinctrl_usdhc3_200mhz: usdhc3grp200mhz { + fsl,pins = < + MX6QDL_PAD_SD3_CMD__SD3_CMD 0x170f9 + MX6QDL_PAD_SD3_CLK__SD3_CLK 0x100f9 + MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x170f9 + MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x170f9 + MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x170f9 + MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x170f9 + MX6QDL_PAD_SD3_DAT5__GPIO7_IO00 0x170f9 /* CD */ + MX6QDL_PAD_NANDF_CS1__SD3_VSELECT 0x170f9 + >; + }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX6QDL_PAD_DISP0_DAT8__WDOG1_B 0x1b0b0 + >; + }; +}; diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi index bad3c9f9eeac86..b63134e3b51a07 100644 --- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi @@ -408,7 +408,7 @@ }; rtc: rtc@68 { - compatible = "st,rv4162"; + compatible = "microcrystal,rv4162"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rv4162>; reg = <0x68>; diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi index 559da17297ef50..aeaa5a6e4fcf46 100644 --- a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi @@ -326,7 +326,7 @@ }; rtc@68 { - compatible = "st,rv4162"; + compatible = "microcrystal,rv4162"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rv4162>; reg = <0x68>; diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi index 82dc5744ae19b1..850ceadbc2cf73 100644 --- a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi +++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi @@ -88,6 +88,7 @@ clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_2p5v>; VDDIO-supply = <®_3p3v>; + lrclk-strength = <3>; }; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index e426faa9c24379..f325411f66aae1 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -156,7 +156,7 @@ <&clks IMX6QDL_CLK_GPU3D_CORE>, <&clks IMX6QDL_CLK_GPU3D_SHADER>; clock-names = "bus", "core", "shader"; - power-domains = <&gpc 1>; + power-domains = <&pd_pu>; }; gpu_2d: gpu@00134000 { @@ -166,7 +166,7 @@ clocks = <&clks IMX6QDL_CLK_GPU2D_AXI>, <&clks IMX6QDL_CLK_GPU2D_CORE>; clock-names = "bus", "core"; - power-domains = <&gpc 1>; + power-domains = <&pd_pu>; }; timer@00a00600 { @@ -434,7 +434,7 @@ clocks = <&clks IMX6QDL_CLK_VPU_AXI>, <&clks IMX6QDL_CLK_MMDC_CH0_AXI>; clock-names = "per", "ahb"; - power-domains = <&gpc 1>; + power-domains = <&pd_pu>; resets = <&src 1>; iram = <&ocram>; }; @@ -644,6 +644,7 @@ anatop-min-bit-val = <4>; anatop-min-voltage = <800000>; anatop-max-voltage = <1375000>; + anatop-enable-bit = <0>; }; regulator-3p0 { @@ -658,6 +659,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2625000>; anatop-max-voltage = <3400000>; + anatop-enable-bit = <0>; }; regulator-2p5 { @@ -672,6 +674,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2100000>; anatop-max-voltage = <2875000>; + anatop-enable-bit = <0>; }; reg_arm: regulator-vddcore { @@ -797,14 +800,29 @@ interrupts = <0 89 IRQ_TYPE_LEVEL_HIGH>, <0 90 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&intc>; - pu-supply = <®_pu>; - clocks = <&clks IMX6QDL_CLK_GPU3D_CORE>, - <&clks IMX6QDL_CLK_GPU3D_SHADER>, - <&clks IMX6QDL_CLK_GPU2D_CORE>, - <&clks IMX6QDL_CLK_GPU2D_AXI>, - <&clks IMX6QDL_CLK_OPENVG_AXI>, - <&clks IMX6QDL_CLK_VPU_AXI>; - #power-domain-cells = <1>; + clocks = <&clks IMX6QDL_CLK_IPG>; + clock-names = "ipg"; + + pgc { + #address-cells = <1>; + #size-cells = <0>; + + power-domain@0 { + reg = <0>; + #power-domain-cells = <0>; + }; + pd_pu: power-domain@1 { + reg = <1>; + #power-domain-cells = <0>; + power-supply = <®_pu>; + clocks = <&clks IMX6QDL_CLK_GPU3D_CORE>, + <&clks IMX6QDL_CLK_GPU3D_SHADER>, + <&clks IMX6QDL_CLK_GPU2D_CORE>, + <&clks IMX6QDL_CLK_GPU2D_AXI>, + <&clks IMX6QDL_CLK_OPENVG_AXI>, + <&clks IMX6QDL_CLK_VPU_AXI>; + }; + }; }; gpr: iomuxc-gpr@020e0000 { diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi index 59453f2ac4bafe..299d863690c5db 100644 --- a/arch/arm/boot/dts/imx6qp.dtsi +++ b/arch/arm/boot/dts/imx6qp.dtsi @@ -120,6 +120,10 @@ <0 119 IRQ_TYPE_LEVEL_HIGH>; }; +&gpc { + compatible = "fsl,imx6qp-gpc", "fsl,imx6q-gpc"; +}; + &ipu1 { compatible = "fsl,imx6qp-ipu", "fsl,imx6q-ipu"; fsl,prg = <&prg1>; diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index cc9572ea2860a5..3243af4a99844b 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -530,6 +530,7 @@ anatop-min-bit-val = <4>; anatop-min-voltage = <800000>; anatop-max-voltage = <1375000>; + anatop-enable-bit = <0>; }; regulator-3p0 { @@ -544,6 +545,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2625000>; anatop-max-voltage = <3400000>; + anatop-enable-bit = <0>; }; regulator-2p5 { @@ -558,6 +560,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2100000>; anatop-max-voltage = <2850000>; + anatop-enable-bit = <0>; }; reg_arm: regulator-vddcore { diff --git a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts index 802da45aa5516f..ac1989e5d5adde 100644 --- a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts +++ b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts @@ -374,7 +374,7 @@ cap-sdio-irq; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&gpio7>; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts index d71da30c9cff23..c0139d7e497ab3 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dts +++ b/arch/arm/boot/dts/imx6sx-sdb.dts @@ -128,3 +128,11 @@ reg = <1>; }; }; + +®_arm { + vin-supply = <&sw1a_reg>; +}; + +®_soc { + vin-supply = <&sw1a_reg>; +}; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 3f1416be4c3609..f16b9df9d0c60a 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -587,6 +587,7 @@ anatop-min-bit-val = <4>; anatop-min-voltage = <800000>; anatop-max-voltage = <1375000>; + anatop-enable-bit = <0>; }; regulator-3p0 { @@ -601,6 +602,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2625000>; anatop-max-voltage = <3400000>; + anatop-enable-bit = <0>; }; regulator-2p5 { @@ -615,6 +617,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2100000>; anatop-max-voltage = <2875000>; + anatop-enable-bit = <0>; }; reg_arm: regulator-vddcore { diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dts b/arch/arm/boot/dts/imx6ul-14x14-evk.dts index f18e1f1d0ce2c6..d2be8aa3370b78 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dts +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dts @@ -120,10 +120,16 @@ ethphy0: ethernet-phy@2 { reg = <2>; + micrel,led-mode = <1>; + clocks = <&clks IMX6UL_CLK_ENET_REF>; + clock-names = "rmii-ref"; }; ethphy1: ethernet-phy@1 { reg = <1>; + micrel,led-mode = <1>; + clocks = <&clks IMX6UL_CLK_ENET2_REF>; + clock-names = "rmii-ref"; }; }; }; diff --git a/arch/arm/boot/dts/imx6ul-opos6ul.dtsi b/arch/arm/boot/dts/imx6ul-opos6ul.dtsi index 51095df33a90c7..aec5ccce0321df 100644 --- a/arch/arm/boot/dts/imx6ul-opos6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul-opos6ul.dtsi @@ -120,7 +120,7 @@ #address-cells = <1>; #size-cells = <0>; - brcmf: bcrmf@1 { + brcmf: wifi@1 { compatible = "brcm,bcm4329-fmac"; reg = <1>; interrupt-parent = <&gpio2>; diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index b9d7d2d09402b3..6da2b77edd460f 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -542,6 +542,7 @@ anatop-min-bit-val = <0>; anatop-min-voltage = <2625000>; anatop-max-voltage = <3400000>; + anatop-enable-bit = <0>; }; reg_arm: regulator-vddcore { diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi index 2d87489f9105cf..d7753f79937a7f 100644 --- a/arch/arm/boot/dts/imx7-colibri.dtsi +++ b/arch/arm/boot/dts/imx7-colibri.dtsi @@ -43,7 +43,7 @@ / { bl: backlight { compatible = "pwm-backlight"; - pwms = <&pwm1 0 5000000>; + pwms = <&pwm1 0 5000000 0>; }; reg_module_3v3: regulator-module-3v3 { diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts index 5d98e2b5d54b93..dd40e49f6c42c4 100644 --- a/arch/arm/boot/dts/imx7d-nitrogen7.dts +++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts @@ -67,7 +67,7 @@ backlight-j20 { compatible = "pwm-backlight"; - pwms = <&pwm1 0 5000000>; + pwms = <&pwm1 0 5000000 0>; brightness-levels = <0 4 8 16 32 64 128 255>; default-brightness-level = <6>; status = "okay"; @@ -279,7 +279,7 @@ status = "okay"; rtc@68 { - compatible = "rv4162"; + compatible = "microcrystal,rv4162"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2_rv4162>; reg = <0x68>; diff --git a/arch/arm/boot/dts/imx7d-pico.dts b/arch/arm/boot/dts/imx7d-pico.dts new file mode 100644 index 00000000000000..ebda3dffc27040 --- /dev/null +++ b/arch/arm/boot/dts/imx7d-pico.dts @@ -0,0 +1,387 @@ +/* + * Copyright 2017 NXP + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; + +#include "imx7d.dtsi" + +/ { + model = "Technexion Pico i.MX7D Board"; + compatible = "technexion,imx7d-pico", "fsl,imx7d"; + + memory { + reg = <0x80000000 0x80000000>; + }; + + reg_2p5v: regulator-2p5v { + compatible = "regulator-fixed"; + regulator-name = "2P5V"; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + + reg_3p3v: regulator-3p3v { + compatible = "regulator-fixed"; + regulator-name = "3P3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_usb_otg1_vbus: regulator-usb-otg1-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb_otg1_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio4 5 GPIO_ACTIVE_LOW>; + }; + + reg_usb_otg2_vbus: regulator-usb-otg2-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb_otg2_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_vref_1v8: regulator-vref-1v8 { + compatible = "regulator-fixed"; + regulator-name = "vref-1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "imx7-sgtl5000"; + simple-audio-card,format = "i2s"; + simple-audio-card,bitclock-master = <&dailink_master>; + simple-audio-card,frame-master = <&dailink_master>; + simple-audio-card,cpu { + sound-dai = <&sai1>; + }; + + dailink_master: simple-audio-card,codec { + sound-dai = <&codec>; + clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>; + }; + }; +}; + +&fec1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_enet1>; + assigned-clocks = <&clks IMX7D_ENET1_TIME_ROOT_SRC>, + <&clks IMX7D_ENET1_TIME_ROOT_CLK>; + assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>; + assigned-clock-rates = <0>, <100000000>; + phy-mode = "rgmii"; + phy-handle = <ðphy0>; + fsl,magic-packet; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + status = "okay"; + }; + }; +}; + +&i2c1 { + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c1>; + status = "okay"; + + codec: sgtl5000@0a { + #sound-dai-cells = <0>; + reg = <0x0a>; + compatible = "fsl,sgtl5000"; + clocks = <&clks IMX7D_AUDIO_MCLK_ROOT_CLK>; + VDDA-supply = <®_2p5v>; + VDDIO-supply = <®_vref_1v8>; + }; +}; + +&i2c4 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c4>; + status = "okay"; + + pmic: pfuze3000@08 { + compatible = "fsl,pfuze3000"; + reg = <0x08>; + + regulators { + sw1a_reg: sw1a { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + /* use sw1c_reg to align with pfuze100/pfuze200 */ + sw1c_reg: sw1b { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1475000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + + sw2_reg: sw2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1850000>; + regulator-boot-on; + regulator-always-on; + }; + + sw3a_reg: sw3 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <1650000>; + regulator-boot-on; + regulator-always-on; + }; + + swbst_reg: swbst { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5150000>; + }; + + snvs_reg: vsnvs { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3000000>; + regulator-boot-on; + regulator-always-on; + }; + + vref_reg: vrefddr { + regulator-boot-on; + regulator-always-on; + }; + + vgen1_reg: vldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen2_reg: vldo2 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1550000>; + }; + + vgen3_reg: vccsd { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen4_reg: v33 { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen5_reg: vldo3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen6_reg: vldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + }; + }; +}; + +&sai1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sai1>; + assigned-clocks = <&clks IMX7D_SAI1_ROOT_SRC>, + <&clks IMX7D_SAI1_ROOT_CLK>; + assigned-clock-parents = <&clks IMX7D_PLL_AUDIO_POST_DIV>; + assigned-clock-rates = <0>, <24576000>; + status = "okay"; +}; + +&uart5 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_uart5>; + assigned-clocks = <&clks IMX7D_UART5_ROOT_SRC>; + assigned-clock-parents = <&clks IMX7D_PLL_SYS_MAIN_240M_CLK>; + status = "okay"; +}; + +&usbotg1 { + vbus-supply = <®_usb_otg1_vbus>; + status = "okay"; +}; + +&usbotg2 { + vbus-supply = <®_usb_otg2_vbus>; + dr_mode = "host"; + status = "okay"; +}; + +&usdhc3 { + pinctrl-names = "default", "state_100mhz", "state_200mhz"; + pinctrl-0 = <&pinctrl_usdhc3>; + pinctrl-1 = <&pinctrl_usdhc3_100mhz>; + pinctrl-2 = <&pinctrl_usdhc3_200mhz>; + assigned-clocks = <&clks IMX7D_USDHC3_ROOT_CLK>; + assigned-clock-rates = <400000000>; + bus-width = <8>; + fsl,tuning-step = <2>; + non-removable; + status = "okay"; +}; + +&iomuxc { + pinctrl_enet1: enet1grp { + fsl,pins = < + MX7D_PAD_SD2_CD_B__ENET1_MDIO 0x3 + MX7D_PAD_SD2_WP__ENET1_MDC 0x3 + MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC 0x1 + MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0 0x1 + MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1 0x1 + MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2 0x1 + MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3 0x1 + MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL 0x1 + MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC 0x1 + MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0 0x1 + MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1 0x1 + MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2 0x1 + MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3 0x1 + MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL 0x1 + >; + }; + + pinctrl_i2c1: i2c1grp { + fsl,pins = < + MX7D_PAD_UART1_TX_DATA__I2C1_SDA 0x4000007f + MX7D_PAD_UART1_RX_DATA__I2C1_SCL 0x4000007f + >; + }; + + pinctrl_i2c4: i2c4grp { + fsl,pins = < + MX7D_PAD_SAI1_RX_BCLK__I2C4_SDA 0x4000007f + MX7D_PAD_SAI1_RX_SYNC__I2C4_SCL 0x4000007f + >; + }; + + pinctrl_sai1: sai1grp { + fsl,pins = < + MX7D_PAD_ENET1_RX_CLK__SAI1_TX_BCLK 0x1f + MX7D_PAD_ENET1_CRS__SAI1_TX_SYNC 0x1f + MX7D_PAD_ENET1_COL__SAI1_TX_DATA0 0x30 + MX7D_PAD_ENET1_TX_CLK__SAI1_RX_DATA0 0x1f + >; + }; + + pinctrl_uart5: uart5grp { + fsl,pins = < + MX7D_PAD_I2C4_SDA__UART5_DCE_TX 0x79 + MX7D_PAD_I2C4_SCL__UART5_DCE_RX 0x79 + >; + }; + + pinctrl_usbotg1_pwr: usbotg_pwr { + fsl,pins = < + MX7D_PAD_UART3_TX_DATA__GPIO4_IO5 0x14 + >; + }; + + pinctrl_usdhc3: usdhc3grp { + fsl,pins = < + MX7D_PAD_SD3_CMD__SD3_CMD 0x59 + MX7D_PAD_SD3_CLK__SD3_CLK 0x19 + MX7D_PAD_SD3_DATA0__SD3_DATA0 0x59 + MX7D_PAD_SD3_DATA1__SD3_DATA1 0x59 + MX7D_PAD_SD3_DATA2__SD3_DATA2 0x59 + MX7D_PAD_SD3_DATA3__SD3_DATA3 0x59 + MX7D_PAD_SD3_DATA4__SD3_DATA4 0x59 + MX7D_PAD_SD3_DATA5__SD3_DATA5 0x59 + MX7D_PAD_SD3_DATA6__SD3_DATA6 0x59 + MX7D_PAD_SD3_DATA7__SD3_DATA7 0x59 + >; + }; + + pinctrl_usdhc3_100mhz: usdhc3grp_100mhz { + fsl,pins = < + MX7D_PAD_SD3_CMD__SD3_CMD 0x5a + MX7D_PAD_SD3_CLK__SD3_CLK 0x1a + MX7D_PAD_SD3_DATA0__SD3_DATA0 0x5a + MX7D_PAD_SD3_DATA1__SD3_DATA1 0x5a + MX7D_PAD_SD3_DATA2__SD3_DATA2 0x5a + MX7D_PAD_SD3_DATA3__SD3_DATA3 0x5a + MX7D_PAD_SD3_DATA4__SD3_DATA4 0x5a + MX7D_PAD_SD3_DATA5__SD3_DATA5 0x5a + MX7D_PAD_SD3_DATA6__SD3_DATA6 0x5a + MX7D_PAD_SD3_DATA7__SD3_DATA7 0x5a + >; + }; + + pinctrl_usdhc3_200mhz: usdhc3grp_200mhz { + fsl,pins = < + MX7D_PAD_SD3_CMD__SD3_CMD 0x5b + MX7D_PAD_SD3_CLK__SD3_CLK 0x1b + MX7D_PAD_SD3_DATA0__SD3_DATA0 0x5b + MX7D_PAD_SD3_DATA1__SD3_DATA1 0x5b + MX7D_PAD_SD3_DATA2__SD3_DATA2 0x5b + MX7D_PAD_SD3_DATA3__SD3_DATA3 0x5b + MX7D_PAD_SD3_DATA4__SD3_DATA4 0x5b + MX7D_PAD_SD3_DATA5__SD3_DATA5 0x5b + MX7D_PAD_SD3_DATA6__SD3_DATA6 0x5b + MX7D_PAD_SD3_DATA7__SD3_DATA7 0x5b + >; + }; +}; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index 5be01a1bf84020..77c400f0017a7d 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -52,6 +52,27 @@ reg = <0x80000000 0x80000000>; }; + spi4 { + compatible = "spi-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi4>; + gpio-sck = <&gpio1 13 GPIO_ACTIVE_HIGH>; + gpio-mosi = <&gpio1 9 GPIO_ACTIVE_HIGH>; + cs-gpios = <&gpio1 12 GPIO_ACTIVE_HIGH>; + num-chipselects = <1>; + #address-cells = <1>; + #size-cells = <0>; + + extended_io: gpio-expander@0 { + compatible = "fairchild,74hc595"; + gpio-controller; + #gpio-cells = <2>; + reg = <0>; + registers-number = <1>; + spi-max-frequency = <100000>; + }; + }; + regulators { compatible = "simple-bus"; #address-cells = <1>; @@ -328,6 +349,11 @@ }; }; +&pcie { + reset-gpio = <&extended_io 1 GPIO_ACTIVE_LOW>; + status = "okay"; +}; + &pwm1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pwm1>; @@ -642,5 +668,13 @@ fsl,pins = < MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT 0x110b0 >; + + pinctrl_spi4: spi4grp { + fsl,pins = < + MX7D_PAD_GPIO1_IO09__GPIO1_IO9 0x59 + MX7D_PAD_GPIO1_IO12__GPIO1_IO12 0x59 + MX7D_PAD_GPIO1_IO13__GPIO1_IO13 0x59 + >; + }; }; }; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index f6dee41a05d95b..f46814a7ea4410 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -42,6 +42,7 @@ */ #include "imx7s.dtsi" +#include / { cpus { @@ -127,6 +128,42 @@ fsl,num-rx-queues=<3>; status = "disabled"; }; + + pcie: pcie@0x33800000 { + compatible = "fsl,imx7d-pcie", "snps,dw-pcie"; + reg = <0x33800000 0x4000>, + <0x4ff00000 0x80000>; + reg-names = "dbi", "config"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x81000000 0 0 0x4ff80000 0 0x00010000 /* downstream I/O */ + 0x82000000 0 0x40000000 0x40000000 0 0x0ff00000>; /* non-prefetchable memory */ + num-lanes = <1>; + interrupts = ; + interrupt-names = "msi"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>, + <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>, + <&clks IMX7D_PCIE_PHY_ROOT_CLK>; + clock-names = "pcie", "pcie_bus", "pcie_phy"; + assigned-clocks = <&clks IMX7D_PCIE_CTRL_ROOT_SRC>, + <&clks IMX7D_PCIE_PHY_ROOT_SRC>; + assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_250M_CLK>, + <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>; + + fsl,max-link-speed = <2>; + power-domains = <&pgc_pcie_phy>; + resets = <&src IMX7_RESET_PCIEPHY>, + <&src IMX7_RESET_PCIE_CTRL_APPS_EN>; + reset-names = "pciephy", "apps"; + status = "disabled"; + }; }; &ca_funnel_ports { diff --git a/arch/arm/boot/dts/imx7s-warp.dts b/arch/arm/boot/dts/imx7s-warp.dts index d5237fd0fa657f..8dfed85471e1e1 100644 --- a/arch/arm/boot/dts/imx7s-warp.dts +++ b/arch/arm/boot/dts/imx7s-warp.dts @@ -295,6 +295,7 @@ assigned-clocks = <&clks IMX7D_USDHC3_ROOT_CLK>; assigned-clock-rates = <400000000>; bus-width = <8>; + no-1-8-v; fsl,tuning-step = <2>; non-removable; status = "okay"; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index c4f12fd2e044e4..4cf6c458b583f6 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -42,6 +42,7 @@ */ #include +#include #include #include #include @@ -119,7 +120,7 @@ #address-cells = <1>; #size-cells = <1>; compatible = "simple-bus"; - interrupt-parent = <&intc>; + interrupt-parent = <&gpc>; ranges; funnel@30041000 { @@ -301,6 +302,7 @@ interrupts = ; #interrupt-cells = <3>; interrupt-controller; + interrupt-parent = <&intc>; reg = <0x31001000 0x1000>, <0x31002000 0x2000>, <0x31004000 0x2000>, @@ -309,6 +311,7 @@ timer { compatible = "arm,armv7-timer"; + interrupt-parent = <&intc>; interrupts = , , , @@ -488,7 +491,8 @@ }; gpr: iomuxc-gpr@30340000 { - compatible = "fsl,imx7d-iomuxc-gpr", "syscon"; + compatible = "fsl,imx7d-iomuxc-gpr", + "fsl,imx6q-iomuxc-gpr", "syscon"; reg = <0x30340000 0x10000>; }; @@ -516,6 +520,7 @@ anatop-min-bit-val = <8>; anatop-min-voltage = <800000>; anatop-max-voltage = <1200000>; + anatop-enable-bit = <0>; }; }; @@ -563,6 +568,27 @@ interrupts = ; #reset-cells = <1>; }; + + gpc: gpc@303a0000 { + compatible = "fsl,imx7d-gpc"; + reg = <0x303a0000 0x10000>; + interrupt-controller; + interrupts = ; + #interrupt-cells = <3>; + interrupt-parent = <&intc>; + #power-domain-cells = <1>; + + pgc { + #address-cells = <1>; + #size-cells = <0>; + + pgc_pcie_phy: pgc-power-domain@IMX7_POWER_DOMAIN_PCIE_PHY { + #power-domain-cells = <0>; + reg = ; + power-supply = <®_1p0d>; + }; + }; + }; }; aips2: aips-bus@30400000 { @@ -609,7 +635,7 @@ clocks = <&clks IMX7D_PWM1_ROOT_CLK>, <&clks IMX7D_PWM1_ROOT_CLK>; clock-names = "ipg", "per"; - #pwm-cells = <2>; + #pwm-cells = <3>; status = "disabled"; }; @@ -620,7 +646,7 @@ clocks = <&clks IMX7D_PWM2_ROOT_CLK>, <&clks IMX7D_PWM2_ROOT_CLK>; clock-names = "ipg", "per"; - #pwm-cells = <2>; + #pwm-cells = <3>; status = "disabled"; }; @@ -631,7 +657,7 @@ clocks = <&clks IMX7D_PWM3_ROOT_CLK>, <&clks IMX7D_PWM3_ROOT_CLK>; clock-names = "ipg", "per"; - #pwm-cells = <2>; + #pwm-cells = <3>; status = "disabled"; }; @@ -642,7 +668,7 @@ clocks = <&clks IMX7D_PWM4_ROOT_CLK>, <&clks IMX7D_PWM4_ROOT_CLK>; clock-names = "ipg", "per"; - #pwm-cells = <2>; + #pwm-cells = <3>; status = "disabled"; }; @@ -934,8 +960,8 @@ compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc"; reg = <0x30b40000 0x10000>; interrupts = ; - clocks = <&clks IMX7D_CLK_DUMMY>, - <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_IPG_ROOT_CLK>, + <&clks IMX7D_NAND_USDHC_BUS_ROOT_CLK>, <&clks IMX7D_USDHC1_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; @@ -946,8 +972,8 @@ compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc"; reg = <0x30b50000 0x10000>; interrupts = ; - clocks = <&clks IMX7D_CLK_DUMMY>, - <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_IPG_ROOT_CLK>, + <&clks IMX7D_NAND_USDHC_BUS_ROOT_CLK>, <&clks IMX7D_USDHC2_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; @@ -958,8 +984,8 @@ compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc"; reg = <0x30b60000 0x10000>; interrupts = ; - clocks = <&clks IMX7D_CLK_DUMMY>, - <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_IPG_ROOT_CLK>, + <&clks IMX7D_NAND_USDHC_BUS_ROOT_CLK>, <&clks IMX7D_USDHC3_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts index 692fcbb1434ab0..61883cb969d213 100644 --- a/arch/arm/boot/dts/keystone-k2g-evm.dts +++ b/arch/arm/boot/dts/keystone-k2g-evm.dts @@ -20,7 +20,7 @@ compatible = "ti,k2g-evm", "ti,k2g", "ti,keystone"; model = "Texas Instruments K2G General Purpose EVM"; - memory { + memory@800000000 { device_type = "memory"; reg = <0x00000008 0x00000000 0x00000000 0x80000000>; }; diff --git a/arch/arm/boot/dts/keystone-k2g-ice.dts b/arch/arm/boot/dts/keystone-k2g-ice.dts new file mode 100644 index 00000000000000..d820d37b5148ec --- /dev/null +++ b/arch/arm/boot/dts/keystone-k2g-ice.dts @@ -0,0 +1,35 @@ +/* + * Device Tree Source for K2G Industrial Communication Engine EVM + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * SPDX-License-Identifier: GPL-2.0 + */ +/dts-v1/; + +#include "keystone-k2g.dtsi" + +/ { + compatible = "ti,k2g-ice", "ti,k2g", "ti,keystone"; + model = "Texas Instruments K2G Industrial Communication EVM"; + + memory@800000000 { + device_type = "memory"; + reg = <0x00000008 0x00000000 0x00000000 0x20000000>; + }; +}; + +&k2g_pinctrl { + uart0_pins: pinmux_uart0_pins { + pinctrl-single,pins = < + K2G_CORE_IOPAD(0x11cc) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0) /* uart0_rxd.uart0_rxd */ + K2G_CORE_IOPAD(0x11d0) (BUFFER_CLASS_B | PIN_PULLDOWN | MUX_MODE0) /* uart0_txd.uart0_txd */ + >; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; + status = "okay"; +}; diff --git a/arch/arm/boot/dts/keystone-k2g.dtsi b/arch/arm/boot/dts/keystone-k2g.dtsi index f59567fe7d91d0..a789f75a1ed522 100644 --- a/arch/arm/boot/dts/keystone-k2g.dtsi +++ b/arch/arm/boot/dts/keystone-k2g.dtsi @@ -15,7 +15,6 @@ #include #include -#include "skeleton.dtsi" / { compatible = "ti,k2g","ti,keystone"; @@ -24,6 +23,8 @@ #size-cells = <2>; interrupt-parent = <&gic>; + chosen { }; + aliases { serial0 = &uart0; }; diff --git a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi index b6f26824e83a96..66f615a74118b9 100644 --- a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi +++ b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi @@ -137,8 +137,8 @@ netcp: netcp@26000000 { /* NetCP address range */ ranges = <0 0x26000000 0x1000000>; - clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>, <&clkosr>; - clock-names = "pa_clk", "ethss_clk", "cpts", "osr_clk"; + clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>; + clock-names = "pa_clk", "ethss_clk", "cpts"; dma-coherent; ti,navigator-dmas = <&dma_gbe 0>, diff --git a/arch/arm/boot/dts/keystone-k2l.dtsi b/arch/arm/boot/dts/keystone-k2l.dtsi index b58e7ebc091994..148650406cf701 100644 --- a/arch/arm/boot/dts/keystone-k2l.dtsi +++ b/arch/arm/boot/dts/keystone-k2l.dtsi @@ -232,6 +232,14 @@ }; }; + osr: sram@70000000 { + compatible = "mmio-sram"; + reg = <0x70000000 0x10000>; + #address-cells = <1>; + #size-cells = <1>; + clocks = <&clkosr>; + }; + dspgpio0: keystone_dsp_gpio@02620240 { compatible = "ti,keystone-dsp-gpio"; gpio-controller; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index efe53998c96124..6d89736c7b44b2 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -7,6 +7,10 @@ #include / { + chosen { + stdout-path = &uart1; + }; + cpus { cpu@0 { cpu0-supply = <&vcc>; diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index 8c77c87660cdf2..8d9c36970dfd29 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -65,100 +65,108 @@ #interrupt-cells = <3>; }; - timer@c1109940 { - compatible = "amlogic,meson6-timer"; - reg = <0xc1109940 0x18>; - interrupts = <0 10 1>; - }; - soc { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; ranges; - wdt: watchdog@c1109900 { - compatible = "amlogic,meson6-wdt"; - reg = <0xc1109900 0x8>; - interrupts = <0 0 1>; - }; - - uart_AO: serial@c81004c0 { - compatible = "amlogic,meson-uart"; - reg = <0xc81004c0 0x18>; - interrupts = <0 90 1>; - clocks = <&clk81>; - status = "disabled"; - }; - - uart_A: serial@c11084c0 { - compatible = "amlogic,meson-uart"; - reg = <0xc11084c0 0x18>; - interrupts = <0 26 1>; - clocks = <&clk81>; - status = "disabled"; - }; - - uart_B: serial@c11084dc { - compatible = "amlogic,meson-uart"; - reg = <0xc11084dc 0x18>; - interrupts = <0 75 1>; - clocks = <&clk81>; - status = "disabled"; - }; - - uart_C: serial@c1108700 { - compatible = "amlogic,meson-uart"; - reg = <0xc1108700 0x18>; - interrupts = <0 93 1>; - clocks = <&clk81>; - status = "disabled"; - }; - - i2c_AO: i2c@c8100500 { - compatible = "amlogic,meson6-i2c"; - reg = <0xc8100500 0x20>; - interrupts = <0 92 1>; - clocks = <&clk81>; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; - }; - - i2c_A: i2c@c1108500 { - compatible = "amlogic,meson6-i2c"; - reg = <0xc1108500 0x20>; - interrupts = <0 21 1>; - clocks = <&clk81>; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; - }; - - i2c_B: i2c@c11087c0 { - compatible = "amlogic,meson6-i2c"; - reg = <0xc11087c0 0x20>; - interrupts = <0 128 1>; - clocks = <&clk81>; + cbus: cbus@c1100000 { + compatible = "simple-bus"; + reg = <0xc1100000 0x200000>; #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; + #size-cells = <1>; + ranges = <0x0 0xc1100000 0x200000>; + + uart_A: serial@84c0 { + compatible = "amlogic,meson-uart"; + reg = <0x84c0 0x18>; + interrupts = <0 26 1>; + status = "disabled"; + }; + + uart_B: serial@84dc { + compatible = "amlogic,meson-uart"; + reg = <0x84dc 0x18>; + interrupts = <0 75 1>; + status = "disabled"; + }; + + i2c_A: i2c@8500 { + compatible = "amlogic,meson6-i2c"; + reg = <0x8500 0x20>; + interrupts = <0 21 1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + uart_C: serial@8700 { + compatible = "amlogic,meson-uart"; + reg = <0x8700 0x18>; + interrupts = <0 93 1>; + status = "disabled"; + }; + + i2c_B: i2c@87c0 { + compatible = "amlogic,meson6-i2c"; + reg = <0x87c0 0x20>; + interrupts = <0 128 1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spifc: spi@8c80 { + compatible = "amlogic,meson6-spifc"; + reg = <0x8c80 0x80>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + wdt: watchdog@9900 { + compatible = "amlogic,meson6-wdt"; + reg = <0x9900 0x8>; + interrupts = <0 0 1>; + }; + + timer@9940 { + compatible = "amlogic,meson6-timer"; + reg = <0x9940 0x18>; + interrupts = <0 10 1>; + }; }; - ir_receiver: ir-receiver@c8100480 { - compatible= "amlogic,meson6-ir"; - reg = <0xc8100480 0x20>; - interrupts = <0 15 1>; - status = "disabled"; - }; - - spifc: spi@c1108c80 { - compatible = "amlogic,meson6-spifc"; - reg = <0xc1108c80 0x80>; + aobus: aobus@c8100000 { + compatible = "simple-bus"; + reg = <0xc8100000 0x100000>; #address-cells = <1>; - #size-cells = <0>; - clocks = <&clk81>; - status = "disabled"; + #size-cells = <1>; + ranges = <0x0 0xc8100000 0x100000>; + + ir_receiver: ir-receiver@480 { + compatible= "amlogic,meson6-ir"; + reg = <0x480 0x20>; + interrupts = <0 15 1>; + status = "disabled"; + }; + + uart_AO: serial@4c0 { + compatible = "amlogic,meson-uart"; + reg = <0x4c0 0x18>; + interrupts = <0 90 1>; + status = "disabled"; + }; + + i2c_AO: i2c@500 { + compatible = "amlogic,meson6-i2c"; + reg = <0x500 0x20>; + interrupts = <0 92 1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; }; ethmac: ethernet@c9410000 { @@ -167,8 +175,6 @@ 0xc1108108 0x4>; interrupts = <0 8 1>; interrupt-names = "macirq"; - clocks = <&clk81>; - clock-names = "stmmaceth"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/meson6.dtsi b/arch/arm/boot/dts/meson6.dtsi index 8b33be15af943c..b0fc91ffd6a139 100644 --- a/arch/arm/boot/dts/meson6.dtsi +++ b/arch/arm/boot/dts/meson6.dtsi @@ -51,8 +51,6 @@ model = "Amlogic Meson6 SoC"; compatible = "amlogic,meson6"; - interrupt-parent = <&gic>; - cpus { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index ebc763eab195a7..6993077331c760 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -50,8 +50,6 @@ model = "Amlogic Meson8 SoC"; compatible = "amlogic,meson8"; - interrupt-parent = <&gic>; - cpus { #address-cells = <1>; #size-cells = <0>; @@ -91,18 +89,55 @@ clock-frequency = <141666666>; }; - pinctrl_cbus: pinctrl@c1109880 { +}; /* end of / */ + +&aobus { + pinctrl_aobus: pinctrl@84 { + compatible = "amlogic,meson8-aobus-pinctrl"; + reg = <0x84 0xc>; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + gpio_ao: ao-bank@14 { + reg = <0x14 0x4>, + <0x2c 0x4>, + <0x24 0x8>; + reg-names = "mux", "pull", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_aobus 0 120 16>; + }; + + uart_ao_a_pins: uart_ao_a { + mux { + groups = "uart_tx_ao_a", "uart_rx_ao_a"; + function = "uart_ao"; + }; + }; + + i2c_ao_pins: i2c_mst_ao { + mux { + groups = "i2c_mst_sck_ao", "i2c_mst_sda_ao"; + function = "i2c_mst_ao"; + }; + }; + }; +}; + +&cbus { + pinctrl_cbus: pinctrl@9880 { compatible = "amlogic,meson8-cbus-pinctrl"; - reg = <0xc1109880 0x10>; + reg = <0x9880 0x10>; #address-cells = <1>; #size-cells = <1>; ranges; - gpio: banks@c11080b0 { - reg = <0xc11080b0 0x28>, - <0xc11080e8 0x18>, - <0xc1108120 0x18>, - <0xc1108030 0x30>; + gpio: banks@80b0 { + reg = <0x80b0 0x28>, + <0x80e8 0x18>, + <0x8120 0x18>, + <0x8030 0x30>; reg-names = "mux", "pull", "pull-enable", "gpio"; gpio-controller; #gpio-cells = <2>; @@ -134,36 +169,47 @@ }; }; }; - - pinctrl_aobus: pinctrl@c8100084 { - compatible = "amlogic,meson8-aobus-pinctrl"; - reg = <0xc8100084 0xc>; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - gpio_ao: ao-bank@c1108030 { - reg = <0xc8100014 0x4>, - <0xc810002c 0x4>, - <0xc8100024 0x8>; - reg-names = "mux", "pull", "gpio"; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pinctrl_aobus 0 120 16>; - }; - - uart_ao_a_pins: uart_ao_a { - mux { - groups = "uart_tx_ao_a", "uart_rx_ao_a"; - function = "uart_ao"; - }; - }; - - i2c_ao_pins: i2c_mst_ao { - mux { - groups = "i2c_mst_sck_ao", "i2c_mst_sda_ao"; - function = "i2c_mst_ao"; - }; - }; - }; -}; /* end of / */ +}; + +ðmac { + clocks = <&clk81>; + clock-names = "stmmaceth"; +}; + +&i2c_AO { + clocks = <&clk81>; +}; + +&i2c_A { + clocks = <&clk81>; +}; + +&i2c_B { + clocks = <&clk81>; +}; + +&L2 { + arm,data-latency = <3 3 3>; + arm,tag-latency = <2 2 2>; + arm,filter-ranges = <0x100000 0xc0000000>; +}; + +&spifc { + clocks = <&clk81>; +}; + +&uart_AO { + clocks = <&clk81>; +}; + +&uart_A { + clocks = <&clk81>; +}; + +&uart_B { + clocks = <&clk81>; +}; + +&uart_C { + clocks = <&clk81>; +}; diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi index 828aa49c678cd4..d9f116a418b23e 100644 --- a/arch/arm/boot/dts/meson8b.dtsi +++ b/arch/arm/boot/dts/meson8b.dtsi @@ -47,11 +47,9 @@ #include #include #include -#include "skeleton.dtsi" +#include "meson.dtsi" / { - interrupt-parent = <&gic>; - cpus { #address-cells = <1>; #size-cells = <0>; @@ -84,147 +82,113 @@ reg = <0x203>; }; }; +}; /* end of / */ - soc { - compatible = "simple-bus"; +&aobus { + pinctrl_aobus: pinctrl@84 { + compatible = "amlogic,meson8b-aobus-pinctrl"; + reg = <0x84 0xc>; #address-cells = <1>; #size-cells = <1>; ranges; - L2: l2-cache-controller@c4200000 { - compatible = "arm,pl310-cache"; - reg = <0xc4200000 0x1000>; - cache-unified; - cache-level = <2>; - }; - - gic: interrupt-controller@c4301000 { - compatible = "arm,cortex-a9-gic"; - reg = <0xc4301000 0x1000>, - <0xc4300100 0x0100>; - interrupt-controller; - #interrupt-cells = <3>; + gpio_ao: ao-bank@14 { + reg = <0x14 0x4>, + <0x2c 0x4>, + <0x24 0x8>; + reg-names = "mux", "pull", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_aobus 0 130 16>; }; - reset: reset-controller@c1104404 { - compatible = "amlogic,meson8b-reset"; - reg = <0xc1104404 0x20>; - #reset-cells = <1>; + uart_ao_a_pins: uart_ao_a { + mux { + groups = "uart_tx_ao_a", "uart_rx_ao_a"; + function = "uart_ao"; + }; }; + }; +}; - wdt: watchdog@c1109900 { - compatible = "amlogic,meson8b-wdt"; - reg = <0xc1109900 0x8>; - interrupts = <0 0 1>; - }; +&cbus { + clkc: clock-controller@4000 { + #clock-cells = <1>; + compatible = "amlogic,meson8b-clkc"; + reg = <0x8000 0x4>, <0x4000 0x460>; + }; - timer@c1109940 { - compatible = "amlogic,meson6-timer"; - reg = <0xc1109940 0x18>; - interrupts = <0 10 1>; - }; + reset: reset-controller@4404 { + compatible = "amlogic,meson8b-reset"; + reg = <0x4404 0x20>; + #reset-cells = <1>; + }; - uart_AO: serial@c81004c0 { - compatible = "amlogic,meson-uart"; - reg = <0xc81004c0 0x18>; - interrupts = <0 90 1>; - clocks = <&clkc CLKID_CLK81>; - status = "disabled"; - }; + pwm_ab: pwm@8550 { + compatible = "amlogic,meson8b-pwm"; + reg = <0x8550 0x10>; + #pwm-cells = <3>; + status = "disabled"; + }; - uart_A: serial@c11084c0 { - compatible = "amlogic,meson-uart"; - reg = <0xc11084c0 0x18>; - interrupts = <0 26 1>; - clocks = <&clkc CLKID_CLK81>; - status = "disabled"; - }; + pwm_cd: pwm@8650 { + compatible = "amlogic,meson8b-pwm"; + reg = <0x8650 0x10>; + #pwm-cells = <3>; + status = "disabled"; + }; - uart_B: serial@c11084dc { - compatible = "amlogic,meson-uart"; - reg = <0xc11084dc 0x18>; - interrupts = <0 75 1>; - clocks = <&clkc CLKID_CLK81>; - status = "disabled"; - }; + pwm_ef: pwm@86c0 { + compatible = "amlogic,meson8b-pwm"; + reg = <0x86c0 0x10>; + #pwm-cells = <3>; + status = "disabled"; + }; - uart_C: serial@c1108700 { - compatible = "amlogic,meson-uart"; - reg = <0xc1108700 0x18>; - interrupts = <0 93 1>; - clocks = <&clkc CLKID_CLK81>; - status = "disabled"; - }; + wdt: watchdog@9900 { + compatible = "amlogic,meson8b-wdt"; + reg = <0x9900 0x8>; + interrupts = <0 0 1>; + }; - clkc: clock-controller@c1104000 { - #clock-cells = <1>; - compatible = "amlogic,meson8b-clkc"; - reg = <0xc1108000 0x4>, <0xc1104000 0x460>; - }; + pinctrl_cbus: pinctrl@9880 { + compatible = "amlogic,meson8b-cbus-pinctrl"; + reg = <0x9880 0x10>; + #address-cells = <1>; + #size-cells = <1>; + ranges; - pwm_ab: pwm@8550 { - compatible = "amlogic,meson8b-pwm"; - reg = <0xc1108550 0x10>; - #pwm-cells = <3>; - status = "disabled"; + gpio: banks@80b0 { + reg = <0x80b0 0x28>, + <0x80e8 0x18>, + <0x8120 0x18>, + <0x8030 0x38>; + reg-names = "mux", "pull", "pull-enable", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_cbus 0 0 130>; }; + }; +}; - pwm_cd: pwm@8650 { - compatible = "amlogic,meson8b-pwm"; - reg = <0xc1108650 0x10>; - #pwm-cells = <3>; - status = "disabled"; - }; +&L2 { + arm,data-latency = <3 3 3>; + arm,tag-latency = <2 2 2>; + arm,filter-ranges = <0x100000 0xc0000000>; +}; - pwm_ef: pwm@86c0 { - compatible = "amlogic,meson8b-pwm"; - reg = <0xc11086c0 0x10>; - #pwm-cells = <3>; - status = "disabled"; - }; +&uart_AO { + clocks = <&clkc CLKID_CLK81>; +}; - pinctrl_cbus: pinctrl@c1109880 { - compatible = "amlogic,meson8b-cbus-pinctrl"; - reg = <0xc1109880 0x10>; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - gpio: banks@c11080b0 { - reg = <0xc11080b0 0x28>, - <0xc11080e8 0x18>, - <0xc1108120 0x18>, - <0xc1108030 0x38>; - reg-names = "mux", "pull", "pull-enable", "gpio"; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pinctrl_cbus 0 0 130>; - }; - }; +&uart_A { + clocks = <&clkc CLKID_CLK81>; +}; - pinctrl_aobus: pinctrl@c8100084 { - compatible = "amlogic,meson8b-aobus-pinctrl"; - reg = <0xc8100084 0xc>; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - gpio_ao: ao-bank@c1108030 { - reg = <0xc8100014 0x4>, - <0xc810002c 0x4>, - <0xc8100024 0x8>; - reg-names = "mux", "pull", "gpio"; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pinctrl_aobus 0 130 16>; - }; +&uart_B { + clocks = <&clkc CLKID_CLK81>; +}; - uart_ao_a_pins: uart_ao_a { - mux { - groups = "uart_tx_ao_a", "uart_rx_ao_a"; - function = "uart_ao"; - }; - }; - }; - }; -}; /* end of / */ +&uart_C { + clocks = <&clkc CLKID_CLK81>; +}; diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi index 57b9a028a49a68..fccd5383243cc1 100644 --- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi +++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi @@ -188,7 +188,7 @@ clock-frequency = <400000>; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c02"; pagesize = <16>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi index f330c69cc683ce..82aa9c4a0f1c33 100644 --- a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi +++ b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi @@ -201,7 +201,8 @@ }; &gpmc { - ranges = <0 0 0x30000000 0x1000000>; /* CS0: 16MB for NAND */ + ranges = <0 0 0x30000000 0x1000000 /* CS0: 16MB for NAND */ + 6 0 0x2c000000 0x1000000>; /* CS6: 16MB for DM9000 */ nand@0,0 { compatible = "ti,omap2-nand"; @@ -256,12 +257,8 @@ reg = <0x680000 0xf980000>; }; }; -}; - -&gpmc { - ranges = <6 0 0x2c000000 0x1000000>; /* CS6: 16MB for DM9000 */ - ethernet@0,0 { + ethernet@6,0 { compatible = "davicom,dm9000"; reg = <6 0x000 2 6 0x400 2>; /* CS6, offset 0 and 0x400, IO size 2 */ diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts index 4f9a765446026f..c963b31ec3b3cd 100644 --- a/arch/arm/boot/dts/omap3-evm-37xx.dts +++ b/arch/arm/boot/dts/omap3-evm-37xx.dts @@ -34,7 +34,15 @@ >; }; +&hsusb2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&ehci_phy_pins>; +}; + &omap3_pmx_core { + pinctrl-names = "default"; + pinctrl-0 = <&on_board_gpio_61 &hsusb2_pins>; + dss_dpi_pins1: pinmux_dss_dpi_pins2 { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ @@ -98,6 +106,37 @@ >; }; + /* Devices are routed with gpmc_nbe1.gpio_61 to on-board devices */ + on_board_gpio_61: pinmux_ehci_port_select_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x20c8, PIN_OUTPUT | MUX_MODE4) + >; + }; + + /* Used by OHCI and EHCI. OHCI won't work without external phy */ + hsusb2_pins: pinmux_hsusb2_pins { + pinctrl-single,pins = < + + /* mcspi1_cs3.hsusb2_data2 */ + OMAP3_CORE1_IOPAD(0x21d4, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* mcspi2_clk.hsusb2_data7 */ + OMAP3_CORE1_IOPAD(0x21d6, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* mcspi2_simo.hsusb2_data4 */ + OMAP3_CORE1_IOPAD(0x21d8, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* mcspi2_somi.hsusb2_data5 */ + OMAP3_CORE1_IOPAD(0x21da, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* mcspi2_cs0.hsusb2_data6 */ + OMAP3_CORE1_IOPAD(0x21dc, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* mcspi2_cs1.hsusb2_data3 */ + OMAP3_CORE1_IOPAD(0x21de, PIN_INPUT_PULLDOWN | MUX_MODE3) + >; + }; + wl12xx_gpio: pinmux_wl12xx_gpio { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2180, PIN_OUTPUT | MUX_MODE4) /* uart1_cts.gpio_150 */ @@ -112,6 +151,46 @@ }; }; +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + + ehci_phy_pins: pinmux_ehci_phy_pins { + pinctrl-single,pins = < + + /* EHCI PHY reset GPIO etk_d7.gpio_21 */ + OMAP3630_CORE2_IOPAD(0x25ea, PIN_OUTPUT | MUX_MODE4) + + /* EHCI VBUS etk_d8.gpio_22 */ + OMAP3630_CORE2_IOPAD(0x25ec, PIN_OUTPUT | MUX_MODE4) + >; + }; + + /* Used by OHCI and EHCI. OHCI won't work without external phy */ + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + + /* etk_d10.hsusb2_clk */ + OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) + + /* etk_d11.hsusb2_stp */ + OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) + + /* etk_d12.hsusb2_dir */ + OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* etk_d13.hsusb2_nxt */ + OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* etk_d14.hsusb2_data0 */ + OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) + + /* etk_d15.hsusb2_data1 */ + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) + >; + }; +}; + &omap3_pmx_wkup { dss_dpi_pins2: pinmux_dss_dpi_pins1 { pinctrl-single,pins = < @@ -153,6 +232,29 @@ pinctrl-0 = <&uart3_pins>; }; +/* + * GPIO_61 (nUSB2_EN_1V8) must be low to enable on-board EHCI USB2 interface + * for bus switch SN74CB3Q3384A, level-shifter SN74AVC16T245DGGR, and 1.8V. + */ +&gpio2 { + en_usb2_port { + gpio-hog; + gpios = <29 GPIO_ACTIVE_HIGH>; /* gpio_61 */ + output-low; + line-name = "enable usb2 port"; + }; +}; + +/* T2_GPIO_2 low to route GPIO_61 to on-board devices */ +&twl_gpio { + en_on_board_gpio_61 { + gpio-hog; + gpios = <2 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "en_hsusb2_clk"; + }; +}; + &gpmc { ranges = <0 0 0x30000000 0x1000000>, /* CS0: 16MB for NAND */ <5 0 0x2c000000 0x01000000>; diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi index 090475083c2f28..2b1d6977a53572 100644 --- a/arch/arm/boot/dts/omap3-evm-common.dtsi +++ b/arch/arm/boot/dts/omap3-evm-common.dtsi @@ -12,6 +12,24 @@ }; }; + /* HS USB Port 2 Power */ + hsusb2_power: hsusb2_power_reg { + compatible = "regulator-fixed"; + regulator-name = "hsusb2_vbus"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio1 22 GPIO_ACTIVE_HIGH>; /* gpio_22 */ + startup-delay-us = <70000>; + enable-active-high; + }; + + /* HS USB Host PHY on PORT 2 */ + hsusb2_phy: hsusb2_phy { + compatible = "usb-nop-xceiv"; + reset-gpios = <&gpio1 21 GPIO_ACTIVE_LOW>; /* gpio_21 */ + vcc-supply = <&hsusb2_power>; + }; + leds { compatible = "gpio-leds"; ledb { @@ -76,7 +94,6 @@ &lcd_3v3 { gpio = <&gpio5 25 GPIO_ACTIVE_LOW>; /* gpio153 */ - enable-active-low; }; &lcd0 { @@ -143,6 +160,14 @@ >; }; +&usbhshost { + port2-mode = "ehci-phy"; +}; + +&usbhsehci { + phys = <0 &hsusb2_phy>; +}; + &usb_otg_hs { interface-type = <0>; usb-phy = <&usb2_phy>; @@ -159,3 +184,10 @@ reg = <5 0 0xff>; }; }; + +&vaux2 { + regulator-name = "usb_1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; +}; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 9ec73706936967..4504908c23fe99 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -419,7 +419,7 @@ /* RFID EEPROM */ m24lr64@50 { - compatible = "at,24c64"; + compatible = "atmel,24c64"; reg = <0x50>; }; }; diff --git a/arch/arm/boot/dts/omap3-sb-t35.dtsi b/arch/arm/boot/dts/omap3-sb-t35.dtsi index 73643fabde5d10..4476fb685a1bf6 100644 --- a/arch/arm/boot/dts/omap3-sb-t35.dtsi +++ b/arch/arm/boot/dts/omap3-sb-t35.dtsi @@ -50,7 +50,6 @@ pinctrl-names = "default"; pinctrl-0 = <&sb_t35_audio_amp>; gpio = <&gpio2 29 GPIO_ACTIVE_LOW>; /* gpio_61 */ - enable-active-low; regulator-always-on; }; }; @@ -90,7 +89,7 @@ clock-frequency = <400000>; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c02"; pagesize = <16>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi index dc80886b532929..06ac0f80bcf083 100644 --- a/arch/arm/boot/dts/omap3-tao3530.dtsi +++ b/arch/arm/boot/dts/omap3-tao3530.dtsi @@ -63,7 +63,6 @@ regulator-min-microvolt = <3150000>; regulator-max-microvolt = <3150000>; gpio = <&gpio5 29 GPIO_ACTIVE_LOW>; /* gpio_157 */ - enable-active-low; startup-delay-us = <10000>; }; }; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 89eb607f4a9e1a..13f8d864020838 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -453,6 +453,15 @@ OMAP4_IOPAD(0x1c8, PIN_INPUT_PULLUP | MUX_MODE7) >; }; + + uart4_pins: pinmux_uart4_pins { + pinctrl-single,pins = < + OMAP4_IOPAD(0x15c, PIN_INPUT | MUX_MODE0) /* uart4_rx */ + OMAP4_IOPAD(0x15e, PIN_OUTPUT | MUX_MODE0) /* uart4_tx */ + OMAP4_IOPAD(0x110, PIN_INPUT_PULLUP | MUX_MODE5) /* uart4_cts */ + OMAP4_IOPAD(0x112, PIN_OUTPUT_PULLUP | MUX_MODE5) /* uart4_rts */ + >; + }; }; &omap4_pmx_wkup { @@ -469,6 +478,17 @@ &omap4_pmx_core 0x17c>; }; +&uart4 { + pinctrl-names = "default"; + pinctrl-0 = <&uart4_pins>; + + bluetooth { + compatible = "ti,wl1285-st"; + enable-gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>; /* gpio 174 */ + max-speed = <3686400>; + }; +}; + &usbhsehci { phys = <&hsusb1_phy>; }; diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi index ec0bd9779e1a58..6e6810c258eb29 100644 --- a/arch/arm/boot/dts/omap4-duovero.dtsi +++ b/arch/arm/boot/dts/omap4-duovero.dtsi @@ -12,6 +12,10 @@ model = "Gumstix Duovero"; compatible = "gumstix,omap4-duovero", "ti,omap4430", "ti,omap4"; + chosen { + stdout-path = &uart3; + }; + memory@80000000 { device_type = "memory"; reg = <0x80000000 0x40000000>; /* 1 GB */ diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi index 758b6eb7ae43d9..6500bfc8d1309a 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi @@ -241,7 +241,7 @@ }; eeprom@50 { - compatible = "microchip,24c32"; + compatible = "microchip,24c32", "atmel,24c32"; reg = <0x50>; }; }; diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index b153f604932a88..78397f66d0b2d5 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -404,7 +404,7 @@ clock-frequency = <400000>; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c02"; pagesize = <16>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/omap5-sbc-t54.dts b/arch/arm/boot/dts/omap5-sbc-t54.dts index 337bbbc01a3506..7b8810d13257eb 100644 --- a/arch/arm/boot/dts/omap5-sbc-t54.dts +++ b/arch/arm/boot/dts/omap5-sbc-t54.dts @@ -44,7 +44,7 @@ clock-frequency = <400000>; at24@50 { - compatible = "at24,24c02"; + compatible = "atmel,24c02"; pagesize = <16>; reg = <0x50>; }; diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index 0d42c46f13e7e3..ec2c8baef62ac0 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -137,6 +137,13 @@ }; }; +&mmc1 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; + + cd-gpios = <&gpio5 24 GPIO_ACTIVE_LOW>; /* gpio5_152 */ +}; + &omap5_pmx_core { evm_keys_pins: pinmux_evm_keys_gpio_pins { pinctrl-single,pins = < @@ -150,6 +157,12 @@ OMAP5_IOPAD(0x1c8, PIN_INPUT | MUX_MODE0) /* i2c5_sda */ >; }; + + mmc1_pins: pinmux_mmc1_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x1d4, PIN_INPUT_PULLUP | MUX_MODE6) /* gpio5_152 */ + >; + }; }; &tpd12s015 { diff --git a/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts index 8f5de029bca9ea..f245064f320ef1 100644 --- a/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts +++ b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts @@ -319,44 +319,38 @@ target-supply = <&pm8921_lvs7>; }; - /* OTG */ - phy@12500000 { - status = "okay"; - dr_mode = "peripheral"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l4>; - }; - - phy@12520000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - phy@12530000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - gadget@12500000 { - status = "okay"; - }; - /* OTG */ usb@12500000 { status = "okay"; + dr_mode = "peripheral"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l4>; + }; + }; }; usb@12520000 { status = "okay"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; usb@12530000 { status = "okay"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; amba { diff --git a/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts b/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts index e39440a867399f..3483a66e44c156 100644 --- a/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts +++ b/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts @@ -320,22 +320,16 @@ }; }; - /* OTG */ - phy@12500000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l4>; - dr_mode = "otg"; - }; - - gadget@12500000 { - status = "okay"; - }; - /* OTG */ usb@12500000 { status = "okay"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l4>; + }; + }; }; amba { diff --git a/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts index 35f1d46edded1a..5b151e425530e8 100644 --- a/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts +++ b/arch/arm/boot/dts/qcom-apq8064-cm-qs600.dts @@ -150,42 +150,37 @@ }; /* OTG */ - usb1_phy: phy@12500000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l4>; - }; - - usb3_phy: phy@12520000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - usb4_phy: phy@12530000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - gadget1: gadget@12500000 { - status = "ok"; - }; - - /* OTG */ - usb1: usb@12500000 { + usb@12500000 { status = "ok"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l4>; + }; + }; }; - usb3: usb@12520000 { + usb@12520000 { status = "okay"; + dr_mode = "host"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; - usb4: usb@12530000 { + usb@12530000 { status = "okay"; + dr_mode = "host"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; /* on board fixed 3.3v supply */ diff --git a/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts b/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts index 881ce707311a05..053b5bdd7808c9 100644 --- a/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts +++ b/arch/arm/boot/dts/qcom-apq8064-ifc6410.dts @@ -244,42 +244,37 @@ }; /* OTG */ - usb1_phy: phy@12500000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l4>; - }; - - usb3_phy: phy@12520000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - usb4_phy: phy@12530000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l23>; - }; - - gadget1: gadget@12500000 { - status = "okay"; - }; - - /* OTG */ - usb1: usb@12500000 { + usb@12500000 { status = "okay"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l4>; + }; + }; }; - usb3: usb@12520000 { + usb@12520000 { status = "okay"; + dr_mode = "host"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; - usb4: usb@12530000 { + usb@12530000 { status = "okay"; + dr_mode = "host"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l23>; + }; + }; }; pci@1b500000 { diff --git a/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts b/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts index a34ba355545495..88a9aff41e2f59 100644 --- a/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts +++ b/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts @@ -349,15 +349,15 @@ }; }; - phy@12500000 { - status = "okay"; - vddcx-supply = <&pm8921_s3>; - v3p3-supply = <&pm8921_l3>; - v1p8-supply = <&pm8921_l4>; - }; - - gadget@12500000 { + usb@12500000 { status = "okay"; + dr_mode = "otg"; + ulpi { + phy { + v3p3-supply = <&pm8921_l3>; + v1p8-supply = <&pm8921_l4>; + }; + }; }; gsbi@1a200000 { diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 14a6f5ed02de66..f3db185a68090c 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -197,7 +197,7 @@ clock-frequency = <27000000>; }; - sleep_clk { + sleep_clk: sleep_clk { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <32768>; @@ -884,81 +884,97 @@ }; }; - usb1_phy: phy@12500000 { - compatible = "qcom,usb-otg-ci"; - reg = <0x12500000 0x400>; - interrupts = ; - status = "disabled"; - - clocks = <&gcc USB_HS1_XCVR_CLK>, - <&gcc USB_HS1_H_CLK>; - clock-names = "core", "iface"; - - resets = <&gcc USB_HS1_RESET>; - reset-names = "link"; - }; - - usb3_phy: phy@12520000 { - compatible = "qcom,usb-otg-ci"; - reg = <0x12520000 0x400>; - interrupts = ; - status = "disabled"; - dr_mode = "host"; - - clocks = <&gcc USB_HS3_XCVR_CLK>, - <&gcc USB_HS3_H_CLK>; - clock-names = "core", "iface"; - - resets = <&gcc USB_HS3_RESET>; - reset-names = "link"; - }; - - usb4_phy: phy@12530000 { - compatible = "qcom,usb-otg-ci"; - reg = <0x12530000 0x400>; - interrupts = ; - status = "disabled"; - dr_mode = "host"; - - clocks = <&gcc USB_HS4_XCVR_CLK>, - <&gcc USB_HS4_H_CLK>; - clock-names = "core", "iface"; - - resets = <&gcc USB_HS4_RESET>; - reset-names = "link"; - }; - - gadget1: gadget@12500000 { - compatible = "qcom,ci-hdrc"; - reg = <0x12500000 0x400>; - status = "disabled"; - dr_mode = "peripheral"; - interrupts = ; - usb-phy = <&usb1_phy>; - }; - usb1: usb@12500000 { - compatible = "qcom,ehci-host"; - reg = <0x12500000 0x400>; - interrupts = ; - status = "disabled"; - usb-phy = <&usb1_phy>; + compatible = "qcom,ci-hdrc"; + reg = <0x12500000 0x200>, + <0x12500200 0x200>; + interrupts = ; + clocks = <&gcc USB_HS1_XCVR_CLK>, <&gcc USB_HS1_H_CLK>; + clock-names = "core", "iface"; + assigned-clocks = <&gcc USB_HS1_XCVR_CLK>; + assigned-clock-rates = <60000000>; + resets = <&gcc USB_HS1_RESET>; + reset-names = "core"; + phy_type = "ulpi"; + ahb-burst-config = <0>; + phys = <&usb_hs1_phy>; + phy-names = "usb-phy"; + status = "disabled"; + #reset-cells = <1>; + + ulpi { + usb_hs1_phy: phy { + compatible = "qcom,usb-hs-phy-apq8064", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&sleep_clk>, <&cxo_board>; + clock-names = "sleep", "ref"; + resets = <&usb1 0>; + reset-names = "por"; + }; + }; }; usb3: usb@12520000 { - compatible = "qcom,ehci-host"; - reg = <0x12520000 0x400>; - interrupts = ; - status = "disabled"; - usb-phy = <&usb3_phy>; + compatible = "qcom,ci-hdrc"; + reg = <0x12520000 0x200>, + <0x12520200 0x200>; + interrupts = ; + clocks = <&gcc USB_HS3_XCVR_CLK>, <&gcc USB_HS3_H_CLK>; + clock-names = "core", "iface"; + assigned-clocks = <&gcc USB_HS3_XCVR_CLK>; + assigned-clock-rates = <60000000>; + resets = <&gcc USB_HS3_RESET>; + reset-names = "core"; + phy_type = "ulpi"; + ahb-burst-config = <0>; + phys = <&usb_hs3_phy>; + phy-names = "usb-phy"; + status = "disabled"; + #reset-cells = <1>; + + ulpi { + usb_hs3_phy: phy { + compatible = "qcom,usb-hs-phy-apq8064", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&sleep_clk>, <&cxo_board>; + clock-names = "sleep", "ref"; + resets = <&usb3 0>; + reset-names = "por"; + }; + }; }; usb4: usb@12530000 { - compatible = "qcom,ehci-host"; - reg = <0x12530000 0x400>; - interrupts = ; - status = "disabled"; - usb-phy = <&usb4_phy>; + compatible = "qcom,ci-hdrc"; + reg = <0x12530000 0x200>, + <0x12530200 0x200>; + interrupts = ; + clocks = <&gcc USB_HS4_XCVR_CLK>, <&gcc USB_HS4_H_CLK>; + clock-names = "core", "iface"; + assigned-clocks = <&gcc USB_HS4_XCVR_CLK>; + assigned-clock-rates = <60000000>; + resets = <&gcc USB_HS4_RESET>; + reset-names = "core"; + phy_type = "ulpi"; + ahb-burst-config = <0>; + phys = <&usb_hs4_phy>; + phy-names = "usb-phy"; + status = "disabled"; + #reset-cells = <1>; + + ulpi { + usb_hs4_phy: phy { + compatible = "qcom,usb-hs-phy-apq8064", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&sleep_clk>, <&cxo_board>; + clock-names = "sleep", "ref"; + resets = <&usb4 0>; + reset-names = "por"; + }; + }; }; sata_phy0: phy@1b400000 { diff --git a/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts b/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts index ad51df27dfb77c..32f3b81f609ced 100644 --- a/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts +++ b/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts @@ -44,6 +44,26 @@ vqmmc-supply = <&pm8941_l13>; }; + usb@f9a55000 { + status = "ok"; + phys = <&usb_hs2_phy>; + phy-select = <&tcsr 0xb000 1>; + extcon = <&smbb>, <&usb_id>; + vbus-supply = <&chg_otg>; + hnp-disable; + srp-disable; + adp-disable; + ulpi { + phy@b { + status = "ok"; + v3p3-supply = <&pm8941_l24>; + v1p8-supply = <&pm8941_l6>; + extcon = <&smbb>; + qcom,init-seq = /bits/ 8 <0x1 0x63>; + }; + }; + }; + pinctrl@fd510000 { i2c11_pins: i2c11 { diff --git a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts index e7c1577d56f481..50966378f9e4da 100644 --- a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts +++ b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts @@ -92,7 +92,6 @@ vdd_l9_l10_l17_l22-supply = <&vreg_boost>; vdd_l13_l20_l23_l24-supply = <&vreg_boost>; vdd_l21-supply = <&vreg_boost>; - vin_5vs-supply = <&pm8941_5v>; s1 { regulator-min-microvolt = <1300000>; diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index 307bf6a647b30a..c5ee68a3f7f5c2 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -3,6 +3,7 @@ #include #include #include +#include #include #include "skeleton.dtsi" @@ -551,6 +552,11 @@ reg = <0xfc400000 0x4000>; }; + tcsr: syscon@fd4a0000 { + compatible = "syscon"; + reg = <0xfd4a0000 0x10000>; + }; + tcsr_mutex_block: syscon@fd484000 { compatible = "syscon"; reg = <0xfd484000 0x2000>; @@ -620,6 +626,50 @@ status = "disabled"; }; + otg: usb@f9a55000 { + compatible = "qcom,ci-hdrc"; + reg = <0xf9a55000 0x200>, + <0xf9a55200 0x200>; + interrupts = ; + clocks = <&gcc GCC_USB_HS_AHB_CLK>, + <&gcc GCC_USB_HS_SYSTEM_CLK>; + clock-names = "iface", "core"; + assigned-clocks = <&gcc GCC_USB_HS_SYSTEM_CLK>; + assigned-clock-rates = <75000000>; + resets = <&gcc GCC_USB_HS_BCR>; + reset-names = "core"; + phy_type = "ulpi"; + dr_mode = "otg"; + ahb-burst-config = <0>; + phy-names = "usb-phy"; + status = "disabled"; + #reset-cells = <1>; + + ulpi { + usb_hs1_phy: phy@a { + compatible = "qcom,usb-hs-phy-msm8974", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&xo_board>, <&gcc GCC_USB2A_PHY_SLEEP_CLK>; + clock-names = "ref", "sleep"; + resets = <&gcc GCC_USB2A_PHY_BCR>, <&otg 0>; + reset-names = "phy", "por"; + status = "disabled"; + }; + + usb_hs2_phy: phy@b { + compatible = "qcom,usb-hs-phy-msm8974", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&xo_board>, <&gcc GCC_USB2B_PHY_SLEEP_CLK>; + clock-names = "ref", "sleep"; + resets = <&gcc GCC_USB2B_PHY_BCR>, <&otg 1>; + reset-names = "phy", "por"; + status = "disabled"; + }; + }; + }; + rng@f9bff000 { compatible = "qcom,prng"; reg = <0xf9bff000 0x200>; @@ -1021,7 +1071,6 @@ pm8941_s1: s1 {}; pm8941_s2: s2 {}; pm8941_s3: s3 {}; - pm8941_5v: s4 {}; pm8941_l1: l1 {}; pm8941_l2: l2 {}; @@ -1051,9 +1100,6 @@ pm8941_lvs1: lvs1 {}; pm8941_lvs2: lvs2 {}; pm8941_lvs3: lvs3 {}; - - pm8941_5vs1: 5vs1 {}; - pm8941_5vs2: 5vs2 {}; }; }; }; diff --git a/arch/arm/boot/dts/qcom-pm8941.dtsi b/arch/arm/boot/dts/qcom-pm8941.dtsi index f8eb5e31c92080..3fc9f34f45bbe5 100644 --- a/arch/arm/boot/dts/qcom-pm8941.dtsi +++ b/arch/arm/boot/dts/qcom-pm8941.dtsi @@ -26,7 +26,14 @@ bias-pull-up; }; - charger@1000 { + usb_id: misc@900 { + compatible = "qcom,pm8941-misc"; + reg = <0x900>; + interrupts = <0x0 0x9 0 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "usb_id"; + }; + + smbb: charger@1000 { compatible = "qcom,pm8941-charger"; reg = <0x1000>; interrupts = <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>, @@ -45,6 +52,10 @@ "chg-gone", "usb-valid", "dc-valid"; + + usb-otg-in-supply = <&pm8941_5vs1>; + + chg_otg: otg-vbus { }; }; pm8941_gpios: gpios@c000 { @@ -171,5 +182,28 @@ status = "disabled"; }; + + regulators { + compatible = "qcom,pm8941-regulators"; + interrupts = <0x1 0x83 0x2 0>, <0x1 0x84 0x2 0>; + interrupt-names = "ocp-5vs1", "ocp-5vs2"; + vin_5vs-supply = <&pm8941_5v>; + + pm8941_5v: s4 { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-enable-ramp-delay = <500>; + }; + + pm8941_5vs1: 5vs1 { + regulator-enable-ramp-delay = <1000>; + regulator-pull-down; + regulator-over-current-protection; + qcom,ocp-max-retries = <10>; + qcom,ocp-retry-delay = <30>; + qcom,vs-soft-start-strength = <0>; + regulator-initial-mode = <1>; + }; + }; }; }; diff --git a/arch/arm/boot/dts/r7s72100-gr-peach.dts b/arch/arm/boot/dts/r7s72100-gr-peach.dts new file mode 100644 index 00000000000000..a1b2aef984f635 --- /dev/null +++ b/arch/arm/boot/dts/r7s72100-gr-peach.dts @@ -0,0 +1,66 @@ +/* + * Device Tree Source for the GR-Peach board + * + * Copyright (C) 2017 Jacopo Mondi + * Copyright (C) 2016 Renesas Electronics + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +/dts-v1/; +#include "r7s72100.dtsi" + +/ { + model = "GR-Peach"; + compatible = "renesas,gr-peach", "renesas,r7s72100"; + + aliases { + serial0 = &scif2; + }; + + chosen { + bootargs = "ignore_loglevel rw root=/dev/mtdblock0"; + stdout-path = "serial0:115200n8"; + }; + + memory@20000000 { + device_type = "memory"; + reg = <0x20000000 0x00a00000>; + + }; + + lbsc { + #address-cells = <1>; + #size-cells = <1>; + }; + + flash@18000000 { + compatible = "mtd-rom"; + probe-type = "map_rom"; + reg = <0x18000000 0x00800000>; + bank-width = <4>; + device-width = <1>; + + #address-cells = <1>; + #size-cells = <1>; + + rootfs@600000 { + label = "rootfs"; + reg = <0x00600000 0x00200000>; + }; + }; +}; + +&extal_clk { + clock-frequency = <13333000>; +}; + +&usb_x1_clk { + clock-frequency = <48000000>; +}; + +&scif2 { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/r7s72100.dtsi b/arch/arm/boot/dts/r7s72100.dtsi index 0423996e4dccf6..5cf53e9943af70 100644 --- a/arch/arm/boot/dts/r7s72100.dtsi +++ b/arch/arm/boot/dts/r7s72100.dtsi @@ -144,9 +144,9 @@ #clock-cells = <1>; compatible = "renesas,r7s72100-mstp-clocks", "renesas,cpg-mstp-clocks"; reg = <0xfcfe0430 4>; - clocks = <&b_clk>; - clock-indices = ; - clock-output-names = "ether"; + clocks = <&b_clk>, <&p1_clk>, <&p1_clk>; + clock-indices = ; + clock-output-names = "ether", "usb0", "usb1"; }; mstp8_clks: mstp8_clks@fcfe0434 { diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi index 1f5c9f6dddba93..310222634570d9 100644 --- a/arch/arm/boot/dts/r8a73a4.dtsi +++ b/arch/arm/boot/dts/r8a73a4.dtsi @@ -219,7 +219,7 @@ power-domains = <&pd_c4>; }; - pfc: pfc@e6050000 { + pfc: pin-controller@e6050000 { compatible = "renesas,pfc-r8a73a4"; reg = <0 0xe6050000 0 0x9000>; gpio-controller; diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi index 34159a8349def8..d37d22682a6320 100644 --- a/arch/arm/boot/dts/r8a7740.dtsi +++ b/arch/arm/boot/dts/r8a7740.dtsi @@ -299,7 +299,7 @@ status = "disabled"; }; - pfc: pfc@e6050000 { + pfc: pin-controller@e6050000 { compatible = "renesas,pfc-r8a7740"; reg = <0xe6050000 0x8000>, <0xe605800c 0x20>; diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi index 1e93c94a9eace1..8f3156c0e5754b 100644 --- a/arch/arm/boot/dts/r8a7778.dtsi +++ b/arch/arm/boot/dts/r8a7778.dtsi @@ -142,7 +142,7 @@ interrupt-controller; }; - pfc: pfc@fffc0000 { + pfc: pin-controller@fffc0000 { compatible = "renesas,pfc-r8a7778"; reg = <0xfffc0000 0x118>; }; diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi index ae2d9a9c65af43..8ee0b2ca5d39a2 100644 --- a/arch/arm/boot/dts/r8a7779.dtsi +++ b/arch/arm/boot/dts/r8a7779.dtsi @@ -286,7 +286,7 @@ status = "disabled"; }; - pfc: pfc@fffc0000 { + pfc: pin-controller@fffc0000 { compatible = "renesas,pfc-r8a7779"; reg = <0xfffc0000 0x23c>; }; diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi index 99269aaca6fc95..416956a42c9345 100644 --- a/arch/arm/boot/dts/r8a7790.dtsi +++ b/arch/arm/boot/dts/r8a7790.dtsi @@ -614,7 +614,7 @@ max-frequency = <97500000>; }; - pfc: pfc@e6060000 { + pfc: pin-controller@e6060000 { compatible = "renesas,pfc-r8a7790"; reg = <0 0xe6060000 0 0x250>; }; diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi index 4d0c2ce59900f8..b730c889a40454 100644 --- a/arch/arm/boot/dts/r8a7791.dtsi +++ b/arch/arm/boot/dts/r8a7791.dtsi @@ -562,7 +562,7 @@ status = "disabled"; }; - pfc: pfc@e6060000 { + pfc: pin-controller@e6060000 { compatible = "renesas,pfc-r8a7791"; reg = <0 0xe6060000 0 0x250>; }; @@ -776,6 +776,15 @@ status = "disabled"; }; + adc: adc@e6e54000 { + compatible = "renesas,r8a7791-gyroadc", "renesas,rcar-gyroadc"; + reg = <0 0xe6e54000 0 64>; + clocks = <&mstp9_clks R8A7791_CLK_GYROADC>; + clock-names = "fck"; + power-domains = <&sysc R8A7791_PD_ALWAYS_ON>; + status = "disabled"; + }; + scif2: serial@e6e58000 { compatible = "renesas,scif-r8a7791", "renesas,rcar-gen2-scif", "renesas,scif"; @@ -1425,13 +1434,15 @@ mstp9_clks: mstp9_clks@e6150994 { compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks"; reg = <0 0xe6150994 0 4>, <0 0xe61509a4 0 4>; - clocks = <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, + clocks = <&p_clk>, + <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, <&cp_clk>, <&p_clk>, <&p_clk>, <&cpg_clocks R8A7791_CLK_QSPI>, <&hp_clk>, <&cp_clk>, <&hp_clk>, <&hp_clk>, <&hp_clk>, <&hp_clk>, <&hp_clk>; #clock-cells = <1>; clock-indices = < + R8A7791_CLK_GYROADC R8A7791_CLK_GPIO7 R8A7791_CLK_GPIO6 R8A7791_CLK_GPIO5 R8A7791_CLK_GPIO4 R8A7791_CLK_GPIO3 R8A7791_CLK_GPIO2 R8A7791_CLK_GPIO1 R8A7791_CLK_GPIO0 R8A7791_CLK_RCAN1 R8A7791_CLK_RCAN0 R8A7791_CLK_QSPI_MOD R8A7791_CLK_I2C5 @@ -1439,6 +1450,7 @@ R8A7791_CLK_I2C1 R8A7791_CLK_I2C0 >; clock-output-names = + "gyroadc", "gpio7", "gpio6", "gpio5", "gpio4", "gpio3", "gpio2", "gpio1", "gpio0", "rcan1", "rcan0", "qspi_mod", "i2c5", "i2c6", "i2c4", "i2c3", "i2c2", "i2c1", "i2c0"; diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts index 806c93f6ae8b9f..30f08352846827 100644 --- a/arch/arm/boot/dts/r8a7793-gose.dts +++ b/arch/arm/boot/dts/r8a7793-gose.dts @@ -253,12 +253,23 @@ }; }; + hdmi-in { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi_con_in: endpoint { + remote-endpoint = <&adv7612_in>; + }; + }; + }; + hdmi-out { compatible = "hdmi-connector"; type = "a"; port { - hdmi_con: endpoint { + hdmi_con_out: endpoint { remote-endpoint = <&adv7511_out>; }; }; @@ -348,16 +359,37 @@ sdhi0_pins: sd0 { groups = "sdhi0_data4", "sdhi0_ctrl"; function = "sdhi0"; + power-source = <3300>; + }; + + sdhi0_pins_uhs: sd0_uhs { + groups = "sdhi0_data4", "sdhi0_ctrl"; + function = "sdhi0"; + power-source = <1800>; }; sdhi1_pins: sd1 { groups = "sdhi1_data4", "sdhi1_ctrl"; function = "sdhi1"; + power-source = <3300>; + }; + + sdhi1_pins_uhs: sd1_uhs { + groups = "sdhi1_data4", "sdhi1_ctrl"; + function = "sdhi1"; + power-source = <1800>; }; sdhi2_pins: sd2 { groups = "sdhi2_data4", "sdhi2_ctrl"; function = "sdhi2"; + power-source = <3300>; + }; + + sdhi2_pins_uhs: sd2_uhs { + groups = "sdhi2_data4", "sdhi2_ctrl"; + function = "sdhi2"; + power-source = <1800>; }; qspi_pins: qspi { @@ -374,6 +406,11 @@ groups = "audio_clk_a"; function = "audio_clk"; }; + + vin0_pins: vin0 { + groups = "vin0_data24", "vin0_sync", "vin0_clkenb", "vin0_clk"; + function = "vin0"; + }; }; ðer { @@ -416,33 +453,40 @@ &sdhi0 { pinctrl-0 = <&sdhi0_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdhi0_pins_uhs>; + pinctrl-names = "default", "state_uhs"; vmmc-supply = <&vcc_sdhi0>; vqmmc-supply = <&vccq_sdhi0>; cd-gpios = <&gpio6 6 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>; + sd-uhs-sdr50; + sd-uhs-sdr104; status = "okay"; }; &sdhi1 { pinctrl-0 = <&sdhi1_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdhi1_pins_uhs>; + pinctrl-names = "default", "state_uhs"; vmmc-supply = <&vcc_sdhi1>; vqmmc-supply = <&vccq_sdhi1>; cd-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio6 15 GPIO_ACTIVE_HIGH>; + sd-uhs-sdr50; status = "okay"; }; &sdhi2 { pinctrl-0 = <&sdhi2_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdhi2_pins_uhs>; + pinctrl-names = "default", "state_uhs"; vmmc-supply = <&vcc_sdhi2>; vqmmc-supply = <&vccq_sdhi2>; cd-gpios = <&gpio6 22 GPIO_ACTIVE_LOW>; + sd-uhs-sdr50; status = "okay"; }; @@ -524,7 +568,34 @@ port@1 { reg = <1>; adv7511_out: endpoint { - remote-endpoint = <&hdmi_con>; + remote-endpoint = <&hdmi_con_out>; + }; + }; + }; + }; + + hdmi-in@4c { + compatible = "adi,adv7612"; + reg = <0x4c>; + interrupt-parent = <&gpio4>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + default-input = <0>; + + port { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + adv7612_in: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; + }; + + port@2 { + reg = <2>; + adv7612_out: endpoint { + remote-endpoint = <&vin0ep2>; }; }; }; @@ -578,3 +649,24 @@ &ssi1 { shared-pin; }; + +/* HDMI video input */ +&vin0 { + status = "okay"; + pinctrl-0 = <&vin0_pins>; + pinctrl-names = "default"; + + port { + #address-cells = <1>; + #size-cells = <0>; + + vin0ep2: endpoint { + remote-endpoint = <&adv7612_out>; + bus-width = <24>; + hsync-active = <0>; + vsync-active = <0>; + pclk-sample = <1>; + data-active = <1>; + }; + }; +}; diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi index 4de6041d61f9d4..13b980f27bbc88 100644 --- a/arch/arm/boot/dts/r8a7793.dtsi +++ b/arch/arm/boot/dts/r8a7793.dtsi @@ -529,7 +529,7 @@ status = "disabled"; }; - pfc: pfc@e6060000 { + pfc: pin-controller@e6060000 { compatible = "renesas,pfc-r8a7793"; reg = <0 0xe6060000 0 0x250>; }; @@ -542,6 +542,7 @@ dmas = <&dmac0 0xcd>, <&dmac0 0xce>, <&dmac1 0xcd>, <&dmac1 0xce>; dma-names = "tx", "rx", "tx", "rx"; + max-frequency = <195000000>; power-domains = <&sysc R8A7793_PD_ALWAYS_ON>; status = "disabled"; }; @@ -554,6 +555,7 @@ dmas = <&dmac0 0xc1>, <&dmac0 0xc2>, <&dmac1 0xc1>, <&dmac1 0xc2>; dma-names = "tx", "rx", "tx", "rx"; + max-frequency = <97500000>; power-domains = <&sysc R8A7793_PD_ALWAYS_ON>; status = "disabled"; }; @@ -566,6 +568,7 @@ dmas = <&dmac0 0xd3>, <&dmac0 0xd4>, <&dmac1 0xd3>, <&dmac1 0xd4>; dma-names = "tx", "rx", "tx", "rx"; + max-frequency = <97500000>; power-domains = <&sysc R8A7793_PD_ALWAYS_ON>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/r8a77xx-aa104xd12-panel.dtsi b/arch/arm/boot/dts/r8a77xx-aa104xd12-panel.dtsi index 65cb50f0c29f59..238d14bb0ebebf 100644 --- a/arch/arm/boot/dts/r8a77xx-aa104xd12-panel.dtsi +++ b/arch/arm/boot/dts/r8a77xx-aa104xd12-panel.dtsi @@ -10,10 +10,11 @@ / { panel { - compatible = "mitsubishi,aa104xd12", "panel-dpi"; + compatible = "mitsubishi,aa104xd12", "panel-lvds"; width-mm = <210>; height-mm = <158>; + data-mapping = "jeida-18"; panel-timing { /* 1024x768 @65Hz */ diff --git a/arch/arm/boot/dts/r8a77xx-aa121td01-panel.dtsi b/arch/arm/boot/dts/r8a77xx-aa121td01-panel.dtsi index a07ebf8f6938fe..04aafd4797750c 100644 --- a/arch/arm/boot/dts/r8a77xx-aa121td01-panel.dtsi +++ b/arch/arm/boot/dts/r8a77xx-aa121td01-panel.dtsi @@ -10,10 +10,11 @@ / { panel { - compatible = "mitsubishi,aa121td01", "panel-dpi"; + compatible = "mitsubishi,aa121td01", "panel-lvds"; width-mm = <261>; height-mm = <163>; + data-mapping = "jeida-18"; panel-timing { /* 1280x800 @60Hz */ diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 48a0c1cf430127..df574135797a54 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -66,10 +66,7 @@ compatible = "arm,cortex-a7"; reg = <0xf00>; resets = <&cru SRST_CORE0>; - operating-points = < - /* KHz uV */ - 816000 1000000 - >; + operating-points-v2 = <&cpu0_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -80,6 +77,7 @@ compatible = "arm,cortex-a7"; reg = <0xf01>; resets = <&cru SRST_CORE1>; + operating-points-v2 = <&cpu0_opp_table>; }; cpu2: cpu@f02 { @@ -87,6 +85,7 @@ compatible = "arm,cortex-a7"; reg = <0xf02>; resets = <&cru SRST_CORE2>; + operating-points-v2 = <&cpu0_opp_table>; }; cpu3: cpu@f03 { @@ -94,6 +93,35 @@ compatible = "arm,cortex-a7"; reg = <0xf03>; resets = <&cru SRST_CORE3>; + operating-points-v2 = <&cpu0_opp_table>; + }; + }; + + cpu0_opp_table: opp_table0 { + compatible = "operating-points-v2"; + opp-shared; + + opp-408000000 { + opp-hz = /bits/ 64 <408000000>; + opp-microvolt = <950000>; + clock-latency-ns = <40000>; + opp-suspend; + }; + opp-600000000 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <975000>; + }; + opp-816000000 { + opp-hz = /bits/ 64 <816000000>; + opp-microvolt = <1000000>; + }; + opp-1008000000 { + opp-hz = /bits/ 64 <1008000000>; + opp-microvolt = <1175000>; + }; + opp-1200000000 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <1275000>; }; }; @@ -280,6 +308,14 @@ status = "disabled"; }; + wdt: watchdog@110a0000 { + compatible = "snps,dw-wdt"; + reg = <0x110a0000 0x100>; + interrupts = ; + clocks = <&cru PCLK_CPU>; + status = "disabled"; + }; + pwm0: pwm@110b0000 { compatible = "rockchip,rk3288-pwm"; reg = <0x110b0000 0x10>; @@ -338,8 +374,18 @@ rockchip,grf = <&grf>; #clock-cells = <1>; #reset-cells = <1>; - assigned-clocks = <&cru PLL_GPLL>; - assigned-clock-rates = <594000000>; + assigned-clocks = + <&cru PLL_GPLL>, <&cru ARMCLK>, + <&cru PLL_CPLL>, <&cru ACLK_PERI>, + <&cru HCLK_PERI>, <&cru PCLK_PERI>, + <&cru ACLK_CPU>, <&cru HCLK_CPU>, + <&cru PCLK_CPU>; + assigned-clock-rates = + <594000000>, <816000000>, + <500000000>, <150000000>, + <150000000>, <75000000>, + <150000000>, <150000000>, + <75000000>; }; thermal-zones { @@ -388,6 +434,8 @@ interrupts = ; clocks = <&cru SCLK_TSADC>, <&cru PCLK_TSADC>; clock-names = "tsadc", "apb_pclk"; + assigned-clocks = <&cru SCLK_TSADC>; + assigned-clock-rates = <32768>; resets = <&cru SRST_TSADC>; reset-names = "tsadc-apb"; pinctrl-names = "init", "default", "sleep"; @@ -621,9 +669,9 @@ <0 12 RK_FUNC_1 &pcfg_pull_none>, <0 13 RK_FUNC_1 &pcfg_pull_none>, <0 14 RK_FUNC_1 &pcfg_pull_none>, - <1 2 RK_FUNC_1 &pcfg_pull_none>, - <1 4 RK_FUNC_1 &pcfg_pull_none>, - <1 5 RK_FUNC_1 &pcfg_pull_none>; + <1 2 RK_FUNC_2 &pcfg_pull_none>, + <1 4 RK_FUNC_2 &pcfg_pull_none>, + <1 5 RK_FUNC_2 &pcfg_pull_none>; }; }; @@ -693,10 +741,15 @@ uart2 { uart2_xfer: uart2-xfer { - rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_none>, + rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>, <1 19 RK_FUNC_2 &pcfg_pull_none>; }; + uart21_xfer: uart21-xfer { + rockchip,pins = <1 10 RK_FUNC_2 &pcfg_pull_up>, + <1 9 RK_FUNC_2 &pcfg_pull_none>; + }; + uart2_cts: uart2-cts { rockchip,pins = <0 25 RK_FUNC_1 &pcfg_pull_none>; }; diff --git a/arch/arm/boot/dts/rk3288-firefly.dtsi b/arch/arm/boot/dts/rk3288-firefly.dtsi index 10793ac185992d..864747342e3e84 100644 --- a/arch/arm/boot/dts/rk3288-firefly.dtsi +++ b/arch/arm/boot/dts/rk3288-firefly.dtsi @@ -219,6 +219,11 @@ status = "ok"; }; +&gpu { + mali-supply = <&vdd_gpu>; + status = "okay"; +}; + &hdmi { ddc-i2c-bus = <&i2c5>; status = "okay"; diff --git a/arch/arm/boot/dts/rk3288-rock2-som.dtsi b/arch/arm/boot/dts/rk3288-rock2-som.dtsi index f0778a46bca9b6..749a9b86e6e27c 100644 --- a/arch/arm/boot/dts/rk3288-rock2-som.dtsi +++ b/arch/arm/boot/dts/rk3288-rock2-som.dtsi @@ -113,6 +113,11 @@ tx_delay = <0x30>; }; +&gpu { + mali-supply = <&vdd_gpu>; + status = "okay"; +}; + &i2c0 { status = "okay"; diff --git a/arch/arm/boot/dts/rk3288-rock2-square.dts b/arch/arm/boot/dts/rk3288-rock2-square.dts index a23a94811be8ad..8ed25e9f60bc48 100644 --- a/arch/arm/boot/dts/rk3288-rock2-square.dts +++ b/arch/arm/boot/dts/rk3288-rock2-square.dts @@ -125,10 +125,6 @@ gpio = <&gpio0 RK_PB6 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&host_vbus_drv>; - /* Always on as the rockchip usb phy doesn't have a vbus-supply - * property - */ - regulator-always-on; regulator-name = "vcc_host"; }; @@ -279,6 +275,10 @@ status = "okay"; }; +&usbphy1 { + vbus-supply = <&vcc_usb_host>; +}; + &usb_host0_ehci { status = "okay"; }; diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi index 5d1eb0a2582755..d709fa1847f9a8 100644 --- a/arch/arm/boot/dts/rk3288-veyron.dtsi +++ b/arch/arm/boot/dts/rk3288-veyron.dtsi @@ -161,6 +161,11 @@ pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>; }; +&gpu { + mali-supply = <&vdd_gpu>; + status = "okay"; +}; + &hdmi { ddc-i2c-bus = <&i2c5>; status = "okay"; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index ad5d6022e95fe5..2484f11761ea24 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -1125,6 +1126,48 @@ }; }; + gpu: mali@ffa30000 { + compatible = "rockchip,rk3288-mali", "arm,mali-t760", "arm,mali-midgard"; + reg = <0xffa30000 0x10000>; + interrupts = , + , + ; + interrupt-names = "job", "mmu", "gpu"; + clocks = <&cru ACLK_GPU>; + operating-points-v2 = <&gpu_opp_table>; + power-domains = <&power RK3288_PD_GPU>; + status = "disabled"; + }; + + gpu_opp_table: gpu-opp-table { + compatible = "operating-points-v2"; + + opp@100000000 { + opp-hz = /bits/ 64 <100000000>; + opp-microvolt = <950000>; + }; + opp@200000000 { + opp-hz = /bits/ 64 <200000000>; + opp-microvolt = <950000>; + }; + opp@300000000 { + opp-hz = /bits/ 64 <300000000>; + opp-microvolt = <1000000>; + }; + opp@400000000 { + opp-hz = /bits/ 64 <400000000>; + opp-microvolt = <1100000>; + }; + opp@500000000 { + opp-hz = /bits/ 64 <500000000>; + opp-microvolt = <1200000>; + }; + opp@600000000 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <1250000>; + }; + }; + qos_gpu_r: qos@ffaa0000 { compatible = "syscon"; reg = <0xffaa0000 0x20>; diff --git a/arch/arm/boot/dts/rk1108-evb.dts b/arch/arm/boot/dts/rv1108-evb.dts similarity index 94% rename from arch/arm/boot/dts/rk1108-evb.dts rename to arch/arm/boot/dts/rv1108-evb.dts index 3956cff4ca796f..58cf4ac079c3de 100644 --- a/arch/arm/boot/dts/rk1108-evb.dts +++ b/arch/arm/boot/dts/rv1108-evb.dts @@ -40,11 +40,11 @@ /dts-v1/; -#include "rk1108.dtsi" +#include "rv1108.dtsi" / { - model = "Rockchip RK1108 Evaluation board"; - compatible = "rockchip,rk1108-evb", "rockchip,rk1108"; + model = "Rockchip RV1108 Evaluation board"; + compatible = "rockchip,rv1108-evb", "rockchip,rv1108"; memory@60000000 { device_type = "memory"; diff --git a/arch/arm/boot/dts/rk1108.dtsi b/arch/arm/boot/dts/rv1108.dtsi similarity index 95% rename from arch/arm/boot/dts/rk1108.dtsi rename to arch/arm/boot/dts/rv1108.dtsi index 1297924db6ad00..437098b556eb8b 100644 --- a/arch/arm/boot/dts/rk1108.dtsi +++ b/arch/arm/boot/dts/rv1108.dtsi @@ -47,7 +47,7 @@ #address-cells = <1>; #size-cells = <1>; - compatible = "rockchip,rk1108"; + compatible = "rockchip,rv1108"; interrupt-parent = <&gic>; @@ -113,7 +113,7 @@ }; uart2: serial@10210000 { - compatible = "rockchip,rk1108-uart", "snps,dw-apb-uart"; + compatible = "rockchip,rv1108-uart", "snps,dw-apb-uart"; reg = <0x10210000 0x100>; interrupts = ; reg-shift = <2>; @@ -127,7 +127,7 @@ }; uart1: serial@10220000 { - compatible = "rockchip,rk1108-uart", "snps,dw-apb-uart"; + compatible = "rockchip,rv1108-uart", "snps,dw-apb-uart"; reg = <0x10220000 0x100>; interrupts = ; reg-shift = <2>; @@ -141,7 +141,7 @@ }; uart0: serial@10230000 { - compatible = "rockchip,rk1108-uart", "snps,dw-apb-uart"; + compatible = "rockchip,rv1108-uart", "snps,dw-apb-uart"; reg = <0x10230000 0x100>; interrupts = ; reg-shift = <2>; @@ -155,17 +155,17 @@ }; grf: syscon@10300000 { - compatible = "rockchip,rk1108-grf", "syscon"; + compatible = "rockchip,rv1108-grf", "syscon"; reg = <0x10300000 0x1000>; }; pmugrf: syscon@20060000 { - compatible = "rockchip,rk1108-pmugrf", "syscon"; + compatible = "rockchip,rv1108-pmugrf", "syscon"; reg = <0x20060000 0x1000>; }; cru: clock-controller@20200000 { - compatible = "rockchip,rk1108-cru"; + compatible = "rockchip,rv1108-cru"; reg = <0x20200000 0x1000>; rockchip,grf = <&grf>; #clock-cells = <1>; @@ -173,7 +173,7 @@ }; emmc: dwmmc@30110000 { - compatible = "rockchip,rk1108-dw-mshc", "rockchip,rk3288-dw-mshc"; + compatible = "rockchip,rv1108-dw-mshc", "rockchip,rk3288-dw-mshc"; clock-freq-min-max = <400000 150000000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; @@ -185,7 +185,7 @@ }; sdio: dwmmc@30120000 { - compatible = "rockchip,rk1108-dw-mshc", "rockchip,rk3288-dw-mshc"; + compatible = "rockchip,rv1108-dw-mshc", "rockchip,rk3288-dw-mshc"; clock-freq-min-max = <400000 150000000>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; @@ -197,7 +197,7 @@ }; sdmmc: dwmmc@30130000 { - compatible = "rockchip,rk1108-dw-mshc", "rockchip,rk3288-dw-mshc"; + compatible = "rockchip,rv1108-dw-mshc", "rockchip,rk3288-dw-mshc"; clock-freq-min-max = <400000 100000000>; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 8067c71c3a38a9..ce95dcb8bdf9a0 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -762,6 +762,18 @@ atmel,clk-output-range = <0 83000000>; }; + can0_clk: can0_clk { + #clock-cells = <0>; + reg = <56>; + atmel,clk-output-range = <0 83000000>; + }; + + can1_clk: can1_clk { + #clock-cells = <0>; + reg = <57>; + atmel,clk-output-range = <0 83000000>; + }; + classd_clk: classd_clk { #clock-cells = <0>; reg = <59>; @@ -890,6 +902,18 @@ #clock-cells = <0>; reg = <55>; }; + + can0_gclk: can0_gclk { + #clock-cells = <0>; + reg = <56>; + atmel,clk-output-range = <0 80000000>; + }; + + can1_gclk: can1_gclk { + #clock-cells = <0>; + reg = <57>; + atmel,clk-output-range = <0 80000000>; + }; }; }; @@ -1144,6 +1168,22 @@ clocks = <&clk32k>; }; + can0: can@f8054000 { + compatible = "bosch,m_can"; + reg = <0xf8054000 0x4000>, <0x210000 0x4000>; + reg-names = "m_can", "message_ram"; + interrupts = <56 IRQ_TYPE_LEVEL_HIGH 7>, + <64 IRQ_TYPE_LEVEL_HIGH 7>; + interrupt-names = "int0", "int1"; + clocks = <&can0_clk>, <&can0_gclk>; + clock-names = "hclk", "cclk"; + assigned-clocks = <&can0_gclk>; + assigned-clock-parents = <&utmi>; + assigned-clock-rates = <40000000>; + bosch,mram-cfg = <0x0 0 0 64 0 0 32 32>; + status = "disabled"; + }; + spi1: spi@fc000000 { compatible = "atmel,at91rm9200-spi"; reg = <0xfc000000 0x100>; @@ -1305,6 +1345,22 @@ status = "okay"; }; + can1: can@fc050000 { + compatible = "bosch,m_can"; + reg = <0xfc050000 0x4000>, <0x210000 0x4000>; + reg-names = "m_can", "message_ram"; + interrupts = <57 IRQ_TYPE_LEVEL_HIGH 7>, + <65 IRQ_TYPE_LEVEL_HIGH 7>; + interrupt-names = "int0", "int1"; + clocks = <&can1_clk>, <&can1_gclk>; + clock-names = "hclk", "cclk"; + assigned-clocks = <&can1_gclk>; + assigned-clock-parents = <&utmi>; + assigned-clock-rates = <40000000>; + bosch,mram-cfg = <0x1100 0 0 64 0 0 32 32>; + status = "disabled"; + }; + sfrbu: sfr@fc05c000 { compatible = "atmel,sama5d2-sfrbu", "syscon"; reg = <0xfc05c000 0x20>; diff --git a/arch/arm/boot/dts/sh73a0.dtsi b/arch/arm/boot/dts/sh73a0.dtsi index 6b01ab354e8896..4ea5c5a16c57ee 100644 --- a/arch/arm/boot/dts/sh73a0.dtsi +++ b/arch/arm/boot/dts/sh73a0.dtsi @@ -444,7 +444,7 @@ status = "disabled"; }; - pfc: pfc@e6050000 { + pfc: pin-controller@e6050000 { compatible = "renesas,pfc-sh73a0"; reg = <0xe6050000 0x8000>, <0xe605801c 0x1c>; diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts index f2a01fe2bebc8a..f80d37ddc4c663 100644 --- a/arch/arm/boot/dts/sun4i-a10-a1000.dts +++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts @@ -171,7 +171,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts b/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts index 942d739a438464..6b02de592a0267 100644 --- a/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts +++ b/arch/arm/boot/dts/sun4i-a10-ba10-tvbox.dts @@ -109,7 +109,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts b/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts index 17f8c5ec011c44..a7d61994b8fd27 100644 --- a/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts +++ b/arch/arm/boot/dts/sun4i-a10-chuwi-v7-cw0825.dts @@ -128,7 +128,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts index d844938e2aa7f5..404ce769489968 100644 --- a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts +++ b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts @@ -142,7 +142,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -182,6 +182,10 @@ #include "axp209.dtsi" +&ac_power_supply { + status = "okay"; +}; + ®_dcdc2 { regulator-always-on; regulator-min-microvolt = <1000000>; diff --git a/arch/arm/boot/dts/sun4i-a10-dserve-dsrv9703c.dts b/arch/arm/boot/dts/sun4i-a10-dserve-dsrv9703c.dts index aad3bec1cb39a6..e0777ae808c749 100644 --- a/arch/arm/boot/dts/sun4i-a10-dserve-dsrv9703c.dts +++ b/arch/arm/boot/dts/sun4i-a10-dserve-dsrv9703c.dts @@ -163,7 +163,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-gemei-g9.dts b/arch/arm/boot/dts/sun4i-a10-gemei-g9.dts index 9616cdecce930b..d8bfd7b7491626 100644 --- a/arch/arm/boot/dts/sun4i-a10-gemei-g9.dts +++ b/arch/arm/boot/dts/sun4i-a10-gemei-g9.dts @@ -146,7 +146,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH01 */ diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts index a1a7282199d52c..856cfc9128e6c5 100644 --- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts +++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts @@ -107,7 +107,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-hyundai-a7hd.dts b/arch/arm/boot/dts/sun4i-a10-hyundai-a7hd.dts index 85dcf81ab64ef0..6506595268b2a5 100644 --- a/arch/arm/boot/dts/sun4i-a10-hyundai-a7hd.dts +++ b/arch/arm/boot/dts/sun4i-a10-hyundai-a7hd.dts @@ -79,7 +79,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -120,10 +120,6 @@ status = "okay"; }; -&usb2_vbus_pin_a { - pins = "PH6"; -}; - &usb_otg { dr_mode = "otg"; status = "okay"; diff --git a/arch/arm/boot/dts/sun4i-a10-inet1.dts b/arch/arm/boot/dts/sun4i-a10-inet1.dts index b8923b92cb3691..d51d8c302dafac 100644 --- a/arch/arm/boot/dts/sun4i-a10-inet1.dts +++ b/arch/arm/boot/dts/sun4i-a10-inet1.dts @@ -161,7 +161,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-inet97fv2.dts b/arch/arm/boot/dts/sun4i-a10-inet97fv2.dts index a1a2bbb3f9d389..a8e479fe43ca83 100644 --- a/arch/arm/boot/dts/sun4i-a10-inet97fv2.dts +++ b/arch/arm/boot/dts/sun4i-a10-inet97fv2.dts @@ -147,7 +147,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-inet9f-rev03.dts b/arch/arm/boot/dts/sun4i-a10-inet9f-rev03.dts index 4a27eb9102cda7..2acb89a87d41f2 100644 --- a/arch/arm/boot/dts/sun4i-a10-inet9f-rev03.dts +++ b/arch/arm/boot/dts/sun4i-a10-inet9f-rev03.dts @@ -305,7 +305,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts b/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts index 4e798f014c992c..92e3e030ced350 100644 --- a/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts +++ b/arch/arm/boot/dts/sun4i-a10-itead-iteaduino-plus.dts @@ -100,7 +100,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts index 308dc15130417f..92b2d4af3d21c6 100644 --- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts +++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts @@ -140,7 +140,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-marsboard.dts b/arch/arm/boot/dts/sun4i-a10-marsboard.dts index 98a5f7258dca44..0f927da28ee167 100644 --- a/arch/arm/boot/dts/sun4i-a10-marsboard.dts +++ b/arch/arm/boot/dts/sun4i-a10-marsboard.dts @@ -141,7 +141,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts index 484c57493bd21d..a5ed9e4e22c611 100644 --- a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts +++ b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts @@ -97,7 +97,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-mk802.dts b/arch/arm/boot/dts/sun4i-a10-mk802.dts index 2b75745cd246a9..81db6824a2c79c 100644 --- a/arch/arm/boot/dts/sun4i-a10-mk802.dts +++ b/arch/arm/boot/dts/sun4i-a10-mk802.dts @@ -72,7 +72,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-mk802ii.dts b/arch/arm/boot/dts/sun4i-a10-mk802ii.dts index c861fa7e356c62..e74a881fd9a7a5 100644 --- a/arch/arm/boot/dts/sun4i-a10-mk802ii.dts +++ b/arch/arm/boot/dts/sun4i-a10-mk802ii.dts @@ -83,7 +83,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts index 3a2522a9419ddc..462412ee903c54 100644 --- a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts +++ b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts @@ -145,7 +145,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-pcduino.dts b/arch/arm/boot/dts/sun4i-a10-pcduino.dts index 83596fd2ccfc38..84f55e76df0c21 100644 --- a/arch/arm/boot/dts/sun4i-a10-pcduino.dts +++ b/arch/arm/boot/dts/sun4i-a10-pcduino.dts @@ -147,7 +147,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10-pov-protab2-ips9.dts b/arch/arm/boot/dts/sun4i-a10-pov-protab2-ips9.dts index a68c7cc53b9450..c0f8c88b5a7d8a 100644 --- a/arch/arm/boot/dts/sun4i-a10-pov-protab2-ips9.dts +++ b/arch/arm/boot/dts/sun4i-a10-pov-protab2-ips9.dts @@ -149,7 +149,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index b63668ece15139..41c2579143fd6b 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -1030,12 +1030,6 @@ bias-pull-up; }; - mmc0_cd_pin_reference_design: mmc0_cd_pin@0 { - pins = "PH1"; - function = "gpio_in"; - bias-pull-up; - }; - ps20_pins_a: ps20@0 { pins = "PI20", "PI21"; function = "ps2"; diff --git a/arch/arm/boot/dts/sun5i-a10s-auxtek-t003.dts b/arch/arm/boot/dts/sun5i-a10s-auxtek-t003.dts index c6f742a7e69f61..d2dee8d434bf33 100644 --- a/arch/arm/boot/dts/sun5i-a10s-auxtek-t003.dts +++ b/arch/arm/boot/dts/sun5i-a10s-auxtek-t003.dts @@ -136,14 +136,6 @@ status = "okay"; }; -&usb0_vbus_pin_a { - pins = "PG13"; -}; - -&usb1_vbus_pin_a { - pins = "PB10"; -}; - &usb_otg { dr_mode = "host"; status = "okay"; diff --git a/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts b/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts index a27c3fa587366a..16f839df42272d 100644 --- a/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts +++ b/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts @@ -168,10 +168,6 @@ status = "okay"; }; -&usb1_vbus_pin_a { - pins = "PG13"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>; diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts index 894f874a5beb32..da95118af4dc25 100644 --- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts +++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts @@ -63,6 +63,17 @@ stdout-path = "serial0:115200n8"; }; + connector { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi_con_in: endpoint { + remote-endpoint = <&hdmi_out_con>; + }; + }; + }; + leds { compatible = "gpio-leds"; pinctrl-names = "default"; @@ -76,6 +87,10 @@ }; }; +&be0 { + status = "okay"; +}; + &ehci0 { status = "okay"; }; @@ -91,6 +106,16 @@ status = "okay"; }; +&hdmi { + status = "okay"; +}; + +&hdmi_out { + hdmi_out_con: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; +}; + &i2c0 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; @@ -248,6 +273,10 @@ status = "okay"; }; +&tcon0 { + status = "okay"; +}; + &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins_a>; @@ -271,10 +300,6 @@ status = "okay"; }; -&usb0_vbus_pin_a { - pins = "PG11"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>; diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts index ea3e5655a61bda..5482be174e1224 100644 --- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts +++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts @@ -216,10 +216,6 @@ status = "okay"; }; -&usb1_vbus_pin_a { - pins = "PG12"; -}; - &usbphy { usb1_vbus-supply = <®_usb1_vbus>; status = "okay"; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index 1e38ff80366c67..18f25c5e75aebc 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -71,7 +71,46 @@ }; }; + display-engine { + compatible = "allwinner,sun5i-a10s-display-engine"; + allwinner,pipelines = <&fe0>; + }; + soc@01c00000 { + hdmi: hdmi@01c16000 { + compatible = "allwinner,sun5i-a10s-hdmi"; + reg = <0x01c16000 0x1000>; + interrupts = <58>; + clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>, + <&ccu 9>, + <&ccu 16>; + clock-names = "ahb", "mod", "pll-0", "pll-1"; + dmas = <&dma SUN4I_DMA_NORMAL 16>, + <&dma SUN4I_DMA_NORMAL 16>, + <&dma SUN4I_DMA_DEDICATED 24>; + dma-names = "ddc-tx", "ddc-rx", "audio-tx"; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + + hdmi_in_tcon0: endpoint { + remote-endpoint = <&tcon0_out_hdmi>; + }; + }; + + hdmi_out: port@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + }; + }; + }; + pwm: pwm@01c20e00 { compatible = "allwinner,sun5i-a10s-pwm"; reg = <0x01c20e00 0xc>; @@ -128,3 +167,11 @@ &sram_a { }; + +&tcon0_out { + tcon0_out_hdmi: endpoint@2 { + reg = <2>; + remote-endpoint = <&hdmi_in_tcon0>; + allwinner,tcon-channel = <1>; + }; +}; diff --git a/arch/arm/boot/dts/sun5i-a13-empire-electronix-d709.dts b/arch/arm/boot/dts/sun5i-a13-empire-electronix-d709.dts index 34411d27aadfd7..3dbb0d7c2f8c78 100644 --- a/arch/arm/boot/dts/sun5i-a13-empire-electronix-d709.dts +++ b/arch/arm/boot/dts/sun5i-a13-empire-electronix-d709.dts @@ -207,10 +207,6 @@ status = "okay"; }; -&usb0_vbus_pin_a { - pins = "PG12"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>; diff --git a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts index 2489c16f7efa52..584fa579ded206 100644 --- a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts +++ b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts @@ -186,7 +186,6 @@ }; ®_usb0_vbus { - pinctrl-0 = <&usb0_vbus_pin_a>; gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */ status = "okay"; }; @@ -202,10 +201,6 @@ status = "okay"; }; -&usb0_vbus_pin_a { - pins = "PG12"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>; diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts index 95f591bb8ced0b..38072c7e10e202 100644 --- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts +++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts @@ -269,10 +269,6 @@ status = "okay"; }; -&usb0_vbus_pin_a { - pins = "PG12"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index d0785602663ba5..879a4b0f3bd5b3 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -132,6 +132,10 @@ status = "okay"; }; +&battery_power_supply { + status = "okay"; +}; + &i2c1 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins_a>; diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi index 5175f9cc9bed0f..0e29f1d98a9e0e 100644 --- a/arch/arm/boot/dts/sun5i.dtsi +++ b/arch/arm/boot/dts/sun5i.dtsi @@ -272,6 +272,7 @@ tcon0_out_tve0: endpoint@1 { reg = <1>; remote-endpoint = <&tve0_in_tcon0>; + allwinner,tcon-channel = <1>; }; }; }; diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts index d4f74f476f25e0..9ecb5f0b3f83e8 100644 --- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts +++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts @@ -253,6 +253,10 @@ #include "axp22x.dtsi" +&ac_power_supply { + status = "okay"; +}; + ®_aldo1 { regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -319,7 +323,6 @@ &tcon0 { pinctrl-names = "default"; pinctrl-0 = <&lcd0_rgb888_pins>; - status = "okay"; }; &tcon0_out { @@ -344,11 +347,6 @@ status = "okay"; }; -&usb1_vbus_pin_a { - /* different pin from sunxi-common-regulators */ - pins = "PH24"; -}; - &usbphy { usb0_id_det-gpio = <&pio 0 15 GPIO_ACTIVE_HIGH>; /* PA15 */ usb0_vbus_det-gpio = <&pio 0 16 GPIO_ACTIVE_HIGH>; /* PA16 */ diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 9c999d3788f681..d0cede5aaeb5ed 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -232,7 +232,7 @@ de: display-engine { compatible = "allwinner,sun6i-a31-display-engine"; - allwinner,pipelines = <&fe0>; + allwinner,pipelines = <&fe0>, <&fe1>; status = "disabled"; }; @@ -264,7 +264,6 @@ "tcon-ch0", "tcon-ch1"; clock-output-names = "tcon0-pixel-clock"; - status = "disabled"; ports { #address-cells = <1>; @@ -289,6 +288,43 @@ }; }; + tcon1: lcd-controller@01c0d000 { + compatible = "allwinner,sun6i-a31-tcon"; + reg = <0x01c0d000 0x1000>; + interrupts = ; + resets = <&ccu RST_AHB1_LCD1>; + reset-names = "lcd"; + clocks = <&ccu CLK_AHB1_LCD1>, + <&ccu CLK_LCD1_CH0>, + <&ccu CLK_LCD1_CH1>; + clock-names = "ahb", + "tcon-ch0", + "tcon-ch1"; + clock-output-names = "tcon1-pixel-clock"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + tcon1_in: port@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + tcon1_in_drc1: endpoint@0 { + reg = <0>; + remote-endpoint = <&drc1_out_tcon1>; + }; + }; + + tcon1_out: port@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + }; + }; + }; + mmc0: mmc@01c0f000 { compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; @@ -896,6 +932,130 @@ reg = <0>; remote-endpoint = <&be0_in_fe0>; }; + + fe0_out_be1: endpoint@1 { + reg = <1>; + remote-endpoint = <&be1_in_fe0>; + }; + }; + }; + }; + + fe1: display-frontend@01e20000 { + compatible = "allwinner,sun6i-a31-display-frontend"; + reg = <0x01e20000 0x20000>; + interrupts = ; + clocks = <&ccu CLK_AHB1_FE1>, <&ccu CLK_FE1>, + <&ccu CLK_DRAM_FE1>; + clock-names = "ahb", "mod", + "ram"; + resets = <&ccu RST_AHB1_FE1>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + fe1_out: port@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + fe1_out_be0: endpoint@0 { + reg = <0>; + remote-endpoint = <&be0_in_fe1>; + }; + + fe1_out_be1: endpoint@1 { + reg = <1>; + remote-endpoint = <&be1_in_fe1>; + }; + }; + }; + }; + + be1: display-backend@01e40000 { + compatible = "allwinner,sun6i-a31-display-backend"; + reg = <0x01e40000 0x10000>; + interrupts = ; + clocks = <&ccu CLK_AHB1_BE1>, <&ccu CLK_BE1>, + <&ccu CLK_DRAM_BE1>; + clock-names = "ahb", "mod", + "ram"; + resets = <&ccu RST_AHB1_BE1>; + + assigned-clocks = <&ccu CLK_BE1>; + assigned-clock-rates = <300000000>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + be1_in: port@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + be1_in_fe0: endpoint@0 { + reg = <0>; + remote-endpoint = <&fe0_out_be1>; + }; + + be1_in_fe1: endpoint@1 { + reg = <1>; + remote-endpoint = <&fe1_out_be1>; + }; + }; + + be1_out: port@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + be1_out_drc1: endpoint@0 { + reg = <0>; + remote-endpoint = <&drc1_in_be1>; + }; + }; + }; + }; + + drc1: drc@01e50000 { + compatible = "allwinner,sun6i-a31-drc"; + reg = <0x01e50000 0x10000>; + interrupts = ; + clocks = <&ccu CLK_AHB1_DRC1>, <&ccu CLK_IEP_DRC1>, + <&ccu CLK_DRAM_DRC1>; + clock-names = "ahb", "mod", + "ram"; + resets = <&ccu RST_AHB1_DRC1>; + + assigned-clocks = <&ccu CLK_IEP_DRC1>; + assigned-clock-rates = <300000000>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + drc1_in: port@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + drc1_in_be1: endpoint@0 { + reg = <0>; + remote-endpoint = <&be1_out_drc1>; + }; + }; + + drc1_out: port@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <1>; + + drc1_out_tcon1: endpoint@0 { + reg = <0>; + remote-endpoint = <&tcon1_in_drc1>; + }; }; }; }; @@ -926,6 +1086,11 @@ reg = <0>; remote-endpoint = <&fe0_out_be0>; }; + + be0_in_fe1: endpoint@1 { + reg = <1>; + remote-endpoint = <&fe1_out_be0>; + }; }; be0_out: port@1 { diff --git a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts index bdfdce8ca6ba12..51e6f1d21c32b7 100644 --- a/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts +++ b/arch/arm/boot/dts/sun6i-a31s-sinovoip-bpi-m2.dts @@ -138,7 +138,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&r_pio>; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts index 08e776ae095a36..eb55e74232c992 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts @@ -144,6 +144,10 @@ #include "axp209.dtsi" +&ac_power_supply { + status = "okay"; +}; + &ir0 { pinctrl-names = "default"; pinctrl-0 = <&ir0_rx_pins_a>; @@ -172,7 +176,7 @@ wakeup-source; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi.dts b/arch/arm/boot/dts/sun7i-a20-bananapi.dts index ed2f35adf5426d..88a1c2363c6ca0 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi.dts @@ -177,6 +177,57 @@ }; &pio { + gpio-line-names = + /* PA */ + "ERXD3", "ERXD2", "ERXD1", "ERXD0", "ETXD3", + "ETXD2", "ETXD1", "ETXD0", + "ERXCK", "ERXERR", "ERXDV", "EMDC", "EMDIO", + "ETXEN", "ETXCK", "ECRS", + "ECOL", "ETXERR", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PB */ + "PMU-SCK", "PMU-SDA", "", "", "", "", "", "", + "", "USB0-DRV", "", "", "", "", "", "", + "", "", "", "", "SCL", "SDA", "", "", + "", "", "", "", "", "", "", "", + /* PC */ + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PD */ + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PE */ + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PF */ + "SD0-D1", "SD0-D0", "SD0-CLK", "SD0-CMD", "SD0-D3", + "SD0-D2", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PG */ + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* PH */ + "TXD0", "RXD0", "IO-1", "PH3", "USB0-IDDET", "PH5", "", "", + "", "", "SD0-DET", "", "", "", "", "", + "", "", "", "", "IO-4", "IO-5", "", "EMAC-PWR-EN", + "LED1", "", "", "", "", "", "", "", + /* PI */ + "", "", "", "IO-GCLK", "", "", "", "", + "", "", "SPI-CE0", "SPI-CLK", "SPI-MOSI", + "SPI-MISO", "SPI-CE1", "", + "IO-6", "IO-3", "IO-2", "IO-0", "", "", "", "", + "", "", "", "", "", "", "", ""; + usb0_id_detect_pin: usb0_id_detect_pin@0 { pins = "PH4"; function = "gpio_in"; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapro.dts b/arch/arm/boot/dts/sun7i-a20-bananapro.dts index 83516bc8122577..e7af1b7c33d592 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapro.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapro.dts @@ -172,7 +172,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; diff --git a/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts index a2eab7aa80e014..2a50207618cb36 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts @@ -137,7 +137,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -174,13 +174,12 @@ status = "okay"; }; -&usb_otg { - dr_mode = "otg"; +#include "axp209.dtsi" + +&ac_power_supply { status = "okay"; }; -#include "axp209.dtsi" - ®_dcdc2 { regulator-always-on; regulator-min-microvolt = <1000000>; @@ -220,6 +219,11 @@ status = "okay"; }; +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>; diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts index 102903e83bd216..bb510187602c1c 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts @@ -178,7 +178,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -195,7 +195,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; @@ -336,6 +336,7 @@ pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>; usb0_id_det-gpios = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */ usb0_vbus_det-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */ + usb0_vbus_power-supply = <&usb_power_supply>; usb0_vbus-supply = <®_usb0_vbus>; usb1_vbus-supply = <®_usb1_vbus>; usb2_vbus-supply = <®_usb2_vbus>; diff --git a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts index 99c00b9a15464f..6e6264cd69f866 100644 --- a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts +++ b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts @@ -160,7 +160,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v0>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts b/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts index 4da49717da2108..55809973a568e7 100644 --- a/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts +++ b/arch/arm/boot/dts/sun7i-a20-i12-tvbox.dts @@ -157,7 +157,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -173,7 +173,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; diff --git a/arch/arm/boot/dts/sun7i-a20-icnova-swac.dts b/arch/arm/boot/dts/sun7i-a20-icnova-swac.dts index 28d3abbdc2d4c9..794e7617f545f8 100644 --- a/arch/arm/boot/dts/sun7i-a20-icnova-swac.dts +++ b/arch/arm/boot/dts/sun7i-a20-icnova-swac.dts @@ -104,7 +104,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 8 5 GPIO_ACTIVE_HIGH>; /* PI5 */ diff --git a/arch/arm/boot/dts/sun7i-a20-itead-ibox.dts b/arch/arm/boot/dts/sun7i-a20-itead-ibox.dts index d52222c82cb8f3..8a8a6dbcd41428 100644 --- a/arch/arm/boot/dts/sun7i-a20-itead-ibox.dts +++ b/arch/arm/boot/dts/sun7i-a20-itead-ibox.dts @@ -121,7 +121,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts index 96bb0bc198baff..004b6ddac8131c 100644 --- a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts +++ b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts @@ -85,10 +85,6 @@ }; }; -&ahci_pwr_pin_a { - pins = "PB3"; -}; - &ahci { target-supply = <®_ahci_5v>; status = "okay"; @@ -319,10 +315,6 @@ status = "okay"; }; -&usb2_vbus_pin_a { - pins = "PH12"; -}; - &usbphy { pinctrl-names = "default"; pinctrl-0 = <&usb0_id_detect_pin>; diff --git a/arch/arm/boot/dts/sun7i-a20-m3.dts b/arch/arm/boot/dts/sun7i-a20-m3.dts index 86f69813683ec1..43c94787ef0794 100644 --- a/arch/arm/boot/dts/sun7i-a20-m3.dts +++ b/arch/arm/boot/dts/sun7i-a20-m3.dts @@ -117,7 +117,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-mk808c.dts b/arch/arm/boot/dts/sun7i-a20-mk808c.dts index c4ee30709f3a18..f7413094183c01 100644 --- a/arch/arm/boot/dts/sun7i-a20-mk808c.dts +++ b/arch/arm/boot/dts/sun7i-a20-mk808c.dts @@ -109,7 +109,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v0>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-olimex-som-evb.dts b/arch/arm/boot/dts/sun7i-a20-olimex-som-evb.dts index 1af5b46862cba9..64c8ef9a275626 100644 --- a/arch/arm/boot/dts/sun7i-a20-olimex-som-evb.dts +++ b/arch/arm/boot/dts/sun7i-a20-olimex-som-evb.dts @@ -187,7 +187,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts index dcd0f7a0dffae7..2ce1a9f13a178f 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime.dts @@ -130,7 +130,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts index e7d45425758ca1..097bd755764cfb 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts @@ -131,7 +131,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts index def0ad8395bb2c..0b7403e4d687ea 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts @@ -198,7 +198,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts index f47a5c46bc20a4..39bc73db72e5da 100644 --- a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts +++ b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts @@ -130,7 +130,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-pcduino3.dts b/arch/arm/boot/dts/sun7i-a20-pcduino3.dts index 7c96b53b76bfe0..777152a3df0f96 100644 --- a/arch/arm/boot/dts/sun7i-a20-pcduino3.dts +++ b/arch/arm/boot/dts/sun7i-a20-pcduino3.dts @@ -106,10 +106,6 @@ status = "okay"; }; -&ahci_pwr_pin_a { - pins = "PH2"; -}; - &codec { status = "okay"; }; @@ -160,7 +156,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-wexler-tab7200.dts b/arch/arm/boot/dts/sun7i-a20-wexler-tab7200.dts index e19f171777551b..f8d0aafb9f88f6 100644 --- a/arch/arm/boot/dts/sun7i-a20-wexler-tab7200.dts +++ b/arch/arm/boot/dts/sun7i-a20-wexler-tab7200.dts @@ -151,7 +151,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ diff --git a/arch/arm/boot/dts/sun7i-a20-wits-pro-a20-dkt.dts b/arch/arm/boot/dts/sun7i-a20-wits-pro-a20-dkt.dts index c3078d4f10930a..7f8405a0dd0fea 100644 --- a/arch/arm/boot/dts/sun7i-a20-wits-pro-a20-dkt.dts +++ b/arch/arm/boot/dts/sun7i-a20-wits-pro-a20-dkt.dts @@ -120,7 +120,7 @@ &mmc0 { pinctrl-names = "default"; - pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_reference_design>; + pinctrl-0 = <&mmc0_pins_a>; vmmc-supply = <®_vcc3v3>; bus-width = <4>; cd-gpios = <&pio 7 1 GPIO_ACTIVE_HIGH>; /* PH1 */ @@ -137,7 +137,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 93aa55970bd7a2..c03b59aaec8202 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -1190,12 +1190,6 @@ bias-pull-up; }; - mmc0_cd_pin_reference_design: mmc0_cd_pin@0 { - pins = "PH1"; - function = "gpio_in"; - bias-pull-up; - }; - mmc2_pins_a: mmc2@0 { pins = "PC6", "PC7", "PC8", "PC9", "PC10", "PC11"; diff --git a/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts b/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts index 9b620cc1d5f132..433cf2a2a9a25b 100644 --- a/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts +++ b/arch/arm/boot/dts/sun8i-a33-sinlinx-sina33.dts @@ -88,13 +88,13 @@ }; &cpu0_opp_table { - opp@1104000000 { + opp-1104000000 { opp-hz = /bits/ 64 <1104000000>; opp-microvolt = <1320000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@1200000000 { + opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <1320000>; clock-latency-ns = <244144>; /* 8 32k periods */ @@ -196,6 +196,10 @@ status = "okay"; }; +&battery_power_supply { + status = "okay"; +}; + ®_aldo1 { regulator-always-on; regulator-min-microvolt = <3000000>; diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi index 01397825937241..22660919bd08ae 100644 --- a/arch/arm/boot/dts/sun8i-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a33.dtsi @@ -50,73 +50,73 @@ compatible = "operating-points-v2"; opp-shared; - opp@120000000 { + opp-120000000 { opp-hz = /bits/ 64 <120000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@240000000 { + opp-240000000 { opp-hz = /bits/ 64 <240000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@312000000 { + opp-312000000 { opp-hz = /bits/ 64 <312000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@408000000 { + opp-408000000 { opp-hz = /bits/ 64 <408000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@480000000 { + opp-480000000 { opp-hz = /bits/ 64 <480000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@504000000 { + opp-504000000 { opp-hz = /bits/ 64 <504000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@600000000 { + opp-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@648000000 { + opp-648000000 { opp-hz = /bits/ 64 <648000000>; opp-microvolt = <1040000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@720000000 { + opp-720000000 { opp-hz = /bits/ 64 <720000000>; opp-microvolt = <1100000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@816000000 { + opp-816000000 { opp-hz = /bits/ 64 <816000000>; opp-microvolt = <1100000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@912000000 { + opp-912000000 { opp-hz = /bits/ 64 <912000000>; opp-microvolt = <1200000>; clock-latency-ns = <244144>; /* 8 32k periods */ }; - opp@1008000000 { + opp-1008000000 { opp-hz = /bits/ 64 <1008000000>; opp-microvolt = <1200000>; clock-latency-ns = <244144>; /* 8 32k periods */ @@ -164,15 +164,15 @@ mali_opp_table: gpu-opp-table { compatible = "operating-points-v2"; - opp@144000000 { + opp-144000000 { opp-hz = /bits/ 64 <144000000>; }; - opp@240000000 { + opp-240000000 { opp-hz = /bits/ 64 <240000000>; }; - opp@384000000 { + opp-384000000 { opp-hz = /bits/ 64 <384000000>; }; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-allwinner-h8homlet-v2.dts b/arch/arm/boot/dts/sun8i-a83t-allwinner-h8homlet-v2.dts index 342e1d33fa1c37..aecdeeb368ed85 100644 --- a/arch/arm/boot/dts/sun8i-a83t-allwinner-h8homlet-v2.dts +++ b/arch/arm/boot/dts/sun8i-a83t-allwinner-h8homlet-v2.dts @@ -59,6 +59,6 @@ &uart0 { pinctrl-names = "default"; - pinctrl-0 = <&uart0_pins_b>; + pinctrl-0 = <&uart0_pb_pins>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index 88b1e0970b8d89..cff33454fc2458 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -45,6 +45,8 @@ /dts-v1/; #include "sun8i-a83t.dtsi" +#include + / { model = "Cubietech Cubietruck Plus"; compatible = "cubietech,cubietruck-plus", "allwinner,sun8i-a83t"; @@ -56,10 +58,56 @@ chosen { stdout-path = "serial0:115200n8"; }; + + leds { + compatible = "gpio-leds"; + + blue { + label = "cubietruck-plus:blue:usr"; + gpios = <&pio 3 25 GPIO_ACTIVE_HIGH>; /* PD25 */ + }; + + orange { + label = "cubietruck-plus:orange:usr"; + gpios = <&pio 3 26 GPIO_ACTIVE_HIGH>; /* PD26 */ + }; + + white { + label = "cubietruck-plus:white:usr"; + gpios = <&pio 3 27 GPIO_ACTIVE_HIGH>; /* PD27 */ + }; + + green { + label = "cubietruck-plus:green:usr"; + gpios = <&pio 4 4 GPIO_ACTIVE_HIGH>; /* PE4 */ + }; + }; + + sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "On-board SPDIF"; + + simple-audio-card,cpu { + sound-dai = <&spdif>; + }; + + simple-audio-card,codec { + sound-dai = <&spdif_out>; + }; + }; + + spdif_out: spdif-out { + #sound-dai-cells = <0>; + compatible = "linux,spdif-dit"; + }; +}; + +&spdif { + status = "okay"; }; &uart0 { pinctrl-names = "default"; - pinctrl-0 = <&uart0_pins_b>; + pinctrl-0 = <&uart0_pb_pins>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi index 0ec143773ee9bf..1dc4cfe815342b 100644 --- a/arch/arm/boot/dts/sun8i-a83t.dtsi +++ b/arch/arm/boot/dts/sun8i-a83t.dtsi @@ -40,15 +40,20 @@ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. - */ -#include "skeleton.dtsi" - #include / { interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + aliases { + }; + + chosen { + }; cpus { #address-cells = <1>; @@ -121,6 +126,7 @@ #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <24000000>; + clock-accuracy = <50000>; clock-output-names = "osc24M"; }; @@ -146,25 +152,49 @@ }; }; + memory { + reg = <0x40000000 0x80000000>; + device_type = "memory"; + }; + soc { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; ranges; - pio: pinctrl@01c20800 { + dma: dma-controller@1c02000 { + compatible = "allwinner,sun8i-a83t-dma"; + reg = <0x01c02000 0x1000>; + interrupts = ; + clocks = <&ccu 21>; + resets = <&ccu 7>; + #dma-cells = <1>; + }; + + ccu: clock@1c20000 { + compatible = "allwinner,sun8i-a83t-ccu"; + reg = <0x01c20000 0x400>; + clocks = <&osc24M>, <&osc16Md512>; + clock-names = "hosc", "losc"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + pio: pinctrl@1c20800 { compatible = "allwinner,sun8i-a83t-pinctrl"; interrupts = , , ; reg = <0x01c20800 0x400>; - clocks = <&osc24M>; + clocks = <&ccu 45>, <&osc24M>, <&osc16Md512>; + clock-names = "apb", "hosc", "losc"; gpio-controller; interrupt-controller; #interrupt-cells = <3>; #gpio-cells = <3>; - mmc0_pins_a: mmc0@0 { + mmc0_pins: mmc0-pins { pins = "PF0", "PF1", "PF2", "PF3", "PF4", "PF5"; function = "mmc0"; @@ -172,18 +202,23 @@ bias-pull-up; }; - uart0_pins_a: uart0@0 { - pins = "PF2", "PF4"; - function = "uart0"; + spdif_tx_pin: spdif-tx-pin { + pins = "PE18"; + function = "spdif"; }; - uart0_pins_b: uart0@1 { + uart0_pb_pins: uart0-pb-pins { pins = "PB9", "PB10"; function = "uart0"; }; + + uart0_pf_pins: uart0-pf-pins { + pins = "PF2", "PF4"; + function = "uart0"; + }; }; - timer@01c20c00 { + timer@1c20c00 { compatible = "allwinner,sun4i-a10-timer"; reg = <0x01c20c00 0xa0>; interrupts = , @@ -191,24 +226,41 @@ clocks = <&osc24M>; }; - watchdog@01c20ca0 { + watchdog@1c20ca0 { compatible = "allwinner,sun6i-a31-wdt"; reg = <0x01c20ca0 0x20>; interrupts = ; clocks = <&osc24M>; }; + spdif: spdif@1c21000 { + #sound-dai-cells = <0>; + compatible = "allwinner,sun8i-a83t-spdif", + "allwinner,sun8i-h3-spdif"; + reg = <0x01c21000 0x400>; + interrupts = ; + clocks = <&ccu 44>, <&ccu 76>; + resets = <&ccu 32>; + clock-names = "apb", "spdif"; + dmas = <&dma 2>; + dma-names = "tx"; + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; + status = "disabled"; + }; + uart0: serial@01c28000 { compatible = "snps,dw-apb-uart"; reg = <0x01c28000 0x400>; interrupts = ; reg-shift = <2>; reg-io-width = <4>; - clocks = <&osc24M>; + clocks = <&ccu 53>; + resets = <&ccu 40>; status = "disabled"; }; - gic: interrupt-controller@01c81000 { + gic: interrupt-controller@1c81000 { compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic"; reg = <0x01c81000 0x1000>, <0x01c82000 0x2000>, diff --git a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts index 9e8b082c134f61..6713d0f2b3f4d3 100644 --- a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts +++ b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts @@ -57,6 +57,7 @@ aliases { serial0 = &uart0; /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ + ethernet0 = &emac; ethernet1 = &xr819; }; @@ -103,6 +104,13 @@ status = "okay"; }; +&emac { + phy-handle = <&int_mii_phy>; + phy-mode = "mii"; + allwinner,leds-active-low; + status = "okay"; +}; + &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>; @@ -143,6 +151,19 @@ status = "okay"; }; +&spi0 { + /* Disable SPI NOR by default: it optional on Orange Pi Zero boards */ + status = "disabled"; + + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "mxicy,mx25l1606e", "winbond,w25q128"; + reg = <0>; + spi-max-frequency = <40000000>; + }; +}; + &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts index 52acbe111cade5..883072b611fa1c 100644 --- a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts @@ -92,6 +92,10 @@ }; }; +&ehci0 { + status = "okay"; +}; + &ehci1 { status = "okay"; }; @@ -126,7 +130,7 @@ non-removable; status = "okay"; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; interrupt-parent = <&pio>; @@ -145,6 +149,10 @@ status = "okay"; }; +&ohci0 { + status = "okay"; +}; + &ohci1 { status = "okay"; }; @@ -170,6 +178,11 @@ }; }; +®_usb0_vbus { + gpio = <&pio 3 11 GPIO_ACTIVE_HIGH>; /* PD11 */ + status = "okay"; +}; + &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins_a>; @@ -182,7 +195,14 @@ status = "okay"; }; +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + &usbphy { - /* USB VBUS is on as long as VCC-IO is on */ + usb0_id_det-gpios = <&r_pio 0 6 GPIO_ACTIVE_HIGH>; /* PL6 */ + usb0_vbus-supply = <®_usb0_vbus>; + /* USB host VBUS is on as long as VCC-IO is on */ status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts index 8d2cc6e9a03faf..78f6c24952dd12 100644 --- a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts +++ b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts @@ -46,3 +46,10 @@ model = "FriendlyARM NanoPi NEO"; compatible = "friendlyarm,nanopi-neo", "allwinner,sun8i-h3"; }; + +&emac { + phy-handle = <&int_mii_phy>; + phy-mode = "mii"; + allwinner,leds-active-low; + status = "okay"; +}; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts index 5b6d14555b7ccb..17cdeae19c6f0f 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts @@ -54,6 +54,7 @@ aliases { serial0 = &uart0; /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ + ethernet0 = &emac; ethernet1 = &rtl8189; }; @@ -104,10 +105,26 @@ }; }; +&codec { + allwinner,pa-gpios = <&pio 0 16 GPIO_ACTIVE_HIGH>; /* PA16 */ + allwinner,audio-routing = + "Speaker", "LINEOUT", + "MIC1", "Mic", + "Mic", "MBIAS"; + status = "okay"; +}; + &ehci1 { status = "okay"; }; +&emac { + phy-handle = <&int_mii_phy>; + phy-mode = "mii"; + allwinner,leds-active-low; + status = "okay"; +}; + &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; @@ -195,10 +212,6 @@ status = "disabled"; }; -&usb1_vbus_pin_a { - pins = "PG13"; -}; - &usbphy { usb1_vbus-supply = <®_usb1_vbus>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts index 5fea430e0eb100..6880268e8b87b0 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts @@ -52,6 +52,7 @@ compatible = "xunlong,orangepi-one", "allwinner,sun8i-h3"; aliases { + ethernet0 = &emac; serial0 = &uart0; }; @@ -97,6 +98,13 @@ status = "okay"; }; +&emac { + phy-handle = <&int_mii_phy>; + phy-mode = "mii"; + allwinner,leds-active-low; + status = "okay"; +}; + &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 8b93f5c781a70b..a10281b455f50c 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,6 +53,11 @@ }; }; +&emac { + /* LEDs changed to active high on the plus */ + /delete-property/ allwinner,leds-active-low; +}; + &mmc1 { pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts index f148111c326d07..998b60f8d295e8 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts @@ -52,6 +52,7 @@ compatible = "xunlong,orangepi-pc", "allwinner,sun8i-h3"; aliases { + ethernet0 = &emac; serial0 = &uart0; }; @@ -97,6 +98,10 @@ status = "okay"; }; +&ehci0 { + status = "okay"; +}; + &ehci1 { status = "okay"; }; @@ -109,6 +114,13 @@ status = "okay"; }; +&emac { + phy-handle = <&int_mii_phy>; + phy-mode = "mii"; + allwinner,leds-active-low; + status = "okay"; +}; + &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; @@ -125,6 +137,10 @@ status = "okay"; }; +&ohci0 { + status = "okay"; +}; + &ohci1 { status = "okay"; }; @@ -156,6 +172,11 @@ }; }; +®_usb0_vbus { + gpio = <&r_pio 0 2 GPIO_ACTIVE_HIGH>; /* PL2 */ + status = "okay"; +}; + &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins_a>; @@ -180,7 +201,14 @@ status = "disabled"; }; +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + &usbphy { - /* USB VBUS is always on */ + usb0_id_det-gpios = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */ + usb0_vbus-supply = <®_usb0_vbus>; + /* VBUS on USB host ports are always on */ status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts new file mode 100644 index 00000000000000..d1311098ea459b --- /dev/null +++ b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts @@ -0,0 +1,96 @@ +/* + * Copyright (C) 2016 Icenowy Zheng + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "sun8i-v3s-licheepi-zero.dts" + +#include + +/ { + model = "Lichee Pi Zero with Dock"; + compatible = "licheepi,licheepi-zero-dock", "licheepi,licheepi-zero", + "allwinner,sun8i-v3s"; + + leds { + /* The LEDs use PG0~2 pins, which conflict with MMC1 */ + status = "disbaled"; + }; +}; + +&mmc1 { + broken-cd; + bus-width = <4>; + vmmc-supply = <®_vcc3v3>; + status = "okay"; +}; + +&lradc { + vref-supply = <®_vcc3v0>; + status = "okay"; + + button@200 { + label = "Volume Up"; + linux,code = ; + channel = <0>; + voltage = <200000>; + }; + + button@400 { + label = "Volume Down"; + linux,code = ; + channel = <0>; + voltage = <400000>; + }; + + button@600 { + label = "Select"; + linux,code = ; + channel = <0>; + voltage = <600000>; + }; + + button@800 { + label = "Start"; + linux,code = ; + channel = <0>; + voltage = <800000>; + }; +}; diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index 71075969e5e602..a49ebef53c91b4 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -41,6 +41,8 @@ */ #include +#include +#include / { #address-cells = <1>; @@ -55,7 +57,7 @@ compatible = "arm,cortex-a7"; device_type = "cpu"; reg = <0>; - clocks = <&ccu 14>; + clocks = <&ccu CLK_CPU>; }; }; @@ -96,15 +98,15 @@ mmc0: mmc@01c0f000 { compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c0f000 0x1000>; - clocks = <&ccu 22>, - <&ccu 45>, - <&ccu 47>, - <&ccu 46>; + clocks = <&ccu CLK_BUS_MMC0>, + <&ccu CLK_MMC0>, + <&ccu CLK_MMC0_OUTPUT>, + <&ccu CLK_MMC0_SAMPLE>; clock-names = "ahb", "mmc", "output", "sample"; - resets = <&ccu 7>; + resets = <&ccu RST_BUS_MMC0>; reset-names = "ahb"; interrupts = ; status = "disabled"; @@ -115,17 +117,19 @@ mmc1: mmc@01c10000 { compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c10000 0x1000>; - clocks = <&ccu 23>, - <&ccu 48>, - <&ccu 50>, - <&ccu 49>; + clocks = <&ccu CLK_BUS_MMC1>, + <&ccu CLK_MMC1>, + <&ccu CLK_MMC1_OUTPUT>, + <&ccu CLK_MMC1_SAMPLE>; clock-names = "ahb", "mmc", "output", "sample"; - resets = <&ccu 8>; + resets = <&ccu RST_BUS_MMC1>; reset-names = "ahb"; interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; status = "disabled"; #address-cells = <1>; #size-cells = <0>; @@ -134,15 +138,15 @@ mmc2: mmc@01c11000 { compatible = "allwinner,sun7i-a20-mmc"; reg = <0x01c11000 0x1000>; - clocks = <&ccu 24>, - <&ccu 51>, - <&ccu 53>, - <&ccu 52>; + clocks = <&ccu CLK_BUS_MMC2>, + <&ccu CLK_MMC2>, + <&ccu CLK_MMC2_OUTPUT>, + <&ccu CLK_MMC2_SAMPLE>; clock-names = "ahb", "mmc", "output", "sample"; - resets = <&ccu 9>; + resets = <&ccu RST_BUS_MMC2>; reset-names = "ahb"; interrupts = ; status = "disabled"; @@ -153,8 +157,8 @@ usb_otg: usb@01c19000 { compatible = "allwinner,sun8i-h3-musb"; reg = <0x01c19000 0x0400>; - clocks = <&ccu 29>; - resets = <&ccu 17>; + clocks = <&ccu CLK_BUS_OTG>; + resets = <&ccu RST_BUS_OTG>; interrupts = ; interrupt-names = "mc"; phys = <&usbphy 0>; @@ -169,9 +173,9 @@ <0x01c1a800 0x4>; reg-names = "phy_ctrl", "pmu0"; - clocks = <&ccu 56>; + clocks = <&ccu CLK_USB_PHY0>; clock-names = "usb0_phy"; - resets = <&ccu 0>; + resets = <&ccu RST_USB_PHY0>; reset-names = "usb0_reset"; status = "disabled"; #phy-cells = <1>; @@ -198,7 +202,7 @@ reg = <0x01c20800 0x400>; interrupts = , ; - clocks = <&ccu 37>, <&osc24M>, <&osc32k>; + clocks = <&ccu CLK_BUS_PIO>, <&osc24M>, <&osc32k>; clock-names = "apb", "hosc", "losc"; gpio-controller; #gpio-cells = <3>; @@ -222,6 +226,19 @@ drive-strength = <30>; bias-pull-up; }; + + mmc1_pins: mmc1 { + pins = "PG0", "PG1", "PG2", "PG3", + "PG4", "PG5"; + function = "mmc1"; + drive-strength = <30>; + bias-pull-up; + }; + + spi0_pins: spi0 { + pins = "PC0", "PC1", "PC2", "PC3"; + function = "spi0"; + }; }; timer@01c20c00 { @@ -238,14 +255,21 @@ interrupts = ; }; + lradc: lradc@1c22800 { + compatible = "allwinner,sun4i-a10-lradc-keys"; + reg = <0x01c22800 0x400>; + interrupts = ; + status = "disabled"; + }; + uart0: serial@01c28000 { compatible = "snps,dw-apb-uart"; reg = <0x01c28000 0x400>; interrupts = ; reg-shift = <2>; reg-io-width = <4>; - clocks = <&ccu 40>; - resets = <&ccu 49>; + clocks = <&ccu CLK_BUS_UART0>; + resets = <&ccu RST_BUS_UART0>; status = "disabled"; }; @@ -255,8 +279,8 @@ interrupts = ; reg-shift = <2>; reg-io-width = <4>; - clocks = <&ccu 41>; - resets = <&ccu 50>; + clocks = <&ccu CLK_BUS_UART1>; + resets = <&ccu RST_BUS_UART1>; status = "disabled"; }; @@ -266,8 +290,8 @@ interrupts = ; reg-shift = <2>; reg-io-width = <4>; - clocks = <&ccu 42>; - resets = <&ccu 51>; + clocks = <&ccu CLK_BUS_UART2>; + resets = <&ccu RST_BUS_UART2>; status = "disabled"; }; @@ -275,8 +299,8 @@ compatible = "allwinner,sun6i-a31-i2c"; reg = <0x01c2ac00 0x400>; interrupts = ; - clocks = <&ccu 38>; - resets = <&ccu 46>; + clocks = <&ccu CLK_BUS_I2C0>; + resets = <&ccu RST_BUS_I2C0>; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; status = "disabled"; @@ -288,8 +312,22 @@ compatible = "allwinner,sun6i-a31-i2c"; reg = <0x01c2b000 0x400>; interrupts = ; - clocks = <&ccu 39>; - resets = <&ccu 47>; + clocks = <&ccu CLK_BUS_I2C1>; + resets = <&ccu RST_BUS_I2C1>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + spi0: spi@1c68000 { + compatible = "allwinner,sun8i-h3-spi"; + reg = <0x01c68000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_SPI0>, <&ccu CLK_SPI0>; + clock-names = "ahb", "mod"; + pinctrl-names = "default"; + pinctrl-0 = <&spi0_pins>; + resets = <&ccu RST_BUS_SPI0>; status = "disabled"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/sunxi-common-regulators.dtsi b/arch/arm/boot/dts/sunxi-common-regulators.dtsi index ce5c53e4452fcd..d8e5826fb3de36 100644 --- a/arch/arm/boot/dts/sunxi-common-regulators.dtsi +++ b/arch/arm/boot/dts/sunxi-common-regulators.dtsi @@ -44,33 +44,9 @@ #include -&pio { - ahci_pwr_pin_a: ahci_pwr_pin@0 { - pins = "PB8"; - function = "gpio_out"; - }; - - usb0_vbus_pin_a: usb0_vbus_pin@0 { - pins = "PB9"; - function = "gpio_out"; - }; - - usb1_vbus_pin_a: usb1_vbus_pin@0 { - pins = "PH6"; - function = "gpio_out"; - }; - - usb2_vbus_pin_a: usb2_vbus_pin@0 { - pins = "PH3"; - function = "gpio_out"; - }; -}; - / { reg_ahci_5v: ahci-5v { compatible = "regulator-fixed"; - pinctrl-names = "default"; - pinctrl-0 = <&ahci_pwr_pin_a>; regulator-name = "ahci-5v"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; @@ -82,8 +58,6 @@ reg_usb0_vbus: usb0-vbus { compatible = "regulator-fixed"; - pinctrl-names = "default"; - pinctrl-0 = <&usb0_vbus_pin_a>; regulator-name = "usb0-vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; @@ -94,8 +68,6 @@ reg_usb1_vbus: usb1-vbus { compatible = "regulator-fixed"; - pinctrl-names = "default"; - pinctrl-0 = <&usb1_vbus_pin_a>; regulator-name = "usb1-vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; @@ -107,8 +79,6 @@ reg_usb2_vbus: usb2-vbus { compatible = "regulator-fixed"; - pinctrl-names = "default"; - pinctrl-0 = <&usb2_vbus_pin_a>; regulator-name = "usb2-vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi index 1aeeacb3a8849b..9e4a496f3cca87 100644 --- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi +++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi @@ -83,6 +83,12 @@ #size-cells = <1>; ranges; + syscon: syscon@1c00000 { + compatible = "allwinner,sun8i-h3-system-controller", + "syscon"; + reg = <0x01c00000 0x1000>; + }; + dma: dma-controller@01c02000 { compatible = "allwinner,sun8i-h3-dma"; reg = <0x01c02000 0x1000>; @@ -279,6 +285,14 @@ interrupt-controller; #interrupt-cells = <3>; + emac_rgmii_pins: emac0 { + pins = "PD0", "PD1", "PD2", "PD3", "PD4", + "PD5", "PD7", "PD8", "PD9", "PD10", + "PD12", "PD13", "PD15", "PD16", "PD17"; + function = "emac"; + drive-strength = <40>; + }; + i2c0_pins: i2c0 { pins = "PA11", "PA12"; function = "i2c0"; @@ -375,6 +389,32 @@ clocks = <&osc24M>; }; + emac: ethernet@1c30000 { + compatible = "allwinner,sun8i-h3-emac"; + syscon = <&syscon>; + reg = <0x01c30000 0x104>; + interrupts = ; + interrupt-names = "macirq"; + resets = <&ccu RST_BUS_EMAC>; + reset-names = "stmmaceth"; + clocks = <&ccu CLK_BUS_EMAC>; + clock-names = "stmmaceth"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + + mdio: mdio { + #address-cells = <1>; + #size-cells = <0>; + int_mii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + clocks = <&ccu CLK_BUS_EPHY>; + resets = <&ccu RST_BUS_EPHY>; + }; + }; + }; + spi0: spi@01c68000 { compatible = "allwinner,sun8i-h3-spi"; reg = <0x01c68000 0x1000>; @@ -558,7 +598,7 @@ }; r_ccu: clock@1f01400 { - compatible = "allwinner,sun50i-a64-r-ccu"; + compatible = "allwinner,sun8i-h3-r-ccu"; reg = <0x01f01400 0x100>; clocks = <&osc24M>, <&osc32k>, <&iosc>; clock-names = "hosc", "losc", "iosc"; diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c index cf062472e07bcb..2b913f17d50f5d 100644 --- a/arch/arm/common/mcpm_entry.c +++ b/arch/arm/common/mcpm_entry.c @@ -235,7 +235,7 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster) return ret; } -typedef void (*phys_reset_t)(unsigned long); +typedef typeof(cpu_reset) phys_reset_t; void mcpm_cpu_power_down(void) { @@ -300,7 +300,7 @@ void mcpm_cpu_power_down(void) * on the CPU. */ phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset); - phys_reset(__pa_symbol(mcpm_entry_point)); + phys_reset(__pa_symbol(mcpm_entry_point), false); /* should never get here */ BUG(); @@ -389,7 +389,7 @@ static int __init nocache_trampoline(unsigned long _arg) __mcpm_cpu_down(cpu, cluster); phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset); - phys_reset(__pa_symbol(mcpm_entry_point)); + phys_reset(__pa_symbol(mcpm_entry_point), false); BUG(); } diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 6dc661c4a2c1a9..960d55445e0507 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -265,6 +265,12 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y CONFIG_DEBUG_USER=y +CONFIG_CRYPTO_USER=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m +CONFIG_CRYPTO_DEV_EXYNOS_RNG=y CONFIG_CRYPTO_DEV_S5P=y CONFIG_ARM_CRYPTO=y CONFIG_CRYPTO_SHA1_ARM_NEON=m diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index bb6fa568b62002..bf1e7e31691802 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -55,6 +55,9 @@ CONFIG_CMDLINE="noinitrd console=ttymxc0,115200" CONFIG_KEXEC=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_ARM_IMX6Q_CPUFREQ=y CONFIG_CPU_IDLE=y CONFIG_VFP=y diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig index 6ba430d2b5b257..e15fa5f168bba0 100644 --- a/arch/arm/configs/lpc32xx_defconfig +++ b/arch/arm/configs/lpc32xx_defconfig @@ -112,7 +112,7 @@ CONFIG_GPIO_SX150X=y CONFIG_GPIO_74X164=y CONFIG_GPIO_MAX7301=y CONFIG_GPIO_MC33880=y -CONFIG_GPIO_MCP23S08=y +CONFIG_PINCTRL_MCP23S08=y CONFIG_SENSORS_DS620=y CONFIG_SENSORS_MAX6639=y CONFIG_WATCHDOG=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 2685e03600b11b..60c0c01002c2cc 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -257,6 +257,7 @@ CONFIG_SMSC911X=y CONFIG_STMMAC_ETH=y CONFIG_STMMAC_PLATFORM=y CONFIG_DWMAC_DWC_QOS_ETH=y +CONFIG_DWMAC_SUN8I=y CONFIG_TI_CPSW=y CONFIG_XILINX_EMACLITE=y CONFIG_AT803X_PHY=y @@ -935,7 +936,13 @@ CONFIG_CPUFREQ_DT=y CONFIG_KEYSTONE_IRQ=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_ST=y +CONFIG_CRYPTO_USER=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_DEV_MARVELL_CESA=m +CONFIG_CRYPTO_DEV_EXYNOS_RNG=m CONFIG_CRYPTO_DEV_S5P=m CONFIG_CRYPTO_DEV_SUN4I_SS=m CONFIG_CRYPTO_DEV_ROCKCHIP=m diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig index f1a0e2503cbe4a..69553704f2dc3a 100644 --- a/arch/arm/configs/mvebu_v7_defconfig +++ b/arch/arm/configs/mvebu_v7_defconfig @@ -135,6 +135,8 @@ CONFIG_DMADEVICES=y CONFIG_MV_XOR=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_MEMORY=y +CONFIG_PWM=y +CONFIG_SENSORS_PWM_FAN=y CONFIG_EXT4_FS=y CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 6e0f751be2293e..aef2b54a691c6e 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -8,6 +8,7 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUPS=y # CONFIG_UTS_NS is not set # CONFIG_IPC_NS is not set # CONFIG_PID_NS is not set @@ -75,6 +76,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_TOUCHSCREEN_MXS_LRADC=y CONFIG_TOUCHSCREEN_TSC2007=m # CONFIG_SERIO is not set CONFIG_DEVPTS_MULTIPLE_INSTANCES=y @@ -95,6 +97,7 @@ CONFIG_GPIO_SYSFS=y # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_STMP3XXX_RTC_WATCHDOG=y +CONFIG_MFD_MXS_LRADC=y CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_FB=y @@ -136,10 +139,9 @@ CONFIG_RTC_DRV_DS1307=m CONFIG_RTC_DRV_STMP=y CONFIG_DMADEVICES=y CONFIG_MXS_DMA=y -CONFIG_STAGING=y -CONFIG_MXS_LRADC=y CONFIG_IIO=y CONFIG_IIO_SYSFS_TRIGGER=y +CONFIG_MXS_LRADC_ADC=y CONFIG_PWM=y CONFIG_PWM_MXS=y CONFIG_NVMEM=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 777c9e98642555..e04494b830ab18 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -3,6 +3,8 @@ CONFIG_SYSVIPC=y CONFIG_FHANDLE=y CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y CONFIG_BLK_DEV_INITRD=y @@ -52,6 +54,7 @@ CONFIG_IP_PNP_RARP=y CONFIG_IPV6_SIT_6RD=y CONFIG_CAN=y CONFIG_CAN_AT91=y +CONFIG_CAN_M_CAN=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 5cd5dd70bc8365..504e0223803143 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -40,6 +40,7 @@ CONFIG_ATA=y CONFIG_AHCI_SUNXI=y CONFIG_NETDEVICES=y CONFIG_SUN4I_EMAC=y +CONFIG_DWMAC_SUN8I=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index 883b84d828c5ac..0f966a8ca1cef5 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -425,9 +426,6 @@ static int __init aes_init(void) int err; int i; - if (!(elf_hwcap2 & HWCAP2_AES)) - return -ENODEV; - err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs)); if (err) return err; @@ -451,5 +449,5 @@ static int __init aes_init(void) return err; } -module_init(aes_init); +module_cpu_feature_match(AES, aes_init); module_exit(aes_exit); diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c index e1566bec1016ee..1b0e0e86ee9c20 100644 --- a/arch/arm/crypto/crc32-ce-glue.c +++ b/arch/arm/crypto/crc32-ce-glue.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ +#include #include #include #include @@ -233,6 +234,11 @@ static void __exit crc32_pmull_mod_exit(void) ARRAY_SIZE(crc32_pmull_algs)); } +static const struct cpu_feature crc32_cpu_feature[] = { + { cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { } +}; +MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature); + module_init(crc32_pmull_mod_init); module_exit(crc32_pmull_mod_exit); diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c index 7546b3c024665e..6bac8bea9f1e8e 100644 --- a/arch/arm/crypto/ghash-ce-glue.c +++ b/arch/arm/crypto/ghash-ce-glue.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -311,9 +312,6 @@ static int __init ghash_ce_mod_init(void) { int err; - if (!(elf_hwcap2 & HWCAP2_PMULL)) - return -ENODEV; - err = crypto_register_shash(&ghash_alg); if (err) return err; @@ -334,5 +332,5 @@ static void __exit ghash_ce_mod_exit(void) crypto_unregister_shash(&ghash_alg); } -module_init(ghash_ce_mod_init); +module_cpu_feature_match(PMULL, ghash_ce_mod_init); module_exit(ghash_ce_mod_exit); diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c index 80bc2fcd241a36..555f72b5e659bb 100644 --- a/arch/arm/crypto/sha1-ce-glue.c +++ b/arch/arm/crypto/sha1-ce-glue.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -82,8 +83,6 @@ static struct shash_alg alg = { static int __init sha1_ce_mod_init(void) { - if (!(elf_hwcap2 & HWCAP2_SHA1)) - return -ENODEV; return crypto_register_shash(&alg); } @@ -92,5 +91,5 @@ static void __exit sha1_ce_mod_fini(void) crypto_unregister_shash(&alg); } -module_init(sha1_ce_mod_init); +module_cpu_feature_match(SHA1, sha1_ce_mod_init); module_exit(sha1_ce_mod_fini); diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c index 0755b2d657f347..df4dcef054aea4 100644 --- a/arch/arm/crypto/sha2-ce-glue.c +++ b/arch/arm/crypto/sha2-ce-glue.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -100,8 +101,6 @@ static struct shash_alg algs[] = { { static int __init sha2_ce_mod_init(void) { - if (!(elf_hwcap2 & HWCAP2_SHA2)) - return -ENODEV; return crypto_register_shashes(algs, ARRAY_SIZE(algs)); } @@ -110,5 +109,5 @@ static void __exit sha2_ce_mod_fini(void) crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); } -module_init(sha2_ce_mod_init); +module_cpu_feature_match(SHA2, sha2_ce_mod_init); module_exit(sha2_ce_mod_fini); diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index 36ec9c8f6e161d..3234fe9bba6e76 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -19,7 +19,8 @@ struct dev_archdata { #ifdef CONFIG_XEN const struct dma_map_ops *dev_dma_ops; #endif - bool dma_coherent; + unsigned int dma_coherent:1; + unsigned int dma_ops_setup:1; }; struct omap_device; diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h index 302240c19a5aa6..a0d726a47c8a27 100644 --- a/arch/arm/include/asm/pgtable-nommu.h +++ b/arch/arm/include/asm/pgtable-nommu.h @@ -66,6 +66,7 @@ typedef pte_t *pte_addr_t; #define pgprot_noncached(prot) (prot) #define pgprot_writecombine(prot) (prot) #define pgprot_dmacoherent(prot) (prot) +#define pgprot_device(prot) (prot) /* diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index be3b3fbd382fbb..63cb4c7c6593d6 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -1090,7 +1090,7 @@ static int __init arch_hw_breakpoint_init(void) * driven low on this core and there isn't an architected way to * determine that. */ - get_online_cpus(); + cpus_read_lock(); register_undef_hook(&debug_reg_hook); /* @@ -1098,15 +1098,16 @@ static int __init arch_hw_breakpoint_init(void) * assume that a halting debugger will leave the world in a nice state * for us. */ - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm/hw_breakpoint:online", - dbg_reset_online, NULL); + ret = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN, + "arm/hw_breakpoint:online", + dbg_reset_online, NULL); unregister_undef_hook(&debug_reg_hook); if (WARN_ON(ret < 0) || !cpumask_empty(&debug_err_mask)) { core_num_brps = 0; core_num_wrps = 0; if (ret > 0) cpuhp_remove_state_nocalls(ret); - put_online_cpus(); + cpus_read_unlock(); return 0; } @@ -1124,7 +1125,7 @@ static int __init arch_hw_breakpoint_init(void) TRAP_HWBKPT, "watchpoint debug exception"); hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT, "breakpoint debug exception"); - put_online_cpus(); + cpus_read_unlock(); /* Register PM notifiers. */ pm_init(); diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index 020560b2dcb78a..a1a34722c655a6 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -124,5 +124,5 @@ void __kprobes patch_text(void *addr, unsigned int insn) .insn = insn, }; - stop_machine(patch_text_stop_machine, &patch, NULL); + stop_machine_cpuslocked(patch_text_stop_machine, &patch, NULL); } diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 939e8b58c59d1e..151cece4a293e5 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -123,10 +123,10 @@ void __show_regs(struct pt_regs *regs) print_symbol("PC is at %s\n", instruction_pointer(regs)); print_symbol("LR is at %s\n", regs->ARM_lr); - printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n" - "sp : %08lx ip : %08lx fp : %08lx\n", - regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr, - regs->ARM_sp, regs->ARM_ip, regs->ARM_fp); + printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n", + regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr); + printk("sp : %08lx ip : %08lx fp : %08lx\n", + regs->ARM_sp, regs->ARM_ip, regs->ARM_fp); printk("r10: %08lx r9 : %08lx r8 : %08lx\n", regs->ARM_r10, regs->ARM_r9, regs->ARM_r8); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 572a8df1b7662d..c9a0a529982793 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -555,8 +555,7 @@ static DEFINE_RAW_SPINLOCK(stop_lock); */ static void ipi_cpu_stop(unsigned int cpu) { - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) { + if (system_state <= SYSTEM_RUNNING) { raw_spin_lock(&stop_lock); pr_crit("CPU%u: stopping\n", cpu); dump_stack(); diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h index f1ead0f13c19e0..e2bd1723796485 100644 --- a/arch/arm/mach-at91/generic.h +++ b/arch/arm/mach-at91/generic.h @@ -15,10 +15,12 @@ extern void __init at91rm9200_pm_init(void); extern void __init at91sam9_pm_init(void); extern void __init sama5_pm_init(void); +extern void __init sama5d2_pm_init(void); #else static inline void __init at91rm9200_pm_init(void) { } static inline void __init at91sam9_pm_init(void) { } static inline void __init sama5_pm_init(void) { } +static inline void __init sama5d2_pm_init(void) { } #endif #endif /* _AT91_GENERIC_H */ diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 283e79ab587de9..667fddac38561e 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -22,6 +23,7 @@ #include #include #include +#include #include "generic.h" #include "pm.h" @@ -37,7 +39,17 @@ extern void at91_pinctrl_gpio_suspend(void); extern void at91_pinctrl_gpio_resume(void); #endif -static struct at91_pm_data pm_data; +static const match_table_t pm_modes __initconst = { + { 0, "standby" }, + { AT91_PM_SLOW_CLOCK, "ulp0" }, + { AT91_PM_BACKUP, "backup" }, + { -1, NULL }, +}; + +static struct at91_pm_data pm_data = { + .standby_mode = 0, + .suspend_mode = AT91_PM_SLOW_CLOCK, +}; #define at91_ramc_read(id, field) \ __raw_readl(pm_data.ramc[id] + field) @@ -58,15 +70,33 @@ static int at91_pm_valid_state(suspend_state_t state) } } +static int canary = 0xA5A5A5A5; -static suspend_state_t target_state; +static struct at91_pm_bu { + int suspended; + unsigned long reserved; + phys_addr_t canary; + phys_addr_t resume; +} *pm_bu; /* * Called after processes are frozen, but before we shutdown devices. */ static int at91_pm_begin(suspend_state_t state) { - target_state = state; + switch (state) { + case PM_SUSPEND_MEM: + pm_data.mode = pm_data.suspend_mode; + break; + + case PM_SUSPEND_STANDBY: + pm_data.mode = pm_data.standby_mode; + break; + + default: + pm_data.mode = -1; + } + return 0; } @@ -115,7 +145,7 @@ static int at91_pm_verify_clocks(void) */ int at91_suspend_entering_slow_clock(void) { - return (target_state == PM_SUSPEND_MEM); + return (pm_data.mode >= AT91_PM_SLOW_CLOCK); } EXPORT_SYMBOL(at91_suspend_entering_slow_clock); @@ -123,50 +153,65 @@ static void (*at91_suspend_sram_fn)(struct at91_pm_data *); extern void at91_pm_suspend_in_sram(struct at91_pm_data *pm_data); extern u32 at91_pm_suspend_in_sram_sz; -static void at91_pm_suspend(suspend_state_t state) +static int at91_suspend_finish(unsigned long val) { - pm_data.mode = (state == PM_SUSPEND_MEM) ? AT91_PM_SLOW_CLOCK : 0; - flush_cache_all(); outer_disable(); at91_suspend_sram_fn(&pm_data); + return 0; +} + +static void at91_pm_suspend(suspend_state_t state) +{ + if (pm_data.mode == AT91_PM_BACKUP) { + pm_bu->suspended = 1; + + cpu_suspend(0, at91_suspend_finish); + + /* The SRAM is lost between suspend cycles */ + at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn, + &at91_pm_suspend_in_sram, + at91_pm_suspend_in_sram_sz); + } else { + at91_suspend_finish(0); + } + outer_resume(); } +/* + * STANDBY mode has *all* drivers suspended; ignores irqs not marked as 'wakeup' + * event sources; and reduces DRAM power. But otherwise it's identical to + * PM_SUSPEND_ON: cpu idle, and nothing fancy done with main or cpu clocks. + * + * AT91_PM_SLOW_CLOCK is like STANDBY plus slow clock mode, so drivers must + * suspend more deeply, the master clock switches to the clk32k and turns off + * the main oscillator + * + * AT91_PM_BACKUP turns off the whole SoC after placing the DDR in self refresh + */ static int at91_pm_enter(suspend_state_t state) { #ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_suspend(); #endif + switch (state) { - /* - * Suspend-to-RAM is like STANDBY plus slow clock mode, so - * drivers must suspend more deeply, the master clock switches - * to the clk32k and turns off the main oscillator - */ case PM_SUSPEND_MEM: + case PM_SUSPEND_STANDBY: /* * Ensure that clocks are in a valid state. */ - if (!at91_pm_verify_clocks()) + if ((pm_data.mode >= AT91_PM_SLOW_CLOCK) && + !at91_pm_verify_clocks()) goto error; at91_pm_suspend(state); break; - /* - * STANDBY mode has *all* drivers suspended; ignores irqs not - * marked as 'wakeup' event sources; and reduces DRAM power. - * But otherwise it's identical to PM_SUSPEND_ON: cpu idle, and - * nothing fancy done with main or cpu clocks. - */ - case PM_SUSPEND_STANDBY: - at91_pm_suspend(state); - break; - case PM_SUSPEND_ON: cpu_do_idle(); break; @@ -177,8 +222,6 @@ static int at91_pm_enter(suspend_state_t state) } error: - target_state = PM_SUSPEND_ON; - #ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_resume(); #endif @@ -190,7 +233,6 @@ static int at91_pm_enter(suspend_state_t state) */ static void at91_pm_end(void) { - target_state = PM_SUSPEND_ON; } @@ -436,6 +478,79 @@ static void __init at91_pm_sram_init(void) &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); } +static void __init at91_pm_backup_init(void) +{ + struct gen_pool *sram_pool; + struct device_node *np; + struct platform_device *pdev = NULL; + + if ((pm_data.standby_mode != AT91_PM_BACKUP) && + (pm_data.suspend_mode != AT91_PM_BACKUP)) + return; + + pm_bu = NULL; + + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-shdwc"); + if (!np) { + pr_warn("%s: failed to find shdwc!\n", __func__); + return; + } + + pm_data.shdwc = of_iomap(np, 0); + of_node_put(np); + + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-sfrbu"); + if (!np) { + pr_warn("%s: failed to find sfrbu!\n", __func__); + goto sfrbu_fail; + } + + pm_data.sfrbu = of_iomap(np, 0); + of_node_put(np); + pm_bu = NULL; + + np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam"); + if (!np) + goto securam_fail; + + pdev = of_find_device_by_node(np); + of_node_put(np); + if (!pdev) { + pr_warn("%s: failed to find securam device!\n", __func__); + goto securam_fail; + } + + sram_pool = gen_pool_get(&pdev->dev, NULL); + if (!sram_pool) { + pr_warn("%s: securam pool unavailable!\n", __func__); + goto securam_fail; + } + + pm_bu = (void *)gen_pool_alloc(sram_pool, sizeof(struct at91_pm_bu)); + if (!pm_bu) { + pr_warn("%s: unable to alloc securam!\n", __func__); + goto securam_fail; + } + + pm_bu->suspended = 0; + pm_bu->canary = virt_to_phys(&canary); + pm_bu->resume = virt_to_phys(cpu_resume); + + return; + +sfrbu_fail: + iounmap(pm_data.shdwc); + pm_data.shdwc = NULL; +securam_fail: + iounmap(pm_data.sfrbu); + pm_data.sfrbu = NULL; + + if (pm_data.standby_mode == AT91_PM_BACKUP) + pm_data.standby_mode = AT91_PM_SLOW_CLOCK; + if (pm_data.suspend_mode == AT91_PM_BACKUP) + pm_data.suspend_mode = AT91_PM_SLOW_CLOCK; +} + struct pmc_info { unsigned long uhp_udp_mask; }; @@ -481,10 +596,14 @@ static void __init at91_pm_init(void (*pm_idle)(void)) at91_pm_sram_init(); - if (at91_suspend_sram_fn) + if (at91_suspend_sram_fn) { suspend_set_ops(&at91_pm_ops); - else + pr_info("AT91: PM: standby: %s, suspend: %s\n", + pm_modes[pm_data.standby_mode].pattern, + pm_modes[pm_data.suspend_mode].pattern); + } else { pr_info("AT91: PM not supported, due to no SRAM allocated\n"); + } } void __init at91rm9200_pm_init(void) @@ -510,3 +629,34 @@ void __init sama5_pm_init(void) at91_dt_ramc(); at91_pm_init(NULL); } + +void __init sama5d2_pm_init(void) +{ + at91_pm_backup_init(); + sama5_pm_init(); +} + +static int __init at91_pm_modes_select(char *str) +{ + char *s; + substring_t args[MAX_OPT_ARGS]; + int standby, suspend; + + if (!str) + return 0; + + s = strsep(&str, ","); + standby = match_token(s, pm_modes, args); + if (standby < 0) + return 0; + + suspend = match_token(str, pm_modes, args); + if (suspend < 0) + return 0; + + pm_data.standby_mode = standby; + pm_data.suspend_mode = suspend; + + return 0; +} +early_param("atmel.pm_modes", at91_pm_modes_select); diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h index fc0f7d048187b6..f95d31496f08f4 100644 --- a/arch/arm/mach-at91/pm.h +++ b/arch/arm/mach-at91/pm.h @@ -22,6 +22,7 @@ #define AT91_MEMCTRL_DDRSDR 2 #define AT91_PM_SLOW_CLOCK 0x01 +#define AT91_PM_BACKUP 0x02 #ifndef __ASSEMBLY__ struct at91_pm_data { @@ -30,6 +31,10 @@ struct at91_pm_data { unsigned long uhp_udp_mask; unsigned int memctrl; unsigned int mode; + void __iomem *shdwc; + void __iomem *sfrbu; + unsigned int standby_mode; + unsigned int suspend_mode; }; #endif diff --git a/arch/arm/mach-at91/pm_data-offsets.c b/arch/arm/mach-at91/pm_data-offsets.c index 30302cb16df065..c0a73e62b7256b 100644 --- a/arch/arm/mach-at91/pm_data-offsets.c +++ b/arch/arm/mach-at91/pm_data-offsets.c @@ -9,5 +9,8 @@ int main(void) DEFINE(PM_DATA_RAMC1, offsetof(struct at91_pm_data, ramc[1])); DEFINE(PM_DATA_MEMCTRL, offsetof(struct at91_pm_data, memctrl)); DEFINE(PM_DATA_MODE, offsetof(struct at91_pm_data, mode)); + DEFINE(PM_DATA_SHDWC, offsetof(struct at91_pm_data, shdwc)); + DEFINE(PM_DATA_SFRBU, offsetof(struct at91_pm_data, sfrbu)); + return 0; } diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S index 96781daa671a33..daca91feea6a26 100644 --- a/arch/arm/mach-at91/pm_suspend.S +++ b/arch/arm/mach-at91/pm_suspend.S @@ -97,15 +97,61 @@ ENTRY(at91_pm_suspend_in_sram) str tmp1, .memtype ldr tmp1, [r0, #PM_DATA_MODE] str tmp1, .pm_mode + /* Both ldrne below are here to preload their address in the TLB */ + ldr tmp1, [r0, #PM_DATA_SHDWC] + str tmp1, .shdwc + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0] + ldr tmp1, [r0, #PM_DATA_SFRBU] + str tmp1, .sfr + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0x10] /* Active the self-refresh mode */ mov r0, #SRAMC_SELF_FRESH_ACTIVE bl at91_sramc_self_refresh ldr r0, .pm_mode - tst r0, #AT91_PM_SLOW_CLOCK - beq skip_disable_main_clock + cmp r0, #AT91_PM_SLOW_CLOCK + beq slow_clock + cmp r0, #AT91_PM_BACKUP + beq backup_mode + /* Wait for interrupt */ + ldr pmc, .pmc_base + at91_cpu_idle + b exit_suspend + +slow_clock: + bl at91_slowck_mode + b exit_suspend +backup_mode: + bl at91_backup_mode + b exit_suspend + +exit_suspend: + /* Exit the self-refresh mode */ + mov r0, #SRAMC_SELF_FRESH_EXIT + bl at91_sramc_self_refresh + + /* Restore registers, and return */ + ldmfd sp!, {r4 - r12, pc} +ENDPROC(at91_pm_suspend_in_sram) + +ENTRY(at91_backup_mode) + /*BUMEN*/ + ldr r0, .sfr + mov tmp1, #0x1 + str tmp1, [r0, #0x10] + + /* Shutdown */ + ldr r0, .shdwc + mov tmp1, #0xA5000000 + add tmp1, tmp1, #0x1 + str tmp1, [r0, #0] +ENDPROC(at91_backup_mode) + +ENTRY(at91_slowck_mode) ldr pmc, .pmc_base /* Save Master clock setting */ @@ -134,18 +180,9 @@ ENTRY(at91_pm_suspend_in_sram) orr tmp1, tmp1, #AT91_PMC_KEY str tmp1, [pmc, #AT91_CKGR_MOR] -skip_disable_main_clock: - ldr pmc, .pmc_base - /* Wait for interrupt */ at91_cpu_idle - ldr r0, .pm_mode - tst r0, #AT91_PM_SLOW_CLOCK - beq skip_enable_main_clock - - ldr pmc, .pmc_base - /* Turn on the main oscillator */ ldr tmp1, [pmc, #AT91_CKGR_MOR] orr tmp1, tmp1, #AT91_PMC_MOSCEN @@ -174,14 +211,8 @@ skip_disable_main_clock: wait_mckrdy -skip_enable_main_clock: - /* Exit the self-refresh mode */ - mov r0, #SRAMC_SELF_FRESH_EXIT - bl at91_sramc_self_refresh - - /* Restore registers, and return */ - ldmfd sp!, {r4 - r12, pc} -ENDPROC(at91_pm_suspend_in_sram) + mov pc, lr +ENDPROC(at91_slowck_mode) /* * void at91_sramc_self_refresh(unsigned int is_active) @@ -314,6 +345,10 @@ ENDPROC(at91_sramc_self_refresh) .word 0 .sramc1_base: .word 0 +.shdwc: + .word 0 +.sfr: + .word 0 .memtype: .word 0 .pm_mode: diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c index 6d157d0ead8e3d..3d0bf95a56ae3a 100644 --- a/arch/arm/mach-at91/sama5.c +++ b/arch/arm/mach-at91/sama5.c @@ -34,7 +34,6 @@ DT_MACHINE_START(sama5_dt, "Atmel SAMA5") MACHINE_END static const char *const sama5_alt_dt_board_compat[] __initconst = { - "atmel,sama5d2", "atmel,sama5d4", NULL }; @@ -45,3 +44,21 @@ DT_MACHINE_START(sama5_alt_dt, "Atmel SAMA5") .dt_compat = sama5_alt_dt_board_compat, .l2c_aux_mask = ~0UL, MACHINE_END + +static void __init sama5d2_init(void) +{ + of_platform_default_populate(NULL, NULL, NULL); + sama5d2_pm_init(); +} + +static const char *const sama5d2_compat[] __initconst = { + "atmel,sama5d2", + NULL +}; + +DT_MACHINE_START(sama5d2, "Atmel SAMA5") + /* Maintainer: Atmel */ + .init_machine = sama5d2_init, + .dt_compat = sama5d2_compat, + .l2c_aux_mask = ~0UL, +MACHINE_END diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c index 58075627c6df3e..f673cd7a676658 100644 --- a/arch/arm/mach-davinci/board-da830-evm.c +++ b/arch/arm/mach-davinci/board-da830-evm.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index 20f1874a5657e2..70e00dbeec9694 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index cb176826d1cbe4..ca69d0b96a4f07 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/arm/mach-davinci/pm.c b/arch/arm/mach-davinci/pm.c index efb80354f3034d..b5cc05dc2cb27c 100644 --- a/arch/arm/mach-davinci/pm.c +++ b/arch/arm/mach-davinci/pm.c @@ -153,7 +153,8 @@ int __init davinci_pm_init(void) davinci_sram_suspend = sram_alloc(davinci_cpu_suspend_sz, NULL); if (!davinci_sram_suspend) { pr_err("PM: cannot allocate SRAM memory\n"); - return -ENOMEM; + ret = -ENOMEM; + goto no_sram_mem; } davinci_sram_push(davinci_sram_suspend, davinci_cpu_suspend, @@ -161,6 +162,10 @@ int __init davinci_pm_init(void) suspend_set_ops(&davinci_pm_ops); + return 0; + +no_sram_mem: + iounmap(pm_config.ddrpsc_reg_base); no_ddrpsc_mem: iounmap(pm_config.ddrpll_reg_base); no_ddrpll_mem: diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index 936c59d0e18be4..782699e6760006 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -536,6 +536,7 @@ config SOC_IMX7D select HAVE_IMX_ANATOP select HAVE_IMX_MMDC select HAVE_IMX_SRC + select IMX_GPCV2 help This enables support for Freescale i.MX7 Dual processor. diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c index 6c52bd32610e10..e48cc06c2aec04 100644 --- a/arch/arm/mach-lpc32xx/phy3250.c +++ b/arch/arm/mach-lpc32xx/phy3250.c @@ -137,6 +137,9 @@ static void pl08x_put_signal(const struct pl08x_channel_data *cd, int ch) } static struct pl08x_platform_data pl08x_pd = { + /* Some reasonable memcpy defaults */ + .memcpy_burst_size = PL08X_BURST_SZ_256, + .memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS, .slave_channels = &pl08x_slave_channels[0], .num_slave_channels = ARRAY_SIZE(pl08x_slave_channels), .get_xfer_signal = pl08x_get_signal, diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 369f95a703ac0a..33ed5d53fa459d 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -58,6 +58,17 @@ static unsigned int irq_banks = DEFAULT_NR_REG_BANKS; static unsigned int max_irqs = DEFAULT_IRQS; static unsigned int omap_secure_apis; +#ifdef CONFIG_CPU_PM +static unsigned int wakeupgen_context[MAX_NR_REG_BANKS]; +#endif + +struct omap_wakeupgen_ops { + void (*save_context)(void); + void (*restore_context)(void); +}; + +static struct omap_wakeupgen_ops *wakeupgen_ops; + /* * Static helper functions. */ @@ -264,6 +275,16 @@ static inline void omap5_irq_save_context(void) } +static inline void am43xx_irq_save_context(void) +{ + u32 i; + + for (i = 0; i < irq_banks; i++) { + wakeupgen_context[i] = wakeupgen_readl(i, 0); + wakeupgen_writel(0, i, CPU0_ID); + } +} + /* * Save WakeupGen interrupt context in SAR BANK3. Restore is done by * ROM code. WakeupGen IP is integrated along with GIC to manage the @@ -280,11 +301,8 @@ static void irq_save_context(void) if (!sar_base) sar_base = omap4_get_sar_ram_base(); - - if (soc_is_omap54xx()) - omap5_irq_save_context(); - else - omap4_irq_save_context(); + if (wakeupgen_ops && wakeupgen_ops->save_context) + wakeupgen_ops->save_context(); } /* @@ -306,6 +324,20 @@ static void irq_sar_clear(void) writel_relaxed(val, sar_base + offset); } +static void am43xx_irq_restore_context(void) +{ + u32 i; + + for (i = 0; i < irq_banks; i++) + wakeupgen_writel(wakeupgen_context[i], i, CPU0_ID); +} + +static void irq_restore_context(void) +{ + if (wakeupgen_ops && wakeupgen_ops->restore_context) + wakeupgen_ops->restore_context(); +} + /* * Save GIC and Wakeupgen interrupt context using secure API * for HS/EMU devices. @@ -319,6 +351,26 @@ static void irq_save_secure_context(void) if (ret != API_HAL_RET_VALUE_OK) pr_err("GIC and Wakeupgen context save failed\n"); } + +/* Define ops for context save and restore for each SoC */ +static struct omap_wakeupgen_ops omap4_wakeupgen_ops = { + .save_context = omap4_irq_save_context, + .restore_context = irq_sar_clear, +}; + +static struct omap_wakeupgen_ops omap5_wakeupgen_ops = { + .save_context = omap5_irq_save_context, + .restore_context = irq_sar_clear, +}; + +static struct omap_wakeupgen_ops am43xx_wakeupgen_ops = { + .save_context = am43xx_irq_save_context, + .restore_context = am43xx_irq_restore_context, +}; +#else +static struct omap_wakeupgen_ops omap4_wakeupgen_ops = {}; +static struct omap_wakeupgen_ops omap5_wakeupgen_ops = {}; +static struct omap_wakeupgen_ops am43xx_wakeupgen_ops = {}; #endif #ifdef CONFIG_HOTPLUG_CPU @@ -359,7 +411,7 @@ static int irq_notifier(struct notifier_block *self, unsigned long cmd, void *v) break; case CPU_CLUSTER_PM_EXIT: if (omap_type() == OMAP2_DEVICE_TYPE_GP) - irq_sar_clear(); + irq_restore_context(); break; } return NOTIFY_OK; @@ -494,9 +546,13 @@ static int __init wakeupgen_init(struct device_node *node, irq_banks = OMAP4_NR_BANKS; max_irqs = OMAP4_NR_IRQS; omap_secure_apis = 1; + wakeupgen_ops = &omap4_wakeupgen_ops; + } else if (soc_is_omap54xx()) { + wakeupgen_ops = &omap5_wakeupgen_ops; } else if (soc_is_am43xx()) { irq_banks = AM43XX_NR_REG_BANKS; max_irqs = AM43XX_IRQS; + wakeupgen_ops = &am43xx_wakeupgen_ops; } domain = irq_domain_add_hierarchy(parent_domain, 0, max_irqs, diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 63027e60cc209f..366158a54fcd8b 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -71,7 +71,7 @@ void omap_pm_get_oscillator(u32 *tstart, u32 *tshut) } #endif -int __init omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused) +int omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused) { clkdm_allow_idle(clkdm); return 0; diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 07dd692c47372f..70670dfd71359a 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -68,6 +68,9 @@ static struct omap_dm_timer clkev; static struct clock_event_device clockevent_gpt; +/* Clockevent hwmod for am335x and am437x suspend */ +static struct omap_hwmod *clockevent_gpt_hwmod; + #ifdef CONFIG_SOC_HAS_REALTIME_COUNTER static unsigned long arch_timer_freq; @@ -125,6 +128,23 @@ static int omap2_gp_timer_set_periodic(struct clock_event_device *evt) return 0; } +static void omap_clkevt_idle(struct clock_event_device *unused) +{ + if (!clockevent_gpt_hwmod) + return; + + omap_hwmod_idle(clockevent_gpt_hwmod); +} + +static void omap_clkevt_unidle(struct clock_event_device *unused) +{ + if (!clockevent_gpt_hwmod) + return; + + omap_hwmod_enable(clockevent_gpt_hwmod); + __omap_dm_timer_int_enable(&clkev, OMAP_TIMER_INT_OVERFLOW); +} + static struct clock_event_device clockevent_gpt = { .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, @@ -358,6 +378,14 @@ static void __init omap2_gp_clockevent_init(int gptimer_id, 3, /* Timer internal resynch latency */ 0xffffffff); + if (soc_is_am33xx() || soc_is_am43xx()) { + clockevent_gpt.suspend = omap_clkevt_idle; + clockevent_gpt.resume = omap_clkevt_unidle; + + clockevent_gpt_hwmod = + omap_hwmod_lookup(clockevent_gpt.name); + } + pr_info("OMAP clockevent source: %s at %lu Hz\n", clockevent_gpt.name, clkev.rate); } diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c index d452a49c039647..1467c1d1e54194 100644 --- a/arch/arm/mach-pxa/balloon3.c +++ b/arch/arm/mach-pxa/balloon3.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c index 051c554776a6e7..fae38fdc8d8e56 100644 --- a/arch/arm/mach-pxa/littleton.c +++ b/arch/arm/mach-pxa/littleton.c @@ -27,7 +27,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c index 7b6610e9dae46c..2d45d18b1a5e0a 100644 --- a/arch/arm/mach-pxa/stargate2.c +++ b/arch/arm/mach-pxa/stargate2.c @@ -26,7 +26,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c index ef0500a4c8ad75..927cf563ea47ba 100644 --- a/arch/arm/mach-rockchip/rockchip.c +++ b/arch/arm/mach-rockchip/rockchip.c @@ -70,6 +70,7 @@ static const char * const rockchip_board_dt_compat[] = { "rockchip,rk3188", "rockchip,rk3228", "rockchip,rk3288", + "rockchip,rv1108", NULL, }; diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig index 459214fa20b40b..5ee5ad74a3d674 100644 --- a/arch/arm/mach-s3c64xx/Kconfig +++ b/arch/arm/mach-s3c64xx/Kconfig @@ -40,7 +40,6 @@ config CPU_S3C6410 config S3C64XX_PL080 def_bool DMADEVICES - select ARM_AMBA select AMBA_PL08X config S3C64XX_SETUP_SDHCI diff --git a/arch/arm/mach-s3c64xx/pl080.c b/arch/arm/mach-s3c64xx/pl080.c index 261820a855ecfb..66fc774b70ec23 100644 --- a/arch/arm/mach-s3c64xx/pl080.c +++ b/arch/arm/mach-s3c64xx/pl080.c @@ -137,16 +137,10 @@ static const struct dma_slave_map s3c64xx_dma0_slave_map[] = { }; struct pl08x_platform_data s3c64xx_dma0_plat_data = { - .memcpy_channel = { - .bus_id = "memcpy", - .cctl_memcpy = - (PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT | - PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | - PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | - PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | - PL080_CONTROL_PROT_SYS), - }, + .memcpy_burst_size = PL08X_BURST_SZ_4, + .memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS, + .memcpy_prot_buff = true, + .memcpy_prot_cache = true, .lli_buses = PL08X_AHB1, .mem_buses = PL08X_AHB1, .get_xfer_signal = pl08x_get_xfer_signal, @@ -238,16 +232,10 @@ static const struct dma_slave_map s3c64xx_dma1_slave_map[] = { }; struct pl08x_platform_data s3c64xx_dma1_plat_data = { - .memcpy_channel = { - .bus_id = "memcpy", - .cctl_memcpy = - (PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT | - PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | - PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | - PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | - PL080_CONTROL_PROT_SYS), - }, + .memcpy_burst_size = PL08X_BURST_SZ_4, + .memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS, + .memcpy_prot_buff = true, + .memcpy_prot_cache = true, .lli_buses = PL08X_AHB1, .mem_buses = PL08X_AHB1, .get_xfer_signal = pl08x_get_xfer_signal, diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c index 23394ac76cf228..8537fcffe5a86e 100644 --- a/arch/arm/mach-spear/spear3xx.c +++ b/arch/arm/mach-spear/spear3xx.c @@ -44,16 +44,10 @@ struct pl022_ssp_controller pl022_plat_data = { /* dmac device registration */ struct pl08x_platform_data pl080_plat_data = { - .memcpy_channel = { - .bus_id = "memcpy", - .cctl_memcpy = - (PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \ - PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \ - PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \ - PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \ - PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | \ - PL080_CONTROL_PROT_SYS), - }, + .memcpy_burst_size = PL08X_BURST_SZ_16, + .memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS, + .memcpy_prot_buff = true, + .memcpy_prot_cache = true, .lli_buses = PL08X_AHB1, .mem_buses = PL08X_AHB1, .get_xfer_signal = pl080_get_signal, diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c index ccf3573b831c47..c5fc110134ba66 100644 --- a/arch/arm/mach-spear/spear6xx.c +++ b/arch/arm/mach-spear/spear6xx.c @@ -322,16 +322,10 @@ static struct pl08x_channel_data spear600_dma_info[] = { }; static struct pl08x_platform_data spear6xx_pl080_plat_data = { - .memcpy_channel = { - .bus_id = "memcpy", - .cctl_memcpy = - (PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \ - PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \ - PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \ - PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \ - PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | \ - PL080_CONTROL_PROT_SYS), - }, + .memcpy_burst_size = PL08X_BURST_SZ_16, + .memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS, + .memcpy_prot_buff = true, + .memcpy_prot_cache = true, .lli_buses = PL08X_AHB1, .mem_buses = PL08X_AHB1, .get_xfer_signal = pl080_get_signal, diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index c6c4c9c8824b0f..4f68659abe6c5a 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -679,7 +679,7 @@ config ARCH_DMA_ADDR_T_64BIT bool config ARM_THUMB - bool "Support Thumb user binaries" if !CPU_THUMBONLY + bool "Support Thumb user binaries" if !CPU_THUMBONLY && EXPERT depends on CPU_THUMB_CAPABLE default y help @@ -690,6 +690,10 @@ config ARM_THUMB instruction set resulting in smaller binaries at the expense of slightly less efficient code. + If this option is disabled, and you run userspace that switches to + Thumb mode, signal handling will not work correctly, resulting in + segmentation faults or illegal instruction aborts. + If you don't know what this all is, saying Y is a safe choice. config ARM_THUMBEE diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c742dfd2967bca..7cd2b198276f75 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2311,7 +2311,14 @@ int arm_iommu_attach_device(struct device *dev, } EXPORT_SYMBOL_GPL(arm_iommu_attach_device); -static void __arm_iommu_detach_device(struct device *dev) +/** + * arm_iommu_detach_device + * @dev: valid struct device pointer + * + * Detaches the provided device from a previously attached map. + * This voids the dma operations (dma_map_ops pointer) + */ +void arm_iommu_detach_device(struct device *dev) { struct dma_iommu_mapping *mapping; @@ -2324,22 +2331,10 @@ static void __arm_iommu_detach_device(struct device *dev) iommu_detach_device(mapping->domain, dev); kref_put(&mapping->kref, release_iommu_mapping); to_dma_iommu_mapping(dev) = NULL; + set_dma_ops(dev, NULL); pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } - -/** - * arm_iommu_detach_device - * @dev: valid struct device pointer - * - * Detaches the provided device from a previously attached map. - * This voids the dma operations (dma_map_ops pointer) - */ -void arm_iommu_detach_device(struct device *dev) -{ - __arm_iommu_detach_device(dev); - set_dma_ops(dev, NULL); -} EXPORT_SYMBOL_GPL(arm_iommu_detach_device); static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent) @@ -2379,8 +2374,9 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) if (!mapping) return; - __arm_iommu_detach_device(dev); + arm_iommu_detach_device(dev); arm_iommu_release_mapping(mapping); + set_dma_ops(dev, NULL); } #else @@ -2430,9 +2426,13 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, dev->dma_ops = xen_dma_ops; } #endif + dev->archdata.dma_ops_setup = true; } void arch_teardown_dma_ops(struct device *dev) { + if (!dev->archdata.dma_ops_setup) + return; + arm_teardown_iommu_dma_ops(dev); } diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index ad1f4e6a9e3393..52d1cd14fda45d 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -182,7 +182,8 @@ void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn) .addr = addr, .insn = insn, }; - stop_machine(__kprobes_remove_breakpoint, &p, cpu_online_mask); + stop_machine_cpuslocked(__kprobes_remove_breakpoint, &p, + cpu_online_mask); } void __kprobes arch_disarm_kprobe(struct kprobe *p) diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 73272f43ca012f..b4e919ac73f665 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -126,6 +126,12 @@ config ARCH_QCOM help This enables support for the ARMv8 based Qualcomm chipsets. +config ARCH_REALTEK + bool "Realtek Platforms" + help + This enables support for the ARMv8 based Realtek chipsets, + like the RTD1295. + config ARCH_ROCKCHIP bool "Rockchip Platforms" select ARCH_HAS_RESET_CONTROLLER diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile index 080232b0270eaf..78f7991a5906fb 100644 --- a/arch/arm64/boot/dts/Makefile +++ b/arch/arm64/boot/dts/Makefile @@ -14,6 +14,7 @@ dts-dirs += marvell dts-dirs += mediatek dts-dirs += nvidia dts-dirs += qcom +dts-dirs += realtek dts-dirs += renesas dts-dirs += rockchip dts-dirs += socionext diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile index 244e8b7565f9b5..546720096aefcf 100644 --- a/arch/arm64/boot/dts/allwinner/Makefile +++ b/arch/arm64/boot/dts/allwinner/Makefile @@ -1,6 +1,8 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-bananapi-m64.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-pine64-plus.dtb sun50i-a64-pine64.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h5-orangepi-pc2.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h5-orangepi-prime.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h5-nanopi-neo2.dtb always := $(dtb-y) subdir-y := $(dts-dirs) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 6872135d7f849b..0d1f026d831aac 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -67,6 +67,14 @@ }; }; +&emac { + pinctrl-names = "default"; + pinctrl-0 = <&rgmii_pins>; + phy-mode = "rgmii"; + phy-handle = <&ext_rgmii_phy>; + status = "okay"; +}; + &i2c1 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; @@ -77,6 +85,13 @@ bias-pull-up; }; +&mdio { + ext_rgmii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; +}; + &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index 790d14daaa6a68..24f1aac366d643 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -46,5 +46,20 @@ model = "Pine64+"; compatible = "pine64,pine64-plus", "allwinner,sun50i-a64"; - /* TODO: Camera, Ethernet PHY, touchscreen, etc. */ + /* TODO: Camera, touchscreen, etc. */ +}; + +&emac { + pinctrl-names = "default"; + pinctrl-0 = <&rgmii_pins>; + phy-mode = "rgmii"; + phy-handle = <&ext_rgmii_phy>; + status = "okay"; +}; + +&mdio { + ext_rgmii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts index c680ed385da356..08cda24ea194cb 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts @@ -52,6 +52,10 @@ aliases { serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; }; chosen { @@ -66,10 +70,23 @@ }; }; +&ehci0 { + status = "okay"; +}; + &ehci1 { status = "okay"; }; +&emac { + pinctrl-names = "default"; + pinctrl-0 = <&rmii_pins>; + phy-mode = "rmii"; + phy-handle = <&ext_rmii_phy1>; + status = "okay"; + +}; + &i2c1 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; @@ -80,6 +97,13 @@ bias-pull-up; }; +&mdio { + ext_rmii_phy1: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; +}; + &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; @@ -91,16 +115,49 @@ status = "okay"; }; +&ohci0 { + status = "okay"; +}; + &ohci1 { status = "okay"; }; +/* On Exp and Euler connectors */ &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins_a>; status = "okay"; }; +/* On Wifi/BT connector, with RTS/CTS */ +&uart1 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins>, <&uart1_rts_cts_pins>; + status = "disabled"; +}; + +/* On Pi-2 connector */ +&uart2 { + pinctrl-names = "default"; + pinctrl-0 = <&uart2_pins>; + status = "disabled"; +}; + +/* On Euler connector */ +&uart3 { + pinctrl-names = "default"; + pinctrl-0 = <&uart3_pins>; + status = "disabled"; +}; + +/* On Euler connector, RTS/CTS optional */ +&uart4 { + pinctrl-names = "default"; + pinctrl-0 = <&uart4_pins>; + status = "disabled"; +}; + &usb_otg { dr_mode = "host"; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index c7f669f5884f91..7a07353ac1f631 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -129,6 +129,12 @@ #size-cells = <1>; ranges; + syscon: syscon@1c00000 { + compatible = "allwinner,sun50i-a64-system-controller", + "syscon"; + reg = <0x01c00000 0x1000>; + }; + mmc0: mmc@1c0f000 { compatible = "allwinner,sun50i-a64-mmc"; reg = <0x01c0f000 0x1000>; @@ -204,6 +210,28 @@ #phy-cells = <1>; }; + ehci0: usb@01c1a000 { + compatible = "allwinner,sun50i-a64-ehci", "generic-ehci"; + reg = <0x01c1a000 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI0>, + <&ccu CLK_BUS_EHCI0>, + <&ccu CLK_USB_OHCI0>; + resets = <&ccu RST_BUS_OHCI0>, + <&ccu RST_BUS_EHCI0>; + status = "disabled"; + }; + + ohci0: usb@01c1a400 { + compatible = "allwinner,sun50i-a64-ohci", "generic-ohci"; + reg = <0x01c1a400 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI0>, + <&ccu CLK_USB_OHCI0>; + resets = <&ccu RST_BUS_OHCI0>; + status = "disabled"; + }; + ehci1: usb@01c1b000 { compatible = "allwinner,sun50i-a64-ehci", "generic-ehci"; reg = <0x01c1b000 0x100>; @@ -281,6 +309,21 @@ bias-pull-up; }; + rmii_pins: rmii_pins { + pins = "PD10", "PD11", "PD13", "PD14", "PD17", + "PD18", "PD19", "PD20", "PD22", "PD23"; + function = "emac"; + drive-strength = <40>; + }; + + rgmii_pins: rgmii_pins { + pins = "PD8", "PD9", "PD10", "PD11", "PD12", + "PD13", "PD15", "PD16", "PD17", "PD18", + "PD19", "PD20", "PD21", "PD22", "PD23"; + function = "emac"; + drive-strength = <40>; + }; + uart0_pins_a: uart0@0 { pins = "PB8", "PB9"; function = "uart0"; @@ -295,6 +338,26 @@ pins = "PG8", "PG9"; function = "uart1"; }; + + uart2_pins: uart2-pins { + pins = "PB0", "PB1"; + function = "uart2"; + }; + + uart3_pins: uart3-pins { + pins = "PD0", "PD1"; + function = "uart3"; + }; + + uart4_pins: uart4-pins { + pins = "PD2", "PD3"; + function = "uart4"; + }; + + uart4_rts_cts_pins: uart4-rts-cts-pins { + pins = "PD4", "PD5"; + function = "uart4"; + }; }; uart0: serial@1c28000 { @@ -385,6 +448,26 @@ #size-cells = <0>; }; + emac: ethernet@1c30000 { + compatible = "allwinner,sun50i-a64-emac"; + syscon = <&syscon>; + reg = <0x01c30000 0x100>; + interrupts = ; + interrupt-names = "macirq"; + resets = <&ccu RST_BUS_EMAC>; + reset-names = "stmmaceth"; + clocks = <&ccu CLK_BUS_EMAC>; + clock-names = "stmmaceth"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + + mdio: mdio { + #address-cells = <1>; + #size-cells = <0>; + }; + }; + gic: interrupt-controller@1c81000 { compatible = "arm,gic-400"; reg = <0x01c81000 0x1000>, @@ -422,6 +505,25 @@ #gpio-cells = <3>; interrupt-controller; #interrupt-cells = <3>; + + r_rsb_pins: rsb@0 { + pins = "PL0", "PL1"; + function = "s_rsb"; + }; + }; + + r_rsb: rsb@1f03400 { + compatible = "allwinner,sun8i-a23-rsb"; + reg = <0x01f03400 0x400>; + interrupts = ; + clocks = <&r_ccu 6>; + clock-frequency = <3000000>; + resets = <&r_ccu 2>; + pinctrl-names = "default"; + pinctrl-0 = <&r_rsb_pins>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; }; }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts new file mode 100644 index 00000000000000..f6d71b0d482a97 --- /dev/null +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts @@ -0,0 +1,134 @@ +/* + * Copyright (C) 2017 Icenowy Zheng + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include "sun50i-h5.dtsi" + +#include + +/ { + model = "FriendlyARM NanoPi NEO 2"; + compatible = "friendlyarm,nanopi-neo2", "allwinner,sun50i-h5"; + + reg_vcc3v3: vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + pwr { + label = "nanopi:green:pwr"; + gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; + default-state = "on"; + }; + + status { + label = "nanopi:blue:status"; + gpios = <&pio 0 10 GPIO_ACTIVE_HIGH>; + }; + }; + + reg_usb0_vbus: usb0-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb0-vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpio = <&r_pio 0 2 GPIO_ACTIVE_HIGH>; /* PL2 */ + status = "okay"; + }; +}; + +&ehci0 { + status = "okay"; +}; + +&ehci3 { + status = "okay"; +}; + +&mmc0 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; + vmmc-supply = <®_vcc3v3>; + bus-width = <4>; + cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */ + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&ohci3 { + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins_a>; + status = "okay"; +}; + +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + +&usbphy { + /* USB Type-A port's VBUS is always on */ + usb0_id_det-gpios = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */ + usb0_vbus-supply = <®_usb0_vbus>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts new file mode 100644 index 00000000000000..28d92a61232911 --- /dev/null +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -0,0 +1,205 @@ +/* + * Copyright (C) 2017 Icenowy Zheng + * + * Based on sun50i-h5-orangepi-pc2.dts, which is: + * Copyright (C) 2016 ARM Ltd. + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include "sun50i-h5.dtsi" + +#include +#include + +/ { + model = "Xunlong Orange Pi Prime"; + compatible = "xunlong,orangepi-prime", "allwinner,sun50i-h5"; + + reg_vcc3v3: vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + pwr { + label = "orangepi:green:pwr"; + gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; + default-state = "on"; + }; + + status { + label = "orangepi:red:status"; + gpios = <&pio 0 20 GPIO_ACTIVE_HIGH>; + }; + }; + + r-gpio-keys { + compatible = "gpio-keys"; + + sw4 { + label = "sw4"; + linux,code = ; + gpios = <&r_pio 0 3 GPIO_ACTIVE_LOW>; + }; + }; + + reg_usb0_vbus: usb0-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb0-vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + enable-active-high; + gpio = <&r_pio 0 2 GPIO_ACTIVE_HIGH>; /* PL2 */ + status = "okay"; + }; + + wifi_pwrseq: wifi_pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 2 14 GPIO_ACTIVE_LOW>; /* PC14 */ + }; +}; + +&codec { + allwinner,audio-routing = + "Line Out", "LINEOUT", + "MIC1", "Mic", + "Mic", "MBIAS"; + status = "okay"; +}; + +&ehci0 { + status = "okay"; +}; + +&ehci1 { + status = "okay"; +}; + +&ehci2 { + status = "okay"; +}; + +&ehci3 { + status = "okay"; +}; + +&ir { + pinctrl-names = "default"; + pinctrl-0 = <&ir_pins_a>; + status = "okay"; +}; + +&mmc0 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; + vmmc-supply = <®_vcc3v3>; + bus-width = <4>; + cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */ + status = "okay"; +}; + +&mmc1 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins_a>; + vmmc-supply = <®_vcc3v3>; + mmc-pwrseq = <&wifi_pwrseq>; + bus-width = <4>; + non-removable; + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&ohci1 { + status = "okay"; +}; + +&ohci2 { + status = "okay"; +}; + +&ohci3 { + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins_a>; + status = "okay"; +}; + +&uart1 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins>; + status = "disabled"; +}; + +&uart2 { + pinctrl-names = "default"; + pinctrl-0 = <&uart2_pins>; + status = "disabled"; +}; + +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + +&usbphy { + /* USB Type-A ports' VBUS is always on */ + usb0_id_det-gpios = <&pio 0 21 GPIO_ACTIVE_HIGH>; /* PA21 */ + usb0_vbus-supply = <®_usb0_vbus>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi index 4d314a253fd9e0..732e2e06f503c8 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi @@ -40,7 +40,7 @@ * OTHER DEALINGS IN THE SOFTWARE. */ -#include "sunxi-h3-h5.dtsi" +#include / { cpus { diff --git a/arch/arm64/boot/dts/amlogic/Makefile b/arch/arm64/boot/dts/amlogic/Makefile index b9ad2db7398ba6..8a0e0925097868 100644 --- a/arch/arm64/boot/dts/amlogic/Makefile +++ b/arch/arm64/boot/dts/amlogic/Makefile @@ -1,3 +1,4 @@ +dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-nanopi-k2.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-nexbox-a95x.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-odroidc2.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-p200.dtb @@ -7,15 +8,16 @@ dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-vega-s95-meta.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-vega-s95-telos.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-wetek-hub.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-wetek-play2.dtb +dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-hwacom-amazetv.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-khadas-vim.dtb +dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-nexbox-a95x.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-p212.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p230.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p231.dtb -dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-hwacom-amazetv.dtb -dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-nexbox-a95x.dtb +dtb-$(CONFIG_ARCH_MESON) += meson-gxm-nexbox-a1.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q200.dtb dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q201.dtb -dtb-$(CONFIG_ARCH_MESON) += meson-gxm-nexbox-a1.dtb +dtb-$(CONFIG_ARCH_MESON) += meson-gxm-rbox-pro.dtb always := $(dtb-y) subdir-y := $(dts-dirs) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index a84e2762263972..dc478d094c113a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -121,19 +121,42 @@ }; }; -/* This UART is brought out to the DB9 connector */ -&uart_AO { +&cvbs_vdac_port { + cvbs_vdac_out: endpoint { + remote-endpoint = <&cvbs_connector_in>; + }; +}; + +ðmac { status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; +}; + +&hdmi_tx { + status = "okay"; + pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; pinctrl-names = "default"; }; +&hdmi_tx_tmds_port { + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; +}; + &ir { status = "okay"; pinctrl-0 = <&remote_input_ao_pins>; pinctrl-names = "default"; }; +&pwm_ef { + status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; +}; + /* Wireless SDIO Module */ &sd_emmc_a { status = "okay"; @@ -154,7 +177,7 @@ vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; }; @@ -198,32 +221,9 @@ vqmmc-supply = <&vddio_boot>; }; -&pwm_ef { - status = "okay"; - pinctrl-0 = <&pwm_e_pins>; - pinctrl-names = "default"; - clocks = <&clkc CLKID_FCLK_DIV4>; - clock-names = "clkin0"; -}; - -ðmac { - status = "okay"; -}; - -&cvbs_vdac_port { - cvbs_vdac_out: endpoint { - remote-endpoint = <&cvbs_connector_in>; - }; -}; - -&hdmi_tx { +/* This UART is brought out to the DB9 connector */ +&uart_AO { status = "okay"; - pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; }; - -&hdmi_tx_tmds_port { - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts new file mode 100644 index 00000000000000..fa462831ccaf45 --- /dev/null +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -0,0 +1,291 @@ +/* + * Copyright (c) 2017 Andreas Färber + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * SPDX-License-Identifier: (GPL-2.0+ OR MIT) + */ + +/dts-v1/; + +#include "meson-gxbb.dtsi" +#include + +/ { + compatible = "friendlyarm,nanopi-k2", "amlogic,meson-gxbb"; + + aliases { + serial0 = &uart_AO; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x80000000>; + }; + + leds { + compatible = "gpio-leds"; + + stat { + label = "nanopi-k2:blue:stat"; + gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_HIGH>; + default-state = "on"; + panic-indicator; + }; + }; + + vdd_5v: regulator-vdd-5v { + compatible = "regulator-fixed"; + regulator-name = "VDD_5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vddio_ao18: regulator-vddio-ao18 { + compatible = "regulator-fixed"; + regulator-name = "VDDIO_AO18"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + vddio_ao3v3: regulator-vddio-ao3v3 { + compatible = "regulator-fixed"; + regulator-name = "VDDIO_AO3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + vddio_tf: regulator-vddio-tf { + compatible = "regulator-gpio"; + + regulator-name = "VDDIO_TF"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + + gpios = <&gpio_ao GPIOAO_2 GPIO_ACTIVE_HIGH>; + gpios-states = <0>; + + states = <3300000 0>, + <1800000 1>; + }; + + wifi_32k: wifi-32k { + compatible = "pwm-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + pwms = <&pwm_ef 0 30518 0>; /* PWM_E at 32.768KHz */ + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&gpio GPIOX_6 GPIO_ACTIVE_LOW>; + clocks = <&wifi_32k>; + clock-names = "ext_clock"; + }; + + vcc1v8: regulator-vcc1v8 { + compatible = "regulator-fixed"; + regulator-name = "VCC1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + vcc3v3: regulator-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "VCC3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + emmc_pwrseq: emmc-pwrseq { + compatible = "mmc-pwrseq-emmc"; + reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>; + }; +}; + +ðmac { + status = "okay"; + pinctrl-0 = <ð_rgmii_pins>; + pinctrl-names = "default"; + + phy-handle = <ð_phy0>; + phy-mode = "rgmii"; + + amlogic,tx-delay-ns = <2>; + + snps,reset-gpio = <&gpio GPIOZ_14 0>; + snps,reset-delays-us = <0 10000 1000000>; + snps,reset-active-low; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + eth_phy0: ethernet-phy@0 { + /* Realtek RTL8211F (0x001cc916) */ + reg = <0>; + }; + }; +}; + +&ir { + status = "okay"; + pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-names = "default"; +}; + +&pwm_ef { + status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; +}; + +&saradc { + status = "okay"; + vref-supply = <&vddio_ao18>; +}; + +/* SDIO */ +&sd_emmc_a { + status = "okay"; + pinctrl-0 = <&sdio_pins>, <&sdio_irq_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + + bus-width = <4>; + cap-sd-highspeed; + max-frequency = <200000000>; + + non-removable; + disable-wp; + + mmc-pwrseq = <&sdio_pwrseq>; + + vmmc-supply = <&vddio_ao3v3>; + vqmmc-supply = <&vddio_ao18>; + + brcmf: wifi@1 { + compatible = "brcm,bcm4329-fmac"; + reg = <1>; + }; +}; + +/* SD */ +&sd_emmc_b { + status = "okay"; + pinctrl-0 = <&sdcard_pins>; + pinctrl-names = "default"; + + bus-width = <4>; + cap-sd-highspeed; + max-frequency = <100000000>; + disable-wp; + + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; + cd-inverted; + + vmmc-supply = <&vddio_ao3v3>; + vqmmc-supply = <&vddio_tf>; +}; + +/* eMMC */ +&sd_emmc_c { + status = "disabled"; + pinctrl-0 = <&emmc_pins>; + pinctrl-names = "default"; + + bus-width = <8>; + cap-sd-highspeed; + max-frequency = <200000000>; + non-removable; + disable-wp; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + + mmc-pwrseq = <&emmc_pwrseq>; + vmmc-supply = <&vcc3v3>; + vqmmc-supply = <&vcc1v8>; +}; + +/* DBG_UART */ +&uart_AO { + status = "okay"; + pinctrl-0 = <&uart_ao_a_pins>; + pinctrl-names = "default"; +}; + +/* Bluetooth on AP6212 */ +&uart_A { + status = "disabled"; + pinctrl-0 = <&uart_a_pins>, <&uart_a_cts_rts_pins>; + pinctrl-names = "default"; +}; + +/* 40-pin CON1 */ +&uart_C { + status = "disabled"; + pinctrl-0 = <&uart_c_pins>; + pinctrl-names = "default"; +}; + +&usb0_phy { + status = "okay"; + phy-supply = <&vdd_5v>; +}; + +&usb1_phy { + status = "okay"; +}; + +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 87198eafb04b67..a1078b3e1c760d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -165,10 +165,10 @@ }; }; -&uart_AO { - status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; - pinctrl-names = "default"; +&cvbs_vdac_port { + cvbs_vdac_out: endpoint { + remote-endpoint = <&cvbs_connector_in>; + }; }; ðmac { @@ -195,12 +195,32 @@ }; }; +&hdmi_tx { + status = "okay"; + pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-names = "default"; +}; + +&hdmi_tx_tmds_port { + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; +}; + &ir { status = "okay"; pinctrl-0 = <&remote_input_ao_pins>; pinctrl-names = "default"; }; +&pwm_ef { + status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; +}; + /* Wireless SDIO Module */ &sd_emmc_a { status = "okay"; @@ -260,28 +280,8 @@ vqmmc-supply = <&vddio_boot>; }; -&pwm_ef { - status = "okay"; - pinctrl-0 = <&pwm_e_pins>; - pinctrl-names = "default"; - clocks = <&clkc CLKID_FCLK_DIV4>; - clock-names = "clkin0"; -}; - -&cvbs_vdac_port { - cvbs_vdac_out: endpoint { - remote-endpoint = <&cvbs_connector_in>; - }; -}; - -&hdmi_tx { +&uart_AO { status = "okay"; - pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; }; - -&hdmi_tx_tmds_port { - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 54a9c6a6b3923c..d147c853ab054d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -137,16 +137,6 @@ }; }; -&scpi_clocks { - status = "disabled"; -}; - -&uart_AO { - status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; - pinctrl-names = "default"; -}; - ðmac { status = "okay"; pinctrl-0 = <ð_rgmii_pins>; @@ -172,6 +162,33 @@ }; }; +&gpio_ao { + /* + * WARNING: The USB Hub on the Odroid-C2 needs a reset signal + * to be turned high in order to be detected by the USB Controller + * This signal should be handled by a USB specific power sequence + * in order to reset the Hub when USB bus is powered down. + */ + usb-hub { + gpio-hog; + gpios = ; + output-high; + line-name = "usb-hub-reset"; + }; +}; + +&i2c_A { + status = "okay"; + pinctrl-0 = <&i2c_a_pins>; + pinctrl-names = "default"; +}; + +&ir { + status = "okay"; + pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-names = "default"; +}; + &pinctrl_aobus { gpio-line-names = "UART TX", "UART RX", "VCCK En", "TF 3V3/1V8 En", "USB HUB nRESET", "USB OTG Power En", @@ -223,55 +240,15 @@ ""; }; -&ir { - status = "okay"; - pinctrl-0 = <&remote_input_ao_pins>; - pinctrl-names = "default"; -}; - -&i2c_A { - status = "okay"; - pinctrl-0 = <&i2c_a_pins>; - pinctrl-names = "default"; -}; - -&gpio_ao { - /* - * WARNING: The USB Hub on the Odroid-C2 needs a reset signal - * to be turned high in order to be detected by the USB Controller - * This signal should be handled by a USB specific power sequence - * in order to reset the Hub when USB bus is powered down. - */ - usb-hub { - gpio-hog; - gpios = ; - output-high; - line-name = "usb-hub-reset"; - }; -}; - -&usb0_phy { - status = "okay"; - phy-supply = <&usb_otg_pwr>; -}; - -&usb1_phy { - status = "okay"; -}; - -&usb0 { - status = "okay"; -}; - -&usb1 { - status = "okay"; -}; - &saradc { status = "okay"; vref-supply = <&vcc1v8>; }; +&scpi_clocks { + status = "disabled"; +}; + /* SD */ &sd_emmc_b { status = "okay"; @@ -309,3 +286,26 @@ vmmc-supply = <&vcc3v3>; vqmmc-supply = <&vcc1v8>; }; + +&uart_AO { + status = "okay"; + pinctrl-0 = <&uart_ao_a_pins>; + pinctrl-names = "default"; +}; + +&usb0_phy { + status = "okay"; + phy-supply = <&usb_otg_pwr>; +}; + +&usb1_phy { + status = "okay"; +}; + +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index 3c6c0b7f4187da..d904deb1018cef 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -126,7 +126,7 @@ clock-names = "ext_clock"; }; - cvbs-connector { + cvbs_connector: cvbs-connector { compatible = "composite-video-connector"; port { @@ -148,34 +148,36 @@ }; }; -/* This UART is brought out to the DB9 connector */ -&uart_AO { - status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; - pinctrl-names = "default"; +&cvbs_vdac_port { + cvbs_vdac_out: endpoint { + remote-endpoint = <&cvbs_connector_in>; + }; }; -&ir { +&hdmi_tx { status = "okay"; - pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; pinctrl-names = "default"; }; -&usb0_phy { - status = "okay"; - phy-supply = <&usb_pwr>; -}; - -&usb1_phy { - status = "okay"; +&hdmi_tx_tmds_port { + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; }; -&usb0 { +&ir { status = "okay"; + pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-names = "default"; }; -&usb1 { +&pwm_ef { status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; }; /* Wireless SDIO Module */ @@ -198,7 +200,7 @@ vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; }; @@ -242,28 +244,26 @@ vqmmc-supply = <&vddio_boot>; }; -&pwm_ef { +/* This UART is brought out to the DB9 connector */ +&uart_AO { status = "okay"; - pinctrl-0 = <&pwm_e_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; - clocks = <&clkc CLKID_FCLK_DIV4>; - clock-names = "clkin0"; }; -&cvbs_vdac_port { - cvbs_vdac_out: endpoint { - remote-endpoint = <&cvbs_connector_in>; - }; +&usb0_phy { + status = "okay"; + phy-supply = <&usb_pwr>; }; -&hdmi_tx { +&usb1_phy { status = "okay"; - pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; - pinctrl-names = "default"; }; -&hdmi_tx_tmds_port { - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index aefa66dff72dc5..346753fb632431 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -111,18 +111,6 @@ }; }; -&uart_AO { - status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; - pinctrl-names = "default"; -}; - -&ir { - status = "okay"; - pinctrl-0 = <&remote_input_ao_pins>; - pinctrl-names = "default"; -}; - ðmac { status = "okay"; pinctrl-0 = <ð_rgmii_pins>; @@ -149,21 +137,18 @@ }; }; -&usb0_phy { - status = "okay"; - phy-supply = <&usb_vbus>; -}; - -&usb1_phy { - status = "okay"; -}; - -&usb0 { +&ir { status = "okay"; + pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-names = "default"; }; -&usb1 { +&pwm_ef { status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; }; /* Wireless SDIO Module */ @@ -186,7 +171,7 @@ vmmc-supply = <&vcc_3v3>; vqmmc-supply = <&vcc_1v8>; - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; }; @@ -229,10 +214,25 @@ vmmcq-sumpply = <&vcc_1v8>; }; -&pwm_ef { +&uart_AO { status = "okay"; - pinctrl-0 = <&pwm_e_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; - clocks = <&clkc CLKID_FCLK_DIV4>; - clock-names = "clkin0"; +}; + +&usb0_phy { + status = "okay"; + phy-supply = <&usb_vbus>; +}; + +&usb1_phy { + status = "okay"; +}; + +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts index f057fb48fee556..1878ac2b2b83e6 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts @@ -59,10 +59,10 @@ panic-indicator; }; }; +}; - cvbs-connector { - status = "disabled"; - }; +&cvbs_connector { + status = "disabled"; }; ðmac { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 86105a69690aa8..dbd300fffa8aee 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -97,13 +97,6 @@ }; }; -ðmac { - clocks = <&clkc CLKID_ETH>, - <&clkc CLKID_FCLK_DIV2>, - <&clkc CLKID_MPLL2>; - clock-names = "stmmaceth", "clkin0", "clkin1"; -}; - &aobus { pinctrl_aobus: pinctrl@14 { compatible = "amlogic,meson-gxbb-aobus-pinctrl"; @@ -249,9 +242,119 @@ function = "spdif_out_ao"; }; }; + + ao_cec_pins: ao_cec { + mux { + groups = "ao_cec"; + function = "cec_ao"; + }; + }; + + ee_cec_pins: ee_cec { + mux { + groups = "ee_cec"; + function = "cec_ao"; + }; + }; }; }; +&apb { + mali: gpu@c0000 { + compatible = "amlogic,meson-gxbb-mali", "arm,mali-450"; + reg = <0x0 0xc0000 0x0 0x40000>; + interrupts = , + , + , + , + , + , + , + , + , + ; + interrupt-names = "gp", "gpmmu", "pp", "pmu", + "pp0", "ppmmu0", "pp1", "ppmmu1", + "pp2", "ppmmu2"; + clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_MALI>; + clock-names = "bus", "core"; + + /* + * Mali clocking is provided by two identical clock paths + * MALI_0 and MALI_1 muxed to a single clock by a glitch + * free mux to safely change frequency while running. + */ + assigned-clocks = <&clkc CLKID_MALI_0_SEL>, + <&clkc CLKID_MALI_0>, + <&clkc CLKID_MALI>; /* Glitch free mux */ + assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>, + <0>, /* Do Nothing */ + <&clkc CLKID_MALI_0>; + assigned-clock-rates = <0>, /* Do Nothing */ + <666666666>, + <0>; /* Do Nothing */ + }; +}; + +&cbus { + spifc: spi@8c80 { + compatible = "amlogic,meson-gxbb-spifc"; + reg = <0x0 0x08c80 0x0 0x80>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkc CLKID_SPI>; + status = "disabled"; + }; +}; + +ðmac { + clocks = <&clkc CLKID_ETH>, + <&clkc CLKID_FCLK_DIV2>, + <&clkc CLKID_MPLL2>; + clock-names = "stmmaceth", "clkin0", "clkin1"; +}; + +&hdmi_tx { + compatible = "amlogic,meson-gxbb-dw-hdmi", "amlogic,meson-gx-dw-hdmi"; + resets = <&reset RESET_HDMITX_CAPB3>, + <&reset RESET_HDMI_SYSTEM_RESET>, + <&reset RESET_HDMI_TX>; + reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; + clocks = <&clkc CLKID_HDMI_PCLK>, + <&clkc CLKID_CLK81>, + <&clkc CLKID_GCLK_VENCI_INT0>; + clock-names = "isfr", "iahb", "venci"; +}; + +&hiubus { + clkc: clock-controller@0 { + compatible = "amlogic,gxbb-clkc"; + #clock-cells = <1>; + reg = <0x0 0x0 0x0 0x3db>; + }; +}; + +&hwrng { + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; +}; + +&i2c_A { + clocks = <&clkc CLKID_I2C>; +}; + +&i2c_AO { + clocks = <&clkc CLKID_AO_I2C>; +}; + +&i2c_B { + clocks = <&clkc CLKID_I2C>; +}; + +&i2c_C { + clocks = <&clkc CLKID_I2C>; +}; + &periphs { pinctrl_periphs: pinctrl@4b0 { compatible = "amlogic,meson-gxbb-periphs-pinctrl"; @@ -262,7 +365,7 @@ gpio: bank@4b0 { reg = <0x0 0x004b0 0x0 0x28>, <0x0 0x004e8 0x0 0x14>, - <0x0 0x00120 0x0 0x14>, + <0x0 0x00520 0x0 0x14>, <0x0 0x00430 0x0 0x40>; reg-names = "mux", "pull", "pull-enable", "gpio"; gpio-controller; @@ -290,6 +393,22 @@ }; }; + spi_pins: spi { + mux { + groups = "spi_miso", + "spi_mosi", + "spi_sclk"; + function = "spi"; + }; + }; + + spi_ss0_pins: spi-ss0 { + mux { + groups = "spi_ss0"; + function = "spi"; + }; + }; + sdcard_pins: sdcard { mux { groups = "sdcard_d0", @@ -521,67 +640,6 @@ }; }; -&hiubus { - clkc: clock-controller@0 { - compatible = "amlogic,gxbb-clkc"; - #clock-cells = <1>; - reg = <0x0 0x0 0x0 0x3db>; - }; -}; - -&apb { - mali: gpu@c0000 { - compatible = "amlogic,meson-gxbb-mali", "arm,mali-450"; - reg = <0x0 0xc0000 0x0 0x40000>; - interrupts = , - , - , - , - , - , - , - , - , - ; - interrupt-names = "gp", "gpmmu", "pp", "pmu", - "pp0", "ppmmu0", "pp1", "ppmmu1", - "pp2", "ppmmu2"; - clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_MALI>; - clock-names = "bus", "core"; - - /* - * Mali clocking is provided by two identical clock paths - * MALI_0 and MALI_1 muxed to a single clock by a glitch - * free mux to safely change frequency while running. - */ - assigned-clocks = <&clkc CLKID_MALI_0_SEL>, - <&clkc CLKID_MALI_0>, - <&clkc CLKID_MALI>; /* Glitch free mux */ - assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>, - <0>, /* Do Nothing */ - <&clkc CLKID_MALI_0>; - assigned-clock-rates = <0>, /* Do Nothing */ - <666666666>, - <0>; /* Do Nothing */ - }; -}; - -&i2c_A { - clocks = <&clkc CLKID_I2C>; -}; - -&i2c_AO { - clocks = <&clkc CLKID_AO_I2C>; -}; - -&i2c_B { - clocks = <&clkc CLKID_I2C>; -}; - -&i2c_C { - clocks = <&clkc CLKID_I2C>; -}; - &saradc { compatible = "amlogic,meson-gxbb-saradc", "amlogic,meson-saradc"; clocks = <&xtal>, @@ -620,20 +678,3 @@ &vpu { compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu"; }; - -&hwrng { - clocks = <&clkc CLKID_RNG0>; - clock-names = "core"; -}; - -&hdmi_tx { - compatible = "amlogic,meson-gxbb-dw-hdmi", "amlogic,meson-gx-dw-hdmi"; - resets = <&reset RESET_HDMITX_CAPB3>, - <&reset RESET_HDMI_SYSTEM_RESET>, - <&reset RESET_HDMI_TX>; - reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, - <&clkc CLKID_GCLK_VENCI_INT0>; - clock-names = "isfr", "iahb", "venci"; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts index 3c8b0b51ef276e..6a81f0168da5ab 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts @@ -95,7 +95,7 @@ }; &sd_emmc_a { - brcmf: bcrmf@1 { + brcmf: wifi@1 { reg = <1>; compatible = "brcm,bcm4329-fmac"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 8873c058fad232..6633a5d8fdd391 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -140,10 +140,10 @@ }; }; -&uart_AO { - status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; - pinctrl-names = "default"; +&cvbs_vdac_port { + cvbs_vdac_out: endpoint { + remote-endpoint = <&cvbs_connector_in>; + }; }; ðmac { @@ -152,12 +152,32 @@ phy-handle = <&internal_phy>; }; +&hdmi_tx { + status = "okay"; + pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-names = "default"; +}; + +&hdmi_tx_tmds_port { + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; +}; + &ir { status = "okay"; pinctrl-0 = <&remote_input_ao_pins>; pinctrl-names = "default"; }; +&pwm_ef { + status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; +}; + /* Wireless SDIO Module */ &sd_emmc_a { status = "okay"; @@ -217,28 +237,8 @@ vqmmc-supply = <&vddio_boot>; }; -&pwm_ef { - status = "okay"; - pinctrl-0 = <&pwm_e_pins>; - pinctrl-names = "default"; - clocks = <&clkc CLKID_FCLK_DIV4>; - clock-names = "clkin0"; -}; - -&cvbs_vdac_port { - cvbs_vdac_out: endpoint { - remote-endpoint = <&cvbs_connector_in>; - }; -}; - -&hdmi_tx { +&uart_AO { status = "okay"; - pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; }; - -&hdmi_tx_tmds_port { - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x.dtsi index 0f78d836edaf5d..3314a0b3dad97d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x.dtsi @@ -48,7 +48,7 @@ compatible = "amlogic,s905x", "amlogic,meson-gxl"; }; -/* S905X Only has access to its internal PHY */ +/* S905X only has access to its internal PHY */ ðmac { phy-mode = "rmii"; phy-handle = <&internal_phy>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index d8e096dff10a49..4dfc22b07bf01e 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -190,9 +190,59 @@ function = "spdif_out_ao"; }; }; + + ao_cec_pins: ao_cec { + mux { + groups = "ao_cec"; + function = "cec_ao"; + }; + }; + + ee_cec_pins: ee_cec { + mux { + groups = "ee_cec"; + function = "cec_ao"; + }; + }; + }; +}; + +&hdmi_tx { + compatible = "amlogic,meson-gxl-dw-hdmi", "amlogic,meson-gx-dw-hdmi"; + resets = <&reset RESET_HDMITX_CAPB3>, + <&reset RESET_HDMI_SYSTEM_RESET>, + <&reset RESET_HDMI_TX>; + reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; + clocks = <&clkc CLKID_HDMI_PCLK>, + <&clkc CLKID_CLK81>, + <&clkc CLKID_GCLK_VENCI_INT0>; + clock-names = "isfr", "iahb", "venci"; +}; + +&hiubus { + clkc: clock-controller@0 { + compatible = "amlogic,gxl-clkc", "amlogic,gxbb-clkc"; + #clock-cells = <1>; + reg = <0x0 0x0 0x0 0x3db>; }; }; +&i2c_A { + clocks = <&clkc CLKID_I2C>; +}; + +&i2c_AO { + clocks = <&clkc CLKID_AO_I2C>; +}; + +&i2c_B { + clocks = <&clkc CLKID_I2C>; +}; + +&i2c_C { + clocks = <&clkc CLKID_I2C>; +}; + &periphs { pinctrl_periphs: pinctrl@4b0 { compatible = "amlogic,meson-gxl-periphs-pinctrl"; @@ -203,12 +253,12 @@ gpio: bank@4b0 { reg = <0x0 0x004b0 0x0 0x28>, <0x0 0x004e8 0x0 0x14>, - <0x0 0x00120 0x0 0x14>, + <0x0 0x00520 0x0 0x14>, <0x0 0x00430 0x0 0x40>; reg-names = "mux", "pull", "pull-enable", "gpio"; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pinctrl_periphs 0 14 101>; + gpio-ranges = <&pinctrl_periphs 0 10 101>; }; emmc_pins: emmc { @@ -231,6 +281,22 @@ }; }; + spi_pins: spi { + mux { + groups = "spi_miso", + "spi_mosi", + "spi_sclk"; + function = "spi"; + }; + }; + + spi_ss0_pins: spi-ss0 { + mux { + groups = "spi_ss0"; + function = "spi"; + }; + }; + sdcard_pins: sdcard { mux { groups = "sdcard_d0", @@ -354,6 +420,20 @@ }; }; + eth_link_led_pins: eth_link_led { + mux { + groups = "eth_link_led"; + function = "eth_led"; + }; + }; + + eth_act_led_pins: eth_act_led { + mux { + groups = "eth_act_led"; + function = "eth_led"; + }; + }; + pwm_a_pins: pwm_a { mux { groups = "pwm_a"; @@ -501,30 +581,6 @@ }; }; -&hiubus { - clkc: clock-controller@0 { - compatible = "amlogic,gxl-clkc", "amlogic,gxbb-clkc"; - #clock-cells = <1>; - reg = <0x0 0x0 0x0 0x3db>; - }; -}; - -&i2c_A { - clocks = <&clkc CLKID_I2C>; -}; - -&i2c_AO { - clocks = <&clkc CLKID_AO_I2C>; -}; - -&i2c_B { - clocks = <&clkc CLKID_I2C>; -}; - -&i2c_C { - clocks = <&clkc CLKID_I2C>; -}; - &saradc { compatible = "amlogic,meson-gxl-saradc", "amlogic,meson-saradc"; clocks = <&xtal>, @@ -563,15 +619,3 @@ &vpu { compatible = "amlogic,meson-gxl-vpu", "amlogic,meson-gx-vpu"; }; - -&hdmi_tx { - compatible = "amlogic,meson-gxl-dw-hdmi", "amlogic,meson-gx-dw-hdmi"; - resets = <&reset RESET_HDMITX_CAPB3>, - <&reset RESET_HDMI_SYSTEM_RESET>, - <&reset RESET_HDMI_TX>; - reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, - <&clkc CLKID_GCLK_VENCI_INT0>; - clock-names = "isfr", "iahb", "venci"; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index 11b0bf46a95c4d..5f626d68308834 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -113,11 +113,49 @@ }; }; -/* This UART is brought out to the DB9 connector */ -&uart_AO { +&cvbs_vdac_port { + cvbs_vdac_out: endpoint { + remote-endpoint = <&cvbs_connector_in>; + }; +}; + +ðmac { status = "okay"; - pinctrl-0 = <&uart_ao_a_pins>; + + pinctrl-0 = <ð_pins>; pinctrl-names = "default"; + + /* Select external PHY by default */ + phy-handle = <&external_phy>; + + amlogic,tx-delay-ns = <2>; + + snps,reset-gpio = <&gpio GPIOZ_14 0>; + snps,reset-delays-us = <0 10000 1000000>; + snps,reset-active-low; + + /* External PHY is in RGMII */ + phy-mode = "rgmii"; +}; + +&external_mdio { + external_phy: ethernet-phy@0 { + compatible = "ethernet-phy-id001c.c916", "ethernet-phy-ieee802.3-c22"; + reg = <0>; + max-speed = <1000>; + }; +}; + +&hdmi_tx { + status = "okay"; + pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-names = "default"; +}; + +&hdmi_tx_tmds_port { + hdmi_tx_tmds_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; }; &ir { @@ -164,47 +202,8 @@ vqmmc-supply = <&vddio_boot>; }; -ðmac { - status = "okay"; - - pinctrl-0 = <ð_pins>; - pinctrl-names = "default"; - - /* Select external PHY by default */ - phy-handle = <&external_phy>; - - amlogic,tx-delay-ns = <2>; - - snps,reset-gpio = <&gpio GPIOZ_14 0>; - snps,reset-delays-us = <0 10000 1000000>; - snps,reset-active-low; - - /* External PHY is in RGMII */ - phy-mode = "rgmii"; -}; - -&external_mdio { - external_phy: ethernet-phy@0 { - compatible = "ethernet-phy-id001c.c916", "ethernet-phy-ieee802.3-c22"; - reg = <0>; - max-speed = <1000>; - }; -}; - -&cvbs_vdac_port { - cvbs_vdac_out: endpoint { - remote-endpoint = <&cvbs_connector_in>; - }; -}; - -&hdmi_tx { +&uart_AO { status = "okay"; - pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>; + pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; }; - -&hdmi_tx_tmds_port { - hdmi_tx_tmds_out: endpoint { - remote-endpoint = <&hdmi_connector_in>; - }; -}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts new file mode 100644 index 00000000000000..08f1dd69b6792e --- /dev/null +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -0,0 +1,240 @@ +/* + * Copyright (c) 2016-2017 Andreas Färber + * + * Based on nexbox-a1: + * + * Copyright (c) 2016 BayLibre, SAS. + * Author: Neil Armstrong + * + * Copyright (c) 2016 Endless Computers, Inc. + * Author: Carlo Caione + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; + +#include "meson-gxm.dtsi" + +/ { + compatible = "kingnovel,r-box-pro", "amlogic,s912", "amlogic,meson-gxm"; + model = "R-Box Pro"; + + aliases { + serial0 = &uart_AO; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x80000000>; /* 2 GiB or 3 GiB */ + }; + + leds { + compatible = "gpio-leds"; + + blue { + label = "rbox-pro:blue:on"; + gpios = <&gpio_ao GPIOAO_9 GPIO_ACTIVE_HIGH>; + default-state = "on"; + }; + + red { + label = "rbox-pro:red:standby"; + gpios = <&gpio GPIODV_28 GPIO_ACTIVE_HIGH>; + default-state = "off"; + retain-state-suspended; + panic-indicator; + }; + }; + + vddio_boot: regulator-vddio-boot { + compatible = "regulator-fixed"; + regulator-name = "VDDIO_BOOT"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + vddao_3v3: regulator-vddao-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VDDAO_3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + vcc_3v3: regulator-vcc-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VCC_3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + emmc_pwrseq: emmc-pwrseq { + compatible = "mmc-pwrseq-emmc"; + reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>; + }; + + wifi32k: wifi32k { + compatible = "pwm-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + pwms = <&pwm_ef 0 30518 0>; /* PWM_E at 32.768KHz */ + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&gpio GPIOX_6 GPIO_ACTIVE_LOW>; + clocks = <&wifi32k>; + clock-names = "ext_clock"; + }; +}; + +ðmac { + status = "okay"; + + pinctrl-0 = <ð_pins>; + pinctrl-names = "default"; + + /* Select external PHY by default */ + phy-handle = <&external_phy>; + + snps,reset-gpio = <&gpio GPIOZ_14 0>; + snps,reset-delays-us = <0 10000 1000000>; + snps,reset-active-low; + + amlogic,tx-delay-ns = <2>; + + /* External PHY is in RGMII */ + phy-mode = "rgmii"; +}; + +&external_mdio { + external_phy: ethernet-phy@0 { + compatible = "ethernet-phy-id001c.c916", "ethernet-phy-ieee802.3-c22"; + reg = <0>; + max-speed = <1000>; + }; +}; + +&ir { + status = "okay"; + pinctrl-0 = <&remote_input_ao_pins>; + pinctrl-names = "default"; +}; + +&pwm_ef { + status = "okay"; + pinctrl-0 = <&pwm_e_pins>; + pinctrl-names = "default"; + clocks = <&clkc CLKID_FCLK_DIV4>; + clock-names = "clkin0"; +}; + +/* Wireless SDIO Module */ +&sd_emmc_a { + status = "okay"; + pinctrl-0 = <&sdio_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + + bus-width = <4>; + cap-sd-highspeed; + max-frequency = <100000000>; + + non-removable; + disable-wp; + + mmc-pwrseq = <&sdio_pwrseq>; + + vmmc-supply = <&vddao_3v3>; + vqmmc-supply = <&vddio_boot>; + + brcmf: brcmf@1 { + reg = <1>; + compatible = "brcm,bcm4329-fmac"; + }; +}; + +/* SD card */ +&sd_emmc_b { + status = "okay"; + pinctrl-0 = <&sdcard_pins>; + pinctrl-names = "default"; + + bus-width = <4>; + cap-sd-highspeed; + max-frequency = <100000000>; + disable-wp; + + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; + cd-inverted; + + vmmc-supply = <&vddao_3v3>; + vqmmc-supply = <&vddio_boot>; +}; + +/* eMMC */ +&sd_emmc_c { + status = "okay"; + pinctrl-0 = <&emmc_pins>; + pinctrl-names = "default"; + + bus-width = <8>; + cap-sd-highspeed; + cap-mmc-highspeed; + max-frequency = <200000000>; + non-removable; + disable-wp; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + + mmc-pwrseq = <&emmc_pwrseq>; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&vddio_boot>; +}; + +&uart_AO { + status = "okay"; + pinctrl-0 = <&uart_ao_a_pins>; + pinctrl-names = "default"; +}; diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts index 3ff95277a8ec92..23191eb9397c36 100644 --- a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts +++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts @@ -60,7 +60,6 @@ vci-supply = <&ldo28_reg>; reset-gpios = <&gpg0 0 GPIO_ACTIVE_LOW>; enable-gpios = <&gpf1 5 GPIO_ACTIVE_HIGH>; - te-gpios = <&gpf1 3 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-frdm.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-frdm.dts index 17fae8112e4d96..7286b1ebfd7acc 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-frdm.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-frdm.dts @@ -1,7 +1,7 @@ /* * Device Tree file for Freescale LS1012A Freedom Board. * - * Copyright 2016, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. * * This file is dual-licensed: you can use it either under the terms * of the GPLv2 or the X11 license, at your option. Note that this dual diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts index e2a93d53d3d8dc..8c013b54db148a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts @@ -1,7 +1,7 @@ /* * Device Tree file for Freescale LS1012A QDS Board. * - * Copyright 2016, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. * * This file is dual-licensed: you can use it either under the terms * of the GPLv2 or the X11 license, at your option. Note that this dual @@ -97,6 +97,14 @@ status = "okay"; }; +&esdhc0 { + status = "okay"; +}; + +&esdhc1 { + status = "okay"; +}; + &i2c0 { status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-rdb.dts index ed77f6b0937b27..c1a119effa6156 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-rdb.dts @@ -1,7 +1,7 @@ /* * Device Tree file for Freescale LS1012A RDB Board. * - * Copyright 2016, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. * * This file is dual-licensed: you can use it either under the terms * of the GPLv2 or the X11 license, at your option. Note that this dual @@ -54,6 +54,19 @@ status = "okay"; }; +&esdhc0 { + sd-uhs-sdr104; + sd-uhs-sdr50; + sd-uhs-sdr25; + sd-uhs-sdr12; + status = "okay"; +}; + +&esdhc1 { + mmc-hs200-1_8v; + status = "okay"; +}; + &i2c0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi index b497ac196ccc1e..9a2ccd86ec121e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1012A family SoC. * - * Copyright 2016, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. * * This file is dual-licensed: you can use it either under the terms * of the GPLv2 or the X11 license, at your option. Note that this dual @@ -117,12 +117,37 @@ #size-cells = <2>; ranges; + esdhc0: esdhc@1560000 { + compatible = "fsl,ls1012a-esdhc", "fsl,esdhc"; + reg = <0x0 0x1560000 0x0 0x10000>; + interrupts = <0 62 0x4>; + clocks = <&clockgen 4 0>; + voltage-ranges = <1800 1800 3300 3300>; + sdhci,auto-cmd12; + big-endian; + bus-width = <4>; + status = "disabled"; + }; + scfg: scfg@1570000 { compatible = "fsl,ls1012a-scfg", "syscon"; reg = <0x0 0x1570000 0x0 0x10000>; big-endian; }; + esdhc1: esdhc@1580000 { + compatible = "fsl,ls1012a-esdhc", "fsl,esdhc"; + reg = <0x0 0x1580000 0x0 0x10000>; + interrupts = <0 65 0x4>; + clocks = <&clockgen 4 0>; + voltage-ranges = <1800 1800 3300 3300>; + sdhci,auto-cmd12; + big-endian; + broken-cd; + bus-width = <4>; + status = "disabled"; + }; + crypto: crypto@1700000 { compatible = "fsl,sec-v5.4", "fsl,sec-v5.0", "fsl,sec-v4.0"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi new file mode 100644 index 00000000000000..169e171407a631 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi @@ -0,0 +1,45 @@ +/* + * QorIQ FMan v3 device tree nodes for ls1043 + * + * Copyright 2015-2016 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +&soc { + +/* include used FMan blocks */ +#include "qoriq-fman3-0.dtsi" +#include "qoriq-fman3-0-1g-0.dtsi" +#include "qoriq-fman3-0-1g-1.dtsi" +#include "qoriq-fman3-0-1g-2.dtsi" +#include "qoriq-fman3-0-1g-3.dtsi" +#include "qoriq-fman3-0-1g-4.dtsi" +#include "qoriq-fman3-0-1g-5.dtsi" +#include "qoriq-fman3-0-10g-0.dtsi" + +}; + +&fman0 { + /* these aliases provide the FMan ports mapping */ + enet0: ethernet@e0000 { + }; + + enet1: ethernet@e2000 { + }; + + enet2: ethernet@e4000 { + }; + + enet3: ethernet@e6000 { + }; + + enet4: ethernet@e8000 { + }; + + enet5: ethernet@ea000 { + }; + + enet6: ethernet@f0000 { + }; +}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts index 0989d635b558fb..6341281485cfe5 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1043A family SoC. * - * Copyright 2014-2015, Freescale Semiconductor + * Copyright 2014-2015 Freescale Semiconductor, Inc. * * Mingkai Hu * @@ -181,3 +181,5 @@ reg = <0>; }; }; + +#include "fsl-ls1043-post.dtsi" diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts index c37110bc150684..df5b180a95a895 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1043A family SoC. * - * Copyright 2014-2015, Freescale Semiconductor + * Copyright 2014-2015 Freescale Semiconductor, Inc. * * Mingkai Hu * @@ -139,3 +139,76 @@ &duart1 { status = "okay"; }; + +#include "fsl-ls1043-post.dtsi" + +&fman0 { + ethernet@e0000 { + phy-handle = <&qsgmii_phy1>; + phy-connection-type = "qsgmii"; + }; + + ethernet@e2000 { + phy-handle = <&qsgmii_phy2>; + phy-connection-type = "qsgmii"; + }; + + ethernet@e4000 { + phy-handle = <&rgmii_phy1>; + phy-connection-type = "rgmii-txid"; + }; + + ethernet@e6000 { + phy-handle = <&rgmii_phy2>; + phy-connection-type = "rgmii-txid"; + }; + + ethernet@e8000 { + phy-handle = <&qsgmii_phy3>; + phy-connection-type = "qsgmii"; + }; + + ethernet@ea000 { + phy-handle = <&qsgmii_phy4>; + phy-connection-type = "qsgmii"; + }; + + ethernet@f0000 { /* 10GEC1 */ + phy-handle = <&aqr105_phy>; + phy-connection-type = "xgmii"; + }; + + mdio@fc000 { + rgmii_phy1: ethernet-phy@1 { + reg = <0x1>; + }; + + rgmii_phy2: ethernet-phy@2 { + reg = <0x2>; + }; + + qsgmii_phy1: ethernet-phy@4 { + reg = <0x4>; + }; + + qsgmii_phy2: ethernet-phy@5 { + reg = <0x5>; + }; + + qsgmii_phy3: ethernet-phy@6 { + reg = <0x6>; + }; + + qsgmii_phy4: ethernet-phy@7 { + reg = <0x7>; + }; + }; + + mdio@fd000 { + aqr105_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c45"; + interrupts = <0 132 4>; + reg = <0x1>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 45cface08cbbf6..31fd77f82ced81 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1043A family SoC. * - * Copyright 2014-2015, Freescale Semiconductor + * Copyright 2014-2015 Freescale Semiconductor, Inc. * * Mingkai Hu * @@ -45,6 +45,7 @@ */ #include +#include / { compatible = "fsl,ls1043a"; @@ -52,6 +53,17 @@ #address-cells = <2>; #size-cells = <2>; + aliases { + fman0 = &fman0; + ethernet0 = &enet0; + ethernet1 = &enet1; + ethernet2 = &enet2; + ethernet3 = &enet3; + ethernet4 = &enet4; + ethernet5 = &enet5; + ethernet6 = &enet6; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -106,6 +118,33 @@ /* DRAM space 1, size: 2GiB DRAM */ }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + compatible = "shared-dma-pool"; + size = <0 0x1000000>; + alignment = <0 0x1000000>; + no-map; + }; + + qman_fqd: qman-fqd { + compatible = "shared-dma-pool"; + size = <0 0x400000>; + alignment = <0 0x400000>; + no-map; + }; + + qman_pfdr: qman-pfdr { + compatible = "shared-dma-pool"; + size = <0 0x2000000>; + alignment = <0 0x2000000>; + no-map; + }; + }; + sysclk: sysclk { compatible = "fixed-clock"; #clock-cells = <0>; @@ -152,7 +191,7 @@ interrupts = <1 9 0xf08>; }; - soc { + soc: soc { compatible = "simple-bus"; #address-cells = <2>; #size-cells = <2>; @@ -223,6 +262,7 @@ ifc: ifc@1530000 { compatible = "fsl,ifc", "simple-bus"; reg = <0x0 0x1530000 0x0 0x10000>; + big-endian; interrupts = <0 43 0x4>; }; @@ -333,6 +373,28 @@ }; }; + qman: qman@1880000 { + compatible = "fsl,qman"; + reg = <0x0 0x1880000 0x0 0x10000>; + interrupts = <0 45 0x4>; + memory-region = <&qman_fqd &qman_pfdr>; + }; + + bman: bman@1890000 { + compatible = "fsl,bman"; + reg = <0x0 0x1890000 0x0 0x10000>; + interrupts = <0 45 0x4>; + memory-region = <&bman_fbpr>; + }; + + bportals: bman-portals@508000000 { + ranges = <0x0 0x5 0x08000000 0x8000000>; + }; + + qportals: qman-portals@500000000 { + ranges = <0x0 0x5 0x00000000 0x8000000>; + }; + dspi0: dspi@2100000 { compatible = "fsl,ls1043a-dspi", "fsl,ls1021a-v1.0-dspi"; #address-cells = <1>; @@ -688,3 +750,6 @@ }; }; + +#include "qoriq-qman-portals.dtsi" +#include "qoriq-bman-portals.dtsi" diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046-post.dtsi new file mode 100644 index 00000000000000..f5017dba0f17f9 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046-post.dtsi @@ -0,0 +1,48 @@ +/* + * QorIQ FMan v3 device tree nodes for ls1046 + * + * Copyright 2015-2016 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +&soc { + +/* include used FMan blocks */ +#include "qoriq-fman3-0.dtsi" +#include "qoriq-fman3-0-1g-0.dtsi" +#include "qoriq-fman3-0-1g-1.dtsi" +#include "qoriq-fman3-0-1g-2.dtsi" +#include "qoriq-fman3-0-1g-3.dtsi" +#include "qoriq-fman3-0-1g-4.dtsi" +#include "qoriq-fman3-0-1g-5.dtsi" +#include "qoriq-fman3-0-10g-0.dtsi" +#include "qoriq-fman3-0-10g-1.dtsi" +}; + +&fman0 { + /* these aliases provide the FMan ports mapping */ + enet0: ethernet@e0000 { + }; + + enet1: ethernet@e2000 { + }; + + enet2: ethernet@e4000 { + }; + + enet3: ethernet@e6000 { + }; + + enet4: ethernet@e8000 { + }; + + enet5: ethernet@ea000 { + }; + + enet6: ethernet@f0000 { + }; + + enet7: ethernet@f2000 { + }; +}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts index 290e5b014414ff..434383bade0edc 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1046A family SoC. * - * Copyright 2016, Freescale Semiconductor, Inc. + * Copyright 2016 Freescale Semiconductor, Inc. * * Shaohui Xie * @@ -210,3 +210,5 @@ reg = <0>; }; }; + +#include "fsl-ls1046-post.dtsi" diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts index d1ccc000d05aa4..5dc2782e2a58e7 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1046A family SoC. * - * Copyright 2016, Freescale Semiconductor, Inc. + * Copyright 2016 Freescale Semiconductor, Inc. * * Mingkai Hu * @@ -72,6 +72,14 @@ status = "okay"; }; +&esdhc { + mmc-hs200-1_8v; + sd-uhs-sdr104; + sd-uhs-sdr50; + sd-uhs-sdr25; + sd-uhs-sdr12; +}; + &i2c0 { status = "okay"; @@ -148,3 +156,63 @@ reg = <1>; }; }; + +#include "fsl-ls1046-post.dtsi" + +&fman0 { + ethernet@e4000 { + phy-handle = <&rgmii_phy1>; + phy-connection-type = "rgmii"; + }; + + ethernet@e6000 { + phy-handle = <&rgmii_phy2>; + phy-connection-type = "rgmii"; + }; + + ethernet@e8000 { + phy-handle = <&sgmii_phy1>; + phy-connection-type = "sgmii"; + }; + + ethernet@ea000 { + phy-handle = <&sgmii_phy2>; + phy-connection-type = "sgmii"; + }; + + ethernet@f0000 { /* 10GEC1 */ + phy-handle = <&aqr106_phy>; + phy-connection-type = "xgmii"; + }; + + ethernet@f2000 { /* 10GEC2 */ + fixed-link = <0 1 1000 0 0>; + phy-connection-type = "xgmii"; + }; + + mdio@fc000 { + rgmii_phy1: ethernet-phy@1 { + reg = <0x1>; + }; + + rgmii_phy2: ethernet-phy@2 { + reg = <0x2>; + }; + + sgmii_phy1: ethernet-phy@3 { + reg = <0x3>; + }; + + sgmii_phy2: ethernet-phy@4 { + reg = <0x4>; + }; + }; + + mdio@fd000 { + aqr106_phy: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c45"; + interrupts = <0 131 4>; + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index f4b8b7edaf9dba..c161df66a9eaf3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-1046A family SoC. * - * Copyright 2016, Freescale Semiconductor, Inc. + * Copyright 2016 Freescale Semiconductor, Inc. * * Mingkai Hu * @@ -55,6 +55,15 @@ aliases { crypto = &crypto; + fman0 = &fman0; + ethernet0 = &enet0; + ethernet1 = &enet1; + ethernet2 = &enet2; + ethernet3 = &enet3; + ethernet4 = &enet4; + ethernet5 = &enet5; + ethernet6 = &enet6; + ethernet7 = &enet7; }; cpus { @@ -174,7 +183,7 @@ IRQ_TYPE_LEVEL_LOW)>; }; - soc { + soc: soc { compatible = "simple-bus"; #address-cells = <2>; #size-cells = <2>; @@ -190,6 +199,7 @@ ifc: ifc@1530000 { compatible = "fsl,ifc", "simple-bus"; reg = <0x0 0x1530000 0x0 0x10000>; + big-endian; interrupts = ; }; @@ -209,10 +219,10 @@ }; esdhc: esdhc@1560000 { - compatible = "fsl,esdhc"; + compatible = "fsl,ls1046a-esdhc", "fsl,esdhc"; reg = <0x0 0x1560000 0x0 0x10000>; interrupts = ; - clock-frequency = <0>; + clocks = <&clockgen 2 1>; voltage-ranges = <1800 1800 3300 3300>; sdhci,auto-cmd12; big-endian; @@ -268,6 +278,30 @@ }; }; + qman: qman@1880000 { + compatible = "fsl,qman"; + reg = <0x0 0x1880000 0x0 0x10000>; + interrupts = <0 45 0x4>; + memory-region = <&qman_fqd &qman_pfdr>; + + }; + + bman: bman@1890000 { + compatible = "fsl,bman"; + reg = <0x0 0x1890000 0x0 0x10000>; + interrupts = <0 45 0x4>; + memory-region = <&bman_fbpr>; + + }; + + qportals: qman-portals@500000000 { + ranges = <0x0 0x5 0x00000000 0x8000000>; + }; + + bportals: bman-portals@508000000 { + ranges = <0x0 0x5 0x08000000 0x8000000>; + }; + dcfg: dcfg@1ee0000 { compatible = "fsl,ls1046a-dcfg", "syscon"; reg = <0x0 0x1ee0000 0x0 0x10000>; @@ -594,4 +628,34 @@ clocks = <&clockgen 4 1>; }; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + bman_fbpr: bman-fbpr { + compatible = "shared-dma-pool"; + size = <0 0x1000000>; + alignment = <0 0x1000000>; + no-map; + }; + + qman_fqd: qman-fqd { + compatible = "shared-dma-pool"; + size = <0 0x800000>; + alignment = <0 0x800000>; + no-map; + }; + + qman_pfdr: qman-pfdr { + compatible = "shared-dma-pool"; + size = <0 0x2000000>; + alignment = <0 0x2000000>; + no-map; + }; + }; }; + +#include "qoriq-qman-portals.dtsi" +#include "qoriq-bman-portals.dtsi" diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts index 8c3cae530f8ff1..30128051d0c02e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts @@ -110,6 +110,30 @@ }; }; +&ifc { + ranges = <0 0 0x5 0x80000000 0x08000000 + 2 0 0x5 0x30000000 0x00010000 + 3 0 0x5 0x20000000 0x00010000>; + status = "okay"; + + nor@0,0 { + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + }; + + fpga: board-control@3,0 { + compatible = "fsl,ls1088aqds-fpga", "fsl,fpga-qixis"; + reg = <0x3 0x0 0x0000100>; + }; +}; + &duart0 { status = "okay"; }; @@ -118,6 +142,10 @@ status = "okay"; }; +&esdhc { + status = "okay"; +}; + &sata { status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts index 8a04fbb25cb499..213abb72de93e9 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts @@ -94,6 +94,22 @@ }; }; +&ifc { + ranges = <0 0 0x5 0x30000000 0x00010000 + 2 0 0x5 0x20000000 0x00010000>; + status = "okay"; + + nand@0,0 { + compatible = "fsl,ifc-nand"; + reg = <0x0 0x0 0x10000>; + }; + + fpga: board-control@2,0 { + compatible = "fsl,ls1088ardb-fpga", "fsl,fpga-qixis"; + reg = <0x2 0x0 0x0000100>; + }; +}; + &duart0 { status = "okay"; }; @@ -102,6 +118,10 @@ status = "okay"; }; +&esdhc { + status = "okay"; +}; + &sata { status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index 2946fd79712148..df16284ec5eca3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -44,6 +44,7 @@ * OTHER DEALINGS IN THE SOFTWARE. */ #include +#include / { compatible = "fsl,ls1088a"; @@ -61,6 +62,7 @@ compatible = "arm,cortex-a53"; reg = <0x0>; clocks = <&clockgen 1 0>; + #cooling-cells = <2>; }; cpu1: cpu@1 { @@ -89,6 +91,7 @@ compatible = "arm,cortex-a53"; reg = <0x100>; clocks = <&clockgen 1 1>; + #cooling-cells = <2>; }; cpu5: cpu@101 { @@ -153,6 +156,91 @@ clocks = <&sysclk>; }; + tmu: tmu@1f80000 { + compatible = "fsl,qoriq-tmu"; + reg = <0x0 0x1f80000 0x0 0x10000>; + interrupts = <0 23 0x4>; + fsl,tmu-range = <0xb0000 0x9002a 0x6004c 0x30062>; + fsl,tmu-calibration = + /* Calibration data group 1 */ + <0x00000000 0x00000026 + 0x00000001 0x0000002d + 0x00000002 0x00000032 + 0x00000003 0x00000039 + 0x00000004 0x0000003f + 0x00000005 0x00000046 + 0x00000006 0x0000004d + 0x00000007 0x00000054 + 0x00000008 0x0000005a + 0x00000009 0x00000061 + 0x0000000a 0x0000006a + 0x0000000b 0x00000071 + /* Calibration data group 2 */ + 0x00010000 0x00000025 + 0x00010001 0x0000002c + 0x00010002 0x00000035 + 0x00010003 0x0000003d + 0x00010004 0x00000045 + 0x00010005 0x0000004e + 0x00010006 0x00000057 + 0x00010007 0x00000061 + 0x00010008 0x0000006b + 0x00010009 0x00000076 + /* Calibration data group 3 */ + 0x00020000 0x00000029 + 0x00020001 0x00000033 + 0x00020002 0x0000003d + 0x00020003 0x00000049 + 0x00020004 0x00000056 + 0x00020005 0x00000061 + 0x00020006 0x0000006d + /* Calibration data group 4 */ + 0x00030000 0x00000021 + 0x00030001 0x0000002a + 0x00030002 0x0000003c + 0x00030003 0x0000004e>; + little-endian; + #thermal-sensor-cells = <1>; + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + thermal-sensors = <&tmu 0>; + + trips { + cpu_alert: cpu-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu_crit: cpu-crit { + temperature = <95000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu_alert>; + cooling-device = + <&cpu0 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + + map1 { + trip = <&cpu_alert>; + cooling-device = + <&cpu4 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + }; + }; + }; + duart0: serial@21c0500 { compatible = "fsl,ns16550", "ns16550a"; reg = <0x0 0x21c0500 0x0 0x100>; @@ -216,10 +304,6 @@ little-endian; #address-cells = <2>; #size-cells = <1>; - - ranges = <0 0 0x5 0x80000000 0x08000000 - 2 0 0x5 0x30000000 0x00010000 - 3 0 0x5 0x20000000 0x00010000>; status = "disabled"; }; @@ -263,11 +347,26 @@ status = "disabled"; }; + esdhc: esdhc@2140000 { + compatible = "fsl,ls1088a-esdhc", "fsl,esdhc"; + reg = <0x0 0x2140000 0x0 0x10000>; + interrupts = <0 28 0x4>; /* Level high type */ + clock-frequency = <0>; + voltage-ranges = <1800 1800 3300 3300>; + sdhci,auto-cmd12; + little-endian; + bus-width = <4>; + status = "disabled"; + }; + sata: sata@3200000 { compatible = "fsl,ls1088a-ahci", "fsl,ls1043a-ahci"; - reg = <0x0 0x3200000 0x0 0x10000>; + reg = <0x0 0x3200000 0x0 0x10000>, + <0x0 0x20140520 0x0 0x4>; + reg-names = "ahci", "sata-ecc"; interrupts = <0 133 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen 4 3>; + dma-coherent; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts index c1e76dfca48efe..ed209cd57283b6 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2080a QDS Board. * - * Copyright (C) 2015-17, Freescale Semiconductor + * Copyright 2015-2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * Bhupesh Sharma diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts index 18ad1958731175..67ec3f9c81a148 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2080a RDB Board. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * Bhupesh Sharma diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts b/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts index 290604b0a603ba..3ee718f0aaf855 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts @@ -1,7 +1,7 @@ /* * Device Tree file for Freescale LS2080a software Simulator model * - * Copyright (C) 2014-2015, Freescale Semiconductor + * Copyright 2014-2015 Freescale Semiconductor, Inc. * * Bhupesh Sharma * diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi index 46a26c0214219c..d789c6814e6a57 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -1,7 +1,7 @@ /* * Device Tree Include file for Freescale Layerscape-2080A family SoC. * - * Copyright (C) 2014-2016, Freescale Semiconductor + * Copyright 2014-2016 Freescale Semiconductor, Inc. * * Abhimanyu Saini * Bhupesh Sharma diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2088a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls2088a-qds.dts index ebcd6ee4da0d6d..4a1df5ce3229c5 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2088a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls2088a-qds.dts @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2088A QDS Board. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls2088a-rdb.dts index 5992dc130faa0f..a76d4b4debd16c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2088a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls2088a-rdb.dts @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2088A RDB Board. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2088a.dtsi index 33ce404cf7e4fa..5c695c65805660 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2088a.dtsi @@ -1,7 +1,8 @@ /* * Device Tree Include file for Freescale Layerscape-2088A family SoC. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi index 8b62048459738b..b2374469a83010 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2080A QDS Board. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * @@ -45,6 +46,7 @@ */ &esdhc { + mmc-hs200-1_8v; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi index 3737587ffb339d..29af54be266501 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi @@ -1,7 +1,8 @@ /* * Device Tree file for Freescale LS2080A RDB Board. * - * Copyright (C) 2016-17, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * @@ -45,6 +46,10 @@ */ &esdhc { + sd-uhs-sdr104; + sd-uhs-sdr50; + sd-uhs-sdr25; + sd-uhs-sdr12; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index abb2fff7d16297..94cdd30450371a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -1,7 +1,8 @@ /* * Device Tree Include file for Freescale Layerscape-2080A family SoC. * - * Copyright (C) 2016-2017, Freescale Semiconductor + * Copyright 2016 Freescale Semiconductor, Inc. + * Copyright 2017 NXP * * Abhimanyu Saini * @@ -471,7 +472,7 @@ compatible = "fsl,ls2080a-esdhc", "fsl,esdhc"; reg = <0x0 0x2140000 0x0 0x10000>; interrupts = <0 28 0x4>; /* Level high type */ - clock-frequency = <0>; /* Updated by bootloader */ + clocks = <&clockgen 4 1>; voltage-ranges = <1800 1800 3300 3300>; sdhci,auto-cmd12; little-endian; diff --git a/arch/arm64/boot/dts/freescale/qoriq-bman-portals.dtsi b/arch/arm64/boot/dts/freescale/qoriq-bman-portals.dtsi new file mode 100644 index 00000000000000..c3c2be4f507284 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-bman-portals.dtsi @@ -0,0 +1,71 @@ +/* + * QorIQ BMan Portals device tree + * + * Copyright 2011-2016 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +&bportals { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + + bman-portal@0 { + /* + * bootloader fix-ups are expected to provide the + * "fsl,bman-portal-" compatible + */ + compatible = "fsl,bman-portal"; + reg = <0x0 0x4000>, <0x4000000 0x4000>; + interrupts = ; + }; + + bman-portal@10000 { + compatible = "fsl,bman-portal"; + reg = <0x10000 0x4000>, <0x4010000 0x4000>; + interrupts = ; + }; + + bman-portal@20000 { + compatible = "fsl,bman-portal"; + reg = <0x20000 0x4000>, <0x4020000 0x4000>; + interrupts = ; + }; + + bman-portal@30000 { + compatible = "fsl,bman-portal"; + reg = <0x30000 0x4000>, <0x4030000 0x4000>; + interrupts = ; + }; + + bman-portal@40000 { + compatible = "fsl,bman-portal"; + reg = <0x40000 0x4000>, <0x4040000 0x4000>; + interrupts = ; + }; + + bman-portal@50000 { + compatible = "fsl,bman-portal"; + reg = <0x50000 0x4000>, <0x4050000 0x4000>; + interrupts = ; + }; + + bman-portal@60000 { + compatible = "fsl,bman-portal"; + reg = <0x60000 0x4000>, <0x4060000 0x4000>; + interrupts = ; + }; + + bman-portal@70000 { + compatible = "fsl,bman-portal"; + reg = <0x70000 0x4000>, <0x4070000 0x4000>; + interrupts = ; + }; + + bman-portal@80000 { + compatible = "fsl,bman-portal"; + reg = <0x80000 0x4000>, <0x4080000 0x4000>; + interrupts = ; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-0.dtsi new file mode 100644 index 00000000000000..ecdffe731b98b2 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-0.dtsi @@ -0,0 +1,42 @@ +/* + * QorIQ FMan v3 10g port #0 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x10: port@90000 { + cell-index = <0x10>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x90000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x30: port@b0000 { + cell-index = <0x30>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xb0000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@f0000 { + cell-index = <0x8>; + compatible = "fsl,fman-memac"; + reg = <0xf0000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x10 &fman0_tx_0x30>; + pcsphy-handle = <&pcsphy6>; + }; + + mdio@f1000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xf1000 0x1000>; + + pcsphy6: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-1.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-1.dtsi new file mode 100644 index 00000000000000..a7f6af56b6a5a7 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-10g-1.dtsi @@ -0,0 +1,42 @@ +/* + * QorIQ FMan v3 10g port #1 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x11: port@91000 { + cell-index = <0x11>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x91000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x31: port@b1000 { + cell-index = <0x31>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xb1000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@f2000 { + cell-index = <0x9>; + compatible = "fsl,fman-memac"; + reg = <0xf2000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x11 &fman0_tx_0x31>; + pcsphy-handle = <&pcsphy7>; + }; + + mdio@f3000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xf3000 0x1000>; + + pcsphy7: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-0.dtsi new file mode 100644 index 00000000000000..d600786719fb2d --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-0.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #0 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x08: port@88000 { + cell-index = <0x8>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x88000 0x1000>; + }; + + fman0_tx_0x28: port@a8000 { + cell-index = <0x28>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa8000 0x1000>; + }; + + ethernet@e0000 { + cell-index = <0>; + compatible = "fsl,fman-memac"; + reg = <0xe0000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x08 &fman0_tx_0x28>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy0>; + }; + + mdio@e1000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe1000 0x1000>; + + pcsphy0: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-1.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-1.dtsi new file mode 100644 index 00000000000000..3c0b76d43043f0 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-1.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #1 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x09: port@89000 { + cell-index = <0x9>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x89000 0x1000>; + }; + + fman0_tx_0x29: port@a9000 { + cell-index = <0x29>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa9000 0x1000>; + }; + + ethernet@e2000 { + cell-index = <1>; + compatible = "fsl,fman-memac"; + reg = <0xe2000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy1>; + }; + + mdio@e3000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe3000 0x1000>; + + pcsphy1: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-2.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-2.dtsi new file mode 100644 index 00000000000000..89633afca26ac2 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-2.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #2 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x0a: port@8a000 { + cell-index = <0xa>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x8a000 0x1000>; + }; + + fman0_tx_0x2a: port@aa000 { + cell-index = <0x2a>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xaa000 0x1000>; + }; + + ethernet@e4000 { + cell-index = <2>; + compatible = "fsl,fman-memac"; + reg = <0xe4000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x0a &fman0_tx_0x2a>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy2>; + }; + + mdio@e5000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe5000 0x1000>; + + pcsphy2: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-3.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-3.dtsi new file mode 100644 index 00000000000000..87c2b705b1f96b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-3.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #3 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x0b: port@8b000 { + cell-index = <0xb>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x8b000 0x1000>; + }; + + fman0_tx_0x2b: port@ab000 { + cell-index = <0x2b>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xab000 0x1000>; + }; + + ethernet@e6000 { + cell-index = <3>; + compatible = "fsl,fman-memac"; + reg = <0xe6000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x0b &fman0_tx_0x2b>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy3>; + }; + + mdio@e7000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe7000 0x1000>; + + pcsphy3: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-4.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-4.dtsi new file mode 100644 index 00000000000000..8f4d74b96b678b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-4.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #4 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x0c: port@8c000 { + cell-index = <0xc>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x8c000 0x1000>; + }; + + fman0_tx_0x2c: port@ac000 { + cell-index = <0x2c>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xac000 0x1000>; + }; + + ethernet@e8000 { + cell-index = <4>; + compatible = "fsl,fman-memac"; + reg = <0xe8000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x0c &fman0_tx_0x2c>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy4>; + }; + + mdio@e9000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe9000 0x1000>; + + pcsphy4: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-5.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-5.dtsi new file mode 100644 index 00000000000000..d534f770f7295b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0-1g-5.dtsi @@ -0,0 +1,41 @@ +/* + * QorIQ FMan v3 1g port #5 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman@1a00000 { + fman0_rx_0x0d: port@8d000 { + cell-index = <0xd>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x8d000 0x1000>; + }; + + fman0_tx_0x2d: port@ad000 { + cell-index = <0x2d>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xad000 0x1000>; + }; + + ethernet@ea000 { + cell-index = <5>; + compatible = "fsl,fman-memac"; + reg = <0xea000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x0d &fman0_tx_0x2d>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy5>; + }; + + mdio@eb000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xeb000 0x1000>; + + pcsphy5: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi new file mode 100644 index 00000000000000..4dd06767f839e0 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -0,0 +1,81 @@ +/* + * QorIQ FMan v3 device tree + * + * Copyright 2012-2015 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +fman0: fman@1a00000 { + #address-cells = <1>; + #size-cells = <1>; + cell-index = <0>; + compatible = "fsl,fman"; + ranges = <0x0 0x0 0x1a00000 0x100000>; + reg = <0x0 0x1a00000 0x0 0x100000>; + interrupts = , + ; + clocks = <&clockgen 3 0>; + clock-names = "fmanclk"; + fsl,qman-channel-range = <0x800 0x10>; + + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x60000>; + }; + + fman0_oh_0x2: port@82000 { + cell-index = <0x2>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x82000 0x1000>; + }; + + fman0_oh_0x3: port@83000 { + cell-index = <0x3>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x83000 0x1000>; + }; + + fman0_oh_0x4: port@84000 { + cell-index = <0x4>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x84000 0x1000>; + }; + + fman0_oh_0x5: port@85000 { + cell-index = <0x5>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x85000 0x1000>; + }; + + fman0_oh_0x6: port@86000 { + cell-index = <0x6>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x86000 0x1000>; + }; + + fman0_oh_0x7: port@87000 { + cell-index = <0x7>; + compatible = "fsl,fman-v3-port-oh"; + reg = <0x87000 0x1000>; + }; + + mdio0: mdio@fc000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xfc000 0x1000>; + }; + + xmdio0: mdio@fd000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xfd000 0x1000>; + }; + + ptp_timer0: ptp-timer@fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0xfe000 0x1000>; + }; +}; diff --git a/arch/arm64/boot/dts/freescale/qoriq-qman-portals.dtsi b/arch/arm64/boot/dts/freescale/qoriq-qman-portals.dtsi new file mode 100644 index 00000000000000..2a9aa060efdac7 --- /dev/null +++ b/arch/arm64/boot/dts/freescale/qoriq-qman-portals.dtsi @@ -0,0 +1,80 @@ +/* + * QorIQ QMan Portals device tree + * + * Copyright 2011-2016 Freescale Semiconductor Inc. + * + * SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + */ + +&qportals { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + + qportal0: qman-portal@0 { + /* + * bootloader fix-ups are expected to provide the + * "fsl,bman-portal-" compatible + */ + compatible = "fsl,qman-portal"; + reg = <0x0 0x4000>, <0x4000000 0x4000>; + interrupts = ; + cell-index = <0>; + }; + + qportal1: qman-portal@10000 { + compatible = "fsl,qman-portal"; + reg = <0x10000 0x4000>, <0x4010000 0x4000>; + interrupts = ; + cell-index = <1>; + }; + + qportal2: qman-portal@20000 { + compatible = "fsl,qman-portal"; + reg = <0x20000 0x4000>, <0x4020000 0x4000>; + interrupts = ; + cell-index = <2>; + }; + + qportal3: qman-portal@30000 { + compatible = "fsl,qman-portal"; + reg = <0x30000 0x4000>, <0x4030000 0x4000>; + interrupts = ; + cell-index = <3>; + }; + + qportal4: qman-portal@40000 { + compatible = "fsl,qman-portal"; + reg = <0x40000 0x4000>, <0x4040000 0x4000>; + interrupts = ; + cell-index = <4>; + }; + + qportal5: qman-portal@50000 { + compatible = "fsl,qman-portal"; + reg = <0x50000 0x4000>, <0x4050000 0x4000>; + interrupts = ; + cell-index = <5>; + }; + + qportal6: qman-portal@60000 { + compatible = "fsl,qman-portal"; + reg = <0x60000 0x4000>, <0x4060000 0x4000>; + interrupts = ; + cell-index = <6>; + }; + + qportal7: qman-portal@70000 { + compatible = "fsl,qman-portal"; + reg = <0x70000 0x4000>, <0x4070000 0x4000>; + interrupts = ; + cell-index = <7>; + }; + + qportal8: qman-portal@80000 { + compatible = "fsl,qman-portal"; + reg = <0x80000 0x4000>, <0x4080000 0x4000>; + interrupts = ; + cell-index = <8>; + }; +}; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-db.dts b/arch/arm64/boot/dts/marvell/armada-8040-db.dts index dc0d084005b2ef..3cde649f96e404 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-db.dts @@ -169,6 +169,22 @@ status = "okay"; }; +&cps_mdio { + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&cps_ethernet { + status = "okay"; +}; + +&cps_eth1 { + status = "okay"; + phy = <&phy0>; + phy-mode = "rgmii-id"; +}; + &ap_sdhci0 { status = "okay"; bus-width = <4>; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts index f7bb0cc03147ad..100861aa7afdaa 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts @@ -95,6 +95,21 @@ status = "okay"; }; +&ap_sdhci0 { + bus-width = <8>; + /* + * Not stable in HS modes - phy needs "more calibration", so add + * the "slow-mode" and disable SDR104, SDR50 and DDR50 modes. + */ + marvell,xenon-phy-slow-mode; + no-1-8-v; + no-sd; + no-sdio; + non-removable; + status = "okay"; + vqmmc-supply = <&v_vddo_h>; +}; + &cpm_i2c0 { clock-frequency = <100000>; status = "okay"; @@ -105,6 +120,14 @@ status = "okay"; }; +&cpm_sdhci0 { + /* U6 */ + broken-cd; + bus-width = <4>; + status = "okay"; + vqmmc-supply = <&v_3_3>; +}; + &cpm_usb3_0 { /* J38? - USB2.0 only */ status = "okay"; diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index fe41bf9c301e2f..9b9e36a627d846 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -159,6 +159,7 @@ reg = <0x400000 0x1000>, <0x410000 0x1000>; msi-parent = <&gic_v2m0>; + clocks = <&ap_syscon 3>; dma-coherent; }; @@ -167,6 +168,7 @@ reg = <0x420000 0x1000>, <0x430000 0x1000>; msi-parent = <&gic_v2m0>; + clocks = <&ap_syscon 3>; dma-coherent; }; @@ -175,6 +177,7 @@ reg = <0x440000 0x1000>, <0x450000 0x1000>; msi-parent = <&gic_v2m0>; + clocks = <&ap_syscon 3>; dma-coherent; }; @@ -183,6 +186,7 @@ reg = <0x460000 0x1000>, <0x470000 0x1000>; msi-parent = <&gic_v2m0>; + clocks = <&ap_syscon 3>; dma-coherent; }; diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi index ac8df5201cd656..b4bc42ece75411 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -231,8 +231,7 @@ cpm_crypto: crypto@800000 { compatible = "inside-secure,safexcel-eip197"; reg = <0x800000 0x200000>; - interrupts = , + interrupts = , , , , diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi index 7740a75a823084..6e2058847ddcd5 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -221,8 +221,7 @@ cps_crypto: crypto@800000 { compatible = "inside-secure,safexcel-eip197"; reg = <0x800000 0x200000>; - interrupts = , + interrupts = , , , , diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi index a17f5b9a5de611..f611647e98805a 100644 --- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi @@ -215,22 +215,16 @@ usb@78d9000 { extcon = <&usb_id>, <&usb_id>; status = "okay"; - }; - - ehci@78d9000 { - status = "okay"; - }; - - phy@78d9000 { - v1p8-supply = <&pm8916_l7>; - v3p3-supply = <&pm8916_l13>; - vddcx-supply = <&pm8916_s1>; - extcon = <&usb_id>, <&usb_id>; - dr_mode = "otg"; - status = "okay"; - switch-gpio = <&pm8916_gpios 4 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&usb_sw_sel_pm>; + adp-disable; + hnp-disable; + srp-disable; + ulpi { + phy { + v1p8-supply = <&pm8916_l7>; + v3p3-supply = <&pm8916_l13>; + extcon = <&usb_id>; + }; + }; }; lpass@07708000 { @@ -348,6 +342,14 @@ pinctrl-0 = <&usb_id_default>; }; + usb-switch { + compatible = "toshiba,tc7usb40mu"; + switch-gpios = <&pm8916_gpios 4 GPIO_ACTIVE_HIGH>; + extcon = <&usb_id>; + pinctrl-names = "default"; + pinctrl-0 = <&usb_sw_sel_pm>; + }; + hdmi-out { compatible = "hdmi-connector"; type = "a"; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index ab3093995ded75..c963ef2ec5f58c 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -546,44 +546,40 @@ status = "disabled"; }; - usb_dev: usb@78d9000 { + otg: usb@78d9000 { compatible = "qcom,ci-hdrc"; - reg = <0x78d9000 0x400>; - dr_mode = "peripheral"; - interrupts = ; - usb-phy = <&usb_otg>; - status = "disabled"; - }; - - usb_host: ehci@78d9000 { - compatible = "qcom,ehci-host"; - reg = <0x78d9000 0x400>; - interrupts = ; - usb-phy = <&usb_otg>; - status = "disabled"; - }; - - usb_otg: phy@78d9000 { - compatible = "qcom,usb-otg-snps"; - reg = <0x78d9000 0x400>; + reg = <0x78d9000 0x200>, + <0x78d9200 0x200>; interrupts = , ; - - qcom,vdd-levels = <500000 1000000 1320000>; - qcom,phy-init-sequence = <0x44 0x6B 0x24 0x13>; - dr_mode = "peripheral"; - qcom,otg-control = <2>; // PMIC - qcom,manual-pullup; - clocks = <&gcc GCC_USB_HS_AHB_CLK>, - <&gcc GCC_USB_HS_SYSTEM_CLK>, - <&gcc GCC_USB2A_PHY_SLEEP_CLK>; - clock-names = "iface", "core", "sleep"; - - resets = <&gcc GCC_USB2A_PHY_BCR>, - <&gcc GCC_USB_HS_BCR>; - reset-names = "phy", "link"; + <&gcc GCC_USB_HS_SYSTEM_CLK>; + clock-names = "iface", "core"; + assigned-clocks = <&gcc GCC_USB_HS_SYSTEM_CLK>; + assigned-clock-rates = <80000000>; + resets = <&gcc GCC_USB_HS_BCR>; + reset-names = "core"; + phy_type = "ulpi"; + dr_mode = "otg"; + ahb-burst-config = <0>; + phy-names = "usb-phy"; + phys = <&usb_hs_phy>; status = "disabled"; + #reset-cells = <1>; + + ulpi { + usb_hs_phy: phy { + compatible = "qcom,usb-hs-phy-msm8916", + "qcom,usb-hs-phy"; + #phy-cells = <0>; + clocks = <&xo_board>, <&gcc GCC_USB2A_PHY_SLEEP_CLK>; + clock-names = "ref", "sleep"; + resets = <&gcc GCC_USB2A_PHY_BCR>, <&otg 0>; + reset-names = "phy", "por"; + qcom,init-seq = /bits/ 8 <0x0 0x44 + 0x1 0x6b 0x2 0x24 0x3 0x13>; + }; + }; }; intc: interrupt-controller@b000000 { diff --git a/arch/arm64/boot/dts/realtek/Makefile b/arch/arm64/boot/dts/realtek/Makefile new file mode 100644 index 00000000000000..8521e921e59a2e --- /dev/null +++ b/arch/arm64/boot/dts/realtek/Makefile @@ -0,0 +1,5 @@ +dtb-$(CONFIG_ARCH_REALTEK) += rtd1295-zidoo-x9s.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/arch/arm64/boot/dts/realtek/rtd1295-zidoo-x9s.dts b/arch/arm64/boot/dts/realtek/rtd1295-zidoo-x9s.dts new file mode 100644 index 00000000000000..6efa8091bb30bb --- /dev/null +++ b/arch/arm64/boot/dts/realtek/rtd1295-zidoo-x9s.dts @@ -0,0 +1,42 @@ +/* + * Copyright (c) 2016-2017 Andreas Färber + * + * SPDX-License-Identifier: (GPL-2.0+ OR MIT) + */ + +/dts-v1/; + +/memreserve/ 0x0000000000000000 0x0000000000030000; +/memreserve/ 0x000000000001f000 0x0000000000001000; +/memreserve/ 0x0000000000030000 0x00000000000d0000; +/memreserve/ 0x0000000001b00000 0x00000000004be000; +/memreserve/ 0x0000000001ffe000 0x0000000000004000; + +#include "rtd1295.dtsi" + +/ { + compatible = "zidoo,x9s", "realtek,rtd1295"; + model = "Zidoo X9S"; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x80000000>; + }; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&uart0 { + status = "okay"; +}; + +&uart1 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/realtek/rtd1295.dtsi b/arch/arm64/boot/dts/realtek/rtd1295.dtsi new file mode 100644 index 00000000000000..d8f84666c8ce3e --- /dev/null +++ b/arch/arm64/boot/dts/realtek/rtd1295.dtsi @@ -0,0 +1,131 @@ +/* + * Realtek RTD1295 SoC + * + * Copyright (c) 2016-2017 Andreas Färber + * + * SPDX-License-Identifier: (GPL-2.0+ OR MIT) + */ + +#include + +/ { + compatible = "realtek,rtd1295"; + interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x0>; + next-level-cache = <&l2>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x1>; + next-level-cache = <&l2>; + }; + + cpu2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x2>; + next-level-cache = <&l2>; + }; + + cpu3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x3>; + next-level-cache = <&l2>; + }; + + l2: l2-cache { + compatible = "cache"; + }; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + tee@10100000 { + reg = <0x10100000 0xf00000>; + no-map; + }; + }; + + arm-pmu { + compatible = "arm,cortex-a53-pmu"; + interrupts = ; + interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + /* Exclude up to 2 GiB of RAM */ + ranges = <0x80000000 0x80000000 0x80000000>; + + uart0: serial@98007800 { + compatible = "snps,dw-apb-uart"; + reg = <0x98007800 0x400>, + <0x98007000 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clock-frequency = <27000000>; + status = "disabled"; + }; + + uart1: serial@9801b200 { + compatible = "snps,dw-apb-uart"; + reg = <0x9801b200 0x100>, + <0x9801b00c 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clock-frequency = <432000000>; + status = "disabled"; + }; + + uart2: serial@9801b400 { + compatible = "snps,dw-apb-uart"; + reg = <0x9801b400 0x100>, + <0x9801b00c 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clock-frequency = <432000000>; + status = "disabled"; + }; + + gic: interrupt-controller@ff011000 { + compatible = "arm,gic-400"; + reg = <0xff011000 0x1000>, + <0xff012000 0x2000>, + <0xff014000 0x2000>, + <0xff016000 0x2000>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile index 1618e0a3c81d48..b6c723d8f6875f 100644 --- a/arch/arm64/boot/dts/renesas/Makefile +++ b/arch/arm64/boot/dts/renesas/Makefile @@ -1,4 +1,5 @@ dtb-$(CONFIG_ARCH_R8A7795) += r8a7795-salvator-x.dtb r8a7795-h3ulcb.dtb +dtb-$(CONFIG_ARCH_R8A7795) += r8a7795-es1-salvator-x.dtb dtb-$(CONFIG_ARCH_R8A7796) += r8a7796-salvator-x.dtb r8a7796-m3ulcb.dtb always := $(dtb-y) diff --git a/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts new file mode 100644 index 00000000000000..b84c156ed69699 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r8a7795-es1-salvator-x.dts @@ -0,0 +1,115 @@ +/* + * Device Tree Source for the Salvator-X board + * + * Copyright (C) 2015 Renesas Electronics Corp. + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#define CPG_AUDIO_CLK_I R8A7795_CLK_S0D4 + +/dts-v1/; +#include "r8a7795-es1.dtsi" +#include "salvator-x.dtsi" + +/ { + model = "Renesas Salvator-X board based on r8a7795 ES1.x"; + compatible = "renesas,salvator-x", "renesas,r8a7795"; + + memory@48000000 { + device_type = "memory"; + /* first 128MB is reserved for secure area. */ + reg = <0x0 0x48000000 0x0 0x38000000>; + }; + + memory@500000000 { + device_type = "memory"; + reg = <0x5 0x00000000 0x0 0x40000000>; + }; + + memory@600000000 { + device_type = "memory"; + reg = <0x6 0x00000000 0x0 0x40000000>; + }; + + memory@700000000 { + device_type = "memory"; + reg = <0x7 0x00000000 0x0 0x40000000>; + }; +}; + +&du { + clocks = <&cpg CPG_MOD 724>, + <&cpg CPG_MOD 723>, + <&cpg CPG_MOD 722>, + <&cpg CPG_MOD 721>, + <&cpg CPG_MOD 727>, + <&versaclock5 1>, + <&x21_clk>, + <&x22_clk>, + <&versaclock5 2>; + clock-names = "du.0", "du.1", "du.2", "du.3", "lvds.0", + "dclkin.0", "dclkin.1", "dclkin.2", "dclkin.3"; +}; + +&ehci2 { + status = "okay"; +}; + +&hdmi0 { + status = "okay"; + + ports { + port@1 { + reg = <1>; + rcar_dw_hdmi0_out: endpoint { + remote-endpoint = <&hdmi0_con>; + }; + }; + }; +}; + +&hdmi0_con { + remote-endpoint = <&rcar_dw_hdmi0_out>; +}; + +&hdmi1 { + status = "okay"; + + ports { + port@1 { + reg = <1>; + rcar_dw_hdmi1_out: endpoint { + remote-endpoint = <&hdmi1_con>; + }; + }; + }; +}; + +&hdmi1_con { + remote-endpoint = <&rcar_dw_hdmi1_out>; +}; + +&ohci2 { + status = "okay"; +}; + +&pfc { + usb2_pins: usb2 { + groups = "usb2"; + function = "usb2"; + }; +}; + +&sata { + status = "okay"; +}; + +&usb2_phy2 { + pinctrl-0 = <&usb2_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi b/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi new file mode 100644 index 00000000000000..a0ba7bd21ea3aa --- /dev/null +++ b/arch/arm64/boot/dts/renesas/r8a7795-es1.dtsi @@ -0,0 +1,84 @@ +/* + * Device Tree Source for the r8a7795 ES1.x SoC + * + * Copyright (C) 2015 Renesas Electronics Corp. + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include "r8a7795.dtsi" + +&soc { + xhci1: usb@ee0400000 { + compatible = "renesas,xhci-r8a7795", "renesas,rcar-gen3-xhci"; + reg = <0 0xee040000 0 0xc00>; + interrupts = ; + clocks = <&cpg CPG_MOD 327>; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 327>; + status = "disabled"; + }; + + fcpf2: fcp@fe952000 { + compatible = "renesas,fcpf"; + reg = <0 0xfe952000 0 0x200>; + clocks = <&cpg CPG_MOD 613>; + power-domains = <&sysc R8A7795_PD_A3VP>; + resets = <&cpg 613>; + }; + + vspi2: vsp@fe9c0000 { + compatible = "renesas,vsp2"; + reg = <0 0xfe9c0000 0 0x8000>; + interrupts = ; + clocks = <&cpg CPG_MOD 629>; + power-domains = <&sysc R8A7795_PD_A3VP>; + resets = <&cpg 629>; + + renesas,fcp = <&fcpvi2>; + }; + + fcpvi2: fcp@fe9cf000 { + compatible = "renesas,fcpv"; + reg = <0 0xfe9cf000 0 0x200>; + clocks = <&cpg CPG_MOD 609>; + power-domains = <&sysc R8A7795_PD_A3VP>; + resets = <&cpg 609>; + }; + + vspd3: vsp@fea38000 { + compatible = "renesas,vsp2"; + reg = <0 0xfea38000 0 0x4000>; + interrupts = ; + clocks = <&cpg CPG_MOD 620>; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 620>; + + renesas,fcp = <&fcpvd3>; + }; + + fcpvd3: fcp@fea3f000 { + compatible = "renesas,fcpv"; + reg = <0 0xfea3f000 0 0x200>; + clocks = <&cpg CPG_MOD 600>; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 600>; + }; + + fdp1@fe948000 { + compatible = "renesas,fdp1"; + reg = <0 0xfe948000 0 0x2400>; + interrupts = ; + clocks = <&cpg CPG_MOD 117>; + power-domains = <&sysc R8A7795_PD_A3VP>; + resets = <&cpg 117>; + renesas,fcp = <&fcpf2>; + }; +}; + +&du { + compatible = "renesas,du-r8a7795"; + vsps = <&vspd0 &vspd1 &vspd2 &vspd3>; +}; diff --git a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts index ab352159de6572..95fe207cb6a3fd 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts +++ b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts @@ -9,24 +9,16 @@ * kind, whether express or implied. */ +#define CPG_AUDIO_CLK_I R8A7795_CLK_S0D4 + /dts-v1/; -#include "r8a7795.dtsi" -#include -#include +#include "r8a7795-es1.dtsi" +#include "ulcb.dtsi" / { - model = "Renesas H3ULCB board based on r8a7795"; + model = "Renesas H3ULCB board based on r8a7795 ES1.x"; compatible = "renesas,h3ulcb", "renesas,r8a7795"; - aliases { - serial0 = &scif2; - ethernet0 = &avb; - }; - - chosen { - stdout-path = "serial0:115200n8"; - }; - memory@48000000 { device_type = "memory"; /* first 128MB is reserved for secure area. */ @@ -47,330 +39,4 @@ device_type = "memory"; reg = <0x7 0x00000000 0x0 0x40000000>; }; - - leds { - compatible = "gpio-leds"; - - led5 { - gpios = <&gpio6 12 GPIO_ACTIVE_HIGH>; - }; - led6 { - gpios = <&gpio6 13 GPIO_ACTIVE_HIGH>; - }; - }; - - keyboard { - compatible = "gpio-keys"; - - key-1 { - linux,code = ; - label = "SW3"; - wakeup-source; - debounce-interval = <20>; - gpios = <&gpio6 11 GPIO_ACTIVE_LOW>; - }; - }; - - x12_clk: x12 { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <24576000>; - }; - - reg_1p8v: regulator0 { - compatible = "regulator-fixed"; - regulator-name = "fixed-1.8V"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - regulator-always-on; - }; - - reg_3p3v: regulator1 { - compatible = "regulator-fixed"; - regulator-name = "fixed-3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - - vcc_sdhi0: regulator-vcc-sdhi0 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI0 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi0: regulator-vccq-sdhi0 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI0 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; - }; - - audio_clkout: audio-clkout { - /* - * This is same as <&rcar_sound 0> - * but needed to avoid cs2000/rcar_sound probe dead-lock - */ - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <11289600>; - }; - - rsnd_ak4613: sound { - compatible = "simple-audio-card"; - - simple-audio-card,format = "left_j"; - simple-audio-card,bitclock-master = <&sndcpu>; - simple-audio-card,frame-master = <&sndcpu>; - - sndcpu: simple-audio-card,cpu { - sound-dai = <&rcar_sound>; - }; - - sndcodec: simple-audio-card,codec { - sound-dai = <&ak4613>; - }; - }; -}; - -&extal_clk { - clock-frequency = <16666666>; -}; - -&extalr_clk { - clock-frequency = <32768>; -}; - -&pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - - scif2_pins: scif2 { - groups = "scif2_data_a"; - function = "scif2"; - }; - - scif_clk_pins: scif_clk { - groups = "scif_clk_a"; - function = "scif_clk"; - }; - - i2c2_pins: i2c2 { - groups = "i2c2_a"; - function = "i2c2"; - }; - - avb_pins: avb { - groups = "avb_mdc"; - function = "avb"; - }; - - sdhi0_pins: sd0 { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <3300>; - }; - - sdhi0_pins_uhs: sd0_uhs { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <1800>; - }; - - sdhi2_pins: sd2 { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <3300>; - }; - - sdhi2_pins_uhs: sd2_uhs { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <1800>; - }; - - sound_pins: sound { - groups = "ssi01239_ctrl", "ssi0_data", "ssi1_data_a"; - function = "ssi"; - }; - - sound_clk_pins: sound-clk { - groups = "audio_clk_a_a", "audio_clk_b_a", "audio_clk_c_a", - "audio_clkout_a", "audio_clkout3_a"; - function = "audio_clk"; - }; - - usb1_pins: usb1 { - groups = "usb1"; - function = "usb1"; - }; -}; - -&scif2 { - pinctrl-0 = <&scif2_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - -&scif_clk { - clock-frequency = <14745600>; -}; - -&i2c2 { - pinctrl-0 = <&i2c2_pins>; - pinctrl-names = "default"; - - status = "okay"; - - clock-frequency = <100000>; - - ak4613: codec@10 { - compatible = "asahi-kasei,ak4613"; - #sound-dai-cells = <0>; - reg = <0x10>; - clocks = <&rcar_sound 3>; - - asahi-kasei,in1-single-end; - asahi-kasei,in2-single-end; - asahi-kasei,out1-single-end; - asahi-kasei,out2-single-end; - asahi-kasei,out3-single-end; - asahi-kasei,out4-single-end; - asahi-kasei,out5-single-end; - asahi-kasei,out6-single-end; - }; - - cs2000: clk-multiplier@4f { - #clock-cells = <0>; - compatible = "cirrus,cs2000-cp"; - reg = <0x4f>; - clocks = <&audio_clkout>, <&x12_clk>; - clock-names = "clk_in", "ref_clk"; - - assigned-clocks = <&cs2000>; - assigned-clock-rates = <24576000>; /* 1/1 divide */ - }; -}; - -&rcar_sound { - pinctrl-0 = <&sound_pins &sound_clk_pins>; - pinctrl-names = "default"; - - /* Single DAI */ - #sound-dai-cells = <0>; - - /* audio_clkout0/1/2/3 */ - #clock-cells = <1>; - clock-frequency = <11289600>; - - status = "okay"; - - /* update to */ - clocks = <&cpg CPG_MOD 1005>, - <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>, - <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>, - <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>, - <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>, - <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>, - <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>, - <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>, - <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>, - <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>, - <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>, - <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, - <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, - <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>, - <&audio_clk_a>, <&cs2000>, - <&audio_clk_c>, - <&cpg CPG_CORE R8A7795_CLK_S0D4>; - - rcar_sound,dai { - dai0 { - playback = <&ssi0 &src0 &dvc0>; - capture = <&ssi1 &src1 &dvc1>; - }; - }; -}; - -&sdhi0 { - pinctrl-0 = <&sdhi0_pins>; - pinctrl-1 = <&sdhi0_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi0>; - vqmmc-supply = <&vccq_sdhi0>; - cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&sdhi2 { - /* used for on-board 8bit eMMC */ - pinctrl-0 = <&sdhi2_pins>; - pinctrl-1 = <&sdhi2_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <®_3p3v>; - vqmmc-supply = <®_1p8v>; - bus-width = <8>; - non-removable; - status = "okay"; -}; - -&ssi1 { - shared-pin; -}; - -&wdt0 { - timeout-sec = <60>; - status = "okay"; -}; - -&audio_clk_a { - clock-frequency = <22579200>; -}; - -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - renesas,no-ether-link; - phy-handle = <&phy0>; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; - }; -}; - -&usb2_phy1 { - pinctrl-0 = <&usb1_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - -&ehci1 { - status = "okay"; -}; - -&ohci1 { - status = "okay"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts index 639aa085d99666..684fb3b9d15455 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts +++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts @@ -8,577 +8,108 @@ * kind, whether express or implied. */ -/* - * SSI-AK4613 - * - * This command is required when Playback/Capture - * - * amixer set "DVC Out" 100% - * amixer set "DVC In" 100% - * - * You can use Mute - * - * amixer set "DVC Out Mute" on - * amixer set "DVC In Mute" on - * - * You can use Volume Ramp - * - * amixer set "DVC Out Ramp Up Rate" "0.125 dB/64 steps" - * amixer set "DVC Out Ramp Down Rate" "0.125 dB/512 steps" - * amixer set "DVC Out Ramp" on - * aplay xxx.wav & - * amixer set "DVC Out" 80% // Volume Down - * amixer set "DVC Out" 100% // Volume Up - */ +#define CPG_AUDIO_CLK_I R8A7795_CLK_S0D4 /dts-v1/; #include "r8a7795.dtsi" -#include +#include "salvator-x.dtsi" / { - model = "Renesas Salvator-X board based on r8a7795"; + model = "Renesas Salvator-X board based on r8a7795 ES2.0+"; compatible = "renesas,salvator-x", "renesas,r8a7795"; - aliases { - serial0 = &scif2; - serial1 = &scif1; - ethernet0 = &avb; - }; - - chosen { - bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp"; - stdout-path = "serial0:115200n8"; - }; - memory@48000000 { device_type = "memory"; /* first 128MB is reserved for secure area. */ reg = <0x0 0x48000000 0x0 0x38000000>; }; - x12_clk: x12 { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <24576000>; - }; - - reg_1p8v: regulator0 { - compatible = "regulator-fixed"; - regulator-name = "fixed-1.8V"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - regulator-always-on; - }; - - reg_3p3v: regulator1 { - compatible = "regulator-fixed"; - regulator-name = "fixed-3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - - vcc_sdhi0: regulator-vcc-sdhi0 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI0 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi0: regulator-vccq-sdhi0 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI0 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; - }; - - vcc_sdhi3: regulator-vcc-sdhi3 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI3 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio3 15 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi3: regulator-vccq-sdhi3 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI3 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio3 14 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; + memory@500000000 { + device_type = "memory"; + reg = <0x5 0x00000000 0x0 0x40000000>; }; - vbus0_usb2: regulator-vbus0-usb2 { - compatible = "regulator-fixed"; - - regulator-name = "USB20_VBUS0"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - - gpio = <&gpio6 16 GPIO_ACTIVE_HIGH>; - enable-active-high; + memory@600000000 { + device_type = "memory"; + reg = <0x6 0x00000000 0x0 0x40000000>; }; - audio_clkout: audio_clkout { - /* - * This is same as <&rcar_sound 0> - * but needed to avoid cs2000/rcar_sound probe dead-lock - */ - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <11289600>; + memory@700000000 { + device_type = "memory"; + reg = <0x7 0x00000000 0x0 0x40000000>; }; +}; - rsnd_ak4613: sound { - compatible = "simple-audio-card"; - - simple-audio-card,format = "left_j"; - simple-audio-card,bitclock-master = <&sndcpu>; - simple-audio-card,frame-master = <&sndcpu>; - - sndcpu: simple-audio-card,cpu { - sound-dai = <&rcar_sound>; - }; - - sndcodec: simple-audio-card,codec { - sound-dai = <&ak4613>; - }; - }; +&du { + clocks = <&cpg CPG_MOD 724>, + <&cpg CPG_MOD 723>, + <&cpg CPG_MOD 722>, + <&cpg CPG_MOD 721>, + <&cpg CPG_MOD 727>, + <&versaclock5 1>, + <&x21_clk>, + <&x22_clk>, + <&versaclock5 2>; + clock-names = "du.0", "du.1", "du.2", "du.3", "lvds.0", + "dclkin.0", "dclkin.1", "dclkin.2", "dclkin.3"; +}; - vga-encoder { - compatible = "adi,adv7123"; +&ehci2 { + status = "okay"; +}; - ports { - #address-cells = <1>; - #size-cells = <0>; +&hdmi0 { + status = "okay"; - port@0 { - reg = <0>; - adv7123_in: endpoint { - remote-endpoint = <&du_out_rgb>; - }; - }; - port@1 { - reg = <1>; - adv7123_out: endpoint { - remote-endpoint = <&vga_in>; - }; + ports { + port@1 { + reg = <1>; + rcar_dw_hdmi0_out: endpoint { + remote-endpoint = <&hdmi0_con>; }; }; }; +}; - vga { - compatible = "vga-connector"; - - port { - vga_in: endpoint { - remote-endpoint = <&adv7123_out>; - }; - }; - }; +&hdmi0_con { + remote-endpoint = <&rcar_dw_hdmi0_out>; }; -&du { - pinctrl-0 = <&du_pins>; - pinctrl-names = "default"; +&hdmi1 { status = "okay"; ports { - port@0 { - endpoint { - remote-endpoint = <&adv7123_in>; - }; - }; - port@3 { - lvds_connector: endpoint { + port@1 { + reg = <1>; + rcar_dw_hdmi1_out: endpoint { + remote-endpoint = <&hdmi1_con>; }; }; }; }; -&extal_clk { - clock-frequency = <16666666>; +&hdmi1_con { + remote-endpoint = <&rcar_dw_hdmi1_out>; }; -&extalr_clk { - clock-frequency = <32768>; +&ohci2 { + status = "okay"; }; &pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - - scif1_pins: scif1 { - groups = "scif1_data_a", "scif1_ctrl"; - function = "scif1"; - }; - scif2_pins: scif2 { - groups = "scif2_data_a"; - function = "scif2"; - }; - scif_clk_pins: scif_clk { - groups = "scif_clk_a"; - function = "scif_clk"; - }; - - i2c2_pins: i2c2 { - groups = "i2c2_a"; - function = "i2c2"; - }; - - avb_pins: avb { - mux { - groups = "avb_link", "avb_phy_int", "avb_mdc", - "avb_mii"; - function = "avb"; - }; - - pins_mdc { - groups = "avb_mdc"; - drive-strength = <24>; - }; - - pins_mii_tx { - pins = "PIN_AVB_TX_CTL", "PIN_AVB_TXC", "PIN_AVB_TD0", - "PIN_AVB_TD1", "PIN_AVB_TD2", "PIN_AVB_TD3"; - drive-strength = <12>; - }; - }; - - du_pins: du { - groups = "du_rgb888", "du_sync", "du_oddf", "du_clk_out_0"; - function = "du"; - }; - - sdhi0_pins: sd0 { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <3300>; - }; - - sdhi0_pins_uhs: sd0_uhs { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <1800>; - }; - - sdhi2_pins: sd2 { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <3300>; - }; - - sdhi2_pins_uhs: sd2_uhs { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <1800>; - }; - - sdhi3_pins: sd3 { - groups = "sdhi3_data4", "sdhi3_ctrl"; - function = "sdhi3"; - power-source = <3300>; - }; - - sdhi3_pins_uhs: sd3_uhs { - groups = "sdhi3_data4", "sdhi3_ctrl"; - function = "sdhi3"; - power-source = <1800>; - }; - - sound_pins: sound { - groups = "ssi01239_ctrl", "ssi0_data", "ssi1_data_a"; - function = "ssi"; - }; - - sound_clk_pins: sound_clk { - groups = "audio_clk_a_a", "audio_clk_b_a", "audio_clk_c_a", - "audio_clkout_a", "audio_clkout3_a"; - function = "audio_clk"; - }; - - usb0_pins: usb0 { - groups = "usb0"; - function = "usb0"; - }; - - usb1_pins: usb1 { - mux { - groups = "usb1"; - function = "usb1"; - }; - - ovc { - pins = "GP_6_27"; - bias-pull-up; - }; - - pwen { - pins = "GP_6_26"; - bias-pull-down; - }; - }; - usb2_pins: usb2 { groups = "usb2"; function = "usb2"; }; }; -&scif1 { - pinctrl-0 = <&scif1_pins>; - pinctrl-names = "default"; - - uart-has-rtscts; - status = "okay"; -}; - -&scif2 { - pinctrl-0 = <&scif2_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - -&scif_clk { - clock-frequency = <14745600>; -}; - -&i2c2 { - pinctrl-0 = <&i2c2_pins>; - pinctrl-names = "default"; - - status = "okay"; - - clock-frequency = <100000>; - - ak4613: codec@10 { - compatible = "asahi-kasei,ak4613"; - #sound-dai-cells = <0>; - reg = <0x10>; - clocks = <&rcar_sound 3>; - - asahi-kasei,in1-single-end; - asahi-kasei,in2-single-end; - asahi-kasei,out1-single-end; - asahi-kasei,out2-single-end; - asahi-kasei,out3-single-end; - asahi-kasei,out4-single-end; - asahi-kasei,out5-single-end; - asahi-kasei,out6-single-end; - }; - - cs2000: clk_multiplier@4f { - #clock-cells = <0>; - compatible = "cirrus,cs2000-cp"; - reg = <0x4f>; - clocks = <&audio_clkout>, <&x12_clk>; - clock-names = "clk_in", "ref_clk"; - - assigned-clocks = <&cs2000>; - assigned-clock-rates = <24576000>; /* 1/1 divide */ - }; -}; - -&rcar_sound { - pinctrl-0 = <&sound_pins &sound_clk_pins>; - pinctrl-names = "default"; - - /* Single DAI */ - #sound-dai-cells = <0>; - - /* audio_clkout0/1/2/3 */ - #clock-cells = <1>; - clock-frequency = <11289600>; - - status = "okay"; - - /* update to */ - clocks = <&cpg CPG_MOD 1005>, - <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>, - <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>, - <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>, - <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>, - <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>, - <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>, - <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>, - <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>, - <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>, - <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>, - <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, - <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, - <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>, - <&audio_clk_a>, <&cs2000>, - <&audio_clk_c>, - <&cpg CPG_CORE R8A7795_CLK_S0D4>; - - rcar_sound,dai { - dai0 { - playback = <&ssi0 &src0 &dvc0>; - capture = <&ssi1 &src1 &dvc1>; - }; - }; -}; - &sata { status = "okay"; }; -&sdhi0 { - pinctrl-0 = <&sdhi0_pins>; - pinctrl-1 = <&sdhi0_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi0>; - vqmmc-supply = <&vccq_sdhi0>; - cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio3 13 GPIO_ACTIVE_HIGH>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&sdhi2 { - /* used for on-board 8bit eMMC */ - pinctrl-0 = <&sdhi2_pins>; - pinctrl-1 = <&sdhi2_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <®_3p3v>; - vqmmc-supply = <®_1p8v>; - bus-width = <8>; - non-removable; - status = "okay"; -}; - -&sdhi3 { - pinctrl-0 = <&sdhi3_pins>; - pinctrl-1 = <&sdhi3_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi3>; - vqmmc-supply = <&vccq_sdhi3>; - cd-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&ssi1 { - shared-pin; -}; - -&wdt0 { - timeout-sec = <60>; - status = "okay"; -}; - -&audio_clk_a { - clock-frequency = <22579200>; -}; - -&i2c_dvfs { - status = "okay"; -}; - -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - renesas,no-ether-link; - phy-handle = <&phy0>; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; - }; -}; - -&xhci0 { - status = "okay"; -}; - -&usb2_phy0 { - pinctrl-0 = <&usb0_pins>; - pinctrl-names = "default"; - - vbus-supply = <&vbus0_usb2>; - status = "okay"; -}; - -&usb2_phy1 { - pinctrl-0 = <&usb1_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - &usb2_phy2 { pinctrl-0 = <&usb2_pins>; pinctrl-names = "default"; status = "okay"; }; - -&ehci0 { - status = "okay"; -}; - -&ehci1 { - status = "okay"; -}; - -&ehci2 { - status = "okay"; -}; - -&ohci0 { - status = "okay"; -}; - -&ohci1 { - status = "okay"; -}; - -&ohci2 { - status = "okay"; -}; - -&hsusb { - status = "okay"; -}; - -&pcie_bus_clk { - clock-frequency = <100000000>; -}; - -&pciec0 { - status = "okay"; -}; - -&pciec1 { - status = "okay"; -}; diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index e99d6443b3e493..24c607e30009b2 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -182,7 +182,7 @@ clock-frequency = <0>; }; - soc { + soc: soc { compatible = "simple-bus"; interrupt-parent = <&gic>; @@ -398,7 +398,7 @@ #power-domain-cells = <1>; }; - pfc: pfc@e6060000 { + pfc: pin-controller@e6060000 { compatible = "renesas,pfc-r8a7795"; reg = <0 0xe6060000 0 0x50c>; }; @@ -1274,16 +1274,6 @@ status = "disabled"; }; - xhci1: usb@ee0400000 { - compatible = "renesas,xhci-r8a7795", "renesas,rcar-gen3-xhci"; - reg = <0 0xee040000 0 0xc00>; - interrupts = ; - clocks = <&cpg CPG_MOD 327>; - power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; - resets = <&cpg 327>; - status = "disabled"; - }; - usb_dmac0: dma-controller@e65a0000 { compatible = "renesas,r8a7795-usb-dmac", "renesas,usb-dmac"; @@ -1568,14 +1558,6 @@ resets = <&cpg 614>; }; - fcpf2: fcp@fe952000 { - compatible = "renesas,fcpf"; - reg = <0 0xfe952000 0 0x200>; - clocks = <&cpg CPG_MOD 613>; - power-domains = <&sysc R8A7795_PD_A3VP>; - resets = <&cpg 613>; - }; - vspbd: vsp@fe960000 { compatible = "renesas,vsp2"; reg = <0 0xfe960000 0 0x8000>; @@ -1633,25 +1615,6 @@ resets = <&cpg 610>; }; - vspi2: vsp@fe9c0000 { - compatible = "renesas,vsp2"; - reg = <0 0xfe9c0000 0 0x8000>; - interrupts = ; - clocks = <&cpg CPG_MOD 629>; - power-domains = <&sysc R8A7795_PD_A3VP>; - resets = <&cpg 629>; - - renesas,fcp = <&fcpvi2>; - }; - - fcpvi2: fcp@fe9cf000 { - compatible = "renesas,fcpv"; - reg = <0 0xfe9cf000 0 0x200>; - clocks = <&cpg CPG_MOD 609>; - power-domains = <&sysc R8A7795_PD_A3VP>; - resets = <&cpg 609>; - }; - vspd0: vsp@fea20000 { compatible = "renesas,vsp2"; reg = <0 0xfea20000 0 0x4000>; @@ -1709,25 +1672,6 @@ resets = <&cpg 601>; }; - vspd3: vsp@fea38000 { - compatible = "renesas,vsp2"; - reg = <0 0xfea38000 0 0x4000>; - interrupts = ; - clocks = <&cpg CPG_MOD 620>; - power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; - resets = <&cpg 620>; - - renesas,fcp = <&fcpvd3>; - }; - - fcpvd3: fcp@fea3f000 { - compatible = "renesas,fcpv"; - reg = <0 0xfea3f000 0 0x200>; - clocks = <&cpg CPG_MOD 600>; - power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; - resets = <&cpg 600>; - }; - fdp1@fe940000 { compatible = "renesas,fdp1"; reg = <0 0xfe940000 0 0x2400>; @@ -1748,18 +1692,57 @@ renesas,fcp = <&fcpf1>; }; - fdp1@fe948000 { - compatible = "renesas,fdp1"; - reg = <0 0xfe948000 0 0x2400>; - interrupts = ; - clocks = <&cpg CPG_MOD 117>; - power-domains = <&sysc R8A7795_PD_A3VP>; - resets = <&cpg 117>; - renesas,fcp = <&fcpf2>; + hdmi0: hdmi0@fead0000 { + compatible = "renesas,r8a7795-hdmi", "renesas,rcar-gen3-hdmi"; + reg = <0 0xfead0000 0 0x10000>; + interrupts = ; + clocks = <&cpg CPG_MOD 729>, <&cpg CPG_CORE R8A7795_CLK_HDMI>; + clock-names = "iahb", "isfr"; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 729>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dw_hdmi0_in: endpoint { + remote-endpoint = <&du_out_hdmi0>; + }; + }; + port@1 { + reg = <1>; + }; + }; + }; + + hdmi1: hdmi1@feae0000 { + compatible = "renesas,r8a7795-hdmi", "renesas,rcar-gen3-hdmi"; + reg = <0 0xfeae0000 0 0x10000>; + interrupts = ; + clocks = <&cpg CPG_MOD 728>, <&cpg CPG_CORE R8A7795_CLK_HDMI>; + clock-names = "iahb", "isfr"; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 728>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dw_hdmi1_in: endpoint { + remote-endpoint = <&du_out_hdmi1>; + }; + }; + port@1 { + reg = <1>; + }; + }; }; du: display@feb00000 { - compatible = "renesas,du-r8a7795"; reg = <0 0xfeb00000 0 0x80000>, <0 0xfeb90000 0 0x14>; reg-names = "du", "lvds.0"; @@ -1775,8 +1758,6 @@ clock-names = "du.0", "du.1", "du.2", "du.3", "lvds.0"; status = "disabled"; - vsps = <&vspd0 &vspd1 &vspd2 &vspd3>; - ports { #address-cells = <1>; #size-cells = <0>; @@ -1789,11 +1770,13 @@ port@1 { reg = <1>; du_out_hdmi0: endpoint { + remote-endpoint = <&dw_hdmi0_in>; }; }; port@2 { reg = <2>; du_out_hdmi1: endpoint { + remote-endpoint = <&dw_hdmi1_in>; }; }; port@3 { diff --git a/arch/arm64/boot/dts/renesas/r8a7796-m3ulcb.dts b/arch/arm64/boot/dts/renesas/r8a7796-m3ulcb.dts index 372b2a9447163b..38b58b7fca4bf0 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796-m3ulcb.dts +++ b/arch/arm64/boot/dts/renesas/r8a7796-m3ulcb.dts @@ -9,180 +9,24 @@ * kind, whether express or implied. */ +#define CPG_AUDIO_CLK_I R8A7796_CLK_S0D4 + /dts-v1/; #include "r8a7796.dtsi" -#include -#include +#include "ulcb.dtsi" / { model = "Renesas M3ULCB board based on r8a7796"; compatible = "renesas,m3ulcb", "renesas,r8a7796"; - aliases { - serial0 = &scif2; - }; - - chosen { - stdout-path = "serial0:115200n8"; - }; - memory@48000000 { device_type = "memory"; /* first 128MB is reserved for secure area. */ reg = <0x0 0x48000000 0x0 0x38000000>; }; - leds { - compatible = "gpio-leds"; - - led5 { - gpios = <&gpio6 12 GPIO_ACTIVE_HIGH>; - }; - led6 { - gpios = <&gpio6 13 GPIO_ACTIVE_HIGH>; - }; - }; - - keyboard { - compatible = "gpio-keys"; - - key-1 { - linux,code = ; - label = "SW3"; - wakeup-source; - debounce-interval = <20>; - gpios = <&gpio6 11 GPIO_ACTIVE_LOW>; - }; - }; - - reg_1p8v: regulator0 { - compatible = "regulator-fixed"; - regulator-name = "fixed-1.8V"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - regulator-always-on; - }; - - reg_3p3v: regulator1 { - compatible = "regulator-fixed"; - regulator-name = "fixed-3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - - vcc_sdhi0: regulator-vcc-sdhi0 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI0 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi0: regulator-vccq-sdhi0 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI0 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; - }; -}; - -&extal_clk { - clock-frequency = <16666666>; -}; - -&extalr_clk { - clock-frequency = <32768>; -}; - -&pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - - scif2_pins: scif2 { - groups = "scif2_data_a"; - function = "scif2"; - }; - - scif_clk_pins: scif_clk { - groups = "scif_clk_a"; - function = "scif_clk"; - }; - - sdhi0_pins: sd0 { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <3300>; - }; - - sdhi0_pins_uhs: sd0_uhs { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <1800>; - }; - - sdhi2_pins: sd2 { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <3300>; - }; - - sdhi2_pins_uhs: sd2_uhs { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <1800>; + memory@600000000 { + device_type = "memory"; + reg = <0x6 0x00000000 0x0 0x40000000>; }; }; - -&sdhi0 { - pinctrl-0 = <&sdhi0_pins>; - pinctrl-1 = <&sdhi0_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi0>; - vqmmc-supply = <&vccq_sdhi0>; - cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&sdhi2 { - /* used for on-board 8bit eMMC */ - pinctrl-0 = <&sdhi2_pins>; - pinctrl-1 = <&sdhi2_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <®_3p3v>; - vqmmc-supply = <®_1p8v>; - bus-width = <8>; - non-removable; - status = "okay"; -}; - -&scif2 { - pinctrl-0 = <&scif2_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - -&scif_clk { - clock-frequency = <14745600>; -}; - -&wdt0 { - timeout-sec = <60>; - status = "okay"; -}; diff --git a/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts index c9f59b6ce33f69..db4f162d6bdd2c 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts +++ b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts @@ -8,25 +8,16 @@ * kind, whether express or implied. */ +#define CPG_AUDIO_CLK_I R8A7796_CLK_S0D4 + /dts-v1/; #include "r8a7796.dtsi" -#include +#include "salvator-x.dtsi" / { model = "Renesas Salvator-X board based on r8a7796"; compatible = "renesas,salvator-x", "renesas,r8a7796"; - aliases { - serial0 = &scif2; - serial1 = &scif1; - ethernet0 = &avb; - }; - - chosen { - bootargs = "ignore_loglevel"; - stdout-path = "serial0:115200n8"; - }; - memory@48000000 { device_type = "memory"; /* first 128MB is reserved for secure area. */ @@ -37,233 +28,4 @@ device_type = "memory"; reg = <0x6 0x00000000 0x0 0x80000000>; }; - - reg_1p8v: regulator0 { - compatible = "regulator-fixed"; - regulator-name = "fixed-1.8V"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-boot-on; - regulator-always-on; - }; - - reg_3p3v: regulator1 { - compatible = "regulator-fixed"; - regulator-name = "fixed-3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-boot-on; - regulator-always-on; - }; - - vcc_sdhi0: regulator-vcc-sdhi0 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI0 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi0: regulator-vccq-sdhi0 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI0 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; - }; - - vcc_sdhi3: regulator-vcc-sdhi3 { - compatible = "regulator-fixed"; - - regulator-name = "SDHI3 Vcc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - - gpio = <&gpio3 15 GPIO_ACTIVE_HIGH>; - enable-active-high; - }; - - vccq_sdhi3: regulator-vccq-sdhi3 { - compatible = "regulator-gpio"; - - regulator-name = "SDHI3 VccQ"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <3300000>; - - gpios = <&gpio3 14 GPIO_ACTIVE_HIGH>; - gpios-states = <1>; - states = <3300000 1 - 1800000 0>; - }; -}; - -&pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - - avb_pins: avb { - groups = "avb_mdc"; - function = "avb"; - }; - - scif1_pins: scif1 { - groups = "scif1_data_a", "scif1_ctrl"; - function = "scif1"; - }; - - scif2_pins: scif2 { - groups = "scif2_data_a"; - function = "scif2"; - }; - scif_clk_pins: scif_clk { - groups = "scif_clk_a"; - function = "scif_clk"; - }; - - i2c2_pins: i2c2 { - groups = "i2c2_a"; - function = "i2c2"; - }; - - sdhi0_pins: sd0 { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <3300>; - }; - - sdhi0_pins_uhs: sd0_uhs { - groups = "sdhi0_data4", "sdhi0_ctrl"; - function = "sdhi0"; - power-source = <1800>; - }; - - sdhi2_pins: sd2 { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <3300>; - }; - - sdhi2_pins_uhs: sd2_uhs { - groups = "sdhi2_data8", "sdhi2_ctrl"; - function = "sdhi2"; - power-source = <1800>; - }; - - sdhi3_pins: sd3 { - groups = "sdhi3_data4", "sdhi3_ctrl"; - function = "sdhi3"; - power-source = <3300>; - }; - - sdhi3_pins_uhs: sd3_uhs { - groups = "sdhi3_data4", "sdhi3_ctrl"; - function = "sdhi3"; - power-source = <1800>; - }; -}; - -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - renesas,no-ether-link; - phy-handle = <&phy0>; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; - }; -}; - -&extal_clk { - clock-frequency = <16666666>; -}; - -&extalr_clk { - clock-frequency = <32768>; -}; - -&sdhi0 { - pinctrl-0 = <&sdhi0_pins>; - pinctrl-1 = <&sdhi0_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi0>; - vqmmc-supply = <&vccq_sdhi0>; - cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio3 13 GPIO_ACTIVE_HIGH>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&sdhi2 { - /* used for on-board 8bit eMMC */ - pinctrl-0 = <&sdhi2_pins>; - pinctrl-1 = <&sdhi2_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <®_3p3v>; - vqmmc-supply = <®_1p8v>; - bus-width = <8>; - non-removable; - status = "okay"; -}; - -&sdhi3 { - pinctrl-0 = <&sdhi3_pins>; - pinctrl-1 = <&sdhi3_pins_uhs>; - pinctrl-names = "default", "state_uhs"; - - vmmc-supply = <&vcc_sdhi3>; - vqmmc-supply = <&vccq_sdhi3>; - cd-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; - bus-width = <4>; - sd-uhs-sdr50; - status = "okay"; -}; - -&scif1 { - pinctrl-0 = <&scif1_pins>; - pinctrl-names = "default"; - - uart-has-rtscts; - status = "okay"; -}; - -&scif2 { - pinctrl-0 = <&scif2_pins>; - pinctrl-names = "default"; - status = "okay"; -}; - -&scif_clk { - clock-frequency = <14745600>; -}; - -&i2c2 { - pinctrl-0 = <&i2c2_pins>; - pinctrl-names = "default"; - - status = "okay"; -}; - -&wdt0 { - timeout-sec = <60>; - status = "okay"; -}; - -&i2c_dvfs { - status = "okay"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index 2ec1ed5f499165..b418a66f4ceccb 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -120,6 +120,29 @@ clock-frequency = <0>; }; + /* + * The external audio clocks are configured as 0 Hz fixed frequency + * clocks by default. + * Boards that provide audio clocks should override them. + */ + audio_clk_a: audio_clk_a { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + audio_clk_b: audio_clk_b { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + audio_clk_c: audio_clk_c { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + /* External CAN clock - to be overridden by boards that provide it */ can_clk: can { compatible = "fixed-clock"; @@ -134,6 +157,13 @@ clock-frequency = <0>; }; + /* External PCIe clock - can be overridden by the board */ + pcie_bus_clk: pcie_bus { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + soc { compatible = "simple-bus"; interrupt-parent = <&gic>; @@ -365,6 +395,76 @@ status = "disabled"; }; + pwm0: pwm@e6e30000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e30000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm1: pwm@e6e31000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e31000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm2: pwm@e6e32000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e32000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm3: pwm@e6e33000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e33000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm4: pwm@e6e34000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e34000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm5: pwm@e6e35000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e35000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + + pwm6: pwm@e6e36000 { + compatible = "renesas,pwm-r8a7796", "renesas,pwm-rcar"; + reg = <0 0xe6e36000 0 8>; + #pwm-cells = <2>; + clocks = <&cpg CPG_MOD 523>; + resets = <&cpg 523>; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + }; + i2c0: i2c@e6500000 { #address-cells = <1>; #size-cells = <0>; @@ -931,6 +1031,106 @@ dma-channels = <16>; }; + audma0: dma-controller@ec700000 { + compatible = "renesas,dmac-r8a7796", + "renesas,rcar-dmac"; + reg = <0 0xec700000 0 0x10000>; + interrupts = ; + interrupt-names = "error", + "ch0", "ch1", "ch2", "ch3", + "ch4", "ch5", "ch6", "ch7", + "ch8", "ch9", "ch10", "ch11", + "ch12", "ch13", "ch14", "ch15"; + clocks = <&cpg CPG_MOD 502>; + clock-names = "fck"; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + resets = <&cpg 502>; + #dma-cells = <1>; + dma-channels = <16>; + }; + + audma1: dma-controller@ec720000 { + compatible = "renesas,dmac-r8a7796", + "renesas,rcar-dmac"; + reg = <0 0xec720000 0 0x10000>; + interrupts = ; + interrupt-names = "error", + "ch0", "ch1", "ch2", "ch3", + "ch4", "ch5", "ch6", "ch7", + "ch8", "ch9", "ch10", "ch11", + "ch12", "ch13", "ch14", "ch15"; + clocks = <&cpg CPG_MOD 501>; + clock-names = "fck"; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + resets = <&cpg 501>; + #dma-cells = <1>; + dma-channels = <16>; + }; + + hsusb: usb@e6590000 { + /* placeholder */ + }; + + xhci0: usb@ee000000 { + /* placeholder */ + }; + + ohci0: usb@ee080000 { + /* placeholder */ + }; + + ehci0: usb@ee080100 { + /* placeholder */ + }; + + usb2_phy0: usb-phy@ee080200 { + /* placeholder */ + }; + + ohci1: usb@ee0a0000 { + /* placeholder */ + }; + + ehci1: usb@ee0a0100 { + /* placeholder */ + }; + + usb2_phy1: usb-phy@ee0a0200 { + /* placeholder */ + }; + sdhi0: sd@ee100000 { compatible = "renesas,sdhi-r8a7796"; reg = <0 0xee100000 0 0x2000>; @@ -1033,5 +1233,214 @@ }; }; }; + + rcar_sound: sound@ec500000 { + /* + * #sound-dai-cells is required + * + * Single DAI : #sound-dai-cells = <0>; <&rcar_sound>; + * Multi DAI : #sound-dai-cells = <1>; <&rcar_sound N>; + */ + /* + * #clock-cells is required for audio_clkout0/1/2/3 + * + * clkout : #clock-cells = <0>; <&rcar_sound>; + * clkout0/1/2/3: #clock-cells = <1>; <&rcar_sound N>; + */ + compatible = "renesas,rcar_sound-r8a7796", "renesas,rcar_sound-gen3"; + reg = <0 0xec500000 0 0x1000>, /* SCU */ + <0 0xec5a0000 0 0x100>, /* ADG */ + <0 0xec540000 0 0x1000>, /* SSIU */ + <0 0xec541000 0 0x280>, /* SSI */ + <0 0xec740000 0 0x200>; /* Audio DMAC peri peri*/ + reg-names = "scu", "adg", "ssiu", "ssi", "audmapp"; + + clocks = <&cpg CPG_MOD 1005>, + <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>, + <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>, + <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>, + <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>, + <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>, + <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>, + <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>, + <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>, + <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>, + <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>, + <&audio_clk_a>, <&audio_clk_b>, + <&audio_clk_c>, + <&cpg CPG_CORE R8A7796_CLK_S0D4>; + clock-names = "ssi-all", + "ssi.9", "ssi.8", "ssi.7", "ssi.6", + "ssi.5", "ssi.4", "ssi.3", "ssi.2", + "ssi.1", "ssi.0", + "src.9", "src.8", "src.7", "src.6", + "src.5", "src.4", "src.3", "src.2", + "src.1", "src.0", + "mix.1", "mix.0", + "ctu.1", "ctu.0", + "dvc.0", "dvc.1", + "clk_a", "clk_b", "clk_c", "clk_i"; + power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; + status = "disabled"; + + rcar_sound,dvc { + dvc0: dvc-0 { + dmas = <&audma1 0xbc>; + dma-names = "tx"; + }; + dvc1: dvc-1 { + dmas = <&audma1 0xbe>; + dma-names = "tx"; + }; + }; + + rcar_sound,mix { + mix0: mix-0 { }; + mix1: mix-1 { }; + }; + + rcar_sound,ctu { + ctu00: ctu-0 { }; + ctu01: ctu-1 { }; + ctu02: ctu-2 { }; + ctu03: ctu-3 { }; + ctu10: ctu-4 { }; + ctu11: ctu-5 { }; + ctu12: ctu-6 { }; + ctu13: ctu-7 { }; + }; + + rcar_sound,src { + src0: src-0 { + interrupts = ; + dmas = <&audma0 0x85>, <&audma1 0x9a>; + dma-names = "rx", "tx"; + }; + src1: src-1 { + interrupts = ; + dmas = <&audma0 0x87>, <&audma1 0x9c>; + dma-names = "rx", "tx"; + }; + src2: src-2 { + interrupts = ; + dmas = <&audma0 0x89>, <&audma1 0x9e>; + dma-names = "rx", "tx"; + }; + src3: src-3 { + interrupts = ; + dmas = <&audma0 0x8b>, <&audma1 0xa0>; + dma-names = "rx", "tx"; + }; + src4: src-4 { + interrupts = ; + dmas = <&audma0 0x8d>, <&audma1 0xb0>; + dma-names = "rx", "tx"; + }; + src5: src-5 { + interrupts = ; + dmas = <&audma0 0x8f>, <&audma1 0xb2>; + dma-names = "rx", "tx"; + }; + src6: src-6 { + interrupts = ; + dmas = <&audma0 0x91>, <&audma1 0xb4>; + dma-names = "rx", "tx"; + }; + src7: src-7 { + interrupts = ; + dmas = <&audma0 0x93>, <&audma1 0xb6>; + dma-names = "rx", "tx"; + }; + src8: src-8 { + interrupts = ; + dmas = <&audma0 0x95>, <&audma1 0xb8>; + dma-names = "rx", "tx"; + }; + src9: src-9 { + interrupts = ; + dmas = <&audma0 0x97>, <&audma1 0xba>; + dma-names = "rx", "tx"; + }; + }; + + rcar_sound,ssi { + ssi0: ssi-0 { + interrupts = ; + dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi1: ssi-1 { + interrupts = ; + dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi2: ssi-2 { + interrupts = ; + dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi3: ssi-3 { + interrupts = ; + dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi4: ssi-4 { + interrupts = ; + dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi5: ssi-5 { + interrupts = ; + dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi6: ssi-6 { + interrupts = ; + dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi7: ssi-7 { + interrupts = ; + dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi8: ssi-8 { + interrupts = ; + dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + ssi9: ssi-9 { + interrupts = ; + dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>; + dma-names = "rx", "tx", "rxu", "txu"; + }; + }; + }; + + pciec0: pcie@fe000000 { + /* placeholder */ + }; + + pciec1: pcie@ee800000 { + /* placeholder */ + }; + + du: display@feb00000 { + /* placeholder */ + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + du_out_rgb: endpoint { + }; + }; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/renesas/salvator-x.dtsi b/arch/arm64/boot/dts/renesas/salvator-x.dtsi new file mode 100644 index 00000000000000..937bdf8842f2e6 --- /dev/null +++ b/arch/arm64/boot/dts/renesas/salvator-x.dtsi @@ -0,0 +1,644 @@ +/* + * Device Tree Source for the Salvator-X board + * + * Copyright (C) 2015-2016 Renesas Electronics Corp. + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +/* + * SSI-AK4613 + * + * This command is required when Playback/Capture + * + * amixer set "DVC Out" 100% + * amixer set "DVC In" 100% + * + * You can use Mute + * + * amixer set "DVC Out Mute" on + * amixer set "DVC In Mute" on + * + * You can use Volume Ramp + * + * amixer set "DVC Out Ramp Up Rate" "0.125 dB/64 steps" + * amixer set "DVC Out Ramp Down Rate" "0.125 dB/512 steps" + * amixer set "DVC Out Ramp" on + * aplay xxx.wav & + * amixer set "DVC Out" 80% // Volume Down + * amixer set "DVC Out" 100% // Volume Up + */ + +#include + +/ { + model = "Renesas Salvator-X board"; + compatible = "renesas,salvator-x"; + + aliases { + serial0 = &scif2; + serial1 = &scif1; + ethernet0 = &avb; + }; + + chosen { + bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp"; + stdout-path = "serial0:115200n8"; + }; + + audio_clkout: audio_clkout { + /* + * This is same as <&rcar_sound 0> + * but needed to avoid cs2000/rcar_sound probe dead-lock + */ + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <11289600>; + }; + + backlight: backlight { + compatible = "pwm-backlight"; + pwms = <&pwm1 0 50000>; + + brightness-levels = <256 128 64 16 8 4 0>; + default-brightness-level = <6>; + + enable-gpios = <&gpio6 7 GPIO_ACTIVE_HIGH>; + }; + + reg_1p8v: regulator0 { + compatible = "regulator-fixed"; + regulator-name = "fixed-1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_3p3v: regulator1 { + compatible = "regulator-fixed"; + regulator-name = "fixed-3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + rsnd_ak4613: sound { + compatible = "simple-audio-card"; + + simple-audio-card,format = "left_j"; + simple-audio-card,bitclock-master = <&sndcpu>; + simple-audio-card,frame-master = <&sndcpu>; + + sndcpu: simple-audio-card,cpu { + sound-dai = <&rcar_sound>; + }; + + sndcodec: simple-audio-card,codec { + sound-dai = <&ak4613>; + }; + }; + + vbus0_usb2: regulator-vbus0-usb2 { + compatible = "regulator-fixed"; + + regulator-name = "USB20_VBUS0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + + gpio = <&gpio6 16 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + vcc_sdhi0: regulator-vcc-sdhi0 { + compatible = "regulator-fixed"; + + regulator-name = "SDHI0 Vcc"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + vccq_sdhi0: regulator-vccq-sdhi0 { + compatible = "regulator-gpio"; + + regulator-name = "SDHI0 VccQ"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + + gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; + gpios-states = <1>; + states = <3300000 1 + 1800000 0>; + }; + + vcc_sdhi3: regulator-vcc-sdhi3 { + compatible = "regulator-fixed"; + + regulator-name = "SDHI3 Vcc"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&gpio3 15 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + vccq_sdhi3: regulator-vccq-sdhi3 { + compatible = "regulator-gpio"; + + regulator-name = "SDHI3 VccQ"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + + gpios = <&gpio3 14 GPIO_ACTIVE_HIGH>; + gpios-states = <1>; + states = <3300000 1 + 1800000 0>; + }; + + hdmi0-out { + compatible = "hdmi-connector"; + label = "HDMI0 OUT"; + type = "a"; + + port { + hdmi0_con: endpoint { + }; + }; + }; + + hdmi1-out { + compatible = "hdmi-connector"; + label = "HDMI1 OUT"; + type = "a"; + + port { + hdmi1_con: endpoint { + }; + }; + }; + + vga { + compatible = "vga-connector"; + + port { + vga_in: endpoint { + remote-endpoint = <&adv7123_out>; + }; + }; + }; + + vga-encoder { + compatible = "adi,adv7123"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + adv7123_in: endpoint { + remote-endpoint = <&du_out_rgb>; + }; + }; + port@1 { + reg = <1>; + adv7123_out: endpoint { + remote-endpoint = <&vga_in>; + }; + }; + }; + }; + + x12_clk: x12 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24576000>; + }; + + /* External DU dot clocks */ + x21_clk: x21-clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <33000000>; + }; + + x22_clk: x22-clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <33000000>; + }; + + x23_clk: x23-clock { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <25000000>; + }; +}; + +&audio_clk_a { + clock-frequency = <22579200>; +}; + +&avb { + pinctrl-0 = <&avb_pins>; + pinctrl-names = "default"; + renesas,no-ether-link; + phy-handle = <&phy0>; + status = "okay"; + + phy0: ethernet-phy@0 { + rxc-skew-ps = <1500>; + reg = <0>; + interrupt-parent = <&gpio2>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + }; +}; + +&du { + pinctrl-0 = <&du_pins>; + pinctrl-names = "default"; + status = "okay"; + + ports { + port@0 { + endpoint { + remote-endpoint = <&adv7123_in>; + }; + }; + port@3 { + lvds_connector: endpoint { + }; + }; + }; +}; + +&ehci0 { + status = "okay"; +}; + +&ehci1 { + status = "okay"; +}; + +&extal_clk { + clock-frequency = <16666666>; +}; + +&extalr_clk { + clock-frequency = <32768>; +}; + +&hsusb { + status = "okay"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_pins>; + pinctrl-names = "default"; + + status = "okay"; + + clock-frequency = <100000>; + + ak4613: codec@10 { + compatible = "asahi-kasei,ak4613"; + #sound-dai-cells = <0>; + reg = <0x10>; + clocks = <&rcar_sound 3>; + + asahi-kasei,in1-single-end; + asahi-kasei,in2-single-end; + asahi-kasei,out1-single-end; + asahi-kasei,out2-single-end; + asahi-kasei,out3-single-end; + asahi-kasei,out4-single-end; + asahi-kasei,out5-single-end; + asahi-kasei,out6-single-end; + }; + + cs2000: clk_multiplier@4f { + #clock-cells = <0>; + compatible = "cirrus,cs2000-cp"; + reg = <0x4f>; + clocks = <&audio_clkout>, <&x12_clk>; + clock-names = "clk_in", "ref_clk"; + + assigned-clocks = <&cs2000>; + assigned-clock-rates = <24576000>; /* 1/1 divide */ + }; +}; + +&i2c4 { + status = "okay"; + + versaclock5: clock-generator@6a { + compatible = "idt,5p49v5923"; + reg = <0x6a>; + #clock-cells = <1>; + clocks = <&x23_clk>; + clock-names = "xin"; + }; + + csa_vdd: adc@7c { + compatible = "maxim,max9611"; + reg = <0x7c>; + + shunt-resistor-micro-ohms = <5000>; + }; + + csa_dvfs: adc@7f { + compatible = "maxim,max9611"; + reg = <0x7f>; + + shunt-resistor-micro-ohms = <5000>; + }; +}; + +&i2c_dvfs { + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&ohci1 { + status = "okay"; +}; + +&pcie_bus_clk { + clock-frequency = <100000000>; +}; + +&pciec0 { + status = "okay"; +}; + +&pciec1 { + status = "okay"; +}; + +&pfc { + pinctrl-0 = <&scif_clk_pins>; + pinctrl-names = "default"; + + avb_pins: avb { + mux { + groups = "avb_link", "avb_phy_int", "avb_mdc", + "avb_mii"; + function = "avb"; + }; + + pins_mdc { + groups = "avb_mdc"; + drive-strength = <24>; + }; + + pins_mii_tx { + pins = "PIN_AVB_TX_CTL", "PIN_AVB_TXC", "PIN_AVB_TD0", + "PIN_AVB_TD1", "PIN_AVB_TD2", "PIN_AVB_TD3"; + drive-strength = <12>; + }; + }; + + du_pins: du { + groups = "du_rgb888", "du_sync", "du_oddf", "du_clk_out_0"; + function = "du"; + }; + + i2c2_pins: i2c2 { + groups = "i2c2_a"; + function = "i2c2"; + }; + + pwm1_pins: pwm { + groups = "pwm1_a"; + function = "pwm1"; + }; + + scif1_pins: scif1 { + groups = "scif1_data_a", "scif1_ctrl"; + function = "scif1"; + }; + + scif2_pins: scif2 { + groups = "scif2_data_a"; + function = "scif2"; + }; + + scif_clk_pins: scif_clk { + groups = "scif_clk_a"; + function = "scif_clk"; + }; + + sdhi0_pins: sd0 { + groups = "sdhi0_data4", "sdhi0_ctrl"; + function = "sdhi0"; + power-source = <3300>; + }; + + sdhi0_pins_uhs: sd0_uhs { + groups = "sdhi0_data4", "sdhi0_ctrl"; + function = "sdhi0"; + power-source = <1800>; + }; + + sdhi2_pins: sd2 { + groups = "sdhi2_data8", "sdhi2_ctrl"; + function = "sdhi2"; + power-source = <3300>; + }; + + sdhi2_pins_uhs: sd2_uhs { + groups = "sdhi2_data8", "sdhi2_ctrl"; + function = "sdhi2"; + power-source = <1800>; + }; + + sdhi3_pins: sd3 { + groups = "sdhi3_data4", "sdhi3_ctrl"; + function = "sdhi3"; + power-source = <3300>; + }; + + sdhi3_pins_uhs: sd3_uhs { + groups = "sdhi3_data4", "sdhi3_ctrl"; + function = "sdhi3"; + power-source = <1800>; + }; + + sound_pins: sound { + groups = "ssi01239_ctrl", "ssi0_data", "ssi1_data_a"; + function = "ssi"; + }; + + sound_clk_pins: sound_clk { + groups = "audio_clk_a_a", "audio_clk_b_a", "audio_clk_c_a", + "audio_clkout_a", "audio_clkout3_a"; + function = "audio_clk"; + }; + + usb0_pins: usb0 { + groups = "usb0"; + function = "usb0"; + }; + + usb1_pins: usb1 { + mux { + groups = "usb1"; + function = "usb1"; + }; + + ovc { + pins = "GP_6_27"; + bias-pull-up; + }; + + pwen { + pins = "GP_6_26"; + bias-pull-down; + }; + }; +}; + +&pwm1 { + pinctrl-0 = <&pwm1_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&rcar_sound { + pinctrl-0 = <&sound_pins &sound_clk_pins>; + pinctrl-names = "default"; + + /* Single DAI */ + #sound-dai-cells = <0>; + + /* audio_clkout0/1/2/3 */ + #clock-cells = <1>; + clock-frequency = <11289600 12288000>; + + status = "okay"; + + /* update to */ + clocks = <&cpg CPG_MOD 1005>, + <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>, + <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>, + <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>, + <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>, + <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>, + <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>, + <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>, + <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>, + <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>, + <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>, + <&audio_clk_a>, <&cs2000>, + <&audio_clk_c>, + <&cpg CPG_CORE CPG_AUDIO_CLK_I>; + + rcar_sound,dai { + dai0 { + playback = <&ssi0 &src0 &dvc0>; + capture = <&ssi1 &src1 &dvc1>; + }; + }; +}; + +&scif1 { + pinctrl-0 = <&scif1_pins>; + pinctrl-names = "default"; + + uart-has-rtscts; + status = "okay"; +}; + +&scif2 { + pinctrl-0 = <&scif2_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&scif_clk { + clock-frequency = <14745600>; +}; + +&sdhi0 { + pinctrl-0 = <&sdhi0_pins>; + pinctrl-1 = <&sdhi0_pins_uhs>; + pinctrl-names = "default", "state_uhs"; + + vmmc-supply = <&vcc_sdhi0>; + vqmmc-supply = <&vccq_sdhi0>; + cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; + wp-gpios = <&gpio3 13 GPIO_ACTIVE_HIGH>; + bus-width = <4>; + sd-uhs-sdr50; + status = "okay"; +}; + +&sdhi2 { + /* used for on-board 8bit eMMC */ + pinctrl-0 = <&sdhi2_pins>; + pinctrl-1 = <&sdhi2_pins_uhs>; + pinctrl-names = "default", "state_uhs"; + + vmmc-supply = <®_3p3v>; + vqmmc-supply = <®_1p8v>; + bus-width = <8>; + mmc-hs200-1_8v; + non-removable; + status = "okay"; +}; + +&sdhi3 { + pinctrl-0 = <&sdhi3_pins>; + pinctrl-1 = <&sdhi3_pins_uhs>; + pinctrl-names = "default", "state_uhs"; + + vmmc-supply = <&vcc_sdhi3>; + vqmmc-supply = <&vccq_sdhi3>; + cd-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; + wp-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; + bus-width = <4>; + sd-uhs-sdr50; + status = "okay"; +}; + +&ssi1 { + shared-pin; +}; + +&usb2_phy0 { + pinctrl-0 = <&usb0_pins>; + pinctrl-names = "default"; + + vbus-supply = <&vbus0_usb2>; + status = "okay"; +}; + +&usb2_phy1 { + pinctrl-0 = <&usb1_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&wdt0 { + timeout-sec = <60>; + status = "okay"; +}; + +&xhci0 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi new file mode 100644 index 00000000000000..b5c6ee07d7f91d --- /dev/null +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -0,0 +1,367 @@ +/* + * Device Tree Source for the R-Car Gen3 ULCB board + * + * Copyright (C) 2016 Renesas Electronics Corp. + * Copyright (C) 2016 Cogent Embedded, Inc. + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include +#include + +/ { + model = "Renesas R-Car Gen3 ULCB board"; + + aliases { + serial0 = &scif2; + ethernet0 = &avb; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + audio_clkout: audio-clkout { + /* + * This is same as <&rcar_sound 0> + * but needed to avoid cs2000/rcar_sound probe dead-lock + */ + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <11289600>; + }; + + keyboard { + compatible = "gpio-keys"; + + key-1 { + linux,code = ; + label = "SW3"; + wakeup-source; + debounce-interval = <20>; + gpios = <&gpio6 11 GPIO_ACTIVE_LOW>; + }; + }; + + leds { + compatible = "gpio-leds"; + + led5 { + gpios = <&gpio6 12 GPIO_ACTIVE_HIGH>; + }; + led6 { + gpios = <&gpio6 13 GPIO_ACTIVE_HIGH>; + }; + }; + + reg_1p8v: regulator0 { + compatible = "regulator-fixed"; + regulator-name = "fixed-1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_3p3v: regulator1 { + compatible = "regulator-fixed"; + regulator-name = "fixed-3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + rsnd_ak4613: sound { + compatible = "simple-audio-card"; + + simple-audio-card,format = "left_j"; + simple-audio-card,bitclock-master = <&sndcpu>; + simple-audio-card,frame-master = <&sndcpu>; + + sndcpu: simple-audio-card,cpu { + sound-dai = <&rcar_sound>; + }; + + sndcodec: simple-audio-card,codec { + sound-dai = <&ak4613>; + }; + }; + + vcc_sdhi0: regulator-vcc-sdhi0 { + compatible = "regulator-fixed"; + + regulator-name = "SDHI0 Vcc"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&gpio5 2 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + vccq_sdhi0: regulator-vccq-sdhi0 { + compatible = "regulator-gpio"; + + regulator-name = "SDHI0 VccQ"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + + gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>; + gpios-states = <1>; + states = <3300000 1 + 1800000 0>; + }; + + x12_clk: x12 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24576000>; + }; +}; + +&audio_clk_a { + clock-frequency = <22579200>; +}; + +&avb { + pinctrl-0 = <&avb_pins>; + pinctrl-names = "default"; + renesas,no-ether-link; + phy-handle = <&phy0>; + status = "okay"; + + phy0: ethernet-phy@0 { + rxc-skew-ps = <1500>; + reg = <0>; + interrupt-parent = <&gpio2>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + }; +}; + +&ehci1 { + status = "okay"; +}; + +&extal_clk { + clock-frequency = <16666666>; +}; + +&extalr_clk { + clock-frequency = <32768>; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_pins>; + pinctrl-names = "default"; + + status = "okay"; + + clock-frequency = <100000>; + + ak4613: codec@10 { + compatible = "asahi-kasei,ak4613"; + #sound-dai-cells = <0>; + reg = <0x10>; + clocks = <&rcar_sound 3>; + + asahi-kasei,in1-single-end; + asahi-kasei,in2-single-end; + asahi-kasei,out1-single-end; + asahi-kasei,out2-single-end; + asahi-kasei,out3-single-end; + asahi-kasei,out4-single-end; + asahi-kasei,out5-single-end; + asahi-kasei,out6-single-end; + }; + + cs2000: clk-multiplier@4f { + #clock-cells = <0>; + compatible = "cirrus,cs2000-cp"; + reg = <0x4f>; + clocks = <&audio_clkout>, <&x12_clk>; + clock-names = "clk_in", "ref_clk"; + + assigned-clocks = <&cs2000>; + assigned-clock-rates = <24576000>; /* 1/1 divide */ + }; +}; + +&ohci1 { + status = "okay"; +}; + +&pfc { + pinctrl-0 = <&scif_clk_pins>; + pinctrl-names = "default"; + + avb_pins: avb { + mux { + groups = "avb_link", "avb_phy_int", "avb_mdc", + "avb_mii"; + function = "avb"; + }; + + pins_mdc { + groups = "avb_mdc"; + drive-strength = <24>; + }; + + pins_mii_tx { + pins = "PIN_AVB_TX_CTL", "PIN_AVB_TXC", "PIN_AVB_TD0", + "PIN_AVB_TD1", "PIN_AVB_TD2", "PIN_AVB_TD3"; + drive-strength = <12>; + }; + }; + + i2c2_pins: i2c2 { + groups = "i2c2_a"; + function = "i2c2"; + }; + + scif2_pins: scif2 { + groups = "scif2_data_a"; + function = "scif2"; + }; + + scif_clk_pins: scif_clk { + groups = "scif_clk_a"; + function = "scif_clk"; + }; + + sdhi0_pins: sd0 { + groups = "sdhi0_data4", "sdhi0_ctrl"; + function = "sdhi0"; + power-source = <3300>; + }; + + sdhi0_pins_uhs: sd0_uhs { + groups = "sdhi0_data4", "sdhi0_ctrl"; + function = "sdhi0"; + power-source = <1800>; + }; + + sdhi2_pins: sd2 { + groups = "sdhi2_data8", "sdhi2_ctrl"; + function = "sdhi2"; + power-source = <3300>; + }; + + sdhi2_pins_uhs: sd2_uhs { + groups = "sdhi2_data8", "sdhi2_ctrl"; + function = "sdhi2"; + power-source = <1800>; + }; + + sound_pins: sound { + groups = "ssi01239_ctrl", "ssi0_data", "ssi1_data_a"; + function = "ssi"; + }; + + sound_clk_pins: sound-clk { + groups = "audio_clk_a_a", "audio_clk_b_a", "audio_clk_c_a", + "audio_clkout_a", "audio_clkout3_a"; + function = "audio_clk"; + }; + + usb1_pins: usb1 { + groups = "usb1"; + function = "usb1"; + }; +}; + +&rcar_sound { + pinctrl-0 = <&sound_pins &sound_clk_pins>; + pinctrl-names = "default"; + + /* Single DAI */ + #sound-dai-cells = <0>; + + /* audio_clkout0/1/2/3 */ + #clock-cells = <1>; + clock-frequency = <11289600 12288000>; + + status = "okay"; + + /* update to */ + clocks = <&cpg CPG_MOD 1005>, + <&cpg CPG_MOD 1006>, <&cpg CPG_MOD 1007>, + <&cpg CPG_MOD 1008>, <&cpg CPG_MOD 1009>, + <&cpg CPG_MOD 1010>, <&cpg CPG_MOD 1011>, + <&cpg CPG_MOD 1012>, <&cpg CPG_MOD 1013>, + <&cpg CPG_MOD 1014>, <&cpg CPG_MOD 1015>, + <&cpg CPG_MOD 1022>, <&cpg CPG_MOD 1023>, + <&cpg CPG_MOD 1024>, <&cpg CPG_MOD 1025>, + <&cpg CPG_MOD 1026>, <&cpg CPG_MOD 1027>, + <&cpg CPG_MOD 1028>, <&cpg CPG_MOD 1029>, + <&cpg CPG_MOD 1030>, <&cpg CPG_MOD 1031>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1020>, <&cpg CPG_MOD 1021>, + <&cpg CPG_MOD 1019>, <&cpg CPG_MOD 1018>, + <&audio_clk_a>, <&cs2000>, + <&audio_clk_c>, + <&cpg CPG_CORE CPG_AUDIO_CLK_I>; + + rcar_sound,dai { + dai0 { + playback = <&ssi0 &src0 &dvc0>; + capture = <&ssi1 &src1 &dvc1>; + }; + }; +}; + +&scif2 { + pinctrl-0 = <&scif2_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&scif_clk { + clock-frequency = <14745600>; +}; + +&sdhi0 { + pinctrl-0 = <&sdhi0_pins>; + pinctrl-1 = <&sdhi0_pins_uhs>; + pinctrl-names = "default", "state_uhs"; + + vmmc-supply = <&vcc_sdhi0>; + vqmmc-supply = <&vccq_sdhi0>; + cd-gpios = <&gpio3 12 GPIO_ACTIVE_LOW>; + bus-width = <4>; + sd-uhs-sdr50; + status = "okay"; +}; + +&sdhi2 { + /* used for on-board 8bit eMMC */ + pinctrl-0 = <&sdhi2_pins>; + pinctrl-1 = <&sdhi2_pins_uhs>; + pinctrl-names = "default", "state_uhs"; + + vmmc-supply = <®_3p3v>; + vqmmc-supply = <®_1p8v>; + bus-width = <8>; + mmc-hs200-1_8v; + non-removable; + status = "okay"; +}; + +&ssi1 { + shared-pin; +}; + +&usb2_phy1 { + pinctrl-0 = <&usb1_pins>; + pinctrl-names = "default"; + + status = "okay"; +}; + +&wdt0 { + timeout-sec = <60>; + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile index b5636bba6b1c0e..bcfa53b1e6b7ef 100644 --- a/arch/arm64/boot/dts/rockchip/Makefile +++ b/arch/arm64/boot/dts/rockchip/Makefile @@ -5,6 +5,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3368-orion-r68-meta.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3368-px5-evb.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3368-r88.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-evb.dtb +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-firefly.dtb dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-gru-kevin.dtb always := $(dtb-y) diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 7e69f1fe78d69c..0be96cee27bd10 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -372,6 +372,39 @@ <32768>; }; + sdmmc: dwmmc@ff500000 { + compatible = "rockchip,rk3328-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff500000 0x0 0x4000>; + interrupts = ; + clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, + <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; + clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + fifo-depth = <0x100>; + status = "disabled"; + }; + + sdio: dwmmc@ff510000 { + compatible = "rockchip,rk3328-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff510000 0x0 0x4000>; + interrupts = ; + clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, + <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; + clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + fifo-depth = <0x100>; + status = "disabled"; + }; + + emmc: dwmmc@ff520000 { + compatible = "rockchip,rk3328-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff520000 0x0 0x4000>; + interrupts = ; + clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, + <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; + clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + fifo-depth = <0x100>; + status = "disabled"; + }; + gmac2io: ethernet@ff540000 { compatible = "rockchip,rk3328-gmac"; reg = <0x0 0xff540000 0x0 0x10000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts new file mode 100644 index 00000000000000..ba1d9810ad1e29 --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3399-firefly.dts @@ -0,0 +1,718 @@ +/* + * Copyright (c) 2017 Fuzhou Rockchip Electronics Co., Ltd. + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/dts-v1/; +#include +#include "rk3399.dtsi" + +/ { + model = "Firefly-RK3399 Board"; + compatible = "firefly,firefly-rk3399", "rockchip,rk3399"; + + backlight: backlight { + compatible = "pwm-backlight"; + enable-gpios = <&gpio1 RK_PB5 GPIO_ACTIVE_HIGH>; + pwms = <&pwm0 0 25000 0>; + brightness-levels = < + 0 1 2 3 4 5 6 7 + 8 9 10 11 12 13 14 15 + 16 17 18 19 20 21 22 23 + 24 25 26 27 28 29 30 31 + 32 33 34 35 36 37 38 39 + 40 41 42 43 44 45 46 47 + 48 49 50 51 52 53 54 55 + 56 57 58 59 60 61 62 63 + 64 65 66 67 68 69 70 71 + 72 73 74 75 76 77 78 79 + 80 81 82 83 84 85 86 87 + 88 89 90 91 92 93 94 95 + 96 97 98 99 100 101 102 103 + 104 105 106 107 108 109 110 111 + 112 113 114 115 116 117 118 119 + 120 121 122 123 124 125 126 127 + 128 129 130 131 132 133 134 135 + 136 137 138 139 140 141 142 143 + 144 145 146 147 148 149 150 151 + 152 153 154 155 156 157 158 159 + 160 161 162 163 164 165 166 167 + 168 169 170 171 172 173 174 175 + 176 177 178 179 180 181 182 183 + 184 185 186 187 188 189 190 191 + 192 193 194 195 196 197 198 199 + 200 201 202 203 204 205 206 207 + 208 209 210 211 212 213 214 215 + 216 217 218 219 220 221 222 223 + 224 225 226 227 228 229 230 231 + 232 233 234 235 236 237 238 239 + 240 241 242 243 244 245 246 247 + 248 249 250 251 252 253 254 255>; + default-brightness-level = <200>; + }; + + clkin_gmac: external-gmac-clock { + compatible = "fixed-clock"; + clock-frequency = <125000000>; + clock-output-names = "clkin_gmac"; + #clock-cells = <0>; + }; + + dc_12v: dc-12v { + compatible = "regulator-fixed"; + regulator-name = "dc_12v"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + }; + + rt5640-sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "rockchip,rt5640-codec"; + simple-audio-card,format = "i2s"; + simple-audio-card,mclk-fs = <256>; + simple-audio-card,widgets = + "Microphone", "Mic Jack", + "Headphone", "Headphone Jack"; + simple-audio-card,routing = + "Mic Jack", "MICBIAS1", + "IN1P", "Mic Jack", + "Headphone Jack", "HPOL", + "Headphone Jack", "HPOR"; + + simple-audio-card,cpu { + sound-dai = <&i2s1>; + }; + + simple-audio-card,codec { + sound-dai = <&rt5640>; + }; + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&rk808 1>; + clock-names = "ext_clock"; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_enable_h>; + + /* + * On the module itself this is one of these (depending + * on the actual card populated): + * - SDIO_RESET_L_WL_REG_ON + * - PDN (power down when low) + */ + reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>; + }; + + /* switched by pmic_sleep */ + vcc1v8_s3: vcca1v8_s3: vcc1v8-s3 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v8_s3"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&vcc_1v8>; + }; + + vcc3v3_pcie: vcc3v3-pcie-regulator { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio1 RK_PC1 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie_pwr_en>; + regulator-name = "vcc3v3_pcie"; + regulator-always-on; + regulator-boot-on; + vin-supply = <&dc_12v>; + }; + + vcc3v3_sys: vcc3v3-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_sys>; + }; + + /* Actually 3 regulators (host0, 1, 2) controlled by the same gpio */ + vcc5v0_host: vcc5v0-host-regulator { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio1 RK_PA0 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_host_en>; + regulator-name = "vcc5v0_host"; + regulator-always-on; + vin-supply = <&vcc_sys>; + }; + + vcc_sys: vcc-sys { + compatible = "regulator-fixed"; + regulator-name = "vcc_sys"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&dc_12v>; + }; + + vdd_log: vdd-log { + compatible = "pwm-regulator"; + pwms = <&pwm2 0 25000 1>; + regulator-name = "vdd_log"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1400000>; + vin-supply = <&vcc_sys>; + }; +}; + +&cpu_l0 { + cpu-supply = <&vdd_cpu_l>; +}; + +&cpu_l1 { + cpu-supply = <&vdd_cpu_l>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_l>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_l>; +}; + +&cpu_b0 { + cpu-supply = <&vdd_cpu_b>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_b>; +}; + +&emmc_phy { + status = "okay"; +}; + +&gmac { + assigned-clocks = <&cru SCLK_RMII_SRC>; + assigned-clock-parents = <&clkin_gmac>; + clock_in_out = "input"; + phy-supply = <&vcc_lan>; + phy-mode = "rgmii"; + pinctrl-names = "default"; + pinctrl-0 = <&rgmii_pins>; + snps,reset-gpio = <&gpio3 RK_PB7 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + snps,reset-delays-us = <0 10000 50000>; + tx_delay = <0x28>; + rx_delay = <0x11>; + status = "okay"; +}; + +&i2c0 { + clock-frequency = <400000>; + i2c-scl-rising-time-ns = <168>; + i2c-scl-falling-time-ns = <4>; + status = "okay"; + + rk808: pmic@1b { + compatible = "rockchip,rk808"; + reg = <0x1b>; + interrupt-parent = <&gpio1>; + interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + #clock-cells = <1>; + clock-output-names = "xin32k", "rk808-clkout2"; + pinctrl-names = "default"; + pinctrl-0 = <&pmic_int_l>; + rockchip,system-power-controller; + wakeup-source; + + vcc1-supply = <&vcc_sys>; + vcc2-supply = <&vcc_sys>; + vcc3-supply = <&vcc_sys>; + vcc4-supply = <&vcc_sys>; + vcc6-supply = <&vcc_sys>; + vcc7-supply = <&vcc_sys>; + vcc8-supply = <&vcc3v3_sys>; + vcc9-supply = <&vcc_sys>; + vcc10-supply = <&vcc_sys>; + vcc11-supply = <&vcc_sys>; + vcc12-supply = <&vcc3v3_sys>; + vddio-supply = <&vcc1v8_pmu>; + + regulators { + vdd_center: DCDC_REG1 { + regulator-name = "vdd_center"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <6001>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_cpu_l: DCDC_REG2 { + regulator-name = "vdd_cpu_l"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <750000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <6001>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_ddr: DCDC_REG3 { + regulator-name = "vcc_ddr"; + regulator-always-on; + regulator-boot-on; + regulator-state-mem { + regulator-on-in-suspend; + }; + }; + + vcc_1v8: DCDC_REG4 { + regulator-name = "vcc_1v8"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vcc1v8_dvp: LDO_REG1 { + regulator-name = "vcc1v8_dvp"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc2v8_dvp: LDO_REG2 { + regulator-name = "vcc2v8_dvp"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc1v8_pmu: LDO_REG3 { + regulator-name = "vcc1v8_pmu"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1800000>; + }; + }; + + vcc_sdio: LDO_REG4 { + regulator-name = "vcc_sdio"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3300000>; + }; + }; + + vcca3v0_codec: LDO_REG5 { + regulator-name = "vcca3v0_codec"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_1v5: LDO_REG6 { + regulator-name = "vcc_1v5"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <1500000>; + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <1500000>; + }; + }; + + vcca1v8_codec: LDO_REG7 { + regulator-name = "vcca1v8_codec"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc_3v0: LDO_REG8 { + regulator-name = "vcc_3v0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; + regulator-state-mem { + regulator-on-in-suspend; + regulator-suspend-microvolt = <3000000>; + }; + }; + + vcc3v3_s3: vcc_lan: SWITCH_REG1 { + regulator-name = "vcc3v3_s3"; + regulator-always-on; + regulator-boot-on; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vcc3v3_s0: SWITCH_REG2 { + regulator-name = "vcc3v3_s0"; + regulator-always-on; + regulator-boot-on; + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + }; + }; + + vdd_cpu_b: regulator@40 { + compatible = "silergy,syr827"; + reg = <0x40>; + fcs,suspend-voltage-selector = <0>; + regulator-name = "vdd_cpu_b"; + regulator-min-microvolt = <712500>; + regulator-max-microvolt = <1500000>; + regulator-ramp-delay = <1000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; + + vdd_gpu: regulator@41 { + compatible = "silergy,syr828"; + reg = <0x41>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_gpu"; + regulator-min-microvolt = <712500>; + regulator-max-microvolt = <1500000>; + regulator-ramp-delay = <1000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + + regulator-state-mem { + regulator-off-in-suspend; + }; + }; +}; + +&i2c1 { + i2c-scl-rising-time-ns = <300>; + i2c-scl-falling-time-ns = <15>; + status = "okay"; + + rt5640: rt5640@1c { + compatible = "realtek,rt5640"; + reg = <0x1c>; + clocks = <&cru SCLK_I2S_8CH_OUT>; + clock-names = "mclk"; + realtek,in1-differential; + #sound-dai-cells = <0>; + pinctrl-names = "default"; + pinctrl-0 = <&rt5640_hpcon>; + }; +}; + +&i2c3 { + i2c-scl-rising-time-ns = <450>; + i2c-scl-falling-time-ns = <15>; + status = "okay"; +}; + +&i2c4 { + i2c-scl-rising-time-ns = <600>; + i2c-scl-falling-time-ns = <20>; + status = "okay"; + + accelerometer@68 { + compatible = "invensense,mpu6500"; + reg = <0x68>; + interrupt-parent = <&gpio1>; + interrupts = ; + }; +}; + +&i2s0 { + rockchip,playback-channels = <8>; + rockchip,capture-channels = <8>; + #sound-dai-cells = <0>; + status = "okay"; +}; + +&i2s1 { + rockchip,playback-channels = <2>; + rockchip,capture-channels = <2>; + #sound-dai-cells = <0>; + status = "okay"; +}; + +&i2s2 { + #sound-dai-cells = <0>; + status = "okay"; +}; + +&io_domains { + status = "okay"; + + bt656-supply = <&vcc1v8_dvp>; + audio-supply = <&vcca1v8_codec>; + sdmmc-supply = <&vcc_sdio>; + gpio1830-supply = <&vcc_3v0>; +}; + +&pcie_phy { + status = "okay"; +}; + +&pcie0 { + ep-gpios = <&gpio4 RK_PD1 GPIO_ACTIVE_HIGH>; + num-lanes = <4>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie_clkreqn>; + status = "okay"; +}; + +&pmu_io_domains { + pmu1830-supply = <&vcc_3v0>; + status = "okay"; +}; + +&pinctrl { + buttons { + pwrbtn: pwrbtn { + rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + lcd-panel { + lcd_panel_reset: lcd-panel-reset { + rockchip,pins = <4 RK_PD6 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + pcie { + pcie_pwr_en: pcie-pwr-en { + rockchip,pins = <1 RK_PC1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie_3g_drv: pcie-3g-drv { + rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + pmic { + vsel1_gpio: vsel1-gpio { + rockchip,pins = <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + vsel2_gpio: vsel2-gpio { + rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_down>; + }; + }; + + sdio-pwrseq { + wifi_enable_h: wifi-enable-h { + rockchip,pins = <0 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + rt5640 { + rt5640_hpcon: rt5640-hpcon { + rockchip,pins = <4 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + pmic { + pmic_int_l: pmic-int-l { + rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + usb2 { + vcc5v0_host_en: vcc5v0-host-en { + rockchip,pins = <1 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +}; + +&pwm0 { + status = "okay"; +}; + +&pwm2 { + status = "okay"; +}; + +&saradc { + vref-supply = <&vcca1v8_s3>; + status = "okay"; +}; + +&sdhci { + bus-width = <8>; + keep-power-in-suspend; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + status = "okay"; +}; + +&tsadc { + /* tshut mode 0:CRU 1:GPIO */ + rockchip,hw-tshut-mode = <1>; + /* tshut polarity 0:LOW 1:HIGH */ + rockchip,hw-tshut-polarity = <1>; + status = "okay"; +}; + +&u2phy0 { + status = "okay"; + + u2phy0_otg: otg-port { + status = "okay"; + }; + + u2phy0_host: host-port { + phy-supply = <&vcc5v0_host>; + status = "okay"; + }; +}; + +&u2phy1 { + status = "okay"; + + u2phy1_otg: otg-port { + status = "okay"; + }; + + u2phy1_host: host-port { + phy-supply = <&vcc5v0_host>; + status = "okay"; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_xfer &uart0_cts>; + status = "okay"; +}; + +&uart2 { + status = "okay"; +}; + +&usb_host0_ehci { + status = "okay"; +}; + +&usb_host0_ohci { + status = "okay"; +}; + +&usb_host1_ehci { + status = "okay"; +}; + +&usb_host1_ohci { + status = "okay"; +}; + +&usbdrd3_0 { + status = "okay"; +}; + +&usbdrd_dwc3_0 { + status = "okay"; + dr_mode = "otg"; +}; + +&usbdrd3_1 { + status = "okay"; +}; + +&usbdrd_dwc3_1 { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 0d960b7f7625e6..eb505934402311 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -44,7 +44,7 @@ #include #include "rk3399.dtsi" -#include "rk3399-opp.dtsi" +#include "rk3399-op1-opp.dtsi" / { chosen { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-op1-opp.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-op1-opp.dtsi new file mode 100644 index 00000000000000..be7fe635f7c15f --- /dev/null +++ b/arch/arm64/boot/dts/rockchip/rk3399-op1-opp.dtsi @@ -0,0 +1,145 @@ +/* + * Copyright (c) 2016-2017 Fuzhou Rockchip Electronics Co., Ltd + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +/ { + cluster0_opp: opp-table0 { + compatible = "operating-points-v2"; + opp-shared; + + opp00 { + opp-hz = /bits/ 64 <408000000>; + opp-microvolt = <800000>; + clock-latency-ns = <40000>; + }; + opp01 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <825000>; + }; + opp02 { + opp-hz = /bits/ 64 <816000000>; + opp-microvolt = <850000>; + }; + opp03 { + opp-hz = /bits/ 64 <1008000000>; + opp-microvolt = <900000>; + }; + opp04 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <975000>; + }; + opp05 { + opp-hz = /bits/ 64 <1416000000>; + opp-microvolt = <1100000>; + }; + opp06 { + opp-hz = /bits/ 64 <1512000000>; + opp-microvolt = <1150000>; + }; + }; + + cluster1_opp: opp-table1 { + compatible = "operating-points-v2"; + opp-shared; + + opp00 { + opp-hz = /bits/ 64 <408000000>; + opp-microvolt = <800000>; + clock-latency-ns = <40000>; + }; + opp01 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <800000>; + }; + opp02 { + opp-hz = /bits/ 64 <816000000>; + opp-microvolt = <825000>; + }; + opp03 { + opp-hz = /bits/ 64 <1008000000>; + opp-microvolt = <850000>; + }; + opp04 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <900000>; + }; + opp05 { + opp-hz = /bits/ 64 <1416000000>; + opp-microvolt = <975000>; + }; + opp06 { + opp-hz = /bits/ 64 <1608000000>; + opp-microvolt = <1050000>; + }; + opp07 { + opp-hz = /bits/ 64 <1800000000>; + opp-microvolt = <1150000>; + }; + opp08 { + opp-hz = /bits/ 64 <2016000000>; + opp-microvolt = <1250000>; + }; + }; +}; + +&cpu_l0 { + operating-points-v2 = <&cluster0_opp>; +}; + +&cpu_l1 { + operating-points-v2 = <&cluster0_opp>; +}; + +&cpu_l2 { + operating-points-v2 = <&cluster0_opp>; +}; + +&cpu_l3 { + operating-points-v2 = <&cluster0_opp>; +}; + +&cpu_b0 { + operating-points-v2 = <&cluster1_opp>; +}; + +&cpu_b1 { + operating-points-v2 = <&cluster1_opp>; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-opp.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-opp.dtsi index dd82e16236a8dd..c83460db130ab3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-opp.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-opp.dtsi @@ -56,22 +56,18 @@ }; opp02 { opp-hz = /bits/ 64 <816000000>; - opp-microvolt = <800000>; + opp-microvolt = <850000>; }; opp03 { opp-hz = /bits/ 64 <1008000000>; - opp-microvolt = <875000>; + opp-microvolt = <925000>; }; opp04 { opp-hz = /bits/ 64 <1200000000>; - opp-microvolt = <925000>; + opp-microvolt = <1000000>; }; opp05 { opp-hz = /bits/ 64 <1416000000>; - opp-microvolt = <1050000>; - }; - opp06 { - opp-hz = /bits/ 64 <1512000000>; opp-microvolt = <1125000>; }; }; @@ -107,15 +103,11 @@ }; opp06 { opp-hz = /bits/ 64 <1608000000>; - opp-microvolt = <1075000>; + opp-microvolt = <1100000>; }; opp07 { opp-hz = /bits/ 64 <1800000000>; - opp-microvolt = <1150000>; - }; - opp08 { - opp-hz = /bits/ 64 <2016000000>; - opp-microvolt = <1250000>; + opp-microvolt = <1200000>; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index f4f3c96c798d0c..69c56f7316c457 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -56,6 +56,7 @@ #size-cells = <2>; aliases { + ethernet0 = &gmac; i2c0 = &i2c0; i2c1 = &i2c1; i2c2 = &i2c2; @@ -220,7 +221,7 @@ #size-cells = <2>; #interrupt-cells = <1>; aspm-no-l0s; - bus-range = <0x0 0x1>; + bus-range = <0x0 0x1f>; clocks = <&cru ACLK_PCIE>, <&cru ACLK_PERF_PCIE>, <&cru PCLK_PCIE>, <&cru SCLK_PCIE_PM>; clock-names = "aclk", "aclk-perf", @@ -239,8 +240,8 @@ msi-map = <0x0 &its 0x0 0x1000>; phys = <&pcie_phy>; phy-names = "pcie-phy"; - ranges = <0x83000000 0x0 0xfa000000 0x0 0xfa000000 0x0 0x600000 - 0x81000000 0x0 0xfa600000 0x0 0xfa600000 0x0 0x100000>; + ranges = <0x83000000 0x0 0xfa000000 0x0 0xfa000000 0x0 0x1e00000 + 0x81000000 0x0 0xfbe00000 0x0 0xfbe00000 0x0 0x100000>; resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>, <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>, <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>, @@ -769,11 +770,6 @@ status = "disabled"; }; - qos_sd: qos@ffa74000 { - compatible = "syscon"; - reg = <0x0 0xffa74000 0x0 0x20>; - }; - qos_emmc: qos@ffa58000 { compatible = "syscon"; reg = <0x0 0xffa58000 0x0 0x20>; @@ -784,6 +780,41 @@ reg = <0x0 0xffa5c000 0x0 0x20>; }; + qos_pcie: qos@ffa60080 { + compatible = "syscon"; + reg = <0x0 0xffa60080 0x0 0x20>; + }; + + qos_usb_host0: qos@ffa60100 { + compatible = "syscon"; + reg = <0x0 0xffa60100 0x0 0x20>; + }; + + qos_usb_host1: qos@ffa60180 { + compatible = "syscon"; + reg = <0x0 0xffa60180 0x0 0x20>; + }; + + qos_usb_otg0: qos@ffa70000 { + compatible = "syscon"; + reg = <0x0 0xffa70000 0x0 0x20>; + }; + + qos_usb_otg1: qos@ffa70080 { + compatible = "syscon"; + reg = <0x0 0xffa70080 0x0 0x20>; + }; + + qos_sd: qos@ffa74000 { + compatible = "syscon"; + reg = <0x0 0xffa74000 0x0 0x20>; + }; + + qos_sdioaudio: qos@ffa76000 { + compatible = "syscon"; + reg = <0x0 0xffa76000 0x0 0x20>; + }; + qos_hdcp: qos@ffa90000 { compatible = "syscon"; reg = <0x0 0xffa90000 0x0 0x20>; @@ -854,6 +885,11 @@ reg = <0x0 0xffad0000 0x0 0x20>; }; + qos_perihp: qos@ffad8080 { + compatible = "syscon"; + reg = <0x0 0xffad8080 0x0 0x20>; + }; + qos_gpu: qos@ffae0000 { compatible = "syscon"; reg = <0x0 0xffae0000 0x0 0x20>; @@ -1676,6 +1712,91 @@ }; }; + sdio0 { + sdio0_bus1: sdio0-bus1 { + rockchip,pins = + <2 RK_PC4 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_bus4: sdio0-bus4 { + rockchip,pins = + <2 RK_PC4 RK_FUNC_1 &pcfg_pull_up>, + <2 RK_PC5 RK_FUNC_1 &pcfg_pull_up>, + <2 RK_PC6 RK_FUNC_1 &pcfg_pull_up>, + <2 RK_PC7 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_cmd: sdio0-cmd { + rockchip,pins = + <2 RK_PD0 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_clk: sdio0-clk { + rockchip,pins = + <2 RK_PD1 RK_FUNC_1 &pcfg_pull_none>; + }; + + sdio0_cd: sdio0-cd { + rockchip,pins = + <2 RK_PD2 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_pwr: sdio0-pwr { + rockchip,pins = + <2 RK_PD3 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_bkpwr: sdio0-bkpwr { + rockchip,pins = + <2 RK_PD4 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_wp: sdio0-wp { + rockchip,pins = + <0 RK_PA3 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_int: sdio0-int { + rockchip,pins = + <0 RK_PA4 RK_FUNC_1 &pcfg_pull_up>; + }; + }; + + sdmmc { + sdmmc_bus1: sdmmc-bus1 { + rockchip,pins = + <4 RK_PB0 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_bus4: sdmmc-bus4 { + rockchip,pins = + <4 RK_PB0 RK_FUNC_1 &pcfg_pull_up>, + <4 RK_PB1 RK_FUNC_1 &pcfg_pull_up>, + <4 RK_PB2 RK_FUNC_1 &pcfg_pull_up>, + <4 RK_PB3 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_clk: sdmmc-clk { + rockchip,pins = + <4 RK_PB4 RK_FUNC_1 &pcfg_pull_none>; + }; + + sdmmc_cmd: sdmmc-cmd { + rockchip,pins = + <4 RK_PB5 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_cd: sdmcc-cd { + rockchip,pins = + <0 RK_PA7 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_wp: sdmmc-wp { + rockchip,pins = + <0 RK_PB0 RK_FUNC_1 &pcfg_pull_up>; + }; + }; + sleep { ap_pwroff: ap-pwroff { rockchip,pins = <1 5 RK_FUNC_1 &pcfg_pull_none>; @@ -1691,6 +1812,11 @@ rockchip,pins = <4 21 RK_FUNC_1 &pcfg_pull_none>; }; + + spdif_bus_1: spdif-bus-1 { + rockchip,pins = + <3 RK_PC0 RK_FUNC_3 &pcfg_pull_none>; + }; }; spi0 { @@ -1950,6 +2076,19 @@ }; }; + hdmi { + hdmi_i2c_xfer: hdmi-i2c-xfer { + rockchip,pins = + <4 RK_PC1 RK_FUNC_3 &pcfg_pull_none>, + <4 RK_PC0 RK_FUNC_3 &pcfg_pull_none>; + }; + + hdmi_cec: hdmi-cec { + rockchip,pins = + <4 RK_PC7 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + pcie { pcie_clkreqn: pci-clkreqn { rockchip,pins = @@ -1960,6 +2099,16 @@ rockchip,pins = <4 24 RK_FUNC_1 &pcfg_pull_none>; }; + + pcie_clkreqn_cpm: pci-clkreqn-cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + pcie_clkreqnb_cpm: pci-clkreqnb-cpm { + rockchip,pins = + <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>; + }; }; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 65cdd878cfbd60..fd7d22b8480cd1 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -68,6 +68,7 @@ CONFIG_PCIE_QCOM=y CONFIG_PCIE_ARMADA_8K=y CONFIG_PCI_AARDVARK=y CONFIG_PCIE_RCAR=y +CONFIG_PCIE_ROCKCHIP=m CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y CONFIG_ARM64_VA_BITS_48=y @@ -190,6 +191,7 @@ CONFIG_RAVB=y CONFIG_SMC91X=y CONFIG_SMSC911X=y CONFIG_STMMAC_ETH=m +CONFIG_DWMAC_SUN8I=m CONFIG_MDIO_BUS_MUX_MMIOREG=y CONFIG_MESON_GXL_PHY=m CONFIG_MICREL_PHY=y @@ -208,6 +210,8 @@ CONFIG_BRCMFMAC=m CONFIG_WL18XX=m CONFIG_WLCORE_SDIO=m CONFIG_INPUT_EVDEV=y +CONFIG_KEYBOARD_ADC=m +CONFIG_KEYBOARD_CROS_EC=y CONFIG_KEYBOARD_GPIO=y CONFIG_INPUT_MISC=y CONFIG_INPUT_PM8941_PWRKEY=y @@ -263,6 +267,7 @@ CONFIG_SPI_MESON_SPIFC=m CONFIG_SPI_ORION=y CONFIG_SPI_PL022=y CONFIG_SPI_QUP=y +CONFIG_SPI_ROCKCHIP=y CONFIG_SPI_S3C64XX=y CONFIG_SPI_SPIDEV=m CONFIG_SPMI=y @@ -292,6 +297,7 @@ CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y CONFIG_CPU_THERMAL=y CONFIG_THERMAL_EMULATION=y CONFIG_EXYNOS_THERMAL=y +CONFIG_ROCKCHIP_THERMAL=m CONFIG_WATCHDOG=y CONFIG_S3C2410_WATCHDOG=y CONFIG_MESON_GXBB_WATCHDOG=m @@ -300,12 +306,14 @@ CONFIG_RENESAS_WDT=y CONFIG_BCM2835_WDT=y CONFIG_MFD_CROS_EC=y CONFIG_MFD_CROS_EC_I2C=y +CONFIG_MFD_CROS_EC_SPI=y CONFIG_MFD_EXYNOS_LPASS=m CONFIG_MFD_HI655X_PMIC=y CONFIG_MFD_MAX77620=y CONFIG_MFD_SPMI_PMIC=y CONFIG_MFD_RK808=y CONFIG_MFD_SEC_CORE=y +CONFIG_REGULATOR_FAN53555=y CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_REGULATOR_GPIO=y CONFIG_REGULATOR_HI655X=y @@ -320,6 +328,11 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_MEDIA_ANALOG_TV_SUPPORT=y CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y CONFIG_MEDIA_CONTROLLER=y +CONFIG_MEDIA_RC_SUPPORT=y +CONFIG_RC_CORE=m +CONFIG_RC_DEVICES=y +CONFIG_RC_DECODERS=y +CONFIG_IR_MESON=m CONFIG_VIDEO_V4L2_SUBDEV_API=y # CONFIG_DVB_NET is not set CONFIG_V4L_MEM2MEM_DRIVERS=y @@ -473,8 +486,10 @@ CONFIG_ARCH_TEGRA_186_SOC=y CONFIG_EXTCON_USB_GPIO=y CONFIG_IIO=y CONFIG_EXYNOS_ADC=y +CONFIG_ROCKCHIP_SARADC=m CONFIG_PWM=y CONFIG_PWM_BCM2835=m +CONFIG_PWM_CROS_EC=m CONFIG_PWM_MESON=m CONFIG_PWM_ROCKCHIP=y CONFIG_PWM_SAMSUNG=y @@ -484,6 +499,7 @@ CONFIG_PHY_HI6220_USB=y CONFIG_PHY_SUN4I_USB=y CONFIG_PHY_ROCKCHIP_INNO_USB2=y CONFIG_PHY_ROCKCHIP_EMMC=y +CONFIG_PHY_ROCKCHIP_PCIE=m CONFIG_PHY_XGENE=y CONFIG_PHY_TEGRA_XUSB=y CONFIG_ARM_SCPI_PROTOCOL=y diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S index c98e7e849f06f4..8550408735a03e 100644 --- a/arch/arm64/crypto/sha1-ce-core.S +++ b/arch/arm64/crypto/sha1-ce-core.S @@ -82,7 +82,8 @@ ENTRY(sha1_ce_transform) ldr dgb, [x0, #16] /* load sha1_ce_state::finalize */ - ldr w4, [x0, #:lo12:sha1_ce_offsetof_finalize] + ldr_l w4, sha1_ce_offsetof_finalize, x4 + ldr w4, [x0, x4] /* load input */ 0: ld1 {v8.4s-v11.4s}, [x1], #64 @@ -132,7 +133,8 @@ CPU_LE( rev32 v11.16b, v11.16b ) * the padding is handled by the C code in that case. */ cbz x4, 3f - ldr x4, [x0, #:lo12:sha1_ce_offsetof_count] + ldr_l w4, sha1_ce_offsetof_count, x4 + ldr x4, [x0, x4] movi v9.2d, #0 mov x8, #0x80000000 movi v10.2d, #0 diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index aefda9868627bd..ea319c055f5dfb 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -17,9 +17,6 @@ #include #include -#define ASM_EXPORT(sym, val) \ - asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val)); - MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel "); MODULE_LICENSE("GPL v2"); @@ -32,6 +29,9 @@ struct sha1_ce_state { asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, int blocks); +const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count); +const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize); + static int sha1_ce_update(struct shash_desc *desc, const u8 *data, unsigned int len) { @@ -52,11 +52,6 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, struct sha1_ce_state *sctx = shash_desc_ctx(desc); bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE); - ASM_EXPORT(sha1_ce_offsetof_count, - offsetof(struct sha1_ce_state, sst.count)); - ASM_EXPORT(sha1_ce_offsetof_finalize, - offsetof(struct sha1_ce_state, finalize)); - /* * Allow the asm code to perform the finalization if there is no * partial data and the input is a round multiple of the block size. diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S index 01cfee066837cd..679c6c002f4fbe 100644 --- a/arch/arm64/crypto/sha2-ce-core.S +++ b/arch/arm64/crypto/sha2-ce-core.S @@ -88,7 +88,8 @@ ENTRY(sha2_ce_transform) ld1 {dgav.4s, dgbv.4s}, [x0] /* load sha256_ce_state::finalize */ - ldr w4, [x0, #:lo12:sha256_ce_offsetof_finalize] + ldr_l w4, sha256_ce_offsetof_finalize, x4 + ldr w4, [x0, x4] /* load input */ 0: ld1 {v16.4s-v19.4s}, [x1], #64 @@ -136,7 +137,8 @@ CPU_LE( rev32 v19.16b, v19.16b ) * the padding is handled by the C code in that case. */ cbz x4, 3f - ldr x4, [x0, #:lo12:sha256_ce_offsetof_count] + ldr_l w4, sha256_ce_offsetof_count, x4 + ldr x4, [x0, x4] movi v17.2d, #0 mov x8, #0x80000000 movi v18.2d, #0 diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 7cd587564a4176..0ed9486f75dd92 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -17,9 +17,6 @@ #include #include -#define ASM_EXPORT(sym, val) \ - asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val)); - MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel "); MODULE_LICENSE("GPL v2"); @@ -32,6 +29,11 @@ struct sha256_ce_state { asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src, int blocks); +const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state, + sst.count); +const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state, + finalize); + static int sha256_ce_update(struct shash_desc *desc, const u8 *data, unsigned int len) { @@ -52,11 +54,6 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, struct sha256_ce_state *sctx = shash_desc_ctx(desc); bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE); - ASM_EXPORT(sha256_ce_offsetof_count, - offsetof(struct sha256_ce_state, sst.count)); - ASM_EXPORT(sha256_ce_offsetof_finalize, - offsetof(struct sha256_ce_state, finalize)); - /* * Allow the asm code to perform the finalization if there is no * partial data and the input is a round multiple of the block size. diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 88808a7618167d..2ad917a475c368 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -142,6 +142,7 @@ typedef struct user_fpsimd_state elf_fpregset_t; ({ \ clear_bit(TIF_32BIT, ¤t->mm->context.flags); \ clear_thread_flag(TIF_32BIT); \ + current->personality &= ~READ_IMPLIES_EXEC; \ }) /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ @@ -187,6 +188,11 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; ((x)->e_flags & EF_ARM_EABI_MASK)) #define compat_start_thread compat_start_thread +/* + * Unlike the native SET_PERSONALITY macro, the compat version inherits + * READ_IMPLIES_EXEC across a fork() since this is the behaviour on + * arch/arm/. + */ #define COMPAT_SET_PERSONALITY(ex) \ ({ \ set_bit(TIF_32BIT, ¤t->mm->context.flags); \ diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 85c4a8981d4703..f32b42e8725dc6 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -48,16 +48,16 @@ do { \ } while (0) static inline int -futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; + int oparg = (int)(encoded_op << 8) >> 20; + int cmparg = (int)(encoded_op << 20) >> 20; int oldval = 0, ret, tmp; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; + oparg = 1U << (oparg & 0x1f); if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 29cb2ca756f6ee..4214c38d016bae 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -433,7 +433,6 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset); bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn); int aarch64_insn_patch_text_nosync(void *addr, u32 insn); -int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); s32 aarch64_insn_adrp_get_offset(u32 insn); diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 801a16dbbdf622..5b6eafccc5d8f7 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -30,5 +30,6 @@ struct stackframe { extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); +extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk); #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 817ce3365e200d..22f554320581a1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -639,8 +639,8 @@ void update_cpu_features(int cpu, * Mismatched CPU features are a recipe for disaster. Don't even * pretend to support them. */ - WARN_TAINT_ONCE(taint, TAINT_CPU_OUT_OF_SPEC, - "Unsupported CPU feature variation.\n"); + pr_warn_once("Unsupported CPU feature variation detected.\n"); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); } u64 read_sanitised_ftr_reg(u32 id) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index b884a926a632e5..cd872133e88ef8 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -255,6 +255,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) return ret; } +static int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt) { struct aarch64_insn_patch patch = { @@ -267,8 +268,8 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt) if (cnt <= 0) return -EINVAL; - return stop_machine(aarch64_insn_patch_text_cb, &patch, - cpu_online_mask); + return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch, + cpu_online_mask); } int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt) diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index 4f0e3ebfea4b4f..10828344333652 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -108,7 +108,10 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) if (!acpi_disabled) { struct pci_config_window *cfg = bridge->bus->sysdata; struct acpi_device *adev = to_acpi_device(cfg->parent); + struct device *bus_dev = &bridge->bus->dev; + ACPI_COMPANION_SET(&bridge->dev, adev); + set_dev_node(bus_dev, acpi_get_node(acpi_device_handle(adev))); } return 0; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c5c45942fb6e66..d849d9804011df 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -522,9 +522,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) pr_err("current sp %lx does not match saved sp %lx\n", orig_sp, stack_addr); pr_err("Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); + __show_regs(saved_regs); pr_err("Current registers\n"); - show_regs(regs); + __show_regs(regs); BUG(); } unpause_graph_tracing(); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index ae2a835898d71a..af1ea258c2126c 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -210,6 +210,7 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs * regs) { __show_regs(regs); + dump_backtrace(regs, NULL); } static void tls_thread_flush(void) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 2c822ef94f3414..d4b740538ad574 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -194,6 +194,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) } name = of_flat_dt_get_machine_name(); + if (!name) + return; + pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6e0e16a3a7d4b1..321119881abfed 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -961,8 +961,7 @@ void smp_send_stop(void) cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) + if (system_state <= SYSTEM_RUNNING) pr_crit("SMP: stopping secondary CPUs\n"); smp_cross_call(&mask, IPI_CPU_STOP); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 0805b44f986a57..3ebfb1d00b53ea 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -140,7 +140,7 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) } } -static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) +void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; unsigned long irq_stack_ptr; @@ -728,8 +728,6 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr) break; case BUG_TRAP_TYPE_WARN: - /* Ideally, report_bug() should backtrace for us... but no. */ - dump_backtrace(regs, NULL); break; default: diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 37b95dff0b07f4..c3f2b1048f83b9 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -250,7 +250,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, tsk->comm, task_pid_nr(tsk), inf->name, sig, addr, esr); show_pte(tsk->mm, addr); - show_regs(regs); + __show_regs(regs); } tsk->thread.fault_address = addr; diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 3f15eb193e3390..3b51876099d8af 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -108,12 +109,18 @@ void arch_pick_mmap_layout(struct mm_struct *mm) */ int valid_phys_addr_range(phys_addr_t addr, size_t size) { - if (addr < PHYS_OFFSET) - return 0; - if (addr + size > __pa(high_memory - 1) + 1) - return 0; - - return 1; + /* + * Check whether addr is covered by a memory region without the + * MEMBLOCK_NOMAP attribute, and whether that region covers the + * entire range. In theory, this could lead to false negatives + * if the range is covered by distinct but adjacent memory regions + * that only differ in other attributes. However, few of such + * attributes have been defined, and it is debatable whether it + * follows that /dev/mem read() calls should be able traverse + * such boundaries. + */ + return memblock_is_region_memory(addr, size) && + memblock_is_map_memory(addr); } /* diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0c429ec6fde810..23c2d89a362e44 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 71f930501ade7c..b1d38eeb24f6f6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -586,7 +586,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; } /* tail call */ - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: if (emit_bpf_tail_call(ctx)) return -EFAULT; break; diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig index ba4267f658af4d..3ce77f07208a35 100644 --- a/arch/blackfin/configs/BF609-EZKIT_defconfig +++ b/arch/blackfin/configs/BF609-EZKIT_defconfig @@ -105,7 +105,7 @@ CONFIG_SPI=y CONFIG_SPI_ADI_V3=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y -CONFIG_GPIO_MCP23S08=y +CONFIG_PINCTRL_MCP23S08=y # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_BFIN_WDT=y diff --git a/arch/blackfin/kernel/module.c b/arch/blackfin/kernel/module.c index 0188c933b155be..15af5768c40393 100644 --- a/arch/blackfin/kernel/module.c +++ b/arch/blackfin/kernel/module.c @@ -4,8 +4,6 @@ * Licensed under the GPL-2 or later */ -#define pr_fmt(fmt) "module %s: " fmt, mod->name - #include #include #include @@ -16,6 +14,11 @@ #include #include +#define mod_err(mod, fmt, ...) \ + pr_err("module %s: " fmt, (mod)->name, ##__VA_ARGS__) +#define mod_debug(mod, fmt, ...) \ + pr_debug("module %s: " fmt, (mod)->name, ##__VA_ARGS__) + /* Transfer the section to the L1 memory */ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, @@ -44,7 +47,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l1_inst_sram_alloc(s->sh_size); mod->arch.text_l1 = dest; if (dest == NULL) { - pr_err("L1 inst memory allocation failed\n"); + mod_err(mod, "L1 inst memory allocation failed\n"); return -1; } dma_memcpy(dest, (void *)s->sh_addr, s->sh_size); @@ -56,7 +59,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l1_data_sram_alloc(s->sh_size); mod->arch.data_a_l1 = dest; if (dest == NULL) { - pr_err("L1 data memory allocation failed\n"); + mod_err(mod, "L1 data memory allocation failed\n"); return -1; } memcpy(dest, (void *)s->sh_addr, s->sh_size); @@ -68,7 +71,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l1_data_sram_zalloc(s->sh_size); mod->arch.bss_a_l1 = dest; if (dest == NULL) { - pr_err("L1 data memory allocation failed\n"); + mod_err(mod, "L1 data memory allocation failed\n"); return -1; } @@ -77,7 +80,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l1_data_B_sram_alloc(s->sh_size); mod->arch.data_b_l1 = dest; if (dest == NULL) { - pr_err("L1 data memory allocation failed\n"); + mod_err(mod, "L1 data memory allocation failed\n"); return -1; } memcpy(dest, (void *)s->sh_addr, s->sh_size); @@ -87,7 +90,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l1_data_B_sram_alloc(s->sh_size); mod->arch.bss_b_l1 = dest; if (dest == NULL) { - pr_err("L1 data memory allocation failed\n"); + mod_err(mod, "L1 data memory allocation failed\n"); return -1; } memset(dest, 0, s->sh_size); @@ -99,7 +102,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l2_sram_alloc(s->sh_size); mod->arch.text_l2 = dest; if (dest == NULL) { - pr_err("L2 SRAM allocation failed\n"); + mod_err(mod, "L2 SRAM allocation failed\n"); return -1; } memcpy(dest, (void *)s->sh_addr, s->sh_size); @@ -111,7 +114,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l2_sram_alloc(s->sh_size); mod->arch.data_l2 = dest; if (dest == NULL) { - pr_err("L2 SRAM allocation failed\n"); + mod_err(mod, "L2 SRAM allocation failed\n"); return -1; } memcpy(dest, (void *)s->sh_addr, s->sh_size); @@ -123,7 +126,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, dest = l2_sram_zalloc(s->sh_size); mod->arch.bss_l2 = dest; if (dest == NULL) { - pr_err("L2 SRAM allocation failed\n"); + mod_err(mod, "L2 SRAM allocation failed\n"); return -1; } @@ -157,8 +160,8 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, Elf32_Sym *sym; unsigned long location, value, size; - pr_debug("applying relocate section %u to %u\n", - relsec, sechdrs[relsec].sh_info); + mod_debug(mod, "applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ @@ -174,14 +177,14 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, #ifdef CONFIG_SMP if (location >= COREB_L1_DATA_A_START) { - pr_err("cannot relocate in L1: %u (SMP kernel)\n", + mod_err(mod, "cannot relocate in L1: %u (SMP kernel)\n", ELF32_R_TYPE(rel[i].r_info)); return -ENOEXEC; } #endif - pr_debug("location is %lx, value is %lx type is %d\n", - location, value, ELF32_R_TYPE(rel[i].r_info)); + mod_debug(mod, "location is %lx, value is %lx type is %d\n", + location, value, ELF32_R_TYPE(rel[i].r_info)); switch (ELF32_R_TYPE(rel[i].r_info)) { @@ -200,12 +203,12 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, case R_BFIN_PCREL12_JUMP: case R_BFIN_PCREL12_JUMP_S: case R_BFIN_PCREL10: - pr_err("unsupported relocation: %u (no -mlong-calls?)\n", + mod_err(mod, "unsupported relocation: %u (no -mlong-calls?)\n", ELF32_R_TYPE(rel[i].r_info)); return -ENOEXEC; default: - pr_err("unknown relocation: %u\n", + mod_err(mod, "unknown relocation: %u\n", ELF32_R_TYPE(rel[i].r_info)); return -ENOEXEC; } @@ -222,7 +225,7 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, isram_memcpy((void *)location, &value, size); break; default: - pr_err("invalid relocation for %#lx\n", location); + mod_err(mod, "invalid relocation for %#lx\n", location); return -ENOEXEC; } } diff --git a/arch/blackfin/mach-bf527/boards/tll6527m.c b/arch/blackfin/mach-bf527/boards/tll6527m.c index c1acce4c2e4569..ce5488e8226ba2 100644 --- a/arch/blackfin/mach-bf527/boards/tll6527m.c +++ b/arch/blackfin/mach-bf527/boards/tll6527m.c @@ -348,14 +348,14 @@ static struct platform_device bfin_i2s = { }; #endif -#if IS_ENABLED(CONFIG_GPIO_MCP23S08) +#if IS_ENABLED(CONFIG_PINCTRL_MCP23S08) #include static const struct mcp23s08_platform_data bfin_mcp23s08_sys_gpio_info = { - .chip[0].is_present = true, + .spi_present_mask = BIT(0), .base = 0x30, }; static const struct mcp23s08_platform_data bfin_mcp23s08_usr_gpio_info = { - .chip[2].is_present = true, + .spi_present_mask = BIT(2), .base = 0x38, }; #endif @@ -423,7 +423,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .mode = SPI_CPHA | SPI_CPOL, }, #endif -#if IS_ENABLED(CONFIG_GPIO_MCP23S08) +#if IS_ENABLED(CONFIG_PINCTRL_MCP23S08) { .modalias = "mcp23s08", .platform_data = &bfin_mcp23s08_sys_gpio_info, diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c index eaec7b4832a29a..24985e658c19cd 100644 --- a/arch/blackfin/mach-bf537/boards/stamp.c +++ b/arch/blackfin/mach-bf537/boards/stamp.c @@ -22,7 +22,7 @@ #include #endif #include -#include +#include #include #include #include diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c index 9231e5a72b93e7..51157a2558241d 100644 --- a/arch/blackfin/mach-bf609/boards/ezkit.c +++ b/arch/blackfin/mach-bf609/boards/ezkit.c @@ -1887,7 +1887,7 @@ static struct platform_device i2c_bfin_twi1_device = { }; #endif -#if IS_ENABLED(CONFIG_GPIO_MCP23S08) +#if IS_ENABLED(CONFIG_PINCTRL_MCP23S08) #include static const struct mcp23s08_platform_data bfin_mcp23s08_soft_switch0 = { .base = 120, @@ -1929,7 +1929,7 @@ static struct i2c_board_info __initdata bfin_i2c_board_info0[] = { I2C_BOARD_INFO("ssm2602", 0x1b), }, #endif -#if IS_ENABLED(CONFIG_GPIO_MCP23S08) +#if IS_ENABLED(CONFIG_PINCTRL_MCP23S08) { I2C_BOARD_INFO("mcp23017", 0x21), .platform_data = (void *)&bfin_mcp23s08_soft_switch0 diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 1ccf45657472a5..e491ff08b9a947 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -98,5 +98,7 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 5de673ac9cb136..a2540e21f9192f 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -117,7 +117,7 @@ extern int valid_mmap_phys_addr_range (unsigned long pfn, size_t count); * following the barrier will arrive after all previous writes. For most * ia64 platforms, this is a simple 'mf.a' instruction. * - * See Documentation/DocBook/deviceiobook.tmpl for more information. + * See Documentation/driver-api/device-io.rst for more information. */ static inline void ___ia64_mmiowb(void) { diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 2c3f4b48042ae3..869372413333f5 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -107,4 +107,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/ia64/sn/kernel/iomv.c b/arch/ia64/sn/kernel/iomv.c index c77ebdf98119ea..2b22a71663c10e 100644 --- a/arch/ia64/sn/kernel/iomv.c +++ b/arch/ia64/sn/kernel/iomv.c @@ -63,7 +63,7 @@ EXPORT_SYMBOL(sn_io_addr); /** * __sn_mmiowb - I/O space memory barrier * - * See arch/ia64/include/asm/io.h and Documentation/DocBook/deviceiobook.tmpl + * See arch/ia64/include/asm/io.h and Documentation/driver-api/device-io.rst * for details. * * On SN2, we wait for the PIO_WRITE_STATUS SHub register to clear. diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index ae6548d29a1819..5d97890a8704d9 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -98,4 +98,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 531cb9eb3319f4..ddff1164aff018 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -349,7 +351,6 @@ CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -361,6 +362,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -414,6 +416,7 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -572,6 +575,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -590,6 +595,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index ca91d39555da2d..17384dc959a572 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -331,7 +333,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -343,6 +344,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -388,6 +390,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -531,6 +534,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -549,6 +554,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 23a3d8a691e223..53a641d62f85d6 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -340,7 +342,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_ATARI_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -352,6 +353,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -399,6 +401,7 @@ CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -552,6 +555,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -570,6 +575,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 95deb95140fe92..3925ae3a5eb32c 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -330,7 +332,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_BVME6000_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -342,6 +343,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index afae6958db2d77..f4a134b390b42a 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -331,7 +333,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -343,6 +344,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -389,6 +391,7 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -533,6 +536,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -551,6 +556,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b010734729a79e..9ed0cef632b768 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -340,7 +342,6 @@ CONFIG_MAC_SCSI=y CONFIG_SCSI_MAC_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -352,6 +353,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -408,6 +410,7 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -555,6 +558,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -573,6 +578,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 0e414549b235b0..efed0d48fd5325 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -22,6 +22,8 @@ CONFIG_UNIXWARE_DISKLABEL=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -373,7 +375,6 @@ CONFIG_BVME6000_SCSI=y CONFIG_SUN3X_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -385,6 +386,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -454,6 +456,7 @@ CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -635,6 +638,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -653,6 +658,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index b2e687a0ec3d47..9040457c7f9c1d 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68030=y @@ -329,7 +331,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME147_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -341,6 +342,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index cbd8ee24d1bc4e..8b17f00e04843b 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -330,7 +332,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME16x_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -342,6 +343,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 1e82cc9443399a..5f3718c62c85f8 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -336,7 +338,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -348,6 +349,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -398,6 +400,7 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -546,6 +549,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -564,6 +569,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index f9e77f57a97250..8c979a68fca5ae 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -26,6 +26,8 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_SUN3=y @@ -327,7 +329,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -339,6 +340,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -385,6 +387,7 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SUN is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -525,6 +528,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -542,6 +547,7 @@ CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 3c394fcfb36836..a1e79530e80650 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -26,6 +26,8 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_SUN3X=y @@ -327,7 +329,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3X_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -339,6 +340,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -385,6 +387,7 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -525,6 +528,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -543,6 +548,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c index 232a12bf3f999e..2dbbb7c66043b2 100644 --- a/arch/metag/kernel/smp.c +++ b/arch/metag/kernel/smp.c @@ -567,8 +567,7 @@ static void stop_this_cpu(void *data) { unsigned int cpu = smp_processor_id(); - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) { + if (system_state <= SYSTEM_RUNNING) { spin_lock(&stop_lock); pr_crit("CPU%u: stopping\n", cpu); dump_stack(); diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 56830ff6533335..83a4ef3a2495a2 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,14 +1,57 @@ generic-y += barrier.h +generic-y += bitops.h +generic-y += bitsperlong.h +generic-y += bug.h +generic-y += bugs.h generic-y += clkdev.h generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h +generic-y += errno.h generic-y += exec.h generic-y += extable.h +generic-y += fb.h +generic-y += fcntl.h +generic-y += hardirq.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += irq_regs.h generic-y += irq_work.h +generic-y += kdebug.h +generic-y += kmap_types.h +generic-y += kprobes.h +generic-y += linkage.h +generic-y += local.h +generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += parport.h +generic-y += percpu.h +generic-y += poll.h generic-y += preempt.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += serial.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h generic-y += syscalls.h +generic-y += termbits.h +generic-y += termios.h +generic-y += topology.h generic-y += trace_clock.h +generic-y += ucontext.h +generic-y += vga.h generic-y += word-at-a-time.h -generic-y += kprobes.h +generic-y += xor.h diff --git a/arch/microblaze/include/asm/bitops.h b/arch/microblaze/include/asm/bitops.h deleted file mode 100644 index a72468f15c8b1c..00000000000000 --- a/arch/microblaze/include/asm/bitops.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/bug.h b/arch/microblaze/include/asm/bug.h deleted file mode 100644 index b12fd89e42e913..00000000000000 --- a/arch/microblaze/include/asm/bug.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/bugs.h b/arch/microblaze/include/asm/bugs.h deleted file mode 100644 index 61791e1ad9f55c..00000000000000 --- a/arch/microblaze/include/asm/bugs.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/div64.h b/arch/microblaze/include/asm/div64.h deleted file mode 100644 index 6cd978cefb2850..00000000000000 --- a/arch/microblaze/include/asm/div64.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/emergency-restart.h b/arch/microblaze/include/asm/emergency-restart.h deleted file mode 100644 index 3711bd9d50bda1..00000000000000 --- a/arch/microblaze/include/asm/emergency-restart.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/fb.h b/arch/microblaze/include/asm/fb.h deleted file mode 100644 index 3a4988e8df4567..00000000000000 --- a/arch/microblaze/include/asm/fb.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/hardirq.h b/arch/microblaze/include/asm/hardirq.h deleted file mode 100644 index fb3c05a0cbbf11..00000000000000 --- a/arch/microblaze/include/asm/hardirq.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/irq_regs.h b/arch/microblaze/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b702704a..00000000000000 --- a/arch/microblaze/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/kdebug.h b/arch/microblaze/include/asm/kdebug.h deleted file mode 100644 index 6ece1b0376655b..00000000000000 --- a/arch/microblaze/include/asm/kdebug.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/kmap_types.h b/arch/microblaze/include/asm/kmap_types.h deleted file mode 100644 index 25975252d83dbd..00000000000000 --- a/arch/microblaze/include/asm/kmap_types.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_MICROBLAZE_KMAP_TYPES_H -#define _ASM_MICROBLAZE_KMAP_TYPES_H - -#include - -#endif /* _ASM_MICROBLAZE_KMAP_TYPES_H */ diff --git a/arch/microblaze/include/asm/linkage.h b/arch/microblaze/include/asm/linkage.h deleted file mode 100644 index 0540bbaad8978a..00000000000000 --- a/arch/microblaze/include/asm/linkage.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/local.h b/arch/microblaze/include/asm/local.h deleted file mode 100644 index c11c530f74d028..00000000000000 --- a/arch/microblaze/include/asm/local.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/local64.h b/arch/microblaze/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239b6..00000000000000 --- a/arch/microblaze/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/parport.h b/arch/microblaze/include/asm/parport.h deleted file mode 100644 index cf252af6459087..00000000000000 --- a/arch/microblaze/include/asm/parport.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/percpu.h b/arch/microblaze/include/asm/percpu.h deleted file mode 100644 index 06a959d6723478..00000000000000 --- a/arch/microblaze/include/asm/percpu.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/serial.h b/arch/microblaze/include/asm/serial.h deleted file mode 100644 index a0cb0caff15241..00000000000000 --- a/arch/microblaze/include/asm/serial.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/shmparam.h b/arch/microblaze/include/asm/shmparam.h deleted file mode 100644 index 93f30deb95d080..00000000000000 --- a/arch/microblaze/include/asm/shmparam.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/topology.h b/arch/microblaze/include/asm/topology.h deleted file mode 100644 index 5428f333a02c70..00000000000000 --- a/arch/microblaze/include/asm/topology.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/ucontext.h b/arch/microblaze/include/asm/ucontext.h deleted file mode 100644 index 9bc07b9f30fba1..00000000000000 --- a/arch/microblaze/include/asm/ucontext.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h index 032fed71223f54..9774e1d9507bae 100644 --- a/arch/microblaze/include/asm/unistd.h +++ b/arch/microblaze/include/asm/unistd.h @@ -38,6 +38,6 @@ #endif /* __ASSEMBLY__ */ -#define __NR_syscalls 398 +#define __NR_syscalls 399 #endif /* _ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/include/asm/vga.h b/arch/microblaze/include/asm/vga.h deleted file mode 100644 index 89d82fd8fcf17b..00000000000000 --- a/arch/microblaze/include/asm/vga.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/asm/xor.h b/arch/microblaze/include/asm/xor.h deleted file mode 100644 index c82eb12a5b1810..00000000000000 --- a/arch/microblaze/include/asm/xor.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/bitsperlong.h b/arch/microblaze/include/uapi/asm/bitsperlong.h deleted file mode 100644 index 6dc0bb0c13b29d..00000000000000 --- a/arch/microblaze/include/uapi/asm/bitsperlong.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/errno.h b/arch/microblaze/include/uapi/asm/errno.h deleted file mode 100644 index 4c82b503d92ffa..00000000000000 --- a/arch/microblaze/include/uapi/asm/errno.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/fcntl.h b/arch/microblaze/include/uapi/asm/fcntl.h deleted file mode 100644 index 46ab12db57397d..00000000000000 --- a/arch/microblaze/include/uapi/asm/fcntl.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/ioctl.h b/arch/microblaze/include/uapi/asm/ioctl.h deleted file mode 100644 index b279fe06dfe5be..00000000000000 --- a/arch/microblaze/include/uapi/asm/ioctl.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/ioctls.h b/arch/microblaze/include/uapi/asm/ioctls.h deleted file mode 100644 index ec34c760665eae..00000000000000 --- a/arch/microblaze/include/uapi/asm/ioctls.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/ipcbuf.h b/arch/microblaze/include/uapi/asm/ipcbuf.h deleted file mode 100644 index 84c7e51cb6d0be..00000000000000 --- a/arch/microblaze/include/uapi/asm/ipcbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/kvm_para.h b/arch/microblaze/include/uapi/asm/kvm_para.h deleted file mode 100644 index 14fab8f0b95767..00000000000000 --- a/arch/microblaze/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/mman.h b/arch/microblaze/include/uapi/asm/mman.h deleted file mode 100644 index 8eebf89f5ab178..00000000000000 --- a/arch/microblaze/include/uapi/asm/mman.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/msgbuf.h b/arch/microblaze/include/uapi/asm/msgbuf.h deleted file mode 100644 index 809134c644a677..00000000000000 --- a/arch/microblaze/include/uapi/asm/msgbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/param.h b/arch/microblaze/include/uapi/asm/param.h deleted file mode 100644 index 965d4542797590..00000000000000 --- a/arch/microblaze/include/uapi/asm/param.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/poll.h b/arch/microblaze/include/uapi/asm/poll.h deleted file mode 100644 index c98509d3149e63..00000000000000 --- a/arch/microblaze/include/uapi/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/resource.h b/arch/microblaze/include/uapi/asm/resource.h deleted file mode 100644 index 04bc4db8921b25..00000000000000 --- a/arch/microblaze/include/uapi/asm/resource.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/sembuf.h b/arch/microblaze/include/uapi/asm/sembuf.h deleted file mode 100644 index 7673b83cfef733..00000000000000 --- a/arch/microblaze/include/uapi/asm/sembuf.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/shmbuf.h b/arch/microblaze/include/uapi/asm/shmbuf.h deleted file mode 100644 index 83c05fc2de385c..00000000000000 --- a/arch/microblaze/include/uapi/asm/shmbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/siginfo.h b/arch/microblaze/include/uapi/asm/siginfo.h deleted file mode 100644 index 0815d29d82e5f5..00000000000000 --- a/arch/microblaze/include/uapi/asm/siginfo.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/signal.h b/arch/microblaze/include/uapi/asm/signal.h deleted file mode 100644 index 7b1573ce19de50..00000000000000 --- a/arch/microblaze/include/uapi/asm/signal.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/socket.h b/arch/microblaze/include/uapi/asm/socket.h deleted file mode 100644 index 6b71384b9d8b42..00000000000000 --- a/arch/microblaze/include/uapi/asm/socket.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/sockios.h b/arch/microblaze/include/uapi/asm/sockios.h deleted file mode 100644 index def6d4746ee7fe..00000000000000 --- a/arch/microblaze/include/uapi/asm/sockios.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/stat.h b/arch/microblaze/include/uapi/asm/stat.h deleted file mode 100644 index 3dc90fa92c704d..00000000000000 --- a/arch/microblaze/include/uapi/asm/stat.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/statfs.h b/arch/microblaze/include/uapi/asm/statfs.h deleted file mode 100644 index 0b91fe198c2014..00000000000000 --- a/arch/microblaze/include/uapi/asm/statfs.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/swab.h b/arch/microblaze/include/uapi/asm/swab.h deleted file mode 100644 index 7847e563ab66f1..00000000000000 --- a/arch/microblaze/include/uapi/asm/swab.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/termbits.h b/arch/microblaze/include/uapi/asm/termbits.h deleted file mode 100644 index 3935b106de79bf..00000000000000 --- a/arch/microblaze/include/uapi/asm/termbits.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/termios.h b/arch/microblaze/include/uapi/asm/termios.h deleted file mode 100644 index 280d78a9d96637..00000000000000 --- a/arch/microblaze/include/uapi/asm/termios.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h index d8086159d996df..a88b3c11cc2006 100644 --- a/arch/microblaze/include/uapi/asm/unistd.h +++ b/arch/microblaze/include/uapi/asm/unistd.h @@ -413,5 +413,6 @@ #define __NR_pkey_mprotect 395 #define __NR_pkey_alloc 396 #define __NR_pkey_free 397 +#define __NR_statx 398 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index 12e093a03e6037..e45ada8fb00669 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -65,8 +65,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, if (attrs & DMA_ATTR_SKIP_CPU_SYNC) continue; - __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, - sg->length, direction); + __dma_sync(sg_phys(sg), sg->length, direction); } return nents; diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S index 6841c2df14d9ac..c48ff4ad2070db 100644 --- a/arch/microblaze/kernel/syscall_table.S +++ b/arch/microblaze/kernel/syscall_table.S @@ -398,3 +398,4 @@ ENTRY(sys_call_table) .long sys_pkey_mprotect /* 395 */ .long sys_pkey_alloc .long sys_pkey_free + .long sys_statx diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c index 99906619271553..545ccd46edb371 100644 --- a/arch/microblaze/kernel/timer.c +++ b/arch/microblaze/kernel/timer.c @@ -178,8 +178,10 @@ static __init int xilinx_clockevent_init(void) clockevent_xilinx_timer.shift); clockevent_xilinx_timer.max_delta_ns = clockevent_delta2ns((u32)~0, &clockevent_xilinx_timer); + clockevent_xilinx_timer.max_delta_ticks = (u32)~0; clockevent_xilinx_timer.min_delta_ns = clockevent_delta2ns(1, &clockevent_xilinx_timer); + clockevent_xilinx_timer.min_delta_ticks = 1; clockevent_xilinx_timer.cpumask = cpumask_of(0); clockevents_register_device(&clockevent_xilinx_timer); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 2828ecde133d97..6abcef37ce061f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1,75 +1,75 @@ config MIPS bool default y - select ARCH_SUPPORTS_UPROBES + select ARCH_BINFMT_ELF_STATE + select ARCH_CLOCKSOURCE_DATA + select ARCH_DISCARD_MEMBLOCK + select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP - select HAVE_CONTEXT_TRACKING - select HAVE_GENERIC_DMA_COHERENT - select HAVE_IDE - select HAVE_IRQ_EXIT_ON_IRQ_STACK - select HAVE_OPROFILE - select HAVE_PERF_EVENTS - select PERF_USE_VMALLOC + select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_WANT_IPC_PARSE_VERSION + select BUILDTIME_EXTABLE_SORT + select CLONE_BACKWARDS + select CPU_PM if CPU_IDLE + select GENERIC_ATOMIC64 if !64BIT + select GENERIC_CLOCKEVENTS + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE + select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW + select GENERIC_PCI_IOMAP + select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC + select GENERIC_SMP_IDLE_THREAD + select GENERIC_TIME_VSYSCALL + select HANDLE_DOMAIN_IRQ + select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select HAVE_CBPF_JIT if !CPU_MICROMIPS - select HAVE_FUNCTION_TRACER + select HAVE_CC_STACKPROTECTOR + select HAVE_CONTEXT_TRACKING + select HAVE_COPY_THREAD_TLS + select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG + select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_C_RECORDMCOUNT select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_GENERIC_DMA_COHERENT + select HAVE_IDE + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_SYSCALL_TRACEPOINTS - select HAVE_DEBUG_KMEMLEAK - select HAVE_SYSCALL_TRACEPOINTS - select ARCH_HAS_ELF_RANDOMIZE - select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT - select RTC_LIB if !MACH_LOONGSON64 - select GENERIC_ATOMIC64 if !64BIT - select HAVE_DMA_CONTIGUOUS - select HAVE_DMA_API_DEBUG - select GENERIC_IRQ_PROBE - select GENERIC_IRQ_SHOW - select GENERIC_PCI_IOMAP - select HAVE_ARCH_JUMP_LABEL - select ARCH_WANT_IPC_PARSE_VERSION - select IRQ_FORCED_THREADING select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select ARCH_DISCARD_MEMBLOCK - select GENERIC_SMP_IDLE_THREAD - select BUILDTIME_EXTABLE_SORT - select GENERIC_CPU_AUTOPROBE - select GENERIC_CLOCKEVENTS - select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC - select GENERIC_CMOS_UPDATE select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select VIRT_TO_BUS - select MODULES_USE_ELF_REL if MODULES + select HAVE_OPROFILE + select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_VIRT_CPU_ACCOUNTING_GEN + select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES && 64BIT - select CLONE_BACKWARDS - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_CC_STACKPROTECTOR - select CPU_PM if CPU_IDLE - select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_BINFMT_ELF_STATE + select MODULES_USE_ELF_REL if MODULES + select PERF_USE_VMALLOC + select RTC_LIB if !MACH_LOONGSON64 select SYSCTL_EXCEPTION_TRACE - select HAVE_VIRT_CPU_ACCOUNTING_GEN - select HAVE_IRQ_TIME_ACCOUNTING - select GENERIC_TIME_VSYSCALL - select ARCH_CLOCKSOURCE_DATA - select HANDLE_DOMAIN_IRQ - select HAVE_EXIT_THREAD - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_COPY_THREAD_TLS + select VIRT_TO_BUS menu "Machine selection" @@ -364,6 +364,7 @@ config MACH_INGENIC select SYS_SUPPORTS_ZBOOT_UART16550 select DMA_NONCOHERENT select IRQ_MIPS_CPU + select PINCTRL select GPIOLIB select COMMON_CLK select GENERIC_IRQ_CHIP diff --git a/arch/mips/ath79/mach-pb44.c b/arch/mips/ath79/mach-pb44.c index 67b980d94fb7aa..be78298dffb4f3 100644 --- a/arch/mips/ath79/mach-pb44.c +++ b/arch/mips/ath79/mach-pb44.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include "machtypes.h" #include "dev-gpio-buttons.h" diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 1652d8d60b1e4b..fd138d9978c11f 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -29,18 +29,30 @@ &uart0 { status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart0>; }; &uart1 { status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart1>; }; &uart3 { status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart2>; }; &uart4 { status = "okay"; + + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart4>; }; &nemc { @@ -61,6 +73,13 @@ ingenic,nemc-tAW = <15>; ingenic,nemc-tSTRV = <100>; + /* + * Only CLE/ALE are needed for the devices that are connected, rather + * than the full address line set. + */ + pinctrl-names = "default"; + pinctrl-0 = <&pins_nemc>; + nand@1 { reg = <1>; @@ -69,6 +88,9 @@ nand-ecc-mode = "hw"; nand-on-flash-bbt; + pinctrl-names = "default"; + pinctrl-0 = <&pins_nemc_cs1>; + partitions { compatible = "fixed-partitions"; #address-cells = <2>; @@ -106,3 +128,41 @@ &bch { status = "okay"; }; + +&pinctrl { + pins_uart0: uart0 { + function = "uart0"; + groups = "uart0-data"; + bias-disable; + }; + + pins_uart1: uart1 { + function = "uart1"; + groups = "uart1-data"; + bias-disable; + }; + + pins_uart2: uart2 { + function = "uart2"; + groups = "uart2-data", "uart2-hwflow"; + bias-disable; + }; + + pins_uart4: uart4 { + function = "uart4"; + groups = "uart4-data"; + bias-disable; + }; + + pins_nemc: nemc { + function = "nemc"; + groups = "nemc-data", "nemc-cle-ale", "nemc-rd-we", "nemc-frd-fwe"; + bias-disable; + }; + + pins_nemc_cs1: nemc-cs1 { + function = "nemc-cs1"; + groups = "nemc-cs1"; + bias-disable; + }; +}; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 3e1587f1f77a37..2ca7ce7481f15b 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -55,6 +55,74 @@ clock-names = "rtc"; }; + pinctrl: pin-controller@10010000 { + compatible = "ingenic,jz4740-pinctrl"; + reg = <0x10010000 0x400>; + + #address-cells = <1>; + #size-cells = <0>; + + gpa: gpio@0 { + compatible = "ingenic,jz4740-gpio"; + reg = <0>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 0 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <28>; + }; + + gpb: gpio@1 { + compatible = "ingenic,jz4740-gpio"; + reg = <1>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 32 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <27>; + }; + + gpc: gpio@2 { + compatible = "ingenic,jz4740-gpio"; + reg = <2>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 64 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <26>; + }; + + gpd: gpio@3 { + compatible = "ingenic,jz4740-gpio"; + reg = <3>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 96 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <25>; + }; + }; + uart0: serial@10030000 { compatible = "ingenic,jz4740-uart"; reg = <0x10030000 0x100>; diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index b868b429add23a..4853ef67b3ab3c 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -44,6 +44,104 @@ #clock-cells = <1>; }; + pinctrl: pin-controller@10010000 { + compatible = "ingenic,jz4780-pinctrl"; + reg = <0x10010000 0x600>; + + #address-cells = <1>; + #size-cells = <0>; + + gpa: gpio@0 { + compatible = "ingenic,jz4780-gpio"; + reg = <0>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 0 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <17>; + }; + + gpb: gpio@1 { + compatible = "ingenic,jz4780-gpio"; + reg = <1>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 32 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <16>; + }; + + gpc: gpio@2 { + compatible = "ingenic,jz4780-gpio"; + reg = <2>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 64 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <15>; + }; + + gpd: gpio@3 { + compatible = "ingenic,jz4780-gpio"; + reg = <3>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 96 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <14>; + }; + + gpe: gpio@4 { + compatible = "ingenic,jz4780-gpio"; + reg = <4>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 128 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <13>; + }; + + gpf: gpio@5 { + compatible = "ingenic,jz4780-gpio"; + reg = <5>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 160 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <12>; + }; + }; + uart0: serial@10030000 { compatible = "ingenic,jz4780-uart"; reg = <0x10030000 0x100>; diff --git a/arch/mips/boot/dts/ingenic/qi_lb60.dts b/arch/mips/boot/dts/ingenic/qi_lb60.dts index be1a7d3a3e1b5a..b715ee2ac2ee9b 100644 --- a/arch/mips/boot/dts/ingenic/qi_lb60.dts +++ b/arch/mips/boot/dts/ingenic/qi_lb60.dts @@ -17,3 +17,16 @@ &rtc_dev { system-power-controller; }; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&pins_uart0>; +}; + +&pinctrl { + pins_uart0: uart0 { + function = "uart0"; + groups = "uart0-data"; + bias-disable; + }; +}; diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index d34536e7653f6a..279b6d14ffeb7c 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -35,7 +35,12 @@ extern pte_t *pkmap_page_table; * easily, subsequent pte tables have to be allocated in one physical * chunk of RAM. */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT +#define LAST_PKMAP 512 +#else #define LAST_PKMAP 1024 +#endif + #define LAST_PKMAP_MASK (LAST_PKMAP-1) #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) #define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) diff --git a/arch/mips/include/asm/mach-jz4740/gpio.h b/arch/mips/include/asm/mach-jz4740/gpio.h index 7c7708a23baa61..fd847c98470111 100644 --- a/arch/mips/include/asm/mach-jz4740/gpio.h +++ b/arch/mips/include/asm/mach-jz4740/gpio.h @@ -16,380 +16,9 @@ #ifndef _JZ_GPIO_H #define _JZ_GPIO_H -#include - -enum jz_gpio_function { - JZ_GPIO_FUNC_NONE, - JZ_GPIO_FUNC1, - JZ_GPIO_FUNC2, - JZ_GPIO_FUNC3, -}; - -/* - Usually a driver for a SoC component has to request several gpio pins and - configure them as function pins. - jz_gpio_bulk_request can be used to ease this process. - Usually one would do something like: - - static const struct jz_gpio_bulk_request i2c_pins[] = { - JZ_GPIO_BULK_PIN(I2C_SDA), - JZ_GPIO_BULK_PIN(I2C_SCK), - }; - - inside the probe function: - - ret = jz_gpio_bulk_request(i2c_pins, ARRAY_SIZE(i2c_pins)); - if (ret) { - ... - - inside the remove function: - - jz_gpio_bulk_free(i2c_pins, ARRAY_SIZE(i2c_pins)); - -*/ - -struct jz_gpio_bulk_request { - int gpio; - const char *name; - enum jz_gpio_function function; -}; - -#define JZ_GPIO_BULK_PIN(pin) { \ - .gpio = JZ_GPIO_ ## pin, \ - .name = #pin, \ - .function = JZ_GPIO_FUNC_ ## pin \ -} - -int jz_gpio_bulk_request(const struct jz_gpio_bulk_request *request, size_t num); -void jz_gpio_bulk_free(const struct jz_gpio_bulk_request *request, size_t num); -void jz_gpio_bulk_suspend(const struct jz_gpio_bulk_request *request, size_t num); -void jz_gpio_bulk_resume(const struct jz_gpio_bulk_request *request, size_t num); -void jz_gpio_enable_pullup(unsigned gpio); -void jz_gpio_disable_pullup(unsigned gpio); -int jz_gpio_set_function(int gpio, enum jz_gpio_function function); - -int jz_gpio_port_direction_input(int port, uint32_t mask); -int jz_gpio_port_direction_output(int port, uint32_t mask); -void jz_gpio_port_set_value(int port, uint32_t value, uint32_t mask); -uint32_t jz_gpio_port_get_value(int port, uint32_t mask); - #define JZ_GPIO_PORTA(x) ((x) + 32 * 0) #define JZ_GPIO_PORTB(x) ((x) + 32 * 1) #define JZ_GPIO_PORTC(x) ((x) + 32 * 2) #define JZ_GPIO_PORTD(x) ((x) + 32 * 3) -/* Port A function pins */ -#define JZ_GPIO_MEM_DATA0 JZ_GPIO_PORTA(0) -#define JZ_GPIO_MEM_DATA1 JZ_GPIO_PORTA(1) -#define JZ_GPIO_MEM_DATA2 JZ_GPIO_PORTA(2) -#define JZ_GPIO_MEM_DATA3 JZ_GPIO_PORTA(3) -#define JZ_GPIO_MEM_DATA4 JZ_GPIO_PORTA(4) -#define JZ_GPIO_MEM_DATA5 JZ_GPIO_PORTA(5) -#define JZ_GPIO_MEM_DATA6 JZ_GPIO_PORTA(6) -#define JZ_GPIO_MEM_DATA7 JZ_GPIO_PORTA(7) -#define JZ_GPIO_MEM_DATA8 JZ_GPIO_PORTA(8) -#define JZ_GPIO_MEM_DATA9 JZ_GPIO_PORTA(9) -#define JZ_GPIO_MEM_DATA10 JZ_GPIO_PORTA(10) -#define JZ_GPIO_MEM_DATA11 JZ_GPIO_PORTA(11) -#define JZ_GPIO_MEM_DATA12 JZ_GPIO_PORTA(12) -#define JZ_GPIO_MEM_DATA13 JZ_GPIO_PORTA(13) -#define JZ_GPIO_MEM_DATA14 JZ_GPIO_PORTA(14) -#define JZ_GPIO_MEM_DATA15 JZ_GPIO_PORTA(15) -#define JZ_GPIO_MEM_DATA16 JZ_GPIO_PORTA(16) -#define JZ_GPIO_MEM_DATA17 JZ_GPIO_PORTA(17) -#define JZ_GPIO_MEM_DATA18 JZ_GPIO_PORTA(18) -#define JZ_GPIO_MEM_DATA19 JZ_GPIO_PORTA(19) -#define JZ_GPIO_MEM_DATA20 JZ_GPIO_PORTA(20) -#define JZ_GPIO_MEM_DATA21 JZ_GPIO_PORTA(21) -#define JZ_GPIO_MEM_DATA22 JZ_GPIO_PORTA(22) -#define JZ_GPIO_MEM_DATA23 JZ_GPIO_PORTA(23) -#define JZ_GPIO_MEM_DATA24 JZ_GPIO_PORTA(24) -#define JZ_GPIO_MEM_DATA25 JZ_GPIO_PORTA(25) -#define JZ_GPIO_MEM_DATA26 JZ_GPIO_PORTA(26) -#define JZ_GPIO_MEM_DATA27 JZ_GPIO_PORTA(27) -#define JZ_GPIO_MEM_DATA28 JZ_GPIO_PORTA(28) -#define JZ_GPIO_MEM_DATA29 JZ_GPIO_PORTA(29) -#define JZ_GPIO_MEM_DATA30 JZ_GPIO_PORTA(30) -#define JZ_GPIO_MEM_DATA31 JZ_GPIO_PORTA(31) - -#define JZ_GPIO_FUNC_MEM_DATA0 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA1 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA2 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA3 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA4 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA5 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA6 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA7 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA8 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA9 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA10 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA11 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA12 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA13 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA14 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA15 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA16 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA17 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA18 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA19 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA20 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA21 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA22 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA23 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA24 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA25 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA26 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA27 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA28 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA29 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA30 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DATA31 JZ_GPIO_FUNC1 - -/* Port B function pins */ -#define JZ_GPIO_MEM_ADDR0 JZ_GPIO_PORTB(0) -#define JZ_GPIO_MEM_ADDR1 JZ_GPIO_PORTB(1) -#define JZ_GPIO_MEM_ADDR2 JZ_GPIO_PORTB(2) -#define JZ_GPIO_MEM_ADDR3 JZ_GPIO_PORTB(3) -#define JZ_GPIO_MEM_ADDR4 JZ_GPIO_PORTB(4) -#define JZ_GPIO_MEM_ADDR5 JZ_GPIO_PORTB(5) -#define JZ_GPIO_MEM_ADDR6 JZ_GPIO_PORTB(6) -#define JZ_GPIO_MEM_ADDR7 JZ_GPIO_PORTB(7) -#define JZ_GPIO_MEM_ADDR8 JZ_GPIO_PORTB(8) -#define JZ_GPIO_MEM_ADDR9 JZ_GPIO_PORTB(9) -#define JZ_GPIO_MEM_ADDR10 JZ_GPIO_PORTB(10) -#define JZ_GPIO_MEM_ADDR11 JZ_GPIO_PORTB(11) -#define JZ_GPIO_MEM_ADDR12 JZ_GPIO_PORTB(12) -#define JZ_GPIO_MEM_ADDR13 JZ_GPIO_PORTB(13) -#define JZ_GPIO_MEM_ADDR14 JZ_GPIO_PORTB(14) -#define JZ_GPIO_MEM_ADDR15 JZ_GPIO_PORTB(15) -#define JZ_GPIO_MEM_ADDR16 JZ_GPIO_PORTB(16) -#define JZ_GPIO_LCD_CLS JZ_GPIO_PORTB(17) -#define JZ_GPIO_LCD_SPL JZ_GPIO_PORTB(18) -#define JZ_GPIO_MEM_DCS JZ_GPIO_PORTB(19) -#define JZ_GPIO_MEM_RAS JZ_GPIO_PORTB(20) -#define JZ_GPIO_MEM_CAS JZ_GPIO_PORTB(21) -#define JZ_GPIO_MEM_SDWE JZ_GPIO_PORTB(22) -#define JZ_GPIO_MEM_CKE JZ_GPIO_PORTB(23) -#define JZ_GPIO_MEM_CKO JZ_GPIO_PORTB(24) -#define JZ_GPIO_MEM_CS0 JZ_GPIO_PORTB(25) -#define JZ_GPIO_MEM_CS1 JZ_GPIO_PORTB(26) -#define JZ_GPIO_MEM_CS2 JZ_GPIO_PORTB(27) -#define JZ_GPIO_MEM_CS3 JZ_GPIO_PORTB(28) -#define JZ_GPIO_MEM_RD JZ_GPIO_PORTB(29) -#define JZ_GPIO_MEM_WR JZ_GPIO_PORTB(30) -#define JZ_GPIO_MEM_WE0 JZ_GPIO_PORTB(31) - -#define JZ_GPIO_FUNC_MEM_ADDR0 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR1 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR2 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR3 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR4 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR5 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR6 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR7 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR8 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR9 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR10 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR11 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR12 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR13 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR14 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR15 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_ADDR16 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_CLS JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_SPL JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_DCS JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_RAS JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CAS JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_SDWE JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CKE JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CKO JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CS0 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CS1 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CS2 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_CS3 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_RD JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WR JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WE0 JZ_GPIO_FUNC1 - - -#define JZ_GPIO_MEM_ADDR21 JZ_GPIO_PORTB(17) -#define JZ_GPIO_MEM_ADDR22 JZ_GPIO_PORTB(18) - -#define JZ_GPIO_FUNC_MEM_ADDR21 JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_ADDR22 JZ_GPIO_FUNC2 - -/* Port C function pins */ -#define JZ_GPIO_LCD_DATA0 JZ_GPIO_PORTC(0) -#define JZ_GPIO_LCD_DATA1 JZ_GPIO_PORTC(1) -#define JZ_GPIO_LCD_DATA2 JZ_GPIO_PORTC(2) -#define JZ_GPIO_LCD_DATA3 JZ_GPIO_PORTC(3) -#define JZ_GPIO_LCD_DATA4 JZ_GPIO_PORTC(4) -#define JZ_GPIO_LCD_DATA5 JZ_GPIO_PORTC(5) -#define JZ_GPIO_LCD_DATA6 JZ_GPIO_PORTC(6) -#define JZ_GPIO_LCD_DATA7 JZ_GPIO_PORTC(7) -#define JZ_GPIO_LCD_DATA8 JZ_GPIO_PORTC(8) -#define JZ_GPIO_LCD_DATA9 JZ_GPIO_PORTC(9) -#define JZ_GPIO_LCD_DATA10 JZ_GPIO_PORTC(10) -#define JZ_GPIO_LCD_DATA11 JZ_GPIO_PORTC(11) -#define JZ_GPIO_LCD_DATA12 JZ_GPIO_PORTC(12) -#define JZ_GPIO_LCD_DATA13 JZ_GPIO_PORTC(13) -#define JZ_GPIO_LCD_DATA14 JZ_GPIO_PORTC(14) -#define JZ_GPIO_LCD_DATA15 JZ_GPIO_PORTC(15) -#define JZ_GPIO_LCD_DATA16 JZ_GPIO_PORTC(16) -#define JZ_GPIO_LCD_DATA17 JZ_GPIO_PORTC(17) -#define JZ_GPIO_LCD_PCLK JZ_GPIO_PORTC(18) -#define JZ_GPIO_LCD_HSYNC JZ_GPIO_PORTC(19) -#define JZ_GPIO_LCD_VSYNC JZ_GPIO_PORTC(20) -#define JZ_GPIO_LCD_DE JZ_GPIO_PORTC(21) -#define JZ_GPIO_LCD_PS JZ_GPIO_PORTC(22) -#define JZ_GPIO_LCD_REV JZ_GPIO_PORTC(23) -#define JZ_GPIO_MEM_WE1 JZ_GPIO_PORTC(24) -#define JZ_GPIO_MEM_WE2 JZ_GPIO_PORTC(25) -#define JZ_GPIO_MEM_WE3 JZ_GPIO_PORTC(26) -#define JZ_GPIO_MEM_WAIT JZ_GPIO_PORTC(27) -#define JZ_GPIO_MEM_FRE JZ_GPIO_PORTC(28) -#define JZ_GPIO_MEM_FWE JZ_GPIO_PORTC(29) - -#define JZ_GPIO_FUNC_LCD_DATA0 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA1 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA2 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA3 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA4 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA5 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA6 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA7 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA8 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA9 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA10 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA11 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA12 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA13 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA14 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA15 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA16 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DATA17 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_PCLK JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_VSYNC JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_HSYNC JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_DE JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_PS JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_LCD_REV JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WE1 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WE2 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WE3 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_WAIT JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_FRE JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MEM_FWE JZ_GPIO_FUNC1 - - -#define JZ_GPIO_MEM_ADDR19 JZ_GPIO_PORTB(22) -#define JZ_GPIO_MEM_ADDR20 JZ_GPIO_PORTB(23) - -#define JZ_GPIO_FUNC_MEM_ADDR19 JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_ADDR20 JZ_GPIO_FUNC2 - -/* Port D function pins */ -#define JZ_GPIO_CIM_DATA0 JZ_GPIO_PORTD(0) -#define JZ_GPIO_CIM_DATA1 JZ_GPIO_PORTD(1) -#define JZ_GPIO_CIM_DATA2 JZ_GPIO_PORTD(2) -#define JZ_GPIO_CIM_DATA3 JZ_GPIO_PORTD(3) -#define JZ_GPIO_CIM_DATA4 JZ_GPIO_PORTD(4) -#define JZ_GPIO_CIM_DATA5 JZ_GPIO_PORTD(5) -#define JZ_GPIO_CIM_DATA6 JZ_GPIO_PORTD(6) -#define JZ_GPIO_CIM_DATA7 JZ_GPIO_PORTD(7) -#define JZ_GPIO_MSC_CMD JZ_GPIO_PORTD(8) -#define JZ_GPIO_MSC_CLK JZ_GPIO_PORTD(9) -#define JZ_GPIO_MSC_DATA0 JZ_GPIO_PORTD(10) -#define JZ_GPIO_MSC_DATA1 JZ_GPIO_PORTD(11) -#define JZ_GPIO_MSC_DATA2 JZ_GPIO_PORTD(12) -#define JZ_GPIO_MSC_DATA3 JZ_GPIO_PORTD(13) -#define JZ_GPIO_CIM_MCLK JZ_GPIO_PORTD(14) -#define JZ_GPIO_CIM_PCLK JZ_GPIO_PORTD(15) -#define JZ_GPIO_CIM_VSYNC JZ_GPIO_PORTD(16) -#define JZ_GPIO_CIM_HSYNC JZ_GPIO_PORTD(17) -#define JZ_GPIO_SPI_CLK JZ_GPIO_PORTD(18) -#define JZ_GPIO_SPI_CE0 JZ_GPIO_PORTD(19) -#define JZ_GPIO_SPI_DT JZ_GPIO_PORTD(20) -#define JZ_GPIO_SPI_DR JZ_GPIO_PORTD(21) -#define JZ_GPIO_SPI_CE1 JZ_GPIO_PORTD(22) -#define JZ_GPIO_PWM0 JZ_GPIO_PORTD(23) -#define JZ_GPIO_PWM1 JZ_GPIO_PORTD(24) -#define JZ_GPIO_PWM2 JZ_GPIO_PORTD(25) -#define JZ_GPIO_PWM3 JZ_GPIO_PORTD(26) -#define JZ_GPIO_PWM4 JZ_GPIO_PORTD(27) -#define JZ_GPIO_PWM5 JZ_GPIO_PORTD(28) -#define JZ_GPIO_PWM6 JZ_GPIO_PORTD(30) -#define JZ_GPIO_PWM7 JZ_GPIO_PORTD(31) - -#define JZ_GPIO_FUNC_CIM_DATA JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_CIM_DATA0 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA1 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA2 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA3 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA4 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA5 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA6 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_CIM_DATA7 JZ_GPIO_FUNC_CIM_DATA -#define JZ_GPIO_FUNC_MSC_CMD JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MSC_CLK JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MSC_DATA JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_MSC_DATA0 JZ_GPIO_FUNC_MSC_DATA -#define JZ_GPIO_FUNC_MSC_DATA1 JZ_GPIO_FUNC_MSC_DATA -#define JZ_GPIO_FUNC_MSC_DATA2 JZ_GPIO_FUNC_MSC_DATA -#define JZ_GPIO_FUNC_MSC_DATA3 JZ_GPIO_FUNC_MSC_DATA -#define JZ_GPIO_FUNC_CIM_MCLK JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_CIM_PCLK JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_CIM_VSYNC JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_CIM_HSYNC JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_SPI_CLK JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_SPI_CE0 JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_SPI_DT JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_SPI_DR JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_SPI_CE1 JZ_GPIO_FUNC1 - -#define JZ_GPIO_FUNC_PWM JZ_GPIO_FUNC1 -#define JZ_GPIO_FUNC_PWM0 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM1 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM2 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM3 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM4 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM5 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM6 JZ_GPIO_FUNC_PWM -#define JZ_GPIO_FUNC_PWM7 JZ_GPIO_FUNC_PWM - -#define JZ_GPIO_MEM_SCLK_RSTN JZ_GPIO_PORTD(18) -#define JZ_GPIO_MEM_BCLK JZ_GPIO_PORTD(19) -#define JZ_GPIO_MEM_SDATO JZ_GPIO_PORTD(20) -#define JZ_GPIO_MEM_SDATI JZ_GPIO_PORTD(21) -#define JZ_GPIO_MEM_SYNC JZ_GPIO_PORTD(22) -#define JZ_GPIO_I2C_SDA JZ_GPIO_PORTD(23) -#define JZ_GPIO_I2C_SCK JZ_GPIO_PORTD(24) -#define JZ_GPIO_UART0_TXD JZ_GPIO_PORTD(25) -#define JZ_GPIO_UART0_RXD JZ_GPIO_PORTD(26) -#define JZ_GPIO_MEM_ADDR17 JZ_GPIO_PORTD(27) -#define JZ_GPIO_MEM_ADDR18 JZ_GPIO_PORTD(28) -#define JZ_GPIO_UART0_CTS JZ_GPIO_PORTD(30) -#define JZ_GPIO_UART0_RTS JZ_GPIO_PORTD(31) - -#define JZ_GPIO_FUNC_MEM_SCLK_RSTN JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_BCLK JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_SDATO JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_SDATI JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_SYNC JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_I2C_SDA JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_I2C_SCK JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_UART0_TXD JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_UART0_RXD JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_ADDR17 JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_MEM_ADDR18 JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_UART0_CTS JZ_GPIO_FUNC2 -#define JZ_GPIO_FUNC_UART0_RTS JZ_GPIO_FUNC2 - -#define JZ_GPIO_UART1_RXD JZ_GPIO_PORTD(30) -#define JZ_GPIO_UART1_TXD JZ_GPIO_PORTD(31) - -#define JZ_GPIO_FUNC_UART1_RXD JZ_GPIO_FUNC3 -#define JZ_GPIO_FUNC_UART1_TXD JZ_GPIO_FUNC3 - #endif diff --git a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h b/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h index 8a7ecb4d5c64d2..bf9dd9eb4cebb3 100644 --- a/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h +++ b/arch/mips/include/asm/mach-loongson64/cs5536/cs5536_pci.h @@ -80,7 +80,6 @@ extern u32 cs5536_pci_conf_read4(int function, int reg); #define PCI_BAR3_REG 0x1c #define PCI_BAR4_REG 0x20 #define PCI_BAR5_REG 0x24 -#define PCI_BAR_COUNT 6 #define PCI_BAR_RANGE_MASK 0xFFFFFFFF /* CARDBUS CIS POINTER */ diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h index 1000c1b4c875af..52f551ee492de2 100644 --- a/arch/mips/include/asm/pci.h +++ b/arch/mips/include/asm/pci.h @@ -39,7 +39,6 @@ struct pci_controller { unsigned long io_offset; unsigned long io_map_base; struct resource *busn_resource; - unsigned long busn_offset; #ifndef CONFIG_PCI_DOMAINS_GENERIC unsigned int index; diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 6f94bed571c441..74afe8c76bdd01 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -19,6 +19,10 @@ #define __ARCH_USE_5LEVEL_HACK #include +#ifdef CONFIG_HIGHMEM +#include +#endif + extern int temp_tlb_entry; /* @@ -62,7 +66,8 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, #define VMALLOC_START MAP_BASE -#define PKMAP_BASE (0xfe000000UL) +#define PKMAP_END ((FIXADDR_START) & ~((LAST_PKMAP << PAGE_SHIFT)-1)) +#define PKMAP_BASE (PKMAP_END - PAGE_SIZE * LAST_PKMAP) #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 3418ec9c1c5016..365ff51f033a95 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -116,4 +116,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/jz4740/Makefile b/arch/mips/jz4740/Makefile index 39d70bde8cfe5a..6b9c1f7c31c9f3 100644 --- a/arch/mips/jz4740/Makefile +++ b/arch/mips/jz4740/Makefile @@ -7,8 +7,6 @@ obj-y += prom.o time.o reset.o setup.o \ platform.o timer.o -obj-$(CONFIG_MACH_JZ4740) += gpio.o - CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt # board specific support diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index a5bd94b952635f..6d7f9755220085 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include #include #include @@ -159,7 +161,7 @@ static struct jz_nand_platform_data qi_lb60_nand_pdata = { static struct gpiod_lookup_table qi_lb60_nand_gpio_table = { .dev_id = "jz4740-nand.0", .table = { - GPIO_LOOKUP("Bank C", 30, "busy", 0), + GPIO_LOOKUP("GPIOC", 30, "busy", 0), { }, }, }; @@ -421,8 +423,8 @@ static struct platform_device qi_lb60_audio_device = { static struct gpiod_lookup_table qi_lb60_audio_gpio_table = { .dev_id = "qi-lb60-audio", .table = { - GPIO_LOOKUP("Bank B", 29, "snd", 0), - GPIO_LOOKUP("Bank D", 4, "amp", 0), + GPIO_LOOKUP("GPIOB", 29, "snd", 0), + GPIO_LOOKUP("GPIOD", 4, "amp", 0), { }, }, }; @@ -447,13 +449,36 @@ static struct platform_device *jz_platform_devices[] __initdata = { &qi_lb60_audio_device, }; -static void __init board_gpio_setup(void) -{ - /* We only need to enable/disable pullup here for pins used in generic - * drivers. Everything else is done by the drivers themselves. */ - jz_gpio_disable_pullup(QI_LB60_GPIO_SD_VCC_EN_N); - jz_gpio_disable_pullup(QI_LB60_GPIO_SD_CD); -} +static unsigned long pin_cfg_bias_disable[] = { + PIN_CONFIG_BIAS_DISABLE, +}; + +static struct pinctrl_map pin_map[] __initdata = { + /* NAND pin configuration */ + PIN_MAP_MUX_GROUP_DEFAULT("jz4740-nand", + "10010000.jz4740-pinctrl", "nand", "nand-cs1"), + + /* fbdev pin configuration */ + PIN_MAP_MUX_GROUP("jz4740-fb", PINCTRL_STATE_DEFAULT, + "10010000.jz4740-pinctrl", "lcd", "lcd-8bit"), + PIN_MAP_MUX_GROUP("jz4740-fb", PINCTRL_STATE_SLEEP, + "10010000.jz4740-pinctrl", "lcd", "lcd-no-pins"), + + /* MMC pin configuration */ + PIN_MAP_MUX_GROUP_DEFAULT("jz4740-mmc.0", + "10010000.jz4740-pinctrl", "mmc", "mmc-1bit"), + PIN_MAP_MUX_GROUP_DEFAULT("jz4740-mmc.0", + "10010000.jz4740-pinctrl", "mmc", "mmc-4bit"), + PIN_MAP_CONFIGS_PIN_DEFAULT("jz4740-mmc.0", + "10010000.jz4740-pinctrl", "PD0", pin_cfg_bias_disable), + PIN_MAP_CONFIGS_PIN_DEFAULT("jz4740-mmc.0", + "10010000.jz4740-pinctrl", "PD2", pin_cfg_bias_disable), + + /* PWM pin configuration */ + PIN_MAP_MUX_GROUP_DEFAULT("jz4740-pwm", + "10010000.jz4740-pinctrl", "pwm4", "pwm4"), +}; + static int __init qi_lb60_init_platform_devices(void) { @@ -469,6 +494,7 @@ static int __init qi_lb60_init_platform_devices(void) ARRAY_SIZE(qi_lb60_spi_board_info)); pwm_add_table(qi_lb60_pwm_lookup, ARRAY_SIZE(qi_lb60_pwm_lookup)); + pinctrl_register_mappings(pin_map, ARRAY_SIZE(pin_map)); return platform_add_devices(jz_platform_devices, ARRAY_SIZE(jz_platform_devices)); @@ -479,8 +505,6 @@ static int __init qi_lb60_board_setup(void) { printk(KERN_INFO "Qi Hardware JZ4740 QI LB60 setup\n"); - board_gpio_setup(); - if (qi_lb60_init_platform_devices()) panic("Failed to initialize platform devices"); diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c deleted file mode 100644 index cac1ccde2214c0..00000000000000 --- a/arch/mips/jz4740/gpio.c +++ /dev/null @@ -1,519 +0,0 @@ -/* - * Copyright (C) 2009-2010, Lars-Peter Clausen - * JZ4740 platform GPIO support - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#include -#include -#include - -#include -#include -/* FIXME: needed for gpio_request(), try to remove consumer API from driver */ -#include -#include -#include -#include -#include - -#include -#include - -#include -#include - -#define JZ4740_GPIO_BASE_A (32*0) -#define JZ4740_GPIO_BASE_B (32*1) -#define JZ4740_GPIO_BASE_C (32*2) -#define JZ4740_GPIO_BASE_D (32*3) - -#define JZ4740_GPIO_NUM_A 32 -#define JZ4740_GPIO_NUM_B 32 -#define JZ4740_GPIO_NUM_C 31 -#define JZ4740_GPIO_NUM_D 32 - -#define JZ4740_IRQ_GPIO_BASE_A (JZ4740_IRQ_GPIO(0) + JZ4740_GPIO_BASE_A) -#define JZ4740_IRQ_GPIO_BASE_B (JZ4740_IRQ_GPIO(0) + JZ4740_GPIO_BASE_B) -#define JZ4740_IRQ_GPIO_BASE_C (JZ4740_IRQ_GPIO(0) + JZ4740_GPIO_BASE_C) -#define JZ4740_IRQ_GPIO_BASE_D (JZ4740_IRQ_GPIO(0) + JZ4740_GPIO_BASE_D) - -#define JZ_REG_GPIO_PIN 0x00 -#define JZ_REG_GPIO_DATA 0x10 -#define JZ_REG_GPIO_DATA_SET 0x14 -#define JZ_REG_GPIO_DATA_CLEAR 0x18 -#define JZ_REG_GPIO_MASK 0x20 -#define JZ_REG_GPIO_MASK_SET 0x24 -#define JZ_REG_GPIO_MASK_CLEAR 0x28 -#define JZ_REG_GPIO_PULL 0x30 -#define JZ_REG_GPIO_PULL_SET 0x34 -#define JZ_REG_GPIO_PULL_CLEAR 0x38 -#define JZ_REG_GPIO_FUNC 0x40 -#define JZ_REG_GPIO_FUNC_SET 0x44 -#define JZ_REG_GPIO_FUNC_CLEAR 0x48 -#define JZ_REG_GPIO_SELECT 0x50 -#define JZ_REG_GPIO_SELECT_SET 0x54 -#define JZ_REG_GPIO_SELECT_CLEAR 0x58 -#define JZ_REG_GPIO_DIRECTION 0x60 -#define JZ_REG_GPIO_DIRECTION_SET 0x64 -#define JZ_REG_GPIO_DIRECTION_CLEAR 0x68 -#define JZ_REG_GPIO_TRIGGER 0x70 -#define JZ_REG_GPIO_TRIGGER_SET 0x74 -#define JZ_REG_GPIO_TRIGGER_CLEAR 0x78 -#define JZ_REG_GPIO_FLAG 0x80 -#define JZ_REG_GPIO_FLAG_CLEAR 0x14 - -#define GPIO_TO_BIT(gpio) BIT(gpio & 0x1f) -#define GPIO_TO_REG(gpio, reg) (gpio_to_jz_gpio_chip(gpio)->base + (reg)) -#define CHIP_TO_REG(chip, reg) (gpio_chip_to_jz_gpio_chip(chip)->base + (reg)) - -struct jz_gpio_chip { - unsigned int irq; - unsigned int irq_base; - uint32_t edge_trigger_both; - - void __iomem *base; - - struct gpio_chip gpio_chip; -}; - -static struct jz_gpio_chip jz4740_gpio_chips[]; - -static inline struct jz_gpio_chip *gpio_to_jz_gpio_chip(unsigned int gpio) -{ - return &jz4740_gpio_chips[gpio >> 5]; -} - -static inline struct jz_gpio_chip *gpio_chip_to_jz_gpio_chip(struct gpio_chip *gc) -{ - return gpiochip_get_data(gc); -} - -static inline struct jz_gpio_chip *irq_to_jz_gpio_chip(struct irq_data *data) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); - return gc->private; -} - -static inline void jz_gpio_write_bit(unsigned int gpio, unsigned int reg) -{ - writel(GPIO_TO_BIT(gpio), GPIO_TO_REG(gpio, reg)); -} - -int jz_gpio_set_function(int gpio, enum jz_gpio_function function) -{ - if (function == JZ_GPIO_FUNC_NONE) { - jz_gpio_write_bit(gpio, JZ_REG_GPIO_FUNC_CLEAR); - jz_gpio_write_bit(gpio, JZ_REG_GPIO_SELECT_CLEAR); - jz_gpio_write_bit(gpio, JZ_REG_GPIO_TRIGGER_CLEAR); - } else { - jz_gpio_write_bit(gpio, JZ_REG_GPIO_FUNC_SET); - jz_gpio_write_bit(gpio, JZ_REG_GPIO_TRIGGER_CLEAR); - switch (function) { - case JZ_GPIO_FUNC1: - jz_gpio_write_bit(gpio, JZ_REG_GPIO_SELECT_CLEAR); - break; - case JZ_GPIO_FUNC3: - jz_gpio_write_bit(gpio, JZ_REG_GPIO_TRIGGER_SET); - case JZ_GPIO_FUNC2: /* Falltrough */ - jz_gpio_write_bit(gpio, JZ_REG_GPIO_SELECT_SET); - break; - default: - BUG(); - break; - } - } - - return 0; -} -EXPORT_SYMBOL_GPL(jz_gpio_set_function); - -int jz_gpio_bulk_request(const struct jz_gpio_bulk_request *request, size_t num) -{ - size_t i; - int ret; - - for (i = 0; i < num; ++i, ++request) { - ret = gpio_request(request->gpio, request->name); - if (ret) - goto err; - jz_gpio_set_function(request->gpio, request->function); - } - - return 0; - -err: - for (--request; i > 0; --i, --request) { - gpio_free(request->gpio); - jz_gpio_set_function(request->gpio, JZ_GPIO_FUNC_NONE); - } - - return ret; -} -EXPORT_SYMBOL_GPL(jz_gpio_bulk_request); - -void jz_gpio_bulk_free(const struct jz_gpio_bulk_request *request, size_t num) -{ - size_t i; - - for (i = 0; i < num; ++i, ++request) { - gpio_free(request->gpio); - jz_gpio_set_function(request->gpio, JZ_GPIO_FUNC_NONE); - } - -} -EXPORT_SYMBOL_GPL(jz_gpio_bulk_free); - -void jz_gpio_bulk_suspend(const struct jz_gpio_bulk_request *request, size_t num) -{ - size_t i; - - for (i = 0; i < num; ++i, ++request) { - jz_gpio_set_function(request->gpio, JZ_GPIO_FUNC_NONE); - jz_gpio_write_bit(request->gpio, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_write_bit(request->gpio, JZ_REG_GPIO_PULL_SET); - } -} -EXPORT_SYMBOL_GPL(jz_gpio_bulk_suspend); - -void jz_gpio_bulk_resume(const struct jz_gpio_bulk_request *request, size_t num) -{ - size_t i; - - for (i = 0; i < num; ++i, ++request) - jz_gpio_set_function(request->gpio, request->function); -} -EXPORT_SYMBOL_GPL(jz_gpio_bulk_resume); - -void jz_gpio_enable_pullup(unsigned gpio) -{ - jz_gpio_write_bit(gpio, JZ_REG_GPIO_PULL_CLEAR); -} -EXPORT_SYMBOL_GPL(jz_gpio_enable_pullup); - -void jz_gpio_disable_pullup(unsigned gpio) -{ - jz_gpio_write_bit(gpio, JZ_REG_GPIO_PULL_SET); -} -EXPORT_SYMBOL_GPL(jz_gpio_disable_pullup); - -static int jz_gpio_get_value(struct gpio_chip *chip, unsigned gpio) -{ - return !!(readl(CHIP_TO_REG(chip, JZ_REG_GPIO_PIN)) & BIT(gpio)); -} - -static void jz_gpio_set_value(struct gpio_chip *chip, unsigned gpio, int value) -{ - uint32_t __iomem *reg = CHIP_TO_REG(chip, JZ_REG_GPIO_DATA_SET); - reg += !value; - writel(BIT(gpio), reg); -} - -static int jz_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, - int value) -{ - writel(BIT(gpio), CHIP_TO_REG(chip, JZ_REG_GPIO_DIRECTION_SET)); - jz_gpio_set_value(chip, gpio, value); - - return 0; -} - -static int jz_gpio_direction_input(struct gpio_chip *chip, unsigned gpio) -{ - writel(BIT(gpio), CHIP_TO_REG(chip, JZ_REG_GPIO_DIRECTION_CLEAR)); - - return 0; -} - -static int jz_gpio_to_irq(struct gpio_chip *chip, unsigned gpio) -{ - struct jz_gpio_chip *jz_gpio = gpiochip_get_data(chip); - - return jz_gpio->irq_base + gpio; -} - -int jz_gpio_port_direction_input(int port, uint32_t mask) -{ - writel(mask, GPIO_TO_REG(port, JZ_REG_GPIO_DIRECTION_CLEAR)); - - return 0; -} -EXPORT_SYMBOL(jz_gpio_port_direction_input); - -int jz_gpio_port_direction_output(int port, uint32_t mask) -{ - writel(mask, GPIO_TO_REG(port, JZ_REG_GPIO_DIRECTION_SET)); - - return 0; -} -EXPORT_SYMBOL(jz_gpio_port_direction_output); - -void jz_gpio_port_set_value(int port, uint32_t value, uint32_t mask) -{ - writel(~value & mask, GPIO_TO_REG(port, JZ_REG_GPIO_DATA_CLEAR)); - writel(value & mask, GPIO_TO_REG(port, JZ_REG_GPIO_DATA_SET)); -} -EXPORT_SYMBOL(jz_gpio_port_set_value); - -uint32_t jz_gpio_port_get_value(int port, uint32_t mask) -{ - uint32_t value = readl(GPIO_TO_REG(port, JZ_REG_GPIO_PIN)); - - return value & mask; -} -EXPORT_SYMBOL(jz_gpio_port_get_value); - -#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f) - -static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq) -{ - uint32_t value; - void __iomem *reg; - uint32_t mask = IRQ_TO_BIT(irq); - - if (!(chip->edge_trigger_both & mask)) - return; - - reg = chip->base; - - value = readl(chip->base + JZ_REG_GPIO_PIN); - if (value & mask) - reg += JZ_REG_GPIO_DIRECTION_CLEAR; - else - reg += JZ_REG_GPIO_DIRECTION_SET; - - writel(mask, reg); -} - -static void jz_gpio_irq_demux_handler(struct irq_desc *desc) -{ - uint32_t flag; - unsigned int gpio_irq; - struct jz_gpio_chip *chip = irq_desc_get_handler_data(desc); - - flag = readl(chip->base + JZ_REG_GPIO_FLAG); - if (!flag) - return; - - gpio_irq = chip->irq_base + __fls(flag); - - jz_gpio_check_trigger_both(chip, gpio_irq); - - generic_handle_irq(gpio_irq); -}; - -static inline void jz_gpio_set_irq_bit(struct irq_data *data, unsigned int reg) -{ - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); - writel(IRQ_TO_BIT(data->irq), chip->base + reg); -} - -static void jz_gpio_irq_unmask(struct irq_data *data) -{ - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); - - jz_gpio_check_trigger_both(chip, data->irq); - irq_gc_unmask_enable_reg(data); -}; - -/* TODO: Check if function is gpio */ -static unsigned int jz_gpio_irq_startup(struct irq_data *data) -{ - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_SELECT_SET); - jz_gpio_irq_unmask(data); - return 0; -} - -static void jz_gpio_irq_shutdown(struct irq_data *data) -{ - irq_gc_mask_disable_reg(data); - - /* Set direction to input */ - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_SELECT_CLEAR); -} - -static int jz_gpio_irq_set_type(struct irq_data *data, unsigned int flow_type) -{ - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); - unsigned int irq = data->irq; - - if (flow_type == IRQ_TYPE_EDGE_BOTH) { - uint32_t value = readl(chip->base + JZ_REG_GPIO_PIN); - if (value & IRQ_TO_BIT(irq)) - flow_type = IRQ_TYPE_EDGE_FALLING; - else - flow_type = IRQ_TYPE_EDGE_RISING; - chip->edge_trigger_both |= IRQ_TO_BIT(irq); - } else { - chip->edge_trigger_both &= ~IRQ_TO_BIT(irq); - } - - switch (flow_type) { - case IRQ_TYPE_EDGE_RISING: - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_SET); - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_SET); - break; - case IRQ_TYPE_EDGE_FALLING: - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_SET); - break; - case IRQ_TYPE_LEVEL_HIGH: - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_SET); - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_CLEAR); - break; - case IRQ_TYPE_LEVEL_LOW: - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_CLEAR); - break; - default: - return -EINVAL; - } - - return 0; -} - -static int jz_gpio_irq_set_wake(struct irq_data *data, unsigned int on) -{ - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); - - irq_gc_set_wake(data, on); - irq_set_irq_wake(chip->irq, on); - - return 0; -} - -#define JZ4740_GPIO_CHIP(_bank) { \ - .irq_base = JZ4740_IRQ_GPIO_BASE_ ## _bank, \ - .gpio_chip = { \ - .label = "Bank " # _bank, \ - .owner = THIS_MODULE, \ - .set = jz_gpio_set_value, \ - .get = jz_gpio_get_value, \ - .direction_output = jz_gpio_direction_output, \ - .direction_input = jz_gpio_direction_input, \ - .to_irq = jz_gpio_to_irq, \ - .base = JZ4740_GPIO_BASE_ ## _bank, \ - .ngpio = JZ4740_GPIO_NUM_ ## _bank, \ - }, \ -} - -static struct jz_gpio_chip jz4740_gpio_chips[] = { - JZ4740_GPIO_CHIP(A), - JZ4740_GPIO_CHIP(B), - JZ4740_GPIO_CHIP(C), - JZ4740_GPIO_CHIP(D), -}; - -static void jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id) -{ - struct irq_chip_generic *gc; - struct irq_chip_type *ct; - - chip->base = ioremap(JZ4740_GPIO_BASE_ADDR + (id * 0x100), 0x100); - - chip->irq = JZ4740_IRQ_INTC_GPIO(id); - irq_set_chained_handler_and_data(chip->irq, - jz_gpio_irq_demux_handler, chip); - - gc = irq_alloc_generic_chip(chip->gpio_chip.label, 1, chip->irq_base, - chip->base, handle_level_irq); - - gc->wake_enabled = IRQ_MSK(chip->gpio_chip.ngpio); - gc->private = chip; - - ct = gc->chip_types; - ct->regs.enable = JZ_REG_GPIO_MASK_CLEAR; - ct->regs.disable = JZ_REG_GPIO_MASK_SET; - ct->regs.ack = JZ_REG_GPIO_FLAG_CLEAR; - - ct->chip.name = "GPIO"; - ct->chip.irq_mask = irq_gc_mask_disable_reg; - ct->chip.irq_unmask = jz_gpio_irq_unmask; - ct->chip.irq_ack = irq_gc_ack_set_bit; - ct->chip.irq_suspend = ingenic_intc_irq_suspend; - ct->chip.irq_resume = ingenic_intc_irq_resume; - ct->chip.irq_startup = jz_gpio_irq_startup; - ct->chip.irq_shutdown = jz_gpio_irq_shutdown; - ct->chip.irq_set_type = jz_gpio_irq_set_type; - ct->chip.irq_set_wake = jz_gpio_irq_set_wake; - ct->chip.flags = IRQCHIP_SET_TYPE_MASKED; - - irq_setup_generic_chip(gc, IRQ_MSK(chip->gpio_chip.ngpio), - IRQ_GC_INIT_NESTED_LOCK, 0, IRQ_NOPROBE | IRQ_LEVEL); - - gpiochip_add_data(&chip->gpio_chip, chip); -} - -static int __init jz4740_gpio_init(void) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); ++i) - jz4740_gpio_chip_init(&jz4740_gpio_chips[i], i); - - printk(KERN_INFO "JZ4740 GPIO initialized\n"); - - return 0; -} -arch_initcall(jz4740_gpio_init); - -#ifdef CONFIG_DEBUG_FS - -static inline void gpio_seq_reg(struct seq_file *s, struct jz_gpio_chip *chip, - const char *name, unsigned int reg) -{ - seq_printf(s, "\t%s: %08x\n", name, readl(chip->base + reg)); -} - -static int gpio_regs_show(struct seq_file *s, void *unused) -{ - struct jz_gpio_chip *chip = jz4740_gpio_chips; - int i; - - for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); ++i, ++chip) { - seq_printf(s, "==GPIO %d==\n", i); - gpio_seq_reg(s, chip, "Pin", JZ_REG_GPIO_PIN); - gpio_seq_reg(s, chip, "Data", JZ_REG_GPIO_DATA); - gpio_seq_reg(s, chip, "Mask", JZ_REG_GPIO_MASK); - gpio_seq_reg(s, chip, "Pull", JZ_REG_GPIO_PULL); - gpio_seq_reg(s, chip, "Func", JZ_REG_GPIO_FUNC); - gpio_seq_reg(s, chip, "Select", JZ_REG_GPIO_SELECT); - gpio_seq_reg(s, chip, "Direction", JZ_REG_GPIO_DIRECTION); - gpio_seq_reg(s, chip, "Trigger", JZ_REG_GPIO_TRIGGER); - gpio_seq_reg(s, chip, "Flag", JZ_REG_GPIO_FLAG); - } - - return 0; -} - -static int gpio_regs_open(struct inode *inode, struct file *file) -{ - return single_open(file, gpio_regs_show, NULL); -} - -static const struct file_operations gpio_regs_operations = { - .open = gpio_regs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init gpio_debugfs_init(void) -{ - (void) debugfs_create_file("jz_regs_gpio", S_IFREG | S_IRUGO, - NULL, NULL, &gpio_regs_operations); - return 0; -} -subsys_initcall(gpio_debugfs_init); - -#endif diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 30a3b75e88eb6a..9d9b8fbae2022a 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -38,20 +38,6 @@ void arch_ftrace_update_code(int command) #endif -/* - * Check if the address is in kernel space - * - * Clone core_kernel_text() from kernel/extable.c, but doesn't call - * init_kernel_text() for Ftrace doesn't trace functions in init sections. - */ -static inline int in_kernel_space(unsigned long ip) -{ - if (ip >= (unsigned long)_stext && - ip <= (unsigned long)_etext) - return 1; - return 0; -} - #ifdef CONFIG_DYNAMIC_FTRACE #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ @@ -198,7 +184,7 @@ int ftrace_make_nop(struct module *mod, * If ip is in kernel space, no long call, otherwise, long call is * needed. */ - new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F; + new = core_kernel_text(ip) ? INSN_NOP : INSN_B_1F; #ifdef CONFIG_64BIT return ftrace_modify_code(ip, new); #else @@ -218,12 +204,12 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) unsigned int new; unsigned long ip = rec->ip; - new = in_kernel_space(ip) ? insn_jal_ftrace_caller : insn_la_mcount[0]; + new = core_kernel_text(ip) ? insn_jal_ftrace_caller : insn_la_mcount[0]; #ifdef CONFIG_64BIT return ftrace_modify_code(ip, new); #else - return ftrace_modify_code_2r(ip, new, in_kernel_space(ip) ? + return ftrace_modify_code_2r(ip, new, core_kernel_text(ip) ? INSN_NOP : insn_la_mcount[1]); #endif } @@ -289,7 +275,7 @@ unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long * instruction "lui v1, hi_16bit_of_mcount"(offset is 24), but for * kernel, move after the instruction "move ra, at"(offset is 16) */ - ip = self_ra - (in_kernel_space(self_ra) ? 16 : 24); + ip = self_ra - (core_kernel_text(self_ra) ? 16 : 24); /* * search the text until finding the non-store instruction or "s{d,w} @@ -394,7 +380,7 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, * entries configured through the tracing/set_graph_function interface. */ - insns = in_kernel_space(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; + insns = core_kernel_text(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; trace.func = self_ra - (MCOUNT_INSN_SIZE * insns); /* Only trace if the calling function expects to */ diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c index 3e586daa3a3247..32e3168316cd98 100644 --- a/arch/mips/kernel/jump_label.c +++ b/arch/mips/kernel/jump_label.c @@ -58,7 +58,6 @@ void arch_jump_label_transform(struct jump_entry *e, insn.word = 0; /* nop */ } - get_online_cpus(); mutex_lock(&text_mutex); if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) { insn_p->halfword[0] = insn.word >> 16; @@ -70,7 +69,6 @@ void arch_jump_label_transform(struct jump_entry *e, (unsigned long)insn_p + sizeof(*insn_p)); mutex_unlock(&text_mutex); - put_online_cpus(); } #endif /* HAVE_JUMP_LABEL */ diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 313a88b2973f67..f3e301f95aef7e 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1597,7 +1597,6 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) break; case CPU_P5600: case CPU_P6600: - case CPU_I6400: /* 8-bit event numbers */ raw_id = config & 0x1ff; base_id = raw_id & 0xff; @@ -1610,6 +1609,11 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) raw_event.range = P; #endif break; + case CPU_I6400: + /* 8-bit event numbers */ + base_id = config & 0xff; + raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; + break; case CPU_1004K: if (IS_BOTH_COUNTERS_1004K_EVENT(base_id)) raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index adc6911ba74891..b19a3c506b1e9d 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -51,15 +51,15 @@ void __init pagetable_init(void) /* * Fixed mappings: */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, vaddr + FIXADDR_SIZE, pgd_base); + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1); + fixrange_init(vaddr & PMD_MASK, vaddr + FIXADDR_SIZE, pgd_base); #ifdef CONFIG_HIGHMEM /* * Permanent kmaps: */ vaddr = PKMAP_BASE; - fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + fixrange_init(vaddr & PMD_MASK, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); pgd = swapper_pg_dir + __pgd_offset(vaddr); pud = pud_offset(pgd, vaddr); diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 3a84f6c0c84056..174575a9a112dc 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -86,8 +86,7 @@ static void pcibios_scanbus(struct pci_controller *hose) hose->mem_resource, hose->mem_offset); pci_add_resource_offset(&resources, hose->io_resource, hose->io_offset); - pci_add_resource_offset(&resources, - hose->busn_resource, hose->busn_offset); + pci_add_resource(&resources, hose->busn_resource); bus = pci_scan_root_bus(NULL, next_busno, hose->pci_ops, hose, &resources); hose->bus = bus; diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index 4526e92301a676..d013c0da0256f0 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -98,4 +98,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/openrisc/configs/or1ksim_defconfig b/arch/openrisc/configs/or1ksim_defconfig index 42fe5303a37008..eb3fc581cf20d7 100644 --- a/arch/openrisc/configs/or1ksim_defconfig +++ b/arch/openrisc/configs/or1ksim_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="or32-linux-" +CONFIG_CROSS_COMPILE="or1k-linux-" CONFIG_NO_HZ=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y diff --git a/arch/openrisc/include/asm/fixmap.h b/arch/openrisc/include/asm/fixmap.h index 52733416c1f313..5a0159546f9eaf 100644 --- a/arch/openrisc/include/asm/fixmap.h +++ b/arch/openrisc/include/asm/fixmap.h @@ -27,6 +27,7 @@ #define FIXADDR_TOP ((unsigned long) (-2*PAGE_SIZE)) #include +#include #include /* diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c index ee3e604959e15c..d7260fdb03514a 100644 --- a/arch/openrisc/kernel/or32_ksyms.c +++ b/arch/openrisc/kernel/or32_ksyms.c @@ -15,7 +15,7 @@ * 2 of the License, or (at your option) any later version. */ -#include +#include #include #include #include diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 106859ae27ffba..ccb7d128dd00c1 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/openrisc/lib/delay.c b/arch/openrisc/lib/delay.c index c82b09f4a106ce..8b13fdf43ec615 100644 --- a/arch/openrisc/lib/delay.c +++ b/arch/openrisc/lib/delay.c @@ -16,8 +16,9 @@ */ #include -#include +#include #include +#include #include #include #include diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index 451906d78136e5..7569627a032bb6 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -6,6 +6,8 @@ #if !defined(__ASSEMBLY__) extern int pdc_type; +extern unsigned long parisc_cell_num; /* cell number the CPU runs on (PAT) */ +extern unsigned long parisc_cell_loc; /* cell location of CPU (PAT) */ /* Values for pdc_type */ #define PDC_TYPE_ILLEGAL -1 @@ -143,6 +145,18 @@ struct pdc_btlb_info { /* PDC_BLOCK_TLB, return of PDC_BTLB_INFO */ #endif /* !CONFIG_PA20 */ +struct pdc_mem_retinfo { /* PDC_MEM/PDC_MEM_MEMINFO (return info) */ + unsigned long pdt_size; + unsigned long pdt_entries; + unsigned long pdt_status; + unsigned long first_dbe_loc; + unsigned long good_mem; +}; + +struct pdc_mem_read_pdt { /* PDC_MEM/PDC_MEM_READ_PDT (return info) */ + unsigned long pdt_entries; +}; + #ifdef CONFIG_64BIT struct pdc_memory_table_raddr { /* PDC_MEM/PDC_MEM_TABLE (return info) */ unsigned long entries_returned; @@ -301,6 +315,10 @@ int pdc_get_initiator(struct hardware_path *, struct pdc_initiator *); int pdc_tod_read(struct pdc_tod *tod); int pdc_tod_set(unsigned long sec, unsigned long usec); +void pdc_pdt_init(void); /* in pdt.c */ +int pdc_mem_pdt_info(struct pdc_mem_retinfo *rinfo); +int pdc_mem_pdt_read_entries(struct pdc_mem_read_pdt *rpdt_read, + unsigned long *pdt_entries_ptr); #ifdef CONFIG_64BIT int pdc_mem_mem_table(struct pdc_memory_table_raddr *r_addr, struct pdc_memory_table *tbl, unsigned long entries); diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h index e1d289092705f0..0ef789e41555f4 100644 --- a/arch/parisc/include/asm/pdcpat.h +++ b/arch/parisc/include/asm/pdcpat.h @@ -147,9 +147,9 @@ #define PDC_PAT_MEM_CELL_CLEAR 6L /* Clear PDT For Cell */ #define PDC_PAT_MEM_CELL_READ 7L /* Read PDT entries For Cell */ #define PDC_PAT_MEM_CELL_RESET 8L /* Reset clear bit For Cell */ -#define PDC_PAT_MEM_SETGM 9L /* Set Golden Memory value */ -#define PDC_PAT_MEM_ADD_PAGE 10L /* ADDs a page to the cell */ -#define PDC_PAT_MEM_ADDRESS 11L /* Get Physical Location From */ +#define PDC_PAT_MEM_SETGM 9L /* Set Good Memory value */ +#define PDC_PAT_MEM_ADD_PAGE 10L /* ADDs a page to the cell */ +#define PDC_PAT_MEM_ADDRESS 11L /* Get Physical Location From */ /* Memory Address */ #define PDC_PAT_MEM_GET_TXT_SIZE 12L /* Get Formatted Text Size */ #define PDC_PAT_MEM_GET_PD_TXT 13L /* Get PD Formatted Text */ @@ -212,6 +212,23 @@ struct pdc_pat_cpu_num { unsigned long cpu_loc; }; +struct pdc_pat_mem_retinfo { /* PDC_PAT_MEM/PDC_PAT_MEM_PD_INFO (return info) */ + unsigned int ke; /* bit 0: memory inside good memory? */ + unsigned int current_pdt_entries:16; + unsigned int max_pdt_entries:16; + unsigned long Cs_bitmap; + unsigned long Ic_bitmap; + unsigned long good_mem; + unsigned long first_dbe_loc; /* first location of double bit error */ + unsigned long clear_time; /* last PDT clear time (since Jan 1970) */ +}; + +struct pdc_pat_mem_read_pd_retinfo { /* PDC_PAT_MEM/PDC_PAT_MEM_PD_READ */ + unsigned long actual_count_bytes; + unsigned long pdt_entries; +}; + + struct pdc_pat_pd_addr_map_entry { unsigned char entry_type; /* 1 = Memory Descriptor Entry Type */ unsigned char reserve1[5]; @@ -290,18 +307,19 @@ extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsign extern int pdc_pat_cell_num_to_loc(void *, unsigned long); extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa); +extern int pdc_pat_cpu_stop_cpu(unsigned long hpa, unsigned long hpa_vec); extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset); - extern int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *val); extern int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val); - -/* Flag to indicate this is a PAT box...don't use this unless you -** really have to...it might go away some day. -*/ -extern int pdc_pat; /* arch/parisc/kernel/inventory.c */ +extern int pdc_pat_mem_pdt_info(struct pdc_pat_mem_retinfo *rinfo); +extern int pdc_pat_mem_read_cell_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long max_entries); +extern int pdc_pat_mem_read_pd_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long count, + unsigned long offset); #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 3a4ed9f91d5727..71ca86cb0f1689 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -511,6 +511,9 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define pte_same(A,B) (pte_val(A) == pte_val(B)) +struct seq_file; +extern void arch_report_meminfo(struct seq_file *m); + #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index a3661ee6b060c1..ea4e6ae091d051 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -103,6 +103,8 @@ struct cpuinfo_parisc { unsigned long bh_count; /* number of times bh was invoked */ unsigned long fp_rev; unsigned long fp_model; + unsigned long cpu_num; /* CPU number from PAT firmware */ + unsigned long cpu_loc; /* CPU location from PAT firmware */ unsigned int state; struct parisc_device *dev; unsigned long loops_per_jiffy; diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 6b113f39f30c9b..c3e114f67485d3 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -68,17 +68,6 @@ struct exception_table_entry { #define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\ ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) -/* - * The page fault handler stores, in a per-cpu area, the following information - * if a fixup routine is available. - */ -struct exception_data { - unsigned long fault_ip; - unsigned long fault_gp; - unsigned long fault_space; - unsigned long fault_addr; -}; - /* * load_sr2() preloads the space register %%sr2 - based on the value of * get_fs() - with either a value of 0 to access kernel space (KERNEL_DS which diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index 0609ff117f67e5..1f30b49772aa87 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -131,12 +131,12 @@ #define PDC_TLB_SETUP 1 /* set up miss handling */ #define PDC_MEM 20 /* Manage memory */ -#define PDC_MEM_MEMINFO 0 -#define PDC_MEM_ADD_PAGE 1 -#define PDC_MEM_CLEAR_PDT 2 -#define PDC_MEM_READ_PDT 3 -#define PDC_MEM_RESET_CLEAR 4 -#define PDC_MEM_GOODMEM 5 +#define PDC_MEM_MEMINFO 0 /* Return PDT info */ +#define PDC_MEM_ADD_PAGE 1 /* Add page to PDT */ +#define PDC_MEM_CLEAR_PDT 2 /* Clear PDT */ +#define PDC_MEM_READ_PDT 3 /* Read PDT entry */ +#define PDC_MEM_RESET_CLEAR 4 /* Reset PDT clear flag */ +#define PDC_MEM_GOODMEM 5 /* Set good_mem value */ #define PDC_MEM_TABLE 128 /* Non contig mem map (sprockets) */ #define PDC_MEM_RETURN_ADDRESS_TABLE PDC_MEM_TABLE #define PDC_MEM_GET_MEMORY_SYSTEM_TABLES_SIZE 131 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 514701840bd934..b893ca14fade22 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -97,4 +97,6 @@ #define SO_COOKIE 0x4032 +#define SCM_TIMESTAMPING_PKTINFO 0x4033 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 69a11183d48d4d..c4294df69fb63a 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y := cache.o pacache.o setup.o traps.o time.o irq.o \ +obj-y := cache.o pacache.o setup.o pdt.o traps.o time.o irq.o \ pa7300lc.o syscall.o entry.o sys_parisc.o firmware.o \ ptrace.o hardware.o inventory.o drivers.o \ signal.o hpmc.o real2.o parisc_ksyms.o unaligned.o \ diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 1c4fe61a592b37..dfff8a0d6fd1e1 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -297,11 +297,6 @@ int main(void) #else DEFINE(HUGEPAGE_SIZE, PAGE_SIZE); #endif - BLANK(); - DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); - DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); - DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); - DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); BLANK(); DEFINE(ASM_PDC_RESULT_SIZE, NUM_PDC_RESULT * sizeof(unsigned long)); BLANK(); diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 9d797ae4fa2224..39fe2e29660745 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -957,6 +957,41 @@ int pdc_tod_read(struct pdc_tod *tod) } EXPORT_SYMBOL(pdc_tod_read); +int pdc_mem_pdt_info(struct pdc_mem_retinfo *rinfo) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_MEM, PDC_MEM_MEMINFO, __pa(pdc_result), 0); + convert_to_wide(pdc_result); + memcpy(rinfo, pdc_result, sizeof(*rinfo)); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + +int pdc_mem_pdt_read_entries(struct pdc_mem_read_pdt *pret, + unsigned long *pdt_entries_ptr) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_MEM, PDC_MEM_READ_PDT, __pa(pdc_result), + __pa(pdc_result2)); + if (retval == PDC_OK) { + convert_to_wide(pdc_result); + memcpy(pret, pdc_result, sizeof(*pret)); + convert_to_wide(pdc_result2); + memcpy(pdt_entries_ptr, pdc_result2, + pret->pdt_entries * sizeof(*pdt_entries_ptr)); + } + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + /** * pdc_tod_set - Set the Time-Of-Day clock. * @sec: The number of seconds since epoch. @@ -1272,6 +1307,28 @@ int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa) return retval; } +/** + * pdc_pat_cpu_stop_cpu - Stop current cpu. + * @hpa: The Hard Physical Address of the CPU which should be informed when + * current cpu has stopped. + * @hpa_vec: Mask of interrupts which should be signalled on CPU at @hpa. + * + * Stop the CPU in which the call is made. Flushes caches and purges TLB and + * places CPU in a firmware loop. If the CPU is the last in a cell, an + * interrupt message is sent to the CPU at @hpa. + */ +int pdc_pat_cpu_stop_cpu(unsigned long hpa, unsigned long hpa_vec) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_CPU, PDC_PAT_CPU_STOP, hpa, hpa_vec); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + /** * pdc_pat_get_irt_size - Retrieve the number of entries in the cell's interrupt table. * @num_entries: The return value. @@ -1383,6 +1440,79 @@ int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val) return retval; } + +/** + * pdc_pat_mem_pdc_info - Retrieve information about page deallocation table + * @rinfo: memory pdt information + * + */ +int pdc_pat_mem_pdt_info(struct pdc_pat_mem_retinfo *rinfo) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_PD_INFO, + __pa(&pdc_result)); + if (retval == PDC_OK) + memcpy(rinfo, &pdc_result, sizeof(*rinfo)); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + +/** + * pdc_pat_mem_read_cell_pdt - Read PDT entries from (old) PAT firmware + * @pret: array of PDT entries + * @pdt_entries_ptr: ptr to hold number of PDT entries + * @max_entries: maximum number of entries to be read + * + */ +int pdc_pat_mem_read_cell_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long max_entries) +{ + int retval; + unsigned long flags, entries; + + spin_lock_irqsave(&pdc_lock, flags); + /* PDC_PAT_MEM_CELL_READ is available on early PAT machines only */ + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_CELL_READ, + __pa(&pdc_result), parisc_cell_num, __pa(&pdc_result2)); + + if (retval == PDC_OK) { + /* build up return value as for PDC_PAT_MEM_PD_READ */ + entries = min(pdc_result[0], max_entries); + pret->pdt_entries = entries; + pret->actual_count_bytes = entries * sizeof(unsigned long); + memcpy(pdt_entries_ptr, &pdc_result2, pret->actual_count_bytes); + } + + spin_unlock_irqrestore(&pdc_lock, flags); + WARN_ON(retval == PDC_OK && pdc_result[0] > max_entries); + + return retval; +} +/** + * pdc_pat_mem_read_pd_pdt - Read PDT entries from (newer) PAT firmware + * @pret: array of PDT entries + * @pdt_entries_ptr: ptr to hold number of PDT entries + * + */ +int pdc_pat_mem_read_pd_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long count, + unsigned long offset) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_PD_READ, + __pa(&pret), __pa(pdt_entries_ptr), + count, offset); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} #endif /* CONFIG_64BIT */ diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index c9789d9c73b404..b0fe19ac4d78f0 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -40,6 +40,11 @@ int pdc_type __read_mostly = PDC_TYPE_ILLEGAL; +/* cell number and location (PAT firmware only) */ +unsigned long parisc_cell_num __read_mostly; +unsigned long parisc_cell_loc __read_mostly; + + void __init setup_pdc(void) { long status; @@ -78,6 +83,10 @@ void __init setup_pdc(void) if (status == PDC_OK) { pdc_type = PDC_TYPE_PAT; pr_cont("64 bit PAT.\n"); + parisc_cell_num = cell_info.cell_num; + parisc_cell_loc = cell_info.cell_loc; + pr_info("PAT: Running on cell %lu and location %lu.\n", + parisc_cell_num, parisc_cell_loc); return; } #endif diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c new file mode 100644 index 00000000000000..f3a797e670b094 --- /dev/null +++ b/arch/parisc/kernel/pdt.c @@ -0,0 +1,143 @@ +/* + * Page Deallocation Table (PDT) support + * + * The Page Deallocation Table (PDT) holds a table with pointers to bad + * memory (broken RAM modules) which is maintained by firmware. + * + * Copyright 2017 by Helge Deller + * + * TODO: + * - check regularily for new bad memory + * - add userspace interface with procfs or sysfs + * - increase number of PDT entries dynamically + */ + +#include +#include + +#include +#include +#include +#include + +enum pdt_access_type { + PDT_NONE, + PDT_PDC, + PDT_PAT_NEW, + PDT_PAT_OLD +}; + +static enum pdt_access_type pdt_type; + +/* global PDT status information */ +static struct pdc_mem_retinfo pdt_status; + +#define MAX_PDT_TABLE_SIZE PAGE_SIZE +#define MAX_PDT_ENTRIES (MAX_PDT_TABLE_SIZE / sizeof(unsigned long)) +static unsigned long pdt_entry[MAX_PDT_ENTRIES] __page_aligned_bss; + + +/* report PDT entries via /proc/meminfo */ +void arch_report_meminfo(struct seq_file *m) +{ + if (pdt_type == PDT_NONE) + return; + + seq_printf(m, "PDT_max_entries: %7lu\n", + pdt_status.pdt_size); + seq_printf(m, "PDT_cur_entries: %7lu\n", + pdt_status.pdt_entries); +} + +/* + * pdc_pdt_init() + * + * Initialize kernel PDT structures, read initial PDT table from firmware, + * report all current PDT entries and mark bad memory with memblock_reserve() + * to avoid that the kernel will use broken memory areas. + * + */ +void __init pdc_pdt_init(void) +{ + int ret, i; + unsigned long entries; + struct pdc_mem_read_pdt pdt_read_ret; + + if (is_pdc_pat()) { + struct pdc_pat_mem_retinfo pat_rinfo; + + pdt_type = PDT_PAT_NEW; + ret = pdc_pat_mem_pdt_info(&pat_rinfo); + pdt_status.pdt_size = pat_rinfo.max_pdt_entries; + pdt_status.pdt_entries = pat_rinfo.current_pdt_entries; + pdt_status.pdt_status = 0; + pdt_status.first_dbe_loc = pat_rinfo.first_dbe_loc; + pdt_status.good_mem = pat_rinfo.good_mem; + } else { + pdt_type = PDT_PDC; + ret = pdc_mem_pdt_info(&pdt_status); + } + + if (ret != PDC_OK) { + pdt_type = PDT_NONE; + pr_info("PDT: Firmware does not provide any page deallocation" + " information.\n"); + return; + } + + entries = pdt_status.pdt_entries; + WARN_ON(entries > MAX_PDT_ENTRIES); + + pr_info("PDT: size %lu, entries %lu, status %lu, dbe_loc 0x%lx," + " good_mem %lu\n", + pdt_status.pdt_size, pdt_status.pdt_entries, + pdt_status.pdt_status, pdt_status.first_dbe_loc, + pdt_status.good_mem); + + if (entries == 0) { + pr_info("PDT: Firmware reports all memory OK.\n"); + return; + } + + if (pdt_status.first_dbe_loc && + pdt_status.first_dbe_loc <= __pa((unsigned long)&_end)) + pr_crit("CRITICAL: Bad memory inside kernel image memory area!\n"); + + pr_warn("PDT: Firmware reports %lu entries of faulty memory:\n", + entries); + + if (pdt_type == PDT_PDC) + ret = pdc_mem_pdt_read_entries(&pdt_read_ret, pdt_entry); + else { +#ifdef CONFIG_64BIT + struct pdc_pat_mem_read_pd_retinfo pat_pret; + + ret = pdc_pat_mem_read_cell_pdt(&pat_pret, pdt_entry, + MAX_PDT_ENTRIES); + if (ret != PDC_OK) { + pdt_type = PDT_PAT_OLD; + ret = pdc_pat_mem_read_pd_pdt(&pat_pret, pdt_entry, + MAX_PDT_TABLE_SIZE, 0); + } +#else + ret = PDC_BAD_PROC; +#endif + } + + if (ret != PDC_OK) { + pdt_type = PDT_NONE; + pr_debug("PDT type %d, retval = %d\n", pdt_type, ret); + return; + } + + for (i = 0; i < pdt_status.pdt_entries; i++) { + if (i < 20) + pr_warn("PDT: BAD PAGE #%d at 0x%08lx (error_type = %lu)\n", + i, + pdt_entry[i] & PAGE_MASK, + pdt_entry[i] & 1); + + /* mark memory page bad */ + memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE); + } +} diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 4516a5b53f38ef..40ea7b432f002b 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include #include @@ -116,6 +117,19 @@ void machine_halt(void) ** The LED/ChassisCodes are updated by the led_halt() ** function, called by the reboot notifier chain. */ + + /* prevent soft lockup/stalled CPU messages for endless loop. */ + rcu_sysrq_start(); + + /* stop all CPUs but the current one. */ + smp_send_stop(); + + /* stop current CPU if possible. */ + if (is_pdc_pat()) + pdc_pat_cpu_stop_cpu(0, 0); + + /* wait until power down. */ + while (1) ; } void (*chassis_power_off)(void); @@ -143,9 +157,7 @@ void machine_power_off(void) printk(KERN_EMERG "System shut down completed.\n" "Please power this system off now."); - /* prevent soft lockup/stalled CPU messages for endless loop. */ - rcu_sysrq_start(); - for (;;); + machine_halt(); } void (*pm_power_off)(void) = machine_power_off; diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 85de47f4eb5945..0ab32779dfa737 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -94,7 +94,7 @@ static int processor_probe(struct parisc_device *dev) unsigned long txn_addr; unsigned long cpuid; struct cpuinfo_parisc *p; - struct pdc_pat_cpu_num cpu_info __maybe_unused; + struct pdc_pat_cpu_num cpu_info = { }; #ifdef CONFIG_SMP if (num_online_cpus() >= nr_cpu_ids) { @@ -113,6 +113,7 @@ static int processor_probe(struct parisc_device *dev) */ cpuid = boot_cpu_data.cpu_count; txn_addr = dev->hpa.start; /* for legacy PDC */ + cpu_info.cpu_num = cpu_info.cpu_loc = cpuid; #ifdef CONFIG_64BIT if (is_pdc_pat()) { @@ -180,6 +181,8 @@ static int processor_probe(struct parisc_device *dev) p->hpa = dev->hpa.start; /* save CPU hpa */ p->cpuid = cpuid; /* save CPU id */ p->txn_addr = txn_addr; /* save CPU IRQ address */ + p->cpu_num = cpu_info.cpu_num; + p->cpu_loc = cpu_info.cpu_loc; #ifdef CONFIG_SMP /* ** FIXME: review if any other initialization is clobbered diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 63365106ea1907..a2d844a8416346 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -42,6 +42,7 @@ #include /* for CPU_IRQ_REGION and friends */ #include #include +#include #include #include #include @@ -112,6 +113,8 @@ halt_processor(void) /* REVISIT : does PM *know* this CPU isn't available? */ set_cpu_online(smp_processor_id(), false); local_irq_disable(); + if (is_pdc_pat()) + pdc_pat_cpu_stop_cpu(0, 0); for (;;) ; } diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 89421df7016083..2d956aa0a38abb 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -243,14 +243,30 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, so mark - * them unstable and lower rating on SMP systems. + * The cr16 interval timers are not syncronized across CPUs on + * different sockets, so mark them unstable and lower rating on + * multi-socket SMP systems. */ if (num_online_cpus() > 1) { - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; + int cpu; + unsigned long cpu0_loc; + cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; + + for_each_online_cpu(cpu) { + if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc) + continue; + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; + break; + } } + /* XXX: We may want to mark sched_clock stable here if cr16 clocks are + * in sync: + * (clocksource_cr16.flags == CLOCK_SOURCE_IS_CONTINUOUS) */ + /* register at clocksource framework */ clocksource_register_hz(&clocksource_cr16, 100 * PAGE0->mem_10msec); diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S index 85c28bb80fb743..d4fe19806d5776 100644 --- a/arch/parisc/lib/lusercopy.S +++ b/arch/parisc/lib/lusercopy.S @@ -56,12 +56,6 @@ mtsp %r1,%sr1 .endm - .macro fixup_branch lbl - ldil L%\lbl, %r1 - ldo R%\lbl(%r1), %r1 - bv %r0(%r1) - .endm - /* * unsigned long lclear_user(void *to, unsigned long n) * @@ -82,16 +76,16 @@ $lclu_loop: $lclu_done: bv %r0(%r2) copy %r25,%r28 - .exit -ENDPROC_CFI(lclear_user) - .section .fixup,"ax" -2: fixup_branch $lclu_done - ldo 1(%r25),%r25 - .previous +2: b $lclu_done + ldo 1(%r25),%r25 ASM_EXCEPTIONTABLE_ENTRY(1b,2b) + .exit +ENDPROC_CFI(lclear_user) + + .procend /* @@ -122,16 +116,15 @@ $lslen_done: $lslen_nzero: b $lslen_done ldo 1(%r26),%r26 /* special case for N == 0 */ -ENDPROC_CFI(lstrnlen_user) - .section .fixup,"ax" -3: fixup_branch $lslen_done +3: b $lslen_done copy %r24,%r26 /* reset r26 so 0 is returned on fault */ - .previous ASM_EXCEPTIONTABLE_ENTRY(1b,3b) ASM_EXCEPTIONTABLE_ENTRY(2b,3b) +ENDPROC_CFI(lstrnlen_user) + .procend diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 32ec22146141e5..fdc34cf4eb0ee0 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -29,8 +29,6 @@ #define BITSSET 0x1c0 /* for identifying LDCW */ -DEFINE_PER_CPU(struct exception_data, exception_data); - int show_unhandled_signals = 1; /* @@ -143,13 +141,6 @@ int fixup_exception(struct pt_regs *regs) fix = search_exception_tables(regs->iaoq[0]); if (fix) { - struct exception_data *d; - d = this_cpu_ptr(&exception_data); - d->fault_ip = regs->iaoq[0]; - d->fault_gp = regs->gr[27]; - d->fault_space = regs->isr; - d->fault_addr = regs->ior; - /* * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 66f3a63451056e..1ca9a2b4239fba 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -381,6 +381,9 @@ static void __init setup_bootmem(void) request_resource(res, &data_resource); } request_resource(&sysram_resources[0], &pdcdata_resource); + + /* Initialize Page Deallocation Table (PDT) and check for bad memory. */ + pdc_pdt_init(); } static int __init parisc_text_address(unsigned long vaddr) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f7c8f9972f6181..a81460b5d6d687 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -208,6 +208,7 @@ config PPC select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING + select HAVE_IRQ_TIME_ACCOUNTING select IRQ_DOMAIN select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA @@ -391,11 +392,6 @@ config PPC_DT_CPU_FTRS firmware provides this binding. If you're not sure say Y. -config PPC_CPUFEATURES_ENABLE_UNKNOWN - bool "cpufeatures pass through unknown features to guest/userspace" - depends on PPC_DT_CPU_FTRS - default y - config HIGHMEM bool "High memory support" depends on PPC32 @@ -454,6 +450,17 @@ config PPC_TRANSACTIONAL_MEM ---help--- Support user-mode Transactional Memory on POWERPC. +config LD_HEAD_STUB_CATCH + bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT + depends on PPC64 + default n + help + Very large kernels can cause linker branch stubs to be generated by + code in head_64.S, which moves the head text sections out of their + specified location. This option can work around the problem. + + If unsure, say "N". + config DISABLE_MPROFILE_KERNEL bool "Disable use of mprofile-kernel for kernel tracing" depends on PPC64 && CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 3e0f0e1fadef87..8d4ed73d549091 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -98,6 +98,7 @@ endif LDFLAGS_vmlinux-y := -Bstatic LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) +LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn) ifeq ($(CONFIG_PPC64),y) ifeq ($(call cc-option-yn,-mcmodel=medium),y) @@ -189,7 +190,17 @@ else CHECKFLAGS += -D__LITTLE_ENDIAN__ endif +ifdef CONFIG_PPC32 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o +else +ifeq ($(call ld-ifversion, -ge, 225000000, y),y) +# Have the linker provide sfpr if possible. +# There is a corresponding test in arch/powerpc/lib/Makefile +KBUILD_LDFLAGS_MODULE += --save-restore-funcs +else +KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o +endif +endif ifeq ($(CONFIG_476FPE_ERR46),y) KBUILD_LDFLAGS_MODULE += --ppc476-workaround \ diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index eccfcc88afae00..5db43ebbe2dfdc 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -10,13 +10,26 @@ __archpost: -include include/config/auto.conf include scripts/Kbuild.include +quiet_cmd_head_check = CHKHEAD $@ + cmd_head_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/head_check.sh "$(NM)" "$@" + quiet_cmd_relocs_check = CHKREL $@ - cmd_relocs_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" +ifdef CONFIG_PPC_BOOK3S_64 + cmd_relocs_check = \ + $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \ + $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" +else + cmd_relocs_check = \ + $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" +endif # `@true` prevents complaint when there is nothing to be done vmlinux: FORCE @true +ifdef CONFIG_PPC64 + $(call cmd,head_check) +endif ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) endif @@ -25,7 +38,7 @@ endif @true clean: - @true + rm -f .tmp_symbols.txt PHONY += FORCE clean diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index e82f333cc84a75..a7814a7b152332 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -95,13 +95,16 @@ libfdtheader := fdt.h libfdt.h libfdt_internal.h $(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ $(addprefix $(obj)/,$(libfdtheader)) -src-wlib-y := string.S crt0.S crtsavres.S stdio.c decompress.c main.c \ +src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ $(libfdt) libfdt-wrapper.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ uartlite.c mpc52xx-psc.c opal.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S +ifndef CONFIG_PPC64_BOOT_WRAPPER +src-wlib-y += crtsavres.S +endif src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c fsl-soc.c diff --git a/arch/powerpc/boot/crtsavres.S b/arch/powerpc/boot/crtsavres.S index f3d9b35c07d476..085fb2b9a8b892 100644 --- a/arch/powerpc/boot/crtsavres.S +++ b/arch/powerpc/boot/crtsavres.S @@ -37,12 +37,13 @@ * the executable file might be covered by the GNU General Public License. */ +#ifdef __powerpc64__ +#error "On PPC64, FPR save/restore functions are provided by the linker." +#endif + .file "crtsavres.S" .section ".text" -/* On PowerPC64 Linux, these functions are provided by the linker. */ -#ifndef __powerpc64__ - #define _GLOBAL(name) \ .type name,@function; \ .globl name; \ @@ -230,4 +231,3 @@ _GLOBAL(_rest32gpr_31_x) mtlr 0 mr 1,11 blr -#endif diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts index 47afa438602ea2..5922c1ea0e96d1 100644 --- a/arch/powerpc/boot/dts/fsl/kmcent2.dts +++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts @@ -293,9 +293,7 @@ compatible = "fsl,ucc-hdlc"; rx-clock-name = "clk9"; tx-clock-name = "clk9"; - fsl,tx-timeslot-mask = <0xfffffffe>; - fsl,rx-timeslot-mask = <0xfffffffe>; - fsl,siram-entry-id = <0>; + fsl,hdlc-bus; }; }; }; diff --git a/arch/powerpc/boot/dts/fsp2.dts b/arch/powerpc/boot/dts/fsp2.dts new file mode 100644 index 00000000000000..475953ada7072c --- /dev/null +++ b/arch/powerpc/boot/dts/fsp2.dts @@ -0,0 +1,608 @@ +/* + * Device Tree Source for FSP2 + * + * Copyright 2010,2012 IBM Corp. + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without + * any warranty of any kind, whether express or implied. + */ + + +/dts-v1/; + +/ { + #address-cells = <2>; + #size-cells = <1>; + model = "ibm,fsp2"; + compatible = "ibm,fsp2"; + dcr-parent = <&{/cpus/cpu@0}>; + + aliases { + ethernet0 = &EMAC0; + ethernet1 = &EMAC1; + serial0 = &UART0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + model = "PowerPC, 476FSP2"; + reg = <0x0>; + clock-frequency = <0>; /* Filled in by cuboot */ + timebase-frequency = <0>; /* Filled in by cuboot */ + i-cache-line-size = <32>; + d-cache-line-size = <32>; + d-cache-size = <32768>; + i-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + }; + }; + + memory { + device_type = "memory"; + reg = <0x00000000 0x00000000 0x00000000>; /* Filled in by + cuboot */ + }; + + clocks { + mmc_clk: mmc_clk { + compatible = "fixed-clock"; + clock-frequency = <50000000>; + clock-output-names = "mmc_clk"; + }; + }; + + UIC0: uic0 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <0>; + dcr-reg = <0x2c0 0x8>; + }; + + /* "interrupts" field is + first pair is non-critical, second is critical */ + UIC1_0: uic1_0 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <1>; + dcr-reg = <0x2c8 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <21 0x4 4 0x84>; + }; + + /* PSI and DMA */ + UIC1_1: uic1_1 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <2>; + dcr-reg = <0x350 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <22 0x4 5 0x84>; + }; + + /* Ethernet and USB */ + UIC1_2: uic1_2 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <3>; + dcr-reg = <0x358 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <23 0x4 6 0x84>; + }; + + /* PLB Errors */ + UIC1_3: uic1_3 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <4>; + dcr-reg = <0x360 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <24 0x4 7 0x84>; + }; + + UIC1_4: uic1_4 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <5>; + dcr-reg = <0x368 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <25 0x4 8 0x84>; + }; + + UIC1_5: uic1_5 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <6>; + dcr-reg = <0x370 0x8>; + interrupt-parent = <&UIC0>; + interrupts = <26 0x4 9 0x84>; + }; + + /* 2nd level UICs for FSI */ + UIC2_0: uic2_0 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <7>; + dcr-reg = <0x2d0 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <16 0x4 0 0x84>; + }; + + UIC2_1: uic2_1 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <8>; + dcr-reg = <0x2d8 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <17 0x4 1 0x84>; + }; + + UIC2_2: uic2_2 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <9>; + dcr-reg = <0x2e0 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <18 0x4 2 0x84>; + }; + + UIC2_3: uic2_3 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <10>; + dcr-reg = <0x2e8 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <19 0x4 3 0x84>; + }; + + UIC2_4: uic2_4 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <11>; + dcr-reg = <0x2f0 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <20 0x4 4 0x84>; + }; + + UIC2_5: uic2_5 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <12>; + dcr-reg = <0x2f8 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <21 0x4 5 0x84>; + }; + + UIC2_6: uic2_6 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <13>; + dcr-reg = <0x300 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <22 0x4 6 0x84>; + }; + + UIC2_7: uic2_7 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <14>; + dcr-reg = <0x308 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <23 0x4 7 0x84>; + }; + + UIC2_8: uic2_8 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <15>; + dcr-reg = <0x310 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <24 0x4 8 0x84>; + }; + + UIC2_9: uic2_9 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <16>; + dcr-reg = <0x318 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <25 0x4 9 0x84>; + }; + + UIC2_10: uic2_10 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <17>; + dcr-reg = <0x320 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <26 0x4 10 0x84>; + }; + + UIC2_11: uic2_11 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <18>; + dcr-reg = <0x328 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <27 0x4 11 0x84>; + }; + + UIC2_12: uic2_12 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <19>; + dcr-reg = <0x330 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <28 0x4 12 0x84>; + }; + + UIC2_13: uic2_13 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <20>; + dcr-reg = <0x338 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <29 0x4 13 0x84>; + }; + + UIC2_14: uic2_14 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <21>; + dcr-reg = <0x340 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <30 0x4 14 0x84>; + }; + + UIC2_15: uic2_15 { + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + + compatible = "ibm,uic"; + interrupt-controller; + cell-index = <22>; + dcr-reg = <0x348 0x8>; + interrupt-parent = <&UIC1_0>; + interrupts = <31 0x4 15 0x84>; + }; + + mmc0: sdhci@020c0000 { + compatible = "st,sdhci-stih407", "st,sdhci"; + status = "disabled"; + reg = <0x020c0000 0x20000>; + reg-names = "mmc"; + interrupt-parent = <&UIC1_3>; + interrupts = <21 0x4 22 0x4>; + interrupt-names = "mmcirq"; + pinctrl-names = "default"; + pinctrl-0 = <>; + clock-names = "mmc"; + clocks = <&mmc_clk>; + }; + + plb6 { + compatible = "ibm,plb6"; + #address-cells = <2>; + #size-cells = <1>; + ranges; + + MCW0: memory-controller-wrapper { + compatible = "ibm,cw-476fsp2"; + dcr-reg = <0x11111800 0x40>; + }; + + MCIF0: memory-controller { + compatible = "ibm,sdram-476fsp2", "ibm,sdram-4xx-ddr3"; + dcr-reg = <0x11120000 0x10000>; + mcer-device = <&MCW0>; + interrupt-parent = <&UIC0>; + interrupts = <10 0x84 /* ECC UE */ + 11 0x84>; /* ECC CE */ + }; + }; + + plb4 { + compatible = "ibm,plb4"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x00000000 0x00000010 0x00000000 0x80000000 + 0x80000000 0x00000010 0x80000000 0x80000000>; + clock-frequency = <333333334>; + + plb6-system-hung-irq { + compatible = "ibm,bus-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <0 0x84>; + }; + + l2-error-irq { + compatible = "ibm,bus-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <20 0x84>; + }; + + plb6-plb4-irq { + compatible = "ibm,bus-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <1 0x84>; + }; + + plb4-ahb-irq { + compatible = "ibm,bus-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC1_3>; + interrupts = <20 0x84>; + }; + + opbd-error-irq { + compatible = "ibm,opbd-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC1_4>; + interrupts = <5 0x84>; + }; + + cmu-error-irq { + compatible = "ibm,cmu-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <28 0x84>; + }; + + conf-error-irq { + compatible = "ibm,conf-error-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC1_4>; + interrupts = <11 0x84>; + }; + + mc-ue-irq { + compatible = "ibm,mc-ue-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <10 0x84>; + }; + + reset-warning-irq { + compatible = "ibm,reset-warning-irq"; + #interrupt-cells = <2>; + interrupt-parent = <&UIC0>; + interrupts = <17 0x84>; + }; + + MAL0: mcmal0 { + #interrupt-cells = <1>; + #address-cells = <0>; + #size-cells = <0>; + compatible = "ibm,mcmal"; + dcr-reg = <0x80 0x80>; + num-tx-chans = <1>; + num-rx-chans = <1>; + interrupt-parent = <&MAL0>; + interrupts = <0 1 2 3 4>; + /* index interrupt-parent interrupt# type */ + interrupt-map = ; + }; + + MAL1: mcmal1 { + #interrupt-cells = <1>; + #address-cells = <0>; + #size-cells = <0>; + compatible = "ibm,mcmal"; + dcr-reg = <0x100 0x80>; + num-tx-chans = <1>; + num-rx-chans = <1>; + interrupt-parent = <&MAL1>; + interrupts = <0 1 2 3 4>; + /* index interrupt-parent interrupt# type */ + interrupt-map = ; + }; + + opb { + compatible = "ibm,opb"; + #address-cells = <1>; + #size-cells = <1>; + ranges; // pass-thru to parent bus + clock-frequency = <83333334>; + + EMAC0: ethernet@b0000000 { + linux,network-index = <0>; + device_type = "network"; + compatible = "ibm,emac4sync"; + has-inverted-stacr-oc; + interrupt-parent = <&UIC1_2>; + interrupts = <1 0x4 0 0x4>; + reg = <0xb0000000 0x100>; + local-mac-address = [000000000000]; /* Filled in by + cuboot */ + mal-device = <&MAL0>; + mal-tx-channel = <0>; + mal-rx-channel = <0>; + cell-index = <0>; + max-frame-size = <1500>; + rx-fifo-size = <4096>; + tx-fifo-size = <4096>; + rx-fifo-size-gige = <16384>; + tx-fifo-size-gige = <8192>; + phy-address = <1>; + phy-mode = "rgmii"; + phy-map = <00000003>; + rgmii-device = <&RGMII>; + rgmii-channel = <0>; + }; + + EMAC1: ethernet@b0000100 { + linux,network-index = <1>; + device_type = "network"; + compatible = "ibm,emac4sync"; + has-inverted-stacr-oc; + interrupt-parent = <&UIC1_2>; + interrupts = <9 0x4 8 0x4>; + reg = <0xb0000100 0x100>; + local-mac-address = [000000000000]; /* Filled in by + cuboot */ + mal-device = <&MAL1>; + mal-tx-channel = <0>; + mal-rx-channel = <0>; + cell-index = <1>; + max-frame-size = <1500>; + rx-fifo-size = <4096>; + tx-fifo-size = <4096>; + rx-fifo-size-gige = <16384>; + tx-fifo-size-gige = <8192>; + phy-address = <2>; + phy-mode = "rgmii"; + phy-map = <00000003>; + rgmii-device = <&RGMII>; + rgmii-channel = <1>; + }; + + RGMII: rgmii@b0000600 { + compatible = "ibm,rgmii"; + has-mdio; + reg = <0xb0000600 0x8>; + }; + + UART0: serial@b0020000 { + device_type = "serial"; + compatible = "ns16550"; + reg = <0xb0020000 0x8>; + virtual-reg = <0xb0020000>; + clock-frequency = <20833333>; + current-speed = <115200>; + interrupt-parent = <&UIC0>; + interrupts = <31 0x4>; + }; + }; + + OHCI1: ohci@02040000 { + compatible = "ohci-le"; + reg = <0x02040000 0xa0>; + interrupt-parent = <&UIC1_3>; + interrupts = <28 0x8 29 0x8>; + }; + + OHCI2: ohci@02080000 { + compatible = "ohci-le"; + reg = <0x02080000 0xa0>; + interrupt-parent = <&UIC1_3>; + interrupts = <30 0x8 31 0x8>; + }; + + EHCI: ehci@02000000 { + compatible = "usb-ehci"; + reg = <0x02000000 0xa4>; + interrupt-parent = <&UIC1_3>; + interrupts = <23 0x4>; + }; + + }; + + chosen { + linux,stdout-path = "/plb/opb/serial@b0020000"; + bootargs = "console=ttyS0,115200 rw log_buf_len=32768 debug"; + }; +}; diff --git a/arch/powerpc/boot/dts/sequoia.dts b/arch/powerpc/boot/dts/sequoia.dts index b1d329246b08dd..e41b88a5eaee5d 100644 --- a/arch/powerpc/boot/dts/sequoia.dts +++ b/arch/powerpc/boot/dts/sequoia.dts @@ -229,7 +229,7 @@ }; partition@84000 { label = "user"; - reg = <0x00000000 0x01f7c000>; + reg = <0x00084000 0x01f7c000>; }; }; }; diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h index b03373d8b386de..68e388ee94fe51 100644 --- a/arch/powerpc/boot/ppc_asm.h +++ b/arch/powerpc/boot/ppc_asm.h @@ -67,13 +67,15 @@ #define MSR_LE 0x0000000000000001 #define FIXUP_ENDIAN \ - tdi 0, 0, 0x48; /* Reverse endian of b . + 8 */ \ - b $+36; /* Skip trampoline if endian is good */ \ - .long 0x05009f42; /* bcl 20,31,$+4 */ \ - .long 0xa602487d; /* mflr r10 */ \ - .long 0x1c004a39; /* addi r10,r10,28 */ \ + tdi 0,0,0x48; /* Reverse endian of b . + 8 */ \ + b $+44; /* Skip trampoline if endian is good */ \ .long 0xa600607d; /* mfmsr r11 */ \ .long 0x01006b69; /* xori r11,r11,1 */ \ + .long 0x00004039; /* li r10,0 */ \ + .long 0x6401417d; /* mtmsrd r10,1 */ \ + .long 0x05009f42; /* bcl 20,31,$+4 */ \ + .long 0xa602487d; /* mflr r10 */ \ + .long 0x14004a39; /* addi r10,r10,20 */ \ .long 0xa6035a7d; /* mtsrr0 r10 */ \ .long 0xa6037b7d; /* mtsrr1 r11 */ \ .long 0x2400004c /* rfid */ diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig new file mode 100644 index 00000000000000..e8e6a69998527e --- /dev/null +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -0,0 +1,126 @@ +CONFIG_44x=y +# CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +# CONFIG_FHANDLE is not set +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=16 +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_EMBEDDED=y +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_PPC_47x=y +# CONFIG_EBONY is not set +CONFIG_FSP2=y +CONFIG_476FPE_ERR46=y +CONFIG_SWIOTLB=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="ip=on rw" +# CONFIG_SUSPEND is not set +# CONFIG_PCI is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_IPV6 is not set +CONFIG_VLAN_8021Q=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_CONNECTOR=y +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=35000 +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_ATA=y +# CONFIG_SATA_PMP is not set +# CONFIG_ATA_SFF is not set +CONFIG_NETDEVICES=y +CONFIG_BONDING=m +CONFIG_IBM_EMAC=m +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=32 +CONFIG_SERIAL_8250_RUNTIME_UARTS=32 +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +CONFIG_I2C=y +CONFIG_I2C_IBM_IIC=y +CONFIG_PTP_1588_CLOCK=y +# CONFIG_HWMON is not set +CONFIG_THERMAL=y +CONFIG_WATCHDOG=y +CONFIG_BOOKE_WDT=y +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_MMC=y +CONFIG_MMC_DEBUG=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_SDHCI_OF_ARASAN=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_M41T80=y +CONFIG_EXT2_FS=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_WBUF_VERIFY=y +CONFIG_JFFS2_SUMMARY=y +CONFIG_JFFS2_FS_XATTR=y +CONFIG_CRAMFS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_DEFAULT="n" +CONFIG_XZ_DEC=y +CONFIG_PRINTK_TIME=y +CONFIG_MESSAGE_LOGLEVEL_DEFAULT=3 +CONFIG_DYNAMIC_DEBUG=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_ECB=y +CONFIG_CRYPTO_PCBC=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c2d509584a9807..d02ad93bf70892 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -214,7 +214,6 @@ enum { #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) -#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000) #define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) #ifndef __ASSEMBLY__ @@ -463,7 +462,7 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index 86eb87382031df..7ab95798f17017 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -49,8 +49,8 @@ * CLOSE_FIXED_SECTION() or elsewhere, there may be something * unexpected being added there. Remove the '. = x_len' line, rebuild, and * check what is pushing the section down. - * - If the build dies in linking, check arch/powerpc/kernel/vmlinux.lds.S - * for instructions. + * - If the build dies in linking, check arch/powerpc/tools/head_check.sh + * comments. * - If the kernel crashes or hangs in very early boot, it could be linker * stubs at the start of the main text. */ @@ -63,11 +63,29 @@ . = 0x0; \ start_##sname: +/* + * .linker_stub_catch section is used to catch linker stubs from being + * inserted in our .text section, above the start_text label (which breaks + * the ABS_ADDR calculation). See kernel/vmlinux.lds.S and tools/head_check.sh + * for more details. We would prefer to just keep a cacheline (0x80), but + * 0x100 seems to be how the linker aligns branch stub groups. + */ +#ifdef CONFIG_LD_HEAD_STUB_CATCH +#define OPEN_TEXT_SECTION(start) \ + .section ".linker_stub_catch","ax",@progbits; \ +linker_stub_catch: \ + . = 0x4; \ + text_start = (start) + 0x100; \ + .section ".text","ax",@progbits; \ + .balign 0x100; \ +start_text: +#else #define OPEN_TEXT_SECTION(start) \ text_start = (start); \ .section ".text","ax",@progbits; \ . = 0x0; \ start_text: +#endif #define ZERO_FIXED_SECTION(sname, start, end) \ sname##_start = (start); \ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 1c09f8fe2ee88a..77f60a0f140510 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -177,6 +177,8 @@ struct paca_struct { * to the sibling threads' paca. */ struct paca_struct **thread_sibling_pacas; + /* The PSSCR value that the kernel requested before going to stop */ + u64 requested_psscr; #endif #ifdef CONFIG_PPC_STD_MMU_64 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 359c443417616c..6baeeb9acd0d6e 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -770,15 +770,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #else #define FIXUP_ENDIAN \ tdi 0,0,0x48; /* Reverse endian of b . + 8 */ \ - b $+36; /* Skip trampoline if endian is good */ \ - .long 0x05009f42; /* bcl 20,31,$+4 */ \ - .long 0xa602487d; /* mflr r10 */ \ - .long 0x1c004a39; /* addi r10,r10,28 */ \ + b $+44; /* Skip trampoline if endian is good */ \ .long 0xa600607d; /* mfmsr r11 */ \ .long 0x01006b69; /* xori r11,r11,1 */ \ + .long 0x00004039; /* li r10,0 */ \ + .long 0x6401417d; /* mtmsrd r10,1 */ \ + .long 0x05009f42; /* bcl 20,31,$+4 */ \ + .long 0xa602487d; /* mflr r10 */ \ + .long 0x14004a39; /* addi r10,r10,20 */ \ .long 0xa6035a7d; /* mtsrr0 r10 */ \ .long 0xa6037b7d; /* mtsrr1 r11 */ \ .long 0x2400004c /* rfid */ + #endif /* !CONFIG_PPC_BOOK3E */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index b15bf6bc0e94f4..0d960ef78a9a95 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,2 +1,8 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += param.h +generic-y += poll.h +generic-y += resource.h +generic-y += sockios.h +generic-y += statfs.h diff --git a/arch/powerpc/include/uapi/asm/param.h b/arch/powerpc/include/uapi/asm/param.h deleted file mode 100644 index 965d4542797590..00000000000000 --- a/arch/powerpc/include/uapi/asm/param.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/powerpc/include/uapi/asm/poll.h b/arch/powerpc/include/uapi/asm/poll.h deleted file mode 100644 index c98509d3149e63..00000000000000 --- a/arch/powerpc/include/uapi/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/powerpc/include/uapi/asm/resource.h b/arch/powerpc/include/uapi/asm/resource.h deleted file mode 100644 index 04bc4db8921b25..00000000000000 --- a/arch/powerpc/include/uapi/asm/resource.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 58e2ec0310fc95..3c590c7c42c074 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -8,28 +8,6 @@ * 2 of the License, or (at your option) any later version. */ -#include - -/* For setsockopt(2) */ -#define SOL_SOCKET 1 - -#define SO_DEBUG 1 -#define SO_REUSEADDR 2 -#define SO_TYPE 3 -#define SO_ERROR 4 -#define SO_DONTROUTE 5 -#define SO_BROADCAST 6 -#define SO_SNDBUF 7 -#define SO_RCVBUF 8 -#define SO_SNDBUFFORCE 32 -#define SO_RCVBUFFORCE 33 -#define SO_KEEPALIVE 9 -#define SO_OOBINLINE 10 -#define SO_NO_CHECK 11 -#define SO_PRIORITY 12 -#define SO_LINGER 13 -#define SO_BSDCOMPAT 14 -#define SO_REUSEPORT 15 #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 #define SO_RCVTIMEO 18 @@ -37,72 +15,6 @@ #define SO_PASSCRED 20 #define SO_PEERCRED 21 -/* Security levels - as per NRL IPv6 - don't actually do anything */ -#define SO_SECURITY_AUTHENTICATION 22 -#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 -#define SO_SECURITY_ENCRYPTION_NETWORK 24 - -#define SO_BINDTODEVICE 25 - -/* Socket filtering */ -#define SO_ATTACH_FILTER 26 -#define SO_DETACH_FILTER 27 -#define SO_GET_FILTER SO_ATTACH_FILTER - -#define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP - -#define SO_ACCEPTCONN 30 - -#define SO_PEERSEC 31 -#define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS - -#define SO_MARK 36 - -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - -#define SO_PROTOCOL 38 -#define SO_DOMAIN 39 - -#define SO_RXQ_OVFL 40 - -#define SO_WIFI_STATUS 41 -#define SCM_WIFI_STATUS SO_WIFI_STATUS -#define SO_PEEK_OFF 42 - -/* Instruct lower device to use last 4-bytes of skb data as FCS */ -#define SO_NOFCS 43 - -#define SO_LOCK_FILTER 44 - -#define SO_SELECT_ERR_QUEUE 45 - -#define SO_BUSY_POLL 46 - -#define SO_MAX_PACING_RATE 47 - -#define SO_BPF_EXTENSIONS 48 - -#define SO_INCOMING_CPU 49 - -#define SO_ATTACH_BPF 50 -#define SO_DETACH_BPF SO_DETACH_FILTER - -#define SO_ATTACH_REUSEPORT_CBPF 51 -#define SO_ATTACH_REUSEPORT_EBPF 52 - -#define SO_CNX_ADVICE 53 - -#define SCM_TIMESTAMPING_OPT_STATS 54 - -#define SO_MEMINFO 55 - -#define SO_INCOMING_NAPI_ID 56 - -#define SO_COOKIE 57 +#include #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/sockios.h b/arch/powerpc/include/uapi/asm/sockios.h deleted file mode 100644 index 55cef7675a31c2..00000000000000 --- a/arch/powerpc/include/uapi/asm/sockios.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _ASM_POWERPC_SOCKIOS_H -#define _ASM_POWERPC_SOCKIOS_H - -/* - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -/* Socket-level I/O control calls. */ -#define FIOSETOWN 0x8901 -#define SIOCSPGRP 0x8902 -#define FIOGETOWN 0x8903 -#define SIOCGPGRP 0x8904 -#define SIOCATMARK 0x8905 -#define SIOCGSTAMP 0x8906 /* Get stamp (timeval) */ -#define SIOCGSTAMPNS 0x8907 /* Get stamp (timespec) */ - -#endif /* _ASM_POWERPC_SOCKIOS_H */ diff --git a/arch/powerpc/include/uapi/asm/statfs.h b/arch/powerpc/include/uapi/asm/statfs.h deleted file mode 100644 index 5244834583a42c..00000000000000 --- a/arch/powerpc/include/uapi/asm/statfs.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_POWERPC_STATFS_H -#define _ASM_POWERPC_STATFS_H - -#include - -#endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 709e23425317c8..e15c178ba079dc 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -742,6 +742,7 @@ int main(void) OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask); OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask); OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas); + OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr); #endif DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index fcc7588a96d694..4c7656dc4e04f0 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -642,7 +643,6 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, - {"subcore", feat_enable, CPU_FTR_SUBCORE}, {"no-execute", feat_enable, 0}, {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, @@ -671,12 +671,24 @@ static struct dt_cpu_feature_match __initdata {"wait-v3", feat_enable, 0}, }; -/* XXX: how to configure this? Default + boot time? */ -#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN -#define CPU_FEATURE_ENABLE_UNKNOWN 1 -#else -#define CPU_FEATURE_ENABLE_UNKNOWN 0 -#endif +static bool __initdata using_dt_cpu_ftrs; +static bool __initdata enable_unknown = true; + +static int __init dt_cpu_ftrs_parse(char *str) +{ + if (!str) + return 0; + + if (!strcmp(str, "off")) + using_dt_cpu_ftrs = false; + else if (!strcmp(str, "known")) + enable_unknown = false; + else + return 1; + + return 0; +} +early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse); static void __init cpufeatures_setup_start(u32 isa) { @@ -707,7 +719,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) } } - if (!known && CPU_FEATURE_ENABLE_UNKNOWN) { + if (!known && enable_unknown) { if (!feat_try_enable_unknown(f)) { pr_info("not enabling: %s (unknown and unsupported by kernel)\n", f->name); @@ -756,6 +768,26 @@ static void __init cpufeatures_setup_finished(void) cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features); } +static int __init disabled_on_cmdline(void) +{ + unsigned long root, chosen; + const char *p; + + root = of_get_flat_dt_root(); + chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); + if (chosen == -FDT_ERR_NOTFOUND) + return false; + + p = of_get_flat_dt_prop(chosen, "bootargs", NULL); + if (!p) + return false; + + if (strstr(p, "dt_cpu_ftrs=off")) + return true; + + return false; +} + static int __init fdt_find_cpu_features(unsigned long node, const char *uname, int depth, void *data) { @@ -766,8 +798,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname, return 0; } -static bool __initdata using_dt_cpu_ftrs = false; - bool __init dt_cpu_ftrs_in_use(void) { return using_dt_cpu_ftrs; @@ -775,6 +805,8 @@ bool __init dt_cpu_ftrs_in_use(void) bool __init dt_cpu_ftrs_init(void *fdt) { + using_dt_cpu_ftrs = false; + /* Setup and verify the FDT, if it fails we just bail */ if (!early_init_dt_verify(fdt)) return false; @@ -782,6 +814,9 @@ bool __init dt_cpu_ftrs_init(void *fdt) if (!of_scan_flat_dt(fdt_find_cpu_features, NULL)) return false; + if (disabled_on_cmdline()) + return false; + cpufeatures_setup_cpu(); using_dt_cpu_ftrs = true; @@ -1027,5 +1062,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char void __init dt_cpu_ftrs_scan(void) { + if (!using_dt_cpu_ftrs) + return; + of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL); } diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 4898d676dcaef1..98a6d07ecb5ca0 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -31,6 +31,7 @@ * registers for winkle support. */ #define _SDR1 GPR3 +#define _PTCR GPR3 #define _RPR GPR4 #define _SPURR GPR5 #define _PURR GPR6 @@ -39,7 +40,7 @@ #define _AMOR GPR9 #define _WORT GPR10 #define _WORC GPR11 -#define _PTCR GPR12 +#define _LPCR GPR12 #define PSSCR_EC_ESL_MASK_SHIFTED (PSSCR_EC | PSSCR_ESL) >> 16 @@ -55,12 +56,14 @@ save_sprs_to_stack: * here since any thread in the core might wake up first */ BEGIN_FTR_SECTION - mfspr r3,SPRN_PTCR - std r3,_PTCR(r1) /* * Note - SDR1 is dropped in Power ISA v3. Hence not restoring * SDR1 here */ + mfspr r3,SPRN_PTCR + std r3,_PTCR(r1) + mfspr r3,SPRN_LPCR + std r3,_LPCR(r1) FTR_SECTION_ELSE mfspr r3,SPRN_SDR1 std r3,_SDR1(r1) @@ -376,6 +379,7 @@ _GLOBAL(power9_idle_stop) mfspr r5,SPRN_PSSCR andc r5,r5,r4 or r3,r3,r5 + std r3, PACA_REQ_PSSCR(r13) mtspr SPRN_PSSCR,r3 LOAD_REG_ADDR(r5,power_enter_stop) li r4,1 @@ -495,12 +499,22 @@ pnv_restore_hyp_resource_arch300: LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) - mfspr r5,SPRN_PSSCR +BEGIN_FTR_SECTION_NESTED(71) + /* + * Assume that we are waking up from the state + * same as the Requested Level (RL) in the PSSCR + * which are Bits 60-63 + */ + ld r5,PACA_REQ_PSSCR(r13) + rldicl r5,r5,0,60 +FTR_SECTION_ELSE_NESTED(71) /* * 0-3 bits correspond to Power-Saving Level Status * which indicates the idle state we are waking up from */ + mfspr r5, SPRN_PSSCR rldicl r5,r5,4,60 +ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71) cmpd cr4,r5,r4 bge cr4,pnv_wakeup_tb_loss /* returns to caller */ @@ -731,13 +745,14 @@ timebase_resync: * Use cr3 which indicates that we are waking up with atleast partial * hypervisor state loss to determine if TIMEBASE RESYNC is needed. */ - ble cr3,clear_lock + ble cr3,.Ltb_resynced /* Time base re-sync */ bl opal_resync_timebase; /* - * If waking up from sleep, per core state is not lost, skip to - * clear_lock. + * If waking up from sleep (POWER8), per core state + * is not lost, skip to clear_lock. */ +.Ltb_resynced: blt cr4,clear_lock /* @@ -812,6 +827,10 @@ no_segments: mtctr r12 bctrl +BEGIN_FTR_SECTION + ld r4,_LPCR(r1) + mtspr SPRN_LPCR,r4 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) hypervisor_state_restored: mtspr SPRN_SRR1,r16 diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index df2a41647d8ed3..1069f74fca47b7 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -97,7 +97,7 @@ int smp_generic_cpu_bootable(unsigned int nr) /* Special case - we inhibit secondary thread startup * during boot if the user requests it. */ - if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) { + if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) return 0; if (smt_enabled_at_boot diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 2b33cfaac7b8ff..60714b8c9a2fe1 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -739,12 +739,20 @@ static int __init get_freq(char *name, int cells, unsigned long *val) static void start_cpu_decrementer(void) { #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) + unsigned int tcr; + /* Clear any pending timer interrupts */ mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); - /* Enable decrementer interrupt */ - mtspr(SPRN_TCR, TCR_DIE); -#endif /* defined(CONFIG_BOOKE) || defined(CONFIG_40x) */ + tcr = mfspr(SPRN_TCR); + /* + * The watchdog may have already been enabled by u-boot. So leave + * TRC[WP] (Watchdog Period) alone. + */ + tcr &= TCR_WP_MASK; /* Clear all bits except for TCR[WP] */ + tcr |= TCR_DIE; /* Enable decrementer */ + mtspr(SPRN_TCR, tcr); +#endif } void __init generic_calibrate_decr(void) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2f793be3d2b1db..ace6b6579961f4 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -58,7 +58,6 @@ SECTIONS #ifdef CONFIG_PPC64 KEEP(*(.head.text.first_256B)); #ifdef CONFIG_PPC_BOOK3E -# define END_FIXED 0x100 #else KEEP(*(.head.text.real_vectors)); *(.head.text.real_trampolines); @@ -66,12 +65,8 @@ SECTIONS *(.head.text.virt_trampolines); # if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) KEEP(*(.head.data.fwnmi_page)); -# define END_FIXED 0x8000 -# else -# define END_FIXED 0x7000 # endif #endif - ASSERT((. == END_FIXED), "vmlinux.lds.S: fixed section overflow error"); #else /* !CONFIG_PPC64 */ HEAD_TEXT #endif @@ -79,23 +74,6 @@ SECTIONS __head_end = .; - /* - * If the build dies here, it's likely code in head_64.S is referencing - * labels it can't reach, and the linker inserting stubs without the - * assembler's knowledge. To debug, remove the above assert and - * rebuild. Look for branch stubs in the fixed section region. - * - * Linker stub generation could be allowed in "trampoline" - * sections if absolutely necessary, but this would require - * some rework of the fixed sections. Before resorting to this, - * consider references that have sufficient addressing range, - * (e.g., hand coded trampolines) so the linker does not have - * to add stubs. - * - * Linker stubs at the top of the main text section are currently not - * detected, and will result in a crash at boot due to offsets being - * wrong. - */ #ifdef CONFIG_PPC64 /* * BLOCK(0) overrides the default output section alignment because @@ -103,18 +81,31 @@ SECTIONS * section placement to work. */ .text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) { +#ifdef CONFIG_LD_HEAD_STUB_CATCH + *(.linker_stub_catch); + . = . ; +#endif + #else .text : AT(ADDR(.text) - LOAD_OFFSET) { ALIGN_FUNCTION(); #endif /* careful! __ftr_alt_* sections need to be close to .text */ - *(.text .fixup __ftr_alt_* .ref.text) + *(.text.hot .text .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text); SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT + /* + * -Os builds call FP save/restore functions. The powerpc64 + * linker generates those on demand in the .sfpr section. + * .sfpr gets placed at the beginning of a group of input + * sections, which can break start-of-text offset if it is + * included with the main text sections, so put it by itself. + */ + *(.sfpr); MEM_KEEP(init.text) MEM_KEEP(exit.text) @@ -267,7 +258,9 @@ SECTIONS .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA *(.sdata) + *(.sdata2) *(.got.plt) *(.got) + *(.plt) } #else .data : AT(ADDR(.data) - LOAD_OFFSET) { @@ -330,6 +323,16 @@ SECTIONS _end = . ; PROVIDE32 (end = .); - /* Sections to be discarded. */ + STABS_DEBUG + + DWARF_DEBUG + DISCARDS + /DISCARD/ : { + *(*.EMB.apuinfo) + *(.glink .iplt .plt .rela* .comment) + *(.gnu.version*) + *(.gnu.attributes) + *(.eh_frame) + } } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 42b7a4fd57d9a5..48a6bd160011e0 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3317,7 +3317,7 @@ void kvmppc_alloc_host_rm_ops(void) return; } - get_online_cpus(); + cpus_read_lock(); for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) { if (!cpu_online(cpu)) @@ -3339,17 +3339,17 @@ void kvmppc_alloc_host_rm_ops(void) l_ops = (unsigned long) ops; if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) { - put_online_cpus(); + cpus_read_unlock(); kfree(ops->rm_core); kfree(ops); return; } - cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE, - "ppc/kvm_book3s:prepare", - kvmppc_set_host_core, - kvmppc_clear_host_core); - put_online_cpus(); + cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE, + "ppc/kvm_book3s:prepare", + kvmppc_set_host_core, + kvmppc_clear_host_core); + cpus_read_unlock(); } void kvmppc_free_host_rm_ops(void) diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index ed7dfce331e022..2c56f4636c2b0b 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -9,10 +9,17 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE) -obj-y += string.o alloc.o crtsavres.o code-patching.o \ - feature-fixups.o +obj-y += string.o alloc.o code-patching.o feature-fixups.o -obj-$(CONFIG_PPC32) += div64.o copy_32.o +obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o + +# See corresponding test in arch/powerpc/Makefile +# 64-bit linker creates .sfpr on demand for final link (vmlinux), +# so it is only needed for modules, and only for older linkers which +# do not support --save-restore-funcs +ifeq ($(call ld-ifversion, -lt, 225000000, y),y) +extra-$(CONFIG_PPC64) += crtsavres.o +endif obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \ diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index a24b4039352cc6..706b7cc1984627 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -82,14 +82,14 @@ _GLOBAL(__copy_tofrom_user_power7) #ifdef CONFIG_ALTIVEC cmpldi r5,16 - cmpldi cr1,r5,4096 + cmpldi cr1,r5,3328 std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy - bgt cr1,.Lvmx_copy + bge cr1,.Lvmx_copy #else cmpldi r5,16 diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S index 18af0b3d3eb238..7e5e1c28e56ac5 100644 --- a/arch/powerpc/lib/crtsavres.S +++ b/arch/powerpc/lib/crtsavres.S @@ -44,10 +44,10 @@ #ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE -#ifndef CONFIG_PPC64 - .section ".text" +#ifndef CONFIG_PPC64 + /* Routines for saving integer registers, called by the compiler. */ /* Called with r11 pointing to the stack header word of the caller of the */ /* function, just beyond the end of the integer save area. */ @@ -314,8 +314,6 @@ _GLOBAL(_restvr_31) #else /* CONFIG_PPC64 */ - .section ".text.save.restore","ax",@progbits - .globl _savegpr0_14 _savegpr0_14: std r14,-144(r1) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index aee2bb817ac68c..a01366584a4b7e 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -938,7 +938,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, /* * Tail call */ - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); break; diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 9b0afe935cc174..01cb109ebf1752 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -199,6 +199,18 @@ config CURRITUCK help This option enables support for the IBM Currituck (476fpe) evaluation board +config FSP2 + bool "IBM FSP2 (476fpe) Support" + depends on PPC_47x + default n + select 476FPE + select IBM_EMAC_EMAC4 if IBM_EMAC + select IBM_EMAC_RGMII if IBM_EMAC + select COMMON_CLK + select DEFAULT_UIMAGE + help + This option enables support for the IBM FSP2 (476fpe) board + config AKEBONO bool "IBM Akebono (476gtr) Support" depends on PPC_47x diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index 26d35b5941f798..72b824160660e0 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -12,3 +12,4 @@ obj-$(CONFIG_ISS4xx) += iss4xx.o obj-$(CONFIG_CANYONLANDS)+= canyonlands.o obj-$(CONFIG_CURRITUCK) += ppc476.o obj-$(CONFIG_AKEBONO) += ppc476.o +obj-$(CONFIG_FSP2) += fsp2.o diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c new file mode 100644 index 00000000000000..92e98048404ff4 --- /dev/null +++ b/arch/powerpc/platforms/44x/fsp2.c @@ -0,0 +1,62 @@ +/* + * FSP-2 board specific routines + * + * Based on earlier code: + * Matt Porter + * Copyright 2002-2005 MontaVista Software Inc. + * + * Eugene Surovegin or + * Copyright (c) 2003-2005 Zultys Technologies + * + * Rewritten and ported to the merged powerpc tree: + * Copyright 2007 David Gibson , IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +static __initdata struct of_device_id fsp2_of_bus[] = { + { .compatible = "ibm,plb4", }, + { .compatible = "ibm,plb6", }, + { .compatible = "ibm,opb", }, + {}, +}; + +static int __init fsp2_device_probe(void) +{ + of_platform_bus_probe(NULL, fsp2_of_bus, NULL); + return 0; +} +machine_device_initcall(fsp2, fsp2_device_probe); + +static int __init fsp2_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (!of_flat_dt_is_compatible(root, "ibm,fsp2")) + return 0; + return 1; +} + +define_machine(fsp2) { + .name = "FSP-2", + .probe = fsp2_probe, + .progress = udbg_progress, + .init_IRQ = uic_init_tree, + .get_irq = uic_get_irq, + .restart = ppc4xx_reset_system, + .calibrate_decr = generic_calibrate_decr, +}; diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index e5a891ae80ee5e..84b7ac926ce656 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -175,6 +175,8 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; + + rc = 0; out: free_page((unsigned long)buf); return rc; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 445f30a2c5ef28..46946a58700413 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -30,8 +30,33 @@ /* Power ISA 3.0 allows for stop states 0x0 - 0xF */ #define MAX_STOP_STATE 0xF +#define P9_STOP_SPR_MSR 2000 +#define P9_STOP_SPR_PSSCR 855 + static u32 supported_cpuidle_states; +/* + * The default stop state that will be used by ppc_md.power_save + * function on platforms that support stop instruction. + */ +static u64 pnv_default_stop_val; +static u64 pnv_default_stop_mask; +static bool default_stop_found; + +/* + * First deep stop state. Used to figure out when to save/restore + * hypervisor context. + */ +u64 pnv_first_deep_stop_state = MAX_STOP_STATE; + +/* + * psscr value and mask of the deepest stop idle state. + * Used when a cpu is offlined. + */ +static u64 pnv_deepest_stop_psscr_val; +static u64 pnv_deepest_stop_psscr_mask; +static bool deepest_stop_found; + static int pnv_save_sprs_for_deep_states(void) { int cpu; @@ -48,6 +73,8 @@ static int pnv_save_sprs_for_deep_states(void) uint64_t hid4_val = mfspr(SPRN_HID4); uint64_t hid5_val = mfspr(SPRN_HID5); uint64_t hmeer_val = mfspr(SPRN_HMEER); + uint64_t msr_val = MSR_IDLE; + uint64_t psscr_val = pnv_deepest_stop_psscr_val; for_each_possible_cpu(cpu) { uint64_t pir = get_hard_smp_processor_id(cpu); @@ -61,6 +88,18 @@ static int pnv_save_sprs_for_deep_states(void) if (rc != 0) return rc; + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + rc = opal_slw_set_reg(pir, P9_STOP_SPR_MSR, msr_val); + if (rc) + return rc; + + rc = opal_slw_set_reg(pir, + P9_STOP_SPR_PSSCR, psscr_val); + + if (rc) + return rc; + } + /* HIDs are per core registers */ if (cpu_thread_in_core(cpu) == 0) { @@ -72,17 +111,21 @@ static int pnv_save_sprs_for_deep_states(void) if (rc != 0) return rc; - rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val); - if (rc != 0) - return rc; + /* Only p8 needs to set extra HID regiters */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { - rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val); - if (rc != 0) - return rc; + rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val); + if (rc != 0) + return rc; - rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val); - if (rc != 0) - return rc; + rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val); + if (rc != 0) + return rc; + } } } @@ -96,15 +139,24 @@ static void pnv_alloc_idle_core_states(void) u32 *core_idle_state; /* - * core_idle_state - First 8 bits track the idle state of each thread - * of the core. The 8th bit is the lock bit. Initially all thread bits - * are set. They are cleared when the thread enters deep idle state - * like sleep and winkle. Initially the lock bit is cleared. - * The lock bit has 2 purposes - * a. While the first thread is restoring core state, it prevents - * other threads in the core from switching to process context. - * b. While the last thread in the core is saving the core state, it - * prevents a different thread from waking up. + * core_idle_state - The lower 8 bits track the idle state of + * each thread of the core. + * + * The most significant bit is the lock bit. + * + * Initially all the bits corresponding to threads_per_core + * are set. They are cleared when the thread enters deep idle + * state like sleep and winkle/stop. + * + * Initially the lock bit is cleared. The lock bit has 2 + * purposes: + * a. While the first thread in the core waking up from + * idle is restoring core state, it prevents other + * threads in the core from switching to process + * context. + * b. While the last thread in the core is saving the + * core state, it prevents a different thread from + * waking up. */ for (i = 0; i < nr_cores; i++) { int first_cpu = i * threads_per_core; @@ -112,7 +164,7 @@ static void pnv_alloc_idle_core_states(void) size_t paca_ptr_array_size; core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node); - *core_idle_state = PNV_CORE_IDLE_THREAD_BITS; + *core_idle_state = (1 << threads_per_core) - 1; paca_ptr_array_size = (threads_per_core * sizeof(struct paca_struct *)); @@ -231,14 +283,6 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600, show_fastsleep_workaround_applyonce, store_fastsleep_workaround_applyonce); -/* - * The default stop state that will be used by ppc_md.power_save - * function on platforms that support stop instruction. - */ -static u64 pnv_default_stop_val; -static u64 pnv_default_stop_mask; -static bool default_stop_found; - /* * Used for ppc_md.power_save which needs a function with no parameters */ @@ -247,20 +291,7 @@ static void power9_idle(void) power9_idle_stop(pnv_default_stop_val, pnv_default_stop_mask); } -/* - * First deep stop state. Used to figure out when to save/restore - * hypervisor context. - */ -u64 pnv_first_deep_stop_state = MAX_STOP_STATE; - -/* - * psscr value and mask of the deepest stop idle state. - * Used when a cpu is offlined. - */ -static u64 pnv_deepest_stop_psscr_val; -static u64 pnv_deepest_stop_psscr_mask; -static bool deepest_stop_found; - +#ifdef CONFIG_HOTPLUG_CPU /* * pnv_cpu_offline: A function that puts the CPU into the deepest * available platform idle state on a CPU-Offline. @@ -293,6 +324,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu) return srr1; } +#endif /* * Power ISA 3.0 idle initialization. diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index f620572f891f4f..4ca6c26a56d5cd 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -99,10 +99,10 @@ opal_return: lwz r4,8(r1); ld r5,PPC_LR_STKOFF(r1); ld r6,PACASAVEDMSR(r13); - mtspr SPRN_SRR0,r5; - mtspr SPRN_SRR1,r6; mtcr r4; - rfid + mtspr SPRN_HSRR0,r5; + mtspr SPRN_HSRR1,r6; + hrfid opal_real_call: mfcr r11 diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 0babef11136fc8..309876d699e947 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -348,7 +348,7 @@ static int set_subcores_per_core(int new_mode) state->master = 0; } - get_online_cpus(); + cpus_read_lock(); /* This cpu will update the globals before exiting stop machine */ this_cpu_ptr(&split_state)->master = 1; @@ -356,9 +356,10 @@ static int set_subcores_per_core(int new_mode) /* Ensure state is consistent before we call the other cpus */ mb(); - stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask); + stop_machine_cpuslocked(cpu_update_split_mode, &new_mode, + cpu_online_mask); - put_online_cpus(); + cpus_read_unlock(); return 0; } @@ -407,7 +408,13 @@ static DEVICE_ATTR(subcores_per_core, 0644, static int subcore_init(void) { - if (!cpu_has_feature(CPU_FTR_SUBCORE)) + unsigned pvr_ver; + + pvr_ver = PVR_VER(mfspr(SPRN_PVR)); + + if (pvr_ver != PVR_POWER8 && + pvr_ver != PVR_POWER8E && + pvr_ver != PVR_POWER8NVL) return 0; /* diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index e104c71ea44ab5..1fb162ba9d1c6a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn) for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index); lmbs[i].flags = be32_to_cpu(lmbs[i].flags); } @@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn, for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index); lmbs[i].flags = cpu_to_be32(lmbs[i].flags); } diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index ef470b470b04ae..6afddae2fb4796 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc); + struct u8_gpio_chip *u8_gc = + container_of(mm_gc, struct u8_gpio_chip, mm_gc); u8_gc->data = in_8(mm_gc->regs); } diff --git a/arch/powerpc/tools/head_check.sh b/arch/powerpc/tools/head_check.sh new file mode 100644 index 00000000000000..ad9e57209aa4c2 --- /dev/null +++ b/arch/powerpc/tools/head_check.sh @@ -0,0 +1,78 @@ +# Copyright © 2016 IBM Corporation + +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; either version +# 2 of the License, or (at your option) any later version. + +# This script checks the head of a vmlinux for linker stubs that +# break our placement of fixed-location code for 64-bit. + +# based on relocs_check.pl +# Copyright © 2009 IBM Corporation + +# NOTE! +# +# If the build dies here, it's likely code in head_64.S/exception-64*.S or +# nearby, is branching to labels it can't reach directly, which results in the +# linker inserting branch stubs. This can move code around in ways that break +# the fixed section calculations (head-64.h). To debug this, disassemble the +# vmlinux and look for branch stubs (long_branch, plt_branch, etc.) in the +# fixed section region (0 - 0x8000ish). Check what code is calling those stubs, +# and perhaps change so a direct branch can reach. +# +# A ".linker_stub_catch" section is used to catch some stubs generated by +# early .text code, which tend to get placed at the start of the section. +# If there are too many such stubs, they can overflow this section. Expanding +# it may help (or reducing the number of stub branches). +# +# Linker stubs use the TOC pointer, so even if fixed section code could +# tolerate them being inserted into head code, they can't be allowed in low +# level entry code (boot, interrupt vectors, etc) until r2 is set up. This +# could cause the kernel to die in early boot. + +# Turn this on if you want more debug output: +# set -x + +if [ $# -lt 2 ]; then + echo "$0 [path to nm] [path to vmlinux]" 1>&2 + exit 1 +fi + +# Have Kbuild supply the path to nm so we handle cross compilation. +nm="$1" +vmlinux="$2" + +# gcc-4.6-era toolchain make _stext an A (absolute) symbol rather than T +$nm "$vmlinux" | grep -e " [TA] _stext$" -e " t start_first_256B$" -e " a text_start$" -e " t start_text$" -m4 > .tmp_symbols.txt + + +vma=$(cat .tmp_symbols.txt | grep -e " [TA] _stext$" | cut -d' ' -f1) + +expected_start_head_addr=$vma + +start_head_addr=$(cat .tmp_symbols.txt | grep " t start_first_256B$" | cut -d' ' -f1) + +if [ "$start_head_addr" != "$expected_start_head_addr" ]; then + echo "ERROR: head code starts at $start_head_addr, should be $expected_start_head_addr" + echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option" + echo "ERROR: see comments in arch/powerpc/tools/head_check.sh" + + exit 1 +fi + +top_vma=$(echo $vma | cut -d'0' -f1) + +expected_start_text_addr=$(cat .tmp_symbols.txt | grep " a text_start$" | cut -d' ' -f1 | sed "s/^0/$top_vma/") + +start_text_addr=$(cat .tmp_symbols.txt | grep " t start_text$" | cut -d' ' -f1) + +if [ "$start_text_addr" != "$expected_start_text_addr" ]; then + echo "ERROR: start_text address is $start_text_addr, should be $expected_start_text_addr" + echo "ERROR: try to enable LD_HEAD_STUB_CATCH config option" + echo "ERROR: see comments in arch/powerpc/tools/head_check.sh" + + exit 1 +fi + +rm -f .tmp_symbols.txt diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh new file mode 100644 index 00000000000000..1e972df3107eed --- /dev/null +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -0,0 +1,57 @@ +# Copyright © 2016 IBM Corporation +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; either version +# 2 of the License, or (at your option) any later version. +# +# This script checks the relocations of a vmlinux for "suspicious" +# branches from unrelocated code (head_64.S code). + +# Turn this on if you want more debug output: +# set -x + +# Have Kbuild supply the path to objdump so we handle cross compilation. +objdump="$1" +vmlinux="$2" + +#__end_interrupts should be located within the first 64K + +end_intr=0x$( +"$objdump" -R "$vmlinux" -d --start-address=0xc000000000000000 \ + --stop-address=0xc000000000010000 | +grep '\<__end_interrupts>:' | +awk '{print $1}' +) + +BRANCHES=$( +"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000 \ + --stop-address=${end_intr} | +grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | +grep -v '\<__start_initialization_multiplatform>' | +grep -v -e 'b.\?.\?ctr' | +grep -v -e 'b.\?.\?lr' | +sed 's/://' | +awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' +) + +for tuple in $BRANCHES +do + from=`echo $tuple | cut -d':' -f1` + branch=`echo $tuple | cut -d':' -f2` + to=`echo $tuple | cut -d':' -f3 | sed 's/cr[0-7],//'` + sym=`echo $tuple | cut -d':' -f4` + + if (( $to > $end_intr )) + then + if [ -z "$bad_branches" ]; then + echo "WARNING: Unrelocated relative branches" + bad_branches="yes" + fi + echo "$from $branch-> $to $sym" + fi +done + +if [ -z "$bad_branches" ]; then + exit 0 +fi diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index f11f65634aab44..a728e191961330 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1242,14 +1242,14 @@ bpt_cmds(void) { int cmd; unsigned long a; - int mode, i; + int i; struct bpt *bp; - const char badaddr[] = "Only kernel addresses are permitted " - "for breakpoints\n"; cmd = inchar(); switch (cmd) { -#ifndef CONFIG_8xx +#ifndef CONFIG_PPC_8xx + static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n"; + int mode; case 'd': /* bd - hardware data breakpoint */ mode = 7; cmd = inchar(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e86d0223119523..6940c68d8437cc 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -184,7 +184,7 @@ config SCHED_OMIT_FRAME_POINTER config PGTABLE_LEVELS int - default 4 + default 5 source "init/Kconfig" diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index 678d9863e3f079..ad4bd777768d16 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o -obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o paes_s390.o +obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o +obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o obj-$(CONFIG_S390_PRNG) += prng.o obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c index 9317b3e645e2fe..36aefc07d10cda 100644 --- a/arch/s390/crypto/arch_random.c +++ b/arch/s390/crypto/arch_random.c @@ -12,6 +12,7 @@ #include #include +#include #include #include diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 45092b12f54f53..b3c88479febab2 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,10 +1,12 @@ generic-y += asm-offsets.h generic-y += cacheflush.h generic-y += clkdev.h +generic-y += device.h generic-y += dma-contiguous.h generic-y += div64.h generic-y += emergency-restart.h generic-y += export.h +generic-y += fb.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kmap_types.h diff --git a/arch/s390/include/asm/device.h b/arch/s390/include/asm/device.h deleted file mode 100644 index 5203fc87f080ed..00000000000000 --- a/arch/s390/include/asm/device.h +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Arch specific extensions to struct device - * - * This file is released under the GPLv2 - */ -struct dev_archdata { -}; - -struct pdev_archdata { -}; diff --git a/arch/s390/include/asm/fb.h b/arch/s390/include/asm/fb.h deleted file mode 100644 index c7df3803099200..00000000000000 --- a/arch/s390/include/asm/fb.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_FB_H_ -#define _ASM_FB_H_ -#include - -#define fb_pgprotect(...) do {} while (0) - -static inline int fb_is_primary_device(struct fb_info *info) -{ - return 0; -} - -#endif /* _ASM_FB_H_ */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 426614a882a9b1..a8cafed79eb445 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -45,6 +45,8 @@ #define KVM_REQ_ENABLE_IBS 8 #define KVM_REQ_DISABLE_IBS 9 #define KVM_REQ_ICPT_OPEREXC 10 +#define KVM_REQ_START_MIGRATION 11 +#define KVM_REQ_STOP_MIGRATION 12 #define SIGP_CTRL_C 0x80 #define SIGP_CTRL_SCN_MASK 0x3f @@ -691,6 +693,12 @@ struct kvm_s390_vsie { struct page *pages[KVM_MAX_VCPUS]; }; +struct kvm_s390_migration_state { + unsigned long bitmap_size; /* in bits (number of guest pages) */ + atomic64_t dirty_pages; /* number of dirty pages */ + unsigned long *pgste_bitmap; +}; + struct kvm_arch{ void *sca; int use_esca; @@ -718,6 +726,7 @@ struct kvm_arch{ struct kvm_s390_crypto crypto; struct kvm_s390_vsie vsie; u64 epoch; + struct kvm_s390_migration_state *migration_state; /* subset of available cpu features enabled by user space */ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); }; diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 69b8a41fca84b4..624deaa44230c2 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -74,6 +74,7 @@ typedef struct { unsigned long pgste; } pgste_t; typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long pmd; } pmd_t; typedef struct { unsigned long pud; } pud_t; +typedef struct { unsigned long p4d; } p4d_t; typedef struct { unsigned long pgd; } pgd_t; typedef pte_t *pgtable_t; @@ -82,12 +83,14 @@ typedef pte_t *pgtable_t; #define pte_val(x) ((x).pte) #define pmd_val(x) ((x).pmd) #define pud_val(x) ((x).pud) +#define p4d_val(x) ((x).p4d) #define pgd_val(x) ((x).pgd) #define __pgste(x) ((pgste_t) { (x) } ) #define __pte(x) ((pte_t) { (x) } ) #define __pmd(x) ((pmd_t) { (x) } ) #define __pud(x) ((pud_t) { (x) } ) +#define __p4d(x) ((p4d_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 166f703dad7c4f..bb0ff1bb0c4a82 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -51,12 +51,24 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _SEGMENT_ENTRY_EMPTY; if (mm->context.asce_limit <= (1UL << 42)) return _REGION3_ENTRY_EMPTY; - return _REGION2_ENTRY_EMPTY; + if (mm->context.asce_limit <= (1UL << 53)) + return _REGION2_ENTRY_EMPTY; + return _REGION1_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *); +int crst_table_upgrade(struct mm_struct *mm, unsigned long limit); void crst_table_downgrade(struct mm_struct *); +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) +{ + unsigned long *table = crst_table_alloc(mm); + + if (table) + crst_table_init(table, _REGION2_ENTRY_EMPTY); + return (p4d_t *) table; +} +#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { unsigned long *table = crst_table_alloc(mm); @@ -86,9 +98,14 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) crst_table_free(mm, (unsigned long *) pmd); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + pgd_val(*pgd) = _REGION1_ENTRY | __pa(p4d); +} + +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { - pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud); + p4d_val(*p4d) = _REGION2_ENTRY | __pa(pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index e6e3b887bee3d6..3effb26f0e1a5e 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -24,7 +24,6 @@ * the S390 page table tree. */ #ifndef __ASSEMBLY__ -#include #include #include #include @@ -87,12 +86,15 @@ extern unsigned long zero_page_mask; */ #define PMD_SHIFT 20 #define PUD_SHIFT 31 -#define PGDIR_SHIFT 42 +#define P4D_SHIFT 42 +#define PGDIR_SHIFT 53 #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) +#define P4D_SIZE (1UL << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) @@ -105,6 +107,7 @@ extern unsigned long zero_page_mask; #define PTRS_PER_PTE 256 #define PTRS_PER_PMD 2048 #define PTRS_PER_PUD 2048 +#define PTRS_PER_P4D 2048 #define PTRS_PER_PGD 2048 #define FIRST_USER_ADDRESS 0UL @@ -115,6 +118,8 @@ extern unsigned long zero_page_mask; printk("%s:%d: bad pmd %p.\n", __FILE__, __LINE__, (void *) pmd_val(e)) #define pud_ERROR(e) \ printk("%s:%d: bad pud %p.\n", __FILE__, __LINE__, (void *) pud_val(e)) +#define p4d_ERROR(e) \ + printk("%s:%d: bad p4d %p.\n", __FILE__, __LINE__, (void *) p4d_val(e)) #define pgd_ERROR(e) \ printk("%s:%d: bad pgd %p.\n", __FILE__, __LINE__, (void *) pgd_val(e)) @@ -310,8 +315,8 @@ static inline int is_module_addr(void *addr) #define _REGION3_ENTRY_SOFT_DIRTY 0x0000 /* SW region soft dirty bit */ #endif -#define _REGION_ENTRY_BITS 0xfffffffffffff227UL -#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe27UL +#define _REGION_ENTRY_BITS 0xfffffffffffff22fUL +#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ #define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL @@ -564,14 +569,14 @@ static inline void crdte(unsigned long old, unsigned long new, */ static inline int pgd_present(pgd_t pgd) { - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1) return 1; return (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) != 0UL; } static inline int pgd_none(pgd_t pgd) { - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1) return 0; return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL; } @@ -589,6 +594,28 @@ static inline int pgd_bad(pgd_t pgd) return (pgd_val(pgd) & mask) != 0; } +static inline int p4d_present(p4d_t p4d) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + return 1; + return (p4d_val(p4d) & _REGION_ENTRY_ORIGIN) != 0UL; +} + +static inline int p4d_none(p4d_t p4d) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + return 0; + return p4d_val(p4d) == _REGION2_ENTRY_EMPTY; +} + +static inline unsigned long p4d_pfn(p4d_t p4d) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + return (p4d_val(p4d) & origin_mask) >> PAGE_SHIFT; +} + static inline int pud_present(pud_t pud) { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) @@ -641,6 +668,13 @@ static inline int pud_bad(pud_t pud) return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0; } +static inline int p4d_bad(p4d_t p4d) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + return pud_bad(__pud(p4d_val(p4d))); + return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0; +} + static inline int pmd_present(pmd_t pmd) { return pmd_val(pmd) != _SEGMENT_ENTRY_EMPTY; @@ -794,8 +828,14 @@ static inline int pte_unused(pte_t pte) static inline void pgd_clear(pgd_t *pgd) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pgd_val(*pgd) = _REGION2_ENTRY_EMPTY; + if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + pgd_val(*pgd) = _REGION1_ENTRY_EMPTY; +} + +static inline void p4d_clear(p4d_t *p4d) +{ + if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + p4d_val(*p4d) = _REGION2_ENTRY_EMPTY; } static inline void pud_clear(pud_t *pud) @@ -1089,6 +1129,7 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) } #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) #define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1)) @@ -1098,19 +1139,31 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) +#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { - pud_t *pud = (pud_t *) pgd; - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pud = (pud_t *) pgd_deref(*pgd); - return pud + pud_index(address); + p4d_t *p4d = (p4d_t *) pgd; + + if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + p4d = (p4d_t *) pgd_deref(*pgd); + return p4d + p4d_index(address); +} + +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + pud_t *pud = (pud_t *) p4d; + + if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + pud = (pud_t *) p4d_deref(*p4d); + return pud + pud_index(address); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { pmd_t *pmd = (pmd_t *) pud; + if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) pmd = (pmd_t *) pud_deref(*pud); return pmd + pmd_index(address); @@ -1122,6 +1175,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) #define pud_page(pud) pfn_to_page(pud_pfn(pud)) +#define p4d_page(pud) pfn_to_page(p4d_pfn(p4d)) /* Find an entry in the lowest level page table.. */ #define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr)) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 60d395fdc86438..f57c017a5c037e 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -92,11 +92,11 @@ extern void execve_tail(void); */ #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_31BIT) ? \ - (1UL << 31) : (1UL << 53)) + (1UL << 31) : -PAGE_SIZE) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) -#define TASK_SIZE_MAX (1UL << 53) +#define TASK_SIZE_MAX (-PAGE_SIZE) #define STACK_TOP (test_thread_flag(TIF_31BIT) ? \ (1UL << 31) : (1UL << 42)) diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h index 72df5f2de6b0b7..020a8814d511e5 100644 --- a/arch/s390/include/asm/sigp.h +++ b/arch/s390/include/asm/sigp.h @@ -59,7 +59,7 @@ static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm, int cc; cc = ____pcpu_sigp(addr, order, parm, &_status); - if (status && cc == 1) + if (status && cc == SIGP_CC_STATUS_STORED) *status = _status; return cc; } diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 853b2a3d8deeea..7317b3108a8885 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,6 +136,21 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, tlb_remove_table(tlb, pmd); } +/* + * p4d_free_tlb frees a pud table and clears the CRSTE for the + * region second table entry from the tlb. + * If the mm uses a four level page table the single p4d is freed + * as the pgd. p4d_free_tlb checks the asce_limit against 8PB + * to avoid the double free of the p4d in this case. + */ +static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long address) +{ + if (tlb->mm->context.asce_limit <= (1UL << 53)) + return; + tlb_remove_table(tlb, p4d); +} + /* * pud_free_tlb frees a pud table and clears the CRSTE for the * region third table entry from the tlb. diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 3dd2a1d308dd0b..d6879a916de525 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -70,6 +70,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_TOD 1 #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 +#define KVM_S390_VM_MIGRATION 4 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 @@ -151,6 +152,11 @@ struct kvm_s390_vm_cpu_subfunc { #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3 +/* kvm attributes for migration mode */ +#define KVM_S390_VM_MIGRATION_STOP 0 +#define KVM_S390_VM_MIGRATION_START 1 +#define KVM_S390_VM_MIGRATION_STATUS 2 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index e8e5ecf673fdd8..fb9769d7e74e26 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -104,4 +104,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index e408d9cc5b96ad..6315037335ba93 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -231,12 +231,17 @@ ENTRY(sie64a) lctlg %c1,%c1,__LC_USER_ASCE # load primary asce .Lsie_done: # some program checks are suppressing. C code (e.g. do_protection_exception) -# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other -# instructions between sie64a and .Lsie_done should not cause program -# interrupts. So lets use a nop (47 00 00 00) as a landing pad. +# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There +# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable. +# Other instructions between sie64a and .Lsie_done should not cause program +# interrupts. So lets use 3 nops as a landing pad for all possible rewinds. # See also .Lcleanup_sie -.Lrewind_pad: - nop 0 +.Lrewind_pad6: + nopr 7 +.Lrewind_pad4: + nopr 7 +.Lrewind_pad2: + nopr 7 .globl sie_exit sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area @@ -249,7 +254,9 @@ sie_exit: stg %r14,__SF_EMPTY+16(%r15) # set exit reason code j sie_exit - EX_TABLE(.Lrewind_pad,.Lsie_fault) + EX_TABLE(.Lrewind_pad6,.Lsie_fault) + EX_TABLE(.Lrewind_pad4,.Lsie_fault) + EX_TABLE(.Lrewind_pad2,.Lsie_fault) EX_TABLE(sie_exit,.Lsie_fault) EXPORT_SYMBOL(sie64a) EXPORT_SYMBOL(sie_exit) diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 6aa630a8d24f4d..262506cee4c32e 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry, args.entry = entry; args.type = type; - stop_machine(__sm_arch_jump_label_transform, &args, NULL); + stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL); } void arch_jump_label_transform_static(struct jump_entry *entry, diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 3d6a997464549c..6842e4501e2e53 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p) { struct swap_insn_args args = {.p = p, .arm_kprobe = 1}; - stop_machine(swap_instruction, &args, NULL); + stop_machine_cpuslocked(swap_instruction, &args, NULL); } NOKPROBE_SYMBOL(arch_arm_kprobe); @@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p) { struct swap_insn_args args = {.p = p, .arm_kprobe = 0}; - stop_machine(swap_instruction, &args, NULL); + stop_machine_cpuslocked(swap_instruction, &args, NULL); } NOKPROBE_SYMBOL(arch_disarm_kprobe); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 363000a77ffc74..1020a11a24e50e 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -207,6 +208,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) kmem_cache_alloc(pcpu_mcesa_cache, GFP_KERNEL); if (!mcesa_origin) goto out; + /* The pointer is stored with mcesa_bits ORed in */ + kmemleak_not_leak((void *) mcesa_origin); mcesa_bits = MACHINE_HAS_GS ? 11 : 0; } } else { diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index c3a52f9a69a059..192efdfac91829 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work) goto out_unlock; memset(&stp_sync, 0, sizeof(stp_sync)); - get_online_cpus(); + cpus_read_lock(); atomic_set(&stp_sync.cpus, num_online_cpus() - 1); - stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask); - put_online_cpus(); + stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask); + cpus_read_unlock(); if (!check_sync_clock()) /* diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index f787b9d8f54c35..442e5423ce3dbc 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "entry.h" diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 10516ae3b55e4e..b89d19f6f2ab4b 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -50,6 +50,56 @@ static struct page **vdso64_pagelist; */ unsigned int __read_mostly vdso_enabled = 1; +static int vdso_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page **vdso_pagelist; + unsigned long vdso_pages; + + vdso_pagelist = vdso64_pagelist; + vdso_pages = vdso64_pages; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + vdso_pagelist = vdso32_pagelist; + vdso_pages = vdso32_pages; + } +#endif + + if (vmf->pgoff >= vdso_pages) + return VM_FAULT_SIGBUS; + + vmf->page = vdso_pagelist[vmf->pgoff]; + get_page(vmf->page); + return 0; +} + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *vma) +{ + unsigned long vdso_pages; + + vdso_pages = vdso64_pages; +#ifdef CONFIG_COMPAT + if (is_compat_task()) + vdso_pages = vdso32_pages; +#endif + + if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start) + return -EINVAL; + + if (WARN_ON_ONCE(current->mm != vma->vm_mm)) + return -EFAULT; + + current->mm->context.vdso_base = vma->vm_start; + return 0; +} + +static const struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .fault = vdso_fault, + .mremap = vdso_mremap, +}; + static int __init vdso_setup(char *s) { unsigned long val; @@ -181,7 +231,7 @@ static void vdso_init_cr5(void) int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; - struct page **vdso_pagelist; + struct vm_area_struct *vma; unsigned long vdso_pages; unsigned long vdso_base; int rc; @@ -194,13 +244,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!uses_interp) return 0; - vdso_pagelist = vdso64_pagelist; vdso_pages = vdso64_pages; #ifdef CONFIG_COMPAT - if (is_compat_task()) { - vdso_pagelist = vdso32_pagelist; + if (is_compat_task()) vdso_pages = vdso32_pages; - } #endif /* * vDSO has a problem and was disabled, just don't "enable" it for @@ -209,8 +256,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (vdso_pages == 0) return 0; - current->mm->context.vdso_base = 0; - /* * pick a base address for the vDSO in process space. We try to put * it at vdso_base which is the "natural" base for it, but we might @@ -224,13 +269,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) goto out_up; } - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - current->mm->context.vdso_base = vdso_base; - /* * our vma flags don't have VM_WRITE so by default, the process * isn't allowed to write those pages. @@ -241,24 +279,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * It's fine to use that for setting breakpoints in the vDSO code * pages though. */ - rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdso_pagelist); - if (rc) - current->mm->context.vdso_base = 0; + vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + &vdso_mapping); + if (IS_ERR(vma)) { + rc = PTR_ERR(vma); + goto out_up; + } + + current->mm->context.vdso_base = vdso_base; + rc = 0; + out_up: up_write(&mm->mmap_sem); return rc; } -const char *arch_vma_name(struct vm_area_struct *vma) -{ - if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base) - return "[vdso]"; - return NULL; -} - static int __init vdso_init(void) { int i; diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 072d84ba42a372..dd7178fbb4f3bd 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -110,11 +110,10 @@ static inline u64 scale_vtime(u64 vtime) return vtime; } -static void account_system_index_scaled(struct task_struct *p, - u64 cputime, u64 scaled, +static void account_system_index_scaled(struct task_struct *p, u64 cputime, enum cpu_usage_stat index) { - p->stimescaled += cputime_to_nsecs(scaled); + p->stimescaled += cputime_to_nsecs(scale_vtime(cputime)); account_system_index_time(p, cputime_to_nsecs(cputime), index); } @@ -176,14 +175,11 @@ static int do_account_vtime(struct task_struct *tsk) } if (system) - account_system_index_scaled(tsk, system, scale_vtime(system), - CPUTIME_SYSTEM); + account_system_index_scaled(tsk, system, CPUTIME_SYSTEM); if (hardirq) - account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq), - CPUTIME_IRQ); + account_system_index_scaled(tsk, hardirq, CPUTIME_IRQ); if (softirq) - account_system_index_scaled(tsk, softirq, scale_vtime(softirq), - CPUTIME_SOFTIRQ); + account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 689ac48361c697..4ef3035d4dc41c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -386,6 +387,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_SKEYS: case KVM_CAP_S390_IRQ_STATE: case KVM_CAP_S390_USER_INSTR0: + case KVM_CAP_S390_CMMA_MIGRATION: case KVM_CAP_S390_AIS: r = 1; break; @@ -750,6 +752,131 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) return 0; } +static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) +{ + int cx; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(cx, vcpu, kvm) + kvm_s390_sync_request(req, vcpu); +} + +/* + * Must be called with kvm->srcu held to avoid races on memslots, and with + * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration. + */ +static int kvm_s390_vm_start_migration(struct kvm *kvm) +{ + struct kvm_s390_migration_state *mgs; + struct kvm_memory_slot *ms; + /* should be the only one */ + struct kvm_memslots *slots; + unsigned long ram_pages; + int slotnr; + + /* migration mode already enabled */ + if (kvm->arch.migration_state) + return 0; + + slots = kvm_memslots(kvm); + if (!slots) + return -EINVAL; + if (!slots->used_slots) + return -EINVAL; + + mgs = kzalloc(sizeof(*mgs), GFP_KERNEL); + if (!mgs) + return -ENOMEM; + kvm->arch.migration_state = mgs; + + if (kvm->arch.use_cmma && slots) { + /* + * Get the last slot. They should be sorted by base_gfn, so the + * last slot is also the one at the end of the address space. + * We have verified above that at least one slot is present. + */ + ms = slots->memslots + slots->used_slots - 1; + /* round up so we only use full longs */ + ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG); + /* allocate enough bytes to store all the bits */ + mgs->pgste_bitmap = vmalloc(ram_pages / 8); + if (!mgs->pgste_bitmap) { + kfree(mgs); + kvm->arch.migration_state = NULL; + return -ENOMEM; + } + + mgs->bitmap_size = ram_pages; + atomic64_set(&mgs->dirty_pages, ram_pages); + /* mark all the pages in active slots as dirty */ + for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { + ms = slots->memslots + slotnr; + bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages); + } + + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION); + } + return 0; +} + +/* + * Must be called with kvm->lock to avoid races with ourselves and + * kvm_s390_vm_start_migration. + */ +static int kvm_s390_vm_stop_migration(struct kvm *kvm) +{ + struct kvm_s390_migration_state *mgs; + + /* migration mode already disabled */ + if (!kvm->arch.migration_state) + return 0; + mgs = kvm->arch.migration_state; + kvm->arch.migration_state = NULL; + + if (kvm->arch.use_cmma) { + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); + vfree(mgs->pgste_bitmap); + } + kfree(mgs); + return 0; +} + +static int kvm_s390_vm_set_migration(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + int idx, res = -ENXIO; + + mutex_lock(&kvm->lock); + switch (attr->attr) { + case KVM_S390_VM_MIGRATION_START: + idx = srcu_read_lock(&kvm->srcu); + res = kvm_s390_vm_start_migration(kvm); + srcu_read_unlock(&kvm->srcu, idx); + break; + case KVM_S390_VM_MIGRATION_STOP: + res = kvm_s390_vm_stop_migration(kvm); + break; + default: + break; + } + mutex_unlock(&kvm->lock); + + return res; +} + +static int kvm_s390_vm_get_migration(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + u64 mig = (kvm->arch.migration_state != NULL); + + if (attr->attr != KVM_S390_VM_MIGRATION_STATUS) + return -ENXIO; + + if (copy_to_user((void __user *)attr->addr, &mig, sizeof(mig))) + return -EFAULT; + return 0; +} + static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) { u8 gtod_high; @@ -1090,6 +1217,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CRYPTO: ret = kvm_s390_vm_set_crypto(kvm, attr); break; + case KVM_S390_VM_MIGRATION: + ret = kvm_s390_vm_set_migration(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1112,6 +1242,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_MODEL: ret = kvm_s390_get_cpu_model(kvm, attr); break; + case KVM_S390_VM_MIGRATION: + ret = kvm_s390_vm_get_migration(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1179,6 +1312,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) break; } break; + case KVM_S390_VM_MIGRATION: + ret = 0; + break; default: ret = -ENXIO; break; @@ -1286,6 +1422,182 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) return r; } +/* + * Base address and length must be sent at the start of each block, therefore + * it's cheaper to send some clean data, as long as it's less than the size of + * two longs. + */ +#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *)) +/* for consistency */ +#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) + +/* + * This function searches for the next page with dirty CMMA attributes, and + * saves the attributes in the buffer up to either the end of the buffer or + * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found; + * no trailing clean bytes are saved. + * In case no dirty bits were found, or if CMMA was not enabled or used, the + * output buffer will indicate 0 as length. + */ +static int kvm_s390_get_cmma_bits(struct kvm *kvm, + struct kvm_s390_cmma_log *args) +{ + struct kvm_s390_migration_state *s = kvm->arch.migration_state; + unsigned long bufsize, hva, pgstev, i, next, cur; + int srcu_idx, peek, r = 0, rr; + u8 *res; + + cur = args->start_gfn; + i = next = pgstev = 0; + + if (unlikely(!kvm->arch.use_cmma)) + return -ENXIO; + /* Invalid/unsupported flags were specified */ + if (args->flags & ~KVM_S390_CMMA_PEEK) + return -EINVAL; + /* Migration mode query, and we are not doing a migration */ + peek = !!(args->flags & KVM_S390_CMMA_PEEK); + if (!peek && !s) + return -EINVAL; + /* CMMA is disabled or was not used, or the buffer has length zero */ + bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX); + if (!bufsize || !kvm->mm->context.use_cmma) { + memset(args, 0, sizeof(*args)); + return 0; + } + + if (!peek) { + /* We are not peeking, and there are no dirty pages */ + if (!atomic64_read(&s->dirty_pages)) { + memset(args, 0, sizeof(*args)); + return 0; + } + cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, + args->start_gfn); + if (cur >= s->bitmap_size) /* nothing found, loop back */ + cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0); + if (cur >= s->bitmap_size) { /* again! (very unlikely) */ + memset(args, 0, sizeof(*args)); + return 0; + } + next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1); + } + + res = vmalloc(bufsize); + if (!res) + return -ENOMEM; + + args->start_gfn = cur; + + down_read(&kvm->mm->mmap_sem); + srcu_idx = srcu_read_lock(&kvm->srcu); + while (i < bufsize) { + hva = gfn_to_hva(kvm, cur); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + break; + } + /* decrement only if we actually flipped the bit to 0 */ + if (!peek && test_and_clear_bit(cur, s->pgste_bitmap)) + atomic64_dec(&s->dirty_pages); + r = get_pgste(kvm->mm, hva, &pgstev); + if (r < 0) + pgstev = 0; + /* save the value */ + res[i++] = (pgstev >> 24) & 0x3; + /* + * if the next bit is too far away, stop. + * if we reached the previous "next", find the next one + */ + if (!peek) { + if (next > cur + KVM_S390_MAX_BIT_DISTANCE) + break; + if (cur == next) + next = find_next_bit(s->pgste_bitmap, + s->bitmap_size, cur + 1); + /* reached the end of the bitmap or of the buffer, stop */ + if ((next >= s->bitmap_size) || + (next >= args->start_gfn + bufsize)) + break; + } + cur++; + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + up_read(&kvm->mm->mmap_sem); + args->count = i; + args->remaining = s ? atomic64_read(&s->dirty_pages) : 0; + + rr = copy_to_user((void __user *)args->values, res, args->count); + if (rr) + r = -EFAULT; + + vfree(res); + return r; +} + +/* + * This function sets the CMMA attributes for the given pages. If the input + * buffer has zero length, no action is taken, otherwise the attributes are + * set and the mm->context.use_cmma flag is set. + */ +static int kvm_s390_set_cmma_bits(struct kvm *kvm, + const struct kvm_s390_cmma_log *args) +{ + unsigned long hva, mask, pgstev, i; + uint8_t *bits; + int srcu_idx, r = 0; + + mask = args->mask; + + if (!kvm->arch.use_cmma) + return -ENXIO; + /* invalid/unsupported flags */ + if (args->flags != 0) + return -EINVAL; + /* Enforce sane limit on memory allocation */ + if (args->count > KVM_S390_CMMA_SIZE_MAX) + return -EINVAL; + /* Nothing to do */ + if (args->count == 0) + return 0; + + bits = vmalloc(sizeof(*bits) * args->count); + if (!bits) + return -ENOMEM; + + r = copy_from_user(bits, (void __user *)args->values, args->count); + if (r) { + r = -EFAULT; + goto out; + } + + down_read(&kvm->mm->mmap_sem); + srcu_idx = srcu_read_lock(&kvm->srcu); + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + break; + } + + pgstev = bits[i]; + pgstev = pgstev << 24; + mask &= _PGSTE_GPS_USAGE_MASK; + set_pgste_bits(kvm->mm, hva, mask, pgstev); + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + up_read(&kvm->mm->mmap_sem); + + if (!kvm->mm->context.use_cmma) { + down_write(&kvm->mm->mmap_sem); + kvm->mm->context.use_cmma = 1; + up_write(&kvm->mm->mmap_sem); + } +out: + vfree(bits); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1364,6 +1676,29 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_s390_set_skeys(kvm, &args); break; } + case KVM_S390_GET_CMMA_BITS: { + struct kvm_s390_cmma_log args; + + r = -EFAULT; + if (copy_from_user(&args, argp, sizeof(args))) + break; + r = kvm_s390_get_cmma_bits(kvm, &args); + if (!r) { + r = copy_to_user(argp, &args, sizeof(args)); + if (r) + r = -EFAULT; + } + break; + } + case KVM_S390_SET_CMMA_BITS: { + struct kvm_s390_cmma_log args; + + r = -EFAULT; + if (copy_from_user(&args, argp, sizeof(args))) + break; + r = kvm_s390_set_cmma_bits(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -1633,6 +1968,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_s390_destroy_adapters(kvm); kvm_s390_clear_float_irqs(kvm); kvm_s390_vsie_destroy(kvm); + if (kvm->arch.migration_state) { + vfree(kvm->arch.migration_state->pgste_bitmap); + kfree(kvm->arch.migration_state); + } KVM_EVENT(3, "vm 0x%pK destroyed", kvm); } @@ -1977,7 +2316,6 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) if (!vcpu->arch.sie_block->cbrlo) return -ENOMEM; - vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; vcpu->arch.sie_block->ecb2 &= ~ECB2_PFMFI; return 0; } @@ -2489,6 +2827,27 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) goto retry; } + if (kvm_check_request(KVM_REQ_START_MIGRATION, vcpu)) { + /* + * Disable CMMA virtualization; we will emulate the ESSA + * instruction manually, in order to provide additional + * functionalities needed for live migration. + */ + vcpu->arch.sie_block->ecb2 &= ~ECB2_CMMA; + goto retry; + } + + if (kvm_check_request(KVM_REQ_STOP_MIGRATION, vcpu)) { + /* + * Re-enable CMMA virtualization if CMMA is available and + * was used. + */ + if ((vcpu->kvm->arch.use_cmma) && + (vcpu->kvm->mm->context.use_cmma)) + vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; + goto retry; + } + /* nothing to do, just clear the request */ kvm_clear_request(KVM_REQ_UNHALT, vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c03106c428cfa8..a226c459809bf0 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -949,13 +950,72 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) return 0; } +static inline int do_essa(struct kvm_vcpu *vcpu, const int orc) +{ + struct kvm_s390_migration_state *ms = vcpu->kvm->arch.migration_state; + int r1, r2, nappended, entries; + unsigned long gfn, hva, res, pgstev, ptev; + unsigned long *cbrlo; + + /* + * We don't need to set SD.FPF.SK to 1 here, because if we have a + * machine check here we either handle it or crash + */ + + kvm_s390_get_regs_rre(vcpu, &r1, &r2); + gfn = vcpu->run->s.regs.gprs[r2] >> PAGE_SHIFT; + hva = gfn_to_hva(vcpu->kvm, gfn); + entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; + + if (kvm_is_error_hva(hva)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + nappended = pgste_perform_essa(vcpu->kvm->mm, hva, orc, &ptev, &pgstev); + if (nappended < 0) { + res = orc ? 0x10 : 0; + vcpu->run->s.regs.gprs[r1] = res; /* Exception Indication */ + return 0; + } + res = (pgstev & _PGSTE_GPS_USAGE_MASK) >> 22; + /* + * Set the block-content state part of the result. 0 means resident, so + * nothing to do if the page is valid. 2 is for preserved pages + * (non-present and non-zero), and 3 for zero pages (non-present and + * zero). + */ + if (ptev & _PAGE_INVALID) { + res |= 2; + if (pgstev & _PGSTE_GPS_ZERO) + res |= 1; + } + vcpu->run->s.regs.gprs[r1] = res; + /* + * It is possible that all the normal 511 slots were full, in which case + * we will now write in the 512th slot, which is reserved for host use. + * In both cases we let the normal essa handling code process all the + * slots, including the reserved one, if needed. + */ + if (nappended > 0) { + cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo & PAGE_MASK); + cbrlo[entries] = gfn << PAGE_SHIFT; + } + + if (orc) { + /* increment only if we are really flipping the bit to 1 */ + if (!test_and_set_bit(gfn, ms->pgste_bitmap)) + atomic64_inc(&ms->dirty_pages); + } + + return nappended; +} + static int handle_essa(struct kvm_vcpu *vcpu) { /* entries expected to be 1FF */ int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; unsigned long *cbrlo; struct gmap *gmap; - int i; + int i, orc; VCPU_EVENT(vcpu, 4, "ESSA: release %d pages", entries); gmap = vcpu->arch.gmap; @@ -965,12 +1025,45 @@ static int handle_essa(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - - if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6) + /* Check for invalid operation request code */ + orc = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; + if (orc > ESSA_MAX) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - /* Retry the ESSA instruction */ - kvm_s390_retry_instr(vcpu); + if (likely(!vcpu->kvm->arch.migration_state)) { + /* + * CMMA is enabled in the KVM settings, but is disabled in + * the SIE block and in the mm_context, and we are not doing + * a migration. Enable CMMA in the mm_context. + * Since we need to take a write lock to write to the context + * to avoid races with storage keys handling, we check if the + * value really needs to be written to; if the value is + * already correct, we do nothing and avoid the lock. + */ + if (vcpu->kvm->mm->context.use_cmma == 0) { + down_write(&vcpu->kvm->mm->mmap_sem); + vcpu->kvm->mm->context.use_cmma = 1; + up_write(&vcpu->kvm->mm->mmap_sem); + } + /* + * If we are here, we are supposed to have CMMA enabled in + * the SIE block. Enabling CMMA works on a per-CPU basis, + * while the context use_cmma flag is per process. + * It's possible that the context flag is enabled and the + * SIE flag is not, so we set the flag always; if it was + * already set, nothing changes, otherwise we enable it + * on this CPU too. + */ + vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; + /* Retry the ESSA instruction */ + kvm_s390_retry_instr(vcpu); + } else { + /* Account for the possible extra cbrl entry */ + i = do_essa(vcpu, orc); + if (i < 0) + return i; + entries += i; + } vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); down_read(&gmap->mm->mmap_sem); diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 1b553d847140d4..049c3c455b32e7 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -149,7 +149,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, } static void walk_pud_level(struct seq_file *m, struct pg_state *st, - pgd_t *pgd, unsigned long addr) + p4d_t *p4d, unsigned long addr) { unsigned int prot; pud_t *pud; @@ -157,7 +157,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++) { st->current_address = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); if (!pud_none(*pud)) if (pud_large(*pud)) { prot = pud_val(*pud) & @@ -172,6 +172,23 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, } } +static void walk_p4d_level(struct seq_file *m, struct pg_state *st, + pgd_t *pgd, unsigned long addr) +{ + p4d_t *p4d; + int i; + + for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++) { + st->current_address = addr; + p4d = p4d_offset(pgd, addr); + if (!p4d_none(*p4d)) + walk_pud_level(m, st, p4d, addr); + else + note_page(m, st, _PAGE_INVALID, 2); + addr += P4D_SIZE; + } +} + static void walk_pgd_level(struct seq_file *m) { unsigned long addr = 0; @@ -184,7 +201,7 @@ static void walk_pgd_level(struct seq_file *m) st.current_address = addr; pgd = pgd_offset_k(addr); if (!pgd_none(*pgd)) - walk_pud_level(m, &st, pgd, addr); + walk_p4d_level(m, &st, pgd, addr); else note_page(m, &st, _PAGE_INVALID, 1); addr += PGDIR_SIZE; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 5845d3028ffca9..14f25798b001ca 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -130,7 +130,7 @@ static int bad_address(void *p) static void dump_pagetable(unsigned long asce, unsigned long address) { - unsigned long *table = __va(asce & PAGE_MASK); + unsigned long *table = __va(asce & _ASCE_ORIGIN); pr_alert("AS:%016lx ", asce); switch (asce & _ASCE_TYPE_MASK) { diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 7f6db1e6c048aa..4fb3d3cdb370db 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -125,7 +125,7 @@ static void gmap_radix_tree_free(struct radix_tree_root *root) struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; - void **slot; + void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ @@ -150,7 +150,7 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; - void **slot; + void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ @@ -537,6 +537,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) unsigned long *table; spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; int rc; @@ -573,7 +574,9 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) mm = gmap->mm; pgd = pgd_offset(mm, vmaddr); VM_BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, vmaddr); + p4d = p4d_offset(pgd, vmaddr); + VM_BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ if (pud_large(*pud)) @@ -1008,7 +1011,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { - void **slot; + void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT); diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index b7b779c40a5bbf..8ecc25e760fa6d 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -166,15 +166,15 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, return 1; } -static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, +static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp, pud; - pudp = (pud_t *) pgdp; - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pudp = (pud_t *) pgd_deref(pgd); + pudp = (pud_t *) p4dp; + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + pudp = (pud_t *) p4d_deref(p4d); pudp += pud_index(addr); do { pud = *pudp; @@ -194,6 +194,29 @@ static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, return 1; } +static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp, p4d; + + p4dp = (p4d_t *) pgdp; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + p4dp = (p4d_t *) pgd_deref(pgd); + p4dp += p4d_index(addr); + do { + p4d = *p4dp; + barrier(); + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except its IRQ-safe in that it won't fall * back to the regular GUP. @@ -228,7 +251,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) break; - if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index ae23afc18493a8..44a8e6f0391ec2 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -162,16 +162,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp = NULL; pgdp = pgd_offset(mm, addr); - pudp = pud_alloc(mm, pgdp, addr); - if (pudp) { - if (sz == PUD_SIZE) - return (pte_t *) pudp; - else if (sz == PMD_SIZE) - pmdp = pmd_alloc(mm, pudp, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (p4dp) { + pudp = pud_alloc(mm, p4dp, addr); + if (pudp) { + if (sz == PUD_SIZE) + return (pte_t *) pudp; + else if (sz == PMD_SIZE) + pmdp = pmd_alloc(mm, pudp, addr); + } } return (pte_t *) pmdp; } @@ -180,16 +184,20 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp = NULL; pgdp = pgd_offset(mm, addr); if (pgd_present(*pgdp)) { - pudp = pud_offset(pgdp, addr); - if (pud_present(*pudp)) { - if (pud_large(*pudp)) - return (pte_t *) pudp; - pmdp = pmd_offset(pudp, addr); + p4dp = p4d_offset(pgdp, addr); + if (p4d_present(*p4dp)) { + pudp = pud_offset(p4dp, addr); + if (pud_present(*pudp)) { + if (pud_large(*pudp)) + return (pte_t *) pudp; + pmdp = pmd_offset(pudp, addr); + } } } return (pte_t *) pmdp; diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b017daed688784..8c5f284044efd2 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -120,7 +120,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, check_asce_limit: if (addr + len > current->mm->context.asce_limit) { - rc = crst_table_upgrade(mm); + rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; } @@ -184,7 +184,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, check_asce_limit: if (addr + len > current->mm->context.asce_limit) { - rc = crst_table_upgrade(mm); + rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 49e721f3645e8c..18048158924658 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -229,14 +229,14 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr, pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3); } -static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long flags) { unsigned long next; pud_t *pudp; int rc = 0; - pudp = pud_offset(pgd, addr); + pudp = pud_offset(p4d, addr); do { if (pud_none(*pudp)) return -EINVAL; @@ -259,6 +259,26 @@ static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end, return rc; } +static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end, + unsigned long flags) +{ + unsigned long next; + p4d_t *p4dp; + int rc = 0; + + p4dp = p4d_offset(pgd, addr); + do { + if (p4d_none(*p4dp)) + return -EINVAL; + next = p4d_addr_end(addr, end); + rc = walk_pud_level(p4dp, addr, next, flags); + p4dp++; + addr = next; + cond_resched(); + } while (addr < end && !rc); + return rc; +} + static DEFINE_MUTEX(cpa_mutex); static int change_page_attr(unsigned long addr, unsigned long end, @@ -278,7 +298,7 @@ static int change_page_attr(unsigned long addr, unsigned long end, if (pgd_none(*pgdp)) break; next = pgd_addr_end(addr, end); - rc = walk_pud_level(pgdp, addr, next, flags); + rc = walk_p4d_level(pgdp, addr, next, flags); if (rc) break; cond_resched(); @@ -319,6 +339,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) unsigned long address; int nr, i, j; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -326,7 +347,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) for (i = 0; i < numpages;) { address = page_to_phys(page + i); pgd = pgd_offset_k(address); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pte = pte_offset_kernel(pmd, address); nr = (unsigned long)pte >> ilog2(sizeof(long)); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index f502cbe657afb0..18918e394ce4b6 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -76,29 +76,46 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm) +int crst_table_upgrade(struct mm_struct *mm, unsigned long end) { unsigned long *table, *pgd; + int rc, notify; - /* upgrade should only happen from 3 to 4 levels */ - BUG_ON(mm->context.asce_limit != (1UL << 42)); - - table = crst_table_alloc(mm); - if (!table) + /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ + BUG_ON(mm->context.asce_limit < (1UL << 42)); + if (end >= TASK_SIZE_MAX) return -ENOMEM; - - spin_lock_bh(&mm->page_table_lock); - pgd = (unsigned long *) mm->pgd; - crst_table_init(table, _REGION2_ENTRY_EMPTY); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->context.asce_limit = 1UL << 53; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION2; - spin_unlock_bh(&mm->page_table_lock); - - on_each_cpu(__crst_table_upgrade, mm, 0); - return 0; + rc = 0; + notify = 0; + while (mm->context.asce_limit < end) { + table = crst_table_alloc(mm); + if (!table) { + rc = -ENOMEM; + break; + } + spin_lock_bh(&mm->page_table_lock); + pgd = (unsigned long *) mm->pgd; + if (mm->context.asce_limit == (1UL << 42)) { + crst_table_init(table, _REGION2_ENTRY_EMPTY); + p4d_populate(mm, (p4d_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + } else { + crst_table_init(table, _REGION1_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = -PAGE_SIZE; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + } + notify = 1; + spin_unlock_bh(&mm->page_table_lock); + } + if (notify) + on_each_cpu(__crst_table_upgrade, mm, 0); + return rc; } void crst_table_downgrade(struct mm_struct *mm) @@ -274,7 +291,7 @@ static void __tlb_remove_table(void *_table) struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT); switch (mask) { - case 0: /* pmd or pud */ + case 0: /* pmd, pud, or p4d */ free_pages((unsigned long) table, 2); break; case 1: /* lower 2K of a 4K page table */ diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 947b66a5cdba73..d4d409ba206b2e 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -610,6 +610,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) { spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgste_t pgste; @@ -618,7 +619,10 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) bool dirty; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return false; + pud = pud_alloc(mm, p4d, addr); if (!pud) return false; pmd = pmd_alloc(mm, pud, addr); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index c33c94b4be6036..d8398962a7236e 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -38,6 +38,17 @@ static void __ref *vmem_alloc_pages(unsigned int order) return (void *) memblock_alloc(size, size); } +static inline p4d_t *vmem_p4d_alloc(void) +{ + p4d_t *p4d = NULL; + + p4d = vmem_alloc_pages(2); + if (!p4d) + return NULL; + clear_table((unsigned long *) p4d, _REGION2_ENTRY_EMPTY, PAGE_SIZE * 4); + return p4d; +} + static inline pud_t *vmem_pud_alloc(void) { pud_t *pud = NULL; @@ -85,6 +96,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size) unsigned long end = start + size; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -102,12 +114,19 @@ static int vmem_add_mem(unsigned long start, unsigned long size) while (address < end) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { + p4_dir = vmem_p4d_alloc(); + if (!p4_dir) + goto out; + pgd_populate(&init_mm, pg_dir, p4_dir); + } + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { pu_dir = vmem_pud_alloc(); if (!pu_dir) goto out; - pgd_populate(&init_mm, pg_dir, pu_dir); + p4d_populate(&init_mm, p4_dir, pu_dir); } - pu_dir = pud_offset(pg_dir, address); + pu_dir = pud_offset(p4_dir, address); if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address && !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) && !debug_pagealloc_enabled()) { @@ -161,6 +180,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size) unsigned long end = start + size; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -172,7 +192,12 @@ static void vmem_remove_range(unsigned long start, unsigned long size) address += PGDIR_SIZE; continue; } - pu_dir = pud_offset(pg_dir, address); + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { + address += P4D_SIZE; + continue; + } + pu_dir = pud_offset(p4_dir, address); if (pud_none(*pu_dir)) { address += PUD_SIZE; continue; @@ -213,6 +238,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) unsigned long pgt_prot, sgt_prot; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -227,13 +253,21 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) for (address = start; address < end;) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { + p4_dir = vmem_p4d_alloc(); + if (!p4_dir) + goto out; + pgd_populate(&init_mm, pg_dir, p4_dir); + } + + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { pu_dir = vmem_pud_alloc(); if (!pu_dir) goto out; - pgd_populate(&init_mm, pg_dir, pu_dir); + p4d_populate(&init_mm, p4_dir, pu_dir); } - pu_dir = pud_offset(pg_dir, address); + pu_dir = pud_offset(p4_dir, address); if (pud_none(*pu_dir)) { pm_dir = vmem_pmd_alloc(); if (!pm_dir) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 6e97a2e3fd8d1f..42ad3832586ce4 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -991,7 +991,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i } break; } - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: /* * Implicit input: * B1: pointer to ctx diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index be63fbd699fd65..025ea20fc4b4b8 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -34,8 +34,6 @@ static struct facility_def facility_defs[] = { 18, /* long displacement facility */ #endif #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES - 7, /* stfle */ - 17, /* message security assist */ 21, /* extended-immediate facility */ 25, /* store clock fast */ #endif diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 6d612792f6b8ec..1faf6cb93dcb56 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 58243b0d21c006..1a83ec9014463e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -83,6 +83,8 @@ config SPARC64 select ARCH_SUPPORTS_ATOMIC_RMW select HAVE_NMI select HAVE_REGS_AND_STACK_ACCESS_API + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS config ARCH_DEFCONFIG string @@ -92,6 +94,9 @@ config ARCH_DEFCONFIG config ARCH_PROC_KCORE_TEXT def_bool y +config CPU_BIG_ENDIAN + def_bool y + config ARCH_ATU bool default y if SPARC64 @@ -295,9 +300,13 @@ config NUMA depends on SPARC64 && SMP config NODES_SHIFT - int - default "4" + int "Maximum NUMA Nodes (as a power of 2)" + range 4 5 if SPARC64 + default "5" depends on NEED_MULTIPLE_NODES + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accommodate various tables. # Some NUMA nodes have memory ranges that span # other nodes. Even though a pfn is valid and diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index faa2f61058c271..4028f4f1e5612b 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -6,6 +6,17 @@ #ifndef __ARCH_SPARC64_CMPXCHG__ #define __ARCH_SPARC64_CMPXCHG__ +static inline unsigned long +__cmpxchg_u32(volatile int *m, int old, int new) +{ + __asm__ __volatile__("cas [%2], %3, %0" + : "=&r" (new) + : "0" (new), "r" (m), "r" (old) + : "memory"); + + return new; +} + static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val) { unsigned long tmp1, tmp2; @@ -44,10 +55,38 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long void __xchg_called_with_bad_pointer(void); +/* + * Use 4 byte cas instruction to achieve 2 byte xchg. Main logic + * here is to get the bit shift of the byte we are interested in. + * The XOR is handy for reversing the bits for big-endian byte order. + */ +static inline unsigned long +xchg16(__volatile__ unsigned short *m, unsigned short val) +{ + unsigned long maddr = (unsigned long)m; + int bit_shift = (((unsigned long)m & 2) ^ 2) << 3; + unsigned int mask = 0xffff << bit_shift; + unsigned int *ptr = (unsigned int *) (maddr & ~2); + unsigned int old32, new32, load32; + + /* Read the old value */ + load32 = *ptr; + + do { + old32 = load32; + new32 = (load32 & (~mask)) | val << bit_shift; + load32 = __cmpxchg_u32(ptr, old32, new32); + } while (load32 != old32); + + return (load32 & mask) >> bit_shift; +} + static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { + case 2: + return xchg16(ptr, x); case 4: return xchg32(ptr, x); case 8: @@ -65,10 +104,11 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, #include + static inline unsigned long -__cmpxchg_u32(volatile int *m, int old, int new) +__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new) { - __asm__ __volatile__("cas [%2], %3, %0" + __asm__ __volatile__("casx [%2], %3, %0" : "=&r" (new) : "0" (new), "r" (m), "r" (old) : "memory"); @@ -76,15 +116,31 @@ __cmpxchg_u32(volatile int *m, int old, int new) return new; } +/* + * Use 4 byte cas instruction to achieve 1 byte cmpxchg. Main logic + * here is to get the bit shift of the byte we are interested in. + * The XOR is handy for reversing the bits for big-endian byte order + */ static inline unsigned long -__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new) +__cmpxchg_u8(volatile unsigned char *m, unsigned char old, unsigned char new) { - __asm__ __volatile__("casx [%2], %3, %0" - : "=&r" (new) - : "0" (new), "r" (m), "r" (old) - : "memory"); - - return new; + unsigned long maddr = (unsigned long)m; + int bit_shift = (((unsigned long)m & 3) ^ 3) << 3; + unsigned int mask = 0xff << bit_shift; + unsigned int *ptr = (unsigned int *) (maddr & ~3); + unsigned int old32, new32, load; + unsigned int load32 = *ptr; + + do { + new32 = (load32 & ~mask) | (new << bit_shift); + old32 = (load32 & ~mask) | (old << bit_shift); + load32 = __cmpxchg_u32(ptr, old32, new32); + if (load32 == old32) + return old; + load = (load32 & mask) >> bit_shift; + } while (load == old); + + return load; } /* This function doesn't exist, so you'll get a linker error @@ -95,6 +151,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) { switch (size) { + case 1: + return __cmpxchg_u8(ptr, old, new); case 4: return __cmpxchg_u32(ptr, old, new); case 8: diff --git a/arch/sparc/include/asm/qrwlock.h b/arch/sparc/include/asm/qrwlock.h new file mode 100644 index 00000000000000..d68a4b1021004c --- /dev/null +++ b/arch/sparc/include/asm/qrwlock.h @@ -0,0 +1,7 @@ +#ifndef _ASM_SPARC_QRWLOCK_H +#define _ASM_SPARC_QRWLOCK_H + +#include +#include + +#endif /* _ASM_SPARC_QRWLOCK_H */ diff --git a/arch/sparc/include/asm/qspinlock.h b/arch/sparc/include/asm/qspinlock.h new file mode 100644 index 00000000000000..5ae9a280284640 --- /dev/null +++ b/arch/sparc/include/asm/qspinlock.h @@ -0,0 +1,7 @@ +#ifndef _ASM_SPARC_QSPINLOCK_H +#define _ASM_SPARC_QSPINLOCK_H + +#include +#include + +#endif /* _ASM_SPARC_QSPINLOCK_H */ diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 07c9f2e9bf5771..f7028f5e1a5a3b 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -10,216 +10,12 @@ #include #include - -/* To get debugging spinlocks which detect and catch - * deadlock situations, set CONFIG_DEBUG_SPINLOCK - * and rebuild your kernel. - */ - -/* Because we play games to save cycles in the non-contention case, we - * need to be extra careful about branch targets into the "spinning" - * code. They live in their own section, but the newer V9 branches - * have a shorter range than the traditional 32-bit sparc branch - * variants. The rule is that the branches that go into and out of - * the spinner sections must be pre-V9 branches. - */ - -#define arch_spin_is_locked(lp) ((lp)->lock != 0) - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - smp_cond_load_acquire(&lock->lock, !VAL); -} - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned long tmp; - - __asm__ __volatile__( -"1: ldstub [%1], %0\n" -" brnz,pn %0, 2f\n" -" nop\n" -" .subsection 2\n" -"2: ldub [%1], %0\n" -" brnz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 1b\n" -" .previous" - : "=&r" (tmp) - : "r" (lock) - : "memory"); -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long result; - - __asm__ __volatile__( -" ldstub [%1], %0\n" - : "=r" (result) - : "r" (lock) - : "memory"); - - return (result == 0UL); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __asm__ __volatile__( -" stb %%g0, [%0]" - : /* No outputs */ - : "r" (lock) - : "memory"); -} - -static inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__( -"1: ldstub [%2], %0\n" -" brnz,pn %0, 2f\n" -" nop\n" -" .subsection 2\n" -"2: rdpr %%pil, %1\n" -" wrpr %3, %%pil\n" -"3: ldub [%2], %0\n" -" brnz,pt %0, 3b\n" -" nop\n" -" ba,pt %%xcc, 1b\n" -" wrpr %1, %%pil\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r"(lock), "r"(flags) - : "memory"); -} - -/* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */ - -static inline void arch_read_lock(arch_rwlock_t *lock) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__ ( -"1: ldsw [%2], %0\n" -" brlz,pn %0, 2f\n" -"4: add %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" .subsection 2\n" -"2: ldsw [%2], %0\n" -" brlz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 4b\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *lock) -{ - int tmp1, tmp2; - - __asm__ __volatile__ ( -"1: ldsw [%2], %0\n" -" brlz,a,pn %0, 2f\n" -" mov 0, %0\n" -" add %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" mov 1, %0\n" -"2:" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); - - return tmp1; -} - -static inline void arch_read_unlock(arch_rwlock_t *lock) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__( -"1: lduw [%2], %0\n" -" sub %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%xcc, 1b\n" -" nop" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); -} - -static inline void arch_write_lock(arch_rwlock_t *lock) -{ - unsigned long mask, tmp1, tmp2; - - mask = 0x80000000UL; - - __asm__ __volatile__( -"1: lduw [%2], %0\n" -" brnz,pn %0, 2f\n" -"4: or %0, %3, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" .subsection 2\n" -"2: lduw [%2], %0\n" -" brnz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 4b\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock), "r" (mask) - : "memory"); -} - -static inline void arch_write_unlock(arch_rwlock_t *lock) -{ - __asm__ __volatile__( -" stw %%g0, [%0]" - : /* no outputs */ - : "r" (lock) - : "memory"); -} - -static inline int arch_write_trylock(arch_rwlock_t *lock) -{ - unsigned long mask, tmp1, tmp2, result; - - mask = 0x80000000UL; - - __asm__ __volatile__( -" mov 0, %2\n" -"1: lduw [%3], %0\n" -" brnz,pn %0, 2f\n" -" or %0, %4, %1\n" -" cas [%3], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" mov 1, %2\n" -"2:" - : "=&r" (tmp1), "=&r" (tmp2), "=&r" (result) - : "r" (lock), "r" (mask) - : "memory"); - - return result; -} +#include +#include #define arch_read_lock_flags(p, f) arch_read_lock(p) #define arch_write_lock_flags(p, f) arch_write_lock(p) -#define arch_read_can_lock(rw) (!((rw)->lock & 0x80000000UL)) -#define arch_write_can_lock(rw) (!(rw)->lock) - #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_types.h b/arch/sparc/include/asm/spinlock_types.h index 9c454fdeaad82a..bce8ef44dfa99b 100644 --- a/arch/sparc/include/asm/spinlock_types.h +++ b/arch/sparc/include/asm/spinlock_types.h @@ -1,20 +1,24 @@ #ifndef __SPARC_SPINLOCK_TYPES_H #define __SPARC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif +#ifdef CONFIG_QUEUED_SPINLOCKS +#include +#else typedef struct { volatile unsigned char lock; } arch_spinlock_t; #define __ARCH_SPIN_LOCK_UNLOCKED { 0 } +#endif /* CONFIG_QUEUED_SPINLOCKS */ +#ifdef CONFIG_QUEUED_RWLOCKS +#include +#else typedef struct { volatile unsigned int lock; } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED { 0 } - +#endif /* CONFIG_QUEUED_RWLOCKS */ #endif diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 3f4ad19d9ec70c..5d673302fd4113 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -94,6 +94,8 @@ #define SO_COOKIE 0x003b +#define SCM_TIMESTAMPING_PKTINFO 0x003c + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index b542cc7c8d94d8..f87265afb1759e 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -909,7 +909,7 @@ static int register_services(struct ds_info *dp) pbuf.req.handle = cp->handle; pbuf.req.major = 1; pbuf.req.minor = 0; - strcpy(pbuf.req.svc_id, cp->service_id); + strcpy(pbuf.id_buf, cp->service_id); err = __ds_send(lp, &pbuf, msg_len); if (err > 0) diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c index 07933b9e9ce00a..93adde1ac1669d 100644 --- a/arch/sparc/kernel/jump_label.c +++ b/arch/sparc/kernel/jump_label.c @@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry, val = 0x01000000; } - get_online_cpus(); mutex_lock(&text_mutex); *insn = val; flushi(insn); mutex_unlock(&text_mutex); - put_online_cpus(); } #endif diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 21de77419f484b..098874a81f6e31 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -802,8 +802,13 @@ static void build_prologue(struct jit_ctx *ctx) { s32 stack_needed = BASE_STACKFRAME; - if (ctx->saw_frame_pointer || ctx->saw_tail_call) - stack_needed += MAX_BPF_STACK; + if (ctx->saw_frame_pointer || ctx->saw_tail_call) { + struct bpf_prog *prog = ctx->prog; + u32 stack_depth; + + stack_depth = prog->aux->stack_depth; + stack_needed += round_up(stack_depth, 16); + } if (ctx->saw_tail_call) stack_needed += 8; @@ -1217,7 +1222,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) } /* tail call */ - case BPF_JMP | BPF_CALL |BPF_X: + case BPF_JMP | BPF_TAIL_CALL: emit_tail_call(ctx); break; diff --git a/arch/tile/include/uapi/arch/abi.h b/arch/tile/include/uapi/arch/abi.h index c55a3d4326444c..328e62260272e0 100644 --- a/arch/tile/include/uapi/arch/abi.h +++ b/arch/tile/include/uapi/arch/abi.h @@ -20,58 +20,17 @@ #ifndef __ARCH_ABI_H__ -#if !defined __need_int_reg_t && !defined __DOXYGEN__ -# define __ARCH_ABI_H__ -# include -#endif - -/* Provide the basic machine types. */ -#ifndef __INT_REG_BITS - -/** Number of bits in a register. */ -#if defined __tilegx__ -# define __INT_REG_BITS 64 -#elif defined __tilepro__ -# define __INT_REG_BITS 32 -#elif !defined __need_int_reg_t +#ifndef __tile__ /* support uncommon use of arch headers in non-tile builds */ # include # define __INT_REG_BITS CHIP_WORD_SIZE() -#else -# error Unrecognized architecture with __need_int_reg_t -#endif - -#if __INT_REG_BITS == 64 - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "ll" - -#else - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "l" - #endif -#endif /* __INT_REG_BITS */ +#include +/* __need_int_reg_t is deprecated: just include */ #ifndef __need_int_reg_t +#define __ARCH_ABI_H__ #ifndef __ASSEMBLER__ /** Unsigned type that can hold a register. */ diff --git a/arch/tile/include/uapi/arch/intreg.h b/arch/tile/include/uapi/arch/intreg.h new file mode 100644 index 00000000000000..1cf2fbf7430659 --- /dev/null +++ b/arch/tile/include/uapi/arch/intreg.h @@ -0,0 +1,70 @@ +/* + * Copyright 2017 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * @file + * + * Provide types and defines for the type that can hold a register, + * in the implementation namespace. + */ + +#ifndef __ARCH_INTREG_H__ +#define __ARCH_INTREG_H__ + +/* + * Get number of bits in a register. __INT_REG_BITS may be defined + * prior to including this header to force a particular bit width. + */ + +#ifndef __INT_REG_BITS +# if defined __tilegx__ +# define __INT_REG_BITS 64 +# elif defined __tilepro__ +# define __INT_REG_BITS 32 +# else +# error Unrecognized architecture +# endif +#endif + +#if __INT_REG_BITS == 64 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "ll" + +#elif __INT_REG_BITS == 32 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "l" + +#else +# error Unrecognized value of __INT_REG_BITS +#endif + +#endif /* !__ARCH_INTREG_H__ */ diff --git a/arch/tile/kernel/jump_label.c b/arch/tile/kernel/jump_label.c index 07802d58698887..93931a46625b9f 100644 --- a/arch/tile/kernel/jump_label.c +++ b/arch/tile/kernel/jump_label.c @@ -45,14 +45,12 @@ static void __jump_label_transform(struct jump_entry *e, void arch_jump_label_transform(struct jump_entry *e, enum jump_label_type type) { - get_online_cpus(); mutex_lock(&text_mutex); __jump_label_transform(e, type); flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits)); mutex_unlock(&text_mutex); - put_online_cpus(); } __init_or_module void arch_jump_label_transform_static(struct jump_entry *e, diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 3a97e4d7205cf2..5f757e04bcd270 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -857,36 +857,6 @@ void __init mem_init(void) #endif } -/* - * this is for the non-NUMA, single node SMP system case. - * Specifically, in the case of x86, we will always add - * memory to the highmem for now. - */ -#ifndef CONFIG_NEED_MULTIPLE_NODES -int arch_add_memory(u64 start, u64 size, bool for_device) -{ - struct pglist_data *pgdata = &contig_page_data; - struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1; - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - - return __add_pages(zone, start_pfn, nr_pages); -} - -int remove_memory(u64 start, u64 size) -{ - return -EINVAL; -} - -#ifdef CONFIG_MEMORY_HOTREMOVE -int arch_remove_memory(u64 start, u64 size) -{ - /* TODO */ - return -EBUSY; -} -#endif -#endif - struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 0769066929c636..0a3bfd1fefcd1d 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -69,6 +69,20 @@ source "kernel/Kconfig.freezer" menu "System Type" +config UNICORE32_OLDABI + bool "Allow old ABI binaries to run with this kernel" + default y + select CLONE_BACKWARDS + select OLD_SIGACTION + select OLD_SIGSUSPEND3 + help + This option preserves the old syscall interface instead of the + asm-generic one. It also provides a compatibility layer to + intercept syscalls that have structure arguments which layout + in memory differs between the asm-generic ABI and this old one. + + If in doubt, say Y. + config MMU def_bool y diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index e9ad511c1043fe..ea47c4bf3aa7f8 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -45,14 +45,11 @@ generic-y += setup.h generic-y += shmbuf.h generic-y += shmparam.h generic-y += siginfo.h -generic-y += signal.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h -generic-y += stat.h generic-y += statfs.h generic-y += swab.h -generic-y += syscalls.h generic-y += termbits.h generic-y += termios.h generic-y += topology.h diff --git a/arch/unicore32/include/asm/signal.h b/arch/unicore32/include/asm/signal.h new file mode 100644 index 00000000000000..a87519883ea625 --- /dev/null +++ b/arch/unicore32/include/asm/signal.h @@ -0,0 +1,21 @@ +/* + * linux/arch/unicore32/include/asm/signal.h + * + * Code specific to UniCore ISA + * + * Copyright (C) 2014 GUAN Xuetao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __UNICORE32_ASM_SIGNAL_H__ +#define __UNICORE32_ASM_SIGNAL_H__ + +#ifdef CONFIG_UNICORE32_OLDABI +#define SA_RESTORER 0x04000000 +#endif + +#include + +#endif /* __UNICORE32_ASM_SIGNAL_H__ */ diff --git a/arch/unicore32/include/asm/syscalls.h b/arch/unicore32/include/asm/syscalls.h new file mode 100644 index 00000000000000..362cf4d15b6752 --- /dev/null +++ b/arch/unicore32/include/asm/syscalls.h @@ -0,0 +1,25 @@ +/* + * linux/arch/unicore32/include/asm/syscalls.h + * + * Code specific to UniCore ISA + * + * Copyright (C) 2014 GUAN Xuetao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __UNICORE32_ASM_SYSCALLS_H__ +#define __UNICORE32_ASM_SYSCALLS_H__ + +#include + +#ifdef CONFIG_UNICORE32_OLDABI +/* Wrapper functions */ +extern asmlinkage long sys_clone_wrapper(unsigned long clone_flags, + unsigned long newsp, int __user *parent_tidptr, + int tls_val, int __user *child_tidptr); +extern asmlinkage long sys_sigreturn_wrapper(struct pt_regs *regs); +#endif /* CONFIG_UNICORE32_OLDABI */ + +#endif /* __UNICORE32_ASM_SYSCALLS_H__ */ diff --git a/arch/unicore32/include/uapi/asm/sigcontext.h b/arch/unicore32/include/uapi/asm/sigcontext.h index 6a2d7671c0527f..cbc3446b9c033d 100644 --- a/arch/unicore32/include/uapi/asm/sigcontext.h +++ b/arch/unicore32/include/uapi/asm/sigcontext.h @@ -18,6 +18,7 @@ * before the signal handler was invoked. Note: only add new entries * to the end of the structure. */ +#ifndef CONFIG_UNICORE32_OLDABI struct sigcontext { unsigned long trap_no; unsigned long error_code; @@ -25,5 +26,18 @@ struct sigcontext { unsigned long fault_address; struct pt_regs regs; }; +#else +struct pt_regs_sigcontext { + unsigned long uregs[33]; +}; + +struct sigcontext { + unsigned long trap_no; + unsigned long error_code; + unsigned long oldmask; + struct pt_regs_sigcontext regs; + unsigned long fault_address; +}; +#endif /* CONFIG_UNICORE32_OLDABI */ #endif diff --git a/arch/unicore32/include/uapi/asm/stat-oldabi.h b/arch/unicore32/include/uapi/asm/stat-oldabi.h new file mode 100644 index 00000000000000..d36ce133cef81a --- /dev/null +++ b/arch/unicore32/include/uapi/asm/stat-oldabi.h @@ -0,0 +1,71 @@ +/* + * Code specific to UniCore32 ISA + * + * Copyright (C) 2014 GUAN Xuetao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __UNICORE32_ASM_STAT_OLDABI_H__ +#define __UNICORE32_ASM_STAT_OLDABI_H__ + +#define STAT_HAVE_NSEC 1 + +struct stat { + unsigned long st_dev; /* Device. */ + unsigned long st_ino; /* File serial number. */ + unsigned int st_mode; /* File mode. */ + unsigned int st_nlink; /* Link count. */ + unsigned int st_uid; /* User ID of the file's owner. */ + unsigned int st_gid; /* Group ID of the file's group. */ + unsigned long st_rdev; /* Device number, if device. */ + unsigned long __pad1; + long st_size; /* Size of file, in bytes. */ + int st_blksize; /* Optimal block size for I/O. */ + int __pad2; + long st_blocks; /* Number 512-byte blocks allocated. */ + int st_atime; /* Time of last access. */ + unsigned int st_atime_nsec; + int st_mtime; /* Time of last modification. */ + unsigned int st_mtime_nsec; + int st_ctime; /* Time of last status change. */ + unsigned int st_ctime_nsec; + unsigned int __unused4; + unsigned int __unused5; +}; + +/* + * This matches struct stat64 in glibc2.1, hence the absolutely + * insane amounts of padding around dev_t's. + * Note: The kernel zero's the padded region because glibc might read them + * in the hope that the kernel has stretched to using larger sizes. + */ +#define STAT64_HAS_BROKEN_ST_INO + +struct stat64 { + unsigned long long st_dev; /* Device. */ + unsigned char __pad0[4]; + unsigned long __st_ino; + unsigned int st_mode; /* File mode. */ + unsigned int st_nlink; /* Link count. */ + unsigned int st_uid; /* UID of the file's owner. */ + unsigned int st_gid; /* GID of the file's group. */ + unsigned long long st_rdev; /* Device number, if device. */ + + unsigned char __pad3[4]; + + long long st_size; /* Size of file, in bytes. */ + int st_blksize; /* Optimal block size for I/O. */ + long long st_blocks; /* Number 512-byte blocks allocated. */ + int st_atime; /* Time of last access. */ + unsigned int st_atime_nsec; + int st_mtime; /* Time of last modification. */ + unsigned int st_mtime_nsec; + int st_ctime; /* Time of last status change. */ + unsigned int st_ctime_nsec; + + unsigned long long st_ino; +}; + +#endif /* __UNICORE32_ASM_STAT_OLDABI_H__ */ diff --git a/arch/unicore32/include/uapi/asm/stat.h b/arch/unicore32/include/uapi/asm/stat.h new file mode 100644 index 00000000000000..2cff377d44e37b --- /dev/null +++ b/arch/unicore32/include/uapi/asm/stat.h @@ -0,0 +1,19 @@ +/* + * Code specific to UniCore32 ISA + * + * Copyright (C) 2014 GUAN Xuetao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __UNICORE32_ASM_STAT_H__ +#define __UNICORE32_ASM_STAT_H__ + +#ifndef CONFIG_UNICORE32_OLDABI +#include +#else +#include +#endif /* CONFIG_UNICORE32_OLDABI */ + +#endif /* __UNICORE32_ASM_STAT_H__ */ diff --git a/arch/unicore32/include/uapi/asm/unistd-oldabi.h b/arch/unicore32/include/uapi/asm/unistd-oldabi.h new file mode 100644 index 00000000000000..0c24fcf3a30179 --- /dev/null +++ b/arch/unicore32/include/uapi/asm/unistd-oldabi.h @@ -0,0 +1,770 @@ +#ifndef CONFIG_UNICORE32_OLDABI +#error unistd-oldabi.h is ONLY used when CONFIG_UNICORE32_OLDABI defined +#endif + +#define __NR_SYSCALL_BASE 0x900000 + +#ifndef __SYSCALL +#define __SYSCALL(x, y) +#endif + +#define __NR_restart_syscall 0 +__SYSCALL(__NR_restart_syscall, sys_restart_syscall) +#define __NR_exit 1 +__SYSCALL(__NR_exit, sys_exit) +#define __NR_fork 2 +__SYSCALL(__NR_fork, sys_fork) +#define __NR_read 3 +__SYSCALL(__NR_read, sys_read) +#define __NR_write 4 +__SYSCALL(__NR_write, sys_write) +#define __NR_open 5 +__SYSCALL(__NR_open, sys_open) +#define __NR_close 6 +__SYSCALL(__NR_close, sys_close) + /* 7 was sys_waitpid */ +#define __NR_creat 8 +__SYSCALL(__NR_creat, sys_creat) +#define __NR_link 9 +__SYSCALL(__NR_link, sys_link) +#define __NR_unlink 10 +__SYSCALL(__NR_unlink, sys_unlink) +#define __NR_execve 11 +__SYSCALL(__NR_execve, sys_execve) +#define __NR_chdir 12 +__SYSCALL(__NR_chdir, sys_chdir) +#define __NR_time 13 +__SYSCALL(__NR_time, sys_time) +#define __NR_mknod 14 +__SYSCALL(__NR_mknod, sys_mknod) +#define __NR_chmod 15 +__SYSCALL(__NR_chmod, sys_chmod) +#define __NR_lchown 16 +__SYSCALL(__NR_lchown, sys_ni_syscall) + /* 17 was sys_break */ + /* 18 was sys_stat */ +#define __NR_lseek 19 +__SYSCALL(__NR_lseek, sys_lseek) +#define __NR_getpid 20 +__SYSCALL(__NR_getpid, sys_getpid) +#define __NR_mount 21 +__SYSCALL(__NR_mount, sys_mount) +#define __NR_umount 22 +__SYSCALL(__NR_umount, sys_oldumount) +#define __NR_setuid 23 +__SYSCALL(__NR_setuid, sys_ni_syscall) +#define __NR_getuid 24 +__SYSCALL(__NR_getuid, sys_ni_syscall) +#define __NR_stime 25 +__SYSCALL(__NR_stime, sys_stime) +#define __NR_ptrace 26 +__SYSCALL(__NR_ptrace, sys_ptrace) +#define __NR_alarm 27 +__SYSCALL(__NR_alarm, sys_alarm) + /* 28 was sys_fstat */ +#define __NR_pause 29 +__SYSCALL(__NR_pause, sys_pause) +#define __NR_utime 30 +__SYSCALL(__NR_utime, sys_utime) + /* 31 was sys_stty */ + /* 32 was sys_gtty */ +#define __NR_access 33 +__SYSCALL(__NR_access, sys_access) +#define __NR_nice 34 +__SYSCALL(__NR_nice, sys_nice) + /* 35 was sys_ftime */ +#define __NR_sync 36 +__SYSCALL(__NR_sync, sys_sync) +#define __NR_kill 37 +__SYSCALL(__NR_kill, sys_kill) +#define __NR_rename 38 +__SYSCALL(__NR_rename, sys_rename) +#define __NR_mkdir 39 +__SYSCALL(__NR_mkdir, sys_mkdir) +#define __NR_rmdir 40 +__SYSCALL(__NR_rmdir, sys_rmdir) +#define __NR_dup 41 +__SYSCALL(__NR_dup, sys_dup) +#define __NR_pipe 42 +__SYSCALL(__NR_pipe, sys_pipe) +#define __NR_times 43 +__SYSCALL(__NR_times, sys_times) + /* 44 was sys_prof */ +#define __NR_brk 45 +__SYSCALL(__NR_brk, sys_brk) +#define __NR_setgid 46 +__SYSCALL(__NR_setgid, sys_ni_syscall) +#define __NR_getgid 47 +__SYSCALL(__NR_getgid, sys_ni_syscall) + /* 48 was sys_signal */ +#define __NR_geteuid 49 +__SYSCALL(__NR_geteuid, sys_ni_syscall) +#define __NR_getegid 50 +__SYSCALL(__NR_getegid, sys_ni_syscall) +#define __NR_acct 51 +__SYSCALL(__NR_acct, sys_acct) +#define __NR_umount2 52 +__SYSCALL(__NR_umount2, sys_umount) + /* 53 was sys_lock */ +#define __NR_ioctl 54 +__SYSCALL(__NR_ioctl, sys_ioctl) +#define __NR_fcntl 55 +__SYSCALL(__NR_fcntl, sys_fcntl) + /* 56 was sys_mpx */ +#define __NR_setpgid 57 +__SYSCALL(__NR_setpgid, sys_setpgid) + /* 58 was sys_ulimit */ + /* 59 was sys_olduname */ +#define __NR_umask 60 +__SYSCALL(__NR_umask, sys_umask) +#define __NR_chroot 61 +__SYSCALL(__NR_chroot, sys_chroot) +#define __NR_ustat 62 +__SYSCALL(__NR_ustat, sys_ustat) +#define __NR_dup2 63 +__SYSCALL(__NR_dup2, sys_dup2) +#define __NR_getppid 64 +__SYSCALL(__NR_getppid, sys_getppid) +#define __NR_getpgrp 65 +__SYSCALL(__NR_getpgrp, sys_getpgrp) +#define __NR_setsid 66 +__SYSCALL(__NR_setsid, sys_setsid) +#define __NR_sigaction 67 +__SYSCALL(__NR_sigaction, sys_sigaction) + /* 68 was sys_sgetmask */ + /* 69 was sys_ssetmask */ +#define __NR_setreuid 70 +__SYSCALL(__NR_setreuid, sys_ni_syscall) +#define __NR_setregid 71 +__SYSCALL(__NR_setregid, sys_ni_syscall) +#define __NR_sigsuspend 72 +__SYSCALL(__NR_sigsuspend, sys_sigsuspend) +#define __NR_sigpending 73 +__SYSCALL(__NR_sigpending, sys_sigpending) +#define __NR_sethostname 74 +__SYSCALL(__NR_sethostname, sys_sethostname) +#define __NR_setrlimit 75 +__SYSCALL(__NR_setrlimit, sys_setrlimit) +#define __NR_getrlimit 76 +__SYSCALL(__NR_getrlimit, sys_old_getrlimit) + /* Back compat 2GB limited rlimit */ +#define __NR_getrusage 77 +__SYSCALL(__NR_getrusage, sys_getrusage) +#define __NR_gettimeofday 78 +__SYSCALL(__NR_gettimeofday, sys_gettimeofday) +#define __NR_settimeofday 79 +__SYSCALL(__NR_settimeofday, sys_settimeofday) +#define __NR_getgroups 80 +__SYSCALL(__NR_getgroups, sys_ni_syscall) +#define __NR_setgroups 81 +__SYSCALL(__NR_setgroups, sys_ni_syscall) +#define __NR_select 82 +__SYSCALL(__NR_select, sys_old_select) +#define __NR_symlink 83 +__SYSCALL(__NR_symlink, sys_symlink) + /* 84 was sys_lstat */ +#define __NR_readlink 85 +__SYSCALL(__NR_readlink, sys_readlink) +#define __NR_uselib 86 +__SYSCALL(__NR_uselib, sys_uselib) +#define __NR_swapon 87 +__SYSCALL(__NR_swapon, sys_swapon) +#define __NR_reboot 88 +__SYSCALL(__NR_reboot, sys_reboot) +#define __NR_readdir 89 +__SYSCALL(__NR_readdir, sys_old_readdir) +#define __NR_mmap 90 +__SYSCALL(__NR_mmap, sys_old_mmap) +#define __NR_munmap 91 +__SYSCALL(__NR_munmap, sys_munmap) +#define __NR_truncate 92 +__SYSCALL(__NR_truncate, sys_truncate) +#define __NR_ftruncate 93 +__SYSCALL(__NR_ftruncate, sys_ftruncate) +#define __NR_fchmod 94 +__SYSCALL(__NR_fchmod, sys_fchmod) +#define __NR_fchown 95 +__SYSCALL(__NR_fchown, sys_ni_syscall) +#define __NR_getpriority 96 +__SYSCALL(__NR_getpriority, sys_getpriority) +#define __NR_setpriority 97 +__SYSCALL(__NR_setpriority, sys_setpriority) + /* 98 was sys_profil */ +#define __NR_statfs 99 +__SYSCALL(__NR_statfs, sys_statfs) +#define __NR_fstatfs 100 +__SYSCALL(__NR_fstatfs, sys_fstatfs) + /* 101 was sys_ioperm */ +#define __NR_socketcall 102 +__SYSCALL(__NR_socketcall, sys_socketcall) +#define __NR_syslog 103 +__SYSCALL(__NR_syslog, sys_syslog) +#define __NR_setitimer 104 +__SYSCALL(__NR_setitimer, sys_setitimer) +#define __NR_getitimer 105 +__SYSCALL(__NR_getitimer, sys_getitimer) +#define __NR_stat 106 +__SYSCALL(__NR_stat, sys_newstat) +#define __NR_lstat 107 +__SYSCALL(__NR_lstat, sys_newlstat) +#define __NR_fstat 108 +__SYSCALL(__NR_fstat, sys_newfstat) + /* 109 was sys_uname */ + /* 110 was sys_iopl */ +#define __NR_vhangup 111 +__SYSCALL(__NR_vhangup, sys_vhangup) + /* 112 was sys_idle */ +#define __NR_syscall 113 +__SYSCALL(__NR_syscall, sys_ni_syscall) + /* syscall to call a syscall! */ +#define __NR_wait4 114 +__SYSCALL(__NR_wait4, sys_wait4) +#define __NR_swapoff 115 +__SYSCALL(__NR_swapoff, sys_swapoff) +#define __NR_sysinfo 116 +__SYSCALL(__NR_sysinfo, sys_sysinfo) +#define __NR_ipc 117 +__SYSCALL(__NR_ipc, sys_ipc) +#define __NR_fsync 118 +__SYSCALL(__NR_fsync, sys_fsync) +#define __NR_sigreturn 119 +__SYSCALL(__NR_sigreturn, sys_sigreturn_wrapper) +#define __NR_clone 120 +__SYSCALL(__NR_clone, sys_clone_wrapper) +#define __NR_setdomainname 121 +__SYSCALL(__NR_setdomainname, sys_setdomainname) +#define __NR_uname 122 +__SYSCALL(__NR_uname, sys_newuname) + /* 123 was sys_modify_ldt */ +#define __NR_adjtimex 124 +__SYSCALL(__NR_adjtimex, sys_adjtimex) +#define __NR_mprotect 125 +__SYSCALL(__NR_mprotect, sys_mprotect) +#define __NR_sigprocmask 126 +__SYSCALL(__NR_sigprocmask, sys_sigprocmask) + /* 127 was sys_create_module */ +#define __NR_init_module 128 +__SYSCALL(__NR_init_module, sys_init_module) +#define __NR_delete_module 129 +__SYSCALL(__NR_delete_module, sys_delete_module) + /* 130 was sys_get_kernel_syms */ +#define __NR_quotactl 131 +__SYSCALL(__NR_quotactl, sys_quotactl) +#define __NR_getpgid 132 +__SYSCALL(__NR_getpgid, sys_getpgid) +#define __NR_fchdir 133 +__SYSCALL(__NR_fchdir, sys_fchdir) +#define __NR_bdflush 134 +__SYSCALL(__NR_bdflush, sys_bdflush) +#define __NR_sysfs 135 +__SYSCALL(__NR_sysfs, sys_sysfs) +#define __NR_personality 136 +__SYSCALL(__NR_personality, sys_personality) + /* 137 was sys_afs_syscall */ +#define __NR_setfsuid 138 +__SYSCALL(__NR_setfsuid, sys_ni_syscall) +#define __NR_setfsgid 139 +__SYSCALL(__NR_setfsgid, sys_ni_syscall) +#define __NR__llseek 140 +__SYSCALL(__NR__llseek, sys_llseek) +#define __NR_getdents 141 +__SYSCALL(__NR_getdents, sys_getdents) +#define __NR__newselect 142 +__SYSCALL(__NR__newselect, sys_select) +#define __NR_flock 143 +__SYSCALL(__NR_flock, sys_flock) +#define __NR_msync 144 +__SYSCALL(__NR_msync, sys_msync) +#define __NR_readv 145 +__SYSCALL(__NR_readv, sys_readv) +#define __NR_writev 146 +__SYSCALL(__NR_writev, sys_writev) +#define __NR_getsid 147 +__SYSCALL(__NR_getsid, sys_getsid) +#define __NR_fdatasync 148 +__SYSCALL(__NR_fdatasync, sys_fdatasync) +#define __NR__sysctl 149 +__SYSCALL(__NR__sysctl, sys_sysctl) +#define __NR_mlock 150 +__SYSCALL(__NR_mlock, sys_mlock) +#define __NR_munlock 151 +__SYSCALL(__NR_munlock, sys_munlock) +#define __NR_mlockall 152 +__SYSCALL(__NR_mlockall, sys_mlockall) +#define __NR_munlockall 153 +__SYSCALL(__NR_munlockall, sys_munlockall) +#define __NR_sched_setparam 154 +__SYSCALL(__NR_sched_setparam, sys_sched_setparam) +#define __NR_sched_getparam 155 +__SYSCALL(__NR_sched_getparam, sys_sched_getparam) +#define __NR_sched_setscheduler 156 +__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) +#define __NR_sched_getscheduler 157 +__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) +#define __NR_sched_yield 158 +__SYSCALL(__NR_sched_yield, sys_sched_yield) +#define __NR_sched_get_priority_max 159 +__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) +#define __NR_sched_get_priority_min 160 +__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) +#define __NR_sched_rr_get_interval 161 +__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval) +#define __NR_nanosleep 162 +__SYSCALL(__NR_nanosleep, sys_nanosleep) +#define __NR_mremap 163 +__SYSCALL(__NR_mremap, sys_mremap) +#define __NR_setresuid 164 +__SYSCALL(__NR_setresuid, sys_ni_syscall) +#define __NR_getresuid 165 +__SYSCALL(__NR_getresuid, sys_ni_syscall) + /* 166 was sys_vm86 */ + /* 167 was sys_query_module */ +#define __NR_poll 168 +__SYSCALL(__NR_poll, sys_poll) +#define __NR_nfsservctl 169 +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) +#define __NR_setresgid 170 +__SYSCALL(__NR_setresgid, sys_ni_syscall) +#define __NR_getresgid 171 +__SYSCALL(__NR_getresgid, sys_ni_syscall) +#define __NR_prctl 172 +__SYSCALL(__NR_prctl, sys_prctl) +#define __NR_rt_sigreturn 173 +__SYSCALL(__NR_rt_sigreturn, sys_rt_sigreturn) +#define __NR_rt_sigaction 174 +__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction) +#define __NR_rt_sigprocmask 175 +__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask) +#define __NR_rt_sigpending 176 +__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending) +#define __NR_rt_sigtimedwait 177 +__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait) +#define __NR_rt_sigqueueinfo 178 +__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo) +#define __NR_rt_sigsuspend 179 +__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend) +#define __NR_pread64 180 +__SYSCALL(__NR_pread64, sys_pread64) +#define __NR_pwrite64 181 +__SYSCALL(__NR_pwrite64, sys_pwrite64) +#define __NR_chown 182 +__SYSCALL(__NR_chown, sys_ni_syscall) +#define __NR_getcwd 183 +__SYSCALL(__NR_getcwd, sys_getcwd) +#define __NR_capget 184 +__SYSCALL(__NR_capget, sys_capget) +#define __NR_capset 185 +__SYSCALL(__NR_capset, sys_capset) +#define __NR_sigaltstack 186 +__SYSCALL(__NR_sigaltstack, sys_sigaltstack) +#define __NR_sendfile 187 +__SYSCALL(__NR_sendfile, sys_sendfile) + /* 188 reserved */ + /* 189 reserved */ +#define __NR_vfork 190 +__SYSCALL(__NR_vfork, sys_vfork) +#define __NR_ugetrlimit 191 +__SYSCALL(__NR_ugetrlimit, sys_getrlimit) + /* SuS compliant getrlimit */ +#define __NR_mmap2 192 +__SYSCALL(__NR_mmap2, sys_mmap_pgoff) +#define __NR_truncate64 193 +__SYSCALL(__NR_truncate64, sys_truncate64) +#define __NR_ftruncate64 194 +__SYSCALL(__NR_ftruncate64, sys_ftruncate64) +#define __NR_stat64 195 +__SYSCALL(__NR_stat64, sys_stat64) +#define __NR_lstat64 196 +__SYSCALL(__NR_lstat64, sys_lstat64) +#define __NR_fstat64 197 +__SYSCALL(__NR_fstat64, sys_fstat64) +#define __NR_lchown32 198 +__SYSCALL(__NR_lchown32, sys_lchown) +#define __NR_getuid32 199 +__SYSCALL(__NR_getuid32, sys_getuid) +#define __NR_getgid32 200 +__SYSCALL(__NR_getgid32, sys_getgid) +#define __NR_geteuid32 201 +__SYSCALL(__NR_geteuid32, sys_geteuid) +#define __NR_getegid32 202 +__SYSCALL(__NR_getegid32, sys_getegid) +#define __NR_setreuid32 203 +__SYSCALL(__NR_setreuid32, sys_setreuid) +#define __NR_setregid32 204 +__SYSCALL(__NR_setregid32, sys_setregid) +#define __NR_getgroups32 205 +__SYSCALL(__NR_getgroups32, sys_getgroups) +#define __NR_setgroups32 206 +__SYSCALL(__NR_setgroups32, sys_setgroups) +#define __NR_fchown32 207 +__SYSCALL(__NR_fchown32, sys_fchown) +#define __NR_setresuid32 208 +__SYSCALL(__NR_setresuid32, sys_setresuid) +#define __NR_getresuid32 209 +__SYSCALL(__NR_getresuid32, sys_getresuid) +#define __NR_setresgid32 210 +__SYSCALL(__NR_setresgid32, sys_setresgid) +#define __NR_getresgid32 211 +__SYSCALL(__NR_getresgid32, sys_getresgid) +#define __NR_chown32 212 +__SYSCALL(__NR_chown32, sys_chown) +#define __NR_setuid32 213 +__SYSCALL(__NR_setuid32, sys_setuid) +#define __NR_setgid32 214 +__SYSCALL(__NR_setgid32, sys_setgid) +#define __NR_setfsuid32 215 +__SYSCALL(__NR_setfsuid32, sys_setfsuid) +#define __NR_setfsgid32 216 +__SYSCALL(__NR_setfsgid32, sys_setfsgid) +#define __NR_getdents64 217 +__SYSCALL(__NR_getdents64, sys_getdents64) +#define __NR_pivot_root 218 +__SYSCALL(__NR_pivot_root, sys_pivot_root) +#define __NR_mincore 219 +__SYSCALL(__NR_mincore, sys_mincore) +#define __NR_madvise 220 +__SYSCALL(__NR_madvise, sys_madvise) +#define __NR_fcntl64 221 +__SYSCALL(__NR_fcntl64, sys_fcntl64) + /* 222 for tux */ + /* 223 is unused */ +#define __NR_gettid 224 +__SYSCALL(__NR_gettid, sys_gettid) +#define __NR_readahead 225 +__SYSCALL(__NR_readahead, sys_readahead) +#define __NR_setxattr 226 +__SYSCALL(__NR_setxattr, sys_setxattr) +#define __NR_lsetxattr 227 +__SYSCALL(__NR_lsetxattr, sys_lsetxattr) +#define __NR_fsetxattr 228 +__SYSCALL(__NR_fsetxattr, sys_fsetxattr) +#define __NR_getxattr 229 +__SYSCALL(__NR_getxattr, sys_getxattr) +#define __NR_lgetxattr 230 +__SYSCALL(__NR_lgetxattr, sys_lgetxattr) +#define __NR_fgetxattr 231 +__SYSCALL(__NR_fgetxattr, sys_fgetxattr) +#define __NR_listxattr 232 +__SYSCALL(__NR_listxattr, sys_listxattr) +#define __NR_llistxattr 233 +__SYSCALL(__NR_llistxattr, sys_llistxattr) +#define __NR_flistxattr 234 +__SYSCALL(__NR_flistxattr, sys_flistxattr) +#define __NR_removexattr 235 +__SYSCALL(__NR_removexattr, sys_removexattr) +#define __NR_lremovexattr 236 +__SYSCALL(__NR_lremovexattr, sys_lremovexattr) +#define __NR_fremovexattr 237 +__SYSCALL(__NR_fremovexattr, sys_fremovexattr) +#define __NR_tkill 238 +__SYSCALL(__NR_tkill, sys_tkill) +#define __NR_sendfile64 239 +__SYSCALL(__NR_sendfile64, sys_sendfile64) +#define __NR_futex 240 +__SYSCALL(__NR_futex, sys_futex) +#define __NR_sched_setaffinity 241 +__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity) +#define __NR_sched_getaffinity 242 +__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity) +#define __NR_io_setup 243 +__SYSCALL(__NR_io_setup, sys_io_setup) +#define __NR_io_destroy 244 +__SYSCALL(__NR_io_destroy, sys_io_destroy) +#define __NR_io_getevents 245 +__SYSCALL(__NR_io_getevents, sys_io_getevents) +#define __NR_io_submit 246 +__SYSCALL(__NR_io_submit, sys_io_submit) +#define __NR_io_cancel 247 +__SYSCALL(__NR_io_cancel, sys_io_cancel) +#define __NR_exit_group 248 +__SYSCALL(__NR_exit_group, sys_exit_group) +#define __NR_lookup_dcookie 249 +__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie) +#define __NR_epoll_create 250 +__SYSCALL(__NR_epoll_create, sys_epoll_create) +#define __NR_epoll_ctl 251 +__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) +#define __NR_epoll_wait 252 +__SYSCALL(__NR_epoll_wait, sys_epoll_wait) +#define __NR_remap_file_pages 253 +__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) + /* 254 for set_thread_area */ + /* 255 for get_thread_area */ +#define __NR_set_tid_address 256 +__SYSCALL(__NR_set_tid_address, sys_set_tid_address) +#define __NR_timer_create 257 +__SYSCALL(__NR_timer_create, sys_timer_create) +#define __NR_timer_settime 258 +__SYSCALL(__NR_timer_settime, sys_timer_settime) +#define __NR_timer_gettime 259 +__SYSCALL(__NR_timer_gettime, sys_timer_gettime) +#define __NR_timer_getoverrun 260 +__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) +#define __NR_timer_delete 261 +__SYSCALL(__NR_timer_delete, sys_timer_delete) +#define __NR_clock_settime 262 +__SYSCALL(__NR_clock_settime, sys_clock_settime) +#define __NR_clock_gettime 263 +__SYSCALL(__NR_clock_gettime, sys_clock_gettime) +#define __NR_clock_getres 264 +__SYSCALL(__NR_clock_getres, sys_clock_getres) +#define __NR_clock_nanosleep 265 +__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep) + /* 266 was sys_statfs64_wrapper */ + /* 267 was sys_fstatfs64_wrapper */ +#define __NR_tgkill 268 +__SYSCALL(__NR_tgkill, sys_tgkill) +#define __NR_utimes 269 +__SYSCALL(__NR_utimes, sys_utimes) + /* 270 was sys_fadvise64_64 */ + /* 271 was sys_pciconfig_iobase */ + /* 272 was sys_pciconfig_read */ + /* 273 was sys_pciconfig_write */ +#define __NR_mq_open 274 +__SYSCALL(__NR_mq_open, sys_mq_open) +#define __NR_mq_unlink 275 +__SYSCALL(__NR_mq_unlink, sys_mq_unlink) +#define __NR_mq_timedsend 276 +__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend) +#define __NR_mq_timedreceive 277 +__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive) +#define __NR_mq_notify 278 +__SYSCALL(__NR_mq_notify, sys_mq_notify) +#define __NR_mq_getsetattr 279 +__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr) +#define __NR_waitid 280 +__SYSCALL(__NR_waitid, sys_waitid) +#define __NR_socket 281 +__SYSCALL(__NR_socket, sys_socket) +#define __NR_bind 282 +__SYSCALL(__NR_bind, sys_bind) +#define __NR_connect 283 +__SYSCALL(__NR_connect, sys_connect) +#define __NR_listen 284 +__SYSCALL(__NR_listen, sys_listen) +#define __NR_accept 285 +__SYSCALL(__NR_accept, sys_accept) +#define __NR_getsockname 286 +__SYSCALL(__NR_getsockname, sys_getsockname) +#define __NR_getpeername 287 +__SYSCALL(__NR_getpeername, sys_getpeername) +#define __NR_socketpair 288 +__SYSCALL(__NR_socketpair, sys_socketpair) +#define __NR_send 289 +__SYSCALL(__NR_send, sys_send) +#define __NR_sendto 290 +__SYSCALL(__NR_sendto, sys_sendto) +#define __NR_recv 291 +__SYSCALL(__NR_recv, sys_recv) +#define __NR_recvfrom 292 +__SYSCALL(__NR_recvfrom, sys_recvfrom) +#define __NR_shutdown 293 +__SYSCALL(__NR_shutdown, sys_shutdown) +#define __NR_setsockopt 294 +__SYSCALL(__NR_setsockopt, sys_setsockopt) +#define __NR_getsockopt 295 +__SYSCALL(__NR_getsockopt, sys_getsockopt) +#define __NR_sendmsg 296 +__SYSCALL(__NR_sendmsg, sys_sendmsg) +#define __NR_recvmsg 297 +__SYSCALL(__NR_recvmsg, sys_recvmsg) +#define __NR_semop 298 +__SYSCALL(__NR_semop, sys_semop) +#define __NR_semget 299 +__SYSCALL(__NR_semget, sys_semget) +#define __NR_semctl 300 +__SYSCALL(__NR_semctl, sys_semctl) +#define __NR_msgsnd 301 +__SYSCALL(__NR_msgsnd, sys_msgsnd) +#define __NR_msgrcv 302 +__SYSCALL(__NR_msgrcv, sys_msgrcv) +#define __NR_msgget 303 +__SYSCALL(__NR_msgget, sys_msgget) +#define __NR_msgctl 304 +__SYSCALL(__NR_msgctl, sys_msgctl) +#define __NR_shmat 305 +__SYSCALL(__NR_shmat, sys_shmat) +#define __NR_shmdt 306 +__SYSCALL(__NR_shmdt, sys_shmdt) +#define __NR_shmget 307 +__SYSCALL(__NR_shmget, sys_shmget) +#define __NR_shmctl 308 +__SYSCALL(__NR_shmctl, sys_shmctl) +#define __NR_add_key 309 +__SYSCALL(__NR_add_key, sys_add_key) +#define __NR_request_key 310 +__SYSCALL(__NR_request_key, sys_request_key) +#define __NR_keyctl 311 +__SYSCALL(__NR_keyctl, sys_keyctl) +#define __NR_semtimedop 312 +__SYSCALL(__NR_semtimedop, sys_semtimedop) + /* 313 was for vserver */ +#define __NR_ioprio_set 314 +__SYSCALL(__NR_ioprio_set, sys_ioprio_set) +#define __NR_ioprio_get 315 +__SYSCALL(__NR_ioprio_get, sys_ioprio_get) +#define __NR_inotify_init 316 +__SYSCALL(__NR_inotify_init, sys_inotify_init) +#define __NR_inotify_add_watch 317 +__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) +#define __NR_inotify_rm_watch 318 +__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) +#define __NR_mbind 319 +__SYSCALL(__NR_mbind, sys_mbind) +#define __NR_get_mempolicy 320 +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) +#define __NR_set_mempolicy 321 +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) +#define __NR_openat 322 +__SYSCALL(__NR_openat, sys_openat) +#define __NR_mkdirat 323 +__SYSCALL(__NR_mkdirat, sys_mkdirat) +#define __NR_mknodat 324 +__SYSCALL(__NR_mknodat, sys_mknodat) +#define __NR_fchownat 325 +__SYSCALL(__NR_fchownat, sys_fchownat) +#define __NR_futimesat 326 +__SYSCALL(__NR_futimesat, sys_futimesat) +#define __NR_fstatat64 327 +__SYSCALL(__NR_fstatat64, sys_fstatat64) +#define __NR_unlinkat 328 +__SYSCALL(__NR_unlinkat, sys_unlinkat) +#define __NR_renameat 329 +__SYSCALL(__NR_renameat, sys_renameat) +#define __NR_linkat 330 +__SYSCALL(__NR_linkat, sys_linkat) +#define __NR_symlinkat 331 +__SYSCALL(__NR_symlinkat, sys_symlinkat) +#define __NR_readlinkat 332 +__SYSCALL(__NR_readlinkat, sys_readlinkat) +#define __NR_fchmodat 333 +__SYSCALL(__NR_fchmodat, sys_fchmodat) +#define __NR_faccessat 334 +__SYSCALL(__NR_faccessat, sys_faccessat) +#define __NR_pselect6 335 +__SYSCALL(__NR_pselect6, sys_pselect6) +#define __NR_ppoll 336 +__SYSCALL(__NR_ppoll, sys_ppoll) +#define __NR_unshare 337 +__SYSCALL(__NR_unshare, sys_unshare) +#define __NR_set_robust_list 338 +__SYSCALL(__NR_set_robust_list, sys_set_robust_list) +#define __NR_get_robust_list 339 +__SYSCALL(__NR_get_robust_list, sys_get_robust_list) +#define __NR_splice 340 +__SYSCALL(__NR_splice, sys_splice) +#define __NR_uc32_sync_file_range 341 +__SYSCALL(__NR_uc32_sync_file_range, sys_sync_file_range2) +#define __NR_sync_file_range2 __NR_uc32_sync_file_range +#define __NR_tee 342 +__SYSCALL(__NR_tee, sys_tee) +#define __NR_vmsplice 343 +__SYSCALL(__NR_vmsplice, sys_vmsplice) +#define __NR_move_pages 344 +__SYSCALL(__NR_move_pages, sys_move_pages) +#define __NR_getcpu 345 +__SYSCALL(__NR_getcpu, sys_getcpu) +#define __NR_epoll_pwait 346 +__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait) +#define __NR_kexec_load 347 +__SYSCALL(__NR_kexec_load, sys_kexec_load) +#define __NR_utimensat 348 +__SYSCALL(__NR_utimensat, sys_utimensat) +#define __NR_signalfd 349 +__SYSCALL(__NR_signalfd, sys_signalfd) +#define __NR_timerfd_create 350 +__SYSCALL(__NR_timerfd_create, sys_timerfd_create) +#define __NR_eventfd 351 +__SYSCALL(__NR_eventfd, sys_eventfd) +#define __NR_fallocate 352 +__SYSCALL(__NR_fallocate, sys_fallocate) +#define __NR_timerfd_settime 353 +__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) +#define __NR_timerfd_gettime 354 +__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) +#define __NR_signalfd4 355 +__SYSCALL(__NR_signalfd4, sys_signalfd4) +#define __NR_eventfd2 356 +__SYSCALL(__NR_eventfd2, sys_eventfd2) +#define __NR_epoll_create1 357 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) +#define __NR_dup3 358 +__SYSCALL(__NR_dup3, sys_dup3) +#define __NR_pipe2 359 +__SYSCALL(__NR_pipe2, sys_pipe2) +#define __NR_inotify_init1 360 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 361 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 362 +__SYSCALL(__NR_pwritev, sys_pwritev) +#define __NR_rt_tgsigqueueinfo 363 +__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) +#define __NR_perf_event_open 364 +__SYSCALL(__NR_perf_event_open, sys_perf_event_open) +#define __NR_recvmmsg 365 +__SYSCALL(__NR_recvmmsg, sys_recvmmsg) +#define __NR_accept4 366 +__SYSCALL(__NR_accept4, sys_accept4) +#define __NR_fanotify_init 367 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 368 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_prlimit64 369 +__SYSCALL(__NR_prlimit64, sys_prlimit64) + +#undef __NR_syscalls +#define __NR_syscalls (__NR_prlimit64+1) + +#ifdef __KERNEL__ + +#define __ARCH_WANT_IPC_PARSE_VERSION +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_PAUSE +#define __ARCH_WANT_SYS_GETPGRP +#define __ARCH_WANT_SYS_LLSEEK +#define __ARCH_WANT_SYS_NICE +#define __ARCH_WANT_SYS_SIGPENDING +#define __ARCH_WANT_SYS_SIGPROCMASK +#define __ARCH_WANT_SYS_RT_SIGACTION +#define __ARCH_WANT_SYS_RT_SIGSUSPEND +#define __ARCH_WANT_SYS_OLD_MMAP +#define __ARCH_WANT_SYS_OLD_SELECT +#define __ARCH_WANT_SYS_TIME +#define __ARCH_WANT_SYS_IPC +#define __ARCH_WANT_SYS_OLDUMOUNT +#define __ARCH_WANT_SYS_ALARM +#define __ARCH_WANT_SYS_UTIME +#define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_OLD_READDIR +#define __ARCH_WANT_SYS_SOCKETCALL +#define __ARCH_WANT_SYS_FORK +#define __ARCH_WANT_SYS_VFORK +#define __ARCH_WANT_SYS_CLONE + +/* + * Unimplemented (or alternatively implemented) syscalls + */ +#define __IGNORE_fadvise64_64 1 +#define __IGNORE_migrate_pages 1 +#define __IGNORE_name_to_handle_at 1 +#define __IGNORE_open_by_handle_at 1 +#define __IGNORE_clock_adjtime 1 +#define __IGNORE_syncfs 1 +#define __IGNORE_sendmmsg 1 +#define __IGNORE_setns 1 +#define __IGNORE_statfs64 1 +#define __IGNORE_fstatfs64 1 +#define __IGNORE_process_vm_readv 1 +#define __IGNORE_process_vm_writev 1 +#define __IGNORE_kcmp 1 +#define __IGNORE_finit_module 1 +#define __IGNORE_sched_setattr 1 +#define __IGNORE_sched_getattr 1 +#define __IGNORE_renameat2 1 +#define __IGNORE_seccomp 1 +#define __IGNORE_getrandom 1 +#define __IGNORE_memfd_create 1 + +#endif /* __KERNEL__ */ diff --git a/arch/unicore32/include/uapi/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h index 1f63c476528e6c..9cf71c7bedb102 100644 --- a/arch/unicore32/include/uapi/asm/unistd.h +++ b/arch/unicore32/include/uapi/asm/unistd.h @@ -12,6 +12,14 @@ #define __ARCH_WANT_RENAMEAT +#ifndef CONFIG_UNICORE32_OLDABI + /* Use the standard ABI for syscalls. */ #include #define __ARCH_WANT_SYS_CLONE + +#else + +#include + +#endif /* CONFIG_UNICORE32_OLDABI */ diff --git a/arch/unicore32/kernel/entry.S b/arch/unicore32/kernel/entry.S index bcdedd80890ea2..3562d08192aeea 100644 --- a/arch/unicore32/kernel/entry.S +++ b/arch/unicore32/kernel/entry.S @@ -668,6 +668,23 @@ __cr_alignment: #endif .ltorg +#ifdef CONFIG_UNICORE32_OLDABI +/* + * Special system call wrappers + */ +ENTRY(sys_clone_wrapper) + add ip, sp, #S_OFF + stw ip, [sp+], #4 + b sys_clone +ENDPROC(sys_clone_wrapper) + +ENTRY(sys_sigreturn_wrapper) + add r0, sp, #S_OFF + mov why, #0 @ prevent syscall restart handling + b __sys_sigreturn +ENDPROC(sys_sigreturn_wrapper) +#endif + ENTRY(sys_rt_sigreturn) add r0, sp, #S_OFF mov why, #0 @ prevent syscall restart handling diff --git a/arch/unicore32/kernel/signal.c b/arch/unicore32/kernel/signal.c index 4ae51cf15adea6..be75ef8c1e0c74 100644 --- a/arch/unicore32/kernel/signal.c +++ b/arch/unicore32/kernel/signal.c @@ -23,9 +23,18 @@ /* * For UniCore syscalls, we encode the syscall number into the instruction. */ +#ifdef CONFIG_UNICORE32_OLDABI +#define SWI_SYS_SIGRETURN (0xff000000 | (__NR_SYSCALL_BASE) \ + | (__NR_sigreturn)) +#define SWI_SYS_RT_SIGRETURN (0xff000000 | (__NR_SYSCALL_BASE) \ + | (__NR_rt_sigreturn)) +#define SWI_SYS_RESTART (0xff000000 | (__NR_SYSCALL_BASE) \ + | (__NR_restart_syscall)) +#else #define SWI_SYS_SIGRETURN (0xff000000) /* error number for new abi */ #define SWI_SYS_RT_SIGRETURN (0xff000000 | (__NR_rt_sigreturn)) #define SWI_SYS_RESTART (0xff000000 | (__NR_restart_syscall)) +#endif #define KERN_SIGRETURN_CODE (KUSER_VECPAGE_BASE + 0x00000500) #define KERN_RESTART_CODE (KERN_SIGRETURN_CODE + sizeof(sigreturn_codes)) @@ -100,6 +109,38 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) return err; } +#ifdef CONFIG_UNICORE32_OLDABI +asmlinkage int __sys_sigreturn(struct pt_regs *regs) +{ + struct sigframe __user *frame; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + /* + * Since we stacked the signal on a 64-bit boundary, + * then 'sp' should be word aligned here. If it's + * not, then the user is trying to mess with us. + */ + if (regs->UCreg_sp & 7) + goto badframe; + + frame = (struct sigframe __user *)regs->UCreg_sp; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + + if (restore_sigframe(regs, frame)) + goto badframe; + + return regs->UCreg_00; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} +#endif + asmlinkage int __sys_rt_sigreturn(struct pt_regs *regs) { struct rt_sigframe __user *frame; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index 73ccf63b0f48c6..9dc1ce6ba3c0c7 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -13,7 +13,7 @@ static inline char rdfs8(addr_t addr) return *((char *)(fs + addr)); } #include "../cmdline.c" -static unsigned long get_cmd_line_ptr(void) +unsigned long get_cmd_line_ptr(void) { unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 54c24f0a43d36c..e0eba12bffe76d 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -9,16 +9,41 @@ * contain the entire properly aligned running kernel image. * */ + +/* + * isspace() in linux/ctype.h is expected by next_args() to filter + * out "space/lf/tab". While boot/ctype.h conflicts with linux/ctype.h, + * since isdigit() is implemented in both of them. Hence disable it + * here. + */ +#define BOOT_CTYPE_H + +/* + * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h. + * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL + * which is meaningless and will cause compiling error in some cases. + * So do not include linux/export.h and define EXPORT_SYMBOL(sym) + * as empty. + */ +#define _LINUX_EXPORT_H +#define EXPORT_SYMBOL(sym) + #include "misc.h" #include "error.h" -#include "../boot.h" #include #include #include #include +#include #include +/* Macros used by the included decompressor code below. */ +#define STATIC +#include + +extern unsigned long get_cmd_line_ptr(void); + /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; @@ -62,6 +87,11 @@ struct mem_vector { static bool memmap_too_large; + +/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ +unsigned long long mem_limit = ULLONG_MAX; + + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, @@ -85,49 +115,14 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } -/** - * _memparse - Parse a string with mem suffixes into a number - * @ptr: Where parse begins - * @retptr: (output) Optional pointer to next char after parse completes - * - * Parses a string into a number. The number stored at @ptr is - * potentially suffixed with K, M, G, T, P, E. - */ -static unsigned long long _memparse(const char *ptr, char **retptr) +char *skip_spaces(const char *str) { - char *endptr; /* Local pointer to end of parsed string */ - - unsigned long long ret = simple_strtoull(ptr, &endptr, 0); - - switch (*endptr) { - case 'E': - case 'e': - ret <<= 10; - case 'P': - case 'p': - ret <<= 10; - case 'T': - case 't': - ret <<= 10; - case 'G': - case 'g': - ret <<= 10; - case 'M': - case 'm': - ret <<= 10; - case 'K': - case 'k': - ret <<= 10; - endptr++; - default: - break; - } - - if (retptr) - *retptr = endptr; - - return ret; + while (isspace(*str)) + ++str; + return (char *)str; } +#include "../../../../lib/ctype.c" +#include "../../../../lib/cmdline.c" static int parse_memmap(char *p, unsigned long long *start, unsigned long long *size) @@ -142,40 +137,41 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) return -EINVAL; oldp = p; - *size = _memparse(p, &p); + *size = memparse(p, &p); if (p == oldp) return -EINVAL; switch (*p) { - case '@': - /* Skip this region, usable */ - *start = 0; - *size = 0; - return 0; case '#': case '$': case '!': - *start = _memparse(p + 1, &p); + *start = memparse(p + 1, &p); + return 0; + case '@': + /* memmap=nn@ss specifies usable region, should be skipped */ + *size = 0; + /* Fall through */ + default: + /* + * If w/o offset, only size specified, memmap=nn[KMG] has the + * same behaviour as mem=nn[KMG]. It limits the max address + * system can use. Region above the limit should be avoided. + */ + *start = 0; return 0; } return -EINVAL; } -static void mem_avoid_memmap(void) +static void mem_avoid_memmap(char *str) { - char arg[128]; + static int i; int rc; - int i; - char *str; - /* See if we have any memmap areas */ - rc = cmdline_find_option("memmap", arg, sizeof(arg)); - if (rc <= 0) + if (i >= MAX_MEMMAP_REGIONS) return; - i = 0; - str = arg; while (str && (i < MAX_MEMMAP_REGIONS)) { int rc; unsigned long long start, size; @@ -188,9 +184,14 @@ static void mem_avoid_memmap(void) if (rc < 0) break; str = k; - /* A usable region that should not be skipped */ - if (size == 0) + + if (start == 0) { + /* Store the specified memory limit if size > 0 */ + if (size > 0) + mem_limit = size; + continue; + } mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; @@ -202,6 +203,57 @@ static void mem_avoid_memmap(void) memmap_too_large = true; } +static int handle_mem_memmap(void) +{ + char *args = (char *)get_cmd_line_ptr(); + size_t len = strlen((char *)args); + char *tmp_cmdline; + char *param, *val; + u64 mem_size; + + if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + return 0; + + tmp_cmdline = malloc(len + 1); + if (!tmp_cmdline ) + error("Failed to allocate space for tmp_cmdline"); + + memcpy(tmp_cmdline, args, len); + tmp_cmdline[len] = 0; + args = tmp_cmdline; + + /* Chew leading spaces */ + args = skip_spaces(args); + + while (*args) { + args = next_arg(args, ¶m, &val); + /* Stop at -- */ + if (!val && strcmp(param, "--") == 0) { + warn("Only '--' specified in cmdline"); + free(tmp_cmdline); + return -1; + } + + if (!strcmp(param, "memmap")) { + mem_avoid_memmap(val); + } else if (!strcmp(param, "mem")) { + char *p = val; + + if (!strcmp(p, "nopentium")) + continue; + mem_size = memparse(p, &p); + if (mem_size == 0) { + free(tmp_cmdline); + return -EINVAL; + } + mem_limit = mem_size; + } + } + + free(tmp_cmdline); + return 0; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -323,7 +375,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - mem_avoid_memmap(); + handle_mem_memmap(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -432,7 +484,8 @@ static void process_e820_entry(struct boot_e820_entry *entry, { struct mem_vector region, overlap; struct slot_area slot_area; - unsigned long start_orig; + unsigned long start_orig, end; + struct boot_e820_entry cur_entry; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) @@ -446,8 +499,15 @@ static void process_e820_entry(struct boot_e820_entry *entry, if (entry->addr + entry->size < minimum) return; - region.start = entry->addr; - region.size = entry->size; + /* Ignore entries above memory limit */ + end = min(entry->size + entry->addr, mem_limit); + if (entry->addr >= end) + return; + cur_entry.addr = entry->addr; + cur_entry.size = end - entry->addr; + + region.start = cur_entry.addr; + region.size = cur_entry.size; /* Give up if slot area array is full. */ while (slot_area_index < MAX_SLOT_AREA) { @@ -461,7 +521,7 @@ static void process_e820_entry(struct boot_e820_entry *entry, region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); /* Did we raise the address above this e820 region? */ - if (region.start > entry->addr + entry->size) + if (region.start > cur_entry.addr + cur_entry.size) return; /* Reduce size by any delta from the original address. */ diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 5457b02fc05077..630e3664906bfc 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -122,6 +122,14 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas return result; } +long simple_strtol(const char *cp, char **endp, unsigned int base) +{ + if (*cp == '-') + return -simple_strtoull(cp + 1, endp, base); + + return simple_strtoull(cp, endp, base); +} + /** * strlen - Find the length of a string * @s: The string to be sized diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S index 91056554716355..8739cf7795de0f 100644 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ b/arch/x86/crypto/aes-x86_64-asm_64.S @@ -42,17 +42,15 @@ #define R5E %esi #define R6 %rdi #define R6E %edi -#define R7 %rbp -#define R7E %ebp +#define R7 %r9 /* don't use %rbp; it breaks stack traces */ +#define R7E %r9d #define R8 %r8 -#define R9 %r9 #define R10 %r10 #define R11 %r11 -#define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \ +#define prologue(FUNC,KEY,B128,B192,r1,r2,r5,r6,r7,r8,r9,r10,r11) \ ENTRY(FUNC); \ movq r1,r2; \ - movq r3,r4; \ leaq KEY+48(r8),r9; \ movq r10,r11; \ movl (r7),r5 ## E; \ @@ -70,9 +68,8 @@ je B192; \ leaq 32(r9),r9; -#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \ +#define epilogue(FUNC,r1,r2,r5,r6,r7,r8,r9) \ movq r1,r2; \ - movq r3,r4; \ movl r5 ## E,(r9); \ movl r6 ## E,4(r9); \ movl r7 ## E,8(r9); \ @@ -88,12 +85,12 @@ movl TAB(,r6,4),r6 ## E; \ roll $16,r2 ## E; \ shrl $16,r4 ## E; \ - movzbl r4 ## H,r7 ## E; \ - movzbl r4 ## L,r4 ## E; \ + movzbl r4 ## L,r7 ## E; \ + movzbl r4 ## H,r4 ## E; \ xorl OFFSET(r8),ra ## E; \ xorl OFFSET+4(r8),rb ## E; \ - xorl TAB+3072(,r7,4),r5 ## E;\ - xorl TAB+2048(,r4,4),r6 ## E;\ + xorl TAB+3072(,r4,4),r5 ## E;\ + xorl TAB+2048(,r7,4),r6 ## E;\ movzbl r1 ## L,r7 ## E; \ movzbl r1 ## H,r4 ## E; \ movl TAB+1024(,r4,4),r4 ## E;\ @@ -101,19 +98,19 @@ roll $16,r1 ## E; \ shrl $16,r3 ## E; \ xorl TAB(,r7,4),r5 ## E; \ - movzbl r3 ## H,r7 ## E; \ - movzbl r3 ## L,r3 ## E; \ - xorl TAB+3072(,r7,4),r4 ## E;\ - xorl TAB+2048(,r3,4),r5 ## E;\ - movzbl r1 ## H,r7 ## E; \ - movzbl r1 ## L,r3 ## E; \ + movzbl r3 ## L,r7 ## E; \ + movzbl r3 ## H,r3 ## E; \ + xorl TAB+3072(,r3,4),r4 ## E;\ + xorl TAB+2048(,r7,4),r5 ## E;\ + movzbl r1 ## L,r7 ## E; \ + movzbl r1 ## H,r3 ## E; \ shrl $16,r1 ## E; \ - xorl TAB+3072(,r7,4),r6 ## E;\ - movl TAB+2048(,r3,4),r3 ## E;\ - movzbl r1 ## H,r7 ## E; \ - movzbl r1 ## L,r1 ## E; \ - xorl TAB+1024(,r7,4),r6 ## E;\ - xorl TAB(,r1,4),r3 ## E; \ + xorl TAB+3072(,r3,4),r6 ## E;\ + movl TAB+2048(,r7,4),r3 ## E;\ + movzbl r1 ## L,r7 ## E; \ + movzbl r1 ## H,r1 ## E; \ + xorl TAB+1024(,r1,4),r6 ## E;\ + xorl TAB(,r7,4),r3 ## E; \ movzbl r2 ## H,r1 ## E; \ movzbl r2 ## L,r7 ## E; \ shrl $16,r2 ## E; \ @@ -131,9 +128,9 @@ movl r4 ## E,r2 ## E; #define entry(FUNC,KEY,B128,B192) \ - prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11) + prologue(FUNC,KEY,B128,B192,R2,R8,R1,R3,R4,R6,R10,R5,R11) -#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11) +#define return(FUNC) epilogue(FUNC,R8,R2,R5,R6,R3,R4,R11) #define encrypt_round(TAB,OFFSET) \ round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \ diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 3c465184ff8ab0..16627fec80b26b 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -89,6 +89,29 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 ALL_F: .octa 0xffffffffffffffffffffffffffffffff .octa 0x00000000000000000000000000000000 +.section .rodata +.align 16 +.type aad_shift_arr, @object +.size aad_shift_arr, 272 +aad_shift_arr: + .octa 0xffffffffffffffffffffffffffffffff + .octa 0xffffffffffffffffffffffffffffff0C + .octa 0xffffffffffffffffffffffffffff0D0C + .octa 0xffffffffffffffffffffffffff0E0D0C + .octa 0xffffffffffffffffffffffff0F0E0D0C + .octa 0xffffffffffffffffffffff0C0B0A0908 + .octa 0xffffffffffffffffffff0D0C0B0A0908 + .octa 0xffffffffffffffffff0E0D0C0B0A0908 + .octa 0xffffffffffffffff0F0E0D0C0B0A0908 + .octa 0xffffffffffffff0C0B0A090807060504 + .octa 0xffffffffffff0D0C0B0A090807060504 + .octa 0xffffffffff0E0D0C0B0A090807060504 + .octa 0xffffffff0F0E0D0C0B0A090807060504 + .octa 0xffffff0C0B0A09080706050403020100 + .octa 0xffff0D0C0B0A09080706050403020100 + .octa 0xff0E0D0C0B0A09080706050403020100 + .octa 0x0F0E0D0C0B0A09080706050403020100 + .text @@ -252,32 +275,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation mov arg8, %r12 # %r12 = aadLen mov %r12, %r11 pxor %xmm\i, %xmm\i + pxor \XMM2, \XMM2 -_get_AAD_loop\num_initial_blocks\operation: - movd (%r10), \TMP1 - pslldq $12, \TMP1 - psrldq $4, %xmm\i + cmp $16, %r11 + jl _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_blocks\num_initial_blocks\operation: + movdqu (%r10), %xmm\i + PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor %xmm\i, \XMM2 + GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\num_initial_blocks\operation + + movdqu \XMM2, %xmm\i + cmp $0, %r11 + je _get_AAD_done\num_initial_blocks\operation + + pxor %xmm\i,%xmm\i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\num_initial_blocks\operation: + cmp $4, %r11 + jle _get_AAD_rest4\num_initial_blocks\operation + movq (%r10), \TMP1 + add $8, %r10 + sub $8, %r11 + pslldq $8, \TMP1 + psrldq $8, %xmm\i pxor \TMP1, %xmm\i + jmp _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_rest4\num_initial_blocks\operation: + cmp $0, %r11 + jle _get_AAD_rest0\num_initial_blocks\operation + mov (%r10), %eax + movq %rax, \TMP1 add $4, %r10 - sub $4, %r12 - jne _get_AAD_loop\num_initial_blocks\operation - - cmp $16, %r11 - je _get_AAD_loop2_done\num_initial_blocks\operation - - mov $16, %r12 -_get_AAD_loop2\num_initial_blocks\operation: + sub $4, %r10 + pslldq $12, \TMP1 psrldq $4, %xmm\i - sub $4, %r12 - cmp %r11, %r12 - jne _get_AAD_loop2\num_initial_blocks\operation - -_get_AAD_loop2_done\num_initial_blocks\operation: + pxor \TMP1, %xmm\i +_get_AAD_rest0\num_initial_blocks\operation: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \TMP1 + PSHUFB_XMM \TMP1, %xmm\i +_get_AAD_rest_final\num_initial_blocks\operation: PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor \XMM2, %xmm\i + GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 +_get_AAD_done\num_initial_blocks\operation: xor %r11, %r11 # initialise the data pointer offset as zero - - # start AES for num_initial_blocks blocks + # start AES for num_initial_blocks blocks mov %arg5, %rax # %rax = *Y0 movdqu (%rax), \XMM0 # XMM0 = Y0 @@ -322,7 +379,7 @@ aes_loop_initial_dec\num_initial_blocks: # prepare plaintext/ciphertext for GHASH computation .endr .endif - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + # apply GHASH on num_initial_blocks blocks .if \i == 5 @@ -477,28 +534,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation mov arg8, %r12 # %r12 = aadLen mov %r12, %r11 pxor %xmm\i, %xmm\i -_get_AAD_loop\num_initial_blocks\operation: - movd (%r10), \TMP1 - pslldq $12, \TMP1 - psrldq $4, %xmm\i + pxor \XMM2, \XMM2 + + cmp $16, %r11 + jl _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_blocks\num_initial_blocks\operation: + movdqu (%r10), %xmm\i + PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor %xmm\i, \XMM2 + GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\num_initial_blocks\operation + + movdqu \XMM2, %xmm\i + cmp $0, %r11 + je _get_AAD_done\num_initial_blocks\operation + + pxor %xmm\i,%xmm\i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some PT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\num_initial_blocks\operation: + cmp $4, %r11 + jle _get_AAD_rest4\num_initial_blocks\operation + movq (%r10), \TMP1 + add $8, %r10 + sub $8, %r11 + pslldq $8, \TMP1 + psrldq $8, %xmm\i pxor \TMP1, %xmm\i + jmp _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_rest4\num_initial_blocks\operation: + cmp $0, %r11 + jle _get_AAD_rest0\num_initial_blocks\operation + mov (%r10), %eax + movq %rax, \TMP1 add $4, %r10 - sub $4, %r12 - jne _get_AAD_loop\num_initial_blocks\operation - cmp $16, %r11 - je _get_AAD_loop2_done\num_initial_blocks\operation - mov $16, %r12 -_get_AAD_loop2\num_initial_blocks\operation: + sub $4, %r10 + pslldq $12, \TMP1 psrldq $4, %xmm\i - sub $4, %r12 - cmp %r11, %r12 - jne _get_AAD_loop2\num_initial_blocks\operation -_get_AAD_loop2_done\num_initial_blocks\operation: + pxor \TMP1, %xmm\i +_get_AAD_rest0\num_initial_blocks\operation: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \TMP1 + PSHUFB_XMM \TMP1, %xmm\i +_get_AAD_rest_final\num_initial_blocks\operation: PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor \XMM2, %xmm\i + GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 +_get_AAD_done\num_initial_blocks\operation: xor %r11, %r11 # initialise the data pointer offset as zero - - # start AES for num_initial_blocks blocks + # start AES for num_initial_blocks blocks mov %arg5, %rax # %rax = *Y0 movdqu (%rax), \XMM0 # XMM0 = Y0 @@ -543,7 +638,7 @@ aes_loop_initial_enc\num_initial_blocks: # prepare plaintext/ciphertext for GHASH computation .endr .endif - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + # apply GHASH on num_initial_blocks blocks .if \i == 5 @@ -1454,18 +1549,35 @@ _return_T_decrypt: mov arg10, %r11 # %r11 = auth_tag_len cmp $16, %r11 je _T_16_decrypt - cmp $12, %r11 - je _T_12_decrypt + cmp $8, %r11 + jl _T_4_decrypt _T_8_decrypt: MOVQ_R64_XMM %xmm0, %rax mov %rax, (%r10) - jmp _return_T_done_decrypt -_T_12_decrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 psrldq $8, %xmm0 + cmp $0, %r11 + je _return_T_done_decrypt +_T_4_decrypt: + movd %xmm0, %eax + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + psrldq $4, %xmm0 + cmp $0, %r11 + je _return_T_done_decrypt +_T_123_decrypt: movd %xmm0, %eax - mov %eax, 8(%r10) + cmp $2, %r11 + jl _T_1_decrypt + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done_decrypt + add $2, %r10 + sar $16, %eax +_T_1_decrypt: + mov %al, (%r10) jmp _return_T_done_decrypt _T_16_decrypt: movdqu %xmm0, (%r10) @@ -1718,18 +1830,35 @@ _return_T_encrypt: mov arg10, %r11 # %r11 = auth_tag_len cmp $16, %r11 je _T_16_encrypt - cmp $12, %r11 - je _T_12_encrypt + cmp $8, %r11 + jl _T_4_encrypt _T_8_encrypt: MOVQ_R64_XMM %xmm0, %rax mov %rax, (%r10) - jmp _return_T_done_encrypt -_T_12_encrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 psrldq $8, %xmm0 + cmp $0, %r11 + je _return_T_done_encrypt +_T_4_encrypt: + movd %xmm0, %eax + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + psrldq $4, %xmm0 + cmp $0, %r11 + je _return_T_done_encrypt +_T_123_encrypt: movd %xmm0, %eax - mov %eax, 8(%r10) + cmp $2, %r11 + jl _T_1_encrypt + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done_encrypt + add $2, %r10 + sar $16, %eax +_T_1_encrypt: + mov %al, (%r10) jmp _return_T_done_encrypt _T_16_encrypt: movdqu %xmm0, (%r10) diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index d664382c6e56b9..faecb1518bf816 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -155,6 +155,30 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 ALL_F: .octa 0xffffffffffffffffffffffffffffffff .octa 0x00000000000000000000000000000000 +.section .rodata +.align 16 +.type aad_shift_arr, @object +.size aad_shift_arr, 272 +aad_shift_arr: + .octa 0xffffffffffffffffffffffffffffffff + .octa 0xffffffffffffffffffffffffffffff0C + .octa 0xffffffffffffffffffffffffffff0D0C + .octa 0xffffffffffffffffffffffffff0E0D0C + .octa 0xffffffffffffffffffffffff0F0E0D0C + .octa 0xffffffffffffffffffffff0C0B0A0908 + .octa 0xffffffffffffffffffff0D0C0B0A0908 + .octa 0xffffffffffffffffff0E0D0C0B0A0908 + .octa 0xffffffffffffffff0F0E0D0C0B0A0908 + .octa 0xffffffffffffff0C0B0A090807060504 + .octa 0xffffffffffff0D0C0B0A090807060504 + .octa 0xffffffffff0E0D0C0B0A090807060504 + .octa 0xffffffff0F0E0D0C0B0A090807060504 + .octa 0xffffff0C0B0A09080706050403020100 + .octa 0xffff0D0C0B0A09080706050403020100 + .octa 0xff0E0D0C0B0A09080706050403020100 + .octa 0x0F0E0D0C0B0A09080706050403020100 + + .text @@ -372,41 +396,72 @@ VARIABLE_OFFSET = 16*8 .macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC i = (8-\num_initial_blocks) + j = 0 setreg - mov arg6, %r10 # r10 = AAD - mov arg7, %r12 # r12 = aadLen - - - mov %r12, %r11 - - vpxor reg_i, reg_i, reg_i -_get_AAD_loop\@: - vmovd (%r10), \T1 - vpslldq $12, \T1, \T1 - vpsrldq $4, reg_i, reg_i - vpxor \T1, reg_i, reg_i - - add $4, %r10 - sub $4, %r12 - jg _get_AAD_loop\@ - - - cmp $16, %r11 - je _get_AAD_loop2_done\@ - mov $16, %r12 - -_get_AAD_loop2\@: - vpsrldq $4, reg_i, reg_i - sub $4, %r12 - cmp %r11, %r12 - jg _get_AAD_loop2\@ - -_get_AAD_loop2_done\@: - - #byte-reflect the AAD data - vpshufb SHUF_MASK(%rip), reg_i, reg_i - + mov arg6, %r10 # r10 = AAD + mov arg7, %r12 # r12 = aadLen + + + mov %r12, %r11 + + vpxor reg_j, reg_j, reg_j + vpxor reg_i, reg_i, reg_i + cmp $16, %r11 + jl _get_AAD_rest8\@ +_get_AAD_blocks\@: + vmovdqu (%r10), reg_i + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_i, reg_j, reg_j + GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\@ + vmovdqu reg_j, reg_i + cmp $0, %r11 + je _get_AAD_done\@ + + vpxor reg_i, reg_i, reg_i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\@: + cmp $4, %r11 + jle _get_AAD_rest4\@ + movq (%r10), \T1 + add $8, %r10 + sub $8, %r11 + vpslldq $8, \T1, \T1 + vpsrldq $8, reg_i, reg_i + vpxor \T1, reg_i, reg_i + jmp _get_AAD_rest8\@ +_get_AAD_rest4\@: + cmp $0, %r11 + jle _get_AAD_rest0\@ + mov (%r10), %eax + movq %rax, \T1 + add $4, %r10 + sub $4, %r11 + vpslldq $12, \T1, \T1 + vpsrldq $4, reg_i, reg_i + vpxor \T1, reg_i, reg_i +_get_AAD_rest0\@: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \T1 + vpshufb \T1, reg_i, reg_i +_get_AAD_rest_final\@: + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_j, reg_i, reg_i + GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6 + +_get_AAD_done\@: # initialize the data pointer offset as zero xor %r11, %r11 @@ -480,7 +535,6 @@ _get_AAD_loop2_done\@: i = (8-\num_initial_blocks) j = (9-\num_initial_blocks) setreg - GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6 .rep \num_initial_blocks vpxor reg_i, reg_j, reg_j @@ -1427,19 +1481,36 @@ _return_T\@: cmp $16, %r11 je _T_16\@ - cmp $12, %r11 - je _T_12\@ + cmp $8, %r11 + jl _T_4\@ _T_8\@: vmovq %xmm9, %rax mov %rax, (%r10) - jmp _return_T_done\@ -_T_12\@: - vmovq %xmm9, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 vpsrldq $8, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_4\@: vmovd %xmm9, %eax - mov %eax, 8(%r10) + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + vpsrldq $4, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_123\@: + vmovd %xmm9, %eax + cmp $2, %r11 + jl _T_1\@ + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done\@ + add $2, %r10 + sar $16, %eax +_T_1\@: + mov %al, (%r10) jmp _return_T_done\@ _T_16\@: @@ -1631,41 +1702,73 @@ ENDPROC(aesni_gcm_dec_avx_gen2) .macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER i = (8-\num_initial_blocks) + j = 0 setreg - mov arg6, %r10 # r10 = AAD - mov arg7, %r12 # r12 = aadLen - - - mov %r12, %r11 - - vpxor reg_i, reg_i, reg_i -_get_AAD_loop\@: - vmovd (%r10), \T1 - vpslldq $12, \T1, \T1 - vpsrldq $4, reg_i, reg_i - vpxor \T1, reg_i, reg_i - - add $4, %r10 - sub $4, %r12 - jg _get_AAD_loop\@ - - - cmp $16, %r11 - je _get_AAD_loop2_done\@ - mov $16, %r12 - -_get_AAD_loop2\@: - vpsrldq $4, reg_i, reg_i - sub $4, %r12 - cmp %r11, %r12 - jg _get_AAD_loop2\@ - -_get_AAD_loop2_done\@: - - #byte-reflect the AAD data - vpshufb SHUF_MASK(%rip), reg_i, reg_i - + mov arg6, %r10 # r10 = AAD + mov arg7, %r12 # r12 = aadLen + + + mov %r12, %r11 + + vpxor reg_j, reg_j, reg_j + vpxor reg_i, reg_i, reg_i + + cmp $16, %r11 + jl _get_AAD_rest8\@ +_get_AAD_blocks\@: + vmovdqu (%r10), reg_i + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_i, reg_j, reg_j + GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\@ + vmovdqu reg_j, reg_i + cmp $0, %r11 + je _get_AAD_done\@ + + vpxor reg_i, reg_i, reg_i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\@: + cmp $4, %r11 + jle _get_AAD_rest4\@ + movq (%r10), \T1 + add $8, %r10 + sub $8, %r11 + vpslldq $8, \T1, \T1 + vpsrldq $8, reg_i, reg_i + vpxor \T1, reg_i, reg_i + jmp _get_AAD_rest8\@ +_get_AAD_rest4\@: + cmp $0, %r11 + jle _get_AAD_rest0\@ + mov (%r10), %eax + movq %rax, \T1 + add $4, %r10 + sub $4, %r11 + vpslldq $12, \T1, \T1 + vpsrldq $4, reg_i, reg_i + vpxor \T1, reg_i, reg_i +_get_AAD_rest0\@: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \T1 + vpshufb \T1, reg_i, reg_i +_get_AAD_rest_final\@: + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_j, reg_i, reg_i + GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6 + +_get_AAD_done\@: # initialize the data pointer offset as zero xor %r11, %r11 @@ -1740,7 +1843,6 @@ _get_AAD_loop2_done\@: i = (8-\num_initial_blocks) j = (9-\num_initial_blocks) setreg - GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6 .rep \num_initial_blocks vpxor reg_i, reg_j, reg_j @@ -2702,19 +2804,36 @@ _return_T\@: cmp $16, %r11 je _T_16\@ - cmp $12, %r11 - je _T_12\@ + cmp $8, %r11 + jl _T_4\@ _T_8\@: vmovq %xmm9, %rax mov %rax, (%r10) - jmp _return_T_done\@ -_T_12\@: - vmovq %xmm9, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 vpsrldq $8, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_4\@: vmovd %xmm9, %eax - mov %eax, 8(%r10) + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + vpsrldq $4, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_123\@: + vmovd %xmm9, %eax + cmp $2, %r11 + jl _T_1\@ + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done\@ + add $2, %r10 + sar $16, %eax +_T_1\@: + mov %al, (%r10) jmp _return_T_done\@ _T_16\@: diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 93de8ea515486a..4a55cdcdc00827 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -61,6 +61,11 @@ struct aesni_rfc4106_gcm_ctx { u8 nonce[4]; }; +struct generic_gcmaes_ctx { + u8 hash_subkey[16] AESNI_ALIGN_ATTR; + struct crypto_aes_ctx aes_key_expanded AESNI_ALIGN_ATTR; +}; + struct aesni_xts_ctx { u8 raw_tweak_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; @@ -102,13 +107,11 @@ asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out, * u8 *out, Ciphertext output. Encrypt in-place is allowed. * const u8 *in, Plaintext input * unsigned long plaintext_len, Length of data in bytes for encryption. - * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association) - * concatenated with 8 byte Initialisation Vector (from IPSec ESP - * Payload) concatenated with 0x00000001. 16-byte aligned pointer. + * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. + * 16-byte aligned pointer. * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. * const u8 *aad, Additional Authentication Data (AAD) - * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this - * is going to be 8 or 12 bytes + * unsigned long aad_len, Length of AAD in bytes. * u8 *auth_tag, Authenticated Tag output. * unsigned long auth_tag_len), Authenticated Tag Length in bytes. * Valid values are 16 (most likely), 12 or 8. @@ -123,9 +126,8 @@ asmlinkage void aesni_gcm_enc(void *ctx, u8 *out, * u8 *out, Plaintext output. Decrypt in-place is allowed. * const u8 *in, Ciphertext input * unsigned long ciphertext_len, Length of data in bytes for decryption. - * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association) - * concatenated with 8 byte Initialisation Vector (from IPSec ESP - * Payload) concatenated with 0x00000001. 16-byte aligned pointer. + * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. + * 16-byte aligned pointer. * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. * const u8 *aad, Additional Authentication Data (AAD) * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this is going @@ -275,6 +277,16 @@ aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) align = 1; return PTR_ALIGN(crypto_aead_ctx(tfm), align); } + +static inline struct +generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm) +{ + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return PTR_ALIGN(crypto_aead_ctx(tfm), align); +} #endif static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) @@ -712,32 +724,34 @@ static int rfc4106_set_authsize(struct crypto_aead *parent, return crypto_aead_setauthsize(&cryptd_tfm->base, authsize); } -static int helper_rfc4106_encrypt(struct aead_request *req) +static int generic_gcmaes_set_authsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + switch (authsize) { + case 4: + case 8: + case 12: + case 13: + case 14: + case 15: + case 16: + break; + default: + return -EINVAL; + } + + return 0; +} + +static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen, + u8 *hash_subkey, u8 *iv, void *aes_ctx) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; - __be32 counter = cpu_to_be32(1); struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); struct scatter_walk src_sg_walk; struct scatter_walk dst_sg_walk = {}; - unsigned int i; - - /* Assuming we are supporting rfc4106 64-bit extended */ - /* sequence numbers We need to have the AAD length equal */ - /* to 16 or 20 bytes */ - if (unlikely(req->assoclen != 16 && req->assoclen != 20)) - return -EINVAL; - - /* IV below built */ - for (i = 0; i < 4; i++) - *(iv+i) = ctx->nonce[i]; - for (i = 0; i < 8; i++) - *(iv+4+i) = req->iv[i]; - *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && (!PageHighMem(sg_page(req->src)) || @@ -768,7 +782,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req) kernel_fpu_begin(); aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv, - ctx->hash_subkey, assoc, req->assoclen - 8, + hash_subkey, assoc, assoclen, dst + req->cryptlen, auth_tag_len); kernel_fpu_end(); @@ -791,37 +805,20 @@ static int helper_rfc4106_encrypt(struct aead_request *req) return 0; } -static int helper_rfc4106_decrypt(struct aead_request *req) +static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen, + u8 *hash_subkey, u8 *iv, void *aes_ctx) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; unsigned long tempCipherLen = 0; - __be32 counter = cpu_to_be32(1); - int retval = 0; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); u8 authTag[16]; struct scatter_walk src_sg_walk; struct scatter_walk dst_sg_walk = {}; - unsigned int i; - - if (unlikely(req->assoclen != 16 && req->assoclen != 20)) - return -EINVAL; - - /* Assuming we are supporting rfc4106 64-bit extended */ - /* sequence numbers We need to have the AAD length */ - /* equal to 16 or 20 bytes */ + int retval = 0; tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len); - /* IV below built */ - for (i = 0; i < 4; i++) - *(iv+i) = ctx->nonce[i]; - for (i = 0; i < 8; i++) - *(iv+4+i) = req->iv[i]; - *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && (!PageHighMem(sg_page(req->src)) || @@ -838,7 +835,6 @@ static int helper_rfc4106_decrypt(struct aead_request *req) scatterwalk_start(&dst_sg_walk, req->dst); dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } - } else { /* Allocate memory for src, dst, assoc */ assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); @@ -850,9 +846,10 @@ static int helper_rfc4106_decrypt(struct aead_request *req) dst = src; } + kernel_fpu_begin(); aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv, - ctx->hash_subkey, assoc, req->assoclen - 8, + hash_subkey, assoc, assoclen, authTag, auth_tag_len); kernel_fpu_end(); @@ -875,6 +872,60 @@ static int helper_rfc4106_decrypt(struct aead_request *req) kfree(assoc); } return retval; + +} + +static int helper_rfc4106_encrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + unsigned int i; + __be32 counter = cpu_to_be32(1); + + /* Assuming we are supporting rfc4106 64-bit extended */ + /* sequence numbers We need to have the AAD length equal */ + /* to 16 or 20 bytes */ + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) + return -EINVAL; + + /* IV below built */ + for (i = 0; i < 4; i++) + *(iv+i) = ctx->nonce[i]; + for (i = 0; i < 8; i++) + *(iv+4+i) = req->iv[i]; + *((__be32 *)(iv+12)) = counter; + + return gcmaes_encrypt(req, req->assoclen - 8, ctx->hash_subkey, iv, + aes_ctx); +} + +static int helper_rfc4106_decrypt(struct aead_request *req) +{ + __be32 counter = cpu_to_be32(1); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + unsigned int i; + + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) + return -EINVAL; + + /* Assuming we are supporting rfc4106 64-bit extended */ + /* sequence numbers We need to have the AAD length */ + /* equal to 16 or 20 bytes */ + + /* IV below built */ + for (i = 0; i < 4; i++) + *(iv+i) = ctx->nonce[i]; + for (i = 0; i < 8; i++) + *(iv+4+i) = req->iv[i]; + *((__be32 *)(iv+12)) = counter; + + return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv, + aes_ctx); } static int rfc4106_encrypt(struct aead_request *req) @@ -1035,6 +1086,46 @@ struct { }; #ifdef CONFIG_X86_64 +static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key, + unsigned int key_len) +{ + struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead); + + return aes_set_key_common(crypto_aead_tfm(aead), + &ctx->aes_key_expanded, key, key_len) ?: + rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); +} + +static int generic_gcmaes_encrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + __be32 counter = cpu_to_be32(1); + + memcpy(iv, req->iv, 12); + *((__be32 *)(iv+12)) = counter; + + return gcmaes_encrypt(req, req->assoclen, ctx->hash_subkey, iv, + aes_ctx); +} + +static int generic_gcmaes_decrypt(struct aead_request *req) +{ + __be32 counter = cpu_to_be32(1); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + + memcpy(iv, req->iv, 12); + *((__be32 *)(iv+12)) = counter; + + return gcmaes_decrypt(req, req->assoclen, ctx->hash_subkey, iv, + aes_ctx); +} + static struct aead_alg aesni_aead_algs[] = { { .setkey = common_rfc4106_set_key, .setauthsize = common_rfc4106_set_authsize, @@ -1069,6 +1160,23 @@ static struct aead_alg aesni_aead_algs[] = { { .cra_ctxsize = sizeof(struct cryptd_aead *), .cra_module = THIS_MODULE, }, +}, { + .setkey = generic_gcmaes_set_key, + .setauthsize = generic_gcmaes_set_authsize, + .encrypt = generic_gcmaes_encrypt, + .decrypt = generic_gcmaes_decrypt, + .ivsize = 12, + .maxauthsize = 16, + .base = { + .cra_name = "gcm(aes)", + .cra_driver_name = "generic-gcm-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct generic_gcmaes_ctx), + .cra_alignmask = AESNI_ALIGN - 1, + .cra_module = THIS_MODULE, + }, } }; #else static struct aead_alg aesni_aead_algs[0]; diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index 2dd3674b5a1e46..458409b7568d10 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -269,19 +269,19 @@ static struct sha512_hash_ctx * LAST */ ctx->error = HASH_CTX_ERROR_INVALID_FLAGS; - return ctx; + goto unlock; } if (ctx->status & HASH_CTX_STS_PROCESSING) { /* Cannot submit to a currently processing job. */ ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING; - return ctx; + goto unlock; } if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) { /* Cannot update a finished job. */ ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED; - return ctx; + goto unlock; } @@ -363,6 +363,7 @@ static struct sha512_hash_ctx } ctx = sha512_ctx_mgr_resubmit(mgr, ctx); +unlock: spin_unlock_irqrestore(&cstate->work_lock, irqflags); return ctx; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 580b60f5ac83ce..637feed9a594ee 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) return ret; } +static struct attribute_group x86_pmu_attr_group; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void) x86_pmu_events_group.attrs = tmp; } + if (x86_pmu.attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs); + if (!WARN_ON(!tmp)) + x86_pmu_attr_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -2224,7 +2234,6 @@ void perf_check_microcode(void) if (x86_pmu.check_microcode) x86_pmu.check_microcode(); } -EXPORT_SYMBOL_GPL(perf_check_microcode); static struct pmu pmu = { .pmu_enable = x86_pmu_enable, @@ -2255,7 +2264,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { - struct cyc2ns_data *data; + struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; @@ -2267,17 +2276,17 @@ void arch_perf_update_userpage(struct perf_event *event, if (!using_native_sched_clock() || !sched_clock_stable()) return; - data = cyc2ns_read_begin(); + cyc2ns_read_begin(&data); - offset = data->cyc2ns_offset + __sched_clock_offset; + offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; - userpg->time_mult = data->cyc2ns_mul; - userpg->time_shift = data->cyc2ns_shift; + userpg->time_mult = data.cyc2ns_mul; + userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* @@ -2289,7 +2298,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->time_zero = offset; } - cyc2ns_read_end(data); + cyc2ns_read_end(); } void diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a6d91d4e37a1f1..de26a370176fe2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3160,6 +3160,19 @@ static int intel_pmu_cpu_prepare(int cpu) return -ENOMEM; } +static void flip_smm_bit(void *data) +{ + unsigned long set = *(unsigned long *)data; + + if (set > 0) { + msr_set_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } else { + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } +} + static void intel_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (!cpuc->shared_regs) return; @@ -3410,12 +3425,10 @@ static void intel_snb_check_microcode(void) int pebs_broken = 0; int cpu; - get_online_cpus(); for_each_online_cpu(cpu) { if ((pebs_broken = intel_snb_pebs_broken(cpu))) break; } - put_online_cpus(); if (pebs_broken == x86_pmu.pebs_broken) return; @@ -3488,7 +3501,9 @@ static bool check_msr(unsigned long msr, u64 mask) static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; + cpus_read_lock(); intel_snb_check_microcode(); + cpus_read_unlock(); } static const struct { int id; char *name; } intel_arch_events_map[] __initconst = { @@ -3595,6 +3610,52 @@ static struct attribute *hsw_events_attrs[] = { NULL }; +static ssize_t freeze_on_smi_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", x86_pmu.attr_freeze_on_smi); +} + +static DEFINE_MUTEX(freeze_on_smi_mutex); + +static ssize_t freeze_on_smi_store(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val > 1) + return -EINVAL; + + mutex_lock(&freeze_on_smi_mutex); + + if (x86_pmu.attr_freeze_on_smi == val) + goto done; + + x86_pmu.attr_freeze_on_smi = val; + + get_online_cpus(); + on_each_cpu(flip_smm_bit, &val, 1); + put_online_cpus(); +done: + mutex_unlock(&freeze_on_smi_mutex); + + return count; +} + +static DEVICE_ATTR_RW(freeze_on_smi); + +static struct attribute *intel_pmu_attrs[] = { + &dev_attr_freeze_on_smi.attr, + NULL, +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -3641,6 +3702,8 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + + x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: @@ -4112,13 +4175,12 @@ static __init int fixup_ht_bug(void) lockup_detector_resume(); - get_online_cpus(); + cpus_read_lock(); - for_each_online_cpu(c) { + for_each_online_cpu(c) free_excl_cntrs(c); - } - put_online_cpus(); + cpus_read_unlock(); pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); return 0; } diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index 8c00dc09a5d2cf..2521f771f2f51b 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -1682,7 +1682,7 @@ static int __init intel_cqm_init(void) * * Also, check that the scales match on all cpus. */ - get_online_cpus(); + cpus_read_lock(); for_each_online_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -1746,14 +1746,14 @@ static int __init intel_cqm_init(void) * Setup the hot cpu notifier once we are sure cqm * is enabled to avoid notifier leak. */ - cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING, - "perf/x86/cqm:starting", - intel_cqm_cpu_starting, NULL); - cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online", - NULL, intel_cqm_cpu_exit); - + cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING, + "perf/x86/cqm:starting", + intel_cqm_cpu_starting, NULL); + cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE, + "perf/x86/cqm:online", + NULL, intel_cqm_cpu_exit); out: - put_online_cpus(); + cpus_read_unlock(); if (ret) { kfree(str); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index be3d36254040f7..53728eea1bedea 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -562,6 +562,9 @@ struct x86_pmu { ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; + unsigned long attr_freeze_on_smi; + struct attribute **attrs; + /* * CPU Hotplug hooks */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 00c88a01301dc2..da181ad1d5f8c3 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -3,6 +3,7 @@ #include #include +#include struct amd_nb_bus_dev_range { u8 bus; @@ -55,7 +56,7 @@ struct threshold_bank { struct threshold_block *blocks; /* initialized to the number of CPUs on the node sharing this bank */ - atomic_t cpus; + refcount_t cpus; }; struct amd_northbridge { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index fba1007139243b..18325dcdb7f12e 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -137,7 +137,6 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) } } -#define hv_get_current_tick(tick) rdmsrl(HV_X64_MSR_TIME_REF_COUNT, tick) #define hv_init_timer(timer, tick) wrmsrl(timer, tick) #define hv_init_timer_config(config, val) wrmsrl(config, val) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 673f9ac50f6d12..d406894cd9a2f5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -137,6 +137,8 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) #define MSR_PEBS_FRONTEND 0x000003f7 @@ -249,9 +251,13 @@ #define HWP_MIN_PERF(x) (x & 0xff) #define HWP_MAX_PERF(x) ((x & 0xff) << 8) #define HWP_DESIRED_PERF(x) ((x & 0xff) << 16) -#define HWP_ENERGY_PERF_PREFERENCE(x) ((x & 0xff) << 24) -#define HWP_ACTIVITY_WINDOW(x) ((x & 0xff3) << 32) -#define HWP_PACKAGE_CONTROL(x) ((x & 0x1) << 42) +#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24) +#define HWP_EPP_PERFORMANCE 0x00 +#define HWP_EPP_BALANCE_PERFORMANCE 0x80 +#define HWP_EPP_BALANCE_POWERSAVE 0xC0 +#define HWP_EPP_POWERSAVE 0xFF +#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32) +#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42) /* IA32_HWP_STATUS */ #define HWP_GUARANTEED_CHANGE(x) (x & 0x1) @@ -474,9 +480,11 @@ #define MSR_MISC_PWR_MGMT 0x000001aa #define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 -#define ENERGY_PERF_BIAS_PERFORMANCE 0 -#define ENERGY_PERF_BIAS_NORMAL 6 -#define ENERGY_PERF_BIAS_POWERSAVE 15 +#define ENERGY_PERF_BIAS_PERFORMANCE 0 +#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4 +#define ENERGY_PERF_BIAS_NORMAL 6 +#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8 +#define ENERGY_PERF_BIAS_POWERSAVE 15 #define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 27e9f9d769b892..2016962103df5b 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -29,11 +29,9 @@ struct cyc2ns_data { u32 cyc2ns_mul; u32 cyc2ns_shift; u64 cyc2ns_offset; - u32 __count; - /* u32 hole */ -}; /* 24 bytes -- do not grow */ +}; /* 16 bytes */ -extern struct cyc2ns_data *cyc2ns_read_begin(void); -extern void cyc2ns_read_end(struct cyc2ns_data *); +extern void cyc2ns_read_begin(struct cyc2ns_data *); +extern void cyc2ns_read_end(void); #endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 00000000000000..01a6de16fb968c --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,16 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include + +#ifdef CONFIG_SMP +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; +#endif + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6ed9ea469b483b..8f6e2f87511b64 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -307,11 +307,15 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); +} + void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -325,6 +329,14 @@ static inline void reset_lazy_tlbstate(void) this_cpu_write(cpu_tlbstate.active_mm, &init_mm); } +static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) +{ + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); +} + +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); + #endif /* SMP */ #ifndef CONFIG_PARAVIRT diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 347bb9f6573723..247880fc29f9be 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1200,28 +1200,6 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); static struct irq_chip ioapic_chip, ioapic_ir_chip; -#ifdef CONFIG_X86_32 -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for_each_ioapic_pin(apic, pin) { - idx = find_irq_entry(apic, pin, mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0))) - return irq_trigger(idx); - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} -#else -static inline int IO_APIC_irq_trigger(int irq) -{ - return 1; -} -#endif - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 6e4a047e4b684b..d00f299f2adae6 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -164,17 +164,48 @@ static void default_deferred_error_interrupt(void) } void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; -static void get_smca_bank_info(unsigned int bank) +static void smca_configure(unsigned int bank, unsigned int cpu) { - unsigned int i, hwid_mcatype, cpu = smp_processor_id(); + unsigned int i, hwid_mcatype; struct smca_hwid *s_hwid; - u32 high, instance_id; + u32 high, low; + u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + /* Set appropriate bits in MCA_CONFIG */ + if (!rdmsr_safe(smca_config, &low, &high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + high |= BIT(0); + + /* + * SMCA sets the Deferred Error Interrupt type per bank. + * + * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us + * if the DeferredIntType bit field is available. + * + * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the + * high portion of the MSR). OS should set this to 0x1 to enable + * APIC based interrupt. First, check that no interrupt has been + * set. + */ + if ((low & BIT(5)) && !((high >> 5) & 0x3)) + high |= BIT(5); + + wrmsr(smca_config, low, high); + } /* Collect bank_info using CPU 0 for now. */ if (cpu) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) { + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -191,7 +222,7 @@ static void get_smca_bank_info(unsigned int bank) smca_get_name(s_hwid->bank_type)); smca_banks[bank].hwid = s_hwid; - smca_banks[bank].id = instance_id; + smca_banks[bank].id = low; smca_banks[bank].sysfs_id = s_hwid->count++; break; } @@ -433,7 +464,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); - u32 smca_low, smca_high, smca_addr; + u32 smca_low, smca_high; struct threshold_block b; int new; @@ -457,51 +488,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, goto set_offset; } - smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - /* - * OS is required to set the MCAX bit to acknowledge that it is - * now using the new MSR ranges and new registers under each - * bank. It also means that the OS will configure deferred - * errors in the new MCx_CONFIG register. If the bit is not set, - * uncorrectable errors will cause a system panic. - * - * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) - */ - smca_high |= BIT(0); - - /* - * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} - * registers with the option of additionally logging to - * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. - * - * This bit is usually set by BIOS to retain the old behavior - * for OSes that don't use the new registers. Linux supports the - * new registers so let's disable that additional logging here. - * - * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high - * portion of the MSR). - */ - smca_high &= ~BIT(2); - - /* - * SMCA sets the Deferred Error Interrupt type per bank. - * - * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us - * if the DeferredIntType bit field is available. - * - * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the - * high portion of the MSR). OS should set this to 0x1 to enable - * APIC based interrupt. First, check that no interrupt has been - * set. - */ - if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3)) - smca_high |= BIT(5); - - wrmsr(smca_addr, smca_low, smca_high); - } - /* Gather LVT offset for thresholding: */ if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) goto out; @@ -530,7 +516,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) - get_smca_bank_info(bank); + smca_configure(bank, cpu); for (block = 0; block < NR_BLOCKS; ++block) { address = get_block_address(cpu, address, low, high, bank, block); @@ -755,37 +741,19 @@ int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) } EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr); -static void -__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) +static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { - u32 msr_status = msr_ops.status(bank); - u32 msr_addr = msr_ops.addr(bank); struct mce m; - u64 status; - - WARN_ON_ONCE(deferred_err && threshold_err); - - if (deferred_err && mce_flags.smca) { - msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); - msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); - } - - rdmsrl(msr_status, status); - - if (!(status & MCI_STATUS_VAL)) - return; mce_setup(&m); m.status = status; + m.misc = misc; m.bank = bank; m.tsc = rdtsc(); - if (threshold_err) - m.misc = misc; - if (m.status & MCI_STATUS_ADDRV) { - rdmsrl(msr_addr, m.addr); + m.addr = addr; /* * Extract [55:] where lsb is the least significant @@ -806,8 +774,6 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) } mce_log(&m); - - wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -832,45 +798,85 @@ asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) exiting_ack_irq(); } -/* APIC interrupt handler for deferred errors */ -static void amd_deferred_error_interrupt(void) +/* + * Returns true if the logged error is deferred. False, otherwise. + */ +static inline bool +_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) { - unsigned int bank; - u32 msr_status; - u64 status; + u64 status, addr = 0; - for (bank = 0; bank < mca_cfg.banks; ++bank) { - msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) - : msr_ops.status(bank); + rdmsrl(msr_stat, status); + if (!(status & MCI_STATUS_VAL)) + return false; - rdmsrl(msr_status, status); + if (status & MCI_STATUS_ADDRV) + rdmsrl(msr_addr, addr); - if (!(status & MCI_STATUS_VAL) || - !(status & MCI_STATUS_DEFERRED)) - continue; + __log_error(bank, status, addr, misc); - __log_error(bank, true, false, 0); - break; - } + wrmsrl(status, 0); + + return status & MCI_STATUS_DEFERRED; } /* - * APIC Interrupt Handler + * We have three scenarios for checking for Deferred errors: + * + * 1) Non-SMCA systems check MCA_STATUS and log error if found. + * 2) SMCA systems check MCA_STATUS. If error is found then log it and also + * clear MCA_DESTAT. + * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and + * log it. */ +static void log_error_deferred(unsigned int bank) +{ + bool defrd; + + defrd = _log_error_bank(bank, msr_ops.status(bank), + msr_ops.addr(bank), 0); + + if (!mce_flags.smca) + return; + + /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ + if (defrd) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return; + } + + /* + * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check + * for a valid error. + */ + _log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank), + MSR_AMD64_SMCA_MCx_DEADDR(bank), 0); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) +{ + unsigned int bank; + + for (bank = 0; bank < mca_cfg.banks; ++bank) + log_error_deferred(bank); +} + +static void log_error_thresholding(unsigned int bank, u64 misc) +{ + _log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc); +} /* - * threshold interrupt handler will service THRESHOLD_APIC_VECTOR. - * the interrupt goes off when error_count reaches threshold_limit. - * the handler will simply log mcelog w/ software defined bank number. + * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt + * goes off when error_count reaches threshold_limit. */ - static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; unsigned int bank, block, cpu = smp_processor_id(); struct thresh_restart tr; - /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; @@ -893,23 +899,18 @@ static void amd_threshold_interrupt(void) (high & MASK_LOCKED_HI)) continue; - /* - * Log the machine check that caused the threshold - * event. - */ - if (high & MASK_OVERFLOW_HI) - goto log; - } - } - return; + if (!(high & MASK_OVERFLOW_HI)) + continue; -log: - __log_error(bank, false, true, ((u64)high << 32) | low); + /* Log the MCE which caused the threshold event. */ + log_error_thresholding(bank, ((u64)high << 32) | low); - /* Reset threshold block after logging error. */ - memset(&tr, 0, sizeof(tr)); - tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; - threshold_restart_bank(&tr); + /* Reset threshold block after logging error. */ + memset(&tr, 0, sizeof(tr)); + tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; + threshold_restart_bank(&tr); + } + } } /* @@ -1202,7 +1203,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; per_cpu(threshold_banks, cpu)[bank] = b; - atomic_inc(&b->cpus); + refcount_inc(&b->cpus); err = __threshold_add_blocks(b); @@ -1225,7 +1226,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) per_cpu(threshold_banks, cpu)[bank] = b; if (is_shared_bank(bank)) { - atomic_set(&b->cpus, 1); + refcount_set(&b->cpus, 1); /* nb is already initialized, see above */ if (nb) { @@ -1289,7 +1290,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) goto free_out; if (is_shared_bank(bank)) { - if (!atomic_dec_and_test(&b->cpus)) { + if (!refcount_dec_and_test(&b->cpus)) { __threshold_remove_blocks(b); per_cpu(threshold_banks, cpu)[bank] = NULL; return; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 2bce84d91c2b6a..c5bb63be4ba1e6 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -807,10 +807,8 @@ void mtrr_save_state(void) if (!mtrr_enabled()) return; - get_online_cpus(); first_cpu = cpumask_first(cpu_online_mask); smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); - put_online_cpus(); } void set_mtrr_aps_delayed_init(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c37bd0f39c708b..ab4f491da2a982 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry, void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - get_online_cpus(); mutex_lock(&text_mutex); __jump_label_transform(entry, type, NULL, 0); mutex_unlock(&text_mutex); - put_online_cpus(); } static enum { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f04479a8f74f55..045e4f993bd2ac 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -863,7 +863,7 @@ static void announce_cpu(int cpu, int apicid) if (cpu == 1) printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state == SYSTEM_BOOTING) { + if (system_state < SYSTEM_RUNNING) { if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 714dfba6a1e713..5270fc0c2df6cc 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,115 +51,34 @@ static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; struct clocksource *art_related_clocksource; -/* - * Use a ring-buffer like data structure, where a writer advances the head by - * writing a new data entry and a reader advances the tail when it observes a - * new entry. - * - * Writers are made to wait on readers until there's space to write a new - * entry. - * - * This means that we can always use an {offset, mul} pair to compute a ns - * value that is 'roughly' in the right direction, even if we're writing a new - * {offset, mul} pair during the clock read. - * - * The down-side is that we can no longer guarantee strict monotonicity anymore - * (assuming the TSC was that to begin with), because while we compute the - * intersection point of the two clock slopes and make sure the time is - * continuous at the point of switching; we can no longer guarantee a reader is - * strictly before or after the switch point. - * - * It does mean a reader no longer needs to disable IRQs in order to avoid - * CPU-Freq updates messing with his times, and similarly an NMI reader will - * no longer run the risk of hitting half-written state. - */ - struct cyc2ns { - struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ - struct cyc2ns_data *head; /* 48 + 8 = 56 */ - struct cyc2ns_data *tail; /* 56 + 8 = 64 */ -}; /* exactly fits one cacheline */ - -static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); - -struct cyc2ns_data *cyc2ns_read_begin(void) -{ - struct cyc2ns_data *head; - - preempt_disable(); - - head = this_cpu_read(cyc2ns.head); - /* - * Ensure we observe the entry when we observe the pointer to it. - * matches the wmb from cyc2ns_write_end(). - */ - smp_read_barrier_depends(); - head->__count++; - barrier(); + struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ + seqcount_t seq; /* 32 + 4 = 36 */ - return head; -} +}; /* fits one cacheline */ -void cyc2ns_read_end(struct cyc2ns_data *head) -{ - barrier(); - /* - * If we're the outer most nested read; update the tail pointer - * when we're done. This notifies possible pending writers - * that we've observed the head pointer and that the other - * entry is now free. - */ - if (!--head->__count) { - /* - * x86-TSO does not reorder writes with older reads; - * therefore once this write becomes visible to another - * cpu, we must be finished reading the cyc2ns_data. - * - * matches with cyc2ns_write_begin(). - */ - this_cpu_write(cyc2ns.tail, head); - } - preempt_enable(); -} +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -/* - * Begin writing a new @data entry for @cpu. - * - * Assumes some sort of write side lock; currently 'provided' by the assumption - * that cpufreq will call its notifiers sequentially. - */ -static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +void cyc2ns_read_begin(struct cyc2ns_data *data) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - struct cyc2ns_data *data = c2n->data; + int seq, idx; - if (data == c2n->head) - data++; + preempt_disable_notrace(); - /* XXX send an IPI to @cpu in order to guarantee a read? */ + do { + seq = this_cpu_read(cyc2ns.seq.sequence); + idx = seq & 1; - /* - * When we observe the tail write from cyc2ns_read_end(), - * the cpu must be done with that entry and its safe - * to start writing to it. - */ - while (c2n->tail == data) - cpu_relax(); + data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); + data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); + data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); - return data; + } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +void cyc2ns_read_end(void) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - - /* - * Ensure the @data writes are visible before we publish the - * entry. Matches the data-depencency in cyc2ns_read_begin(). - */ - smp_wmb(); - - ACCESS_ONCE(c2n->head) = data; + preempt_enable_notrace(); } /* @@ -191,7 +110,6 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_mul = 0; data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; - data->__count = 0; } static void cyc2ns_init(int cpu) @@ -201,51 +119,29 @@ static void cyc2ns_init(int cpu) cyc2ns_data_init(&c2n->data[0]); cyc2ns_data_init(&c2n->data[1]); - c2n->head = c2n->data; - c2n->tail = c2n->data; + seqcount_init(&c2n->seq); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data, *tail; + struct cyc2ns_data data; unsigned long long ns; - /* - * See cyc2ns_read_*() for details; replicated in order to avoid - * an extra few instructions that came with the abstraction. - * Notable, it allows us to only do the __count and tail update - * dance when its actually needed. - */ - - preempt_disable_notrace(); - data = this_cpu_read(cyc2ns.head); - tail = this_cpu_read(cyc2ns.tail); - - if (likely(data == tail)) { - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); - } else { - data->__count++; - - barrier(); - - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + cyc2ns_read_begin(&data); - barrier(); + ns = data.cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); - if (!--data->__count) - this_cpu_write(cyc2ns.tail, data); - } - preempt_enable_notrace(); + cyc2ns_read_end(); return ns; } -static void set_cyc2ns_scale(unsigned long khz, int cpu) +static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { - unsigned long long tsc_now, ns_now; - struct cyc2ns_data *data; + unsigned long long ns_now; + struct cyc2ns_data data; + struct cyc2ns *c2n; unsigned long flags; local_irq_save(flags); @@ -254,9 +150,6 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) if (!khz) goto done; - data = cyc2ns_write_begin(cpu); - - tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -264,7 +157,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz, + clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* @@ -273,20 +166,26 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ - if (data->cyc2ns_shift == 32) { - data->cyc2ns_shift = 31; - data->cyc2ns_mul >>= 1; + if (data.cyc2ns_shift == 32) { + data.cyc2ns_shift = 31; + data.cyc2ns_mul >>= 1; } - data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); + data.cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); + + c2n = per_cpu_ptr(&cyc2ns, cpu); - cyc2ns_write_end(cpu, data); + raw_write_seqcount_latch(&c2n->seq); + c2n->data[0] = data; + raw_write_seqcount_latch(&c2n->seq); + c2n->data[1] = data; done: - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); local_irq_restore(flags); } + /* * Scheduler clock - returns current time in nanosec units. */ @@ -374,6 +273,8 @@ static int __init tsc_setup(char *str) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; + if (!strcmp(str, "unstable")) + mark_tsc_unstable("boot parameter"); return 1; } @@ -986,7 +887,6 @@ void tsc_restore_sched_clock_state(void) } #ifdef CONFIG_CPU_FREQ - /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency * changes. * @@ -1027,7 +927,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc()); } return 0; @@ -1127,6 +1027,15 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) pr_info("Marking TSC unstable due to clocksource watchdog\n"); } +static void tsc_cs_tick_stable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + + if (using_native_sched_clock()) + sched_clock_tick_stable(); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1140,6 +1049,7 @@ static struct clocksource clocksource_tsc = { .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, + .tick_stable = tsc_cs_tick_stable, }; void mark_tsc_unstable(char *reason) @@ -1255,6 +1165,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; + int cpu; /* Don't bother refining TSC on unstable systems */ if (check_tsc_unstable()) @@ -1305,6 +1216,10 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); + /* Update the sched_clock() rate to match the clocksource one */ + for_each_possible_cpu(cpu) + set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; @@ -1350,7 +1265,7 @@ device_initcall(init_tsc_clocksource); void __init tsc_init(void) { - u64 lpj; + u64 lpj, cyc; int cpu; if (!boot_cpu_has(X86_FEATURE_TSC)) { @@ -1390,9 +1305,10 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ + cyc = rdtsc(); for_each_possible_cpu(cpu) { cyc2ns_init(cpu); - set_cyc2ns_scale(tsc_khz, cpu); + set_cyc2ns_scale(tsc_khz, cpu, cyc); } if (tsc_disabled > 0) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0816ab2e8adcae..0f0815c824de7f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3940,6 +3940,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +/* + * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save + * and restore MXCSR. + */ +static size_t __fxstate_size(int nregs) +{ + return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16; +} + +static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt) +{ + bool cr4_osfxsr; + if (ctxt->mode == X86EMUL_MODE_PROT64) + return __fxstate_size(16); + + cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR; + return __fxstate_size(cr4_osfxsr ? 8 : 0); +} + /* * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, * 1) 16 bit mode @@ -3961,7 +3980,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) static int em_fxsave(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; - size_t size; int rc; rc = check_fxsr(ctxt); @@ -3977,68 +3995,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR) - size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]); - else - size = offsetof(struct fxregs_state, xmm_space[0]); - - return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); -} - -static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, - struct fxregs_state *new) -{ - int rc = X86EMUL_CONTINUE; - struct fxregs_state old; - - rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old)); - if (rc != X86EMUL_CONTINUE) - return rc; - - /* - * 64 bit host will restore XMM 8-15, which is not correct on non-64 - * bit guests. Load the current values in order to preserve 64 bit - * XMMs after fxrstor. - */ -#ifdef CONFIG_X86_64 - /* XXX: accessing XMM 8-15 very awkwardly */ - memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16); -#endif - - /* - * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but - * does save and restore MXCSR. - */ - if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) - memcpy(new->xmm_space, old.xmm_space, 8 * 16); - - return rc; + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, + fxstate_size(ctxt)); } static int em_fxrstor(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; + size_t size; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); - if (rc != X86EMUL_CONTINUE) - return rc; + ctxt->ops->get_fpu(ctxt); - if (fx_state.mxcsr >> 16) - return emulate_gp(ctxt, 0); + size = fxstate_size(ctxt); + if (size < __fxstate_size(16)) { + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + if (rc != X86EMUL_CONTINUE) + goto out; + } - ctxt->ops->get_fpu(ctxt); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); + if (rc != X86EMUL_CONTINUE) + goto out; - if (ctxt->mode < X86EMUL_MODE_PROT64) - rc = fxrstor_fixup(ctxt, &fx_state); + if (fx_state.mxcsr >> 16) { + rc = emulate_gp(ctxt, 0); + goto out; + } if (rc == X86EMUL_CONTINUE) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); +out: ctxt->ops->put_fpu(ctxt); return rc; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ba9891ac5c568f..6e3095d1bad4f8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2369,8 +2369,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static int nested_svm_check_permissions(struct vcpu_svm *svm) { - if (!(svm->vcpu.arch.efer & EFER_SVME) - || !is_paging(&svm->vcpu)) { + if (!(svm->vcpu.arch.efer & EFER_SVME) || + !is_paging(&svm->vcpu)) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } @@ -2380,7 +2380,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) return 1; } - return 0; + return 0; } static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9b4b5d6dcd3475..60fa010d3fa139 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2769,7 +2769,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept_ad_bits) { vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_PML; - vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; + vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; } } else vmx->nested.nested_vmx_ept_caps = 0; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6e7bedf69af78d..743e4c6b4529b5 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -237,24 +237,26 @@ static void flush_tlb_func(void *info) return; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) { - local_flush_tlb(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); - } else { - unsigned long addr; - unsigned long nr_pages = - (f->flush_end - f->flush_start) / PAGE_SIZE; - addr = f->flush_start; - while (addr < f->flush_end) { - __flush_tlb_single(addr); - addr += PAGE_SIZE; - } - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); - } - } else + + if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { leave_mm(smp_processor_id()); + return; + } + if (f->flush_end == TLB_FLUSH_ALL) { + local_flush_tlb(); + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); + } else { + unsigned long addr; + unsigned long nr_pages = + (f->flush_end - f->flush_start) / PAGE_SIZE; + addr = f->flush_start; + while (addr < f->flush_end) { + __flush_tlb_single(addr); + addr += PAGE_SIZE; + } + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); + } } void native_flush_tlb_others(const struct cpumask *cpumask, @@ -354,33 +356,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, preempt_enable(); } -void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) -{ - struct mm_struct *mm = vma->vm_mm; - - preempt_disable(); - - if (current->active_mm == mm) { - if (current->mm) { - /* - * Implicit full barrier (INVLPG) that synchronizes - * with switch_mm. - */ - __flush_tlb_one(start); - } else { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); - } - } - - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); - - preempt_enable(); -} - static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -420,6 +395,23 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) } } +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, NULL, 0, TLB_FLUSH_ALL); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index f2a7faf4706eb6..b33093f8452866 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -19,9 +19,6 @@ */ #define SKBDATA %r10 #define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ -#define MAX_BPF_STACK (512 /* from filter.h */ + \ - 32 /* space for rbx,r13,r14,r15 */ + \ - 8 /* space for skb_copy_bits */) #define FUNC(name) \ .globl name; \ @@ -66,7 +63,7 @@ FUNC(sk_load_byte_positive_offset) /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ - lea -MAX_BPF_STACK + 32(%rbp), %rdx;\ + lea 32(%rbp), %rdx;\ FRAME_BEGIN; \ mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ @@ -83,14 +80,14 @@ FUNC(sk_load_byte_positive_offset) bpf_slow_path_word: bpf_slow_path_common(4) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%eax + mov 32(%rbp),%eax bswap %eax ret bpf_slow_path_half: bpf_slow_path_common(2) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%ax + mov 32(%rbp),%ax rol $8,%ax movzwl %ax,%eax ret @@ -98,7 +95,7 @@ bpf_slow_path_half: bpf_slow_path_byte: bpf_slow_path_common(1) js bpf_error - movzbl - MAX_BPF_STACK + 32(%rbp),%eax + movzbl 32(%rbp),%eax ret #define sk_negative_common(SIZE) \ @@ -148,9 +145,10 @@ FUNC(sk_load_byte_negative_offset) bpf_error: # force a return 0 from jit handler xor %eax,%eax - mov - MAX_BPF_STACK(%rbp),%rbx - mov - MAX_BPF_STACK + 8(%rbp),%r13 - mov - MAX_BPF_STACK + 16(%rbp),%r14 - mov - MAX_BPF_STACK + 24(%rbp),%r15 + mov (%rbp),%rbx + mov 8(%rbp),%r13 + mov 16(%rbp),%r14 + mov 24(%rbp),%r15 + add $40, %rbp leaveq ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f58939393eefe2..617eac9c4511a6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -197,17 +197,16 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define STACKSIZE \ - (MAX_BPF_STACK + \ - 32 /* space for rbx, r13, r14, r15 */ + \ +#define AUX_STACK_SPACE \ + (32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 48 +#define PROLOGUE_SIZE 37 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program */ -static void emit_prologue(u8 **pprog) +static void emit_prologue(u8 **pprog, u32 stack_depth) { u8 *prog = *pprog; int cnt = 0; @@ -215,13 +214,17 @@ static void emit_prologue(u8 **pprog) EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ - /* sub rsp, STACKSIZE */ - EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE); + /* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */ + EMIT3_off32(0x48, 0x81, 0xEC, + round_up(stack_depth, 8) + AUX_STACK_SPACE); + + /* sub rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE); /* all classic BPF filters use R6(rbx) save it */ - /* mov qword ptr [rbp-X],rbx */ - EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE); + /* mov qword ptr [rbp+0],rbx */ + EMIT4(0x48, 0x89, 0x5D, 0); /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and @@ -231,12 +234,12 @@ static void emit_prologue(u8 **pprog) * than synthetic ones. Therefore not worth adding complexity. */ - /* mov qword ptr [rbp-X],r13 */ - EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8); - /* mov qword ptr [rbp-X],r14 */ - EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16); - /* mov qword ptr [rbp-X],r15 */ - EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); + /* mov qword ptr [rbp+8],r13 */ + EMIT4(0x4C, 0x89, 0x6D, 8); + /* mov qword ptr [rbp+16],r14 */ + EMIT4(0x4C, 0x89, 0x75, 16); + /* mov qword ptr [rbp+24],r15 */ + EMIT4(0x4C, 0x89, 0x7D, 24); /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls * we need to reset the counter to 0. It's done in two instructions, @@ -246,8 +249,8 @@ static void emit_prologue(u8 **pprog) /* xor eax, eax */ EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp-X], rax */ - EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); + /* mov qword ptr [rbp+32], rax */ + EMIT4(0x48, 0x89, 0x45, 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); *pprog = prog; @@ -289,13 +292,13 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ + EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ #define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ + EMIT2_off32(0x89, 0x85, 36); /* mov dword ptr [rbp + 36], eax */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ @@ -361,7 +364,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int proglen = 0; u8 *prog = temp; - emit_prologue(&prog); + emit_prologue(&prog, bpf_prog->aux->stack_depth); if (seen_ld_abs) emit_load_skb_data_hlen(&prog); @@ -877,7 +880,7 @@ xadd: if (is_imm8(insn->off)) } break; - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: emit_bpf_tail_call(&prog); break; @@ -1036,15 +1039,17 @@ xadd: if (is_imm8(insn->off)) seen_exit = true; /* update cleanup_addr */ ctx->cleanup_addr = proglen; - /* mov rbx, qword ptr [rbp-X] */ - EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE); - /* mov r13, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8); - /* mov r14, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16); - /* mov r15, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24); - + /* mov rbx, qword ptr [rbp+0] */ + EMIT4(0x48, 0x8B, 0x5D, 0); + /* mov r13, qword ptr [rbp+8] */ + EMIT4(0x4C, 0x8B, 0x6D, 8); + /* mov r14, qword ptr [rbp+16] */ + EMIT4(0x4C, 0x8B, 0x75, 16); + /* mov r15, qword ptr [rbp+24] */ + EMIT4(0x4C, 0x8B, 0x7D, 24); + + /* add rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ break; diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index c1bdb9edcae7cb..76595408ff53f2 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -46,7 +46,7 @@ static inline void set_bios_x(void) pcibios_enabled = 1; set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT); if (__supported_pte_mask & _PAGE_NX) - printk(KERN_INFO "PCI : PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n"); + printk(KERN_INFO "PCI: PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n"); } /* diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 42e65fee5673e2..795671593528c6 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -456,12 +456,13 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) */ static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long ns; - ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + cyc2ns_read_begin(&data); + ns = mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); + cyc2ns_read_end(); - cyc2ns_read_end(data); return ns; } @@ -470,12 +471,13 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) */ static inline unsigned long long ns_2_cycles(unsigned long long ns) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long cyc; - cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul; + cyc2ns_read_begin(&data); + cyc = (ns << data.cyc2ns_shift) / data.cyc2ns_mul; + cyc2ns_read_end(); - cyc2ns_read_end(data); return cyc; } diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 1eb6d2fe70d348..982c2533f912bb 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -109,4 +109,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* _XTENSA_SOCKET_H */ diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 803aed4d72216f..9edebbdce0bdfc 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf, blk_mq_run_hw_queues(q, true); } else if (strcmp(op, "start") == 0) { blk_mq_start_stopped_hw_queues(q, true); + } else if (strcmp(op, "kick") == 0) { + blk_mq_kick_requeue_list(q); } else { pr_err("%s: unsupported operation '%s'\n", __func__, op); inval: - pr_err("%s: use either 'run' or 'start'\n", __func__); + pr_err("%s: use 'run', 'start' or 'kick'\n", __func__); return -EINVAL; } return count; @@ -267,6 +269,14 @@ static const char *const rqf_name[] = { }; #undef RQF_NAME +#define RQAF_NAME(name) [REQ_ATOM_##name] = #name +static const char *const rqaf_name[] = { + RQAF_NAME(COMPLETE), + RQAF_NAME(STARTED), + RQAF_NAME(POLL_SLEPT), +}; +#undef RQAF_NAME + int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) { const struct blk_mq_ops *const mq_ops = rq->q->mq_ops; @@ -283,6 +293,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) seq_puts(m, ", .rq_flags="); blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name, ARRAY_SIZE(rqf_name)); + seq_puts(m, ", .atomic_flags="); + blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name)); seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag, rq->internal_tag); if (mq_ops->show_rq) @@ -298,6 +310,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) } EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show); +static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos) + __acquires(&q->requeue_lock) +{ + struct request_queue *q = m->private; + + spin_lock_irq(&q->requeue_lock); + return seq_list_start(&q->requeue_list, *pos); +} + +static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct request_queue *q = m->private; + + return seq_list_next(v, &q->requeue_list, pos); +} + +static void queue_requeue_list_stop(struct seq_file *m, void *v) + __releases(&q->requeue_lock) +{ + struct request_queue *q = m->private; + + spin_unlock_irq(&q->requeue_lock); +} + +static const struct seq_operations queue_requeue_list_seq_ops = { + .start = queue_requeue_list_start, + .next = queue_requeue_list_next, + .stop = queue_requeue_list_stop, + .show = blk_mq_debugfs_rq_show, +}; + static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos) __acquires(&hctx->lock) { @@ -329,6 +372,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = { .show = blk_mq_debugfs_rq_show, }; +struct show_busy_params { + struct seq_file *m; + struct blk_mq_hw_ctx *hctx; +}; + +/* + * Note: the state of a request may change while this function is in progress, + * e.g. due to a concurrent blk_mq_finish_request() call. + */ +static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved) +{ + const struct show_busy_params *params = data; + + if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx && + test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) + __blk_mq_debugfs_rq_show(params->m, + list_entry_rq(&rq->queuelist)); +} + +static int hctx_busy_show(void *data, struct seq_file *m) +{ + struct blk_mq_hw_ctx *hctx = data; + struct show_busy_params params = { .m = m, .hctx = hctx }; + + blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq, + ¶ms); + + return 0; +} + static int hctx_ctx_map_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; @@ -655,6 +728,7 @@ const struct file_operations blk_mq_debugfs_fops = { static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = { {"poll_stat", 0400, queue_poll_stat_show}, + {"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops}, {"state", 0600, queue_state_show, queue_state_write}, {}, }; @@ -663,6 +737,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"state", 0400, hctx_state_show}, {"flags", 0400, hctx_flags_show}, {"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops}, + {"busy", 0400, hctx_busy_show}, {"ctx_map", 0400, hctx_ctx_map_show}, {"tags", 0400, hctx_tags_show}, {"tags_bitmap", 0400, hctx_tags_bitmap_show}, diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 1f5b692526ae1a..c4e2afb9d12db8 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -221,19 +221,71 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); +/* + * Reverse check our software queue for entries that we could potentially + * merge with. Currently includes a hand-wavy stop count of 8, to not spend + * too much time checking for merges. + */ +static bool blk_mq_attempt_merge(struct request_queue *q, + struct blk_mq_ctx *ctx, struct bio *bio) +{ + struct request *rq; + int checked = 8; + + list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { + bool merged = false; + + if (!checked--) + break; + + if (!blk_rq_merge_ok(rq, bio)) + continue; + + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_back_merge(q, rq, bio); + break; + case ELEVATOR_FRONT_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_front_merge(q, rq, bio); + break; + case ELEVATOR_DISCARD_MERGE: + merged = bio_attempt_discard_merge(q, rq, bio); + break; + default: + continue; + } + + if (merged) + ctx->rq_merged++; + return merged; + } + + return false; +} + bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { struct elevator_queue *e = q->elevator; + struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); + bool ret = false; - if (e->type->ops.mq.bio_merge) { - struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); - + if (e && e->type->ops.mq.bio_merge) { blk_mq_put_ctx(ctx); return e->type->ops.mq.bio_merge(hctx, bio); } - return false; + if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) { + /* default per sw-queue merge */ + spin_lock(&ctx->lock); + ret = blk_mq_attempt_merge(q, ctx, bio); + spin_unlock(&ctx->lock); + } + + blk_mq_put_ctx(ctx); + return ret; } bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq) diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index edafb5383b7bbd..b87e5be5db8cfb 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -38,9 +38,7 @@ int blk_mq_sched_init(struct request_queue *q); static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { - struct elevator_queue *e = q->elevator; - - if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio)) + if (blk_queue_nomerges(q) || !bio_mergeable(bio)) return false; return __blk_mq_sched_bio_merge(q, bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index f2224ffd225da8..22438d5036a31e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -753,50 +753,6 @@ static void blk_mq_timeout_work(struct work_struct *work) blk_queue_exit(q); } -/* - * Reverse check our software queue for entries that we could potentially - * merge with. Currently includes a hand-wavy stop count of 8, to not spend - * too much time checking for merges. - */ -static bool blk_mq_attempt_merge(struct request_queue *q, - struct blk_mq_ctx *ctx, struct bio *bio) -{ - struct request *rq; - int checked = 8; - - list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { - bool merged = false; - - if (!checked--) - break; - - if (!blk_rq_merge_ok(rq, bio)) - continue; - - switch (blk_try_merge(rq, bio)) { - case ELEVATOR_BACK_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_back_merge(q, rq, bio); - break; - case ELEVATOR_FRONT_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_front_merge(q, rq, bio); - break; - case ELEVATOR_DISCARD_MERGE: - merged = bio_attempt_discard_merge(q, rq, bio); - break; - default: - continue; - } - - if (merged) - ctx->rq_merged++; - return merged; - } - - return false; -} - struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; @@ -1427,30 +1383,13 @@ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx) !blk_queue_nomerges(hctx->queue); } -static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, - struct request *rq, struct bio *bio) +static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *ctx, + struct request *rq) { - if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) { - blk_mq_bio_to_request(rq, bio); - spin_lock(&ctx->lock); -insert_rq: - __blk_mq_insert_request(hctx, rq, false); - spin_unlock(&ctx->lock); - return false; - } else { - struct request_queue *q = hctx->queue; - - spin_lock(&ctx->lock); - if (!blk_mq_attempt_merge(q, ctx, bio)) { - blk_mq_bio_to_request(rq, bio); - goto insert_rq; - } - - spin_unlock(&ctx->lock); - __blk_mq_finish_request(hctx, ctx, rq); - return true; - } + spin_lock(&ctx->lock); + __blk_mq_insert_request(hctx, rq, false); + spin_unlock(&ctx->lock); } static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq) @@ -1630,11 +1569,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); blk_mq_sched_insert_request(rq, false, true, true, true); - } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) { + } else { blk_mq_put_ctx(data.ctx); + blk_mq_bio_to_request(rq, bio); + blk_mq_queue_io(data.hctx, data.ctx, rq); blk_mq_run_hw_queue(data.hctx, true); - } else - blk_mq_put_ctx(data.ctx); + } return cookie; } diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 0a23dbba2d3018..9b91daefcd9b6d 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -246,6 +246,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, q->bsg_job_size = dd_job_size; q->bsg_job_fn = job_fn; queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q); + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); blk_queue_softirq_done(q, bsg_softirq_done); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); diff --git a/block/bsg.c b/block/bsg.c index 6fd08544d77eaa..40db8ff4c61894 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -750,6 +750,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode, #ifdef BSG_DEBUG unsigned char buf[32]; #endif + + if (!blk_queue_scsi_passthrough(rq)) { + WARN_ONCE(true, "Attempt to register a non-SCSI queue\n"); + return ERR_PTR(-EINVAL); + } + if (!blk_get_queue(rq)) return ERR_PTR(-ENXIO); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index da69b079725fbf..f57bc7d5c48376 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -978,15 +978,6 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) return min_vdisktime; } -static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime) -{ - s64 delta = (s64)(vdisktime - min_vdisktime); - if (delta < 0) - min_vdisktime = vdisktime; - - return min_vdisktime; -} - static void update_min_vdisktime(struct cfq_rb_root *st) { struct cfq_group *cfqg; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index d3a989e718f535..3cd6e12cfc467d 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -141,7 +141,7 @@ int public_key_verify_signature(const struct public_key *pkey, * signature and returns that to us. */ ret = crypto_akcipher_verify(req); - if (ret == -EINPROGRESS) { + if ((ret == -EINPROGRESS) || (ret == -EBUSY)) { wait_for_completion(&compl.completion); ret = compl.err; } diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index 672a94c2c3ffa3..d178650fd524cf 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -381,7 +381,7 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen, } error: - kfree(desc); + kzfree(desc); error_no_desc: crypto_free_shash(tfm); kleave(" = %d", ret); @@ -450,6 +450,6 @@ int verify_pefile_signature(const void *pebuf, unsigned pelen, ret = pefile_digest_pe(pebuf, pelen, &ctx); error: - kfree(ctx.digest); + kzfree(ctx.digest); return ret; } diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index f83de99d7d71cf..56bd612927ab16 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -62,9 +62,6 @@ do_async_gen_syndrome(struct dma_chan *chan, dma_addr_t dma_dest[2]; int src_off = 0; - if (submit->flags & ASYNC_TX_FENCE) - dma_flags |= DMA_PREP_FENCE; - while (src_cnt > 0) { submit->flags = flags_orig; pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags)); @@ -83,6 +80,8 @@ do_async_gen_syndrome(struct dma_chan *chan, if (cb_fn_orig) dma_flags |= DMA_PREP_INTERRUPT; } + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; /* Drivers force forward progress in case they can not provide * a descriptor diff --git a/crypto/drbg.c b/crypto/drbg.c index fa749f47013508..cdb27ac4b2266e 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1767,9 +1767,8 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, break; case -EINPROGRESS: case -EBUSY: - ret = wait_for_completion_interruptible( - &drbg->ctr_completion); - if (!ret && !drbg->ctr_async_err) { + wait_for_completion(&drbg->ctr_completion); + if (!drbg->ctr_async_err) { reinit_completion(&drbg->ctr_completion); break; } diff --git a/crypto/gcm.c b/crypto/gcm.c index b7ad808be3d4ec..3841b5eafa7ee2 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key, err = crypto_skcipher_encrypt(&data->req); if (err == -EINPROGRESS || err == -EBUSY) { - err = wait_for_completion_interruptible( - &data->result.completion); - if (!err) - err = data->result.err; + wait_for_completion(&data->result.completion); + err = data->result.err; } if (err) diff --git a/crypto/hmac.c b/crypto/hmac.c index 72e38c098bb318..92871dc2a63ec6 100644 --- a/crypto/hmac.c +++ b/crypto/hmac.c @@ -16,6 +16,7 @@ * */ +#include #include #include #include @@ -74,8 +75,8 @@ static int hmac_setkey(struct crypto_shash *parent, memcpy(opad, ipad, bs); for (i = 0; i < bs; i++) { - ipad[i] ^= 0x36; - opad[i] ^= 0x5c; + ipad[i] ^= HMAC_IPAD_VALUE; + opad[i] ^= HMAC_OPAD_VALUE; } return crypto_shash_init(shash) ?: diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 9a11f3c2bf983e..0dd6a432d6ca95 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -138,8 +138,6 @@ static int test_aead_cycles(struct aead_request *req, int enc, int blen) int ret = 0; int i; - local_irq_disable(); - /* Warm-up run. */ for (i = 0; i < 4; i++) { if (enc) @@ -169,8 +167,6 @@ static int test_aead_cycles(struct aead_request *req, int enc, int blen) } out: - local_irq_enable(); - if (ret == 0) printk("1 operation in %lu cycles (%d bytes)\n", (cycles + 4) / 8, blen); diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 5a968a78652bd2..7abe6650573950 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -418,11 +418,7 @@ acpi_tb_get_table(struct acpi_table_desc *table_desc, table_desc->validation_count++; if (table_desc->validation_count == 0) { - ACPI_ERROR((AE_INFO, - "Table %p, Validation count is zero after increment\n", - table_desc)); table_desc->validation_count--; - return_ACPI_STATUS(AE_LIMIT); } *out_table = table_desc->pointer; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index d0855c09f32f36..d2c8a9286fa8ea 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -89,14 +89,14 @@ bool ghes_disable; module_param_named(disable, ghes_disable, bool, 0); /* - * All error sources notified with SCI shares one notifier function, - * so they need to be linked and checked one by one. This is applied - * to NMI too. + * All error sources notified with HED (Hardware Error Device) share a + * single notifier callback, so they need to be linked and checked one + * by one. This holds true for NMI too. * * RCU is used for these lists, so ghes_list_mutex is only used for * list changing, not for traversing. */ -static LIST_HEAD(ghes_sci); +static LIST_HEAD(ghes_hed); static DEFINE_MUTEX(ghes_list_mutex); /* @@ -702,14 +702,14 @@ static irqreturn_t ghes_irq_func(int irq, void *data) return IRQ_HANDLED; } -static int ghes_notify_sci(struct notifier_block *this, - unsigned long event, void *data) +static int ghes_notify_hed(struct notifier_block *this, unsigned long event, + void *data) { struct ghes *ghes; int ret = NOTIFY_DONE; rcu_read_lock(); - list_for_each_entry_rcu(ghes, &ghes_sci, list) { + list_for_each_entry_rcu(ghes, &ghes_hed, list) { if (!ghes_proc(ghes)) ret = NOTIFY_OK; } @@ -718,8 +718,8 @@ static int ghes_notify_sci(struct notifier_block *this, return ret; } -static struct notifier_block ghes_notifier_sci = { - .notifier_call = ghes_notify_sci, +static struct notifier_block ghes_notifier_hed = { + .notifier_call = ghes_notify_hed, }; #ifdef CONFIG_HAVE_ACPI_APEI_NMI @@ -966,7 +966,10 @@ static int ghes_probe(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_POLLED: case ACPI_HEST_NOTIFY_EXTERNAL: case ACPI_HEST_NOTIFY_SCI: + case ACPI_HEST_NOTIFY_GSIV: + case ACPI_HEST_NOTIFY_GPIO: break; + case ACPI_HEST_NOTIFY_NMI: if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) { pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n", @@ -1024,13 +1027,17 @@ static int ghes_probe(struct platform_device *ghes_dev) goto err_edac_unreg; } break; + case ACPI_HEST_NOTIFY_SCI: + case ACPI_HEST_NOTIFY_GSIV: + case ACPI_HEST_NOTIFY_GPIO: mutex_lock(&ghes_list_mutex); - if (list_empty(&ghes_sci)) - register_acpi_hed_notifier(&ghes_notifier_sci); - list_add_rcu(&ghes->list, &ghes_sci); + if (list_empty(&ghes_hed)) + register_acpi_hed_notifier(&ghes_notifier_hed); + list_add_rcu(&ghes->list, &ghes_hed); mutex_unlock(&ghes_list_mutex); break; + case ACPI_HEST_NOTIFY_NMI: ghes_nmi_add(ghes); break; @@ -1066,14 +1073,18 @@ static int ghes_remove(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_EXTERNAL: free_irq(ghes->irq, ghes); break; + case ACPI_HEST_NOTIFY_SCI: + case ACPI_HEST_NOTIFY_GSIV: + case ACPI_HEST_NOTIFY_GPIO: mutex_lock(&ghes_list_mutex); list_del_rcu(&ghes->list); - if (list_empty(&ghes_sci)) - unregister_acpi_hed_notifier(&ghes_notifier_sci); + if (list_empty(&ghes_hed)) + unregister_acpi_hed_notifier(&ghes_notifier_hed); mutex_unlock(&ghes_list_mutex); synchronize_rcu(); break; + case ACPI_HEST_NOTIFY_NMI: ghes_nmi_remove(ghes); break; diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index c5fecf97ee2f52..797b28dc7b3410 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -666,14 +666,6 @@ static const struct iommu_ops *iort_iommu_xlate(struct device *dev, int ret = -ENODEV; struct fwnode_handle *iort_fwnode; - /* - * If we already translated the fwspec there - * is nothing left to do, return the iommu_ops. - */ - ops = iort_fwspec_iommu_ops(dev->iommu_fwspec); - if (ops) - return ops; - if (node) { iort_fwnode = iort_get_fwnode(node); if (!iort_fwnode) @@ -735,6 +727,14 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) u32 streamid = 0; int err; + /* + * If we already translated the fwspec there + * is nothing left to do, return the iommu_ops. + */ + ops = iort_fwspec_iommu_ops(dev->iommu_fwspec); + if (ops) + return ops; + if (dev_is_pci(dev)) { struct pci_bus *bus = to_pci_dev(dev)->bus; u32 rid; @@ -782,6 +782,12 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) if (err) ops = ERR_PTR(err); + /* Ignore all other errors apart from EPROBE_DEFER */ + if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) { + dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops)); + ops = NULL; + } + return ops; } diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 25aba9b107dd51..9ad8cdb58743b7 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -113,7 +113,7 @@ struct acpi_button { static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier); static struct acpi_device *lid_device; -static u8 lid_init_state = ACPI_BUTTON_LID_INIT_OPEN; +static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD; static unsigned long lid_report_interval __read_mostly = 500; module_param(lid_report_interval, ulong, 0644); diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 919be0aa257876..240544253ccdf2 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -523,7 +523,7 @@ static int acpi_pci_root_add(struct acpi_device *device, struct acpi_pci_root *root; acpi_handle handle = device->handle; int no_aspm = 0; - bool hotadd = system_state != SYSTEM_BOOTING; + bool hotadd = system_state == SYSTEM_RUNNING; root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL); if (!root) diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 8697a82bd4659b..591d1dd3f04e29 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -268,9 +268,9 @@ static int acpi_processor_start(struct device *dev) return -ENODEV; /* Protect against concurrent CPU hotplug operations */ - get_online_cpus(); + cpu_hotplug_disable(); ret = __acpi_processor_start(device); - put_online_cpus(); + cpu_hotplug_enable(); return ret; } diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index 3de34633f7f9b3..7f9aff4b8d627d 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -909,6 +909,13 @@ static long __acpi_processor_get_throttling(void *data) return pr->throttling.acpi_processor_get_throttling(pr); } +static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct) +{ + if (direct || (is_percpu_thread() && cpu == smp_processor_id())) + return fn(arg); + return work_on_cpu(cpu, fn, arg); +} + static int acpi_processor_get_throttling(struct acpi_processor *pr) { if (!pr) @@ -926,7 +933,7 @@ static int acpi_processor_get_throttling(struct acpi_processor *pr) if (!cpu_online(pr->id)) return -ENODEV; - return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr); + return call_on_cpu(pr->id, __acpi_processor_get_throttling, pr, false); } static int acpi_processor_get_fadt_info(struct acpi_processor *pr) @@ -1076,13 +1083,6 @@ static long acpi_processor_throttling_fn(void *data) arg->target_state, arg->force); } -static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct) -{ - if (direct) - return fn(arg); - return work_on_cpu(cpu, fn, arg); -} - static int __acpi_processor_set_throttling(struct acpi_processor *pr, int state, bool force, bool direct) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index e39ec7b7cb674f..3a10d7573477e7 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1371,8 +1371,8 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) iort_set_dma_mask(dev); iommu = iort_iommu_configure(dev); - if (IS_ERR(iommu)) - return PTR_ERR(iommu); + if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) + return -EPROBE_DEFER; size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1); /* diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 1b5ee1e0e5a307..e414fabf73158d 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -333,14 +333,17 @@ static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj, container_of(bin_attr, struct acpi_table_attr, attr); struct acpi_table_header *table_header = NULL; acpi_status status; + ssize_t rc; status = acpi_get_table(table_attr->name, table_attr->instance, &table_header); if (ACPI_FAILURE(status)) return -ENODEV; - return memory_read_from_buffer(buf, count, &offset, - table_header, table_header->length); + rc = memory_read_from_buffer(buf, count, &offset, table_header, + table_header->length); + acpi_put_table(table_header); + return rc; } static int acpi_table_attr_init(struct kobject *tables_obj, diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index ed6a30cd681a04..940ddbc59aa71f 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * AHCI hardware documentation: * http://www.intel.com/technology/serialata/pdf/rev1_0.pdf diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 2fc52407306c15..1e1c355121e4aa 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -24,7 +24,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * AHCI hardware documentation: * http://www.intel.com/technology/serialata/pdf/rev1_0.pdf @@ -1364,6 +1364,40 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) {} #endif +/* + * On the Acer Aspire Switch Alpha 12, sometimes all SATA ports are detected + * as DUMMY, or detected but eventually get a "link down" and never get up + * again. When this happens, CAP.NP may hold a value of 0x00 or 0x01, and the + * port_map may hold a value of 0x00. + * + * Overriding CAP.NP to 0x02 and the port_map to 0x7 will reveal all 3 ports + * and can significantly reduce the occurrence of the problem. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=189471 + */ +static void acer_sa5_271_workaround(struct ahci_host_priv *hpriv, + struct pci_dev *pdev) +{ + static const struct dmi_system_id sysids[] = { + { + .ident = "Acer Switch Alpha 12", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271") + }, + }, + { } + }; + + if (dmi_check_system(sysids)) { + dev_info(&pdev->dev, "enabling Acer Switch Alpha 12 workaround\n"); + if ((hpriv->saved_cap & 0xC734FF00) == 0xC734FF00) { + hpriv->port_map = 0x7; + hpriv->cap = 0xC734FF02; + } + } +} + #ifdef CONFIG_ARM64 /* * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently. @@ -1636,6 +1670,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) "online status unreliable, applying workaround\n"); } + + /* Acer SA5-271 workaround modifies private_data */ + acer_sa5_271_workaround(hpriv, pdev); + /* CAP.NP sometimes indicate the index of the last enabled * port, at other times, that of the last possible port, so * determining the maximum port number requires looking at diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 5db6ab26164310..30f67a1a4f54c4 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -24,7 +24,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * AHCI hardware documentation: * http://www.intel.com/technology/serialata/pdf/rev1_0.pdf diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index ffbe625e6fd273..8401c3b5be9213 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -33,7 +33,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available at http://developer.intel.com/ * diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 3159f9e66d8f06..6154f0e2b81a9e 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -24,7 +24,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * AHCI hardware documentation: * http://www.intel.com/technology/serialata/pdf/rev1_0.pdf diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index aaa761b9081cc0..cd2eab6aa92ea2 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -514,8 +514,9 @@ int ahci_platform_init_host(struct platform_device *pdev, irq = platform_get_irq(pdev, 0); if (irq <= 0) { - dev_err(dev, "no irq\n"); - return -EINVAL; + if (irq != -EPROBE_DEFER) + dev_err(dev, "no irq\n"); + return irq; } hpriv->irq = irq; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 2d83b8c7596567..b82d6bb88d275d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ and * http://www.sata-io.org/ @@ -6800,7 +6800,7 @@ static int __init ata_parse_force_one(char **cur, } force_ent->port = simple_strtoul(id, &endp, 10); - if (p == endp || *endp != '\0') { + if (id == endp || *endp != '\0') { *reason = "invalid port/link"; return -EINVAL; } diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index ef68232b52228f..7e33e200aae55b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ and * http://www.sata-io.org/ diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 49ba9834c71536..b0866f040d1fcd 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from * - http://www.t10.org/ @@ -3398,9 +3398,10 @@ static size_t ata_format_dsm_trim_descr(struct scsi_cmnd *cmd, u32 trmax, * * Translate a SCSI WRITE SAME command to be either a DSM TRIM command or * an SCT Write Same command. - * Based on WRITE SAME has the UNMAP flag - * When set translate to DSM TRIM - * When clear translate to SCT Write Same + * Based on WRITE SAME has the UNMAP flag: + * + * - When set translate to DSM TRIM + * - When clear translate to SCT Write Same */ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) { diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 274d6d7193d7ca..cc2f2e35f4c2e4 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ and * http://www.sata-io.org/ @@ -716,24 +716,10 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); - if (PageHighMem(page)) { - unsigned long flags; - - /* FIXME: use a bounce buffer */ - local_irq_save(flags); - buf = kmap_atomic(page); - - /* do the actual data transfer */ - ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, - do_write); - - kunmap_atomic(buf); - local_irq_restore(flags); - } else { - buf = page_address(page); - ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, - do_write); - } + /* do the actual data transfer */ + buf = kmap_atomic(page); + ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, do_write); + kunmap_atomic(buf); if (!do_write && !PageSlab(page)) flush_dcache_page(page); @@ -861,24 +847,10 @@ static int __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes) DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); - if (PageHighMem(page)) { - unsigned long flags; - - /* FIXME: use bounce buffer */ - local_irq_save(flags); - buf = kmap_atomic(page); - - /* do the actual data transfer */ - consumed = ap->ops->sff_data_xfer(qc, buf + offset, - count, rw); - - kunmap_atomic(buf); - local_irq_restore(flags); - } else { - buf = page_address(page); - consumed = ap->ops->sff_data_xfer(qc, buf + offset, - count, rw); - } + /* do the actual data transfer */ + buf = kmap_atomic(page); + consumed = ap->ops->sff_data_xfer(qc, buf + offset, count, rw); + kunmap_atomic(buf); bytes -= min(bytes, consumed); qc->curbytes += count; diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 120fce0befd3a5..5afe35baf61b78 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -21,7 +21,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * */ diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c index 9c5780a7e1b925..0e55a8da274878 100644 --- a/drivers/ata/pata_bf54x.c +++ b/drivers/ata/pata_bf54x.c @@ -1597,8 +1597,6 @@ static int bfin_atapi_probe(struct platform_device *pdev) return -ENODEV; } - platform_set_drvdata(pdev, host); - return 0; } diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index bf1b910c5d691b..0a550190955ad2 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -944,7 +944,6 @@ static int ep93xx_pata_probe(struct platform_device *pdev) goto err_rel_gpio; } - platform_set_drvdata(pdev, drv_data); drv_data->pdev = pdev; drv_data->ide_base = ide_base; drv_data->udma_in_phys = mem_res->start + IDEUDMADATAIN; diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c index d9ef9e27622545..82bfd51692f316 100644 --- a/drivers/ata/pata_pdc2027x.c +++ b/drivers/ata/pata_pdc2027x.c @@ -17,7 +17,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware information only available under NDA. * diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index c8b6a780a29050..653b9a0bf72745 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -148,8 +148,6 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) if (!ah) return -ENOMEM; - platform_set_drvdata(pdev, ah); - info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c index 431c7de30ce64e..50801c40b02952 100644 --- a/drivers/ata/pata_samsung_cf.c +++ b/drivers/ata/pata_samsung_cf.c @@ -582,8 +582,6 @@ static int __init pata_s3c_probe(struct platform_device *pdev) /* Set endianness and enable the interface */ pata_s3c_hwinit(info, pdata); - platform_set_drvdata(pdev, host); - ret = ata_host_activate(host, info->irq, info->irq ? pata_s3c_irq : NULL, 0, &pata_s3c_sht); diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index 64d682c6ee57e2..f1e873a37465e4 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -21,7 +21,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * * Supports ATA disks in single-packet ADMA mode. diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index e0939bd5ea7352..ce128d5a6ded21 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -1285,7 +1285,6 @@ static int sata_dwc_probe(struct platform_device *ofdev) if (err) dev_err(&ofdev->dev, "failed to activate host"); - dev_set_drvdata(&ofdev->dev, host); return 0; error_out: diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 01734d54c69cdc..95bf3abda6f656 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1523,8 +1523,6 @@ static int sata_fsl_probe(struct platform_device *ofdev) ata_host_activate(host, irq, sata_fsl_interrupt, SATA_FSL_IRQ_FLAG, &sata_fsl_sht); - platform_set_drvdata(ofdev, host); - host_priv->intr_coalescing.show = fsl_sata_intr_coalescing_show; host_priv->intr_coalescing.store = fsl_sata_intr_coalescing_store; sysfs_attr_init(&host_priv->intr_coalescing.attr); diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index b66bcda88320fe..3b2246dded74fb 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4067,7 +4067,6 @@ static int mv_platform_probe(struct platform_device *pdev) struct ata_host *host; struct mv_host_priv *hpriv; struct resource *res; - void __iomem *mmio; int n_ports = 0, irq = 0; int rc; int port; @@ -4086,9 +4085,8 @@ static int mv_platform_probe(struct platform_device *pdev) * Get the register base first */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mmio = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mmio)) - return PTR_ERR(mmio); + if (res == NULL) + return -EINVAL; /* allocate host */ if (pdev->dev.of_node) { @@ -4132,7 +4130,12 @@ static int mv_platform_probe(struct platform_device *pdev) hpriv->board_idx = chip_soc; host->iomap = NULL; - hpriv->base = mmio - SATAHC0_REG_BASE; + hpriv->base = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!hpriv->base) + return -ENOMEM; + + hpriv->base -= SATAHC0_REG_BASE; hpriv->clk = clk_get(&pdev->dev, NULL); if (IS_ERR(hpriv->clk)) diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 734f563b8d37b0..8c683ddd0f5802 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -21,7 +21,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * No hardware documentation available outside of NVIDIA. * This driver programs the NVIDIA SATA controller in a similar diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 0fa211e2831cda..d032bf657f709a 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware information only available under NDA. * diff --git a/drivers/ata/sata_promise.h b/drivers/ata/sata_promise.h index 00d6000e546ff5..61633ef5ed725d 100644 --- a/drivers/ata/sata_promise.h +++ b/drivers/ata/sata_promise.h @@ -20,7 +20,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * */ diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index af987a4f33d190..1fe941688e95d6 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -23,7 +23,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * */ diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 5d38245a7a73a7..b7939a2c1fab53 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -890,7 +890,10 @@ static int sata_rcar_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to get access to sata clock\n"); return PTR_ERR(priv->clk); } - clk_prepare_enable(priv->clk); + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; host = ata_host_alloc(&pdev->dev, 1); if (!host) { @@ -970,8 +973,11 @@ static int sata_rcar_resume(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct sata_rcar_priv *priv = host->private_data; void __iomem *base = priv->base; + int ret; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; /* ack and mask */ iowrite32(0, base + SATAINTSTAT_REG); @@ -988,8 +994,11 @@ static int sata_rcar_restore(struct device *dev) { struct ata_host *host = dev_get_drvdata(dev); struct sata_rcar_priv *priv = host->private_data; + int ret; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; sata_rcar_setup_port(host); diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index 29bcff086bcedd..ed76f070d21e4e 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Documentation for SiI 3112: * http://gkernel.sourceforge.net/specs/sii/3112A_SiI-DS-0095-B2.pdf.bz2 diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c index d1637ac40a73a8..30f4f35f36d466 100644 --- a/drivers/ata/sata_sis.c +++ b/drivers/ata/sata_sis.c @@ -24,7 +24,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available under NDA. * diff --git a/drivers/ata/sata_svw.c b/drivers/ata/sata_svw.c index ff614be55d0f58..0fd6ac7e57ba11 100644 --- a/drivers/ata/sata_svw.c +++ b/drivers/ata/sata_svw.c @@ -30,7 +30,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available under NDA. * diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 48301cb3a3165a..405e606a234d1e 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -24,7 +24,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available under NDA. * diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c index 08f98c3ed5c8e2..4f6e8d8156de55 100644 --- a/drivers/ata/sata_uli.c +++ b/drivers/ata/sata_uli.c @@ -18,7 +18,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available under NDA. * diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c index f3f538eec7b3bb..22e96fc77d09ba 100644 --- a/drivers/ata/sata_via.c +++ b/drivers/ata/sata_via.c @@ -25,7 +25,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available under NDA. * diff --git a/drivers/ata/sata_vsc.c b/drivers/ata/sata_vsc.c index 183eb52085df14..9648127cca70c9 100644 --- a/drivers/ata/sata_vsc.c +++ b/drivers/ata/sata_vsc.c @@ -26,7 +26,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Vitesse hardware documentation presumably available under NDA. * Intel 31244 (same hardware interface) documentation presumably diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index e0c014c2356ffb..7a8b8fb2f572c4 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1345,14 +1345,11 @@ static inline void input_state_falling(struct logical_input *input) static void panel_process_inputs(void) { - struct list_head *item; struct logical_input *input; keypressed = 0; inputs_stable = 1; - list_for_each(item, &logical_inputs) { - input = list_entry(item, struct logical_input, list); - + list_for_each_entry(input, &logical_inputs, list) { switch (input->state) { case INPUT_ST_LOW: if ((phys_curr & input->mask) != input->value) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 6470eb8088f4f4..f945f2f0ee06cf 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -648,10 +648,7 @@ static void remove_probe_files(struct bus_type *bus) static ssize_t uevent_store(struct device_driver *drv, const char *buf, size_t count) { - enum kobject_action action; - - if (kobject_action_type(buf, count, &action) == 0) - kobject_uevent(&drv->p->kobj, action); + kobject_synth_uevent(&drv->p->kobj, buf, count); return count; } static DRIVER_ATTR_WO(uevent); @@ -868,10 +865,7 @@ static void klist_devices_put(struct klist_node *n) static ssize_t bus_uevent_store(struct bus_type *bus, const char *buf, size_t count) { - enum kobject_action action; - - if (kobject_action_type(buf, count, &action) == 0) - kobject_uevent(&bus->p->subsys.kobj, action); + kobject_synth_uevent(&bus->p->subsys.kobj, buf, count); return count; } static BUS_ATTR(uevent, S_IWUSR, NULL, bus_uevent_store); diff --git a/drivers/base/core.c b/drivers/base/core.c index bbecaf9293bed4..6564339d7f590c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -981,12 +981,9 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, static ssize_t uevent_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - enum kobject_action action; + if (kobject_synth_uevent(&dev->kobj, buf, count)) + dev_err(dev, "uevent: failed to send synthetic uevent\n"); - if (kobject_action_type(buf, count, &action) == 0) - kobject_uevent(&dev->kobj, action); - else - dev_err(dev, "uevent: unknown action-string\n"); return count; } static DEVICE_ATTR_RW(uevent); diff --git a/drivers/base/node.c b/drivers/base/node.c index d97914c7f304a6..73d39bc58c42d6 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -373,7 +373,7 @@ static int __ref get_nid_for_pfn(unsigned long pfn) if (!pfn_valid_within(pfn)) return -1; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT - if (system_state == SYSTEM_BOOTING) + if (system_state < SYSTEM_RUNNING) return early_pfn_to_nid(pfn); #endif return pfn_to_nid(pfn); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index a102152301c832..97332d094fe23a 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -866,7 +866,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct platform_device *pdev = to_platform_device(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; if (count > PATH_MAX) return -EINVAL; @@ -879,12 +879,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -895,8 +898,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct platform_device *pdev = to_platform_device(dev); + ssize_t len; - return sprintf(buf, "%s\n", pdev->driver_override); + device_lock(dev); + len = sprintf(buf, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index cd375503f7b0d8..3761066fe89ddc 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1956,6 +1956,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, disk->queue->cmd_size = sizeof(struct scsi_request); disk->queue->request_fn = do_cciss_request; disk->queue->queue_lock = &h->lock; + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, disk->queue); if (blk_init_allocated_queue(disk->queue) < 0) goto cleanup_queue; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9a7bb2c2944772..c5e52f66d3d44b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -400,6 +400,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) unsigned long size = blk_rq_bytes(req); struct bio *bio; u32 type; + u32 nbd_cmd_flags = 0; u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; @@ -429,6 +430,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return -EIO; } + if (req->cmd_flags & REQ_FUA) + nbd_cmd_flags |= NBD_CMD_FLAG_FUA; + /* We did a partial send previously, and we at least sent the whole * request struct, so just go and send the rest of the pages in the * request. @@ -442,7 +446,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) } cmd->index = index; cmd->cookie = nsock->cookie; - request.type = htonl(type); + request.type = htonl(type | nbd_cmd_flags); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); @@ -965,8 +969,12 @@ static void nbd_parse_flags(struct nbd_device *nbd) set_disk_ro(nbd->disk, false); if (config->flags & NBD_FLAG_SEND_TRIM) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue); - if (config->flags & NBD_FLAG_SEND_FLUSH) - blk_queue_write_cache(nbd->disk->queue, true, false); + if (config->flags & NBD_FLAG_SEND_FLUSH) { + if (config->flags & NBD_FLAG_SEND_FUA) + blk_queue_write_cache(nbd->disk->queue, true, true); + else + blk_queue_write_cache(nbd->disk->queue, true, false); + } else blk_queue_write_cache(nbd->disk->queue, false, false); } @@ -1309,6 +1317,8 @@ static int nbd_dbg_flags_show(struct seq_file *s, void *unused) seq_puts(s, "NBD_FLAG_READ_ONLY\n"); if (flags & NBD_FLAG_SEND_FLUSH) seq_puts(s, "NBD_FLAG_SEND_FLUSH\n"); + if (flags & NBD_FLAG_SEND_FUA) + seq_puts(s, "NBD_FLAG_SEND_FUA\n"); if (flags & NBD_FLAG_SEND_TRIM) seq_puts(s, "NBD_FLAG_SEND_TRIM\n"); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 205b865ebeb9f1..42e3c880a8a5d7 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2583,6 +2583,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) bdev = bdget(dev); if (!bdev) return -ENOMEM; + if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) { + WARN_ONCE(true, "Attempt to register a non-SCSI queue\n"); + bdput(bdev); + return -EINVAL; + } ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL); if (ret) return ret; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 454bf9c34882f3..c16f74547804cc 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4023,6 +4023,7 @@ static void rbd_queue_workfn(struct work_struct *work) switch (req_op(rq)) { case REQ_OP_DISCARD: + case REQ_OP_WRITE_ZEROES: op_type = OBJ_OP_DISCARD; break; case REQ_OP_WRITE: @@ -4420,6 +4421,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) q->limits.discard_granularity = segment_size; q->limits.discard_alignment = segment_size; blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE); + blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE); if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig index 737d93ef27c5da..35952a94875e82 100644 --- a/drivers/bluetooth/Kconfig +++ b/drivers/bluetooth/Kconfig @@ -97,6 +97,7 @@ config BT_HCIUART_NOKIA depends on BT_HCIUART depends on BT_HCIUART_SERDEV depends on PM + select BT_HCIUART_H4 help Nokia H4+ is serial protocol for communication between Bluetooth device and host. This protocol is required for Bluetooth devices @@ -131,7 +132,7 @@ config BT_HCIUART_ATH3K config BT_HCIUART_LL bool "HCILL protocol support" - depends on BT_HCIUART + depends on BT_HCIUART_SERDEV help HCILL (HCI Low Level) is a serial protocol for communication between Bluetooth device and host. This protocol is required for diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index fce1548557181e..d32e109bd5cb51 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -575,3 +575,5 @@ MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_FIRMWARE("intel/ibt-11-5.sfi"); MODULE_FIRMWARE("intel/ibt-11-5.ddc"); +MODULE_FIRMWARE("intel/ibt-12-16.sfi"); +MODULE_FIRMWARE("intel/ibt-12-16.ddc"); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 7fa373b428f8dc..278e8118615036 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -336,6 +336,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_NEW }, { USB_DEVICE(0x8087, 0x0aa7), .driver_info = BTUSB_INTEL }, + { USB_DEVICE(0x8087, 0x0aaa), .driver_info = BTUSB_INTEL_NEW }, /* Other Intel Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01), @@ -2036,6 +2037,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) switch (ver.hw_variant) { case 0x0b: /* SfP */ case 0x0c: /* WsP */ + case 0x11: /* JfP */ case 0x12: /* ThP */ break; default: @@ -2138,6 +2140,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * Currently the supported hardware variants are: * 11 (0x0b) for iBT3.0 (LnP/SfP) * 12 (0x0c) for iBT3.5 (WsP) + * 17 (0x11) for iBT3.5 (JfP) + * 18 (0x12) for iBT3.5 (ThP) */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi", le16_to_cpu(ver.hw_variant), diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c index b6bb58c41df5b7..85a3978b064fb8 100644 --- a/drivers/bluetooth/btwilink.c +++ b/drivers/bluetooth/btwilink.c @@ -262,7 +262,6 @@ static int ti_st_send_frame(struct hci_dev *hdev, struct sk_buff *skb) pkt_type = hci_skb_pkt_type(skb); len = hst->st_write(skb); if (len < 0) { - kfree_skb(skb); BT_ERR("ST write failed (%ld)", len); /* Try Again, would only fail if UART has gone bad */ return -EAGAIN; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 2edd30556956d8..8397b716fa654e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -114,8 +114,12 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu) struct sk_buff *skb = hu->tx_skb; if (!skb) { + read_lock(&hu->proto_lock); + if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) skb = hu->proto->dequeue(hu); + + read_unlock(&hu->proto_lock); } else { hu->tx_skb = NULL; } @@ -125,18 +129,23 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu) int hci_uart_tx_wakeup(struct hci_uart *hu) { + read_lock(&hu->proto_lock); + if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) - return 0; + goto no_schedule; if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) { set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); - return 0; + goto no_schedule; } BT_DBG(""); schedule_work(&hu->write_work); +no_schedule: + read_unlock(&hu->proto_lock); + return 0; } EXPORT_SYMBOL_GPL(hci_uart_tx_wakeup); @@ -237,9 +246,13 @@ static int hci_uart_flush(struct hci_dev *hdev) tty_ldisc_flush(tty); tty_driver_flush_buffer(tty); + read_lock(&hu->proto_lock); + if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) hu->proto->flush(hu); + read_unlock(&hu->proto_lock); + return 0; } @@ -261,10 +274,15 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s: type %d len %d", hdev->name, hci_skb_pkt_type(skb), skb->len); - if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) + read_lock(&hu->proto_lock); + + if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) { + read_unlock(&hu->proto_lock); return -EUNATCH; + } hu->proto->enqueue(hu, skb); + read_unlock(&hu->proto_lock); hci_uart_tx_wakeup(hu); @@ -460,6 +478,8 @@ static int hci_uart_tty_open(struct tty_struct *tty) INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); + rwlock_init(&hu->proto_lock); + /* Flush any pending characters in the driver */ tty_driver_flush_buffer(tty); @@ -475,6 +495,7 @@ static void hci_uart_tty_close(struct tty_struct *tty) { struct hci_uart *hu = tty->disc_data; struct hci_dev *hdev; + unsigned long flags; BT_DBG("tty %p", tty); @@ -490,7 +511,11 @@ static void hci_uart_tty_close(struct tty_struct *tty) cancel_work_sync(&hu->write_work); - if (test_and_clear_bit(HCI_UART_PROTO_READY, &hu->flags)) { + if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) { + write_lock_irqsave(&hu->proto_lock, flags); + clear_bit(HCI_UART_PROTO_READY, &hu->flags); + write_unlock_irqrestore(&hu->proto_lock, flags); + if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) hci_unregister_dev(hdev); @@ -549,13 +574,18 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, if (!hu || tty != hu->tty) return; - if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) + read_lock(&hu->proto_lock); + + if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) { + read_unlock(&hu->proto_lock); return; + } /* It does not need a lock here as it is already protected by a mutex in * tty caller */ hu->proto->recv(hu, data, count); + read_unlock(&hu->proto_lock); if (hu->hdev) hu->hdev->stat.byte_rx += count; diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index adc444f309a3cf..200288c87fc431 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -624,6 +624,7 @@ static int download_firmware(struct ll_device *lldev) skb = __hci_cmd_sync(lldev->hu.hdev, cmd->opcode, cmd->plen, &cmd->speed, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { bt_dev_err(lldev->hu.hdev, "send command failed\n"); + err = PTR_ERR(skb); goto out_rel_fw; } kfree_skb(skb); diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index 2b05e557fad01e..c6e9e1cf63f886 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -87,6 +87,7 @@ struct hci_uart { struct work_struct write_work; const struct hci_uart_proto *proto; + rwlock_t proto_lock; /* Stop work for proto close */ void *priv; struct sk_buff *tx_skb; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 76c952fd9ab905..ff19cfc587f04a 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2178,6 +2178,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, if (!q) return -ENXIO; + if (!blk_queue_scsi_passthrough(q)) { + WARN_ONCE(true, + "Attempt read CDDA info through a non-SCSI queue\n"); + return -EINVAL; + } + cdi->last_sense = 0; while (nframes) { diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 31adbebf812edb..2af70014ee5a80 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -539,15 +539,6 @@ config HANGCHECK_TIMER out to lunch past a certain margin. It can reboot the system or merely print a warning. -config MMTIMER - tristate "MMTIMER Memory mapped RTC for SGI Altix" - depends on IA64_GENERIC || IA64_SGI_SN2 - depends on POSIX_TIMERS - default y - help - The mmtimer device allows direct userspace access to the - Altix system timer. - config UV_MMTIMER tristate "UV_MMTIMER Memory mapped RTC for SGI UV" depends on X86_UV diff --git a/drivers/char/Makefile b/drivers/char/Makefile index 6e6c244a66a02c..53e33720818c0a 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o obj-$(CONFIG_RAW_DRIVER) += raw.o obj-$(CONFIG_SGI_SNSC) += snsc.o snsc_event.o obj-$(CONFIG_MSPEC) += mspec.o -obj-$(CONFIG_MMTIMER) += mmtimer.o obj-$(CONFIG_UV_MMTIMER) += uv_mmtimer.o obj-$(CONFIG_IBM_BSR) += bsr.o obj-$(CONFIG_SGI_MBCS) += mbcs.o diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c index 37a58d78aab317..38b719017186ef 100644 --- a/drivers/char/hw_random/omap3-rom-rng.c +++ b/drivers/char/hw_random/omap3-rom-rng.c @@ -53,7 +53,10 @@ static int omap3_rom_rng_get_random(void *buf, unsigned int count) cancel_delayed_work_sync(&idle_work); if (rng_idle) { - clk_prepare_enable(rng_clk); + r = clk_prepare_enable(rng_clk); + if (r) + return r; + r = omap3_rom_rng_call(0, 0, RNG_GEN_PRNG_HW_INIT); if (r != 0) { clk_disable_unprepare(rng_clk); @@ -88,6 +91,8 @@ static struct hwrng omap3_rom_rng_ops = { static int omap3_rom_rng_probe(struct platform_device *pdev) { + int ret = 0; + pr_info("initializing\n"); omap3_rom_rng_call = pdev->dev.platform_data; @@ -104,7 +109,9 @@ static int omap3_rom_rng_probe(struct platform_device *pdev) } /* Leave the RNG in reset state. */ - clk_prepare_enable(rng_clk); + ret = clk_prepare_enable(rng_clk); + if (ret) + return ret; omap3_rom_rng_idle(0); return hwrng_register(&omap3_rom_rng_ops); diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c index a0faa5f05debae..03ff5483d8654b 100644 --- a/drivers/char/hw_random/timeriomem-rng.c +++ b/drivers/char/hw_random/timeriomem-rng.c @@ -151,8 +151,15 @@ static int timeriomem_rng_probe(struct platform_device *pdev) dev_err(&pdev->dev, "missing period\n"); return -EINVAL; } + + if (!of_property_read_u32(pdev->dev.of_node, + "quality", &i)) + priv->rng_ops.quality = i; + else + priv->rng_ops.quality = 0; } else { period = pdata->period; + priv->rng_ops.quality = pdata->quality; } priv->period = ns_to_ktime(period * NSEC_PER_USEC); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 0b22a9be502915..1d4fd846e45748 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -408,6 +408,7 @@ static void start_event_fetch(struct ssif_info *ssif_info, unsigned long *flags) msg = ipmi_alloc_smi_msg(); if (!msg) { ssif_info->ssif_state = SSIF_NORMAL; + ipmi_ssif_unlock_cond(ssif_info, flags); return; } @@ -430,6 +431,7 @@ static void start_recv_msg_fetch(struct ssif_info *ssif_info, msg = ipmi_alloc_smi_msg(); if (!msg) { ssif_info->ssif_state = SSIF_NORMAL; + ipmi_ssif_unlock_cond(ssif_info, flags); return; } @@ -1417,8 +1419,7 @@ static int find_slave_address(struct i2c_client *client, int slave_addr) list_for_each_entry(info, &ssif_infos, link) { if (info->binfo.addr != client->addr) continue; - if (info->adapter_name && client->adapter->name && - strcmp_nospace(info->adapter_name, + if (info->adapter_name && strcmp_nospace(info->adapter_name, client->adapter->name)) continue; if (info->slave_addr) { diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index d165af8abe36c7..4161d9961a2416 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -1163,10 +1163,11 @@ static int wdog_reboot_handler(struct notifier_block *this, ipmi_watchdog_state = WDOG_TIMEOUT_NONE; ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB); } else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) { - /* Set a long timer to let the reboot happens, but - reboot if it hangs, but only if the watchdog + /* Set a long timer to let the reboot happen or + reset if it hangs, but only if the watchdog timer was already running. */ - timeout = 120; + if (timeout < 120) + timeout = 120; pretimeout = 0; ipmi_watchdog_state = WDOG_TIMEOUT_RESET; ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB); diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c deleted file mode 100644 index 0e7fcb04f01e74..00000000000000 --- a/drivers/char/mmtimer.c +++ /dev/null @@ -1,858 +0,0 @@ -/* - * Timer device implementation for SGI SN platforms. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2001-2006 Silicon Graphics, Inc. All rights reserved. - * - * This driver exports an API that should be supportable by any HPET or IA-PC - * multimedia timer. The code below is currently specific to the SGI Altix - * SHub RTC, however. - * - * 11/01/01 - jbarnes - initial revision - * 9/10/04 - Christoph Lameter - remove interrupt support for kernel inclusion - * 10/1/04 - Christoph Lameter - provide posix clock CLOCK_SGI_CYCLE - * 10/13/04 - Christoph Lameter, Dimitri Sivanich - provide timer interrupt - * support via the posix timer interface - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include - -MODULE_AUTHOR("Jesse Barnes "); -MODULE_DESCRIPTION("SGI Altix RTC Timer"); -MODULE_LICENSE("GPL"); - -/* name of the device, usually in /dev */ -#define MMTIMER_NAME "mmtimer" -#define MMTIMER_DESC "SGI Altix RTC Timer" -#define MMTIMER_VERSION "2.1" - -#define RTC_BITS 55 /* 55 bits for this implementation */ - -static struct k_clock sgi_clock; - -extern unsigned long sn_rtc_cycles_per_second; - -#define RTC_COUNTER_ADDR ((long *)LOCAL_MMR_ADDR(SH_RTC)) - -#define rtc_time() (*RTC_COUNTER_ADDR) - -static DEFINE_MUTEX(mmtimer_mutex); -static long mmtimer_ioctl(struct file *file, unsigned int cmd, - unsigned long arg); -static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma); - -/* - * Period in femtoseconds (10^-15 s) - */ -static unsigned long mmtimer_femtoperiod = 0; - -static const struct file_operations mmtimer_fops = { - .owner = THIS_MODULE, - .mmap = mmtimer_mmap, - .unlocked_ioctl = mmtimer_ioctl, - .llseek = noop_llseek, -}; - -/* - * We only have comparison registers RTC1-4 currently available per - * node. RTC0 is used by SAL. - */ -/* Check for an RTC interrupt pending */ -static int mmtimer_int_pending(int comparator) -{ - if (HUB_L((unsigned long *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED)) & - SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator) - return 1; - else - return 0; -} - -/* Clear the RTC interrupt pending bit */ -static void mmtimer_clr_int_pending(int comparator) -{ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED_ALIAS), - SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator); -} - -/* Setup timer on comparator RTC1 */ -static void mmtimer_setup_int_0(int cpu, u64 expires) -{ - u64 val; - - /* Disable interrupt */ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 0UL); - - /* Initialize comparator value */ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), -1L); - - /* Clear pending bit */ - mmtimer_clr_int_pending(0); - - val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC1_INT_CONFIG_IDX_SHFT) | - ((u64)cpu_physical_id(cpu) << - SH_RTC1_INT_CONFIG_PID_SHFT); - - /* Set configuration */ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_CONFIG), val); - - /* Enable RTC interrupts */ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 1UL); - - /* Initialize comparator value */ - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), expires); - - -} - -/* Setup timer on comparator RTC2 */ -static void mmtimer_setup_int_1(int cpu, u64 expires) -{ - u64 val; - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 0UL); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), -1L); - - mmtimer_clr_int_pending(1); - - val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC2_INT_CONFIG_IDX_SHFT) | - ((u64)cpu_physical_id(cpu) << - SH_RTC2_INT_CONFIG_PID_SHFT); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_CONFIG), val); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 1UL); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), expires); -} - -/* Setup timer on comparator RTC3 */ -static void mmtimer_setup_int_2(int cpu, u64 expires) -{ - u64 val; - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 0UL); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), -1L); - - mmtimer_clr_int_pending(2); - - val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC3_INT_CONFIG_IDX_SHFT) | - ((u64)cpu_physical_id(cpu) << - SH_RTC3_INT_CONFIG_PID_SHFT); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_CONFIG), val); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 1UL); - - HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), expires); -} - -/* - * This function must be called with interrupts disabled and preemption off - * in order to insure that the setup succeeds in a deterministic time frame. - * It will check if the interrupt setup succeeded. - */ -static int mmtimer_setup(int cpu, int comparator, unsigned long expires, - u64 *set_completion_time) -{ - switch (comparator) { - case 0: - mmtimer_setup_int_0(cpu, expires); - break; - case 1: - mmtimer_setup_int_1(cpu, expires); - break; - case 2: - mmtimer_setup_int_2(cpu, expires); - break; - } - /* We might've missed our expiration time */ - *set_completion_time = rtc_time(); - if (*set_completion_time <= expires) - return 1; - - /* - * If an interrupt is already pending then its okay - * if not then we failed - */ - return mmtimer_int_pending(comparator); -} - -static int mmtimer_disable_int(long nasid, int comparator) -{ - switch (comparator) { - case 0: - nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), - 0UL) : REMOTE_HUB_S(nasid, SH_RTC1_INT_ENABLE, 0UL); - break; - case 1: - nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), - 0UL) : REMOTE_HUB_S(nasid, SH_RTC2_INT_ENABLE, 0UL); - break; - case 2: - nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), - 0UL) : REMOTE_HUB_S(nasid, SH_RTC3_INT_ENABLE, 0UL); - break; - default: - return -EFAULT; - } - return 0; -} - -#define COMPARATOR 1 /* The comparator to use */ - -#define TIMER_OFF 0xbadcabLL /* Timer is not setup */ -#define TIMER_SET 0 /* Comparator is set for this timer */ - -#define MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT 40 - -/* There is one of these for each timer */ -struct mmtimer { - struct rb_node list; - struct k_itimer *timer; - int cpu; -}; - -struct mmtimer_node { - spinlock_t lock ____cacheline_aligned; - struct rb_root timer_head; - struct rb_node *next; - struct tasklet_struct tasklet; -}; -static struct mmtimer_node *timers; - -static unsigned mmtimer_interval_retry_increment = - MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT; -module_param(mmtimer_interval_retry_increment, uint, 0644); -MODULE_PARM_DESC(mmtimer_interval_retry_increment, - "RTC ticks to add to expiration on interval retry (default 40)"); - -/* - * Add a new mmtimer struct to the node's mmtimer list. - * This function assumes the struct mmtimer_node is locked. - */ -static void mmtimer_add_list(struct mmtimer *n) -{ - int nodeid = n->timer->it.mmtimer.node; - unsigned long expires = n->timer->it.mmtimer.expires; - struct rb_node **link = &timers[nodeid].timer_head.rb_node; - struct rb_node *parent = NULL; - struct mmtimer *x; - - /* - * Find the right place in the rbtree: - */ - while (*link) { - parent = *link; - x = rb_entry(parent, struct mmtimer, list); - - if (expires < x->timer->it.mmtimer.expires) - link = &(*link)->rb_left; - else - link = &(*link)->rb_right; - } - - /* - * Insert the timer to the rbtree and check whether it - * replaces the first pending timer - */ - rb_link_node(&n->list, parent, link); - rb_insert_color(&n->list, &timers[nodeid].timer_head); - - if (!timers[nodeid].next || expires < rb_entry(timers[nodeid].next, - struct mmtimer, list)->timer->it.mmtimer.expires) - timers[nodeid].next = &n->list; -} - -/* - * Set the comparator for the next timer. - * This function assumes the struct mmtimer_node is locked. - */ -static void mmtimer_set_next_timer(int nodeid) -{ - struct mmtimer_node *n = &timers[nodeid]; - struct mmtimer *x; - struct k_itimer *t; - u64 expires, exp, set_completion_time; - int i; - -restart: - if (n->next == NULL) - return; - - x = rb_entry(n->next, struct mmtimer, list); - t = x->timer; - if (!t->it.mmtimer.incr) { - /* Not an interval timer */ - if (!mmtimer_setup(x->cpu, COMPARATOR, - t->it.mmtimer.expires, - &set_completion_time)) { - /* Late setup, fire now */ - tasklet_schedule(&n->tasklet); - } - return; - } - - /* Interval timer */ - i = 0; - expires = exp = t->it.mmtimer.expires; - while (!mmtimer_setup(x->cpu, COMPARATOR, expires, - &set_completion_time)) { - int to; - - i++; - expires = set_completion_time + - mmtimer_interval_retry_increment + (1 << i); - /* Calculate overruns as we go. */ - to = ((u64)(expires - exp) / t->it.mmtimer.incr); - if (to) { - t->it_overrun += to; - t->it.mmtimer.expires += t->it.mmtimer.incr * to; - exp = t->it.mmtimer.expires; - } - if (i > 20) { - printk(KERN_ALERT "mmtimer: cannot reschedule timer\n"); - t->it.mmtimer.clock = TIMER_OFF; - n->next = rb_next(&x->list); - rb_erase(&x->list, &n->timer_head); - kfree(x); - goto restart; - } - } -} - -/** - * mmtimer_ioctl - ioctl interface for /dev/mmtimer - * @file: file structure for the device - * @cmd: command to execute - * @arg: optional argument to command - * - * Executes the command specified by @cmd. Returns 0 for success, < 0 for - * failure. - * - * Valid commands: - * - * %MMTIMER_GETOFFSET - Should return the offset (relative to the start - * of the page where the registers are mapped) for the counter in question. - * - * %MMTIMER_GETRES - Returns the resolution of the clock in femto (10^-15) - * seconds - * - * %MMTIMER_GETFREQ - Copies the frequency of the clock in Hz to the address - * specified by @arg - * - * %MMTIMER_GETBITS - Returns the number of bits in the clock's counter - * - * %MMTIMER_MMAPAVAIL - Returns 1 if the registers can be mmap'd into userspace - * - * %MMTIMER_GETCOUNTER - Gets the current value in the counter and places it - * in the address specified by @arg. - */ -static long mmtimer_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - int ret = 0; - - mutex_lock(&mmtimer_mutex); - - switch (cmd) { - case MMTIMER_GETOFFSET: /* offset of the counter */ - /* - * SN RTC registers are on their own 64k page - */ - if(PAGE_SIZE <= (1 << 16)) - ret = (((long)RTC_COUNTER_ADDR) & (PAGE_SIZE-1)) / 8; - else - ret = -ENOSYS; - break; - - case MMTIMER_GETRES: /* resolution of the clock in 10^-15 s */ - if(copy_to_user((unsigned long __user *)arg, - &mmtimer_femtoperiod, sizeof(unsigned long))) - ret = -EFAULT; - break; - - case MMTIMER_GETFREQ: /* frequency in Hz */ - if(copy_to_user((unsigned long __user *)arg, - &sn_rtc_cycles_per_second, - sizeof(unsigned long))) - ret = -EFAULT; - break; - - case MMTIMER_GETBITS: /* number of bits in the clock */ - ret = RTC_BITS; - break; - - case MMTIMER_MMAPAVAIL: /* can we mmap the clock into userspace? */ - ret = (PAGE_SIZE <= (1 << 16)) ? 1 : 0; - break; - - case MMTIMER_GETCOUNTER: - if(copy_to_user((unsigned long __user *)arg, - RTC_COUNTER_ADDR, sizeof(unsigned long))) - ret = -EFAULT; - break; - default: - ret = -ENOTTY; - break; - } - mutex_unlock(&mmtimer_mutex); - return ret; -} - -/** - * mmtimer_mmap - maps the clock's registers into userspace - * @file: file structure for the device - * @vma: VMA to map the registers into - * - * Calls remap_pfn_range() to map the clock's registers into - * the calling process' address space. - */ -static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma) -{ - unsigned long mmtimer_addr; - - if (vma->vm_end - vma->vm_start != PAGE_SIZE) - return -EINVAL; - - if (vma->vm_flags & VM_WRITE) - return -EPERM; - - if (PAGE_SIZE > (1 << 16)) - return -ENOSYS; - - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - - mmtimer_addr = __pa(RTC_COUNTER_ADDR); - mmtimer_addr &= ~(PAGE_SIZE - 1); - mmtimer_addr &= 0xfffffffffffffffUL; - - if (remap_pfn_range(vma, vma->vm_start, mmtimer_addr >> PAGE_SHIFT, - PAGE_SIZE, vma->vm_page_prot)) { - printk(KERN_ERR "remap_pfn_range failed in mmtimer.c\n"); - return -EAGAIN; - } - - return 0; -} - -static struct miscdevice mmtimer_miscdev = { - .minor = SGI_MMTIMER, - .name = MMTIMER_NAME, - .fops = &mmtimer_fops -}; - -static struct timespec sgi_clock_offset; -static int sgi_clock_period; - -/* - * Posix Timer Interface - */ - -static struct timespec sgi_clock_offset; -static int sgi_clock_period; - -static int sgi_clock_get(clockid_t clockid, struct timespec64 *tp) -{ - u64 nsec; - - nsec = rtc_time() * sgi_clock_period - + sgi_clock_offset.tv_nsec; - *tp = ns_to_timespec64(nsec); - tp->tv_sec += sgi_clock_offset.tv_sec; - return 0; -}; - -static int sgi_clock_set(const clockid_t clockid, const struct timespec64 *tp) -{ - - u64 nsec; - u32 rem; - - nsec = rtc_time() * sgi_clock_period; - - sgi_clock_offset.tv_sec = tp->tv_sec - div_u64_rem(nsec, NSEC_PER_SEC, &rem); - - if (rem <= tp->tv_nsec) - sgi_clock_offset.tv_nsec = tp->tv_sec - rem; - else { - sgi_clock_offset.tv_nsec = tp->tv_sec + NSEC_PER_SEC - rem; - sgi_clock_offset.tv_sec--; - } - return 0; -} - -/** - * mmtimer_interrupt - timer interrupt handler - * @irq: irq received - * @dev_id: device the irq came from - * - * Called when one of the comarators matches the counter, This - * routine will send signals to processes that have requested - * them. - * - * This interrupt is run in an interrupt context - * by the SHUB. It is therefore safe to locally access SHub - * registers. - */ -static irqreturn_t -mmtimer_interrupt(int irq, void *dev_id) -{ - unsigned long expires = 0; - int result = IRQ_NONE; - unsigned indx = cpu_to_node(smp_processor_id()); - struct mmtimer *base; - - spin_lock(&timers[indx].lock); - base = rb_entry(timers[indx].next, struct mmtimer, list); - if (base == NULL) { - spin_unlock(&timers[indx].lock); - return result; - } - - if (base->cpu == smp_processor_id()) { - if (base->timer) - expires = base->timer->it.mmtimer.expires; - /* expires test won't work with shared irqs */ - if ((mmtimer_int_pending(COMPARATOR) > 0) || - (expires && (expires <= rtc_time()))) { - mmtimer_clr_int_pending(COMPARATOR); - tasklet_schedule(&timers[indx].tasklet); - result = IRQ_HANDLED; - } - } - spin_unlock(&timers[indx].lock); - return result; -} - -static void mmtimer_tasklet(unsigned long data) -{ - int nodeid = data; - struct mmtimer_node *mn = &timers[nodeid]; - struct mmtimer *x; - struct k_itimer *t; - unsigned long flags; - - /* Send signal and deal with periodic signals */ - spin_lock_irqsave(&mn->lock, flags); - if (!mn->next) - goto out; - - x = rb_entry(mn->next, struct mmtimer, list); - t = x->timer; - - if (t->it.mmtimer.clock == TIMER_OFF) - goto out; - - t->it_overrun = 0; - - mn->next = rb_next(&x->list); - rb_erase(&x->list, &mn->timer_head); - - if (posix_timer_event(t, 0) != 0) - t->it_overrun++; - - if(t->it.mmtimer.incr) { - t->it.mmtimer.expires += t->it.mmtimer.incr; - mmtimer_add_list(x); - } else { - /* Ensure we don't false trigger in mmtimer_interrupt */ - t->it.mmtimer.clock = TIMER_OFF; - t->it.mmtimer.expires = 0; - kfree(x); - } - /* Set comparator for next timer, if there is one */ - mmtimer_set_next_timer(nodeid); - - t->it_overrun_last = t->it_overrun; -out: - spin_unlock_irqrestore(&mn->lock, flags); -} - -static int sgi_timer_create(struct k_itimer *timer) -{ - /* Insure that a newly created timer is off */ - timer->it.mmtimer.clock = TIMER_OFF; - return 0; -} - -/* This does not really delete a timer. It just insures - * that the timer is not active - * - * Assumption: it_lock is already held with irq's disabled - */ -static int sgi_timer_del(struct k_itimer *timr) -{ - cnodeid_t nodeid = timr->it.mmtimer.node; - unsigned long irqflags; - - spin_lock_irqsave(&timers[nodeid].lock, irqflags); - if (timr->it.mmtimer.clock != TIMER_OFF) { - unsigned long expires = timr->it.mmtimer.expires; - struct rb_node *n = timers[nodeid].timer_head.rb_node; - struct mmtimer *uninitialized_var(t); - int r = 0; - - timr->it.mmtimer.clock = TIMER_OFF; - timr->it.mmtimer.expires = 0; - - while (n) { - t = rb_entry(n, struct mmtimer, list); - if (t->timer == timr) - break; - - if (expires < t->timer->it.mmtimer.expires) - n = n->rb_left; - else - n = n->rb_right; - } - - if (!n) { - spin_unlock_irqrestore(&timers[nodeid].lock, irqflags); - return 0; - } - - if (timers[nodeid].next == n) { - timers[nodeid].next = rb_next(n); - r = 1; - } - - rb_erase(n, &timers[nodeid].timer_head); - kfree(t); - - if (r) { - mmtimer_disable_int(cnodeid_to_nasid(nodeid), - COMPARATOR); - mmtimer_set_next_timer(nodeid); - } - } - spin_unlock_irqrestore(&timers[nodeid].lock, irqflags); - return 0; -} - -/* Assumption: it_lock is already held with irq's disabled */ -static void sgi_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) -{ - - if (timr->it.mmtimer.clock == TIMER_OFF) { - cur_setting->it_interval.tv_nsec = 0; - cur_setting->it_interval.tv_sec = 0; - cur_setting->it_value.tv_nsec = 0; - cur_setting->it_value.tv_sec =0; - return; - } - - cur_setting->it_interval = ns_to_timespec64(timr->it.mmtimer.incr * sgi_clock_period); - cur_setting->it_value = ns_to_timespec64((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period); -} - - -static int sgi_timer_set(struct k_itimer *timr, int flags, - struct itimerspec64 *new_setting, - struct itimerspec64 *old_setting) -{ - unsigned long when, period, irqflags; - int err = 0; - cnodeid_t nodeid; - struct mmtimer *base; - struct rb_node *n; - - if (old_setting) - sgi_timer_get(timr, old_setting); - - sgi_timer_del(timr); - when = timespec64_to_ns(&new_setting->it_value); - period = timespec64_to_ns(&new_setting->it_interval); - - if (when == 0) - /* Clear timer */ - return 0; - - base = kmalloc(sizeof(struct mmtimer), GFP_KERNEL); - if (base == NULL) - return -ENOMEM; - - if (flags & TIMER_ABSTIME) { - struct timespec64 n; - unsigned long now; - - getnstimeofday64(&n); - now = timespec64_to_ns(&n); - if (when > now) - when -= now; - else - /* Fire the timer immediately */ - when = 0; - } - - /* - * Convert to sgi clock period. Need to keep rtc_time() as near as possible - * to getnstimeofday() in order to be as faithful as possible to the time - * specified. - */ - when = (when + sgi_clock_period - 1) / sgi_clock_period + rtc_time(); - period = (period + sgi_clock_period - 1) / sgi_clock_period; - - /* - * We are allocating a local SHub comparator. If we would be moved to another - * cpu then another SHub may be local to us. Prohibit that by switching off - * preemption. - */ - preempt_disable(); - - nodeid = cpu_to_node(smp_processor_id()); - - /* Lock the node timer structure */ - spin_lock_irqsave(&timers[nodeid].lock, irqflags); - - base->timer = timr; - base->cpu = smp_processor_id(); - - timr->it.mmtimer.clock = TIMER_SET; - timr->it.mmtimer.node = nodeid; - timr->it.mmtimer.incr = period; - timr->it.mmtimer.expires = when; - - n = timers[nodeid].next; - - /* Add the new struct mmtimer to node's timer list */ - mmtimer_add_list(base); - - if (timers[nodeid].next == n) { - /* No need to reprogram comparator for now */ - spin_unlock_irqrestore(&timers[nodeid].lock, irqflags); - preempt_enable(); - return err; - } - - /* We need to reprogram the comparator */ - if (n) - mmtimer_disable_int(cnodeid_to_nasid(nodeid), COMPARATOR); - - mmtimer_set_next_timer(nodeid); - - /* Unlock the node timer structure */ - spin_unlock_irqrestore(&timers[nodeid].lock, irqflags); - - preempt_enable(); - - return err; -} - -static int sgi_clock_getres(const clockid_t which_clock, struct timespec64 *tp) -{ - tp->tv_sec = 0; - tp->tv_nsec = sgi_clock_period; - return 0; -} - -static struct k_clock sgi_clock = { - .clock_set = sgi_clock_set, - .clock_get = sgi_clock_get, - .clock_getres = sgi_clock_getres, - .timer_create = sgi_timer_create, - .timer_set = sgi_timer_set, - .timer_del = sgi_timer_del, - .timer_get = sgi_timer_get -}; - -/** - * mmtimer_init - device initialization routine - * - * Does initial setup for the mmtimer device. - */ -static int __init mmtimer_init(void) -{ - cnodeid_t node, maxn = -1; - - if (!ia64_platform_is("sn2")) - return 0; - - /* - * Sanity check the cycles/sec variable - */ - if (sn_rtc_cycles_per_second < 100000) { - printk(KERN_ERR "%s: unable to determine clock frequency\n", - MMTIMER_NAME); - goto out1; - } - - mmtimer_femtoperiod = ((unsigned long)1E15 + sn_rtc_cycles_per_second / - 2) / sn_rtc_cycles_per_second; - - if (request_irq(SGI_MMTIMER_VECTOR, mmtimer_interrupt, IRQF_PERCPU, MMTIMER_NAME, NULL)) { - printk(KERN_WARNING "%s: unable to allocate interrupt.", - MMTIMER_NAME); - goto out1; - } - - if (misc_register(&mmtimer_miscdev)) { - printk(KERN_ERR "%s: failed to register device\n", - MMTIMER_NAME); - goto out2; - } - - /* Get max numbered node, calculate slots needed */ - for_each_online_node(node) { - maxn = node; - } - maxn++; - - /* Allocate list of node ptrs to mmtimer_t's */ - timers = kzalloc(sizeof(struct mmtimer_node)*maxn, GFP_KERNEL); - if (!timers) { - printk(KERN_ERR "%s: failed to allocate memory for device\n", - MMTIMER_NAME); - goto out3; - } - - /* Initialize struct mmtimer's for each online node */ - for_each_online_node(node) { - spin_lock_init(&timers[node].lock); - tasklet_init(&timers[node].tasklet, mmtimer_tasklet, - (unsigned long) node); - } - - sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second; - posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock); - - printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION, - sn_rtc_cycles_per_second/(unsigned long)1E6); - - return 0; - -out3: - misc_deregister(&mmtimer_miscdev); -out2: - free_irq(SGI_MMTIMER_VECTOR, NULL); -out1: - return -1; -} - -module_init(mmtimer_init); diff --git a/drivers/char/random.c b/drivers/char/random.c index 0ab0249189072b..a561f0c2f428df 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1097,12 +1097,16 @@ static void add_interrupt_bench(cycles_t start) static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) { __u32 *ptr = (__u32 *) regs; + unsigned long flags; if (regs == NULL) return 0; + local_irq_save(flags); if (f->reg_idx >= sizeof(struct pt_regs) / sizeof(__u32)) f->reg_idx = 0; - return *(ptr + f->reg_idx++); + ptr += f->reg_idx++; + local_irq_restore(flags); + return *ptr; } void add_interrupt_randomness(int irq, int irq_flags) diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 158c1db83f0516..a965a9f0e5d2ea 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -429,8 +429,9 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, rc = chip->ops->send(chip, (u8 *) buf, count); if (rc < 0) { - dev_err(&chip->dev, - "tpm_transmit: tpm_send: error %d\n", rc); + if (rc != -EPIPE) + dev_err(&chip->dev, + "%s: tpm_send: error %d\n", __func__, rc); goto out; } @@ -540,55 +541,57 @@ ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_space *space, #define TPM_DIGEST_SIZE 20 #define TPM_RET_CODE_IDX 6 #define TPM_INTERNAL_RESULT_SIZE 200 -#define TPM_ORD_GET_CAP cpu_to_be32(101) -#define TPM_ORD_GET_RANDOM cpu_to_be32(70) +#define TPM_ORD_GET_CAP 101 +#define TPM_ORD_GET_RANDOM 70 static const struct tpm_input_header tpm_getcap_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(22), - .ordinal = TPM_ORD_GET_CAP + .ordinal = cpu_to_be32(TPM_ORD_GET_CAP) }; ssize_t tpm_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, const char *desc, size_t min_cap_length) { - struct tpm_cmd_t tpm_cmd; + struct tpm_buf buf; int rc; - tpm_cmd.header.in = tpm_getcap_header; + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_CAP); + if (rc) + return rc; + if (subcap_id == TPM_CAP_VERSION_1_1 || subcap_id == TPM_CAP_VERSION_1_2) { - tpm_cmd.params.getcap_in.cap = cpu_to_be32(subcap_id); - /*subcap field not necessary */ - tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(0); - tpm_cmd.header.in.length -= cpu_to_be32(sizeof(__be32)); + tpm_buf_append_u32(&buf, subcap_id); + tpm_buf_append_u32(&buf, 0); } else { if (subcap_id == TPM_CAP_FLAG_PERM || subcap_id == TPM_CAP_FLAG_VOL) - tpm_cmd.params.getcap_in.cap = - cpu_to_be32(TPM_CAP_FLAG); + tpm_buf_append_u32(&buf, TPM_CAP_FLAG); else - tpm_cmd.params.getcap_in.cap = - cpu_to_be32(TPM_CAP_PROP); - tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4); - tpm_cmd.params.getcap_in.subcap = cpu_to_be32(subcap_id); + tpm_buf_append_u32(&buf, TPM_CAP_PROP); + + tpm_buf_append_u32(&buf, 4); + tpm_buf_append_u32(&buf, subcap_id); } - rc = tpm_transmit_cmd(chip, NULL, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, min_cap_length, 0, desc); if (!rc) - *cap = tpm_cmd.params.getcap_out.cap; + *cap = *(cap_t *)&buf.data[TPM_HEADER_SIZE + 4]; + + tpm_buf_destroy(&buf); return rc; } EXPORT_SYMBOL_GPL(tpm_getcap); -#define TPM_ORD_STARTUP cpu_to_be32(153) +#define TPM_ORD_STARTUP 153 #define TPM_ST_CLEAR cpu_to_be16(1) #define TPM_ST_STATE cpu_to_be16(2) #define TPM_ST_DEACTIVATED cpu_to_be16(3) static const struct tpm_input_header tpm_startup_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(12), - .ordinal = TPM_ORD_STARTUP + .ordinal = cpu_to_be32(TPM_ORD_STARTUP) }; static int tpm_startup(struct tpm_chip *chip, __be16 startup_type) @@ -737,7 +740,7 @@ EXPORT_SYMBOL_GPL(tpm_get_timeouts); #define CONTINUE_SELFTEST_RESULT_SIZE 10 static const struct tpm_input_header continue_selftest_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(10), .ordinal = cpu_to_be32(TPM_ORD_CONTINUE_SELFTEST), }; @@ -760,13 +763,13 @@ static int tpm_continue_selftest(struct tpm_chip *chip) return rc; } -#define TPM_ORDINAL_PCRREAD cpu_to_be32(21) +#define TPM_ORDINAL_PCRREAD 21 #define READ_PCR_RESULT_SIZE 30 #define READ_PCR_RESULT_BODY_SIZE 20 static const struct tpm_input_header pcrread_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(14), - .ordinal = TPM_ORDINAL_PCRREAD + .ordinal = cpu_to_be32(TPM_ORDINAL_PCRREAD) }; int tpm_pcr_read_dev(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) @@ -838,15 +841,34 @@ int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) } EXPORT_SYMBOL_GPL(tpm_pcr_read); -#define TPM_ORD_PCR_EXTEND cpu_to_be32(20) +#define TPM_ORD_PCR_EXTEND 20 #define EXTEND_PCR_RESULT_SIZE 34 #define EXTEND_PCR_RESULT_BODY_SIZE 20 static const struct tpm_input_header pcrextend_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(34), - .ordinal = TPM_ORD_PCR_EXTEND + .ordinal = cpu_to_be32(TPM_ORD_PCR_EXTEND) }; +static int tpm1_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash, + char *log_msg) +{ + struct tpm_buf buf; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_EXTEND); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, pcr_idx); + tpm_buf_append(&buf, hash, TPM_DIGEST_SIZE); + + rc = tpm_transmit_cmd(chip, NULL, buf.data, EXTEND_PCR_RESULT_SIZE, + EXTEND_PCR_RESULT_BODY_SIZE, 0, log_msg); + tpm_buf_destroy(&buf); + return rc; +} + /** * tpm_pcr_extend - extend pcr value with hash * @chip_num: tpm idx # or AN& @@ -859,7 +881,6 @@ static const struct tpm_input_header pcrextend_header = { */ int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) { - struct tpm_cmd_t cmd; int rc; struct tpm_chip *chip; struct tpm2_digest digest_list[ARRAY_SIZE(chip->active_banks)]; @@ -885,13 +906,8 @@ int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) return rc; } - cmd.header.in = pcrextend_header; - cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(pcr_idx); - memcpy(cmd.params.pcrextend_in.hash, hash, TPM_DIGEST_SIZE); - rc = tpm_transmit_cmd(chip, NULL, &cmd, EXTEND_PCR_RESULT_SIZE, - EXTEND_PCR_RESULT_BODY_SIZE, 0, - "attempting extend a PCR value"); - + rc = tpm1_pcr_extend(chip, pcr_idx, hash, + "attempting extend a PCR value"); tpm_put_ops(chip); return rc; } @@ -1060,13 +1076,13 @@ int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout, } EXPORT_SYMBOL_GPL(wait_for_tpm_stat); -#define TPM_ORD_SAVESTATE cpu_to_be32(152) +#define TPM_ORD_SAVESTATE 152 #define SAVESTATE_RESULT_SIZE 10 static const struct tpm_input_header savestate_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(10), - .ordinal = TPM_ORD_SAVESTATE + .ordinal = cpu_to_be32(TPM_ORD_SAVESTATE) }; /* @@ -1090,15 +1106,9 @@ int tpm_pm_suspend(struct device *dev) } /* for buggy tpm, flush pcrs with extend to selected dummy */ - if (tpm_suspend_pcr) { - cmd.header.in = pcrextend_header; - cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(tpm_suspend_pcr); - memcpy(cmd.params.pcrextend_in.hash, dummy_hash, - TPM_DIGEST_SIZE); - rc = tpm_transmit_cmd(chip, NULL, &cmd, EXTEND_PCR_RESULT_SIZE, - EXTEND_PCR_RESULT_BODY_SIZE, 0, - "extending dummy pcr before suspend"); - } + if (tpm_suspend_pcr) + rc = tpm1_pcr_extend(chip, tpm_suspend_pcr, dummy_hash, + "extending dummy pcr before suspend"); /* now do the actual savestate */ for (try = 0; try < TPM_RETRY; try++) { @@ -1149,9 +1159,9 @@ EXPORT_SYMBOL_GPL(tpm_pm_resume); #define TPM_GETRANDOM_RESULT_SIZE 18 static const struct tpm_input_header tpm_getrandom_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(14), - .ordinal = TPM_ORD_GET_RANDOM + .ordinal = cpu_to_be32(TPM_ORD_GET_RANDOM) }; /** diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index 55405dbe43fa6d..4bd0997cfa2d3e 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -22,11 +22,11 @@ #define READ_PUBEK_RESULT_SIZE 314 #define READ_PUBEK_RESULT_MIN_BODY_SIZE (28 + 256) -#define TPM_ORD_READPUBEK cpu_to_be32(124) +#define TPM_ORD_READPUBEK 124 static const struct tpm_input_header tpm_readpubek_header = { - .tag = TPM_TAG_RQU_COMMAND, + .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), .length = cpu_to_be32(30), - .ordinal = TPM_ORD_READPUBEK + .ordinal = cpu_to_be32(TPM_ORD_READPUBEK) }; static ssize_t pubek_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 4b4c8dee30965a..af05c1403c6e4c 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -247,7 +247,7 @@ struct tpm_output_header { __be32 return_code; } __packed; -#define TPM_TAG_RQU_COMMAND cpu_to_be16(193) +#define TPM_TAG_RQU_COMMAND 193 struct stclear_flags_t { __be16 tag; @@ -339,17 +339,6 @@ enum tpm_sub_capabilities { TPM_CAP_PROP_TIS_DURATION = 0x120, }; -struct tpm_getcap_params_in { - __be32 cap; - __be32 subcap_size; - __be32 subcap; -} __packed; - -struct tpm_getcap_params_out { - __be32 cap_size; - cap_t cap; -} __packed; - struct tpm_readpubek_params_out { u8 algorithm[4]; u8 encscheme[2]; @@ -374,11 +363,6 @@ struct tpm_pcrread_in { __be32 pcr_idx; } __packed; -struct tpm_pcrextend_in { - __be32 pcr_idx; - u8 hash[TPM_DIGEST_SIZE]; -} __packed; - /* 128 bytes is an arbitrary cap. This could be as large as TPM_BUFSIZE - 18 * bytes, but 128 is still a relatively large number of random bytes and * anything much bigger causes users of struct tpm_cmd_t to start getting @@ -399,13 +383,10 @@ struct tpm_startup_in { } __packed; typedef union { - struct tpm_getcap_params_out getcap_out; struct tpm_readpubek_params_out readpubek_out; u8 readpubek_out_buffer[sizeof(struct tpm_readpubek_params_out)]; - struct tpm_getcap_params_in getcap_in; struct tpm_pcrread_in pcrread_in; struct tpm_pcrread_out pcrread_out; - struct tpm_pcrextend_in pcrextend_in; struct tpm_getrandom_in getrandom_in; struct tpm_getrandom_out getrandom_out; struct tpm_startup_in startup_in; diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 3ee6883f26c190..3a996432627930 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -840,7 +840,7 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type) /* In places where shutdown command is sent there's no much we can do * except print the error code on a system failure. */ - if (rc < 0) + if (rc < 0 && rc != -EPIPE) dev_warn(&chip->dev, "transmit returned %d while stopping the TPM", rc); } diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index dc47fa222a2650..79d6bbb58e39b8 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -70,6 +70,7 @@ struct tpm_inf_dev { u8 buf[TPM_BUFSIZE + sizeof(u8)]; /* max. buffer size + addr */ struct tpm_chip *chip; enum i2c_chip_type chip_type; + unsigned int adapterlimit; }; static struct tpm_inf_dev tpm_dev; @@ -111,6 +112,7 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len) int rc = 0; int count; + unsigned int msglen = len; /* Lock the adapter for the duration of the whole sequence. */ if (!tpm_dev.client->adapter->algo->master_xfer) @@ -131,27 +133,61 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len) usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI); } } else { - /* slb9635 protocol should work in all cases */ - for (count = 0; count < MAX_COUNT; count++) { - rc = __i2c_transfer(tpm_dev.client->adapter, &msg1, 1); - if (rc > 0) - break; /* break here to skip sleep */ - - usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI); - } - - if (rc <= 0) - goto out; - - /* After the TPM has successfully received the register address - * it needs some time, thus we're sleeping here again, before - * retrieving the data + /* Expect to send one command message and one data message, but + * support looping over each or both if necessary. */ - for (count = 0; count < MAX_COUNT; count++) { - usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI); - rc = __i2c_transfer(tpm_dev.client->adapter, &msg2, 1); - if (rc > 0) - break; + while (len > 0) { + /* slb9635 protocol should work in all cases */ + for (count = 0; count < MAX_COUNT; count++) { + rc = __i2c_transfer(tpm_dev.client->adapter, + &msg1, 1); + if (rc > 0) + break; /* break here to skip sleep */ + + usleep_range(SLEEP_DURATION_LOW, + SLEEP_DURATION_HI); + } + + if (rc <= 0) + goto out; + + /* After the TPM has successfully received the register + * address it needs some time, thus we're sleeping here + * again, before retrieving the data + */ + for (count = 0; count < MAX_COUNT; count++) { + if (tpm_dev.adapterlimit) { + msglen = min_t(unsigned int, + tpm_dev.adapterlimit, + len); + msg2.len = msglen; + } + usleep_range(SLEEP_DURATION_LOW, + SLEEP_DURATION_HI); + rc = __i2c_transfer(tpm_dev.client->adapter, + &msg2, 1); + if (rc > 0) { + /* Since len is unsigned, make doubly + * sure we do not underflow it. + */ + if (msglen > len) + len = 0; + else + len -= msglen; + msg2.buf += msglen; + break; + } + /* If the I2C adapter rejected the request (e.g + * when the quirk read_max_len < len) fall back + * to a sane minimum value and try again. + */ + if (rc == -EOPNOTSUPP) + tpm_dev.adapterlimit = + I2C_SMBUS_BLOCK_MAX; + } + + if (rc <= 0) + goto out; } } diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c index e3cf9f3545c57a..3b1b9f9322d554 100644 --- a/drivers/char/tpm/tpm_infineon.c +++ b/drivers/char/tpm/tpm_infineon.c @@ -397,7 +397,7 @@ static int tpm_inf_pnp_probe(struct pnp_dev *dev, int vendorid[2]; int version[2]; int productid[2]; - char chipname[20]; + const char *chipname; struct tpm_chip *chip; /* read IO-ports through PnP */ @@ -488,13 +488,13 @@ static int tpm_inf_pnp_probe(struct pnp_dev *dev, switch ((productid[0] << 8) | productid[1]) { case 6: - snprintf(chipname, sizeof(chipname), " (SLD 9630 TT 1.1)"); + chipname = " (SLD 9630 TT 1.1)"; break; case 11: - snprintf(chipname, sizeof(chipname), " (SLB 9635 TT 1.2)"); + chipname = " (SLB 9635 TT 1.2)"; break; default: - snprintf(chipname, sizeof(chipname), " (unknown chip)"); + chipname = " (unknown chip)"; break; } diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index c7e1384f1b0802..b14d4aa97af87a 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -80,6 +80,8 @@ static int has_hid(struct acpi_device *dev, const char *hid) static inline int is_itpm(struct acpi_device *dev) { + if (!dev) + return 0; return has_hid(dev, "INTC0102"); } #else @@ -89,6 +91,47 @@ static inline int is_itpm(struct acpi_device *dev) } #endif +#if defined(CONFIG_ACPI) +#define DEVICE_IS_TPM2 1 + +static const struct acpi_device_id tpm_acpi_tbl[] = { + {"MSFT0101", DEVICE_IS_TPM2}, + {}, +}; +MODULE_DEVICE_TABLE(acpi, tpm_acpi_tbl); + +static int check_acpi_tpm2(struct device *dev) +{ + const struct acpi_device_id *aid = acpi_match_device(tpm_acpi_tbl, dev); + struct acpi_table_tpm2 *tbl; + acpi_status st; + + if (!aid || aid->driver_data != DEVICE_IS_TPM2) + return 0; + + /* If the ACPI TPM2 signature is matched then a global ACPI_SIG_TPM2 + * table is mandatory + */ + st = + acpi_get_table(ACPI_SIG_TPM2, 1, (struct acpi_table_header **)&tbl); + if (ACPI_FAILURE(st) || tbl->header.length < sizeof(*tbl)) { + dev_err(dev, FW_BUG "failed to get TPM2 ACPI table\n"); + return -EINVAL; + } + + /* The tpm2_crb driver handles this device */ + if (tbl->start_method != ACPI_TPM2_MEMORY_MAPPED) + return -ENODEV; + + return 0; +} +#else +static int check_acpi_tpm2(struct device *dev) +{ + return 0; +} +#endif + static int tpm_tcg_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len, u8 *result) { @@ -141,11 +184,15 @@ static const struct tpm_tis_phy_ops tpm_tcg = { .write32 = tpm_tcg_write32, }; -static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, - acpi_handle acpi_dev_handle) +static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info) { struct tpm_tis_tcg_phy *phy; int irq = -1; + int rc; + + rc = check_acpi_tpm2(dev); + if (rc) + return rc; phy = devm_kzalloc(dev, sizeof(struct tpm_tis_tcg_phy), GFP_KERNEL); if (phy == NULL) @@ -158,11 +205,11 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, if (interrupts) irq = tpm_info->irq; - if (itpm) + if (itpm || is_itpm(ACPI_COMPANION(dev))) phy->priv.flags |= TPM_TIS_ITPM_WORKAROUND; return tpm_tis_core_init(dev, &phy->priv, irq, &tpm_tcg, - acpi_dev_handle); + ACPI_HANDLE(dev)); } static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume); @@ -171,7 +218,6 @@ static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev, const struct pnp_device_id *pnp_id) { struct tpm_info tpm_info = {}; - acpi_handle acpi_dev_handle = NULL; struct resource *res; res = pnp_get_resource(pnp_dev, IORESOURCE_MEM, 0); @@ -184,14 +230,7 @@ static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev, else tpm_info.irq = -1; - if (pnp_acpi_device(pnp_dev)) { - if (is_itpm(pnp_acpi_device(pnp_dev))) - itpm = true; - - acpi_dev_handle = ACPI_HANDLE(&pnp_dev->dev); - } - - return tpm_tis_init(&pnp_dev->dev, &tpm_info, acpi_dev_handle); + return tpm_tis_init(&pnp_dev->dev, &tpm_info); } static struct pnp_device_id tpm_pnp_tbl[] = { @@ -231,93 +270,6 @@ module_param_string(hid, tpm_pnp_tbl[TIS_HID_USR_IDX].id, sizeof(tpm_pnp_tbl[TIS_HID_USR_IDX].id), 0444); MODULE_PARM_DESC(hid, "Set additional specific HID for this driver to probe"); -#ifdef CONFIG_ACPI -static int tpm_check_resource(struct acpi_resource *ares, void *data) -{ - struct tpm_info *tpm_info = (struct tpm_info *) data; - struct resource res; - - if (acpi_dev_resource_interrupt(ares, 0, &res)) - tpm_info->irq = res.start; - else if (acpi_dev_resource_memory(ares, &res)) { - tpm_info->res = res; - tpm_info->res.name = NULL; - } - - return 1; -} - -static int tpm_tis_acpi_init(struct acpi_device *acpi_dev) -{ - struct acpi_table_tpm2 *tbl; - acpi_status st; - struct list_head resources; - struct tpm_info tpm_info = {}; - int ret; - - st = acpi_get_table(ACPI_SIG_TPM2, 1, - (struct acpi_table_header **) &tbl); - if (ACPI_FAILURE(st) || tbl->header.length < sizeof(*tbl)) { - dev_err(&acpi_dev->dev, - FW_BUG "failed to get TPM2 ACPI table\n"); - return -EINVAL; - } - - if (tbl->start_method != ACPI_TPM2_MEMORY_MAPPED) - return -ENODEV; - - INIT_LIST_HEAD(&resources); - tpm_info.irq = -1; - ret = acpi_dev_get_resources(acpi_dev, &resources, tpm_check_resource, - &tpm_info); - if (ret < 0) - return ret; - - acpi_dev_free_resource_list(&resources); - - if (resource_type(&tpm_info.res) != IORESOURCE_MEM) { - dev_err(&acpi_dev->dev, - FW_BUG "TPM2 ACPI table does not define a memory resource\n"); - return -EINVAL; - } - - if (is_itpm(acpi_dev)) - itpm = true; - - return tpm_tis_init(&acpi_dev->dev, &tpm_info, acpi_dev->handle); -} - -static int tpm_tis_acpi_remove(struct acpi_device *dev) -{ - struct tpm_chip *chip = dev_get_drvdata(&dev->dev); - - tpm_chip_unregister(chip); - tpm_tis_remove(chip); - - return 0; -} - -static struct acpi_device_id tpm_acpi_tbl[] = { - {"MSFT0101", 0}, /* TPM 2.0 */ - /* Add new here */ - {"", 0}, /* User Specified */ - {"", 0} /* Terminator */ -}; -MODULE_DEVICE_TABLE(acpi, tpm_acpi_tbl); - -static struct acpi_driver tis_acpi_driver = { - .name = "tpm_tis", - .ids = tpm_acpi_tbl, - .ops = { - .add = tpm_tis_acpi_init, - .remove = tpm_tis_acpi_remove, - }, - .drv = { - .pm = &tpm_tis_pm, - }, -}; -#endif - static struct platform_device *force_pdev; static int tpm_tis_plat_probe(struct platform_device *pdev) @@ -332,18 +284,16 @@ static int tpm_tis_plat_probe(struct platform_device *pdev) } tpm_info.res = *res; - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (res) { - tpm_info.irq = res->start; - } else { - if (pdev == force_pdev) + tpm_info.irq = platform_get_irq(pdev, 0); + if (tpm_info.irq <= 0) { + if (pdev != force_pdev) tpm_info.irq = -1; else /* When forcing auto probe the IRQ */ tpm_info.irq = 0; } - return tpm_tis_init(&pdev->dev, &tpm_info, NULL); + return tpm_tis_init(&pdev->dev, &tpm_info); } static int tpm_tis_plat_remove(struct platform_device *pdev) @@ -371,6 +321,7 @@ static struct platform_driver tis_drv = { .name = "tpm_tis", .pm = &tpm_tis_pm, .of_match_table = of_match_ptr(tis_of_platform_match), + .acpi_match_table = ACPI_PTR(tpm_acpi_tbl), }, }; @@ -413,11 +364,6 @@ static int __init init_tis(void) if (rc) goto err_platform; -#ifdef CONFIG_ACPI - rc = acpi_bus_register_driver(&tis_acpi_driver); - if (rc) - goto err_acpi; -#endif if (IS_ENABLED(CONFIG_PNP)) { rc = pnp_register_driver(&tis_pnp_driver); @@ -428,10 +374,6 @@ static int __init init_tis(void) return 0; err_pnp: -#ifdef CONFIG_ACPI - acpi_bus_unregister_driver(&tis_acpi_driver); -err_acpi: -#endif platform_driver_unregister(&tis_drv); err_platform: if (force_pdev) @@ -443,9 +385,6 @@ static int __init init_tis(void) static void __exit cleanup_tis(void) { pnp_unregister_driver(&tis_pnp_driver); -#ifdef CONFIG_ACPI - acpi_bus_unregister_driver(&tis_acpi_driver); -#endif platform_driver_unregister(&tis_drv); if (force_pdev) diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index c636e7fdd1f513..1a0e97a5da5a45 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -45,7 +45,7 @@ static int tpmrm_release(struct inode *inode, struct file *file) return 0; } -ssize_t tpmrm_write(struct file *file, const char __user *buf, +static ssize_t tpmrm_write(struct file *file, const char __user *buf, size_t size, loff_t *off) { struct file_priv *fpriv = file->private_data; diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 36cfea38135f6a..a0fd60f0cc894c 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -224,6 +224,7 @@ source "drivers/clk/meson/Kconfig" source "drivers/clk/mvebu/Kconfig" source "drivers/clk/qcom/Kconfig" source "drivers/clk/renesas/Kconfig" +source "drivers/clk/rockchip/Kconfig" source "drivers/clk/samsung/Kconfig" source "drivers/clk/sunxi-ng/Kconfig" source "drivers/clk/tegra/Kconfig" diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index 96386ffc84835f..9bb472cccca6e0 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -275,7 +275,8 @@ static int _next_div(const struct clk_div_table *table, int div, return div; } -static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, +static int clk_divider_bestdiv(struct clk_hw *hw, struct clk_hw *parent, + unsigned long rate, unsigned long *best_parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags) @@ -314,8 +315,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, *best_parent_rate = parent_rate_saved; return i; } - parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), - rate * i); + parent_rate = clk_hw_round_rate(parent, rate * i); now = DIV_ROUND_UP_ULL((u64)parent_rate, i); if (_is_best_div(rate, now, best, flags)) { bestdiv = i; @@ -326,23 +326,24 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, if (!bestdiv) { bestdiv = _get_maxdiv(table, width, flags); - *best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), 1); + *best_parent_rate = clk_hw_round_rate(parent, 1); } return bestdiv; } -long divider_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate, const struct clk_div_table *table, - u8 width, unsigned long flags) +long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, + unsigned long rate, unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags) { int div; - div = clk_divider_bestdiv(hw, rate, prate, table, width, flags); + div = clk_divider_bestdiv(hw, parent, rate, prate, table, width, flags); return DIV_ROUND_UP_ULL((u64)*prate, div); } -EXPORT_SYMBOL_GPL(divider_round_rate); +EXPORT_SYMBOL_GPL(divider_round_rate_parent); static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig index 19480bcc704630..2f29ee1a4d0054 100644 --- a/drivers/clk/meson/Kconfig +++ b/drivers/clk/meson/Kconfig @@ -14,6 +14,7 @@ config COMMON_CLK_MESON8B config COMMON_CLK_GXBB bool depends on COMMON_CLK_AMLOGIC + select RESET_CONTROLLER help Support for the clock controller on AmLogic S905 devices, aka gxbb. Say Y if you want peripherals and CPU frequency scaling to work. diff --git a/drivers/clk/mvebu/ap806-system-controller.c b/drivers/clk/mvebu/ap806-system-controller.c index 8155baccc98e49..fa2fbd2cef4a34 100644 --- a/drivers/clk/mvebu/ap806-system-controller.c +++ b/drivers/clk/mvebu/ap806-system-controller.c @@ -32,24 +32,38 @@ static struct clk_onecell_data ap806_clk_data = { .clk_num = AP806_CLK_NUM, }; -static int ap806_syscon_clk_probe(struct platform_device *pdev) +static char *ap806_unique_name(struct device *dev, struct device_node *np, + char *name) +{ + const __be32 *reg; + u64 addr; + + reg = of_get_property(np, "reg", NULL); + addr = of_translate_address(np, reg); + return devm_kasprintf(dev, GFP_KERNEL, "%llx-%s", + (unsigned long long)addr, name); +} + +static int ap806_syscon_common_probe(struct platform_device *pdev, + struct device_node *syscon_node) { unsigned int freq_mode, cpuclk_freq; const char *name, *fixedclk_name; - struct device_node *np = pdev->dev.of_node; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; struct regmap *regmap; u32 reg; int ret; - regmap = syscon_node_to_regmap(np); + regmap = syscon_node_to_regmap(syscon_node); if (IS_ERR(regmap)) { - dev_err(&pdev->dev, "cannot get regmap\n"); + dev_err(dev, "cannot get regmap\n"); return PTR_ERR(regmap); } ret = regmap_read(regmap, AP806_SAR_REG, ®); if (ret) { - dev_err(&pdev->dev, "cannot read from regmap\n"); + dev_err(dev, "cannot read from regmap\n"); return ret; } @@ -89,7 +103,7 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) cpuclk_freq = 600; break; default: - dev_err(&pdev->dev, "invalid SAR value\n"); + dev_err(dev, "invalid SAR value\n"); return -EINVAL; } @@ -97,18 +111,16 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) cpuclk_freq *= 1000 * 1000; /* CPU clocks depend on the Sample At Reset configuration */ - of_property_read_string_index(np, "clock-output-names", - 0, &name); - ap806_clks[0] = clk_register_fixed_rate(&pdev->dev, name, NULL, + name = ap806_unique_name(dev, syscon_node, "cpu-cluster-0"); + ap806_clks[0] = clk_register_fixed_rate(dev, name, NULL, 0, cpuclk_freq); if (IS_ERR(ap806_clks[0])) { ret = PTR_ERR(ap806_clks[0]); goto fail0; } - of_property_read_string_index(np, "clock-output-names", - 1, &name); - ap806_clks[1] = clk_register_fixed_rate(&pdev->dev, name, NULL, 0, + name = ap806_unique_name(dev, syscon_node, "cpu-cluster-1"); + ap806_clks[1] = clk_register_fixed_rate(dev, name, NULL, 0, cpuclk_freq); if (IS_ERR(ap806_clks[1])) { ret = PTR_ERR(ap806_clks[1]); @@ -116,9 +128,8 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) } /* Fixed clock is always 1200 Mhz */ - of_property_read_string_index(np, "clock-output-names", - 2, &fixedclk_name); - ap806_clks[2] = clk_register_fixed_rate(&pdev->dev, fixedclk_name, NULL, + fixedclk_name = ap806_unique_name(dev, syscon_node, "fixed"); + ap806_clks[2] = clk_register_fixed_rate(dev, fixedclk_name, NULL, 0, 1200 * 1000 * 1000); if (IS_ERR(ap806_clks[2])) { ret = PTR_ERR(ap806_clks[2]); @@ -126,8 +137,7 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) } /* MSS Clock is fixed clock divided by 6 */ - of_property_read_string_index(np, "clock-output-names", - 3, &name); + name = ap806_unique_name(dev, syscon_node, "mss"); ap806_clks[3] = clk_register_fixed_factor(NULL, name, fixedclk_name, 0, 1, 6); if (IS_ERR(ap806_clks[3])) { @@ -135,20 +145,14 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) goto fail3; } - /* eMMC Clock is fixed clock divided by 3 */ - if (of_property_read_string_index(np, "clock-output-names", - 4, &name)) { - ap806_clk_data.clk_num--; - dev_warn(&pdev->dev, - "eMMC clock missing: update the device tree!\n"); - } else { - ap806_clks[4] = clk_register_fixed_factor(NULL, name, - fixedclk_name, - 0, 1, 3); - if (IS_ERR(ap806_clks[4])) { - ret = PTR_ERR(ap806_clks[4]); - goto fail4; - } + /* SDIO(/eMMC) Clock is fixed clock divided by 3 */ + name = ap806_unique_name(dev, syscon_node, "sdio"); + ap806_clks[4] = clk_register_fixed_factor(NULL, name, + fixedclk_name, + 0, 1, 3); + if (IS_ERR(ap806_clks[4])) { + ret = PTR_ERR(ap806_clks[4]); + goto fail4; } of_clk_add_provider(np, of_clk_src_onecell_get, &ap806_clk_data); @@ -172,17 +176,48 @@ static int ap806_syscon_clk_probe(struct platform_device *pdev) return ret; } -static const struct of_device_id ap806_syscon_of_match[] = { +static int ap806_syscon_legacy_probe(struct platform_device *pdev) +{ + dev_warn(&pdev->dev, FW_WARN "Using legacy device tree binding\n"); + dev_warn(&pdev->dev, FW_WARN "Update your device tree:\n"); + dev_warn(&pdev->dev, FW_WARN + "This binding won't be supported in future kernel\n"); + + return ap806_syscon_common_probe(pdev, pdev->dev.of_node); + +} + +static int ap806_clock_probe(struct platform_device *pdev) +{ + return ap806_syscon_common_probe(pdev, pdev->dev.of_node->parent); +} + +static const struct of_device_id ap806_syscon_legacy_of_match[] = { { .compatible = "marvell,ap806-system-controller", }, { } }; -static struct platform_driver ap806_syscon_driver = { - .probe = ap806_syscon_clk_probe, +static struct platform_driver ap806_syscon_legacy_driver = { + .probe = ap806_syscon_legacy_probe, .driver = { .name = "marvell-ap806-system-controller", - .of_match_table = ap806_syscon_of_match, + .of_match_table = ap806_syscon_legacy_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(ap806_syscon_legacy_driver); + +static const struct of_device_id ap806_clock_of_match[] = { + { .compatible = "marvell,ap806-clock", }, + { } +}; + +static struct platform_driver ap806_clock_driver = { + .probe = ap806_clock_probe, + .driver = { + .name = "marvell-ap806-clock", + .of_match_table = ap806_clock_of_match, .suppress_bind_attrs = true, }, }; -builtin_platform_driver(ap806_syscon_driver); +builtin_platform_driver(ap806_clock_driver); diff --git a/drivers/clk/rockchip/Kconfig b/drivers/clk/rockchip/Kconfig new file mode 100644 index 00000000000000..60c05d900622f8 --- /dev/null +++ b/drivers/clk/rockchip/Kconfig @@ -0,0 +1,39 @@ +config COMMON_CLK_RV1108 + bool "Clock driver for Rockchip RV1108" + depends on (ARCH_ROCKCHIP && ARM) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM + +config COMMON_CLK_RK3036 + bool "Clock driver for Rockchip RK3036" + depends on (ARCH_ROCKCHIP && ARM) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM + +config COMMON_CLK_RK3188 + bool "Clock driver for Rockchip RK3066 and RK3188" + depends on (ARCH_ROCKCHIP && ARM) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM + +config COMMON_CLK_RK3228 + bool "Clock driver for Rockchip RK3228 and RK3229" + depends on (ARCH_ROCKCHIP && ARM) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM + +config COMMON_CLK_RK3288 + bool "Clock driver for Rockchip RK3288" + depends on (ARCH_ROCKCHIP && ARM) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM + +config COMMON_CLK_RK3328 + bool "Clock driver for Rockchip RK3328" + depends on (ARCH_ROCKCHIP && ARM64) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM64 + +config COMMON_CLK_RK3368 + bool "Clock driver for Rockchip RK3368" + depends on (ARCH_ROCKCHIP && ARM64) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM64 + +config COMMON_CLK_RK3399 + bool "Clock driver for Rockchip RK3399" + depends on (ARCH_ROCKCHIP && ARM64) || COMPILE_TEST + default ARCH_ROCKCHIP && ARM64 diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile index 26b220c988b29c..497b7606217b7d 100644 --- a/drivers/clk/rockchip/Makefile +++ b/drivers/clk/rockchip/Makefile @@ -12,11 +12,11 @@ obj-y += clk-muxgrf.o obj-y += clk-ddr.o obj-$(CONFIG_RESET_CONTROLLER) += softrst.o -obj-y += clk-rv1108.o -obj-y += clk-rk3036.o -obj-y += clk-rk3188.o -obj-y += clk-rk3228.o -obj-y += clk-rk3288.o -obj-y += clk-rk3328.o -obj-y += clk-rk3368.o -obj-y += clk-rk3399.o +obj-$(CONFIG_COMMON_CLK_RV1108) += clk-rv1108.o +obj-$(CONFIG_COMMON_CLK_RK3036) += clk-rk3036.o +obj-$(CONFIG_COMMON_CLK_RK3188) += clk-rk3188.o +obj-$(CONFIG_COMMON_CLK_RK3228) += clk-rk3228.o +obj-$(CONFIG_COMMON_CLK_RK3288) += clk-rk3288.o +obj-$(CONFIG_COMMON_CLK_RK3328) += clk-rk3328.o +obj-$(CONFIG_COMMON_CLK_RK3368) += clk-rk3368.o +obj-$(CONFIG_COMMON_CLK_RK3399) += clk-rk3399.o diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c index db6e5a9e6de64a..d76da6d37c8b89 100644 --- a/drivers/clk/rockchip/clk-rk3228.c +++ b/drivers/clk/rockchip/clk-rk3228.c @@ -86,25 +86,43 @@ static struct rockchip_pll_rate_table rk3228_pll_rates[] = { #define RK3228_DIV_PCLK_MASK 0x7 #define RK3228_DIV_PCLK_SHIFT 12 -#define RK3228_CLKSEL1(_core_peri_div) \ +#define RK3228_CLKSEL1(_core_aclk_div, _core_peri_div) \ { \ .reg = RK2928_CLKSEL_CON(1), \ .val = HIWORD_UPDATE(_core_peri_div, RK3228_DIV_PERI_MASK, \ - RK3228_DIV_PERI_SHIFT) \ - } + RK3228_DIV_PERI_SHIFT) | \ + HIWORD_UPDATE(_core_aclk_div, RK3228_DIV_ACLK_MASK, \ + RK3228_DIV_ACLK_SHIFT), \ +} -#define RK3228_CPUCLK_RATE(_prate, _core_peri_div) \ - { \ - .prate = _prate, \ - .divs = { \ - RK3228_CLKSEL1(_core_peri_div), \ - }, \ +#define RK3228_CPUCLK_RATE(_prate, _core_aclk_div, _core_peri_div) \ + { \ + .prate = _prate, \ + .divs = { \ + RK3228_CLKSEL1(_core_aclk_div, _core_peri_div), \ + }, \ } static struct rockchip_cpuclk_rate_table rk3228_cpuclk_rates[] __initdata = { - RK3228_CPUCLK_RATE(816000000, 4), - RK3228_CPUCLK_RATE(600000000, 4), - RK3228_CPUCLK_RATE(312000000, 4), + RK3228_CPUCLK_RATE(1800000000, 1, 7), + RK3228_CPUCLK_RATE(1704000000, 1, 7), + RK3228_CPUCLK_RATE(1608000000, 1, 7), + RK3228_CPUCLK_RATE(1512000000, 1, 7), + RK3228_CPUCLK_RATE(1488000000, 1, 5), + RK3228_CPUCLK_RATE(1416000000, 1, 5), + RK3228_CPUCLK_RATE(1392000000, 1, 5), + RK3228_CPUCLK_RATE(1296000000, 1, 5), + RK3228_CPUCLK_RATE(1200000000, 1, 5), + RK3228_CPUCLK_RATE(1104000000, 1, 5), + RK3228_CPUCLK_RATE(1008000000, 1, 5), + RK3228_CPUCLK_RATE(912000000, 1, 5), + RK3228_CPUCLK_RATE(816000000, 1, 3), + RK3228_CPUCLK_RATE(696000000, 1, 3), + RK3228_CPUCLK_RATE(600000000, 1, 3), + RK3228_CPUCLK_RATE(408000000, 1, 1), + RK3228_CPUCLK_RATE(312000000, 1, 1), + RK3228_CPUCLK_RATE(216000000, 1, 1), + RK3228_CPUCLK_RATE(96000000, 1, 1), }; static const struct rockchip_cpuclk_reg_data rk3228_cpuclk_data = { @@ -252,15 +270,15 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { RK2928_CLKGATE_CON(0), 1, GFLAGS), COMPOSITE_NOGATE(0, "aclk_cpu_src", mux_aclk_cpu_src_p, 0, RK2928_CLKSEL_CON(0), 13, 2, MFLAGS, 8, 5, DFLAGS), - GATE(ARMCLK, "aclk_cpu", "aclk_cpu_src", 0, + GATE(ACLK_CPU, "aclk_cpu", "aclk_cpu_src", 0, RK2928_CLKGATE_CON(6), 0, GFLAGS), - COMPOSITE_NOMUX(0, "hclk_cpu", "aclk_cpu_src", 0, + COMPOSITE_NOMUX(HCLK_CPU, "hclk_cpu", "aclk_cpu_src", 0, RK2928_CLKSEL_CON(1), 8, 2, DFLAGS, RK2928_CLKGATE_CON(6), 1, GFLAGS), COMPOSITE_NOMUX(0, "pclk_bus_src", "aclk_cpu_src", 0, RK2928_CLKSEL_CON(1), 12, 3, DFLAGS, RK2928_CLKGATE_CON(6), 2, GFLAGS), - GATE(0, "pclk_cpu", "pclk_bus_src", 0, + GATE(PCLK_CPU, "pclk_cpu", "pclk_bus_src", 0, RK2928_CLKGATE_CON(6), 3, GFLAGS), GATE(0, "pclk_phy_pre", "pclk_bus_src", 0, RK2928_CLKGATE_CON(6), 4, GFLAGS), @@ -268,58 +286,58 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { RK2928_CLKGATE_CON(6), 13, GFLAGS), /* PD_VIDEO */ - COMPOSITE(0, "aclk_vpu_pre", mux_pll_src_4plls_p, 0, + COMPOSITE(ACLK_VPU_PRE, "aclk_vpu_pre", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(32), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 11, GFLAGS), - FACTOR_GATE(0, "hclk_vpu_pre", "aclk_vpu_pre", 0, 1, 4, + FACTOR_GATE(HCLK_VPU_PRE, "hclk_vpu_pre", "aclk_vpu_pre", 0, 1, 4, RK2928_CLKGATE_CON(4), 4, GFLAGS), - COMPOSITE(0, "aclk_rkvdec_pre", mux_pll_src_4plls_p, 0, + COMPOSITE(ACLK_RKVDEC_PRE, "aclk_rkvdec_pre", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(28), 6, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 2, GFLAGS), - FACTOR_GATE(0, "hclk_rkvdec_pre", "aclk_rkvdec_pre", 0, 1, 4, + FACTOR_GATE(HCLK_RKVDEC_PRE, "hclk_rkvdec_pre", "aclk_rkvdec_pre", 0, 1, 4, RK2928_CLKGATE_CON(4), 5, GFLAGS), - COMPOSITE(0, "sclk_vdec_cabac", mux_pll_src_4plls_p, 0, + COMPOSITE(SCLK_VDEC_CABAC, "sclk_vdec_cabac", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(28), 14, 2, MFLAGS, 8, 5, DFLAGS, RK2928_CLKGATE_CON(3), 3, GFLAGS), - COMPOSITE(0, "sclk_vdec_core", mux_pll_src_4plls_p, 0, + COMPOSITE(SCLK_VDEC_CORE, "sclk_vdec_core", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(34), 13, 2, MFLAGS, 8, 5, DFLAGS, RK2928_CLKGATE_CON(3), 4, GFLAGS), /* PD_VIO */ - COMPOSITE(0, "aclk_iep_pre", mux_pll_src_4plls_p, 0, + COMPOSITE(ACLK_IEP_PRE, "aclk_iep_pre", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(31), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 0, GFLAGS), - DIV(0, "hclk_vio_pre", "aclk_iep_pre", 0, + DIV(HCLK_VIO_PRE, "hclk_vio_pre", "aclk_iep_pre", 0, RK2928_CLKSEL_CON(2), 0, 5, DFLAGS), - COMPOSITE(0, "aclk_hdcp_pre", mux_pll_src_4plls_p, 0, + COMPOSITE(ACLK_HDCP_PRE, "aclk_hdcp_pre", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(31), 13, 2, MFLAGS, 8, 5, DFLAGS, RK2928_CLKGATE_CON(1), 4, GFLAGS), MUX(0, "sclk_rga_src", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(33), 13, 2, MFLAGS), - COMPOSITE_NOMUX(0, "aclk_rga_pre", "sclk_rga_src", 0, + COMPOSITE_NOMUX(ACLK_RGA_PRE, "aclk_rga_pre", "sclk_rga_src", 0, RK2928_CLKSEL_CON(33), 8, 5, DFLAGS, RK2928_CLKGATE_CON(1), 2, GFLAGS), - COMPOSITE(0, "sclk_rga", mux_sclk_rga_p, 0, + COMPOSITE(SCLK_RGA, "sclk_rga", mux_sclk_rga_p, 0, RK2928_CLKSEL_CON(22), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 6, GFLAGS), - COMPOSITE(0, "aclk_vop_pre", mux_pll_src_4plls_p, 0, + COMPOSITE(ACLK_VOP_PRE, "aclk_vop_pre", mux_pll_src_4plls_p, 0, RK2928_CLKSEL_CON(33), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(1), 1, GFLAGS), - COMPOSITE(0, "sclk_hdcp", mux_pll_src_3plls_p, 0, + COMPOSITE(SCLK_HDCP, "sclk_hdcp", mux_pll_src_3plls_p, 0, RK2928_CLKSEL_CON(23), 14, 2, MFLAGS, 8, 6, DFLAGS, RK2928_CLKGATE_CON(3), 5, GFLAGS), GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0, RK2928_CLKGATE_CON(3), 7, GFLAGS), - COMPOSITE(0, "sclk_hdmi_cec", mux_sclk_hdmi_cec_p, 0, + COMPOSITE(SCLK_HDMI_CEC, "sclk_hdmi_cec", mux_sclk_hdmi_cec_p, 0, RK2928_CLKSEL_CON(21), 14, 2, MFLAGS, 0, 14, DFLAGS, RK2928_CLKGATE_CON(3), 8, GFLAGS), @@ -354,18 +372,18 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(SCLK_TIMER5, "sclk_timer5", "xin24m", 0, RK2928_CLKGATE_CON(6), 10, GFLAGS), - COMPOSITE(0, "sclk_crypto", mux_pll_src_2plls_p, 0, + COMPOSITE(SCLK_CRYPTO, "sclk_crypto", mux_pll_src_2plls_p, 0, RK2928_CLKSEL_CON(24), 5, 1, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(2), 7, GFLAGS), - COMPOSITE(0, "sclk_tsp", mux_pll_src_2plls_p, 0, + COMPOSITE(SCLK_TSP, "sclk_tsp", mux_pll_src_2plls_p, 0, RK2928_CLKSEL_CON(22), 15, 1, MFLAGS, 8, 5, DFLAGS, RK2928_CLKGATE_CON(2), 6, GFLAGS), - GATE(0, "sclk_hsadc", "ext_hsadc", 0, + GATE(SCLK_HSADC, "sclk_hsadc", "ext_hsadc", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS), - COMPOSITE(0, "sclk_wifi", mux_pll_src_cpll_gpll_usb480m_p, 0, + COMPOSITE(SCLK_WIFI, "sclk_wifi", mux_pll_src_cpll_gpll_usb480m_p, 0, RK2928_CLKSEL_CON(23), 5, 2, MFLAGS, 0, 6, DFLAGS, RK2928_CLKGATE_CON(2), 15, GFLAGS), @@ -448,9 +466,9 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(0, "jtag", "ext_jtag", 0, RK2928_CLKGATE_CON(1), 3, GFLAGS), - GATE(0, "sclk_otgphy0", "xin24m", 0, + GATE(SCLK_OTGPHY0, "sclk_otgphy0", "xin24m", 0, RK2928_CLKGATE_CON(1), 5, GFLAGS), - GATE(0, "sclk_otgphy1", "xin24m", 0, + GATE(SCLK_OTGPHY1, "sclk_otgphy1", "xin24m", 0, RK2928_CLKGATE_CON(1), 6, GFLAGS), COMPOSITE_NOMUX(SCLK_TSADC, "sclk_tsadc", "xin24m", 0, @@ -526,28 +544,28 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { */ /* PD_VOP */ - GATE(0, "aclk_rga", "aclk_rga_pre", 0, RK2928_CLKGATE_CON(13), 0, GFLAGS), + GATE(ACLK_RGA, "aclk_rga", "aclk_rga_pre", 0, RK2928_CLKGATE_CON(13), 0, GFLAGS), GATE(0, "aclk_rga_noc", "aclk_rga_pre", 0, RK2928_CLKGATE_CON(13), 11, GFLAGS), - GATE(0, "aclk_iep", "aclk_iep_pre", 0, RK2928_CLKGATE_CON(13), 2, GFLAGS), + GATE(ACLK_IEP, "aclk_iep", "aclk_iep_pre", 0, RK2928_CLKGATE_CON(13), 2, GFLAGS), GATE(0, "aclk_iep_noc", "aclk_iep_pre", 0, RK2928_CLKGATE_CON(13), 9, GFLAGS), GATE(ACLK_VOP, "aclk_vop", "aclk_vop_pre", 0, RK2928_CLKGATE_CON(13), 5, GFLAGS), GATE(0, "aclk_vop_noc", "aclk_vop_pre", 0, RK2928_CLKGATE_CON(13), 12, GFLAGS), - GATE(0, "aclk_hdcp", "aclk_hdcp_pre", 0, RK2928_CLKGATE_CON(14), 10, GFLAGS), + GATE(ACLK_HDCP, "aclk_hdcp", "aclk_hdcp_pre", 0, RK2928_CLKGATE_CON(14), 10, GFLAGS), GATE(0, "aclk_hdcp_noc", "aclk_hdcp_pre", 0, RK2928_CLKGATE_CON(13), 10, GFLAGS), - GATE(0, "hclk_rga", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 1, GFLAGS), - GATE(0, "hclk_iep", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 3, GFLAGS), + GATE(HCLK_RGA, "hclk_rga", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 1, GFLAGS), + GATE(HCLK_IEP, "hclk_iep", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 3, GFLAGS), GATE(HCLK_VOP, "hclk_vop", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 6, GFLAGS), GATE(0, "hclk_vio_ahb_arbi", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 7, GFLAGS), GATE(0, "hclk_vio_noc", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 8, GFLAGS), GATE(0, "hclk_vop_noc", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(13), 13, GFLAGS), - GATE(0, "hclk_vio_h2p", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 7, GFLAGS), - GATE(0, "hclk_hdcp_mmu", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 12, GFLAGS), + GATE(HCLK_VIO_H2P, "hclk_vio_h2p", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 7, GFLAGS), + GATE(HCLK_HDCP_MMU, "hclk_hdcp_mmu", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 12, GFLAGS), GATE(PCLK_HDMI_CTRL, "pclk_hdmi_ctrl", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 6, GFLAGS), - GATE(0, "pclk_vio_h2p", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 8, GFLAGS), - GATE(0, "pclk_hdcp", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 11, GFLAGS), + GATE(PCLK_VIO_H2P, "pclk_vio_h2p", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 8, GFLAGS), + GATE(PCLK_HDCP, "pclk_hdcp", "hclk_vio_pre", 0, RK2928_CLKGATE_CON(14), 11, GFLAGS), /* PD_PERI */ GATE(0, "aclk_peri_noc", "aclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 0, GFLAGS), @@ -557,12 +575,12 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(HCLK_SDIO, "hclk_sdio", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 1, GFLAGS), GATE(HCLK_EMMC, "hclk_emmc", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 2, GFLAGS), GATE(HCLK_NANDC, "hclk_nandc", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 3, GFLAGS), - GATE(0, "hclk_host0", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 6, GFLAGS), + GATE(HCLK_HOST0, "hclk_host0", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 6, GFLAGS), GATE(0, "hclk_host0_arb", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 7, GFLAGS), - GATE(0, "hclk_host1", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 8, GFLAGS), + GATE(HCLK_HOST1, "hclk_host1", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 8, GFLAGS), GATE(0, "hclk_host1_arb", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 9, GFLAGS), - GATE(0, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 10, GFLAGS), - GATE(0, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 12, GFLAGS), + GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 10, GFLAGS), + GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 12, GFLAGS), GATE(0, "hclk_otg_pmu", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 13, GFLAGS), GATE(0, "hclk_host2_arb", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 14, GFLAGS), GATE(0, "hclk_peri_noc", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 1, GFLAGS), @@ -571,7 +589,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS), /* PD_GPU */ - GATE(0, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS), + GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS), GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 15, GFLAGS), /* PD_BUS */ @@ -585,16 +603,16 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(HCLK_I2S1_8CH, "hclk_i2s1_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 8, GFLAGS), GATE(HCLK_I2S2_2CH, "hclk_i2s2_2ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 9, GFLAGS), GATE(HCLK_SPDIF_8CH, "hclk_spdif_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 10, GFLAGS), - GATE(0, "hclk_tsp", "hclk_cpu", 0, RK2928_CLKGATE_CON(10), 11, GFLAGS), - GATE(0, "hclk_crypto_mst", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 11, GFLAGS), - GATE(0, "hclk_crypto_slv", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 12, GFLAGS), + GATE(HCLK_TSP, "hclk_tsp", "hclk_cpu", 0, RK2928_CLKGATE_CON(10), 11, GFLAGS), + GATE(HCLK_M_CRYPTO, "hclk_crypto_mst", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 11, GFLAGS), + GATE(HCLK_S_CRYPTO, "hclk_crypto_slv", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 12, GFLAGS), GATE(0, "pclk_ddrupctl", "pclk_ddr_pre", 0, RK2928_CLKGATE_CON(8), 4, GFLAGS), GATE(0, "pclk_ddrmon", "pclk_ddr_pre", 0, RK2928_CLKGATE_CON(8), 6, GFLAGS), GATE(0, "pclk_msch_noc", "pclk_ddr_pre", 0, RK2928_CLKGATE_CON(10), 2, GFLAGS), - GATE(0, "pclk_efuse_1024", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 13, GFLAGS), - GATE(0, "pclk_efuse_256", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 14, GFLAGS), + GATE(PCLK_EFUSE_1024, "pclk_efuse_1024", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 13, GFLAGS), + GATE(PCLK_EFUSE_256, "pclk_efuse_256", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 14, GFLAGS), GATE(PCLK_I2C0, "pclk_i2c0", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 15, GFLAGS), GATE(PCLK_I2C1, "pclk_i2c1", "pclk_cpu", 0, RK2928_CLKGATE_CON(9), 0, GFLAGS), GATE(PCLK_I2C2, "pclk_i2c2", "pclk_cpu", 0, RK2928_CLKGATE_CON(9), 1, GFLAGS), @@ -622,13 +640,13 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(0, "pclk_vdacphy", "pclk_phy_pre", 0, RK2928_CLKGATE_CON(10), 8, GFLAGS), GATE(0, "pclk_phy_noc", "pclk_phy_pre", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS), - GATE(0, "aclk_vpu", "aclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 0, GFLAGS), + GATE(ACLK_VPU, "aclk_vpu", "aclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 0, GFLAGS), GATE(0, "aclk_vpu_noc", "aclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 4, GFLAGS), - GATE(0, "aclk_rkvdec", "aclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 2, GFLAGS), + GATE(ACLK_RKVDEC, "aclk_rkvdec", "aclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 2, GFLAGS), GATE(0, "aclk_rkvdec_noc", "aclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 6, GFLAGS), - GATE(0, "hclk_vpu", "hclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 1, GFLAGS), + GATE(HCLK_VPU, "hclk_vpu", "hclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 1, GFLAGS), GATE(0, "hclk_vpu_noc", "hclk_vpu_pre", 0, RK2928_CLKGATE_CON(15), 5, GFLAGS), - GATE(0, "hclk_rkvdec", "hclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 3, GFLAGS), + GATE(HCLK_RKVDEC, "hclk_rkvdec", "hclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 3, GFLAGS), GATE(0, "hclk_rkvdec_noc", "hclk_rkvdec_pre", 0, RK2928_CLKGATE_CON(15), 7, GFLAGS), /* PD_MMC */ diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index fa3cbef0877632..6847120b61cdef 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1066,13 +1066,13 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { /* cif_testout */ MUX(0, "clk_testout1_pll_src", mux_pll_src_cpll_gpll_npll_p, 0, RK3399_CLKSEL_CON(38), 6, 2, MFLAGS), - COMPOSITE(0, "clk_testout1", mux_clk_testout1_p, 0, + COMPOSITE(SCLK_TESTCLKOUT1, "clk_testout1", mux_clk_testout1_p, 0, RK3399_CLKSEL_CON(38), 5, 1, MFLAGS, 0, 5, DFLAGS, RK3399_CLKGATE_CON(13), 14, GFLAGS), MUX(0, "clk_testout2_pll_src", mux_pll_src_cpll_gpll_npll_p, 0, RK3399_CLKSEL_CON(38), 14, 2, MFLAGS), - COMPOSITE(0, "clk_testout2", mux_clk_testout2_p, 0, + COMPOSITE(SCLK_TESTCLKOUT2, "clk_testout2", mux_clk_testout2_p, 0, RK3399_CLKSEL_CON(38), 13, 1, MFLAGS, 8, 5, DFLAGS, RK3399_CLKGATE_CON(13), 15, GFLAGS), diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index b0d551a8efe4d6..67acef3d2494b6 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -116,6 +116,18 @@ config SUN8I_A33_CCU default MACH_SUN8I depends on MACH_SUN8I || COMPILE_TEST +config SUN8I_A83T_CCU + bool "Support for the Allwinner A83T CCU" + select SUNXI_CCU_DIV + select SUNXI_CCU_GATE + select SUNXI_CCU_MP + select SUNXI_CCU_MULT + select SUNXI_CCU_MUX + select SUNXI_CCU_NKMP + select SUNXI_CCU_NM + select SUNXI_CCU_PHASE + default MACH_SUN8I + config SUN8I_H3_CCU bool "Support for the Allwinner H3 CCU" select SUNXI_CCU_DIV @@ -140,6 +152,11 @@ config SUN8I_V3S_CCU default MACH_SUN8I depends on MACH_SUN8I || COMPILE_TEST +config SUN8I_DE2_CCU + bool "Support for the Allwinner SoCs DE2 CCU" + select SUNXI_CCU_DIV + select SUNXI_CCU_GATE + config SUN9I_A80_CCU bool "Support for the Allwinner A80 CCU" select SUNXI_CCU_DIV @@ -156,6 +173,7 @@ config SUN8I_R_CCU bool "Support for Allwinner SoCs' PRCM CCUs" select SUNXI_CCU_DIV select SUNXI_CCU_GATE + select SUNXI_CCU_MP default MACH_SUN8I || (ARCH_SUNXI && ARM64) endif diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile index 0ec02fe14c502c..0185c6ffadcbef 100644 --- a/drivers/clk/sunxi-ng/Makefile +++ b/drivers/clk/sunxi-ng/Makefile @@ -23,8 +23,10 @@ obj-$(CONFIG_SUN5I_CCU) += ccu-sun5i.o obj-$(CONFIG_SUN6I_A31_CCU) += ccu-sun6i-a31.o obj-$(CONFIG_SUN8I_A23_CCU) += ccu-sun8i-a23.o obj-$(CONFIG_SUN8I_A33_CCU) += ccu-sun8i-a33.o +obj-$(CONFIG_SUN8I_A83T_CCU) += ccu-sun8i-a83t.o obj-$(CONFIG_SUN8I_H3_CCU) += ccu-sun8i-h3.o obj-$(CONFIG_SUN8I_V3S_CCU) += ccu-sun8i-v3s.o +obj-$(CONFIG_SUN8I_DE2_CCU) += ccu-sun8i-de2.o obj-$(CONFIG_SUN8I_R_CCU) += ccu-sun8i-r.o obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80.o obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-de.o diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index f54114c607df76..2bb4cabf802f0f 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -211,6 +211,9 @@ static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x050, 0, 2, 0); static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi", "pll-periph0" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -218,11 +221,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h index 9b3cd24b78d232..061b6fbb4f9591 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h @@ -31,7 +31,9 @@ #define CLK_PLL_VIDEO0_2X 8 #define CLK_PLL_VE 9 #define CLK_PLL_DDR0 10 -#define CLK_PLL_PERIPH0 11 + +/* PLL_PERIPH0 exported for PRCM */ + #define CLK_PLL_PERIPH0_2X 12 #define CLK_PLL_PERIPH1 13 #define CLK_PLL_PERIPH1_2X 14 diff --git a/drivers/clk/sunxi-ng/ccu-sun5i.c b/drivers/clk/sunxi-ng/ccu-sun5i.c index 5c476f966a7220..5372bf8be5e6fb 100644 --- a/drivers/clk/sunxi-ng/ccu-sun5i.c +++ b/drivers/clk/sunxi-ng/ccu-sun5i.c @@ -243,7 +243,7 @@ static SUNXI_CCU_GATE(ahb_ss_clk, "ahb-ss", "ahb", static SUNXI_CCU_GATE(ahb_dma_clk, "ahb-dma", "ahb", 0x060, BIT(6), 0); static SUNXI_CCU_GATE(ahb_bist_clk, "ahb-bist", "ahb", - 0x060, BIT(6), 0); + 0x060, BIT(7), 0); static SUNXI_CCU_GATE(ahb_mmc0_clk, "ahb-mmc0", "ahb", 0x060, BIT(8), 0); static SUNXI_CCU_GATE(ahb_mmc1_clk, "ahb-mmc1", "ahb", diff --git a/drivers/clk/sunxi-ng/ccu-sun5i.h b/drivers/clk/sunxi-ng/ccu-sun5i.h index 8144487eb7caa4..93a275fbd9a907 100644 --- a/drivers/clk/sunxi-ng/ccu-sun5i.h +++ b/drivers/clk/sunxi-ng/ccu-sun5i.h @@ -28,15 +28,17 @@ #define CLK_PLL_AUDIO_4X 6 #define CLK_PLL_AUDIO_8X 7 #define CLK_PLL_VIDEO0 8 -#define CLK_PLL_VIDEO0_2X 9 + +/* The PLL_VIDEO0_2X is exported for HDMI */ + #define CLK_PLL_VE 10 #define CLK_PLL_DDR_BASE 11 #define CLK_PLL_DDR 12 #define CLK_PLL_DDR_OTHER 13 #define CLK_PLL_PERIPH 14 #define CLK_PLL_VIDEO1 15 -#define CLK_PLL_VIDEO1_2X 16 +/* The PLL_VIDEO1_2X is exported for HDMI */ /* The CPU clock is exported */ #define CLK_AXI 18 diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 89e68d29bf456a..4d6078fca9aca6 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -195,6 +195,9 @@ static SUNXI_CCU_DIV_TABLE(axi_clk, "axi", "cpu", static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi", "pll-periph" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -203,11 +206,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { @@ -556,7 +556,7 @@ static SUNXI_CCU_M_WITH_MUX_GATE(lcd0_ch1_clk, "lcd0-ch1", lcd_ch1_parents, 0x12c, 0, 4, 24, 3, BIT(31), CLK_SET_RATE_PARENT); static SUNXI_CCU_M_WITH_MUX_GATE(lcd1_ch1_clk, "lcd1-ch1", lcd_ch1_parents, - 0x12c, 0, 4, 24, 3, BIT(31), + 0x130, 0, 4, 24, 3, BIT(31), CLK_SET_RATE_PARENT); static const char * const csi_sclk_parents[] = { "pll-video0", "pll-video1", diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a23.c b/drivers/clk/sunxi-ng/ccu-sun8i-a23.c index 5c6d37bdf247cf..8a753ed0426d40 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a23.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a23.c @@ -169,6 +169,9 @@ static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x050, 0, 2, 0); static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi" , "pll-periph" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -176,11 +179,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c index 8d38e6510e2959..10b38dc46f7595 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c @@ -180,6 +180,9 @@ static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x050, 0, 2, 0); static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi" , "pll-periph" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -187,11 +190,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c new file mode 100644 index 00000000000000..947f9f6e05d2c7 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c @@ -0,0 +1,922 @@ +/* + * Copyright (c) 2017 Chen-Yu Tsai. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include + +#include "ccu_common.h" +#include "ccu_reset.h" + +#include "ccu_div.h" +#include "ccu_gate.h" +#include "ccu_mp.h" +#include "ccu_mux.h" +#include "ccu_nkmp.h" +#include "ccu_nm.h" +#include "ccu_phase.h" + +#include "ccu-sun8i-a83t.h" + +#define CCU_SUN8I_A83T_LOCK_REG 0x20c + +/* + * The CPU PLLs are actually NP clocks, with P being /1 or /4. However + * P should only be used for output frequencies lower than 228 MHz. + * Neither mainline Linux, U-boot, nor the vendor BSPs use these. + * + * For now we can just model it as a multiplier clock, and force P to /1. + */ +#define SUN8I_A83T_PLL_C0CPUX_REG 0x000 +#define SUN8I_A83T_PLL_C1CPUX_REG 0x004 + +static struct ccu_mult pll_c0cpux_clk = { + .enable = BIT(31), + .lock = BIT(0), + .mult = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .common = { + .reg = SUN8I_A83T_PLL_C0CPUX_REG, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-c0cpux", "osc24M", + &ccu_mult_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_mult pll_c1cpux_clk = { + .enable = BIT(31), + .lock = BIT(1), + .mult = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .common = { + .reg = SUN8I_A83T_PLL_C1CPUX_REG, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-c1cpux", "osc24M", + &ccu_mult_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +/* + * The Audio PLL has d1, d2 dividers in addition to the usual N, M + * factors. Since we only need 2 frequencies from this PLL: 22.5792 MHz + * and 24.576 MHz, ignore them for now. Enforce the default for them, + * which is d1 = 0, d2 = 1. + */ +#define SUN8I_A83T_PLL_AUDIO_REG 0x008 + +static struct ccu_nm pll_audio_clk = { + .enable = BIT(31), + .lock = BIT(2), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(0, 6), + .common = { + .reg = SUN8I_A83T_PLL_AUDIO_REG, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-audio", "osc24M", + &ccu_nm_ops, CLK_SET_RATE_UNGATE), + }, +}; + +/* Some PLLs are input * N / div1 / P. Model them as NKMP with no K */ +static struct ccu_nkmp pll_video0_clk = { + .enable = BIT(31), + .lock = BIT(3), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 2), /* output divider */ + .common = { + .reg = 0x010, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-video0", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_ve_clk = { + .enable = BIT(31), + .lock = BIT(4), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x018, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-ve", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_ddr_clk = { + .enable = BIT(31), + .lock = BIT(5), + .n = _SUNXI_CCU_MULT_MIN(8, 8, 12), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x020, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-ddr", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_periph_clk = { + .enable = BIT(31), + .lock = BIT(6), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x028, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-periph", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_gpu_clk = { + .enable = BIT(31), + .lock = BIT(7), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x038, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-gpu", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_hsic_clk = { + .enable = BIT(31), + .lock = BIT(8), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x044, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-hsic", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_de_clk = { + .enable = BIT(31), + .lock = BIT(9), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(18, 1), /* output divider */ + .common = { + .reg = 0x048, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-de", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static struct ccu_nkmp pll_video1_clk = { + .enable = BIT(31), + .lock = BIT(10), + .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0), + .m = _SUNXI_CCU_DIV(16, 1), /* input divider */ + .p = _SUNXI_CCU_DIV(0, 2), /* external divider p */ + .common = { + .reg = 0x04c, + .lock_reg = CCU_SUN8I_A83T_LOCK_REG, + .features = CCU_FEATURE_LOCK_REG, + .hw.init = CLK_HW_INIT("pll-video1", "osc24M", + &ccu_nkmp_ops, + CLK_SET_RATE_UNGATE), + }, +}; + +static const char * const c0cpux_parents[] = { "osc24M", "pll-c0cpux" }; +static SUNXI_CCU_MUX(c0cpux_clk, "c0cpux", c0cpux_parents, + 0x50, 12, 1, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); + +static const char * const c1cpux_parents[] = { "osc24M", "pll-c1cpux" }; +static SUNXI_CCU_MUX(c1cpux_clk, "c1cpux", c1cpux_parents, + 0x50, 28, 1, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); + +static SUNXI_CCU_M(axi0_clk, "axi0", "c0cpux", 0x050, 0, 2, 0); +static SUNXI_CCU_M(axi1_clk, "axi1", "c1cpux", 0x050, 16, 2, 0); + +static const char * const ahb1_parents[] = { "osc16M-d512", "osc24M", + "pll-periph", + "pll-periph" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 2, .shift = 6, .width = 2 }, + { .index = 3, .shift = 6, .width = 2 }, +}; +static struct ccu_div ahb1_clk = { + .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), + .mux = { + .shift = 12, + .width = 2, + + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), + }, + .common = { + .reg = 0x054, + .hw.init = CLK_HW_INIT_PARENTS("ahb1", + ahb1_parents, + &ccu_div_ops, + 0), + }, +}; + +static SUNXI_CCU_M(apb1_clk, "apb1", "ahb1", 0x054, 8, 2, 0); + +static const char * const apb2_parents[] = { "osc16M-d512", "osc24M", + "pll-periph", "pll-periph" }; + +static SUNXI_CCU_MP_WITH_MUX(apb2_clk, "apb2", apb2_parents, 0x058, + 0, 5, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + 0); + +static const char * const ahb2_parents[] = { "ahb1", "pll-periph" }; +static const struct ccu_mux_fixed_prediv ahb2_prediv = { + .index = 1, .div = 2 +}; +static struct ccu_mux ahb2_clk = { + .mux = { + .shift = 0, + .width = 2, + .fixed_predivs = &ahb2_prediv, + .n_predivs = 1, + }, + .common = { + .reg = 0x05c, + .hw.init = CLK_HW_INIT_PARENTS("ahb2", + ahb2_parents, + &ccu_mux_ops, + 0), + }, +}; + +static SUNXI_CCU_GATE(bus_mipi_dsi_clk, "bus-mipi-dsi", "ahb1", + 0x060, BIT(1), 0); +static SUNXI_CCU_GATE(bus_ss_clk, "bus-ss", "ahb1", + 0x060, BIT(5), 0); +static SUNXI_CCU_GATE(bus_dma_clk, "bus-dma", "ahb1", + 0x060, BIT(6), 0); +static SUNXI_CCU_GATE(bus_mmc0_clk, "bus-mmc0", "ahb1", + 0x060, BIT(8), 0); +static SUNXI_CCU_GATE(bus_mmc1_clk, "bus-mmc1", "ahb1", + 0x060, BIT(9), 0); +static SUNXI_CCU_GATE(bus_mmc2_clk, "bus-mmc2", "ahb1", + 0x060, BIT(10), 0); +static SUNXI_CCU_GATE(bus_nand_clk, "bus-nand", "ahb1", + 0x060, BIT(13), 0); +static SUNXI_CCU_GATE(bus_dram_clk, "bus-dram", "ahb1", + 0x060, BIT(14), 0); +static SUNXI_CCU_GATE(bus_emac_clk, "bus-emac", "ahb2", + 0x060, BIT(17), 0); +static SUNXI_CCU_GATE(bus_hstimer_clk, "bus-hstimer", "ahb1", + 0x060, BIT(19), 0); +static SUNXI_CCU_GATE(bus_spi0_clk, "bus-spi0", "ahb1", + 0x060, BIT(20), 0); +static SUNXI_CCU_GATE(bus_spi1_clk, "bus-spi1", "ahb1", + 0x060, BIT(21), 0); +static SUNXI_CCU_GATE(bus_otg_clk, "bus-otg", "ahb1", + 0x060, BIT(24), 0); +static SUNXI_CCU_GATE(bus_ehci0_clk, "bus-ehci0", "ahb2", + 0x060, BIT(26), 0); +static SUNXI_CCU_GATE(bus_ehci1_clk, "bus-ehci1", "ahb2", + 0x060, BIT(27), 0); +static SUNXI_CCU_GATE(bus_ohci0_clk, "bus-ohci0", "ahb2", + 0x060, BIT(29), 0); + +static SUNXI_CCU_GATE(bus_ve_clk, "bus-ve", "ahb1", + 0x064, BIT(0), 0); +static SUNXI_CCU_GATE(bus_tcon0_clk, "bus-tcon0", "ahb1", + 0x064, BIT(4), 0); +static SUNXI_CCU_GATE(bus_tcon1_clk, "bus-tcon1", "ahb1", + 0x064, BIT(5), 0); +static SUNXI_CCU_GATE(bus_csi_clk, "bus-csi", "ahb1", + 0x064, BIT(8), 0); +static SUNXI_CCU_GATE(bus_hdmi_clk, "bus-hdmi", "ahb1", + 0x064, BIT(11), 0); +static SUNXI_CCU_GATE(bus_de_clk, "bus-de", "ahb1", + 0x064, BIT(12), 0); +static SUNXI_CCU_GATE(bus_gpu_clk, "bus-gpu", "ahb1", + 0x064, BIT(20), 0); +static SUNXI_CCU_GATE(bus_msgbox_clk, "bus-msgbox", "ahb1", + 0x064, BIT(21), 0); +static SUNXI_CCU_GATE(bus_spinlock_clk, "bus-spinlock", "ahb1", + 0x064, BIT(22), 0); + +static SUNXI_CCU_GATE(bus_spdif_clk, "bus-spdif", "apb1", + 0x068, BIT(1), 0); +static SUNXI_CCU_GATE(bus_pio_clk, "bus-pio", "apb1", + 0x068, BIT(5), 0); +static SUNXI_CCU_GATE(bus_i2s0_clk, "bus-i2s0", "apb1", + 0x068, BIT(12), 0); +static SUNXI_CCU_GATE(bus_i2s1_clk, "bus-i2s1", "apb1", + 0x068, BIT(13), 0); +static SUNXI_CCU_GATE(bus_i2s2_clk, "bus-i2s2", "apb1", + 0x068, BIT(14), 0); +static SUNXI_CCU_GATE(bus_tdm_clk, "bus-tdm", "apb1", + 0x068, BIT(15), 0); + +static SUNXI_CCU_GATE(bus_i2c0_clk, "bus-i2c0", "apb2", + 0x06c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_i2c1_clk, "bus-i2c1", "apb2", + 0x06c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_i2c2_clk, "bus-i2c2", "apb2", + 0x06c, BIT(0), 0); +static SUNXI_CCU_GATE(bus_uart0_clk, "bus-uart0", "apb2", + 0x06c, BIT(16), 0); +static SUNXI_CCU_GATE(bus_uart1_clk, "bus-uart1", "apb2", + 0x06c, BIT(17), 0); +static SUNXI_CCU_GATE(bus_uart2_clk, "bus-uart2", "apb2", + 0x06c, BIT(18), 0); +static SUNXI_CCU_GATE(bus_uart3_clk, "bus-uart3", "apb2", + 0x06c, BIT(19), 0); +static SUNXI_CCU_GATE(bus_uart4_clk, "bus-uart4", "apb2", + 0x06c, BIT(20), 0); + +static const char * const cci400_parents[] = { "osc24M", "pll-periph", + "pll-hsic" }; +static struct ccu_div cci400_clk = { + .div = _SUNXI_CCU_DIV_FLAGS(0, 2, 0), + .mux = _SUNXI_CCU_MUX(24, 2), + .common = { + .reg = 0x078, + .hw.init = CLK_HW_INIT_PARENTS("cci400", + cci400_parents, + &ccu_div_ops, + CLK_IS_CRITICAL), + }, +}; + +static const char * const mod0_default_parents[] = { "osc24M", "pll-periph" }; + +static SUNXI_CCU_MP_WITH_MUX_GATE(nand_clk, "nand", mod0_default_parents, + 0x080, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(mmc0_clk, "mmc0", mod0_default_parents, + 0x088, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_PHASE(mmc0_sample_clk, "mmc0-sample", "mmc0", + 0x088, 20, 3, 0); +static SUNXI_CCU_PHASE(mmc0_output_clk, "mmc0-output", "mmc0", + 0x088, 8, 3, 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(mmc1_clk, "mmc1", mod0_default_parents, + 0x08c, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_PHASE(mmc1_sample_clk, "mmc1-sample", "mmc1", + 0x08c, 20, 3, 0); +static SUNXI_CCU_PHASE(mmc1_output_clk, "mmc1-output", "mmc1", + 0x08c, 8, 3, 0); + +/* TODO Support MMC2 clock's new timing mode. */ +static SUNXI_CCU_MP_WITH_MUX_GATE(mmc2_clk, "mmc2", mod0_default_parents, + 0x090, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_PHASE(mmc2_sample_clk, "mmc2-sample", "mmc2", + 0x090, 20, 3, 0); +static SUNXI_CCU_PHASE(mmc2_output_clk, "mmc2-output", "mmc2", + 0x090, 8, 3, 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(ss_clk, "ss", mod0_default_parents, + 0x09c, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 2, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(spi0_clk, "spi0", mod0_default_parents, + 0x0a0, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 4, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_MP_WITH_MUX_GATE(spi1_clk, "spi1", mod0_default_parents, + 0x0a4, + 0, 4, /* M */ + 16, 2, /* P */ + 24, 4, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_M_WITH_GATE(i2s0_clk, "i2s0", "pll-audio", + 0x0b0, 0, 4, BIT(31), CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_GATE(i2s1_clk, "i2s1", "pll-audio", + 0x0b4, 0, 4, BIT(31), CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_GATE(i2s2_clk, "i2s2", "pll-audio", + 0x0b8, 0, 4, BIT(31), CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_GATE(tdm_clk, "tdm", "pll-audio", + 0x0bc, 0, 4, BIT(31), CLK_SET_RATE_PARENT); +static SUNXI_CCU_M_WITH_GATE(spdif_clk, "spdif", "pll-audio", + 0x0c0, 0, 4, BIT(31), CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(usb_phy0_clk, "usb-phy0", "osc24M", + 0x0cc, BIT(8), 0); +static SUNXI_CCU_GATE(usb_phy1_clk, "usb-phy1", "osc24M", + 0x0cc, BIT(9), 0); +static SUNXI_CCU_GATE(usb_hsic_clk, "usb-hsic", "pll-hsic", + 0x0cc, BIT(10), 0); +static struct ccu_gate usb_hsic_12m_clk = { + .enable = BIT(11), + .common = { + .reg = 0x0cc, + .prediv = 2, + .features = CCU_FEATURE_ALL_PREDIV, + .hw.init = CLK_HW_INIT("usb-hsic-12m", "osc24M", + &ccu_gate_ops, 0), + } +}; +static SUNXI_CCU_GATE(usb_ohci0_clk, "usb-ohci0", "osc24M", + 0x0cc, BIT(16), 0); + +/* TODO divider has minimum of 2 */ +static SUNXI_CCU_M(dram_clk, "dram", "pll-ddr", 0x0f4, 0, 4, CLK_IS_CRITICAL); + +static SUNXI_CCU_GATE(dram_ve_clk, "dram-ve", "dram", + 0x100, BIT(0), 0); +static SUNXI_CCU_GATE(dram_csi_clk, "dram-csi", "dram", + 0x100, BIT(1), 0); + +static const char * const tcon0_parents[] = { "pll-video0" }; +static SUNXI_CCU_MUX_WITH_GATE(tcon0_clk, "tcon0", tcon0_parents, + 0x118, 24, 3, BIT(31), CLK_SET_RATE_PARENT); + +static const char * const tcon1_parents[] = { "pll-video1" }; +static SUNXI_CCU_MUX_WITH_GATE(tcon1_clk, "tcon1", tcon1_parents, + 0x11c, 24, 3, BIT(31), CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(csi_misc_clk, "csi-misc", "osc24M", 0x130, BIT(16), 0); + +static SUNXI_CCU_GATE(mipi_csi_clk, "mipi-csi", "osc24M", 0x130, BIT(31), 0); + +static const char * const csi_mclk_parents[] = { "pll-de", "osc24M" }; +static const u8 csi_mclk_table[] = { 3, 5 }; +static SUNXI_CCU_M_WITH_MUX_TABLE_GATE(csi_mclk_clk, "csi-mclk", + csi_mclk_parents, csi_mclk_table, + 0x134, + 0, 5, /* M */ + 10, 3, /* mux */ + BIT(15), /* gate */ + 0); + +static const char * const csi_sclk_parents[] = { "pll-periph", "pll-ve" }; +static const u8 csi_sclk_table[] = { 0, 5 }; +static SUNXI_CCU_M_WITH_MUX_TABLE_GATE(csi_sclk_clk, "csi-sclk", + csi_sclk_parents, csi_sclk_table, + 0x134, + 16, 4, /* M */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 0); + +static SUNXI_CCU_M_WITH_GATE(ve_clk, "ve", "pll-ve", 0x13c, + 16, 3, BIT(31), CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(avs_clk, "avs", "osc24M", 0x144, BIT(31), 0); + +static const char * const hdmi_parents[] = { "pll-video1" }; +static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", hdmi_parents, + 0x150, + 0, 4, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_GATE(hdmi_slow_clk, "hdmi-slow", "osc24M", 0x154, BIT(31), 0); + +static const char * const mbus_parents[] = { "osc24M", "pll-periph", + "pll-ddr" }; +static SUNXI_CCU_M_WITH_MUX_GATE(mbus_clk, "mbus", mbus_parents, + 0x15c, + 0, 3, /* M */ + 24, 2, /* mux */ + BIT(31), /* gate */ + CLK_IS_CRITICAL); + +static const char * const mipi_dsi0_parents[] = { "pll-video0" }; +static const u8 mipi_dsi0_table[] = { 8 }; +static SUNXI_CCU_M_WITH_MUX_TABLE_GATE(mipi_dsi0_clk, "mipi-dsi0", + mipi_dsi0_parents, mipi_dsi0_table, + 0x168, + 0, 4, /* M */ + 24, 4, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static const char * const mipi_dsi1_parents[] = { "osc24M", "pll-video0" }; +static const u8 mipi_dsi1_table[] = { 0, 9 }; +static SUNXI_CCU_M_WITH_MUX_TABLE_GATE(mipi_dsi1_clk, "mipi-dsi1", + mipi_dsi1_parents, mipi_dsi1_table, + 0x16c, + 0, 4, /* M */ + 24, 4, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_M_WITH_GATE(gpu_core_clk, "gpu-core", "pll-gpu", 0x1a0, + 0, 3, BIT(31), CLK_SET_RATE_PARENT); + +static const char * const gpu_memory_parents[] = { "pll-gpu", "pll-ddr" }; +static SUNXI_CCU_M_WITH_MUX_GATE(gpu_memory_clk, "gpu-memory", + gpu_memory_parents, + 0x1a4, + 0, 3, /* M */ + 24, 1, /* mux */ + BIT(31), /* gate */ + CLK_SET_RATE_PARENT); + +static SUNXI_CCU_M_WITH_GATE(gpu_hyd_clk, "gpu-hyd", "pll-gpu", 0x1a8, + 0, 3, BIT(31), CLK_SET_RATE_PARENT); + +static struct ccu_common *sun8i_a83t_ccu_clks[] = { + &pll_c0cpux_clk.common, + &pll_c1cpux_clk.common, + &pll_audio_clk.common, + &pll_video0_clk.common, + &pll_ve_clk.common, + &pll_ddr_clk.common, + &pll_periph_clk.common, + &pll_gpu_clk.common, + &pll_hsic_clk.common, + &pll_de_clk.common, + &pll_video1_clk.common, + &c0cpux_clk.common, + &c1cpux_clk.common, + &axi0_clk.common, + &axi1_clk.common, + &ahb1_clk.common, + &ahb2_clk.common, + &apb1_clk.common, + &apb2_clk.common, + &bus_mipi_dsi_clk.common, + &bus_ss_clk.common, + &bus_dma_clk.common, + &bus_mmc0_clk.common, + &bus_mmc1_clk.common, + &bus_mmc2_clk.common, + &bus_nand_clk.common, + &bus_dram_clk.common, + &bus_emac_clk.common, + &bus_hstimer_clk.common, + &bus_spi0_clk.common, + &bus_spi1_clk.common, + &bus_otg_clk.common, + &bus_ehci0_clk.common, + &bus_ehci1_clk.common, + &bus_ohci0_clk.common, + &bus_ve_clk.common, + &bus_tcon0_clk.common, + &bus_tcon1_clk.common, + &bus_csi_clk.common, + &bus_hdmi_clk.common, + &bus_de_clk.common, + &bus_gpu_clk.common, + &bus_msgbox_clk.common, + &bus_spinlock_clk.common, + &bus_spdif_clk.common, + &bus_pio_clk.common, + &bus_i2s0_clk.common, + &bus_i2s1_clk.common, + &bus_i2s2_clk.common, + &bus_tdm_clk.common, + &bus_i2c0_clk.common, + &bus_i2c1_clk.common, + &bus_i2c2_clk.common, + &bus_uart0_clk.common, + &bus_uart1_clk.common, + &bus_uart2_clk.common, + &bus_uart3_clk.common, + &bus_uart4_clk.common, + &cci400_clk.common, + &nand_clk.common, + &mmc0_clk.common, + &mmc0_sample_clk.common, + &mmc0_output_clk.common, + &mmc1_clk.common, + &mmc1_sample_clk.common, + &mmc1_output_clk.common, + &mmc2_clk.common, + &mmc2_sample_clk.common, + &mmc2_output_clk.common, + &ss_clk.common, + &spi0_clk.common, + &spi1_clk.common, + &i2s0_clk.common, + &i2s1_clk.common, + &i2s2_clk.common, + &tdm_clk.common, + &spdif_clk.common, + &usb_phy0_clk.common, + &usb_phy1_clk.common, + &usb_hsic_clk.common, + &usb_hsic_12m_clk.common, + &usb_ohci0_clk.common, + &dram_clk.common, + &dram_ve_clk.common, + &dram_csi_clk.common, + &tcon0_clk.common, + &tcon1_clk.common, + &csi_misc_clk.common, + &mipi_csi_clk.common, + &csi_mclk_clk.common, + &csi_sclk_clk.common, + &ve_clk.common, + &avs_clk.common, + &hdmi_clk.common, + &hdmi_slow_clk.common, + &mbus_clk.common, + &mipi_dsi0_clk.common, + &mipi_dsi1_clk.common, + &gpu_core_clk.common, + &gpu_memory_clk.common, + &gpu_hyd_clk.common, +}; + +static struct clk_hw_onecell_data sun8i_a83t_hw_clks = { + .hws = { + [CLK_PLL_C0CPUX] = &pll_c0cpux_clk.common.hw, + [CLK_PLL_C1CPUX] = &pll_c1cpux_clk.common.hw, + [CLK_PLL_AUDIO] = &pll_audio_clk.common.hw, + [CLK_PLL_VIDEO0] = &pll_video0_clk.common.hw, + [CLK_PLL_VE] = &pll_ve_clk.common.hw, + [CLK_PLL_DDR] = &pll_ddr_clk.common.hw, + [CLK_PLL_PERIPH] = &pll_periph_clk.common.hw, + [CLK_PLL_GPU] = &pll_gpu_clk.common.hw, + [CLK_PLL_HSIC] = &pll_hsic_clk.common.hw, + [CLK_PLL_DE] = &pll_de_clk.common.hw, + [CLK_PLL_VIDEO1] = &pll_video1_clk.common.hw, + [CLK_C0CPUX] = &c0cpux_clk.common.hw, + [CLK_C1CPUX] = &c1cpux_clk.common.hw, + [CLK_AXI0] = &axi0_clk.common.hw, + [CLK_AXI1] = &axi1_clk.common.hw, + [CLK_AHB1] = &ahb1_clk.common.hw, + [CLK_AHB2] = &ahb2_clk.common.hw, + [CLK_APB1] = &apb1_clk.common.hw, + [CLK_APB2] = &apb2_clk.common.hw, + [CLK_BUS_MIPI_DSI] = &bus_mipi_dsi_clk.common.hw, + [CLK_BUS_SS] = &bus_ss_clk.common.hw, + [CLK_BUS_DMA] = &bus_dma_clk.common.hw, + [CLK_BUS_MMC0] = &bus_mmc0_clk.common.hw, + [CLK_BUS_MMC1] = &bus_mmc1_clk.common.hw, + [CLK_BUS_MMC2] = &bus_mmc2_clk.common.hw, + [CLK_BUS_NAND] = &bus_nand_clk.common.hw, + [CLK_BUS_DRAM] = &bus_dram_clk.common.hw, + [CLK_BUS_EMAC] = &bus_emac_clk.common.hw, + [CLK_BUS_HSTIMER] = &bus_hstimer_clk.common.hw, + [CLK_BUS_SPI0] = &bus_spi0_clk.common.hw, + [CLK_BUS_SPI1] = &bus_spi1_clk.common.hw, + [CLK_BUS_OTG] = &bus_otg_clk.common.hw, + [CLK_BUS_EHCI0] = &bus_ehci0_clk.common.hw, + [CLK_BUS_EHCI1] = &bus_ehci1_clk.common.hw, + [CLK_BUS_OHCI0] = &bus_ohci0_clk.common.hw, + [CLK_BUS_VE] = &bus_ve_clk.common.hw, + [CLK_BUS_TCON0] = &bus_tcon0_clk.common.hw, + [CLK_BUS_TCON1] = &bus_tcon1_clk.common.hw, + [CLK_BUS_CSI] = &bus_csi_clk.common.hw, + [CLK_BUS_HDMI] = &bus_hdmi_clk.common.hw, + [CLK_BUS_DE] = &bus_de_clk.common.hw, + [CLK_BUS_GPU] = &bus_gpu_clk.common.hw, + [CLK_BUS_MSGBOX] = &bus_msgbox_clk.common.hw, + [CLK_BUS_SPINLOCK] = &bus_spinlock_clk.common.hw, + [CLK_BUS_SPDIF] = &bus_spdif_clk.common.hw, + [CLK_BUS_PIO] = &bus_pio_clk.common.hw, + [CLK_BUS_I2S0] = &bus_i2s0_clk.common.hw, + [CLK_BUS_I2S1] = &bus_i2s1_clk.common.hw, + [CLK_BUS_I2S2] = &bus_i2s2_clk.common.hw, + [CLK_BUS_TDM] = &bus_tdm_clk.common.hw, + [CLK_BUS_I2C0] = &bus_i2c0_clk.common.hw, + [CLK_BUS_I2C1] = &bus_i2c1_clk.common.hw, + [CLK_BUS_I2C2] = &bus_i2c2_clk.common.hw, + [CLK_BUS_UART0] = &bus_uart0_clk.common.hw, + [CLK_BUS_UART1] = &bus_uart1_clk.common.hw, + [CLK_BUS_UART2] = &bus_uart2_clk.common.hw, + [CLK_BUS_UART3] = &bus_uart3_clk.common.hw, + [CLK_BUS_UART4] = &bus_uart4_clk.common.hw, + [CLK_CCI400] = &cci400_clk.common.hw, + [CLK_NAND] = &nand_clk.common.hw, + [CLK_MMC0] = &mmc0_clk.common.hw, + [CLK_MMC0_SAMPLE] = &mmc0_sample_clk.common.hw, + [CLK_MMC0_OUTPUT] = &mmc0_output_clk.common.hw, + [CLK_MMC1] = &mmc1_clk.common.hw, + [CLK_MMC1_SAMPLE] = &mmc1_sample_clk.common.hw, + [CLK_MMC1_OUTPUT] = &mmc1_output_clk.common.hw, + [CLK_MMC2] = &mmc2_clk.common.hw, + [CLK_MMC2_SAMPLE] = &mmc2_sample_clk.common.hw, + [CLK_MMC2_OUTPUT] = &mmc2_output_clk.common.hw, + [CLK_SS] = &ss_clk.common.hw, + [CLK_SPI0] = &spi0_clk.common.hw, + [CLK_SPI1] = &spi1_clk.common.hw, + [CLK_I2S0] = &i2s0_clk.common.hw, + [CLK_I2S1] = &i2s1_clk.common.hw, + [CLK_I2S2] = &i2s2_clk.common.hw, + [CLK_TDM] = &tdm_clk.common.hw, + [CLK_SPDIF] = &spdif_clk.common.hw, + [CLK_USB_PHY0] = &usb_phy0_clk.common.hw, + [CLK_USB_PHY1] = &usb_phy1_clk.common.hw, + [CLK_USB_HSIC] = &usb_hsic_clk.common.hw, + [CLK_USB_HSIC_12M] = &usb_hsic_12m_clk.common.hw, + [CLK_USB_OHCI0] = &usb_ohci0_clk.common.hw, + [CLK_DRAM] = &dram_clk.common.hw, + [CLK_DRAM_VE] = &dram_ve_clk.common.hw, + [CLK_DRAM_CSI] = &dram_csi_clk.common.hw, + [CLK_TCON0] = &tcon0_clk.common.hw, + [CLK_TCON1] = &tcon1_clk.common.hw, + [CLK_CSI_MISC] = &csi_misc_clk.common.hw, + [CLK_MIPI_CSI] = &mipi_csi_clk.common.hw, + [CLK_CSI_MCLK] = &csi_mclk_clk.common.hw, + [CLK_CSI_SCLK] = &csi_sclk_clk.common.hw, + [CLK_VE] = &ve_clk.common.hw, + [CLK_AVS] = &avs_clk.common.hw, + [CLK_HDMI] = &hdmi_clk.common.hw, + [CLK_HDMI_SLOW] = &hdmi_slow_clk.common.hw, + [CLK_MBUS] = &mbus_clk.common.hw, + [CLK_MIPI_DSI0] = &mipi_dsi0_clk.common.hw, + [CLK_MIPI_DSI1] = &mipi_dsi1_clk.common.hw, + [CLK_GPU_CORE] = &gpu_core_clk.common.hw, + [CLK_GPU_MEMORY] = &gpu_memory_clk.common.hw, + [CLK_GPU_HYD] = &gpu_hyd_clk.common.hw, + }, + .num = CLK_NUMBER, +}; + +static struct ccu_reset_map sun8i_a83t_ccu_resets[] = { + [RST_USB_PHY0] = { 0x0cc, BIT(0) }, + [RST_USB_PHY1] = { 0x0cc, BIT(1) }, + [RST_USB_HSIC] = { 0x0cc, BIT(2) }, + [RST_DRAM] = { 0x0f4, BIT(31) }, + [RST_MBUS] = { 0x0fc, BIT(31) }, + [RST_BUS_MIPI_DSI] = { 0x2c0, BIT(1) }, + [RST_BUS_SS] = { 0x2c0, BIT(5) }, + [RST_BUS_DMA] = { 0x2c0, BIT(6) }, + [RST_BUS_MMC0] = { 0x2c0, BIT(8) }, + [RST_BUS_MMC1] = { 0x2c0, BIT(9) }, + [RST_BUS_MMC2] = { 0x2c0, BIT(10) }, + [RST_BUS_NAND] = { 0x2c0, BIT(13) }, + [RST_BUS_DRAM] = { 0x2c0, BIT(14) }, + [RST_BUS_EMAC] = { 0x2c0, BIT(17) }, + [RST_BUS_HSTIMER] = { 0x2c0, BIT(19) }, + [RST_BUS_SPI0] = { 0x2c0, BIT(20) }, + [RST_BUS_SPI1] = { 0x2c0, BIT(21) }, + [RST_BUS_OTG] = { 0x2c0, BIT(24) }, + [RST_BUS_EHCI0] = { 0x2c0, BIT(26) }, + [RST_BUS_EHCI1] = { 0x2c0, BIT(27) }, + [RST_BUS_OHCI0] = { 0x2c0, BIT(29) }, + [RST_BUS_VE] = { 0x2c4, BIT(0) }, + [RST_BUS_TCON0] = { 0x2c4, BIT(4) }, + [RST_BUS_TCON1] = { 0x2c4, BIT(5) }, + [RST_BUS_CSI] = { 0x2c4, BIT(8) }, + [RST_BUS_HDMI0] = { 0x2c4, BIT(10) }, + [RST_BUS_HDMI1] = { 0x2c4, BIT(11) }, + [RST_BUS_DE] = { 0x2c4, BIT(12) }, + [RST_BUS_GPU] = { 0x2c4, BIT(20) }, + [RST_BUS_MSGBOX] = { 0x2c4, BIT(21) }, + [RST_BUS_SPINLOCK] = { 0x2c4, BIT(22) }, + [RST_BUS_LVDS] = { 0x2c8, BIT(0) }, + [RST_BUS_SPDIF] = { 0x2d0, BIT(1) }, + [RST_BUS_I2S0] = { 0x2d0, BIT(12) }, + [RST_BUS_I2S1] = { 0x2d0, BIT(13) }, + [RST_BUS_I2S2] = { 0x2d0, BIT(14) }, + [RST_BUS_TDM] = { 0x2d0, BIT(15) }, + [RST_BUS_I2C0] = { 0x2d8, BIT(0) }, + [RST_BUS_I2C1] = { 0x2d8, BIT(1) }, + [RST_BUS_I2C2] = { 0x2d8, BIT(2) }, + [RST_BUS_UART0] = { 0x2d8, BIT(16) }, + [RST_BUS_UART1] = { 0x2d8, BIT(17) }, + [RST_BUS_UART2] = { 0x2d8, BIT(18) }, + [RST_BUS_UART3] = { 0x2d8, BIT(19) }, + [RST_BUS_UART4] = { 0x2d8, BIT(20) }, +}; + +static const struct sunxi_ccu_desc sun8i_a83t_ccu_desc = { + .ccu_clks = sun8i_a83t_ccu_clks, + .num_ccu_clks = ARRAY_SIZE(sun8i_a83t_ccu_clks), + + .hw_clks = &sun8i_a83t_hw_clks, + + .resets = sun8i_a83t_ccu_resets, + .num_resets = ARRAY_SIZE(sun8i_a83t_ccu_resets), +}; + +#define SUN8I_A83T_PLL_P_SHIFT 16 +#define SUN8I_A83T_PLL_N_SHIFT 8 +#define SUN8I_A83T_PLL_N_WIDTH 8 + +static void sun8i_a83t_cpu_pll_fixup(void __iomem *reg) +{ + u32 val = readl(reg); + + /* bail out if P divider is not used */ + if (!(val & BIT(SUN8I_A83T_PLL_P_SHIFT))) + return; + + /* + * If P is used, output should be less than 288 MHz. When we + * set P to 1, we should also decrease the multiplier so the + * output doesn't go out of range, but not too much such that + * the multiplier stays above 12, the minimal operation value. + * + * To keep it simple, set the multiplier to 17, the reset value. + */ + val &= ~GENMASK(SUN8I_A83T_PLL_N_SHIFT + SUN8I_A83T_PLL_N_WIDTH - 1, + SUN8I_A83T_PLL_N_SHIFT); + val |= 17 << SUN8I_A83T_PLL_N_SHIFT; + + /* And clear P */ + val &= ~BIT(SUN8I_A83T_PLL_P_SHIFT); + + writel(val, reg); +} + +static int sun8i_a83t_ccu_probe(struct platform_device *pdev) +{ + struct resource *res; + void __iomem *reg; + u32 val; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + reg = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(reg)) + return PTR_ERR(reg); + + /* Enforce d1 = 0, d2 = 0 for Audio PLL */ + val = readl(reg + SUN8I_A83T_PLL_AUDIO_REG); + val &= ~(BIT(16) | BIT(18)); + writel(val, reg + SUN8I_A83T_PLL_AUDIO_REG); + + /* Enforce P = 1 for both CPU cluster PLLs */ + sun8i_a83t_cpu_pll_fixup(reg + SUN8I_A83T_PLL_C0CPUX_REG); + sun8i_a83t_cpu_pll_fixup(reg + SUN8I_A83T_PLL_C1CPUX_REG); + + return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun8i_a83t_ccu_desc); +} + +static const struct of_device_id sun8i_a83t_ccu_ids[] = { + { .compatible = "allwinner,sun8i-a83t-ccu" }, + { } +}; + +static struct platform_driver sun8i_a83t_ccu_driver = { + .probe = sun8i_a83t_ccu_probe, + .driver = { + .name = "sun8i-a83t-ccu", + .of_match_table = sun8i_a83t_ccu_ids, + }, +}; +builtin_platform_driver(sun8i_a83t_ccu_driver); diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.h b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.h new file mode 100644 index 00000000000000..d67edaf76748be --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.h @@ -0,0 +1,64 @@ +/* + * Copyright 2016 Chen-Yu Tsai + * + * Chen-Yu Tsai + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CCU_SUN8I_A83T_H_ +#define _CCU_SUN8I_A83T_H_ + +#include +#include + +#define CLK_PLL_C0CPUX 0 +#define CLK_PLL_C1CPUX 1 +#define CLK_PLL_AUDIO 2 +#define CLK_PLL_VIDEO0 3 +#define CLK_PLL_VE 4 +#define CLK_PLL_DDR 5 + +/* pll-periph is exported to the PRCM block */ + +#define CLK_PLL_GPU 7 +#define CLK_PLL_HSIC 8 + +/* pll-de is exported for the display engine */ + +#define CLK_PLL_VIDEO1 10 + +/* The CPUX clocks are exported */ + +#define CLK_AXI0 13 +#define CLK_AXI1 14 +#define CLK_AHB1 15 +#define CLK_AHB2 16 +#define CLK_APB1 17 +#define CLK_APB2 18 + +/* bus gates exported */ + +#define CLK_CCI400 58 + +/* module and usb clocks exported */ + +#define CLK_DRAM 82 + +/* dram gates and more module clocks exported */ + +#define CLK_MBUS 95 + +/* more module clocks exported */ + +#define CLK_NUMBER (CLK_GPU_HYD + 1) + +#endif /* _CCU_SUN8I_A83T_H_ */ diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c new file mode 100644 index 00000000000000..5cdaf52669e443 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c @@ -0,0 +1,260 @@ +/* + * Copyright (c) 2017 Icenowy Zheng + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include + +#include "ccu_common.h" +#include "ccu_div.h" +#include "ccu_gate.h" +#include "ccu_reset.h" + +#include "ccu-sun8i-de2.h" + +static SUNXI_CCU_GATE(bus_mixer0_clk, "bus-mixer0", "bus-de", + 0x04, BIT(0), 0); +static SUNXI_CCU_GATE(bus_mixer1_clk, "bus-mixer1", "bus-de", + 0x04, BIT(1), 0); +static SUNXI_CCU_GATE(bus_wb_clk, "bus-wb", "bus-de", + 0x04, BIT(2), 0); + +static SUNXI_CCU_GATE(mixer0_clk, "mixer0", "mixer0-div", + 0x00, BIT(0), CLK_SET_RATE_PARENT); +static SUNXI_CCU_GATE(mixer1_clk, "mixer1", "mixer1-div", + 0x00, BIT(1), CLK_SET_RATE_PARENT); +static SUNXI_CCU_GATE(wb_clk, "wb", "wb-div", + 0x00, BIT(2), CLK_SET_RATE_PARENT); + +static SUNXI_CCU_M(mixer0_div_clk, "mixer0-div", "de", 0x0c, 0, 4, + CLK_SET_RATE_PARENT); +static SUNXI_CCU_M(mixer1_div_clk, "mixer1-div", "de", 0x0c, 4, 4, + CLK_SET_RATE_PARENT); +static SUNXI_CCU_M(wb_div_clk, "wb-div", "de", 0x0c, 8, 4, + CLK_SET_RATE_PARENT); + +static struct ccu_common *sun8i_a83t_de2_clks[] = { + &mixer0_clk.common, + &mixer1_clk.common, + &wb_clk.common, + + &bus_mixer0_clk.common, + &bus_mixer1_clk.common, + &bus_wb_clk.common, + + &mixer0_div_clk.common, + &mixer1_div_clk.common, + &wb_div_clk.common, +}; + +static struct ccu_common *sun8i_v3s_de2_clks[] = { + &mixer0_clk.common, + &wb_clk.common, + + &bus_mixer0_clk.common, + &bus_wb_clk.common, + + &mixer0_div_clk.common, + &wb_div_clk.common, +}; + +static struct clk_hw_onecell_data sun8i_a83t_de2_hw_clks = { + .hws = { + [CLK_MIXER0] = &mixer0_clk.common.hw, + [CLK_MIXER1] = &mixer1_clk.common.hw, + [CLK_WB] = &wb_clk.common.hw, + + [CLK_BUS_MIXER0] = &bus_mixer0_clk.common.hw, + [CLK_BUS_MIXER1] = &bus_mixer1_clk.common.hw, + [CLK_BUS_WB] = &bus_wb_clk.common.hw, + + [CLK_MIXER0_DIV] = &mixer0_div_clk.common.hw, + [CLK_MIXER1_DIV] = &mixer1_div_clk.common.hw, + [CLK_WB_DIV] = &wb_div_clk.common.hw, + }, + .num = CLK_NUMBER, +}; + +static struct clk_hw_onecell_data sun8i_v3s_de2_hw_clks = { + .hws = { + [CLK_MIXER0] = &mixer0_clk.common.hw, + [CLK_WB] = &wb_clk.common.hw, + + [CLK_BUS_MIXER0] = &bus_mixer0_clk.common.hw, + [CLK_BUS_WB] = &bus_wb_clk.common.hw, + + [CLK_MIXER0_DIV] = &mixer0_div_clk.common.hw, + [CLK_WB_DIV] = &wb_div_clk.common.hw, + }, + .num = CLK_NUMBER, +}; + +static struct ccu_reset_map sun8i_a83t_de2_resets[] = { + [RST_MIXER0] = { 0x08, BIT(0) }, + /* + * For A83T, H3 and R40, mixer1 reset line is shared with wb, so + * only RST_WB is exported here. + * For V3s there's just no mixer1, so it also shares this struct. + */ + [RST_WB] = { 0x08, BIT(2) }, +}; + +static struct ccu_reset_map sun50i_a64_de2_resets[] = { + [RST_MIXER0] = { 0x08, BIT(0) }, + [RST_MIXER1] = { 0x08, BIT(1) }, + [RST_WB] = { 0x08, BIT(2) }, +}; + +static const struct sunxi_ccu_desc sun8i_a83t_de2_clk_desc = { + .ccu_clks = sun8i_a83t_de2_clks, + .num_ccu_clks = ARRAY_SIZE(sun8i_a83t_de2_clks), + + .hw_clks = &sun8i_a83t_de2_hw_clks, + + .resets = sun8i_a83t_de2_resets, + .num_resets = ARRAY_SIZE(sun8i_a83t_de2_resets), +}; + +static const struct sunxi_ccu_desc sun50i_a64_de2_clk_desc = { + .ccu_clks = sun8i_a83t_de2_clks, + .num_ccu_clks = ARRAY_SIZE(sun8i_a83t_de2_clks), + + .hw_clks = &sun8i_a83t_de2_hw_clks, + + .resets = sun50i_a64_de2_resets, + .num_resets = ARRAY_SIZE(sun50i_a64_de2_resets), +}; + +static const struct sunxi_ccu_desc sun8i_v3s_de2_clk_desc = { + .ccu_clks = sun8i_v3s_de2_clks, + .num_ccu_clks = ARRAY_SIZE(sun8i_v3s_de2_clks), + + .hw_clks = &sun8i_v3s_de2_hw_clks, + + .resets = sun8i_a83t_de2_resets, + .num_resets = ARRAY_SIZE(sun8i_a83t_de2_resets), +}; + +static int sunxi_de2_clk_probe(struct platform_device *pdev) +{ + struct resource *res; + struct clk *bus_clk, *mod_clk; + struct reset_control *rstc; + void __iomem *reg; + const struct sunxi_ccu_desc *ccu_desc; + int ret; + + ccu_desc = of_device_get_match_data(&pdev->dev); + if (!ccu_desc) + return -EINVAL; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + reg = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(reg)) + return PTR_ERR(reg); + + bus_clk = devm_clk_get(&pdev->dev, "bus"); + if (IS_ERR(bus_clk)) { + ret = PTR_ERR(bus_clk); + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "Couldn't get bus clk: %d\n", ret); + return ret; + } + + mod_clk = devm_clk_get(&pdev->dev, "mod"); + if (IS_ERR(mod_clk)) { + ret = PTR_ERR(mod_clk); + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "Couldn't get mod clk: %d\n", ret); + return ret; + } + + rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(rstc)) { + ret = PTR_ERR(rstc); + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, + "Couldn't get reset control: %d\n", ret); + return ret; + } + + /* The clocks need to be enabled for us to access the registers */ + ret = clk_prepare_enable(bus_clk); + if (ret) { + dev_err(&pdev->dev, "Couldn't enable bus clk: %d\n", ret); + return ret; + } + + ret = clk_prepare_enable(mod_clk); + if (ret) { + dev_err(&pdev->dev, "Couldn't enable mod clk: %d\n", ret); + goto err_disable_bus_clk; + } + + /* The reset control needs to be asserted for the controls to work */ + ret = reset_control_deassert(rstc); + if (ret) { + dev_err(&pdev->dev, + "Couldn't deassert reset control: %d\n", ret); + goto err_disable_mod_clk; + } + + ret = sunxi_ccu_probe(pdev->dev.of_node, reg, ccu_desc); + if (ret) + goto err_assert_reset; + + return 0; + +err_assert_reset: + reset_control_assert(rstc); +err_disable_mod_clk: + clk_disable_unprepare(mod_clk); +err_disable_bus_clk: + clk_disable_unprepare(bus_clk); + return ret; +} + +static const struct of_device_id sunxi_de2_clk_ids[] = { + { + .compatible = "allwinner,sun8i-a83t-de2-clk", + .data = &sun8i_a83t_de2_clk_desc, + }, + { + .compatible = "allwinner,sun8i-v3s-de2-clk", + .data = &sun8i_v3s_de2_clk_desc, + }, + { + .compatible = "allwinner,sun50i-h5-de2-clk", + .data = &sun50i_a64_de2_clk_desc, + }, + /* + * The Allwinner A64 SoC needs some bit to be poke in syscon to make + * DE2 really working. + * So there's currently no A64 compatible here. + * H5 shares the same reset line with A64, so here H5 is using the + * clock description of A64. + */ + { } +}; + +static struct platform_driver sunxi_de2_clk_driver = { + .probe = sunxi_de2_clk_probe, + .driver = { + .name = "sunxi-de2-clks", + .of_match_table = sunxi_de2_clk_ids, + }, +}; +builtin_platform_driver(sunxi_de2_clk_driver); diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-de2.h b/drivers/clk/sunxi-ng/ccu-sun8i-de2.h new file mode 100644 index 00000000000000..530c006e0ae9e2 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun8i-de2.h @@ -0,0 +1,28 @@ +/* + * Copyright 2016 Icenowy Zheng + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CCU_SUN8I_DE2_H_ +#define _CCU_SUN8I_DE2_H_ + +#include +#include + +/* Intermediary clock dividers are not exported */ +#define CLK_MIXER0_DIV 3 +#define CLK_MIXER1_DIV 4 +#define CLK_WB_DIV 5 + +#define CLK_NUMBER (CLK_WB + 1) + +#endif /* _CCU_SUN8I_DE2_H_ */ diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c index 4cbc1b701b7cf5..62e4f0d2b2fcfd 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c @@ -141,6 +141,9 @@ static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x050, 0, 2, 0); static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi" , "pll-periph0" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -148,11 +151,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.h b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h index 85973d1e8165f9..1b4baea37d8103 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-h3.h +++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h @@ -29,7 +29,9 @@ #define CLK_PLL_VIDEO 6 #define CLK_PLL_VE 7 #define CLK_PLL_DDR 8 -#define CLK_PLL_PERIPH0 9 + +/* PLL_PERIPH0 exported for PRCM */ + #define CLK_PLL_PERIPH0_2X 10 #define CLK_PLL_GPU 11 #define CLK_PLL_PERIPH1 12 diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r.c b/drivers/clk/sunxi-ng/ccu-sun8i-r.c index 119f47b568eaef..e54816ec1dbe33 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-r.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-r.c @@ -27,6 +27,11 @@ static const char * const ar100_parents[] = { "osc32k", "osc24M", "pll-periph0", "iosc" }; +static const char * const a83t_ar100_parents[] = { "osc16M-d512", "osc24M", + "pll-periph0", "iosc" }; +static const struct ccu_mux_var_prediv ar100_predivs[] = { + { .index = 2, .shift = 8, .width = 5 }, +}; static struct ccu_div ar100_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -35,11 +40,8 @@ static struct ccu_div ar100_clk = { .shift = 16, .width = 2, - .variable_prediv = { - .index = 2, - .shift = 8, - .width = 5, - }, + .var_predivs = ar100_predivs, + .n_var_predivs = ARRAY_SIZE(ar100_predivs), }, .common = { @@ -52,6 +54,27 @@ static struct ccu_div ar100_clk = { }, }; +static struct ccu_div a83t_ar100_clk = { + .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), + + .mux = { + .shift = 16, + .width = 2, + + .var_predivs = ar100_predivs, + .n_var_predivs = ARRAY_SIZE(ar100_predivs), + }, + + .common = { + .reg = 0x00, + .features = CCU_FEATURE_VARIABLE_PREDIV, + .hw.init = CLK_HW_INIT_PARENTS("ar100", + a83t_ar100_parents, + &ccu_div_ops, + 0), + }, +}; + static CLK_FIXED_FACTOR(ahb0_clk, "ahb0", "ar100", 1, 1, 0); static struct ccu_div apb0_clk = { @@ -66,6 +89,8 @@ static struct ccu_div apb0_clk = { }, }; +static SUNXI_CCU_M(a83t_apb0_clk, "apb0", "ahb0", 0x0c, 0, 2, 0); + static SUNXI_CCU_GATE(apb0_pio_clk, "apb0-pio", "apb0", 0x28, BIT(0), 0); static SUNXI_CCU_GATE(apb0_ir_clk, "apb0-ir", "apb0", @@ -90,6 +115,46 @@ static SUNXI_CCU_MP_WITH_MUX_GATE(ir_clk, "ir", BIT(31), /* gate */ 0); +static const char *const a83t_r_mod0_parents[] = { "osc16M", "osc24M" }; +static const struct ccu_mux_fixed_prediv a83t_ir_predivs[] = { + { .index = 0, .div = 16 }, +}; +static struct ccu_mp a83t_ir_clk = { + .enable = BIT(31), + + .m = _SUNXI_CCU_DIV(0, 4), + .p = _SUNXI_CCU_DIV(16, 2), + + .mux = { + .shift = 24, + .width = 2, + .fixed_predivs = a83t_ir_predivs, + .n_predivs = ARRAY_SIZE(a83t_ir_predivs), + }, + + .common = { + .reg = 0x54, + .features = CCU_FEATURE_VARIABLE_PREDIV, + .hw.init = CLK_HW_INIT_PARENTS("ir", + a83t_r_mod0_parents, + &ccu_mp_ops, + 0), + }, +}; + +static struct ccu_common *sun8i_a83t_r_ccu_clks[] = { + &a83t_ar100_clk.common, + &a83t_apb0_clk.common, + &apb0_pio_clk.common, + &apb0_ir_clk.common, + &apb0_timer_clk.common, + &apb0_rsb_clk.common, + &apb0_uart_clk.common, + &apb0_i2c_clk.common, + &apb0_twd_clk.common, + &a83t_ir_clk.common, +}; + static struct ccu_common *sun8i_h3_r_ccu_clks[] = { &ar100_clk.common, &apb0_clk.common, @@ -115,6 +180,23 @@ static struct ccu_common *sun50i_a64_r_ccu_clks[] = { &ir_clk.common, }; +static struct clk_hw_onecell_data sun8i_a83t_r_hw_clks = { + .hws = { + [CLK_AR100] = &a83t_ar100_clk.common.hw, + [CLK_AHB0] = &ahb0_clk.hw, + [CLK_APB0] = &a83t_apb0_clk.common.hw, + [CLK_APB0_PIO] = &apb0_pio_clk.common.hw, + [CLK_APB0_IR] = &apb0_ir_clk.common.hw, + [CLK_APB0_TIMER] = &apb0_timer_clk.common.hw, + [CLK_APB0_RSB] = &apb0_rsb_clk.common.hw, + [CLK_APB0_UART] = &apb0_uart_clk.common.hw, + [CLK_APB0_I2C] = &apb0_i2c_clk.common.hw, + [CLK_APB0_TWD] = &apb0_twd_clk.common.hw, + [CLK_IR] = &a83t_ir_clk.common.hw, + }, + .num = CLK_NUMBER, +}; + static struct clk_hw_onecell_data sun8i_h3_r_hw_clks = { .hws = { [CLK_AR100] = &ar100_clk.common.hw, @@ -148,6 +230,14 @@ static struct clk_hw_onecell_data sun50i_a64_r_hw_clks = { .num = CLK_NUMBER, }; +static struct ccu_reset_map sun8i_a83t_r_ccu_resets[] = { + [RST_APB0_IR] = { 0xb0, BIT(1) }, + [RST_APB0_TIMER] = { 0xb0, BIT(2) }, + [RST_APB0_RSB] = { 0xb0, BIT(3) }, + [RST_APB0_UART] = { 0xb0, BIT(4) }, + [RST_APB0_I2C] = { 0xb0, BIT(6) }, +}; + static struct ccu_reset_map sun8i_h3_r_ccu_resets[] = { [RST_APB0_IR] = { 0xb0, BIT(1) }, [RST_APB0_TIMER] = { 0xb0, BIT(2) }, @@ -163,6 +253,16 @@ static struct ccu_reset_map sun50i_a64_r_ccu_resets[] = { [RST_APB0_I2C] = { 0xb0, BIT(6) }, }; +static const struct sunxi_ccu_desc sun8i_a83t_r_ccu_desc = { + .ccu_clks = sun8i_a83t_r_ccu_clks, + .num_ccu_clks = ARRAY_SIZE(sun8i_a83t_r_ccu_clks), + + .hw_clks = &sun8i_a83t_r_hw_clks, + + .resets = sun8i_a83t_r_ccu_resets, + .num_resets = ARRAY_SIZE(sun8i_a83t_r_ccu_resets), +}; + static const struct sunxi_ccu_desc sun8i_h3_r_ccu_desc = { .ccu_clks = sun8i_h3_r_ccu_clks, .num_ccu_clks = ARRAY_SIZE(sun8i_h3_r_ccu_clks), @@ -198,6 +298,13 @@ static void __init sunxi_r_ccu_init(struct device_node *node, sunxi_ccu_probe(node, reg, desc); } +static void __init sun8i_a83t_r_ccu_setup(struct device_node *node) +{ + sunxi_r_ccu_init(node, &sun8i_a83t_r_ccu_desc); +} +CLK_OF_DECLARE(sun8i_a83t_r_ccu, "allwinner,sun8i-a83t-r-ccu", + sun8i_a83t_r_ccu_setup); + static void __init sun8i_h3_r_ccu_setup(struct device_node *node) { sunxi_r_ccu_init(node, &sun8i_h3_r_ccu_desc); diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c index e58706b40ae982..a34a78d7fb280e 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c @@ -132,6 +132,9 @@ static SUNXI_CCU_M(axi_clk, "axi", "cpu", 0x050, 0, 2, 0); static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi", "pll-periph0" }; +static const struct ccu_mux_var_prediv ahb1_predivs[] = { + { .index = 3, .shift = 6, .width = 2 }, +}; static struct ccu_div ahb1_clk = { .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO), @@ -139,11 +142,8 @@ static struct ccu_div ahb1_clk = { .shift = 12, .width = 2, - .variable_prediv = { - .index = 3, - .shift = 6, - .width = 2, - }, + .var_predivs = ahb1_predivs, + .n_var_predivs = ARRAY_SIZE(ahb1_predivs), }, .common = { @@ -537,7 +537,7 @@ static struct ccu_reset_map sun8i_v3s_ccu_resets[] = { [RST_BUS_EMAC] = { 0x2c0, BIT(17) }, [RST_BUS_HSTIMER] = { 0x2c0, BIT(19) }, [RST_BUS_SPI0] = { 0x2c0, BIT(20) }, - [RST_BUS_OTG] = { 0x2c0, BIT(23) }, + [RST_BUS_OTG] = { 0x2c0, BIT(24) }, [RST_BUS_EHCI0] = { 0x2c0, BIT(26) }, [RST_BUS_OHCI0] = { 0x2c0, BIT(29) }, diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c index 4057e6021aa9f7..c0e5c10d009103 100644 --- a/drivers/clk/sunxi-ng/ccu_div.c +++ b/drivers/clk/sunxi-ng/ccu_div.c @@ -14,23 +14,17 @@ #include "ccu_div.h" static unsigned long ccu_div_round_rate(struct ccu_mux_internal *mux, - unsigned long parent_rate, + struct clk_hw *parent, + unsigned long *parent_rate, unsigned long rate, void *data) { struct ccu_div *cd = data; - unsigned long val; - - /* - * We can't use divider_round_rate that assumes that there's - * several parents, while we might be called to evaluate - * several different parents. - */ - val = divider_get_val(rate, parent_rate, cd->div.table, cd->div.width, - cd->div.flags); - return divider_recalc_rate(&cd->common.hw, parent_rate, val, - cd->div.table, cd->div.flags); + return divider_round_rate_parent(&cd->common.hw, parent, + rate, parent_rate, + cd->div.table, cd->div.width, + cd->div.flags); } static void ccu_div_disable(struct clk_hw *hw) @@ -65,8 +59,8 @@ static unsigned long ccu_div_recalc_rate(struct clk_hw *hw, val = reg >> cd->div.shift; val &= (1 << cd->div.width) - 1; - ccu_mux_helper_adjust_parent_for_prediv(&cd->common, &cd->mux, -1, - &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cd->common, &cd->mux, -1, + parent_rate); return divider_recalc_rate(hw, parent_rate, val, cd->div.table, cd->div.flags); @@ -77,18 +71,6 @@ static int ccu_div_determine_rate(struct clk_hw *hw, { struct ccu_div *cd = hw_to_ccu_div(hw); - if (clk_hw_get_num_parents(hw) == 1) { - req->rate = divider_round_rate(hw, req->rate, - &req->best_parent_rate, - cd->div.table, - cd->div.width, - cd->div.flags); - - req->best_parent_hw = clk_hw_get_parent(hw); - - return 0; - } - return ccu_mux_helper_determine_rate(&cd->common, &cd->mux, req, ccu_div_round_rate, cd); } @@ -101,8 +83,8 @@ static int ccu_div_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long val; u32 reg; - ccu_mux_helper_adjust_parent_for_prediv(&cd->common, &cd->mux, -1, - &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cd->common, &cd->mux, -1, + parent_rate); val = divider_get_val(rate, parent_rate, cd->div.table, cd->div.width, cd->div.flags); diff --git a/drivers/clk/sunxi-ng/ccu_mp.c b/drivers/clk/sunxi-ng/ccu_mp.c index b583f186a804df..b917ad7a386c0e 100644 --- a/drivers/clk/sunxi-ng/ccu_mp.c +++ b/drivers/clk/sunxi-ng/ccu_mp.c @@ -41,7 +41,8 @@ static void ccu_mp_find_best(unsigned long parent, unsigned long rate, } static unsigned long ccu_mp_round_rate(struct ccu_mux_internal *mux, - unsigned long parent_rate, + struct clk_hw *hw, + unsigned long *parent_rate, unsigned long rate, void *data) { @@ -52,9 +53,9 @@ static unsigned long ccu_mp_round_rate(struct ccu_mux_internal *mux, max_m = cmp->m.max ?: 1 << cmp->m.width; max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1); - ccu_mp_find_best(parent_rate, rate, max_m, max_p, &m, &p); + ccu_mp_find_best(*parent_rate, rate, max_m, max_p, &m, &p); - return parent_rate / p / m; + return *parent_rate / p / m; } static void ccu_mp_disable(struct clk_hw *hw) @@ -86,8 +87,8 @@ static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw, u32 reg; /* Adjust parent_rate according to pre-dividers */ - ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux, - -1, &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cmp->common, &cmp->mux, -1, + parent_rate); reg = readl(cmp->common.base + cmp->common.reg); @@ -122,8 +123,8 @@ static int ccu_mp_set_rate(struct clk_hw *hw, unsigned long rate, u32 reg; /* Adjust parent_rate according to pre-dividers */ - ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux, - -1, &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cmp->common, &cmp->mux, -1, + parent_rate); max_m = cmp->m.max ?: 1 << cmp->m.width; max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1); diff --git a/drivers/clk/sunxi-ng/ccu_mult.c b/drivers/clk/sunxi-ng/ccu_mult.c index 67114135989529..20d0300867f29a 100644 --- a/drivers/clk/sunxi-ng/ccu_mult.c +++ b/drivers/clk/sunxi-ng/ccu_mult.c @@ -33,9 +33,10 @@ static void ccu_mult_find_best(unsigned long parent, unsigned long rate, } static unsigned long ccu_mult_round_rate(struct ccu_mux_internal *mux, - unsigned long parent_rate, - unsigned long rate, - void *data) + struct clk_hw *parent, + unsigned long *parent_rate, + unsigned long rate, + void *data) { struct ccu_mult *cm = data; struct _ccu_mult _cm; @@ -47,9 +48,9 @@ static unsigned long ccu_mult_round_rate(struct ccu_mux_internal *mux, else _cm.max = (1 << cm->mult.width) + cm->mult.offset - 1; - ccu_mult_find_best(parent_rate, rate, &_cm); + ccu_mult_find_best(*parent_rate, rate, &_cm); - return parent_rate * _cm.mult; + return *parent_rate * _cm.mult; } static void ccu_mult_disable(struct clk_hw *hw) @@ -87,8 +88,8 @@ static unsigned long ccu_mult_recalc_rate(struct clk_hw *hw, val = reg >> cm->mult.shift; val &= (1 << cm->mult.width) - 1; - ccu_mux_helper_adjust_parent_for_prediv(&cm->common, &cm->mux, -1, - &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cm->common, &cm->mux, -1, + parent_rate); return parent_rate * (val + cm->mult.offset); } @@ -115,8 +116,8 @@ static int ccu_mult_set_rate(struct clk_hw *hw, unsigned long rate, else ccu_frac_helper_disable(&cm->common, &cm->frac); - ccu_mux_helper_adjust_parent_for_prediv(&cm->common, &cm->mux, -1, - &parent_rate); + parent_rate = ccu_mux_helper_apply_prediv(&cm->common, &cm->mux, -1, + parent_rate); _cm.min = cm->mult.min; diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c index c6bb1f5232326f..cfe4538304fb5b 100644 --- a/drivers/clk/sunxi-ng/ccu_mux.c +++ b/drivers/clk/sunxi-ng/ccu_mux.c @@ -15,24 +15,20 @@ #include "ccu_gate.h" #include "ccu_mux.h" -void ccu_mux_helper_adjust_parent_for_prediv(struct ccu_common *common, - struct ccu_mux_internal *cm, - int parent_index, - unsigned long *parent_rate) +static u16 ccu_mux_get_prediv(struct ccu_common *common, + struct ccu_mux_internal *cm, + int parent_index) { u16 prediv = 1; u32 reg; - int i; if (!((common->features & CCU_FEATURE_FIXED_PREDIV) || (common->features & CCU_FEATURE_VARIABLE_PREDIV) || (common->features & CCU_FEATURE_ALL_PREDIV))) - return; + return 1; - if (common->features & CCU_FEATURE_ALL_PREDIV) { - *parent_rate = *parent_rate / common->prediv; - return; - } + if (common->features & CCU_FEATURE_ALL_PREDIV) + return common->prediv; reg = readl(common->base + common->reg); if (parent_index < 0) { @@ -40,28 +36,52 @@ void ccu_mux_helper_adjust_parent_for_prediv(struct ccu_common *common, parent_index &= (1 << cm->width) - 1; } - if (common->features & CCU_FEATURE_FIXED_PREDIV) + if (common->features & CCU_FEATURE_FIXED_PREDIV) { + int i; + for (i = 0; i < cm->n_predivs; i++) if (parent_index == cm->fixed_predivs[i].index) prediv = cm->fixed_predivs[i].div; + } - if (common->features & CCU_FEATURE_VARIABLE_PREDIV) - if (parent_index == cm->variable_prediv.index) { - u8 div; + if (common->features & CCU_FEATURE_VARIABLE_PREDIV) { + int i; - div = reg >> cm->variable_prediv.shift; - div &= (1 << cm->variable_prediv.width) - 1; - prediv = div + 1; - } + for (i = 0; i < cm->n_var_predivs; i++) + if (parent_index == cm->var_predivs[i].index) { + u8 div; + + div = reg >> cm->var_predivs[i].shift; + div &= (1 << cm->var_predivs[i].width) - 1; + prediv = div + 1; + } + } + + return prediv; +} - *parent_rate = *parent_rate / prediv; +unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common, + struct ccu_mux_internal *cm, + int parent_index, + unsigned long parent_rate) +{ + return parent_rate / ccu_mux_get_prediv(common, cm, parent_index); +} + +unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common, + struct ccu_mux_internal *cm, + int parent_index, + unsigned long parent_rate) +{ + return parent_rate * ccu_mux_get_prediv(common, cm, parent_index); } int ccu_mux_helper_determine_rate(struct ccu_common *common, struct ccu_mux_internal *cm, struct clk_rate_request *req, unsigned long (*round)(struct ccu_mux_internal *, - unsigned long, + struct clk_hw *, + unsigned long *, unsigned long, void *), void *data) @@ -75,41 +95,43 @@ int ccu_mux_helper_determine_rate(struct ccu_common *common, best_parent = clk_hw_get_parent(hw); best_parent_rate = clk_hw_get_rate(best_parent); + adj_parent_rate = ccu_mux_helper_apply_prediv(common, cm, -1, + best_parent_rate); - adj_parent_rate = best_parent_rate; - ccu_mux_helper_adjust_parent_for_prediv(common, cm, -1, - &adj_parent_rate); + best_rate = round(cm, best_parent, &adj_parent_rate, + req->rate, data); - best_rate = round(cm, adj_parent_rate, req->rate, data); + /* + * adj_parent_rate might have been modified by our clock. + * Unapply the pre-divider if there's one, and give + * the actual frequency the parent needs to run at. + */ + best_parent_rate = ccu_mux_helper_unapply_prediv(common, cm, -1, + adj_parent_rate); goto out; } for (i = 0; i < clk_hw_get_num_parents(hw); i++) { - unsigned long tmp_rate, parent_rate, adj_parent_rate; + unsigned long tmp_rate, parent_rate; struct clk_hw *parent; parent = clk_hw_get_parent_by_index(hw, i); if (!parent) continue; - if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) { - struct clk_rate_request parent_req = *req; - int ret = __clk_determine_rate(parent, &parent_req); - - if (ret) - continue; + parent_rate = ccu_mux_helper_apply_prediv(common, cm, i, + clk_hw_get_rate(parent)); - parent_rate = parent_req.rate; - } else { - parent_rate = clk_hw_get_rate(parent); - } + tmp_rate = round(cm, parent, &parent_rate, req->rate, data); - adj_parent_rate = parent_rate; - ccu_mux_helper_adjust_parent_for_prediv(common, cm, i, - &adj_parent_rate); - - tmp_rate = round(cm, adj_parent_rate, req->rate, data); + /* + * parent_rate might have been modified by our clock. + * Unapply the pre-divider if there's one, and give + * the actual frequency the parent needs to run at. + */ + parent_rate = ccu_mux_helper_unapply_prediv(common, cm, i, + parent_rate); if (tmp_rate == req->rate) { best_parent = parent; best_parent_rate = parent_rate; @@ -217,10 +239,8 @@ static unsigned long ccu_mux_recalc_rate(struct clk_hw *hw, { struct ccu_mux *cm = hw_to_ccu_mux(hw); - ccu_mux_helper_adjust_parent_for_prediv(&cm->common, &cm->mux, -1, - &parent_rate); - - return parent_rate; + return ccu_mux_helper_apply_prediv(&cm->common, &cm->mux, -1, + parent_rate); } const struct clk_ops ccu_mux_ops = { diff --git a/drivers/clk/sunxi-ng/ccu_mux.h b/drivers/clk/sunxi-ng/ccu_mux.h index 47aba3a48245f8..f20c0bd62a47fb 100644 --- a/drivers/clk/sunxi-ng/ccu_mux.h +++ b/drivers/clk/sunxi-ng/ccu_mux.h @@ -10,6 +10,12 @@ struct ccu_mux_fixed_prediv { u16 div; }; +struct ccu_mux_var_prediv { + u8 index; + u8 shift; + u8 width; +}; + struct ccu_mux_internal { u8 shift; u8 width; @@ -18,11 +24,8 @@ struct ccu_mux_internal { const struct ccu_mux_fixed_prediv *fixed_predivs; u8 n_predivs; - struct { - u8 index; - u8 shift; - u8 width; - } variable_prediv; + const struct ccu_mux_var_prediv *var_predivs; + u8 n_var_predivs; }; #define _SUNXI_CCU_MUX_TABLE(_shift, _width, _table) \ @@ -78,15 +81,16 @@ static inline struct ccu_mux *hw_to_ccu_mux(struct clk_hw *hw) extern const struct clk_ops ccu_mux_ops; -void ccu_mux_helper_adjust_parent_for_prediv(struct ccu_common *common, - struct ccu_mux_internal *cm, - int parent_index, - unsigned long *parent_rate); +unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common, + struct ccu_mux_internal *cm, + int parent_index, + unsigned long parent_rate); int ccu_mux_helper_determine_rate(struct ccu_common *common, struct ccu_mux_internal *cm, struct clk_rate_request *req, unsigned long (*round)(struct ccu_mux_internal *, - unsigned long, + struct clk_hw *, + unsigned long *, unsigned long, void *), void *data); diff --git a/drivers/clk/sunxi-ng/ccu_nkm.c b/drivers/clk/sunxi-ng/ccu_nkm.c index cba84afe1cf1d4..44b16dc8fea6b8 100644 --- a/drivers/clk/sunxi-ng/ccu_nkm.c +++ b/drivers/clk/sunxi-ng/ccu_nkm.c @@ -102,7 +102,8 @@ static unsigned long ccu_nkm_recalc_rate(struct clk_hw *hw, } static unsigned long ccu_nkm_round_rate(struct ccu_mux_internal *mux, - unsigned long parent_rate, + struct clk_hw *hw, + unsigned long *parent_rate, unsigned long rate, void *data) { @@ -116,9 +117,9 @@ static unsigned long ccu_nkm_round_rate(struct ccu_mux_internal *mux, _nkm.min_m = 1; _nkm.max_m = nkm->m.max ?: 1 << nkm->m.width; - ccu_nkm_find_best(parent_rate, rate, &_nkm); + ccu_nkm_find_best(*parent_rate, rate, &_nkm); - return parent_rate * _nkm.n * _nkm.k / _nkm.m; + return *parent_rate * _nkm.n * _nkm.k / _nkm.m; } static int ccu_nkm_determine_rate(struct clk_hw *hw, diff --git a/drivers/clk/sunxi-ng/ccu_reset.h b/drivers/clk/sunxi-ng/ccu_reset.h index 36a4679210bd4d..ff8f5ebca43575 100644 --- a/drivers/clk/sunxi-ng/ccu_reset.h +++ b/drivers/clk/sunxi-ng/ccu_reset.h @@ -15,6 +15,7 @@ #define _CCU_RESET_H_ #include +#include struct ccu_reset_map { u16 reg; diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index 418042201e6da9..ea6d62547b10de 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -540,7 +540,7 @@ static void bL_cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); cdev[cur_cluster] = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(cdev[cur_cluster])) { dev_err(cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index c943787d761ee4..fef3c21606911b 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -326,7 +326,7 @@ static void cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); priv->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(priv->cdev)) { dev_err(priv->cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 0e3f6496524d92..29c5b0cbad967e 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -887,7 +887,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; - get_online_cpus(); + cpus_read_lock(); if (cpu_online(policy->cpu)) { down_write(&policy->rwsem); @@ -895,7 +895,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, up_write(&policy->rwsem); } - put_online_cpus(); + cpus_read_unlock(); return ret; } @@ -2441,7 +2441,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) pr_debug("trying to register driver %s\n", driver_data->name); /* Protect against concurrent CPU online/offline. */ - get_online_cpus(); + cpus_read_lock(); write_lock_irqsave(&cpufreq_driver_lock, flags); if (cpufreq_driver) { @@ -2468,14 +2468,16 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && list_empty(&cpufreq_policy_list)) { /* if all ->init() calls failed, unregister */ + ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, driver_data->name); goto err_if_unreg; } - ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online", - cpuhp_cpufreq_online, - cpuhp_cpufreq_offline); + ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, + "cpufreq:online", + cpuhp_cpufreq_online, + cpuhp_cpufreq_offline); if (ret < 0) goto err_if_unreg; hp_online = ret; @@ -2493,7 +2495,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) cpufreq_driver = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); out: - put_online_cpus(); + cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(cpufreq_register_driver); @@ -2516,17 +2518,17 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) pr_debug("unregistering driver %s\n", driver->name); /* Protect against concurrent cpu hotplug */ - get_online_cpus(); + cpus_read_lock(); subsys_interface_unregister(&cpufreq_interface); remove_boost_sysfs_file(); - cpuhp_remove_state_nocalls(hp_online); + cpuhp_remove_state_nocalls_cpuslocked(hp_online); write_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - put_online_cpus(); + cpus_read_unlock(); return 0; } diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index f570ead624547e..9c3d319dc1290f 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -170,11 +170,10 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) unsigned int i = 0, count = 0, ret = -ENOMEM; struct cpufreq_stats *stats; unsigned int alloc_size; - struct cpufreq_frequency_table *pos, *table; + struct cpufreq_frequency_table *pos; - /* We need cpufreq table for creating stats table */ - table = policy->freq_table; - if (unlikely(!table)) + count = cpufreq_table_count_valid_entries(policy); + if (!count) return; /* stats already initialized */ @@ -185,10 +184,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) if (!stats) return; - /* Find total allocation size */ - cpufreq_for_each_valid_entry(pos, table) - count++; - alloc_size = count * sizeof(int) + count * sizeof(u64); alloc_size += count * count * sizeof(int); @@ -205,7 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->max_state = count; /* Find valid-unique entries */ - cpufreq_for_each_valid_entry(pos, table) + cpufreq_for_each_valid_entry(pos, policy->freq_table) if (freq_table_get_index(stats, pos->frequency) == -1) stats->freq_table[i++] = pos->frequency; diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c index 3575b82210ba05..4ee0431579c173 100644 --- a/drivers/cpufreq/dbx500-cpufreq.c +++ b/drivers/cpufreq/dbx500-cpufreq.c @@ -43,7 +43,7 @@ static int dbx500_cpufreq_exit(struct cpufreq_policy *policy) static void dbx500_cpufreq_ready(struct cpufreq_policy *policy) { - cdev = cpufreq_cooling_register(policy->cpus); + cdev = cpufreq_cooling_register(policy); if (IS_ERR(cdev)) pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev)); else diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7de5bd76a3174..36ba6082d084b4 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -652,6 +652,12 @@ static const char * const energy_perf_strings[] = { "power", NULL }; +static const unsigned int epp_values[] = { + HWP_EPP_PERFORMANCE, + HWP_EPP_BALANCE_PERFORMANCE, + HWP_EPP_BALANCE_POWERSAVE, + HWP_EPP_POWERSAVE +}; static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) { @@ -663,17 +669,14 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) return epp; if (static_cpu_has(X86_FEATURE_HWP_EPP)) { - /* - * Range: - * 0x00-0x3F : Performance - * 0x40-0x7F : Balance performance - * 0x80-0xBF : Balance power - * 0xC0-0xFF : Power - * The EPP is a 8 bit value, but our ranges restrict the - * value which can be set. Here only using top two bits - * effectively. - */ - index = (epp >> 6) + 1; + if (epp == HWP_EPP_PERFORMANCE) + return 1; + if (epp <= HWP_EPP_BALANCE_PERFORMANCE) + return 2; + if (epp <= HWP_EPP_BALANCE_POWERSAVE) + return 3; + else + return 4; } else if (static_cpu_has(X86_FEATURE_EPB)) { /* * Range: @@ -711,15 +714,8 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, value &= ~GENMASK_ULL(31, 24); - /* - * If epp is not default, convert from index into - * energy_perf_strings to epp value, by shifting 6 - * bits left to use only top two bits in epp. - * The resultant epp need to shifted by 24 bits to - * epp position in MSR_HWP_REQUEST. - */ if (epp == -EINVAL) - epp = (pref_index - 1) << 6; + epp = epp_values[pref_index - 1]; value |= (u64)epp << 24; ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value); diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c index 1b9bcd76c60e33..c2dd43f3f5d8a3 100644 --- a/drivers/cpufreq/kirkwood-cpufreq.c +++ b/drivers/cpufreq/kirkwood-cpufreq.c @@ -127,7 +127,12 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev) return PTR_ERR(priv.cpu_clk); } - clk_prepare_enable(priv.cpu_clk); + err = clk_prepare_enable(priv.cpu_clk); + if (err) { + dev_err(priv.dev, "Unable to prepare cpuclk\n"); + return err; + } + kirkwood_freq_table[0].frequency = clk_get_rate(priv.cpu_clk) / 1000; priv.ddr_clk = of_clk_get_by_name(np, "ddrclk"); @@ -137,7 +142,11 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev) goto out_cpu; } - clk_prepare_enable(priv.ddr_clk); + err = clk_prepare_enable(priv.ddr_clk); + if (err) { + dev_err(priv.dev, "Unable to prepare ddrclk\n"); + goto out_cpu; + } kirkwood_freq_table[1].frequency = clk_get_rate(priv.ddr_clk) / 1000; priv.powersave_clk = of_clk_get_by_name(np, "powersave"); @@ -146,7 +155,11 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev) err = PTR_ERR(priv.powersave_clk); goto out_ddr; } - clk_prepare_enable(priv.powersave_clk); + err = clk_prepare_enable(priv.powersave_clk); + if (err) { + dev_err(priv.dev, "Unable to prepare powersave clk\n"); + goto out_ddr; + } of_node_put(np); np = NULL; diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index fd1886faf33abc..f9f00fb4bc3a82 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -320,9 +320,7 @@ static void mtk_cpufreq_ready(struct cpufreq_policy *policy) of_property_read_u32(np, DYNAMIC_POWER, &capacitance); info->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, - capacitance, - NULL); + policy, capacitance, NULL); if (IS_ERR(info->cdev)) { dev_err(info->cpu_dev, diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 35dd4d7ffee082..b257fc7d520410 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -226,7 +226,7 @@ static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) * We don't support CPU hotplug. Don't unmap after the system * has already made it to a running state. */ - if (system_state != SYSTEM_BOOTING) + if (system_state >= SYSTEM_RUNNING) return 0; if (sdcasr_mapbase) diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index e2ea433a5f9c3c..4ada55b8856e1e 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -278,8 +278,7 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy) struct device_node *np = of_get_cpu_node(policy->cpu, NULL); if (of_find_property(np, "#cooling-cells", NULL)) { - cpud->cdev = of_cpufreq_cooling_register(np, - policy->related_cpus); + cpud->cdev = of_cpufreq_cooling_register(np, policy); if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) { pr_err("cpu%d is not running as cooling device: %ld\n", diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 12409a519cc5c4..45eaf06462aedd 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -354,6 +354,7 @@ static int powernv_add_idle_states(void) for (i = 0; i < dt_idle_states; i++) { unsigned int exit_latency, target_residency; + bool stops_timebase = false; /* * If an idle state has exit latency beyond * POWERNV_THRESHOLD_LATENCY_NS then don't use it @@ -381,6 +382,9 @@ static int powernv_add_idle_states(void) } } + if (flags[i] & OPAL_PM_TIMEBASE_STOP) + stops_timebase = true; + /* * For nap and fastsleep, use default target_residency * values if f/w does not expose it. @@ -392,8 +396,7 @@ static int powernv_add_idle_states(void) add_powernv_state(nr_idle_states, "Nap", CPUIDLE_FLAG_NONE, nap_loop, target_residency, exit_latency, 0, 0); - } else if ((flags[i] & OPAL_PM_STOP_INST_FAST) && - !(flags[i] & OPAL_PM_TIMEBASE_STOP)) { + } else if (has_stop_states && !stops_timebase) { add_powernv_state(nr_idle_states, names[i], CPUIDLE_FLAG_NONE, stop_loop, target_residency, exit_latency, @@ -405,8 +408,8 @@ static int powernv_add_idle_states(void) * within this config dependency check. */ #ifdef CONFIG_TICK_ONESHOT - if (flags[i] & OPAL_PM_SLEEP_ENABLED || - flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) { + else if (flags[i] & OPAL_PM_SLEEP_ENABLED || + flags[i] & OPAL_PM_SLEEP_ENABLED_ER1) { if (!rc) target_residency = 300000; /* Add FASTSLEEP state */ @@ -414,14 +417,15 @@ static int powernv_add_idle_states(void) CPUIDLE_FLAG_TIMER_STOP, fastsleep_loop, target_residency, exit_latency, 0, 0); - } else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) && - (flags[i] & OPAL_PM_TIMEBASE_STOP)) { + } else if (has_stop_states && stops_timebase) { add_powernv_state(nr_idle_states, names[i], CPUIDLE_FLAG_TIMER_STOP, stop_loop, target_residency, exit_latency, psscr_val[i], psscr_mask[i]); } #endif + else + continue; nr_idle_states++; } out: diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 2706be7ed3340f..60bb64f4329da2 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -220,6 +220,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, entered_state = target_state->enter(dev, drv, index); start_critical_timings(); + sched_clock_idle_wakeup_event(); time_end = ns_to_ktime(local_clock()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index fb1e60f5002ef9..9c7951bb05ac77 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -89,6 +89,20 @@ config PKEY requires to have at least one CEX card in coprocessor mode available at runtime. +config CRYPTO_PAES_S390 + tristate "PAES cipher algorithms" + depends on S390 + depends on ZCRYPT + depends on PKEY + select CRYPTO_ALGAPI + select CRYPTO_BLKCIPHER + help + This is the s390 hardware accelerated implementation of the + AES cipher algorithms for use with protected key. + + Select this option if you want to use the paes cipher + for example to use protected key encrypted devices. + config CRYPTO_SHA1_S390 tristate "SHA1 digest algorithm" depends on S390 @@ -137,7 +151,6 @@ config CRYPTO_AES_S390 depends on S390 select CRYPTO_ALGAPI select CRYPTO_BLKCIPHER - select PKEY help This is the s390 hardware accelerated implementation of the AES cipher algorithms (FIPS-197). diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c index cc0d5b98006ea9..61393dc70b0bc2 100644 --- a/drivers/crypto/bcm/cipher.c +++ b/drivers/crypto/bcm/cipher.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -2510,8 +2511,8 @@ static int ahash_hmac_setkey(struct crypto_ahash *ahash, const u8 *key, memcpy(ctx->opad, ctx->ipad, blocksize); for (index = 0; index < blocksize; index++) { - ctx->ipad[index] ^= 0x36; - ctx->opad[index] ^= 0x5c; + ctx->ipad[index] ^= HMAC_IPAD_VALUE; + ctx->opad[index] ^= HMAC_OPAD_VALUE; } flow_dump(" ipad: ", ctx->ipad, blocksize); diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index 49cbdcba788307..57f399caa977b1 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -18,6 +18,10 @@ #define DESC_RSA_PUB_LEN (2 * CAAM_CMD_SZ + sizeof(struct rsa_pub_pdb)) #define DESC_RSA_PRIV_F1_LEN (2 * CAAM_CMD_SZ + \ sizeof(struct rsa_priv_f1_pdb)) +#define DESC_RSA_PRIV_F2_LEN (2 * CAAM_CMD_SZ + \ + sizeof(struct rsa_priv_f2_pdb)) +#define DESC_RSA_PRIV_F3_LEN (2 * CAAM_CMD_SZ + \ + sizeof(struct rsa_priv_f3_pdb)) static void rsa_io_unmap(struct device *dev, struct rsa_edesc *edesc, struct akcipher_request *req) @@ -54,6 +58,42 @@ static void rsa_priv_f1_unmap(struct device *dev, struct rsa_edesc *edesc, dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE); } +static void rsa_priv_f2_unmap(struct device *dev, struct rsa_edesc *edesc, + struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct caam_rsa_key *key = &ctx->key; + struct rsa_priv_f2_pdb *pdb = &edesc->pdb.priv_f2; + size_t p_sz = key->p_sz; + size_t q_sz = key->p_sz; + + dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); +} + +static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc, + struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct caam_rsa_key *key = &ctx->key; + struct rsa_priv_f3_pdb *pdb = &edesc->pdb.priv_f3; + size_t p_sz = key->p_sz; + size_t q_sz = key->p_sz; + + dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->dp_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->dq_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); +} + /* RSA Job Completion handler */ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context) { @@ -90,6 +130,42 @@ static void rsa_priv_f1_done(struct device *dev, u32 *desc, u32 err, akcipher_request_complete(req, err); } +static void rsa_priv_f2_done(struct device *dev, u32 *desc, u32 err, + void *context) +{ + struct akcipher_request *req = context; + struct rsa_edesc *edesc; + + if (err) + caam_jr_strstatus(dev, err); + + edesc = container_of(desc, struct rsa_edesc, hw_desc[0]); + + rsa_priv_f2_unmap(dev, edesc, req); + rsa_io_unmap(dev, edesc, req); + kfree(edesc); + + akcipher_request_complete(req, err); +} + +static void rsa_priv_f3_done(struct device *dev, u32 *desc, u32 err, + void *context) +{ + struct akcipher_request *req = context; + struct rsa_edesc *edesc; + + if (err) + caam_jr_strstatus(dev, err); + + edesc = container_of(desc, struct rsa_edesc, hw_desc[0]); + + rsa_priv_f3_unmap(dev, edesc, req); + rsa_io_unmap(dev, edesc, req); + kfree(edesc); + + akcipher_request_complete(req, err); +} + static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req, size_t desclen) { @@ -258,6 +334,172 @@ static int set_rsa_priv_f1_pdb(struct akcipher_request *req, return 0; } +static int set_rsa_priv_f2_pdb(struct akcipher_request *req, + struct rsa_edesc *edesc) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct caam_rsa_key *key = &ctx->key; + struct device *dev = ctx->dev; + struct rsa_priv_f2_pdb *pdb = &edesc->pdb.priv_f2; + int sec4_sg_index = 0; + size_t p_sz = key->p_sz; + size_t q_sz = key->p_sz; + + pdb->d_dma = dma_map_single(dev, key->d, key->d_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->d_dma)) { + dev_err(dev, "Unable to map RSA private exponent memory\n"); + return -ENOMEM; + } + + pdb->p_dma = dma_map_single(dev, key->p, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->p_dma)) { + dev_err(dev, "Unable to map RSA prime factor p memory\n"); + goto unmap_d; + } + + pdb->q_dma = dma_map_single(dev, key->q, q_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->q_dma)) { + dev_err(dev, "Unable to map RSA prime factor q memory\n"); + goto unmap_p; + } + + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->tmp1_dma)) { + dev_err(dev, "Unable to map RSA tmp1 memory\n"); + goto unmap_q; + } + + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->tmp2_dma)) { + dev_err(dev, "Unable to map RSA tmp2 memory\n"); + goto unmap_tmp1; + } + + if (edesc->src_nents > 1) { + pdb->sgf |= RSA_PRIV_PDB_SGF_G; + pdb->g_dma = edesc->sec4_sg_dma; + sec4_sg_index += edesc->src_nents; + } else { + pdb->g_dma = sg_dma_address(req->src); + } + + if (edesc->dst_nents > 1) { + pdb->sgf |= RSA_PRIV_PDB_SGF_F; + pdb->f_dma = edesc->sec4_sg_dma + + sec4_sg_index * sizeof(struct sec4_sg_entry); + } else { + pdb->f_dma = sg_dma_address(req->dst); + } + + pdb->sgf |= (key->d_sz << RSA_PDB_D_SHIFT) | key->n_sz; + pdb->p_q_len = (q_sz << RSA_PDB_Q_SHIFT) | p_sz; + + return 0; + +unmap_tmp1: + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); +unmap_q: + dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); +unmap_p: + dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); +unmap_d: + dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE); + + return -ENOMEM; +} + +static int set_rsa_priv_f3_pdb(struct akcipher_request *req, + struct rsa_edesc *edesc) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct caam_rsa_key *key = &ctx->key; + struct device *dev = ctx->dev; + struct rsa_priv_f3_pdb *pdb = &edesc->pdb.priv_f3; + int sec4_sg_index = 0; + size_t p_sz = key->p_sz; + size_t q_sz = key->p_sz; + + pdb->p_dma = dma_map_single(dev, key->p, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->p_dma)) { + dev_err(dev, "Unable to map RSA prime factor p memory\n"); + return -ENOMEM; + } + + pdb->q_dma = dma_map_single(dev, key->q, q_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->q_dma)) { + dev_err(dev, "Unable to map RSA prime factor q memory\n"); + goto unmap_p; + } + + pdb->dp_dma = dma_map_single(dev, key->dp, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->dp_dma)) { + dev_err(dev, "Unable to map RSA exponent dp memory\n"); + goto unmap_q; + } + + pdb->dq_dma = dma_map_single(dev, key->dq, q_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->dq_dma)) { + dev_err(dev, "Unable to map RSA exponent dq memory\n"); + goto unmap_dp; + } + + pdb->c_dma = dma_map_single(dev, key->qinv, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->c_dma)) { + dev_err(dev, "Unable to map RSA CRT coefficient qinv memory\n"); + goto unmap_dq; + } + + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->tmp1_dma)) { + dev_err(dev, "Unable to map RSA tmp1 memory\n"); + goto unmap_qinv; + } + + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + if (dma_mapping_error(dev, pdb->tmp2_dma)) { + dev_err(dev, "Unable to map RSA tmp2 memory\n"); + goto unmap_tmp1; + } + + if (edesc->src_nents > 1) { + pdb->sgf |= RSA_PRIV_PDB_SGF_G; + pdb->g_dma = edesc->sec4_sg_dma; + sec4_sg_index += edesc->src_nents; + } else { + pdb->g_dma = sg_dma_address(req->src); + } + + if (edesc->dst_nents > 1) { + pdb->sgf |= RSA_PRIV_PDB_SGF_F; + pdb->f_dma = edesc->sec4_sg_dma + + sec4_sg_index * sizeof(struct sec4_sg_entry); + } else { + pdb->f_dma = sg_dma_address(req->dst); + } + + pdb->sgf |= key->n_sz; + pdb->p_q_len = (q_sz << RSA_PDB_Q_SHIFT) | p_sz; + + return 0; + +unmap_tmp1: + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); +unmap_qinv: + dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); +unmap_dq: + dma_unmap_single(dev, pdb->dq_dma, q_sz, DMA_TO_DEVICE); +unmap_dp: + dma_unmap_single(dev, pdb->dp_dma, p_sz, DMA_TO_DEVICE); +unmap_q: + dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); +unmap_p: + dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); + + return -ENOMEM; +} + static int caam_rsa_enc(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); @@ -301,24 +543,14 @@ static int caam_rsa_enc(struct akcipher_request *req) return ret; } -static int caam_rsa_dec(struct akcipher_request *req) +static int caam_rsa_dec_priv_f1(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); - struct caam_rsa_key *key = &ctx->key; struct device *jrdev = ctx->dev; struct rsa_edesc *edesc; int ret; - if (unlikely(!key->n || !key->d)) - return -EINVAL; - - if (req->dst_len < key->n_sz) { - req->dst_len = key->n_sz; - dev_err(jrdev, "Output buffer length less than parameter n\n"); - return -EOVERFLOW; - } - /* Allocate extended descriptor */ edesc = rsa_edesc_alloc(req, DESC_RSA_PRIV_F1_LEN); if (IS_ERR(edesc)) @@ -344,17 +576,147 @@ static int caam_rsa_dec(struct akcipher_request *req) return ret; } +static int caam_rsa_dec_priv_f2(struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct device *jrdev = ctx->dev; + struct rsa_edesc *edesc; + int ret; + + /* Allocate extended descriptor */ + edesc = rsa_edesc_alloc(req, DESC_RSA_PRIV_F2_LEN); + if (IS_ERR(edesc)) + return PTR_ERR(edesc); + + /* Set RSA Decrypt Protocol Data Block - Private Key Form #2 */ + ret = set_rsa_priv_f2_pdb(req, edesc); + if (ret) + goto init_fail; + + /* Initialize Job Descriptor */ + init_rsa_priv_f2_desc(edesc->hw_desc, &edesc->pdb.priv_f2); + + ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_priv_f2_done, req); + if (!ret) + return -EINPROGRESS; + + rsa_priv_f2_unmap(jrdev, edesc, req); + +init_fail: + rsa_io_unmap(jrdev, edesc, req); + kfree(edesc); + return ret; +} + +static int caam_rsa_dec_priv_f3(struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct device *jrdev = ctx->dev; + struct rsa_edesc *edesc; + int ret; + + /* Allocate extended descriptor */ + edesc = rsa_edesc_alloc(req, DESC_RSA_PRIV_F3_LEN); + if (IS_ERR(edesc)) + return PTR_ERR(edesc); + + /* Set RSA Decrypt Protocol Data Block - Private Key Form #3 */ + ret = set_rsa_priv_f3_pdb(req, edesc); + if (ret) + goto init_fail; + + /* Initialize Job Descriptor */ + init_rsa_priv_f3_desc(edesc->hw_desc, &edesc->pdb.priv_f3); + + ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_priv_f3_done, req); + if (!ret) + return -EINPROGRESS; + + rsa_priv_f3_unmap(jrdev, edesc, req); + +init_fail: + rsa_io_unmap(jrdev, edesc, req); + kfree(edesc); + return ret; +} + +static int caam_rsa_dec(struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm); + struct caam_rsa_key *key = &ctx->key; + int ret; + + if (unlikely(!key->n || !key->d)) + return -EINVAL; + + if (req->dst_len < key->n_sz) { + req->dst_len = key->n_sz; + dev_err(ctx->dev, "Output buffer length less than parameter n\n"); + return -EOVERFLOW; + } + + if (key->priv_form == FORM3) + ret = caam_rsa_dec_priv_f3(req); + else if (key->priv_form == FORM2) + ret = caam_rsa_dec_priv_f2(req); + else + ret = caam_rsa_dec_priv_f1(req); + + return ret; +} + static void caam_rsa_free_key(struct caam_rsa_key *key) { kzfree(key->d); + kzfree(key->p); + kzfree(key->q); + kzfree(key->dp); + kzfree(key->dq); + kzfree(key->qinv); + kzfree(key->tmp1); + kzfree(key->tmp2); kfree(key->e); kfree(key->n); - key->d = NULL; - key->e = NULL; - key->n = NULL; - key->d_sz = 0; - key->e_sz = 0; - key->n_sz = 0; + memset(key, 0, sizeof(*key)); +} + +static void caam_rsa_drop_leading_zeros(const u8 **ptr, size_t *nbytes) +{ + while (!**ptr && *nbytes) { + (*ptr)++; + (*nbytes)--; + } +} + +/** + * caam_read_rsa_crt - Used for reading dP, dQ, qInv CRT members. + * dP, dQ and qInv could decode to less than corresponding p, q length, as the + * BER-encoding requires that the minimum number of bytes be used to encode the + * integer. dP, dQ, qInv decoded values have to be zero-padded to appropriate + * length. + * + * @ptr : pointer to {dP, dQ, qInv} CRT member + * @nbytes: length in bytes of {dP, dQ, qInv} CRT member + * @dstlen: length in bytes of corresponding p or q prime factor + */ +static u8 *caam_read_rsa_crt(const u8 *ptr, size_t nbytes, size_t dstlen) +{ + u8 *dst; + + caam_rsa_drop_leading_zeros(&ptr, &nbytes); + if (!nbytes) + return NULL; + + dst = kzalloc(dstlen, GFP_DMA | GFP_KERNEL); + if (!dst) + return NULL; + + memcpy(dst + (dstlen - nbytes), ptr, nbytes); + + return dst; } /** @@ -370,10 +732,9 @@ static inline u8 *caam_read_raw_data(const u8 *buf, size_t *nbytes) { u8 *val; - while (!*buf && *nbytes) { - buf++; - (*nbytes)--; - } + caam_rsa_drop_leading_zeros(&buf, nbytes); + if (!*nbytes) + return NULL; val = kzalloc(*nbytes, GFP_DMA | GFP_KERNEL); if (!val) @@ -437,6 +798,64 @@ static int caam_rsa_set_pub_key(struct crypto_akcipher *tfm, const void *key, return -ENOMEM; } +static void caam_rsa_set_priv_key_form(struct caam_rsa_ctx *ctx, + struct rsa_key *raw_key) +{ + struct caam_rsa_key *rsa_key = &ctx->key; + size_t p_sz = raw_key->p_sz; + size_t q_sz = raw_key->q_sz; + + rsa_key->p = caam_read_raw_data(raw_key->p, &p_sz); + if (!rsa_key->p) + return; + rsa_key->p_sz = p_sz; + + rsa_key->q = caam_read_raw_data(raw_key->q, &q_sz); + if (!rsa_key->q) + goto free_p; + rsa_key->q_sz = q_sz; + + rsa_key->tmp1 = kzalloc(raw_key->p_sz, GFP_DMA | GFP_KERNEL); + if (!rsa_key->tmp1) + goto free_q; + + rsa_key->tmp2 = kzalloc(raw_key->q_sz, GFP_DMA | GFP_KERNEL); + if (!rsa_key->tmp2) + goto free_tmp1; + + rsa_key->priv_form = FORM2; + + rsa_key->dp = caam_read_rsa_crt(raw_key->dp, raw_key->dp_sz, p_sz); + if (!rsa_key->dp) + goto free_tmp2; + + rsa_key->dq = caam_read_rsa_crt(raw_key->dq, raw_key->dq_sz, q_sz); + if (!rsa_key->dq) + goto free_dp; + + rsa_key->qinv = caam_read_rsa_crt(raw_key->qinv, raw_key->qinv_sz, + q_sz); + if (!rsa_key->qinv) + goto free_dq; + + rsa_key->priv_form = FORM3; + + return; + +free_dq: + kzfree(rsa_key->dq); +free_dp: + kzfree(rsa_key->dp); +free_tmp2: + kzfree(rsa_key->tmp2); +free_tmp1: + kzfree(rsa_key->tmp1); +free_q: + kzfree(rsa_key->q); +free_p: + kzfree(rsa_key->p); +} + static int caam_rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) { @@ -483,6 +902,8 @@ static int caam_rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key, memcpy(rsa_key->d, raw_key.d, raw_key.d_sz); memcpy(rsa_key->e, raw_key.e, raw_key.e_sz); + caam_rsa_set_priv_key_form(ctx, &raw_key); + return 0; err: diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h index f595d159b112dd..87ab75e9df43d6 100644 --- a/drivers/crypto/caam/caampkc.h +++ b/drivers/crypto/caam/caampkc.h @@ -12,22 +12,76 @@ #include "compat.h" #include "pdb.h" +/** + * caam_priv_key_form - CAAM RSA private key representation + * CAAM RSA private key may have either of three forms. + * + * 1. The first representation consists of the pair (n, d), where the + * components have the following meanings: + * n the RSA modulus + * d the RSA private exponent + * + * 2. The second representation consists of the triplet (p, q, d), where the + * components have the following meanings: + * p the first prime factor of the RSA modulus n + * q the second prime factor of the RSA modulus n + * d the RSA private exponent + * + * 3. The third representation consists of the quintuple (p, q, dP, dQ, qInv), + * where the components have the following meanings: + * p the first prime factor of the RSA modulus n + * q the second prime factor of the RSA modulus n + * dP the first factors's CRT exponent + * dQ the second factors's CRT exponent + * qInv the (first) CRT coefficient + * + * The benefit of using the third or the second key form is lower computational + * cost for the decryption and signature operations. + */ +enum caam_priv_key_form { + FORM1, + FORM2, + FORM3 +}; + /** * caam_rsa_key - CAAM RSA key structure. Keys are allocated in DMA zone. * @n : RSA modulus raw byte stream * @e : RSA public exponent raw byte stream * @d : RSA private exponent raw byte stream + * @p : RSA prime factor p of RSA modulus n + * @q : RSA prime factor q of RSA modulus n + * @dp : RSA CRT exponent of p + * @dp : RSA CRT exponent of q + * @qinv : RSA CRT coefficient + * @tmp1 : CAAM uses this temporary buffer as internal state buffer. + * It is assumed to be as long as p. + * @tmp2 : CAAM uses this temporary buffer as internal state buffer. + * It is assumed to be as long as q. * @n_sz : length in bytes of RSA modulus n * @e_sz : length in bytes of RSA public exponent * @d_sz : length in bytes of RSA private exponent + * @p_sz : length in bytes of RSA prime factor p of RSA modulus n + * @q_sz : length in bytes of RSA prime factor q of RSA modulus n + * @priv_form : CAAM RSA private key representation */ struct caam_rsa_key { u8 *n; u8 *e; u8 *d; + u8 *p; + u8 *q; + u8 *dp; + u8 *dq; + u8 *qinv; + u8 *tmp1; + u8 *tmp2; size_t n_sz; size_t e_sz; size_t d_sz; + size_t p_sz; + size_t q_sz; + enum caam_priv_key_form priv_form; }; /** @@ -59,6 +113,8 @@ struct rsa_edesc { union { struct rsa_pub_pdb pub; struct rsa_priv_f1_pdb priv_f1; + struct rsa_priv_f2_pdb priv_f2; + struct rsa_priv_f3_pdb priv_f3; } pdb; u32 hw_desc[]; }; @@ -66,5 +122,7 @@ struct rsa_edesc { /* Descriptor construction primitives. */ void init_rsa_pub_desc(u32 *desc, struct rsa_pub_pdb *pdb); void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb); +void init_rsa_priv_f2_desc(u32 *desc, struct rsa_priv_f2_pdb *pdb); +void init_rsa_priv_f3_desc(u32 *desc, struct rsa_priv_f3_pdb *pdb); #endif diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h index aaa00dd1c6017e..31e59963f4d227 100644 --- a/drivers/crypto/caam/pdb.h +++ b/drivers/crypto/caam/pdb.h @@ -483,6 +483,8 @@ struct dsa_verify_pdb { #define RSA_PDB_E_MASK (0xFFF << RSA_PDB_E_SHIFT) #define RSA_PDB_D_SHIFT 12 #define RSA_PDB_D_MASK (0xFFF << RSA_PDB_D_SHIFT) +#define RSA_PDB_Q_SHIFT 12 +#define RSA_PDB_Q_MASK (0xFFF << RSA_PDB_Q_SHIFT) #define RSA_PDB_SGF_F (0x8 << RSA_PDB_SGF_SHIFT) #define RSA_PDB_SGF_G (0x4 << RSA_PDB_SGF_SHIFT) @@ -490,6 +492,8 @@ struct dsa_verify_pdb { #define RSA_PRIV_PDB_SGF_G (0x8 << RSA_PDB_SGF_SHIFT) #define RSA_PRIV_KEY_FRM_1 0 +#define RSA_PRIV_KEY_FRM_2 1 +#define RSA_PRIV_KEY_FRM_3 2 /** * RSA Encrypt Protocol Data Block @@ -525,4 +529,62 @@ struct rsa_priv_f1_pdb { dma_addr_t d_dma; } __packed; +/** + * RSA Decrypt PDB - Private Key Form #2 + * @sgf : scatter-gather field + * @g_dma : dma address of encrypted input data + * @f_dma : dma address of output data + * @d_dma : dma address of RSA private exponent + * @p_dma : dma address of RSA prime factor p of RSA modulus n + * @q_dma : dma address of RSA prime factor q of RSA modulus n + * @tmp1_dma: dma address of temporary buffer. CAAM uses this temporary buffer + * as internal state buffer. It is assumed to be as long as p. + * @tmp2_dma: dma address of temporary buffer. CAAM uses this temporary buffer + * as internal state buffer. It is assumed to be as long as q. + * @p_q_len : length in bytes of first two prime factors of the RSA modulus n + */ +struct rsa_priv_f2_pdb { + u32 sgf; + dma_addr_t g_dma; + dma_addr_t f_dma; + dma_addr_t d_dma; + dma_addr_t p_dma; + dma_addr_t q_dma; + dma_addr_t tmp1_dma; + dma_addr_t tmp2_dma; + u32 p_q_len; +} __packed; + +/** + * RSA Decrypt PDB - Private Key Form #3 + * This is the RSA Chinese Reminder Theorem (CRT) form for two prime factors of + * the RSA modulus. + * @sgf : scatter-gather field + * @g_dma : dma address of encrypted input data + * @f_dma : dma address of output data + * @c_dma : dma address of RSA CRT coefficient + * @p_dma : dma address of RSA prime factor p of RSA modulus n + * @q_dma : dma address of RSA prime factor q of RSA modulus n + * @dp_dma : dma address of RSA CRT exponent of RSA prime factor p + * @dp_dma : dma address of RSA CRT exponent of RSA prime factor q + * @tmp1_dma: dma address of temporary buffer. CAAM uses this temporary buffer + * as internal state buffer. It is assumed to be as long as p. + * @tmp2_dma: dma address of temporary buffer. CAAM uses this temporary buffer + * as internal state buffer. It is assumed to be as long as q. + * @p_q_len : length in bytes of first two prime factors of the RSA modulus n + */ +struct rsa_priv_f3_pdb { + u32 sgf; + dma_addr_t g_dma; + dma_addr_t f_dma; + dma_addr_t c_dma; + dma_addr_t p_dma; + dma_addr_t q_dma; + dma_addr_t dp_dma; + dma_addr_t dq_dma; + dma_addr_t tmp1_dma; + dma_addr_t tmp2_dma; + u32 p_q_len; +} __packed; + #endif diff --git a/drivers/crypto/caam/pkc_desc.c b/drivers/crypto/caam/pkc_desc.c index 4e4183e615eaaa..9e2ce6fe2e43f7 100644 --- a/drivers/crypto/caam/pkc_desc.c +++ b/drivers/crypto/caam/pkc_desc.c @@ -34,3 +34,39 @@ void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb) append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSADEC_PRVKEY | RSA_PRIV_KEY_FRM_1); } + +/* Descriptor for RSA Private operation - Private Key Form #2 */ +void init_rsa_priv_f2_desc(u32 *desc, struct rsa_priv_f2_pdb *pdb) +{ + init_job_desc_pdb(desc, 0, sizeof(*pdb)); + append_cmd(desc, pdb->sgf); + append_ptr(desc, pdb->g_dma); + append_ptr(desc, pdb->f_dma); + append_ptr(desc, pdb->d_dma); + append_ptr(desc, pdb->p_dma); + append_ptr(desc, pdb->q_dma); + append_ptr(desc, pdb->tmp1_dma); + append_ptr(desc, pdb->tmp2_dma); + append_cmd(desc, pdb->p_q_len); + append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSADEC_PRVKEY | + RSA_PRIV_KEY_FRM_2); +} + +/* Descriptor for RSA Private operation - Private Key Form #3 */ +void init_rsa_priv_f3_desc(u32 *desc, struct rsa_priv_f3_pdb *pdb) +{ + init_job_desc_pdb(desc, 0, sizeof(*pdb)); + append_cmd(desc, pdb->sgf); + append_ptr(desc, pdb->g_dma); + append_ptr(desc, pdb->f_dma); + append_ptr(desc, pdb->c_dma); + append_ptr(desc, pdb->p_dma); + append_ptr(desc, pdb->q_dma); + append_ptr(desc, pdb->dp_dma); + append_ptr(desc, pdb->dq_dma); + append_ptr(desc, pdb->tmp1_dma); + append_ptr(desc, pdb->tmp2_dma); + append_cmd(desc, pdb->p_q_len); + append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSADEC_PRVKEY | + RSA_PRIV_KEY_FRM_3); +} diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c index 6b46eea94932e1..ce97b3868f4a6c 100644 --- a/drivers/crypto/ccp/ccp-crypto-sha.c +++ b/drivers/crypto/ccp/ccp-crypto-sha.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -308,8 +309,8 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key, } for (i = 0; i < block_size; i++) { - ctx->u.sha.ipad[i] = ctx->u.sha.key[i] ^ 0x36; - ctx->u.sha.opad[i] = ctx->u.sha.key[i] ^ 0x5c; + ctx->u.sha.ipad[i] = ctx->u.sha.key[i] ^ HMAC_IPAD_VALUE; + ctx->u.sha.opad[i] = ctx->u.sha.key[i] ^ HMAC_OPAD_VALUE; } sg_init_one(&ctx->u.sha.opad_sg, ctx->u.sha.opad, block_size); diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c index 92d1c6959f08b8..b7504562715cf8 100644 --- a/drivers/crypto/ccp/ccp-dev.c +++ b/drivers/crypto/ccp/ccp-dev.c @@ -31,6 +31,7 @@ #include "ccp-dev.h" MODULE_AUTHOR("Tom Lendacky "); +MODULE_AUTHOR("Gary R Hook "); MODULE_LICENSE("GPL"); MODULE_VERSION("1.0.0"); MODULE_DESCRIPTION("AMD Cryptographic Coprocessor driver"); diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c index 9b07f3d88febff..0c6a917a9ab80e 100644 --- a/drivers/crypto/img-hash.c +++ b/drivers/crypto/img-hash.c @@ -1088,9 +1088,17 @@ static int img_hash_suspend(struct device *dev) static int img_hash_resume(struct device *dev) { struct img_hash_dev *hdev = dev_get_drvdata(dev); + int ret; - clk_prepare_enable(hdev->hash_clk); - clk_prepare_enable(hdev->sys_clk); + ret = clk_prepare_enable(hdev->hash_clk); + if (ret) + return ret; + + ret = clk_prepare_enable(hdev->sys_clk); + if (ret) { + clk_disable_unprepare(hdev->hash_clk); + return ret; + } return 0; } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 771dd26c7076e1..427cbe01272926 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -90,8 +91,6 @@ #define CTL_FLAG_PERFORM_AEAD 0x0008 #define CTL_FLAG_MASK 0x000f -#define HMAC_IPAD_VALUE 0x36 -#define HMAC_OPAD_VALUE 0x5C #define HMAC_PAD_BLOCKLEN SHA1_BLOCK_SIZE #define MD5_DIGEST_SIZE 16 diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c index 77c0fb936f4794..e61b0856609327 100644 --- a/drivers/crypto/marvell/hash.c +++ b/drivers/crypto/marvell/hash.c @@ -12,6 +12,7 @@ * by the Free Software Foundation. */ +#include #include #include @@ -1164,8 +1165,8 @@ static int mv_cesa_ahmac_pad_init(struct ahash_request *req, memcpy(opad, ipad, blocksize); for (i = 0; i < blocksize; i++) { - ipad[i] ^= 0x36; - opad[i] ^= 0x5c; + ipad[i] ^= HMAC_IPAD_VALUE; + opad[i] ^= HMAC_OPAD_VALUE; } return 0; diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c index 2226f12d1c7afa..5f4f845adbb8ec 100644 --- a/drivers/crypto/mediatek/mtk-sha.c +++ b/drivers/crypto/mediatek/mtk-sha.c @@ -12,6 +12,7 @@ * Some ideas are from atmel-sha.c and omap-sham.c drivers. */ +#include #include #include "mtk-platform.h" @@ -825,8 +826,8 @@ static int mtk_sha_setkey(struct crypto_ahash *tfm, const u8 *key, memcpy(bctx->opad, bctx->ipad, bs); for (i = 0; i < bs; i++) { - bctx->ipad[i] ^= 0x36; - bctx->opad[i] ^= 0x5c; + bctx->ipad[i] ^= HMAC_IPAD_VALUE; + bctx->opad[i] ^= HMAC_OPAD_VALUE; } return 0; diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c index 451fa18c1c7b95..bf25f415eea659 100644 --- a/drivers/crypto/mv_cesa.c +++ b/drivers/crypto/mv_cesa.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -822,8 +823,8 @@ static int mv_hash_setkey(struct crypto_ahash *tfm, const u8 * key, memcpy(opad, ipad, bs); for (i = 0; i < bs; i++) { - ipad[i] ^= 0x36; - opad[i] ^= 0x5c; + ipad[i] ^= HMAC_IPAD_VALUE; + opad[i] ^= HMAC_OPAD_VALUE; } rc = crypto_shash_init(shash) ? : diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index d0b16e5e4ee56a..1864a57caaa4f4 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #define MD5_DIGEST_SIZE 16 @@ -1326,8 +1327,8 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key, memcpy(bctx->opad, bctx->ipad, bs); for (i = 0; i < bs; i++) { - bctx->ipad[i] ^= 0x36; - bctx->opad[i] ^= 0x5c; + bctx->ipad[i] ^= HMAC_IPAD_VALUE; + bctx->opad[i] ^= HMAC_OPAD_VALUE; } } diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c index 2839fccdd84bee..d3e25c37dc339d 100644 --- a/drivers/crypto/qat/qat_common/adf_aer.c +++ b/drivers/crypto/qat/qat_common/adf_aer.c @@ -109,20 +109,7 @@ EXPORT_SYMBOL_GPL(adf_reset_sbr); void adf_reset_flr(struct adf_accel_dev *accel_dev) { - struct pci_dev *pdev = accel_to_pci_dev(accel_dev); - u16 control = 0; - int pos = 0; - - dev_info(&GET_DEV(accel_dev), "Function level reset\n"); - pos = pci_pcie_cap(pdev); - if (!pos) { - dev_err(&GET_DEV(accel_dev), "Restart device failed\n"); - return; - } - pci_read_config_word(pdev, pos + PCI_EXP_DEVCTL, &control); - control |= PCI_EXP_DEVCTL_BCR_FLR; - pci_write_config_word(pdev, pos + PCI_EXP_DEVCTL, control); - msleep(100); + pcie_flr(accel_to_pci_dev(accel_dev)); } EXPORT_SYMBOL_GPL(adf_reset_flr); diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index 20f35df8a01faf..5b5efcc52cb5e8 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -178,8 +179,8 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash, for (i = 0; i < block_size; i++) { char *ipad_ptr = ipad + i; char *opad_ptr = opad + i; - *ipad_ptr ^= 0x36; - *opad_ptr ^= 0x5C; + *ipad_ptr ^= HMAC_IPAD_VALUE; + *opad_ptr ^= HMAC_OPAD_VALUE; } if (crypto_shash_init(shash)) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 512bdbc23bbb43..4a038dcf53612c 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -558,8 +558,8 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, if (WARN_ON(!dmabuf || !dev)) return ERR_PTR(-EINVAL); - attach = kzalloc(sizeof(struct dma_buf_attachment), GFP_KERNEL); - if (attach == NULL) + attach = kzalloc(sizeof(*attach), GFP_KERNEL); + if (!attach) return ERR_PTR(-ENOMEM); attach->dev = dev; @@ -1122,9 +1122,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) attach_count = 0; list_for_each_entry(attach_obj, &buf_obj->attachments, node) { - seq_puts(s, "\t"); - - seq_printf(s, "%s\n", dev_name(attach_obj->dev)); + seq_printf(s, "\t%s\n", dev_name(attach_obj->dev)); attach_count++; } diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 0918d3f003d65d..57da14c15987fc 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -402,6 +402,11 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) } } + if (!timeout) { + ret = 0; + goto out; + } + cb.base.func = dma_fence_default_wait_cb; cb.task = current; list_add(&cb.base.node, &fence->cb_list); diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c index c769dc653b344a..82a6e7f6d37f4c 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -110,7 +110,7 @@ static void sync_print_fence(struct seq_file *s, } } - seq_puts(s, "\n"); + seq_putc(s, '\n'); } static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) @@ -132,9 +132,11 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) static void sync_print_sync_file(struct seq_file *s, struct sync_file *sync_file) { + char buf[128]; int i; - seq_printf(s, "[%p] %s: %s\n", sync_file, sync_file->name, + seq_printf(s, "[%p] %s: %s\n", sync_file, + sync_file_get_name(sync_file, buf, sizeof(buf)), sync_status_str(dma_fence_get_status(sync_file->fence))); if (dma_fence_is_array(sync_file->fence)) { @@ -161,7 +163,7 @@ static int sync_debugfs_show(struct seq_file *s, void *unused) sync_timeline_list); sync_print_obj(s, obj); - seq_puts(s, "\n"); + seq_putc(s, '\n'); } spin_unlock_irqrestore(&sync_timeline_list_lock, flags); @@ -173,7 +175,7 @@ static int sync_debugfs_show(struct seq_file *s, void *unused) container_of(pos, struct sync_file, sync_file_list); sync_print_sync_file(s, sync_file); - seq_puts(s, "\n"); + seq_putc(s, '\n'); } spin_unlock_irqrestore(&sync_file_list_lock, flags); return 0; diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 2321035f6204bc..545e2c5c4815d4 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -41,8 +41,6 @@ static struct sync_file *sync_file_alloc(void) if (IS_ERR(sync_file->file)) goto err; - kref_init(&sync_file->kref); - init_waitqueue_head(&sync_file->wq); INIT_LIST_HEAD(&sync_file->cb.node); @@ -82,11 +80,6 @@ struct sync_file *sync_file_create(struct dma_fence *fence) sync_file->fence = dma_fence_get(fence); - snprintf(sync_file->name, sizeof(sync_file->name), "%s-%s%llu-%d", - fence->ops->get_driver_name(fence), - fence->ops->get_timeline_name(fence), fence->context, - fence->seqno); - return sync_file; } EXPORT_SYMBOL(sync_file_create); @@ -131,6 +124,36 @@ struct dma_fence *sync_file_get_fence(int fd) } EXPORT_SYMBOL(sync_file_get_fence); +/** + * sync_file_get_name - get the name of the sync_file + * @sync_file: sync_file to get the fence from + * @buf: destination buffer to copy sync_file name into + * @len: available size of destination buffer. + * + * Each sync_file may have a name assigned either by the user (when merging + * sync_files together) or created from the fence it contains. In the latter + * case construction of the name is deferred until use, and so requires + * sync_file_get_name(). + * + * Returns: a string representing the name. + */ +char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) +{ + if (sync_file->user_name[0]) { + strlcpy(buf, sync_file->user_name, len); + } else { + struct dma_fence *fence = sync_file->fence; + + snprintf(buf, len, "%s-%s%llu-%d", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), + fence->context, + fence->seqno); + } + + return buf; +} + static int sync_file_set_fence(struct sync_file *sync_file, struct dma_fence **fences, int num_fences) { @@ -268,7 +291,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, goto err; } - strlcpy(sync_file->name, name, sizeof(sync_file->name)); + strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; err: @@ -277,22 +300,15 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, } -static void sync_file_free(struct kref *kref) +static int sync_file_release(struct inode *inode, struct file *file) { - struct sync_file *sync_file = container_of(kref, struct sync_file, - kref); + struct sync_file *sync_file = file->private_data; if (test_bit(POLL_ENABLED, &sync_file->fence->flags)) dma_fence_remove_callback(sync_file->fence, &sync_file->cb); dma_fence_put(sync_file->fence); kfree(sync_file); -} - -static int sync_file_release(struct inode *inode, struct file *file) -{ - struct sync_file *sync_file = file->private_data; - kref_put(&sync_file->kref, sync_file_free); return 0; } @@ -422,7 +438,7 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, } no_fences: - strlcpy(info.name, sync_file->name, sizeof(info.name)); + sync_file_get_name(sync_file, info.name, sizeof(info.name)); info.status = dma_fence_is_signaled(sync_file->fence); info.num_fences = num_fences; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 24e8597b2c3ed3..fd724692bb3fa7 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -62,8 +62,10 @@ config AMBA_PL08X select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help - Platform has a PL08x DMAC device - which can provide DMA engine support + Say yes if your platform has a PL08x DMAC device which can + provide DMA engine support. This includes the original ARM + PL080 and PL081, Samsungs PL080 derivative and Faraday + Technology's FTDMAC020 PL080 derivative. config AMCC_PPC440SPE_ADMA tristate "AMCC PPC440SPe ADMA support" @@ -99,6 +101,21 @@ config AXI_DMAC controller is often used in Analog Device's reference designs for FPGA platforms. +config BCM_SBA_RAID + tristate "Broadcom SBA RAID engine support" + depends on ARM64 || COMPILE_TEST + depends on MAILBOX && RAID6_PQ + select DMA_ENGINE + select DMA_ENGINE_RAID + select ASYNC_TX_DISABLE_XOR_VAL_DMA + select ASYNC_TX_DISABLE_PQ_VAL_DMA + default ARCH_BCM_IPROC + help + Enable support for Broadcom SBA RAID Engine. The SBA RAID + engine is available on most of the Broadcom iProc SoCs. It + has the capability to offload memcpy, xor and pq computation + for raid5/6. + config COH901318 bool "ST-Ericsson COH901318 DMA support" select DMA_ENGINE diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 0b723e94d9e6d3..d12ab2985ed121 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o +obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 6bb8813ca27538..13cc95c0474c7e 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -1,9 +1,10 @@ /* * Copyright (c) 2006 ARM Ltd. * Copyright (c) 2010 ST-Ericsson SA + * Copyirght (c) 2017 Linaro Ltd. * * Author: Peter Pearse - * Author: Linus Walleij + * Author: Linus Walleij * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -110,11 +111,12 @@ struct pl08x_driver_data; * @channels: the number of channels available in this variant * @signals: the number of request signals available from the hardware * @dualmaster: whether this version supports dual AHB masters or not. - * @nomadik: whether the channels have Nomadik security extension bits - * that need to be checked for permission before use and some registers are - * missing - * @pl080s: whether this version is a PL080S, which has separate register and - * LLI word for transfer size. + * @nomadik: whether this variant is a ST Microelectronics Nomadik, where the + * channels have Nomadik security extension bits that need to be checked + * for permission before use and some registers are missing + * @pl080s: whether this variant is a Samsung PL080S, which has separate + * register and LLI word for transfer size. + * @ftdmac020: whether this variant is a Faraday Technology FTDMAC020 * @max_transfer_size: the maximum single element transfer size for this * PL08x variant. */ @@ -125,6 +127,7 @@ struct vendor_data { bool dualmaster; bool nomadik; bool pl080s; + bool ftdmac020; u32 max_transfer_size; }; @@ -148,19 +151,34 @@ struct pl08x_bus_data { * @id: physical index to this channel * @base: memory base address for this physical channel * @reg_config: configuration address for this physical channel + * @reg_control: control address for this physical channel + * @reg_src: transfer source address register + * @reg_dst: transfer destination address register + * @reg_lli: transfer LLI address register + * @reg_busy: if the variant has a special per-channel busy register, + * this contains a pointer to it * @lock: a lock to use when altering an instance of this struct * @serving: the virtual channel currently being served by this physical * channel * @locked: channel unavailable for the system, e.g. dedicated to secure * world + * @ftdmac020: channel is on a FTDMAC020 + * @pl080s: channel is on a PL08s */ struct pl08x_phy_chan { unsigned int id; void __iomem *base; void __iomem *reg_config; + void __iomem *reg_control; + void __iomem *reg_src; + void __iomem *reg_dst; + void __iomem *reg_lli; + void __iomem *reg_busy; spinlock_t lock; struct pl08x_dma_chan *serving; bool locked; + bool ftdmac020; + bool pl080s; }; /** @@ -253,8 +271,9 @@ struct pl08x_dma_chan { /** * struct pl08x_driver_data - the local state holder for the PL08x - * @slave: slave engine for this instance + * @slave: optional slave engine for this instance * @memcpy: memcpy engine for this instance + * @has_slave: the PL08x has a slave engine (routed signals) * @base: virtual memory base (remapped) for the PL08x * @adev: the corresponding AMBA (PrimeCell) bus entry * @vd: vendor data for this PL08x variant @@ -269,6 +288,7 @@ struct pl08x_dma_chan { struct pl08x_driver_data { struct dma_device slave; struct dma_device memcpy; + bool has_slave; void __iomem *base; struct amba_device *adev; const struct vendor_data *vd; @@ -360,10 +380,24 @@ static int pl08x_phy_channel_busy(struct pl08x_phy_chan *ch) { unsigned int val; + /* If we have a special busy register, take a shortcut */ + if (ch->reg_busy) { + val = readl(ch->reg_busy); + return !!(val & BIT(ch->id)); + } val = readl(ch->reg_config); return val & PL080_CONFIG_ACTIVE; } +/* + * pl08x_write_lli() - Write an LLI into the DMA controller. + * + * The PL08x derivatives support linked lists, but the first item of the + * list containing the source, destination, control word and next LLI is + * ignored. Instead the driver has to write those values directly into the + * SRC, DST, LLI and control registers. On FTDMAC020 also the SIZE + * register need to be set up for the first transfer. + */ static void pl08x_write_lli(struct pl08x_driver_data *pl08x, struct pl08x_phy_chan *phychan, const u32 *lli, u32 ccfg) { @@ -381,11 +415,112 @@ static void pl08x_write_lli(struct pl08x_driver_data *pl08x, phychan->id, lli[PL080_LLI_SRC], lli[PL080_LLI_DST], lli[PL080_LLI_LLI], lli[PL080_LLI_CCTL], ccfg); - writel_relaxed(lli[PL080_LLI_SRC], phychan->base + PL080_CH_SRC_ADDR); - writel_relaxed(lli[PL080_LLI_DST], phychan->base + PL080_CH_DST_ADDR); - writel_relaxed(lli[PL080_LLI_LLI], phychan->base + PL080_CH_LLI); - writel_relaxed(lli[PL080_LLI_CCTL], phychan->base + PL080_CH_CONTROL); + writel_relaxed(lli[PL080_LLI_SRC], phychan->reg_src); + writel_relaxed(lli[PL080_LLI_DST], phychan->reg_dst); + writel_relaxed(lli[PL080_LLI_LLI], phychan->reg_lli); + + /* + * The FTMAC020 has a different layout in the CCTL word of the LLI + * and the CCTL register which is split in CSR and SIZE registers. + * Convert the LLI item CCTL into the proper values to write into + * the CSR and SIZE registers. + */ + if (phychan->ftdmac020) { + u32 llictl = lli[PL080_LLI_CCTL]; + u32 val = 0; + + /* Write the transfer size (12 bits) to the size register */ + writel_relaxed(llictl & FTDMAC020_LLI_TRANSFER_SIZE_MASK, + phychan->base + FTDMAC020_CH_SIZE); + /* + * Then write the control bits 28..16 to the control register + * by shuffleing the bits around to where they are in the + * main register. The mapping is as follows: + * Bit 28: TC_MSK - mask on all except last LLI + * Bit 27..25: SRC_WIDTH + * Bit 24..22: DST_WIDTH + * Bit 21..20: SRCAD_CTRL + * Bit 19..17: DSTAD_CTRL + * Bit 17: SRC_SEL + * Bit 16: DST_SEL + */ + if (llictl & FTDMAC020_LLI_TC_MSK) + val |= FTDMAC020_CH_CSR_TC_MSK; + val |= ((llictl & FTDMAC020_LLI_SRC_WIDTH_MSK) >> + (FTDMAC020_LLI_SRC_WIDTH_SHIFT - + FTDMAC020_CH_CSR_SRC_WIDTH_SHIFT)); + val |= ((llictl & FTDMAC020_LLI_DST_WIDTH_MSK) >> + (FTDMAC020_LLI_DST_WIDTH_SHIFT - + FTDMAC020_CH_CSR_DST_WIDTH_SHIFT)); + val |= ((llictl & FTDMAC020_LLI_SRCAD_CTL_MSK) >> + (FTDMAC020_LLI_SRCAD_CTL_SHIFT - + FTDMAC020_CH_CSR_SRCAD_CTL_SHIFT)); + val |= ((llictl & FTDMAC020_LLI_DSTAD_CTL_MSK) >> + (FTDMAC020_LLI_DSTAD_CTL_SHIFT - + FTDMAC020_CH_CSR_DSTAD_CTL_SHIFT)); + if (llictl & FTDMAC020_LLI_SRC_SEL) + val |= FTDMAC020_CH_CSR_SRC_SEL; + if (llictl & FTDMAC020_LLI_DST_SEL) + val |= FTDMAC020_CH_CSR_DST_SEL; + + /* + * Set up the bits that exist in the CSR but are not + * part the LLI, i.e. only gets written to the control + * register right here. + * + * FIXME: do not just handle memcpy, also handle slave DMA. + */ + switch (pl08x->pd->memcpy_burst_size) { + default: + case PL08X_BURST_SZ_1: + val |= PL080_BSIZE_1 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_4: + val |= PL080_BSIZE_4 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_8: + val |= PL080_BSIZE_8 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_16: + val |= PL080_BSIZE_16 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_32: + val |= PL080_BSIZE_32 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_64: + val |= PL080_BSIZE_64 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_128: + val |= PL080_BSIZE_128 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_256: + val |= PL080_BSIZE_256 << + FTDMAC020_CH_CSR_SRC_SIZE_SHIFT; + break; + } + + /* Protection flags */ + if (pl08x->pd->memcpy_prot_buff) + val |= FTDMAC020_CH_CSR_PROT2; + if (pl08x->pd->memcpy_prot_cache) + val |= FTDMAC020_CH_CSR_PROT3; + /* We are the kernel, so we are in privileged mode */ + val |= FTDMAC020_CH_CSR_PROT1; + + writel_relaxed(val, phychan->reg_control); + } else { + /* Bits are just identical */ + writel_relaxed(lli[PL080_LLI_CCTL], phychan->reg_control); + } + /* Second control word on the PL080s */ if (pl08x->vd->pl080s) writel_relaxed(lli[PL080S_LLI_CCTL2], phychan->base + PL080S_CH_CONTROL2); @@ -423,11 +558,25 @@ static void pl08x_start_next_txd(struct pl08x_dma_chan *plchan) cpu_relax(); /* Do not access config register until channel shows as inactive */ - val = readl(phychan->reg_config); - while ((val & PL080_CONFIG_ACTIVE) || (val & PL080_CONFIG_ENABLE)) + if (phychan->ftdmac020) { + val = readl(phychan->reg_config); + while (val & FTDMAC020_CH_CFG_BUSY) + val = readl(phychan->reg_config); + + val = readl(phychan->reg_control); + while (val & FTDMAC020_CH_CSR_EN) + val = readl(phychan->reg_control); + + writel(val | FTDMAC020_CH_CSR_EN, + phychan->reg_control); + } else { val = readl(phychan->reg_config); + while ((val & PL080_CONFIG_ACTIVE) || + (val & PL080_CONFIG_ENABLE)) + val = readl(phychan->reg_config); - writel(val | PL080_CONFIG_ENABLE, phychan->reg_config); + writel(val | PL080_CONFIG_ENABLE, phychan->reg_config); + } } /* @@ -445,6 +594,14 @@ static void pl08x_pause_phy_chan(struct pl08x_phy_chan *ch) u32 val; int timeout; + if (ch->ftdmac020) { + /* Use the enable bit on the FTDMAC020 */ + val = readl(ch->reg_control); + val &= ~FTDMAC020_CH_CSR_EN; + writel(val, ch->reg_control); + return; + } + /* Set the HALT bit and wait for the FIFO to drain */ val = readl(ch->reg_config); val |= PL080_CONFIG_HALT; @@ -464,6 +621,14 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch) { u32 val; + /* Use the enable bit on the FTDMAC020 */ + if (ch->ftdmac020) { + val = readl(ch->reg_control); + val |= FTDMAC020_CH_CSR_EN; + writel(val, ch->reg_control); + return; + } + /* Clear the HALT bit */ val = readl(ch->reg_config); val &= ~PL080_CONFIG_HALT; @@ -479,25 +644,68 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch) static void pl08x_terminate_phy_chan(struct pl08x_driver_data *pl08x, struct pl08x_phy_chan *ch) { - u32 val = readl(ch->reg_config); + u32 val; + /* The layout for the FTDMAC020 is different */ + if (ch->ftdmac020) { + /* Disable all interrupts */ + val = readl(ch->reg_config); + val |= (FTDMAC020_CH_CFG_INT_ABT_MASK | + FTDMAC020_CH_CFG_INT_ERR_MASK | + FTDMAC020_CH_CFG_INT_TC_MASK); + writel(val, ch->reg_config); + + /* Abort and disable channel */ + val = readl(ch->reg_control); + val &= ~FTDMAC020_CH_CSR_EN; + val |= FTDMAC020_CH_CSR_ABT; + writel(val, ch->reg_control); + + /* Clear ABT and ERR interrupt flags */ + writel(BIT(ch->id) | BIT(ch->id + 16), + pl08x->base + PL080_ERR_CLEAR); + writel(BIT(ch->id), pl08x->base + PL080_TC_CLEAR); + + return; + } + + val = readl(ch->reg_config); val &= ~(PL080_CONFIG_ENABLE | PL080_CONFIG_ERR_IRQ_MASK | PL080_CONFIG_TC_IRQ_MASK); - writel(val, ch->reg_config); writel(BIT(ch->id), pl08x->base + PL080_ERR_CLEAR); writel(BIT(ch->id), pl08x->base + PL080_TC_CLEAR); } -static inline u32 get_bytes_in_cctl(u32 cctl) +static u32 get_bytes_in_phy_channel(struct pl08x_phy_chan *ch) { - /* The source width defines the number of bytes */ - u32 bytes = cctl & PL080_CONTROL_TRANSFER_SIZE_MASK; + u32 val; + u32 bytes; + + if (ch->ftdmac020) { + bytes = readl(ch->base + FTDMAC020_CH_SIZE); - cctl &= PL080_CONTROL_SWIDTH_MASK; + val = readl(ch->reg_control); + val &= FTDMAC020_CH_CSR_SRC_WIDTH_MSK; + val >>= FTDMAC020_CH_CSR_SRC_WIDTH_SHIFT; + } else if (ch->pl080s) { + val = readl(ch->base + PL080S_CH_CONTROL2); + bytes = val & PL080S_CONTROL_TRANSFER_SIZE_MASK; - switch (cctl >> PL080_CONTROL_SWIDTH_SHIFT) { + val = readl(ch->reg_control); + val &= PL080_CONTROL_SWIDTH_MASK; + val >>= PL080_CONTROL_SWIDTH_SHIFT; + } else { + /* Plain PL08x */ + val = readl(ch->reg_control); + bytes = val & PL080_CONTROL_TRANSFER_SIZE_MASK; + + val &= PL080_CONTROL_SWIDTH_MASK; + val >>= PL080_CONTROL_SWIDTH_SHIFT; + } + + switch (val) { case PL080_WIDTH_8BIT: break; case PL080_WIDTH_16BIT: @@ -510,14 +718,35 @@ static inline u32 get_bytes_in_cctl(u32 cctl) return bytes; } -static inline u32 get_bytes_in_cctl_pl080s(u32 cctl, u32 cctl1) +static u32 get_bytes_in_lli(struct pl08x_phy_chan *ch, const u32 *llis_va) { - /* The source width defines the number of bytes */ - u32 bytes = cctl1 & PL080S_CONTROL_TRANSFER_SIZE_MASK; + u32 val; + u32 bytes; + + if (ch->ftdmac020) { + val = llis_va[PL080_LLI_CCTL]; + bytes = val & FTDMAC020_LLI_TRANSFER_SIZE_MASK; + + val = llis_va[PL080_LLI_CCTL]; + val &= FTDMAC020_LLI_SRC_WIDTH_MSK; + val >>= FTDMAC020_LLI_SRC_WIDTH_SHIFT; + } else if (ch->pl080s) { + val = llis_va[PL080S_LLI_CCTL2]; + bytes = val & PL080S_CONTROL_TRANSFER_SIZE_MASK; + + val = llis_va[PL080_LLI_CCTL]; + val &= PL080_CONTROL_SWIDTH_MASK; + val >>= PL080_CONTROL_SWIDTH_SHIFT; + } else { + /* Plain PL08x */ + val = llis_va[PL080_LLI_CCTL]; + bytes = val & PL080_CONTROL_TRANSFER_SIZE_MASK; - cctl &= PL080_CONTROL_SWIDTH_MASK; + val &= PL080_CONTROL_SWIDTH_MASK; + val >>= PL080_CONTROL_SWIDTH_SHIFT; + } - switch (cctl >> PL080_CONTROL_SWIDTH_SHIFT) { + switch (val) { case PL080_WIDTH_8BIT: break; case PL080_WIDTH_16BIT: @@ -552,15 +781,10 @@ static u32 pl08x_getbytes_chan(struct pl08x_dma_chan *plchan) * Follow the LLIs to get the number of remaining * bytes in the currently active transaction. */ - clli = readl(ch->base + PL080_CH_LLI) & ~PL080_LLI_LM_AHB2; + clli = readl(ch->reg_lli) & ~PL080_LLI_LM_AHB2; /* First get the remaining bytes in the active transfer */ - if (pl08x->vd->pl080s) - bytes = get_bytes_in_cctl_pl080s( - readl(ch->base + PL080_CH_CONTROL), - readl(ch->base + PL080S_CH_CONTROL2)); - else - bytes = get_bytes_in_cctl(readl(ch->base + PL080_CH_CONTROL)); + bytes = get_bytes_in_phy_channel(ch); if (!clli) return bytes; @@ -581,12 +805,7 @@ static u32 pl08x_getbytes_chan(struct pl08x_dma_chan *plchan) llis_va_limit = llis_va + llis_max_words; for (; llis_va < llis_va_limit; llis_va += pl08x->lli_words) { - if (pl08x->vd->pl080s) - bytes += get_bytes_in_cctl_pl080s( - llis_va[PL080_LLI_CCTL], - llis_va[PL080S_LLI_CCTL2]); - else - bytes += get_bytes_in_cctl(llis_va[PL080_LLI_CCTL]); + bytes += get_bytes_in_lli(ch, llis_va); /* * A LLI pointer going backward terminates the LLI list @@ -705,7 +924,7 @@ static void pl08x_phy_free(struct pl08x_dma_chan *plchan) break; } - if (!next) { + if (!next && pl08x->has_slave) { list_for_each_entry(p, &pl08x->slave.channels, vc.chan.device_node) if (p->state == PL08X_CHAN_WAITING) { next = p; @@ -746,9 +965,30 @@ static void pl08x_phy_free(struct pl08x_dma_chan *plchan) * LLI handling */ -static inline unsigned int pl08x_get_bytes_for_cctl(unsigned int coded) +static inline unsigned int +pl08x_get_bytes_for_lli(struct pl08x_driver_data *pl08x, + u32 cctl, + bool source) { - switch (coded) { + u32 val; + + if (pl08x->vd->ftdmac020) { + if (source) + val = (cctl & FTDMAC020_LLI_SRC_WIDTH_MSK) >> + FTDMAC020_LLI_SRC_WIDTH_SHIFT; + else + val = (cctl & FTDMAC020_LLI_DST_WIDTH_MSK) >> + FTDMAC020_LLI_DST_WIDTH_SHIFT; + } else { + if (source) + val = (cctl & PL080_CONTROL_SWIDTH_MASK) >> + PL080_CONTROL_SWIDTH_SHIFT; + else + val = (cctl & PL080_CONTROL_DWIDTH_MASK) >> + PL080_CONTROL_DWIDTH_SHIFT; + } + + switch (val) { case PL080_WIDTH_8BIT: return 1; case PL080_WIDTH_16BIT: @@ -762,49 +1002,106 @@ static inline unsigned int pl08x_get_bytes_for_cctl(unsigned int coded) return 0; } -static inline u32 pl08x_cctl_bits(u32 cctl, u8 srcwidth, u8 dstwidth, - size_t tsize) +static inline u32 pl08x_lli_control_bits(struct pl08x_driver_data *pl08x, + u32 cctl, + u8 srcwidth, u8 dstwidth, + size_t tsize) { u32 retbits = cctl; - /* Remove all src, dst and transfer size bits */ - retbits &= ~PL080_CONTROL_DWIDTH_MASK; - retbits &= ~PL080_CONTROL_SWIDTH_MASK; - retbits &= ~PL080_CONTROL_TRANSFER_SIZE_MASK; + /* + * Remove all src, dst and transfer size bits, then set the + * width and size according to the parameters. The bit offsets + * are different in the FTDMAC020 so we need to accound for this. + */ + if (pl08x->vd->ftdmac020) { + retbits &= ~FTDMAC020_LLI_DST_WIDTH_MSK; + retbits &= ~FTDMAC020_LLI_SRC_WIDTH_MSK; + retbits &= ~FTDMAC020_LLI_TRANSFER_SIZE_MASK; + + switch (srcwidth) { + case 1: + retbits |= PL080_WIDTH_8BIT << + FTDMAC020_LLI_SRC_WIDTH_SHIFT; + break; + case 2: + retbits |= PL080_WIDTH_16BIT << + FTDMAC020_LLI_SRC_WIDTH_SHIFT; + break; + case 4: + retbits |= PL080_WIDTH_32BIT << + FTDMAC020_LLI_SRC_WIDTH_SHIFT; + break; + default: + BUG(); + break; + } - /* Then set the bits according to the parameters */ - switch (srcwidth) { - case 1: - retbits |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT; - break; - case 2: - retbits |= PL080_WIDTH_16BIT << PL080_CONTROL_SWIDTH_SHIFT; - break; - case 4: - retbits |= PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT; - break; - default: - BUG(); - break; - } + switch (dstwidth) { + case 1: + retbits |= PL080_WIDTH_8BIT << + FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + case 2: + retbits |= PL080_WIDTH_16BIT << + FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + case 4: + retbits |= PL080_WIDTH_32BIT << + FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + default: + BUG(); + break; + } - switch (dstwidth) { - case 1: - retbits |= PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT; - break; - case 2: - retbits |= PL080_WIDTH_16BIT << PL080_CONTROL_DWIDTH_SHIFT; - break; - case 4: - retbits |= PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT; - break; - default: - BUG(); - break; + tsize &= FTDMAC020_LLI_TRANSFER_SIZE_MASK; + retbits |= tsize << FTDMAC020_LLI_TRANSFER_SIZE_SHIFT; + } else { + retbits &= ~PL080_CONTROL_DWIDTH_MASK; + retbits &= ~PL080_CONTROL_SWIDTH_MASK; + retbits &= ~PL080_CONTROL_TRANSFER_SIZE_MASK; + + switch (srcwidth) { + case 1: + retbits |= PL080_WIDTH_8BIT << + PL080_CONTROL_SWIDTH_SHIFT; + break; + case 2: + retbits |= PL080_WIDTH_16BIT << + PL080_CONTROL_SWIDTH_SHIFT; + break; + case 4: + retbits |= PL080_WIDTH_32BIT << + PL080_CONTROL_SWIDTH_SHIFT; + break; + default: + BUG(); + break; + } + + switch (dstwidth) { + case 1: + retbits |= PL080_WIDTH_8BIT << + PL080_CONTROL_DWIDTH_SHIFT; + break; + case 2: + retbits |= PL080_WIDTH_16BIT << + PL080_CONTROL_DWIDTH_SHIFT; + break; + case 4: + retbits |= PL080_WIDTH_32BIT << + PL080_CONTROL_DWIDTH_SHIFT; + break; + default: + BUG(); + break; + } + + tsize &= PL080_CONTROL_TRANSFER_SIZE_MASK; + retbits |= tsize << PL080_CONTROL_TRANSFER_SIZE_SHIFT; } - tsize &= PL080_CONTROL_TRANSFER_SIZE_MASK; - retbits |= tsize << PL080_CONTROL_TRANSFER_SIZE_SHIFT; return retbits; } @@ -825,13 +1122,35 @@ struct pl08x_lli_build_data { * - prefers the destination bus if both available * - prefers bus with fixed address (i.e. peripheral) */ -static void pl08x_choose_master_bus(struct pl08x_lli_build_data *bd, - struct pl08x_bus_data **mbus, struct pl08x_bus_data **sbus, u32 cctl) +static void pl08x_choose_master_bus(struct pl08x_driver_data *pl08x, + struct pl08x_lli_build_data *bd, + struct pl08x_bus_data **mbus, + struct pl08x_bus_data **sbus, + u32 cctl) { - if (!(cctl & PL080_CONTROL_DST_INCR)) { + bool dst_incr; + bool src_incr; + + /* + * The FTDMAC020 only supports memory-to-memory transfer, so + * source and destination always increase. + */ + if (pl08x->vd->ftdmac020) { + dst_incr = true; + src_incr = true; + } else { + dst_incr = !!(cctl & PL080_CONTROL_DST_INCR); + src_incr = !!(cctl & PL080_CONTROL_SRC_INCR); + } + + /* + * If either bus is not advancing, i.e. it is a peripheral, that + * one becomes master + */ + if (!dst_incr) { *mbus = &bd->dstbus; *sbus = &bd->srcbus; - } else if (!(cctl & PL080_CONTROL_SRC_INCR)) { + } else if (!src_incr) { *mbus = &bd->srcbus; *sbus = &bd->dstbus; } else { @@ -869,10 +1188,16 @@ static void pl08x_fill_lli_for_desc(struct pl08x_driver_data *pl08x, if (pl08x->vd->pl080s) llis_va[PL080S_LLI_CCTL2] = cctl2; - if (cctl & PL080_CONTROL_SRC_INCR) + if (pl08x->vd->ftdmac020) { + /* FIXME: only memcpy so far so both increase */ bd->srcbus.addr += len; - if (cctl & PL080_CONTROL_DST_INCR) bd->dstbus.addr += len; + } else { + if (cctl & PL080_CONTROL_SRC_INCR) + bd->srcbus.addr += len; + if (cctl & PL080_CONTROL_DST_INCR) + bd->dstbus.addr += len; + } BUG_ON(bd->remainder < len); @@ -883,12 +1208,12 @@ static inline void prep_byte_width_lli(struct pl08x_driver_data *pl08x, struct pl08x_lli_build_data *bd, u32 *cctl, u32 len, int num_llis, size_t *total_bytes) { - *cctl = pl08x_cctl_bits(*cctl, 1, 1, len); + *cctl = pl08x_lli_control_bits(pl08x, *cctl, 1, 1, len); pl08x_fill_lli_for_desc(pl08x, bd, num_llis, len, *cctl, len); (*total_bytes) += len; } -#ifdef VERBOSE_DEBUG +#if 1 static void pl08x_dump_lli(struct pl08x_driver_data *pl08x, const u32 *llis_va, int num_llis) { @@ -953,14 +1278,10 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, cctl = txd->cctl; /* Find maximum width of the source bus */ - bd.srcbus.maxwidth = - pl08x_get_bytes_for_cctl((cctl & PL080_CONTROL_SWIDTH_MASK) >> - PL080_CONTROL_SWIDTH_SHIFT); + bd.srcbus.maxwidth = pl08x_get_bytes_for_lli(pl08x, cctl, true); /* Find maximum width of the destination bus */ - bd.dstbus.maxwidth = - pl08x_get_bytes_for_cctl((cctl & PL080_CONTROL_DWIDTH_MASK) >> - PL080_CONTROL_DWIDTH_SHIFT); + bd.dstbus.maxwidth = pl08x_get_bytes_for_lli(pl08x, cctl, false); list_for_each_entry(dsg, &txd->dsg_list, node) { total_bytes = 0; @@ -972,7 +1293,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, bd.srcbus.buswidth = bd.srcbus.maxwidth; bd.dstbus.buswidth = bd.dstbus.maxwidth; - pl08x_choose_master_bus(&bd, &mbus, &sbus, cctl); + pl08x_choose_master_bus(pl08x, &bd, &mbus, &sbus, cctl); dev_vdbg(&pl08x->adev->dev, "src=0x%08llx%s/%u dst=0x%08llx%s/%u len=%zu\n", @@ -1009,8 +1330,14 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, * supported. Thus, we can't have scattered addresses. */ if (!bd.remainder) { - u32 fc = (txd->ccfg & PL080_CONFIG_FLOW_CONTROL_MASK) >> - PL080_CONFIG_FLOW_CONTROL_SHIFT; + u32 fc; + + /* FTDMAC020 only does memory-to-memory */ + if (pl08x->vd->ftdmac020) + fc = PL080_FLOW_MEM2MEM; + else + fc = (txd->ccfg & PL080_CONFIG_FLOW_CONTROL_MASK) >> + PL080_CONFIG_FLOW_CONTROL_SHIFT; if (!((fc >= PL080_FLOW_SRC2DST_DST) && (fc <= PL080_FLOW_SRC2DST_SRC))) { dev_err(&pl08x->adev->dev, "%s sg len can't be zero", @@ -1027,8 +1354,9 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, return 0; } - cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth, - bd.dstbus.buswidth, 0); + cctl = pl08x_lli_control_bits(pl08x, cctl, + bd.srcbus.buswidth, bd.dstbus.buswidth, + 0); pl08x_fill_lli_for_desc(pl08x, &bd, num_llis++, 0, cctl, 0); break; @@ -1107,8 +1435,9 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, "size 0x%08zx (remainder 0x%08zx)\n", __func__, lli_len, bd.remainder); - cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth, - bd.dstbus.buswidth, tsize); + cctl = pl08x_lli_control_bits(pl08x, cctl, + bd.srcbus.buswidth, bd.dstbus.buswidth, + tsize); pl08x_fill_lli_for_desc(pl08x, &bd, num_llis++, lli_len, cctl, tsize); total_bytes += lli_len; @@ -1151,7 +1480,10 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x, /* The final LLI terminates the LLI. */ last_lli[PL080_LLI_LLI] = 0; /* The final LLI element shall also fire an interrupt. */ - last_lli[PL080_LLI_CCTL] |= PL080_CONTROL_TC_IRQ_EN; + if (pl08x->vd->ftdmac020) + last_lli[PL080_LLI_CCTL] &= ~FTDMAC020_LLI_TC_MSK; + else + last_lli[PL080_LLI_CCTL] |= PL080_CONTROL_TC_IRQ_EN; } pl08x_dump_lli(pl08x, llis_va, num_llis); @@ -1317,14 +1649,25 @@ static const struct burst_table burst_sizes[] = { * will be routed to each port. We try to have source and destination * on separate ports, but always respect the allowable settings. */ -static u32 pl08x_select_bus(u8 src, u8 dst) +static u32 pl08x_select_bus(bool ftdmac020, u8 src, u8 dst) { u32 cctl = 0; + u32 dst_ahb2; + u32 src_ahb2; + + /* The FTDMAC020 use different bits to indicate src/dst bus */ + if (ftdmac020) { + dst_ahb2 = FTDMAC020_LLI_DST_SEL; + src_ahb2 = FTDMAC020_LLI_SRC_SEL; + } else { + dst_ahb2 = PL080_CONTROL_DST_AHB2; + src_ahb2 = PL080_CONTROL_SRC_AHB2; + } if (!(dst & PL08X_AHB1) || ((dst & PL08X_AHB2) && (src & PL08X_AHB1))) - cctl |= PL080_CONTROL_DST_AHB2; + cctl |= dst_ahb2; if (!(src & PL08X_AHB1) || ((src & PL08X_AHB2) && !(dst & PL08X_AHB2))) - cctl |= PL080_CONTROL_SRC_AHB2; + cctl |= src_ahb2; return cctl; } @@ -1412,14 +1755,134 @@ static struct pl08x_txd *pl08x_get_txd(struct pl08x_dma_chan *plchan) { struct pl08x_txd *txd = kzalloc(sizeof(*txd), GFP_NOWAIT); - if (txd) { + if (txd) INIT_LIST_HEAD(&txd->dsg_list); + return txd; +} - /* Always enable error and terminal interrupts */ - txd->ccfg = PL080_CONFIG_ERR_IRQ_MASK | - PL080_CONFIG_TC_IRQ_MASK; +static u32 pl08x_memcpy_cctl(struct pl08x_driver_data *pl08x) +{ + u32 cctl = 0; + + /* Conjure cctl */ + switch (pl08x->pd->memcpy_burst_size) { + default: + dev_err(&pl08x->adev->dev, + "illegal burst size for memcpy, set to 1\n"); + /* Fall through */ + case PL08X_BURST_SZ_1: + cctl |= PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_4: + cctl |= PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_8: + cctl |= PL080_BSIZE_8 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_8 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_16: + cctl |= PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_32: + cctl |= PL080_BSIZE_32 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_32 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_64: + cctl |= PL080_BSIZE_64 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_64 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_128: + cctl |= PL080_BSIZE_128 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_128 << PL080_CONTROL_DB_SIZE_SHIFT; + break; + case PL08X_BURST_SZ_256: + cctl |= PL080_BSIZE_256 << PL080_CONTROL_SB_SIZE_SHIFT | + PL080_BSIZE_256 << PL080_CONTROL_DB_SIZE_SHIFT; + break; } - return txd; + + switch (pl08x->pd->memcpy_bus_width) { + default: + dev_err(&pl08x->adev->dev, + "illegal bus width for memcpy, set to 8 bits\n"); + /* Fall through */ + case PL08X_BUS_WIDTH_8_BITS: + cctl |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT | + PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT; + break; + case PL08X_BUS_WIDTH_16_BITS: + cctl |= PL080_WIDTH_16BIT << PL080_CONTROL_SWIDTH_SHIFT | + PL080_WIDTH_16BIT << PL080_CONTROL_DWIDTH_SHIFT; + break; + case PL08X_BUS_WIDTH_32_BITS: + cctl |= PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | + PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT; + break; + } + + /* Protection flags */ + if (pl08x->pd->memcpy_prot_buff) + cctl |= PL080_CONTROL_PROT_BUFF; + if (pl08x->pd->memcpy_prot_cache) + cctl |= PL080_CONTROL_PROT_CACHE; + + /* We are the kernel, so we are in privileged mode */ + cctl |= PL080_CONTROL_PROT_SYS; + + /* Both to be incremented or the code will break */ + cctl |= PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR; + + if (pl08x->vd->dualmaster) + cctl |= pl08x_select_bus(false, + pl08x->mem_buses, + pl08x->mem_buses); + + return cctl; +} + +static u32 pl08x_ftdmac020_memcpy_cctl(struct pl08x_driver_data *pl08x) +{ + u32 cctl = 0; + + /* Conjure cctl */ + switch (pl08x->pd->memcpy_bus_width) { + default: + dev_err(&pl08x->adev->dev, + "illegal bus width for memcpy, set to 8 bits\n"); + /* Fall through */ + case PL08X_BUS_WIDTH_8_BITS: + cctl |= PL080_WIDTH_8BIT << FTDMAC020_LLI_SRC_WIDTH_SHIFT | + PL080_WIDTH_8BIT << FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + case PL08X_BUS_WIDTH_16_BITS: + cctl |= PL080_WIDTH_16BIT << FTDMAC020_LLI_SRC_WIDTH_SHIFT | + PL080_WIDTH_16BIT << FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + case PL08X_BUS_WIDTH_32_BITS: + cctl |= PL080_WIDTH_32BIT << FTDMAC020_LLI_SRC_WIDTH_SHIFT | + PL080_WIDTH_32BIT << FTDMAC020_LLI_DST_WIDTH_SHIFT; + break; + } + + /* + * By default mask the TC IRQ on all LLIs, it will be unmasked on + * the last LLI item by other code. + */ + cctl |= FTDMAC020_LLI_TC_MSK; + + /* + * Both to be incremented so leave bits FTDMAC020_LLI_SRCAD_CTL + * and FTDMAC020_LLI_DSTAD_CTL as zero + */ + if (pl08x->vd->dualmaster) + cctl |= pl08x_select_bus(true, + pl08x->mem_buses, + pl08x->mem_buses); + + return cctl; } /* @@ -1452,18 +1915,16 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_memcpy( dsg->src_addr = src; dsg->dst_addr = dest; dsg->len = len; - - /* Set platform data for m2m */ - txd->ccfg |= PL080_FLOW_MEM2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT; - txd->cctl = pl08x->pd->memcpy_channel.cctl_memcpy & - ~(PL080_CONTROL_DST_AHB2 | PL080_CONTROL_SRC_AHB2); - - /* Both to be incremented or the code will break */ - txd->cctl |= PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR; - - if (pl08x->vd->dualmaster) - txd->cctl |= pl08x_select_bus(pl08x->mem_buses, - pl08x->mem_buses); + if (pl08x->vd->ftdmac020) { + /* Writing CCFG zero ENABLES all interrupts */ + txd->ccfg = 0; + txd->cctl = pl08x_ftdmac020_memcpy_cctl(pl08x); + } else { + txd->ccfg = PL080_CONFIG_ERR_IRQ_MASK | + PL080_CONFIG_TC_IRQ_MASK | + PL080_FLOW_MEM2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT; + txd->cctl = pl08x_memcpy_cctl(pl08x); + } ret = pl08x_fill_llis_for_desc(plchan->host, txd); if (!ret) { @@ -1527,7 +1988,7 @@ static struct pl08x_txd *pl08x_init_txd( return NULL; } - txd->cctl = cctl | pl08x_select_bus(src_buses, dst_buses); + txd->cctl = cctl | pl08x_select_bus(false, src_buses, dst_buses); if (plchan->cfg.device_fc) tmp = (direction == DMA_MEM_TO_DEV) ? PL080_FLOW_MEM2PER_PER : @@ -1536,7 +1997,9 @@ static struct pl08x_txd *pl08x_init_txd( tmp = (direction == DMA_MEM_TO_DEV) ? PL080_FLOW_MEM2PER : PL080_FLOW_PER2MEM; - txd->ccfg |= tmp << PL080_CONFIG_FLOW_CONTROL_SHIFT; + txd->ccfg = PL080_CONFIG_ERR_IRQ_MASK | + PL080_CONFIG_TC_IRQ_MASK | + tmp << PL080_CONFIG_FLOW_CONTROL_SHIFT; ret = pl08x_request_mux(plchan); if (ret < 0) { @@ -1813,6 +2276,11 @@ static void pl08x_ensure_on(struct pl08x_driver_data *pl08x) /* The Nomadik variant does not have the config register */ if (pl08x->vd->nomadik) return; + /* The FTDMAC020 variant does this in another register */ + if (pl08x->vd->ftdmac020) { + writel(PL080_CONFIG_ENABLE, pl08x->base + FTDMAC020_CSR); + return; + } writel(PL080_CONFIG_ENABLE, pl08x->base + PL080_CONFIG); } @@ -1925,9 +2393,16 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x, chan->signal = i; pl08x_dma_slave_init(chan); } else { - chan->cd = &pl08x->pd->memcpy_channel; + chan->cd = kzalloc(sizeof(*chan->cd), GFP_KERNEL); + if (!chan->cd) { + kfree(chan); + return -ENOMEM; + } + chan->cd->bus_id = "memcpy"; + chan->cd->periph_buses = pl08x->pd->mem_buses; chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i); if (!chan->name) { + kfree(chan->cd); kfree(chan); return -ENOMEM; } @@ -2009,12 +2484,15 @@ static int pl08x_debugfs_show(struct seq_file *s, void *data) pl08x_state_str(chan->state)); } - seq_printf(s, "\nPL08x virtual slave channels:\n"); - seq_printf(s, "CHANNEL:\tSTATE:\n"); - seq_printf(s, "--------\t------\n"); - list_for_each_entry(chan, &pl08x->slave.channels, vc.chan.device_node) { - seq_printf(s, "%s\t\t%s\n", chan->name, - pl08x_state_str(chan->state)); + if (pl08x->has_slave) { + seq_printf(s, "\nPL08x virtual slave channels:\n"); + seq_printf(s, "CHANNEL:\tSTATE:\n"); + seq_printf(s, "--------\t------\n"); + list_for_each_entry(chan, &pl08x->slave.channels, + vc.chan.device_node) { + seq_printf(s, "%s\t\t%s\n", chan->name, + pl08x_state_str(chan->state)); + } } return 0; @@ -2052,6 +2530,10 @@ static struct dma_chan *pl08x_find_chan_id(struct pl08x_driver_data *pl08x, { struct pl08x_dma_chan *chan; + /* Trying to get a slave channel from something with no slave support */ + if (!pl08x->has_slave) + return NULL; + list_for_each_entry(chan, &pl08x->slave.channels, vc.chan.device_node) { if (chan->signal == id) return &chan->vc.chan; @@ -2099,7 +2581,6 @@ static int pl08x_of_probe(struct amba_device *adev, { struct pl08x_platform_data *pd; struct pl08x_channel_data *chanp = NULL; - u32 cctl_memcpy = 0; u32 val; int ret; int i; @@ -2139,36 +2620,28 @@ static int pl08x_of_probe(struct amba_device *adev, dev_err(&adev->dev, "illegal burst size for memcpy, set to 1\n"); /* Fall through */ case 1: - cctl_memcpy |= PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_1; break; case 4: - cctl_memcpy |= PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_4; break; case 8: - cctl_memcpy |= PL080_BSIZE_8 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_8 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_8; break; case 16: - cctl_memcpy |= PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_16; break; case 32: - cctl_memcpy |= PL080_BSIZE_32 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_32 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_32; break; case 64: - cctl_memcpy |= PL080_BSIZE_64 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_64 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_64; break; case 128: - cctl_memcpy |= PL080_BSIZE_128 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_128 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_128; break; case 256: - cctl_memcpy |= PL080_BSIZE_256 << PL080_CONTROL_SB_SIZE_SHIFT | - PL080_BSIZE_256 << PL080_CONTROL_DB_SIZE_SHIFT; + pd->memcpy_burst_size = PL08X_BURST_SZ_256; break; } @@ -2182,48 +2655,40 @@ static int pl08x_of_probe(struct amba_device *adev, dev_err(&adev->dev, "illegal bus width for memcpy, set to 8 bits\n"); /* Fall through */ case 8: - cctl_memcpy |= PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT | - PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT; + pd->memcpy_bus_width = PL08X_BUS_WIDTH_8_BITS; break; case 16: - cctl_memcpy |= PL080_WIDTH_16BIT << PL080_CONTROL_SWIDTH_SHIFT | - PL080_WIDTH_16BIT << PL080_CONTROL_DWIDTH_SHIFT; + pd->memcpy_bus_width = PL08X_BUS_WIDTH_16_BITS; break; case 32: - cctl_memcpy |= PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | - PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT; + pd->memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS; break; } - /* This is currently the only thing making sense */ - cctl_memcpy |= PL080_CONTROL_PROT_SYS; - - /* Set up memcpy channel */ - pd->memcpy_channel.bus_id = "memcpy"; - pd->memcpy_channel.cctl_memcpy = cctl_memcpy; - /* Use the buses that can access memory, obviously */ - pd->memcpy_channel.periph_buses = pd->mem_buses; - /* * Allocate channel data for all possible slave channels (one * for each possible signal), channels will then be allocated * for a device and have it's AHB interfaces set up at * translation time. */ - chanp = devm_kcalloc(&adev->dev, - pl08x->vd->signals, - sizeof(struct pl08x_channel_data), - GFP_KERNEL); - if (!chanp) - return -ENOMEM; + if (pl08x->vd->signals) { + chanp = devm_kcalloc(&adev->dev, + pl08x->vd->signals, + sizeof(struct pl08x_channel_data), + GFP_KERNEL); + if (!chanp) + return -ENOMEM; - pd->slave_channels = chanp; - for (i = 0; i < pl08x->vd->signals; i++) { - /* chanp->periph_buses will be assigned at translation */ - chanp->bus_id = kasprintf(GFP_KERNEL, "slave%d", i); - chanp++; + pd->slave_channels = chanp; + for (i = 0; i < pl08x->vd->signals; i++) { + /* + * chanp->periph_buses will be assigned at translation + */ + chanp->bus_id = kasprintf(GFP_KERNEL, "slave%d", i); + chanp++; + } + pd->num_slave_channels = pl08x->vd->signals; } - pd->num_slave_channels = pl08x->vd->signals; pl08x->pd = pd; @@ -2242,7 +2707,7 @@ static inline int pl08x_of_probe(struct amba_device *adev, static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) { struct pl08x_driver_data *pl08x; - const struct vendor_data *vd = id->data; + struct vendor_data *vd = id->data; struct device_node *np = adev->dev.of_node; u32 tsfr_size; int ret = 0; @@ -2268,6 +2733,34 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) pl08x->adev = adev; pl08x->vd = vd; + pl08x->base = ioremap(adev->res.start, resource_size(&adev->res)); + if (!pl08x->base) { + ret = -ENOMEM; + goto out_no_ioremap; + } + + if (vd->ftdmac020) { + u32 val; + + val = readl(pl08x->base + FTDMAC020_REVISION); + dev_info(&pl08x->adev->dev, "FTDMAC020 %d.%d rel %d\n", + (val >> 16) & 0xff, (val >> 8) & 0xff, val & 0xff); + val = readl(pl08x->base + FTDMAC020_FEATURE); + dev_info(&pl08x->adev->dev, "FTDMAC020 %d channels, " + "%s built-in bridge, %s, %s linked lists\n", + (val >> 12) & 0x0f, + (val & BIT(10)) ? "no" : "has", + (val & BIT(9)) ? "AHB0 and AHB1" : "AHB0", + (val & BIT(8)) ? "supports" : "does not support"); + + /* Vendor data from feature register */ + if (!(val & BIT(8))) + dev_warn(&pl08x->adev->dev, + "linked lists not supported, required\n"); + vd->channels = (val >> 12) & 0x0f; + vd->dualmaster = !!(val & BIT(9)); + } + /* Initialize memcpy engine */ dma_cap_set(DMA_MEMCPY, pl08x->memcpy.cap_mask); pl08x->memcpy.dev = &adev->dev; @@ -2284,25 +2777,38 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS; pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM); pl08x->memcpy.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + if (vd->ftdmac020) + pl08x->memcpy.copy_align = DMAENGINE_ALIGN_4_BYTES; - /* Initialize slave engine */ - dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask); - dma_cap_set(DMA_CYCLIC, pl08x->slave.cap_mask); - pl08x->slave.dev = &adev->dev; - pl08x->slave.device_free_chan_resources = pl08x_free_chan_resources; - pl08x->slave.device_prep_dma_interrupt = pl08x_prep_dma_interrupt; - pl08x->slave.device_tx_status = pl08x_dma_tx_status; - pl08x->slave.device_issue_pending = pl08x_issue_pending; - pl08x->slave.device_prep_slave_sg = pl08x_prep_slave_sg; - pl08x->slave.device_prep_dma_cyclic = pl08x_prep_dma_cyclic; - pl08x->slave.device_config = pl08x_config; - pl08x->slave.device_pause = pl08x_pause; - pl08x->slave.device_resume = pl08x_resume; - pl08x->slave.device_terminate_all = pl08x_terminate_all; - pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS; - pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS; - pl08x->slave.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); - pl08x->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + + /* + * Initialize slave engine, if the block has no signals, that means + * we have no slave support. + */ + if (vd->signals) { + pl08x->has_slave = true; + dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask); + dma_cap_set(DMA_CYCLIC, pl08x->slave.cap_mask); + pl08x->slave.dev = &adev->dev; + pl08x->slave.device_free_chan_resources = + pl08x_free_chan_resources; + pl08x->slave.device_prep_dma_interrupt = + pl08x_prep_dma_interrupt; + pl08x->slave.device_tx_status = pl08x_dma_tx_status; + pl08x->slave.device_issue_pending = pl08x_issue_pending; + pl08x->slave.device_prep_slave_sg = pl08x_prep_slave_sg; + pl08x->slave.device_prep_dma_cyclic = pl08x_prep_dma_cyclic; + pl08x->slave.device_config = pl08x_config; + pl08x->slave.device_pause = pl08x_pause; + pl08x->slave.device_resume = pl08x_resume; + pl08x->slave.device_terminate_all = pl08x_terminate_all; + pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->slave.directions = + BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + pl08x->slave.residue_granularity = + DMA_RESIDUE_GRANULARITY_SEGMENT; + } /* Get the platform data */ pl08x->pd = dev_get_platdata(&adev->dev); @@ -2344,19 +2850,18 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) goto out_no_lli_pool; } - pl08x->base = ioremap(adev->res.start, resource_size(&adev->res)); - if (!pl08x->base) { - ret = -ENOMEM; - goto out_no_ioremap; - } - /* Turn on the PL08x */ pl08x_ensure_on(pl08x); - /* Attach the interrupt handler */ - writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR); + /* Clear any pending interrupts */ + if (vd->ftdmac020) + /* This variant has error IRQs in bits 16-19 */ + writel(0x0000FFFF, pl08x->base + PL080_ERR_CLEAR); + else + writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR); writel(0x000000FF, pl08x->base + PL080_TC_CLEAR); + /* Attach the interrupt handler */ ret = request_irq(adev->irq[0], pl08x_irq, 0, DRIVER_NAME, pl08x); if (ret) { dev_err(&adev->dev, "%s failed to request interrupt %d\n", @@ -2377,7 +2882,25 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) ch->id = i; ch->base = pl08x->base + PL080_Cx_BASE(i); - ch->reg_config = ch->base + vd->config_offset; + if (vd->ftdmac020) { + /* FTDMA020 has a special channel busy register */ + ch->reg_busy = ch->base + FTDMAC020_CH_BUSY; + ch->reg_config = ch->base + FTDMAC020_CH_CFG; + ch->reg_control = ch->base + FTDMAC020_CH_CSR; + ch->reg_src = ch->base + FTDMAC020_CH_SRC_ADDR; + ch->reg_dst = ch->base + FTDMAC020_CH_DST_ADDR; + ch->reg_lli = ch->base + FTDMAC020_CH_LLP; + ch->ftdmac020 = true; + } else { + ch->reg_config = ch->base + vd->config_offset; + ch->reg_control = ch->base + PL080_CH_CONTROL; + ch->reg_src = ch->base + PL080_CH_SRC_ADDR; + ch->reg_dst = ch->base + PL080_CH_DST_ADDR; + ch->reg_lli = ch->base + PL080_CH_LLI; + } + if (vd->pl080s) + ch->pl080s = true; + spin_lock_init(&ch->lock); /* @@ -2410,13 +2933,15 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) } /* Register slave channels */ - ret = pl08x_dma_init_virtual_channels(pl08x, &pl08x->slave, - pl08x->pd->num_slave_channels, true); - if (ret < 0) { - dev_warn(&pl08x->adev->dev, - "%s failed to enumerate slave channels - %d\n", - __func__, ret); - goto out_no_slave; + if (pl08x->has_slave) { + ret = pl08x_dma_init_virtual_channels(pl08x, &pl08x->slave, + pl08x->pd->num_slave_channels, true); + if (ret < 0) { + dev_warn(&pl08x->adev->dev, + "%s failed to enumerate slave channels - %d\n", + __func__, ret); + goto out_no_slave; + } } ret = dma_async_device_register(&pl08x->memcpy); @@ -2427,12 +2952,14 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) goto out_no_memcpy_reg; } - ret = dma_async_device_register(&pl08x->slave); - if (ret) { - dev_warn(&pl08x->adev->dev, + if (pl08x->has_slave) { + ret = dma_async_device_register(&pl08x->slave); + if (ret) { + dev_warn(&pl08x->adev->dev, "%s failed to register slave as an async device - %d\n", __func__, ret); - goto out_no_slave_reg; + goto out_no_slave_reg; + } } amba_set_drvdata(adev, pl08x); @@ -2446,7 +2973,8 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) out_no_slave_reg: dma_async_device_unregister(&pl08x->memcpy); out_no_memcpy_reg: - pl08x_free_virtual_channels(&pl08x->slave); + if (pl08x->has_slave) + pl08x_free_virtual_channels(&pl08x->slave); out_no_slave: pl08x_free_virtual_channels(&pl08x->memcpy); out_no_memcpy: @@ -2454,11 +2982,11 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) out_no_phychans: free_irq(adev->irq[0], pl08x); out_no_irq: - iounmap(pl08x->base); -out_no_ioremap: dma_pool_destroy(pl08x->pool); out_no_lli_pool: out_no_platdata: + iounmap(pl08x->base); +out_no_ioremap: kfree(pl08x); out_no_pl08x: amba_release_regions(adev); @@ -2499,6 +3027,12 @@ static struct vendor_data vendor_pl081 = { .max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK, }; +static struct vendor_data vendor_ftdmac020 = { + .config_offset = PL080_CH_CONFIG, + .ftdmac020 = true, + .max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK, +}; + static struct amba_id pl08x_ids[] = { /* Samsung PL080S variant */ { @@ -2524,6 +3058,12 @@ static struct amba_id pl08x_ids[] = { .mask = 0x00ffffff, .data = &vendor_nomadik, }, + /* Faraday Technology FTDMAC020 */ + { + .id = 0x0003b080, + .mask = 0x000fffff, + .data = &vendor_ftdmac020, + }, { 0, 0 }, }; diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c new file mode 100644 index 00000000000000..e41bbc7cb0941b --- /dev/null +++ b/drivers/dma/bcm-sba-raid.c @@ -0,0 +1,1785 @@ +/* + * Copyright (C) 2017 Broadcom + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Broadcom SBA RAID Driver + * + * The Broadcom stream buffer accelerator (SBA) provides offloading + * capabilities for RAID operations. The SBA offload engine is accessible + * via Broadcom SoC specific ring manager. Two or more offload engines + * can share same Broadcom SoC specific ring manager due to this Broadcom + * SoC specific ring manager driver is implemented as a mailbox controller + * driver and offload engine drivers are implemented as mallbox clients. + * + * Typically, Broadcom SoC specific ring manager will implement larger + * number of hardware rings over one or more SBA hardware devices. By + * design, the internal buffer size of SBA hardware device is limited + * but all offload operations supported by SBA can be broken down into + * multiple small size requests and executed parallely on multiple SBA + * hardware devices for achieving high through-put. + * + * The Broadcom SBA RAID driver does not require any register programming + * except submitting request to SBA hardware device via mailbox channels. + * This driver implements a DMA device with one DMA channel using a set + * of mailbox channels provided by Broadcom SoC specific ring manager + * driver. To exploit parallelism (as described above), all DMA request + * coming to SBA RAID DMA channel are broken down to smaller requests + * and submitted to multiple mailbox channels in round-robin fashion. + * For having more SBA DMA channels, we can create more SBA device nodes + * in Broadcom SoC specific DTS based on number of hardware rings supported + * by Broadcom SoC ring manager. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dmaengine.h" + +/* SBA command related defines */ +#define SBA_TYPE_SHIFT 48 +#define SBA_TYPE_MASK GENMASK(1, 0) +#define SBA_TYPE_A 0x0 +#define SBA_TYPE_B 0x2 +#define SBA_TYPE_C 0x3 +#define SBA_USER_DEF_SHIFT 32 +#define SBA_USER_DEF_MASK GENMASK(15, 0) +#define SBA_R_MDATA_SHIFT 24 +#define SBA_R_MDATA_MASK GENMASK(7, 0) +#define SBA_C_MDATA_MS_SHIFT 18 +#define SBA_C_MDATA_MS_MASK GENMASK(1, 0) +#define SBA_INT_SHIFT 17 +#define SBA_INT_MASK BIT(0) +#define SBA_RESP_SHIFT 16 +#define SBA_RESP_MASK BIT(0) +#define SBA_C_MDATA_SHIFT 8 +#define SBA_C_MDATA_MASK GENMASK(7, 0) +#define SBA_C_MDATA_BNUMx_SHIFT(__bnum) (2 * (__bnum)) +#define SBA_C_MDATA_BNUMx_MASK GENMASK(1, 0) +#define SBA_C_MDATA_DNUM_SHIFT 5 +#define SBA_C_MDATA_DNUM_MASK GENMASK(4, 0) +#define SBA_C_MDATA_LS(__v) ((__v) & 0xff) +#define SBA_C_MDATA_MS(__v) (((__v) >> 8) & 0x3) +#define SBA_CMD_SHIFT 0 +#define SBA_CMD_MASK GENMASK(3, 0) +#define SBA_CMD_ZERO_BUFFER 0x4 +#define SBA_CMD_ZERO_ALL_BUFFERS 0x8 +#define SBA_CMD_LOAD_BUFFER 0x9 +#define SBA_CMD_XOR 0xa +#define SBA_CMD_GALOIS_XOR 0xb +#define SBA_CMD_WRITE_BUFFER 0xc +#define SBA_CMD_GALOIS 0xe + +/* Driver helper macros */ +#define to_sba_request(tx) \ + container_of(tx, struct sba_request, tx) +#define to_sba_device(dchan) \ + container_of(dchan, struct sba_device, dma_chan) + +enum sba_request_state { + SBA_REQUEST_STATE_FREE = 1, + SBA_REQUEST_STATE_ALLOCED = 2, + SBA_REQUEST_STATE_PENDING = 3, + SBA_REQUEST_STATE_ACTIVE = 4, + SBA_REQUEST_STATE_RECEIVED = 5, + SBA_REQUEST_STATE_COMPLETED = 6, + SBA_REQUEST_STATE_ABORTED = 7, +}; + +struct sba_request { + /* Global state */ + struct list_head node; + struct sba_device *sba; + enum sba_request_state state; + bool fence; + /* Chained requests management */ + struct sba_request *first; + struct list_head next; + unsigned int next_count; + atomic_t next_pending_count; + /* BRCM message data */ + void *resp; + dma_addr_t resp_dma; + struct brcm_sba_command *cmds; + struct brcm_message msg; + struct dma_async_tx_descriptor tx; +}; + +enum sba_version { + SBA_VER_1 = 0, + SBA_VER_2 +}; + +struct sba_device { + /* Underlying device */ + struct device *dev; + /* DT configuration parameters */ + enum sba_version ver; + /* Derived configuration parameters */ + u32 max_req; + u32 hw_buf_size; + u32 hw_resp_size; + u32 max_pq_coefs; + u32 max_pq_srcs; + u32 max_cmd_per_req; + u32 max_xor_srcs; + u32 max_resp_pool_size; + u32 max_cmds_pool_size; + /* Maibox client and Mailbox channels */ + struct mbox_client client; + int mchans_count; + atomic_t mchans_current; + struct mbox_chan **mchans; + struct device *mbox_dev; + /* DMA device and DMA channel */ + struct dma_device dma_dev; + struct dma_chan dma_chan; + /* DMA channel resources */ + void *resp_base; + dma_addr_t resp_dma_base; + void *cmds_base; + dma_addr_t cmds_dma_base; + spinlock_t reqs_lock; + struct sba_request *reqs; + bool reqs_fence; + struct list_head reqs_alloc_list; + struct list_head reqs_pending_list; + struct list_head reqs_active_list; + struct list_head reqs_received_list; + struct list_head reqs_completed_list; + struct list_head reqs_aborted_list; + struct list_head reqs_free_list; + int reqs_free_count; +}; + +/* ====== SBA command helper routines ===== */ + +static inline u64 __pure sba_cmd_enc(u64 cmd, u32 val, u32 shift, u32 mask) +{ + cmd &= ~((u64)mask << shift); + cmd |= ((u64)(val & mask) << shift); + return cmd; +} + +static inline u32 __pure sba_cmd_load_c_mdata(u32 b0) +{ + return b0 & SBA_C_MDATA_BNUMx_MASK; +} + +static inline u32 __pure sba_cmd_write_c_mdata(u32 b0) +{ + return b0 & SBA_C_MDATA_BNUMx_MASK; +} + +static inline u32 __pure sba_cmd_xor_c_mdata(u32 b1, u32 b0) +{ + return (b0 & SBA_C_MDATA_BNUMx_MASK) | + ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1)); +} + +static inline u32 __pure sba_cmd_pq_c_mdata(u32 d, u32 b1, u32 b0) +{ + return (b0 & SBA_C_MDATA_BNUMx_MASK) | + ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1)) | + ((d & SBA_C_MDATA_DNUM_MASK) << SBA_C_MDATA_DNUM_SHIFT); +} + +/* ====== Channel resource management routines ===== */ + +static struct sba_request *sba_alloc_request(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req = NULL; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + req = list_first_entry_or_null(&sba->reqs_free_list, + struct sba_request, node); + if (req) { + list_move_tail(&req->node, &sba->reqs_alloc_list); + req->state = SBA_REQUEST_STATE_ALLOCED; + req->fence = false; + req->first = req; + INIT_LIST_HEAD(&req->next); + req->next_count = 1; + atomic_set(&req->next_pending_count, 1); + + sba->reqs_free_count--; + + dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan); + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); + + return req; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_pending_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_PENDING; + list_move_tail(&req->node, &sba->reqs_pending_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; +} + +/* Note: Must be called with sba->reqs_lock held */ +static bool _sba_active_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + if (sba->reqs_fence) + return false; + req->state = SBA_REQUEST_STATE_ACTIVE; + list_move_tail(&req->node, &sba->reqs_active_list); + if (req->fence) + sba->reqs_fence = true; + return true; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_abort_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_ABORTED; + list_move_tail(&req->node, &sba->reqs_aborted_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; +} + +/* Note: Must be called with sba->reqs_lock held */ +static void _sba_free_request(struct sba_device *sba, + struct sba_request *req) +{ + lockdep_assert_held(&sba->reqs_lock); + req->state = SBA_REQUEST_STATE_FREE; + list_move_tail(&req->node, &sba->reqs_free_list); + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + sba->reqs_free_count++; +} + +static void sba_received_request(struct sba_request *req) +{ + unsigned long flags; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + req->state = SBA_REQUEST_STATE_RECEIVED; + list_move_tail(&req->node, &sba->reqs_received_list); + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_complete_chained_requests(struct sba_request *req) +{ + unsigned long flags; + struct sba_request *nreq; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + req->state = SBA_REQUEST_STATE_COMPLETED; + list_move_tail(&req->node, &sba->reqs_completed_list); + list_for_each_entry(nreq, &req->next, next) { + nreq->state = SBA_REQUEST_STATE_COMPLETED; + list_move_tail(&nreq->node, &sba->reqs_completed_list); + } + if (list_empty(&sba->reqs_active_list)) + sba->reqs_fence = false; + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_free_chained_requests(struct sba_request *req) +{ + unsigned long flags; + struct sba_request *nreq; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + _sba_free_request(sba, req); + list_for_each_entry(nreq, &req->next, next) + _sba_free_request(sba, nreq); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_chain_request(struct sba_request *first, + struct sba_request *req) +{ + unsigned long flags; + struct sba_device *sba = req->sba; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + list_add_tail(&req->next, &first->next); + req->first = first; + first->next_count++; + atomic_set(&first->next_pending_count, first->next_count); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_cleanup_nonpending_requests(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req, *req1; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Freeup all alloced request */ + list_for_each_entry_safe(req, req1, &sba->reqs_alloc_list, node) + _sba_free_request(sba, req); + + /* Freeup all received request */ + list_for_each_entry_safe(req, req1, &sba->reqs_received_list, node) + _sba_free_request(sba, req); + + /* Freeup all completed request */ + list_for_each_entry_safe(req, req1, &sba->reqs_completed_list, node) + _sba_free_request(sba, req); + + /* Set all active requests as aborted */ + list_for_each_entry_safe(req, req1, &sba->reqs_active_list, node) + _sba_abort_request(sba, req); + + /* + * Note: We expect that aborted request will be eventually + * freed by sba_receive_message() + */ + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static void sba_cleanup_pending_requests(struct sba_device *sba) +{ + unsigned long flags; + struct sba_request *req, *req1; + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Freeup all pending request */ + list_for_each_entry_safe(req, req1, &sba->reqs_pending_list, node) + _sba_free_request(sba, req); + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +/* ====== DMAENGINE callbacks ===== */ + +static void sba_free_chan_resources(struct dma_chan *dchan) +{ + /* + * Channel resources are pre-alloced so we just free-up + * whatever we can so that we can re-use pre-alloced + * channel resources next time. + */ + sba_cleanup_nonpending_requests(to_sba_device(dchan)); +} + +static int sba_device_terminate_all(struct dma_chan *dchan) +{ + /* Cleanup all pending requests */ + sba_cleanup_pending_requests(to_sba_device(dchan)); + + return 0; +} + +static int sba_send_mbox_request(struct sba_device *sba, + struct sba_request *req) +{ + int mchans_idx, ret = 0; + + /* Select mailbox channel in round-robin fashion */ + mchans_idx = atomic_inc_return(&sba->mchans_current); + mchans_idx = mchans_idx % sba->mchans_count; + + /* Send message for the request */ + req->msg.error = 0; + ret = mbox_send_message(sba->mchans[mchans_idx], &req->msg); + if (ret < 0) { + dev_err(sba->dev, "send message failed with error %d", ret); + return ret; + } + ret = req->msg.error; + if (ret < 0) { + dev_err(sba->dev, "message error %d", ret); + return ret; + } + + return 0; +} + +static void sba_issue_pending(struct dma_chan *dchan) +{ + int ret; + unsigned long flags; + struct sba_request *req, *req1; + struct sba_device *sba = to_sba_device(dchan); + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Process all pending request */ + list_for_each_entry_safe(req, req1, &sba->reqs_pending_list, node) { + /* Try to make request active */ + if (!_sba_active_request(sba, req)) + break; + + /* Send request to mailbox channel */ + spin_unlock_irqrestore(&sba->reqs_lock, flags); + ret = sba_send_mbox_request(sba, req); + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* If something went wrong then keep request pending */ + if (ret < 0) { + _sba_pending_request(sba, req); + break; + } + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); +} + +static dma_cookie_t sba_tx_submit(struct dma_async_tx_descriptor *tx) +{ + unsigned long flags; + dma_cookie_t cookie; + struct sba_device *sba; + struct sba_request *req, *nreq; + + if (unlikely(!tx)) + return -EINVAL; + + sba = to_sba_device(tx->chan); + req = to_sba_request(tx); + + /* Assign cookie and mark all chained requests pending */ + spin_lock_irqsave(&sba->reqs_lock, flags); + cookie = dma_cookie_assign(tx); + _sba_pending_request(sba, req); + list_for_each_entry(nreq, &req->next, next) + _sba_pending_request(sba, nreq); + spin_unlock_irqrestore(&sba->reqs_lock, flags); + + return cookie; +} + +static enum dma_status sba_tx_status(struct dma_chan *dchan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + int mchan_idx; + enum dma_status ret; + struct sba_device *sba = to_sba_device(dchan); + + for (mchan_idx = 0; mchan_idx < sba->mchans_count; mchan_idx++) + mbox_client_peek_data(sba->mchans[mchan_idx]); + + ret = dma_cookie_status(dchan, cookie, txstate); + if (ret == DMA_COMPLETE) + return ret; + + return dma_cookie_status(dchan, cookie, txstate); +} + +static void sba_fillup_interrupt_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg) +{ + u64 cmd; + u32 c_mdata; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load dummy data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = req->resp_dma; + cmdsp->data_len = req->sba->hw_resp_size; + cmdsp++; + + /* Type-A command to write buf0 to dummy location */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = req->resp_dma; + cmdsp->data_len = req->sba->hw_resp_size; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_interrupt(struct dma_chan *dchan, unsigned long flags) +{ + struct sba_request *req = NULL; + struct sba_device *sba = to_sba_device(dchan); + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + + /* + * Force fence so that no requests are submitted + * until DMA callback for this request is invoked. + */ + req->fence = true; + + /* Fillup request message */ + sba_fillup_interrupt_msg(req, req->cmds, &req->msg); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return &req->tx; +} + +static void sba_fillup_memcpy_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t dst, dma_addr_t src) +{ + u64 cmd; + u32 c_mdata; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = dst + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +static struct sba_request * +sba_prep_dma_memcpy_req(struct sba_device *sba, + dma_addr_t off, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request message */ + sba_fillup_memcpy_msg(req, req->cmds, &req->msg, + off, len, dst, src); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + size_t req_len; + dma_addr_t off = 0; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + req = sba_prep_dma_memcpy_req(sba, off, dst, src, + req_len, flags); + if (!req) { + if (first) + sba_free_chained_requests(first); + return NULL; + } + + if (first) + sba_chain_request(first, req); + else + first = req; + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; +} + +static void sba_fillup_xor_msg(struct sba_request *req, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t dst, dma_addr_t *src, u32 src_cnt) +{ + u64 cmd; + u32 c_mdata; + unsigned int i; + struct brcm_sba_command *cmdsp = cmds; + + /* Type-B command to load data into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[0] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Type-B commands to xor data with buf0 and put it back in buf0 */ + for (i = 1; i < src_cnt; i++) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[i] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = dst + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_xor_req(struct sba_device *sba, + dma_addr_t off, dma_addr_t dst, dma_addr_t *src, + u32 src_cnt, size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request message */ + sba_fillup_xor_msg(req, req->cmds, &req->msg, + off, len, dst, src, src_cnt); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_xor(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t *src, + u32 src_cnt, size_t len, unsigned long flags) +{ + size_t req_len; + dma_addr_t off = 0; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Sanity checks */ + if (unlikely(src_cnt > sba->max_xor_srcs)) + return NULL; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + req = sba_prep_dma_xor_req(sba, off, dst, src, src_cnt, + req_len, flags); + if (!req) { + if (first) + sba_free_chained_requests(first); + return NULL; + } + + if (first) + sba_chain_request(first, req); + else + first = req; + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; +} + +static void sba_fillup_pq_msg(struct sba_request *req, + bool pq_continue, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t *dst_p, dma_addr_t *dst_q, + const u8 *scf, dma_addr_t *src, u32 src_cnt) +{ + u64 cmd; + u32 c_mdata; + unsigned int i; + struct brcm_sba_command *cmdsp = cmds; + + if (pq_continue) { + /* Type-B command to load old P into buf0 */ + if (dst_p) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-B command to load old Q into buf1 */ + if (dst_q) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + } else { + /* Type-A command to zero all buffers */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + } + + /* Type-B commands for generate P onto buf0 and Q onto buf1 */ + for (i = 0; i < src_cnt; i++) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(raid6_gflog[scf[i]], 1, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src[i] + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + if (dst_p) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf1 */ + if (dst_q) { + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_pq_req(struct sba_device *sba, dma_addr_t off, + dma_addr_t *dst_p, dma_addr_t *dst_q, dma_addr_t *src, + u32 src_cnt, const u8 *scf, size_t len, unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request messages */ + sba_fillup_pq_msg(req, dmaf_continue(flags), + req->cmds, &req->msg, + off, len, dst_p, dst_q, scf, src, src_cnt); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static void sba_fillup_pq_single_msg(struct sba_request *req, + bool pq_continue, + struct brcm_sba_command *cmds, + struct brcm_message *msg, + dma_addr_t msg_offset, size_t msg_len, + dma_addr_t *dst_p, dma_addr_t *dst_q, + dma_addr_t src, u8 scf) +{ + u64 cmd; + u32 c_mdata; + u8 pos, dpos = raid6_gflog[scf]; + struct brcm_sba_command *cmdsp = cmds; + + if (!dst_p) + goto skip_p; + + if (pq_continue) { + /* Type-B command to load old P into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + /* + * Type-B commands to xor data with buf0 and put it + * back in buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } else { + /* Type-B command to load old P into buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_load_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_p + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + +skip_p: + if (!dst_q) + goto skip_q; + + /* Type-A command to zero all buffers */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + + if (dpos == 255) + goto skip_q_computation; + pos = (dpos < req->sba->max_pq_coefs) ? + dpos : (req->sba->max_pq_coefs - 1); + + /* + * Type-B command to generate initial Q from data + * and store output into buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(pos, 0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = src + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + + dpos -= pos; + + /* Multiple Type-A command to generate final Q */ + while (dpos) { + pos = (dpos < req->sba->max_pq_coefs) ? + dpos : (req->sba->max_pq_coefs - 1); + + /* + * Type-A command to generate Q with buf0 and + * buf1 store result in buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_pq_c_mdata(pos, 0, 1); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata), + SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + cmdsp++; + + dpos -= pos; + } + +skip_q_computation: + if (pq_continue) { + /* + * Type-B command to XOR previous output with + * buf0 and write it into buf0 + */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_B, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + c_mdata = sba_cmd_xor_c_mdata(0, 0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_XOR, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_B; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + } + + /* Type-A command to write buf0 */ + cmd = sba_cmd_enc(0x0, SBA_TYPE_A, + SBA_TYPE_SHIFT, SBA_TYPE_MASK); + cmd = sba_cmd_enc(cmd, msg_len, + SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK); + cmd = sba_cmd_enc(cmd, 0x1, + SBA_RESP_SHIFT, SBA_RESP_MASK); + c_mdata = sba_cmd_write_c_mdata(0); + cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata), + SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK); + cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER, + SBA_CMD_SHIFT, SBA_CMD_MASK); + cmdsp->cmd = cmd; + *cmdsp->cmd_dma = cpu_to_le64(cmd); + cmdsp->flags = BRCM_SBA_CMD_TYPE_A; + if (req->sba->hw_resp_size) { + cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP; + cmdsp->resp = req->resp_dma; + cmdsp->resp_len = req->sba->hw_resp_size; + } + cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT; + cmdsp->data = *dst_q + msg_offset; + cmdsp->data_len = msg_len; + cmdsp++; + +skip_q: + /* Fillup brcm_message */ + msg->type = BRCM_MESSAGE_SBA; + msg->sba.cmds = cmds; + msg->sba.cmds_count = cmdsp - cmds; + msg->ctx = req; + msg->error = 0; +} + +struct sba_request * +sba_prep_dma_pq_single_req(struct sba_device *sba, dma_addr_t off, + dma_addr_t *dst_p, dma_addr_t *dst_q, + dma_addr_t src, u8 scf, size_t len, + unsigned long flags) +{ + struct sba_request *req = NULL; + + /* Alloc new request */ + req = sba_alloc_request(sba); + if (!req) + return NULL; + req->fence = (flags & DMA_PREP_FENCE) ? true : false; + + /* Fillup request messages */ + sba_fillup_pq_single_msg(req, dmaf_continue(flags), + req->cmds, &req->msg, off, len, + dst_p, dst_q, src, scf); + + /* Init async_tx descriptor */ + req->tx.flags = flags; + req->tx.cookie = -EBUSY; + + return req; +} + +static struct dma_async_tx_descriptor * +sba_prep_dma_pq(struct dma_chan *dchan, dma_addr_t *dst, dma_addr_t *src, + u32 src_cnt, const u8 *scf, size_t len, unsigned long flags) +{ + u32 i, dst_q_index; + size_t req_len; + bool slow = false; + dma_addr_t off = 0; + dma_addr_t *dst_p = NULL, *dst_q = NULL; + struct sba_device *sba = to_sba_device(dchan); + struct sba_request *first = NULL, *req; + + /* Sanity checks */ + if (unlikely(src_cnt > sba->max_pq_srcs)) + return NULL; + for (i = 0; i < src_cnt; i++) + if (sba->max_pq_coefs <= raid6_gflog[scf[i]]) + slow = true; + + /* Figure-out P and Q destination addresses */ + if (!(flags & DMA_PREP_PQ_DISABLE_P)) + dst_p = &dst[0]; + if (!(flags & DMA_PREP_PQ_DISABLE_Q)) + dst_q = &dst[1]; + + /* Create chained requests where each request is upto hw_buf_size */ + while (len) { + req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size; + + if (slow) { + dst_q_index = src_cnt; + + if (dst_q) { + for (i = 0; i < src_cnt; i++) { + if (*dst_q == src[i]) { + dst_q_index = i; + break; + } + } + } + + if (dst_q_index < src_cnt) { + i = dst_q_index; + req = sba_prep_dma_pq_single_req(sba, + off, dst_p, dst_q, src[i], scf[i], + req_len, flags | DMA_PREP_FENCE); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + + flags |= DMA_PREP_CONTINUE; + } + + for (i = 0; i < src_cnt; i++) { + if (dst_q_index == i) + continue; + + req = sba_prep_dma_pq_single_req(sba, + off, dst_p, dst_q, src[i], scf[i], + req_len, flags | DMA_PREP_FENCE); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + + flags |= DMA_PREP_CONTINUE; + } + } else { + req = sba_prep_dma_pq_req(sba, off, + dst_p, dst_q, src, src_cnt, + scf, req_len, flags); + if (!req) + goto fail; + + if (first) + sba_chain_request(first, req); + else + first = req; + } + + off += req_len; + len -= req_len; + } + + return (first) ? &first->tx : NULL; + +fail: + if (first) + sba_free_chained_requests(first); + return NULL; +} + +/* ====== Mailbox callbacks ===== */ + +static void sba_dma_tx_actions(struct sba_request *req) +{ + struct dma_async_tx_descriptor *tx = &req->tx; + + WARN_ON(tx->cookie < 0); + + if (tx->cookie > 0) { + dma_cookie_complete(tx); + + /* + * Call the callback (must not sleep or submit new + * operations to this channel) + */ + if (tx->callback) + tx->callback(tx->callback_param); + + dma_descriptor_unmap(tx); + } + + /* Run dependent operations */ + dma_run_dependencies(tx); + + /* If waiting for 'ack' then move to completed list */ + if (!async_tx_test_ack(&req->tx)) + sba_complete_chained_requests(req); + else + sba_free_chained_requests(req); +} + +static void sba_receive_message(struct mbox_client *cl, void *msg) +{ + unsigned long flags; + struct brcm_message *m = msg; + struct sba_request *req = m->ctx, *req1; + struct sba_device *sba = req->sba; + + /* Error count if message has error */ + if (m->error < 0) + dev_err(sba->dev, "%s got message with error %d", + dma_chan_name(&sba->dma_chan), m->error); + + /* Mark request as received */ + sba_received_request(req); + + /* Wait for all chained requests to be completed */ + if (atomic_dec_return(&req->first->next_pending_count)) + goto done; + + /* Point to first request */ + req = req->first; + + /* Update request */ + if (req->state == SBA_REQUEST_STATE_RECEIVED) + sba_dma_tx_actions(req); + else + sba_free_chained_requests(req); + + spin_lock_irqsave(&sba->reqs_lock, flags); + + /* Re-check all completed request waiting for 'ack' */ + list_for_each_entry_safe(req, req1, &sba->reqs_completed_list, node) { + spin_unlock_irqrestore(&sba->reqs_lock, flags); + sba_dma_tx_actions(req); + spin_lock_irqsave(&sba->reqs_lock, flags); + } + + spin_unlock_irqrestore(&sba->reqs_lock, flags); + +done: + /* Try to submit pending request */ + sba_issue_pending(&sba->dma_chan); +} + +/* ====== Platform driver routines ===== */ + +static int sba_prealloc_channel_resources(struct sba_device *sba) +{ + int i, j, p, ret = 0; + struct sba_request *req = NULL; + + sba->resp_base = dma_alloc_coherent(sba->dma_dev.dev, + sba->max_resp_pool_size, + &sba->resp_dma_base, GFP_KERNEL); + if (!sba->resp_base) + return -ENOMEM; + + sba->cmds_base = dma_alloc_coherent(sba->dma_dev.dev, + sba->max_cmds_pool_size, + &sba->cmds_dma_base, GFP_KERNEL); + if (!sba->cmds_base) { + ret = -ENOMEM; + goto fail_free_resp_pool; + } + + spin_lock_init(&sba->reqs_lock); + sba->reqs_fence = false; + INIT_LIST_HEAD(&sba->reqs_alloc_list); + INIT_LIST_HEAD(&sba->reqs_pending_list); + INIT_LIST_HEAD(&sba->reqs_active_list); + INIT_LIST_HEAD(&sba->reqs_received_list); + INIT_LIST_HEAD(&sba->reqs_completed_list); + INIT_LIST_HEAD(&sba->reqs_aborted_list); + INIT_LIST_HEAD(&sba->reqs_free_list); + + sba->reqs = devm_kcalloc(sba->dev, sba->max_req, + sizeof(*req), GFP_KERNEL); + if (!sba->reqs) { + ret = -ENOMEM; + goto fail_free_cmds_pool; + } + + for (i = 0, p = 0; i < sba->max_req; i++) { + req = &sba->reqs[i]; + INIT_LIST_HEAD(&req->node); + req->sba = sba; + req->state = SBA_REQUEST_STATE_FREE; + INIT_LIST_HEAD(&req->next); + req->next_count = 1; + atomic_set(&req->next_pending_count, 0); + req->fence = false; + req->resp = sba->resp_base + p; + req->resp_dma = sba->resp_dma_base + p; + p += sba->hw_resp_size; + req->cmds = devm_kcalloc(sba->dev, sba->max_cmd_per_req, + sizeof(*req->cmds), GFP_KERNEL); + if (!req->cmds) { + ret = -ENOMEM; + goto fail_free_cmds_pool; + } + for (j = 0; j < sba->max_cmd_per_req; j++) { + req->cmds[j].cmd = 0; + req->cmds[j].cmd_dma = sba->cmds_base + + (i * sba->max_cmd_per_req + j) * sizeof(u64); + req->cmds[j].cmd_dma_addr = sba->cmds_dma_base + + (i * sba->max_cmd_per_req + j) * sizeof(u64); + req->cmds[j].flags = 0; + } + memset(&req->msg, 0, sizeof(req->msg)); + dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan); + req->tx.tx_submit = sba_tx_submit; + req->tx.phys = req->resp_dma; + list_add_tail(&req->node, &sba->reqs_free_list); + } + + sba->reqs_free_count = sba->max_req; + + return 0; + +fail_free_cmds_pool: + dma_free_coherent(sba->dma_dev.dev, + sba->max_cmds_pool_size, + sba->cmds_base, sba->cmds_dma_base); +fail_free_resp_pool: + dma_free_coherent(sba->dma_dev.dev, + sba->max_resp_pool_size, + sba->resp_base, sba->resp_dma_base); + return ret; +} + +static void sba_freeup_channel_resources(struct sba_device *sba) +{ + dmaengine_terminate_all(&sba->dma_chan); + dma_free_coherent(sba->dma_dev.dev, sba->max_cmds_pool_size, + sba->cmds_base, sba->cmds_dma_base); + dma_free_coherent(sba->dma_dev.dev, sba->max_resp_pool_size, + sba->resp_base, sba->resp_dma_base); + sba->resp_base = NULL; + sba->resp_dma_base = 0; +} + +static int sba_async_register(struct sba_device *sba) +{ + int ret; + struct dma_device *dma_dev = &sba->dma_dev; + + /* Initialize DMA channel cookie */ + sba->dma_chan.device = dma_dev; + dma_cookie_init(&sba->dma_chan); + + /* Initialize DMA device capability mask */ + dma_cap_zero(dma_dev->cap_mask); + dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask); + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + dma_cap_set(DMA_XOR, dma_dev->cap_mask); + dma_cap_set(DMA_PQ, dma_dev->cap_mask); + + /* + * Set mailbox channel device as the base device of + * our dma_device because the actual memory accesses + * will be done by mailbox controller + */ + dma_dev->dev = sba->mbox_dev; + + /* Set base prep routines */ + dma_dev->device_free_chan_resources = sba_free_chan_resources; + dma_dev->device_terminate_all = sba_device_terminate_all; + dma_dev->device_issue_pending = sba_issue_pending; + dma_dev->device_tx_status = sba_tx_status; + + /* Set interrupt routine */ + if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask)) + dma_dev->device_prep_dma_interrupt = sba_prep_dma_interrupt; + + /* Set memcpy routine */ + if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) + dma_dev->device_prep_dma_memcpy = sba_prep_dma_memcpy; + + /* Set xor routine and capability */ + if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_xor = sba_prep_dma_xor; + dma_dev->max_xor = sba->max_xor_srcs; + } + + /* Set pq routine and capability */ + if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_pq = sba_prep_dma_pq; + dma_set_maxpq(dma_dev, sba->max_pq_srcs, 0); + } + + /* Initialize DMA device channel list */ + INIT_LIST_HEAD(&dma_dev->channels); + list_add_tail(&sba->dma_chan.device_node, &dma_dev->channels); + + /* Register with Linux async DMA framework*/ + ret = dma_async_device_register(dma_dev); + if (ret) { + dev_err(sba->dev, "async device register error %d", ret); + return ret; + } + + dev_info(sba->dev, "%s capabilities: %s%s%s%s\n", + dma_chan_name(&sba->dma_chan), + dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "interrupt " : "", + dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "memcpy " : "", + dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "", + dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : ""); + + return 0; +} + +static int sba_probe(struct platform_device *pdev) +{ + int i, ret = 0, mchans_count; + struct sba_device *sba; + struct platform_device *mbox_pdev; + struct of_phandle_args args; + + /* Allocate main SBA struct */ + sba = devm_kzalloc(&pdev->dev, sizeof(*sba), GFP_KERNEL); + if (!sba) + return -ENOMEM; + + sba->dev = &pdev->dev; + platform_set_drvdata(pdev, sba); + + /* Determine SBA version from DT compatible string */ + if (of_device_is_compatible(sba->dev->of_node, "brcm,iproc-sba")) + sba->ver = SBA_VER_1; + else if (of_device_is_compatible(sba->dev->of_node, + "brcm,iproc-sba-v2")) + sba->ver = SBA_VER_2; + else + return -ENODEV; + + /* Derived Configuration parameters */ + switch (sba->ver) { + case SBA_VER_1: + sba->max_req = 1024; + sba->hw_buf_size = 4096; + sba->hw_resp_size = 8; + sba->max_pq_coefs = 6; + sba->max_pq_srcs = 6; + break; + case SBA_VER_2: + sba->max_req = 1024; + sba->hw_buf_size = 4096; + sba->hw_resp_size = 8; + sba->max_pq_coefs = 30; + /* + * We can support max_pq_srcs == max_pq_coefs because + * we are limited by number of SBA commands that we can + * fit in one message for underlying ring manager HW. + */ + sba->max_pq_srcs = 12; + break; + default: + return -EINVAL; + } + sba->max_cmd_per_req = sba->max_pq_srcs + 3; + sba->max_xor_srcs = sba->max_cmd_per_req - 1; + sba->max_resp_pool_size = sba->max_req * sba->hw_resp_size; + sba->max_cmds_pool_size = sba->max_req * + sba->max_cmd_per_req * sizeof(u64); + + /* Setup mailbox client */ + sba->client.dev = &pdev->dev; + sba->client.rx_callback = sba_receive_message; + sba->client.tx_block = false; + sba->client.knows_txdone = false; + sba->client.tx_tout = 0; + + /* Number of channels equals number of mailbox channels */ + ret = of_count_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells"); + if (ret <= 0) + return -ENODEV; + mchans_count = ret; + sba->mchans_count = 0; + atomic_set(&sba->mchans_current, 0); + + /* Allocate mailbox channel array */ + sba->mchans = devm_kcalloc(&pdev->dev, sba->mchans_count, + sizeof(*sba->mchans), GFP_KERNEL); + if (!sba->mchans) + return -ENOMEM; + + /* Request mailbox channels */ + for (i = 0; i < mchans_count; i++) { + sba->mchans[i] = mbox_request_channel(&sba->client, i); + if (IS_ERR(sba->mchans[i])) { + ret = PTR_ERR(sba->mchans[i]); + goto fail_free_mchans; + } + sba->mchans_count++; + } + + /* Find-out underlying mailbox device */ + ret = of_parse_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells", 0, &args); + if (ret) + goto fail_free_mchans; + mbox_pdev = of_find_device_by_node(args.np); + of_node_put(args.np); + if (!mbox_pdev) { + ret = -ENODEV; + goto fail_free_mchans; + } + sba->mbox_dev = &mbox_pdev->dev; + + /* All mailbox channels should be of same ring manager device */ + for (i = 1; i < mchans_count; i++) { + ret = of_parse_phandle_with_args(pdev->dev.of_node, + "mboxes", "#mbox-cells", i, &args); + if (ret) + goto fail_free_mchans; + mbox_pdev = of_find_device_by_node(args.np); + of_node_put(args.np); + if (sba->mbox_dev != &mbox_pdev->dev) { + ret = -EINVAL; + goto fail_free_mchans; + } + } + + /* Register DMA device with linux async framework */ + ret = sba_async_register(sba); + if (ret) + goto fail_free_mchans; + + /* Prealloc channel resource */ + ret = sba_prealloc_channel_resources(sba); + if (ret) + goto fail_async_dev_unreg; + + /* Print device info */ + dev_info(sba->dev, "%s using SBAv%d and %d mailbox channels", + dma_chan_name(&sba->dma_chan), sba->ver+1, + sba->mchans_count); + + return 0; + +fail_async_dev_unreg: + dma_async_device_unregister(&sba->dma_dev); +fail_free_mchans: + for (i = 0; i < sba->mchans_count; i++) + mbox_free_channel(sba->mchans[i]); + return ret; +} + +static int sba_remove(struct platform_device *pdev) +{ + int i; + struct sba_device *sba = platform_get_drvdata(pdev); + + sba_freeup_channel_resources(sba); + + dma_async_device_unregister(&sba->dma_dev); + + for (i = 0; i < sba->mchans_count; i++) + mbox_free_channel(sba->mchans[i]); + + return 0; +} + +static const struct of_device_id sba_of_match[] = { + { .compatible = "brcm,iproc-sba", }, + { .compatible = "brcm,iproc-sba-v2", }, + {}, +}; +MODULE_DEVICE_TABLE(of, sba_of_match); + +static struct platform_driver sba_driver = { + .probe = sba_probe, + .remove = sba_remove, + .driver = { + .name = "bcm-sba-raid", + .of_match_table = sba_of_match, + }, +}; +module_platform_driver(sba_driver); + +MODULE_DESCRIPTION("Broadcom SBA RAID driver"); +MODULE_AUTHOR("Anup Patel "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index 5a37b9fcf40ddf..04b9728c1d269e 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -6,17 +6,12 @@ config DW_DMAC_CORE tristate select DMA_ENGINE -config DW_DMAC_BIG_ENDIAN_IO - bool - config DW_DMAC tristate "Synopsys DesignWare AHB DMA platform driver" select DW_DMAC_CORE - select DW_DMAC_BIG_ENDIAN_IO if AVR32 - default y if CPU_AT32AP7000 help Support the Synopsys DesignWare AHB DMA controller. This - can be integrated in chips such as the Atmel AT32ap7000. + can be integrated in chips such as the Intel Cherrytrail. config DW_DMAC_PCI tristate "Synopsys DesignWare AHB DMA PCI driver" diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index e500950dad822a..f43e6dafe446d4 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -561,92 +561,14 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc) dwc_descriptor_complete(dwc, bad_desc, true); } -/* --------------------- Cyclic DMA API extensions -------------------- */ - -dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - return channel_readl(dwc, SAR); -} -EXPORT_SYMBOL(dw_dma_get_src_addr); - -dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - return channel_readl(dwc, DAR); -} -EXPORT_SYMBOL(dw_dma_get_dst_addr); - -/* Called with dwc->lock held and all DMAC interrupts disabled */ -static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, - u32 status_block, u32 status_err, u32 status_xfer) -{ - unsigned long flags; - - if (status_block & dwc->mask) { - void (*callback)(void *param); - void *callback_param; - - dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n", - channel_readl(dwc, LLP)); - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - - callback = dwc->cdesc->period_callback; - callback_param = dwc->cdesc->period_callback_param; - - if (callback) - callback(callback_param); - } - - /* - * Error and transfer complete are highly unlikely, and will most - * likely be due to a configuration error by the user. - */ - if (unlikely(status_err & dwc->mask) || - unlikely(status_xfer & dwc->mask)) { - unsigned int i; - - dev_err(chan2dev(&dwc->chan), - "cyclic DMA unexpected %s interrupt, stopping DMA transfer\n", - status_xfer ? "xfer" : "error"); - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_dump_chan_regs(dwc); - - dwc_chan_disable(dw, dwc); - - /* Make sure DMA does not restart by loading a new list */ - channel_writel(dwc, LLP, 0); - channel_writel(dwc, CTL_LO, 0); - channel_writel(dwc, CTL_HI, 0); - - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - for (i = 0; i < dwc->cdesc->periods; i++) - dwc_dump_lli(dwc, dwc->cdesc->desc[i]); - - spin_unlock_irqrestore(&dwc->lock, flags); - } - - /* Re-enable interrupts */ - channel_set_bit(dw, MASK.BLOCK, dwc->mask); -} - -/* ------------------------------------------------------------------------- */ - static void dw_dma_tasklet(unsigned long data) { struct dw_dma *dw = (struct dw_dma *)data; struct dw_dma_chan *dwc; - u32 status_block; u32 status_xfer; u32 status_err; unsigned int i; - status_block = dma_readl(dw, RAW.BLOCK); status_xfer = dma_readl(dw, RAW.XFER); status_err = dma_readl(dw, RAW.ERROR); @@ -655,8 +577,7 @@ static void dw_dma_tasklet(unsigned long data) for (i = 0; i < dw->dma.chancnt; i++) { dwc = &dw->chan[i]; if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) - dwc_handle_cyclic(dw, dwc, status_block, status_err, - status_xfer); + dev_vdbg(dw->dma.dev, "Cyclic xfer is not implemented\n"); else if (status_err & (1 << i)) dwc_handle_error(dw, dwc); else if (status_xfer & (1 << i)) @@ -1264,255 +1185,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan) dev_vdbg(chan2dev(chan), "%s: done\n", __func__); } -/* --------------------- Cyclic DMA API extensions -------------------- */ - -/** - * dw_dma_cyclic_start - start the cyclic DMA transfer - * @chan: the DMA channel to start - * - * Must be called with soft interrupts disabled. Returns zero on success or - * -errno on failure. - */ -int dw_dma_cyclic_start(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(chan->device); - unsigned long flags; - - if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { - dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n"); - return -ENODEV; - } - - spin_lock_irqsave(&dwc->lock, flags); - - /* Enable interrupts to perform cyclic transfer */ - channel_set_bit(dw, MASK.BLOCK, dwc->mask); - - dwc_dostart(dwc, dwc->cdesc->desc[0]); - - spin_unlock_irqrestore(&dwc->lock, flags); - - return 0; -} -EXPORT_SYMBOL(dw_dma_cyclic_start); - -/** - * dw_dma_cyclic_stop - stop the cyclic DMA transfer - * @chan: the DMA channel to stop - * - * Must be called with soft interrupts disabled. - */ -void dw_dma_cyclic_stop(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - unsigned long flags; - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_chan_disable(dw, dwc); - - spin_unlock_irqrestore(&dwc->lock, flags); -} -EXPORT_SYMBOL(dw_dma_cyclic_stop); - -/** - * dw_dma_cyclic_prep - prepare the cyclic DMA transfer - * @chan: the DMA channel to prepare - * @buf_addr: physical DMA address where the buffer starts - * @buf_len: total number of bytes for the entire buffer - * @period_len: number of bytes for each period - * @direction: transfer direction, to or from device - * - * Must be called before trying to start the transfer. Returns a valid struct - * dw_cyclic_desc if successful or an ERR_PTR(-errno) if not successful. - */ -struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, - dma_addr_t buf_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dma_slave_config *sconfig = &dwc->dma_sconfig; - struct dw_cyclic_desc *cdesc; - struct dw_cyclic_desc *retval = NULL; - struct dw_desc *desc; - struct dw_desc *last = NULL; - u8 lms = DWC_LLP_LMS(dwc->dws.m_master); - unsigned long was_cyclic; - unsigned int reg_width; - unsigned int periods; - unsigned int i; - unsigned long flags; - - spin_lock_irqsave(&dwc->lock, flags); - if (dwc->nollp) { - spin_unlock_irqrestore(&dwc->lock, flags); - dev_dbg(chan2dev(&dwc->chan), - "channel doesn't support LLP transfers\n"); - return ERR_PTR(-EINVAL); - } - - if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) { - spin_unlock_irqrestore(&dwc->lock, flags); - dev_dbg(chan2dev(&dwc->chan), - "queue and/or active list are not empty\n"); - return ERR_PTR(-EBUSY); - } - - was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags); - spin_unlock_irqrestore(&dwc->lock, flags); - if (was_cyclic) { - dev_dbg(chan2dev(&dwc->chan), - "channel already prepared for cyclic DMA\n"); - return ERR_PTR(-EBUSY); - } - - retval = ERR_PTR(-EINVAL); - - if (unlikely(!is_slave_direction(direction))) - goto out_err; - - dwc->direction = direction; - - if (direction == DMA_MEM_TO_DEV) - reg_width = __ffs(sconfig->dst_addr_width); - else - reg_width = __ffs(sconfig->src_addr_width); - - periods = buf_len / period_len; - - /* Check for too big/unaligned periods and unaligned DMA buffer. */ - if (period_len > (dwc->block_size << reg_width)) - goto out_err; - if (unlikely(period_len & ((1 << reg_width) - 1))) - goto out_err; - if (unlikely(buf_addr & ((1 << reg_width) - 1))) - goto out_err; - - retval = ERR_PTR(-ENOMEM); - - cdesc = kzalloc(sizeof(struct dw_cyclic_desc), GFP_KERNEL); - if (!cdesc) - goto out_err; - - cdesc->desc = kzalloc(sizeof(struct dw_desc *) * periods, GFP_KERNEL); - if (!cdesc->desc) - goto out_err_alloc; - - for (i = 0; i < periods; i++) { - desc = dwc_desc_get(dwc); - if (!desc) - goto out_err_desc_get; - - switch (direction) { - case DMA_MEM_TO_DEV: - lli_write(desc, dar, sconfig->dst_addr); - lli_write(desc, sar, buf_addr + period_len * i); - lli_write(desc, ctllo, (DWC_DEFAULT_CTLLO(chan) - | DWC_CTLL_DST_WIDTH(reg_width) - | DWC_CTLL_SRC_WIDTH(reg_width) - | DWC_CTLL_DST_FIX - | DWC_CTLL_SRC_INC - | DWC_CTLL_INT_EN)); - - lli_set(desc, ctllo, sconfig->device_fc ? - DWC_CTLL_FC(DW_DMA_FC_P_M2P) : - DWC_CTLL_FC(DW_DMA_FC_D_M2P)); - - break; - case DMA_DEV_TO_MEM: - lli_write(desc, dar, buf_addr + period_len * i); - lli_write(desc, sar, sconfig->src_addr); - lli_write(desc, ctllo, (DWC_DEFAULT_CTLLO(chan) - | DWC_CTLL_SRC_WIDTH(reg_width) - | DWC_CTLL_DST_WIDTH(reg_width) - | DWC_CTLL_DST_INC - | DWC_CTLL_SRC_FIX - | DWC_CTLL_INT_EN)); - - lli_set(desc, ctllo, sconfig->device_fc ? - DWC_CTLL_FC(DW_DMA_FC_P_P2M) : - DWC_CTLL_FC(DW_DMA_FC_D_P2M)); - - break; - default: - break; - } - - lli_write(desc, ctlhi, period_len >> reg_width); - cdesc->desc[i] = desc; - - if (last) - lli_write(last, llp, desc->txd.phys | lms); - - last = desc; - } - - /* Let's make a cyclic list */ - lli_write(last, llp, cdesc->desc[0]->txd.phys | lms); - - dev_dbg(chan2dev(&dwc->chan), - "cyclic prepared buf %pad len %zu period %zu periods %d\n", - &buf_addr, buf_len, period_len, periods); - - cdesc->periods = periods; - dwc->cdesc = cdesc; - - return cdesc; - -out_err_desc_get: - while (i--) - dwc_desc_put(dwc, cdesc->desc[i]); -out_err_alloc: - kfree(cdesc); -out_err: - clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); - return (struct dw_cyclic_desc *)retval; -} -EXPORT_SYMBOL(dw_dma_cyclic_prep); - -/** - * dw_dma_cyclic_free - free a prepared cyclic DMA transfer - * @chan: the DMA channel to free - */ -void dw_dma_cyclic_free(struct dma_chan *chan) -{ - struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); - struct dw_cyclic_desc *cdesc = dwc->cdesc; - unsigned int i; - unsigned long flags; - - dev_dbg(chan2dev(&dwc->chan), "%s\n", __func__); - - if (!cdesc) - return; - - spin_lock_irqsave(&dwc->lock, flags); - - dwc_chan_disable(dw, dwc); - - dma_writel(dw, CLEAR.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - spin_unlock_irqrestore(&dwc->lock, flags); - - for (i = 0; i < cdesc->periods; i++) - dwc_desc_put(dwc, cdesc->desc[i]); - - kfree(cdesc->desc); - kfree(cdesc); - - dwc->cdesc = NULL; - - clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); -} -EXPORT_SYMBOL(dw_dma_cyclic_free); - -/*----------------------------------------------------------------------*/ - int dw_dma_probe(struct dw_dma_chip *chip) { struct dw_dma_platform_data *pdata; @@ -1642,7 +1314,7 @@ int dw_dma_probe(struct dw_dma_chip *chip) if (autocfg) { unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1; void __iomem *addr = &__dw_regs(dw)->DWC_PARAMS[r]; - unsigned int dwc_params = dma_readl_native(addr); + unsigned int dwc_params = readl(addr); dev_dbg(chip->dev, "DWC_PARAMS[%d]: 0x%08x\n", i, dwc_params); diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index c639c60b825abf..bc31fe8020619d 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -306,8 +306,12 @@ static int dw_resume_early(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct dw_dma_chip *chip = platform_get_drvdata(pdev); + int ret; + + ret = clk_prepare_enable(chip->clk); + if (ret) + return ret; - clk_prepare_enable(chip->clk); return dw_dma_enable(chip); } diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h index 32a328721c8872..09e7dfdbb7907d 100644 --- a/drivers/dma/dw/regs.h +++ b/drivers/dma/dw/regs.h @@ -116,20 +116,6 @@ struct dw_dma_regs { DW_REG(GLOBAL_CFG); }; -/* - * Big endian I/O access when reading and writing to the DMA controller - * registers. This is needed on some platforms, like the Atmel AVR32 - * architecture. - */ - -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -#define dma_readl_native ioread32be -#define dma_writel_native iowrite32be -#else -#define dma_readl_native readl -#define dma_writel_native writel -#endif - /* Bitfields in DW_PARAMS */ #define DW_PARAMS_NR_CHAN 8 /* number of channels */ #define DW_PARAMS_NR_MASTER 11 /* number of AHB masters */ @@ -280,7 +266,6 @@ struct dw_dma_chan { unsigned long flags; struct list_head active_list; struct list_head queue; - struct dw_cyclic_desc *cdesc; unsigned int descs_allocated; @@ -302,9 +287,9 @@ __dwc_regs(struct dw_dma_chan *dwc) } #define channel_readl(dwc, name) \ - dma_readl_native(&(__dwc_regs(dwc)->name)) + readl(&(__dwc_regs(dwc)->name)) #define channel_writel(dwc, name, val) \ - dma_writel_native((val), &(__dwc_regs(dwc)->name)) + writel((val), &(__dwc_regs(dwc)->name)) static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan) { @@ -333,9 +318,9 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw) } #define dma_readl(dw, name) \ - dma_readl_native(&(__dw_regs(dw)->name)) + readl(&(__dw_regs(dw)->name)) #define dma_writel(dw, name, val) \ - dma_writel_native((val), &(__dw_regs(dw)->name)) + writel((val), &(__dw_regs(dw)->name)) #define idma32_readq(dw, name) \ hi_lo_readq(&(__dw_regs(dw)->name)) @@ -352,43 +337,30 @@ static inline struct dw_dma *to_dw_dma(struct dma_device *ddev) return container_of(ddev, struct dw_dma, dma); } -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -typedef __be32 __dw32; -#else -typedef __le32 __dw32; -#endif - /* LLI == Linked List Item; a.k.a. DMA block descriptor */ struct dw_lli { /* values that are not changed by hardware */ - __dw32 sar; - __dw32 dar; - __dw32 llp; /* chain to next lli */ - __dw32 ctllo; + __le32 sar; + __le32 dar; + __le32 llp; /* chain to next lli */ + __le32 ctllo; /* values that may get written back: */ - __dw32 ctlhi; + __le32 ctlhi; /* sstat and dstat can snapshot peripheral register state. * silicon config may discard either or both... */ - __dw32 sstat; - __dw32 dstat; + __le32 sstat; + __le32 dstat; }; struct dw_desc { /* FIRST values the hardware uses */ struct dw_lli lli; -#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO -#define lli_set(d, reg, v) ((d)->lli.reg |= cpu_to_be32(v)) -#define lli_clear(d, reg, v) ((d)->lli.reg &= ~cpu_to_be32(v)) -#define lli_read(d, reg) be32_to_cpu((d)->lli.reg) -#define lli_write(d, reg, v) ((d)->lli.reg = cpu_to_be32(v)) -#else #define lli_set(d, reg, v) ((d)->lli.reg |= cpu_to_le32(v)) #define lli_clear(d, reg, v) ((d)->lli.reg &= ~cpu_to_le32(v)) #define lli_read(d, reg) le32_to_cpu((d)->lli.reg) #define lli_write(d, reg, v) ((d)->lli.reg = cpu_to_le32(v)) -#endif /* THEN values for driver housekeeping */ struct list_head desc_node; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 085993cb2ccc58..a67ec1bdc4e0c9 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1323,7 +1323,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( } if (period_len > 0xffff) { - dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %d > %d\n", + dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %zu > %d\n", channel, period_len, 0xffff); goto err_out; } @@ -1347,7 +1347,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( if (i + 1 == num_periods) param |= BD_WRAP; - dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n", + dev_dbg(sdma->dev, "entry %d: count: %zu dma: %#llx %s%s\n", i, period_len, (u64)dma_addr, param & BD_WRAP ? "wrap" : "", param & BD_INTR ? " intr" : ""); @@ -1755,19 +1755,26 @@ static int sdma_probe(struct platform_device *pdev) if (IS_ERR(sdma->clk_ahb)) return PTR_ERR(sdma->clk_ahb); - clk_prepare(sdma->clk_ipg); - clk_prepare(sdma->clk_ahb); + ret = clk_prepare(sdma->clk_ipg); + if (ret) + return ret; + + ret = clk_prepare(sdma->clk_ahb); + if (ret) + goto err_clk; ret = devm_request_irq(&pdev->dev, irq, sdma_int_handler, 0, "sdma", sdma); if (ret) - return ret; + goto err_irq; sdma->irq = irq; sdma->script_addrs = kzalloc(sizeof(*sdma->script_addrs), GFP_KERNEL); - if (!sdma->script_addrs) - return -ENOMEM; + if (!sdma->script_addrs) { + ret = -ENOMEM; + goto err_irq; + } /* initially no scripts available */ saddr_arr = (s32 *)sdma->script_addrs; @@ -1882,6 +1889,10 @@ static int sdma_probe(struct platform_device *pdev) dma_async_device_unregister(&sdma->dma_device); err_init: kfree(sdma->script_addrs); +err_irq: + clk_unprepare(sdma->clk_ahb); +err_clk: + clk_unprepare(sdma->clk_ipg); return ret; } @@ -1893,6 +1904,8 @@ static int sdma_remove(struct platform_device *pdev) devm_free_irq(&pdev->dev, sdma->irq, sdma); dma_async_device_unregister(&sdma->dma_device); kfree(sdma->script_addrs); + clk_unprepare(sdma->clk_ahb); + clk_unprepare(sdma->clk_ipg); /* Kill the tasklet */ for (i = 0; i < MAX_DMA_CHANNELS; i++) { struct sdma_channel *sdmac = &sdma->channel[i]; diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index f3e211f8f6c58c..d7eb807eef776d 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -42,6 +42,7 @@ #define MV_XOR_V2_DMA_IMSG_THRD_OFF 0x018 #define MV_XOR_V2_DMA_IMSG_THRD_MASK 0x7FFF #define MV_XOR_V2_DMA_IMSG_THRD_SHIFT 0x0 +#define MV_XOR_V2_DMA_IMSG_TIMER_EN BIT(18) #define MV_XOR_V2_DMA_DESQ_AWATTR_OFF 0x01C /* Same flags as MV_XOR_V2_DMA_DESQ_ARATTR_OFF */ #define MV_XOR_V2_DMA_DESQ_ALLOC_OFF 0x04C @@ -55,6 +56,9 @@ #define MV_XOR_V2_DMA_DESQ_STOP_OFF 0x800 #define MV_XOR_V2_DMA_DESQ_DEALLOC_OFF 0x804 #define MV_XOR_V2_DMA_DESQ_ADD_OFF 0x808 +#define MV_XOR_V2_DMA_IMSG_TMOT 0x810 +#define MV_XOR_V2_DMA_IMSG_TIMER_THRD_MASK 0x1FFF +#define MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT 0 /* XOR Global registers */ #define MV_XOR_V2_GLOB_BW_CTRL 0x4 @@ -90,6 +94,13 @@ */ #define MV_XOR_V2_DESC_NUM 1024 +/* + * Threshold values for descriptors and timeout, determined by + * experimentation as giving a good level of performance. + */ +#define MV_XOR_V2_DONE_IMSG_THRD 0x14 +#define MV_XOR_V2_TIMER_THRD 0xB0 + /** * struct mv_xor_v2_descriptor - DMA HW descriptor * @desc_id: used by S/W and is not affected by H/W. @@ -246,6 +257,32 @@ static int mv_xor_v2_set_desc_size(struct mv_xor_v2_device *xor_dev) return MV_XOR_V2_EXT_DESC_SIZE; } +<<<<<<< HEAD +======= +/* + * Set the IMSG threshold + */ +static inline +void mv_xor_v2_enable_imsg_thrd(struct mv_xor_v2_device *xor_dev) +{ + u32 reg; + + /* Configure threshold of number of descriptors, and enable timer */ + reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF); + reg &= (~MV_XOR_V2_DMA_IMSG_THRD_MASK << MV_XOR_V2_DMA_IMSG_THRD_SHIFT); + reg |= (MV_XOR_V2_DONE_IMSG_THRD << MV_XOR_V2_DMA_IMSG_THRD_SHIFT); + reg |= MV_XOR_V2_DMA_IMSG_TIMER_EN; + writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF); + + /* Configure Timer Threshold */ + reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_TMOT); + reg &= (~MV_XOR_V2_DMA_IMSG_TIMER_THRD_MASK << + MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT); + reg |= (MV_XOR_V2_TIMER_THRD << MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT); + writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_TMOT); +} + +>>>>>>> linux-next/akpm-base static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data) { struct mv_xor_v2_device *xor_dev = data; @@ -501,9 +538,6 @@ static void mv_xor_v2_issue_pending(struct dma_chan *chan) mv_xor_v2_add_desc_to_desq(xor_dev, xor_dev->npendings); xor_dev->npendings = 0; - /* Activate the channel */ - writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF); - spin_unlock_bh(&xor_dev->lock); } @@ -662,6 +696,30 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev) /* enable the DMA engine */ writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF); +<<<<<<< HEAD +======= + return 0; +} + +static int mv_xor_v2_suspend(struct platform_device *dev, pm_message_t state) +{ + struct mv_xor_v2_device *xor_dev = platform_get_drvdata(dev); + + /* Set this bit to disable to stop the XOR unit. */ + writel(0x1, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF); + + return 0; +} + +static int mv_xor_v2_resume(struct platform_device *dev) +{ + struct mv_xor_v2_device *xor_dev = platform_get_drvdata(dev); + + mv_xor_v2_set_desc_size(xor_dev); + mv_xor_v2_enable_imsg_thrd(xor_dev); + mv_xor_v2_descq_init(xor_dev); + +>>>>>>> linux-next/akpm-base return 0; } @@ -795,6 +853,8 @@ static int mv_xor_v2_probe(struct platform_device *pdev) list_add_tail(&xor_dev->dmachan.device_node, &dma_dev->channels); + mv_xor_v2_enable_imsg_thrd(xor_dev); + mv_xor_v2_descq_init(xor_dev); ret = dma_async_device_register(dma_dev); @@ -844,6 +904,8 @@ MODULE_DEVICE_TABLE(of, mv_xor_v2_dt_ids); static struct platform_driver mv_xor_v2_driver = { .probe = mv_xor_v2_probe, + .suspend = mv_xor_v2_suspend, + .resume = mv_xor_v2_resume, .remove = mv_xor_v2_remove, .driver = { .name = "mv_xor_v2", diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index e90a7a0d760af6..c12aae06f67dbe 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -443,7 +443,10 @@ struct dma_pl330_chan { /* For D-to-M and M-to-D channels */ int burst_sz; /* the peripheral fifo width */ int burst_len; /* the number of burst */ - dma_addr_t fifo_addr; + phys_addr_t fifo_addr; + /* DMA-mapped view of the FIFO; may differ if an IOMMU is present */ + dma_addr_t fifo_dma; + enum dma_data_direction dir; /* for cyclic capability */ bool cyclic; @@ -2120,11 +2123,60 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan) return 1; } +/* + * We need the data direction between the DMAC (the dma-mapping "device") and + * the FIFO (the dmaengine "dev"), from the FIFO's point of view. Confusing! + */ +static enum dma_data_direction +pl330_dma_slave_map_dir(enum dma_transfer_direction dir) +{ + switch (dir) { + case DMA_MEM_TO_DEV: + return DMA_FROM_DEVICE; + case DMA_DEV_TO_MEM: + return DMA_TO_DEVICE; + case DMA_DEV_TO_DEV: + return DMA_BIDIRECTIONAL; + default: + return DMA_NONE; + } +} + +static void pl330_unprep_slave_fifo(struct dma_pl330_chan *pch) +{ + if (pch->dir != DMA_NONE) + dma_unmap_resource(pch->chan.device->dev, pch->fifo_dma, + 1 << pch->burst_sz, pch->dir, 0); + pch->dir = DMA_NONE; +} + + +static bool pl330_prep_slave_fifo(struct dma_pl330_chan *pch, + enum dma_transfer_direction dir) +{ + struct device *dev = pch->chan.device->dev; + enum dma_data_direction dma_dir = pl330_dma_slave_map_dir(dir); + + /* Already mapped for this config? */ + if (pch->dir == dma_dir) + return true; + + pl330_unprep_slave_fifo(pch); + pch->fifo_dma = dma_map_resource(dev, pch->fifo_addr, + 1 << pch->burst_sz, dma_dir, 0); + if (dma_mapping_error(dev, pch->fifo_dma)) + return false; + + pch->dir = dma_dir; + return true; +} + static int pl330_config(struct dma_chan *chan, struct dma_slave_config *slave_config) { struct dma_pl330_chan *pch = to_pchan(chan); + pl330_unprep_slave_fifo(pch); if (slave_config->direction == DMA_MEM_TO_DEV) { if (slave_config->dst_addr) pch->fifo_addr = slave_config->dst_addr; @@ -2235,6 +2287,7 @@ static void pl330_free_chan_resources(struct dma_chan *chan) spin_unlock_irqrestore(&pl330->lock, flags); pm_runtime_mark_last_busy(pch->dmac->ddma.dev); pm_runtime_put_autosuspend(pch->dmac->ddma.dev); + pl330_unprep_slave_fifo(pch); } static int pl330_get_current_xferred_count(struct dma_pl330_chan *pch, @@ -2564,6 +2617,9 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( return NULL; } + if (!pl330_prep_slave_fifo(pch, direction)) + return NULL; + for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { @@ -2593,12 +2649,12 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( desc->rqcfg.src_inc = 1; desc->rqcfg.dst_inc = 0; src = dma_addr; - dst = pch->fifo_addr; + dst = pch->fifo_dma; break; case DMA_DEV_TO_MEM: desc->rqcfg.src_inc = 0; desc->rqcfg.dst_inc = 1; - src = pch->fifo_addr; + src = pch->fifo_dma; dst = dma_addr; break; default: @@ -2711,12 +2767,12 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, struct dma_pl330_chan *pch = to_pchan(chan); struct scatterlist *sg; int i; - dma_addr_t addr; if (unlikely(!pch || !sgl || !sg_len)) return NULL; - addr = pch->fifo_addr; + if (!pl330_prep_slave_fifo(pch, direction)) + return NULL; first = NULL; @@ -2742,13 +2798,13 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (direction == DMA_MEM_TO_DEV) { desc->rqcfg.src_inc = 1; desc->rqcfg.dst_inc = 0; - fill_px(&desc->px, - addr, sg_dma_address(sg), sg_dma_len(sg)); + fill_px(&desc->px, pch->fifo_dma, sg_dma_address(sg), + sg_dma_len(sg)); } else { desc->rqcfg.src_inc = 0; desc->rqcfg.dst_inc = 1; - fill_px(&desc->px, - sg_dma_address(sg), addr, sg_dma_len(sg)); + fill_px(&desc->px, sg_dma_address(sg), pch->fifo_dma, + sg_dma_len(sg)); } desc->rqcfg.brst_size = pch->burst_sz; @@ -2906,6 +2962,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pch->thread = NULL; pch->chan.device = pd; pch->dmac = pl330; + pch->dir = DMA_NONE; /* Add the channel to the DMAC list */ list_add_tail(&pch->chan.device_node, &pd->channels); diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index bd261c9e9664b6..ffcadca53243d9 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -144,6 +144,7 @@ struct rcar_dmac_chan_map { * @chan: base DMA channel object * @iomem: channel I/O memory base * @index: index of this channel in the controller + * @irq: channel IRQ * @src: slave memory address and size on the source side * @dst: slave memory address and size on the destination side * @mid_rid: hardware MID/RID for the DMA client using this channel @@ -161,6 +162,7 @@ struct rcar_dmac_chan { struct dma_chan chan; void __iomem *iomem; unsigned int index; + int irq; struct rcar_dmac_chan_slave src; struct rcar_dmac_chan_slave dst; @@ -1008,7 +1010,11 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan) rcar_dmac_chan_halt(rchan); spin_unlock_irq(&rchan->lock); - /* Now no new interrupts will occur */ + /* + * Now no new interrupts will occur, but one might already be + * running. Wait for it to finish before freeing resources. + */ + synchronize_irq(rchan->irq); if (rchan->mid_rid >= 0) { /* The caller is holding dma_list_mutex */ @@ -1366,6 +1372,13 @@ static void rcar_dmac_issue_pending(struct dma_chan *chan) spin_unlock_irqrestore(&rchan->lock, flags); } +static void rcar_dmac_device_synchronize(struct dma_chan *chan) +{ + struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan); + + synchronize_irq(rchan->irq); +} + /* ----------------------------------------------------------------------------- * IRQ handling */ @@ -1650,7 +1663,6 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac, struct dma_chan *chan = &rchan->chan; char pdev_irqname[5]; char *irqname; - int irq; int ret; rchan->index = index; @@ -1667,8 +1679,8 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac, /* Request the channel interrupt. */ sprintf(pdev_irqname, "ch%u", index); - irq = platform_get_irq_byname(pdev, pdev_irqname); - if (irq < 0) { + rchan->irq = platform_get_irq_byname(pdev, pdev_irqname); + if (rchan->irq < 0) { dev_err(dmac->dev, "no IRQ specified for channel %u\n", index); return -ENODEV; } @@ -1678,11 +1690,13 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac, if (!irqname) return -ENOMEM; - ret = devm_request_threaded_irq(dmac->dev, irq, rcar_dmac_isr_channel, + ret = devm_request_threaded_irq(dmac->dev, rchan->irq, + rcar_dmac_isr_channel, rcar_dmac_isr_channel_thread, 0, irqname, rchan); if (ret) { - dev_err(dmac->dev, "failed to request IRQ %u (%d)\n", irq, ret); + dev_err(dmac->dev, "failed to request IRQ %u (%d)\n", + rchan->irq, ret); return ret; } @@ -1846,6 +1860,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) engine->device_terminate_all = rcar_dmac_chan_terminate_all; engine->device_tx_status = rcar_dmac_tx_status; engine->device_issue_pending = rcar_dmac_issue_pending; + engine->device_synchronize = rcar_dmac_device_synchronize; ret = dma_async_device_register(engine); if (ret < 0) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 7717b094fabb66..122637530b15ee 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1839,7 +1839,7 @@ static int a10_eccmgr_irqdomain_map(struct irq_domain *d, unsigned int irq, return 0; } -static struct irq_domain_ops a10_eccmgr_ic_ops = { +static const struct irq_domain_ops a10_eccmgr_ic_ops = { .map = a10_eccmgr_irqdomain_map, .xlate = irq_domain_xlate_twocell, }; diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 2733fb5938a422..4260579e6901de 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -18,10 +18,12 @@ * 0c04: Xeon E3-1200 v3/4th Gen Core Processor DRAM Controller * 0c08: Xeon E3-1200 v3 Processor DRAM Controller * 1918: Xeon E3-1200 v5 Skylake Host Bridge/DRAM Registers + * 5918: Xeon E3-1200 Xeon E3-1200 v6/7th Gen Core Processor Host Bridge/DRAM Registers * * Based on Intel specification: * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v3-vol-2-datasheet.pdf * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e3-1200-family-vol-2-datasheet.html + * http://www.intel.com/content/www/us/en/processors/core/7th-gen-core-family-mobile-h-processor-lines-datasheet-vol-2.html * * According to the above datasheet (p.16): * " @@ -57,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04 #define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08 #define PCI_DEVICE_ID_INTEL_IE31200_HB_8 0x1918 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_9 0x5918 #define IE31200_DIMMS 4 #define IE31200_RANKS 8 @@ -376,7 +379,12 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) void __iomem *window; struct ie31200_priv *priv; u32 addr_decode, mad_offset; - bool skl = (pdev->device == PCI_DEVICE_ID_INTEL_IE31200_HB_8); + + /* + * Kaby Lake seems to work like Skylake. Please re-visit this logic + * when adding new CPU support. + */ + bool skl = (pdev->device >= PCI_DEVICE_ID_INTEL_IE31200_HB_8); edac_dbg(0, "MC:\n"); @@ -559,6 +567,9 @@ static const struct pci_device_id ie31200_pci_tbl[] = { { PCI_VEND_DEV(INTEL, IE31200_HB_8), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200}, + { + PCI_VEND_DEV(INTEL, IE31200_HB_9), PCI_ANY_ID, PCI_ANY_ID, 0, 0, + IE31200}, { 0, } /* 0 terminated list. */ diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c index 14b7e7b71eaa2f..77bfc3d882a884 100644 --- a/drivers/edac/mv64x60_edac.c +++ b/drivers/edac/mv64x60_edac.c @@ -32,21 +32,21 @@ static void mv64x60_pci_check(struct edac_pci_ctl_info *pci) struct mv64x60_pci_pdata *pdata = pci->pvt_info; u32 cause; - cause = in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + cause = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (!cause) return; printk(KERN_ERR "Error in PCI %d Interface\n", pdata->pci_hose); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_LO)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_HI)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_HI)); printk(KERN_ERR "Attribute: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ATTR)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ATTR)); printk(KERN_ERR "Command: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CMD)); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE, ~cause); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CMD)); + writel(~cause, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (cause & MV64X60_PCI_PE_MASK) edac_pci_handle_pe(pci, pci->ctl_name); @@ -61,7 +61,7 @@ static irqreturn_t mv64x60_pci_isr(int irq, void *dev_id) struct mv64x60_pci_pdata *pdata = pci->pvt_info; u32 val; - val = in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + val = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (!val) return IRQ_NONE; @@ -93,7 +93,7 @@ static int __init mv64x60_pci_fixup(struct platform_device *pdev) if (!pci_serr) return -ENOMEM; - out_le32(pci_serr, in_le32(pci_serr) & ~0x1); + writel(readl(pci_serr) & ~0x1, pci_serr); iounmap(pci_serr); return 0; @@ -116,7 +116,7 @@ static int mv64x60_pci_err_probe(struct platform_device *pdev) pdata = pci->pvt_info; pdata->pci_hose = pdev->id; - pdata->name = "mpc85xx_pci_err"; + pdata->name = "mv64x60_pci_err"; platform_set_drvdata(pdev, pci); pci->dev = &pdev->dev; pci->dev_name = dev_name(&pdev->dev); @@ -161,10 +161,10 @@ static int mv64x60_pci_err_probe(struct platform_device *pdev) goto err; } - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE, 0); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_MASK, 0); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_MASK, - MV64X60_PCIx_ERR_MASK_VAL); + writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_MASK); + writel(MV64X60_PCIx_ERR_MASK_VAL, + pdata->pci_vbase + MV64X60_PCI_ERROR_MASK); if (edac_pci_add_device(pci, pdata->edac_idx) > 0) { edac_dbg(3, "failed edac_pci_add_device()\n"); @@ -233,23 +233,23 @@ static void mv64x60_sram_check(struct edac_device_ctl_info *edac_dev) struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); + cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); if (!cause) return; printk(KERN_ERR "Error in internal SRAM\n"); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_LO)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_HI)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_HI)); printk(KERN_ERR "Data Low: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_LO)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_LO)); printk(KERN_ERR "Data High: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_HI)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_HI)); printk(KERN_ERR "Parity: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); - out_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE, 0); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); + writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); } @@ -260,7 +260,7 @@ static irqreturn_t mv64x60_sram_isr(int irq, void *dev_id) struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); + cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); if (!cause) return IRQ_NONE; @@ -322,7 +322,7 @@ static int mv64x60_sram_err_probe(struct platform_device *pdev) } /* setup SRAM err registers */ - out_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE, 0); + writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); edac_dev->mod_name = EDAC_MOD_STR; edac_dev->ctl_name = pdata->name; @@ -398,7 +398,7 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & + cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & MV64x60_CPU_CAUSE_MASK; if (!cause) return; @@ -406,16 +406,16 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) printk(KERN_ERR "Error on CPU interface\n"); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_LO)); + readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_HI)); + readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_HI)); printk(KERN_ERR "Data Low: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_LO)); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_LO)); printk(KERN_ERR "Data High: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_HI)); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_HI)); printk(KERN_ERR "Parity: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE, 0); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); } @@ -426,7 +426,7 @@ static irqreturn_t mv64x60_cpu_isr(int irq, void *dev_id) struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & + cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & MV64x60_CPU_CAUSE_MASK; if (!cause) return IRQ_NONE; @@ -515,9 +515,9 @@ static int mv64x60_cpu_err_probe(struct platform_device *pdev) } /* setup CPU err registers */ - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE, 0); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK, 0); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK, 0x000000ff); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK); + writel(0x000000ff, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK); edac_dev->mod_name = EDAC_MOD_STR; edac_dev->ctl_name = pdata->name; @@ -596,13 +596,13 @@ static void mv64x60_mc_check(struct mem_ctl_info *mci) u32 comp_ecc; u32 syndrome; - reg = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); if (!reg) return; err_addr = reg & ~0x3; - sdram_ecc = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_RCVD); - comp_ecc = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CALC); + sdram_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_RCVD); + comp_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CALC); syndrome = sdram_ecc ^ comp_ecc; /* first bit clear in ECC Err Reg, 1 bit error, correctable by HW */ @@ -620,7 +620,7 @@ static void mv64x60_mc_check(struct mem_ctl_info *mci) mci->ctl_name, ""); /* clear the error */ - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR, 0); + writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); } static irqreturn_t mv64x60_mc_isr(int irq, void *dev_id) @@ -629,7 +629,7 @@ static irqreturn_t mv64x60_mc_isr(int irq, void *dev_id) struct mv64x60_mc_pdata *pdata = mci->pvt_info; u32 reg; - reg = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); if (!reg) return IRQ_NONE; @@ -664,7 +664,7 @@ static void mv64x60_init_csrows(struct mem_ctl_info *mci, get_total_mem(pdata); - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); csrow = mci->csrows[0]; dimm = csrow->channels[0]->dimm; @@ -753,7 +753,7 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev) goto err; } - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); if (!(ctl & MV64X60_SDRAM_ECC)) { /* Non-ECC RAM? */ printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__); @@ -779,10 +779,10 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev) mv64x60_init_csrows(mci, pdata); /* setup MC registers */ - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR, 0); - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); + writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); ctl = (ctl & 0xff00ffff) | 0x10000; - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL, ctl); + writel(ctl, pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); res = edac_mc_add_mc(mci); if (res) { @@ -853,10 +853,15 @@ static struct platform_driver * const drivers[] = { static int __init mv64x60_edac_init(void) { - int ret = 0; + int ret; + + ret = platform_register_drivers(drivers, ARRAY_SIZE(drivers)); + if (ret) + return ret; printk(KERN_INFO "Marvell MV64x60 EDAC driver " MV64x60_REVISION "\n"); printk(KERN_INFO "\t(C) 2006-2007 MontaVista Software\n"); + /* make sure error reporting method is sane */ switch (edac_op_state) { case EDAC_OPSTATE_POLL: @@ -867,7 +872,7 @@ static int __init mv64x60_edac_init(void) break; } - return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); + return 0; } module_init(mv64x60_edac_init); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index ea21cb651b3c0b..89fd6bd64df68d 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -35,7 +35,7 @@ static LIST_HEAD(sbridge_edac_list); /* * Alter this version for the module when modifications are made */ -#define SBRIDGE_REVISION " Ver: 1.1.1 " +#define SBRIDGE_REVISION " Ver: 1.1.2 " #define EDAC_MOD_STR "sbridge_edac" /* @@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 8 /* 2MC per socket, four chan per MC */ +#define NUM_CHANNELS 4 /* Max channels per MC */ #define MAX_DIMMS 3 /* Max DIMMS per channel */ #define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */ #define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */ @@ -294,6 +294,12 @@ enum type { KNIGHTS_LANDING, }; +enum domain { + IMC0 = 0, + IMC1, + SOCK, +}; + struct sbridge_pvt; struct sbridge_info { enum type type; @@ -324,11 +330,14 @@ struct sbridge_channel { struct pci_id_descr { int dev_id; int optional; + enum domain dom; }; struct pci_id_table { const struct pci_id_descr *descr; - int n_devs; + int n_devs_per_imc; + int n_devs_per_sock; + int n_imcs_per_sock; enum type type; }; @@ -337,7 +346,9 @@ struct sbridge_dev { u8 bus, mc; u8 node_id, source_id; struct pci_dev **pdev; + enum domain dom; int n_devs; + int i_devs; struct mem_ctl_info *mci; }; @@ -352,11 +363,12 @@ struct knl_pvt { }; struct sbridge_pvt { - struct pci_dev *pci_ta, *pci_ddrio, *pci_ras; + /* Devices per socket */ + struct pci_dev *pci_ddrio; struct pci_dev *pci_sad0, *pci_sad1; - struct pci_dev *pci_ha0, *pci_ha1; struct pci_dev *pci_br0, *pci_br1; - struct pci_dev *pci_ha1_ta; + /* Devices per memory controller */ + struct pci_dev *pci_ha, *pci_ta, *pci_ras; struct pci_dev *pci_tad[NUM_CHANNELS]; struct sbridge_dev *sbridge_dev; @@ -373,39 +385,42 @@ struct sbridge_pvt { struct knl_pvt knl; }; -#define PCI_DESCR(device_id, opt) \ +#define PCI_DESCR(device_id, opt, domain) \ .dev_id = (device_id), \ - .optional = opt + .optional = opt, \ + .dom = domain static const struct pci_id_descr pci_dev_descr_sbridge[] = { /* Processor Home Agent */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0, 0, IMC0) }, /* Memory controller */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO, 1, SOCK) }, /* System Address Decoder */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1, 0, SOCK) }, /* Broadcast Registers */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0, SOCK) }, }; -#define PCI_ID_TABLE_ENTRY(A, T) { \ +#define PCI_ID_TABLE_ENTRY(A, N, M, T) { \ .descr = A, \ - .n_devs = ARRAY_SIZE(A), \ + .n_devs_per_imc = N, \ + .n_devs_per_sock = ARRAY_SIZE(A), \ + .n_imcs_per_sock = M, \ .type = T \ } static const struct pci_id_table pci_dev_descr_sbridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE), + PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, ARRAY_SIZE(pci_dev_descr_sbridge), 1, SANDY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -439,40 +454,39 @@ static const struct pci_id_table pci_dev_descr_sbridge_table[] = { static const struct pci_id_descr pci_dev_descr_ibridge[] = { /* Processor Home Agent */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0, 0, IMC0) }, /* Memory controller */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3, 0, IMC0) }, + + /* Optional, mode 2HA */ + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_1HA_DDRIO0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_2HA_DDRIO0, 1, SOCK) }, /* System Address Decoder */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_SAD, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_SAD, 0, SOCK) }, /* Broadcast Registers */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR1, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR1, 0, SOCK) }, - /* Optional, mode 2HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1, 1) }, -#if 0 - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS, 1) }, -#endif - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_1HA_DDRIO0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_2HA_DDRIO0, 1) }, }; static const struct pci_id_table pci_dev_descr_ibridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE), + PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, 12, 2, IVY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -498,9 +512,9 @@ static const struct pci_id_table pci_dev_descr_ibridge_table[] = { #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0 0x2fa0 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1 0x2f60 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA 0x2fa8 -#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL 0x2f71 +#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM 0x2f71 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA 0x2f68 -#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_THERMAL 0x2f79 +#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM 0x2f79 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0 0x2ffc #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1 0x2ffd #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0 0x2faa @@ -517,35 +531,33 @@ static const struct pci_id_table pci_dev_descr_ibridge_table[] = { #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3 0x2fbb static const struct pci_id_descr pci_dev_descr_haswell[] = { /* first item must be the HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_THERMAL, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2, 1, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3, 1, IMC0) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO1, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO2, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3, 1, SOCK) }, }; static const struct pci_id_table pci_dev_descr_haswell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL), + PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, 13, 2, HASWELL), {0,} /* 0 terminated list. */ }; @@ -559,7 +571,7 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { /* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840 /* DRAM channel stuff; bank addrs, dimmmtr, etc.. 2-8-2 - 2-9-4 (6 of these) */ -#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL 0x7843 +#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN 0x7843 /* kdrwdbu TAD limits/offsets, MCMTR - 2-10-1, 2-11-1 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_TA 0x7844 /* CHA broadcast registers, dram rules - 1-29-0 (1 of these) */ @@ -579,17 +591,17 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { */ static const struct pci_id_descr pci_dev_descr_knl[] = { - [0] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0, 0) }, - [1] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1, 0) }, - [2 ... 3] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_MC, 0)}, - [4 ... 41] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHA, 0) }, - [42 ... 47] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL, 0) }, - [48] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TA, 0) }, - [49] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM, 0) }, + [0 ... 1] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_MC, 0, IMC0)}, + [2 ... 7] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN, 0, IMC0) }, + [8] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TA, 0, IMC0) }, + [9] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM, 0, IMC0) }, + [10] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0, 0, SOCK) }, + [11] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1, 0, SOCK) }, + [12 ... 49] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHA, 0, SOCK) }, }; static const struct pci_id_table pci_dev_descr_knl_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING), + PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, ARRAY_SIZE(pci_dev_descr_knl), 1, KNIGHTS_LANDING), {0,} }; @@ -615,9 +627,9 @@ static const struct pci_id_table pci_dev_descr_knl_table[] = { #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0 0x6fa0 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1 0x6f60 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA 0x6fa8 -#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL 0x6f71 +#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM 0x6f71 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA 0x6f68 -#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_THERMAL 0x6f79 +#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM 0x6f79 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0 0x6ffc #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1 0x6ffd #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0 0x6faa @@ -632,32 +644,30 @@ static const struct pci_id_table pci_dev_descr_knl_table[] = { static const struct pci_id_descr pci_dev_descr_broadwell[] = { /* first item must be the HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_THERMAL, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2, 1, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3, 1, IMC0) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0, 1, SOCK) }, }; static const struct pci_id_table pci_dev_descr_broadwell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL), + PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, 10, 2, BROADWELL), {0,} /* 0 terminated list. */ }; @@ -709,7 +719,8 @@ static inline int numcol(u32 mtr) return 1 << cols; } -static struct sbridge_dev *get_sbridge_dev(u8 bus, int multi_bus) +static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bus, + struct sbridge_dev *prev) { struct sbridge_dev *sbridge_dev; @@ -722,16 +733,19 @@ static struct sbridge_dev *get_sbridge_dev(u8 bus, int multi_bus) struct sbridge_dev, list); } - list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) { - if (sbridge_dev->bus == bus) + sbridge_dev = list_entry(prev ? prev->list.next + : sbridge_edac_list.next, struct sbridge_dev, list); + + list_for_each_entry_from(sbridge_dev, &sbridge_edac_list, list) { + if (sbridge_dev->bus == bus && (dom == SOCK || dom == sbridge_dev->dom)) return sbridge_dev; } return NULL; } -static struct sbridge_dev *alloc_sbridge_dev(u8 bus, - const struct pci_id_table *table) +static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom, + const struct pci_id_table *table) { struct sbridge_dev *sbridge_dev; @@ -739,15 +753,17 @@ static struct sbridge_dev *alloc_sbridge_dev(u8 bus, if (!sbridge_dev) return NULL; - sbridge_dev->pdev = kzalloc(sizeof(*sbridge_dev->pdev) * table->n_devs, - GFP_KERNEL); + sbridge_dev->pdev = kcalloc(table->n_devs_per_imc, + sizeof(*sbridge_dev->pdev), + GFP_KERNEL); if (!sbridge_dev->pdev) { kfree(sbridge_dev); return NULL; } sbridge_dev->bus = bus; - sbridge_dev->n_devs = table->n_devs; + sbridge_dev->dom = dom; + sbridge_dev->n_devs = table->n_devs_per_imc; list_add_tail(&sbridge_dev->list, &sbridge_edac_list); return sbridge_dev; @@ -1044,79 +1060,6 @@ static int haswell_chan_hash(int idx, u64 addr) return idx; } -/**************************************************************************** - Memory check routines - ****************************************************************************/ -static struct pci_dev *get_pdev_same_bus(u8 bus, u32 id) -{ - struct pci_dev *pdev = NULL; - - do { - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, id, pdev); - if (pdev && pdev->bus->number == bus) - break; - } while (pdev); - - return pdev; -} - -/** - * check_if_ecc_is_active() - Checks if ECC is active - * @bus: Device bus - * @type: Memory controller type - * returns: 0 in case ECC is active, -ENODEV if it can't be determined or - * disabled - */ -static int check_if_ecc_is_active(const u8 bus, enum type type) -{ - struct pci_dev *pdev = NULL; - u32 mcmtr, id; - - switch (type) { - case IVY_BRIDGE: - id = PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA; - break; - case HASWELL: - id = PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA; - break; - case SANDY_BRIDGE: - id = PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA; - break; - case BROADWELL: - id = PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA; - break; - case KNIGHTS_LANDING: - /* - * KNL doesn't group things by bus the same way - * SB/IB/Haswell does. - */ - id = PCI_DEVICE_ID_INTEL_KNL_IMC_TA; - break; - default: - return -ENODEV; - } - - if (type != KNIGHTS_LANDING) - pdev = get_pdev_same_bus(bus, id); - else - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, id, 0); - - if (!pdev) { - sbridge_printk(KERN_ERR, "Couldn't find PCI device " - "%04x:%04x! on bus %02d\n", - PCI_VENDOR_ID_INTEL, id, bus); - return -ENODEV; - } - - pci_read_config_dword(pdev, - type == KNIGHTS_LANDING ? KNL_MCMTR : MCMTR, &mcmtr); - if (!IS_ECC_ENABLED(mcmtr)) { - sbridge_printk(KERN_ERR, "ECC is disabled. Aborting\n"); - return -ENODEV; - } - return 0; -} - /* Low bits of TAD limit, and some metadata. */ static const u32 knl_tad_dram_limit_lo[] = { 0x400, 0x500, 0x600, 0x700, @@ -1587,25 +1530,13 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes) return 0; } -static int get_dimm_config(struct mem_ctl_info *mci) +static void get_source_id(struct mem_ctl_info *mci) { struct sbridge_pvt *pvt = mci->pvt_info; - struct dimm_info *dimm; - unsigned i, j, banks, ranks, rows, cols, npages; - u64 size; u32 reg; - enum edac_type mode; - enum mem_type mtype; - int channels = pvt->info.type == KNIGHTS_LANDING ? - KNL_MAX_CHANNELS : NUM_CHANNELS; - u64 knl_mc_sizes[KNL_MAX_CHANNELS]; - if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL) { - pci_read_config_dword(pvt->pci_ha0, HASWELL_HASYSDEFEATURE2, ®); - pvt->is_chan_hash = GET_BITFIELD(reg, 21, 21); - } if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL || - pvt->info.type == KNIGHTS_LANDING) + pvt->info.type == KNIGHTS_LANDING) pci_read_config_dword(pvt->pci_sad1, SAD_TARGET, ®); else pci_read_config_dword(pvt->pci_br0, SAD_TARGET, ®); @@ -1614,50 +1545,19 @@ static int get_dimm_config(struct mem_ctl_info *mci) pvt->sbridge_dev->source_id = SOURCE_ID_KNL(reg); else pvt->sbridge_dev->source_id = SOURCE_ID(reg); +} - pvt->sbridge_dev->node_id = pvt->info.get_node_id(pvt); - edac_dbg(0, "mc#%d: Node ID: %d, source ID: %d\n", - pvt->sbridge_dev->mc, - pvt->sbridge_dev->node_id, - pvt->sbridge_dev->source_id); - - /* KNL doesn't support mirroring or lockstep, - * and is always closed page - */ - if (pvt->info.type == KNIGHTS_LANDING) { - mode = EDAC_S4ECD4ED; - pvt->is_mirrored = false; - - if (knl_get_dimm_capacity(pvt, knl_mc_sizes) != 0) - return -1; - } else { - pci_read_config_dword(pvt->pci_ras, RASENABLES, ®); - if (IS_MIRROR_ENABLED(reg)) { - edac_dbg(0, "Memory mirror is enabled\n"); - pvt->is_mirrored = true; - } else { - edac_dbg(0, "Memory mirror is disabled\n"); - pvt->is_mirrored = false; - } - - pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr); - if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) { - edac_dbg(0, "Lockstep is enabled\n"); - mode = EDAC_S8ECD8ED; - pvt->is_lockstep = true; - } else { - edac_dbg(0, "Lockstep is disabled\n"); - mode = EDAC_S4ECD4ED; - pvt->is_lockstep = false; - } - if (IS_CLOSE_PG(pvt->info.mcmtr)) { - edac_dbg(0, "address map is on closed page mode\n"); - pvt->is_close_pg = true; - } else { - edac_dbg(0, "address map is on open page mode\n"); - pvt->is_close_pg = false; - } - } +static int __populate_dimms(struct mem_ctl_info *mci, + u64 knl_mc_sizes[KNL_MAX_CHANNELS], + enum edac_type mode) +{ + struct sbridge_pvt *pvt = mci->pvt_info; + int channels = pvt->info.type == KNIGHTS_LANDING ? KNL_MAX_CHANNELS + : NUM_CHANNELS; + unsigned int i, j, banks, ranks, rows, cols, npages; + struct dimm_info *dimm; + enum mem_type mtype; + u64 size; mtype = pvt->info.get_memory_type(pvt); if (mtype == MEM_RDDR3 || mtype == MEM_RDDR4) @@ -1688,8 +1588,7 @@ static int get_dimm_config(struct mem_ctl_info *mci) } for (j = 0; j < max_dimms_per_channel; j++) { - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - i, j, 0); + dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); if (pvt->info.type == KNIGHTS_LANDING) { pci_read_config_dword(pvt->knl.pci_channel[i], knl_mtr_reg, &mtr); @@ -1699,6 +1598,12 @@ static int get_dimm_config(struct mem_ctl_info *mci) } edac_dbg(4, "Channel #%d MTR%d = %x\n", i, j, mtr); if (IS_DIMM_PRESENT(mtr)) { + if (!IS_ECC_ENABLED(pvt->info.mcmtr)) { + sbridge_printk(KERN_ERR, "CPU SrcID #%d, Ha #%d, Channel #%d has DIMMs, but ECC is disabled\n", + pvt->sbridge_dev->source_id, + pvt->sbridge_dev->dom, i); + return -ENODEV; + } pvt->channel[i].dimms++; ranks = numrank(pvt->info.type, mtr); @@ -1717,7 +1622,7 @@ static int get_dimm_config(struct mem_ctl_info *mci) npages = MiB_TO_PAGES(size); edac_dbg(0, "mc#%d: ha %d channel %d, dimm %d, %lld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", - pvt->sbridge_dev->mc, i/4, i%4, j, + pvt->sbridge_dev->mc, pvt->sbridge_dev->dom, i, j, size, npages, banks, ranks, rows, cols); @@ -1727,8 +1632,8 @@ static int get_dimm_config(struct mem_ctl_info *mci) dimm->mtype = mtype; dimm->edac_mode = mode; snprintf(dimm->label, sizeof(dimm->label), - "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u", - pvt->sbridge_dev->source_id, i/4, i%4, j); + "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom, i, j); } } } @@ -1736,6 +1641,65 @@ static int get_dimm_config(struct mem_ctl_info *mci) return 0; } +static int get_dimm_config(struct mem_ctl_info *mci) +{ + struct sbridge_pvt *pvt = mci->pvt_info; + u64 knl_mc_sizes[KNL_MAX_CHANNELS]; + enum edac_type mode; + u32 reg; + + if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL) { + pci_read_config_dword(pvt->pci_ha, HASWELL_HASYSDEFEATURE2, ®); + pvt->is_chan_hash = GET_BITFIELD(reg, 21, 21); + } + pvt->sbridge_dev->node_id = pvt->info.get_node_id(pvt); + edac_dbg(0, "mc#%d: Node ID: %d, source ID: %d\n", + pvt->sbridge_dev->mc, + pvt->sbridge_dev->node_id, + pvt->sbridge_dev->source_id); + + /* KNL doesn't support mirroring or lockstep, + * and is always closed page + */ + if (pvt->info.type == KNIGHTS_LANDING) { + mode = EDAC_S4ECD4ED; + pvt->is_mirrored = false; + + if (knl_get_dimm_capacity(pvt, knl_mc_sizes) != 0) + return -1; + pci_read_config_dword(pvt->pci_ta, KNL_MCMTR, &pvt->info.mcmtr); + } else { + pci_read_config_dword(pvt->pci_ras, RASENABLES, ®); + if (IS_MIRROR_ENABLED(reg)) { + edac_dbg(0, "Memory mirror is enabled\n"); + pvt->is_mirrored = true; + } else { + edac_dbg(0, "Memory mirror is disabled\n"); + pvt->is_mirrored = false; + } + + pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr); + if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) { + edac_dbg(0, "Lockstep is enabled\n"); + mode = EDAC_S8ECD8ED; + pvt->is_lockstep = true; + } else { + edac_dbg(0, "Lockstep is disabled\n"); + mode = EDAC_S4ECD4ED; + pvt->is_lockstep = false; + } + if (IS_CLOSE_PG(pvt->info.mcmtr)) { + edac_dbg(0, "address map is on closed page mode\n"); + pvt->is_close_pg = true; + } else { + edac_dbg(0, "address map is on open page mode\n"); + pvt->is_close_pg = false; + } + } + + return __populate_dimms(mci, knl_mc_sizes, mode); +} + static void get_memory_layout(const struct mem_ctl_info *mci) { struct sbridge_pvt *pvt = mci->pvt_info; @@ -1816,8 +1780,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) */ prv = 0; for (n_tads = 0; n_tads < MAX_TAD; n_tads++) { - pci_read_config_dword(pvt->pci_ha0, tad_dram_rule[n_tads], - ®); + pci_read_config_dword(pvt->pci_ha, tad_dram_rule[n_tads], ®); limit = TAD_LIMIT(reg); if (limit <= prv) break; @@ -1899,12 +1862,12 @@ static void get_memory_layout(const struct mem_ctl_info *mci) } } -static struct mem_ctl_info *get_mci_for_node_id(u8 node_id) +static struct mem_ctl_info *get_mci_for_node_id(u8 node_id, u8 ha) { struct sbridge_dev *sbridge_dev; list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) { - if (sbridge_dev->node_id == node_id) + if (sbridge_dev->node_id == node_id && sbridge_dev->dom == ha) return sbridge_dev->mci; } return NULL; @@ -1925,7 +1888,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, int interleave_mode, shiftup = 0; unsigned sad_interleave[pvt->info.max_interleave]; u32 reg, dram_rule; - u8 ch_way, sck_way, pkg, sad_ha = 0, ch_add = 0; + u8 ch_way, sck_way, pkg, sad_ha = 0; u32 tad_offset; u32 rir_way; u32 mb, gb; @@ -2038,13 +2001,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pkg = sad_pkg(pvt->info.interleave_pkg, reg, idx); *socket = sad_pkg_socket(pkg); sad_ha = sad_pkg_ha(pkg); - if (sad_ha) - ch_add = 4; if (a7mode) { /* MCChanShiftUpEnable */ - pci_read_config_dword(pvt->pci_ha0, - HASWELL_HASYSDEFEATURE2, ®); + pci_read_config_dword(pvt->pci_ha, HASWELL_HASYSDEFEATURE2, ®); shiftup = GET_BITFIELD(reg, 22, 22); } @@ -2056,8 +2016,6 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pkg = sad_pkg(pvt->info.interleave_pkg, reg, idx); *socket = sad_pkg_socket(pkg); sad_ha = sad_pkg_ha(pkg); - if (sad_ha) - ch_add = 4; edac_dbg(0, "SAD interleave package: %d = CPU socket %d, HA %d\n", idx, *socket, sad_ha); } @@ -2068,7 +2026,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Move to the proper node structure, in order to access the * right PCI registers */ - new_mci = get_mci_for_node_id(*socket); + new_mci = get_mci_for_node_id(*socket, sad_ha); if (!new_mci) { sprintf(msg, "Struct for socket #%u wasn't initialized", *socket); @@ -2081,14 +2039,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Step 2) Get memory channel */ prv = 0; - if (pvt->info.type == SANDY_BRIDGE) - pci_ha = pvt->pci_ha0; - else { - if (sad_ha) - pci_ha = pvt->pci_ha1; - else - pci_ha = pvt->pci_ha0; - } + pci_ha = pvt->pci_ha; for (n_tads = 0; n_tads < MAX_TAD; n_tads++) { pci_read_config_dword(pci_ha, tad_dram_rule[n_tads], ®); limit = TAD_LIMIT(reg); @@ -2139,9 +2090,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, } *channel_mask = 1 << base_ch; - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - tad_ch_nilv_offset[n_tads], - &tad_offset); + pci_read_config_dword(pvt->pci_tad[base_ch], tad_ch_nilv_offset[n_tads], &tad_offset); if (pvt->is_mirrored) { *channel_mask |= 1 << ((base_ch + 2) % 4); @@ -2192,9 +2141,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Step 3) Decode rank */ for (n_rir = 0; n_rir < MAX_RIR_RANGES; n_rir++) { - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - rir_way_limit[n_rir], - ®); + pci_read_config_dword(pvt->pci_tad[base_ch], rir_way_limit[n_rir], ®); if (!IS_RIR_VALID(reg)) continue; @@ -2222,9 +2169,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, idx = (ch_addr >> 13); /* FIXME: Datasheet says to shift by 15 */ idx %= 1 << rir_way; - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - rir_offset[n_rir][idx], - ®); + pci_read_config_dword(pvt->pci_tad[base_ch], rir_offset[n_rir][idx], ®); *rank = RIR_RNK_TGT(pvt->info.type, reg); edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", @@ -2277,10 +2222,11 @@ static int sbridge_get_onedevice(struct pci_dev **prev, const unsigned devno, const int multi_bus) { - struct sbridge_dev *sbridge_dev; + struct sbridge_dev *sbridge_dev = NULL; const struct pci_id_descr *dev_descr = &table->descr[devno]; struct pci_dev *pdev = NULL; u8 bus = 0; + int i = 0; sbridge_printk(KERN_DEBUG, "Seeking for: PCI ID %04x:%04x\n", @@ -2311,9 +2257,10 @@ static int sbridge_get_onedevice(struct pci_dev **prev, } bus = pdev->bus->number; - sbridge_dev = get_sbridge_dev(bus, multi_bus); +next_imc: + sbridge_dev = get_sbridge_dev(bus, dev_descr->dom, multi_bus, sbridge_dev); if (!sbridge_dev) { - sbridge_dev = alloc_sbridge_dev(bus, table); + sbridge_dev = alloc_sbridge_dev(bus, dev_descr->dom, table); if (!sbridge_dev) { pci_dev_put(pdev); return -ENOMEM; @@ -2321,7 +2268,7 @@ static int sbridge_get_onedevice(struct pci_dev **prev, (*num_mc)++; } - if (sbridge_dev->pdev[devno]) { + if (sbridge_dev->pdev[sbridge_dev->i_devs]) { sbridge_printk(KERN_ERR, "Duplicated device for %04x:%04x\n", PCI_VENDOR_ID_INTEL, dev_descr->dev_id); @@ -2329,7 +2276,14 @@ static int sbridge_get_onedevice(struct pci_dev **prev, return -ENODEV; } - sbridge_dev->pdev[devno] = pdev; + sbridge_dev->pdev[sbridge_dev->i_devs++] = pdev; + + /* pdev belongs to more than one IMC, do extra gets */ + if (++i > 1) + pci_dev_get(pdev); + + if (dev_descr->dom == SOCK && i < table->n_imcs_per_sock) + goto next_imc; /* Be sure that the device is enabled */ if (unlikely(pci_enable_device(pdev) < 0)) { @@ -2374,7 +2328,7 @@ static int sbridge_get_all_devices(u8 *num_mc, if (table->type == KNIGHTS_LANDING) allow_dups = multi_bus = 1; while (table && table->descr) { - for (i = 0; i < table->n_devs; i++) { + for (i = 0; i < table->n_devs_per_sock; i++) { if (!allow_dups || i == 0 || table->descr[i].dev_id != table->descr[i-1].dev_id) { @@ -2385,7 +2339,7 @@ static int sbridge_get_all_devices(u8 *num_mc, table, i, multi_bus); if (rc < 0) { if (i == 0) { - i = table->n_devs; + i = table->n_devs_per_sock; break; } sbridge_put_all_devices(); @@ -2399,6 +2353,13 @@ static int sbridge_get_all_devices(u8 *num_mc, return 0; } +/* + * Device IDs for {SBRIDGE,IBRIDGE,HASWELL,BROADWELL}_IMC_HA0_TAD0 are in + * the format: XXXa. So we can convert from a device to the corresponding + * channel like this + */ +#define TAD_DEV_TO_CHAN(dev) (((dev) & 0xf) - 0xa) + static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, struct sbridge_dev *sbridge_dev) { @@ -2423,7 +2384,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_br0 = pdev; break; case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0: - pvt->pci_ha0 = pdev; + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA: pvt->pci_ta = pdev; @@ -2436,7 +2397,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2: case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2455,7 +2416,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha0 || + if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha || !pvt->pci_ras || !pvt->pci_ta) goto enodev; @@ -2488,19 +2449,26 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA: pvt->pci_ta = pdev; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2520,19 +2488,6 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_IBRIDGE_BR1: pvt->pci_br1 = pdev; break; - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0 + 4; - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; default: goto error; } @@ -2544,13 +2499,12 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_br0 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_br0 || !pvt->pci_br1 || !pvt->pci_ras || !pvt->pci_ta) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2593,32 +2547,27 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_sad1 = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA: pvt->pci_ta = pdev; break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0; - - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0 + 4; - + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2630,12 +2579,6 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, if (!pvt->pci_ddrio) pvt->pci_ddrio = pdev; break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA: - pvt->pci_ha1_ta = pdev; - break; default: break; } @@ -2647,13 +2590,12 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_sad1 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_sad1 || !pvt->pci_ras || !pvt->pci_ta || !pvt->info.pci_vtd) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2690,30 +2632,27 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_sad1 = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA: pvt->pci_ta = pdev; break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0; - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0 + 4; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2721,12 +2660,6 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0: pvt->pci_ddrio = pdev; break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA: - pvt->pci_ha1_ta = pdev; - break; default: break; } @@ -2738,13 +2671,12 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_sad1 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_sad1 || !pvt->pci_ras || !pvt->pci_ta || !pvt->info.pci_vtd) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2812,7 +2744,7 @@ static int knl_mci_bind_devs(struct mem_ctl_info *mci, pvt->knl.pci_cha[devidx] = pdev; break; - case PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL: + case PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN: devidx = -1; /* @@ -3006,7 +2938,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, if (rc < 0) goto err_parsing; - new_mci = get_mci_for_node_id(socket); + new_mci = get_mci_for_node_id(socket, ha); if (!new_mci) { strcpy(msg, "Error: socket got corrupted!"); goto err_parsing; @@ -3053,7 +2985,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, - 4*ha+channel, dimm, -1, + channel, dimm, -1, optype, msg); return; err_parsing: @@ -3078,7 +3010,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, if (edac_get_report_status() == EDAC_REPORTING_DISABLED) return NOTIFY_DONE; - mci = get_mci_for_node_id(mce->socketid); + mci = get_mci_for_node_id(mce->socketid, IMC0); if (!mci) return NOTIFY_DONE; pvt = mci->pvt_info; @@ -3159,11 +3091,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) struct pci_dev *pdev = sbridge_dev->pdev[0]; int rc; - /* Check the number of active and not disabled channels */ - rc = check_if_ecc_is_active(sbridge_dev->bus, type); - if (unlikely(rc < 0)) - return rc; - /* allocate a new MC control structure */ layers[0].type = EDAC_MC_LAYER_CHANNEL; layers[0].size = type == KNIGHTS_LANDING ? @@ -3192,7 +3119,7 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) MEM_FLAG_DDR4 : MEM_FLAG_DDR3; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; - mci->mod_name = "sbridge_edac.c"; + mci->mod_name = "sb_edac.c"; mci->mod_ver = SBRIDGE_REVISION; mci->dev_name = pci_name(pdev); mci->ctl_page_to_phys = NULL; @@ -3215,12 +3142,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = ibridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Ivy Bridge Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = ibridge_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Ivy Bridge SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case SANDY_BRIDGE: pvt->info.rankcfgr = SB_RANK_CFG_A; @@ -3238,12 +3167,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(sbridge_interleave_list); pvt->info.interleave_pkg = sbridge_interleave_pkg; pvt->info.get_width = sbridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Sandy Bridge Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = sbridge_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Sandy Bridge SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case HASWELL: /* rankcfgr isn't used */ @@ -3261,12 +3192,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = ibridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Haswell Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = haswell_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Haswell SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case BROADWELL: /* rankcfgr isn't used */ @@ -3284,12 +3217,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = broadwell_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Broadwell Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = broadwell_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Broadwell SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case KNIGHTS_LANDING: /* pvt->info.rankcfgr == ??? */ @@ -3307,17 +3242,22 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(knl_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = knl_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, - "Knights Landing Socket#%d", mci->mc_idx); rc = knl_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Knights Landing SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; } /* Get dimm basic config and the memory layout */ - get_dimm_config(mci); + rc = get_dimm_config(mci); + if (rc < 0) { + edac_dbg(0, "MC: failed to get_dimm_config()\n"); + goto fail; + } get_memory_layout(mci); /* record ptr to the generic device */ @@ -3327,13 +3267,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) if (unlikely(edac_mc_add_mc(mci))) { edac_dbg(0, "MC: failed edac_mc_add_mc()\n"); rc = -EINVAL; - goto fail0; + goto fail; } return 0; -fail0: +fail: kfree(mci->ctl_name); +fail0: edac_mc_free(mci); sbridge_dev->mci = NULL; return rc; diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 86d585cb6d321b..2d352b40ae1c8c 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -2080,7 +2080,7 @@ static int thunderx_l2c_probe(struct pci_dev *pdev, if (IS_ENABLED(CONFIG_EDAC_DEBUG)) { l2c->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name); - thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr, + ret = thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr, l2c, dfs_entries); if (ret != dfs_entries) { diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 32f2dc8e4702c8..6d50071f07d554 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -115,6 +115,7 @@ config EXTCON_PALMAS config EXTCON_QCOM_SPMI_MISC tristate "Qualcomm USB extcon support" + depends on ARCH_QCOM || COMPILE_TEST help Say Y here to enable SPMI PMIC based USB cable detection support on Qualcomm PMICs such as PM8941. diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c index e2d78cd7030d3b..f84da4a17724c4 100644 --- a/drivers/extcon/extcon-arizona.c +++ b/drivers/extcon/extcon-arizona.c @@ -1271,9 +1271,7 @@ static int arizona_extcon_get_micd_configs(struct device *dev, goto out; nconfs /= entries_per_config; - - micd_configs = devm_kzalloc(dev, - nconfs * sizeof(struct arizona_micd_range), + micd_configs = devm_kcalloc(dev, nconfs, sizeof(*micd_configs), GFP_KERNEL); if (!micd_configs) { ret = -ENOMEM; diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index f422a78ba34242..8eccf7b1493700 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -964,12 +964,12 @@ EXPORT_SYMBOL_GPL(extcon_unregister_notifier); /** * extcon_register_notifier_all() - Register a notifier block for all connectors - * @edev: the extcon device that has the external connecotr. + * @edev: the extcon device that has the external connector. * @nb: a notifier block to be registered. * - * This fucntion registers a notifier block in order to receive the state + * This function registers a notifier block in order to receive the state * change of all supported external connectors from extcon device. - * And The second parameter given to the callback of nb (val) is + * And the second parameter given to the callback of nb (val) is * the current state and third parameter is the edev pointer. * * Returns 0 if success or error number if fail @@ -1252,9 +1252,8 @@ int extcon_dev_register(struct extcon_dev *edev) } spin_lock_init(&edev->lock); - - edev->nh = devm_kzalloc(&edev->dev, - sizeof(*edev->nh) * edev->max_supported, GFP_KERNEL); + edev->nh = devm_kcalloc(&edev->dev, edev->max_supported, + sizeof(*edev->nh), GFP_KERNEL); if (!edev->nh) { ret = -ENOMEM; goto err_dev; diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index 5d3640264f2da1..655c259e37fde5 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -1482,9 +1482,14 @@ static int fwnet_probe(struct fw_unit *unit, goto out; dev->local_fifo = dev->handler.offset; + /* + * default MTU: RFC 2734 cl. 4, RFC 3146 cl. 4 + * maximum MTU: RFC 2734 cl. 4.2, fragment encapsulation header's + * maximum possible datagram_size + 1 = 0xfff + 1 + */ net->mtu = 1500U; net->min_mtu = ETH_MIN_MTU; - net->max_mtu = 0xfff; + net->max_mtu = 4096U; /* Set our hardware address while we're at it */ ha = (union fwnet_hwaddr *)net->dev_addr; diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 93f7acdaac7ac1..82ee042f075cf9 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -649,6 +649,21 @@ void __init dmi_scan_machine(void) if (p == NULL) goto error; + /* + * Same logic as above, look for a 64-bit entry point + * first, and if not found, fall back to 32-bit entry point. + */ + memcpy_fromio(buf, p, 16); + for (q = p + 16; q < p + 0x10000; q += 16) { + memcpy_fromio(buf + 16, q, 16); + if (!dmi_smbios3_present(buf)) { + dmi_available = 1; + dmi_early_unmap(p, 0x10000); + goto out; + } + memcpy(buf, buf + 16, 16); + } + /* * Iterate over all possible DMI header addresses q. * Maintain the 32 bytes around q in buf. On the @@ -659,7 +674,7 @@ void __init dmi_scan_machine(void) memset(buf, 0, 16); for (q = p; q < p + 0x10000; q += 16) { memcpy_fromio(buf + 16, q, 16); - if (!dmi_smbios3_present(buf) || !dmi_present(buf)) { + if (!dmi_present(buf)) { dmi_available = 1; dmi_early_unmap(p, 0x10000); goto out; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index ef1fafdad4008a..5a0fa939d70f96 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -4,7 +4,7 @@ #include #include -#define DUMP_NAME_LEN 52 +#define DUMP_NAME_LEN 66 static bool efivars_pstore_disable = IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE); @@ -244,12 +244,12 @@ static int efi_pstore_write(struct pstore_record *record) efi_guid_t vendor = LINUX_EFI_CRASH_GUID; int i, ret = 0; - record->time.tv_sec = get_seconds(); - record->time.tv_nsec = 0; - record->id = generic_id(record->time.tv_sec, record->part, record->count); + /* Since we copy the entire length of name, make sure it is wiped. */ + memset(name, 0, sizeof(name)); + snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu-%c", record->type, record->part, record->count, record->time.tv_sec, record->compressed ? 'C' : 'D'); @@ -267,44 +267,20 @@ static int efi_pstore_write(struct pstore_record *record) return ret; }; -struct pstore_erase_data { - struct pstore_record *record; - efi_char16_t *name; -}; - /* * Clean up an entry with the same name */ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data) { - struct pstore_erase_data *ed = data; + efi_char16_t *efi_name = data; efi_guid_t vendor = LINUX_EFI_CRASH_GUID; - efi_char16_t efi_name_old[DUMP_NAME_LEN]; - efi_char16_t *efi_name = ed->name; - unsigned long ucs2_len = ucs2_strlen(ed->name); - char name_old[DUMP_NAME_LEN]; - int i; + unsigned long ucs2_len = ucs2_strlen(efi_name); if (efi_guidcmp(entry->var.VendorGuid, vendor)) return 0; - if (ucs2_strncmp(entry->var.VariableName, - efi_name, (size_t)ucs2_len)) { - /* - * Check if an old format, which doesn't support - * holding multiple logs, remains. - */ - snprintf(name_old, sizeof(name_old), "dump-type%u-%u-%lu", - ed->record->type, ed->record->part, - ed->record->time.tv_sec); - - for (i = 0; i < DUMP_NAME_LEN; i++) - efi_name_old[i] = name_old[i]; - - if (ucs2_strncmp(entry->var.VariableName, efi_name_old, - ucs2_strlen(efi_name_old))) - return 0; - } + if (ucs2_strncmp(entry->var.VariableName, efi_name, (size_t)ucs2_len)) + return 0; if (entry->scanning) { /* @@ -321,35 +297,48 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data) return 1; } -static int efi_pstore_erase(struct pstore_record *record) +static int efi_pstore_erase_name(const char *name) { - struct pstore_erase_data edata; struct efivar_entry *entry = NULL; - char name[DUMP_NAME_LEN]; efi_char16_t efi_name[DUMP_NAME_LEN]; int found, i; - snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu", - record->type, record->part, record->count, - record->time.tv_sec); - - for (i = 0; i < DUMP_NAME_LEN; i++) + for (i = 0; i < DUMP_NAME_LEN; i++) { efi_name[i] = name[i]; - - edata.record = record; - edata.name = efi_name; + if (name[i] == '\0') + break; + } if (efivar_entry_iter_begin()) return -EINTR; - found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry); - if (found && !entry->scanning) { - efivar_entry_iter_end(); + found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, + efi_name, &entry); + efivar_entry_iter_end(); + + if (found && !entry->scanning) efivar_unregister(entry); - } else - efivar_entry_iter_end(); - return 0; + return found ? 0 : -ENOENT; +} + +static int efi_pstore_erase(struct pstore_record *record) +{ + char name[DUMP_NAME_LEN]; + int ret; + + snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu", + record->type, record->part, record->count, + record->time.tv_sec); + ret = efi_pstore_erase_name(name); + if (ret != -ENOENT) + return ret; + + snprintf(name, sizeof(name), "dump-type%u-%u-%lu", + record->type, record->part, record->time.tv_sec); + ret = efi_pstore_erase_name(name); + + return ret; } static struct pstore_info efi_pstore_info = { diff --git a/drivers/firmware/google/memconsole-coreboot.c b/drivers/firmware/google/memconsole-coreboot.c index 02711114deceb6..52738887735c1d 100644 --- a/drivers/firmware/google/memconsole-coreboot.c +++ b/drivers/firmware/google/memconsole-coreboot.c @@ -26,12 +26,52 @@ /* CBMEM firmware console log descriptor. */ struct cbmem_cons { - u32 buffer_size; - u32 buffer_cursor; - u8 buffer_body[0]; + u32 size_dont_access_after_boot; + u32 cursor; + u8 body[0]; } __packed; +#define CURSOR_MASK ((1 << 28) - 1) +#define OVERFLOW (1 << 31) + static struct cbmem_cons __iomem *cbmem_console; +static u32 cbmem_console_size; + +/* + * The cbmem_console structure is read again on every access because it may + * change at any time if runtime firmware logs new messages. This may rarely + * lead to race conditions where the firmware overwrites the beginning of the + * ring buffer with more lines after we have already read |cursor|. It should be + * rare and harmless enough that we don't spend extra effort working around it. + */ +static ssize_t memconsole_coreboot_read(char *buf, loff_t pos, size_t count) +{ + u32 cursor = cbmem_console->cursor & CURSOR_MASK; + u32 flags = cbmem_console->cursor & ~CURSOR_MASK; + u32 size = cbmem_console_size; + struct seg { /* describes ring buffer segments in logical order */ + u32 phys; /* physical offset from start of mem buffer */ + u32 len; /* length of segment */ + } seg[2] = { {0}, {0} }; + size_t done = 0; + int i; + + if (flags & OVERFLOW) { + if (cursor > size) /* Shouldn't really happen, but... */ + cursor = 0; + seg[0] = (struct seg){.phys = cursor, .len = size - cursor}; + seg[1] = (struct seg){.phys = 0, .len = cursor}; + } else { + seg[0] = (struct seg){.phys = 0, .len = min(cursor, size)}; + } + + for (i = 0; i < ARRAY_SIZE(seg) && count > done; i++) { + done += memory_read_from_buffer(buf + done, count - done, &pos, + cbmem_console->body + seg[i].phys, seg[i].len); + pos -= seg[i].len; + } + return done; +} static int memconsole_coreboot_init(phys_addr_t physaddr) { @@ -42,17 +82,17 @@ static int memconsole_coreboot_init(phys_addr_t physaddr) if (!tmp_cbmc) return -ENOMEM; + /* Read size only once to prevent overrun attack through /dev/mem. */ + cbmem_console_size = tmp_cbmc->size_dont_access_after_boot; cbmem_console = memremap(physaddr, - tmp_cbmc->buffer_size + sizeof(*cbmem_console), + cbmem_console_size + sizeof(*cbmem_console), MEMREMAP_WB); memunmap(tmp_cbmc); if (!cbmem_console) return -ENOMEM; - memconsole_setup(cbmem_console->buffer_body, - min(cbmem_console->buffer_cursor, cbmem_console->buffer_size)); - + memconsole_setup(memconsole_coreboot_read); return 0; } diff --git a/drivers/firmware/google/memconsole-x86-legacy.c b/drivers/firmware/google/memconsole-x86-legacy.c index 1f279ee883b9ae..8c1bf6dbdaa643 100644 --- a/drivers/firmware/google/memconsole-x86-legacy.c +++ b/drivers/firmware/google/memconsole-x86-legacy.c @@ -48,6 +48,15 @@ struct biosmemcon_ebda { }; } __packed; +static char *memconsole_baseaddr; +static size_t memconsole_length; + +static ssize_t memconsole_read(char *buf, loff_t pos, size_t count) +{ + return memory_read_from_buffer(buf, count, &pos, memconsole_baseaddr, + memconsole_length); +} + static void found_v1_header(struct biosmemcon_ebda *hdr) { pr_info("memconsole: BIOS console v1 EBDA structure found at %p\n", @@ -56,7 +65,9 @@ static void found_v1_header(struct biosmemcon_ebda *hdr) hdr->v1.buffer_addr, hdr->v1.start, hdr->v1.end, hdr->v1.num_chars); - memconsole_setup(phys_to_virt(hdr->v1.buffer_addr), hdr->v1.num_chars); + memconsole_baseaddr = phys_to_virt(hdr->v1.buffer_addr); + memconsole_length = hdr->v1.num_chars; + memconsole_setup(memconsole_read); } static void found_v2_header(struct biosmemcon_ebda *hdr) @@ -67,8 +78,9 @@ static void found_v2_header(struct biosmemcon_ebda *hdr) hdr->v2.buffer_addr, hdr->v2.start, hdr->v2.end, hdr->v2.num_bytes); - memconsole_setup(phys_to_virt(hdr->v2.buffer_addr + hdr->v2.start), - hdr->v2.end - hdr->v2.start); + memconsole_baseaddr = phys_to_virt(hdr->v2.buffer_addr + hdr->v2.start); + memconsole_length = hdr->v2.end - hdr->v2.start; + memconsole_setup(memconsole_read); } /* diff --git a/drivers/firmware/google/memconsole.c b/drivers/firmware/google/memconsole.c index 94e200ddb4faf8..166f07c68c02c8 100644 --- a/drivers/firmware/google/memconsole.c +++ b/drivers/firmware/google/memconsole.c @@ -22,15 +22,15 @@ #include "memconsole.h" -static char *memconsole_baseaddr; -static size_t memconsole_length; +static ssize_t (*memconsole_read_func)(char *, loff_t, size_t); static ssize_t memconsole_read(struct file *filp, struct kobject *kobp, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { - return memory_read_from_buffer(buf, count, &pos, memconsole_baseaddr, - memconsole_length); + if (WARN_ON_ONCE(!memconsole_read_func)) + return -EIO; + return memconsole_read_func(buf, pos, count); } static struct bin_attribute memconsole_bin_attr = { @@ -38,16 +38,14 @@ static struct bin_attribute memconsole_bin_attr = { .read = memconsole_read, }; -void memconsole_setup(void *baseaddr, size_t length) +void memconsole_setup(ssize_t (*read_func)(char *, loff_t, size_t)) { - memconsole_baseaddr = baseaddr; - memconsole_length = length; + memconsole_read_func = read_func; } EXPORT_SYMBOL(memconsole_setup); int memconsole_sysfs_init(void) { - memconsole_bin_attr.size = memconsole_length; return sysfs_create_bin_file(firmware_kobj, &memconsole_bin_attr); } EXPORT_SYMBOL(memconsole_sysfs_init); diff --git a/drivers/firmware/google/memconsole.h b/drivers/firmware/google/memconsole.h index 190fc03a51aee0..ff1592dc7d1a4b 100644 --- a/drivers/firmware/google/memconsole.h +++ b/drivers/firmware/google/memconsole.h @@ -18,13 +18,14 @@ #ifndef __FIRMWARE_GOOGLE_MEMCONSOLE_H #define __FIRMWARE_GOOGLE_MEMCONSOLE_H +#include + /* * memconsole_setup * - * Initialize the memory console from raw (virtual) base - * address and length. + * Initialize the memory console, passing the function to handle read accesses. */ -void memconsole_setup(void *baseaddr, size_t length); +void memconsole_setup(ssize_t (*read_func)(char *, loff_t, size_t)); /* * memconsole_sysfs_init diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c index 1e7860f02f4fa9..78945729388e32 100644 --- a/drivers/firmware/google/vpd.c +++ b/drivers/firmware/google/vpd.c @@ -118,14 +118,13 @@ static int vpd_section_attrib_add(const u8 *key, s32 key_len, info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; - info->key = kzalloc(key_len + 1, GFP_KERNEL); + + info->key = kstrndup(key, key_len, GFP_KERNEL); if (!info->key) { ret = -ENOMEM; goto free_info; } - memcpy(info->key, key, key_len); - sysfs_bin_attr_init(&info->bin_attr); info->bin_attr.attr.name = info->key; info->bin_attr.attr.mode = 0444; @@ -136,12 +135,12 @@ static int vpd_section_attrib_add(const u8 *key, s32 key_len, info->value = value; INIT_LIST_HEAD(&info->list); - list_add_tail(&info->list, &sec->attribs); ret = sysfs_create_bin_file(sec->kobj, &info->bin_attr); if (ret) goto free_info_key; + list_add_tail(&info->list, &sec->attribs); return 0; free_info_key: @@ -158,8 +157,8 @@ static void vpd_section_attrib_destroy(struct vpd_section *sec) struct vpd_attrib_info *temp; list_for_each_entry_safe(info, temp, &sec->attribs, list) { - kfree(info->key); sysfs_remove_bin_file(sec->kobj, &info->bin_attr); + kfree(info->key); kfree(info); } } @@ -191,8 +190,7 @@ static int vpd_section_create_attribs(struct vpd_section *sec) static int vpd_section_init(const char *name, struct vpd_section *sec, phys_addr_t physaddr, size_t size) { - int ret; - int raw_len; + int err; sec->baseaddr = memremap(physaddr, size, MEMREMAP_WB); if (!sec->baseaddr) @@ -201,10 +199,11 @@ static int vpd_section_init(const char *name, struct vpd_section *sec, sec->name = name; /* We want to export the raw partion with name ${name}_raw */ - raw_len = strlen(name) + 5; - sec->raw_name = kzalloc(raw_len, GFP_KERNEL); - strncpy(sec->raw_name, name, raw_len); - strncat(sec->raw_name, "_raw", raw_len); + sec->raw_name = kasprintf(GFP_KERNEL, "%s_raw", name); + if (!sec->raw_name) { + err = -ENOMEM; + goto err_iounmap; + } sysfs_bin_attr_init(&sec->bin_attr); sec->bin_attr.attr.name = sec->raw_name; @@ -213,14 +212,14 @@ static int vpd_section_init(const char *name, struct vpd_section *sec, sec->bin_attr.read = vpd_section_read; sec->bin_attr.private = sec; - ret = sysfs_create_bin_file(vpd_kobj, &sec->bin_attr); - if (ret) - goto free_sec; + err = sysfs_create_bin_file(vpd_kobj, &sec->bin_attr); + if (err) + goto err_free_raw_name; sec->kobj = kobject_create_and_add(name, vpd_kobj); if (!sec->kobj) { - ret = -EINVAL; - goto sysfs_remove; + err = -EINVAL; + goto err_sysfs_remove; } INIT_LIST_HEAD(&sec->attribs); @@ -230,21 +229,20 @@ static int vpd_section_init(const char *name, struct vpd_section *sec, return 0; -sysfs_remove: +err_sysfs_remove: sysfs_remove_bin_file(vpd_kobj, &sec->bin_attr); - -free_sec: +err_free_raw_name: kfree(sec->raw_name); +err_iounmap: iounmap(sec->baseaddr); - - return ret; + return err; } static int vpd_section_destroy(struct vpd_section *sec) { if (sec->enabled) { vpd_section_attrib_destroy(sec); - kobject_del(sec->kobj); + kobject_put(sec->kobj); sysfs_remove_bin_file(vpd_kobj, &sec->bin_attr); kfree(sec->raw_name); iounmap(sec->baseaddr); @@ -319,9 +317,6 @@ static int __init vpd_platform_init(void) if (!vpd_kobj) return -ENOMEM; - memset(&ro_vpd, 0, sizeof(ro_vpd)); - memset(&rw_vpd, 0, sizeof(rw_vpd)); - platform_driver_register(&vpd_driver); return 0; @@ -331,7 +326,7 @@ static void __exit vpd_platform_exit(void) { vpd_section_destroy(&ro_vpd); vpd_section_destroy(&rw_vpd); - kobject_del(vpd_kobj); + kobject_put(vpd_kobj); } module_init(vpd_platform_init); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 23ca51ee6b28e4..2e7d9ff74334e8 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -242,6 +242,17 @@ config GPIO_ICH If unsure, say N. +config GPIO_INGENIC + tristate "Ingenic JZ47xx SoCs GPIO support" + depends on OF + depends on MACH_INGENIC || COMPILE_TEST + select GPIOLIB_IRQCHIP + help + Say yes here to support the GPIO functionality present on the + JZ4740 and JZ4780 SoCs from Ingenic. + + If unsure, say N. + config GPIO_IOP tristate "Intel IOP GPIO" depends on ARCH_IOP32X || ARCH_IOP33X || COMPILE_TEST @@ -326,9 +337,10 @@ config GPIO_MPC8XXX config GPIO_MVEBU def_bool y - depends on PLAT_ORION + depends on PLAT_ORION || ARCH_MVEBU depends on OF_GPIO select GENERIC_IRQ_CHIP + select REGMAP_MMIO config GPIO_MXC def_bool y @@ -504,12 +516,13 @@ config GPIO_XILINX config GPIO_XLP tristate "Netlogic XLP GPIO support" - depends on OF_GPIO && (CPU_XLP || ARCH_VULCAN || ARCH_THUNDER2 || COMPILE_TEST) + depends on OF_GPIO && (CPU_XLP || ARCH_THUNDER2 || COMPILE_TEST) select GPIOLIB_IRQCHIP help This driver provides support for GPIO interface on Netlogic XLP MIPS64 SoCs. Currently supported XLP variants are XLP8XX, XLP3XX, XLP2XX, - XLP9XX and XLP5XX. + XLP9XX and XLP5XX. The same GPIO controller block is also present in + Cavium's ThunderX2 CN99XX SoCs. If unsure, say N. @@ -1225,22 +1238,11 @@ config GPIO_PISOSR GPIO driver for SPI compatible parallel-in/serial-out shift registers. These are input only devices. -endmenu - -menu "SPI or I2C GPIO expanders" - depends on (SPI_MASTER && !I2C) || I2C - -config GPIO_MCP23S08 - tristate "Microchip MCP23xxx I/O expander" - depends on OF_GPIO - select GPIOLIB_IRQCHIP - select REGMAP_I2C if I2C - select REGMAP if SPI_MASTER +config GPIO_XRA1403 + tristate "EXAR XRA1403 16-bit GPIO expander" + select REGMAP_SPI help - SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017 - I/O expanders. - This provides a GPIO interface supporting inputs and outputs. - The I2C versions of the chips can be used as interrupt-controller. + GPIO driver for EXAR XRA1403 16-bit SPI-based GPIO expander. endmenu diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index 68b96277d9fa46..bcd0a0beb73f3a 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -55,6 +55,7 @@ obj-$(CONFIG_GPIO_GPIO_MM) += gpio-gpio-mm.o obj-$(CONFIG_GPIO_GRGPIO) += gpio-grgpio.o obj-$(CONFIG_HTC_EGPIO) += gpio-htc-egpio.o obj-$(CONFIG_GPIO_ICH) += gpio-ich.o +obj-$(CONFIG_GPIO_INGENIC) += gpio-ingenic.o obj-$(CONFIG_GPIO_IOP) += gpio-iop.o obj-$(CONFIG_GPIO_IT87) += gpio-it87.o obj-$(CONFIG_GPIO_JANZ_TTL) += gpio-janz-ttl.o @@ -77,7 +78,6 @@ obj-$(CONFIG_GPIO_MENZ127) += gpio-menz127.o obj-$(CONFIG_GPIO_MERRIFIELD) += gpio-merrifield.o obj-$(CONFIG_GPIO_MC33880) += gpio-mc33880.o obj-$(CONFIG_GPIO_MC9S08DZ60) += gpio-mc9s08dz60.o -obj-$(CONFIG_GPIO_MCP23S08) += gpio-mcp23s08.o obj-$(CONFIG_GPIO_ML_IOH) += gpio-ml-ioh.o obj-$(CONFIG_GPIO_MM_LANTIQ) += gpio-mm-lantiq.o obj-$(CONFIG_GPIO_MOCKUP) += gpio-mockup.o @@ -141,6 +141,7 @@ obj-$(CONFIG_GPIO_XGENE) += gpio-xgene.o obj-$(CONFIG_GPIO_XGENE_SB) += gpio-xgene-sb.o obj-$(CONFIG_GPIO_XILINX) += gpio-xilinx.o obj-$(CONFIG_GPIO_XLP) += gpio-xlp.o +obj-$(CONFIG_GPIO_XRA1403) += gpio-xra1403.o obj-$(CONFIG_GPIO_XTENSA) += gpio-xtensa.o obj-$(CONFIG_GPIO_ZEVIO) += gpio-zevio.o obj-$(CONFIG_GPIO_ZYNQ) += gpio-zynq.o diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c index c0f718b1231727..e717f8dc39667c 100644 --- a/drivers/gpio/gpio-adp5588.c +++ b/drivers/gpio/gpio-adp5588.c @@ -16,7 +16,7 @@ #include #include -#include +#include #define DRV_NAME "adp5588-gpio" diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index cd23fd727f9528..d4e6ba0301bc31 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -33,9 +33,23 @@ static int arizona_gpio_direction_in(struct gpio_chip *chip, unsigned offset) { struct arizona_gpio *arizona_gpio = gpiochip_get_data(chip); struct arizona *arizona = arizona_gpio->arizona; + bool persistent = gpiochip_line_is_persistent(chip, offset); + bool change; + int ret; - return regmap_update_bits(arizona->regmap, ARIZONA_GPIO1_CTRL + offset, - ARIZONA_GPN_DIR, ARIZONA_GPN_DIR); + ret = regmap_update_bits_check(arizona->regmap, + ARIZONA_GPIO1_CTRL + offset, + ARIZONA_GPN_DIR, ARIZONA_GPN_DIR, + &change); + if (ret < 0) + return ret; + + if (change && persistent) { + pm_runtime_mark_last_busy(chip->parent); + pm_runtime_put_autosuspend(chip->parent); + } + + return 0; } static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset) @@ -85,6 +99,21 @@ static int arizona_gpio_direction_out(struct gpio_chip *chip, { struct arizona_gpio *arizona_gpio = gpiochip_get_data(chip); struct arizona *arizona = arizona_gpio->arizona; + bool persistent = gpiochip_line_is_persistent(chip, offset); + unsigned int val; + int ret; + + ret = regmap_read(arizona->regmap, ARIZONA_GPIO1_CTRL + offset, &val); + if (ret < 0) + return ret; + + if ((val & ARIZONA_GPN_DIR) && persistent) { + ret = pm_runtime_get_sync(chip->parent); + if (ret < 0) { + dev_err(chip->parent, "Failed to resume: %d\n", ret); + return ret; + } + } if (value) value = ARIZONA_GPN_LVL; @@ -158,6 +187,8 @@ static int arizona_gpio_probe(struct platform_device *pdev) else arizona_gpio->gpio_chip.base = -1; + pm_runtime_enable(&pdev->dev); + ret = devm_gpiochip_add_data(&pdev->dev, &arizona_gpio->gpio_chip, arizona_gpio); if (ret < 0) { diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index ccea609676eebf..4ca436e66bdb24 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -646,6 +646,9 @@ static int enable_debounce(struct gpio_chip *chip, unsigned int offset, int rc; int i; + if (!gpio->clk) + return -EINVAL; + rc = usecs_to_cycles(gpio, usecs, &requested_cycles); if (rc < 0) { dev_warn(chip->parent, "Failed to convert %luus to cycles at %luHz: %d\n", diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 2197368cc899d0..e60156ec0c1842 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -90,8 +90,18 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) { int reg; - if (gpio == 94) - return GPIOPANELCTL; + if (gpio >= CRYSTALCOVE_GPIO_NUM) { + /* + * Virtual GPIO called from ACPI, for now we only support + * the panel ctl. + */ + switch (gpio) { + case 0x5e: + return GPIOPANELCTL; + default: + return -EOPNOTSUPP; + } + } if (reg_type == CTRL_IN) { if (gpio < 8) @@ -130,36 +140,36 @@ static void crystalcove_update_irq_ctrl(struct crystalcove_gpio *cg, int gpio) static int crystalcove_gpio_dir_in(struct gpio_chip *chip, unsigned gpio) { struct crystalcove_gpio *cg = gpiochip_get_data(chip); + int reg = to_reg(gpio, CTRL_OUT); - if (gpio > CRYSTALCOVE_VGPIO_NUM) + if (reg < 0) return 0; - return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT), - CTLO_INPUT_SET); + return regmap_write(cg->regmap, reg, CTLO_INPUT_SET); } static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned gpio, int value) { struct crystalcove_gpio *cg = gpiochip_get_data(chip); + int reg = to_reg(gpio, CTRL_OUT); - if (gpio > CRYSTALCOVE_VGPIO_NUM) + if (reg < 0) return 0; - return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT), - CTLO_OUTPUT_SET | value); + return regmap_write(cg->regmap, reg, CTLO_OUTPUT_SET | value); } static int crystalcove_gpio_get(struct gpio_chip *chip, unsigned gpio) { struct crystalcove_gpio *cg = gpiochip_get_data(chip); - int ret; unsigned int val; + int ret, reg = to_reg(gpio, CTRL_IN); - if (gpio > CRYSTALCOVE_VGPIO_NUM) + if (reg < 0) return 0; - ret = regmap_read(cg->regmap, to_reg(gpio, CTRL_IN), &val); + ret = regmap_read(cg->regmap, reg, &val); if (ret) return ret; @@ -170,14 +180,15 @@ static void crystalcove_gpio_set(struct gpio_chip *chip, unsigned gpio, int value) { struct crystalcove_gpio *cg = gpiochip_get_data(chip); + int reg = to_reg(gpio, CTRL_OUT); - if (gpio > CRYSTALCOVE_VGPIO_NUM) + if (reg < 0) return; if (value) - regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 1); + regmap_update_bits(cg->regmap, reg, 1, 1); else - regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 0); + regmap_update_bits(cg->regmap, reg, 1, 0); } static int crystalcove_irq_type(struct irq_data *data, unsigned type) @@ -185,6 +196,9 @@ static int crystalcove_irq_type(struct irq_data *data, unsigned type) struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data)); + if (data->hwirq >= CRYSTALCOVE_GPIO_NUM) + return 0; + switch (type) { case IRQ_TYPE_NONE: cg->intcnt_value = CTLI_INTCNT_DIS; @@ -235,8 +249,10 @@ static void crystalcove_irq_unmask(struct irq_data *data) struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data)); - cg->set_irq_mask = false; - cg->update |= UPDATE_IRQ_MASK; + if (data->hwirq < CRYSTALCOVE_GPIO_NUM) { + cg->set_irq_mask = false; + cg->update |= UPDATE_IRQ_MASK; + } } static void crystalcove_irq_mask(struct irq_data *data) @@ -244,8 +260,10 @@ static void crystalcove_irq_mask(struct irq_data *data) struct crystalcove_gpio *cg = gpiochip_get_data(irq_data_get_irq_chip_data(data)); - cg->set_irq_mask = true; - cg->update |= UPDATE_IRQ_MASK; + if (data->hwirq < CRYSTALCOVE_GPIO_NUM) { + cg->set_irq_mask = true; + cg->update |= UPDATE_IRQ_MASK; + } } static struct irq_chip crystalcove_irqchip = { diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index ac173575d3f69b..65cb359308e3fd 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -437,6 +437,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) { unsigned gpio, bank; int irq; + int ret; struct clk *clk; u32 binten = 0; unsigned ngpio, bank_irq; @@ -480,12 +481,15 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) PTR_ERR(clk)); return PTR_ERR(clk); } - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); + if (ret) + return ret; if (!pdata->gpio_unbanked) { irq = devm_irq_alloc_descs(dev, -1, 0, ngpio, 0); if (irq < 0) { dev_err(dev, "Couldn't allocate IRQ numbers\n"); + clk_disable_unprepare(clk); return irq; } @@ -494,6 +498,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) chips); if (!irq_domain) { dev_err(dev, "Couldn't register an IRQ domain\n"); + clk_disable_unprepare(clk); return -ENODEV; } } @@ -562,8 +567,10 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev) sizeof(struct davinci_gpio_irq_data), GFP_KERNEL); - if (!irqdata) + if (!irqdata) { + clk_disable_unprepare(clk); return -ENOMEM; + } irqdata->regs = g; irqdata->bank_num = bank; diff --git a/drivers/gpio/gpio-ingenic.c b/drivers/gpio/gpio-ingenic.c new file mode 100644 index 00000000000000..254780730b9570 --- /dev/null +++ b/drivers/gpio/gpio-ingenic.c @@ -0,0 +1,394 @@ +/* + * Ingenic JZ47xx GPIO driver + * + * Copyright (c) 2017 Paul Cercueil + * + * License terms: GNU General Public License (GPL) version 2 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define GPIO_PIN 0x00 +#define GPIO_MSK 0x20 + +#define JZ4740_GPIO_DATA 0x10 +#define JZ4740_GPIO_SELECT 0x50 +#define JZ4740_GPIO_DIR 0x60 +#define JZ4740_GPIO_TRIG 0x70 +#define JZ4740_GPIO_FLAG 0x80 + +#define JZ4770_GPIO_INT 0x10 +#define JZ4770_GPIO_PAT1 0x30 +#define JZ4770_GPIO_PAT0 0x40 +#define JZ4770_GPIO_FLAG 0x50 + +#define REG_SET(x) ((x) + 0x4) +#define REG_CLEAR(x) ((x) + 0x8) + +enum jz_version { + ID_JZ4740, + ID_JZ4770, + ID_JZ4780, +}; + +struct ingenic_gpio_chip { + struct regmap *map; + struct gpio_chip gc; + struct irq_chip irq_chip; + unsigned int irq, reg_base; + enum jz_version version; +}; + +static u32 gpio_ingenic_read_reg(struct ingenic_gpio_chip *jzgc, u8 reg) +{ + unsigned int val; + + regmap_read(jzgc->map, jzgc->reg_base + reg, &val); + + return (u32) val; +} + +static void gpio_ingenic_set_bit(struct ingenic_gpio_chip *jzgc, + u8 reg, u8 offset, bool set) +{ + if (set) + reg = REG_SET(reg); + else + reg = REG_CLEAR(reg); + + regmap_write(jzgc->map, jzgc->reg_base + reg, BIT(offset)); +} + +static inline bool gpio_get_value(struct ingenic_gpio_chip *jzgc, u8 offset) +{ + unsigned int val = gpio_ingenic_read_reg(jzgc, GPIO_PIN); + + return !!(val & BIT(offset)); +} + +static void gpio_set_value(struct ingenic_gpio_chip *jzgc, u8 offset, int value) +{ + if (jzgc->version >= ID_JZ4770) + gpio_ingenic_set_bit(jzgc, JZ4770_GPIO_PAT0, offset, !!value); + else + gpio_ingenic_set_bit(jzgc, JZ4740_GPIO_DATA, offset, !!value); +} + +static void irq_set_type(struct ingenic_gpio_chip *jzgc, + u8 offset, unsigned int type) +{ + u8 reg1, reg2; + + if (jzgc->version >= ID_JZ4770) { + reg1 = JZ4770_GPIO_PAT1; + reg2 = JZ4770_GPIO_PAT0; + } else { + reg1 = JZ4740_GPIO_TRIG; + reg2 = JZ4740_GPIO_DIR; + } + + switch (type) { + case IRQ_TYPE_EDGE_RISING: + gpio_ingenic_set_bit(jzgc, reg2, offset, true); + gpio_ingenic_set_bit(jzgc, reg1, offset, true); + break; + case IRQ_TYPE_EDGE_FALLING: + gpio_ingenic_set_bit(jzgc, reg2, offset, false); + gpio_ingenic_set_bit(jzgc, reg1, offset, true); + break; + case IRQ_TYPE_LEVEL_HIGH: + gpio_ingenic_set_bit(jzgc, reg2, offset, true); + gpio_ingenic_set_bit(jzgc, reg1, offset, false); + break; + case IRQ_TYPE_LEVEL_LOW: + default: + gpio_ingenic_set_bit(jzgc, reg2, offset, false); + gpio_ingenic_set_bit(jzgc, reg1, offset, false); + break; + } +} + +static void ingenic_gpio_irq_mask(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + gpio_ingenic_set_bit(jzgc, GPIO_MSK, irqd->hwirq, true); +} + +static void ingenic_gpio_irq_unmask(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + gpio_ingenic_set_bit(jzgc, GPIO_MSK, irqd->hwirq, false); +} + +static void ingenic_gpio_irq_enable(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + int irq = irqd->hwirq; + + if (jzgc->version >= ID_JZ4770) + gpio_ingenic_set_bit(jzgc, JZ4770_GPIO_INT, irq, true); + else + gpio_ingenic_set_bit(jzgc, JZ4740_GPIO_SELECT, irq, true); + + ingenic_gpio_irq_unmask(irqd); +} + +static void ingenic_gpio_irq_disable(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + int irq = irqd->hwirq; + + ingenic_gpio_irq_mask(irqd); + + if (jzgc->version >= ID_JZ4770) + gpio_ingenic_set_bit(jzgc, JZ4770_GPIO_INT, irq, false); + else + gpio_ingenic_set_bit(jzgc, JZ4740_GPIO_SELECT, irq, false); +} + +static void ingenic_gpio_irq_ack(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + int irq = irqd->hwirq; + bool high; + + if (irqd_get_trigger_type(irqd) == IRQ_TYPE_EDGE_BOTH) { + /* + * Switch to an interrupt for the opposite edge to the one that + * triggered the interrupt being ACKed. + */ + high = gpio_get_value(jzgc, irq); + if (high) + irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_FALLING); + else + irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_RISING); + } + + if (jzgc->version >= ID_JZ4770) + gpio_ingenic_set_bit(jzgc, JZ4770_GPIO_FLAG, irq, false); + else + gpio_ingenic_set_bit(jzgc, JZ4740_GPIO_DATA, irq, true); +} + +static int ingenic_gpio_irq_set_type(struct irq_data *irqd, unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + switch (type) { + case IRQ_TYPE_EDGE_BOTH: + case IRQ_TYPE_EDGE_RISING: + case IRQ_TYPE_EDGE_FALLING: + irq_set_handler_locked(irqd, handle_edge_irq); + break; + case IRQ_TYPE_LEVEL_HIGH: + case IRQ_TYPE_LEVEL_LOW: + irq_set_handler_locked(irqd, handle_level_irq); + break; + default: + irq_set_handler_locked(irqd, handle_bad_irq); + } + + if (type == IRQ_TYPE_EDGE_BOTH) { + /* + * The hardware does not support interrupts on both edges. The + * best we can do is to set up a single-edge interrupt and then + * switch to the opposing edge when ACKing the interrupt. + */ + bool high = gpio_get_value(jzgc, irqd->hwirq); + + type = high ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING; + } + + irq_set_type(jzgc, irqd->hwirq, type); + return 0; +} + +static int ingenic_gpio_irq_set_wake(struct irq_data *irqd, unsigned int on) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + return irq_set_irq_wake(jzgc->irq, on); +} + +static void ingenic_gpio_irq_handler(struct irq_desc *desc) +{ + struct gpio_chip *gc = irq_desc_get_handler_data(desc); + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + struct irq_chip *irq_chip = irq_data_get_irq_chip(&desc->irq_data); + unsigned long flag, i; + + chained_irq_enter(irq_chip, desc); + + if (jzgc->version >= ID_JZ4770) + flag = gpio_ingenic_read_reg(jzgc, JZ4770_GPIO_FLAG); + else + flag = gpio_ingenic_read_reg(jzgc, JZ4740_GPIO_FLAG); + + for_each_set_bit(i, &flag, 32) + generic_handle_irq(irq_linear_revmap(gc->irqdomain, i)); + chained_irq_exit(irq_chip, desc); +} + +static void ingenic_gpio_set(struct gpio_chip *gc, + unsigned int offset, int value) +{ + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + gpio_set_value(jzgc, offset, value); +} + +static int ingenic_gpio_get(struct gpio_chip *gc, unsigned int offset) +{ + struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); + + return (int) gpio_get_value(jzgc, offset); +} + +static int ingenic_gpio_direction_input(struct gpio_chip *gc, + unsigned int offset) +{ + return pinctrl_gpio_direction_input(gc->base + offset); +} + +static int ingenic_gpio_direction_output(struct gpio_chip *gc, + unsigned int offset, int value) +{ + ingenic_gpio_set(gc, offset, value); + return pinctrl_gpio_direction_output(gc->base + offset); +} + +static const struct of_device_id ingenic_gpio_of_match[] = { + { .compatible = "ingenic,jz4740-gpio", .data = (void *)ID_JZ4740 }, + { .compatible = "ingenic,jz4770-gpio", .data = (void *)ID_JZ4770 }, + { .compatible = "ingenic,jz4780-gpio", .data = (void *)ID_JZ4780 }, + {}, +}; +MODULE_DEVICE_TABLE(of, ingenic_gpio_of_match); + +static int ingenic_gpio_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct of_device_id *of_id = of_match_device( + ingenic_gpio_of_match, dev); + struct ingenic_gpio_chip *jzgc; + u32 bank; + int err; + + jzgc = devm_kzalloc(dev, sizeof(*jzgc), GFP_KERNEL); + if (!jzgc) + return -ENOMEM; + + jzgc->map = dev_get_drvdata(dev->parent); + if (!jzgc->map) { + dev_err(dev, "Cannot get parent regmap\n"); + return -ENXIO; + } + + err = of_property_read_u32(dev->of_node, "reg", &bank); + if (err) { + dev_err(dev, "Cannot read \"reg\" property: %i\n", err); + return err; + } + + jzgc->reg_base = bank * 0x100; + + jzgc->gc.label = devm_kasprintf(dev, GFP_KERNEL, "GPIO%c", 'A' + bank); + if (!jzgc->gc.label) + return -ENOMEM; + + /* DO NOT EXPAND THIS: FOR BACKWARD GPIO NUMBERSPACE COMPATIBIBILITY + * ONLY: WORK TO TRANSITION CONSUMERS TO USE THE GPIO DESCRIPTOR API IN + * INSTEAD. + */ + jzgc->gc.base = bank * 32; + + jzgc->gc.ngpio = 32; + jzgc->gc.parent = dev; + jzgc->gc.of_node = dev->of_node; + jzgc->gc.owner = THIS_MODULE; + jzgc->version = (enum jz_version)of_id->data; + + jzgc->gc.set = ingenic_gpio_set; + jzgc->gc.get = ingenic_gpio_get; + jzgc->gc.direction_input = ingenic_gpio_direction_input; + jzgc->gc.direction_output = ingenic_gpio_direction_output; + + if (of_property_read_bool(dev->of_node, "gpio-ranges")) { + jzgc->gc.request = gpiochip_generic_request; + jzgc->gc.free = gpiochip_generic_free; + } + + err = devm_gpiochip_add_data(dev, &jzgc->gc, jzgc); + if (err) + return err; + + jzgc->irq = irq_of_parse_and_map(dev->of_node, 0); + if (!jzgc->irq) + return -EINVAL; + + jzgc->irq_chip.name = jzgc->gc.label; + jzgc->irq_chip.irq_enable = ingenic_gpio_irq_enable; + jzgc->irq_chip.irq_disable = ingenic_gpio_irq_disable; + jzgc->irq_chip.irq_unmask = ingenic_gpio_irq_unmask; + jzgc->irq_chip.irq_mask = ingenic_gpio_irq_mask; + jzgc->irq_chip.irq_ack = ingenic_gpio_irq_ack; + jzgc->irq_chip.irq_set_type = ingenic_gpio_irq_set_type; + jzgc->irq_chip.irq_set_wake = ingenic_gpio_irq_set_wake; + jzgc->irq_chip.flags = IRQCHIP_MASK_ON_SUSPEND; + + err = gpiochip_irqchip_add(&jzgc->gc, &jzgc->irq_chip, 0, + handle_level_irq, IRQ_TYPE_NONE); + if (err) + return err; + + gpiochip_set_chained_irqchip(&jzgc->gc, &jzgc->irq_chip, + jzgc->irq, ingenic_gpio_irq_handler); + return 0; +} + +static int ingenic_gpio_remove(struct platform_device *pdev) +{ + return 0; +} + +static struct platform_driver ingenic_gpio_driver = { + .driver = { + .name = "gpio-ingenic", + .of_match_table = of_match_ptr(ingenic_gpio_of_match), + }, + .probe = ingenic_gpio_probe, + .remove = ingenic_gpio_remove, +}; + +static int __init ingenic_gpio_drv_register(void) +{ + return platform_driver_register(&ingenic_gpio_driver); +} +subsys_initcall(ingenic_gpio_drv_register); + +static void __exit ingenic_gpio_drv_unregister(void) +{ + platform_driver_unregister(&ingenic_gpio_driver); +} +module_exit(ingenic_gpio_drv_unregister); + +MODULE_AUTHOR("Paul Cercueil "); +MODULE_DESCRIPTION("Ingenic JZ47xx GPIO driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c index 4ea4c6a1313b13..7f4d26ce5f231a 100644 --- a/drivers/gpio/gpio-max732x.c +++ b/drivers/gpio/gpio-max732x.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c index 78896a869fd9bb..74fdce096c26ed 100644 --- a/drivers/gpio/gpio-ml-ioh.c +++ b/drivers/gpio/gpio-ml-ioh.c @@ -385,14 +385,18 @@ static irqreturn_t ioh_gpio_handler(int irq, void *dev_id) return ret; } -static void ioh_gpio_alloc_generic_chip(struct ioh_gpio *chip, - unsigned int irq_start, unsigned int num) +static int ioh_gpio_alloc_generic_chip(struct ioh_gpio *chip, + unsigned int irq_start, + unsigned int num) { struct irq_chip_generic *gc; struct irq_chip_type *ct; gc = irq_alloc_generic_chip("ioh_gpio", 1, irq_start, chip->base, handle_simple_irq); + if (!gc) + return -ENOMEM; + gc->private = chip; ct = gc->chip_types; @@ -404,6 +408,8 @@ static void ioh_gpio_alloc_generic_chip(struct ioh_gpio *chip, irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE, IRQ_NOREQUEST | IRQ_NOPROBE, 0); + + return 0; } static int ioh_gpio_probe(struct pci_dev *pdev, @@ -468,7 +474,11 @@ static int ioh_gpio_probe(struct pci_dev *pdev, goto err_gpiochip_add; } chip->irq_base = irq_base; - ioh_gpio_alloc_generic_chip(chip, irq_base, num_ports[j]); + + ret = ioh_gpio_alloc_generic_chip(chip, + irq_base, num_ports[j]); + if (ret) + goto err_gpiochip_add; } chip = chip_save; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index c6dadac7059323..ba8d62aa801a87 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -29,8 +29,8 @@ #define GPIO_MOCKUP_MAX_GC 10 enum { - DIR_IN = 0, - DIR_OUT, + GPIO_MOCKUP_DIR_OUT = 0, + GPIO_MOCKUP_DIR_IN = 1, }; /* @@ -41,6 +41,7 @@ enum { struct gpio_mockup_line_status { int dir; bool value; + bool irq_enabled; }; struct gpio_mockup_irq_context { @@ -93,7 +94,7 @@ static int gpio_mockup_dirout(struct gpio_chip *gc, unsigned int offset, struct gpio_mockup_chip *chip = gpiochip_get_data(gc); gpio_mockup_set(gc, offset, value); - chip->lines[offset].dir = DIR_OUT; + chip->lines[offset].dir = GPIO_MOCKUP_DIR_OUT; return 0; } @@ -102,7 +103,7 @@ static int gpio_mockup_dirin(struct gpio_chip *gc, unsigned int offset) { struct gpio_mockup_chip *chip = gpiochip_get_data(gc); - chip->lines[offset].dir = DIR_IN; + chip->lines[offset].dir = GPIO_MOCKUP_DIR_IN; return 0; } @@ -142,12 +143,21 @@ static int gpio_mockup_to_irq(struct gpio_chip *chip, unsigned int offset) return chip->irq_base + offset; } -/* - * While we should generally support irqmask and irqunmask, this driver is - * for testing purposes only so we don't care. - */ -static void gpio_mockup_irqmask(struct irq_data *d) { } -static void gpio_mockup_irqunmask(struct irq_data *d) { } +static void gpio_mockup_irqmask(struct irq_data *data) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct gpio_mockup_chip *chip = gpiochip_get_data(gc); + + chip->lines[data->irq - gc->irq_base].irq_enabled = false; +} + +static void gpio_mockup_irqunmask(struct irq_data *data) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct gpio_mockup_chip *chip = gpiochip_get_data(gc); + + chip->lines[data->irq - gc->irq_base].irq_enabled = true; +} static struct irq_chip gpio_mockup_irqchip = { .name = GPIO_MOCKUP_NAME, @@ -178,6 +188,7 @@ static int gpio_mockup_irqchip_setup(struct device *dev, for (i = 0; i < gc->ngpio; i++) { irq_set_chip(irq_base + i, gc->irqchip); + irq_set_chip_data(irq_base + i, gc); irq_set_handler(irq_base + i, &handle_simple_irq); irq_modify_status(irq_base + i, IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE); @@ -206,6 +217,9 @@ static ssize_t gpio_mockup_event_write(struct file *file, chip = priv->chip; gc = &chip->gc; + if (!chip->lines[priv->offset].irq_enabled) + return size; + if (copy_from_user(&buf, usr_buf, 1)) return -EFAULT; @@ -364,9 +378,6 @@ static int gpio_mockup_probe(struct platform_device *pdev) return ret; } - - dev_info(dev, "gpio<%d..%d> add successful!", - base, base + ngpio); } return 0; diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 19a92efabbef70..3d03740a20e7c5 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -33,21 +33,22 @@ * interrupts. */ +#include +#include #include -#include #include +#include +#include #include -#include +#include #include -#include -#include #include -#include -#include +#include #include -#include #include -#include +#include +#include +#include #include "gpiolib.h" @@ -106,9 +107,8 @@ struct mvebu_pwm { struct mvebu_gpio_chip { struct gpio_chip chip; - spinlock_t lock; - void __iomem *membase; - void __iomem *percpu_membase; + struct regmap *regs; + struct regmap *percpu_regs; int irqbase; struct irq_domain *domain; int soc_variant; @@ -130,92 +130,149 @@ struct mvebu_gpio_chip { * Functions returning addresses of individual registers for a given * GPIO controller. */ -static void __iomem *mvebu_gpioreg_out(struct mvebu_gpio_chip *mvchip) -{ - return mvchip->membase + GPIO_OUT_OFF; -} -static void __iomem *mvebu_gpioreg_blink(struct mvebu_gpio_chip *mvchip) +static void mvebu_gpioreg_edge_cause(struct mvebu_gpio_chip *mvchip, + struct regmap **map, unsigned int *offset) { - return mvchip->membase + GPIO_BLINK_EN_OFF; -} + int cpu; -static void __iomem *mvebu_gpioreg_blink_counter_select(struct mvebu_gpio_chip - *mvchip) -{ - return mvchip->membase + GPIO_BLINK_CNT_SELECT_OFF; + switch (mvchip->soc_variant) { + case MVEBU_GPIO_SOC_VARIANT_ORION: + case MVEBU_GPIO_SOC_VARIANT_MV78200: + *map = mvchip->regs; + *offset = GPIO_EDGE_CAUSE_OFF; + break; + case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: + cpu = smp_processor_id(); + *map = mvchip->percpu_regs; + *offset = GPIO_EDGE_CAUSE_ARMADAXP_OFF(cpu); + break; + default: + BUG(); + } } -static void __iomem *mvebu_gpioreg_io_conf(struct mvebu_gpio_chip *mvchip) +static u32 +mvebu_gpio_read_edge_cause(struct mvebu_gpio_chip *mvchip) { - return mvchip->membase + GPIO_IO_CONF_OFF; -} + struct regmap *map; + unsigned int offset; + u32 val; -static void __iomem *mvebu_gpioreg_in_pol(struct mvebu_gpio_chip *mvchip) -{ - return mvchip->membase + GPIO_IN_POL_OFF; + mvebu_gpioreg_edge_cause(mvchip, &map, &offset); + regmap_read(map, offset, &val); + + return val; } -static void __iomem *mvebu_gpioreg_data_in(struct mvebu_gpio_chip *mvchip) +static void +mvebu_gpio_write_edge_cause(struct mvebu_gpio_chip *mvchip, u32 val) { - return mvchip->membase + GPIO_DATA_IN_OFF; + struct regmap *map; + unsigned int offset; + + mvebu_gpioreg_edge_cause(mvchip, &map, &offset); + regmap_write(map, offset, val); } -static void __iomem *mvebu_gpioreg_edge_cause(struct mvebu_gpio_chip *mvchip) +static inline void +mvebu_gpioreg_edge_mask(struct mvebu_gpio_chip *mvchip, + struct regmap **map, unsigned int *offset) { int cpu; switch (mvchip->soc_variant) { case MVEBU_GPIO_SOC_VARIANT_ORION: + *map = mvchip->regs; + *offset = GPIO_EDGE_MASK_OFF; + break; case MVEBU_GPIO_SOC_VARIANT_MV78200: - return mvchip->membase + GPIO_EDGE_CAUSE_OFF; + cpu = smp_processor_id(); + *map = mvchip->regs; + *offset = GPIO_EDGE_MASK_MV78200_OFF(cpu); + break; case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: cpu = smp_processor_id(); - return mvchip->percpu_membase + - GPIO_EDGE_CAUSE_ARMADAXP_OFF(cpu); + *map = mvchip->percpu_regs; + *offset = GPIO_EDGE_MASK_ARMADAXP_OFF(cpu); + break; default: BUG(); } } -static void __iomem *mvebu_gpioreg_edge_mask(struct mvebu_gpio_chip *mvchip) +static u32 +mvebu_gpio_read_edge_mask(struct mvebu_gpio_chip *mvchip) { - int cpu; + struct regmap *map; + unsigned int offset; + u32 val; - switch (mvchip->soc_variant) { - case MVEBU_GPIO_SOC_VARIANT_ORION: - return mvchip->membase + GPIO_EDGE_MASK_OFF; - case MVEBU_GPIO_SOC_VARIANT_MV78200: - cpu = smp_processor_id(); - return mvchip->membase + GPIO_EDGE_MASK_MV78200_OFF(cpu); - case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: - cpu = smp_processor_id(); - return mvchip->percpu_membase + - GPIO_EDGE_MASK_ARMADAXP_OFF(cpu); - default: - BUG(); - } + mvebu_gpioreg_edge_mask(mvchip, &map, &offset); + regmap_read(map, offset, &val); + + return val; } -static void __iomem *mvebu_gpioreg_level_mask(struct mvebu_gpio_chip *mvchip) +static void +mvebu_gpio_write_edge_mask(struct mvebu_gpio_chip *mvchip, u32 val) +{ + struct regmap *map; + unsigned int offset; + + mvebu_gpioreg_edge_mask(mvchip, &map, &offset); + regmap_write(map, offset, val); +} + +static void +mvebu_gpioreg_level_mask(struct mvebu_gpio_chip *mvchip, + struct regmap **map, unsigned int *offset) { int cpu; switch (mvchip->soc_variant) { case MVEBU_GPIO_SOC_VARIANT_ORION: - return mvchip->membase + GPIO_LEVEL_MASK_OFF; + *map = mvchip->regs; + *offset = GPIO_LEVEL_MASK_OFF; + break; case MVEBU_GPIO_SOC_VARIANT_MV78200: cpu = smp_processor_id(); - return mvchip->membase + GPIO_LEVEL_MASK_MV78200_OFF(cpu); + *map = mvchip->regs; + *offset = GPIO_LEVEL_MASK_MV78200_OFF(cpu); + break; case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: cpu = smp_processor_id(); - return mvchip->percpu_membase + - GPIO_LEVEL_MASK_ARMADAXP_OFF(cpu); + *map = mvchip->percpu_regs; + *offset = GPIO_LEVEL_MASK_ARMADAXP_OFF(cpu); + break; default: BUG(); } } +static u32 +mvebu_gpio_read_level_mask(struct mvebu_gpio_chip *mvchip) +{ + struct regmap *map; + unsigned int offset; + u32 val; + + mvebu_gpioreg_level_mask(mvchip, &map, &offset); + regmap_read(map, offset, &val); + + return val; +} + +static void +mvebu_gpio_write_level_mask(struct mvebu_gpio_chip *mvchip, u32 val) +{ + struct regmap *map; + unsigned int offset; + + mvebu_gpioreg_level_mask(mvchip, &map, &offset); + regmap_write(map, offset, val); +} + /* * Functions returning addresses of individual registers for a given * PWM controller. @@ -236,17 +293,9 @@ static void __iomem *mvebu_pwmreg_blink_off_duration(struct mvebu_pwm *mvpwm) static void mvebu_gpio_set(struct gpio_chip *chip, unsigned int pin, int value) { struct mvebu_gpio_chip *mvchip = gpiochip_get_data(chip); - unsigned long flags; - u32 u; - spin_lock_irqsave(&mvchip->lock, flags); - u = readl_relaxed(mvebu_gpioreg_out(mvchip)); - if (value) - u |= BIT(pin); - else - u &= ~BIT(pin); - writel_relaxed(u, mvebu_gpioreg_out(mvchip)); - spin_unlock_irqrestore(&mvchip->lock, flags); + regmap_update_bits(mvchip->regs, GPIO_OUT_OFF, + BIT(pin), value ? BIT(pin) : 0); } static int mvebu_gpio_get(struct gpio_chip *chip, unsigned int pin) @@ -254,11 +303,16 @@ static int mvebu_gpio_get(struct gpio_chip *chip, unsigned int pin) struct mvebu_gpio_chip *mvchip = gpiochip_get_data(chip); u32 u; - if (readl_relaxed(mvebu_gpioreg_io_conf(mvchip)) & BIT(pin)) { - u = readl_relaxed(mvebu_gpioreg_data_in(mvchip)) ^ - readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); + regmap_read(mvchip->regs, GPIO_IO_CONF_OFF, &u); + + if (u & BIT(pin)) { + u32 data_in, in_pol; + + regmap_read(mvchip->regs, GPIO_DATA_IN_OFF, &data_in); + regmap_read(mvchip->regs, GPIO_IN_POL_OFF, &in_pol); + u = data_in ^ in_pol; } else { - u = readl_relaxed(mvebu_gpioreg_out(mvchip)); + regmap_read(mvchip->regs, GPIO_OUT_OFF, &u); } return (u >> pin) & 1; @@ -268,25 +322,15 @@ static void mvebu_gpio_blink(struct gpio_chip *chip, unsigned int pin, int value) { struct mvebu_gpio_chip *mvchip = gpiochip_get_data(chip); - unsigned long flags; - u32 u; - spin_lock_irqsave(&mvchip->lock, flags); - u = readl_relaxed(mvebu_gpioreg_blink(mvchip)); - if (value) - u |= BIT(pin); - else - u &= ~BIT(pin); - writel_relaxed(u, mvebu_gpioreg_blink(mvchip)); - spin_unlock_irqrestore(&mvchip->lock, flags); + regmap_update_bits(mvchip->regs, GPIO_BLINK_EN_OFF, + BIT(pin), value ? BIT(pin) : 0); } static int mvebu_gpio_direction_input(struct gpio_chip *chip, unsigned int pin) { struct mvebu_gpio_chip *mvchip = gpiochip_get_data(chip); - unsigned long flags; int ret; - u32 u; /* * Check with the pinctrl driver whether this pin is usable as @@ -296,11 +340,8 @@ static int mvebu_gpio_direction_input(struct gpio_chip *chip, unsigned int pin) if (ret) return ret; - spin_lock_irqsave(&mvchip->lock, flags); - u = readl_relaxed(mvebu_gpioreg_io_conf(mvchip)); - u |= BIT(pin); - writel_relaxed(u, mvebu_gpioreg_io_conf(mvchip)); - spin_unlock_irqrestore(&mvchip->lock, flags); + regmap_update_bits(mvchip->regs, GPIO_IO_CONF_OFF, + BIT(pin), 1); return 0; } @@ -309,9 +350,7 @@ static int mvebu_gpio_direction_output(struct gpio_chip *chip, unsigned int pin, int value) { struct mvebu_gpio_chip *mvchip = gpiochip_get_data(chip); - unsigned long flags; int ret; - u32 u; /* * Check with the pinctrl driver whether this pin is usable as @@ -324,11 +363,8 @@ static int mvebu_gpio_direction_output(struct gpio_chip *chip, unsigned int pin, mvebu_gpio_blink(chip, pin, 0); mvebu_gpio_set(chip, pin, value); - spin_lock_irqsave(&mvchip->lock, flags); - u = readl_relaxed(mvebu_gpioreg_io_conf(mvchip)); - u &= ~BIT(pin); - writel_relaxed(u, mvebu_gpioreg_io_conf(mvchip)); - spin_unlock_irqrestore(&mvchip->lock, flags); + regmap_update_bits(mvchip->regs, GPIO_IO_CONF_OFF, + BIT(pin), 0); return 0; } @@ -350,7 +386,7 @@ static void mvebu_gpio_irq_ack(struct irq_data *d) u32 mask = d->mask; irq_gc_lock(gc); - writel_relaxed(~mask, mvebu_gpioreg_edge_cause(mvchip)); + mvebu_gpio_write_edge_cause(mvchip, ~mask); irq_gc_unlock(gc); } @@ -363,8 +399,7 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d) irq_gc_lock(gc); ct->mask_cache_priv &= ~mask; - - writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); + mvebu_gpio_write_edge_mask(mvchip, ct->mask_cache_priv); irq_gc_unlock(gc); } @@ -377,7 +412,7 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d) irq_gc_lock(gc); ct->mask_cache_priv |= mask; - writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); + mvebu_gpio_write_edge_mask(mvchip, ct->mask_cache_priv); irq_gc_unlock(gc); } @@ -390,7 +425,7 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d) irq_gc_lock(gc); ct->mask_cache_priv &= ~mask; - writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); + mvebu_gpio_write_level_mask(mvchip, ct->mask_cache_priv); irq_gc_unlock(gc); } @@ -403,7 +438,7 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d) irq_gc_lock(gc); ct->mask_cache_priv |= mask; - writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); + mvebu_gpio_write_level_mask(mvchip, ct->mask_cache_priv); irq_gc_unlock(gc); } @@ -443,8 +478,8 @@ static int mvebu_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin = d->hwirq; - u = readl_relaxed(mvebu_gpioreg_io_conf(mvchip)) & BIT(pin); - if (!u) + regmap_read(mvchip->regs, GPIO_IO_CONF_OFF, &u); + if ((u & BIT(pin)) == 0) return -EINVAL; type &= IRQ_TYPE_SENSE_MASK; @@ -462,31 +497,30 @@ static int mvebu_gpio_irq_set_type(struct irq_data *d, unsigned int type) switch (type) { case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_LEVEL_HIGH: - u = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); - u &= ~BIT(pin); - writel_relaxed(u, mvebu_gpioreg_in_pol(mvchip)); + regmap_update_bits(mvchip->regs, GPIO_IN_POL_OFF, + BIT(pin), 0); break; case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_LEVEL_LOW: - u = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); - u |= BIT(pin); - writel_relaxed(u, mvebu_gpioreg_in_pol(mvchip)); + regmap_update_bits(mvchip->regs, GPIO_IN_POL_OFF, + BIT(pin), 1); break; case IRQ_TYPE_EDGE_BOTH: { - u32 v; + u32 data_in, in_pol, val; - v = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)) ^ - readl_relaxed(mvebu_gpioreg_data_in(mvchip)); + regmap_read(mvchip->regs, GPIO_IN_POL_OFF, &in_pol); + regmap_read(mvchip->regs, GPIO_DATA_IN_OFF, &data_in); /* * set initial polarity based on current input level */ - u = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); - if (v & BIT(pin)) - u |= BIT(pin); /* falling */ + if ((data_in ^ in_pol) & BIT(pin)) + val = BIT(pin); /* falling */ else - u &= ~BIT(pin); /* rising */ - writel_relaxed(u, mvebu_gpioreg_in_pol(mvchip)); + val = 0; /* raising */ + + regmap_update_bits(mvchip->regs, GPIO_IN_POL_OFF, + BIT(pin), val); break; } } @@ -497,7 +531,7 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc) { struct mvebu_gpio_chip *mvchip = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - u32 cause, type; + u32 cause, type, data_in, level_mask, edge_cause, edge_mask; int i; if (mvchip == NULL) @@ -505,10 +539,12 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc) chained_irq_enter(chip, desc); - cause = readl_relaxed(mvebu_gpioreg_data_in(mvchip)) & - readl_relaxed(mvebu_gpioreg_level_mask(mvchip)); - cause |= readl_relaxed(mvebu_gpioreg_edge_cause(mvchip)) & - readl_relaxed(mvebu_gpioreg_edge_mask(mvchip)); + regmap_read(mvchip->regs, GPIO_DATA_IN_OFF, &data_in); + level_mask = mvebu_gpio_read_level_mask(mvchip); + edge_cause = mvebu_gpio_read_edge_cause(mvchip); + edge_mask = mvebu_gpio_read_edge_mask(mvchip); + + cause = (data_in ^ level_mask) | (edge_cause & edge_mask); for (i = 0; i < mvchip->chip.ngpio; i++) { int irq; @@ -523,9 +559,9 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc) /* Swap polarity (race with GPIO line) */ u32 polarity; - polarity = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); + regmap_read(mvchip->regs, GPIO_IN_POL_OFF, &polarity); polarity ^= BIT(i); - writel_relaxed(polarity, mvebu_gpioreg_in_pol(mvchip)); + regmap_write(mvchip->regs, GPIO_IN_POL_OFF, polarity); } generic_handle_irq(irq); @@ -628,7 +664,7 @@ static void mvebu_pwm_get_state(struct pwm_chip *chip, state->period = 1; } - u = readl_relaxed(mvebu_gpioreg_blink(mvchip)); + regmap_read(mvchip->regs, GPIO_BLINK_EN_OFF, &u); if (u) state->enabled = true; else @@ -691,8 +727,8 @@ static void __maybe_unused mvebu_pwm_suspend(struct mvebu_gpio_chip *mvchip) { struct mvebu_pwm *mvpwm = mvchip->mvpwm; - mvpwm->blink_select = - readl_relaxed(mvebu_gpioreg_blink_counter_select(mvchip)); + regmap_read(mvchip->regs, GPIO_BLINK_CNT_SELECT_OFF, + &mvpwm->blink_select); mvpwm->blink_on_duration = readl_relaxed(mvebu_pwmreg_blink_on_duration(mvpwm)); mvpwm->blink_off_duration = @@ -703,8 +739,8 @@ static void __maybe_unused mvebu_pwm_resume(struct mvebu_gpio_chip *mvchip) { struct mvebu_pwm *mvpwm = mvchip->mvpwm; - writel_relaxed(mvpwm->blink_select, - mvebu_gpioreg_blink_counter_select(mvchip)); + regmap_write(mvchip->regs, GPIO_BLINK_CNT_SELECT_OFF, + mvpwm->blink_select); writel_relaxed(mvpwm->blink_on_duration, mvebu_pwmreg_blink_on_duration(mvpwm)); writel_relaxed(mvpwm->blink_off_duration, @@ -747,7 +783,7 @@ static int mvebu_pwm_probe(struct platform_device *pdev, set = U32_MAX; else return -EINVAL; - writel_relaxed(0, mvebu_gpioreg_blink_counter_select(mvchip)); + regmap_write(mvchip->regs, GPIO_BLINK_CNT_SELECT_OFF, 0); mvpwm = devm_kzalloc(dev, sizeof(struct mvebu_pwm), GFP_KERNEL); if (!mvpwm) @@ -783,14 +819,14 @@ static void mvebu_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) u32 out, io_conf, blink, in_pol, data_in, cause, edg_msk, lvl_msk; int i; - out = readl_relaxed(mvebu_gpioreg_out(mvchip)); - io_conf = readl_relaxed(mvebu_gpioreg_io_conf(mvchip)); - blink = readl_relaxed(mvebu_gpioreg_blink(mvchip)); - in_pol = readl_relaxed(mvebu_gpioreg_in_pol(mvchip)); - data_in = readl_relaxed(mvebu_gpioreg_data_in(mvchip)); - cause = readl_relaxed(mvebu_gpioreg_edge_cause(mvchip)); - edg_msk = readl_relaxed(mvebu_gpioreg_edge_mask(mvchip)); - lvl_msk = readl_relaxed(mvebu_gpioreg_level_mask(mvchip)); + regmap_read(mvchip->regs, GPIO_OUT_OFF, &out); + regmap_read(mvchip->regs, GPIO_IO_CONF_OFF, &io_conf); + regmap_read(mvchip->regs, GPIO_BLINK_EN_OFF, &blink); + regmap_read(mvchip->regs, GPIO_IN_POL_OFF, &in_pol); + regmap_read(mvchip->regs, GPIO_DATA_IN_OFF, &data_in); + cause = mvebu_gpio_read_edge_cause(mvchip); + edg_msk = mvebu_gpio_read_edge_mask(mvchip); + lvl_msk = mvebu_gpio_read_level_mask(mvchip); for (i = 0; i < chip->ngpio; i++) { const char *label; @@ -858,36 +894,36 @@ static int mvebu_gpio_suspend(struct platform_device *pdev, pm_message_t state) struct mvebu_gpio_chip *mvchip = platform_get_drvdata(pdev); int i; - mvchip->out_reg = readl(mvebu_gpioreg_out(mvchip)); - mvchip->io_conf_reg = readl(mvebu_gpioreg_io_conf(mvchip)); - mvchip->blink_en_reg = readl(mvebu_gpioreg_blink(mvchip)); - mvchip->in_pol_reg = readl(mvebu_gpioreg_in_pol(mvchip)); + regmap_read(mvchip->regs, GPIO_OUT_OFF, &mvchip->out_reg); + regmap_read(mvchip->regs, GPIO_IO_CONF_OFF, &mvchip->io_conf_reg); + regmap_read(mvchip->regs, GPIO_BLINK_EN_OFF, &mvchip->blink_en_reg); + regmap_read(mvchip->regs, GPIO_IN_POL_OFF, &mvchip->in_pol_reg); switch (mvchip->soc_variant) { case MVEBU_GPIO_SOC_VARIANT_ORION: - mvchip->edge_mask_regs[0] = - readl(mvchip->membase + GPIO_EDGE_MASK_OFF); - mvchip->level_mask_regs[0] = - readl(mvchip->membase + GPIO_LEVEL_MASK_OFF); + regmap_read(mvchip->regs, GPIO_EDGE_MASK_OFF, + &mvchip->edge_mask_regs[0]); + regmap_read(mvchip->regs, GPIO_LEVEL_MASK_OFF, + &mvchip->level_mask_regs[0]); break; case MVEBU_GPIO_SOC_VARIANT_MV78200: for (i = 0; i < 2; i++) { - mvchip->edge_mask_regs[i] = - readl(mvchip->membase + - GPIO_EDGE_MASK_MV78200_OFF(i)); - mvchip->level_mask_regs[i] = - readl(mvchip->membase + - GPIO_LEVEL_MASK_MV78200_OFF(i)); + regmap_read(mvchip->regs, + GPIO_EDGE_MASK_MV78200_OFF(i), + &mvchip->edge_mask_regs[i]); + regmap_read(mvchip->regs, + GPIO_LEVEL_MASK_MV78200_OFF(i), + &mvchip->level_mask_regs[i]); } break; case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: for (i = 0; i < 4; i++) { - mvchip->edge_mask_regs[i] = - readl(mvchip->membase + - GPIO_EDGE_MASK_ARMADAXP_OFF(i)); - mvchip->level_mask_regs[i] = - readl(mvchip->membase + - GPIO_LEVEL_MASK_ARMADAXP_OFF(i)); + regmap_read(mvchip->regs, + GPIO_EDGE_MASK_ARMADAXP_OFF(i), + &mvchip->edge_mask_regs[i]); + regmap_read(mvchip->regs, + GPIO_LEVEL_MASK_ARMADAXP_OFF(i), + &mvchip->level_mask_regs[i]); } break; default: @@ -905,35 +941,36 @@ static int mvebu_gpio_resume(struct platform_device *pdev) struct mvebu_gpio_chip *mvchip = platform_get_drvdata(pdev); int i; - writel(mvchip->out_reg, mvebu_gpioreg_out(mvchip)); - writel(mvchip->io_conf_reg, mvebu_gpioreg_io_conf(mvchip)); - writel(mvchip->blink_en_reg, mvebu_gpioreg_blink(mvchip)); - writel(mvchip->in_pol_reg, mvebu_gpioreg_in_pol(mvchip)); + regmap_write(mvchip->regs, GPIO_OUT_OFF, mvchip->out_reg); + regmap_write(mvchip->regs, GPIO_IO_CONF_OFF, mvchip->io_conf_reg); + regmap_write(mvchip->regs, GPIO_BLINK_EN_OFF, mvchip->blink_en_reg); + regmap_write(mvchip->regs, GPIO_IN_POL_OFF, mvchip->in_pol_reg); switch (mvchip->soc_variant) { case MVEBU_GPIO_SOC_VARIANT_ORION: - writel(mvchip->edge_mask_regs[0], - mvchip->membase + GPIO_EDGE_MASK_OFF); - writel(mvchip->level_mask_regs[0], - mvchip->membase + GPIO_LEVEL_MASK_OFF); + regmap_write(mvchip->regs, GPIO_EDGE_MASK_OFF, + mvchip->edge_mask_regs[0]); + regmap_write(mvchip->regs, GPIO_LEVEL_MASK_OFF, + mvchip->level_mask_regs[0]); break; case MVEBU_GPIO_SOC_VARIANT_MV78200: for (i = 0; i < 2; i++) { - writel(mvchip->edge_mask_regs[i], - mvchip->membase + GPIO_EDGE_MASK_MV78200_OFF(i)); - writel(mvchip->level_mask_regs[i], - mvchip->membase + - GPIO_LEVEL_MASK_MV78200_OFF(i)); + regmap_write(mvchip->regs, + GPIO_EDGE_MASK_MV78200_OFF(i), + mvchip->edge_mask_regs[i]); + regmap_write(mvchip->regs, + GPIO_LEVEL_MASK_MV78200_OFF(i), + mvchip->level_mask_regs[i]); } break; case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: for (i = 0; i < 4; i++) { - writel(mvchip->edge_mask_regs[i], - mvchip->membase + - GPIO_EDGE_MASK_ARMADAXP_OFF(i)); - writel(mvchip->level_mask_regs[i], - mvchip->membase + - GPIO_LEVEL_MASK_ARMADAXP_OFF(i)); + regmap_write(mvchip->regs, + GPIO_EDGE_MASK_ARMADAXP_OFF(i), + mvchip->edge_mask_regs[i]); + regmap_write(mvchip->regs, + GPIO_LEVEL_MASK_ARMADAXP_OFF(i), + mvchip->level_mask_regs[i]); } break; default: @@ -946,6 +983,13 @@ static int mvebu_gpio_resume(struct platform_device *pdev) return 0; } +static const struct regmap_config mvebu_gpio_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .fast_io = true, +}; + static int mvebu_gpio_probe(struct platform_device *pdev) { struct mvebu_gpio_chip *mvchip; @@ -954,6 +998,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev) struct resource *res; struct irq_chip_generic *gc; struct irq_chip_type *ct; + void __iomem *base; unsigned int ngpios; bool have_irqs; int soc_variant; @@ -1009,11 +1054,15 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip->chip.of_node = np; mvchip->chip.dbg_show = mvebu_gpio_dbg_show; - spin_lock_init(&mvchip->lock); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mvchip->membase = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mvchip->membase)) - return PTR_ERR(mvchip->membase); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + mvchip->regs = devm_regmap_init_mmio(&pdev->dev, base, + &mvebu_gpio_regmap_config); + if (IS_ERR(mvchip->regs)) + return PTR_ERR(mvchip->regs); /* * The Armada XP has a second range of registers for the @@ -1021,10 +1070,15 @@ static int mvebu_gpio_probe(struct platform_device *pdev) */ if (soc_variant == MVEBU_GPIO_SOC_VARIANT_ARMADAXP) { res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - mvchip->percpu_membase = devm_ioremap_resource(&pdev->dev, - res); - if (IS_ERR(mvchip->percpu_membase)) - return PTR_ERR(mvchip->percpu_membase); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + mvchip->percpu_regs = + devm_regmap_init_mmio(&pdev->dev, base, + &mvebu_gpio_regmap_config); + if (IS_ERR(mvchip->percpu_regs)) + return PTR_ERR(mvchip->percpu_regs); } /* @@ -1032,30 +1086,30 @@ static int mvebu_gpio_probe(struct platform_device *pdev) */ switch (soc_variant) { case MVEBU_GPIO_SOC_VARIANT_ORION: - writel_relaxed(0, mvchip->membase + GPIO_EDGE_CAUSE_OFF); - writel_relaxed(0, mvchip->membase + GPIO_EDGE_MASK_OFF); - writel_relaxed(0, mvchip->membase + GPIO_LEVEL_MASK_OFF); + regmap_write(mvchip->regs, GPIO_EDGE_CAUSE_OFF, 0); + regmap_write(mvchip->regs, GPIO_EDGE_MASK_OFF, 0); + regmap_write(mvchip->regs, GPIO_LEVEL_MASK_OFF, 0); break; case MVEBU_GPIO_SOC_VARIANT_MV78200: - writel_relaxed(0, mvchip->membase + GPIO_EDGE_CAUSE_OFF); + regmap_write(mvchip->regs, GPIO_EDGE_CAUSE_OFF, 0); for (cpu = 0; cpu < 2; cpu++) { - writel_relaxed(0, mvchip->membase + - GPIO_EDGE_MASK_MV78200_OFF(cpu)); - writel_relaxed(0, mvchip->membase + - GPIO_LEVEL_MASK_MV78200_OFF(cpu)); + regmap_write(mvchip->regs, + GPIO_EDGE_MASK_MV78200_OFF(cpu), 0); + regmap_write(mvchip->regs, + GPIO_LEVEL_MASK_MV78200_OFF(cpu), 0); } break; case MVEBU_GPIO_SOC_VARIANT_ARMADAXP: - writel_relaxed(0, mvchip->membase + GPIO_EDGE_CAUSE_OFF); - writel_relaxed(0, mvchip->membase + GPIO_EDGE_MASK_OFF); - writel_relaxed(0, mvchip->membase + GPIO_LEVEL_MASK_OFF); + regmap_write(mvchip->regs, GPIO_EDGE_CAUSE_OFF, 0); + regmap_write(mvchip->regs, GPIO_EDGE_MASK_OFF, 0); + regmap_write(mvchip->regs, GPIO_LEVEL_MASK_OFF, 0); for (cpu = 0; cpu < 4; cpu++) { - writel_relaxed(0, mvchip->percpu_membase + - GPIO_EDGE_CAUSE_ARMADAXP_OFF(cpu)); - writel_relaxed(0, mvchip->percpu_membase + - GPIO_EDGE_MASK_ARMADAXP_OFF(cpu)); - writel_relaxed(0, mvchip->percpu_membase + - GPIO_LEVEL_MASK_ARMADAXP_OFF(cpu)); + regmap_write(mvchip->percpu_regs, + GPIO_EDGE_CAUSE_ARMADAXP_OFF(cpu), 0); + regmap_write(mvchip->percpu_regs, + GPIO_EDGE_MASK_ARMADAXP_OFF(cpu), 0); + regmap_write(mvchip->percpu_regs, + GPIO_LEVEL_MASK_ARMADAXP_OFF(cpu), 0); } break; default: diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c index 8ddf9302ce3b07..a4fd78b9c0e4e3 100644 --- a/drivers/gpio/gpio-pcf857x.c +++ b/drivers/gpio/gpio-pcf857x.c @@ -20,7 +20,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c index 71bc6da1133727..f6600f8ada5206 100644 --- a/drivers/gpio/gpio-pch.c +++ b/drivers/gpio/gpio-pch.c @@ -331,14 +331,18 @@ static irqreturn_t pch_gpio_handler(int irq, void *dev_id) return ret; } -static void pch_gpio_alloc_generic_chip(struct pch_gpio *chip, - unsigned int irq_start, unsigned int num) +static int pch_gpio_alloc_generic_chip(struct pch_gpio *chip, + unsigned int irq_start, + unsigned int num) { struct irq_chip_generic *gc; struct irq_chip_type *ct; gc = irq_alloc_generic_chip("pch_gpio", 1, irq_start, chip->base, handle_simple_irq); + if (!gc) + return -ENOMEM; + gc->private = chip; ct = gc->chip_types; @@ -349,6 +353,8 @@ static void pch_gpio_alloc_generic_chip(struct pch_gpio *chip, irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE, IRQ_NOREQUEST | IRQ_NOPROBE, 0); + + return 0; } static int pch_gpio_probe(struct pci_dev *pdev, @@ -425,7 +431,10 @@ static int pch_gpio_probe(struct pci_dev *pdev, goto err_request_irq; } - pch_gpio_alloc_generic_chip(chip, irq_base, gpio_pins[chip->ioh]); + ret = pch_gpio_alloc_generic_chip(chip, irq_base, + gpio_pins[chip->ioh]); + if (ret) + goto err_request_irq; end: return 0; diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c index 39df0620fa38d1..9e705162da8d73 100644 --- a/drivers/gpio/gpio-sta2x11.c +++ b/drivers/gpio/gpio-sta2x11.c @@ -320,13 +320,16 @@ static irqreturn_t gsta_gpio_handler(int irq, void *dev_id) return ret; } -static void gsta_alloc_irq_chip(struct gsta_gpio *chip) +static int gsta_alloc_irq_chip(struct gsta_gpio *chip) { struct irq_chip_generic *gc; struct irq_chip_type *ct; gc = irq_alloc_generic_chip(KBUILD_MODNAME, 1, chip->irq_base, chip->reg_base, handle_simple_irq); + if (!gc) + return -ENOMEM; + gc->private = chip; ct = gc->chip_types; @@ -350,6 +353,8 @@ static void gsta_alloc_irq_chip(struct gsta_gpio *chip) } gc->irq_cnt = i - gc->irq_base; } + + return 0; } /* The platform device used here is instantiated by the MFD device */ @@ -400,7 +405,10 @@ static int gsta_probe(struct platform_device *dev) return err; } chip->irq_base = err; - gsta_alloc_irq_chip(chip); + + err = gsta_alloc_irq_chip(chip); + if (err) + return err; err = devm_request_irq(&dev->dev, pdev->irq, gsta_gpio_handler, IRQF_SHARED, KBUILD_MODNAME, chip); diff --git a/drivers/gpio/gpio-xra1403.c b/drivers/gpio/gpio-xra1403.c new file mode 100644 index 00000000000000..0230e4b7a2fb48 --- /dev/null +++ b/drivers/gpio/gpio-xra1403.c @@ -0,0 +1,237 @@ +/* + * GPIO driver for EXAR XRA1403 16-bit GPIO expander + * + * Copyright (c) 2017, General Electric Company + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* XRA1403 registers */ +#define XRA_GSR 0x00 /* GPIO State */ +#define XRA_OCR 0x02 /* Output Control */ +#define XRA_PIR 0x04 /* Input Polarity Inversion */ +#define XRA_GCR 0x06 /* GPIO Configuration */ +#define XRA_PUR 0x08 /* Input Internal Pull-up Resistor Enable/Disable */ +#define XRA_IER 0x0A /* Input Interrupt Enable */ +#define XRA_TSCR 0x0C /* Output Three-State Control */ +#define XRA_ISR 0x0E /* Input Interrupt Status */ +#define XRA_REIR 0x10 /* Input Rising Edge Interrupt Enable */ +#define XRA_FEIR 0x12 /* Input Falling Edge Interrupt Enable */ +#define XRA_IFR 0x14 /* Input Filter Enable/Disable */ + +struct xra1403 { + struct gpio_chip chip; + struct regmap *regmap; +}; + +static const struct regmap_config xra1403_regmap_cfg = { + .reg_bits = 7, + .pad_bits = 1, + .val_bits = 8, + + .max_register = XRA_IFR | 0x01, +}; + +static unsigned int to_reg(unsigned int reg, unsigned int offset) +{ + return reg + (offset > 7); +} + +static int xra1403_direction_input(struct gpio_chip *chip, unsigned int offset) +{ + struct xra1403 *xra = gpiochip_get_data(chip); + + return regmap_update_bits(xra->regmap, to_reg(XRA_GCR, offset), + BIT(offset % 8), BIT(offset % 8)); +} + +static int xra1403_direction_output(struct gpio_chip *chip, unsigned int offset, + int value) +{ + int ret; + struct xra1403 *xra = gpiochip_get_data(chip); + + ret = regmap_update_bits(xra->regmap, to_reg(XRA_GCR, offset), + BIT(offset % 8), 0); + if (ret) + return ret; + + ret = regmap_update_bits(xra->regmap, to_reg(XRA_OCR, offset), + BIT(offset % 8), value ? BIT(offset % 8) : 0); + + return ret; +} + +static int xra1403_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + int ret; + unsigned int val; + struct xra1403 *xra = gpiochip_get_data(chip); + + ret = regmap_read(xra->regmap, to_reg(XRA_GCR, offset), &val); + if (ret) + return ret; + + return !!(val & BIT(offset % 8)); +} + +static int xra1403_get(struct gpio_chip *chip, unsigned int offset) +{ + int ret; + unsigned int val; + struct xra1403 *xra = gpiochip_get_data(chip); + + ret = regmap_read(xra->regmap, to_reg(XRA_GSR, offset), &val); + if (ret) + return ret; + + return !!(val & BIT(offset % 8)); +} + +static void xra1403_set(struct gpio_chip *chip, unsigned int offset, int value) +{ + int ret; + struct xra1403 *xra = gpiochip_get_data(chip); + + ret = regmap_update_bits(xra->regmap, to_reg(XRA_OCR, offset), + BIT(offset % 8), value ? BIT(offset % 8) : 0); + if (ret) + dev_err(chip->parent, "Failed to set pin: %d, ret: %d\n", + offset, ret); +} + +#ifdef CONFIG_DEBUG_FS +static void xra1403_dbg_show(struct seq_file *s, struct gpio_chip *chip) +{ + int reg; + struct xra1403 *xra = gpiochip_get_data(chip); + int value[xra1403_regmap_cfg.max_register]; + int i; + unsigned int gcr; + unsigned int gsr; + + seq_puts(s, "xra reg:"); + for (reg = 0; reg <= xra1403_regmap_cfg.max_register; reg++) + seq_printf(s, " %2.2x", reg); + seq_puts(s, "\n value:"); + for (reg = 0; reg < xra1403_regmap_cfg.max_register; reg++) { + regmap_read(xra->regmap, reg, &value[reg]); + seq_printf(s, " %2.2x", value[reg]); + } + seq_puts(s, "\n"); + + gcr = value[XRA_GCR + 1] << 8 | value[XRA_GCR]; + gsr = value[XRA_GSR + 1] << 8 | value[XRA_GSR]; + for (i = 0; i < chip->ngpio; i++) { + const char *label = gpiochip_is_requested(chip, i); + + if (!label) + continue; + + seq_printf(s, " gpio-%-3d (%-12s) %s %s\n", + chip->base + i, label, + (gcr & BIT(i)) ? "in" : "out", + (gsr & BIT(i)) ? "hi" : "lo"); + } +} +#else +#define xra1403_dbg_show NULL +#endif + +static int xra1403_probe(struct spi_device *spi) +{ + struct xra1403 *xra; + struct gpio_desc *reset_gpio; + int ret; + + xra = devm_kzalloc(&spi->dev, sizeof(*xra), GFP_KERNEL); + if (!xra) + return -ENOMEM; + + /* bring the chip out of reset if reset pin is provided*/ + reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(reset_gpio)) + dev_warn(&spi->dev, "Could not get reset-gpios\n"); + + xra->chip.direction_input = xra1403_direction_input; + xra->chip.direction_output = xra1403_direction_output; + xra->chip.get_direction = xra1403_get_direction; + xra->chip.get = xra1403_get; + xra->chip.set = xra1403_set; + + xra->chip.dbg_show = xra1403_dbg_show; + + xra->chip.ngpio = 16; + xra->chip.label = "xra1403"; + + xra->chip.base = -1; + xra->chip.can_sleep = true; + xra->chip.parent = &spi->dev; + xra->chip.owner = THIS_MODULE; + + xra->regmap = devm_regmap_init_spi(spi, &xra1403_regmap_cfg); + if (IS_ERR(xra->regmap)) { + ret = PTR_ERR(xra->regmap); + dev_err(&spi->dev, "Failed to allocate regmap: %d\n", ret); + return ret; + } + + ret = devm_gpiochip_add_data(&spi->dev, &xra->chip, xra); + if (ret < 0) { + dev_err(&spi->dev, "Unable to register gpiochip\n"); + return ret; + } + + spi_set_drvdata(spi, xra); + + return 0; +} + +static const struct spi_device_id xra1403_ids[] = { + { "xra1403" }, + {}, +}; +MODULE_DEVICE_TABLE(spi, xra1403_ids); + +static const struct of_device_id xra1403_spi_of_match[] = { + { .compatible = "exar,xra1403" }, + {}, +}; +MODULE_DEVICE_TABLE(of, xra1403_spi_of_match); + +static struct spi_driver xra1403_driver = { + .probe = xra1403_probe, + .id_table = xra1403_ids, + .driver = { + .name = "xra1403", + .of_match_table = of_match_ptr(xra1403_spi_of_match), + }, +}; + +module_spi_driver(xra1403_driver); + +MODULE_AUTHOR("Nandor Han "); +MODULE_AUTHOR("Semi Malinen "); +MODULE_DESCRIPTION("GPIO expander driver for EXAR XRA1403"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index 6b4d10d6e10f6c..ed87c9a6e0e69b 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -651,9 +651,8 @@ static const struct zynq_platform_data zynq_gpio_def = { }; static const struct of_device_id zynq_gpio_of_match[] = { - { .compatible = "xlnx,zynq-gpio-1.0", .data = (void *)&zynq_gpio_def }, - { .compatible = "xlnx,zynqmp-gpio-1.0", - .data = (void *)&zynqmp_gpio_def }, + { .compatible = "xlnx,zynq-gpio-1.0", .data = &zynq_gpio_def }, + { .compatible = "xlnx,zynqmp-gpio-1.0", .data = &zynqmp_gpio_def }, { /* end of table */ } }; MODULE_DEVICE_TABLE(of, zynq_gpio_of_match); diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 2185232da823e6..6bea176b066c4e 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -165,6 +165,23 @@ static void acpi_gpio_chip_dh(acpi_handle handle, void *data) /* The address of this function is used as a key. */ } +bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + struct acpi_resource_gpio *gpio; + + if (ares->type != ACPI_RESOURCE_TYPE_GPIO) + return false; + + gpio = &ares->data.gpio; + if (gpio->connection_type != ACPI_RESOURCE_GPIO_TYPE_INT) + return false; + + *agpio = gpio; + return true; +} +EXPORT_SYMBOL_GPL(acpi_gpio_get_irq_resource); + static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, void *context) { @@ -178,11 +195,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, unsigned long irqflags; int ret, pin, irq; - if (ares->type != ACPI_RESOURCE_TYPE_GPIO) - return AE_OK; - - agpio = &ares->data.gpio; - if (agpio->connection_type != ACPI_RESOURCE_GPIO_TYPE_INT) + if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; handle = ACPI_HANDLE(chip->parent); @@ -423,6 +436,59 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev, return false; } +static enum gpiod_flags +acpi_gpio_to_gpiod_flags(const struct acpi_resource_gpio *agpio) +{ + bool pull_up = agpio->pin_config == ACPI_PIN_CONFIG_PULLUP; + + switch (agpio->io_restriction) { + case ACPI_IO_RESTRICT_INPUT: + return GPIOD_IN; + case ACPI_IO_RESTRICT_OUTPUT: + /* + * ACPI GPIO resources don't contain an initial value for the + * GPIO. Therefore we deduce that value from the pull field + * instead. If the pin is pulled up we assume default to be + * high, otherwise low. + */ + return pull_up ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; + default: + /* + * Assume that the BIOS has configured the direction and pull + * accordingly. + */ + return GPIOD_ASIS; + } +} + +int +acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update) +{ + int ret = 0; + + /* + * Check if the BIOS has IoRestriction with explicitly set direction + * and update @flags accordingly. Otherwise use whatever caller asked + * for. + */ + if (update & GPIOD_FLAGS_BIT_DIR_SET) { + enum gpiod_flags diff = *flags ^ update; + + /* + * Check if caller supplied incompatible GPIO initialization + * flags. + * + * Return %-EINVAL to notify that firmware has different + * settings and we are going to use them. + */ + if (((*flags & GPIOD_FLAGS_BIT_DIR_SET) && (diff & GPIOD_FLAGS_BIT_DIR_OUT)) || + ((*flags & GPIOD_FLAGS_BIT_DIR_OUT) && (diff & GPIOD_FLAGS_BIT_DIR_VAL))) + ret = -EINVAL; + *flags = update; + } + return ret; +} + struct acpi_gpio_lookup { struct acpi_gpio_info info; int index; @@ -460,8 +526,11 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data) * - ACPI_ACTIVE_HIGH == GPIO_ACTIVE_HIGH */ if (lookup->info.gpioint) { + lookup->info.flags = GPIOD_IN; lookup->info.polarity = agpio->polarity; lookup->info.triggering = agpio->triggering; + } else { + lookup->info.flags = acpi_gpio_to_gpiod_flags(agpio); } } @@ -588,18 +657,19 @@ static struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev, struct gpio_desc *acpi_find_gpio(struct device *dev, const char *con_id, unsigned int idx, - enum gpiod_flags flags, + enum gpiod_flags *dflags, enum gpio_lookup_flags *lookupflags) { struct acpi_device *adev = ACPI_COMPANION(dev); struct acpi_gpio_info info; struct gpio_desc *desc; char propname[32]; + int err; int i; /* Try first from _DSD */ for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { - if (con_id && strcmp(con_id, "gpios")) { + if (con_id) { snprintf(propname, sizeof(propname), "%s-%s", con_id, gpio_suffixes[i]); } else { @@ -622,17 +692,21 @@ struct gpio_desc *acpi_find_gpio(struct device *dev, desc = acpi_get_gpiod_by_index(adev, NULL, idx, &info); if (IS_ERR(desc)) return desc; + } - if ((flags == GPIOD_OUT_LOW || flags == GPIOD_OUT_HIGH) && - info.gpioint) { - dev_dbg(dev, "refusing GpioInt() entry when doing GPIOD_OUT_* lookup\n"); - return ERR_PTR(-ENOENT); - } + if (info.gpioint && + (*dflags == GPIOD_OUT_LOW || *dflags == GPIOD_OUT_HIGH)) { + dev_dbg(dev, "refusing GpioInt() entry when doing GPIOD_OUT_* lookup\n"); + return ERR_PTR(-ENOENT); } if (info.polarity == GPIO_ACTIVE_LOW) *lookupflags |= GPIO_ACTIVE_LOW; + err = acpi_gpio_update_gpiod_flags(dflags, info.flags); + if (err) + dev_dbg(dev, "Override GPIO initialization flags\n"); + return desc; } @@ -686,12 +760,16 @@ struct gpio_desc *acpi_node_get_gpiod(struct fwnode_handle *fwnode, * used to translate from the GPIO offset in the resource to the Linux IRQ * number. * + * The function is idempotent, though each time it runs it will configure GPIO + * pin direction according to the flags in GpioInt resource. + * * Return: Linux IRQ number (>%0) on success, negative errno on failure. */ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { int idx, i; unsigned int irq_flags; + int ret; for (i = 0, idx = 0; idx <= index; i++) { struct acpi_gpio_info info; @@ -704,6 +782,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) return PTR_ERR(desc); if (info.gpioint && idx++ == index) { + char label[32]; int irq; if (IS_ERR(desc)) @@ -713,6 +792,11 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) if (irq < 0) return irq; + snprintf(label, sizeof(label), "GpioInt() %d", index); + ret = gpiod_configure_flags(desc, label, 0, info.flags); + if (ret < 0) + return ret; + irq_flags = acpi_dev_get_irq_type(info.triggering, info.polarity); @@ -740,7 +824,6 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, struct acpi_resource *ares; int pin_index = (int)address; acpi_status status; - bool pull_up; int length; int i; @@ -755,7 +838,6 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, } agpio = &ares->data.gpio; - pull_up = agpio->pin_config == ACPI_PIN_CONFIG_PULLUP; if (WARN_ON(agpio->io_restriction == ACPI_IO_RESTRICT_INPUT && function == ACPI_WRITE)) { @@ -806,35 +888,23 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, } if (!found) { - desc = gpiochip_request_own_desc(chip, pin, - "ACPI:OpRegion"); + enum gpiod_flags flags = acpi_gpio_to_gpiod_flags(agpio); + const char *label = "ACPI:OpRegion"; + int err; + + desc = gpiochip_request_own_desc(chip, pin, label); if (IS_ERR(desc)) { status = AE_ERROR; mutex_unlock(&achip->conn_lock); goto out; } - switch (agpio->io_restriction) { - case ACPI_IO_RESTRICT_INPUT: - gpiod_direction_input(desc); - break; - case ACPI_IO_RESTRICT_OUTPUT: - /* - * ACPI GPIO resources don't contain an - * initial value for the GPIO. Therefore we - * deduce that value from the pull field - * instead. If the pin is pulled up we - * assume default to be high, otherwise - * low. - */ - gpiod_direction_output(desc, pull_up); - break; - default: - /* - * Assume that the BIOS has configured the - * direction and pull accordingly. - */ - break; + err = gpiod_configure_flags(desc, label, 0, flags); + if (err < 0) { + status = AE_NOT_CONFIGURED; + gpiochip_free_own_desc(desc); + mutex_unlock(&achip->conn_lock); + goto out; } conn = kzalloc(sizeof(*conn), GFP_KERNEL); @@ -1089,7 +1159,7 @@ int acpi_gpio_count(struct device *dev, const char *con_id) /* Try first from _DSD */ for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { - if (con_id && strcmp(con_id, "gpios")) + if (con_id) snprintf(propname, sizeof(propname), "%s-%s", con_id, gpio_suffixes[i]); else @@ -1119,6 +1189,9 @@ int acpi_gpio_count(struct device *dev, const char *con_id) struct list_head resource_list; unsigned int crs_count = 0; + if (!acpi_can_fallback_to_crs(adev, con_id)) + return count; + INIT_LIST_HEAD(&resource_list); acpi_dev_get_resources(adev, &resource_list, acpi_find_gpio_count, &crs_count); @@ -1129,45 +1202,11 @@ int acpi_gpio_count(struct device *dev, const char *con_id) return count ? count : -ENOENT; } -struct acpi_crs_lookup { - struct list_head node; - struct acpi_device *adev; - const char *con_id; -}; - -static DEFINE_MUTEX(acpi_crs_lookup_lock); -static LIST_HEAD(acpi_crs_lookup_list); - bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) { - struct acpi_crs_lookup *l, *lookup = NULL; - /* Never allow fallback if the device has properties */ if (adev->data.properties || adev->driver_gpios) return false; - mutex_lock(&acpi_crs_lookup_lock); - - list_for_each_entry(l, &acpi_crs_lookup_list, node) { - if (l->adev == adev) { - lookup = l; - break; - } - } - - if (!lookup) { - lookup = kmalloc(sizeof(*lookup), GFP_KERNEL); - if (lookup) { - lookup->adev = adev; - lookup->con_id = kstrdup(con_id, GFP_KERNEL); - list_add_tail(&lookup->node, &acpi_crs_lookup_list); - } - } - - mutex_unlock(&acpi_crs_lookup_lock); - - return lookup && - ((!lookup->con_id && !con_id) || - (lookup->con_id && con_id && - strcmp(lookup->con_id, con_id) == 0)); + return con_id == NULL; } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index b13b7c7c335f41..e2abf0eabaf880 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -153,6 +153,9 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, *flags |= GPIO_OPEN_SOURCE; } + if (of_flags & OF_GPIO_SLEEP_MAY_LOOSE_VALUE) + *flags |= GPIO_SLEEP_MAY_LOOSE_VALUE; + return desc; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 5db44139cef8ca..62ffb4e293d212 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1,4 +1,4 @@ -#include +#include #include #include #include @@ -1471,8 +1471,6 @@ static struct gpio_chip *find_chip_by_name(const char *name) static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip) { - int i; - if (!gpiochip->irq_need_valid_mask) return 0; @@ -1482,8 +1480,7 @@ static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip) return -ENOMEM; /* Assume by default all GPIOs are valid */ - for (i = 0; i < gpiochip->ngpio; i++) - set_bit(i, gpiochip->irq_valid_mask); + bitmap_fill(gpiochip->irq_valid_mask, gpiochip->ngpio); return 0; } @@ -2869,6 +2866,16 @@ bool gpiochip_line_is_open_source(struct gpio_chip *chip, unsigned int offset) } EXPORT_SYMBOL_GPL(gpiochip_line_is_open_source); +bool gpiochip_line_is_persistent(struct gpio_chip *chip, unsigned int offset) +{ + if (offset >= chip->ngpio) + return false; + + return !test_bit(FLAG_SLEEP_MAY_LOOSE_VALUE, + &chip->gpiodev->descs[offset].flags); +} +EXPORT_SYMBOL_GPL(gpiochip_line_is_persistent); + /** * gpiod_get_raw_value_cansleep() - return a gpio's raw value * @desc: gpio whose value will be returned @@ -3008,6 +3015,7 @@ void gpiod_add_lookup_table(struct gpiod_lookup_table *table) mutex_unlock(&gpio_lookup_lock); } +EXPORT_SYMBOL_GPL(gpiod_add_lookup_table); /** * gpiod_remove_lookup_table() - unregister GPIO device consumers @@ -3021,6 +3029,7 @@ void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) mutex_unlock(&gpio_lookup_lock); } +EXPORT_SYMBOL_GPL(gpiod_remove_lookup_table); static struct gpiod_lookup_table *gpiod_find_lookup_table(struct device *dev) { @@ -3212,7 +3221,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_optional); * requested function and/or index, or another IS_ERR() code if an error * occurred while trying to acquire the GPIO. */ -static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, +int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, unsigned long lflags, enum gpiod_flags dflags) { int status; @@ -3223,6 +3232,8 @@ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, set_bit(FLAG_OPEN_DRAIN, &desc->flags); if (lflags & GPIO_OPEN_SOURCE) set_bit(FLAG_OPEN_SOURCE, &desc->flags); + if (lflags & GPIO_SLEEP_MAY_LOOSE_VALUE) + set_bit(FLAG_SLEEP_MAY_LOOSE_VALUE, &desc->flags); /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { @@ -3272,7 +3283,7 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, desc = of_find_gpio(dev, con_id, idx, &lookupflags); } else if (ACPI_COMPANION(dev)) { dev_dbg(dev, "using ACPI for GPIO lookup\n"); - desc = acpi_find_gpio(dev, con_id, idx, flags, &lookupflags); + desc = acpi_find_gpio(dev, con_id, idx, &flags, &lookupflags); } } @@ -3353,8 +3364,12 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, struct acpi_gpio_info info; desc = acpi_node_get_gpiod(fwnode, propname, index, &info); - if (!IS_ERR(desc)) + if (!IS_ERR(desc)) { active_low = info.polarity == GPIO_ACTIVE_LOW; + ret = acpi_gpio_update_gpiod_flags(&dflags, info.flags); + if (ret) + pr_debug("Override GPIO initialization flags\n"); + } } if (IS_ERR(desc)) diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 2495b7ee1b4269..a8be286eff86f6 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -75,11 +75,13 @@ struct gpio_device { /** * struct acpi_gpio_info - ACPI GPIO specific information + * @flags: GPIO initialization flags * @gpioint: if %true this GPIO is of type GpioInt otherwise type is GpioIo * @polarity: interrupt polarity as provided by ACPI * @triggering: triggering type as provided by ACPI */ struct acpi_gpio_info { + enum gpiod_flags flags; bool gpioint; int polarity; int triggering; @@ -121,10 +123,13 @@ void acpi_gpiochip_remove(struct gpio_chip *chip); void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); void acpi_gpiochip_free_interrupts(struct gpio_chip *chip); +int acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, + enum gpiod_flags update); + struct gpio_desc *acpi_find_gpio(struct device *dev, const char *con_id, unsigned int idx, - enum gpiod_flags flags, + enum gpiod_flags *dflags, enum gpio_lookup_flags *lookupflags); struct gpio_desc *acpi_node_get_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, @@ -143,9 +148,15 @@ acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { } +static inline int +acpi_gpio_update_gpiod_flags(enum gpiod_flags *flags, enum gpiod_flags update) +{ + return 0; +} + static inline struct gpio_desc * acpi_find_gpio(struct device *dev, const char *con_id, - unsigned int idx, enum gpiod_flags flags, + unsigned int idx, enum gpiod_flags *dflags, enum gpio_lookup_flags *lookupflags) { return ERR_PTR(-ENOENT); @@ -190,6 +201,7 @@ struct gpio_desc { #define FLAG_OPEN_SOURCE 8 /* Gpio is open source type */ #define FLAG_USED_AS_IRQ 9 /* GPIO is connected to an IRQ */ #define FLAG_IS_HOGGED 11 /* GPIO is hogged */ +#define FLAG_SLEEP_MAY_LOOSE_VALUE 12 /* GPIO may loose value in sleep */ /* Connection label */ const char *label; @@ -199,6 +211,8 @@ struct gpio_desc { int gpiod_request(struct gpio_desc *desc, const char *label); void gpiod_free(struct gpio_desc *desc); +int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, + unsigned long lflags, enum gpiod_flags dflags); int gpiod_hog(struct gpio_desc *desc, const char *name, unsigned long lflags, enum gpiod_flags dflags); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 78d7fc0ebb57e6..83cb2a88c204f7 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -246,6 +246,8 @@ source "drivers/gpu/drm/fsl-dcu/Kconfig" source "drivers/gpu/drm/tegra/Kconfig" +source "drivers/gpu/drm/stm/Kconfig" + source "drivers/gpu/drm/panel/Kconfig" source "drivers/gpu/drm/bridge/Kconfig" @@ -274,6 +276,8 @@ source "drivers/gpu/drm/meson/Kconfig" source "drivers/gpu/drm/tinydrm/Kconfig" +source "drivers/gpu/drm/pl111/Kconfig" + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 59f0f9b696eb8f..c156fecfb3624e 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_DRM_BOCHS) += bochs/ obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio/ obj-$(CONFIG_DRM_MSM) += msm/ obj-$(CONFIG_DRM_TEGRA) += tegra/ +obj-$(CONFIG_DRM_STM) += stm/ obj-$(CONFIG_DRM_STI) += sti/ obj-$(CONFIG_DRM_IMX) += imx/ obj-$(CONFIG_DRM_MEDIATEK) += mediatek/ @@ -96,3 +97,4 @@ obj-y += hisilicon/ obj-$(CONFIG_DRM_ZTE) += zte/ obj-$(CONFIG_DRM_MXSFB) += mxsfb/ obj-$(CONFIG_DRM_TINYDRM) += tinydrm/ +obj-$(CONFIG_DRM_PL111) += pl111/ diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 660786aba7d222..20bde726419ee2 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -4,7 +4,7 @@ FULL_AMD_PATH=$(src)/.. -ccflags-y := -Iinclude/drm -I$(FULL_AMD_PATH)/include/asic_reg \ +ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \ -I$(FULL_AMD_PATH)/include \ -I$(FULL_AMD_PATH)/amdgpu \ -I$(FULL_AMD_PATH)/scheduler \ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 833c3c16501a02..77ff68f9932b92 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -36,11 +36,11 @@ #include #include -#include -#include -#include -#include -#include +#include +#include +#include +#include +#include #include #include @@ -1912,10 +1912,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon); u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe); int amdgpu_enable_vblank_kms(struct drm_device *dev, unsigned int pipe); void amdgpu_disable_vblank_kms(struct drm_device *dev, unsigned int pipe); -int amdgpu_get_vblank_timestamp_kms(struct drm_device *dev, unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags); long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index a6649874e6ce95..9f0247cdda5e69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -96,7 +96,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, int r; unsigned long total_size = 0; - array = drm_malloc_ab(num_entries, sizeof(struct amdgpu_bo_list_entry)); + array = kvmalloc_array(num_entries, sizeof(struct amdgpu_bo_list_entry), GFP_KERNEL); if (!array) return -ENOMEM; memset(array, 0, num_entries * sizeof(struct amdgpu_bo_list_entry)); @@ -148,7 +148,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, for (i = 0; i < list->num_entries; ++i) amdgpu_bo_unref(&list->array[i].robj); - drm_free_large(list->array); + kvfree(list->array); list->gds_obj = gds_obj; list->gws_obj = gws_obj; @@ -163,7 +163,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, error_free: while (i--) amdgpu_bo_unref(&array[i].robj); - drm_free_large(array); + kvfree(array); return r; } @@ -224,7 +224,7 @@ void amdgpu_bo_list_free(struct amdgpu_bo_list *list) amdgpu_bo_unref(&list->array[i].robj); mutex_destroy(&list->lock); - drm_free_large(list->array); + kvfree(list->array); kfree(list); } @@ -244,8 +244,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, int r; - info = drm_malloc_ab(args->in.bo_number, - sizeof(struct drm_amdgpu_bo_list_entry)); + info = kvmalloc_array(args->in.bo_number, + sizeof(struct drm_amdgpu_bo_list_entry), GFP_KERNEL); if (!info) return -ENOMEM; @@ -311,11 +311,11 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, memset(args, 0, sizeof(*args)); args->out.list_handle = handle; - drm_free_large(info); + kvfree(info); return 0; error_free: - drm_free_large(info); + kvfree(info); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4e6b9501ab0aac..5b3e0f63a1151f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -194,7 +194,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) size = p->chunks[i].length_dw; cdata = (void __user *)(uintptr_t)user_chunk.chunk_data; - p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t)); + p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), GFP_KERNEL); if (p->chunks[i].kdata == NULL) { ret = -ENOMEM; i--; @@ -247,7 +247,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) i = p->nchunks - 1; free_partial_kdata: for (; i >= 0; i--) - drm_free_large(p->chunks[i].kdata); + kvfree(p->chunks[i].kdata); kfree(p->chunks); p->chunks = NULL; p->nchunks = 0; @@ -505,7 +505,7 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p, return r; if (binding_userptr) { - drm_free_large(lobj->user_pages); + kvfree(lobj->user_pages); lobj->user_pages = NULL; } } @@ -571,7 +571,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, release_pages(e->user_pages, e->robj->tbo.ttm->num_pages, false); - drm_free_large(e->user_pages); + kvfree(e->user_pages); e->user_pages = NULL; } @@ -601,8 +601,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, list_for_each_entry(e, &need_pages, tv.head) { struct ttm_tt *ttm = e->robj->tbo.ttm; - e->user_pages = drm_calloc_large(ttm->num_pages, - sizeof(struct page*)); + e->user_pages = kvmalloc_array(ttm->num_pages, + sizeof(struct page*), + GFP_KERNEL | __GFP_ZERO); if (!e->user_pages) { r = -ENOMEM; DRM_ERROR("calloc failure in %s\n", __func__); @@ -612,7 +613,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, r = amdgpu_ttm_tt_get_user_pages(ttm, e->user_pages); if (r) { DRM_ERROR("amdgpu_ttm_tt_get_user_pages failed.\n"); - drm_free_large(e->user_pages); + kvfree(e->user_pages); e->user_pages = NULL; goto error_free_pages; } @@ -708,7 +709,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, release_pages(e->user_pages, e->robj->tbo.ttm->num_pages, false); - drm_free_large(e->user_pages); + kvfree(e->user_pages); } } @@ -761,7 +762,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo amdgpu_bo_list_put(parser->bo_list); for (i = 0; i < parser->nchunks; i++) - drm_free_large(parser->chunks[i].kdata); + kvfree(parser->chunks[i].kdata); kfree(parser->chunks); if (parser->job) amdgpu_job_free(parser->job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c index 38e9b0d3659ae2..1cb52fd1906038 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_atombios.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f2d705e6a75aa4..31eddd85eb4090 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -39,7 +39,7 @@ #include #include #include -#include "drm_crtc_helper.h" +#include #include "amdgpu.h" #include "amdgpu_irq.h" @@ -715,6 +715,16 @@ static const struct file_operations amdgpu_driver_kms_fops = { #endif }; +static bool +amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, + bool in_vblank_irq, int *vpos, int *hpos, + ktime_t *stime, ktime_t *etime, + const struct drm_display_mode *mode) +{ + return amdgpu_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos, + stime, etime, mode); +} + static struct drm_driver kms_driver = { .driver_features = DRIVER_USE_AGP | @@ -729,8 +739,8 @@ static struct drm_driver kms_driver = { .get_vblank_counter = amdgpu_get_vblank_counter_kms, .enable_vblank = amdgpu_enable_vblank_kms, .disable_vblank = amdgpu_disable_vblank_kms, - .get_vblank_timestamp = amdgpu_get_vblank_timestamp_kms, - .get_scanout_position = amdgpu_get_crtc_scanoutpos, + .get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos, + .get_scanout_position = amdgpu_get_crtc_scanout_position, #if defined(CONFIG_DEBUG_FS) .debugfs_init = amdgpu_debugfs_init, #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 96c34167078253..dca4be970d1361 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -945,47 +945,6 @@ void amdgpu_disable_vblank_kms(struct drm_device *dev, unsigned int pipe) amdgpu_irq_put(adev, &adev->crtc_irq, idx); } -/** - * amdgpu_get_vblank_timestamp_kms - get vblank timestamp - * - * @dev: drm dev pointer - * @crtc: crtc to get the timestamp for - * @max_error: max error - * @vblank_time: time value - * @flags: flags passed to the driver - * - * Gets the timestamp on the requested crtc based on the - * scanout position. (all asics). - * Returns postive status flags on success, negative error on failure. - */ -int amdgpu_get_vblank_timestamp_kms(struct drm_device *dev, unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags) -{ - struct drm_crtc *crtc; - struct amdgpu_device *adev = dev->dev_private; - - if (pipe >= dev->num_crtcs) { - DRM_ERROR("Invalid crtc %u\n", pipe); - return -EINVAL; - } - - /* Get associated drm_crtc: */ - crtc = &adev->mode_info.crtcs[pipe]->base; - if (!crtc) { - /* This can occur on driver load if some component fails to - * initialize completely and driver is unloaded */ - DRM_ERROR("Uninitialized crtc %d\n", pipe); - return -EINVAL; - } - - /* Helper routine in DRM core does all the work: */ - return drm_calc_vbltimestamp_from_scanoutpos(dev, pipe, max_error, - vblank_time, flags, - &crtc->hwmode); -} - const struct drm_ioctl_desc amdgpu_ioctls_kms[] = { DRM_IOCTL_DEF_DRV(AMDGPU_GEM_CREATE, amdgpu_gem_create_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(AMDGPU_CTX, amdgpu_ctx_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index dbd10618ec2085..43a9d3aec6c426 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -534,6 +534,9 @@ struct amdgpu_framebuffer { ((em) == ATOM_ENCODER_MODE_DP_MST)) /* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */ +#define DRM_SCANOUTPOS_VALID (1 << 0) +#define DRM_SCANOUTPOS_IN_VBLANK (1 << 1) +#define DRM_SCANOUTPOS_ACCURATE (1 << 2) #define USE_REAL_VBLANKSTART (1 << 30) #define GET_DISTANCE_TO_VBLANKSTART (1 << 31) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index ac5e92e5d59d3c..596e3957bdd986 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -24,7 +24,7 @@ */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_psp.h" #include "amdgpu_ucode.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 5db0230e45c6db..b5fa003c134168 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -29,11 +29,11 @@ * Thomas Hellstrom * Dave Airlie */ -#include -#include -#include -#include -#include +#include +#include +#include +#include +#include #include #include #include diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8ecf82c5fe74dc..83c172a6e938a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -279,8 +279,9 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev, if (!parent->entries) { unsigned num_entries = amdgpu_vm_num_entries(adev, level); - parent->entries = drm_calloc_large(num_entries, - sizeof(struct amdgpu_vm_pt)); + parent->entries = kvmalloc_array(num_entries, + sizeof(struct amdgpu_vm_pt), + GFP_KERNEL | __GFP_ZERO); if (!parent->entries) return -ENOMEM; memset(parent->entries, 0 , sizeof(struct amdgpu_vm_pt)); @@ -2219,7 +2220,7 @@ static void amdgpu_vm_free_levels(struct amdgpu_vm_pt *level) for (i = 0; i <= level->last_entry_used; i++) amdgpu_vm_free_levels(&level->entries[i]); - drm_free_large(level->entries); + kvfree(level->entries); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index ec93714e4524ee..cb508a211b2f6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -22,7 +22,7 @@ */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_ucode.h" diff --git a/drivers/gpu/drm/amd/amdgpu/ci_smc.c b/drivers/gpu/drm/amd/amdgpu/ci_smc.c index 7eb9069db8e3fe..b8ba51e045b560 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_smc.c @@ -23,7 +23,7 @@ */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "cikd.h" #include "ppsmc.h" diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 9d33e56414194d..6b2034533f68c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -24,7 +24,7 @@ #include #include #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_atombios.h" #include "amdgpu_ih.h" diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index c57c3f18af019f..b8918432c5722b 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "cikd.h" diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index a5f294ebff5cc3..0c1209cdd1cb83 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "vid.h" diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 0cdeb6a2e4a016..3c62c45f43a149 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 773654a19749fa..c8ed0facddcd04 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 1f3552967ba374..3f3a2549332792 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 3c558c170e5e68..3e90c19b9c7f76 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index f1b479b6ac983d..90bb08309a533c 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_i2c.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index ee2f2139e2eba6..f7414cabd4ff6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "amdgpu_gfx.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 758d636a6f52b3..404d1278585359 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_gfx.h" #include "vi.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 0c16b7563b7317..125b119500719a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_gfx.h" #include "soc15.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index d860939152df23..9776ad3d2d7106 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "gmc_v6_0.h" #include "amdgpu_ucode.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 2750e5c2381301..fca8e77182c985 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "cikd.h" #include "cik.h" diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index f56b4089ee9f3f..e9c127037b39f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "gmc_v8_0.h" #include "amdgpu_ucode.h" diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index cb622add99a729..7a0ea27ac42959 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "vid.h" diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 79a52ad2c80df4..3bbf2ccfca89c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "cikd.h" diff --git a/drivers/gpu/drm/amd/amdgpu/kv_smc.c b/drivers/gpu/drm/amd/amdgpu/kv_smc.c index e6b7b42acfe146..b82e33c0157117 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_smc.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "amdgpu.h" #include "cikd.h" #include "kv_dpm.h" diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index 60a6407ba267b6..eef89abc0cee5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -24,7 +24,7 @@ */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_psp.h" #include "amdgpu_ucode.h" diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index c0b1aabf282f5a..2431639baf47b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -24,7 +24,7 @@ #include #include #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_atombios.h" #include "amdgpu_ih.h" diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 7c1c5d127281cd..a7ad8390981c7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_dpm.h" diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index e66084211c7487..ce25e03a077daf 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "sid.h" diff --git a/drivers/gpu/drm/amd/amdgpu/si_smc.c b/drivers/gpu/drm/amd/amdgpu/si_smc.c index 0726bc3b6f90e1..4a2fd8b61940e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/si_smc.c @@ -23,7 +23,7 @@ */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "sid.h" #include "ppsmc.h" diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 6b55d451ae7f94..e945f8b074877b 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -23,7 +23,7 @@ #include #include #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_atomfirmware.h" #include "amdgpu_ih.h" diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 3a5097ac2bb495..923df2c0e5352b 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "vid.h" diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 071f56e439bb67..3b9740fb2c412b 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -20,7 +20,7 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_ih.h" #include "soc15.h" diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index b1132f5e84fc10..3a187619286fc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -21,7 +21,7 @@ * */ #include -#include "drmP.h" +#include #include "amdgpu.h" #include "amdgpu_atombios.h" #include "amdgpu_ih.h" diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile index 7fc9b0f444cbba..b400d5664252c3 100644 --- a/drivers/gpu/drm/amd/amdkfd/Makefile +++ b/drivers/gpu/drm/amd/amdkfd/Makefile @@ -2,7 +2,7 @@ # Makefile for Heterogenous System Architecture support for AMD GPU devices # -ccflags-y := -Iinclude/drm -Idrivers/gpu/drm/amd/include/ \ +ccflags-y := -Idrivers/gpu/drm/amd/include/ \ -Idrivers/gpu/drm/amd/include/asic_reg amdkfd-y := kfd_module.o kfd_device.o kfd_chardev.o kfd_topology.o \ diff --git a/drivers/gpu/drm/amd/powerplay/Makefile b/drivers/gpu/drm/amd/powerplay/Makefile index 043e6ebab57579..4e132b936e3d2a 100644 --- a/drivers/gpu/drm/amd/powerplay/Makefile +++ b/drivers/gpu/drm/amd/powerplay/Makefile @@ -1,5 +1,5 @@ -subdir-ccflags-y += -Iinclude/drm \ +subdir-ccflags-y += \ -I$(FULL_AMD_PATH)/powerplay/inc/ \ -I$(FULL_AMD_PATH)/include/asic_reg \ -I$(FULL_AMD_PATH)/include \ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c index ff4ae3de6bb660..963a9e017a28fc 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c @@ -22,10 +22,10 @@ */ #include "pp_debug.h" -#include "linux/delay.h" -#include +#include #include #include +#include #include #include "cgs_common.h" #include "power_state.h" diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c index f5e8fda964f783..f6b4dd96c0ecce 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c @@ -21,8 +21,8 @@ * */ +#include #include -#include "linux/delay.h" #include "hwmgr.h" #include "amd_acpi.h" #include "pp_acpi.h" diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 102eb6d029faeb..1f01020ce3a92a 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -21,11 +21,11 @@ * */ #include "pp_debug.h" +#include +#include #include #include -#include #include -#include "linux/delay.h" #include "pp_acpi.h" #include "ppatomctrl.h" #include "atombios.h" diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index 2614af2f553f30..ab17350e853d9d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -20,10 +20,11 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ + +#include +#include #include #include -#include -#include "linux/delay.h" #include "hwmgr.h" #include "amd_powerplay.h" diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c index 1f6744a443d4ec..39c7091866e8be 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c @@ -20,11 +20,13 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include + +#include +#include #include #include -#include -#include "linux/delay.h" +#include + #include "cgs_common.h" #include "smu/smu_8_0_d.h" #include "smu/smu_8_0_sh_mask.h" diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index c0d75766bbc880..2e954a44bac1b8 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -20,15 +20,16 @@ * OTHER DEALINGS IN THE SOFTWARE. * */ -#include + +#include #include #include #include +#include #include #include "pp_instance.h" #include "smumgr.h" #include "cgs_common.h" -#include "linux/delay.h" MODULE_FIRMWARE("amdgpu/topaz_smc.bin"); MODULE_FIRMWARE("amdgpu/topaz_k_smc.bin"); diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h index 040311ffcaecc8..2e2033140efc0b 100644 --- a/drivers/gpu/drm/arm/malidp_drv.h +++ b/drivers/gpu/drm/arm/malidp_drv.h @@ -65,6 +65,6 @@ void malidp_de_planes_destroy(struct drm_device *drm); int malidp_crtc_init(struct drm_device *drm); /* often used combination of rotational bits */ -#define MALIDP_ROTATED_MASK (DRM_ROTATE_90 | DRM_ROTATE_270) +#define MALIDP_ROTATED_MASK (DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270) #endif /* __MALIDP_DRV_H__ */ diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index 814fda23ceade6..063a8d2b0be3c4 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -80,7 +80,7 @@ static void malidp_plane_reset(struct drm_plane *plane) state = kzalloc(sizeof(*state), GFP_KERNEL); if (state) { state->base.plane = plane; - state->base.rotation = DRM_ROTATE_0; + state->base.rotation = DRM_MODE_ROTATE_0; plane->state = &state->base; } } @@ -221,7 +221,7 @@ static int malidp_de_plane_check(struct drm_plane *plane, return ret; /* packed RGB888 / BGR888 can't be rotated or flipped */ - if (state->rotation != DRM_ROTATE_0 && + if (state->rotation != DRM_MODE_ROTATE_0 && (fb->format->format == DRM_FORMAT_RGB888 || fb->format->format == DRM_FORMAT_BGR888)) return -EINVAL; @@ -315,12 +315,12 @@ static void malidp_de_plane_update(struct drm_plane *plane, val &= ~LAYER_ROT_MASK; /* setup the rotation and axis flip bits */ - if (plane->state->rotation & DRM_ROTATE_MASK) - val |= ilog2(plane->state->rotation & DRM_ROTATE_MASK) << + if (plane->state->rotation & DRM_MODE_ROTATE_MASK) + val |= ilog2(plane->state->rotation & DRM_MODE_ROTATE_MASK) << LAYER_ROT_OFFSET; - if (plane->state->rotation & DRM_REFLECT_X) + if (plane->state->rotation & DRM_MODE_REFLECT_X) val |= LAYER_H_FLIP; - if (plane->state->rotation & DRM_REFLECT_Y) + if (plane->state->rotation & DRM_MODE_REFLECT_Y) val |= LAYER_V_FLIP; /* @@ -370,8 +370,8 @@ int malidp_de_planes_init(struct drm_device *drm) struct malidp_plane *plane = NULL; enum drm_plane_type plane_type; unsigned long crtcs = 1 << drm->mode_config.num_crtc; - unsigned long flags = DRM_ROTATE_0 | DRM_ROTATE_90 | DRM_ROTATE_180 | - DRM_ROTATE_270 | DRM_REFLECT_X | DRM_REFLECT_Y; + unsigned long flags = DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 | + DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; u32 *formats; int ret, i, j, n; @@ -420,7 +420,7 @@ int malidp_de_planes_init(struct drm_device *drm) continue; } - drm_plane_create_rotation_property(&plane->base, DRM_ROTATE_0, flags); + drm_plane_create_rotation_property(&plane->base, DRM_MODE_ROTATE_0, flags); malidp_hw_write(malidp->dev, MALIDP_ALPHA_LUT, plane->layer->base + MALIDP_LAYER_COMPOSE); } diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index 424e465ff407e5..e9a29df4b44383 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -125,7 +125,7 @@ armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, src_x, src_y, src_w, src_h); ret = drm_plane_helper_check_update(plane, crtc, fb, &src, &dest, &clip, - DRM_ROTATE_0, + DRM_MODE_ROTATE_0, 0, INT_MAX, true, false, &visible); if (ret) return ret; diff --git a/drivers/gpu/drm/ast/Makefile b/drivers/gpu/drm/ast/Makefile index 171aa0622b665e..617fdd39519c4e 100644 --- a/drivers/gpu/drm/ast/Makefile +++ b/drivers/gpu/drm/ast/Makefile @@ -2,8 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm - ast-y := ast_drv.o ast_main.o ast_mode.o ast_fb.o ast_ttm.o ast_post.o ast_dp501.o obj-$(CONFIG_DRM_AST) := ast.o diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c index e879496b8a4231..58084985e6cfe2 100644 --- a/drivers/gpu/drm/ast/ast_ttm.c +++ b/drivers/gpu/drm/ast/ast_ttm.c @@ -26,8 +26,9 @@ * Authors: Dave Airlie */ #include +#include + #include "ast_drv.h" -#include static inline struct ast_private * ast_bdev(struct ttm_bo_device *bd) diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index 29cc10d053ebc3..1124200bb280d8 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -678,8 +678,8 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p, if (!state->bpp[i]) return -EINVAL; - switch (state->base.rotation & DRM_ROTATE_MASK) { - case DRM_ROTATE_90: + switch (state->base.rotation & DRM_MODE_ROTATE_MASK) { + case DRM_MODE_ROTATE_90: offset = ((y_offset + state->src_y + patched_src_w - 1) / ydiv) * fb->pitches[i]; offset += ((x_offset + state->src_x) / xdiv) * @@ -688,7 +688,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p, fb->pitches[i]; state->pstride[i] = -fb->pitches[i] - state->bpp[i]; break; - case DRM_ROTATE_180: + case DRM_MODE_ROTATE_180: offset = ((y_offset + state->src_y + patched_src_h - 1) / ydiv) * fb->pitches[i]; offset += ((x_offset + state->src_x + patched_src_w - 1) / @@ -697,7 +697,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p, state->bpp[i]) - fb->pitches[i]; state->pstride[i] = -2 * state->bpp[i]; break; - case DRM_ROTATE_270: + case DRM_MODE_ROTATE_270: offset = ((y_offset + state->src_y) / ydiv) * fb->pitches[i]; offset += ((x_offset + state->src_x + patched_src_h - 1) / @@ -707,7 +707,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p, (2 * state->bpp[i]); state->pstride[i] = fb->pitches[i] - state->bpp[i]; break; - case DRM_ROTATE_0: + case DRM_MODE_ROTATE_0: default: offset = ((y_offset + state->src_y) / ydiv) * fb->pitches[i]; @@ -864,11 +864,11 @@ static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane, int ret; ret = drm_plane_create_rotation_property(&plane->base, - DRM_ROTATE_0, - DRM_ROTATE_0 | - DRM_ROTATE_90 | - DRM_ROTATE_180 | - DRM_ROTATE_270); + DRM_MODE_ROTATE_0, + DRM_MODE_ROTATE_0 | + DRM_MODE_ROTATE_90 | + DRM_MODE_ROTATE_180 | + DRM_MODE_ROTATE_270); if (ret) return ret; } diff --git a/drivers/gpu/drm/bochs/Makefile b/drivers/gpu/drm/bochs/Makefile index 844a556149207d..98ef60a19e8f06 100644 --- a/drivers/gpu/drm/bochs/Makefile +++ b/drivers/gpu/drm/bochs/Makefile @@ -1,4 +1,3 @@ -ccflags-y := -Iinclude/drm bochs-drm-y := bochs_drv.o bochs_mm.o bochs_kms.o bochs_fbdev.o bochs_hw.o obj-$(CONFIG_DRM_BOCHS) += bochs-drm.o diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h index f626bab7f5e3d6..76c490c3cdbcaa 100644 --- a/drivers/gpu/drm/bochs/bochs.h +++ b/drivers/gpu/drm/bochs/bochs.h @@ -9,8 +9,8 @@ #include -#include -#include +#include +#include /* ---------------------------------------------------------------------- */ diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index 3fe2226ee2f221..defcf1e7ca1c69 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -1,5 +1,3 @@ -ccflags-y := -Iinclude/drm - obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o obj-$(CONFIG_DRM_DUMB_VGA_DAC) += dumb-vga-dac.o obj-$(CONFIG_DRM_LVDS_ENCODER) += lvds-encoder.o diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index 351704390d0262..4f64e717e01be4 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -20,15 +20,13 @@ #include #include #include - +#include +#include +#include +#include #include #include - -#include "drm_crtc.h" -#include "drm_crtc_helper.h" -#include "drm_atomic_helper.h" -#include "drm_edid.h" -#include "drmP.h" +#include #define PTN3460_EDID_ADDR 0x0 #define PTN3460_EDID_EMULATION_ADDR 0x84 diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c index 1dcec3b97e6777..6f22f9fec9bfed 100644 --- a/drivers/gpu/drm/bridge/parade-ps8622.c +++ b/drivers/gpu/drm/bridge/parade-ps8622.c @@ -24,14 +24,12 @@ #include #include #include - +#include +#include +#include #include #include - -#include "drmP.h" -#include "drm_crtc.h" -#include "drm_crtc_helper.h" -#include "drm_atomic_helper.h" +#include /* Brightness scale on the Parade chip */ #define PS8622_MAX_BRIGHTNESS 0xff diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 9126d0306ab524..9b87067c022cd8 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -160,7 +160,7 @@ static int sii902x_get_modes(struct drm_connector *connector) time_before(jiffies, timeout)); if (!(status & SII902X_SYS_CTRL_DDC_BUS_GRTD)) { - dev_err(&sii902x->i2c->dev, "failed to acquire the i2c bus"); + dev_err(&sii902x->i2c->dev, "failed to acquire the i2c bus\n"); return -ETIMEDOUT; } @@ -202,7 +202,7 @@ static int sii902x_get_modes(struct drm_connector *connector) if (status & (SII902X_SYS_CTRL_DDC_BUS_REQ | SII902X_SYS_CTRL_DDC_BUS_GRTD)) { - dev_err(&sii902x->i2c->dev, "failed to release the i2c bus"); + dev_err(&sii902x->i2c->dev, "failed to release the i2c bus\n"); return -ETIMEDOUT; } @@ -298,7 +298,7 @@ static int sii902x_bridge_attach(struct drm_bridge *bridge) if (!drm_core_check_feature(drm, DRIVER_ATOMIC)) { dev_err(&sii902x->i2c->dev, - "sii902x driver is only compatible with DRM devices supporting atomic updates"); + "sii902x driver is only compatible with DRM devices supporting atomic updates\n"); return -ENOTSUPP; } diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 4e1f54a675d8de..8737de8c1c5216 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -173,6 +173,8 @@ struct dw_hdmi { unsigned int reg_shift; struct regmap *regm; + void (*enable_audio)(struct dw_hdmi *hdmi); + void (*disable_audio)(struct dw_hdmi *hdmi); }; #define HDMI_IH_PHY_STAT0_RX_SENSE \ @@ -542,13 +544,41 @@ void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate) } EXPORT_SYMBOL_GPL(dw_hdmi_set_sample_rate); +static void hdmi_enable_audio_clk(struct dw_hdmi *hdmi, bool enable) +{ + hdmi_modb(hdmi, enable ? 0 : HDMI_MC_CLKDIS_AUDCLK_DISABLE, + HDMI_MC_CLKDIS_AUDCLK_DISABLE, HDMI_MC_CLKDIS); +} + +static void dw_hdmi_ahb_audio_enable(struct dw_hdmi *hdmi) +{ + hdmi_set_cts_n(hdmi, hdmi->audio_cts, hdmi->audio_n); +} + +static void dw_hdmi_ahb_audio_disable(struct dw_hdmi *hdmi) +{ + hdmi_set_cts_n(hdmi, hdmi->audio_cts, 0); +} + +static void dw_hdmi_i2s_audio_enable(struct dw_hdmi *hdmi) +{ + hdmi_set_cts_n(hdmi, hdmi->audio_cts, hdmi->audio_n); + hdmi_enable_audio_clk(hdmi, true); +} + +static void dw_hdmi_i2s_audio_disable(struct dw_hdmi *hdmi) +{ + hdmi_enable_audio_clk(hdmi, false); +} + void dw_hdmi_audio_enable(struct dw_hdmi *hdmi) { unsigned long flags; spin_lock_irqsave(&hdmi->audio_lock, flags); hdmi->audio_enable = true; - hdmi_set_cts_n(hdmi, hdmi->audio_cts, hdmi->audio_n); + if (hdmi->enable_audio) + hdmi->enable_audio(hdmi); spin_unlock_irqrestore(&hdmi->audio_lock, flags); } EXPORT_SYMBOL_GPL(dw_hdmi_audio_enable); @@ -559,7 +589,8 @@ void dw_hdmi_audio_disable(struct dw_hdmi *hdmi) spin_lock_irqsave(&hdmi->audio_lock, flags); hdmi->audio_enable = false; - hdmi_set_cts_n(hdmi, hdmi->audio_cts, 0); + if (hdmi->disable_audio) + hdmi->disable_audio(hdmi); spin_unlock_irqrestore(&hdmi->audio_lock, flags); } EXPORT_SYMBOL_GPL(dw_hdmi_audio_disable); @@ -1573,11 +1604,6 @@ static void dw_hdmi_enable_video_path(struct dw_hdmi *hdmi) HDMI_MC_FLOWCTRL); } -static void hdmi_enable_audio_clk(struct dw_hdmi *hdmi) -{ - hdmi_modb(hdmi, 0, HDMI_MC_CLKDIS_AUDCLK_DISABLE, HDMI_MC_CLKDIS); -} - /* Workaround to clear the overflow condition */ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) { @@ -1691,7 +1717,7 @@ static int dw_hdmi_setup(struct dw_hdmi *hdmi, struct drm_display_mode *mode) /* HDMI Initialization Step E - Configure audio */ hdmi_clk_regenerator_update_pixel_clock(hdmi); - hdmi_enable_audio_clk(hdmi); + hdmi_enable_audio_clk(hdmi, true); } /* not for DVI mode */ @@ -2403,6 +2429,8 @@ __dw_hdmi_probe(struct platform_device *pdev, audio.irq = irq; audio.hdmi = hdmi; audio.eld = hdmi->connector.eld; + hdmi->enable_audio = dw_hdmi_ahb_audio_enable; + hdmi->disable_audio = dw_hdmi_ahb_audio_disable; pdevinfo.name = "dw-hdmi-ahb-audio"; pdevinfo.data = &audio; @@ -2415,6 +2443,8 @@ __dw_hdmi_probe(struct platform_device *pdev, audio.hdmi = hdmi; audio.write = hdmi_writeb; audio.read = hdmi_readb; + hdmi->enable_audio = dw_hdmi_i2s_audio_enable; + hdmi->disable_audio = dw_hdmi_i2s_audio_disable; pdevinfo.name = "dw-hdmi-i2s-audio"; pdevinfo.data = &audio; diff --git a/drivers/gpu/drm/cirrus/Makefile b/drivers/gpu/drm/cirrus/Makefile index 69ffe7006d55ed..919c0a336c9777 100644 --- a/drivers/gpu/drm/cirrus/Makefile +++ b/drivers/gpu/drm/cirrus/Makefile @@ -1,4 +1,3 @@ -ccflags-y := -Iinclude/drm cirrus-y := cirrus_main.o cirrus_mode.o \ cirrus_drv.o cirrus_fbdev.o cirrus_ttm.o diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c index 93dbcd38355d9c..1ff1838c0d44fc 100644 --- a/drivers/gpu/drm/cirrus/cirrus_ttm.c +++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c @@ -26,8 +26,9 @@ * Authors: Dave Airlie */ #include +#include + #include "cirrus_drv.h" -#include static inline struct cirrus_device * cirrus_bdev(struct ttm_bo_device *bd) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index f32506a7c1d61e..e1637011e18ab0 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -57,6 +57,7 @@ void drm_atomic_state_default_release(struct drm_atomic_state *state) kfree(state->connectors); kfree(state->crtcs); kfree(state->planes); + kfree(state->private_objs); } EXPORT_SYMBOL(drm_atomic_state_default_release); @@ -184,6 +185,17 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->planes[i].ptr = NULL; state->planes[i].state = NULL; } + + for (i = 0; i < state->num_private_objs; i++) { + void *obj_state = state->private_objs[i].obj_state; + + state->private_objs[i].funcs->destroy_state(obj_state); + state->private_objs[i].obj = NULL; + state->private_objs[i].obj_state = NULL; + state->private_objs[i].funcs = NULL; + } + state->num_private_objs = 0; + } EXPORT_SYMBOL(drm_atomic_state_default_clear); @@ -425,7 +437,7 @@ drm_atomic_replace_property_blob(struct drm_property_blob **blob, } static int -drm_atomic_replace_property_blob_from_id(struct drm_crtc *crtc, +drm_atomic_replace_property_blob_from_id(struct drm_device *dev, struct drm_property_blob **blob, uint64_t blob_id, ssize_t expected_size, @@ -434,7 +446,7 @@ drm_atomic_replace_property_blob_from_id(struct drm_crtc *crtc, struct drm_property_blob *new_blob = NULL; if (blob_id != 0) { - new_blob = drm_property_lookup_blob(crtc->dev, blob_id); + new_blob = drm_property_lookup_blob(dev, blob_id); if (new_blob == NULL) return -EINVAL; @@ -483,7 +495,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, drm_property_blob_put(mode); return ret; } else if (property == config->degamma_lut_property) { - ret = drm_atomic_replace_property_blob_from_id(crtc, + ret = drm_atomic_replace_property_blob_from_id(dev, &state->degamma_lut, val, -1, @@ -491,7 +503,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, state->color_mgmt_changed |= replaced; return ret; } else if (property == config->ctm_property) { - ret = drm_atomic_replace_property_blob_from_id(crtc, + ret = drm_atomic_replace_property_blob_from_id(dev, &state->ctm, val, sizeof(struct drm_color_ctm), @@ -499,7 +511,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, state->color_mgmt_changed |= replaced; return ret; } else if (property == config->gamma_lut_property) { - ret = drm_atomic_replace_property_blob_from_id(crtc, + ret = drm_atomic_replace_property_blob_from_id(dev, &state->gamma_lut, val, -1, @@ -769,7 +781,7 @@ int drm_atomic_plane_set_property(struct drm_plane *plane, } else if (property == config->prop_src_h) { state->src_h = val; } else if (property == plane->rotation_property) { - if (!is_power_of_2(val & DRM_ROTATE_MASK)) + if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK)) return -EINVAL; state->rotation = val; } else if (property == plane->zpos_property) { @@ -977,6 +989,59 @@ static void drm_atomic_plane_print_state(struct drm_printer *p, plane->funcs->atomic_print_state(p, state); } +/** + * drm_atomic_get_private_obj_state - get private object state + * @state: global atomic state + * @obj: private object to get the state for + * @funcs: pointer to the struct of function pointers that identify the object + * type + * + * This function returns the private object state for the given private object, + * allocating the state if needed. It does not grab any locks as the caller is + * expected to care of any required locking. + * + * RETURNS: + * + * Either the allocated state or the error code encoded into a pointer. + */ +void * +drm_atomic_get_private_obj_state(struct drm_atomic_state *state, void *obj, + const struct drm_private_state_funcs *funcs) +{ + int index, num_objs, i; + size_t size; + struct __drm_private_objs_state *arr; + + for (i = 0; i < state->num_private_objs; i++) + if (obj == state->private_objs[i].obj && + state->private_objs[i].obj_state) + return state->private_objs[i].obj_state; + + num_objs = state->num_private_objs + 1; + size = sizeof(*state->private_objs) * num_objs; + arr = krealloc(state->private_objs, size, GFP_KERNEL); + if (!arr) + return ERR_PTR(-ENOMEM); + + state->private_objs = arr; + index = state->num_private_objs; + memset(&state->private_objs[index], 0, sizeof(*state->private_objs)); + + state->private_objs[index].obj_state = funcs->duplicate_state(state, obj); + if (!state->private_objs[index].obj_state) + return ERR_PTR(-ENOMEM); + + state->private_objs[index].obj = obj; + state->private_objs[index].funcs = funcs; + state->num_private_objs = num_objs; + + DRM_DEBUG_ATOMIC("Added new private object state %p to %p\n", + state->private_objs[index].obj_state, state); + + return state->private_objs[index].obj_state; +} +EXPORT_SYMBOL(drm_atomic_get_private_obj_state); + /** * drm_atomic_get_connector_state - get connector state * @state: global atomic state object @@ -1123,6 +1188,10 @@ int drm_atomic_connector_set_property(struct drm_connector *connector, */ if (state->link_status != DRM_LINK_STATUS_GOOD) state->link_status = val; + } else if (property == config->aspect_ratio_property) { + state->picture_aspect_ratio = val; + } else if (property == connector->scaling_mode_property) { + state->scaling_mode = val; } else if (connector->funcs->atomic_set_property) { return connector->funcs->atomic_set_property(connector, state, property, val); @@ -1199,6 +1268,10 @@ drm_atomic_connector_get_property(struct drm_connector *connector, *val = state->tv.hue; } else if (property == config->link_status_property) { *val = state->link_status; + } else if (property == config->aspect_ratio_property) { + *val = state->picture_aspect_ratio; + } else if (property == connector->scaling_mode_property) { + *val = state->scaling_mode; } else if (connector->funcs->atomic_get_property) { return connector->funcs->atomic_get_property(connector, state, property, val); @@ -1618,7 +1691,7 @@ int drm_atomic_commit(struct drm_atomic_state *state) if (ret) return ret; - DRM_DEBUG_ATOMIC("commiting %p\n", state); + DRM_DEBUG_ATOMIC("committing %p\n", state); return config->funcs->atomic_commit(state->dev, state, false); } @@ -1647,7 +1720,7 @@ int drm_atomic_nonblocking_commit(struct drm_atomic_state *state) if (ret) return ret; - DRM_DEBUG_ATOMIC("commiting %p nonblocking\n", state); + DRM_DEBUG_ATOMIC("committing %p nonblocking\n", state); return config->funcs->atomic_commit(state->dev, state, true); } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 8be9719284b047..bb6dc4e71fe166 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -508,6 +508,8 @@ drm_atomic_helper_check_modeset(struct drm_device *dev, bool has_connectors = !!new_crtc_state->connector_mask; + WARN_ON(!drm_modeset_is_locked(&crtc->mutex)); + if (!drm_mode_equal(&old_crtc_state->mode, &new_crtc_state->mode)) { DRM_DEBUG_ATOMIC("[CRTC:%d:%s] mode changed\n", crtc->base.id, crtc->name); @@ -551,6 +553,8 @@ drm_atomic_helper_check_modeset(struct drm_device *dev, for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) { const struct drm_connector_helper_funcs *funcs = connector->helper_private; + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + /* * This only sets crtc->connectors_changed for routing changes, * drivers must set crtc->connectors_changed themselves when @@ -650,6 +654,8 @@ drm_atomic_helper_check_planes(struct drm_device *dev, for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { const struct drm_plane_helper_funcs *funcs; + WARN_ON(!drm_modeset_is_locked(&plane->mutex)); + funcs = plane->helper_private; drm_atomic_helper_plane_changed(state, old_plane_state, new_plane_state, plane); @@ -1070,8 +1076,8 @@ EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_enables); * * Note that @pre_swap is needed since the point where we block for fences moves * around depending upon whether an atomic commit is blocking or - * non-blocking. For async commit all waiting needs to happen after - * drm_atomic_helper_swap_state() is called, but for synchronous commits we want + * non-blocking. For non-blocking commit all waiting needs to happen after + * drm_atomic_helper_swap_state() is called, but for blocking commits we want * to wait **before** we do anything that can't be easily rolled back. That is * before we call drm_atomic_helper_swap_state(). * @@ -2032,6 +2038,8 @@ void drm_atomic_helper_swap_state(struct drm_atomic_state *state, struct drm_plane *plane; struct drm_plane_state *old_plane_state, *new_plane_state; struct drm_crtc_commit *commit; + void *obj, *obj_state; + const struct drm_private_state_funcs *funcs; if (stall) { for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { @@ -2092,6 +2100,9 @@ void drm_atomic_helper_swap_state(struct drm_atomic_state *state, state->planes[i].state = old_plane_state; plane->state = new_plane_state; } + + __for_each_private_obj(state, obj, obj_state, i, funcs) + funcs->swap_state(obj, &state->private_objs[i].obj_state); } EXPORT_SYMBOL(drm_atomic_helper_swap_state); @@ -2663,7 +2674,12 @@ int drm_atomic_helper_resume(struct drm_device *dev, drm_modeset_acquire_init(&ctx, 0); while (1) { + err = drm_modeset_lock_all_ctx(dev, &ctx); + if (err) + goto out; + err = drm_atomic_helper_commit_duplicated_state(state, &ctx); +out: if (err != -EDEADLK) break; @@ -3220,7 +3236,7 @@ void drm_atomic_helper_plane_reset(struct drm_plane *plane) if (plane->state) { plane->state->plane = plane; - plane->state->rotation = DRM_ROTATE_0; + plane->state->rotation = DRM_MODE_ROTATE_0; } } EXPORT_SYMBOL(drm_atomic_helper_plane_reset); @@ -3517,7 +3533,8 @@ EXPORT_SYMBOL(drm_atomic_helper_connector_destroy_state); * * Implements support for legacy gamma correction table for drivers * that support color management through the DEGAMMA_LUT/GAMMA_LUT - * properties. + * properties. See drm_crtc_enable_color_mgmt() and the containing chapter for + * how the atomic color management and gamma tables work. */ int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue, diff --git a/drivers/gpu/drm/drm_blend.c b/drivers/gpu/drm/drm_blend.c index a0d0d684328822..db6aeec50b821e 100644 --- a/drivers/gpu/drm/drm_blend.c +++ b/drivers/gpu/drm/drm_blend.c @@ -119,17 +119,17 @@ * drm_property_create_bitmask()) called "rotation" and has the following * bitmask enumaration values: * - * DRM_ROTATE_0: + * DRM_MODE_ROTATE_0: * "rotate-0" - * DRM_ROTATE_90: + * DRM_MODE_ROTATE_90: * "rotate-90" - * DRM_ROTATE_180: + * DRM_MODE_ROTATE_180: * "rotate-180" - * DRM_ROTATE_270: + * DRM_MODE_ROTATE_270: * "rotate-270" - * DRM_REFLECT_X: + * DRM_MODE_REFLECT_X: * "reflect-x" - * DRM_REFELCT_Y: + * DRM_MODE_REFLECT_Y: * "reflect-y" * * Rotation is the specified amount in degrees in counter clockwise direction, @@ -142,17 +142,17 @@ int drm_plane_create_rotation_property(struct drm_plane *plane, unsigned int supported_rotations) { static const struct drm_prop_enum_list props[] = { - { __builtin_ffs(DRM_ROTATE_0) - 1, "rotate-0" }, - { __builtin_ffs(DRM_ROTATE_90) - 1, "rotate-90" }, - { __builtin_ffs(DRM_ROTATE_180) - 1, "rotate-180" }, - { __builtin_ffs(DRM_ROTATE_270) - 1, "rotate-270" }, - { __builtin_ffs(DRM_REFLECT_X) - 1, "reflect-x" }, - { __builtin_ffs(DRM_REFLECT_Y) - 1, "reflect-y" }, + { __builtin_ffs(DRM_MODE_ROTATE_0) - 1, "rotate-0" }, + { __builtin_ffs(DRM_MODE_ROTATE_90) - 1, "rotate-90" }, + { __builtin_ffs(DRM_MODE_ROTATE_180) - 1, "rotate-180" }, + { __builtin_ffs(DRM_MODE_ROTATE_270) - 1, "rotate-270" }, + { __builtin_ffs(DRM_MODE_REFLECT_X) - 1, "reflect-x" }, + { __builtin_ffs(DRM_MODE_REFLECT_Y) - 1, "reflect-y" }, }; struct drm_property *prop; - WARN_ON((supported_rotations & DRM_ROTATE_MASK) == 0); - WARN_ON(!is_power_of_2(rotation & DRM_ROTATE_MASK)); + WARN_ON((supported_rotations & DRM_MODE_ROTATE_MASK) == 0); + WARN_ON(!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK)); WARN_ON(rotation & ~supported_rotations); prop = drm_property_create_bitmask(plane->dev, 0, "rotation", @@ -178,14 +178,14 @@ EXPORT_SYMBOL(drm_plane_create_rotation_property); * @supported_rotations: Supported rotations * * Attempt to simplify the rotation to a form that is supported. - * Eg. if the hardware supports everything except DRM_REFLECT_X + * Eg. if the hardware supports everything except DRM_MODE_REFLECT_X * one could call this function like this: * - * drm_rotation_simplify(rotation, DRM_ROTATE_0 | - * DRM_ROTATE_90 | DRM_ROTATE_180 | - * DRM_ROTATE_270 | DRM_REFLECT_Y); + * drm_rotation_simplify(rotation, DRM_MODE_ROTATE_0 | + * DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 | + * DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_Y); * - * to eliminate the DRM_ROTATE_X flag. Depending on what kind of + * to eliminate the DRM_MODE_ROTATE_X flag. Depending on what kind of * transforms the hardware supports, this function may not * be able to produce a supported transform, so the caller should * check the result afterwards. @@ -194,9 +194,10 @@ unsigned int drm_rotation_simplify(unsigned int rotation, unsigned int supported_rotations) { if (rotation & ~supported_rotations) { - rotation ^= DRM_REFLECT_X | DRM_REFLECT_Y; - rotation = (rotation & DRM_REFLECT_MASK) | - BIT((ffs(rotation & DRM_ROTATE_MASK) + 1) % 4); + rotation ^= DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; + rotation = (rotation & DRM_MODE_REFLECT_MASK) | + BIT((ffs(rotation & DRM_MODE_ROTATE_MASK) + 1) + % 4); } return rotation; diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 533f3a3e687779..3eda500fc005ea 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -43,7 +43,8 @@ * * Setting this to NULL (blob property value set to 0) means a * linear/pass-thru gamma table should be used. This is generally the - * driver boot-up state too. + * driver boot-up state too. Drivers can access this blob through + * &drm_crtc_state.degamma_lut. * * “DEGAMMA_LUT_SIZE”: * Unsinged range property to give the size of the lookup table to be set @@ -60,7 +61,8 @@ * * Setting this to NULL (blob property value set to 0) means a * unit/pass-thru matrix should be used. This is generally the driver - * boot-up state too. + * boot-up state too. Drivers can access the blob for the color conversion + * matrix through &drm_crtc_state.ctm. * * “GAMMA_LUT”: * Blob property to set the gamma lookup table (LUT) mapping pixel data @@ -72,7 +74,8 @@ * * Setting this to NULL (blob property value set to 0) means a * linear/pass-thru gamma table should be used. This is generally the - * driver boot-up state too. + * driver boot-up state too. Drivers can access this blob through + * &drm_crtc_state.gamma_lut. * * “GAMMA_LUT_SIZE”: * Unsigned range property to give the size of the lookup table to be set diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 9f847615ac74ab..5cd61aff785767 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -941,6 +941,10 @@ EXPORT_SYMBOL(drm_mode_create_tv_properties); * * Called by a driver the first time it's needed, must be attached to desired * connectors. + * + * Atomic drivers should use drm_connector_attach_scaling_mode_property() + * instead to correctly assign &drm_connector_state.picture_aspect_ratio + * in the atomic state. */ int drm_mode_create_scaling_mode_property(struct drm_device *dev) { @@ -960,6 +964,66 @@ int drm_mode_create_scaling_mode_property(struct drm_device *dev) } EXPORT_SYMBOL(drm_mode_create_scaling_mode_property); +/** + * drm_connector_attach_scaling_mode_property - attach atomic scaling mode property + * @connector: connector to attach scaling mode property on. + * @scaling_mode_mask: or'ed mask of BIT(%DRM_MODE_SCALE_\*). + * + * This is used to add support for scaling mode to atomic drivers. + * The scaling mode will be set to &drm_connector_state.picture_aspect_ratio + * and can be used from &drm_connector_helper_funcs->atomic_check for validation. + * + * This is the atomic version of drm_mode_create_scaling_mode_property(). + * + * Returns: + * Zero on success, negative errno on failure. + */ +int drm_connector_attach_scaling_mode_property(struct drm_connector *connector, + u32 scaling_mode_mask) +{ + struct drm_device *dev = connector->dev; + struct drm_property *scaling_mode_property; + int i, j = 0; + const unsigned valid_scaling_mode_mask = + (1U << ARRAY_SIZE(drm_scaling_mode_enum_list)) - 1; + + if (WARN_ON(hweight32(scaling_mode_mask) < 2 || + scaling_mode_mask & ~valid_scaling_mode_mask)) + return -EINVAL; + + scaling_mode_property = + drm_property_create(dev, DRM_MODE_PROP_ENUM, "scaling mode", + hweight32(scaling_mode_mask)); + + if (!scaling_mode_property) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(drm_scaling_mode_enum_list); i++) { + int ret; + + if (!(BIT(i) & scaling_mode_mask)) + continue; + + ret = drm_property_add_enum(scaling_mode_property, j++, + drm_scaling_mode_enum_list[i].type, + drm_scaling_mode_enum_list[i].name); + + if (ret) { + drm_property_destroy(dev, scaling_mode_property); + + return ret; + } + } + + drm_object_attach_property(&connector->base, + scaling_mode_property, 0); + + connector->scaling_mode_property = scaling_mode_property; + + return 0; +} +EXPORT_SYMBOL(drm_connector_attach_scaling_mode_property); + /** * drm_mode_create_aspect_ratio_property - create aspect ratio property * @dev: DRM device diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index d3fc7e4e85b741..222eb1a8549b01 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -737,16 +737,16 @@ static void drm_dp_mst_put_payload_id(struct drm_dp_mst_topology_mgr *mgr, static bool check_txmsg_state(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_sideband_msg_tx *txmsg) { - bool ret; + unsigned int state; /* * All updates to txmsg->state are protected by mgr->qlock, and the two * cases we check here are terminal states. For those the barriers * provided by the wake_up/wait_event pair are enough. */ - ret = (txmsg->state == DRM_DP_SIDEBAND_TX_RX || - txmsg->state == DRM_DP_SIDEBAND_TX_TIMEOUT); - return ret; + state = READ_ONCE(txmsg->state); + return (state == DRM_DP_SIDEBAND_TX_RX || + state == DRM_DP_SIDEBAND_TX_TIMEOUT); } static int drm_dp_mst_wait_tx_reply(struct drm_dp_mst_branch *mstb, @@ -855,7 +855,7 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) mutex_unlock(&mstb->mgr->qlock); if (wake_tx) - wake_up(&mstb->mgr->tx_waitq); + wake_up_all(&mstb->mgr->tx_waitq); kref_put(kref, drm_dp_free_mst_branch_device); } @@ -1510,7 +1510,7 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) if (txmsg->seqno != -1) txmsg->dst->tx_slots[txmsg->seqno] = NULL; txmsg->state = DRM_DP_SIDEBAND_TX_TIMEOUT; - wake_up(&mgr->tx_waitq); + wake_up_all(&mgr->tx_waitq); } } @@ -2258,7 +2258,7 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) mstb->tx_slots[slot] = NULL; mutex_unlock(&mgr->qlock); - wake_up(&mgr->tx_waitq); + wake_up_all(&mgr->tx_waitq); } return ret; } @@ -2497,6 +2497,81 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr, return 0; } +/** + * drm_dp_atomic_find_vcpi_slots() - Find and add vcpi slots to the state + * @state: global atomic state + * @mgr: MST topology manager for the port + * @port: port to find vcpi slots for + * @pbn: bandwidth required for the mode in PBN + * + * RETURNS: + * Total slots in the atomic state assigned for this port or error + */ +int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, int pbn) +{ + struct drm_dp_mst_topology_state *topology_state; + int req_slots; + + topology_state = drm_atomic_get_mst_topology_state(state, mgr); + if (topology_state == NULL) + return -ENOMEM; + + port = drm_dp_get_validated_port_ref(mgr, port); + if (port == NULL) + return -EINVAL; + req_slots = DIV_ROUND_UP(pbn, mgr->pbn_div); + DRM_DEBUG_KMS("vcpi slots req=%d, avail=%d\n", + req_slots, topology_state->avail_slots); + + if (req_slots > topology_state->avail_slots) { + drm_dp_put_port(port); + return -ENOSPC; + } + + topology_state->avail_slots -= req_slots; + DRM_DEBUG_KMS("vcpi slots avail=%d", topology_state->avail_slots); + + drm_dp_put_port(port); + return req_slots; +} +EXPORT_SYMBOL(drm_dp_atomic_find_vcpi_slots); + +/** + * drm_dp_atomic_release_vcpi_slots() - Release allocated vcpi slots + * @state: global atomic state + * @mgr: MST topology manager for the port + * @slots: number of vcpi slots to release + * + * RETURNS: + * 0 if @slots were added back to &drm_dp_mst_topology_state->avail_slots or + * negative error code + */ +int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + int slots) +{ + struct drm_dp_mst_topology_state *topology_state; + + topology_state = drm_atomic_get_mst_topology_state(state, mgr); + if (topology_state == NULL) + return -ENOMEM; + + /* We cannot rely on port->vcpi.num_slots to update + * topology_state->avail_slots as the port may not exist if the parent + * branch device was unplugged. This should be fixed by tracking + * per-port slot allocation in drm_dp_mst_topology_state instead of + * depending on the caller to tell us how many slots to release. + */ + topology_state->avail_slots += slots; + DRM_DEBUG_KMS("vcpi slots released=%d, avail=%d\n", + slots, topology_state->avail_slots); + + return 0; +} +EXPORT_SYMBOL(drm_dp_atomic_release_vcpi_slots); + /** * drm_dp_mst_allocate_vcpi() - Allocate a virtual channel * @mgr: manager for this port @@ -2936,6 +3011,69 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) (*mgr->cbs->hotplug)(mgr); } +void *drm_dp_mst_duplicate_state(struct drm_atomic_state *state, void *obj) +{ + struct drm_dp_mst_topology_mgr *mgr = obj; + struct drm_dp_mst_topology_state *new_mst_state; + + if (WARN_ON(!mgr->state)) + return NULL; + + new_mst_state = kmemdup(mgr->state, sizeof(*new_mst_state), GFP_KERNEL); + if (new_mst_state) + new_mst_state->state = state; + return new_mst_state; +} + +void drm_dp_mst_swap_state(void *obj, void **obj_state_ptr) +{ + struct drm_dp_mst_topology_mgr *mgr = obj; + struct drm_dp_mst_topology_state **topology_state_ptr; + + topology_state_ptr = (struct drm_dp_mst_topology_state **)obj_state_ptr; + + mgr->state->state = (*topology_state_ptr)->state; + swap(*topology_state_ptr, mgr->state); + mgr->state->state = NULL; +} + +void drm_dp_mst_destroy_state(void *obj_state) +{ + kfree(obj_state); +} + +static const struct drm_private_state_funcs mst_state_funcs = { + .duplicate_state = drm_dp_mst_duplicate_state, + .swap_state = drm_dp_mst_swap_state, + .destroy_state = drm_dp_mst_destroy_state, +}; + +/** + * drm_atomic_get_mst_topology_state: get MST topology state + * + * @state: global atomic state + * @mgr: MST topology manager, also the private object in this case + * + * This function wraps drm_atomic_get_priv_obj_state() passing in the MST atomic + * state vtable so that the private object state returned is that of a MST + * topology object. Also, drm_atomic_get_private_obj_state() expects the caller + * to care of the locking, so warn if don't hold the connection_mutex. + * + * RETURNS: + * + * The MST topology state or error pointer. + */ +struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr) +{ + struct drm_device *dev = mgr->dev; + + WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + return drm_atomic_get_private_obj_state(state, mgr, + &mst_state_funcs); +} +EXPORT_SYMBOL(drm_atomic_get_mst_topology_state); + /** * drm_dp_mst_topology_mgr_init - initialise a topology manager * @mgr: manager struct to initialise @@ -2980,6 +3118,15 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, if (test_calc_pbn_mode() < 0) DRM_ERROR("MST PBN self-test failed\n"); + mgr->state = kzalloc(sizeof(*mgr->state), GFP_KERNEL); + if (mgr->state == NULL) + return -ENOMEM; + mgr->state->mgr = mgr; + + /* max. time slots - one slot for MTP header */ + mgr->state->avail_slots = 63; + mgr->funcs = &mst_state_funcs; + return 0; } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_init); @@ -3000,6 +3147,9 @@ void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr) mutex_unlock(&mgr->payload_lock); mgr->dev = NULL; mgr->aux = NULL; + kfree(mgr->state); + mgr->state = NULL; + mgr->funcs = NULL; } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_destroy); diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index 50abd1faf38f08..53f9bdf470d77e 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -189,7 +189,7 @@ struct drm_framebuffer *drm_fb_cma_create_with_funcs(struct drm_device *dev, obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]); if (!obj) { dev_err(dev->dev, "Failed to lookup GEM object\n"); - ret = -ENXIO; + ret = -ENOENT; goto err_gem_object_put; } @@ -259,6 +259,33 @@ struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb, } EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_obj); +/** + * drm_fb_cma_get_gem_addr() - Get physical address for framebuffer + * @fb: The framebuffer + * @state: Which state of drm plane + * @plane: Which plane + * Return the CMA GEM address for given framebuffer. + * + * This function will usually be called from the PLANE callback functions. + */ +dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb, + struct drm_plane_state *state, + unsigned int plane) +{ + struct drm_fb_cma *fb_cma = to_fb_cma(fb); + dma_addr_t paddr; + + if (plane >= 4) + return 0; + + paddr = fb_cma->obj[plane]->paddr + fb->offsets[plane]; + paddr += fb->format->cpp[plane] * (state->src_x >> 16); + paddr += fb->pitches[plane] * (state->src_y >> 16); + + return paddr; +} +EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr); + /** * drm_fb_cma_prepare_fb() - Prepare CMA framebuffer * @plane: Which plane diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 1f178b878e42f0..574af01d3ce94a 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -378,7 +378,7 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper) goto fail; } - plane_state->rotation = DRM_ROTATE_0; + plane_state->rotation = DRM_MODE_ROTATE_0; plane->old_fb = plane->fb; plane_mask |= 1 << drm_plane_index(plane); @@ -431,7 +431,7 @@ static int restore_fbdev_mode_legacy(struct drm_fb_helper *fb_helper) if (plane->rotation_property) drm_mode_plane_set_obj_prop(plane, plane->rotation_property, - DRM_ROTATE_0); + DRM_MODE_ROTATE_0); } for (i = 0; i < fb_helper->crtc_count; i++) { diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 3783b659cd38a6..caad93dab54bb3 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -351,9 +351,8 @@ void drm_lastclose(struct drm_device * dev) * * This function must be used by drivers as their &file_operations.release * method. It frees any resources associated with the open file, and calls the - * &drm_driver.preclose and &drm_driver.lastclose driver callbacks. If this is - * the last open file for the DRM device also proceeds to call the - * &drm_driver.lastclose driver callback. + * &drm_driver.postclose driver callback. If this is the last open file for the + * DRM device also proceeds to call the &drm_driver.lastclose driver callback. * * RETURNS: * @@ -373,7 +372,8 @@ int drm_release(struct inode *inode, struct file *filp) list_del(&file_priv->lhead); mutex_unlock(&dev->filelist_mutex); - if (dev->driver->preclose) + if (drm_core_check_feature(dev, DRIVER_LEGACY) && + dev->driver->preclose) dev->driver->preclose(dev, file_priv); /* ======================================================== diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index b1e28c94463709..8dc11064253d9e 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -521,7 +521,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) npages = obj->size >> PAGE_SHIFT; - pages = drm_malloc_ab(npages, sizeof(struct page *)); + pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (pages == NULL) return ERR_PTR(-ENOMEM); @@ -546,7 +546,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) while (i--) put_page(pages[i]); - drm_free_large(pages); + kvfree(pages); return ERR_CAST(p); } EXPORT_SYMBOL(drm_gem_get_pages); @@ -582,7 +582,7 @@ void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages, put_page(pages[i]); } - drm_free_large(pages); + kvfree(pages); } EXPORT_SYMBOL(drm_gem_put_pages); diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 8c866cac62dd27..c7debaad67f87a 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -54,7 +54,7 @@ static bool drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe, - struct timeval *tvblank, unsigned flags); + struct timeval *tvblank, bool in_vblank_irq); static unsigned int drm_timestamp_precision = 20; /* Default to 20 usecs. */ @@ -138,7 +138,7 @@ static void drm_reset_vblank_timestamp(struct drm_device *dev, unsigned int pipe */ do { cur_vblank = __get_vblank_counter(dev, pipe); - rc = drm_get_last_vbltimestamp(dev, pipe, &t_vblank, 0); + rc = drm_get_last_vbltimestamp(dev, pipe, &t_vblank, false); } while (cur_vblank != __get_vblank_counter(dev, pipe) && --count > 0); /* @@ -171,7 +171,7 @@ static void drm_reset_vblank_timestamp(struct drm_device *dev, unsigned int pipe * device vblank fields. */ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, - unsigned long flags) + bool in_vblank_irq) { struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; u32 cur_vblank, diff; @@ -194,7 +194,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, */ do { cur_vblank = __get_vblank_counter(dev, pipe); - rc = drm_get_last_vbltimestamp(dev, pipe, &t_vblank, flags); + rc = drm_get_last_vbltimestamp(dev, pipe, &t_vblank, in_vblank_irq); } while (cur_vblank != __get_vblank_counter(dev, pipe) && --count > 0); if (dev->max_vblank_count != 0) { @@ -214,13 +214,13 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, */ diff = DIV_ROUND_CLOSEST_ULL(diff_ns, framedur_ns); - if (diff == 0 && flags & DRM_CALLED_FROM_VBLIRQ) + if (diff == 0 && in_vblank_irq) DRM_DEBUG_VBL("crtc %u: Redundant vblirq ignored." " diff_ns = %lld, framedur_ns = %d)\n", pipe, (long long) diff_ns, framedur_ns); } else { /* some kind of default for drivers w/o accurate vbl timestamping */ - diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; + diff = in_vblank_irq ? 1 : 0; } /* @@ -253,7 +253,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, * Otherwise reinitialize delayed at next vblank interrupt and assign 0 * for now, to mark the vblanktimestamp as invalid. */ - if (!rc && (flags & DRM_CALLED_FROM_VBLIRQ) == 0) + if (!rc && in_vblank_irq) t_vblank = (struct timeval) {0, 0}; store_vblank(dev, pipe, diff, &t_vblank, cur_vblank); @@ -291,7 +291,7 @@ u32 drm_accurate_vblank_count(struct drm_crtc *crtc) spin_lock_irqsave(&dev->vblank_time_lock, flags); - drm_update_vblank_count(dev, pipe, 0); + drm_update_vblank_count(dev, pipe, false); vblank = drm_vblank_count(dev, pipe); spin_unlock_irqrestore(&dev->vblank_time_lock, flags); @@ -349,7 +349,7 @@ static void vblank_disable_and_save(struct drm_device *dev, unsigned int pipe) * this time. This makes the count account for the entire time * between drm_crtc_vblank_on() and drm_crtc_vblank_off(). */ - drm_update_vblank_count(dev, pipe, 0); + drm_update_vblank_count(dev, pipe, false); spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags); } @@ -684,6 +684,7 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc, vblank->linedur_ns = linedur_ns; vblank->framedur_ns = framedur_ns; + vblank->hwmode = *mode; DRM_DEBUG("crtc %u: hwmode: htotal %d, vtotal %d, vdisplay %d\n", crtc->base.id, mode->crtc_htotal, @@ -700,10 +701,10 @@ EXPORT_SYMBOL(drm_calc_timestamping_constants); * @max_error: Desired maximum allowable error in timestamps (nanosecs) * On return contains true maximum error of timestamp * @vblank_time: Pointer to struct timeval which should receive the timestamp - * @flags: Flags to pass to driver: - * 0 = Default, - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler - * @mode: mode which defines the scanout timings + * @in_vblank_irq: + * True when called from drm_crtc_handle_vblank(). Some drivers + * need to apply some workarounds for gpu-specific vblank irq quirks + * if flag is set. * * Implements calculation of exact vblank timestamps from given drm_display_mode * timings and current video scanout position of a CRTC. This can be called from @@ -723,52 +724,62 @@ EXPORT_SYMBOL(drm_calc_timestamping_constants); * returns as no operation if a doublescan or interlaced video mode is * active. Higher level code is expected to handle this. * - * Returns: - * Negative value on error, failure or if not supported in current - * video mode: - * - * -EINVAL Invalid CRTC. - * -EAGAIN Temporary unavailable, e.g., called before initial modeset. - * -ENOTSUPP Function not supported in current display mode. - * -EIO Failed, e.g., due to failed scanout position query. + * This function can be used to implement the &drm_driver.get_vblank_timestamp + * directly, if the driver implements the &drm_driver.get_scanout_position hook. * - * Returns or'ed positive status flags on success: + * Note that atomic drivers must call drm_calc_timestamping_constants() before + * enabling a CRTC. The atomic helpers already take care of that in + * drm_atomic_helper_update_legacy_modeset_state(). * - * DRM_VBLANKTIME_SCANOUTPOS_METHOD - Signal this method used for timestamping. - * DRM_VBLANKTIME_INVBL - Timestamp taken while scanout was in vblank interval. + * Returns: * + * Returns true on success, and false on failure, i.e. when no accurate + * timestamp could be acquired. */ -int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, - unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags, - const struct drm_display_mode *mode) +bool drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, + unsigned int pipe, + int *max_error, + struct timeval *vblank_time, + bool in_vblank_irq) { struct timeval tv_etime; ktime_t stime, etime; - unsigned int vbl_status; - int ret = DRM_VBLANKTIME_SCANOUTPOS_METHOD; + bool vbl_status; + struct drm_crtc *crtc; + const struct drm_display_mode *mode; + struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; int vpos, hpos, i; int delta_ns, duration_ns; - if (pipe >= dev->num_crtcs) { + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return false; + + crtc = drm_crtc_from_index(dev, pipe); + + if (pipe >= dev->num_crtcs || !crtc) { DRM_ERROR("Invalid crtc %u\n", pipe); - return -EINVAL; + return false; } /* Scanout position query not supported? Should not happen. */ if (!dev->driver->get_scanout_position) { DRM_ERROR("Called from driver w/o get_scanout_position()!?\n"); - return -EIO; + return false; } + if (drm_drv_uses_atomic_modeset(dev)) + mode = &vblank->hwmode; + else + mode = &crtc->hwmode; + /* If mode timing undefined, just return as no-op: * Happens during initial modesetting of a crtc. */ if (mode->crtc_clock == 0) { DRM_DEBUG("crtc %u: Noop due to uninitialized mode.\n", pipe); - return -EAGAIN; + WARN_ON_ONCE(drm_drv_uses_atomic_modeset(dev)); + + return false; } /* Get current scanout position with system timestamp. @@ -783,16 +794,17 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, * Get vertical and horizontal scanout position vpos, hpos, * and bounding timestamps stime, etime, pre/post query. */ - vbl_status = dev->driver->get_scanout_position(dev, pipe, flags, + vbl_status = dev->driver->get_scanout_position(dev, pipe, + in_vblank_irq, &vpos, &hpos, &stime, &etime, mode); /* Return as no-op if scanout query unsupported or failed. */ - if (!(vbl_status & DRM_SCANOUTPOS_VALID)) { - DRM_DEBUG("crtc %u : scanoutpos query failed [0x%x].\n", - pipe, vbl_status); - return -EIO; + if (!vbl_status) { + DRM_DEBUG("crtc %u : scanoutpos query failed.\n", + pipe); + return false; } /* Compute uncertainty in timestamp of scanout position query. */ @@ -830,13 +842,13 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, etime = ktime_sub_ns(etime, delta_ns); *vblank_time = ktime_to_timeval(etime); - DRM_DEBUG_VBL("crtc %u : v 0x%x p(%d,%d)@ %ld.%ld -> %ld.%ld [e %d us, %d rep]\n", - pipe, vbl_status, hpos, vpos, + DRM_DEBUG_VBL("crtc %u : v p(%d,%d)@ %ld.%ld -> %ld.%ld [e %d us, %d rep]\n", + pipe, hpos, vpos, (long)tv_etime.tv_sec, (long)tv_etime.tv_usec, (long)vblank_time->tv_sec, (long)vblank_time->tv_usec, duration_ns/1000, i); - return ret; + return true; } EXPORT_SYMBOL(drm_calc_vbltimestamp_from_scanoutpos); @@ -854,9 +866,10 @@ static struct timeval get_drm_timestamp(void) * @dev: DRM device * @pipe: index of CRTC whose vblank timestamp to retrieve * @tvblank: Pointer to target struct timeval which should receive the timestamp - * @flags: Flags to pass to driver: - * 0 = Default, - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler + * @in_vblank_irq: + * True when called from drm_crtc_handle_vblank(). Some drivers + * need to apply some workarounds for gpu-specific vblank irq quirks + * if flag is set. * * Fetches the system timestamp corresponding to the time of the most recent * vblank interval on specified CRTC. May call into kms-driver to @@ -870,27 +883,25 @@ static struct timeval get_drm_timestamp(void) */ static bool drm_get_last_vbltimestamp(struct drm_device *dev, unsigned int pipe, - struct timeval *tvblank, unsigned flags) + struct timeval *tvblank, bool in_vblank_irq) { - int ret; + bool ret = false; /* Define requested maximum error on timestamps (nanoseconds). */ int max_error = (int) drm_timestamp_precision * 1000; /* Query driver if possible and precision timestamping enabled. */ - if (dev->driver->get_vblank_timestamp && (max_error > 0)) { + if (dev->driver->get_vblank_timestamp && (max_error > 0)) ret = dev->driver->get_vblank_timestamp(dev, pipe, &max_error, - tvblank, flags); - if (ret > 0) - return true; - } + tvblank, in_vblank_irq); /* GPU high precision timestamp query unsupported or failed. * Return current monotonic/gettimeofday timestamp as best estimate. */ - *tvblank = get_drm_timestamp(); + if (!ret) + *tvblank = get_drm_timestamp(); - return false; + return ret; } /** @@ -1329,6 +1340,10 @@ void drm_crtc_vblank_off(struct drm_crtc *crtc) send_vblank_event(dev, e, seq, &now); } spin_unlock_irqrestore(&dev->event_lock, irqflags); + + /* Will be reset by the modeset helpers when re-enabling the crtc by + * calling drm_calc_timestamping_constants(). */ + vblank->hwmode.crtc_clock = 0; } EXPORT_SYMBOL(drm_crtc_vblank_off); @@ -1760,7 +1775,7 @@ bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe) return false; } - drm_update_vblank_count(dev, pipe, DRM_CALLED_FROM_VBLIRQ); + drm_update_vblank_count(dev, pipe, true); spin_unlock(&dev->vblank_time_lock); diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index b84a295230fcd4..06aee1741e96a7 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -336,7 +336,7 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc, ret = drm_plane_helper_check_update(plane, crtc, fb, &src, &dest, &clip, - DRM_ROTATE_0, + DRM_MODE_ROTATE_0, DRM_PLANE_HELPER_NO_SCALING, DRM_PLANE_HELPER_NO_SCALING, false, false, &visible); @@ -381,6 +381,7 @@ EXPORT_SYMBOL(drm_primary_helper_update); /** * drm_primary_helper_disable() - Helper for primary plane disable * @plane: plane to disable + * @ctx: lock acquire context, not used here * * Provides a default plane disable handler for primary planes. This is handler * is called in response to a userspace SetPlane operation on the plane with a @@ -510,12 +511,10 @@ int drm_plane_helper_commit(struct drm_plane *plane, if (plane_funcs->cleanup_fb) plane_funcs->cleanup_fb(plane, plane_state); out: - if (plane_state) { - if (plane->funcs->atomic_destroy_state) - plane->funcs->atomic_destroy_state(plane, plane_state); - else - drm_atomic_helper_plane_destroy_state(plane, plane_state); - } + if (plane->funcs->atomic_destroy_state) + plane->funcs->atomic_destroy_state(plane, plane_state); + else + drm_atomic_helper_plane_destroy_state(plane, plane_state); return ret; } diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 954eb848b5e212..22408badc617b0 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -595,15 +595,18 @@ int drm_gem_prime_handle_to_fd(struct drm_device *dev, EXPORT_SYMBOL(drm_gem_prime_handle_to_fd); /** - * drm_gem_prime_import - helper library implementation of the import callback + * drm_gem_prime_import_dev - core implementation of the import callback * @dev: drm_device to import into * @dma_buf: dma-buf object to import + * @attach_dev: struct device to dma_buf attach * - * This is the implementation of the gem_prime_import functions for GEM drivers - * using the PRIME helpers. + * This is the core of drm_gem_prime_import. It's designed to be called by + * drivers who want to use a different device structure than dev->dev for + * attaching via dma_buf. */ -struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, - struct dma_buf *dma_buf) +struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev, + struct dma_buf *dma_buf, + struct device *attach_dev) { struct dma_buf_attachment *attach; struct sg_table *sgt; @@ -625,7 +628,7 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, if (!dev->driver->gem_prime_import_sg_table) return ERR_PTR(-EINVAL); - attach = dma_buf_attach(dma_buf, dev->dev); + attach = dma_buf_attach(dma_buf, attach_dev); if (IS_ERR(attach)) return ERR_CAST(attach); @@ -655,6 +658,21 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, return ERR_PTR(ret); } +EXPORT_SYMBOL(drm_gem_prime_import_dev); + +/** + * drm_gem_prime_import - helper library implementation of the import callback + * @dev: drm_device to import into + * @dma_buf: dma-buf object to import + * + * This is the implementation of the gem_prime_import functions for GEM drivers + * using the PRIME helpers. + */ +struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + return drm_gem_prime_import_dev(dev, dma_buf, dev->dev); +} EXPORT_SYMBOL(drm_gem_prime_import); /** diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c index bc5575960ebce1..9817c1445ba9ea 100644 --- a/drivers/gpu/drm/drm_rect.c +++ b/drivers/gpu/drm/drm_rect.c @@ -310,38 +310,38 @@ void drm_rect_rotate(struct drm_rect *r, { struct drm_rect tmp; - if (rotation & (DRM_REFLECT_X | DRM_REFLECT_Y)) { + if (rotation & (DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y)) { tmp = *r; - if (rotation & DRM_REFLECT_X) { + if (rotation & DRM_MODE_REFLECT_X) { r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; } - if (rotation & DRM_REFLECT_Y) { + if (rotation & DRM_MODE_REFLECT_Y) { r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; } } - switch (rotation & DRM_ROTATE_MASK) { - case DRM_ROTATE_0: + switch (rotation & DRM_MODE_ROTATE_MASK) { + case DRM_MODE_ROTATE_0: break; - case DRM_ROTATE_90: + case DRM_MODE_ROTATE_90: tmp = *r; r->x1 = tmp.y1; r->x2 = tmp.y2; r->y1 = width - tmp.x2; r->y2 = width - tmp.x1; break; - case DRM_ROTATE_180: + case DRM_MODE_ROTATE_180: tmp = *r; r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; break; - case DRM_ROTATE_270: + case DRM_MODE_ROTATE_270: tmp = *r; r->x1 = height - tmp.y2; r->x2 = height - tmp.y1; @@ -373,8 +373,8 @@ EXPORT_SYMBOL(drm_rect_rotate); * them when doing a rotatation and its inverse. * That is, if you do :: * - * drm_rotate(&r, width, height, rotation); - * drm_rotate_inv(&r, width, height, rotation); + * DRM_MODE_PROP_ROTATE(&r, width, height, rotation); + * DRM_MODE_ROTATE_inv(&r, width, height, rotation); * * you will always get back the original rectangle. */ @@ -384,24 +384,24 @@ void drm_rect_rotate_inv(struct drm_rect *r, { struct drm_rect tmp; - switch (rotation & DRM_ROTATE_MASK) { - case DRM_ROTATE_0: + switch (rotation & DRM_MODE_ROTATE_MASK) { + case DRM_MODE_ROTATE_0: break; - case DRM_ROTATE_90: + case DRM_MODE_ROTATE_90: tmp = *r; r->x1 = width - tmp.y2; r->x2 = width - tmp.y1; r->y1 = tmp.x1; r->y2 = tmp.x2; break; - case DRM_ROTATE_180: + case DRM_MODE_ROTATE_180: tmp = *r; r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; break; - case DRM_ROTATE_270: + case DRM_MODE_ROTATE_270: tmp = *r; r->x1 = tmp.y1; r->x2 = tmp.y2; @@ -412,15 +412,15 @@ void drm_rect_rotate_inv(struct drm_rect *r, break; } - if (rotation & (DRM_REFLECT_X | DRM_REFLECT_Y)) { + if (rotation & (DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y)) { tmp = *r; - if (rotation & DRM_REFLECT_X) { + if (rotation & DRM_MODE_REFLECT_X) { r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; } - if (rotation & DRM_REFLECT_Y) { + if (rotation & DRM_MODE_REFLECT_Y) { r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; } diff --git a/drivers/gpu/drm/etnaviv/common.xml.h b/drivers/gpu/drm/etnaviv/common.xml.h index e881482b5971d1..207f45c999c34e 100644 --- a/drivers/gpu/drm/etnaviv/common.xml.h +++ b/drivers/gpu/drm/etnaviv/common.xml.h @@ -8,10 +8,38 @@ This file was generated by the rules-ng-ng headergen tool in this git repository git clone git://0x04.net/rules-ng-ng The rules-ng-ng source files this header was generated from are: -- state_hi.xml ( 24309 bytes, from 2015-12-12 09:02:53) -- common.xml ( 18379 bytes, from 2015-12-12 09:02:53) +- state.xml ( 19930 bytes, from 2017-03-09 15:43:43) +- common.xml ( 23473 bytes, from 2017-03-09 15:43:43) +- state_hi.xml ( 26403 bytes, from 2017-03-09 15:43:43) +- copyright.xml ( 1597 bytes, from 2016-12-08 16:37:56) +- state_2d.xml ( 51552 bytes, from 2016-12-08 16:37:56) +- state_3d.xml ( 66957 bytes, from 2017-03-09 15:43:43) +- state_vg.xml ( 5975 bytes, from 2016-12-08 16:37:56) -Copyright (C) 2015 +Copyright (C) 2012-2017 by the following authors: +- Wladimir J. van der Laan +- Christian Gmeiner +- Lucas Stach +- Russell King + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the "Software"), +to deal in the Software without restriction, including without limitation +the rights to use, copy, modify, merge, publish, distribute, sub license, +and/or sell copies of the Software, and to permit persons to whom the +Software is furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice (including the +next paragraph) shall be included in all copies or substantial portions +of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL +THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. */ @@ -162,129 +190,129 @@ Copyright (C) 2015 #define chipMinorFeatures1_FC_FLUSH_STALL 0x80000000 #define chipMinorFeatures2_LINE_LOOP 0x00000001 #define chipMinorFeatures2_LOGIC_OP 0x00000002 -#define chipMinorFeatures2_UNK2 0x00000004 +#define chipMinorFeatures2_SEAMLESS_CUBE_MAP 0x00000004 #define chipMinorFeatures2_SUPERTILED_TEXTURE 0x00000008 -#define chipMinorFeatures2_UNK4 0x00000010 +#define chipMinorFeatures2_LINEAR_PE 0x00000010 #define chipMinorFeatures2_RECT_PRIMITIVE 0x00000020 #define chipMinorFeatures2_COMPOSITION 0x00000040 #define chipMinorFeatures2_CORRECT_AUTO_DISABLE_COUNT 0x00000080 -#define chipMinorFeatures2_UNK8 0x00000100 -#define chipMinorFeatures2_UNK9 0x00000200 -#define chipMinorFeatures2_UNK10 0x00000400 +#define chipMinorFeatures2_PE_SWIZZLE 0x00000100 +#define chipMinorFeatures2_END_EVENT 0x00000200 +#define chipMinorFeatures2_S1S8 0x00000400 #define chipMinorFeatures2_HALTI1 0x00000800 -#define chipMinorFeatures2_UNK12 0x00001000 -#define chipMinorFeatures2_UNK13 0x00002000 -#define chipMinorFeatures2_UNK14 0x00004000 +#define chipMinorFeatures2_RGB888 0x00001000 +#define chipMinorFeatures2_TX__YUV_ASSEMBLER 0x00002000 +#define chipMinorFeatures2_DYNAMIC_FREQUENCY_SCALING 0x00004000 #define chipMinorFeatures2_EXTRA_TEXTURE_STATE 0x00008000 #define chipMinorFeatures2_FULL_DIRECTFB 0x00010000 #define chipMinorFeatures2_2D_TILING 0x00020000 #define chipMinorFeatures2_THREAD_WALKER_IN_PS 0x00040000 #define chipMinorFeatures2_TILE_FILLER 0x00080000 -#define chipMinorFeatures2_UNK20 0x00100000 +#define chipMinorFeatures2_YUV_STANDARD 0x00100000 #define chipMinorFeatures2_2D_MULTI_SOURCE_BLIT 0x00200000 -#define chipMinorFeatures2_UNK22 0x00400000 -#define chipMinorFeatures2_UNK23 0x00800000 -#define chipMinorFeatures2_UNK24 0x01000000 +#define chipMinorFeatures2_YUV_CONVERSION 0x00400000 +#define chipMinorFeatures2_FLUSH_FIXED_2D 0x00800000 +#define chipMinorFeatures2_INTERLEAVER 0x01000000 #define chipMinorFeatures2_MIXED_STREAMS 0x02000000 #define chipMinorFeatures2_2D_420_L2CACHE 0x04000000 -#define chipMinorFeatures2_UNK27 0x08000000 +#define chipMinorFeatures2_BUG_FIXES7 0x08000000 #define chipMinorFeatures2_2D_NO_INDEX8_BRUSH 0x10000000 #define chipMinorFeatures2_TEXTURE_TILED_READ 0x20000000 -#define chipMinorFeatures2_UNK30 0x40000000 -#define chipMinorFeatures2_UNK31 0x80000000 +#define chipMinorFeatures2_DECOMPRESS_Z16 0x40000000 +#define chipMinorFeatures2_BUG_FIXES8 0x80000000 #define chipMinorFeatures3_ROTATION_STALL_FIX 0x00000001 -#define chipMinorFeatures3_UNK1 0x00000002 +#define chipMinorFeatures3_OCL_ONLY 0x00000002 #define chipMinorFeatures3_2D_MULTI_SOURCE_BLT_EX 0x00000004 -#define chipMinorFeatures3_UNK3 0x00000008 -#define chipMinorFeatures3_UNK4 0x00000010 -#define chipMinorFeatures3_UNK5 0x00000020 -#define chipMinorFeatures3_UNK6 0x00000040 -#define chipMinorFeatures3_UNK7 0x00000080 +#define chipMinorFeatures3_INSTRUCTION_CACHE 0x00000008 +#define chipMinorFeatures3_GEOMETRY_SHADER 0x00000010 +#define chipMinorFeatures3_TEX_COMPRESSION_SUPERTILED 0x00000020 +#define chipMinorFeatures3_GENERICS 0x00000040 +#define chipMinorFeatures3_BUG_FIXES9 0x00000080 #define chipMinorFeatures3_FAST_MSAA 0x00000100 -#define chipMinorFeatures3_UNK9 0x00000200 +#define chipMinorFeatures3_WCLIP 0x00000200 #define chipMinorFeatures3_BUG_FIXES10 0x00000400 -#define chipMinorFeatures3_UNK11 0x00000800 +#define chipMinorFeatures3_UNIFIED_SAMPLERS 0x00000800 #define chipMinorFeatures3_BUG_FIXES11 0x00001000 -#define chipMinorFeatures3_UNK13 0x00002000 -#define chipMinorFeatures3_UNK14 0x00004000 -#define chipMinorFeatures3_UNK15 0x00008000 -#define chipMinorFeatures3_UNK16 0x00010000 -#define chipMinorFeatures3_UNK17 0x00020000 +#define chipMinorFeatures3_PERFORMANCE_COUNTERS 0x00002000 +#define chipMinorFeatures3_HAS_FAST_TRANSCENDENTALS 0x00004000 +#define chipMinorFeatures3_BUG_FIXES12 0x00008000 +#define chipMinorFeatures3_BUG_FIXES13 0x00010000 +#define chipMinorFeatures3_DE_ENHANCEMENTS1 0x00020000 #define chipMinorFeatures3_ACE 0x00040000 -#define chipMinorFeatures3_UNK19 0x00080000 -#define chipMinorFeatures3_UNK20 0x00100000 -#define chipMinorFeatures3_UNK21 0x00200000 +#define chipMinorFeatures3_TX_ENHANCEMENTS1 0x00080000 +#define chipMinorFeatures3_SH_ENHANCEMENTS1 0x00100000 +#define chipMinorFeatures3_SH_ENHANCEMENTS2 0x00200000 #define chipMinorFeatures3_UNK22 0x00400000 -#define chipMinorFeatures3_UNK23 0x00800000 +#define chipMinorFeatures3_2D_FC_SOURCE 0x00800000 #define chipMinorFeatures3_UNK24 0x01000000 #define chipMinorFeatures3_UNK25 0x02000000 #define chipMinorFeatures3_NEW_HZ 0x04000000 #define chipMinorFeatures3_UNK27 0x08000000 #define chipMinorFeatures3_UNK28 0x10000000 -#define chipMinorFeatures3_UNK29 0x20000000 +#define chipMinorFeatures3_SH_ENHANCEMENTS3 0x20000000 #define chipMinorFeatures3_UNK30 0x40000000 #define chipMinorFeatures3_UNK31 0x80000000 #define chipMinorFeatures4_UNK0 0x00000001 -#define chipMinorFeatures4_UNK1 0x00000002 -#define chipMinorFeatures4_UNK2 0x00000004 +#define chipMinorFeatures4_PE_ENHANCEMENTS2 0x00000002 +#define chipMinorFeatures4_FRUSTUM_CLIP_FIX 0x00000004 #define chipMinorFeatures4_UNK3 0x00000008 #define chipMinorFeatures4_UNK4 0x00000010 -#define chipMinorFeatures4_UNK5 0x00000020 -#define chipMinorFeatures4_UNK6 0x00000040 +#define chipMinorFeatures4_2D_GAMMA 0x00000020 +#define chipMinorFeatures4_SINGLE_BUFFER 0x00000040 #define chipMinorFeatures4_UNK7 0x00000080 #define chipMinorFeatures4_UNK8 0x00000100 #define chipMinorFeatures4_UNK9 0x00000200 #define chipMinorFeatures4_UNK10 0x00000400 -#define chipMinorFeatures4_UNK11 0x00000800 -#define chipMinorFeatures4_UNK12 0x00001000 -#define chipMinorFeatures4_UNK13 0x00002000 +#define chipMinorFeatures4_TX_LERP_PRECISION_FIX 0x00000800 +#define chipMinorFeatures4_2D_COLOR_SPACE_CONVERSION 0x00001000 +#define chipMinorFeatures4_TEXTURE_ASTC 0x00002000 #define chipMinorFeatures4_UNK14 0x00004000 #define chipMinorFeatures4_UNK15 0x00008000 #define chipMinorFeatures4_HALTI2 0x00010000 #define chipMinorFeatures4_UNK17 0x00020000 #define chipMinorFeatures4_SMALL_MSAA 0x00040000 #define chipMinorFeatures4_UNK19 0x00080000 -#define chipMinorFeatures4_UNK20 0x00100000 -#define chipMinorFeatures4_UNK21 0x00200000 -#define chipMinorFeatures4_UNK22 0x00400000 -#define chipMinorFeatures4_UNK23 0x00800000 -#define chipMinorFeatures4_UNK24 0x01000000 -#define chipMinorFeatures4_UNK25 0x02000000 -#define chipMinorFeatures4_UNK26 0x04000000 -#define chipMinorFeatures4_UNK27 0x08000000 +#define chipMinorFeatures4_NEW_RA 0x00100000 +#define chipMinorFeatures4_2D_OPF_YUV_OUTPUT 0x00200000 +#define chipMinorFeatures4_2D_MULTI_SOURCE_BLT_EX2 0x00400000 +#define chipMinorFeatures4_NO_USER_CSC 0x00800000 +#define chipMinorFeatures4_ZFIXES 0x01000000 +#define chipMinorFeatures4_BUG_FIXES18 0x02000000 +#define chipMinorFeatures4_2D_COMPRESSION 0x04000000 +#define chipMinorFeatures4_PROBE 0x08000000 #define chipMinorFeatures4_UNK28 0x10000000 -#define chipMinorFeatures4_UNK29 0x20000000 +#define chipMinorFeatures4_2D_SUPER_TILE_VERSION 0x20000000 #define chipMinorFeatures4_UNK30 0x40000000 #define chipMinorFeatures4_UNK31 0x80000000 #define chipMinorFeatures5_UNK0 0x00000001 #define chipMinorFeatures5_UNK1 0x00000002 #define chipMinorFeatures5_UNK2 0x00000004 #define chipMinorFeatures5_UNK3 0x00000008 -#define chipMinorFeatures5_UNK4 0x00000010 +#define chipMinorFeatures5_EEZ 0x00000010 #define chipMinorFeatures5_UNK5 0x00000020 #define chipMinorFeatures5_UNK6 0x00000040 #define chipMinorFeatures5_UNK7 0x00000080 #define chipMinorFeatures5_UNK8 0x00000100 #define chipMinorFeatures5_HALTI3 0x00000200 #define chipMinorFeatures5_UNK10 0x00000400 -#define chipMinorFeatures5_UNK11 0x00000800 +#define chipMinorFeatures5_2D_ONE_PASS_FILTER_TAP 0x00000800 #define chipMinorFeatures5_UNK12 0x00001000 -#define chipMinorFeatures5_UNK13 0x00002000 -#define chipMinorFeatures5_UNK14 0x00004000 +#define chipMinorFeatures5_SEPARATE_SRC_DST 0x00002000 +#define chipMinorFeatures5_HALTI4 0x00004000 #define chipMinorFeatures5_UNK15 0x00008000 -#define chipMinorFeatures5_UNK16 0x00010000 -#define chipMinorFeatures5_UNK17 0x00020000 +#define chipMinorFeatures5_ANDROID_ONLY 0x00010000 +#define chipMinorFeatures5_HAS_PRODUCTID 0x00020000 #define chipMinorFeatures5_UNK18 0x00040000 #define chipMinorFeatures5_UNK19 0x00080000 -#define chipMinorFeatures5_UNK20 0x00100000 +#define chipMinorFeatures5_PE_DITHER_FIX2 0x00100000 #define chipMinorFeatures5_UNK21 0x00200000 #define chipMinorFeatures5_UNK22 0x00400000 #define chipMinorFeatures5_UNK23 0x00800000 #define chipMinorFeatures5_UNK24 0x01000000 #define chipMinorFeatures5_UNK25 0x02000000 #define chipMinorFeatures5_UNK26 0x04000000 -#define chipMinorFeatures5_UNK27 0x08000000 -#define chipMinorFeatures5_UNK28 0x10000000 +#define chipMinorFeatures5_RS_DEPTHSTENCIL_NATIVE_SUPPORT 0x08000000 +#define chipMinorFeatures5_V2_MSAA_COMP_FIX 0x10000000 #define chipMinorFeatures5_UNK29 0x20000000 #define chipMinorFeatures5_UNK30 0x40000000 #define chipMinorFeatures5_UNK31 0x80000000 diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 5255278dde5603..91e17aeee1da5f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -495,6 +495,7 @@ static struct drm_driver etnaviv_drm_driver = { .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, + .gem_prime_res_obj = etnaviv_gem_prime_res_obj, .gem_prime_pin = etnaviv_gem_prime_pin, .gem_prime_unpin = etnaviv_gem_prime_unpin, .gem_prime_get_sg_table = etnaviv_gem_prime_get_sg_table, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h index e41f38667c1c85..058389f93b697a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h @@ -80,6 +80,7 @@ void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj); void etnaviv_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); int etnaviv_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); +struct reservation_object *etnaviv_gem_prime_res_obj(struct drm_gem_object *obj); struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); int etnaviv_gem_prime_pin(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index fd56f92f3469a0..d6fb724fc3ccc9 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -748,7 +748,7 @@ static struct page **etnaviv_gem_userptr_do_get_pages( uintptr_t ptr; unsigned int flags = 0; - pvec = drm_malloc_ab(npages, sizeof(struct page *)); + pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!pvec) return ERR_PTR(-ENOMEM); @@ -772,7 +772,7 @@ static struct page **etnaviv_gem_userptr_do_get_pages( if (ret < 0) { release_pages(pvec, pinned, 0); - drm_free_large(pvec); + kvfree(pvec); return ERR_PTR(ret); } @@ -823,7 +823,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) mm = get_task_mm(etnaviv_obj->userptr.task); pinned = 0; if (mm == current->mm) { - pvec = drm_malloc_ab(npages, sizeof(struct page *)); + pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!pvec) { mmput(mm); return -ENOMEM; @@ -832,7 +832,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) pinned = __get_user_pages_fast(etnaviv_obj->userptr.ptr, npages, !etnaviv_obj->userptr.ro, pvec); if (pinned < 0) { - drm_free_large(pvec); + kvfree(pvec); mmput(mm); return pinned; } @@ -845,7 +845,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) } release_pages(pvec, pinned, 0); - drm_free_large(pvec); + kvfree(pvec); work = kmalloc(sizeof(*work), GFP_KERNEL); if (!work) { @@ -879,7 +879,7 @@ static void etnaviv_gem_userptr_release(struct etnaviv_gem_object *etnaviv_obj) int npages = etnaviv_obj->base.size >> PAGE_SHIFT; release_pages(etnaviv_obj->pages, npages, 0); - drm_free_large(etnaviv_obj->pages); + kvfree(etnaviv_obj->pages); } put_task_struct(etnaviv_obj->userptr.task); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index 62b47972a52e6e..e5da4f2300ba13 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -87,7 +87,7 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj) * ours, just free the array we allocated: */ if (etnaviv_obj->pages) - drm_free_large(etnaviv_obj->pages); + kvfree(etnaviv_obj->pages); drm_prime_gem_destroy(&etnaviv_obj->base, etnaviv_obj->sgt); } @@ -128,7 +128,7 @@ struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, npages = size / PAGE_SIZE; etnaviv_obj->sgt = sgt; - etnaviv_obj->pages = drm_malloc_ab(npages, sizeof(struct page *)); + etnaviv_obj->pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!etnaviv_obj->pages) { ret = -ENOMEM; goto fail; @@ -150,3 +150,10 @@ struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, return ERR_PTR(ret); } + +struct reservation_object *etnaviv_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + + return etnaviv_obj->resv; +} diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index de80ee1b71dfa2..ee7069e93eda28 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -345,9 +345,9 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, * Copy the command submission and bo array to kernel space in * one go, and do this outside of any locks. */ - bos = drm_malloc_ab(args->nr_bos, sizeof(*bos)); - relocs = drm_malloc_ab(args->nr_relocs, sizeof(*relocs)); - stream = drm_malloc_ab(1, args->stream_size); + bos = kvmalloc_array(args->nr_bos, sizeof(*bos), GFP_KERNEL); + relocs = kvmalloc_array(args->nr_relocs, sizeof(*relocs), GFP_KERNEL); + stream = kvmalloc_array(1, args->stream_size, GFP_KERNEL); cmdbuf = etnaviv_cmdbuf_new(gpu->cmdbuf_suballoc, ALIGN(args->stream_size, 8) + 8, args->nr_bos); @@ -489,11 +489,11 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, if (cmdbuf) etnaviv_cmdbuf_free(cmdbuf); if (stream) - drm_free_large(stream); + kvfree(stream); if (bos) - drm_free_large(bos); + kvfree(bos); if (relocs) - drm_free_large(relocs); + kvfree(relocs); return ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 9a9c407178018a..ada45fdd0eaeea 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -412,13 +412,19 @@ static void etnaviv_gpu_load_clock(struct etnaviv_gpu *gpu, u32 clock) static void etnaviv_gpu_update_clock(struct etnaviv_gpu *gpu) { - unsigned int fscale = 1 << (6 - gpu->freq_scale); - u32 clock; - - clock = VIVS_HI_CLOCK_CONTROL_DISABLE_DEBUG_REGISTERS | - VIVS_HI_CLOCK_CONTROL_FSCALE_VAL(fscale); + if (gpu->identity.minor_features2 & + chipMinorFeatures2_DYNAMIC_FREQUENCY_SCALING) { + clk_set_rate(gpu->clk_core, + gpu->base_rate_core >> gpu->freq_scale); + clk_set_rate(gpu->clk_shader, + gpu->base_rate_shader >> gpu->freq_scale); + } else { + unsigned int fscale = 1 << (6 - gpu->freq_scale); + u32 clock = VIVS_HI_CLOCK_CONTROL_DISABLE_DEBUG_REGISTERS | + VIVS_HI_CLOCK_CONTROL_FSCALE_VAL(fscale); - etnaviv_gpu_load_clock(gpu, clock); + etnaviv_gpu_load_clock(gpu, clock); + } } static int etnaviv_hw_reset(struct etnaviv_gpu *gpu) @@ -523,9 +529,10 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) pmc = gpu_read(gpu, VIVS_PM_MODULE_CONTROLS); - /* Disable PA clock gating for GC400+ except for GC420 */ + /* Disable PA clock gating for GC400+ without bugfix except for GC420 */ if (gpu->identity.model >= chipModel_GC400 && - gpu->identity.model != chipModel_GC420) + gpu->identity.model != chipModel_GC420 && + !(gpu->identity.minor_features3 & chipMinorFeatures3_BUG_FIXES12)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PA; /* @@ -541,6 +548,11 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) if (gpu->identity.revision < 0x5422) pmc |= BIT(15); /* Unknown bit */ + /* Disable TX clock gating on affected core revisions. */ + if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) || + etnaviv_is_model_rev(gpu, GC2000, 0x5108)) + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ; pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ; @@ -1736,11 +1748,13 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) DBG("clk_core: %p", gpu->clk_core); if (IS_ERR(gpu->clk_core)) gpu->clk_core = NULL; + gpu->base_rate_core = clk_get_rate(gpu->clk_core); gpu->clk_shader = devm_clk_get(&pdev->dev, "shader"); DBG("clk_shader: %p", gpu->clk_shader); if (IS_ERR(gpu->clk_shader)) gpu->clk_shader = NULL; + gpu->base_rate_shader = clk_get_rate(gpu->clk_shader); /* TODO: figure out max mapped size */ dev_set_drvdata(dev, gpu); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 9227a97404473b..689cb8f3680c97 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -152,6 +152,8 @@ struct etnaviv_gpu { u32 hangcheck_dma_addr; struct work_struct recover_work; unsigned int freq_scale; + unsigned long base_rate_core; + unsigned long base_rate_shader; }; static inline void gpu_write(struct etnaviv_gpu *gpu, u32 reg, u32 data) diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 55a1579d11b3d7..c23479be485000 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -59,7 +59,8 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem *exynos_gem) nr_pages = exynos_gem->size >> PAGE_SHIFT; - exynos_gem->pages = drm_calloc_large(nr_pages, sizeof(struct page *)); + exynos_gem->pages = kvmalloc_array(nr_pages, sizeof(struct page *), + GFP_KERNEL | __GFP_ZERO); if (!exynos_gem->pages) { DRM_ERROR("failed to allocate pages.\n"); return -ENOMEM; @@ -101,7 +102,7 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem *exynos_gem) dma_free_attrs(to_dma_dev(dev), exynos_gem->size, exynos_gem->cookie, exynos_gem->dma_addr, exynos_gem->dma_attrs); err_free: - drm_free_large(exynos_gem->pages); + kvfree(exynos_gem->pages); return ret; } @@ -122,7 +123,7 @@ static void exynos_drm_free_buf(struct exynos_drm_gem *exynos_gem) (dma_addr_t)exynos_gem->dma_addr, exynos_gem->dma_attrs); - drm_free_large(exynos_gem->pages); + kvfree(exynos_gem->pages); } static int exynos_drm_gem_handle_create(struct drm_gem_object *obj, @@ -559,7 +560,7 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, exynos_gem->dma_addr = sg_dma_address(sgt->sgl); npages = exynos_gem->size >> PAGE_SHIFT; - exynos_gem->pages = drm_malloc_ab(npages, sizeof(struct page *)); + exynos_gem->pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!exynos_gem->pages) { ret = -ENOMEM; goto err; @@ -588,7 +589,7 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, return &exynos_gem->base; err_free_large: - drm_free_large(exynos_gem->pages); + kvfree(exynos_gem->pages); err: drm_gem_object_release(&exynos_gem->base); kfree(exynos_gem); diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile index 190e55f2f89104..c1c8dc18aa5357 100644 --- a/drivers/gpu/drm/gma500/Makefile +++ b/drivers/gpu/drm/gma500/Makefile @@ -1,7 +1,6 @@ # # KMS driver for the GMA500 # -ccflags-y += -I$(srctree)/include/drm gma500_gfx-y += \ accel_2d.o \ diff --git a/drivers/gpu/drm/gma500/mdfld_tpo_vid.c b/drivers/gpu/drm/gma500/mdfld_tpo_vid.c index d8d4170725b293..a9420bf9a4198e 100644 --- a/drivers/gpu/drm/gma500/mdfld_tpo_vid.c +++ b/drivers/gpu/drm/gma500/mdfld_tpo_vid.c @@ -30,55 +30,20 @@ static struct drm_display_mode *tpo_vid_get_config_mode(struct drm_device *dev) { struct drm_display_mode *mode; - struct drm_psb_private *dev_priv = dev->dev_private; - struct oaktrail_timing_info *ti = &dev_priv->gct_data.DTD; - bool use_gct = false; mode = kzalloc(sizeof(*mode), GFP_KERNEL); if (!mode) return NULL; - if (use_gct) { - mode->hdisplay = (ti->hactive_hi << 8) | ti->hactive_lo; - mode->vdisplay = (ti->vactive_hi << 8) | ti->vactive_lo; - mode->hsync_start = mode->hdisplay + - ((ti->hsync_offset_hi << 8) | - ti->hsync_offset_lo); - mode->hsync_end = mode->hsync_start + - ((ti->hsync_pulse_width_hi << 8) | - ti->hsync_pulse_width_lo); - mode->htotal = mode->hdisplay + ((ti->hblank_hi << 8) | - ti->hblank_lo); - mode->vsync_start = - mode->vdisplay + ((ti->vsync_offset_hi << 8) | - ti->vsync_offset_lo); - mode->vsync_end = - mode->vsync_start + ((ti->vsync_pulse_width_hi << 8) | - ti->vsync_pulse_width_lo); - mode->vtotal = mode->vdisplay + - ((ti->vblank_hi << 8) | ti->vblank_lo); - mode->clock = ti->pixel_clock * 10; - - dev_dbg(dev->dev, "hdisplay is %d\n", mode->hdisplay); - dev_dbg(dev->dev, "vdisplay is %d\n", mode->vdisplay); - dev_dbg(dev->dev, "HSS is %d\n", mode->hsync_start); - dev_dbg(dev->dev, "HSE is %d\n", mode->hsync_end); - dev_dbg(dev->dev, "htotal is %d\n", mode->htotal); - dev_dbg(dev->dev, "VSS is %d\n", mode->vsync_start); - dev_dbg(dev->dev, "VSE is %d\n", mode->vsync_end); - dev_dbg(dev->dev, "vtotal is %d\n", mode->vtotal); - dev_dbg(dev->dev, "clock is %d\n", mode->clock); - } else { - mode->hdisplay = 864; - mode->vdisplay = 480; - mode->hsync_start = 873; - mode->hsync_end = 876; - mode->htotal = 887; - mode->vsync_start = 487; - mode->vsync_end = 490; - mode->vtotal = 499; - mode->clock = 33264; - } + mode->hdisplay = 864; + mode->vdisplay = 480; + mode->hsync_start = 873; + mode->hsync_end = 876; + mode->htotal = 887; + mode->vsync_start = 487; + mode->vsync_end = 490; + mode->vtotal = 499; + mode->clock = 33264; drm_mode_set_name(mode); drm_mode_set_crtcinfo(mode, 0); diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile index f2e04c0356734a..3df726696372fd 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Makefile +++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile @@ -1,4 +1,3 @@ -ccflags-y := -Iinclude/drm hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_fbdev.o hibmc_ttm.o obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c index 20732b62d4c95d..ac457c779caad6 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c @@ -17,7 +17,7 @@ */ #include -#include +#include #include "hibmc_drm_drv.h" diff --git a/drivers/gpu/drm/i2c/Makefile b/drivers/gpu/drm/i2c/Makefile index 43aa33baebed8e..a77acfc1852ebc 100644 --- a/drivers/gpu/drm/i2c/Makefile +++ b/drivers/gpu/drm/i2c/Makefile @@ -1,5 +1,3 @@ -ccflags-y := -Iinclude/drm - ch7006-y := ch7006_drv.o ch7006_mode.o obj-$(CONFIG_DRM_I2C_CH7006) += ch7006.o diff --git a/drivers/gpu/drm/i810/Makefile b/drivers/gpu/drm/i810/Makefile index 43844ecafcc56b..639f8596c9789c 100644 --- a/drivers/gpu/drm/i810/Makefile +++ b/drivers/gpu/drm/i810/Makefile @@ -2,7 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm i810-y := i810_drv.o i810_dma.o obj-$(CONFIG_DRM_I810) += i810.o diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index b00edd3b8800d2..78c5c049a347bc 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -61,6 +61,18 @@ config DRM_I915_SW_FENCE_DEBUG_OBJECTS If in doubt, say "N". +config DRM_I915_SW_FENCE_CHECK_DAG + bool "Enable additional driver debugging for detecting dependency cycles" + depends on DRM_I915 + default n + help + Choose this option to turn on extra driver debugging that may affect + performance but will catch some internal issues. + + Recommended for driver developers only. + + If in doubt, say "N". + config DRM_I915_SELFTEST bool "Enable selftests upon driver load" depends on DRM_I915 diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 2cf04504e494bd..16dccf550412dc 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -16,6 +16,7 @@ i915-y := i915_drv.o \ i915_params.o \ i915_pci.o \ i915_suspend.o \ + i915_syncmap.o \ i915_sw_fence.o \ i915_sysfs.o \ intel_csr.o \ @@ -57,6 +58,7 @@ i915-y += i915_cmd_parser.o \ # general-purpose microcontroller (GuC) support i915-y += intel_uc.o \ + intel_guc_ct.o \ intel_guc_log.o \ intel_guc_loader.o \ intel_huc.o \ diff --git a/drivers/gpu/drm/i915/dvo_ch7017.c b/drivers/gpu/drm/i915/dvo_ch7017.c index b3c7c199200cd3..80b3e16cf48c0a 100644 --- a/drivers/gpu/drm/i915/dvo_ch7017.c +++ b/drivers/gpu/drm/i915/dvo_ch7017.c @@ -280,10 +280,10 @@ static void ch7017_mode_set(struct intel_dvo_device *dvo, (0 << CH7017_PHASE_DETECTOR_SHIFT); } else { outputs_enable = CH7017_LVDS_CHANNEL_A | CH7017_CHARGE_PUMP_HIGH; - lvds_pll_feedback_div = CH7017_LVDS_PLL_FEEDBACK_DEFAULT_RESERVED | + lvds_pll_feedback_div = + CH7017_LVDS_PLL_FEEDBACK_DEFAULT_RESERVED | (2 << CH7017_LVDS_PLL_FEED_BACK_DIVIDER_SHIFT) | (3 << CH7017_LVDS_PLL_FEED_FORWARD_DIVIDER_SHIFT); - lvds_pll_feedback_div = 35; lvds_control_2 = (3 << CH7017_LOOP_FILTER_SHIFT) | (0 << CH7017_PHASE_DETECTOR_SHIFT); if (1) { /* XXX: dual channel panel detection. Assume yes for now. */ diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c index 44b3159f2fe830..7aeeffd2428b68 100644 --- a/drivers/gpu/drm/i915/dvo_ch7xxx.c +++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c @@ -217,9 +217,8 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo, name = ch7xxx_get_id(vendor); if (!name) { - DRM_DEBUG_KMS("ch7xxx not detected; got 0x%02x from %s " - "slave %d.\n", - vendor, adapter->name, dvo->slave_addr); + DRM_DEBUG_KMS("ch7xxx not detected; got VID 0x%02x from %s slave %d.\n", + vendor, adapter->name, dvo->slave_addr); goto out; } @@ -229,9 +228,8 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo, devid = ch7xxx_get_did(device); if (!devid) { - DRM_DEBUG_KMS("ch7xxx not detected; got 0x%02x from %s " - "slave %d.\n", - vendor, adapter->name, dvo->slave_addr); + DRM_DEBUG_KMS("ch7xxx not detected; got DID 0x%02x from %s slave %d.\n", + device, adapter->name, dvo->slave_addr); goto out; } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index bada32b332378a..6ae286cb5804ae 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -69,8 +69,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) gvt_dbg_sched("ring id %d workload lrca %x", ring_id, workload->ctx_desc.lrca); - context_page_num = intel_lr_context_size( - gvt->dev_priv->engine[ring_id]); + context_page_num = gvt->dev_priv->engine[ring_id]->context_size; context_page_num = context_page_num >> PAGE_SHIFT; @@ -181,6 +180,7 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) struct intel_engine_cs *engine = dev_priv->engine[ring_id]; struct drm_i915_gem_request *rq; struct intel_vgpu *vgpu = workload->vgpu; + struct intel_ring *ring; int ret; gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n", @@ -199,8 +199,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) * shadow_ctx pages invalid. So gvt need to pin itself. After update * the guest context, gvt can unpin the shadow_ctx safely. */ - ret = engine->context_pin(engine, shadow_ctx); - if (ret) { + ring = engine->context_pin(engine, shadow_ctx); + if (IS_ERR(ring)) { + ret = PTR_ERR(ring); gvt_vgpu_err("fail to pin shadow context\n"); workload->status = ret; mutex_unlock(&dev_priv->drm.struct_mutex); @@ -330,8 +331,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload) gvt_dbg_sched("ring id %d workload lrca %x\n", ring_id, workload->ctx_desc.lrca); - context_page_num = intel_lr_context_size( - gvt->dev_priv->engine[ring_id]); + context_page_num = gvt->dev_priv->engine[ring_id]->context_size; context_page_num = context_page_num >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 7af100f844101c..f0cb22cc0dd6e5 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1166,8 +1166,8 @@ static bool check_cmd(const struct intel_engine_cs *engine, find_reg(engine, is_master, reg_addr); if (!reg) { - DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (exec_id=%d)\n", - reg_addr, *cmd, engine->exec_id); + DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n", + reg_addr, *cmd, engine->name); return false; } @@ -1222,11 +1222,11 @@ static bool check_cmd(const struct intel_engine_cs *engine, desc->bits[i].mask; if (dword != desc->bits[i].expected) { - DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (exec_id=%d)\n", + DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n", *cmd, desc->bits[i].mask, desc->bits[i].expected, - dword, engine->exec_id); + dword, engine->name); return false; } } @@ -1284,7 +1284,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, if (*cmd == MI_BATCH_BUFFER_END) { if (needs_clflush_after) { - void *ptr = ptr_mask_bits(shadow_batch_obj->mm.mapping); + void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr); } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index d689e511744e8f..3b088685a553a4 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -229,7 +229,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data) int ret; total = READ_ONCE(dev_priv->mm.object_count); - objects = drm_malloc_ab(total, sizeof(*objects)); + objects = kvmalloc_array(total, sizeof(*objects), GFP_KERNEL); if (!objects) return -ENOMEM; @@ -274,7 +274,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data) mutex_unlock(&dev->struct_mutex); out: - drm_free_large(objects); + kvfree(objects); return ret; } @@ -2482,8 +2482,6 @@ static void i915_guc_client_info(struct seq_file *m, client->wq_size, client->wq_offset, client->wq_tail); seq_printf(m, "\tWork queue full: %u\n", client->no_wq_space); - seq_printf(m, "\tFailed doorbell: %u\n", client->b_fail); - seq_printf(m, "\tLast submission result: %d\n", client->retcode); for_each_engine(engine, dev_priv, id) { u64 submissions = client->submissions[id]; @@ -2494,42 +2492,34 @@ static void i915_guc_client_info(struct seq_file *m, seq_printf(m, "\tTotal: %llu\n", tot); } -static int i915_guc_info(struct seq_file *m, void *data) +static bool check_guc_submission(struct seq_file *m) { struct drm_i915_private *dev_priv = node_to_i915(m->private); const struct intel_guc *guc = &dev_priv->guc; - struct intel_engine_cs *engine; - enum intel_engine_id id; - u64 total; if (!guc->execbuf_client) { seq_printf(m, "GuC submission %s\n", HAS_GUC_SCHED(dev_priv) ? "disabled" : "not supported"); - return 0; + return false; } + return true; +} + +static int i915_guc_info(struct seq_file *m, void *data) +{ + struct drm_i915_private *dev_priv = node_to_i915(m->private); + const struct intel_guc *guc = &dev_priv->guc; + + if (!check_guc_submission(m)) + return 0; + seq_printf(m, "Doorbell map:\n"); seq_printf(m, "\t%*pb\n", GUC_NUM_DOORBELLS, guc->doorbell_bitmap); seq_printf(m, "Doorbell next cacheline: 0x%x\n\n", guc->db_cacheline); - seq_printf(m, "GuC total action count: %llu\n", guc->action_count); - seq_printf(m, "GuC action failure count: %u\n", guc->action_fail); - seq_printf(m, "GuC last action command: 0x%x\n", guc->action_cmd); - seq_printf(m, "GuC last action status: 0x%x\n", guc->action_status); - seq_printf(m, "GuC last action error code: %d\n", guc->action_err); - - total = 0; - seq_printf(m, "\nGuC submissions:\n"); - for_each_engine(engine, dev_priv, id) { - u64 submissions = guc->submissions[id]; - total += submissions; - seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x\n", - engine->name, submissions, guc->last_seqno[id]); - } - seq_printf(m, "\t%s: %llu\n", "Total", total); - seq_printf(m, "\nGuC execbuf client @ %p:\n", guc->execbuf_client); i915_guc_client_info(m, dev_priv, guc->execbuf_client); @@ -2540,36 +2530,99 @@ static int i915_guc_info(struct seq_file *m, void *data) return 0; } -static int i915_guc_log_dump(struct seq_file *m, void *data) +static int i915_guc_stage_pool(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_i915_gem_object *obj; - int i = 0, pg; + const struct intel_guc *guc = &dev_priv->guc; + struct guc_stage_desc *desc = guc->stage_desc_pool_vaddr; + struct i915_guc_client *client = guc->execbuf_client; + unsigned int tmp; + int index; - if (!dev_priv->guc.log.vma) + if (!check_guc_submission(m)) return 0; - obj = dev_priv->guc.log.vma->obj; - for (pg = 0; pg < obj->base.size / PAGE_SIZE; pg++) { - u32 *log = kmap_atomic(i915_gem_object_get_page(obj, pg)); + for (index = 0; index < GUC_MAX_STAGE_DESCRIPTORS; index++, desc++) { + struct intel_engine_cs *engine; - for (i = 0; i < PAGE_SIZE / sizeof(u32); i += 4) - seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n", - *(log + i), *(log + i + 1), - *(log + i + 2), *(log + i + 3)); + if (!(desc->attribute & GUC_STAGE_DESC_ATTR_ACTIVE)) + continue; + + seq_printf(m, "GuC stage descriptor %u:\n", index); + seq_printf(m, "\tIndex: %u\n", desc->stage_id); + seq_printf(m, "\tAttribute: 0x%x\n", desc->attribute); + seq_printf(m, "\tPriority: %d\n", desc->priority); + seq_printf(m, "\tDoorbell id: %d\n", desc->db_id); + seq_printf(m, "\tEngines used: 0x%x\n", + desc->engines_used); + seq_printf(m, "\tDoorbell trigger phy: 0x%llx, cpu: 0x%llx, uK: 0x%x\n", + desc->db_trigger_phy, + desc->db_trigger_cpu, + desc->db_trigger_uk); + seq_printf(m, "\tProcess descriptor: 0x%x\n", + desc->process_desc); + seq_printf(m, "\tWorkqueue address: 0x%x, size: 0x%x\n", + desc->wq_addr, desc->wq_size); + seq_putc(m, '\n'); + + for_each_engine_masked(engine, dev_priv, client->engines, tmp) { + u32 guc_engine_id = engine->guc_id; + struct guc_execlist_context *lrc = + &desc->lrc[guc_engine_id]; + + seq_printf(m, "\t%s LRC:\n", engine->name); + seq_printf(m, "\t\tContext desc: 0x%x\n", + lrc->context_desc); + seq_printf(m, "\t\tContext id: 0x%x\n", lrc->context_id); + seq_printf(m, "\t\tLRCA: 0x%x\n", lrc->ring_lrca); + seq_printf(m, "\t\tRing begin: 0x%x\n", lrc->ring_begin); + seq_printf(m, "\t\tRing end: 0x%x\n", lrc->ring_end); + seq_putc(m, '\n'); + } + } + + return 0; +} + +static int i915_guc_log_dump(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_i915_private *dev_priv = node_to_i915(node); + bool dump_load_err = !!node->info_ent->data; + struct drm_i915_gem_object *obj = NULL; + u32 *log; + int i = 0; + + if (dump_load_err) + obj = dev_priv->guc.load_err_log; + else if (dev_priv->guc.log.vma) + obj = dev_priv->guc.log.vma->obj; - kunmap_atomic(log); + if (!obj) + return 0; + + log = i915_gem_object_pin_map(obj, I915_MAP_WC); + if (IS_ERR(log)) { + DRM_DEBUG("Failed to pin object\n"); + seq_puts(m, "(log data unaccessible)\n"); + return PTR_ERR(log); } + for (i = 0; i < obj->base.size / sizeof(u32); i += 4) + seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n", + *(log + i), *(log + i + 1), + *(log + i + 2), *(log + i + 3)); + seq_putc(m, '\n'); + i915_gem_object_unpin_map(obj); + return 0; } static int i915_guc_log_control_get(void *data, u64 *val) { - struct drm_device *dev = data; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = data; if (!dev_priv->guc.log.vma) return -EINVAL; @@ -2581,14 +2634,13 @@ static int i915_guc_log_control_get(void *data, u64 *val) static int i915_guc_log_control_set(void *data, u64 val) { - struct drm_device *dev = data; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = data; int ret; if (!dev_priv->guc.log.vma) return -EINVAL; - ret = mutex_lock_interruptible(&dev->struct_mutex); + ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex); if (ret) return ret; @@ -2596,7 +2648,7 @@ static int i915_guc_log_control_set(void *data, u64 val) ret = i915_guc_log_control(dev_priv, val); intel_runtime_pm_put(dev_priv); - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&dev_priv->drm.struct_mutex); return ret; } @@ -2855,7 +2907,8 @@ static int i915_dmc_info(struct seq_file *m, void *unused) seq_printf(m, "version: %d.%d\n", CSR_VERSION_MAJOR(csr->version), CSR_VERSION_MINOR(csr->version)); - if (IS_SKYLAKE(dev_priv) && csr->version >= CSR_VERSION(1, 6)) { + if (IS_KABYLAKE(dev_priv) || + (IS_SKYLAKE(dev_priv) && csr->version >= CSR_VERSION(1, 6))) { seq_printf(m, "DC3 -> DC5 count: %d\n", I915_READ(SKL_CSR_DC3_DC5_COUNT)); seq_printf(m, "DC5 -> DC6 count: %d\n", @@ -3043,36 +3096,6 @@ static void intel_connector_info(struct seq_file *m, intel_seq_print_mode(m, 2, mode); } -static bool cursor_active(struct drm_i915_private *dev_priv, int pipe) -{ - u32 state; - - if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) - state = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; - else - state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; - - return state; -} - -static bool cursor_position(struct drm_i915_private *dev_priv, - int pipe, int *x, int *y) -{ - u32 pos; - - pos = I915_READ(CURPOS(pipe)); - - *x = (pos >> CURSOR_X_SHIFT) & CURSOR_POS_MASK; - if (pos & (CURSOR_POS_SIGN << CURSOR_X_SHIFT)) - *x = -*x; - - *y = (pos >> CURSOR_Y_SHIFT) & CURSOR_POS_MASK; - if (pos & (CURSOR_POS_SIGN << CURSOR_Y_SHIFT)) - *y = -*y; - - return cursor_active(dev_priv, pipe); -} - static const char *plane_type(enum drm_plane_type type) { switch (type) { @@ -3095,17 +3118,17 @@ static const char *plane_rotation(unsigned int rotation) { static char buf[48]; /* - * According to doc only one DRM_ROTATE_ is allowed but this + * According to doc only one DRM_MODE_ROTATE_ is allowed but this * will print them all to visualize if the values are misused */ snprintf(buf, sizeof(buf), "%s%s%s%s%s%s(0x%08x)", - (rotation & DRM_ROTATE_0) ? "0 " : "", - (rotation & DRM_ROTATE_90) ? "90 " : "", - (rotation & DRM_ROTATE_180) ? "180 " : "", - (rotation & DRM_ROTATE_270) ? "270 " : "", - (rotation & DRM_REFLECT_X) ? "FLIPX " : "", - (rotation & DRM_REFLECT_Y) ? "FLIPY " : "", + (rotation & DRM_MODE_ROTATE_0) ? "0 " : "", + (rotation & DRM_MODE_ROTATE_90) ? "90 " : "", + (rotation & DRM_MODE_ROTATE_180) ? "180 " : "", + (rotation & DRM_MODE_ROTATE_270) ? "270 " : "", + (rotation & DRM_MODE_REFLECT_X) ? "FLIPX " : "", + (rotation & DRM_MODE_REFLECT_Y) ? "FLIPY " : "", rotation); return buf; @@ -3194,9 +3217,7 @@ static int i915_display_info(struct seq_file *m, void *unused) seq_printf(m, "CRTC info\n"); seq_printf(m, "---------\n"); for_each_intel_crtc(dev, crtc) { - bool active; struct intel_crtc_state *pipe_config; - int x, y; drm_modeset_lock(&crtc->base.mutex, NULL); pipe_config = to_intel_crtc_state(crtc->base.state); @@ -3208,14 +3229,18 @@ static int i915_display_info(struct seq_file *m, void *unused) yesno(pipe_config->dither), pipe_config->pipe_bpp); if (pipe_config->base.active) { + struct intel_plane *cursor = + to_intel_plane(crtc->base.cursor); + intel_crtc_info(m, crtc); - active = cursor_position(dev_priv, crtc->pipe, &x, &y); - seq_printf(m, "\tcursor visible? %s, position (%d, %d), size %dx%d, addr 0x%08x, active? %s\n", - yesno(crtc->cursor_base), - x, y, crtc->base.cursor->state->crtc_w, - crtc->base.cursor->state->crtc_h, - crtc->cursor_addr, yesno(active)); + seq_printf(m, "\tcursor visible? %s, position (%d, %d), size %dx%d, addr 0x%08x\n", + yesno(cursor->base.state->visible), + cursor->base.state->crtc_x, + cursor->base.state->crtc_y, + cursor->base.state->crtc_w, + cursor->base.state->crtc_h, + cursor->cursor.base); intel_scaler_info(m, crtc); intel_plane_info(m, crtc); } @@ -3316,7 +3341,7 @@ static int i915_engine_info(struct seq_file *m, void *unused) if (i915.enable_execlists) { u32 ptr, read, write; - struct rb_node *rb; + unsigned int idx; seq_printf(m, "\tExeclist status: 0x%08x %08x\n", I915_READ(RING_EXECLIST_STATUS_LO(engine)), @@ -3334,8 +3359,7 @@ static int i915_engine_info(struct seq_file *m, void *unused) if (read > write) write += GEN8_CSB_ENTRIES; while (read < write) { - unsigned int idx = ++read % GEN8_CSB_ENTRIES; - + idx = ++read % GEN8_CSB_ENTRIES; seq_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n", idx, I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)), @@ -3343,28 +3367,30 @@ static int i915_engine_info(struct seq_file *m, void *unused) } rcu_read_lock(); - rq = READ_ONCE(engine->execlist_port[0].request); - if (rq) { - seq_printf(m, "\t\tELSP[0] count=%d, ", - engine->execlist_port[0].count); - print_request(m, rq, "rq: "); - } else { - seq_printf(m, "\t\tELSP[0] idle\n"); - } - rq = READ_ONCE(engine->execlist_port[1].request); - if (rq) { - seq_printf(m, "\t\tELSP[1] count=%d, ", - engine->execlist_port[1].count); - print_request(m, rq, "rq: "); - } else { - seq_printf(m, "\t\tELSP[1] idle\n"); + for (idx = 0; idx < ARRAY_SIZE(engine->execlist_port); idx++) { + unsigned int count; + + rq = port_unpack(&engine->execlist_port[idx], + &count); + if (rq) { + seq_printf(m, "\t\tELSP[%d] count=%d, ", + idx, count); + print_request(m, rq, "rq: "); + } else { + seq_printf(m, "\t\tELSP[%d] idle\n", + idx); + } } rcu_read_unlock(); spin_lock_irq(&engine->timeline->lock); - for (rb = engine->execlist_first; rb; rb = rb_next(rb)) { - rq = rb_entry(rb, typeof(*rq), priotree.node); - print_request(m, rq, "\t\tQ "); + for (rb = engine->execlist_first; rb; rb = rb_next(rb)){ + struct i915_priolist *p = + rb_entry(rb, typeof(*p), node); + + list_for_each_entry(rq, &p->requests, + priotree.link) + print_request(m, rq, "\t\tQ "); } spin_unlock_irq(&engine->timeline->lock); } else if (INTEL_GEN(dev_priv) > 6) { @@ -3704,16 +3730,10 @@ static ssize_t i915_displayport_test_active_write(struct file *file, if (len == 0) return 0; - input_buffer = kmalloc(len + 1, GFP_KERNEL); - if (!input_buffer) - return -ENOMEM; - - if (copy_from_user(input_buffer, ubuf, len)) { - status = -EFAULT; - goto out; - } + input_buffer = memdup_user_nul(ubuf, len); + if (IS_ERR(input_buffer)) + return PTR_ERR(input_buffer); - input_buffer[len] = '\0'; DRM_DEBUG_DRIVER("Copied %d bytes from user\n", (unsigned int)len); drm_connector_list_iter_begin(dev, &conn_iter); @@ -3739,7 +3759,6 @@ static ssize_t i915_displayport_test_active_write(struct file *file, } } drm_connector_list_iter_end(&conn_iter); -out: kfree(input_buffer); if (status < 0) return status; @@ -3900,6 +3919,8 @@ static void wm_latency_show(struct seq_file *m, const uint16_t wm[8]) num_levels = 3; else if (IS_VALLEYVIEW(dev_priv)) num_levels = 1; + else if (IS_G4X(dev_priv)) + num_levels = 3; else num_levels = ilk_wm_max_level(dev_priv) + 1; @@ -3912,8 +3933,10 @@ static void wm_latency_show(struct seq_file *m, const uint16_t wm[8]) * - WM1+ latency values in 0.5us units * - latencies are in us on gen9/vlv/chv */ - if (INTEL_GEN(dev_priv) >= 9 || IS_VALLEYVIEW(dev_priv) || - IS_CHERRYVIEW(dev_priv)) + if (INTEL_GEN(dev_priv) >= 9 || + IS_VALLEYVIEW(dev_priv) || + IS_CHERRYVIEW(dev_priv) || + IS_G4X(dev_priv)) latency *= 10; else if (level > 0) latency *= 5; @@ -3974,7 +3997,7 @@ static int pri_wm_latency_open(struct inode *inode, struct file *file) { struct drm_i915_private *dev_priv = inode->i_private; - if (INTEL_GEN(dev_priv) < 5) + if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) return -ENODEV; return single_open(file, pri_wm_latency_show, dev_priv); @@ -4016,6 +4039,8 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf, num_levels = 3; else if (IS_VALLEYVIEW(dev_priv)) num_levels = 1; + else if (IS_G4X(dev_priv)) + num_levels = 3; else num_levels = ilk_wm_max_level(dev_priv) + 1; @@ -4264,26 +4289,27 @@ i915_drop_caches_set(void *data, u64 val) { struct drm_i915_private *dev_priv = data; struct drm_device *dev = &dev_priv->drm; - int ret; + int ret = 0; DRM_DEBUG("Dropping caches: 0x%08llx\n", val); /* No need to check and wait for gpu resets, only libdrm auto-restarts * on ioctls on -EAGAIN. */ - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; - - if (val & DROP_ACTIVE) { - ret = i915_gem_wait_for_idle(dev_priv, - I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED); + if (val & (DROP_ACTIVE | DROP_RETIRE)) { + ret = mutex_lock_interruptible(&dev->struct_mutex); if (ret) - goto unlock; - } + return ret; + + if (val & DROP_ACTIVE) + ret = i915_gem_wait_for_idle(dev_priv, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_LOCKED); - if (val & DROP_RETIRE) - i915_gem_retire_requests(dev_priv); + if (val & DROP_RETIRE) + i915_gem_retire_requests(dev_priv); + + mutex_unlock(&dev->struct_mutex); + } lockdep_set_current_reclaim_state(GFP_KERNEL); if (val & DROP_BOUND) @@ -4296,9 +4322,6 @@ i915_drop_caches_set(void *data, u64 val) i915_gem_shrink_all(dev_priv); lockdep_clear_current_reclaim_state(); -unlock: - mutex_unlock(&dev->struct_mutex); - if (val & DROP_FREED) { synchronize_rcu(); i915_gem_drain_freed_objects(dev_priv); @@ -4776,6 +4799,8 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_guc_info", i915_guc_info, 0}, {"i915_guc_load_status", i915_guc_load_status_info, 0}, {"i915_guc_log_dump", i915_guc_log_dump, 0}, + {"i915_guc_load_err_log_dump", i915_guc_log_dump, 0, (void *)1}, + {"i915_guc_stage_pool", i915_guc_stage_pool, 0}, {"i915_huc_load_status", i915_huc_load_status_info, 0}, {"i915_frequency_info", i915_frequency_info, 0}, {"i915_hangcheck_info", i915_hangcheck_info, 0}, diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index c994fe6e65b2ea..2fdfaf135ea9bf 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -350,6 +350,7 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_HAS_EXEC_SOFTPIN: case I915_PARAM_HAS_EXEC_ASYNC: case I915_PARAM_HAS_EXEC_FENCE: + case I915_PARAM_HAS_EXEC_CAPTURE: /* For the time being all of these are always true; * if some supported hardware does not have one of these * features this value needs to be provided from @@ -834,10 +835,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, intel_uc_init_early(dev_priv); i915_memcpy_init_early(dev_priv); - ret = intel_engines_init_early(dev_priv); - if (ret) - return ret; - ret = i915_workqueues_init(dev_priv); if (ret < 0) goto err_engines; @@ -855,7 +852,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, intel_init_audio_hooks(dev_priv); ret = i915_gem_load_init(dev_priv); if (ret < 0) - goto err_workqueues; + goto err_irq; intel_display_crc_init(dev_priv); @@ -867,7 +864,8 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, return 0; -err_workqueues: +err_irq: + intel_irq_fini(dev_priv); i915_workqueues_cleanup(dev_priv); err_engines: i915_engines_cleanup(dev_priv); @@ -882,6 +880,7 @@ static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv) { i915_perf_fini(dev_priv); i915_gem_load_cleanup(dev_priv); + intel_irq_fini(dev_priv); i915_workqueues_cleanup(dev_priv); i915_engines_cleanup(dev_priv); } @@ -947,14 +946,21 @@ static int i915_driver_init_mmio(struct drm_i915_private *dev_priv) ret = i915_mmio_setup(dev_priv); if (ret < 0) - goto put_bridge; + goto err_bridge; intel_uncore_init(dev_priv); + + ret = intel_engines_init_mmio(dev_priv); + if (ret) + goto err_uncore; + i915_gem_init_mmio(dev_priv); return 0; -put_bridge: +err_uncore: + intel_uncore_fini(dev_priv); +err_bridge: pci_dev_put(dev_priv->bridge_dev); return ret; @@ -991,6 +997,8 @@ static void intel_sanitize_options(struct drm_i915_private *dev_priv) DRM_DEBUG_DRIVER("use GPU semaphores? %s\n", yesno(i915.semaphores)); intel_uc_sanitize_options(dev_priv); + + intel_gvt_sanitize_options(dev_priv); } /** @@ -1213,9 +1221,8 @@ int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent) struct drm_i915_private *dev_priv; int ret; - /* Enable nuclear pageflip on ILK+, except vlv/chv */ - if (!i915.nuclear_pageflip && - (match_info->gen < 5 || match_info->has_gmch_display)) + /* Enable nuclear pageflip on ILK+ */ + if (!i915.nuclear_pageflip && match_info->gen < 5) driver.driver_features &= ~DRIVER_ATOMIC; ret = -ENOMEM; @@ -1235,6 +1242,15 @@ int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_fini; pci_set_drvdata(pdev, &dev_priv->drm); + /* + * Disable the system suspend direct complete optimization, which can + * leave the device suspended skipping the driver's suspend handlers + * if the device was already runtime suspended. This is needed due to + * the difference in our runtime and system suspend sequence and + * becaue the HDA driver may require us to enable the audio power + * domain during system suspend. + */ + pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; ret = i915_driver_init_early(dev_priv, ent); if (ret < 0) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index c9b0949f6c1a2a..a3b2674a4b7de3 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -55,6 +55,7 @@ #include "i915_reg.h" #include "i915_utils.h" +#include "intel_uncore.h" #include "intel_bios.h" #include "intel_dpll_mgr.h" #include "intel_uc.h" @@ -79,8 +80,8 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20170403" -#define DRIVER_TIMESTAMP 1491198738 +#define DRIVER_DATE "20170529" +#define DRIVER_TIMESTAMP 1496041258 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and * WARN_ON()) for hw state sanity checks to check for unexpected conditions @@ -114,6 +115,13 @@ typedef struct { fp; \ }) +static inline bool is_fixed16_zero(uint_fixed_16_16_t val) +{ + if (val.val == 0) + return true; + return false; +} + static inline uint_fixed_16_16_t u32_to_fixed_16_16(uint32_t val) { uint_fixed_16_16_t fp; @@ -152,8 +160,39 @@ static inline uint_fixed_16_16_t max_fixed_16_16(uint_fixed_16_16_t max1, return max; } -static inline uint_fixed_16_16_t fixed_16_16_div_round_up(uint32_t val, - uint32_t d) +static inline uint32_t div_round_up_fixed16(uint_fixed_16_16_t val, + uint_fixed_16_16_t d) +{ + return DIV_ROUND_UP(val.val, d.val); +} + +static inline uint32_t mul_round_up_u32_fixed16(uint32_t val, + uint_fixed_16_16_t mul) +{ + uint64_t intermediate_val; + uint32_t result; + + intermediate_val = (uint64_t) val * mul.val; + intermediate_val = DIV_ROUND_UP_ULL(intermediate_val, 1 << 16); + WARN_ON(intermediate_val >> 32); + result = clamp_t(uint32_t, intermediate_val, 0, ~0); + return result; +} + +static inline uint_fixed_16_16_t mul_fixed16(uint_fixed_16_16_t val, + uint_fixed_16_16_t mul) +{ + uint64_t intermediate_val; + uint_fixed_16_16_t fp; + + intermediate_val = (uint64_t) val.val * mul.val; + intermediate_val = intermediate_val >> 16; + WARN_ON(intermediate_val >> 32); + fp.val = clamp_t(uint32_t, intermediate_val, 0, ~0); + return fp; +} + +static inline uint_fixed_16_16_t fixed_16_16_div(uint32_t val, uint32_t d) { uint_fixed_16_16_t fp, res; @@ -162,8 +201,7 @@ static inline uint_fixed_16_16_t fixed_16_16_div_round_up(uint32_t val, return res; } -static inline uint_fixed_16_16_t fixed_16_16_div_round_up_u64(uint32_t val, - uint32_t d) +static inline uint_fixed_16_16_t fixed_16_16_div_u64(uint32_t val, uint32_t d) { uint_fixed_16_16_t res; uint64_t interm_val; @@ -176,6 +214,17 @@ static inline uint_fixed_16_16_t fixed_16_16_div_round_up_u64(uint32_t val, return res; } +static inline uint32_t div_round_up_u32_fixed16(uint32_t val, + uint_fixed_16_16_t d) +{ + uint64_t interm_val; + + interm_val = (uint64_t)val << 16; + interm_val = DIV_ROUND_UP_ULL(interm_val, d.val); + WARN_ON(interm_val >> 32); + return clamp_t(uint32_t, interm_val, 0, ~0); +} + static inline uint_fixed_16_16_t mul_u32_fixed_16_16(uint32_t val, uint_fixed_16_16_t mul) { @@ -676,116 +725,6 @@ struct drm_i915_display_funcs { void (*load_luts)(struct drm_crtc_state *crtc_state); }; -enum forcewake_domain_id { - FW_DOMAIN_ID_RENDER = 0, - FW_DOMAIN_ID_BLITTER, - FW_DOMAIN_ID_MEDIA, - - FW_DOMAIN_ID_COUNT -}; - -enum forcewake_domains { - FORCEWAKE_RENDER = BIT(FW_DOMAIN_ID_RENDER), - FORCEWAKE_BLITTER = BIT(FW_DOMAIN_ID_BLITTER), - FORCEWAKE_MEDIA = BIT(FW_DOMAIN_ID_MEDIA), - FORCEWAKE_ALL = (FORCEWAKE_RENDER | - FORCEWAKE_BLITTER | - FORCEWAKE_MEDIA) -}; - -#define FW_REG_READ (1) -#define FW_REG_WRITE (2) - -enum decoupled_power_domain { - GEN9_DECOUPLED_PD_BLITTER = 0, - GEN9_DECOUPLED_PD_RENDER, - GEN9_DECOUPLED_PD_MEDIA, - GEN9_DECOUPLED_PD_ALL -}; - -enum decoupled_ops { - GEN9_DECOUPLED_OP_WRITE = 0, - GEN9_DECOUPLED_OP_READ -}; - -enum forcewake_domains -intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv, - i915_reg_t reg, unsigned int op); - -struct intel_uncore_funcs { - void (*force_wake_get)(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); - void (*force_wake_put)(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); - - uint8_t (*mmio_readb)(struct drm_i915_private *dev_priv, - i915_reg_t r, bool trace); - uint16_t (*mmio_readw)(struct drm_i915_private *dev_priv, - i915_reg_t r, bool trace); - uint32_t (*mmio_readl)(struct drm_i915_private *dev_priv, - i915_reg_t r, bool trace); - uint64_t (*mmio_readq)(struct drm_i915_private *dev_priv, - i915_reg_t r, bool trace); - - void (*mmio_writeb)(struct drm_i915_private *dev_priv, - i915_reg_t r, uint8_t val, bool trace); - void (*mmio_writew)(struct drm_i915_private *dev_priv, - i915_reg_t r, uint16_t val, bool trace); - void (*mmio_writel)(struct drm_i915_private *dev_priv, - i915_reg_t r, uint32_t val, bool trace); -}; - -struct intel_forcewake_range { - u32 start; - u32 end; - - enum forcewake_domains domains; -}; - -struct intel_uncore { - spinlock_t lock; /** lock is also taken in irq contexts. */ - - const struct intel_forcewake_range *fw_domains_table; - unsigned int fw_domains_table_entries; - - struct notifier_block pmic_bus_access_nb; - struct intel_uncore_funcs funcs; - - unsigned fifo_count; - - enum forcewake_domains fw_domains; - enum forcewake_domains fw_domains_active; - - u32 fw_set; - u32 fw_clear; - u32 fw_reset; - - struct intel_uncore_forcewake_domain { - enum forcewake_domain_id id; - enum forcewake_domains mask; - unsigned wake_count; - struct hrtimer timer; - i915_reg_t reg_set; - i915_reg_t reg_ack; - } fw_domain[FW_DOMAIN_ID_COUNT]; - - int unclaimed_mmio_check; -}; - -#define __mask_next_bit(mask) ({ \ - int __idx = ffs(mask) - 1; \ - mask &= ~BIT(__idx); \ - __idx; \ -}) - -/* Iterate over initialised fw domains */ -#define for_each_fw_domain_masked(domain__, mask__, dev_priv__, tmp__) \ - for (tmp__ = (mask__); \ - tmp__ ? (domain__ = &(dev_priv__)->uncore.fw_domain[__mask_next_bit(tmp__)]), 1 : 0;) - -#define for_each_fw_domain(domain__, dev_priv__, tmp__) \ - for_each_fw_domain_masked(domain__, (dev_priv__)->uncore.fw_domains, dev_priv__, tmp__) - #define CSR_VERSION(major, minor) ((major) << 16 | (minor)) #define CSR_VERSION_MAJOR(version) ((version) >> 16) #define CSR_VERSION_MINOR(version) ((version) & 0xffff) @@ -812,7 +751,6 @@ struct intel_csr { func(has_aliasing_ppgtt); \ func(has_csr); \ func(has_ddi); \ - func(has_decoupled_mmio); \ func(has_dp_mst); \ func(has_fbc); \ func(has_fpga_dbg); \ @@ -821,8 +759,8 @@ struct intel_csr { func(has_gmbus_irq); \ func(has_gmch_display); \ func(has_guc); \ + func(has_guc_ct); \ func(has_hotplug); \ - func(has_hw_contexts); \ func(has_l3_dpf); \ func(has_llc); \ func(has_logical_ring_contexts); \ @@ -1025,6 +963,9 @@ struct i915_gpu_state { u32 *pages[0]; } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page; + struct drm_i915_error_object **user_bo; + long user_bo_count; + struct drm_i915_error_object *wa_ctx; struct drm_i915_error_request { @@ -1511,11 +1452,7 @@ struct i915_gem_mm { /** LRU list of objects with fence regs on them. */ struct list_head fence_list; - /** - * Are we in a non-interruptible section of code like - * modesetting? - */ - bool interruptible; + u64 unordered_timeline; /* the indicator for dispatch video commands on two BSD rings */ atomic_t bsd_engine_dispatch_index; @@ -1566,7 +1503,7 @@ struct i915_gpu_error { * * This is a counter which gets incremented when reset is triggered, * - * Before the reset commences, the I915_RESET_IN_PROGRESS bit is set + * Before the reset commences, the I915_RESET_BACKOFF bit is set * meaning that any waiters holding onto the struct_mutex should * relinquish the lock immediately in order for the reset to start. * @@ -1763,13 +1700,15 @@ struct ilk_wm_values { enum intel_ddb_partitioning partitioning; }; -struct vlv_pipe_wm { +struct g4x_pipe_wm { uint16_t plane[I915_MAX_PLANES]; + uint16_t fbc; }; -struct vlv_sr_wm { +struct g4x_sr_wm { uint16_t plane; uint16_t cursor; + uint16_t fbc; }; struct vlv_wm_ddl_values { @@ -1777,13 +1716,22 @@ struct vlv_wm_ddl_values { }; struct vlv_wm_values { - struct vlv_pipe_wm pipe[3]; - struct vlv_sr_wm sr; + struct g4x_pipe_wm pipe[3]; + struct g4x_sr_wm sr; struct vlv_wm_ddl_values ddl[3]; uint8_t level; bool cxsr; }; +struct g4x_wm_values { + struct g4x_pipe_wm pipe[2]; + struct g4x_sr_wm sr; + struct g4x_sr_wm hpll; + bool cxsr; + bool hpll_en; + bool fbc_en; +}; + struct skl_ddb_entry { uint16_t start, end; /* in number of blocks, 'end' is exclusive */ }; @@ -2100,7 +2048,7 @@ struct i915_oa_ops { size_t *offset); /** - * @oa_buffer_is_empty: Check if OA buffer empty (false positives OK) + * @oa_buffer_check: Check for OA buffer data + update tail * * This is either called via fops or the poll check hrtimer (atomic * ctx) without any locks taken. @@ -2113,7 +2061,7 @@ struct i915_oa_ops { * here, which will be handled gracefully - likely resulting in an * %EAGAIN error for userspace. */ - bool (*oa_buffer_is_empty)(struct drm_i915_private *dev_priv); + bool (*oa_buffer_check)(struct drm_i915_private *dev_priv); }; struct intel_cdclk_state { @@ -2127,6 +2075,7 @@ struct drm_i915_private { struct kmem_cache *vmas; struct kmem_cache *requests; struct kmem_cache *dependencies; + struct kmem_cache *priorities; const struct intel_device_info info; @@ -2362,7 +2311,6 @@ struct drm_i915_private { */ struct mutex av_mutex; - uint32_t hw_context_size; struct list_head context_list; u32 fdi_rx_config; @@ -2413,6 +2361,7 @@ struct drm_i915_private { struct ilk_wm_values hw; struct skl_wm_values skl_hw; struct vlv_wm_values vlv; + struct g4x_wm_values g4x; }; uint8_t max_level; @@ -2454,11 +2403,14 @@ struct drm_i915_private { wait_queue_head_t poll_wq; bool pollin; + /** + * For rate limiting any notifications of spurious + * invalid OA reports + */ + struct ratelimit_state spurious_report_rs; + bool periodic; int period_exponent; - int timestamp_frequency; - - int tail_margin; int metrics_set; @@ -2472,6 +2424,70 @@ struct drm_i915_private { u8 *vaddr; int format; int format_size; + + /** + * Locks reads and writes to all head/tail state + * + * Consider: the head and tail pointer state + * needs to be read consistently from a hrtimer + * callback (atomic context) and read() fop + * (user context) with tail pointer updates + * happening in atomic context and head updates + * in user context and the (unlikely) + * possibility of read() errors needing to + * reset all head/tail state. + * + * Note: Contention or performance aren't + * currently a significant concern here + * considering the relatively low frequency of + * hrtimer callbacks (5ms period) and that + * reads typically only happen in response to a + * hrtimer event and likely complete before the + * next callback. + * + * Note: This lock is not held *while* reading + * and copying data to userspace so the value + * of head observed in htrimer callbacks won't + * represent any partial consumption of data. + */ + spinlock_t ptr_lock; + + /** + * One 'aging' tail pointer and one 'aged' + * tail pointer ready to used for reading. + * + * Initial values of 0xffffffff are invalid + * and imply that an update is required + * (and should be ignored by an attempted + * read) + */ + struct { + u32 offset; + } tails[2]; + + /** + * Index for the aged tail ready to read() + * data up to. + */ + unsigned int aged_tail_idx; + + /** + * A monotonic timestamp for when the current + * aging tail pointer was read; used to + * determine when it is old enough to trust. + */ + u64 aging_timestamp; + + /** + * Although we can always read back the head + * pointer register, we prefer to avoid + * trusting the HW state, just to avoid any + * risk that some hardware condition could + * somehow bump the head pointer unpredictably + * and cause us to forward the wrong OA buffer + * data to userspace. + */ + u32 head; } oa_buffer; u32 gen7_latched_oastatus1; @@ -2870,7 +2886,6 @@ intel_info(const struct drm_i915_private *dev_priv) #define HWS_NEEDS_PHYSICAL(dev_priv) ((dev_priv)->info.hws_needs_physical) -#define HAS_HW_CONTEXTS(dev_priv) ((dev_priv)->info.has_hw_contexts) #define HAS_LOGICAL_RING_CONTEXTS(dev_priv) \ ((dev_priv)->info.has_logical_ring_contexts) #define USES_PPGTT(dev_priv) (i915.enable_ppgtt) @@ -2909,6 +2924,7 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_FW_BLC(dev_priv) (INTEL_GEN(dev_priv) > 2) #define HAS_PIPE_CXSR(dev_priv) ((dev_priv)->info.has_pipe_cxsr) #define HAS_FBC(dev_priv) ((dev_priv)->info.has_fbc) +#define HAS_CUR_FBC(dev_priv) (!HAS_GMCH_DISPLAY(dev_priv) && INTEL_INFO(dev_priv)->gen >= 7) #define HAS_IPS(dev_priv) (IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv)) @@ -2931,6 +2947,7 @@ intel_info(const struct drm_i915_private *dev_priv) * properties, so we have separate macros to test them. */ #define HAS_GUC(dev_priv) ((dev_priv)->info.has_guc) +#define HAS_GUC_CT(dev_priv) ((dev_priv)->info.has_guc_ct) #define HAS_GUC_UCODE(dev_priv) (HAS_GUC(dev_priv)) #define HAS_GUC_SCHED(dev_priv) (HAS_GUC(dev_priv)) #define HAS_HUC_UCODE(dev_priv) (HAS_GUC(dev_priv)) @@ -2977,19 +2994,28 @@ intel_info(const struct drm_i915_private *dev_priv) #define GT_FREQUENCY_MULTIPLIER 50 #define GEN9_FREQ_SCALER 3 -#define HAS_DECOUPLED_MMIO(dev_priv) (INTEL_INFO(dev_priv)->has_decoupled_mmio) - #include "i915_trace.h" -static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) +static inline bool intel_vtd_active(void) { #ifdef CONFIG_INTEL_IOMMU - if (INTEL_GEN(dev_priv) >= 6 && intel_iommu_gfx_mapped) + if (intel_iommu_gfx_mapped) return true; #endif return false; } +static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) +{ + return INTEL_GEN(dev_priv) >= 6 && intel_vtd_active(); +} + +static inline bool +intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv) +{ + return IS_BROXTON(dev_priv) && intel_vtd_active(); +} + int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, int enable_ppgtt); @@ -3026,7 +3052,7 @@ extern unsigned long i915_gfx_val(struct drm_i915_private *dev_priv); extern void i915_update_gfx_val(struct drm_i915_private *dev_priv); int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on); -int intel_engines_init_early(struct drm_i915_private *dev_priv); +int intel_engines_init_mmio(struct drm_i915_private *dev_priv); int intel_engines_init(struct drm_i915_private *dev_priv); /* intel_hotplug.c */ @@ -3063,43 +3089,10 @@ void i915_handle_error(struct drm_i915_private *dev_priv, const char *fmt, ...); extern void intel_irq_init(struct drm_i915_private *dev_priv); +extern void intel_irq_fini(struct drm_i915_private *dev_priv); int intel_irq_install(struct drm_i915_private *dev_priv); void intel_irq_uninstall(struct drm_i915_private *dev_priv); -extern void intel_uncore_sanitize(struct drm_i915_private *dev_priv); -extern void intel_uncore_init(struct drm_i915_private *dev_priv); -extern bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv); -extern bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv); -extern void intel_uncore_fini(struct drm_i915_private *dev_priv); -extern void intel_uncore_suspend(struct drm_i915_private *dev_priv); -extern void intel_uncore_resume_early(struct drm_i915_private *dev_priv); -const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id); -void intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); -void intel_uncore_forcewake_put(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); -/* Like above but the caller must manage the uncore.lock itself. - * Must be used with I915_READ_FW and friends. - */ -void intel_uncore_forcewake_get__locked(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); -void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv, - enum forcewake_domains domains); -u64 intel_uncore_edram_size(struct drm_i915_private *dev_priv); - -void assert_forcewakes_inactive(struct drm_i915_private *dev_priv); - -int intel_wait_for_register(struct drm_i915_private *dev_priv, - i915_reg_t reg, - const u32 mask, - const u32 value, - const unsigned long timeout_ms); -int intel_wait_for_register_fw(struct drm_i915_private *dev_priv, - i915_reg_t reg, - const u32 mask, - const u32 value, - const unsigned long timeout_ms); - static inline bool intel_gvt_active(struct drm_i915_private *dev_priv) { return dev_priv->gvt; @@ -3447,8 +3440,9 @@ int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, #define I915_PRIORITY_DISPLAY I915_PRIORITY_MAX int __must_check -i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, - bool write); +i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write); +int __must_check +i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write); int __must_check i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write); struct i915_vma * __must_check @@ -3711,8 +3705,8 @@ int intel_lpe_audio_init(struct drm_i915_private *dev_priv); void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv); void intel_lpe_audio_irq_handler(struct drm_i915_private *dev_priv); void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, - void *eld, int port, int pipe, int tmds_clk_speed, - bool dp_output, int link_rate); + enum pipe pipe, enum port port, + const void *eld, int ls_clock, bool dp_output); /* intel_i2c.c */ extern int intel_setup_gmbus(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b6ac3df18b5825..7b676fd1f07546 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -46,8 +46,6 @@ #include static void i915_gem_flush_free_objects(struct drm_i915_private *i915); -static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj); -static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj); static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj) { @@ -705,6 +703,61 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data, args->size, &args->handle); } +static inline enum fb_op_origin +fb_write_origin(struct drm_i915_gem_object *obj, unsigned int domain) +{ + return (domain == I915_GEM_DOMAIN_GTT ? + obj->frontbuffer_ggtt_origin : ORIGIN_CPU); +} + +static void +flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains) +{ + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); + + if (!(obj->base.write_domain & flush_domains)) + return; + + /* No actual flushing is required for the GTT write domain. Writes + * to it "immediately" go to main memory as far as we know, so there's + * no chipset flush. It also doesn't land in render cache. + * + * However, we do have to enforce the order so that all writes through + * the GTT land before any writes to the device, such as updates to + * the GATT itself. + * + * We also have to wait a bit for the writes to land from the GTT. + * An uncached read (i.e. mmio) seems to be ideal for the round-trip + * timing. This issue has only been observed when switching quickly + * between GTT writes and CPU reads from inside the kernel on recent hw, + * and it appears to only affect discrete GTT blocks (i.e. on LLC + * system agents we cannot reproduce this behaviour). + */ + wmb(); + + switch (obj->base.write_domain) { + case I915_GEM_DOMAIN_GTT: + if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv)) { + if (intel_runtime_pm_get_if_in_use(dev_priv)) { + spin_lock_irq(&dev_priv->uncore.lock); + POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); + spin_unlock_irq(&dev_priv->uncore.lock); + intel_runtime_pm_put(dev_priv); + } + } + + intel_fb_obj_flush(obj, + fb_write_origin(obj, I915_GEM_DOMAIN_GTT)); + break; + + case I915_GEM_DOMAIN_CPU: + i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC); + break; + } + + obj->base.write_domain = 0; +} + static inline int __copy_to_user_swizzled(char __user *cpu_vaddr, const char *gpu_vaddr, int gpu_offset, @@ -794,7 +847,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj, goto out; } - i915_gem_object_flush_gtt_write_domain(obj); + flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU); /* If we're not in the cpu read domain, set ourself into the gtt * read domain and manually flush cachelines (if required). This @@ -846,7 +899,7 @@ int i915_gem_obj_prepare_shmem_write(struct drm_i915_gem_object *obj, goto out; } - i915_gem_object_flush_gtt_write_domain(obj); + flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU); /* If we're not in the cpu write domain, set ourself into the * gtt write domain and manually flush cachelines (as required). @@ -1501,13 +1554,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, return ret; } -static inline enum fb_op_origin -write_origin(struct drm_i915_gem_object *obj, unsigned domain) -{ - return (domain == I915_GEM_DOMAIN_GTT ? - obj->frontbuffer_ggtt_origin : ORIGIN_CPU); -} - static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915; @@ -1591,10 +1637,12 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, if (err) goto out_unpin; - if (read_domains & I915_GEM_DOMAIN_GTT) - err = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0); + if (read_domains & I915_GEM_DOMAIN_WC) + err = i915_gem_object_set_to_wc_domain(obj, write_domain); + else if (read_domains & I915_GEM_DOMAIN_GTT) + err = i915_gem_object_set_to_gtt_domain(obj, write_domain); else - err = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0); + err = i915_gem_object_set_to_cpu_domain(obj, write_domain); /* And bump the LRU for this access */ i915_gem_object_bump_inactive_ggtt(obj); @@ -1602,7 +1650,8 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, mutex_unlock(&dev->struct_mutex); if (write_domain != 0) - intel_fb_obj_invalidate(obj, write_origin(obj, write_domain)); + intel_fb_obj_invalidate(obj, + fb_write_origin(obj, write_domain)); out_unpin: i915_gem_object_unpin_pages(obj); @@ -1737,6 +1786,9 @@ static unsigned int tile_row_pages(struct drm_i915_gem_object *obj) * into userspace. (This view is aligned and sized appropriately for * fenced access.) * + * 2 - Recognise WC as a separate cache domain so that we can flush the + * delayed writes via GTT before performing direct access via WC. + * * Restrictions: * * * snoopable objects cannot be accessed via the GTT. It can cause machine @@ -1764,7 +1816,7 @@ static unsigned int tile_row_pages(struct drm_i915_gem_object *obj) */ int i915_gem_mmap_gtt_version(void) { - return 1; + return 2; } static inline struct i915_ggtt_view @@ -2228,7 +2280,7 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj, if (obj->mm.mapping) { void *ptr; - ptr = ptr_mask_bits(obj->mm.mapping); + ptr = page_mask_bits(obj->mm.mapping); if (is_vmalloc_addr(ptr)) vunmap(ptr); else @@ -2504,7 +2556,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, if (n_pages > ARRAY_SIZE(stack_pages)) { /* Too big for stack -- allocate temporary array instead */ - pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY); + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_TEMPORARY); if (!pages) return NULL; } @@ -2526,7 +2578,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, addr = vmap(pages, n_pages, 0, pgprot); if (pages != stack_pages) - drm_free_large(pages); + kvfree(pages); return addr; } @@ -2560,7 +2612,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } GEM_BUG_ON(!obj->mm.pages); - ptr = ptr_unpack_bits(obj->mm.mapping, has_type); + ptr = page_unpack_bits(obj->mm.mapping, &has_type); if (ptr && has_type != type) { if (pinned) { ret = -EBUSY; @@ -2582,7 +2634,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, goto err_unpin; } - obj->mm.mapping = ptr_pack_bits(ptr, type); + obj->mm.mapping = page_pack_bits(ptr, type); } out_unlock: @@ -2967,12 +3019,14 @@ static void engine_set_wedged(struct intel_engine_cs *engine) */ if (i915.enable_execlists) { + struct execlist_port *port = engine->execlist_port; unsigned long flags; + unsigned int n; spin_lock_irqsave(&engine->timeline->lock, flags); - i915_gem_request_put(engine->execlist_port[0].request); - i915_gem_request_put(engine->execlist_port[1].request); + for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) + i915_gem_request_put(port_request(&port[n])); memset(engine->execlist_port, 0, sizeof(engine->execlist_port)); engine->execlist_queue = RB_ROOT; engine->execlist_first = NULL; @@ -3101,8 +3155,6 @@ i915_gem_idle_work_handler(struct work_struct *work) struct drm_i915_private *dev_priv = container_of(work, typeof(*dev_priv), gt.idle_work.work); struct drm_device *dev = &dev_priv->drm; - struct intel_engine_cs *engine; - enum intel_engine_id id; bool rearm_hangcheck; if (!READ_ONCE(dev_priv->gt.awake)) @@ -3140,10 +3192,8 @@ i915_gem_idle_work_handler(struct work_struct *work) if (wait_for(intel_engines_are_idle(dev_priv), 10)) DRM_ERROR("Timeout waiting for engines to idle\n"); - for_each_engine(engine, dev_priv, id) { - intel_engine_disarm_breadcrumbs(engine); - i915_gem_batch_pool_fini(&engine->batch_pool); - } + intel_engines_mark_idle(dev_priv); + i915_gem_timelines_mark_idle(dev_priv); GEM_BUG_ON(!dev_priv->gt.awake); dev_priv->gt.awake = false; @@ -3298,6 +3348,10 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags) { int ret; + /* If the device is asleep, we have no requests outstanding */ + if (!READ_ONCE(i915->gt.awake)) + return 0; + if (flags & I915_WAIT_LOCKED) { struct i915_gem_timeline *tl; @@ -3320,56 +3374,6 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags) return ret; } -/** Flushes the GTT write domain for the object if it's dirty. */ -static void -i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj) -{ - struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - - if (obj->base.write_domain != I915_GEM_DOMAIN_GTT) - return; - - /* No actual flushing is required for the GTT write domain. Writes - * to it "immediately" go to main memory as far as we know, so there's - * no chipset flush. It also doesn't land in render cache. - * - * However, we do have to enforce the order so that all writes through - * the GTT land before any writes to the device, such as updates to - * the GATT itself. - * - * We also have to wait a bit for the writes to land from the GTT. - * An uncached read (i.e. mmio) seems to be ideal for the round-trip - * timing. This issue has only been observed when switching quickly - * between GTT writes and CPU reads from inside the kernel on recent hw, - * and it appears to only affect discrete GTT blocks (i.e. on LLC - * system agents we cannot reproduce this behaviour). - */ - wmb(); - if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv)) { - if (intel_runtime_pm_get_if_in_use(dev_priv)) { - spin_lock_irq(&dev_priv->uncore.lock); - POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base)); - spin_unlock_irq(&dev_priv->uncore.lock); - intel_runtime_pm_put(dev_priv); - } - } - - intel_fb_obj_flush(obj, write_origin(obj, I915_GEM_DOMAIN_GTT)); - - obj->base.write_domain = 0; -} - -/** Flushes the CPU write domain for the object if it's dirty. */ -static void -i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj) -{ - if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) - return; - - i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC); - obj->base.write_domain = 0; -} - static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj) { if (obj->base.write_domain != I915_GEM_DOMAIN_CPU && !obj->cache_dirty) @@ -3389,6 +3393,69 @@ void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj) mutex_unlock(&obj->base.dev->struct_mutex); } +/** + * Moves a single object to the WC read, and possibly write domain. + * @obj: object to act on + * @write: ask for write access or read only + * + * This function returns when the move is complete, including waiting on + * flushes to occur. + */ +int +i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write) +{ + int ret; + + lockdep_assert_held(&obj->base.dev->struct_mutex); + + ret = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_LOCKED | + (write ? I915_WAIT_ALL : 0), + MAX_SCHEDULE_TIMEOUT, + NULL); + if (ret) + return ret; + + if (obj->base.write_domain == I915_GEM_DOMAIN_WC) + return 0; + + /* Flush and acquire obj->pages so that we are coherent through + * direct access in memory with previous cached writes through + * shmemfs and that our cache domain tracking remains valid. + * For example, if the obj->filp was moved to swap without us + * being notified and releasing the pages, we would mistakenly + * continue to assume that the obj remained out of the CPU cached + * domain. + */ + ret = i915_gem_object_pin_pages(obj); + if (ret) + return ret; + + flush_write_domain(obj, ~I915_GEM_DOMAIN_WC); + + /* Serialise direct access to this object with the barriers for + * coherent writes from the GPU, by effectively invalidating the + * WC domain upon first access. + */ + if ((obj->base.read_domains & I915_GEM_DOMAIN_WC) == 0) + mb(); + + /* It should now be out of any other write domains, and we can update + * the domain values for our changes. + */ + GEM_BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_WC) != 0); + obj->base.read_domains |= I915_GEM_DOMAIN_WC; + if (write) { + obj->base.read_domains = I915_GEM_DOMAIN_WC; + obj->base.write_domain = I915_GEM_DOMAIN_WC; + obj->mm.dirty = true; + } + + i915_gem_object_unpin_pages(obj); + return 0; +} + /** * Moves a single object to the GTT read, and possibly write domain. * @obj: object to act on @@ -3428,7 +3495,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) if (ret) return ret; - i915_gem_object_flush_cpu_write_domain(obj); + flush_write_domain(obj, ~I915_GEM_DOMAIN_GTT); /* Serialise direct access to this object with the barriers for * coherent writes from the GPU, by effectively invalidating the @@ -3802,7 +3869,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write) if (obj->base.write_domain == I915_GEM_DOMAIN_CPU) return 0; - i915_gem_object_flush_gtt_write_domain(obj); + flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU); /* Flush the CPU cache if it's still invalid. */ if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) { @@ -3996,7 +4063,7 @@ __busy_set_if_active(const struct dma_fence *fence, if (i915_gem_request_completed(rq)) return 0; - return flag(rq->engine->exec_id); + return flag(rq->engine->uabi_id); } static __always_inline unsigned int @@ -4195,7 +4262,7 @@ i915_gem_object_create(struct drm_i915_private *dev_priv, u64 size) * catch if we ever need to fix it. In the meantime, if you do spot * such a local variable, please consider fixing! */ - if (WARN_ON(size >> PAGE_SHIFT > INT_MAX)) + if (size >> PAGE_SHIFT > INT_MAX) return ERR_PTR(-E2BIG); if (overflows_type(size, obj->base.size)) @@ -4302,6 +4369,8 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); + cond_resched(); + llist_for_each_entry_safe(obj, on, freed, freed) { GEM_BUG_ON(obj->bind_count); GEM_BUG_ON(atomic_read(&obj->frontbuffer_bits)); @@ -4349,8 +4418,11 @@ static void __i915_gem_free_work(struct work_struct *work) * unbound now. */ - while ((freed = llist_del_all(&i915->mm.free_list))) + while ((freed = llist_del_all(&i915->mm.free_list))) { __i915_gem_free_objects(i915, freed); + if (need_resched()) + break; + } } static void __i915_gem_free_object_rcu(struct rcu_head *head) @@ -4415,10 +4487,9 @@ void i915_gem_sanitize(struct drm_i915_private *i915) * try to take over. The only way to remove the earlier state * is by resetting. However, resetting on earlier gen is tricky as * it may impact the display and we are uncertain about the stability - * of the reset, so we only reset recent machines with logical - * context support (that must be reset to remove any stray contexts). + * of the reset, so this could be applied to even earlier gen. */ - if (HAS_HW_CONTEXTS(i915)) { + if (INTEL_GEN(i915) >= 5) { int reset = intel_gpu_reset(i915, ALL_ENGINES); WARN_ON(reset && reset != -ENODEV); } @@ -4661,11 +4732,9 @@ bool intel_sanitize_semaphores(struct drm_i915_private *dev_priv, int value) if (value >= 0) return value; -#ifdef CONFIG_INTEL_IOMMU /* Enable semaphores on SNB when IO remapping is off */ - if (INTEL_INFO(dev_priv)->gen == 6 && intel_iommu_gfx_mapped) + if (IS_GEN6(dev_priv) && intel_vtd_active()) return false; -#endif return true; } @@ -4676,7 +4745,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->drm.struct_mutex); - i915_gem_clflush_init(dev_priv); + dev_priv->mm.unordered_timeline = dma_fence_context_alloc(1); if (!i915.enable_execlists) { dev_priv->gt.resume = intel_legacy_submission_resume; @@ -4799,12 +4868,16 @@ i915_gem_load_init(struct drm_i915_private *dev_priv) if (!dev_priv->dependencies) goto err_requests; + dev_priv->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN); + if (!dev_priv->priorities) + goto err_dependencies; + mutex_lock(&dev_priv->drm.struct_mutex); INIT_LIST_HEAD(&dev_priv->gt.timelines); err = i915_gem_timeline_init__global(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); if (err) - goto err_dependencies; + goto err_priorities; INIT_LIST_HEAD(&dev_priv->context_list); INIT_WORK(&dev_priv->mm.free_work, __i915_gem_free_work); @@ -4822,14 +4895,14 @@ i915_gem_load_init(struct drm_i915_private *dev_priv) init_waitqueue_head(&dev_priv->pending_flip_queue); - dev_priv->mm.interruptible = true; - atomic_set(&dev_priv->mm.bsd_engine_dispatch_index, 0); spin_lock_init(&dev_priv->fb_tracking.lock); return 0; +err_priorities: + kmem_cache_destroy(dev_priv->priorities); err_dependencies: kmem_cache_destroy(dev_priv->dependencies); err_requests: @@ -4853,6 +4926,7 @@ void i915_gem_load_cleanup(struct drm_i915_private *dev_priv) WARN_ON(!list_empty(&dev_priv->gt.timelines)); mutex_unlock(&dev_priv->drm.struct_mutex); + kmem_cache_destroy(dev_priv->priorities); kmem_cache_destroy(dev_priv->dependencies); kmem_cache_destroy(dev_priv->requests); kmem_cache_destroy(dev_priv->vmas); @@ -4864,9 +4938,10 @@ void i915_gem_load_cleanup(struct drm_i915_private *dev_priv) int i915_gem_freeze(struct drm_i915_private *dev_priv) { - mutex_lock(&dev_priv->drm.struct_mutex); + /* Discard all purgeable objects, let userspace recover those as + * required after resuming. + */ i915_gem_shrink_all(dev_priv); - mutex_unlock(&dev_priv->drm.struct_mutex); return 0; } @@ -4891,12 +4966,13 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv) * we update that state just before writing out the image. * * To try and reduce the hibernation image, we manually shrink - * the objects as well. + * the objects as well, see i915_gem_freeze() */ - mutex_lock(&dev_priv->drm.struct_mutex); i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND); + i915_gem_drain_freed_objects(dev_priv); + mutex_lock(&dev_priv->drm.struct_mutex); for (p = phases; *p; p++) { list_for_each_entry(obj, *p, global_link) { obj->base.read_domains = I915_GEM_DOMAIN_CPU; diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h index 5a49487368ca39..ee54597465b60e 100644 --- a/drivers/gpu/drm/i915/i915_gem.h +++ b/drivers/gpu/drm/i915/i915_gem.h @@ -25,6 +25,8 @@ #ifndef __I915_GEM_H__ #define __I915_GEM_H__ +#include + #ifdef CONFIG_DRM_I915_DEBUG_GEM #define GEM_BUG_ON(expr) BUG_ON(expr) #define GEM_WARN_ON(expr) WARN_ON(expr) diff --git a/drivers/gpu/drm/i915/i915_gem_clflush.c b/drivers/gpu/drm/i915/i915_gem_clflush.c index ffd01e02fe94b5..ffac7a1f0caf34 100644 --- a/drivers/gpu/drm/i915/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/i915_gem_clflush.c @@ -27,7 +27,6 @@ #include "i915_gem_clflush.h" static DEFINE_SPINLOCK(clflush_lock); -static u64 clflush_context; struct clflush { struct dma_fence dma; /* Must be first for dma_fence_free() */ @@ -157,7 +156,7 @@ void i915_gem_clflush_object(struct drm_i915_gem_object *obj, dma_fence_init(&clflush->dma, &i915_clflush_ops, &clflush_lock, - clflush_context, + to_i915(obj->base.dev)->mm.unordered_timeline, 0); i915_sw_fence_init(&clflush->wait, i915_clflush_notify); @@ -182,8 +181,3 @@ void i915_gem_clflush_object(struct drm_i915_gem_object *obj, GEM_BUG_ON(obj->base.write_domain != I915_GEM_DOMAIN_CPU); } } - -void i915_gem_clflush_init(struct drm_i915_private *i915) -{ - clflush_context = dma_fence_context_alloc(1); -} diff --git a/drivers/gpu/drm/i915/i915_gem_clflush.h b/drivers/gpu/drm/i915/i915_gem_clflush.h index b62d61a2d15fb6..2455a7820937b0 100644 --- a/drivers/gpu/drm/i915/i915_gem_clflush.h +++ b/drivers/gpu/drm/i915/i915_gem_clflush.h @@ -28,7 +28,6 @@ struct drm_i915_private; struct drm_i915_gem_object; -void i915_gem_clflush_init(struct drm_i915_private *i915); void i915_gem_clflush_object(struct drm_i915_gem_object *obj, unsigned int flags); #define I915_CLFLUSH_FORCE BIT(0) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 8bd0c4966913f5..c5d1666d707127 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -92,33 +92,6 @@ #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1 -static int get_context_size(struct drm_i915_private *dev_priv) -{ - int ret; - u32 reg; - - switch (INTEL_GEN(dev_priv)) { - case 6: - reg = I915_READ(CXT_SIZE); - ret = GEN6_CXT_TOTAL_SIZE(reg) * 64; - break; - case 7: - reg = I915_READ(GEN7_CXT_SIZE); - if (IS_HASWELL(dev_priv)) - ret = HSW_CXT_TOTAL_SIZE; - else - ret = GEN7_CXT_TOTAL_SIZE(reg) * 64; - break; - case 8: - ret = GEN8_CXT_TOTAL_SIZE; - break; - default: - BUG(); - } - - return ret; -} - void i915_gem_context_free(struct kref *ctx_ref) { struct i915_gem_context *ctx = container_of(ctx_ref, typeof(*ctx), ref); @@ -151,45 +124,6 @@ void i915_gem_context_free(struct kref *ctx_ref) kfree(ctx); } -static struct drm_i915_gem_object * -alloc_context_obj(struct drm_i915_private *dev_priv, u64 size) -{ - struct drm_i915_gem_object *obj; - int ret; - - lockdep_assert_held(&dev_priv->drm.struct_mutex); - - obj = i915_gem_object_create(dev_priv, size); - if (IS_ERR(obj)) - return obj; - - /* - * Try to make the context utilize L3 as well as LLC. - * - * On VLV we don't have L3 controls in the PTEs so we - * shouldn't touch the cache level, especially as that - * would make the object snooped which might have a - * negative performance impact. - * - * Snooping is required on non-llc platforms in execlist - * mode, but since all GGTT accesses use PAT entry 0 we - * get snooping anyway regardless of cache_level. - * - * This is only applicable for Ivy Bridge devices since - * later platforms don't have L3 control bits in the PTE. - */ - if (IS_IVYBRIDGE(dev_priv)) { - ret = i915_gem_object_set_cache_level(obj, I915_CACHE_L3_LLC); - /* Failure shouldn't ever happen this early */ - if (WARN_ON(ret)) { - i915_gem_object_put(obj); - return ERR_PTR(ret); - } - } - - return obj; -} - static void context_close(struct i915_gem_context *ctx) { i915_gem_context_set_closed(ctx); @@ -265,26 +199,7 @@ __create_hw_context(struct drm_i915_private *dev_priv, kref_init(&ctx->ref); list_add_tail(&ctx->link, &dev_priv->context_list); ctx->i915 = dev_priv; - - if (dev_priv->hw_context_size) { - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - - obj = alloc_context_obj(dev_priv, dev_priv->hw_context_size); - if (IS_ERR(obj)) { - ret = PTR_ERR(obj); - goto err_out; - } - - vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL); - if (IS_ERR(vma)) { - i915_gem_object_put(obj); - ret = PTR_ERR(vma); - goto err_out; - } - - ctx->engine[RCS].state = vma; - } + ctx->priority = I915_PRIORITY_NORMAL; /* Default context will never have a file_priv */ ret = DEFAULT_CONTEXT_HANDLE; @@ -443,21 +358,6 @@ int i915_gem_context_init(struct drm_i915_private *dev_priv) BUILD_BUG_ON(MAX_CONTEXT_HW_ID > INT_MAX); ida_init(&dev_priv->context_hw_ida); - if (i915.enable_execlists) { - /* NB: intentionally left blank. We will allocate our own - * backing objects as we need them, thank you very much */ - dev_priv->hw_context_size = 0; - } else if (HAS_HW_CONTEXTS(dev_priv)) { - dev_priv->hw_context_size = - round_up(get_context_size(dev_priv), - I915_GTT_PAGE_SIZE); - if (dev_priv->hw_context_size > (1<<20)) { - DRM_DEBUG_DRIVER("Disabling HW Contexts; invalid size %d\n", - dev_priv->hw_context_size); - dev_priv->hw_context_size = 0; - } - } - ctx = i915_gem_create_context(dev_priv, NULL); if (IS_ERR(ctx)) { DRM_ERROR("Failed to create default global context (error %ld)\n", @@ -477,8 +377,8 @@ int i915_gem_context_init(struct drm_i915_private *dev_priv) GEM_BUG_ON(!i915_gem_context_is_kernel(ctx)); DRM_DEBUG_DRIVER("%s context support initialized\n", - i915.enable_execlists ? "LR" : - dev_priv->hw_context_size ? "HW" : "fake"); + dev_priv->engine[RCS]->context_size ? "logical" : + "fake"); return 0; } @@ -941,11 +841,6 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv) return 0; } -static bool contexts_enabled(struct drm_device *dev) -{ - return i915.enable_execlists || to_i915(dev)->hw_context_size; -} - static bool client_is_banned(struct drm_i915_file_private *file_priv) { return file_priv->context_bans > I915_MAX_CLIENT_CONTEXT_BANS; @@ -954,12 +849,13 @@ static bool client_is_banned(struct drm_i915_file_private *file_priv) int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { + struct drm_i915_private *dev_priv = to_i915(dev); struct drm_i915_gem_context_create *args = data; struct drm_i915_file_private *file_priv = file->driver_priv; struct i915_gem_context *ctx; int ret; - if (!contexts_enabled(dev)) + if (!dev_priv->engine[RCS]->context_size) return -ENODEV; if (args->pad != 0) @@ -977,7 +873,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, if (ret) return ret; - ctx = i915_gem_create_context(to_i915(dev), file_priv); + ctx = i915_gem_create_context(dev_priv, file_priv); mutex_unlock(&dev->struct_mutex); if (IS_ERR(ctx)) return PTR_ERR(ctx); diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index f225bf680b6de1..6176e589cf09f9 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -122,12 +122,36 @@ static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long } static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) { + struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); + struct page *page; + + if (page_num >= obj->base.size >> PAGE_SHIFT) + return NULL; + + if (!i915_gem_object_has_struct_page(obj)) + return NULL; + + if (i915_gem_object_pin_pages(obj)) + return NULL; + + /* Synchronisation is left to the caller (via .begin_cpu_access()) */ + page = i915_gem_object_get_page(obj, page_num); + if (IS_ERR(page)) + goto err_unpin; + + return kmap(page); + +err_unpin: + i915_gem_object_unpin_pages(obj); return NULL; } static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr) { + struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); + kunmap(virt_to_page(addr)); + i915_gem_object_unpin_pages(obj); } static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index a3e59c8ef27baf..04211c970b9f23 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1019,11 +1019,11 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, for (i = 0; i < count; i++) total += exec[i].relocation_count; - reloc_offset = drm_malloc_ab(count, sizeof(*reloc_offset)); - reloc = drm_malloc_ab(total, sizeof(*reloc)); + reloc_offset = kvmalloc_array(count, sizeof(*reloc_offset), GFP_KERNEL); + reloc = kvmalloc_array(total, sizeof(*reloc), GFP_KERNEL); if (reloc == NULL || reloc_offset == NULL) { - drm_free_large(reloc); - drm_free_large(reloc_offset); + kvfree(reloc); + kvfree(reloc_offset); mutex_lock(&dev->struct_mutex); return -ENOMEM; } @@ -1099,8 +1099,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, */ err: - drm_free_large(reloc); - drm_free_large(reloc_offset); + kvfree(reloc); + kvfree(reloc_offset); return ret; } @@ -1114,6 +1114,18 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, list_for_each_entry(vma, vmas, exec_list) { struct drm_i915_gem_object *obj = vma->obj; + if (vma->exec_entry->flags & EXEC_OBJECT_CAPTURE) { + struct i915_gem_capture_list *capture; + + capture = kmalloc(sizeof(*capture), GFP_KERNEL); + if (unlikely(!capture)) + return -ENOMEM; + + capture->next = req->capture_list; + capture->vma = vma; + req->capture_list = capture; + } + if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC) continue; @@ -1859,13 +1871,13 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, } /* Copy in the exec list from userland */ - exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count); - exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); + exec_list = kvmalloc_array(sizeof(*exec_list), args->buffer_count, GFP_KERNEL); + exec2_list = kvmalloc_array(sizeof(*exec2_list), args->buffer_count, GFP_KERNEL); if (exec_list == NULL || exec2_list == NULL) { DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); - drm_free_large(exec_list); - drm_free_large(exec2_list); + kvfree(exec_list); + kvfree(exec2_list); return -ENOMEM; } ret = copy_from_user(exec_list, @@ -1874,8 +1886,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); - drm_free_large(exec_list); - drm_free_large(exec2_list); + kvfree(exec_list); + kvfree(exec2_list); return -EFAULT; } @@ -1924,8 +1936,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, } } - drm_free_large(exec_list); - drm_free_large(exec2_list); + kvfree(exec_list); + kvfree(exec2_list); return ret; } @@ -1943,7 +1955,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, return -EINVAL; } - exec2_list = drm_malloc_gfp(args->buffer_count, + exec2_list = kvmalloc_array(args->buffer_count, sizeof(*exec2_list), GFP_TEMPORARY); if (exec2_list == NULL) { @@ -1957,7 +1969,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); - drm_free_large(exec2_list); + kvfree(exec2_list); return -EFAULT; } @@ -1984,6 +1996,6 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, } } - drm_free_large(exec2_list); + kvfree(exec2_list); return ret; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 50b8f1139ff99d..4ff854e6413cf8 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -168,13 +168,11 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, if (enable_ppgtt == 3 && has_full_48bit_ppgtt) return 3; -#ifdef CONFIG_INTEL_IOMMU /* Disable ppgtt on SNB if VT-d is on. */ - if (IS_GEN6(dev_priv) && intel_iommu_gfx_mapped) { + if (IS_GEN6(dev_priv) && intel_vtd_active()) { DRM_INFO("Disabling PPGTT because VT-d is on\n"); return 0; } -#endif /* Early VLV doesn't have this */ if (IS_VALLEYVIEW(dev_priv) && dev_priv->drm.pdev->revision < 0xb) { @@ -1992,14 +1990,10 @@ void i915_ppgtt_release(struct kref *kref) */ static bool needs_idle_maps(struct drm_i915_private *dev_priv) { -#ifdef CONFIG_INTEL_IOMMU /* Query intel_iommu to see if we need the workaround. Presumably that * was loaded first. */ - if (IS_GEN5(dev_priv) && IS_MOBILE(dev_priv) && intel_iommu_gfx_mapped) - return true; -#endif - return false; + return IS_GEN5(dev_priv) && IS_MOBILE(dev_priv) && intel_vtd_active(); } void i915_check_and_clear_faults(struct drm_i915_private *dev_priv) @@ -2191,6 +2185,101 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm, gen8_set_pte(>t_base[i], scratch_pte); } +static void bxt_vtd_ggtt_wa(struct i915_address_space *vm) +{ + struct drm_i915_private *dev_priv = vm->i915; + + /* + * Make sure the internal GAM fifo has been cleared of all GTT + * writes before exiting stop_machine(). This guarantees that + * any aperture accesses waiting to start in another process + * cannot back up behind the GTT writes causing a hang. + * The register can be any arbitrary GAM register. + */ + POSTING_READ(GFX_FLSH_CNTL_GEN6); +} + +struct insert_page { + struct i915_address_space *vm; + dma_addr_t addr; + u64 offset; + enum i915_cache_level level; +}; + +static int bxt_vtd_ggtt_insert_page__cb(void *_arg) +{ + struct insert_page *arg = _arg; + + gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0); + bxt_vtd_ggtt_wa(arg->vm); + + return 0; +} + +static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm, + dma_addr_t addr, + u64 offset, + enum i915_cache_level level, + u32 unused) +{ + struct insert_page arg = { vm, addr, offset, level }; + + stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL); +} + +struct insert_entries { + struct i915_address_space *vm; + struct sg_table *st; + u64 start; + enum i915_cache_level level; +}; + +static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) +{ + struct insert_entries *arg = _arg; + + gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0); + bxt_vtd_ggtt_wa(arg->vm); + + return 0; +} + +static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm, + struct sg_table *st, + u64 start, + enum i915_cache_level level, + u32 unused) +{ + struct insert_entries arg = { vm, st, start, level }; + + stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL); +} + +struct clear_range { + struct i915_address_space *vm; + u64 start; + u64 length; +}; + +static int bxt_vtd_ggtt_clear_range__cb(void *_arg) +{ + struct clear_range *arg = _arg; + + gen8_ggtt_clear_range(arg->vm, arg->start, arg->length); + bxt_vtd_ggtt_wa(arg->vm); + + return 0; +} + +static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm, + u64 start, + u64 length) +{ + struct clear_range arg = { vm, start, length }; + + stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL); +} + static void gen6_ggtt_clear_range(struct i915_address_space *vm, u64 start, u64 length) { @@ -2583,14 +2672,14 @@ static size_t gen6_get_stolen_size(u16 snb_gmch_ctl) { snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT; snb_gmch_ctl &= SNB_GMCH_GMS_MASK; - return snb_gmch_ctl << 25; /* 32 MB units */ + return (size_t)snb_gmch_ctl << 25; /* 32 MB units */ } static size_t gen8_get_stolen_size(u16 bdw_gmch_ctl) { bdw_gmch_ctl >>= BDW_GMCH_GMS_SHIFT; bdw_gmch_ctl &= BDW_GMCH_GMS_MASK; - return bdw_gmch_ctl << 25; /* 32 MB units */ + return (size_t)bdw_gmch_ctl << 25; /* 32 MB units */ } static size_t chv_get_stolen_size(u16 gmch_ctrl) @@ -2604,11 +2693,11 @@ static size_t chv_get_stolen_size(u16 gmch_ctrl) * 0x17 to 0x1d: 4MB increments start at 36MB */ if (gmch_ctrl < 0x11) - return gmch_ctrl << 25; + return (size_t)gmch_ctrl << 25; else if (gmch_ctrl < 0x17) - return (gmch_ctrl - 0x11 + 2) << 22; + return (size_t)(gmch_ctrl - 0x11 + 2) << 22; else - return (gmch_ctrl - 0x17 + 9) << 22; + return (size_t)(gmch_ctrl - 0x17 + 9) << 22; } static size_t gen9_get_stolen_size(u16 gen9_gmch_ctl) @@ -2617,10 +2706,10 @@ static size_t gen9_get_stolen_size(u16 gen9_gmch_ctl) gen9_gmch_ctl &= BDW_GMCH_GMS_MASK; if (gen9_gmch_ctl < 0xf0) - return gen9_gmch_ctl << 25; /* 32 MB units */ + return (size_t)gen9_gmch_ctl << 25; /* 32 MB units */ else /* 4MB increments starting at 0xf0 for 4MB */ - return (gen9_gmch_ctl - 0xf0 + 1) << 22; + return (size_t)(gen9_gmch_ctl - 0xf0 + 1) << 22; } static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) @@ -2747,13 +2836,17 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) struct pci_dev *pdev = dev_priv->drm.pdev; unsigned int size; u16 snb_gmch_ctl; + int err; /* TODO: We're not aware of mappable constraints on gen8 yet */ ggtt->mappable_base = pci_resource_start(pdev, 2); ggtt->mappable_end = pci_resource_len(pdev, 2); - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(39))) - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); + if (!err) + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); + if (err) + DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err); pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); @@ -2785,6 +2878,14 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->base.insert_entries = gen8_ggtt_insert_entries; + /* Serialize GTT updates with aperture access on BXT if VT-d is on. */ + if (intel_ggtt_update_needs_vtd_wa(dev_priv)) { + ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL; + ggtt->base.insert_page = bxt_vtd_ggtt_insert_page__BKL; + if (ggtt->base.clear_range != nop_clear_range) + ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL; + } + ggtt->invalidate = gen6_ggtt_invalidate; return ggtt_probe_common(ggtt, size); @@ -2796,6 +2897,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) struct pci_dev *pdev = dev_priv->drm.pdev; unsigned int size; u16 snb_gmch_ctl; + int err; ggtt->mappable_base = pci_resource_start(pdev, 2); ggtt->mappable_end = pci_resource_len(pdev, 2); @@ -2808,8 +2910,11 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) return -ENXIO; } - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(40))) - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40)); + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40)); + if (!err) + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40)); + if (err) + DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err); pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); ggtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl); @@ -2928,10 +3033,8 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv) ggtt->base.total >> 20); DRM_DEBUG_DRIVER("GMADR size = %lldM\n", ggtt->mappable_end >> 20); DRM_DEBUG_DRIVER("GTT stolen size = %uM\n", ggtt->stolen_size >> 20); -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_gfx_mapped) + if (intel_vtd_active()) DRM_INFO("VT-d active for gfx access\n"); -#endif return 0; } @@ -2992,11 +3095,16 @@ int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv) void i915_ggtt_enable_guc(struct drm_i915_private *i915) { + GEM_BUG_ON(i915->ggtt.invalidate != gen6_ggtt_invalidate); + i915->ggtt.invalidate = guc_ggtt_invalidate; } void i915_ggtt_disable_guc(struct drm_i915_private *i915) { + /* We should only be called after i915_ggtt_enable_guc() */ + GEM_BUG_ON(i915->ggtt.invalidate != guc_ggtt_invalidate); + i915->ggtt.invalidate = gen6_ggtt_invalidate; } @@ -3106,7 +3214,7 @@ intel_rotate_pages(struct intel_rotation_info *rot_info, int ret = -ENOMEM; /* Allocate a temporary list of source pages for random access. */ - page_addr_list = drm_malloc_gfp(n_pages, + page_addr_list = kvmalloc_array(n_pages, sizeof(dma_addr_t), GFP_TEMPORARY); if (!page_addr_list) @@ -3139,14 +3247,14 @@ intel_rotate_pages(struct intel_rotation_info *rot_info, DRM_DEBUG_KMS("Created rotated page mapping for object size %zu (%ux%u tiles, %u pages)\n", obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size); - drm_free_large(page_addr_list); + kvfree(page_addr_list); return st; err_sg_alloc: kfree(st); err_st_alloc: - drm_free_large(page_addr_list); + kvfree(page_addr_list); DRM_DEBUG_KMS("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n", obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size); diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h index 174cf923c23633..915057824284bb 100644 --- a/drivers/gpu/drm/i915/i915_gem_object.h +++ b/drivers/gpu/drm/i915/i915_gem_object.h @@ -37,8 +37,8 @@ struct drm_i915_gem_object_ops { unsigned int flags; -#define I915_GEM_OBJECT_HAS_STRUCT_PAGE 0x1 -#define I915_GEM_OBJECT_IS_SHRINKABLE 0x2 +#define I915_GEM_OBJECT_HAS_STRUCT_PAGE BIT(0) +#define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) /* Interface between the GEM object and its backing storage. * get_pages() is called once prior to the use of the associated set @@ -68,8 +68,23 @@ struct drm_i915_gem_object { const struct drm_i915_gem_object_ops *ops; - /** List of VMAs backed by this object */ + /** + * @vma_list: List of VMAs backed by this object + * + * The VMA on this list are ordered by type, all GGTT vma are placed + * at the head and all ppGTT vma are placed at the tail. The different + * types of GGTT vma are unordered between themselves, use the + * @vma_tree (which has a defined order between all VMA) to find an + * exact match. + */ struct list_head vma_list; + /** + * @vma_tree: Ordered tree of VMAs backed by this object + * + * All VMA created for this object are placed in the @vma_tree for + * fast retrieval via a binary search in i915_vma_instance(). + * They are also added to @vma_list for easy iteration. + */ struct rb_root vma_tree; /** Stolen memory for this object, instead of being backed by shmem. */ diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 5ddbc94997751a..0d1e0d8873ef61 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -61,7 +61,7 @@ static bool i915_fence_enable_signaling(struct dma_fence *fence) if (i915_fence_signaled(fence)) return false; - intel_engine_enable_signaling(to_request(fence)); + intel_engine_enable_signaling(to_request(fence), true); return true; } @@ -159,7 +159,7 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt) { struct i915_dependency *dep, *next; - GEM_BUG_ON(!RB_EMPTY_NODE(&pt->node)); + GEM_BUG_ON(!list_empty(&pt->link)); /* Everyone we depended upon (the fences we wait to be signaled) * should retire before us and remove themselves from our list. @@ -185,7 +185,7 @@ i915_priotree_init(struct i915_priotree *pt) { INIT_LIST_HEAD(&pt->signalers_list); INIT_LIST_HEAD(&pt->waiters_list); - RB_CLEAR_NODE(&pt->node); + INIT_LIST_HEAD(&pt->link); pt->priority = INT_MIN; } @@ -214,12 +214,12 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno) } /* Finally reset hw state */ - tl->seqno = seqno; intel_engine_init_global_seqno(engine, seqno); + tl->seqno = seqno; list_for_each_entry(timeline, &i915->gt.timelines, link) - memset(timeline->engine[id].sync_seqno, 0, - sizeof(timeline->engine[id].sync_seqno)); + memset(timeline->engine[id].global_sync, 0, + sizeof(timeline->engine[id].global_sync)); } return 0; @@ -271,6 +271,48 @@ void i915_gem_retire_noop(struct i915_gem_active *active, /* Space left intentionally blank */ } +static void advance_ring(struct drm_i915_gem_request *request) +{ + unsigned int tail; + + /* We know the GPU must have read the request to have + * sent us the seqno + interrupt, so use the position + * of tail of the request to update the last known position + * of the GPU head. + * + * Note this requires that we are always called in request + * completion order. + */ + if (list_is_last(&request->ring_link, &request->ring->request_list)) { + /* We may race here with execlists resubmitting this request + * as we retire it. The resubmission will move the ring->tail + * forwards (to request->wa_tail). We either read the + * current value that was written to hw, or the value that + * is just about to be. Either works, if we miss the last two + * noops - they are safe to be replayed on a reset. + */ + tail = READ_ONCE(request->ring->tail); + } else { + tail = request->postfix; + } + list_del(&request->ring_link); + + request->ring->head = tail; +} + +static void free_capture_list(struct drm_i915_gem_request *request) +{ + struct i915_gem_capture_list *capture; + + capture = request->capture_list; + while (capture) { + struct i915_gem_capture_list *next = capture->next; + + kfree(capture); + capture = next; + } +} + static void i915_gem_request_retire(struct drm_i915_gem_request *request) { struct intel_engine_cs *engine = request->engine; @@ -287,16 +329,6 @@ static void i915_gem_request_retire(struct drm_i915_gem_request *request) list_del_init(&request->link); spin_unlock_irq(&engine->timeline->lock); - /* We know the GPU must have read the request to have - * sent us the seqno + interrupt, so use the position - * of tail of the request to update the last known position - * of the GPU head. - * - * Note this requires that we are always called in request - * completion order. - */ - list_del(&request->ring_link); - request->ring->head = request->postfix; if (!--request->i915->gt.active_requests) { GEM_BUG_ON(!request->i915->gt.awake); mod_delayed_work(request->i915->wq, @@ -304,6 +336,9 @@ static void i915_gem_request_retire(struct drm_i915_gem_request *request) msecs_to_jiffies(100)); } unreserve_seqno(request->engine); + advance_ring(request); + + free_capture_list(request); /* Walk through the active list, calling retire on each. This allows * objects to track their GPU activity and mark themselves as idle @@ -402,7 +437,7 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request) spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); request->global_seqno = seqno; if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags)) - intel_engine_enable_signaling(request); + intel_engine_enable_signaling(request, false); spin_unlock(&request->lock); engine->emit_breadcrumb(request, @@ -503,9 +538,6 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) * * @engine: engine that we wish to issue the request on. * @ctx: context that the request will be associated with. - * This can be NULL if the request is not directly related to - * any specific user context, in which case this function will - * choose an appropriate context to use. * * Returns a pointer to the allocated request if successful, * or an error code if not. @@ -516,6 +548,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine, { struct drm_i915_private *dev_priv = engine->i915; struct drm_i915_gem_request *req; + struct intel_ring *ring; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -530,9 +563,10 @@ i915_gem_request_alloc(struct intel_engine_cs *engine, * GGTT space, so do this first before we reserve a seqno for * ourselves. */ - ret = engine->context_pin(engine, ctx); - if (ret) - return ERR_PTR(ret); + ring = engine->context_pin(engine, ctx); + if (IS_ERR(ring)) + return ERR_CAST(ring); + GEM_BUG_ON(!ring); ret = reserve_seqno(engine); if (ret) @@ -598,11 +632,13 @@ i915_gem_request_alloc(struct intel_engine_cs *engine, req->i915 = dev_priv; req->engine = engine; req->ctx = ctx; + req->ring = ring; /* No zalloc, must clear what we need by hand */ req->global_seqno = 0; req->file_priv = NULL; req->batch = NULL; + req->capture_list = NULL; /* * Reserve space in the ring buffer for all the commands required to @@ -623,7 +659,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine, * GPU processing the request, we never over-estimate the * position of the head. */ - req->head = req->ring->tail; + req->head = req->ring->emit; /* Check that we didn't interrupt ourselves with a new request */ GEM_BUG_ON(req->timeline->seqno != req->fence.seqno); @@ -651,6 +687,7 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to, int ret; GEM_BUG_ON(to == from); + GEM_BUG_ON(to->timeline == from->timeline); if (i915_gem_request_completed(from)) return 0; @@ -663,9 +700,6 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to, return ret; } - if (to->timeline == from->timeline) - return 0; - if (to->engine == from->engine) { ret = i915_sw_fence_await_sw_fence_gfp(&to->submit, &from->submit, @@ -674,55 +708,45 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to, } seqno = i915_gem_request_global_seqno(from); - if (!seqno) { - ret = i915_sw_fence_await_dma_fence(&to->submit, - &from->fence, 0, - GFP_KERNEL); - return ret < 0 ? ret : 0; - } + if (!seqno) + goto await_dma_fence; - if (seqno <= to->timeline->sync_seqno[from->engine->id]) - return 0; + if (!to->engine->semaphore.sync_to) { + if (!__i915_gem_request_started(from, seqno)) + goto await_dma_fence; - trace_i915_gem_ring_sync_to(to, from); - if (!i915.semaphores) { - if (!i915_spin_request(from, TASK_INTERRUPTIBLE, 2)) { - ret = i915_sw_fence_await_dma_fence(&to->submit, - &from->fence, 0, - GFP_KERNEL); - if (ret < 0) - return ret; - } + if (!__i915_spin_request(from, seqno, TASK_INTERRUPTIBLE, 2)) + goto await_dma_fence; } else { + GEM_BUG_ON(!from->engine->semaphore.signal); + + if (seqno <= to->timeline->global_sync[from->engine->id]) + return 0; + + trace_i915_gem_ring_sync_to(to, from); ret = to->engine->semaphore.sync_to(to, from); if (ret) return ret; + + to->timeline->global_sync[from->engine->id] = seqno; } - to->timeline->sync_seqno[from->engine->id] = seqno; return 0; + +await_dma_fence: + ret = i915_sw_fence_await_dma_fence(&to->submit, + &from->fence, 0, + GFP_KERNEL); + return ret < 0 ? ret : 0; } int i915_gem_request_await_dma_fence(struct drm_i915_gem_request *req, struct dma_fence *fence) { - struct dma_fence_array *array; + struct dma_fence **child = &fence; + unsigned int nchild = 1; int ret; - int i; - - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return 0; - - if (dma_fence_is_i915(fence)) - return i915_gem_request_await_request(req, to_request(fence)); - - if (!dma_fence_is_array(fence)) { - ret = i915_sw_fence_await_dma_fence(&req->submit, - fence, I915_FENCE_TIMEOUT, - GFP_KERNEL); - return ret < 0 ? ret : 0; - } /* Note that if the fence-array was created in signal-on-any mode, * we should *not* decompose it into its individual fences. However, @@ -731,21 +755,46 @@ i915_gem_request_await_dma_fence(struct drm_i915_gem_request *req, * amdgpu and we should not see any incoming fence-array from * sync-file being in signal-on-any mode. */ + if (dma_fence_is_array(fence)) { + struct dma_fence_array *array = to_dma_fence_array(fence); + + child = array->fences; + nchild = array->num_fences; + GEM_BUG_ON(!nchild); + } + + do { + fence = *child++; + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + continue; + + /* + * Requests on the same timeline are explicitly ordered, along + * with their dependencies, by i915_add_request() which ensures + * that requests are submitted in-order through each ring. + */ + if (fence->context == req->fence.context) + continue; - array = to_dma_fence_array(fence); - for (i = 0; i < array->num_fences; i++) { - struct dma_fence *child = array->fences[i]; + /* Squash repeated waits to the same timelines */ + if (fence->context != req->i915->mm.unordered_timeline && + intel_timeline_sync_is_later(req->timeline, fence)) + continue; - if (dma_fence_is_i915(child)) + if (dma_fence_is_i915(fence)) ret = i915_gem_request_await_request(req, - to_request(child)); + to_request(fence)); else - ret = i915_sw_fence_await_dma_fence(&req->submit, - child, I915_FENCE_TIMEOUT, + ret = i915_sw_fence_await_dma_fence(&req->submit, fence, + I915_FENCE_TIMEOUT, GFP_KERNEL); if (ret < 0) return ret; - } + + /* Record the latest fence used against each timeline */ + if (fence->context != req->i915->mm.unordered_timeline) + intel_timeline_sync_set(req->timeline, fence); + } while (--nchild); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h index 129c58bb480550..7b7c84369d782e 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.h +++ b/drivers/gpu/drm/i915/i915_gem_request.h @@ -67,12 +67,18 @@ struct i915_dependency { struct i915_priotree { struct list_head signalers_list; /* those before us, we depend upon */ struct list_head waiters_list; /* those after us, they depend upon us */ - struct rb_node node; + struct list_head link; int priority; #define I915_PRIORITY_MAX 1024 +#define I915_PRIORITY_NORMAL 0 #define I915_PRIORITY_MIN (-I915_PRIORITY_MAX) }; +struct i915_gem_capture_list { + struct i915_gem_capture_list *next; + struct i915_vma *vma; +}; + /** * Request queue structure. * @@ -167,6 +173,12 @@ struct drm_i915_gem_request { * error state dump only). */ struct i915_vma *batch; + /** Additional buffers requested by userspace to be captured upon + * a GPU hang. The vma/obj on this list are protected by their + * active reference - all objects on this list must also be + * on the active_list (of their final request). + */ + struct i915_gem_capture_list *capture_list; struct list_head active_list; /** Time at which this request was emitted, in jiffies. */ diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 57d9f7f4ef159c..0fd2b58ce47517 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -35,9 +35,9 @@ #include "i915_drv.h" #include "i915_trace.h" -static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) +static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock) { - switch (mutex_trylock_recursive(&dev->struct_mutex)) { + switch (mutex_trylock_recursive(&dev_priv->drm.struct_mutex)) { case MUTEX_TRYLOCK_FAILED: return false; @@ -53,21 +53,29 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) BUG(); } -static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock) +static void shrinker_unlock(struct drm_i915_private *dev_priv, bool unlock) { if (!unlock) return; - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&dev_priv->drm.struct_mutex); } static bool any_vma_pinned(struct drm_i915_gem_object *obj) { struct i915_vma *vma; - list_for_each_entry(vma, &obj->vma_list, obj_link) + list_for_each_entry(vma, &obj->vma_list, obj_link) { + /* Only GGTT vma may be permanently pinned, and are always + * at the start of the list. We can stop hunting as soon + * as we see a ppGTT vma. + */ + if (!i915_vma_is_ggtt(vma)) + break; + if (i915_vma_is_pinned(vma)) return true; + } return false; } @@ -153,7 +161,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, unsigned long count = 0; bool unlock; - if (!i915_gem_shrinker_lock(&dev_priv->drm, &unlock)) + if (!shrinker_lock(dev_priv, &unlock)) return 0; trace_i915_gem_shrink(dev_priv, target, flags); @@ -241,7 +249,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, i915_gem_retire_requests(dev_priv); - i915_gem_shrinker_unlock(&dev_priv->drm, unlock); + shrinker_unlock(dev_priv, unlock); return count; } @@ -279,12 +287,11 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = container_of(shrinker, struct drm_i915_private, mm.shrinker); - struct drm_device *dev = &dev_priv->drm; struct drm_i915_gem_object *obj; unsigned long count; bool unlock; - if (!i915_gem_shrinker_lock(dev, &unlock)) + if (!shrinker_lock(dev_priv, &unlock)) return 0; i915_gem_retire_requests(dev_priv); @@ -299,7 +306,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; } - i915_gem_shrinker_unlock(dev, unlock); + shrinker_unlock(dev_priv, unlock); return count; } @@ -309,11 +316,10 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = container_of(shrinker, struct drm_i915_private, mm.shrinker); - struct drm_device *dev = &dev_priv->drm; unsigned long freed; bool unlock; - if (!i915_gem_shrinker_lock(dev, &unlock)) + if (!shrinker_lock(dev_priv, &unlock)) return SHRINK_STOP; freed = i915_gem_shrink(dev_priv, @@ -327,26 +333,20 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); - i915_gem_shrinker_unlock(dev, unlock); + shrinker_unlock(dev_priv, unlock); return freed; } -struct shrinker_lock_uninterruptible { - bool was_interruptible; - bool unlock; -}; - static bool -i915_gem_shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv, - struct shrinker_lock_uninterruptible *slu, - int timeout_ms) +shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv, bool *unlock, + int timeout_ms) { unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms); do { if (i915_gem_wait_for_idle(dev_priv, 0) == 0 && - i915_gem_shrinker_lock(&dev_priv->drm, &slu->unlock)) + shrinker_lock(dev_priv, unlock)) break; schedule_timeout_killable(1); @@ -359,29 +359,19 @@ i915_gem_shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv, } } while (1); - slu->was_interruptible = dev_priv->mm.interruptible; - dev_priv->mm.interruptible = false; return true; } -static void -i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv, - struct shrinker_lock_uninterruptible *slu) -{ - dev_priv->mm.interruptible = slu->was_interruptible; - i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock); -} - static int i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) { struct drm_i915_private *dev_priv = container_of(nb, struct drm_i915_private, mm.oom_notifier); - struct shrinker_lock_uninterruptible slu; struct drm_i915_gem_object *obj; unsigned long unevictable, bound, unbound, freed_pages; + bool unlock; - if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000)) + if (!shrinker_lock_uninterruptible(dev_priv, &unlock, 5000)) return NOTIFY_DONE; freed_pages = i915_gem_shrink_all(dev_priv); @@ -410,7 +400,7 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) bound += obj->base.size >> PAGE_SHIFT; } - i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu); + shrinker_unlock(dev_priv, unlock); if (freed_pages || unbound || bound) pr_info("Purging GPU memory, %lu pages freed, " @@ -430,12 +420,12 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr { struct drm_i915_private *dev_priv = container_of(nb, struct drm_i915_private, mm.vmap_notifier); - struct shrinker_lock_uninterruptible slu; struct i915_vma *vma, *next; unsigned long freed_pages = 0; + bool unlock; int ret; - if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000)) + if (!shrinker_lock_uninterruptible(dev_priv, &unlock, 5000)) return NOTIFY_DONE; /* Force everything onto the inactive lists */ @@ -460,7 +450,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr } out: - i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu); + shrinker_unlock(dev_priv, unlock); *(unsigned long *)ptr += freed_pages; return NOTIFY_DONE; diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index f3abdc27c5dd16..681db6083f4dac 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -414,12 +414,10 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) return 0; } -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_gfx_mapped && INTEL_GEN(dev_priv) < 8) { + if (intel_vtd_active() && INTEL_GEN(dev_priv) < 8) { DRM_INFO("DMAR active, disabling use of stolen memory\n"); return 0; } -#endif if (ggtt->stolen_size == 0) return 0; diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index a0d6d4317a490b..fb5231f98c0d62 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -278,7 +278,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->mm.quirked = false; } if (!i915_gem_object_is_tiled(obj)) { - GEM_BUG_ON(!obj->mm.quirked); + GEM_BUG_ON(obj->mm.quirked); __i915_gem_object_pin_pages(obj); obj->mm.quirked = true; } diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.c b/drivers/gpu/drm/i915/i915_gem_timeline.c index b596ca7ee058cc..c597ce277a043b 100644 --- a/drivers/gpu/drm/i915/i915_gem_timeline.c +++ b/drivers/gpu/drm/i915/i915_gem_timeline.c @@ -23,6 +23,32 @@ */ #include "i915_drv.h" +#include "i915_syncmap.h" + +static void __intel_timeline_init(struct intel_timeline *tl, + struct i915_gem_timeline *parent, + u64 context, + struct lock_class_key *lockclass, + const char *lockname) +{ + tl->fence_context = context; + tl->common = parent; +#ifdef CONFIG_DEBUG_SPINLOCK + __raw_spin_lock_init(&tl->lock.rlock, lockname, lockclass); +#else + spin_lock_init(&tl->lock); +#endif + init_request_active(&tl->last_request, NULL); + INIT_LIST_HEAD(&tl->requests); + i915_syncmap_init(&tl->sync); +} + +static void __intel_timeline_fini(struct intel_timeline *tl) +{ + GEM_BUG_ON(!list_empty(&tl->requests)); + + i915_syncmap_free(&tl->sync); +} static int __i915_gem_timeline_init(struct drm_i915_private *i915, struct i915_gem_timeline *timeline, @@ -35,6 +61,14 @@ static int __i915_gem_timeline_init(struct drm_i915_private *i915, lockdep_assert_held(&i915->drm.struct_mutex); + /* + * Ideally we want a set of engines on a single leaf as we expect + * to mostly be tracking synchronisation between engines. It is not + * a huge issue if this is not the case, but we may want to mitigate + * any page crossing penalties if they become an issue. + */ + BUILD_BUG_ON(KSYNCMAP < I915_NUM_ENGINES); + timeline->i915 = i915; timeline->name = kstrdup(name ?: "[kernel]", GFP_KERNEL); if (!timeline->name) @@ -44,19 +78,10 @@ static int __i915_gem_timeline_init(struct drm_i915_private *i915, /* Called during early_init before we know how many engines there are */ fences = dma_fence_context_alloc(ARRAY_SIZE(timeline->engine)); - for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) { - struct intel_timeline *tl = &timeline->engine[i]; - - tl->fence_context = fences++; - tl->common = timeline; -#ifdef CONFIG_DEBUG_SPINLOCK - __raw_spin_lock_init(&tl->lock.rlock, lockname, lockclass); -#else - spin_lock_init(&tl->lock); -#endif - init_request_active(&tl->last_request, NULL); - INIT_LIST_HEAD(&tl->requests); - } + for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) + __intel_timeline_init(&timeline->engine[i], + timeline, fences++, + lockclass, lockname); return 0; } @@ -81,18 +106,52 @@ int i915_gem_timeline_init__global(struct drm_i915_private *i915) &class, "&global_timeline->lock"); } +/** + * i915_gem_timelines_mark_idle -- called when the driver idles + * @i915 - the drm_i915_private device + * + * When the driver is completely idle, we know that all of our sync points + * have been signaled and our tracking is then entirely redundant. Any request + * to wait upon an older sync point will be completed instantly as we know + * the fence is signaled and therefore we will not even look them up in the + * sync point map. + */ +void i915_gem_timelines_mark_idle(struct drm_i915_private *i915) +{ + struct i915_gem_timeline *timeline; + int i; + + lockdep_assert_held(&i915->drm.struct_mutex); + + list_for_each_entry(timeline, &i915->gt.timelines, link) { + for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) { + struct intel_timeline *tl = &timeline->engine[i]; + + /* + * All known fences are completed so we can scrap + * the current sync point tracking and start afresh, + * any attempt to wait upon a previous sync point + * will be skipped as the fence was signaled. + */ + i915_syncmap_free(&tl->sync); + } + } +} + void i915_gem_timeline_fini(struct i915_gem_timeline *timeline) { int i; lockdep_assert_held(&timeline->i915->drm.struct_mutex); - for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) { - struct intel_timeline *tl = &timeline->engine[i]; - - GEM_BUG_ON(!list_empty(&tl->requests)); - } + for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) + __intel_timeline_fini(&timeline->engine[i]); list_del(&timeline->link); kfree(timeline->name); } + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/mock_timeline.c" +#include "selftests/i915_gem_timeline.c" +#endif diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.h b/drivers/gpu/drm/i915/i915_gem_timeline.h index 6c53e14cab2a4d..bfb5eb94c64d0e 100644 --- a/drivers/gpu/drm/i915/i915_gem_timeline.h +++ b/drivers/gpu/drm/i915/i915_gem_timeline.h @@ -27,7 +27,9 @@ #include +#include "i915_utils.h" #include "i915_gem_request.h" +#include "i915_syncmap.h" struct i915_gem_timeline; @@ -55,7 +57,25 @@ struct intel_timeline { * struct_mutex. */ struct i915_gem_active last_request; - u32 sync_seqno[I915_NUM_ENGINES]; + + /** + * We track the most recent seqno that we wait on in every context so + * that we only have to emit a new await and dependency on a more + * recent sync point. As the contexts may be executed out-of-order, we + * have to track each individually and can not rely on an absolute + * global_seqno. When we know that all tracked fences are completed + * (i.e. when the driver is idle), we know that the syncmap is + * redundant and we can discard it without loss of generality. + */ + struct i915_syncmap *sync; + /** + * Separately to the inter-context seqno map above, we track the last + * barrier (e.g. semaphore wait) to the global engine timelines. Note + * that this tracks global_seqno rather than the context.seqno, and + * so it is subject to the limitations of hw wraparound and that we + * may need to revoke global_seqno (on pre-emption). + */ + u32 global_sync[I915_NUM_ENGINES]; struct i915_gem_timeline *common; }; @@ -73,6 +93,31 @@ int i915_gem_timeline_init(struct drm_i915_private *i915, struct i915_gem_timeline *tl, const char *name); int i915_gem_timeline_init__global(struct drm_i915_private *i915); +void i915_gem_timelines_mark_idle(struct drm_i915_private *i915); void i915_gem_timeline_fini(struct i915_gem_timeline *tl); +static inline int __intel_timeline_sync_set(struct intel_timeline *tl, + u64 context, u32 seqno) +{ + return i915_syncmap_set(&tl->sync, context, seqno); +} + +static inline int intel_timeline_sync_set(struct intel_timeline *tl, + const struct dma_fence *fence) +{ + return __intel_timeline_sync_set(tl, fence->context, fence->seqno); +} + +static inline bool __intel_timeline_sync_is_later(struct intel_timeline *tl, + u64 context, u32 seqno) +{ + return i915_syncmap_is_later(&tl->sync, context, seqno); +} + +static inline bool intel_timeline_sync_is_later(struct intel_timeline *tl, + const struct dma_fence *fence) +{ + return __intel_timeline_sync_is_later(tl, fence->context, fence->seqno); +} + #endif diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 58ccf8b8ca1c92..1a0ce1dc68f548 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) ret = -ENOMEM; pinned = 0; - pvec = drm_malloc_gfp(npages, sizeof(struct page *), GFP_TEMPORARY); + pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_TEMPORARY); if (pvec != NULL) { struct mm_struct *mm = obj->userptr.mm->mm; unsigned int flags = 0; @@ -555,7 +555,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) mutex_unlock(&obj->mm.lock); release_pages(pvec, pinned, 0); - drm_free_large(pvec); + kvfree(pvec); i915_gem_object_put(obj); put_task_struct(work->task); @@ -642,7 +642,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) pinned = 0; if (mm == current->mm) { - pvec = drm_malloc_gfp(num_pages, sizeof(struct page *), + pvec = kvmalloc_array(num_pages, sizeof(struct page *), GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN); @@ -669,7 +669,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) if (IS_ERR(pages)) release_pages(pvec, pinned, 0); - drm_free_large(pvec); + kvfree(pvec); return pages; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8effc59f5cb572..e18f350bc36425 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -712,6 +712,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, print_error_obj(m, dev_priv->engine[i], NULL, obj); } + for (j = 0; j < ee->user_bo_count; j++) + print_error_obj(m, dev_priv->engine[i], + "user", ee->user_bo[j]); + if (ee->num_requests) { err_printf(m, "%s --- %d requests\n", dev_priv->engine[i]->name, @@ -825,11 +829,15 @@ void __i915_gpu_state_free(struct kref *error_ref) { struct i915_gpu_state *error = container_of(error_ref, typeof(*error), ref); - int i; + long i, j; for (i = 0; i < ARRAY_SIZE(error->engine); i++) { struct drm_i915_error_engine *ee = &error->engine[i]; + for (j = 0; j < ee->user_bo_count; j++) + i915_error_object_free(ee->user_bo[j]); + kfree(ee->user_bo); + i915_error_object_free(ee->batchbuffer); i915_error_object_free(ee->wa_batchbuffer); i915_error_object_free(ee->ringbuffer); @@ -1316,12 +1324,17 @@ static void engine_record_requests(struct intel_engine_cs *engine, static void error_record_engine_execlists(struct intel_engine_cs *engine, struct drm_i915_error_engine *ee) { + const struct execlist_port *port = engine->execlist_port; unsigned int n; - for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) - if (engine->execlist_port[n].request) - record_request(engine->execlist_port[n].request, - &ee->execlist[n]); + for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) { + struct drm_i915_gem_request *rq = port_request(&port[n]); + + if (!rq) + break; + + record_request(rq, &ee->execlist[n]); + } } static void record_context(struct drm_i915_error_context *e, @@ -1346,6 +1359,35 @@ static void record_context(struct drm_i915_error_context *e, e->active = ctx->active_count; } +static void request_record_user_bo(struct drm_i915_gem_request *request, + struct drm_i915_error_engine *ee) +{ + struct i915_gem_capture_list *c; + struct drm_i915_error_object **bo; + long count; + + count = 0; + for (c = request->capture_list; c; c = c->next) + count++; + + bo = NULL; + if (count) + bo = kcalloc(count, sizeof(*bo), GFP_ATOMIC); + if (!bo) + return; + + count = 0; + for (c = request->capture_list; c; c = c->next) { + bo[count] = i915_error_object_create(request->i915, c->vma); + if (!bo[count]) + break; + count++; + } + + ee->user_bo = bo; + ee->user_bo_count = count; +} + static void i915_gem_record_rings(struct drm_i915_private *dev_priv, struct i915_gpu_state *error) { @@ -1392,6 +1434,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, ee->wa_batchbuffer = i915_error_object_create(dev_priv, engine->scratch); + request_record_user_bo(request, ee); ee->ctx = i915_error_object_create(dev_priv, @@ -1560,6 +1603,9 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, error->done_reg = I915_READ(DONE_REG); } + if (INTEL_GEN(dev_priv) >= 5) + error->ccid = I915_READ(CCID); + /* 3: Feature specific registers */ if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) { error->gam_ecochk = I915_READ(GAM_ECOCHK); @@ -1567,9 +1613,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, } /* 4: Everything else */ - if (HAS_HW_CONTEXTS(dev_priv)) - error->ccid = I915_READ(CCID); - if (INTEL_GEN(dev_priv) >= 8) { error->ier = I915_READ(GEN8_DE_MISC_IER); for (i = 0; i < 4; i++) diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c index 1642fff9cf135d..48a1e9349a2ce2 100644 --- a/drivers/gpu/drm/i915/i915_guc_submission.c +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -105,7 +105,7 @@ static int __reserve_doorbell(struct i915_guc_client *client) end += offset; } - id = find_next_zero_bit(client->guc->doorbell_bitmap, offset, end); + id = find_next_zero_bit(client->guc->doorbell_bitmap, end, offset); if (id == end) return -ENOSPC; @@ -480,9 +480,7 @@ static void guc_wq_item_append(struct i915_guc_client *client, GEM_BUG_ON(freespace < wqi_size); /* The GuC firmware wants the tail index in QWords, not bytes */ - tail = rq->tail; - assert_ring_tail_valid(rq->ring, rq->tail); - tail >>= 3; + tail = intel_ring_set_tail(rq->ring, rq->tail) >> 3; GEM_BUG_ON(tail > WQ_RING_TAIL_MAX); /* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we @@ -616,12 +614,6 @@ static void __i915_guc_submit(struct drm_i915_gem_request *rq) b_ret = guc_ring_doorbell(client); client->submissions[engine_id] += 1; - client->retcode = b_ret; - if (b_ret) - client->b_fail += 1; - - guc->submissions[engine_id] += 1; - guc->last_seqno[engine_id] = rq->global_seqno; spin_unlock_irqrestore(&client->wq_lock, flags); } @@ -651,47 +643,68 @@ static void nested_enable_signaling(struct drm_i915_gem_request *rq) trace_dma_fence_enable_signal(&rq->fence); spin_lock_nested(&rq->lock, SINGLE_DEPTH_NESTING); - intel_engine_enable_signaling(rq); + intel_engine_enable_signaling(rq, true); spin_unlock(&rq->lock); } +static void port_assign(struct execlist_port *port, + struct drm_i915_gem_request *rq) +{ + GEM_BUG_ON(rq == port_request(port)); + + if (port_isset(port)) + i915_gem_request_put(port_request(port)); + + port_set(port, i915_gem_request_get(rq)); + nested_enable_signaling(rq); +} + static bool i915_guc_dequeue(struct intel_engine_cs *engine) { struct execlist_port *port = engine->execlist_port; - struct drm_i915_gem_request *last = port[0].request; + struct drm_i915_gem_request *last = port_request(port); struct rb_node *rb; bool submit = false; spin_lock_irq(&engine->timeline->lock); rb = engine->execlist_first; + GEM_BUG_ON(rb_first(&engine->execlist_queue) != rb); while (rb) { - struct drm_i915_gem_request *rq = - rb_entry(rb, typeof(*rq), priotree.node); - - if (last && rq->ctx != last->ctx) { - if (port != engine->execlist_port) - break; - - i915_gem_request_assign(&port->request, last); - nested_enable_signaling(last); - port++; + struct i915_priolist *p = rb_entry(rb, typeof(*p), node); + struct drm_i915_gem_request *rq, *rn; + + list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) { + if (last && rq->ctx != last->ctx) { + if (port != engine->execlist_port) { + __list_del_many(&p->requests, + &rq->priotree.link); + goto done; + } + + if (submit) + port_assign(port, last); + port++; + } + + INIT_LIST_HEAD(&rq->priotree.link); + rq->priotree.priority = INT_MAX; + + i915_guc_submit(rq); + trace_i915_gem_request_in(rq, port_index(port, engine)); + last = rq; + submit = true; } rb = rb_next(rb); - rb_erase(&rq->priotree.node, &engine->execlist_queue); - RB_CLEAR_NODE(&rq->priotree.node); - rq->priotree.priority = INT_MAX; - - i915_guc_submit(rq); - trace_i915_gem_request_in(rq, port - engine->execlist_port); - last = rq; - submit = true; - } - if (submit) { - i915_gem_request_assign(&port->request, last); - nested_enable_signaling(last); - engine->execlist_first = rb; + rb_erase(&p->node, &engine->execlist_queue); + INIT_LIST_HEAD(&p->requests); + if (p->priority != I915_PRIORITY_NORMAL) + kmem_cache_free(engine->i915->priorities, p); } +done: + engine->execlist_first = rb; + if (submit) + port_assign(port, last); spin_unlock_irq(&engine->timeline->lock); return submit; @@ -705,17 +718,19 @@ static void i915_guc_irq_handler(unsigned long data) bool submit; do { - rq = port[0].request; + rq = port_request(&port[0]); while (rq && i915_gem_request_completed(rq)) { trace_i915_gem_request_out(rq); i915_gem_request_put(rq); - port[0].request = port[1].request; - port[1].request = NULL; - rq = port[0].request; + + port[0] = port[1]; + memset(&port[1], 0, sizeof(port[1])); + + rq = port_request(&port[0]); } submit = false; - if (!port[1].request) + if (!port_count(&port[1])) submit = i915_guc_dequeue(engine); } while (submit); } @@ -1053,8 +1068,7 @@ static int guc_ads_create(struct intel_guc *guc) dev_priv->engine[RCS]->status_page.ggtt_offset; for_each_engine(engine, dev_priv, id) - blob->ads.eng_state_size[engine->guc_id] = - intel_lr_context_size(engine); + blob->ads.eng_state_size[engine->guc_id] = engine->context_size; base = guc_ggtt_offset(vma); blob->ads.scheduler_policies = base + ptr_offset(blob, policies); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 190f6aa5d15eb8..7b7f55a28eec20 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -720,9 +720,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, unsigned int pipe) struct drm_i915_private *dev_priv = to_i915(dev); i915_reg_t high_frame, low_frame; u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal; - struct intel_crtc *intel_crtc = intel_get_crtc_for_pipe(dev_priv, - pipe); - const struct drm_display_mode *mode = &intel_crtc->base.hwmode; + const struct drm_display_mode *mode = &dev->vblank[pipe].hwmode; unsigned long irqflags; htotal = mode->crtc_htotal; @@ -779,13 +777,17 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); - const struct drm_display_mode *mode = &crtc->base.hwmode; + const struct drm_display_mode *mode; + struct drm_vblank_crtc *vblank; enum pipe pipe = crtc->pipe; int position, vtotal; if (!crtc->active) return -1; + vblank = &crtc->base.dev->vblank[drm_crtc_index(&crtc->base)]; + mode = &vblank->hwmode; + vtotal = mode->crtc_vtotal; if (mode->flags & DRM_MODE_FLAG_INTERLACE) vtotal /= 2; @@ -827,10 +829,10 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc) return (position + crtc->scanline_offset) % vtotal; } -static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, - unsigned int flags, int *vpos, int *hpos, - ktime_t *stime, ktime_t *etime, - const struct drm_display_mode *mode) +static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, + bool in_vblank_irq, int *vpos, int *hpos, + ktime_t *stime, ktime_t *etime, + const struct drm_display_mode *mode) { struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc = intel_get_crtc_for_pipe(dev_priv, @@ -838,13 +840,12 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, int position; int vbl_start, vbl_end, hsync_start, htotal, vtotal; bool in_vbl = true; - int ret = 0; unsigned long irqflags; if (WARN_ON(!mode->crtc_clock)) { DRM_DEBUG_DRIVER("trying to get scanoutpos for disabled " "pipe %c\n", pipe_name(pipe)); - return 0; + return false; } htotal = mode->crtc_htotal; @@ -859,8 +860,6 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, vtotal /= 2; } - ret |= DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE; - /* * Lock uncore.lock, as we will do multiple timing critical raw * register reads, potentially with preemption disabled, so the @@ -944,11 +943,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, *hpos = position - (*vpos * htotal); } - /* In vblank? */ - if (in_vbl) - ret |= DRM_SCANOUTPOS_IN_VBLANK; - - return ret; + return true; } int intel_get_crtc_scanline(struct intel_crtc *crtc) @@ -964,37 +959,6 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc) return position; } -static int i915_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags) -{ - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *crtc; - - if (pipe >= INTEL_INFO(dev_priv)->num_pipes) { - DRM_ERROR("Invalid crtc %u\n", pipe); - return -EINVAL; - } - - /* Get drm_crtc to timestamp: */ - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - if (crtc == NULL) { - DRM_ERROR("Invalid crtc %u\n", pipe); - return -EINVAL; - } - - if (!crtc->base.hwmode.crtc_clock) { - DRM_DEBUG_KMS("crtc %u is disabled\n", pipe); - return -EBUSY; - } - - /* Helper routine in DRM core does all the work: */ - return drm_calc_vbltimestamp_from_scanoutpos(dev, pipe, max_error, - vblank_time, flags, - &crtc->base.hwmode); -} - static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv) { u32 busy_up, busy_down, max_avg, min_avg; @@ -1236,7 +1200,7 @@ static void gen6_pm_rps_work(struct work_struct *work) static void ivybridge_parity_work(struct work_struct *work) { struct drm_i915_private *dev_priv = - container_of(work, struct drm_i915_private, l3_parity.error_work); + container_of(work, typeof(*dev_priv), l3_parity.error_work); u32 error_status, row, bank, subbank; char *parity_event[6]; uint32_t misccpctl; @@ -1353,14 +1317,16 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv, ivybridge_parity_error_irq_handler(dev_priv, gt_iir); } -static __always_inline void +static void gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift) { bool tasklet = false; if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift)) { - set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); - tasklet = true; + if (port_count(&engine->execlist_port[0])) { + __set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); + tasklet = true; + } } if (iir & (GT_RENDER_USER_INTERRUPT << test_shift)) { @@ -4230,11 +4196,15 @@ static void i965_irq_uninstall(struct drm_device * dev) void intel_irq_init(struct drm_i915_private *dev_priv) { struct drm_device *dev = &dev_priv->drm; + int i; intel_hpd_init_work(dev_priv); INIT_WORK(&dev_priv->rps.work, gen6_pm_rps_work); + INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work); + for (i = 0; i < MAX_L3_SLICES; ++i) + dev_priv->l3_parity.remap_info[i] = NULL; if (HAS_GUC_SCHED(dev_priv)) dev_priv->pm_guc_events = GEN9_GUC_TO_HOST_INT_EVENT; @@ -4291,7 +4261,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev_priv->hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD; - dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp; + dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos; dev->driver->get_scanout_position = i915_get_crtc_scanoutpos; if (IS_CHERRYVIEW(dev_priv)) { @@ -4359,6 +4329,20 @@ void intel_irq_init(struct drm_i915_private *dev_priv) } } +/** + * intel_irq_fini - deinitializes IRQ support + * @i915: i915 device instance + * + * This function deinitializes all the IRQ support. + */ +void intel_irq_fini(struct drm_i915_private *i915) +{ + int i; + + for (i = 0; i < MAX_L3_SLICES; ++i) + kfree(i915->l3_parity.remap_info[i]); +} + /** * intel_irq_install - enables the hardware interrupt * @dev_priv: i915 device instance diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index f87b0c4e564d8b..cf43dc1d539fdb 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -220,7 +220,6 @@ static const struct intel_device_info intel_ironlake_m_info = { .has_rc6 = 1, \ .has_rc6p = 1, \ .has_gmbus_irq = 1, \ - .has_hw_contexts = 1, \ .has_aliasing_ppgtt = 1, \ GEN_DEFAULT_PIPEOFFSETS, \ CURSOR_OFFSETS @@ -245,7 +244,6 @@ static const struct intel_device_info intel_sandybridge_m_info = { .has_rc6 = 1, \ .has_rc6p = 1, \ .has_gmbus_irq = 1, \ - .has_hw_contexts = 1, \ .has_aliasing_ppgtt = 1, \ .has_full_ppgtt = 1, \ GEN_DEFAULT_PIPEOFFSETS, \ @@ -280,7 +278,6 @@ static const struct intel_device_info intel_valleyview_info = { .has_runtime_pm = 1, .has_rc6 = 1, .has_gmbus_irq = 1, - .has_hw_contexts = 1, .has_gmch_display = 1, .has_hotplug = 1, .has_aliasing_ppgtt = 1, @@ -340,7 +337,6 @@ static const struct intel_device_info intel_cherryview_info = { .has_resource_streamer = 1, .has_rc6 = 1, .has_gmbus_irq = 1, - .has_hw_contexts = 1, .has_logical_ring_contexts = 1, .has_gmch_display = 1, .has_aliasing_ppgtt = 1, @@ -387,10 +383,8 @@ static const struct intel_device_info intel_skylake_gt3_info = { .has_rc6 = 1, \ .has_dp_mst = 1, \ .has_gmbus_irq = 1, \ - .has_hw_contexts = 1, \ .has_logical_ring_contexts = 1, \ .has_guc = 1, \ - .has_decoupled_mmio = 1, \ .has_aliasing_ppgtt = 1, \ .has_full_ppgtt = 1, \ .has_full_48bit_ppgtt = 1, \ diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 060b171480d550..85269bcc8372c6 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -205,25 +205,49 @@ #define OA_TAKEN(tail, head) ((tail - head) & (OA_BUFFER_SIZE - 1)) -/* There's a HW race condition between OA unit tail pointer register updates and +/** + * DOC: OA Tail Pointer Race + * + * There's a HW race condition between OA unit tail pointer register updates and * writes to memory whereby the tail pointer can sometimes get ahead of what's - * been written out to the OA buffer so far. + * been written out to the OA buffer so far (in terms of what's visible to the + * CPU). + * + * Although this can be observed explicitly while copying reports to userspace + * by checking for a zeroed report-id field in tail reports, we want to account + * for this earlier, as part of the _oa_buffer_check to avoid lots of redundant + * read() attempts. + * + * In effect we define a tail pointer for reading that lags the real tail + * pointer by at least %OA_TAIL_MARGIN_NSEC nanoseconds, which gives enough + * time for the corresponding reports to become visible to the CPU. + * + * To manage this we actually track two tail pointers: + * 1) An 'aging' tail with an associated timestamp that is tracked until we + * can trust the corresponding data is visible to the CPU; at which point + * it is considered 'aged'. + * 2) An 'aged' tail that can be used for read()ing. + * + * The two separate pointers let us decouple read()s from tail pointer aging. + * + * The tail pointers are checked and updated at a limited rate within a hrtimer + * callback (the same callback that is used for delivering POLLIN events) * - * Although this can be observed explicitly by checking for a zeroed report-id - * field in tail reports, it seems preferable to account for this earlier e.g. - * as part of the _oa_buffer_is_empty checks to minimize -EAGAIN polling cycles - * in this situation. + * Initially the tails are marked invalid with %INVALID_TAIL_PTR which + * indicates that an updated tail pointer is needed. * - * To give time for the most recent reports to land before they may be copied to - * userspace, the driver operates as if the tail pointer effectively lags behind - * the HW tail pointer by 'tail_margin' bytes. The margin in bytes is calculated - * based on this constant in nanoseconds, the current OA sampling exponent - * and current report size. + * Most of the implementation details for this workaround are in + * gen7_oa_buffer_check_unlocked() and gen7_appand_oa_reports() * - * There is also a fallback check while reading to simply skip over reports with - * a zeroed report-id. + * Note for posterity: previously the driver used to define an effective tail + * pointer that lagged the real pointer by a 'tail margin' measured in bytes + * derived from %OA_TAIL_MARGIN_NSEC and the configured sampling frequency. + * This was flawed considering that the OA unit may also automatically generate + * non-periodic reports (such as on context switch) or the OA unit may be + * enabled without any periodic sampling. */ #define OA_TAIL_MARGIN_NSEC 100000ULL +#define INVALID_TAIL_PTR 0xffffffff /* frequency for checking whether the OA unit has written new reports to the * circular OA buffer... @@ -308,27 +332,121 @@ struct perf_open_properties { int oa_period_exponent; }; -/* NB: This is either called via fops or the poll check hrtimer (atomic ctx) +/** + * gen7_oa_buffer_check_unlocked - check for data and update tail ptr state + * @dev_priv: i915 device instance + * + * This is either called via fops (for blocking reads in user ctx) or the poll + * check hrtimer (atomic ctx) to check the OA buffer tail pointer and check + * if there is data available for userspace to read. * - * It's safe to read OA config state here unlocked, assuming that this is only - * called while the stream is enabled, while the global OA configuration can't - * be modified. + * This function is central to providing a workaround for the OA unit tail + * pointer having a race with respect to what data is visible to the CPU. + * It is responsible for reading tail pointers from the hardware and giving + * the pointers time to 'age' before they are made available for reading. + * (See description of OA_TAIL_MARGIN_NSEC above for further details.) * - * Note: we don't lock around the head/tail reads even though there's the slim - * possibility of read() fop errors forcing a re-init of the OA buffer - * pointers. A race here could result in a false positive !empty status which - * is acceptable. + * Besides returning true when there is data available to read() this function + * also has the side effect of updating the oa_buffer.tails[], .aging_timestamp + * and .aged_tail_idx state used for reading. + * + * Note: It's safe to read OA config state here unlocked, assuming that this is + * only called while the stream is enabled, while the global OA configuration + * can't be modified. + * + * Returns: %true if the OA buffer contains data, else %false */ -static bool gen7_oa_buffer_is_empty_fop_unlocked(struct drm_i915_private *dev_priv) +static bool gen7_oa_buffer_check_unlocked(struct drm_i915_private *dev_priv) { int report_size = dev_priv->perf.oa.oa_buffer.format_size; - u32 oastatus2 = I915_READ(GEN7_OASTATUS2); - u32 oastatus1 = I915_READ(GEN7_OASTATUS1); - u32 head = oastatus2 & GEN7_OASTATUS2_HEAD_MASK; - u32 tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK; + unsigned long flags; + unsigned int aged_idx; + u32 oastatus1; + u32 head, hw_tail, aged_tail, aging_tail; + u64 now; + + /* We have to consider the (unlikely) possibility that read() errors + * could result in an OA buffer reset which might reset the head, + * tails[] and aged_tail state. + */ + spin_lock_irqsave(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); + + /* NB: The head we observe here might effectively be a little out of + * date (between head and tails[aged_idx].offset if there is currently + * a read() in progress. + */ + head = dev_priv->perf.oa.oa_buffer.head; + + aged_idx = dev_priv->perf.oa.oa_buffer.aged_tail_idx; + aged_tail = dev_priv->perf.oa.oa_buffer.tails[aged_idx].offset; + aging_tail = dev_priv->perf.oa.oa_buffer.tails[!aged_idx].offset; - return OA_TAKEN(tail, head) < - dev_priv->perf.oa.tail_margin + report_size; + oastatus1 = I915_READ(GEN7_OASTATUS1); + hw_tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK; + + /* The tail pointer increases in 64 byte increments, + * not in report_size steps... + */ + hw_tail &= ~(report_size - 1); + + now = ktime_get_mono_fast_ns(); + + /* Update the aged tail + * + * Flip the tail pointer available for read()s once the aging tail is + * old enough to trust that the corresponding data will be visible to + * the CPU... + * + * Do this before updating the aging pointer in case we may be able to + * immediately start aging a new pointer too (if new data has become + * available) without needing to wait for a later hrtimer callback. + */ + if (aging_tail != INVALID_TAIL_PTR && + ((now - dev_priv->perf.oa.oa_buffer.aging_timestamp) > + OA_TAIL_MARGIN_NSEC)) { + aged_idx ^= 1; + dev_priv->perf.oa.oa_buffer.aged_tail_idx = aged_idx; + + aged_tail = aging_tail; + + /* Mark that we need a new pointer to start aging... */ + dev_priv->perf.oa.oa_buffer.tails[!aged_idx].offset = INVALID_TAIL_PTR; + aging_tail = INVALID_TAIL_PTR; + } + + /* Update the aging tail + * + * We throttle aging tail updates until we have a new tail that + * represents >= one report more data than is already available for + * reading. This ensures there will be enough data for a successful + * read once this new pointer has aged and ensures we will give the new + * pointer time to age. + */ + if (aging_tail == INVALID_TAIL_PTR && + (aged_tail == INVALID_TAIL_PTR || + OA_TAKEN(hw_tail, aged_tail) >= report_size)) { + struct i915_vma *vma = dev_priv->perf.oa.oa_buffer.vma; + u32 gtt_offset = i915_ggtt_offset(vma); + + /* Be paranoid and do a bounds check on the pointer read back + * from hardware, just in case some spurious hardware condition + * could put the tail out of bounds... + */ + if (hw_tail >= gtt_offset && + hw_tail < (gtt_offset + OA_BUFFER_SIZE)) { + dev_priv->perf.oa.oa_buffer.tails[!aged_idx].offset = + aging_tail = hw_tail; + dev_priv->perf.oa.oa_buffer.aging_timestamp = now; + } else { + DRM_ERROR("Ignoring spurious out of range OA buffer tail pointer = %u\n", + hw_tail); + } + } + + spin_unlock_irqrestore(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); + + return aged_tail == INVALID_TAIL_PTR ? + false : OA_TAKEN(aged_tail, head) >= report_size; } /** @@ -421,8 +539,6 @@ static int append_oa_sample(struct i915_perf_stream *stream, * @buf: destination buffer given by userspace * @count: the number of bytes userspace wants to read * @offset: (inout): the current position for writing into @buf - * @head_ptr: (inout): the current oa buffer cpu read position - * @tail: the current oa buffer gpu write position * * Notably any error condition resulting in a short read (-%ENOSPC or * -%EFAULT) will be returned even though one or more records may @@ -431,7 +547,7 @@ static int append_oa_sample(struct i915_perf_stream *stream, * userspace. * * Note: reports are consumed from the head, and appended to the - * tail, so the head chases the tail?... If you think that's mad + * tail, so the tail chases the head?... If you think that's mad * and back-to-front you're not alone, but this follows the * Gen PRM naming convention. * @@ -440,57 +556,55 @@ static int append_oa_sample(struct i915_perf_stream *stream, static int gen7_append_oa_reports(struct i915_perf_stream *stream, char __user *buf, size_t count, - size_t *offset, - u32 *head_ptr, - u32 tail) + size_t *offset) { struct drm_i915_private *dev_priv = stream->dev_priv; int report_size = dev_priv->perf.oa.oa_buffer.format_size; u8 *oa_buf_base = dev_priv->perf.oa.oa_buffer.vaddr; - int tail_margin = dev_priv->perf.oa.tail_margin; u32 gtt_offset = i915_ggtt_offset(dev_priv->perf.oa.oa_buffer.vma); u32 mask = (OA_BUFFER_SIZE - 1); - u32 head; + size_t start_offset = *offset; + unsigned long flags; + unsigned int aged_tail_idx; + u32 head, tail; u32 taken; int ret = 0; if (WARN_ON(!stream->enabled)) return -EIO; - head = *head_ptr - gtt_offset; - tail -= gtt_offset; + spin_lock_irqsave(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); - /* The OA unit is expected to wrap the tail pointer according to the OA - * buffer size and since we should never write a misaligned head - * pointer we don't expect to read one back either... - */ - if (tail > OA_BUFFER_SIZE || head > OA_BUFFER_SIZE || - head % report_size) { - DRM_ERROR("Inconsistent OA buffer pointer (head = %u, tail = %u): force restart\n", - head, tail); - dev_priv->perf.oa.ops.oa_disable(dev_priv); - dev_priv->perf.oa.ops.oa_enable(dev_priv); - *head_ptr = I915_READ(GEN7_OASTATUS2) & - GEN7_OASTATUS2_HEAD_MASK; - return -EIO; - } + head = dev_priv->perf.oa.oa_buffer.head; + aged_tail_idx = dev_priv->perf.oa.oa_buffer.aged_tail_idx; + tail = dev_priv->perf.oa.oa_buffer.tails[aged_tail_idx].offset; + spin_unlock_irqrestore(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); - /* The tail pointer increases in 64 byte increments, not in report_size - * steps... + /* An invalid tail pointer here means we're still waiting for the poll + * hrtimer callback to give us a pointer */ - tail &= ~(report_size - 1); + if (tail == INVALID_TAIL_PTR) + return -EAGAIN; - /* Move the tail pointer back by the current tail_margin to account for - * the possibility that the latest reports may not have really landed - * in memory yet... + /* NB: oa_buffer.head/tail include the gtt_offset which we don't want + * while indexing relative to oa_buf_base. */ + head -= gtt_offset; + tail -= gtt_offset; - if (OA_TAKEN(tail, head) < report_size + tail_margin) - return -EAGAIN; + /* An out of bounds or misaligned head or tail pointer implies a driver + * bug since we validate + align the tail pointers we read from the + * hardware and we are in full control of the head pointer which should + * only be incremented by multiples of the report size (notably also + * all a power of two). + */ + if (WARN_ONCE(head > OA_BUFFER_SIZE || head % report_size || + tail > OA_BUFFER_SIZE || tail % report_size, + "Inconsistent OA buffer pointers: head = %u, tail = %u\n", + head, tail)) + return -EIO; - tail -= tail_margin; - tail &= mask; for (/* none */; (taken = OA_TAKEN(tail, head)); @@ -518,7 +632,8 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, * copying it to userspace... */ if (report32[0] == 0) { - DRM_NOTE("Skipping spurious, invalid OA report\n"); + if (__ratelimit(&dev_priv->perf.oa.spurious_report_rs)) + DRM_NOTE("Skipping spurious, invalid OA report\n"); continue; } @@ -535,7 +650,21 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, report32[0] = 0; } - *head_ptr = gtt_offset + head; + if (start_offset != *offset) { + spin_lock_irqsave(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); + + /* We removed the gtt_offset for the copy loop above, indexing + * relative to oa_buf_base so put back here... + */ + head += gtt_offset; + + I915_WRITE(GEN7_OASTATUS2, + ((head & GEN7_OASTATUS2_HEAD_MASK) | + OA_MEM_SELECT_GGTT)); + dev_priv->perf.oa.oa_buffer.head = head; + + spin_unlock_irqrestore(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); + } return ret; } @@ -562,22 +691,14 @@ static int gen7_oa_read(struct i915_perf_stream *stream, size_t *offset) { struct drm_i915_private *dev_priv = stream->dev_priv; - int report_size = dev_priv->perf.oa.oa_buffer.format_size; - u32 oastatus2; u32 oastatus1; - u32 head; - u32 tail; int ret; if (WARN_ON(!dev_priv->perf.oa.oa_buffer.vaddr)) return -EIO; - oastatus2 = I915_READ(GEN7_OASTATUS2); oastatus1 = I915_READ(GEN7_OASTATUS1); - head = oastatus2 & GEN7_OASTATUS2_HEAD_MASK; - tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK; - /* XXX: On Haswell we don't have a safe way to clear oastatus1 * bits while the OA unit is enabled (while the tail pointer * may be updated asynchronously) so we ignore status bits @@ -616,11 +737,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream, dev_priv->perf.oa.ops.oa_disable(dev_priv); dev_priv->perf.oa.ops.oa_enable(dev_priv); - oastatus2 = I915_READ(GEN7_OASTATUS2); oastatus1 = I915_READ(GEN7_OASTATUS1); - - head = oastatus2 & GEN7_OASTATUS2_HEAD_MASK; - tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK; } if (unlikely(oastatus1 & GEN7_OASTATUS1_REPORT_LOST)) { @@ -632,29 +749,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream, GEN7_OASTATUS1_REPORT_LOST; } - ret = gen7_append_oa_reports(stream, buf, count, offset, - &head, tail); - - /* All the report sizes are a power of two and the - * head should always be incremented by some multiple - * of the report size. - * - * A warning here, but notably if we later read back a - * misaligned pointer we will treat that as a bug since - * it could lead to a buffer overrun. - */ - WARN_ONCE(head & (report_size - 1), - "i915: Writing misaligned OA head pointer"); - - /* Note: we update the head pointer here even if an error - * was returned since the error may represent a short read - * where some some reports were successfully copied. - */ - I915_WRITE(GEN7_OASTATUS2, - ((head & GEN7_OASTATUS2_HEAD_MASK) | - OA_MEM_SELECT_GGTT)); - - return ret; + return gen7_append_oa_reports(stream, buf, count, offset); } /** @@ -679,14 +774,8 @@ static int i915_oa_wait_unlocked(struct i915_perf_stream *stream) if (!dev_priv->perf.oa.periodic) return -EIO; - /* Note: the oa_buffer_is_empty() condition is ok to run unlocked as it - * just performs mmio reads of the OA buffer head + tail pointers and - * it's assumed we're handling some operation that implies the stream - * can't be destroyed until completion (such as a read()) that ensures - * the device + OA buffer can't disappear - */ return wait_event_interruptible(dev_priv->perf.oa.poll_wq, - !dev_priv->perf.oa.ops.oa_buffer_is_empty(dev_priv)); + dev_priv->perf.oa.ops.oa_buffer_check(dev_priv)); } /** @@ -744,6 +833,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) { struct drm_i915_private *dev_priv = stream->dev_priv; struct intel_engine_cs *engine = dev_priv->engine[RCS]; + struct intel_ring *ring; int ret; ret = i915_mutex_lock_interruptible(&dev_priv->drm); @@ -755,9 +845,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * * NB: implied RCS engine... */ - ret = engine->context_pin(engine, stream->ctx); - if (ret) - goto unlock; + ring = engine->context_pin(engine, stream->ctx); + mutex_unlock(&dev_priv->drm.struct_mutex); + if (IS_ERR(ring)) + return PTR_ERR(ring); /* Explicitly track the ID (instead of calling i915_ggtt_offset() * on the fly) considering the difference with gen8+ and @@ -766,10 +857,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) dev_priv->perf.oa.specific_ctx_id = i915_ggtt_offset(stream->ctx->engine[engine->id].state); -unlock: - mutex_unlock(&dev_priv->drm.struct_mutex); - - return ret; + return 0; } /** @@ -824,19 +912,36 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) oa_put_render_ctx_id(stream); dev_priv->perf.oa.exclusive_stream = NULL; + + if (dev_priv->perf.oa.spurious_report_rs.missed) { + DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n", + dev_priv->perf.oa.spurious_report_rs.missed); + } } static void gen7_init_oa_buffer(struct drm_i915_private *dev_priv) { u32 gtt_offset = i915_ggtt_offset(dev_priv->perf.oa.oa_buffer.vma); + unsigned long flags; + + spin_lock_irqsave(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); /* Pre-DevBDW: OABUFFER must be set with counters off, * before OASTATUS1, but after OASTATUS2 */ I915_WRITE(GEN7_OASTATUS2, gtt_offset | OA_MEM_SELECT_GGTT); /* head */ + dev_priv->perf.oa.oa_buffer.head = gtt_offset; + I915_WRITE(GEN7_OABUFFER, gtt_offset); + I915_WRITE(GEN7_OASTATUS1, gtt_offset | OABUFFER_SIZE_16M); /* tail */ + /* Mark that we need updated tail pointers to read from... */ + dev_priv->perf.oa.oa_buffer.tails[0].offset = INVALID_TAIL_PTR; + dev_priv->perf.oa.oa_buffer.tails[1].offset = INVALID_TAIL_PTR; + + spin_unlock_irqrestore(&dev_priv->perf.oa.oa_buffer.ptr_lock, flags); + /* On Haswell we have to track which OASTATUS1 flags we've * already seen since they can't be cleared while periodic * sampling is enabled. @@ -1094,12 +1199,6 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream) hrtimer_cancel(&dev_priv->perf.oa.poll_check_timer); } -static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent) -{ - return div_u64(1000000000ULL * (2ULL << exponent), - dev_priv->perf.oa.timestamp_frequency); -} - static const struct i915_perf_stream_ops i915_oa_stream_ops = { .destroy = i915_oa_stream_destroy, .enable = i915_oa_stream_enable, @@ -1173,6 +1272,26 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return -EINVAL; } + /* We set up some ratelimit state to potentially throttle any _NOTES + * about spurious, invalid OA reports which we don't forward to + * userspace. + * + * The initialization is associated with opening the stream (not driver + * init) considering we print a _NOTE about any throttling when closing + * the stream instead of waiting until driver _fini which no one would + * ever see. + * + * Using the same limiting factors as printk_ratelimit() + */ + ratelimit_state_init(&dev_priv->perf.oa.spurious_report_rs, + 5 * HZ, 10); + /* Since we use a DRM_NOTE for spurious reports it would be + * inconsistent to let __ratelimit() automatically print a warning for + * throttling. + */ + ratelimit_set_flags(&dev_priv->perf.oa.spurious_report_rs, + RATELIMIT_MSG_ON_RELEASE); + stream->sample_size = sizeof(struct drm_i915_perf_record_header); format_size = dev_priv->perf.oa.oa_formats[props->oa_format].size; @@ -1190,20 +1309,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, dev_priv->perf.oa.metrics_set = props->metrics_set; dev_priv->perf.oa.periodic = props->oa_periodic; - if (dev_priv->perf.oa.periodic) { - u32 tail; - + if (dev_priv->perf.oa.periodic) dev_priv->perf.oa.period_exponent = props->oa_period_exponent; - /* See comment for OA_TAIL_MARGIN_NSEC for details - * about this tail_margin... - */ - tail = div64_u64(OA_TAIL_MARGIN_NSEC, - oa_exponent_to_ns(dev_priv, - props->oa_period_exponent)); - dev_priv->perf.oa.tail_margin = (tail + 1) * format_size; - } - if (stream->ctx) { ret = oa_get_render_ctx_id(stream); if (ret) @@ -1352,7 +1460,15 @@ static ssize_t i915_perf_read(struct file *file, mutex_unlock(&dev_priv->perf.lock); } - if (ret >= 0) { + /* We allow the poll checking to sometimes report false positive POLLIN + * events where we might actually report EAGAIN on read() if there's + * not really any data available. In this situation though we don't + * want to enter a busy loop between poll() reporting a POLLIN event + * and read() returning -EAGAIN. Clearing the oa.pollin state here + * effectively ensures we back off until the next hrtimer callback + * before reporting another POLLIN event. + */ + if (ret >= 0 || ret == -EAGAIN) { /* Maybe make ->pollin per-stream state if we support multiple * concurrent streams in the future. */ @@ -1368,7 +1484,7 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) container_of(hrtimer, typeof(*dev_priv), perf.oa.poll_check_timer); - if (!dev_priv->perf.oa.ops.oa_buffer_is_empty(dev_priv)) { + if (dev_priv->perf.oa.ops.oa_buffer_check(dev_priv)) { dev_priv->perf.oa.pollin = true; wake_up(&dev_priv->perf.oa.poll_wq); } @@ -1817,11 +1933,13 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv, break; case DRM_I915_PERF_PROP_OA_FORMAT: if (value == 0 || value >= I915_OA_FORMAT_MAX) { - DRM_DEBUG("Invalid OA report format\n"); + DRM_DEBUG("Out-of-range OA report format %llu\n", + value); return -EINVAL; } if (!dev_priv->perf.oa.oa_formats[value].size) { - DRM_DEBUG("Invalid OA report format\n"); + DRM_DEBUG("Unsupported OA report format %llu\n", + value); return -EINVAL; } props->oa_format = value; @@ -2063,6 +2181,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv) INIT_LIST_HEAD(&dev_priv->perf.streams); mutex_init(&dev_priv->perf.lock); spin_lock_init(&dev_priv->perf.hook_lock); + spin_lock_init(&dev_priv->perf.oa.oa_buffer.ptr_lock); dev_priv->perf.oa.ops.init_oa_buffer = gen7_init_oa_buffer; dev_priv->perf.oa.ops.enable_metric_set = hsw_enable_metric_set; @@ -2070,10 +2189,8 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.oa_enable = gen7_oa_enable; dev_priv->perf.oa.ops.oa_disable = gen7_oa_disable; dev_priv->perf.oa.ops.read = gen7_oa_read; - dev_priv->perf.oa.ops.oa_buffer_is_empty = - gen7_oa_buffer_is_empty_fop_unlocked; - - dev_priv->perf.oa.timestamp_frequency = 12500000; + dev_priv->perf.oa.ops.oa_buffer_check = + gen7_oa_buffer_check_unlocked; dev_priv->perf.oa.oa_formats = hsw_oa_formats; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 65b837e96fe629..231ee86625cdc8 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -85,6 +85,14 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define VECS_HW 3 #define VCS2_HW 4 +/* Engine class */ + +#define RENDER_CLASS 0 +#define VIDEO_DECODE_CLASS 1 +#define VIDEO_ENHANCEMENT_CLASS 2 +#define COPY_ENGINE_CLASS 3 +#define OTHER_CLASS 4 + /* PCI config space */ #define MCHBAR_I915 0x44 @@ -3366,16 +3374,6 @@ enum skl_disp_power_wells { #define GEN7_CXT_VFSTATE_SIZE(ctx_reg) (((ctx_reg) >> 0) & 0x3f) #define GEN7_CXT_TOTAL_SIZE(ctx_reg) (GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \ GEN7_CXT_VFSTATE_SIZE(ctx_reg)) -/* Haswell does have the CXT_SIZE register however it does not appear to be - * valid. Now, docs explain in dwords what is in the context object. The full - * size is 70720 bytes, however, the power context and execlist context will - * never be saved (power context is stored elsewhere, and execlists don't work - * on HSW) - so the final size, including the extra state required for the - * Resource Streamer, is 66944 bytes, which rounds to 17 pages. - */ -#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) -/* Same as Haswell, but 72064 bytes now. */ -#define GEN8_CXT_TOTAL_SIZE (18 * PAGE_SIZE) enum { INTEL_ADVANCED_CONTEXT = 0, @@ -5441,9 +5439,7 @@ enum { #define CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX) #define CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX) #define CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX) -#define MCURSOR_PIPE_SELECT (1 << 28) -#define MCURSOR_PIPE_A 0x00 -#define MCURSOR_PIPE_B (1 << 28) +#define MCURSOR_PIPE_SELECT(pipe) ((pipe) << 28) #define MCURSOR_GAMMA_ENABLE (1 << 26) #define CURSOR_ROTATE_180 (1<<15) #define CURSOR_TRICKLE_FEED_DISABLE (1 << 14) @@ -5453,7 +5449,9 @@ enum { #define CURSOR_POS_SIGN 0x8000 #define CURSOR_X_SHIFT 0 #define CURSOR_Y_SHIFT 16 -#define CURSIZE _MMIO(0x700a0) +#define CURSIZE _MMIO(0x700a0) /* 845/865 */ +#define _CUR_FBC_CTL_A 0x700a0 /* ivb+ */ +#define CUR_FBC_CTL_EN (1 << 31) #define _CURBCNTR 0x700c0 #define _CURBBASE 0x700c4 #define _CURBPOS 0x700c8 @@ -5469,6 +5467,7 @@ enum { #define CURCNTR(pipe) _CURSOR2(pipe, _CURACNTR) #define CURBASE(pipe) _CURSOR2(pipe, _CURABASE) #define CURPOS(pipe) _CURSOR2(pipe, _CURAPOS) +#define CUR_FBC_CTL(pipe) _CURSOR2(pipe, _CUR_FBC_CTL_A) #define CURSOR_A_OFFSET 0x70080 #define CURSOR_B_OFFSET 0x700c0 @@ -5501,8 +5500,7 @@ enum { #define DISPPLANE_PIPE_CSC_ENABLE (1<<24) #define DISPPLANE_SEL_PIPE_SHIFT 24 #define DISPPLANE_SEL_PIPE_MASK (3< #include "i915_sw_fence.h" +#include "i915_selftest.h" #define I915_SW_FENCE_FLAG_ALLOC BIT(3) /* after WQ_FLAG_* for safety */ @@ -120,34 +121,6 @@ void i915_sw_fence_fini(struct i915_sw_fence *fence) } #endif -static void i915_sw_fence_release(struct kref *kref) -{ - struct i915_sw_fence *fence = container_of(kref, typeof(*fence), kref); - - WARN_ON(atomic_read(&fence->pending) > 0); - debug_fence_destroy(fence); - - if (fence->flags & I915_SW_FENCE_MASK) { - __i915_sw_fence_notify(fence, FENCE_FREE); - } else { - i915_sw_fence_fini(fence); - kfree(fence); - } -} - -static void i915_sw_fence_put(struct i915_sw_fence *fence) -{ - debug_fence_assert(fence); - kref_put(&fence->kref, i915_sw_fence_release); -} - -static struct i915_sw_fence *i915_sw_fence_get(struct i915_sw_fence *fence) -{ - debug_fence_assert(fence); - kref_get(&fence->kref); - return fence; -} - static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, struct list_head *continuation) { @@ -202,13 +175,15 @@ static void __i915_sw_fence_complete(struct i915_sw_fence *fence, debug_fence_set_state(fence, DEBUG_FENCE_IDLE, DEBUG_FENCE_NOTIFY); - if (fence->flags & I915_SW_FENCE_MASK && - __i915_sw_fence_notify(fence, FENCE_COMPLETE) != NOTIFY_DONE) + if (__i915_sw_fence_notify(fence, FENCE_COMPLETE) != NOTIFY_DONE) return; debug_fence_set_state(fence, DEBUG_FENCE_NOTIFY, DEBUG_FENCE_IDLE); __i915_sw_fence_wake_up_all(fence, continuation); + + debug_fence_destroy(fence); + __i915_sw_fence_notify(fence, FENCE_FREE); } static void i915_sw_fence_complete(struct i915_sw_fence *fence) @@ -232,33 +207,26 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence, const char *name, struct lock_class_key *key) { - BUG_ON((unsigned long)fn & ~I915_SW_FENCE_MASK); + BUG_ON(!fn || (unsigned long)fn & ~I915_SW_FENCE_MASK); debug_fence_init(fence); __init_waitqueue_head(&fence->wait, name, key); - kref_init(&fence->kref); atomic_set(&fence->pending, 1); fence->flags = (unsigned long)fn; } -static void __i915_sw_fence_commit(struct i915_sw_fence *fence) -{ - i915_sw_fence_complete(fence); - i915_sw_fence_put(fence); -} - void i915_sw_fence_commit(struct i915_sw_fence *fence) { debug_fence_activate(fence); - __i915_sw_fence_commit(fence); + i915_sw_fence_complete(fence); } static int i915_sw_fence_wake(wait_queue_t *wq, unsigned mode, int flags, void *key) { list_del(&wq->task_list); __i915_sw_fence_complete(wq->private, key); - i915_sw_fence_put(wq->private); + if (wq->flags & I915_SW_FENCE_FLAG_ALLOC) kfree(wq); return 0; @@ -307,7 +275,7 @@ static bool i915_sw_fence_check_if_after(struct i915_sw_fence *fence, unsigned long flags; bool err; - if (!IS_ENABLED(CONFIG_I915_SW_FENCE_CHECK_DAG)) + if (!IS_ENABLED(CONFIG_DRM_I915_SW_FENCE_CHECK_DAG)) return false; spin_lock_irqsave(&i915_sw_fence_lock, flags); @@ -353,7 +321,7 @@ static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, INIT_LIST_HEAD(&wq->task_list); wq->flags = pending; wq->func = i915_sw_fence_wake; - wq->private = i915_sw_fence_get(fence); + wq->private = fence; i915_sw_fence_await(fence); @@ -402,7 +370,7 @@ static void timer_i915_sw_fence_wake(unsigned long data) dma_fence_put(cb->dma); cb->dma = NULL; - __i915_sw_fence_commit(cb->fence); + i915_sw_fence_complete(cb->fence); cb->timer.function = NULL; } @@ -413,7 +381,7 @@ static void dma_i915_sw_fence_wake(struct dma_fence *dma, del_timer_sync(&cb->timer); if (cb->timer.function) - __i915_sw_fence_commit(cb->fence); + i915_sw_fence_complete(cb->fence); dma_fence_put(cb->dma); kfree(cb); @@ -440,7 +408,7 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence, return dma_fence_wait(dma, false); } - cb->fence = i915_sw_fence_get(fence); + cb->fence = fence; i915_sw_fence_await(fence); cb->dma = NULL; @@ -523,3 +491,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, return ret; } + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/i915_sw_fence.c" +#endif diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index d31cefbbcc0433..1d3b6051daaf5a 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -23,7 +23,6 @@ struct reservation_object; struct i915_sw_fence { wait_queue_head_t wait; unsigned long flags; - struct kref kref; atomic_t pending; }; diff --git a/drivers/gpu/drm/i915/i915_syncmap.c b/drivers/gpu/drm/i915/i915_syncmap.c new file mode 100644 index 00000000000000..0087acf731a851 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_syncmap.c @@ -0,0 +1,412 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include + +#include "i915_syncmap.h" + +#include "i915_gem.h" /* GEM_BUG_ON() */ +#include "i915_selftest.h" + +#define SHIFT ilog2(KSYNCMAP) +#define MASK (KSYNCMAP - 1) + +/* + * struct i915_syncmap is a layer of a radixtree that maps a u64 fence + * context id to the last u32 fence seqno waited upon from that context. + * Unlike lib/radixtree it uses a parent pointer that allows traversal back to + * the root. This allows us to access the whole tree via a single pointer + * to the most recently used layer. We expect fence contexts to be dense + * and most reuse to be on the same i915_gem_context but on neighbouring + * engines (i.e. on adjacent contexts) and reuse the same leaf, a very + * effective lookup cache. If the new lookup is not on the same leaf, we + * expect it to be on the neighbouring branch. + * + * A leaf holds an array of u32 seqno, and has height 0. The bitmap field + * allows us to store whether a particular seqno is valid (i.e. allows us + * to distinguish unset from 0). + * + * A branch holds an array of layer pointers, and has height > 0, and always + * has at least 2 layers (either branches or leaves) below it. + * + * For example, + * for x in + * 0 1 2 0x10 0x11 0x200 0x201 + * 0x500000 0x500001 0x503000 0x503001 + * 0xE<<60: + * i915_syncmap_set(&sync, x, lower_32_bits(x)); + * will build a tree like: + * 0xXXXXXXXXXXXXXXXX + * 0-> 0x0000000000XXXXXX + * | 0-> 0x0000000000000XXX + * | | 0-> 0x00000000000000XX + * | | | 0-> 0x000000000000000X 0:0, 1:1, 2:2 + * | | | 1-> 0x000000000000001X 0:10, 1:11 + * | | 2-> 0x000000000000020X 0:200, 1:201 + * | 5-> 0x000000000050XXXX + * | 0-> 0x000000000050000X 0:500000, 1:500001 + * | 3-> 0x000000000050300X 0:503000, 1:503001 + * e-> 0xe00000000000000X e:e + */ + +struct i915_syncmap { + u64 prefix; + unsigned int height; + unsigned int bitmap; + struct i915_syncmap *parent; + /* + * Following this header is an array of either seqno or child pointers: + * union { + * u32 seqno[KSYNCMAP]; + * struct i915_syncmap *child[KSYNCMAP]; + * }; + */ +}; + +/** + * i915_syncmap_init -- initialise the #i915_syncmap + * @root - pointer to the #i915_syncmap + */ +void i915_syncmap_init(struct i915_syncmap **root) +{ + BUILD_BUG_ON_NOT_POWER_OF_2(KSYNCMAP); + BUILD_BUG_ON_NOT_POWER_OF_2(SHIFT); + BUILD_BUG_ON(KSYNCMAP > BITS_PER_BYTE * sizeof((*root)->bitmap)); + *root = NULL; +} + +static inline u32 *__sync_seqno(struct i915_syncmap *p) +{ + GEM_BUG_ON(p->height); + return (u32 *)(p + 1); +} + +static inline struct i915_syncmap **__sync_child(struct i915_syncmap *p) +{ + GEM_BUG_ON(!p->height); + return (struct i915_syncmap **)(p + 1); +} + +static inline unsigned int +__sync_branch_idx(const struct i915_syncmap *p, u64 id) +{ + return (id >> p->height) & MASK; +} + +static inline unsigned int +__sync_leaf_idx(const struct i915_syncmap *p, u64 id) +{ + GEM_BUG_ON(p->height); + return id & MASK; +} + +static inline u64 __sync_branch_prefix(const struct i915_syncmap *p, u64 id) +{ + return id >> p->height >> SHIFT; +} + +static inline u64 __sync_leaf_prefix(const struct i915_syncmap *p, u64 id) +{ + GEM_BUG_ON(p->height); + return id >> SHIFT; +} + +static inline bool seqno_later(u32 a, u32 b) +{ + return (s32)(a - b) >= 0; +} + +/** + * i915_syncmap_is_later -- compare against the last know sync point + * @root - pointer to the #i915_syncmap + * @id - the context id (other timeline) we are synchronising to + * @seqno - the sequence number along the other timeline + * + * If we have already synchronised this @root timeline with another (@id) then + * we can omit any repeated or earlier synchronisation requests. If the two + * timelines are already coupled, we can also omit the dependency between the + * two as that is already known via the timeline. + * + * Returns true if the two timelines are already synchronised wrt to @seqno, + * false if not and the synchronisation must be emitted. + */ +bool i915_syncmap_is_later(struct i915_syncmap **root, u64 id, u32 seqno) +{ + struct i915_syncmap *p; + unsigned int idx; + + p = *root; + if (!p) + return false; + + if (likely(__sync_leaf_prefix(p, id) == p->prefix)) + goto found; + + /* First climb the tree back to a parent branch */ + do { + p = p->parent; + if (!p) + return false; + + if (__sync_branch_prefix(p, id) == p->prefix) + break; + } while (1); + + /* And then descend again until we find our leaf */ + do { + if (!p->height) + break; + + p = __sync_child(p)[__sync_branch_idx(p, id)]; + if (!p) + return false; + + if (__sync_branch_prefix(p, id) != p->prefix) + return false; + } while (1); + + *root = p; +found: + idx = __sync_leaf_idx(p, id); + if (!(p->bitmap & BIT(idx))) + return false; + + return seqno_later(__sync_seqno(p)[idx], seqno); +} + +static struct i915_syncmap * +__sync_alloc_leaf(struct i915_syncmap *parent, u64 id) +{ + struct i915_syncmap *p; + + p = kmalloc(sizeof(*p) + KSYNCMAP * sizeof(u32), GFP_KERNEL); + if (unlikely(!p)) + return NULL; + + p->parent = parent; + p->height = 0; + p->bitmap = 0; + p->prefix = __sync_leaf_prefix(p, id); + return p; +} + +static inline void __sync_set_seqno(struct i915_syncmap *p, u64 id, u32 seqno) +{ + unsigned int idx = __sync_leaf_idx(p, id); + + p->bitmap |= BIT(idx); + __sync_seqno(p)[idx] = seqno; +} + +static inline void __sync_set_child(struct i915_syncmap *p, + unsigned int idx, + struct i915_syncmap *child) +{ + p->bitmap |= BIT(idx); + __sync_child(p)[idx] = child; +} + +static noinline int __sync_set(struct i915_syncmap **root, u64 id, u32 seqno) +{ + struct i915_syncmap *p = *root; + unsigned int idx; + + if (!p) { + p = __sync_alloc_leaf(NULL, id); + if (unlikely(!p)) + return -ENOMEM; + + goto found; + } + + /* Caller handled the likely cached case */ + GEM_BUG_ON(__sync_leaf_prefix(p, id) == p->prefix); + + /* Climb back up the tree until we find a common prefix */ + do { + if (!p->parent) + break; + + p = p->parent; + + if (__sync_branch_prefix(p, id) == p->prefix) + break; + } while (1); + + /* + * No shortcut, we have to descend the tree to find the right layer + * containing this fence. + * + * Each layer in the tree holds 16 (KSYNCMAP) pointers, either fences + * or lower layers. Leaf nodes (height = 0) contain the fences, all + * other nodes (height > 0) are internal layers that point to a lower + * node. Each internal layer has at least 2 descendents. + * + * Starting at the top, we check whether the current prefix matches. If + * it doesn't, we have gone past our target and need to insert a join + * into the tree, and a new leaf node for the target as a descendent + * of the join, as well as the original layer. + * + * The matching prefix means we are still following the right branch + * of the tree. If it has height 0, we have found our leaf and just + * need to replace the fence slot with ourselves. If the height is + * not zero, our slot contains the next layer in the tree (unless + * it is empty, in which case we can add ourselves as a new leaf). + * As descend the tree the prefix grows (and height decreases). + */ + do { + struct i915_syncmap *next; + + if (__sync_branch_prefix(p, id) != p->prefix) { + unsigned int above; + + /* Insert a join above the current layer */ + next = kzalloc(sizeof(*next) + KSYNCMAP * sizeof(next), + GFP_KERNEL); + if (unlikely(!next)) + return -ENOMEM; + + /* Compute the height at which these two diverge */ + above = fls64(__sync_branch_prefix(p, id) ^ p->prefix); + above = round_up(above, SHIFT); + next->height = above + p->height; + next->prefix = __sync_branch_prefix(next, id); + + /* Insert the join into the parent */ + if (p->parent) { + idx = __sync_branch_idx(p->parent, id); + __sync_child(p->parent)[idx] = next; + GEM_BUG_ON(!(p->parent->bitmap & BIT(idx))); + } + next->parent = p->parent; + + /* Compute the idx of the other branch, not our id! */ + idx = p->prefix >> (above - SHIFT) & MASK; + __sync_set_child(next, idx, p); + p->parent = next; + + /* Ascend to the join */ + p = next; + } else { + if (!p->height) + break; + } + + /* Descend into the next layer */ + GEM_BUG_ON(!p->height); + idx = __sync_branch_idx(p, id); + next = __sync_child(p)[idx]; + if (!next) { + next = __sync_alloc_leaf(p, id); + if (unlikely(!next)) + return -ENOMEM; + + __sync_set_child(p, idx, next); + p = next; + break; + } + + p = next; + } while (1); + +found: + GEM_BUG_ON(p->prefix != __sync_leaf_prefix(p, id)); + __sync_set_seqno(p, id, seqno); + *root = p; + return 0; +} + +/** + * i915_syncmap_set -- mark the most recent syncpoint between contexts + * @root - pointer to the #i915_syncmap + * @id - the context id (other timeline) we have synchronised to + * @seqno - the sequence number along the other timeline + * + * When we synchronise this @root timeline with another (@id), we also know + * that we have synchronized with all previous seqno along that timeline. If + * we then have a request to synchronise with the same seqno or older, we can + * omit it, see i915_syncmap_is_later() + * + * Returns 0 on success, or a negative error code. + */ +int i915_syncmap_set(struct i915_syncmap **root, u64 id, u32 seqno) +{ + struct i915_syncmap *p = *root; + + /* + * We expect to be called in sequence following is_later(id), which + * should have preloaded the root for us. + */ + if (likely(p && __sync_leaf_prefix(p, id) == p->prefix)) { + __sync_set_seqno(p, id, seqno); + return 0; + } + + return __sync_set(root, id, seqno); +} + +static void __sync_free(struct i915_syncmap *p) +{ + if (p->height) { + unsigned int i; + + while ((i = ffs(p->bitmap))) { + p->bitmap &= ~0u << i; + __sync_free(__sync_child(p)[i - 1]); + } + } + + kfree(p); +} + +/** + * i915_syncmap_free -- free all memory associated with the syncmap + * @root - pointer to the #i915_syncmap + * + * Either when the timeline is to be freed and we no longer need the sync + * point tracking, or when the fences are all known to be signaled and the + * sync point tracking is redundant, we can free the #i915_syncmap to recover + * its allocations. + * + * Will reinitialise the @root pointer so that the #i915_syncmap is ready for + * reuse. + */ +void i915_syncmap_free(struct i915_syncmap **root) +{ + struct i915_syncmap *p; + + p = *root; + if (!p) + return; + + while (p->parent) + p = p->parent; + + __sync_free(p); + *root = NULL; +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/i915_syncmap.c" +#endif diff --git a/drivers/gpu/drm/i915/i915_syncmap.h b/drivers/gpu/drm/i915/i915_syncmap.h new file mode 100644 index 00000000000000..0653f70bee8284 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_syncmap.h @@ -0,0 +1,38 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#ifndef __I915_SYNCMAP_H__ +#define __I915_SYNCMAP_H__ + +#include + +struct i915_syncmap; +#define KSYNCMAP 16 /* radix of the tree, how many slots in each layer */ + +void i915_syncmap_init(struct i915_syncmap **root); +int i915_syncmap_set(struct i915_syncmap **root, u64 id, u32 seqno); +bool i915_syncmap_is_later(struct i915_syncmap **root, u64 id, u32 seqno); +void i915_syncmap_free(struct i915_syncmap **root); + +#endif /* __I915_SYNCMAP_H__ */ diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index f3fdfda5e5588d..1eef3fae4db313 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -181,13 +181,10 @@ i915_l3_write(struct file *filp, struct kobject *kobj, struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); struct drm_device *dev = &dev_priv->drm; struct i915_gem_context *ctx; - u32 *temp = NULL; /* Just here to make handling failures easy */ int slice = (int)(uintptr_t)attr->private; + u32 **remap_info; int ret; - if (!HAS_HW_CONTEXTS(dev_priv)) - return -ENXIO; - ret = l3_access_valid(dev_priv, offset); if (ret) return ret; @@ -196,11 +193,12 @@ i915_l3_write(struct file *filp, struct kobject *kobj, if (ret) return ret; - if (!dev_priv->l3_parity.remap_info[slice]) { - temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL); - if (!temp) { - mutex_unlock(&dev->struct_mutex); - return -ENOMEM; + remap_info = &dev_priv->l3_parity.remap_info[slice]; + if (!*remap_info) { + *remap_info = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL); + if (!*remap_info) { + ret = -ENOMEM; + goto out; } } @@ -208,18 +206,18 @@ i915_l3_write(struct file *filp, struct kobject *kobj, * aren't propagated. Since I cannot find a stable way to reset the GPU * at this point it is left as a TODO. */ - if (temp) - dev_priv->l3_parity.remap_info[slice] = temp; - - memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count); + memcpy(*remap_info + (offset/4), buf, count); /* NB: We defer the remapping until we switch to the context */ list_for_each_entry(ctx, &dev_priv->context_list, link) ctx->remap_slice |= (1<struct_mutex); - return count; + return ret; } static struct bin_attribute dpf_attrs = { diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 66404c5aee82e5..b24a83d435592b 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -89,6 +89,55 @@ TRACE_EVENT(intel_memory_cxsr, __entry->frame[PIPE_C], __entry->scanline[PIPE_C]) ); +TRACE_EVENT(g4x_wm, + TP_PROTO(struct intel_crtc *crtc, const struct g4x_wm_values *wm), + TP_ARGS(crtc, wm), + + TP_STRUCT__entry( + __field(enum pipe, pipe) + __field(u32, frame) + __field(u32, scanline) + __field(u16, primary) + __field(u16, sprite) + __field(u16, cursor) + __field(u16, sr_plane) + __field(u16, sr_cursor) + __field(u16, sr_fbc) + __field(u16, hpll_plane) + __field(u16, hpll_cursor) + __field(u16, hpll_fbc) + __field(bool, cxsr) + __field(bool, hpll) + __field(bool, fbc) + ), + + TP_fast_assign( + __entry->pipe = crtc->pipe; + __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, + crtc->pipe); + __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; + __entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; + __entry->cursor = wm->pipe[crtc->pipe].plane[PLANE_CURSOR]; + __entry->sr_plane = wm->sr.plane; + __entry->sr_cursor = wm->sr.cursor; + __entry->sr_fbc = wm->sr.fbc; + __entry->hpll_plane = wm->hpll.plane; + __entry->hpll_cursor = wm->hpll.cursor; + __entry->hpll_fbc = wm->hpll.fbc; + __entry->cxsr = wm->cxsr; + __entry->hpll = wm->hpll_en; + __entry->fbc = wm->fbc_en; + ), + + TP_printk("pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s", + pipe_name(__entry->pipe), __entry->frame, __entry->scanline, + __entry->primary, __entry->sprite, __entry->cursor, + yesno(__entry->cxsr), __entry->sr_plane, __entry->sr_cursor, __entry->sr_fbc, + yesno(__entry->hpll), __entry->hpll_plane, __entry->hpll_cursor, __entry->hpll_fbc, + yesno(__entry->fbc)) +); + TRACE_EVENT(vlv_wm, TP_PROTO(struct intel_crtc *crtc, const struct vlv_wm_values *wm), TP_ARGS(crtc, wm), diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index c5455d36b6172b..16ecd1ab108d48 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -70,20 +70,27 @@ #define overflows_type(x, T) \ (sizeof(x) > sizeof(T) && (x) >> (sizeof(T) * BITS_PER_BYTE)) -#define ptr_mask_bits(ptr) ({ \ +#define ptr_mask_bits(ptr, n) ({ \ unsigned long __v = (unsigned long)(ptr); \ - (typeof(ptr))(__v & PAGE_MASK); \ + (typeof(ptr))(__v & -BIT(n)); \ }) -#define ptr_unpack_bits(ptr, bits) ({ \ +#define ptr_unmask_bits(ptr, n) ((unsigned long)(ptr) & (BIT(n) - 1)) + +#define ptr_unpack_bits(ptr, bits, n) ({ \ unsigned long __v = (unsigned long)(ptr); \ - (bits) = __v & ~PAGE_MASK; \ - (typeof(ptr))(__v & PAGE_MASK); \ + *(bits) = __v & (BIT(n) - 1); \ + (typeof(ptr))(__v & -BIT(n)); \ }) -#define ptr_pack_bits(ptr, bits) \ +#define ptr_pack_bits(ptr, bits, n) \ ((typeof(ptr))((unsigned long)(ptr) | (bits))) +#define page_mask_bits(ptr) ptr_mask_bits(ptr, PAGE_SHIFT) +#define page_unmask_bits(ptr) ptr_unmask_bits(ptr, PAGE_SHIFT) +#define page_pack_bits(ptr, bits) ptr_pack_bits(ptr, bits, PAGE_SHIFT) +#define page_unpack_bits(ptr, bits) ptr_unpack_bits(ptr, bits, PAGE_SHIFT) + #define ptr_offset(ptr, member) offsetof(typeof(*(ptr)), member) #define fetch_and_zero(ptr) ({ \ @@ -92,4 +99,19 @@ __T; \ }) +#define __mask_next_bit(mask) ({ \ + int __idx = ffs(mask) - 1; \ + mask &= ~BIT(__idx); \ + __idx; \ +}) + +#include + +static inline void __list_del_many(struct list_head *head, + struct list_head *first) +{ + first->prev = head; + WRITE_ONCE(head->next, first); +} + #endif /* !__I915_UTILS_H */ diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index 50fb1f76cc5fe8..d791b3ef89b55b 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -36,44 +36,121 @@ #include "intel_drv.h" /** - * intel_connector_atomic_get_property - fetch connector property value - * @connector: connector to fetch property for - * @state: state containing the property value - * @property: property to look up - * @val: pointer to write property value into + * intel_digital_connector_atomic_get_property - hook for connector->atomic_get_property. + * @connector: Connector to get the property for. + * @state: Connector state to retrieve the property from. + * @property: Property to retrieve. + * @val: Return value for the property. * - * The DRM core does not store shadow copies of properties for - * atomic-capable drivers. This entrypoint is used to fetch - * the current value of a driver-specific connector property. + * Returns the atomic property value for a digital connector. */ -int -intel_connector_atomic_get_property(struct drm_connector *connector, - const struct drm_connector_state *state, - struct drm_property *property, - uint64_t *val) +int intel_digital_connector_atomic_get_property(struct drm_connector *connector, + const struct drm_connector_state *state, + struct drm_property *property, + uint64_t *val) { - int i; + struct drm_device *dev = connector->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(state); + + if (property == dev_priv->force_audio_property) + *val = intel_conn_state->force_audio; + else if (property == dev_priv->broadcast_rgb_property) + *val = intel_conn_state->broadcast_rgb; + else { + DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name); + return -EINVAL; + } - /* - * TODO: We only have atomic modeset for planes at the moment, so the - * crtc/connector code isn't quite ready yet. Until it's ready, - * continue to look up all property values in the DRM's shadow copy - * in obj->properties->values[]. - * - * When the crtc/connector state work matures, this function should - * be updated to read the values out of the state structure instead. - */ - for (i = 0; i < connector->base.properties->count; i++) { - if (connector->base.properties->properties[i] == property) { - *val = connector->base.properties->values[i]; - return 0; - } + return 0; +} + +/** + * intel_digital_connector_atomic_set_property - hook for connector->atomic_set_property. + * @connector: Connector to set the property for. + * @state: Connector state to set the property on. + * @property: Property to set. + * @val: New value for the property. + * + * Sets the atomic property value for a digital connector. + */ +int intel_digital_connector_atomic_set_property(struct drm_connector *connector, + struct drm_connector_state *state, + struct drm_property *property, + uint64_t val) +{ + struct drm_device *dev = connector->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(state); + + if (property == dev_priv->force_audio_property) { + intel_conn_state->force_audio = val; + return 0; } + if (property == dev_priv->broadcast_rgb_property) { + intel_conn_state->broadcast_rgb = val; + return 0; + } + + DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name); return -EINVAL; } -/* +int intel_digital_connector_atomic_check(struct drm_connector *conn, + struct drm_connector_state *new_state) +{ + struct intel_digital_connector_state *new_conn_state = + to_intel_digital_connector_state(new_state); + struct drm_connector_state *old_state = + drm_atomic_get_old_connector_state(new_state->state, conn); + struct intel_digital_connector_state *old_conn_state = + to_intel_digital_connector_state(old_state); + struct drm_crtc_state *crtc_state; + + if (!new_state->crtc) + return 0; + + crtc_state = drm_atomic_get_new_crtc_state(new_state->state, new_state->crtc); + + /* + * These properties are handled by fastset, and might not end + * up in a modeset. + */ + if (new_conn_state->force_audio != old_conn_state->force_audio || + new_conn_state->broadcast_rgb != old_conn_state->broadcast_rgb || + new_conn_state->base.picture_aspect_ratio != old_conn_state->base.picture_aspect_ratio || + new_conn_state->base.scaling_mode != old_conn_state->base.scaling_mode) + crtc_state->mode_changed = true; + + return 0; +} + +/** + * intel_digital_connector_duplicate_state - duplicate connector state + * @connector: digital connector + * + * Allocates and returns a copy of the connector state (both common and + * digital connector specific) for the specified connector. + * + * Returns: The newly allocated connector state, or NULL on failure. + */ +struct drm_connector_state * +intel_digital_connector_duplicate_state(struct drm_connector *connector) +{ + struct intel_digital_connector_state *state; + + state = kmemdup(connector->state, sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_connector_duplicate_state(connector, &state->base); + return &state->base; +} + +/** * intel_crtc_duplicate_state - duplicate crtc state * @crtc: drm crtc * diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index cfb47293fd53cf..4325cb0a04f5db 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -55,7 +55,7 @@ intel_create_plane_state(struct drm_plane *plane) return NULL; state->base.plane = plane; - state->base.rotation = DRM_ROTATE_0; + state->base.rotation = DRM_MODE_ROTATE_0; state->ckey.flags = I915_SET_COLORKEY_NONE; return state; @@ -102,23 +102,7 @@ void intel_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state) { - struct i915_vma *vma; - - vma = fetch_and_zero(&to_intel_plane_state(state)->vma); - - /* - * FIXME: Normally intel_cleanup_plane_fb handles destruction of vma. - * We currently don't clear all planes during driver unload, so we have - * to be able to unpin vma here for now. - * - * Normally this can only happen during unload when kmscon is disabled - * and userspace doesn't attempt to set a framebuffer at all. - */ - if (vma) { - mutex_lock(&plane->dev->struct_mutex); - intel_unpin_fb_vma(vma); - mutex_unlock(&plane->dev->struct_mutex); - } + WARN_ON(to_intel_plane_state(state)->vma); drm_atomic_helper_plane_destroy_state(plane, state); } @@ -178,14 +162,14 @@ int intel_plane_atomic_check_with_state(struct intel_crtc_state *crtc_state, /* CHV ignores the mirror bit when the rotate bit is set :( */ if (IS_CHERRYVIEW(dev_priv) && - state->rotation & DRM_ROTATE_180 && - state->rotation & DRM_REFLECT_X) { + state->rotation & DRM_MODE_ROTATE_180 && + state->rotation & DRM_MODE_REFLECT_X) { DRM_DEBUG_KMS("Cannot rotate and reflect at the same time\n"); return -EINVAL; } intel_state->base.visible = false; - ret = intel_plane->check_plane(plane, crtc_state, intel_state); + ret = intel_plane->check_plane(intel_plane, crtc_state, intel_state); if (ret) return ret; @@ -235,14 +219,14 @@ static void intel_plane_atomic_update(struct drm_plane *plane, trace_intel_update_plane(plane, to_intel_crtc(crtc)); - intel_plane->update_plane(plane, + intel_plane->update_plane(intel_plane, to_intel_crtc_state(crtc->state), intel_state); } else { trace_intel_disable_plane(plane, to_intel_crtc(crtc)); - intel_plane->disable_plane(plane, crtc); + intel_plane->disable_plane(intel_plane, to_intel_crtc(crtc)); } } diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 52c207e81f413a..d805b6e6fe7146 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -632,20 +632,9 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder, (int) port, (int) pipe); } - switch (intel_encoder->type) { - case INTEL_OUTPUT_HDMI: - intel_lpe_audio_notify(dev_priv, connector->eld, port, pipe, - crtc_state->port_clock, - false, 0); - break; - case INTEL_OUTPUT_DP: - intel_lpe_audio_notify(dev_priv, connector->eld, port, pipe, - adjusted_mode->crtc_clock, - true, crtc_state->port_clock); - break; - default: - break; - } + intel_lpe_audio_notify(dev_priv, pipe, port, connector->eld, + crtc_state->port_clock, + intel_encoder->type == INTEL_OUTPUT_DP); } /** @@ -680,7 +669,7 @@ void intel_audio_codec_disable(struct intel_encoder *intel_encoder) (int) port, (int) pipe); } - intel_lpe_audio_notify(dev_priv, NULL, port, pipe, 0, false, 0); + intel_lpe_audio_notify(dev_priv, pipe, port, NULL, 0, false); } /** diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 9ccbf26124c616..183afcb036aa91 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -64,10 +64,12 @@ static unsigned long wait_timeout(void) static noinline void missed_breadcrumb(struct intel_engine_cs *engine) { - DRM_DEBUG_DRIVER("%s missed breadcrumb at %pF, irq posted? %s\n", + DRM_DEBUG_DRIVER("%s missed breadcrumb at %pF, irq posted? %s, current seqno=%x, last=%x\n", engine->name, __builtin_return_address(0), yesno(test_bit(ENGINE_IRQ_BREADCRUMB, - &engine->irq_posted))); + &engine->irq_posted)), + intel_engine_get_seqno(engine), + intel_engine_last_submit(engine)); set_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings); } @@ -665,12 +667,13 @@ static int intel_breadcrumbs_signaler(void *arg) return 0; } -void intel_engine_enable_signaling(struct drm_i915_gem_request *request) +void intel_engine_enable_signaling(struct drm_i915_gem_request *request, + bool wakeup) { struct intel_engine_cs *engine = request->engine; struct intel_breadcrumbs *b = &engine->breadcrumbs; struct rb_node *parent, **p; - bool first, wakeup; + bool first; u32 seqno; /* Note that we may be called from an interrupt handler on another @@ -703,7 +706,7 @@ void intel_engine_enable_signaling(struct drm_i915_gem_request *request) * If we are the oldest waiter, enable the irq (after which we * must double check that the seqno did not complete). */ - wakeup = __intel_engine_add_wait(engine, &request->signaling.wait); + wakeup &= __intel_engine_add_wait(engine, &request->signaling.wait); /* Now insert ourselves into the retirement ordered list of signals * on this engine. We track the oldest seqno as that will be the diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index f29a226e24d883..29792972d55db9 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1071,9 +1071,15 @@ static int bxt_calc_cdclk(int max_pixclk) static int glk_calc_cdclk(int max_pixclk) { - if (max_pixclk > 2 * 158400) + /* + * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk + * as a temporary workaround. Use a higher cdclk instead. (Note that + * intel_compute_max_dotclk() limits the max pixel clock to 99% of max + * cdclk.) + */ + if (max_pixclk > DIV_ROUND_UP(2 * 158400 * 99, 100)) return 316800; - else if (max_pixclk > 2 * 79200) + else if (max_pixclk > DIV_ROUND_UP(2 * 79200 * 99, 100)) return 158400; else return 79200; @@ -1664,7 +1670,11 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) int max_cdclk_freq = dev_priv->max_cdclk_freq; if (IS_GEMINILAKE(dev_priv)) - return 2 * max_cdclk_freq; + /* + * FIXME: Limiting to 99% as a temporary workaround. See + * glk_calc_cdclk() for details. + */ + return 2 * max_cdclk_freq * 99 / 100; else if (INTEL_INFO(dev_priv)->gen >= 9 || IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) return max_cdclk_freq; diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 2797bf37c3ac0c..84a1f5e85153fe 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -777,13 +777,6 @@ static int intel_crt_get_modes(struct drm_connector *connector) return ret; } -static int intel_crt_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t value) -{ - return 0; -} - void intel_crt_reset(struct drm_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->dev); @@ -814,10 +807,9 @@ static const struct drm_connector_funcs intel_crt_connector_funcs = { .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_crt_destroy, - .set_property = intel_crt_set_property, + .set_property = drm_atomic_helper_connector_set_property, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_get_property = intel_connector_atomic_get_property, }; static const struct drm_connector_helper_funcs intel_crt_connector_helper_funcs = { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 0914ad96a71b0e..8bac62805cd10a 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1732,12 +1732,18 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder, struct drm_i915_private *dev_priv = to_i915(encoder->dev); enum port port = intel_ddi_get_encoder_port(intel_encoder); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + struct intel_dp *intel_dp = NULL; int type = intel_encoder->type; uint32_t val; bool wait = false; /* old_crtc_state and old_conn_state are NULL when called from DP_MST */ + if (type == INTEL_OUTPUT_DP || type == INTEL_OUTPUT_EDP) { + intel_dp = enc_to_intel_dp(encoder); + intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + } + val = I915_READ(DDI_BUF_CTL(port)); if (val & DDI_BUF_CTL_ENABLE) { val &= ~DDI_BUF_CTL_ENABLE; @@ -1753,9 +1759,7 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder, if (wait) intel_wait_ddi_buf_idle(dev_priv, port); - if (type == INTEL_OUTPUT_DP || type == INTEL_OUTPUT_EDP) { - struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + if (intel_dp) { intel_edp_panel_vdd_on(intel_dp); intel_edp_panel_off(intel_dp); } diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 7d01dfe7faacec..3718341662c232 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -337,7 +337,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { for_each_pipe(dev_priv, pipe) info->num_sprites[pipe] = 2; - } else if (INTEL_GEN(dev_priv) >= 5) { + } else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { for_each_pipe(dev_priv, pipe) info->num_sprites[pipe] = 1; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3617927af269af..91b010134724da 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1277,7 +1277,7 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv, I915_STATE_WARN(val & SPRITE_ENABLE, "sprite %c assertion failure, should be off on pipe %c but is still active\n", plane_name(pipe), pipe_name(pipe)); - } else if (INTEL_GEN(dev_priv) >= 5) { + } else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { u32 val = I915_READ(DVSCNTR(pipe)); I915_STATE_WARN(val & DVS_ENABLE, "sprite %c assertion failure, should be off on pipe %c but is still active\n", @@ -2084,6 +2084,18 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, } } +static unsigned int intel_cursor_alignment(const struct drm_i915_private *dev_priv) +{ + if (IS_I830(dev_priv)) + return 16 * 1024; + else if (IS_I85X(dev_priv)) + return 256; + else if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) + return 32; + else + return 4 * 1024; +} + static unsigned int intel_linear_alignment(const struct drm_i915_private *dev_priv) { if (INTEL_INFO(dev_priv)->gen >= 9) @@ -2386,11 +2398,17 @@ u32 intel_compute_tile_offset(int *x, int *y, const struct intel_plane_state *state, int plane) { - const struct drm_i915_private *dev_priv = to_i915(state->base.plane->dev); + struct intel_plane *intel_plane = to_intel_plane(state->base.plane); + struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev); const struct drm_framebuffer *fb = state->base.fb; unsigned int rotation = state->base.rotation; int pitch = intel_fb_pitch(fb, plane, rotation); - u32 alignment = intel_surf_alignment(fb, plane); + u32 alignment; + + if (intel_plane->id == PLANE_CURSOR) + alignment = intel_cursor_alignment(dev_priv); + else + alignment = intel_surf_alignment(fb, plane); return _intel_compute_tile_offset(dev_priv, x, y, fb, plane, pitch, rotation, alignment); @@ -2468,7 +2486,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, offset = _intel_compute_tile_offset(dev_priv, &x, &y, fb, i, fb->pitches[i], - DRM_ROTATE_0, tile_size); + DRM_MODE_ROTATE_0, tile_size); offset /= tile_size; if (fb->modifier != DRM_FORMAT_MOD_LINEAR) { @@ -2503,7 +2521,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, drm_rect_rotate(&r, rot_info->plane[i].width * tile_width, rot_info->plane[i].height * tile_height, - DRM_ROTATE_270); + DRM_MODE_ROTATE_270); x = r.x1; y = r.y1; @@ -2750,7 +2768,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, false); intel_pre_disable_primary_noatomic(&intel_crtc->base); trace_intel_disable_plane(primary, intel_crtc); - intel_plane->disable_plane(primary, &intel_crtc->base); + intel_plane->disable_plane(intel_plane, intel_crtc); return; @@ -2939,7 +2957,7 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) if (drm_rotation_90_or_270(rotation)) drm_rect_rotate(&plane_state->base.src, fb->width << 16, fb->height << 16, - DRM_ROTATE_270); + DRM_MODE_ROTATE_270); /* * Handle the AUX surface first since @@ -2981,10 +2999,8 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state, if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) dspcntr |= DISPPLANE_PIPE_CSC_ENABLE; - if (INTEL_GEN(dev_priv) < 4) { - if (crtc->pipe == PIPE_B) - dspcntr |= DISPPLANE_SEL_PIPE_B; - } + if (INTEL_GEN(dev_priv) < 4) + dspcntr |= DISPPLANE_SEL_PIPE(crtc->pipe); switch (fb->format->format) { case DRM_FORMAT_C8: @@ -3017,10 +3033,10 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state, fb->modifier == I915_FORMAT_MOD_X_TILED) dspcntr |= DISPPLANE_TILED; - if (rotation & DRM_ROTATE_180) + if (rotation & DRM_MODE_ROTATE_180) dspcntr |= DISPPLANE_ROTATE_180; - if (rotation & DRM_REFLECT_X) + if (rotation & DRM_MODE_REFLECT_X) dspcntr |= DISPPLANE_MIRROR; return dspcntr; @@ -3048,10 +3064,10 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state) int src_w = drm_rect_width(&plane_state->base.src) >> 16; int src_h = drm_rect_height(&plane_state->base.src) >> 16; - if (rotation & DRM_ROTATE_180) { + if (rotation & DRM_MODE_ROTATE_180) { src_x += src_w - 1; src_y += src_h - 1; - } else if (rotation & DRM_REFLECT_X) { + } else if (rotation & DRM_MODE_REFLECT_X) { src_x += src_w - 1; } } @@ -3063,14 +3079,14 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state) return 0; } -static void i9xx_update_primary_plane(struct drm_plane *primary, +static void i9xx_update_primary_plane(struct intel_plane *primary, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_i915_private *dev_priv = to_i915(primary->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); - struct drm_framebuffer *fb = plane_state->base.fb; - int plane = intel_crtc->plane; + struct drm_i915_private *dev_priv = to_i915(primary->base.dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum plane plane = primary->plane; u32 linear_offset; u32 dspcntr = plane_state->ctl; i915_reg_t reg = DSPCNTR(plane); @@ -3081,12 +3097,12 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0); if (INTEL_GEN(dev_priv) >= 4) - intel_crtc->dspaddr_offset = plane_state->main.offset; + crtc->dspaddr_offset = plane_state->main.offset; else - intel_crtc->dspaddr_offset = linear_offset; + crtc->dspaddr_offset = linear_offset; - intel_crtc->adjusted_x = x; - intel_crtc->adjusted_y = y; + crtc->adjusted_x = x; + crtc->adjusted_y = y; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -3112,31 +3128,29 @@ static void i9xx_update_primary_plane(struct drm_plane *primary, if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { I915_WRITE_FW(DSPSURF(plane), intel_plane_ggtt_offset(plane_state) + - intel_crtc->dspaddr_offset); + crtc->dspaddr_offset); I915_WRITE_FW(DSPOFFSET(plane), (y << 16) | x); } else if (INTEL_GEN(dev_priv) >= 4) { I915_WRITE_FW(DSPSURF(plane), intel_plane_ggtt_offset(plane_state) + - intel_crtc->dspaddr_offset); + crtc->dspaddr_offset); I915_WRITE_FW(DSPTILEOFF(plane), (y << 16) | x); I915_WRITE_FW(DSPLINOFF(plane), linear_offset); } else { I915_WRITE_FW(DSPADDR(plane), intel_plane_ggtt_offset(plane_state) + - intel_crtc->dspaddr_offset); + crtc->dspaddr_offset); } POSTING_READ_FW(reg); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static void i9xx_disable_primary_plane(struct drm_plane *primary, - struct drm_crtc *crtc) +static void i9xx_disable_primary_plane(struct intel_plane *primary, + struct intel_crtc *crtc) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int plane = intel_crtc->plane; + struct drm_i915_private *dev_priv = to_i915(primary->base.dev); + enum plane plane = primary->plane; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -3271,17 +3285,17 @@ static u32 skl_plane_ctl_tiling(uint64_t fb_modifier) static u32 skl_plane_ctl_rotation(unsigned int rotation) { switch (rotation) { - case DRM_ROTATE_0: + case DRM_MODE_ROTATE_0: break; /* - * DRM_ROTATE_ is counter clockwise to stay compatible with Xrandr + * DRM_MODE_ROTATE_ is counter clockwise to stay compatible with Xrandr * while i915 HW rotation is clockwise, thats why this swapping. */ - case DRM_ROTATE_90: + case DRM_MODE_ROTATE_90: return PLANE_CTL_ROTATE_270; - case DRM_ROTATE_180: + case DRM_MODE_ROTATE_180: return PLANE_CTL_ROTATE_180; - case DRM_ROTATE_270: + case DRM_MODE_ROTATE_270: return PLANE_CTL_ROTATE_90; default: MISSING_CASE(rotation); @@ -3321,16 +3335,15 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state, return plane_ctl; } -static void skylake_update_primary_plane(struct drm_plane *plane, +static void skylake_update_primary_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); - struct drm_framebuffer *fb = plane_state->base.fb; - enum plane_id plane_id = to_intel_plane(plane)->id; - enum pipe pipe = to_intel_plane(plane)->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; u32 plane_ctl = plane_state->ctl; unsigned int rotation = plane_state->base.rotation; u32 stride = skl_plane_stride(fb, 0, rotation); @@ -3352,10 +3365,10 @@ static void skylake_update_primary_plane(struct drm_plane *plane, dst_w--; dst_h--; - intel_crtc->dspaddr_offset = surf_addr; + crtc->dspaddr_offset = surf_addr; - intel_crtc->adjusted_x = src_x; - intel_crtc->adjusted_y = src_y; + crtc->adjusted_x = src_x; + crtc->adjusted_y = src_y; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -3394,13 +3407,12 @@ static void skylake_update_primary_plane(struct drm_plane *plane, spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static void skylake_disable_primary_plane(struct drm_plane *primary, - struct drm_crtc *crtc) +static void skylake_disable_primary_plane(struct intel_plane *primary, + struct intel_crtc *crtc) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - enum plane_id plane_id = to_intel_plane(primary)->id; - enum pipe pipe = to_intel_plane(primary)->pipe; + struct drm_i915_private *dev_priv = to_i915(primary->base.dev); + enum plane_id plane_id = primary->id; + enum pipe pipe = primary->pipe; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -3433,7 +3445,7 @@ static void intel_update_primary_planes(struct drm_device *dev) trace_intel_update_plane(&plane->base, to_intel_crtc(crtc)); - plane->update_plane(&plane->base, + plane->update_plane(plane, to_intel_crtc_state(crtc->state), plane_state); } @@ -4671,7 +4683,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode; return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, - &state->scaler_state.scaler_id, DRM_ROTATE_0, + &state->scaler_state.scaler_id, DRM_MODE_ROTATE_0, state->pipe_src_w, state->pipe_src_h, adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } @@ -4861,12 +4873,9 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc) { if (intel_crtc->overlay) { struct drm_device *dev = intel_crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); mutex_lock(&dev->struct_mutex); - dev_priv->mm.interruptible = false; (void) intel_overlay_switch_off(intel_crtc->overlay); - dev_priv->mm.interruptible = true; mutex_unlock(&dev->struct_mutex); } @@ -5086,7 +5095,7 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc, unsigned plane_mask intel_crtc_dpms_overlay_disable(intel_crtc); drm_for_each_plane_mask(p, dev, plane_mask) - to_intel_plane(p)->disable_plane(p, crtc); + to_intel_plane(p)->disable_plane(to_intel_plane(p), intel_crtc); /* * FIXME: Once we grow proper nuclear flip support out of this we need @@ -5722,6 +5731,8 @@ static void i9xx_set_pll_dividers(struct intel_crtc *crtc) static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config, struct drm_atomic_state *old_state) { + struct intel_atomic_state *old_intel_state = + to_intel_atomic_state(old_state); struct drm_crtc *crtc = pipe_config->base.crtc; struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); @@ -5754,7 +5765,11 @@ static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config, intel_color_load_luts(&pipe_config->base); - intel_update_watermarks(intel_crtc); + if (dev_priv->display.initial_watermarks != NULL) + dev_priv->display.initial_watermarks(old_intel_state, + intel_crtc->config); + else + intel_update_watermarks(intel_crtc); intel_enable_pipe(intel_crtc); assert_vblank_disabled(crtc); @@ -5920,9 +5935,10 @@ void intel_encoder_destroy(struct drm_encoder *encoder) /* Cross check the actual hw state with our own modeset state tracking (and it's * internal consistency). */ -static void intel_connector_verify_state(struct intel_connector *connector) +static void intel_connector_verify_state(struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { - struct drm_crtc *crtc = connector->base.state->crtc; + struct intel_connector *connector = to_intel_connector(conn_state->connector); DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.base.id, @@ -5930,15 +5946,14 @@ static void intel_connector_verify_state(struct intel_connector *connector) if (connector->get_hw_state(connector)) { struct intel_encoder *encoder = connector->encoder; - struct drm_connector_state *conn_state = connector->base.state; - I915_STATE_WARN(!crtc, + I915_STATE_WARN(!crtc_state, "connector enabled without attached crtc\n"); - if (!crtc) + if (!crtc_state) return; - I915_STATE_WARN(!crtc->state->active, + I915_STATE_WARN(!crtc_state->active, "connector is active, but attached crtc isn't\n"); if (!encoder || encoder->type == INTEL_OUTPUT_DP_MST) @@ -5950,20 +5965,30 @@ static void intel_connector_verify_state(struct intel_connector *connector) I915_STATE_WARN(conn_state->crtc != encoder->base.crtc, "attached encoder crtc differs from connector crtc\n"); } else { - I915_STATE_WARN(crtc && crtc->state->active, + I915_STATE_WARN(crtc_state && crtc_state->active, "attached crtc is active, but connector isn't\n"); - I915_STATE_WARN(!crtc && connector->base.state->best_encoder, + I915_STATE_WARN(!crtc_state && conn_state->best_encoder, "best encoder set without crtc!\n"); } } int intel_connector_init(struct intel_connector *connector) { - drm_atomic_helper_connector_reset(&connector->base); + struct intel_digital_connector_state *conn_state; - if (!connector->base.state) + /* + * Allocate enough memory to hold intel_digital_connector_state, + * This might be a few bytes too many, but for connectors that don't + * need it we'll free the state and allocate a smaller one on the first + * succesful commit anyway. + */ + conn_state = kzalloc(sizeof(*conn_state), GFP_KERNEL); + if (!conn_state) return -ENOMEM; + __drm_atomic_helper_connector_reset(&connector->base, + &conn_state->base); + return 0; } @@ -6372,8 +6397,8 @@ static void vlv_pllb_recal_opamp(struct drm_i915_private *dev_priv, enum pipe vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW9(1), reg_val); reg_val = vlv_dpio_read(dev_priv, pipe, VLV_REF_DW13); - reg_val &= 0x8cffffff; - reg_val = 0x8c000000; + reg_val &= 0x00ffffff; + reg_val |= 0x8c000000; vlv_dpio_write(dev_priv, pipe, VLV_REF_DW13, reg_val); reg_val = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW9(1)); @@ -8177,9 +8202,6 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); - struct dpll reduced_clock; - bool has_reduced_clock = false; - struct intel_shared_dpll *pll; const struct intel_limit *limit; int refclk = 120000; @@ -8221,20 +8243,14 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc, return -EINVAL; } - ironlake_compute_dpll(crtc, crtc_state, - has_reduced_clock ? &reduced_clock : NULL); + ironlake_compute_dpll(crtc, crtc_state, NULL); - pll = intel_get_shared_dpll(crtc, crtc_state, NULL); - if (pll == NULL) { + if (!intel_get_shared_dpll(crtc, crtc_state, NULL)) { DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n", pipe_name(crtc->pipe)); return -EINVAL; } - if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) && - has_reduced_clock) - crtc->lowfreq_avail = true; - return 0; } @@ -9138,38 +9154,171 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return active; } +static u32 intel_cursor_base(const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = + to_i915(plane_state->base.plane->dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + const struct drm_i915_gem_object *obj = intel_fb_obj(fb); + u32 base; + + if (INTEL_INFO(dev_priv)->cursor_needs_physical) + base = obj->phys_handle->busaddr; + else + base = intel_plane_ggtt_offset(plane_state); + + base += plane_state->main.offset; + + /* ILK+ do this automagically */ + if (HAS_GMCH_DISPLAY(dev_priv) && + plane_state->base.rotation & DRM_MODE_ROTATE_180) + base += (plane_state->base.crtc_h * + plane_state->base.crtc_w - 1) * fb->format->cpp[0]; + + return base; +} + +static u32 intel_cursor_position(const struct intel_plane_state *plane_state) +{ + int x = plane_state->base.crtc_x; + int y = plane_state->base.crtc_y; + u32 pos = 0; + + if (x < 0) { + pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; + x = -x; + } + pos |= x << CURSOR_X_SHIFT; + + if (y < 0) { + pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; + y = -y; + } + pos |= y << CURSOR_Y_SHIFT; + + return pos; +} + +static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state) +{ + const struct drm_mode_config *config = + &plane_state->base.plane->dev->mode_config; + int width = plane_state->base.crtc_w; + int height = plane_state->base.crtc_h; + + return width > 0 && width <= config->cursor_width && + height > 0 && height <= config->cursor_height; +} + +static int intel_check_cursor(struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state) +{ + const struct drm_framebuffer *fb = plane_state->base.fb; + int src_x, src_y; + u32 offset; + int ret; + + ret = drm_plane_helper_check_state(&plane_state->base, + &plane_state->clip, + DRM_PLANE_HELPER_NO_SCALING, + DRM_PLANE_HELPER_NO_SCALING, + true, true); + if (ret) + return ret; + + if (!fb) + return 0; + + if (fb->modifier != DRM_FORMAT_MOD_LINEAR) { + DRM_DEBUG_KMS("cursor cannot be tiled\n"); + return -EINVAL; + } + + src_x = plane_state->base.src_x >> 16; + src_y = plane_state->base.src_y >> 16; + + intel_add_fb_offsets(&src_x, &src_y, plane_state, 0); + offset = intel_compute_tile_offset(&src_x, &src_y, plane_state, 0); + + if (src_x != 0 || src_y != 0) { + DRM_DEBUG_KMS("Arbitrary cursor panning not supported\n"); + return -EINVAL; + } + + plane_state->main.offset = offset; + + return 0; +} + static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - unsigned int width = plane_state->base.crtc_w; - unsigned int stride = roundup_pow_of_two(width) * 4; + const struct drm_framebuffer *fb = plane_state->base.fb; - switch (stride) { - default: - WARN_ONCE(1, "Invalid cursor width/stride, width=%u, stride=%u\n", - width, stride); - stride = 256; - /* fallthrough */ + return CURSOR_ENABLE | + CURSOR_GAMMA_ENABLE | + CURSOR_FORMAT_ARGB | + CURSOR_STRIDE(fb->pitches[0]); +} + +static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state) +{ + int width = plane_state->base.crtc_w; + + /* + * 845g/865g are only limited by the width of their cursors, + * the height is arbitrary up to the precision of the register. + */ + return intel_cursor_size_ok(plane_state) && IS_ALIGNED(width, 64); +} + +static int i845_check_cursor(struct intel_plane *plane, + struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state) +{ + const struct drm_framebuffer *fb = plane_state->base.fb; + int ret; + + ret = intel_check_cursor(crtc_state, plane_state); + if (ret) + return ret; + + /* if we want to turn off the cursor ignore width and height */ + if (!fb) + return 0; + + /* Check for which cursor types we support */ + if (!i845_cursor_size_ok(plane_state)) { + DRM_DEBUG("Cursor dimension %dx%d not supported\n", + plane_state->base.crtc_w, + plane_state->base.crtc_h); + return -EINVAL; + } + + switch (fb->pitches[0]) { case 256: case 512: case 1024: case 2048: break; + default: + DRM_DEBUG_KMS("Invalid cursor stride (%u)\n", + fb->pitches[0]); + return -EINVAL; } - return CURSOR_ENABLE | - CURSOR_GAMMA_ENABLE | - CURSOR_FORMAT_ARGB | - CURSOR_STRIDE(stride); + plane_state->ctl = i845_cursor_ctl(crtc_state, plane_state); + + return 0; } -static void i845_update_cursor(struct drm_crtc *crtc, u32 base, +static void i845_update_cursor(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - uint32_t cntl = 0, size = 0; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + u32 cntl = 0, base = 0, pos = 0, size = 0; + unsigned long irqflags; if (plane_state && plane_state->base.visible) { unsigned int width = plane_state->base.crtc_w; @@ -9177,35 +9326,41 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base, cntl = plane_state->ctl; size = (height << 12) | width; - } - if (intel_crtc->cursor_cntl != 0 && - (intel_crtc->cursor_base != base || - intel_crtc->cursor_size != size || - intel_crtc->cursor_cntl != cntl)) { - /* On these chipsets we can only modify the base/size/stride - * whilst the cursor is disabled. - */ - I915_WRITE_FW(CURCNTR(PIPE_A), 0); - POSTING_READ_FW(CURCNTR(PIPE_A)); - intel_crtc->cursor_cntl = 0; + base = intel_cursor_base(plane_state); + pos = intel_cursor_position(plane_state); } - if (intel_crtc->cursor_base != base) { - I915_WRITE_FW(CURBASE(PIPE_A), base); - intel_crtc->cursor_base = base; - } + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - if (intel_crtc->cursor_size != size) { + /* On these chipsets we can only modify the base/size/stride + * whilst the cursor is disabled. + */ + if (plane->cursor.base != base || + plane->cursor.size != size || + plane->cursor.cntl != cntl) { + I915_WRITE_FW(CURCNTR(PIPE_A), 0); + I915_WRITE_FW(CURBASE(PIPE_A), base); I915_WRITE_FW(CURSIZE, size); - intel_crtc->cursor_size = size; - } - - if (intel_crtc->cursor_cntl != cntl) { + I915_WRITE_FW(CURPOS(PIPE_A), pos); I915_WRITE_FW(CURCNTR(PIPE_A), cntl); - POSTING_READ_FW(CURCNTR(PIPE_A)); - intel_crtc->cursor_cntl = cntl; + + plane->cursor.base = base; + plane->cursor.size = size; + plane->cursor.cntl = cntl; + } else { + I915_WRITE_FW(CURPOS(PIPE_A), pos); } + + POSTING_READ_FW(CURCNTR(PIPE_A)); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void i845_disable_cursor(struct intel_plane *plane, + struct intel_crtc *crtc) +{ + i845_update_cursor(plane, NULL, NULL); } static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, @@ -9214,7 +9369,6 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev); struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - enum pipe pipe = crtc->pipe; u32 cntl; cntl = MCURSOR_GAMMA_ENABLE; @@ -9222,7 +9376,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, if (HAS_DDI(dev_priv)) cntl |= CURSOR_PIPE_CSC_ENABLE; - cntl |= pipe << 28; /* Connect to correct pipe */ + cntl |= MCURSOR_PIPE_SELECT(crtc->pipe); switch (plane_state->base.crtc_w) { case 64: @@ -9239,122 +9393,160 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, return 0; } - if (plane_state->base.rotation & DRM_ROTATE_180) + if (plane_state->base.rotation & DRM_MODE_ROTATE_180) cntl |= CURSOR_ROTATE_180; return cntl; } -static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, - const struct intel_plane_state *plane_state) +static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - uint32_t cntl = 0; + struct drm_i915_private *dev_priv = + to_i915(plane_state->base.plane->dev); + int width = plane_state->base.crtc_w; + int height = plane_state->base.crtc_h; - if (plane_state && plane_state->base.visible) - cntl = plane_state->ctl; + if (!intel_cursor_size_ok(plane_state)) + return false; - if (intel_crtc->cursor_cntl != cntl) { - I915_WRITE_FW(CURCNTR(pipe), cntl); - POSTING_READ_FW(CURCNTR(pipe)); - intel_crtc->cursor_cntl = cntl; + /* Cursor width is limited to a few power-of-two sizes */ + switch (width) { + case 256: + case 128: + case 64: + break; + default: + return false; } - /* and commit changes on next vblank */ - I915_WRITE_FW(CURBASE(pipe), base); - POSTING_READ_FW(CURBASE(pipe)); + /* + * IVB+ have CUR_FBC_CTL which allows an arbitrary cursor + * height from 8 lines up to the cursor width, when the + * cursor is not rotated. Everything else requires square + * cursors. + */ + if (HAS_CUR_FBC(dev_priv) && + plane_state->base.rotation & DRM_MODE_ROTATE_0) { + if (height < 8 || height > width) + return false; + } else { + if (height != width) + return false; + } - intel_crtc->cursor_base = base; + return true; } -/* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ -static void intel_crtc_update_cursor(struct drm_crtc *crtc, - const struct intel_plane_state *plane_state) +static int i9xx_check_cursor(struct intel_plane *plane, + struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - u32 base = intel_crtc->cursor_addr; - unsigned long irqflags; - u32 pos = 0; - - if (plane_state) { - int x = plane_state->base.crtc_x; - int y = plane_state->base.crtc_y; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; + int ret; - if (x < 0) { - pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; - x = -x; - } - pos |= x << CURSOR_X_SHIFT; + ret = intel_check_cursor(crtc_state, plane_state); + if (ret) + return ret; - if (y < 0) { - pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; - y = -y; - } - pos |= y << CURSOR_Y_SHIFT; + /* if we want to turn off the cursor ignore width and height */ + if (!fb) + return 0; - /* ILK+ do this automagically */ - if (HAS_GMCH_DISPLAY(dev_priv) && - plane_state->base.rotation & DRM_ROTATE_180) { - base += (plane_state->base.crtc_h * - plane_state->base.crtc_w - 1) * 4; - } + /* Check for which cursor types we support */ + if (!i9xx_cursor_size_ok(plane_state)) { + DRM_DEBUG("Cursor dimension %dx%d not supported\n", + plane_state->base.crtc_w, + plane_state->base.crtc_h); + return -EINVAL; } - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + if (fb->pitches[0] != plane_state->base.crtc_w * fb->format->cpp[0]) { + DRM_DEBUG_KMS("Invalid cursor stride (%u) (cursor width %d)\n", + fb->pitches[0], plane_state->base.crtc_w); + return -EINVAL; + } - I915_WRITE_FW(CURPOS(pipe), pos); + /* + * There's something wrong with the cursor on CHV pipe C. + * If it straddles the left edge of the screen then + * moving it away from the edge or disabling it often + * results in a pipe underrun, and often that can lead to + * dead pipe (constant underrun reported, and it scans + * out just a solid color). To recover from that, the + * display power well must be turned off and on again. + * Refuse the put the cursor into that compromised position. + */ + if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_C && + plane_state->base.visible && plane_state->base.crtc_x < 0) { + DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n"); + return -EINVAL; + } - if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) - i845_update_cursor(crtc, base, plane_state); - else - i9xx_update_cursor(crtc, base, plane_state); + plane_state->ctl = i9xx_cursor_ctl(crtc_state, plane_state); - spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + return 0; } -static bool cursor_size_ok(struct drm_i915_private *dev_priv, - uint32_t width, uint32_t height) +static void i9xx_update_cursor(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { - if (width == 0 || height == 0) - return false; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + u32 cntl = 0, base = 0, pos = 0, fbc_ctl = 0; + unsigned long irqflags; - /* - * 845g/865g are special in that they are only limited by - * the width of their cursors, the height is arbitrary up to - * the precision of the register. Everything else requires - * square cursors, limited to a few power-of-two sizes. - */ - if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) { - if ((width & 63) != 0) - return false; + if (plane_state && plane_state->base.visible) { + cntl = plane_state->ctl; - if (width > (IS_I845G(dev_priv) ? 64 : 512)) - return false; + if (plane_state->base.crtc_h != plane_state->base.crtc_w) + fbc_ctl = CUR_FBC_CTL_EN | (plane_state->base.crtc_h - 1); - if (height > 1023) - return false; + base = intel_cursor_base(plane_state); + pos = intel_cursor_position(plane_state); + } + + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + /* + * On some platforms writing CURCNTR first will also + * cause CURPOS to be armed by the CURBASE write. + * Without the CURCNTR write the CURPOS write would + * arm itself. + * + * CURCNTR and CUR_FBC_CTL are always + * armed by the CURBASE write only. + */ + if (plane->cursor.base != base || + plane->cursor.size != fbc_ctl || + plane->cursor.cntl != cntl) { + I915_WRITE_FW(CURCNTR(pipe), cntl); + if (HAS_CUR_FBC(dev_priv)) + I915_WRITE_FW(CUR_FBC_CTL(pipe), fbc_ctl); + I915_WRITE_FW(CURPOS(pipe), pos); + I915_WRITE_FW(CURBASE(pipe), base); + + plane->cursor.base = base; + plane->cursor.size = fbc_ctl; + plane->cursor.cntl = cntl; } else { - switch (width | height) { - case 256: - case 128: - if (IS_GEN2(dev_priv)) - return false; - case 64: - break; - default: - return false; - } + I915_WRITE_FW(CURPOS(pipe), pos); } - return true; + POSTING_READ_FW(CURBASE(pipe)); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); +} + +static void i9xx_disable_cursor(struct intel_plane *plane, + struct intel_crtc *crtc) +{ + i9xx_update_cursor(plane, NULL, NULL); } + /* VESA 640x480x72Hz mode to set on the pipe */ static struct drm_display_mode load_detect_mode = { DRM_MODE("640x480", DRM_MODE_TYPE_DEFAULT, 31500, 640, 664, @@ -9566,6 +9758,7 @@ int intel_get_load_detect_pipe(struct drm_connector *connector, */ if (!crtc) { DRM_DEBUG_KMS("no pipe available for load-detect\n"); + ret = -ENODEV; goto fail; } @@ -9622,6 +9815,7 @@ int intel_get_load_detect_pipe(struct drm_connector *connector, DRM_DEBUG_KMS("reusing fbdev for load-detection framebuffer\n"); if (IS_ERR(fb)) { DRM_DEBUG_KMS("failed to allocate framebuffer for load-detection\n"); + ret = PTR_ERR(fb); goto fail; } @@ -10853,21 +11047,21 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, turn_off, turn_on, mode_changed); if (turn_on) { - if (INTEL_GEN(dev_priv) < 5) + if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) pipe_config->update_wm_pre = true; /* must disable cxsr around plane enable/disable */ if (plane->id != PLANE_CURSOR) pipe_config->disable_cxsr = true; } else if (turn_off) { - if (INTEL_GEN(dev_priv) < 5) + if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) pipe_config->update_wm_post = true; /* must disable cxsr around plane enable/disable */ if (plane->id != PLANE_CURSOR) pipe_config->disable_cxsr = true; } else if (intel_wm_need_update(&plane->base, plane_state)) { - if (INTEL_GEN(dev_priv) < 5) { + if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) { /* FIXME bollocks */ pipe_config->update_wm_pre = true; pipe_config->update_wm_post = true; @@ -10992,6 +11186,9 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, if (mode_changed) ret = skl_update_scaler_crtc(pipe_config); + if (!ret) + ret = skl_check_pipe_max_pixel_rate(intel_crtc, + pipe_config); if (!ret) ret = intel_atomic_setup_scalers(dev_priv, intel_crtc, pipe_config); @@ -11291,7 +11488,8 @@ clear_intel_crtc_state(struct intel_crtc_state *crtc_state) shared_dpll = crtc_state->shared_dpll; dpll_hw_state = crtc_state->dpll_hw_state; force_thru = crtc_state->pch_pfit.force_thru; - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + if (IS_G4X(dev_priv) || + IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) wm_state = crtc_state->wm; /* Keep base drm_crtc_state intact, only clear our extended struct */ @@ -11303,7 +11501,8 @@ clear_intel_crtc_state(struct intel_crtc_state *crtc_state) crtc_state->shared_dpll = shared_dpll; crtc_state->dpll_hw_state = dpll_hw_state; crtc_state->pch_pfit.force_thru = force_thru; - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + if (IS_G4X(dev_priv) || + IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) crtc_state->wm = wm_state; } @@ -11444,12 +11643,6 @@ intel_modeset_update_crtc_state(struct drm_atomic_state *state) for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { to_intel_crtc(crtc)->config = to_intel_crtc_state(new_crtc_state); - /* Update hwmode for vblank functions */ - if (new_crtc_state->active) - crtc->hwmode = new_crtc_state->adjusted_mode; - else - crtc->hwmode.crtc_clock = 0; - /* * Update legacy state to satisfy fbc code. This can * be removed when fbc uses the atomic state. @@ -11871,7 +12064,7 @@ static void verify_wm_state(struct drm_crtc *crtc, * allocation. In that case since the ddb allocation will be updated * once the plane becomes visible, we can skip this check */ - if (intel_crtc->cursor_addr) { + if (1) { hw_plane_wm = &hw_wm.planes[PLANE_CURSOR]; sw_plane_wm = &sw_wm->planes[PLANE_CURSOR]; @@ -11927,11 +12120,15 @@ verify_connector_state(struct drm_device *dev, for_each_new_connector_in_state(state, connector, new_conn_state, i) { struct drm_encoder *encoder = connector->encoder; + struct drm_crtc_state *crtc_state = NULL; if (new_conn_state->crtc != crtc) continue; - intel_connector_verify_state(to_intel_connector(connector)); + if (crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc); + + intel_connector_verify_state(crtc_state, new_conn_state); I915_STATE_WARN(new_conn_state->best_encoder != encoder, "connector's atomic encoder doesn't match legacy encoder\n"); @@ -12049,7 +12246,7 @@ verify_crtc_state(struct drm_crtc *crtc, intel_pipe_config_sanity_check(dev_priv, pipe_config); - sw_config = to_intel_crtc_state(crtc->state); + sw_config = to_intel_crtc_state(new_crtc_state); if (!intel_pipe_config_compare(dev_priv, sw_config, pipe_config, false)) { I915_STATE_WARN(1, "pipe state doesn't match!\n"); @@ -13068,43 +13265,6 @@ static int intel_atomic_commit(struct drm_device *dev, return 0; } -void intel_crtc_restore_mode(struct drm_crtc *crtc) -{ - struct drm_device *dev = crtc->dev; - struct drm_atomic_state *state; - struct drm_crtc_state *crtc_state; - int ret; - - state = drm_atomic_state_alloc(dev); - if (!state) { - DRM_DEBUG_KMS("[CRTC:%d:%s] crtc restore failed, out of memory", - crtc->base.id, crtc->name); - return; - } - - state->acquire_ctx = crtc->dev->mode_config.acquire_ctx; - -retry: - crtc_state = drm_atomic_get_crtc_state(state, crtc); - ret = PTR_ERR_OR_ZERO(crtc_state); - if (!ret) { - if (!crtc_state->active) - goto out; - - crtc_state->mode_changed = true; - ret = drm_atomic_commit(state); - } - - if (ret == -EDEADLK) { - drm_atomic_state_clear(state); - drm_modeset_backoff(state->acquire_ctx); - goto retry; - } - -out: - drm_atomic_state_put(state); -} - static const struct drm_crtc_funcs intel_crtc_funcs = { .gamma_set = drm_atomic_helper_legacy_gamma_set, .set_config = drm_atomic_helper_set_config, @@ -13145,7 +13305,7 @@ intel_prepare_plane_fb(struct drm_plane *plane, if (obj) { if (plane->type == DRM_PLANE_TYPE_CURSOR && INTEL_INFO(dev_priv)->cursor_needs_physical) { - const int align = IS_I830(dev_priv) ? 16 * 1024 : 256; + const int align = intel_cursor_alignment(dev_priv); ret = i915_gem_object_attach_phys(obj, align); if (ret) { @@ -13275,11 +13435,11 @@ skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state } static int -intel_check_primary_plane(struct drm_plane *plane, +intel_check_primary_plane(struct intel_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state) { - struct drm_i915_private *dev_priv = to_i915(plane->dev); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); struct drm_crtc *crtc = state->base.crtc; int min_scale = DRM_PLANE_HELPER_NO_SCALING; int max_scale = DRM_PLANE_HELPER_NO_SCALING; @@ -13458,7 +13618,7 @@ intel_legacy_cursor_update(struct drm_plane *plane, goto out_free; if (INTEL_INFO(dev_priv)->cursor_needs_physical) { - int align = IS_I830(dev_priv) ? 16 * 1024 : 256; + int align = intel_cursor_alignment(dev_priv); ret = i915_gem_object_attach_phys(intel_fb_obj(fb), align); if (ret) { @@ -13494,12 +13654,12 @@ intel_legacy_cursor_update(struct drm_plane *plane, if (plane->state->visible) { trace_intel_update_plane(plane, to_intel_crtc(crtc)); - intel_plane->update_plane(plane, + intel_plane->update_plane(intel_plane, to_intel_crtc_state(crtc->state), to_intel_plane_state(plane->state)); } else { trace_intel_disable_plane(plane, to_intel_crtc(crtc)); - intel_plane->disable_plane(plane, crtc); + intel_plane->disable_plane(intel_plane, to_intel_crtc(crtc)); } intel_cleanup_plane_fb(plane, new_plane_state); @@ -13613,22 +13773,22 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) if (INTEL_GEN(dev_priv) >= 9) { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_90 | - DRM_ROTATE_180 | DRM_ROTATE_270; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | + DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270; } else if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_180 | - DRM_REFLECT_X; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 | + DRM_MODE_REFLECT_X; } else if (INTEL_GEN(dev_priv) >= 4) { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_180; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180; } else { - supported_rotations = DRM_ROTATE_0; + supported_rotations = DRM_MODE_ROTATE_0; } if (INTEL_GEN(dev_priv) >= 4) drm_plane_create_rotation_property(&primary->base, - DRM_ROTATE_0, + DRM_MODE_ROTATE_0, supported_rotations); drm_plane_helper_add(&primary->base, &intel_plane_helper_funcs); @@ -13642,107 +13802,9 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) return ERR_PTR(ret); } -static int -intel_check_cursor_plane(struct drm_plane *plane, - struct intel_crtc_state *crtc_state, - struct intel_plane_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(plane->dev); - struct drm_framebuffer *fb = state->base.fb; - struct drm_i915_gem_object *obj = intel_fb_obj(fb); - enum pipe pipe = to_intel_plane(plane)->pipe; - unsigned stride; - int ret; - - ret = drm_plane_helper_check_state(&state->base, - &state->clip, - DRM_PLANE_HELPER_NO_SCALING, - DRM_PLANE_HELPER_NO_SCALING, - true, true); - if (ret) - return ret; - - /* if we want to turn off the cursor ignore width and height */ - if (!obj) - return 0; - - /* Check for which cursor types we support */ - if (!cursor_size_ok(dev_priv, state->base.crtc_w, - state->base.crtc_h)) { - DRM_DEBUG("Cursor dimension %dx%d not supported\n", - state->base.crtc_w, state->base.crtc_h); - return -EINVAL; - } - - stride = roundup_pow_of_two(state->base.crtc_w) * 4; - if (obj->base.size < stride * state->base.crtc_h) { - DRM_DEBUG_KMS("buffer is too small\n"); - return -ENOMEM; - } - - if (fb->modifier != DRM_FORMAT_MOD_LINEAR) { - DRM_DEBUG_KMS("cursor cannot be tiled\n"); - return -EINVAL; - } - - /* - * There's something wrong with the cursor on CHV pipe C. - * If it straddles the left edge of the screen then - * moving it away from the edge or disabling it often - * results in a pipe underrun, and often that can lead to - * dead pipe (constant underrun reported, and it scans - * out just a solid color). To recover from that, the - * display power well must be turned off and on again. - * Refuse the put the cursor into that compromised position. - */ - if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_C && - state->base.visible && state->base.crtc_x < 0) { - DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n"); - return -EINVAL; - } - - if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) - state->ctl = i845_cursor_ctl(crtc_state, state); - else - state->ctl = i9xx_cursor_ctl(crtc_state, state); - - return 0; -} - -static void -intel_disable_cursor_plane(struct drm_plane *plane, - struct drm_crtc *crtc) -{ - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - - intel_crtc->cursor_addr = 0; - intel_crtc_update_cursor(crtc, NULL); -} - -static void -intel_update_cursor_plane(struct drm_plane *plane, - const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *state) -{ - struct drm_crtc *crtc = crtc_state->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_i915_private *dev_priv = to_i915(plane->dev); - struct drm_i915_gem_object *obj = intel_fb_obj(state->base.fb); - uint32_t addr; - - if (!obj) - addr = 0; - else if (!INTEL_INFO(dev_priv)->cursor_needs_physical) - addr = intel_plane_ggtt_offset(state); - else - addr = obj->phys_handle->busaddr; - - intel_crtc->cursor_addr = addr; - intel_crtc_update_cursor(crtc, state); -} - static struct intel_plane * -intel_cursor_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) +intel_cursor_plane_create(struct drm_i915_private *dev_priv, + enum pipe pipe) { struct intel_plane *cursor = NULL; struct intel_plane_state *state = NULL; @@ -13768,9 +13830,22 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) cursor->plane = pipe; cursor->id = PLANE_CURSOR; cursor->frontbuffer_bit = INTEL_FRONTBUFFER_CURSOR(pipe); - cursor->check_plane = intel_check_cursor_plane; - cursor->update_plane = intel_update_cursor_plane; - cursor->disable_plane = intel_disable_cursor_plane; + + if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) { + cursor->update_plane = i845_update_cursor; + cursor->disable_plane = i845_disable_cursor; + cursor->check_plane = i845_check_cursor; + } else { + cursor->update_plane = i9xx_update_cursor; + cursor->disable_plane = i9xx_disable_cursor; + cursor->check_plane = i9xx_check_cursor; + } + + cursor->cursor.base = ~0; + cursor->cursor.cntl = ~0; + + if (IS_I845G(dev_priv) || IS_I865G(dev_priv) || HAS_CUR_FBC(dev_priv)) + cursor->cursor.size = ~0; ret = drm_universal_plane_init(&dev_priv->drm, &cursor->base, 0, &intel_cursor_plane_funcs, @@ -13783,9 +13858,9 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) if (INTEL_GEN(dev_priv) >= 4) drm_plane_create_rotation_property(&cursor->base, - DRM_ROTATE_0, - DRM_ROTATE_0 | - DRM_ROTATE_180); + DRM_MODE_ROTATE_0, + DRM_MODE_ROTATE_0 | + DRM_MODE_ROTATE_180); if (INTEL_GEN(dev_priv) >= 9) state->scaler_id = -1; @@ -13879,10 +13954,6 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe) intel_crtc->pipe = pipe; intel_crtc->plane = primary->plane; - intel_crtc->cursor_base = ~0; - intel_crtc->cursor_cntl = ~0; - intel_crtc->cursor_size = ~0; - /* initialize shared scalers */ intel_crtc_init_scalers(intel_crtc, crtc_state); @@ -14422,7 +14493,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, case DRM_FORMAT_UYVY: case DRM_FORMAT_YVYU: case DRM_FORMAT_VYUY: - if (INTEL_GEN(dev_priv) < 5) { + if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) { DRM_DEBUG_KMS("unsupported pixel format: %s\n", drm_get_format_name(mode_cmd->pixel_format, &format_name)); goto err; @@ -14934,6 +15005,7 @@ int intel_modeset_init(struct drm_device *dev) dev->mode_config.funcs = &intel_mode_funcs; + init_llist_head(&dev_priv->atomic_helper.free_list); INIT_WORK(&dev_priv->atomic_helper.free_work, intel_atomic_helper_free_state_worker); @@ -15155,7 +15227,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) continue; trace_intel_disable_plane(&plane->base, crtc); - plane->disable_plane(&plane->base, &crtc->base); + plane->disable_plane(plane, crtc); } } @@ -15425,8 +15497,6 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) to_intel_crtc_state(crtc->base.state); int pixclk = 0; - crtc->base.hwmode = crtc_state->base.adjusted_mode; - memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); if (crtc_state->base.active) { intel_mode_from_pipe_config(&crtc->base.mode, crtc_state); @@ -15456,7 +15526,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled) pixclk = DIV_ROUND_UP(pixclk * 100, 95); - drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode); + drm_calc_timestamping_constants(&crtc->base, + &crtc_state->base.adjusted_mode); update_scanline_offset(crtc); } @@ -15527,7 +15598,10 @@ intel_modeset_setup_hw_state(struct drm_device *dev) pll->on = false; } - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { + if (IS_G4X(dev_priv)) { + g4x_wm_get_hw_state(dev); + g4x_wm_sanitize(dev_priv); + } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { vlv_wm_get_hw_state(dev); vlv_wm_sanitize(dev_priv); } else if (IS_GEN9(dev_priv)) { @@ -15561,13 +15635,6 @@ void intel_display_resume(struct drm_device *dev) if (state) state->acquire_ctx = &ctx; - /* - * This is a cludge because with real atomic modeset mode_config.mutex - * won't be taken. Unfortunately some probed state like - * audio_codec_enable is still protected by mode_config.mutex, so lock - * it here for now. - */ - mutex_lock(&dev->mode_config.mutex); drm_modeset_acquire_init(&ctx, 0); while (1) { @@ -15583,7 +15650,6 @@ void intel_display_resume(struct drm_device *dev) drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); - mutex_unlock(&dev->mode_config.mutex); if (ret) DRM_ERROR("Restoring old state failed with %i\n", ret); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index ee77b519835c5f..49a1db3787c555 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -133,36 +133,55 @@ static void vlv_steal_power_sequencer(struct drm_device *dev, enum pipe pipe); static void intel_dp_unset_edid(struct intel_dp *intel_dp); -static int -intel_dp_max_link_bw(struct intel_dp *intel_dp) +static int intel_dp_num_rates(u8 link_bw_code) { - int max_link_bw = intel_dp->dpcd[DP_MAX_LINK_RATE]; - - switch (max_link_bw) { + switch (link_bw_code) { + default: + WARN(1, "invalid max DP link bw val %x, using 1.62Gbps\n", + link_bw_code); case DP_LINK_BW_1_62: + return 1; case DP_LINK_BW_2_7: + return 2; case DP_LINK_BW_5_4: - break; - default: - WARN(1, "invalid max DP link bw val %x, using 1.62Gbps\n", - max_link_bw); - max_link_bw = DP_LINK_BW_1_62; - break; + return 3; } - return max_link_bw; } -static u8 intel_dp_max_lane_count(struct intel_dp *intel_dp) +/* update sink rates from dpcd */ +static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) { - struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - u8 source_max, sink_max; + int i, num_rates; + + num_rates = intel_dp_num_rates(intel_dp->dpcd[DP_MAX_LINK_RATE]); - source_max = intel_dig_port->max_lanes; - sink_max = intel_dp->max_sink_lane_count; + for (i = 0; i < num_rates; i++) + intel_dp->sink_rates[i] = default_rates[i]; + + intel_dp->num_sink_rates = num_rates; +} + +/* Theoretical max between source and sink */ +static int intel_dp_max_common_rate(struct intel_dp *intel_dp) +{ + return intel_dp->common_rates[intel_dp->num_common_rates - 1]; +} + +/* Theoretical max between source and sink */ +static int intel_dp_max_common_lane_count(struct intel_dp *intel_dp) +{ + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + int source_max = intel_dig_port->max_lanes; + int sink_max = drm_dp_max_lane_count(intel_dp->dpcd); return min(source_max, sink_max); } +int intel_dp_max_lane_count(struct intel_dp *intel_dp) +{ + return intel_dp->max_link_lane_count; +} + int intel_dp_link_required(int pixel_clock, int bpp) { @@ -205,34 +224,25 @@ intel_dp_downstream_max_dotclock(struct intel_dp *intel_dp) return max_dotclk; } -static int -intel_dp_sink_rates(struct intel_dp *intel_dp, const int **sink_rates) -{ - if (intel_dp->num_sink_rates) { - *sink_rates = intel_dp->sink_rates; - return intel_dp->num_sink_rates; - } - - *sink_rates = default_rates; - - return (intel_dp->max_sink_link_bw >> 3) + 1; -} - -static int -intel_dp_source_rates(struct intel_dp *intel_dp, const int **source_rates) +static void +intel_dp_set_source_rates(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); + const int *source_rates; int size; + /* This should only be done once */ + WARN_ON(intel_dp->source_rates || intel_dp->num_source_rates); + if (IS_GEN9_LP(dev_priv)) { - *source_rates = bxt_rates; + source_rates = bxt_rates; size = ARRAY_SIZE(bxt_rates); } else if (IS_GEN9_BC(dev_priv)) { - *source_rates = skl_rates; + source_rates = skl_rates; size = ARRAY_SIZE(skl_rates); } else { - *source_rates = default_rates; + source_rates = default_rates; size = ARRAY_SIZE(default_rates); } @@ -240,7 +250,8 @@ intel_dp_source_rates(struct intel_dp *intel_dp, const int **source_rates) if (!intel_dp_source_supports_hbr2(intel_dp)) size--; - return size; + intel_dp->source_rates = source_rates; + intel_dp->num_source_rates = size; } static int intersect_rates(const int *source_rates, int source_len, @@ -266,50 +277,83 @@ static int intersect_rates(const int *source_rates, int source_len, return k; } -static int intel_dp_common_rates(struct intel_dp *intel_dp, - int *common_rates) +/* return index of rate in rates array, or -1 if not found */ +static int intel_dp_rate_index(const int *rates, int len, int rate) { - const int *source_rates, *sink_rates; - int source_len, sink_len; + int i; - sink_len = intel_dp_sink_rates(intel_dp, &sink_rates); - source_len = intel_dp_source_rates(intel_dp, &source_rates); + for (i = 0; i < len; i++) + if (rate == rates[i]) + return i; - return intersect_rates(source_rates, source_len, - sink_rates, sink_len, - common_rates); + return -1; } -static int intel_dp_link_rate_index(struct intel_dp *intel_dp, - int *common_rates, int link_rate) +static void intel_dp_set_common_rates(struct intel_dp *intel_dp) { - int common_len; - int index; + WARN_ON(!intel_dp->num_source_rates || !intel_dp->num_sink_rates); + + intel_dp->num_common_rates = intersect_rates(intel_dp->source_rates, + intel_dp->num_source_rates, + intel_dp->sink_rates, + intel_dp->num_sink_rates, + intel_dp->common_rates); + + /* Paranoia, there should always be something in common. */ + if (WARN_ON(intel_dp->num_common_rates == 0)) { + intel_dp->common_rates[0] = default_rates[0]; + intel_dp->num_common_rates = 1; + } +} - common_len = intel_dp_common_rates(intel_dp, common_rates); - for (index = 0; index < common_len; index++) { - if (link_rate == common_rates[common_len - index - 1]) - return common_len - index - 1; +/* get length of common rates potentially limited by max_rate */ +static int intel_dp_common_len_rate_limit(struct intel_dp *intel_dp, + int max_rate) +{ + const int *common_rates = intel_dp->common_rates; + int i, common_len = intel_dp->num_common_rates; + + /* Limit results by potentially reduced max rate */ + for (i = 0; i < common_len; i++) { + if (common_rates[common_len - i - 1] <= max_rate) + return common_len - i; } - return -1; + return 0; +} + +static bool intel_dp_link_params_valid(struct intel_dp *intel_dp) +{ + /* + * FIXME: we need to synchronize the current link parameters with + * hardware readout. Currently fast link training doesn't work on + * boot-up. + */ + if (intel_dp->link_rate == 0 || + intel_dp->link_rate > intel_dp->max_link_rate) + return false; + + if (intel_dp->lane_count == 0 || + intel_dp->lane_count > intel_dp_max_lane_count(intel_dp)) + return false; + + return true; } int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, int link_rate, uint8_t lane_count) { - int common_rates[DP_MAX_SUPPORTED_RATES]; - int link_rate_index; + int index; - link_rate_index = intel_dp_link_rate_index(intel_dp, - common_rates, - link_rate); - if (link_rate_index > 0) { - intel_dp->max_sink_link_bw = drm_dp_link_rate_to_bw_code(common_rates[link_rate_index - 1]); - intel_dp->max_sink_lane_count = lane_count; + index = intel_dp_rate_index(intel_dp->common_rates, + intel_dp->num_common_rates, + link_rate); + if (index > 0) { + intel_dp->max_link_rate = intel_dp->common_rates[index - 1]; + intel_dp->max_link_lane_count = lane_count; } else if (lane_count > 1) { - intel_dp->max_sink_link_bw = intel_dp_max_link_bw(intel_dp); - intel_dp->max_sink_lane_count = lane_count >> 1; + intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); + intel_dp->max_link_lane_count = lane_count >> 1; } else { DRM_ERROR("Link Training Unsuccessful\n"); return -1; @@ -1486,24 +1530,21 @@ static void snprintf_int_array(char *str, size_t len, static void intel_dp_print_rates(struct intel_dp *intel_dp) { - const int *source_rates, *sink_rates; - int source_len, sink_len, common_len; - int common_rates[DP_MAX_SUPPORTED_RATES]; char str[128]; /* FIXME: too big for stack? */ if ((drm_debug & DRM_UT_KMS) == 0) return; - source_len = intel_dp_source_rates(intel_dp, &source_rates); - snprintf_int_array(str, sizeof(str), source_rates, source_len); + snprintf_int_array(str, sizeof(str), + intel_dp->source_rates, intel_dp->num_source_rates); DRM_DEBUG_KMS("source rates: %s\n", str); - sink_len = intel_dp_sink_rates(intel_dp, &sink_rates); - snprintf_int_array(str, sizeof(str), sink_rates, sink_len); + snprintf_int_array(str, sizeof(str), + intel_dp->sink_rates, intel_dp->num_sink_rates); DRM_DEBUG_KMS("sink rates: %s\n", str); - common_len = intel_dp_common_rates(intel_dp, common_rates); - snprintf_int_array(str, sizeof(str), common_rates, common_len); + snprintf_int_array(str, sizeof(str), + intel_dp->common_rates, intel_dp->num_common_rates); DRM_DEBUG_KMS("common rates: %s\n", str); } @@ -1538,39 +1579,34 @@ bool intel_dp_read_desc(struct intel_dp *intel_dp) return true; } -static int rate_to_index(int find, const int *rates) -{ - int i = 0; - - for (i = 0; i < DP_MAX_SUPPORTED_RATES; ++i) - if (find == rates[i]) - break; - - return i; -} - int intel_dp_max_link_rate(struct intel_dp *intel_dp) { - int rates[DP_MAX_SUPPORTED_RATES] = {}; int len; - len = intel_dp_common_rates(intel_dp, rates); + len = intel_dp_common_len_rate_limit(intel_dp, intel_dp->max_link_rate); if (WARN_ON(len <= 0)) return 162000; - return rates[len - 1]; + return intel_dp->common_rates[len - 1]; } int intel_dp_rate_select(struct intel_dp *intel_dp, int rate) { - return rate_to_index(rate, intel_dp->sink_rates); + int i = intel_dp_rate_index(intel_dp->sink_rates, + intel_dp->num_sink_rates, rate); + + if (WARN_ON(i < 0)) + i = 0; + + return i; } void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, uint8_t *link_bw, uint8_t *rate_select) { - if (intel_dp->num_sink_rates) { + /* eDP 1.4 rate select method. */ + if (intel_dp->use_rate_select) { *link_bw = 0; *rate_select = intel_dp_rate_select(intel_dp, port_clock); @@ -1612,20 +1648,21 @@ intel_dp_compute_config(struct intel_encoder *encoder, enum port port = dp_to_dig_port(intel_dp)->port; struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc); struct intel_connector *intel_connector = intel_dp->attached_connector; + struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(conn_state); int lane_count, clock; int min_lane_count = 1; int max_lane_count = intel_dp_max_lane_count(intel_dp); /* Conveniently, the link BW constants become indices with a shift...*/ int min_clock = 0; int max_clock; - int link_rate_index; int bpp, mode_rate; int link_avail, link_clock; - int common_rates[DP_MAX_SUPPORTED_RATES] = {}; int common_len; uint8_t link_bw, rate_select; - common_len = intel_dp_common_rates(intel_dp, common_rates); + common_len = intel_dp_common_len_rate_limit(intel_dp, + intel_dp->max_link_rate); /* No common link rates between source and sink */ WARN_ON(common_len <= 0); @@ -1636,7 +1673,12 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; pipe_config->has_drrs = false; - pipe_config->has_audio = intel_dp->has_audio && port != PORT_A; + if (port == PORT_A) + pipe_config->has_audio = false; + else if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) + pipe_config->has_audio = intel_dp->has_audio; + else + pipe_config->has_audio = intel_conn_state->force_audio == HDMI_AUDIO_ON; if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) { intel_fixed_panel_mode(intel_connector->panel.fixed_mode, @@ -1651,10 +1693,10 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (HAS_GMCH_DISPLAY(dev_priv)) intel_gmch_panel_fitting(intel_crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); else intel_pch_panel_fitting(intel_crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); } if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) @@ -1662,16 +1704,18 @@ intel_dp_compute_config(struct intel_encoder *encoder, /* Use values requested by Compliance Test Request */ if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) { - link_rate_index = intel_dp_link_rate_index(intel_dp, - common_rates, - intel_dp->compliance.test_link_rate); - if (link_rate_index >= 0) - min_clock = max_clock = link_rate_index; + int index; + + index = intel_dp_rate_index(intel_dp->common_rates, + intel_dp->num_common_rates, + intel_dp->compliance.test_link_rate); + if (index >= 0) + min_clock = max_clock = index; min_lane_count = max_lane_count = intel_dp->compliance.test_lane_count; } DRM_DEBUG_KMS("DP link computation with max lane count %i " "max bw %d pixel clock %iKHz\n", - max_lane_count, common_rates[max_clock], + max_lane_count, intel_dp->common_rates[max_clock], adjusted_mode->crtc_clock); /* Walk through all bpp values. Luckily they're all nicely spaced with 2 @@ -1707,7 +1751,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, lane_count <= max_lane_count; lane_count <<= 1) { - link_clock = common_rates[clock]; + link_clock = intel_dp->common_rates[clock]; link_avail = intel_dp_max_data_rate(link_clock, lane_count); @@ -1721,7 +1765,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, return false; found: - if (intel_dp->color_range_auto) { + if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) { /* * See: * CEA-861-E - 5.1 Default Encoding Parameters @@ -1733,13 +1777,13 @@ intel_dp_compute_config(struct intel_encoder *encoder, HDMI_QUANTIZATION_RANGE_LIMITED; } else { pipe_config->limited_color_range = - intel_dp->limited_color_range; + intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED; } pipe_config->lane_count = lane_count; pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = common_rates[clock]; + pipe_config->port_clock = intel_dp->common_rates[clock]; intel_dp_compute_rate(intel_dp, pipe_config->port_clock, &link_bw, &rate_select); @@ -3051,7 +3095,8 @@ static bool intel_dp_get_y_cord_status(struct intel_dp *intel_dp) { uint8_t psr_caps = 0; - drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_CAPS, &psr_caps); + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_CAPS, &psr_caps) != 1) + return false; return psr_caps & DP_PSR2_SU_Y_COORDINATE_REQUIRED; } @@ -3059,9 +3104,9 @@ static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) { uint8_t dprx = 0; - drm_dp_dpcd_readb(&intel_dp->aux, - DP_DPRX_FEATURE_ENUMERATION_LIST, - &dprx); + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_DPRX_FEATURE_ENUMERATION_LIST, + &dprx) != 1) + return false; return dprx & DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED; } @@ -3069,7 +3114,9 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp) { uint8_t alpm_caps = 0; - drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, &alpm_caps); + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, + &alpm_caps) != 1) + return false; return alpm_caps & DP_ALPM_CAP; } @@ -3642,9 +3689,10 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) uint8_t frame_sync_cap; dev_priv->psr.sink_support = true; - drm_dp_dpcd_read(&intel_dp->aux, - DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP, - &frame_sync_cap, 1); + if (drm_dp_dpcd_readb(&intel_dp->aux, + DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP, + &frame_sync_cap) != 1) + frame_sync_cap = 0; dev_priv->psr.aux_frame_sync = frame_sync_cap ? true : false; /* PSR2 needs frame sync as well */ dev_priv->psr.psr2_support = dev_priv->psr.aux_frame_sync; @@ -3695,6 +3743,13 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) intel_dp->num_sink_rates = i; } + if (intel_dp->num_sink_rates) + intel_dp->use_rate_select = true; + else + intel_dp_set_sink_rates(intel_dp); + + intel_dp_set_common_rates(intel_dp); + return true; } @@ -3702,11 +3757,18 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) static bool intel_dp_get_dpcd(struct intel_dp *intel_dp) { + u8 sink_count; + if (!intel_dp_read_dpcd(intel_dp)) return false; - if (drm_dp_dpcd_read(&intel_dp->aux, DP_SINK_COUNT, - &intel_dp->sink_count, 1) < 0) + /* Don't clobber cached eDP rates. */ + if (!is_edp(intel_dp)) { + intel_dp_set_sink_rates(intel_dp); + intel_dp_set_common_rates(intel_dp); + } + + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_COUNT, &sink_count) <= 0) return false; /* @@ -3714,7 +3776,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) * a member variable in intel_dp will track any changes * between short pulse interrupts. */ - intel_dp->sink_count = DP_GET_SINK_COUNT(intel_dp->sink_count); + intel_dp->sink_count = DP_GET_SINK_COUNT(sink_count); /* * SINK_COUNT == 0 and DOWNSTREAM_PORT_PRESENT == 1 implies that @@ -3743,7 +3805,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) static bool intel_dp_can_mst(struct intel_dp *intel_dp) { - u8 buf[1]; + u8 mstm_cap; if (!i915.enable_dp_mst) return false; @@ -3754,10 +3816,10 @@ intel_dp_can_mst(struct intel_dp *intel_dp) if (intel_dp->dpcd[DP_DPCD_REV] < 0x12) return false; - if (drm_dp_dpcd_read(&intel_dp->aux, DP_MSTM_CAP, buf, 1) != 1) + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_MSTM_CAP, &mstm_cap) != 1) return false; - return buf[0] & DP_MST_CAP; + return mstm_cap & DP_MST_CAP; } static void @@ -3903,9 +3965,8 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc) static bool intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector) { - return drm_dp_dpcd_read(&intel_dp->aux, - DP_DEVICE_SERVICE_IRQ_VECTOR, - sink_irq_vector, 1) == 1; + return drm_dp_dpcd_readb(&intel_dp->aux, DP_DEVICE_SERVICE_IRQ_VECTOR, + sink_irq_vector) == 1; } static bool @@ -3926,7 +3987,6 @@ static uint8_t intel_dp_autotest_link_training(struct intel_dp *intel_dp) { int status = 0; int min_lane_count = 1; - int common_rates[DP_MAX_SUPPORTED_RATES] = {}; int link_rate_index, test_link_rate; uint8_t test_lane_count, test_link_bw; /* (DP CTS 1.2) @@ -3943,7 +4003,7 @@ static uint8_t intel_dp_autotest_link_training(struct intel_dp *intel_dp) test_lane_count &= DP_MAX_LANE_COUNT_MASK; /* Validate the requested lane count */ if (test_lane_count < min_lane_count || - test_lane_count > intel_dp->max_sink_lane_count) + test_lane_count > intel_dp->max_link_lane_count) return DP_TEST_NAK; status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_LINK_RATE, @@ -3954,9 +4014,9 @@ static uint8_t intel_dp_autotest_link_training(struct intel_dp *intel_dp) } /* Validate the requested link rate */ test_link_rate = drm_dp_bw_code_to_link_rate(test_link_bw); - link_rate_index = intel_dp_link_rate_index(intel_dp, - common_rates, - test_link_rate); + link_rate_index = intel_dp_rate_index(intel_dp->common_rates, + intel_dp->num_common_rates, + test_link_rate); if (link_rate_index < 0) return DP_TEST_NAK; @@ -3969,13 +4029,13 @@ static uint8_t intel_dp_autotest_link_training(struct intel_dp *intel_dp) static uint8_t intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) { uint8_t test_pattern; - uint16_t test_misc; + uint8_t test_misc; __be16 h_width, v_height; int status = 0; /* Read the TEST_PATTERN (DP CTS 3.1.5) */ - status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_PATTERN, - &test_pattern, 1); + status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_PATTERN, + &test_pattern); if (status <= 0) { DRM_DEBUG_KMS("Test pattern read failed\n"); return DP_TEST_NAK; @@ -3997,8 +4057,8 @@ static uint8_t intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) return DP_TEST_NAK; } - status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_MISC0, - &test_misc, 1); + status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_MISC0, + &test_misc); if (status <= 0) { DRM_DEBUG_KMS("TEST MISC read failed\n"); return DP_TEST_NAK; @@ -4057,10 +4117,8 @@ static uint8_t intel_dp_autotest_edid(struct intel_dp *intel_dp) */ block += intel_connector->detect_edid->extensions; - if (!drm_dp_dpcd_write(&intel_dp->aux, - DP_TEST_EDID_CHECKSUM, - &block->checksum, - 1)) + if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_EDID_CHECKSUM, + block->checksum) <= 0) DRM_DEBUG_KMS("Failed to write EDID checksum\n"); test_result = DP_TEST_ACK | DP_TEST_EDID_CHECKSUM_WRITE; @@ -4224,9 +4282,11 @@ intel_dp_check_link_status(struct intel_dp *intel_dp) if (!to_intel_crtc(intel_encoder->base.crtc)->active) return; - /* FIXME: we need to synchronize this sort of stuff with hardware - * readout. Currently fast link training doesn't work on boot-up. */ - if (!intel_dp->lane_count) + /* + * Validate the cached values of intel_dp->link_rate and + * intel_dp->lane_count before attempting to retrain. + */ + if (!intel_dp_link_params_valid(intel_dp)) return; /* Retrain if Channel EQ or CR not ok */ @@ -4549,10 +4609,7 @@ intel_dp_set_edid(struct intel_dp *intel_dp) edid = intel_dp_get_edid(intel_dp); intel_connector->detect_edid = edid; - if (intel_dp->force_audio != HDMI_AUDIO_AUTO) - intel_dp->has_audio = intel_dp->force_audio == HDMI_AUDIO_ON; - else - intel_dp->has_audio = drm_detect_monitor_audio(edid); + intel_dp->has_audio = drm_detect_monitor_audio(edid); } static void @@ -4613,11 +4670,11 @@ intel_dp_long_pulse(struct intel_connector *intel_connector) yesno(drm_dp_tps3_supported(intel_dp->dpcd))); if (intel_dp->reset_link_params) { - /* Set the max lane count for sink */ - intel_dp->max_sink_lane_count = drm_dp_max_lane_count(intel_dp->dpcd); + /* Initial max link lane count */ + intel_dp->max_link_lane_count = intel_dp_max_common_lane_count(intel_dp); - /* Set the max link BW for sink */ - intel_dp->max_sink_link_bw = intel_dp_max_link_bw(intel_dp); + /* Initial max link rate */ + intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); intel_dp->reset_link_params = false; } @@ -4760,112 +4817,6 @@ static int intel_dp_get_modes(struct drm_connector *connector) return 0; } -static bool -intel_dp_detect_audio(struct drm_connector *connector) -{ - bool has_audio = false; - struct edid *edid; - - edid = to_intel_connector(connector)->detect_edid; - if (edid) - has_audio = drm_detect_monitor_audio(edid); - - return has_audio; -} - -static int -intel_dp_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t val) -{ - struct drm_i915_private *dev_priv = to_i915(connector->dev); - struct intel_connector *intel_connector = to_intel_connector(connector); - struct intel_encoder *intel_encoder = intel_attached_encoder(connector); - struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); - int ret; - - ret = drm_object_property_set_value(&connector->base, property, val); - if (ret) - return ret; - - if (property == dev_priv->force_audio_property) { - int i = val; - bool has_audio; - - if (i == intel_dp->force_audio) - return 0; - - intel_dp->force_audio = i; - - if (i == HDMI_AUDIO_AUTO) - has_audio = intel_dp_detect_audio(connector); - else - has_audio = (i == HDMI_AUDIO_ON); - - if (has_audio == intel_dp->has_audio) - return 0; - - intel_dp->has_audio = has_audio; - goto done; - } - - if (property == dev_priv->broadcast_rgb_property) { - bool old_auto = intel_dp->color_range_auto; - bool old_range = intel_dp->limited_color_range; - - switch (val) { - case INTEL_BROADCAST_RGB_AUTO: - intel_dp->color_range_auto = true; - break; - case INTEL_BROADCAST_RGB_FULL: - intel_dp->color_range_auto = false; - intel_dp->limited_color_range = false; - break; - case INTEL_BROADCAST_RGB_LIMITED: - intel_dp->color_range_auto = false; - intel_dp->limited_color_range = true; - break; - default: - return -EINVAL; - } - - if (old_auto == intel_dp->color_range_auto && - old_range == intel_dp->limited_color_range) - return 0; - - goto done; - } - - if (is_edp(intel_dp) && - property == connector->dev->mode_config.scaling_mode_property) { - if (val == DRM_MODE_SCALE_NONE) { - DRM_DEBUG_KMS("no scaling not supported\n"); - return -EINVAL; - } - if (HAS_GMCH_DISPLAY(dev_priv) && - val == DRM_MODE_SCALE_CENTER) { - DRM_DEBUG_KMS("centering not supported\n"); - return -EINVAL; - } - - if (intel_connector->panel.fitting_mode == val) { - /* the eDP scaling property is not changed */ - return 0; - } - intel_connector->panel.fitting_mode = val; - - goto done; - } - - return -EINVAL; - -done: - if (intel_encoder->base.crtc) - intel_crtc_restore_mode(intel_encoder->base.crtc); - - return 0; -} - static int intel_dp_connector_register(struct drm_connector *connector) { @@ -5024,19 +4975,21 @@ static const struct drm_connector_funcs intel_dp_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .force = intel_dp_force, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_dp_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, + .atomic_get_property = intel_digital_connector_atomic_get_property, + .atomic_set_property = intel_digital_connector_atomic_set_property, .late_register = intel_dp_connector_register, .early_unregister = intel_dp_connector_unregister, .destroy = intel_dp_connector_destroy, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_duplicate_state = intel_digital_connector_duplicate_state, }; static const struct drm_connector_helper_funcs intel_dp_connector_helper_funcs = { .detect_ctx = intel_dp_detect, .get_modes = intel_dp_get_modes, .mode_valid = intel_dp_mode_valid, + .atomic_check = intel_digital_connector_atomic_check, }; static const struct drm_encoder_funcs intel_dp_enc_funcs = { @@ -5127,22 +5080,25 @@ bool intel_dp_is_edp(struct drm_i915_private *dev_priv, enum port port) return intel_bios_is_port_edp(dev_priv, port); } -void +static void intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector) { - struct intel_connector *intel_connector = to_intel_connector(connector); + struct drm_i915_private *dev_priv = to_i915(connector->dev); intel_attach_force_audio_property(connector); intel_attach_broadcast_rgb_property(connector); - intel_dp->color_range_auto = true; if (is_edp(intel_dp)) { - drm_mode_create_scaling_mode_property(connector->dev); - drm_object_attach_property( - &connector->base, - connector->dev->mode_config.scaling_mode_property, - DRM_MODE_SCALE_ASPECT); - intel_connector->panel.fitting_mode = DRM_MODE_SCALE_ASPECT; + u32 allowed_scalers; + + allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); + if (!HAS_GMCH_DISPLAY(dev_priv)) + allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); + + drm_connector_attach_scaling_mode_property(connector, allowed_scalers); + + connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT; + } } @@ -5932,6 +5888,29 @@ intel_dp_init_connector_port_info(struct intel_digital_port *intel_dig_port) } } +static void intel_dp_modeset_retry_work_fn(struct work_struct *work) +{ + struct intel_connector *intel_connector; + struct drm_connector *connector; + + intel_connector = container_of(work, typeof(*intel_connector), + modeset_retry_work); + connector = &intel_connector->base; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, + connector->name); + + /* Grab the locks before changing connector property*/ + mutex_lock(&connector->dev->mode_config.mutex); + /* Set connector link status to BAD and send a Uevent to notify + * userspace to do a modeset. + */ + drm_mode_connector_set_link_status_property(connector, + DRM_MODE_LINK_STATUS_BAD); + mutex_unlock(&connector->dev->mode_config.mutex); + /* Send Hotplug uevent so userspace can reprobe */ + drm_kms_helper_hotplug_event(connector->dev); +} + bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port, struct intel_connector *intel_connector) @@ -5944,11 +5923,17 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; int type; + /* Initialize the work for modeset in case of link train failure */ + INIT_WORK(&intel_connector->modeset_retry_work, + intel_dp_modeset_retry_work_fn); + if (WARN(intel_dig_port->max_lanes < 1, "Not enough lanes (%d) for DP on port %c\n", intel_dig_port->max_lanes, port_name(port))) return false; + intel_dp_set_source_rates(intel_dp); + intel_dp->reset_link_params = true; intel_dp->pps_pipe = INVALID_PIPE; intel_dp->active_pipe = INVALID_PIPE; diff --git a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c index 6532e226db29b6..a0995c00fc84ea 100644 --- a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c @@ -28,6 +28,10 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) { uint8_t reg_val = 0; + /* Early return when display use other mechanism to enable backlight. */ + if (!(intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP)) + return; + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER, ®_val) < 0) { DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n", @@ -97,15 +101,37 @@ static void intel_dp_aux_enable_backlight(struct intel_connector *connector) { struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base); uint8_t dpcd_buf = 0; + uint8_t edp_backlight_mode = 0; - set_aux_backlight_enable(intel_dp, true); + if (drm_dp_dpcd_readb(&intel_dp->aux, + DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) { + DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n", + DP_EDP_BACKLIGHT_MODE_SET_REGISTER); + return; + } + + edp_backlight_mode = dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK; + + switch (edp_backlight_mode) { + case DP_EDP_BACKLIGHT_CONTROL_MODE_PWM: + case DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET: + case DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT: + dpcd_buf &= ~DP_EDP_BACKLIGHT_CONTROL_MODE_MASK; + dpcd_buf |= DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; + if (drm_dp_dpcd_writeb(&intel_dp->aux, + DP_EDP_BACKLIGHT_MODE_SET_REGISTER, dpcd_buf) < 0) { + DRM_DEBUG_KMS("Failed to write aux backlight mode\n"); + } + break; + + /* Do nothing when it is already DPCD mode */ + case DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD: + default: + break; + } - if ((drm_dp_dpcd_readb(&intel_dp->aux, - DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) == 1) && - ((dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) == - DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET)) - drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, - (dpcd_buf | DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD)); + set_aux_backlight_enable(intel_dp, true); + intel_dp_aux_set_backlight(connector, connector->panel.backlight.level); } static void intel_dp_aux_disable_backlight(struct intel_connector *connector) @@ -143,9 +169,8 @@ intel_dp_aux_display_control_capable(struct intel_connector *connector) * the panel can support backlight control over the aux channel */ if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP && - (intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) && - !((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_PIN_ENABLE_CAP) || - (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP))) { + (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP) && + !(intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP)) { DRM_DEBUG_KMS("AUX Backlight Control Supported!\n"); return true; } diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c index 0048b520baf7c7..b79c1c0e404cc3 100644 --- a/drivers/gpu/drm/i915/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/intel_dp_link_training.c @@ -146,7 +146,8 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); - if (intel_dp->num_sink_rates) + /* eDP 1.4 rate select method. */ + if (!link_bw) drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, &rate_select, 1); @@ -313,6 +314,24 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp) void intel_dp_start_link_train(struct intel_dp *intel_dp) { - intel_dp_link_training_clock_recovery(intel_dp); - intel_dp_link_training_channel_equalization(intel_dp); + struct intel_connector *intel_connector = intel_dp->attached_connector; + + if (!intel_dp_link_training_clock_recovery(intel_dp)) + goto failure_handling; + if (!intel_dp_link_training_channel_equalization(intel_dp)) + goto failure_handling; + + DRM_DEBUG_KMS("Link Training Passed at Link Rate = %d, Lane count = %d", + intel_dp->link_rate, intel_dp->lane_count); + return; + + failure_handling: + DRM_DEBUG_KMS("Link Training failed at link rate = %d, lane count = %d", + intel_dp->link_rate, intel_dp->lane_count); + if (!intel_dp_get_link_train_fallback_values(intel_dp, + intel_dp->link_rate, + intel_dp->lane_count)) + /* Schedule a Hotplug Uevent to userspace to start modeset */ + schedule_work(&intel_connector->modeset_retry_work); + return; } diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index c1f62eb07c07a7..3715386e427270 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -39,7 +39,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, struct intel_dp *intel_dp = &intel_dig_port->dp; struct intel_connector *connector = to_intel_connector(conn_state->connector); - struct drm_atomic_state *state; + struct drm_atomic_state *state = pipe_config->base.state; int bpp; int lane_count, slots; const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; @@ -56,21 +56,26 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, * for MST we always configure max link bw - the spec doesn't * seem to suggest we should do otherwise. */ - lane_count = drm_dp_max_lane_count(intel_dp->dpcd); + lane_count = intel_dp_max_lane_count(intel_dp); pipe_config->lane_count = lane_count; pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = intel_dp_max_link_rate(intel_dp); - state = pipe_config->base.state; + pipe_config->port_clock = intel_dp_max_link_rate(intel_dp); if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, connector->port)) pipe_config->has_audio = true; - mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp); + mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp); pipe_config->pbn = mst_pbn; - slots = drm_dp_find_vcpi_slots(&intel_dp->mst_mgr, mst_pbn); + + slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr, + connector->port, mst_pbn); + if (slots < 0) { + DRM_DEBUG_KMS("failed finding vcpi slots:%d\n", slots); + return false; + } intel_link_compute_m_n(bpp, lane_count, adjusted_mode->crtc_clock, @@ -80,7 +85,38 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, pipe_config->dp_m_n.tu = slots; return true; +} + +static int intel_dp_mst_atomic_check(struct drm_connector *connector, + struct drm_connector_state *new_conn_state) +{ + struct drm_atomic_state *state = new_conn_state->state; + struct drm_connector_state *old_conn_state; + struct drm_crtc *old_crtc; + struct drm_crtc_state *crtc_state; + int slots, ret = 0; + + old_conn_state = drm_atomic_get_old_connector_state(state, connector); + old_crtc = old_conn_state->crtc; + if (!old_crtc) + return ret; + + crtc_state = drm_atomic_get_new_crtc_state(state, old_crtc); + slots = to_intel_crtc_state(crtc_state)->dp_m_n.tu; + if (drm_atomic_crtc_needs_modeset(crtc_state) && slots > 0) { + struct drm_dp_mst_topology_mgr *mgr; + struct drm_encoder *old_encoder; + + old_encoder = old_conn_state->best_encoder; + mgr = &enc_to_mst(old_encoder)->primary->dp.mst_mgr; + ret = drm_dp_atomic_release_vcpi_slots(state, mgr, slots); + if (ret) + DRM_DEBUG_KMS("failed releasing %d vcpi slots:%d\n", slots, ret); + else + to_intel_crtc_state(crtc_state)->dp_m_n.tu = 0; + } + return ret; } static void intel_mst_disable_dp(struct intel_encoder *encoder, @@ -294,14 +330,6 @@ intel_dp_mst_detect(struct drm_connector *connector, bool force) return drm_dp_mst_detect_port(connector, &intel_dp->mst_mgr, intel_connector->port); } -static int -intel_dp_mst_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t val) -{ - return 0; -} - static void intel_dp_mst_connector_destroy(struct drm_connector *connector) { @@ -318,8 +346,7 @@ static const struct drm_connector_funcs intel_dp_mst_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .detect = intel_dp_mst_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_dp_mst_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_dp_mst_connector_destroy, @@ -343,7 +370,7 @@ intel_dp_mst_mode_valid(struct drm_connector *connector, int max_rate, mode_rate, max_lanes, max_link_clock; max_link_clock = intel_dp_max_link_rate(intel_dp); - max_lanes = drm_dp_max_lane_count(intel_dp->dpcd); + max_lanes = intel_dp_max_lane_count(intel_dp); max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes); mode_rate = intel_dp_link_required(mode->clock, bpp); @@ -387,6 +414,7 @@ static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_fun .mode_valid = intel_dp_mst_mode_valid, .atomic_best_encoder = intel_mst_atomic_best_encoder, .best_encoder = intel_mst_best_encoder, + .atomic_check = intel_dp_mst_atomic_check, }; static void intel_dp_mst_encoder_destroy(struct drm_encoder *encoder) @@ -459,7 +487,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo drm_mode_connector_attach_encoder(&intel_connector->base, &intel_dp->mst_encoders[i]->base.base); } - intel_dp_add_properties(intel_dp, connector); drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index aaee3949a42267..ac5cd41ab4209a 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -88,7 +88,6 @@ int cpu, ret, timeout = (US) * 1000; \ u64 base; \ _WAIT_FOR_ATOMIC_CHECK(ATOMIC); \ - BUILD_BUG_ON((US) > 50000); \ if (!(ATOMIC)) { \ preempt_disable(); \ cpu = smp_processor_id(); \ @@ -130,8 +129,14 @@ ret__; \ }) -#define wait_for_atomic(COND, MS) _wait_for_atomic((COND), (MS) * 1000, 1) -#define wait_for_atomic_us(COND, US) _wait_for_atomic((COND), (US), 1) +#define wait_for_atomic_us(COND, US) \ +({ \ + BUILD_BUG_ON(!__builtin_constant_p(US)); \ + BUILD_BUG_ON((US) > 50000); \ + _wait_for_atomic((COND), (US), 1); \ +}) + +#define wait_for_atomic(COND, MS) wait_for_atomic_us((COND), (MS) * 1000) #define KHz(x) (1000 * (x)) #define MHz(x) KHz(1000 * (x)) @@ -261,7 +266,6 @@ struct intel_encoder { struct intel_panel { struct drm_display_mode *fixed_mode; struct drm_display_mode *downclock_mode; - int fitting_mode; /* backlight */ struct { @@ -321,8 +325,20 @@ struct intel_connector { void *port; /* store this opaque as its illegal to dereference it */ struct intel_dp *mst_port; + + /* Work struct to schedule a uevent on link train failure */ + struct work_struct modeset_retry_work; }; +struct intel_digital_connector_state { + struct drm_connector_state base; + + enum hdmi_force_audio force_audio; + int broadcast_rgb; +}; + +#define to_intel_digital_connector_state(x) container_of(x, struct intel_digital_connector_state, base) + struct dpll { /* given values */ int n; @@ -504,8 +520,8 @@ enum vlv_wm_level { }; struct vlv_wm_state { - struct vlv_pipe_wm wm[NUM_VLV_WM_LEVELS]; - struct vlv_sr_wm sr[NUM_VLV_WM_LEVELS]; + struct g4x_pipe_wm wm[NUM_VLV_WM_LEVELS]; + struct g4x_sr_wm sr[NUM_VLV_WM_LEVELS]; uint8_t num_levels; bool cxsr; }; @@ -514,6 +530,22 @@ struct vlv_fifo_state { u16 plane[I915_MAX_PLANES]; }; +enum g4x_wm_level { + G4X_WM_LEVEL_NORMAL, + G4X_WM_LEVEL_SR, + G4X_WM_LEVEL_HPLL, + NUM_G4X_WM_LEVELS, +}; + +struct g4x_wm_state { + struct g4x_pipe_wm wm; + struct g4x_sr_wm sr; + struct g4x_sr_wm hpll; + bool cxsr; + bool hpll_en; + bool fbc_en; +}; + struct intel_crtc_wm_state { union { struct { @@ -541,7 +573,7 @@ struct intel_crtc_wm_state { struct { /* "raw" watermarks (not inverted) */ - struct vlv_pipe_wm raw[NUM_VLV_WM_LEVELS]; + struct g4x_pipe_wm raw[NUM_VLV_WM_LEVELS]; /* intermediate watermarks (inverted) */ struct vlv_wm_state intermediate; /* optimal watermarks (inverted) */ @@ -549,6 +581,15 @@ struct intel_crtc_wm_state { /* display FIFO split */ struct vlv_fifo_state fifo_state; } vlv; + + struct { + /* "raw" watermarks */ + struct g4x_pipe_wm raw[NUM_G4X_WM_LEVELS]; + /* intermediate watermarks */ + struct g4x_wm_state intermediate; + /* optimal watermarks */ + struct g4x_wm_state optimal; + } g4x; }; /* @@ -766,11 +807,6 @@ struct intel_crtc { int adjusted_x; int adjusted_y; - uint32_t cursor_addr; - uint32_t cursor_cntl; - uint32_t cursor_size; - uint32_t cursor_base; - struct intel_crtc_state *config; /* global reset count when the last flip was submitted */ @@ -786,6 +822,7 @@ struct intel_crtc { union { struct intel_pipe_wm ilk; struct vlv_wm_state vlv; + struct g4x_wm_state g4x; } active; } wm; @@ -811,18 +848,22 @@ struct intel_plane { int max_downscale; uint32_t frontbuffer_bit; + struct { + u32 base, cntl, size; + } cursor; + /* * NOTE: Do not place new plane state fields here (e.g., when adding * new plane properties). New runtime state should now be placed in * the intel_plane_state structure and accessed via plane_state. */ - void (*update_plane)(struct drm_plane *plane, + void (*update_plane)(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); - void (*disable_plane)(struct drm_plane *plane, - struct drm_crtc *crtc); - int (*check_plane)(struct drm_plane *plane, + void (*disable_plane)(struct intel_plane *plane, + struct intel_crtc *crtc); + int (*check_plane)(struct intel_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state); }; @@ -863,13 +904,9 @@ struct intel_hdmi { enum drm_dp_dual_mode_type type; int max_tmds_clock; } dp_dual_mode; - bool limited_color_range; - bool color_range_auto; bool has_hdmi_sink; bool has_audio; - enum hdmi_force_audio force_audio; bool rgb_quant_range_selectable; - enum hdmi_picture_aspect aspect_ratio; struct intel_connector *attached_connector; void (*write_infoframe)(struct drm_encoder *encoder, const struct intel_crtc_state *crtc_state, @@ -942,20 +979,24 @@ struct intel_dp { bool detect_done; bool channel_eq_status; bool reset_link_params; - enum hdmi_force_audio force_audio; - bool limited_color_range; - bool color_range_auto; uint8_t dpcd[DP_RECEIVER_CAP_SIZE]; uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE]; uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; uint8_t edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]; - /* sink rates as reported by DP_SUPPORTED_LINK_RATES */ - uint8_t num_sink_rates; + /* source rates */ + int num_source_rates; + const int *source_rates; + /* sink rates as reported by DP_MAX_LINK_RATE/DP_SUPPORTED_LINK_RATES */ + int num_sink_rates; int sink_rates[DP_MAX_SUPPORTED_RATES]; - /* Max lane count for the sink as per DPCD registers */ - uint8_t max_sink_lane_count; - /* Max link BW for the sink as per DPCD registers */ - int max_sink_link_bw; + bool use_rate_select; + /* intersection of source and sink rates */ + int num_common_rates; + int common_rates[DP_MAX_SUPPORTED_RATES]; + /* Max lane count for the current link */ + int max_link_lane_count; + /* Max rate for the current link */ + int max_link_rate; /* sink or branch descriptor */ struct intel_dp_desc desc; struct drm_dp_aux aux; @@ -1308,7 +1349,6 @@ unsigned int intel_rotation_info_size(const struct intel_rotation_info *rot_info bool intel_has_pending_fb_unpin(struct drm_i915_private *dev_priv); void intel_mark_busy(struct drm_i915_private *dev_priv); void intel_mark_idle(struct drm_i915_private *dev_priv); -void intel_crtc_restore_mode(struct drm_crtc *crtc); int intel_display_suspend(struct drm_device *dev); void intel_pps_unlock_regs_wa(struct drm_i915_private *dev_priv); void intel_encoder_destroy(struct drm_encoder *encoder); @@ -1492,10 +1532,10 @@ void intel_edp_backlight_off(struct intel_dp *intel_dp); void intel_edp_panel_vdd_on(struct intel_dp *intel_dp); void intel_edp_panel_on(struct intel_dp *intel_dp); void intel_edp_panel_off(struct intel_dp *intel_dp); -void intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector); void intel_dp_mst_suspend(struct drm_device *dev); void intel_dp_mst_resume(struct drm_device *dev); int intel_dp_max_link_rate(struct intel_dp *intel_dp); +int intel_dp_max_lane_count(struct intel_dp *intel_dp); int intel_dp_rate_select(struct intel_dp *intel_dp, int rate); void intel_dp_hot_plug(struct intel_encoder *intel_encoder); void intel_power_sequencer_reset(struct drm_i915_private *dev_priv); @@ -1826,6 +1866,7 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv, struct intel_rps_client *rps, unsigned long submitted); void intel_queue_rps_boost_for_request(struct drm_i915_gem_request *req); +void g4x_wm_get_hw_state(struct drm_device *dev); void vlv_wm_get_hw_state(struct drm_device *dev); void ilk_wm_get_hw_state(struct drm_device *dev); void skl_wm_get_hw_state(struct drm_device *dev); @@ -1833,6 +1874,7 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc, struct skl_pipe_wm *out); +void g4x_wm_sanitize(struct drm_i915_private *dev_priv); void vlv_wm_sanitize(struct drm_i915_private *dev_priv); bool intel_can_enable_sagv(struct drm_atomic_state *state); int intel_enable_sagv(struct drm_i915_private *dev_priv); @@ -1844,6 +1886,8 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry **entries, int ignore); bool ilk_disable_lp_wm(struct drm_device *dev); int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6); +int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc, + struct intel_crtc_state *cstate); static inline int intel_enable_rc6(void) { return i915.enable_rc6; @@ -1868,10 +1912,19 @@ void intel_pipe_update_end(struct intel_crtc *crtc, struct intel_flip_work *work void intel_tv_init(struct drm_i915_private *dev_priv); /* intel_atomic.c */ -int intel_connector_atomic_get_property(struct drm_connector *connector, - const struct drm_connector_state *state, - struct drm_property *property, - uint64_t *val); +int intel_digital_connector_atomic_get_property(struct drm_connector *connector, + const struct drm_connector_state *state, + struct drm_property *property, + uint64_t *val); +int intel_digital_connector_atomic_set_property(struct drm_connector *connector, + struct drm_connector_state *state, + struct drm_property *property, + uint64_t val); +int intel_digital_connector_atomic_check(struct drm_connector *conn, + struct drm_connector_state *new_state); +struct drm_connector_state * +intel_digital_connector_duplicate_state(struct drm_connector *connector); + struct drm_crtc_state *intel_crtc_duplicate_state(struct drm_crtc *crtc); void intel_crtc_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *state); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index fc0ef492252ac7..54030b68406a7a 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -320,10 +320,10 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder, if (HAS_GMCH_DISPLAY(dev_priv)) intel_gmch_panel_fitting(crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); else intel_pch_panel_fitting(crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); } /* DSI uses short packets for sync events, so clear mode flags for DSI */ @@ -1587,48 +1587,6 @@ static int intel_dsi_get_modes(struct drm_connector *connector) return 1; } -static int intel_dsi_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t val) -{ - struct drm_device *dev = connector->dev; - struct intel_connector *intel_connector = to_intel_connector(connector); - struct drm_crtc *crtc; - int ret; - - ret = drm_object_property_set_value(&connector->base, property, val); - if (ret) - return ret; - - if (property == dev->mode_config.scaling_mode_property) { - if (val == DRM_MODE_SCALE_NONE) { - DRM_DEBUG_KMS("no scaling not supported\n"); - return -EINVAL; - } - if (HAS_GMCH_DISPLAY(to_i915(dev)) && - val == DRM_MODE_SCALE_CENTER) { - DRM_DEBUG_KMS("centering not supported\n"); - return -EINVAL; - } - - if (intel_connector->panel.fitting_mode == val) - return 0; - - intel_connector->panel.fitting_mode = val; - } - - crtc = connector->state->crtc; - if (crtc && crtc->state->enable) { - /* - * If the CRTC is enabled, the display will be changed - * according to the new panel fitting mode. - */ - intel_crtc_restore_mode(crtc); - } - - return 0; -} - static void intel_dsi_connector_destroy(struct drm_connector *connector) { struct intel_connector *intel_connector = to_intel_connector(connector); @@ -1657,6 +1615,7 @@ static const struct drm_encoder_funcs intel_dsi_funcs = { static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = { .get_modes = intel_dsi_get_modes, .mode_valid = intel_dsi_mode_valid, + .atomic_check = intel_digital_connector_atomic_check, }; static const struct drm_connector_funcs intel_dsi_connector_funcs = { @@ -1665,22 +1624,28 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = { .early_unregister = intel_connector_unregister, .destroy = intel_dsi_connector_destroy, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_dsi_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, + .atomic_get_property = intel_digital_connector_atomic_get_property, + .atomic_set_property = intel_digital_connector_atomic_set_property, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_duplicate_state = intel_digital_connector_duplicate_state, }; static void intel_dsi_add_properties(struct intel_connector *connector) { - struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = to_i915(connector->base.dev); if (connector->panel.fixed_mode) { - drm_mode_create_scaling_mode_property(dev); - drm_object_attach_property(&connector->base.base, - dev->mode_config.scaling_mode_property, - DRM_MODE_SCALE_ASPECT); - connector->panel.fitting_mode = DRM_MODE_SCALE_ASPECT; + u32 allowed_scalers; + + allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); + if (!HAS_GMCH_DISPLAY(dev_priv)) + allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); + + drm_connector_attach_scaling_mode_property(&connector->base, + allowed_scalers); + + connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT; } } diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c index 0dce7792643abb..7158c7ce9c0941 100644 --- a/drivers/gpu/drm/i915/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c @@ -694,8 +694,8 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id) clk_zero_cnt << 8 | prepare_cnt; /* - * LP to HS switch count = 4TLPX + PREP_COUNT * 2 + EXIT_ZERO_COUNT * 2 - * + 10UI + Extra Byte Count + * LP to HS switch count = 4TLPX + PREP_COUNT * mul + EXIT_ZERO_COUNT * + * mul + 10UI + Extra Byte Count * * HS to LP switch count = THS-TRAIL + 2TLPX + Extra Byte Count * Extra Byte Count is calculated according to number of lanes. @@ -708,8 +708,8 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id) /* B044 */ /* FIXME: * The comment above does not match with the code */ - lp_to_hs_switch = DIV_ROUND_UP(4 * tlpx_ui + prepare_cnt * 2 + - exit_zero_cnt * 2 + 10, 8); + lp_to_hs_switch = DIV_ROUND_UP(4 * tlpx_ui + prepare_cnt * mul + + exit_zero_cnt * mul + 10, 8); hs_to_lp_switch = DIV_ROUND_UP(mipi_config->ths_trail + 2 * tlpx_ui, 8); diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 6025839ed3b7b1..c1544a53095ddb 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -350,7 +350,7 @@ static const struct drm_connector_funcs intel_dvo_connector_funcs = { .early_unregister = intel_connector_unregister, .destroy = intel_dvo_destroy, .fill_modes = drm_helper_probe_single_connector_modes, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, }; diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 854e8e0c836bd2..bc38bd128b7693 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -26,69 +26,177 @@ #include "intel_ringbuffer.h" #include "intel_lrc.h" -static const struct engine_info { +/* Haswell does have the CXT_SIZE register however it does not appear to be + * valid. Now, docs explain in dwords what is in the context object. The full + * size is 70720 bytes, however, the power context and execlist context will + * never be saved (power context is stored elsewhere, and execlists don't work + * on HSW) - so the final size, including the extra state required for the + * Resource Streamer, is 66944 bytes, which rounds to 17 pages. + */ +#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) +/* Same as Haswell, but 72064 bytes now. */ +#define GEN8_CXT_TOTAL_SIZE (18 * PAGE_SIZE) + +#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE) +#define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE) + +#define GEN8_LR_CONTEXT_OTHER_SIZE ( 2 * PAGE_SIZE) + +struct engine_class_info { const char *name; - unsigned int exec_id; + int (*init_legacy)(struct intel_engine_cs *engine); + int (*init_execlists)(struct intel_engine_cs *engine); +}; + +static const struct engine_class_info intel_engine_classes[] = { + [RENDER_CLASS] = { + .name = "rcs", + .init_execlists = logical_render_ring_init, + .init_legacy = intel_init_render_ring_buffer, + }, + [COPY_ENGINE_CLASS] = { + .name = "bcs", + .init_execlists = logical_xcs_ring_init, + .init_legacy = intel_init_blt_ring_buffer, + }, + [VIDEO_DECODE_CLASS] = { + .name = "vcs", + .init_execlists = logical_xcs_ring_init, + .init_legacy = intel_init_bsd_ring_buffer, + }, + [VIDEO_ENHANCEMENT_CLASS] = { + .name = "vecs", + .init_execlists = logical_xcs_ring_init, + .init_legacy = intel_init_vebox_ring_buffer, + }, +}; + +struct engine_info { unsigned int hw_id; + unsigned int uabi_id; + u8 class; + u8 instance; u32 mmio_base; unsigned irq_shift; - int (*init_legacy)(struct intel_engine_cs *engine); - int (*init_execlists)(struct intel_engine_cs *engine); -} intel_engines[] = { +}; + +static const struct engine_info intel_engines[] = { [RCS] = { - .name = "rcs", .hw_id = RCS_HW, - .exec_id = I915_EXEC_RENDER, + .uabi_id = I915_EXEC_RENDER, + .class = RENDER_CLASS, + .instance = 0, .mmio_base = RENDER_RING_BASE, .irq_shift = GEN8_RCS_IRQ_SHIFT, - .init_execlists = logical_render_ring_init, - .init_legacy = intel_init_render_ring_buffer, }, [BCS] = { - .name = "bcs", .hw_id = BCS_HW, - .exec_id = I915_EXEC_BLT, + .uabi_id = I915_EXEC_BLT, + .class = COPY_ENGINE_CLASS, + .instance = 0, .mmio_base = BLT_RING_BASE, .irq_shift = GEN8_BCS_IRQ_SHIFT, - .init_execlists = logical_xcs_ring_init, - .init_legacy = intel_init_blt_ring_buffer, }, [VCS] = { - .name = "vcs", .hw_id = VCS_HW, - .exec_id = I915_EXEC_BSD, + .uabi_id = I915_EXEC_BSD, + .class = VIDEO_DECODE_CLASS, + .instance = 0, .mmio_base = GEN6_BSD_RING_BASE, .irq_shift = GEN8_VCS1_IRQ_SHIFT, - .init_execlists = logical_xcs_ring_init, - .init_legacy = intel_init_bsd_ring_buffer, }, [VCS2] = { - .name = "vcs2", .hw_id = VCS2_HW, - .exec_id = I915_EXEC_BSD, + .uabi_id = I915_EXEC_BSD, + .class = VIDEO_DECODE_CLASS, + .instance = 1, .mmio_base = GEN8_BSD2_RING_BASE, .irq_shift = GEN8_VCS2_IRQ_SHIFT, - .init_execlists = logical_xcs_ring_init, - .init_legacy = intel_init_bsd2_ring_buffer, }, [VECS] = { - .name = "vecs", .hw_id = VECS_HW, - .exec_id = I915_EXEC_VEBOX, + .uabi_id = I915_EXEC_VEBOX, + .class = VIDEO_ENHANCEMENT_CLASS, + .instance = 0, .mmio_base = VEBOX_RING_BASE, .irq_shift = GEN8_VECS_IRQ_SHIFT, - .init_execlists = logical_xcs_ring_init, - .init_legacy = intel_init_vebox_ring_buffer, }, }; +/** + * ___intel_engine_context_size() - return the size of the context for an engine + * @dev_priv: i915 device private + * @class: engine class + * + * Each engine class may require a different amount of space for a context + * image. + * + * Return: size (in bytes) of an engine class specific context image + * + * Note: this size includes the HWSP, which is part of the context image + * in LRC mode, but does not include the "shared data page" used with + * GuC submission. The caller should account for this if using the GuC. + */ +static u32 +__intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class) +{ + u32 cxt_size; + + BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE); + + switch (class) { + case RENDER_CLASS: + switch (INTEL_GEN(dev_priv)) { + default: + MISSING_CASE(INTEL_GEN(dev_priv)); + case 9: + return GEN9_LR_CONTEXT_RENDER_SIZE; + case 8: + return i915.enable_execlists ? + GEN8_LR_CONTEXT_RENDER_SIZE : + GEN8_CXT_TOTAL_SIZE; + case 7: + if (IS_HASWELL(dev_priv)) + return HSW_CXT_TOTAL_SIZE; + + cxt_size = I915_READ(GEN7_CXT_SIZE); + return round_up(GEN7_CXT_TOTAL_SIZE(cxt_size) * 64, + PAGE_SIZE); + case 6: + cxt_size = I915_READ(CXT_SIZE); + return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64, + PAGE_SIZE); + case 5: + case 4: + case 3: + case 2: + /* For the special day when i810 gets merged. */ + case 1: + return 0; + } + break; + default: + MISSING_CASE(class); + case VIDEO_DECODE_CLASS: + case VIDEO_ENHANCEMENT_CLASS: + case COPY_ENGINE_CLASS: + if (INTEL_GEN(dev_priv) < 8) + return 0; + return GEN8_LR_CONTEXT_OTHER_SIZE; + } +} + static int intel_engine_setup(struct drm_i915_private *dev_priv, enum intel_engine_id id) { const struct engine_info *info = &intel_engines[id]; + const struct engine_class_info *class_info; struct intel_engine_cs *engine; + GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes)); + class_info = &intel_engine_classes[info->class]; + GEM_BUG_ON(dev_priv->engine[id]); engine = kzalloc(sizeof(*engine), GFP_KERNEL); if (!engine) @@ -96,11 +204,20 @@ intel_engine_setup(struct drm_i915_private *dev_priv, engine->id = id; engine->i915 = dev_priv; - engine->name = info->name; - engine->exec_id = info->exec_id; + WARN_ON(snprintf(engine->name, sizeof(engine->name), "%s%u", + class_info->name, info->instance) >= + sizeof(engine->name)); + engine->uabi_id = info->uabi_id; engine->hw_id = engine->guc_id = info->hw_id; engine->mmio_base = info->mmio_base; engine->irq_shift = info->irq_shift; + engine->class = info->class; + engine->instance = info->instance; + + engine->context_size = __intel_engine_context_size(dev_priv, + engine->class); + if (WARN_ON(engine->context_size > BIT(20))) + engine->context_size = 0; /* Nothing to do here, execute in order of dependencies */ engine->schedule = NULL; @@ -112,18 +229,18 @@ intel_engine_setup(struct drm_i915_private *dev_priv, } /** - * intel_engines_init_early() - allocate the Engine Command Streamers + * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers * @dev_priv: i915 device private * * Return: non-zero if the initialization failed. */ -int intel_engines_init_early(struct drm_i915_private *dev_priv) +int intel_engines_init_mmio(struct drm_i915_private *dev_priv) { struct intel_device_info *device_info = mkwrite_device_info(dev_priv); - unsigned int ring_mask = INTEL_INFO(dev_priv)->ring_mask; - unsigned int mask = 0; + const unsigned int ring_mask = INTEL_INFO(dev_priv)->ring_mask; struct intel_engine_cs *engine; enum intel_engine_id id; + unsigned int mask = 0; unsigned int i; int err; @@ -150,6 +267,12 @@ int intel_engines_init_early(struct drm_i915_private *dev_priv) if (WARN_ON(mask != ring_mask)) device_info->ring_mask = mask; + /* We always presume we have at least RCS available for later probing */ + if (WARN_ON(!HAS_ENGINE(dev_priv, RCS))) { + err = -ENODEV; + goto cleanup; + } + device_info->num_rings = hweight32(mask); return 0; @@ -161,7 +284,7 @@ int intel_engines_init_early(struct drm_i915_private *dev_priv) } /** - * intel_engines_init() - allocate, populate and init the Engine Command Streamers + * intel_engines_init() - init the Engine Command Streamers * @dev_priv: i915 device private * * Return: non-zero if the initialization failed. @@ -175,12 +298,14 @@ int intel_engines_init(struct drm_i915_private *dev_priv) int err = 0; for_each_engine(engine, dev_priv, id) { + const struct engine_class_info *class_info = + &intel_engine_classes[engine->class]; int (*init)(struct intel_engine_cs *engine); if (i915.enable_execlists) - init = intel_engines[id].init_execlists; + init = class_info->init_execlists; else - init = intel_engines[id].init_legacy; + init = class_info->init_legacy; if (!init) { kfree(engine); dev_priv->engine[id] = NULL; @@ -223,6 +348,9 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno) { struct drm_i915_private *dev_priv = engine->i915; + GEM_BUG_ON(!intel_engine_is_idle(engine)); + GEM_BUG_ON(i915_gem_active_isset(&engine->timeline->last_request)); + /* Our semaphore implementation is strictly monotonic (i.e. we proceed * so long as the semaphore value in the register/page is greater * than the sync value), so whenever we reset the seqno, @@ -253,13 +381,12 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno) intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno); clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); - GEM_BUG_ON(i915_gem_active_isset(&engine->timeline->last_request)); - engine->hangcheck.seqno = seqno; - /* After manually advancing the seqno, fake the interrupt in case * there are any waiters for that seqno. */ intel_engine_wakeup(engine); + + GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno); } static void intel_engine_init_timeline(struct intel_engine_cs *engine) @@ -342,6 +469,7 @@ static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine) */ int intel_engine_init_common(struct intel_engine_cs *engine) { + struct intel_ring *ring; int ret; engine->set_default_submission(engine); @@ -353,9 +481,9 @@ int intel_engine_init_common(struct intel_engine_cs *engine) * be available. To avoid this we always pin the default * context. */ - ret = engine->context_pin(engine, engine->i915->kernel_context); - if (ret) - return ret; + ring = engine->context_pin(engine, engine->i915->kernel_context); + if (IS_ERR(ring)) + return PTR_ERR(ring); ret = intel_engine_init_breadcrumbs(engine); if (ret) @@ -723,8 +851,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) */ } + /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk */ /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, + GEN9_ENABLE_YV12_BUGFIX | GEN9_ENABLE_GPGPU_PREEMPTION); /* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk */ @@ -1075,6 +1205,27 @@ int intel_ring_workarounds_emit(struct drm_i915_gem_request *req) return 0; } +static bool ring_is_idle(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + bool idle = true; + + intel_runtime_pm_get(dev_priv); + + /* First check that no commands are left in the ring */ + if ((I915_READ_HEAD(engine) & HEAD_ADDR) != + (I915_READ_TAIL(engine) & TAIL_ADDR)) + idle = false; + + /* No bit for gen2, so assume the CS parser is idle */ + if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE)) + idle = false; + + intel_runtime_pm_put(dev_priv); + + return idle; +} + /** * intel_engine_is_idle() - Report if the engine has finished process all work * @engine: the intel_engine_cs @@ -1086,21 +1237,28 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + /* More white lies, if wedged, hw state is inconsistent */ + if (i915_terminally_wedged(&dev_priv->gpu_error)) + return true; + /* Any inflight/incomplete requests? */ if (!i915_seqno_passed(intel_engine_get_seqno(engine), intel_engine_last_submit(engine))) return false; + if (I915_SELFTEST_ONLY(engine->breadcrumbs.mock)) + return true; + /* Interrupt/tasklet pending? */ if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) return false; /* Both ports drained, no more ELSP submission? */ - if (engine->execlist_port[0].request) + if (port_request(&engine->execlist_port[0])) return false; /* Ring stopped? */ - if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE)) + if (!ring_is_idle(engine)) return false; return true; @@ -1137,6 +1295,18 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915) engine->set_default_submission(engine); } +void intel_engines_mark_idle(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, i915, id) { + intel_engine_disarm_breadcrumbs(engine); + i915_gem_batch_pool_fini(&engine->batch_pool); + engine->no_priolist = false; + } +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/mock_engine.c" #endif diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index ded2add18b2612..ff2fc5bc4af479 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -801,7 +801,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) return false; } if (INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv) && - cache->plane.rotation != DRM_ROTATE_0) { + cache->plane.rotation != DRM_MODE_ROTATE_0) { fbc->no_fbc_reason = "rotation unsupported"; return false; } @@ -1312,14 +1312,12 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) { -#ifdef CONFIG_INTEL_IOMMU /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ - if (intel_iommu_gfx_mapped && + if (intel_vtd_active() && (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) { DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); return true; } -#endif return false; } diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 332254a8eebe98..03347c6ae5993a 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -211,7 +211,7 @@ static int intelfb_create(struct drm_fb_helper *helper, * This also validates that any existing fb inherited from the * BIOS is suitable for own access. */ - vma = intel_pin_and_fence_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0); + vma = intel_pin_and_fence_fb_obj(&ifbdev->fb->base, DRM_MODE_ROTATE_0); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out_unlock; diff --git a/drivers/gpu/drm/i915/intel_guc_ct.c b/drivers/gpu/drm/i915/intel_guc_ct.c new file mode 100644 index 00000000000000..c4cbec140101b3 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_guc_ct.c @@ -0,0 +1,461 @@ +/* + * Copyright © 2016-2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#include "i915_drv.h" +#include "intel_guc_ct.h" + +enum { CTB_SEND = 0, CTB_RECV = 1 }; + +enum { CTB_OWNER_HOST = 0 }; + +void intel_guc_ct_init_early(struct intel_guc_ct *ct) +{ + /* we're using static channel owners */ + ct->host_channel.owner = CTB_OWNER_HOST; +} + +static inline const char *guc_ct_buffer_type_to_str(u32 type) +{ + switch (type) { + case INTEL_GUC_CT_BUFFER_TYPE_SEND: + return "SEND"; + case INTEL_GUC_CT_BUFFER_TYPE_RECV: + return "RECV"; + default: + return ""; + } +} + +static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc, + u32 cmds_addr, u32 size, u32 owner) +{ + DRM_DEBUG_DRIVER("CT: desc %p init addr=%#x size=%u owner=%u\n", + desc, cmds_addr, size, owner); + memset(desc, 0, sizeof(*desc)); + desc->addr = cmds_addr; + desc->size = size; + desc->owner = owner; +} + +static void guc_ct_buffer_desc_reset(struct guc_ct_buffer_desc *desc) +{ + DRM_DEBUG_DRIVER("CT: desc %p reset head=%u tail=%u\n", + desc, desc->head, desc->tail); + desc->head = 0; + desc->tail = 0; + desc->is_in_error = 0; +} + +static int guc_action_register_ct_buffer(struct intel_guc *guc, + u32 desc_addr, + u32 type) +{ + u32 action[] = { + INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER, + desc_addr, + sizeof(struct guc_ct_buffer_desc), + type + }; + int err; + + /* Can't use generic send(), CT registration must go over MMIO */ + err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action)); + if (err) + DRM_ERROR("CT: register %s buffer failed; err=%d\n", + guc_ct_buffer_type_to_str(type), err); + return err; +} + +static int guc_action_deregister_ct_buffer(struct intel_guc *guc, + u32 owner, + u32 type) +{ + u32 action[] = { + INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER, + owner, + type + }; + int err; + + /* Can't use generic send(), CT deregistration must go over MMIO */ + err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action)); + if (err) + DRM_ERROR("CT: deregister %s buffer failed; owner=%d err=%d\n", + guc_ct_buffer_type_to_str(type), owner, err); + return err; +} + +static bool ctch_is_open(struct intel_guc_ct_channel *ctch) +{ + return ctch->vma != NULL; +} + +static int ctch_init(struct intel_guc *guc, + struct intel_guc_ct_channel *ctch) +{ + struct i915_vma *vma; + void *blob; + int err; + int i; + + GEM_BUG_ON(ctch->vma); + + /* We allocate 1 page to hold both descriptors and both buffers. + * ___________..................... + * |desc (SEND)| : + * |___________| PAGE/4 + * :___________....................: + * |desc (RECV)| : + * |___________| PAGE/4 + * :_______________________________: + * |cmds (SEND) | + * | PAGE/4 + * |_______________________________| + * |cmds (RECV) | + * | PAGE/4 + * |_______________________________| + * + * Each message can use a maximum of 32 dwords and we don't expect to + * have more than 1 in flight at any time, so we have enough space. + * Some logic further ahead will rely on the fact that there is only 1 + * page and that it is always mapped, so if the size is changed the + * other code will need updating as well. + */ + + /* allocate vma */ + vma = intel_guc_allocate_vma(guc, PAGE_SIZE); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_out; + } + ctch->vma = vma; + + /* map first page */ + blob = i915_gem_object_pin_map(vma->obj, I915_MAP_WB); + if (IS_ERR(blob)) { + err = PTR_ERR(blob); + goto err_vma; + } + DRM_DEBUG_DRIVER("CT: vma base=%#x\n", guc_ggtt_offset(ctch->vma)); + + /* store pointers to desc and cmds */ + for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) { + GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV)); + ctch->ctbs[i].desc = blob + PAGE_SIZE/4 * i; + ctch->ctbs[i].cmds = blob + PAGE_SIZE/4 * i + PAGE_SIZE/2; + } + + return 0; + +err_vma: + i915_vma_unpin_and_release(&ctch->vma); +err_out: + DRM_DEBUG_DRIVER("CT: channel %d initialization failed; err=%d\n", + ctch->owner, err); + return err; +} + +static void ctch_fini(struct intel_guc *guc, + struct intel_guc_ct_channel *ctch) +{ + GEM_BUG_ON(!ctch->vma); + + i915_gem_object_unpin_map(ctch->vma->obj); + i915_vma_unpin_and_release(&ctch->vma); +} + +static int ctch_open(struct intel_guc *guc, + struct intel_guc_ct_channel *ctch) +{ + u32 base; + int err; + int i; + + DRM_DEBUG_DRIVER("CT: channel %d reopen=%s\n", + ctch->owner, yesno(ctch_is_open(ctch))); + + if (!ctch->vma) { + err = ctch_init(guc, ctch); + if (unlikely(err)) + goto err_out; + } + + /* vma should be already allocated and map'ed */ + base = guc_ggtt_offset(ctch->vma); + + /* (re)initialize descriptors + * cmds buffers are in the second half of the blob page + */ + for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) { + GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV)); + guc_ct_buffer_desc_init(ctch->ctbs[i].desc, + base + PAGE_SIZE/4 * i + PAGE_SIZE/2, + PAGE_SIZE/4, + ctch->owner); + } + + /* register buffers, starting wirh RECV buffer + * descriptors are in first half of the blob + */ + err = guc_action_register_ct_buffer(guc, + base + PAGE_SIZE/4 * CTB_RECV, + INTEL_GUC_CT_BUFFER_TYPE_RECV); + if (unlikely(err)) + goto err_fini; + + err = guc_action_register_ct_buffer(guc, + base + PAGE_SIZE/4 * CTB_SEND, + INTEL_GUC_CT_BUFFER_TYPE_SEND); + if (unlikely(err)) + goto err_deregister; + + return 0; + +err_deregister: + guc_action_deregister_ct_buffer(guc, + ctch->owner, + INTEL_GUC_CT_BUFFER_TYPE_RECV); +err_fini: + ctch_fini(guc, ctch); +err_out: + DRM_ERROR("CT: can't open channel %d; err=%d\n", ctch->owner, err); + return err; +} + +static void ctch_close(struct intel_guc *guc, + struct intel_guc_ct_channel *ctch) +{ + GEM_BUG_ON(!ctch_is_open(ctch)); + + guc_action_deregister_ct_buffer(guc, + ctch->owner, + INTEL_GUC_CT_BUFFER_TYPE_SEND); + guc_action_deregister_ct_buffer(guc, + ctch->owner, + INTEL_GUC_CT_BUFFER_TYPE_RECV); + ctch_fini(guc, ctch); +} + +static u32 ctch_get_next_fence(struct intel_guc_ct_channel *ctch) +{ + /* For now it's trivial */ + return ++ctch->next_fence; +} + +static int ctb_write(struct intel_guc_ct_buffer *ctb, + const u32 *action, + u32 len /* in dwords */, + u32 fence) +{ + struct guc_ct_buffer_desc *desc = ctb->desc; + u32 head = desc->head / 4; /* in dwords */ + u32 tail = desc->tail / 4; /* in dwords */ + u32 size = desc->size / 4; /* in dwords */ + u32 used; /* in dwords */ + u32 header; + u32 *cmds = ctb->cmds; + unsigned int i; + + GEM_BUG_ON(desc->size % 4); + GEM_BUG_ON(desc->head % 4); + GEM_BUG_ON(desc->tail % 4); + GEM_BUG_ON(tail >= size); + + /* + * tail == head condition indicates empty. GuC FW does not support + * using up the entire buffer to get tail == head meaning full. + */ + if (tail < head) + used = (size - head) + tail; + else + used = tail - head; + + /* make sure there is a space including extra dw for the fence */ + if (unlikely(used + len + 1 >= size)) + return -ENOSPC; + + /* Write the message. The format is the following: + * DW0: header (including action code) + * DW1: fence + * DW2+: action data + */ + header = (len << GUC_CT_MSG_LEN_SHIFT) | + (GUC_CT_MSG_WRITE_FENCE_TO_DESC) | + (action[0] << GUC_CT_MSG_ACTION_SHIFT); + + cmds[tail] = header; + tail = (tail + 1) % size; + + cmds[tail] = fence; + tail = (tail + 1) % size; + + for (i = 1; i < len; i++) { + cmds[tail] = action[i]; + tail = (tail + 1) % size; + } + + /* now update desc tail (back in bytes) */ + desc->tail = tail * 4; + GEM_BUG_ON(desc->tail > desc->size); + + return 0; +} + +/* Wait for the response from the GuC. + * @fence: response fence + * @status: placeholder for status + * return: 0 response received (status is valid) + * -ETIMEDOUT no response within hardcoded timeout + * -EPROTO no response, ct buffer was in error + */ +static int wait_for_response(struct guc_ct_buffer_desc *desc, + u32 fence, + u32 *status) +{ + int err; + + /* + * Fast commands should complete in less than 10us, so sample quickly + * up to that length of time, then switch to a slower sleep-wait loop. + * No GuC command should ever take longer than 10ms. + */ +#define done (READ_ONCE(desc->fence) == fence) + err = wait_for_us(done, 10); + if (err) + err = wait_for(done, 10); +#undef done + + if (unlikely(err)) { + DRM_ERROR("CT: fence %u failed; reported fence=%u\n", + fence, desc->fence); + + if (WARN_ON(desc->is_in_error)) { + /* Something went wrong with the messaging, try to reset + * the buffer and hope for the best + */ + guc_ct_buffer_desc_reset(desc); + err = -EPROTO; + } + } + + *status = desc->status; + return err; +} + +static int ctch_send(struct intel_guc *guc, + struct intel_guc_ct_channel *ctch, + const u32 *action, + u32 len, + u32 *status) +{ + struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_SEND]; + struct guc_ct_buffer_desc *desc = ctb->desc; + u32 fence; + int err; + + GEM_BUG_ON(!ctch_is_open(ctch)); + GEM_BUG_ON(!len); + GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK); + + fence = ctch_get_next_fence(ctch); + err = ctb_write(ctb, action, len, fence); + if (unlikely(err)) + return err; + + intel_guc_notify(guc); + + err = wait_for_response(desc, fence, status); + if (unlikely(err)) + return err; + if (*status != INTEL_GUC_STATUS_SUCCESS) + return -EIO; + return 0; +} + +/* + * Command Transport (CT) buffer based GuC send function. + */ +static int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len) +{ + struct intel_guc_ct_channel *ctch = &guc->ct.host_channel; + u32 status = ~0; /* undefined */ + int err; + + mutex_lock(&guc->send_mutex); + + err = ctch_send(guc, ctch, action, len, &status); + if (unlikely(err)) { + DRM_ERROR("CT: send action %#X failed; err=%d status=%#X\n", + action[0], err, status); + } + + mutex_unlock(&guc->send_mutex); + return err; +} + +/** + * Enable buffer based command transport + * Shall only be called for platforms with HAS_GUC_CT. + * @guc: the guc + * return: 0 on success + * non-zero on failure + */ +int intel_guc_enable_ct(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct intel_guc_ct_channel *ctch = &guc->ct.host_channel; + int err; + + GEM_BUG_ON(!HAS_GUC_CT(dev_priv)); + + err = ctch_open(guc, ctch); + if (unlikely(err)) + return err; + + /* Switch into cmd transport buffer based send() */ + guc->send = intel_guc_send_ct; + DRM_INFO("CT: %s\n", enableddisabled(true)); + return 0; +} + +/** + * Disable buffer based command transport. + * Shall only be called for platforms with HAS_GUC_CT. + * @guc: the guc + */ +void intel_guc_disable_ct(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct intel_guc_ct_channel *ctch = &guc->ct.host_channel; + + GEM_BUG_ON(!HAS_GUC_CT(dev_priv)); + + if (!ctch_is_open(ctch)) + return; + + ctch_close(guc, ctch); + + /* Disable send */ + guc->send = intel_guc_send_nop; + DRM_INFO("CT: %s\n", enableddisabled(false)); +} diff --git a/drivers/gpu/drm/i915/intel_guc_ct.h b/drivers/gpu/drm/i915/intel_guc_ct.h new file mode 100644 index 00000000000000..6d97f36fcc62c4 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_guc_ct.h @@ -0,0 +1,86 @@ +/* + * Copyright © 2016-2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _INTEL_GUC_CT_H_ +#define _INTEL_GUC_CT_H_ + +struct intel_guc; +struct i915_vma; + +#include "intel_guc_fwif.h" + +/** + * DOC: Command Transport (CT). + * + * Buffer based command transport is a replacement for MMIO based mechanism. + * It can be used to perform both host-2-guc and guc-to-host communication. + */ + +/** Represents single command transport buffer. + * + * A single command transport buffer consists of two parts, the header + * record (command transport buffer descriptor) and the actual buffer which + * holds the commands. + * + * @desc: pointer to the buffer descriptor + * @cmds: pointer to the commands buffer + */ +struct intel_guc_ct_buffer { + struct guc_ct_buffer_desc *desc; + u32 *cmds; +}; + +/** Represents pair of command transport buffers. + * + * Buffers go in pairs to allow bi-directional communication. + * To simplify the code we place both of them in the same vma. + * Buffers from the same pair must share unique owner id. + * + * @vma: pointer to the vma with pair of CT buffers + * @ctbs: buffers for sending(0) and receiving(1) commands + * @owner: unique identifier + * @next_fence: fence to be used with next send command + */ +struct intel_guc_ct_channel { + struct i915_vma *vma; + struct intel_guc_ct_buffer ctbs[2]; + u32 owner; + u32 next_fence; +}; + +/** Holds all command transport channels. + * + * @host_channel: main channel used by the host + */ +struct intel_guc_ct { + struct intel_guc_ct_channel host_channel; + /* other channels are tbd */ +}; + +void intel_guc_ct_init_early(struct intel_guc_ct *ct); + +/* XXX: move to intel_uc.h ? don't fit there either */ +int intel_guc_enable_ct(struct intel_guc *guc); +void intel_guc_disable_ct(struct intel_guc *guc); + +#endif /* _INTEL_GUC_CT_H_ */ diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h index cb36cbf3818f33..5fa28607481179 100644 --- a/drivers/gpu/drm/i915/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/intel_guc_fwif.h @@ -23,8 +23,8 @@ #ifndef _INTEL_GUC_FWIF_H #define _INTEL_GUC_FWIF_H -#define GFXCORE_FAMILY_GEN9 12 -#define GFXCORE_FAMILY_UNKNOWN 0x7fffffff +#define GUC_CORE_FAMILY_GEN9 12 +#define GUC_CORE_FAMILY_UNKNOWN 0x7fffffff #define GUC_CLIENT_PRIORITY_KMD_HIGH 0 #define GUC_CLIENT_PRIORITY_HIGH 1 @@ -331,6 +331,47 @@ struct guc_stage_desc { u64 desc_private; } __packed; +/* + * Describes single command transport buffer. + * Used by both guc-master and clients. + */ +struct guc_ct_buffer_desc { + u32 addr; /* gfx address */ + u64 host_private; /* host private data */ + u32 size; /* size in bytes */ + u32 head; /* offset updated by GuC*/ + u32 tail; /* offset updated by owner */ + u32 is_in_error; /* error indicator */ + u32 fence; /* fence updated by GuC */ + u32 status; /* status updated by GuC */ + u32 owner; /* id of the channel owner */ + u32 owner_sub_id; /* owner-defined field for extra tracking */ + u32 reserved[5]; +} __packed; + +/* Type of command transport buffer */ +#define INTEL_GUC_CT_BUFFER_TYPE_SEND 0x0u +#define INTEL_GUC_CT_BUFFER_TYPE_RECV 0x1u + +/* + * Definition of the command transport message header (DW0) + * + * bit[4..0] message len (in dwords) + * bit[7..5] reserved + * bit[8] write fence to desc + * bit[9] write status to H2G buff + * bit[10] send status (via G2H) + * bit[15..11] reserved + * bit[31..16] action code + */ +#define GUC_CT_MSG_LEN_SHIFT 0 +#define GUC_CT_MSG_LEN_MASK 0x1F +#define GUC_CT_MSG_WRITE_FENCE_TO_DESC (1 << 8) +#define GUC_CT_MSG_WRITE_STATUS_TO_BUFF (1 << 9) +#define GUC_CT_MSG_SEND_STATUS (1 << 10) +#define GUC_CT_MSG_ACTION_SHIFT 16 +#define GUC_CT_MSG_ACTION_MASK 0xFFFF + #define GUC_FORCEWAKE_RENDER (1 << 0) #define GUC_FORCEWAKE_MEDIA (1 << 1) @@ -515,6 +556,8 @@ enum intel_guc_action { INTEL_GUC_ACTION_EXIT_S_STATE = 0x502, INTEL_GUC_ACTION_SLPC_REQUEST = 0x3003, INTEL_GUC_ACTION_AUTHENTICATE_HUC = 0x4000, + INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505, + INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506, INTEL_GUC_ACTION_UK_LOG_ENABLE_LOGGING = 0x0E000, INTEL_GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c index 8a1a023e48b28c..d9045b6e897b4b 100644 --- a/drivers/gpu/drm/i915/intel_guc_loader.c +++ b/drivers/gpu/drm/i915/intel_guc_loader.c @@ -61,6 +61,9 @@ #define KBL_FW_MAJOR 9 #define KBL_FW_MINOR 14 +#define GLK_FW_MAJOR 10 +#define GLK_FW_MINOR 56 + #define GUC_FW_PATH(platform, major, minor) \ "i915/" __stringify(platform) "_guc_ver" __stringify(major) "_" __stringify(minor) ".bin" @@ -73,6 +76,8 @@ MODULE_FIRMWARE(I915_BXT_GUC_UCODE); #define I915_KBL_GUC_UCODE GUC_FW_PATH(kbl, KBL_FW_MAJOR, KBL_FW_MINOR) MODULE_FIRMWARE(I915_KBL_GUC_UCODE); +#define I915_GLK_GUC_UCODE GUC_FW_PATH(glk, GLK_FW_MAJOR, GLK_FW_MINOR) + static u32 get_gttype(struct drm_i915_private *dev_priv) { @@ -86,11 +91,11 @@ static u32 get_core_family(struct drm_i915_private *dev_priv) switch (gen) { case 9: - return GFXCORE_FAMILY_GEN9; + return GUC_CORE_FAMILY_GEN9; default: - WARN(1, "GEN%d does not support GuC operation!\n", gen); - return GFXCORE_FAMILY_UNKNOWN; + MISSING_CASE(gen); + return GUC_CORE_FAMILY_UNKNOWN; } } @@ -280,10 +285,6 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv) intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - /* init WOPCM */ - I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(dev_priv)); - I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE); - /* Enable MIA caching. GuC clock gating is disabled. */ I915_WRITE(GUC_SHIM_CONTROL, GUC_SHIM_CONTROL_VALUE); @@ -405,6 +406,10 @@ int intel_guc_select_fw(struct intel_guc *guc) guc->fw.path = I915_KBL_GUC_UCODE; guc->fw.major_ver_wanted = KBL_FW_MAJOR; guc->fw.minor_ver_wanted = KBL_FW_MINOR; + } else if (IS_GEMINILAKE(dev_priv)) { + guc->fw.path = I915_GLK_GUC_UCODE; + guc->fw.major_ver_wanted = GLK_FW_MAJOR; + guc->fw.minor_ver_wanted = GLK_FW_MINOR; } else { DRM_ERROR("No GuC firmware known for platform with GuC!\n"); return -ENOENT; diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c index 6fb63a3c65b030..16d3b8719cab43 100644 --- a/drivers/gpu/drm/i915/intel_guc_log.c +++ b/drivers/gpu/drm/i915/intel_guc_log.c @@ -359,12 +359,16 @@ static int guc_log_runtime_create(struct intel_guc *guc) void *vaddr; struct rchan *guc_log_relay_chan; size_t n_subbufs, subbuf_size; - int ret = 0; + int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); GEM_BUG_ON(guc_log_has_runtime(guc)); + ret = i915_gem_object_set_to_wc_domain(guc->log.vma->obj, true); + if (ret) + return ret; + /* Create a WC (Uncached for read) vmalloc mapping of log * buffer pages, so that we can directly get the data * (up-to-date) from memory. diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index e1ab6432a91464..52d5b82790d9fa 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -50,6 +50,32 @@ static bool is_supported_device(struct drm_i915_private *dev_priv) return false; } +/** + * intel_gvt_sanitize_options - sanitize GVT related options + * @dev_priv: drm i915 private data + * + * This function is called at the i915 options sanitize stage. + */ +void intel_gvt_sanitize_options(struct drm_i915_private *dev_priv) +{ + if (!i915.enable_gvt) + return; + + if (intel_vgpu_active(dev_priv)) { + DRM_INFO("GVT-g is disabled for guest\n"); + goto bail; + } + + if (!is_supported_device(dev_priv)) { + DRM_INFO("Unsupported device. GVT-g is disabled\n"); + goto bail; + } + + return; +bail: + i915.enable_gvt = 0; +} + /** * intel_gvt_init - initialize GVT components * @dev_priv: drm i915 private data @@ -69,19 +95,14 @@ int intel_gvt_init(struct drm_i915_private *dev_priv) return 0; } - if (intel_vgpu_active(dev_priv)) { - DRM_DEBUG_DRIVER("GVT-g is disabled for guest\n"); - goto bail; - } - - if (!is_supported_device(dev_priv)) { - DRM_DEBUG_DRIVER("Unsupported device. GVT-g is disabled\n"); - goto bail; + if (!i915.enable_execlists) { + DRM_ERROR("i915 GVT-g loading failed due to disabled execlists mode\n"); + return -EIO; } - if (!i915.enable_execlists) { - DRM_INFO("GPU guest virtualisation [GVT-g] disabled due to disabled execlist submission [i915.enable_execlists module parameter]\n"); - goto bail; + if (i915.enable_guc_submission) { + DRM_ERROR("i915 GVT-g loading failed due to Graphics virtualization is not yet supported with GuC submission\n"); + return -EIO; } /* diff --git a/drivers/gpu/drm/i915/intel_gvt.h b/drivers/gpu/drm/i915/intel_gvt.h index 25df2d65b985ce..61b24647028286 100644 --- a/drivers/gpu/drm/i915/intel_gvt.h +++ b/drivers/gpu/drm/i915/intel_gvt.h @@ -32,6 +32,7 @@ void intel_gvt_cleanup(struct drm_i915_private *dev_priv); int intel_gvt_init_device(struct drm_i915_private *dev_priv); void intel_gvt_clean_device(struct drm_i915_private *dev_priv); int intel_gvt_init_host(void); +void intel_gvt_sanitize_options(struct drm_i915_private *dev_priv); #else static inline int intel_gvt_init(struct drm_i915_private *dev_priv) { @@ -40,6 +41,10 @@ static inline int intel_gvt_init(struct drm_i915_private *dev_priv) static inline void intel_gvt_cleanup(struct drm_i915_private *dev_priv) { } + +static inline void intel_gvt_sanitize_options(struct drm_i915_private *dev_priv) +{ +} #endif #endif /* _INTEL_GVT_H_ */ diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c index dce742243ba665..9b0ece427bdc8a 100644 --- a/drivers/gpu/drm/i915/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/intel_hangcheck.c @@ -407,7 +407,7 @@ static void hangcheck_declare_hang(struct drm_i915_private *i915, "%s, ", engine->name); msg[len-2] = '\0'; - return i915_handle_error(i915, hung, msg); + return i915_handle_error(i915, hung, "%s", msg); } /* diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 1d623b5e09d62c..41267ffb36248d 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1218,7 +1218,8 @@ static int intel_hdmi_source_max_tmds_clock(struct drm_i915_private *dev_priv) } static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, - bool respect_downstream_limits) + bool respect_downstream_limits, + bool force_dvi) { struct drm_device *dev = intel_hdmi_to_dev(hdmi); int max_tmds_clock = intel_hdmi_source_max_tmds_clock(to_i915(dev)); @@ -1234,7 +1235,7 @@ static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, if (info->max_tmds_clock) max_tmds_clock = min(max_tmds_clock, info->max_tmds_clock); - else if (!hdmi->has_hdmi_sink) + else if (!hdmi->has_hdmi_sink || force_dvi) max_tmds_clock = min(max_tmds_clock, 165000); } @@ -1243,13 +1244,14 @@ static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, static enum drm_mode_status hdmi_port_clock_valid(struct intel_hdmi *hdmi, - int clock, bool respect_downstream_limits) + int clock, bool respect_downstream_limits, + bool force_dvi) { struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi)); if (clock < 25000) return MODE_CLOCK_LOW; - if (clock > hdmi_port_clock_limit(hdmi, respect_downstream_limits)) + if (clock > hdmi_port_clock_limit(hdmi, respect_downstream_limits, force_dvi)) return MODE_CLOCK_HIGH; /* BXT DPLL can't generate 223-240 MHz */ @@ -1273,6 +1275,8 @@ intel_hdmi_mode_valid(struct drm_connector *connector, enum drm_mode_status status; int clock; int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + bool force_dvi = + READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; @@ -1289,11 +1293,11 @@ intel_hdmi_mode_valid(struct drm_connector *connector, clock *= 2; /* check if we can do 8bpc */ - status = hdmi_port_clock_valid(hdmi, clock, true); + status = hdmi_port_clock_valid(hdmi, clock, true, force_dvi); /* if we can't do 8bpc we may still be able to do 12bpc */ - if (!HAS_GMCH_DISPLAY(dev_priv) && status != MODE_OK) - status = hdmi_port_clock_valid(hdmi, clock * 3 / 2, true); + if (!HAS_GMCH_DISPLAY(dev_priv) && status != MODE_OK && hdmi->has_hdmi_sink && !force_dvi) + status = hdmi_port_clock_valid(hdmi, clock * 3 / 2, true, force_dvi); return status; } @@ -1327,6 +1331,11 @@ static bool hdmi_12bpc_possible(struct intel_crtc_state *crtc_state) return false; } + /* Display Wa #1139 */ + if (IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1) && + crtc_state->base.adjusted_mode.htotal > 5460) + return false; + return true; } @@ -1338,16 +1347,19 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; struct drm_scdc *scdc = &conn_state->connector->display_info.hdmi.scdc; + struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(conn_state); int clock_8bpc = pipe_config->base.adjusted_mode.crtc_clock; int clock_12bpc = clock_8bpc * 3 / 2; int desired_bpp; + bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI; - pipe_config->has_hdmi_sink = intel_hdmi->has_hdmi_sink; + pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink; if (pipe_config->has_hdmi_sink) pipe_config->has_infoframe = true; - if (intel_hdmi->color_range_auto) { + if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ pipe_config->limited_color_range = pipe_config->has_hdmi_sink && @@ -1355,7 +1367,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, HDMI_QUANTIZATION_RANGE_LIMITED; } else { pipe_config->limited_color_range = - intel_hdmi->limited_color_range; + intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED; } if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) { @@ -1367,8 +1379,13 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv)) pipe_config->has_pch_encoder = true; - if (pipe_config->has_hdmi_sink && intel_hdmi->has_audio) - pipe_config->has_audio = true; + if (pipe_config->has_hdmi_sink) { + if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) + pipe_config->has_audio = intel_hdmi->has_audio; + else + pipe_config->has_audio = + intel_conn_state->force_audio == HDMI_AUDIO_ON; + } /* * HDMI is either 12 or 8, so if the display lets 10bpc sneak @@ -1376,8 +1393,8 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, * outputs. We also need to check that the higher clock still fits * within limits. */ - if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink && - hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true) == MODE_OK && + if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink && !force_dvi && + hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true, force_dvi) == MODE_OK && hdmi_12bpc_possible(pipe_config)) { DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n"); desired_bpp = 12*3; @@ -1392,18 +1409,18 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, } if (!pipe_config->bw_constrained) { - DRM_DEBUG_KMS("forcing pipe bpc to %i for HDMI\n", desired_bpp); + DRM_DEBUG_KMS("forcing pipe bpp to %i for HDMI\n", desired_bpp); pipe_config->pipe_bpp = desired_bpp; } if (hdmi_port_clock_valid(intel_hdmi, pipe_config->port_clock, - false) != MODE_OK) { + false, force_dvi) != MODE_OK) { DRM_DEBUG_KMS("unsupported HDMI clock, rejecting mode\n"); return false; } /* Set user selected PAR to incoming mode's member */ - adjusted_mode->picture_aspect_ratio = intel_hdmi->aspect_ratio; + adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio; pipe_config->lane_count = 4; @@ -1504,13 +1521,7 @@ intel_hdmi_set_edid(struct drm_connector *connector) drm_rgb_quant_range_selectable(edid); intel_hdmi->has_audio = drm_detect_monitor_audio(edid); - if (intel_hdmi->force_audio != HDMI_AUDIO_AUTO) - intel_hdmi->has_audio = - intel_hdmi->force_audio == HDMI_AUDIO_ON; - - if (intel_hdmi->force_audio != HDMI_AUDIO_OFF_DVI) - intel_hdmi->has_hdmi_sink = - drm_detect_hdmi_monitor(edid); + intel_hdmi->has_hdmi_sink = drm_detect_hdmi_monitor(edid); connected = true; } @@ -1572,108 +1583,6 @@ static int intel_hdmi_get_modes(struct drm_connector *connector) return intel_connector_update_modes(connector, edid); } -static bool -intel_hdmi_detect_audio(struct drm_connector *connector) -{ - bool has_audio = false; - struct edid *edid; - - edid = to_intel_connector(connector)->detect_edid; - if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) - has_audio = drm_detect_monitor_audio(edid); - - return has_audio; -} - -static int -intel_hdmi_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t val) -{ - struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); - struct intel_digital_port *intel_dig_port = - hdmi_to_dig_port(intel_hdmi); - struct drm_i915_private *dev_priv = to_i915(connector->dev); - int ret; - - ret = drm_object_property_set_value(&connector->base, property, val); - if (ret) - return ret; - - if (property == dev_priv->force_audio_property) { - enum hdmi_force_audio i = val; - bool has_audio; - - if (i == intel_hdmi->force_audio) - return 0; - - intel_hdmi->force_audio = i; - - if (i == HDMI_AUDIO_AUTO) - has_audio = intel_hdmi_detect_audio(connector); - else - has_audio = (i == HDMI_AUDIO_ON); - - if (i == HDMI_AUDIO_OFF_DVI) - intel_hdmi->has_hdmi_sink = 0; - - intel_hdmi->has_audio = has_audio; - goto done; - } - - if (property == dev_priv->broadcast_rgb_property) { - bool old_auto = intel_hdmi->color_range_auto; - bool old_range = intel_hdmi->limited_color_range; - - switch (val) { - case INTEL_BROADCAST_RGB_AUTO: - intel_hdmi->color_range_auto = true; - break; - case INTEL_BROADCAST_RGB_FULL: - intel_hdmi->color_range_auto = false; - intel_hdmi->limited_color_range = false; - break; - case INTEL_BROADCAST_RGB_LIMITED: - intel_hdmi->color_range_auto = false; - intel_hdmi->limited_color_range = true; - break; - default: - return -EINVAL; - } - - if (old_auto == intel_hdmi->color_range_auto && - old_range == intel_hdmi->limited_color_range) - return 0; - - goto done; - } - - if (property == connector->dev->mode_config.aspect_ratio_property) { - switch (val) { - case DRM_MODE_PICTURE_ASPECT_NONE: - intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; - break; - case DRM_MODE_PICTURE_ASPECT_4_3: - intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_4_3; - break; - case DRM_MODE_PICTURE_ASPECT_16_9: - intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_16_9; - break; - default: - return -EINVAL; - } - goto done; - } - - return -EINVAL; - -done: - if (intel_dig_port->base.base.crtc) - intel_crtc_restore_mode(intel_dig_port->base.base.crtc); - - return 0; -} - static void intel_hdmi_pre_enable(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) @@ -1798,18 +1707,20 @@ static const struct drm_connector_funcs intel_hdmi_connector_funcs = { .detect = intel_hdmi_detect, .force = intel_hdmi_force, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_hdmi_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, + .atomic_get_property = intel_digital_connector_atomic_get_property, + .atomic_set_property = intel_digital_connector_atomic_set_property, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_hdmi_destroy, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_duplicate_state = intel_digital_connector_duplicate_state, }; static const struct drm_connector_helper_funcs intel_hdmi_connector_helper_funcs = { .get_modes = intel_hdmi_get_modes, .mode_valid = intel_hdmi_mode_valid, + .atomic_check = intel_digital_connector_atomic_check, }; static const struct drm_encoder_funcs intel_hdmi_enc_funcs = { @@ -1821,9 +1732,8 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c { intel_attach_force_audio_property(connector); intel_attach_broadcast_rgb_property(connector); - intel_hdmi->color_range_auto = true; intel_attach_aspect_ratio_property(connector); - intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; + connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE; } /* diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c index 9ee819666a4c9c..f5eb18d0e2d139 100644 --- a/drivers/gpu/drm/i915/intel_huc.c +++ b/drivers/gpu/drm/i915/intel_huc.c @@ -52,6 +52,10 @@ #define KBL_HUC_FW_MINOR 00 #define KBL_BLD_NUM 1810 +#define GLK_HUC_FW_MAJOR 02 +#define GLK_HUC_FW_MINOR 00 +#define GLK_BLD_NUM 1748 + #define HUC_FW_PATH(platform, major, minor, bld_num) \ "i915/" __stringify(platform) "_huc_ver" __stringify(major) "_" \ __stringify(minor) "_" __stringify(bld_num) ".bin" @@ -68,6 +72,9 @@ MODULE_FIRMWARE(I915_BXT_HUC_UCODE); KBL_HUC_FW_MINOR, KBL_BLD_NUM) MODULE_FIRMWARE(I915_KBL_HUC_UCODE); +#define I915_GLK_HUC_UCODE HUC_FW_PATH(glk, GLK_HUC_FW_MAJOR, \ + GLK_HUC_FW_MINOR, GLK_BLD_NUM) + /** * huc_ucode_xfer() - DMA's the firmware * @dev_priv: the drm_i915_private device @@ -99,11 +106,6 @@ static int huc_ucode_xfer(struct drm_i915_private *dev_priv) intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - /* init WOPCM */ - I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(dev_priv)); - I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE | - HUC_LOADING_AGENT_GUC); - /* Set the source address for the uCode */ offset = guc_ggtt_offset(vma) + huc_fw->header_offset; I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset)); @@ -169,6 +171,10 @@ void intel_huc_select_fw(struct intel_huc *huc) huc->fw.path = I915_KBL_HUC_UCODE; huc->fw.major_ver_wanted = KBL_HUC_FW_MAJOR; huc->fw.minor_ver_wanted = KBL_HUC_FW_MINOR; + } else if (IS_GEMINILAKE(dev_priv)) { + huc->fw.path = I915_GLK_HUC_UCODE; + huc->fw.major_ver_wanted = GLK_HUC_FW_MAJOR; + huc->fw.minor_ver_wanted = GLK_HUC_FW_MINOR; } else { DRM_ERROR("No HuC firmware known for platform with HuC!\n"); return; @@ -186,68 +192,36 @@ void intel_huc_select_fw(struct intel_huc *huc) * earlier call to intel_huc_init(), so here we need only check that * is succeeded, and then transfer the image to the h/w. * - * Return: non-zero code on error */ -int intel_huc_init_hw(struct intel_huc *huc) +void intel_huc_init_hw(struct intel_huc *huc) { struct drm_i915_private *dev_priv = huc_to_i915(huc); int err; - if (huc->fw.fetch_status == INTEL_UC_FIRMWARE_NONE) - return 0; - DRM_DEBUG_DRIVER("%s fw status: fetch %s, load %s\n", huc->fw.path, intel_uc_fw_status_repr(huc->fw.fetch_status), intel_uc_fw_status_repr(huc->fw.load_status)); - if (huc->fw.fetch_status == INTEL_UC_FIRMWARE_SUCCESS && - huc->fw.load_status == INTEL_UC_FIRMWARE_FAIL) - return -ENOEXEC; + if (huc->fw.fetch_status != INTEL_UC_FIRMWARE_SUCCESS) + return; huc->fw.load_status = INTEL_UC_FIRMWARE_PENDING; - switch (huc->fw.fetch_status) { - case INTEL_UC_FIRMWARE_FAIL: - /* something went wrong :( */ - err = -EIO; - goto fail; - - case INTEL_UC_FIRMWARE_NONE: - case INTEL_UC_FIRMWARE_PENDING: - default: - /* "can't happen" */ - WARN_ONCE(1, "HuC fw %s invalid fetch_status %s [%d]\n", - huc->fw.path, - intel_uc_fw_status_repr(huc->fw.fetch_status), - huc->fw.fetch_status); - err = -ENXIO; - goto fail; - - case INTEL_UC_FIRMWARE_SUCCESS: - break; - } - err = huc_ucode_xfer(dev_priv); - if (err) - goto fail; - huc->fw.load_status = INTEL_UC_FIRMWARE_SUCCESS; + huc->fw.load_status = err ? + INTEL_UC_FIRMWARE_FAIL : INTEL_UC_FIRMWARE_SUCCESS; DRM_DEBUG_DRIVER("%s fw status: fetch %s, load %s\n", huc->fw.path, intel_uc_fw_status_repr(huc->fw.fetch_status), intel_uc_fw_status_repr(huc->fw.load_status)); - return 0; - -fail: - if (huc->fw.load_status == INTEL_UC_FIRMWARE_PENDING) - huc->fw.load_status = INTEL_UC_FIRMWARE_FAIL; - - DRM_ERROR("Failed to complete HuC uCode load with ret %d\n", err); + if (huc->fw.load_status != INTEL_UC_FIRMWARE_SUCCESS) + DRM_ERROR("Failed to complete HuC uCode load with ret %d\n", err); - return err; + return; } /** diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index 292fedf30b0010..3bf65288ffffd5 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -111,6 +111,11 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) pinfo.size_data = sizeof(*pdata); pinfo.dma_mask = DMA_BIT_MASK(32); + pdata->num_pipes = INTEL_INFO(dev_priv)->num_pipes; + pdata->num_ports = IS_CHERRYVIEW(dev_priv) ? 3 : 2; /* B,C,D or B,C */ + pdata->port[0].pipe = -1; + pdata->port[1].pipe = -1; + pdata->port[2].pipe = -1; spin_lock_init(&pdata->lpe_audio_slock); platdev = platform_device_register_full(&pinfo); @@ -306,53 +311,47 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) * intel_lpe_audio_notify() - notify lpe audio event * audio driver and i915 * @dev_priv: the i915 drm device private data + * @pipe: pipe + * @port: port * @eld : ELD data - * @pipe: pipe id - * @port: port id - * @tmds_clk_speed: tmds clock frequency in Hz + * @ls_clock: Link symbol clock in kHz + * @dp_output: Driving a DP output? * * Notify lpe audio driver of eld change. */ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, - void *eld, int port, int pipe, int tmds_clk_speed, - bool dp_output, int link_rate) + enum pipe pipe, enum port port, + const void *eld, int ls_clock, bool dp_output) { - unsigned long irq_flags; - struct intel_hdmi_lpe_audio_pdata *pdata = NULL; + unsigned long irqflags; + struct intel_hdmi_lpe_audio_pdata *pdata; + struct intel_hdmi_lpe_audio_port_pdata *ppdata; u32 audio_enable; if (!HAS_LPE_AUDIO(dev_priv)) return; - pdata = dev_get_platdata( - &(dev_priv->lpe_audio.platdev->dev)); + pdata = dev_get_platdata(&dev_priv->lpe_audio.platdev->dev); + ppdata = &pdata->port[port - PORT_B]; - spin_lock_irqsave(&pdata->lpe_audio_slock, irq_flags); + spin_lock_irqsave(&pdata->lpe_audio_slock, irqflags); audio_enable = I915_READ(VLV_AUD_PORT_EN_DBG(port)); if (eld != NULL) { - memcpy(pdata->eld.eld_data, eld, - HDMI_MAX_ELD_BYTES); - pdata->eld.port_id = port; - pdata->eld.pipe_id = pipe; - pdata->hdmi_connected = true; - - pdata->dp_output = dp_output; - if (tmds_clk_speed) - pdata->tmds_clock_speed = tmds_clk_speed; - if (link_rate) - pdata->link_rate = link_rate; + memcpy(ppdata->eld, eld, HDMI_MAX_ELD_BYTES); + ppdata->pipe = pipe; + ppdata->ls_clock = ls_clock; + ppdata->dp_output = dp_output; /* Unmute the amp for both DP and HDMI */ I915_WRITE(VLV_AUD_PORT_EN_DBG(port), audio_enable & ~VLV_AMP_MUTE); - } else { - memset(pdata->eld.eld_data, 0, - HDMI_MAX_ELD_BYTES); - pdata->hdmi_connected = false; - pdata->dp_output = false; + memset(ppdata->eld, 0, HDMI_MAX_ELD_BYTES); + ppdata->pipe = -1; + ppdata->ls_clock = 0; + ppdata->dp_output = false; /* Mute the amp for both DP and HDMI */ I915_WRITE(VLV_AUD_PORT_EN_DBG(port), @@ -360,10 +359,7 @@ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, } if (pdata->notify_audio_lpe) - pdata->notify_audio_lpe(dev_priv->lpe_audio.platdev); - else - pdata->notify_pending = true; + pdata->notify_audio_lpe(dev_priv->lpe_audio.platdev, port - PORT_B); - spin_unlock_irqrestore(&pdata->lpe_audio_slock, - irq_flags); + spin_unlock_irqrestore(&pdata->lpe_audio_slock, irqflags); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index dac4e003c1f317..014b30ace8a0af 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -138,10 +138,6 @@ #include "i915_drv.h" #include "intel_mocs.h" -#define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE) -#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE) -#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE) - #define RING_EXECLIST_QFULL (1 << 0x2) #define RING_EXECLIST1_VALID (1 << 0x3) #define RING_EXECLIST0_VALID (1 << 0x4) @@ -326,8 +322,7 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq) rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; u32 *reg_state = ce->lrc_reg_state; - assert_ring_tail_valid(rq->ring, rq->tail); - reg_state[CTX_RING_TAIL+1] = rq->tail; + reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail); /* True 32b PPGTT with dynamic page allocation: update PDP * registers and point the unallocated PDPs to scratch page. @@ -342,39 +337,32 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq) static void execlists_submit_ports(struct intel_engine_cs *engine) { - struct drm_i915_private *dev_priv = engine->i915; struct execlist_port *port = engine->execlist_port; u32 __iomem *elsp = - dev_priv->regs + i915_mmio_reg_offset(RING_ELSP(engine)); - u64 desc[2]; - - GEM_BUG_ON(port[0].count > 1); - if (!port[0].count) - execlists_context_status_change(port[0].request, - INTEL_CONTEXT_SCHEDULE_IN); - desc[0] = execlists_update_context(port[0].request); - GEM_DEBUG_EXEC(port[0].context_id = upper_32_bits(desc[0])); - port[0].count++; - - if (port[1].request) { - GEM_BUG_ON(port[1].count); - execlists_context_status_change(port[1].request, - INTEL_CONTEXT_SCHEDULE_IN); - desc[1] = execlists_update_context(port[1].request); - GEM_DEBUG_EXEC(port[1].context_id = upper_32_bits(desc[1])); - port[1].count = 1; - } else { - desc[1] = 0; - } - GEM_BUG_ON(desc[0] == desc[1]); - - /* You must always write both descriptors in the order below. */ - writel(upper_32_bits(desc[1]), elsp); - writel(lower_32_bits(desc[1]), elsp); + engine->i915->regs + i915_mmio_reg_offset(RING_ELSP(engine)); + unsigned int n; + + for (n = ARRAY_SIZE(engine->execlist_port); n--; ) { + struct drm_i915_gem_request *rq; + unsigned int count; + u64 desc; + + rq = port_unpack(&port[n], &count); + if (rq) { + GEM_BUG_ON(count > !n); + if (!count++) + execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN); + port_set(&port[n], port_pack(rq, count)); + desc = execlists_update_context(rq); + GEM_DEBUG_EXEC(port[n].context_id = upper_32_bits(desc)); + } else { + GEM_BUG_ON(!n); + desc = 0; + } - writel(upper_32_bits(desc[0]), elsp); - /* The context is automatically loaded after the following */ - writel(lower_32_bits(desc[0]), elsp); + writel(upper_32_bits(desc), elsp); + writel(lower_32_bits(desc), elsp); + } } static bool ctx_single_port_submission(const struct i915_gem_context *ctx) @@ -395,6 +383,17 @@ static bool can_merge_ctx(const struct i915_gem_context *prev, return true; } +static void port_assign(struct execlist_port *port, + struct drm_i915_gem_request *rq) +{ + GEM_BUG_ON(rq == port_request(port)); + + if (port_isset(port)) + i915_gem_request_put(port_request(port)); + + port_set(port, port_pack(i915_gem_request_get(rq), port_count(port))); +} + static void execlists_dequeue(struct intel_engine_cs *engine) { struct drm_i915_gem_request *last; @@ -402,7 +401,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) struct rb_node *rb; bool submit = false; - last = port->request; + last = port_request(port); if (last) /* WaIdleLiteRestore:bdw,skl * Apply the wa NOOPs to prevent ring:HEAD == req:TAIL @@ -412,7 +411,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ last->tail = last->wa_tail; - GEM_BUG_ON(port[1].request); + GEM_BUG_ON(port_isset(&port[1])); /* Hardware submission is through 2 ports. Conceptually each port * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is @@ -437,72 +436,86 @@ static void execlists_dequeue(struct intel_engine_cs *engine) spin_lock_irq(&engine->timeline->lock); rb = engine->execlist_first; + GEM_BUG_ON(rb_first(&engine->execlist_queue) != rb); while (rb) { - struct drm_i915_gem_request *cursor = - rb_entry(rb, typeof(*cursor), priotree.node); - - /* Can we combine this request with the current port? It has to - * be the same context/ringbuffer and not have any exceptions - * (e.g. GVT saying never to combine contexts). - * - * If we can combine the requests, we can execute both by - * updating the RING_TAIL to point to the end of the second - * request, and so we never need to tell the hardware about - * the first. - */ - if (last && !can_merge_ctx(cursor->ctx, last->ctx)) { - /* If we are on the second port and cannot combine - * this request with the last, then we are done. - */ - if (port != engine->execlist_port) - break; - - /* If GVT overrides us we only ever submit port[0], - * leaving port[1] empty. Note that we also have - * to be careful that we don't queue the same - * context (even though a different request) to - * the second port. + struct i915_priolist *p = rb_entry(rb, typeof(*p), node); + struct drm_i915_gem_request *rq, *rn; + + list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) { + /* + * Can we combine this request with the current port? + * It has to be the same context/ringbuffer and not + * have any exceptions (e.g. GVT saying never to + * combine contexts). + * + * If we can combine the requests, we can execute both + * by updating the RING_TAIL to point to the end of the + * second request, and so we never need to tell the + * hardware about the first. */ - if (ctx_single_port_submission(last->ctx) || - ctx_single_port_submission(cursor->ctx)) - break; + if (last && !can_merge_ctx(rq->ctx, last->ctx)) { + /* + * If we are on the second port and cannot + * combine this request with the last, then we + * are done. + */ + if (port != engine->execlist_port) { + __list_del_many(&p->requests, + &rq->priotree.link); + goto done; + } + + /* + * If GVT overrides us we only ever submit + * port[0], leaving port[1] empty. Note that we + * also have to be careful that we don't queue + * the same context (even though a different + * request) to the second port. + */ + if (ctx_single_port_submission(last->ctx) || + ctx_single_port_submission(rq->ctx)) { + __list_del_many(&p->requests, + &rq->priotree.link); + goto done; + } + + GEM_BUG_ON(last->ctx == rq->ctx); + + if (submit) + port_assign(port, last); + port++; + } - GEM_BUG_ON(last->ctx == cursor->ctx); + INIT_LIST_HEAD(&rq->priotree.link); + rq->priotree.priority = INT_MAX; - i915_gem_request_assign(&port->request, last); - port++; + __i915_gem_request_submit(rq); + trace_i915_gem_request_in(rq, port_index(port, engine)); + last = rq; + submit = true; } rb = rb_next(rb); - rb_erase(&cursor->priotree.node, &engine->execlist_queue); - RB_CLEAR_NODE(&cursor->priotree.node); - cursor->priotree.priority = INT_MAX; - - __i915_gem_request_submit(cursor); - trace_i915_gem_request_in(cursor, port - engine->execlist_port); - last = cursor; - submit = true; - } - if (submit) { - i915_gem_request_assign(&port->request, last); - engine->execlist_first = rb; + rb_erase(&p->node, &engine->execlist_queue); + INIT_LIST_HEAD(&p->requests); + if (p->priority != I915_PRIORITY_NORMAL) + kmem_cache_free(engine->i915->priorities, p); } +done: + engine->execlist_first = rb; + if (submit) + port_assign(port, last); spin_unlock_irq(&engine->timeline->lock); if (submit) execlists_submit_ports(engine); } -static bool execlists_elsp_idle(struct intel_engine_cs *engine) -{ - return !engine->execlist_port[0].request; -} - static bool execlists_elsp_ready(const struct intel_engine_cs *engine) { const struct execlist_port *port = engine->execlist_port; - return port[0].count + port[1].count < 2; + return port_count(&port[0]) + port_count(&port[1]) < 2; } /* @@ -515,6 +528,15 @@ static void intel_lrc_irq_handler(unsigned long data) struct execlist_port *port = engine->execlist_port; struct drm_i915_private *dev_priv = engine->i915; + /* We can skip acquiring intel_runtime_pm_get() here as it was taken + * on our behalf by the request (see i915_gem_mark_busy()) and it will + * not be relinquished until the device is idle (see + * i915_gem_idle_work_handler()). As a precaution, we make sure + * that all ELSP are drained i.e. we have processed the CSB, + * before allowing ourselves to idle and calling intel_runtime_pm_put(). + */ + GEM_BUG_ON(!dev_priv->gt.awake); + intel_uncore_forcewake_get(dev_priv, engine->fw_domains); /* Prefer doing test_and_clear_bit() as a two stage operation to avoid @@ -543,7 +565,9 @@ static void intel_lrc_irq_handler(unsigned long data) tail = GEN8_CSB_WRITE_PTR(head); head = GEN8_CSB_READ_PTR(head); while (head != tail) { + struct drm_i915_gem_request *rq; unsigned int status; + unsigned int count; if (++head == GEN8_CSB_ENTRIES) head = 0; @@ -571,22 +595,26 @@ static void intel_lrc_irq_handler(unsigned long data) /* Check the context/desc id for this event matches */ GEM_DEBUG_BUG_ON(readl(buf + 2 * head + 1) != - port[0].context_id); + port->context_id); - GEM_BUG_ON(port[0].count == 0); - if (--port[0].count == 0) { + rq = port_unpack(port, &count); + GEM_BUG_ON(count == 0); + if (--count == 0) { GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED); - GEM_BUG_ON(!i915_gem_request_completed(port[0].request)); - execlists_context_status_change(port[0].request, - INTEL_CONTEXT_SCHEDULE_OUT); + GEM_BUG_ON(!i915_gem_request_completed(rq)); + execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); + + trace_i915_gem_request_out(rq); + i915_gem_request_put(rq); - trace_i915_gem_request_out(port[0].request); - i915_gem_request_put(port[0].request); port[0] = port[1]; memset(&port[1], 0, sizeof(port[1])); + } else { + port_set(port, port_pack(rq, count)); } - GEM_BUG_ON(port[0].count == 0 && + /* After the final element, the hw should be idle */ + GEM_BUG_ON(port_count(port) == 0 && !(status & GEN8_CTX_STATUS_ACTIVE_IDLE)); } @@ -600,28 +628,66 @@ static void intel_lrc_irq_handler(unsigned long data) intel_uncore_forcewake_put(dev_priv, engine->fw_domains); } -static bool insert_request(struct i915_priotree *pt, struct rb_root *root) +static bool +insert_request(struct intel_engine_cs *engine, + struct i915_priotree *pt, + int prio) { - struct rb_node **p, *rb; + struct i915_priolist *p; + struct rb_node **parent, *rb; bool first = true; + if (unlikely(engine->no_priolist)) + prio = I915_PRIORITY_NORMAL; + +find_priolist: /* most positive priority is scheduled first, equal priorities fifo */ rb = NULL; - p = &root->rb_node; - while (*p) { - struct i915_priotree *pos; - - rb = *p; - pos = rb_entry(rb, typeof(*pos), node); - if (pt->priority > pos->priority) { - p = &rb->rb_left; - } else { - p = &rb->rb_right; + parent = &engine->execlist_queue.rb_node; + while (*parent) { + rb = *parent; + p = rb_entry(rb, typeof(*p), node); + if (prio > p->priority) { + parent = &rb->rb_left; + } else if (prio < p->priority) { + parent = &rb->rb_right; first = false; + } else { + list_add_tail(&pt->link, &p->requests); + return false; } } - rb_link_node(&pt->node, rb, p); - rb_insert_color(&pt->node, root); + + if (prio == I915_PRIORITY_NORMAL) { + p = &engine->default_priolist; + } else { + p = kmem_cache_alloc(engine->i915->priorities, GFP_ATOMIC); + /* Convert an allocation failure to a priority bump */ + if (unlikely(!p)) { + prio = I915_PRIORITY_NORMAL; /* recurses just once */ + + /* To maintain ordering with all rendering, after an + * allocation failure we have to disable all scheduling. + * Requests will then be executed in fifo, and schedule + * will ensure that dependencies are emitted in fifo. + * There will be still some reordering with existing + * requests, so if userspace lied about their + * dependencies that reordering may be visible. + */ + engine->no_priolist = true; + goto find_priolist; + } + } + + p->priority = prio; + rb_link_node(&p->node, rb, parent); + rb_insert_color(&p->node, &engine->execlist_queue); + + INIT_LIST_HEAD(&p->requests); + list_add_tail(&pt->link, &p->requests); + + if (first) + engine->execlist_first = &p->node; return first; } @@ -634,12 +700,16 @@ static void execlists_submit_request(struct drm_i915_gem_request *request) /* Will be called from irq-context when using foreign fences. */ spin_lock_irqsave(&engine->timeline->lock, flags); - if (insert_request(&request->priotree, &engine->execlist_queue)) { - engine->execlist_first = &request->priotree.node; + if (insert_request(engine, + &request->priotree, + request->priotree.priority)) { if (execlists_elsp_ready(engine)) tasklet_hi_schedule(&engine->irq_tasklet); } + GEM_BUG_ON(!engine->execlist_first); + GEM_BUG_ON(list_empty(&request->priotree.link)); + spin_unlock_irqrestore(&engine->timeline->lock, flags); } @@ -709,6 +779,19 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) list_safe_reset_next(dep, p, dfs_link); } + /* If we didn't need to bump any existing priorities, and we haven't + * yet submitted this request (i.e. there is no potential race with + * execlists_submit_request()), we can set our own priority and skip + * acquiring the engine locks. + */ + if (request->priotree.priority == INT_MIN) { + GEM_BUG_ON(!list_empty(&request->priotree.link)); + request->priotree.priority = prio; + if (stack.dfs_link.next == stack.dfs_link.prev) + return; + __list_del_entry(&stack.dfs_link); + } + engine = request->engine; spin_lock_irq(&engine->timeline->lock); @@ -724,10 +807,9 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) continue; pt->priority = prio; - if (!RB_EMPTY_NODE(&pt->node)) { - rb_erase(&pt->node, &engine->execlist_queue); - if (insert_request(pt, &engine->execlist_queue)) - engine->execlist_first = &pt->node; + if (!list_empty(&pt->link)) { + __list_del_entry(&pt->link); + insert_request(engine, pt, prio); } } @@ -736,8 +818,9 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) /* XXX Do we need to preempt to make room for us and our deps? */ } -static int execlists_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static struct intel_ring * +execlists_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { struct intel_context *ce = &ctx->engine[engine->id]; unsigned int flags; @@ -746,8 +829,8 @@ static int execlists_context_pin(struct intel_engine_cs *engine, lockdep_assert_held(&ctx->i915->drm.struct_mutex); - if (ce->pin_count++) - return 0; + if (likely(ce->pin_count++)) + goto out; GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ if (!ce->state) { @@ -771,7 +854,7 @@ static int execlists_context_pin(struct intel_engine_cs *engine, goto unpin_vma; } - ret = intel_ring_pin(ce->ring, ctx->ggtt_offset_bias); + ret = intel_ring_pin(ce->ring, ctx->i915, ctx->ggtt_offset_bias); if (ret) goto unpin_map; @@ -784,7 +867,8 @@ static int execlists_context_pin(struct intel_engine_cs *engine, ce->state->obj->mm.dirty = true; i915_gem_context_get(ctx); - return 0; +out: + return ce->ring; unpin_map: i915_gem_object_unpin_map(ce->state->obj); @@ -792,7 +876,7 @@ static int execlists_context_pin(struct intel_engine_cs *engine, __i915_vma_unpin(ce->state); err: ce->pin_count = 0; - return ret; + return ERR_PTR(ret); } static void execlists_context_unpin(struct intel_engine_cs *engine, @@ -829,9 +913,6 @@ static int execlists_request_alloc(struct drm_i915_gem_request *request) */ request->reserved_space += EXECLISTS_REQUEST_SIZE; - GEM_BUG_ON(!ce->ring); - request->ring = ce->ring; - if (i915.enable_guc_submission) { /* * Check that the GuC has space for the request before @@ -1139,14 +1220,12 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine) return ret; } -static u32 port_seqno(struct execlist_port *port) -{ - return port->request ? port->request->global_seqno : 0; -} - static int gen8_init_common_ring(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + struct execlist_port *port = engine->execlist_port; + unsigned int n; + bool submit; int ret; ret = intel_mocs_init_engine(engine); @@ -1167,16 +1246,24 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) /* After a GPU reset, we may have requests to replay */ clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); - if (!i915.enable_guc_submission && !execlists_elsp_idle(engine)) { - DRM_DEBUG_DRIVER("Restarting %s from requests [0x%x, 0x%x]\n", - engine->name, - port_seqno(&engine->execlist_port[0]), - port_seqno(&engine->execlist_port[1])); - engine->execlist_port[0].count = 0; - engine->execlist_port[1].count = 0; - execlists_submit_ports(engine); + + submit = false; + for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) { + if (!port_isset(&port[n])) + break; + + DRM_DEBUG_DRIVER("Restarting %s:%d from 0x%x\n", + engine->name, n, + port_request(&port[n])->global_seqno); + + /* Discard the current inflight count */ + port_set(&port[n], port_request(&port[n])); + submit = true; } + if (submit && !i915.enable_guc_submission) + execlists_submit_ports(engine); + return 0; } @@ -1252,13 +1339,13 @@ static void reset_common_ring(struct intel_engine_cs *engine, intel_ring_update_space(request->ring); /* Catch up with any missed context-switch interrupts */ - if (request->ctx != port[0].request->ctx) { - i915_gem_request_put(port[0].request); + if (request->ctx != port_request(port)->ctx) { + i915_gem_request_put(port_request(port)); port[0] = port[1]; memset(&port[1], 0, sizeof(port[1])); } - GEM_BUG_ON(request->ctx != port[0].request->ctx); + GEM_BUG_ON(request->ctx != port_request(port)->ctx); /* Reset WaIdleLiteRestore:bdw,skl as well */ request->tail = @@ -1907,44 +1994,6 @@ populate_lr_context(struct i915_gem_context *ctx, return 0; } -/** - * intel_lr_context_size() - return the size of the context for an engine - * @engine: which engine to find the context size for - * - * Each engine may require a different amount of space for a context image, - * so when allocating (or copying) an image, this function can be used to - * find the right size for the specific engine. - * - * Return: size (in bytes) of an engine-specific context image - * - * Note: this size includes the HWSP, which is part of the context image - * in LRC mode, but does not include the "shared data page" used with - * GuC submission. The caller should account for this if using the GuC. - */ -uint32_t intel_lr_context_size(struct intel_engine_cs *engine) -{ - int ret = 0; - - WARN_ON(INTEL_GEN(engine->i915) < 8); - - switch (engine->id) { - case RCS: - if (INTEL_GEN(engine->i915) >= 9) - ret = GEN9_LR_CONTEXT_RENDER_SIZE; - else - ret = GEN8_LR_CONTEXT_RENDER_SIZE; - break; - case VCS: - case BCS: - case VECS: - case VCS2: - ret = GEN8_LR_CONTEXT_OTHER_SIZE; - break; - } - - return ret; -} - static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { @@ -1957,8 +2006,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, WARN_ON(ce->state); - context_size = round_up(intel_lr_context_size(engine), - I915_GTT_PAGE_SIZE); + context_size = round_up(engine->context_size, I915_GTT_PAGE_SIZE); /* One extra page as the sharing data between driver and GuC */ context_size += PAGE_SIZE * LRC_PPHWSP_PN; @@ -2036,8 +2084,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv) ce->state->obj->mm.dirty = true; i915_gem_object_unpin_map(ce->state->obj); - ce->ring->head = ce->ring->tail = 0; - intel_ring_update_space(ce->ring); + intel_ring_reset(ce->ring, 0); } } } diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index e8015e7bf4e902..52b3a1fd4059ba 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -78,8 +78,6 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine); struct drm_i915_private; struct i915_gem_context; -uint32_t intel_lr_context_size(struct intel_engine_cs *engine); - void intel_lr_context_resume(struct drm_i915_private *dev_priv); uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx, struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 8b942ef2b3ec3f..d2c2bca1b32718 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -433,10 +433,10 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder, pipe_config->has_pch_encoder = true; intel_pch_panel_fitting(intel_crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); } else { intel_gmch_panel_fitting(intel_crtc, pipe_config, - intel_connector->panel.fitting_mode); + conn_state->scaling_mode); } @@ -598,56 +598,24 @@ static void intel_lvds_destroy(struct drm_connector *connector) kfree(connector); } -static int intel_lvds_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t value) -{ - struct intel_connector *intel_connector = to_intel_connector(connector); - struct drm_device *dev = connector->dev; - - if (property == dev->mode_config.scaling_mode_property) { - struct drm_crtc *crtc; - - if (value == DRM_MODE_SCALE_NONE) { - DRM_DEBUG_KMS("no scaling not supported\n"); - return -EINVAL; - } - - if (intel_connector->panel.fitting_mode == value) { - /* the LVDS scaling property is not changed */ - return 0; - } - intel_connector->panel.fitting_mode = value; - - crtc = intel_attached_encoder(connector)->base.crtc; - if (crtc && crtc->state->enable) { - /* - * If the CRTC is enabled, the display will be changed - * according to the new panel fitting mode. - */ - intel_crtc_restore_mode(crtc); - } - } - - return 0; -} - static const struct drm_connector_helper_funcs intel_lvds_connector_helper_funcs = { .get_modes = intel_lvds_get_modes, .mode_valid = intel_lvds_mode_valid, + .atomic_check = intel_digital_connector_atomic_check, }; static const struct drm_connector_funcs intel_lvds_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .detect = intel_lvds_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_lvds_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, + .atomic_get_property = intel_digital_connector_atomic_get_property, + .atomic_set_property = intel_digital_connector_atomic_set_property, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_lvds_destroy, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_duplicate_state = intel_digital_connector_duplicate_state, }; static const struct drm_encoder_funcs intel_lvds_enc_funcs = { @@ -988,6 +956,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) u32 lvds; int pipe; u8 pin; + u32 allowed_scalers; if (!intel_lvds_supported(dev_priv)) return; @@ -1083,11 +1052,11 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) lvds_encoder->reg = lvds_reg; /* create the scaling mode property */ - drm_mode_create_scaling_mode_property(dev); - drm_object_attach_property(&connector->base, - dev->mode_config.scaling_mode_property, - DRM_MODE_SCALE_ASPECT); - intel_connector->panel.fitting_mode = DRM_MODE_SCALE_ASPECT; + allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT); + allowed_scalers |= BIT(DRM_MODE_SCALE_FULLSCREEN); + allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); + drm_connector_attach_scaling_mode_property(connector, allowed_scalers); + connector->state->scaling_mode = DRM_MODE_SCALE_ASPECT; intel_lvds_pps_get_hw_state(dev_priv, &lvds_encoder->init_pps); lvds_encoder->init_lvds_val = lvds; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index cb50c527401fe1..c8103f8d4dfa77 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -888,10 +888,14 @@ static void pch_enable_backlight(struct intel_connector *connector) struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_panel *panel = &connector->panel; enum pipe pipe = intel_get_pipe_from_connector(connector); - enum transcoder cpu_transcoder = - intel_pipe_to_cpu_transcoder(dev_priv, pipe); + enum transcoder cpu_transcoder; u32 cpu_ctl2, pch_ctl1, pch_ctl2; + if (!WARN_ON_ONCE(pipe == INVALID_PIPE)) + cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, pipe); + else + cpu_transcoder = TRANSCODER_EDP; + cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2); if (cpu_ctl2 & BLM_PWM_ENABLE) { DRM_DEBUG_KMS("cpu backlight already enabled\n"); @@ -973,6 +977,9 @@ static void i965_enable_backlight(struct intel_connector *connector) enum pipe pipe = intel_get_pipe_from_connector(connector); u32 ctl, ctl2, freq; + if (WARN_ON_ONCE(pipe == INVALID_PIPE)) + pipe = PIPE_A; + ctl2 = I915_READ(BLC_PWM_CTL2); if (ctl2 & BLM_PWM_ENABLE) { DRM_DEBUG_KMS("backlight already enabled\n"); @@ -1037,6 +1044,9 @@ static void bxt_enable_backlight(struct intel_connector *connector) enum pipe pipe = intel_get_pipe_from_connector(connector); u32 pwm_ctl, val; + if (WARN_ON_ONCE(pipe == INVALID_PIPE)) + pipe = PIPE_A; + /* Controller 1 uses the utility pin. */ if (panel->backlight.controller == 1) { val = I915_READ(UTIL_PIN_CTL); @@ -1093,7 +1103,8 @@ void intel_panel_enable_backlight(struct intel_connector *connector) if (!panel->backlight.present) return; - DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe)); + if (!WARN_ON_ONCE(pipe == INVALID_PIPE)) + DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe)); mutex_lock(&dev_priv->backlight_lock); diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c index 206ee4f0150e7f..8fbd2bd0877fbc 100644 --- a/drivers/gpu/drm/i915/intel_pipe_crc.c +++ b/drivers/gpu/drm/i915/intel_pipe_crc.c @@ -513,16 +513,20 @@ static void hsw_trans_edp_pipe_A_crc_wa(struct drm_i915_private *dev_priv, struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_A); struct intel_crtc_state *pipe_config; struct drm_atomic_state *state; + struct drm_modeset_acquire_ctx ctx; int ret = 0; - drm_modeset_lock_all(dev); + drm_modeset_acquire_init(&ctx, 0); + state = drm_atomic_state_alloc(dev); if (!state) { ret = -ENOMEM; goto unlock; } - state->acquire_ctx = crtc->base.dev->mode_config.acquire_ctx; + state->acquire_ctx = &ctx; + +retry: pipe_config = intel_atomic_get_crtc_state(state, crtc); if (IS_ERR(pipe_config)) { ret = PTR_ERR(pipe_config); @@ -537,10 +541,17 @@ static void hsw_trans_edp_pipe_A_crc_wa(struct drm_i915_private *dev_priv, ret = drm_atomic_commit(state); put_state: + if (ret == -EDEADLK) { + drm_atomic_state_clear(state); + drm_modeset_backoff(&ctx); + goto retry; + } + drm_atomic_state_put(state); unlock: WARN(ret, "Toggling workaround to %i returns %i\n", enable, ret); - drm_modeset_unlock_all(dev); + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } static int ivb_pipe_crc_ctl_reg(struct drm_i915_private *dev_priv, @@ -842,19 +853,12 @@ static ssize_t display_crc_ctl_write(struct file *file, const char __user *ubuf, return -E2BIG; } - tmpbuf = kmalloc(len + 1, GFP_KERNEL); - if (!tmpbuf) - return -ENOMEM; - - if (copy_from_user(tmpbuf, ubuf, len)) { - ret = -EFAULT; - goto out; - } - tmpbuf[len] = '\0'; + tmpbuf = memdup_user_nul(ubuf, len); + if (IS_ERR(tmpbuf)) + return PTR_ERR(tmpbuf); ret = display_crc_ctl_parse(dev_priv, tmpbuf, len); -out: kfree(tmpbuf); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 570bd603f401d5..ae36df02948a17 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -386,13 +386,53 @@ static bool _intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enabl return was_enabled; } +/** + * intel_set_memory_cxsr - Configure CxSR state + * @dev_priv: i915 device + * @enable: Allow vs. disallow CxSR + * + * Allow or disallow the system to enter a special CxSR + * (C-state self refresh) state. What typically happens in CxSR mode + * is that several display FIFOs may get combined into a single larger + * FIFO for a particular plane (so called max FIFO mode) to allow the + * system to defer memory fetches longer, and the memory will enter + * self refresh. + * + * Note that enabling CxSR does not guarantee that the system enter + * this special mode, nor does it guarantee that the system stays + * in that mode once entered. So this just allows/disallows the system + * to autonomously utilize the CxSR mode. Other factors such as core + * C-states will affect when/if the system actually enters/exits the + * CxSR mode. + * + * Note that on VLV/CHV this actually only controls the max FIFO mode, + * and the system is free to enter/exit memory self refresh at any time + * even when the use of CxSR has been disallowed. + * + * While the system is actually in the CxSR/max FIFO mode, some plane + * control registers will not get latched on vblank. Thus in order to + * guarantee the system will respond to changes in the plane registers + * we must always disallow CxSR prior to making changes to those registers. + * Unfortunately the system will re-evaluate the CxSR conditions at + * frame start which happens after vblank start (which is when the plane + * registers would get latched), so we can't proceed with the plane update + * during the same frame where we disallowed CxSR. + * + * Certain platforms also have a deeper HPLL SR mode. Fortunately the + * HPLL SR mode depends on CxSR itself, so we don't have to hand hold + * the hardware w.r.t. HPLL SR when writing to plane registers. + * Disallowing just CxSR is sufficient. + */ bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) { bool ret; mutex_lock(&dev_priv->wm.wm_mutex); ret = _intel_set_memory_cxsr(dev_priv, enable); - dev_priv->wm.vlv.cxsr = enable; + if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + dev_priv->wm.vlv.cxsr = enable; + else if (IS_G4X(dev_priv)) + dev_priv->wm.g4x.cxsr = enable; mutex_unlock(&dev_priv->wm.wm_mutex); return ret; @@ -454,13 +494,6 @@ static void vlv_get_fifo_size(struct intel_crtc_state *crtc_state) fifo_state->plane[PLANE_SPRITE0] = sprite1_start - sprite0_start; fifo_state->plane[PLANE_SPRITE1] = 511 - sprite1_start; fifo_state->plane[PLANE_CURSOR] = 63; - - DRM_DEBUG_KMS("Pipe %c FIFO size: %d/%d/%d/%d\n", - pipe_name(pipe), - fifo_state->plane[PLANE_PRIMARY], - fifo_state->plane[PLANE_SPRITE0], - fifo_state->plane[PLANE_SPRITE1], - fifo_state->plane[PLANE_CURSOR]); } static int i9xx_get_fifo_size(struct drm_i915_private *dev_priv, int plane) @@ -538,20 +571,6 @@ static const struct intel_watermark_params pineview_cursor_hplloff_wm = { .guard_size = PINEVIEW_CURSOR_GUARD_WM, .cacheline_size = PINEVIEW_FIFO_LINE_SIZE, }; -static const struct intel_watermark_params g4x_wm_info = { - .fifo_size = G4X_FIFO_SIZE, - .max_wm = G4X_MAX_WM, - .default_wm = G4X_MAX_WM, - .guard_size = 2, - .cacheline_size = G4X_FIFO_LINE_SIZE, -}; -static const struct intel_watermark_params g4x_cursor_wm_info = { - .fifo_size = I965_CURSOR_FIFO, - .max_wm = I965_CURSOR_MAX_WM, - .default_wm = I965_CURSOR_DFT_WM, - .guard_size = 2, - .cacheline_size = G4X_FIFO_LINE_SIZE, -}; static const struct intel_watermark_params i965_cursor_wm_info = { .fifo_size = I965_CURSOR_FIFO, .max_wm = I965_CURSOR_MAX_WM, @@ -595,9 +614,105 @@ static const struct intel_watermark_params i845_wm_info = { .cacheline_size = I830_FIFO_LINE_SIZE, }; +/** + * intel_wm_method1 - Method 1 / "small buffer" watermark formula + * @pixel_rate: Pipe pixel rate in kHz + * @cpp: Plane bytes per pixel + * @latency: Memory wakeup latency in 0.1us units + * + * Compute the watermark using the method 1 or "small buffer" + * formula. The caller may additonally add extra cachelines + * to account for TLB misses and clock crossings. + * + * This method is concerned with the short term drain rate + * of the FIFO, ie. it does not account for blanking periods + * which would effectively reduce the average drain rate across + * a longer period. The name "small" refers to the fact the + * FIFO is relatively small compared to the amount of data + * fetched. + * + * The FIFO level vs. time graph might look something like: + * + * |\ |\ + * | \ | \ + * __---__---__ (- plane active, _ blanking) + * -> time + * + * or perhaps like this: + * + * |\|\ |\|\ + * __----__----__ (- plane active, _ blanking) + * -> time + * + * Returns: + * The watermark in bytes + */ +static unsigned int intel_wm_method1(unsigned int pixel_rate, + unsigned int cpp, + unsigned int latency) +{ + uint64_t ret; + + ret = (uint64_t) pixel_rate * cpp * latency; + ret = DIV_ROUND_UP_ULL(ret, 10000); + + return ret; +} + +/** + * intel_wm_method2 - Method 2 / "large buffer" watermark formula + * @pixel_rate: Pipe pixel rate in kHz + * @htotal: Pipe horizontal total + * @width: Plane width in pixels + * @cpp: Plane bytes per pixel + * @latency: Memory wakeup latency in 0.1us units + * + * Compute the watermark using the method 2 or "large buffer" + * formula. The caller may additonally add extra cachelines + * to account for TLB misses and clock crossings. + * + * This method is concerned with the long term drain rate + * of the FIFO, ie. it does account for blanking periods + * which effectively reduce the average drain rate across + * a longer period. The name "large" refers to the fact the + * FIFO is relatively large compared to the amount of data + * fetched. + * + * The FIFO level vs. time graph might look something like: + * + * |\___ |\___ + * | \___ | \___ + * | \ | \ + * __ --__--__--__--__--__--__ (- plane active, _ blanking) + * -> time + * + * Returns: + * The watermark in bytes + */ +static unsigned int intel_wm_method2(unsigned int pixel_rate, + unsigned int htotal, + unsigned int width, + unsigned int cpp, + unsigned int latency) +{ + unsigned int ret; + + /* + * FIXME remove once all users are computing + * watermarks in the correct place. + */ + if (WARN_ON_ONCE(htotal == 0)) + htotal = 1; + + ret = (latency * pixel_rate) / (htotal * 10000); + ret = (ret + 1) * width * cpp; + + return ret; +} + /** * intel_calculate_wm - calculate watermark level - * @clock_in_khz: pixel clock + * @pixel_rate: pixel clock * @wm: chip FIFO params * @cpp: bytes per pixel * @latency_ns: memory latency for the platform @@ -613,12 +728,12 @@ static const struct intel_watermark_params i845_wm_info = { * past the watermark point. If the FIFO drains completely, a FIFO underrun * will occur, and a display engine hang could result. */ -static unsigned long intel_calculate_wm(unsigned long clock_in_khz, - const struct intel_watermark_params *wm, - int fifo_size, int cpp, - unsigned long latency_ns) +static unsigned int intel_calculate_wm(int pixel_rate, + const struct intel_watermark_params *wm, + int fifo_size, int cpp, + unsigned int latency_ns) { - long entries_required, wm_size; + int entries, wm_size; /* * Note: we need to make sure we don't overflow for various clock & @@ -626,18 +741,17 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, * clocks go from a few thousand to several hundred thousand. * latency is usually a few thousand */ - entries_required = ((clock_in_khz / 1000) * cpp * latency_ns) / - 1000; - entries_required = DIV_ROUND_UP(entries_required, wm->cacheline_size); - - DRM_DEBUG_KMS("FIFO entries required for mode: %ld\n", entries_required); - - wm_size = fifo_size - (entries_required + wm->guard_size); + entries = intel_wm_method1(pixel_rate, cpp, + latency_ns / 100); + entries = DIV_ROUND_UP(entries, wm->cacheline_size) + + wm->guard_size; + DRM_DEBUG_KMS("FIFO entries required for mode: %d\n", entries); - DRM_DEBUG_KMS("FIFO watermark level: %ld\n", wm_size); + wm_size = fifo_size - entries; + DRM_DEBUG_KMS("FIFO watermark level: %d\n", wm_size); /* Don't promote wm_size to unsigned... */ - if (wm_size > (long)wm->max_wm) + if (wm_size > wm->max_wm) wm_size = wm->max_wm; if (wm_size <= 0) wm_size = wm->default_wm; @@ -655,6 +769,21 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, return wm_size; } +static bool is_disabling(int old, int new, int threshold) +{ + return old >= threshold && new < threshold; +} + +static bool is_enabling(int old, int new, int threshold) +{ + return old < threshold && new >= threshold; +} + +static int intel_wm_num_levels(struct drm_i915_private *dev_priv) +{ + return dev_priv->wm.max_level + 1; +} + static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -699,7 +828,7 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc) struct intel_crtc *crtc; const struct cxsr_latency *latency; u32 reg; - unsigned long wm; + unsigned int wm; latency = intel_get_cxsr_latency(IS_PINEVIEW_G(dev_priv), dev_priv->is_ddr3, @@ -733,7 +862,7 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc) /* cursor SR */ wm = intel_calculate_wm(clock, &pineview_cursor_wm, pineview_display_wm.fifo_size, - cpp, latency->cursor_sr); + 4, latency->cursor_sr); reg = I915_READ(DSPFW3); reg &= ~DSPFW_CURSOR_SR_MASK; reg |= FW_WM(wm, CURSOR_SR); @@ -751,7 +880,7 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc) /* cursor HPLL off SR */ wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm, pineview_display_hplloff_wm.fifo_size, - cpp, latency->cursor_hpll_disable); + 4, latency->cursor_hpll_disable); reg = I915_READ(DSPFW3); reg &= ~DSPFW_HPLL_CURSOR_MASK; reg |= FW_WM(wm, HPLL_CURSOR); @@ -764,144 +893,50 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc) } } -static bool g4x_compute_wm0(struct drm_i915_private *dev_priv, - int plane, - const struct intel_watermark_params *display, - int display_latency_ns, - const struct intel_watermark_params *cursor, - int cursor_latency_ns, - int *plane_wm, - int *cursor_wm) -{ - struct intel_crtc *crtc; - const struct drm_display_mode *adjusted_mode; - const struct drm_framebuffer *fb; - int htotal, hdisplay, clock, cpp; - int line_time_us, line_count; - int entries, tlb_miss; - - crtc = intel_get_crtc_for_plane(dev_priv, plane); - if (!intel_crtc_active(crtc)) { - *cursor_wm = cursor->guard_size; - *plane_wm = display->guard_size; - return false; - } - - adjusted_mode = &crtc->config->base.adjusted_mode; - fb = crtc->base.primary->state->fb; - clock = adjusted_mode->crtc_clock; - htotal = adjusted_mode->crtc_htotal; - hdisplay = crtc->config->pipe_src_w; - cpp = fb->format->cpp[0]; - - /* Use the small buffer method to calculate plane watermark */ - entries = ((clock * cpp / 1000) * display_latency_ns) / 1000; - tlb_miss = display->fifo_size*display->cacheline_size - hdisplay * 8; - if (tlb_miss > 0) - entries += tlb_miss; - entries = DIV_ROUND_UP(entries, display->cacheline_size); - *plane_wm = entries + display->guard_size; - if (*plane_wm > (int)display->max_wm) - *plane_wm = display->max_wm; - - /* Use the large buffer method to calculate cursor watermark */ - line_time_us = max(htotal * 1000 / clock, 1); - line_count = (cursor_latency_ns / line_time_us + 1000) / 1000; - entries = line_count * crtc->base.cursor->state->crtc_w * cpp; - tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8; - if (tlb_miss > 0) - entries += tlb_miss; - entries = DIV_ROUND_UP(entries, cursor->cacheline_size); - *cursor_wm = entries + cursor->guard_size; - if (*cursor_wm > (int)cursor->max_wm) - *cursor_wm = (int)cursor->max_wm; - - return true; -} - /* - * Check the wm result. - * - * If any calculated watermark values is larger than the maximum value that - * can be programmed into the associated watermark register, that watermark - * must be disabled. + * Documentation says: + * "If the line size is small, the TLB fetches can get in the way of the + * data fetches, causing some lag in the pixel data return which is not + * accounted for in the above formulas. The following adjustment only + * needs to be applied if eight whole lines fit in the buffer at once. + * The WM is adjusted upwards by the difference between the FIFO size + * and the size of 8 whole lines. This adjustment is always performed + * in the actual pixel depth regardless of whether FBC is enabled or not." */ -static bool g4x_check_srwm(struct drm_i915_private *dev_priv, - int display_wm, int cursor_wm, - const struct intel_watermark_params *display, - const struct intel_watermark_params *cursor) +static int g4x_tlb_miss_wa(int fifo_size, int width, int cpp) { - DRM_DEBUG_KMS("SR watermark: display plane %d, cursor %d\n", - display_wm, cursor_wm); + int tlb_miss = fifo_size * 64 - width * cpp * 8; - if (display_wm > display->max_wm) { - DRM_DEBUG_KMS("display watermark is too large(%d/%u), disabling\n", - display_wm, display->max_wm); - return false; - } - - if (cursor_wm > cursor->max_wm) { - DRM_DEBUG_KMS("cursor watermark is too large(%d/%u), disabling\n", - cursor_wm, cursor->max_wm); - return false; - } - - if (!(display_wm || cursor_wm)) { - DRM_DEBUG_KMS("SR latency is 0, disabling\n"); - return false; - } - - return true; + return max(0, tlb_miss); } -static bool g4x_compute_srwm(struct drm_i915_private *dev_priv, - int plane, - int latency_ns, - const struct intel_watermark_params *display, - const struct intel_watermark_params *cursor, - int *display_wm, int *cursor_wm) +static void g4x_write_wm_values(struct drm_i915_private *dev_priv, + const struct g4x_wm_values *wm) { - struct intel_crtc *crtc; - const struct drm_display_mode *adjusted_mode; - const struct drm_framebuffer *fb; - int hdisplay, htotal, cpp, clock; - unsigned long line_time_us; - int line_count, line_size; - int small, large; - int entries; - - if (!latency_ns) { - *display_wm = *cursor_wm = 0; - return false; - } - - crtc = intel_get_crtc_for_plane(dev_priv, plane); - adjusted_mode = &crtc->config->base.adjusted_mode; - fb = crtc->base.primary->state->fb; - clock = adjusted_mode->crtc_clock; - htotal = adjusted_mode->crtc_htotal; - hdisplay = crtc->config->pipe_src_w; - cpp = fb->format->cpp[0]; - - line_time_us = max(htotal * 1000 / clock, 1); - line_count = (latency_ns / line_time_us + 1000) / 1000; - line_size = hdisplay * cpp; - - /* Use the minimum of the small and large buffer method for primary */ - small = ((clock * cpp / 1000) * latency_ns) / 1000; - large = line_count * line_size; + enum pipe pipe; - entries = DIV_ROUND_UP(min(small, large), display->cacheline_size); - *display_wm = entries + display->guard_size; + for_each_pipe(dev_priv, pipe) + trace_g4x_wm(intel_get_crtc_for_pipe(dev_priv, pipe), wm); - /* calculate the self-refresh watermark for display cursor */ - entries = line_count * cpp * crtc->base.cursor->state->crtc_w; - entries = DIV_ROUND_UP(entries, cursor->cacheline_size); - *cursor_wm = entries + cursor->guard_size; + I915_WRITE(DSPFW1, + FW_WM(wm->sr.plane, SR) | + FW_WM(wm->pipe[PIPE_B].plane[PLANE_CURSOR], CURSORB) | + FW_WM(wm->pipe[PIPE_B].plane[PLANE_PRIMARY], PLANEB) | + FW_WM(wm->pipe[PIPE_A].plane[PLANE_PRIMARY], PLANEA)); + I915_WRITE(DSPFW2, + (wm->fbc_en ? DSPFW_FBC_SR_EN : 0) | + FW_WM(wm->sr.fbc, FBC_SR) | + FW_WM(wm->hpll.fbc, FBC_HPLL_SR) | + FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE0], SPRITEB) | + FW_WM(wm->pipe[PIPE_A].plane[PLANE_CURSOR], CURSORA) | + FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE0], SPRITEA)); + I915_WRITE(DSPFW3, + (wm->hpll_en ? DSPFW_HPLL_SR_EN : 0) | + FW_WM(wm->sr.cursor, CURSOR_SR) | + FW_WM(wm->hpll.cursor, HPLL_CURSOR) | + FW_WM(wm->hpll.plane, HPLL_SR)); - return g4x_check_srwm(dev_priv, - *display_wm, *cursor_wm, - display, cursor); + POSTING_READ(DSPFW1); } #define FW_WM_VLV(value, plane) \ @@ -985,17 +1020,535 @@ static void vlv_write_wm_values(struct drm_i915_private *dev_priv, #undef FW_WM_VLV +static void g4x_setup_wm_latency(struct drm_i915_private *dev_priv) +{ + /* all latencies in usec */ + dev_priv->wm.pri_latency[G4X_WM_LEVEL_NORMAL] = 5; + dev_priv->wm.pri_latency[G4X_WM_LEVEL_SR] = 12; + dev_priv->wm.pri_latency[G4X_WM_LEVEL_HPLL] = 35; + + dev_priv->wm.max_level = G4X_WM_LEVEL_HPLL; +} + +static int g4x_plane_fifo_size(enum plane_id plane_id, int level) +{ + /* + * DSPCNTR[13] supposedly controls whether the + * primary plane can use the FIFO space otherwise + * reserved for the sprite plane. It's not 100% clear + * what the actual FIFO size is, but it looks like we + * can happily set both primary and sprite watermarks + * up to 127 cachelines. So that would seem to mean + * that either DSPCNTR[13] doesn't do anything, or that + * the total FIFO is >= 256 cachelines in size. Either + * way, we don't seem to have to worry about this + * repartitioning as the maximum watermark value the + * register can hold for each plane is lower than the + * minimum FIFO size. + */ + switch (plane_id) { + case PLANE_CURSOR: + return 63; + case PLANE_PRIMARY: + return level == G4X_WM_LEVEL_NORMAL ? 127 : 511; + case PLANE_SPRITE0: + return level == G4X_WM_LEVEL_NORMAL ? 127 : 0; + default: + MISSING_CASE(plane_id); + return 0; + } +} + +static int g4x_fbc_fifo_size(int level) +{ + switch (level) { + case G4X_WM_LEVEL_SR: + return 7; + case G4X_WM_LEVEL_HPLL: + return 15; + default: + MISSING_CASE(level); + return 0; + } +} + +static uint16_t g4x_compute_wm(const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + int level) +{ + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_display_mode *adjusted_mode = + &crtc_state->base.adjusted_mode; + int clock, htotal, cpp, width, wm; + int latency = dev_priv->wm.pri_latency[level] * 10; + + if (latency == 0) + return USHRT_MAX; + + if (!intel_wm_plane_visible(crtc_state, plane_state)) + return 0; + + /* + * Not 100% sure which way ELK should go here as the + * spec only says CL/CTG should assume 32bpp and BW + * doesn't need to. But as these things followed the + * mobile vs. desktop lines on gen3 as well, let's + * assume ELK doesn't need this. + * + * The spec also fails to list such a restriction for + * the HPLL watermark, which seems a little strange. + * Let's use 32bpp for the HPLL watermark as well. + */ + if (IS_GM45(dev_priv) && plane->id == PLANE_PRIMARY && + level != G4X_WM_LEVEL_NORMAL) + cpp = 4; + else + cpp = plane_state->base.fb->format->cpp[0]; + + clock = adjusted_mode->crtc_clock; + htotal = adjusted_mode->crtc_htotal; + + if (plane->id == PLANE_CURSOR) + width = plane_state->base.crtc_w; + else + width = drm_rect_width(&plane_state->base.dst); + + if (plane->id == PLANE_CURSOR) { + wm = intel_wm_method2(clock, htotal, width, cpp, latency); + } else if (plane->id == PLANE_PRIMARY && + level == G4X_WM_LEVEL_NORMAL) { + wm = intel_wm_method1(clock, cpp, latency); + } else { + int small, large; + + small = intel_wm_method1(clock, cpp, latency); + large = intel_wm_method2(clock, htotal, width, cpp, latency); + + wm = min(small, large); + } + + wm += g4x_tlb_miss_wa(g4x_plane_fifo_size(plane->id, level), + width, cpp); + + wm = DIV_ROUND_UP(wm, 64) + 2; + + return min_t(int, wm, USHRT_MAX); +} + +static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state, + int level, enum plane_id plane_id, u16 value) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + bool dirty = false; + + for (; level < intel_wm_num_levels(dev_priv); level++) { + struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level]; + + dirty |= raw->plane[plane_id] != value; + raw->plane[plane_id] = value; + } + + return dirty; +} + +static bool g4x_raw_fbc_wm_set(struct intel_crtc_state *crtc_state, + int level, u16 value) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + bool dirty = false; + + /* NORMAL level doesn't have an FBC watermark */ + level = max(level, G4X_WM_LEVEL_SR); + + for (; level < intel_wm_num_levels(dev_priv); level++) { + struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level]; + + dirty |= raw->fbc != value; + raw->fbc = value; + } + + return dirty; +} + +static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate, + uint32_t pri_val); + +static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + int num_levels = intel_wm_num_levels(to_i915(plane->base.dev)); + enum plane_id plane_id = plane->id; + bool dirty = false; + int level; + + if (!intel_wm_plane_visible(crtc_state, plane_state)) { + dirty |= g4x_raw_plane_wm_set(crtc_state, 0, plane_id, 0); + if (plane_id == PLANE_PRIMARY) + dirty |= g4x_raw_fbc_wm_set(crtc_state, 0, 0); + goto out; + } + + for (level = 0; level < num_levels; level++) { + struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level]; + int wm, max_wm; + + wm = g4x_compute_wm(crtc_state, plane_state, level); + max_wm = g4x_plane_fifo_size(plane_id, level); + + if (wm > max_wm) + break; + + dirty |= raw->plane[plane_id] != wm; + raw->plane[plane_id] = wm; + + if (plane_id != PLANE_PRIMARY || + level == G4X_WM_LEVEL_NORMAL) + continue; + + wm = ilk_compute_fbc_wm(crtc_state, plane_state, + raw->plane[plane_id]); + max_wm = g4x_fbc_fifo_size(level); + + /* + * FBC wm is not mandatory as we + * can always just disable its use. + */ + if (wm > max_wm) + wm = USHRT_MAX; + + dirty |= raw->fbc != wm; + raw->fbc = wm; + } + + /* mark watermarks as invalid */ + dirty |= g4x_raw_plane_wm_set(crtc_state, level, plane_id, USHRT_MAX); + + if (plane_id == PLANE_PRIMARY) + dirty |= g4x_raw_fbc_wm_set(crtc_state, level, USHRT_MAX); + + out: + if (dirty) { + DRM_DEBUG_KMS("%s watermarks: normal=%d, SR=%d, HPLL=%d\n", + plane->base.name, + crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id], + crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id], + crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]); + + if (plane_id == PLANE_PRIMARY) + DRM_DEBUG_KMS("FBC watermarks: SR=%d, HPLL=%d\n", + crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc, + crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc); + } + + return dirty; +} + +static bool g4x_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state, + enum plane_id plane_id, int level) +{ + const struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level]; + + return raw->plane[plane_id] <= g4x_plane_fifo_size(plane_id, level); +} + +static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, + int level) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + + if (level > dev_priv->wm.max_level) + return false; + + return g4x_raw_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) && + g4x_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE0, level) && + g4x_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level); +} + +/* mark all levels starting from 'level' as invalid */ +static void g4x_invalidate_wms(struct intel_crtc *crtc, + struct g4x_wm_state *wm_state, int level) +{ + if (level <= G4X_WM_LEVEL_NORMAL) { + enum plane_id plane_id; + + for_each_plane_id_on_crtc(crtc, plane_id) + wm_state->wm.plane[plane_id] = USHRT_MAX; + } + + if (level <= G4X_WM_LEVEL_SR) { + wm_state->cxsr = false; + wm_state->sr.cursor = USHRT_MAX; + wm_state->sr.plane = USHRT_MAX; + wm_state->sr.fbc = USHRT_MAX; + } + + if (level <= G4X_WM_LEVEL_HPLL) { + wm_state->hpll_en = false; + wm_state->hpll.cursor = USHRT_MAX; + wm_state->hpll.plane = USHRT_MAX; + wm_state->hpll.fbc = USHRT_MAX; + } +} + +static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(crtc_state->base.state); + struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal; + int num_active_planes = hweight32(crtc_state->active_planes & + ~BIT(PLANE_CURSOR)); + const struct g4x_pipe_wm *raw; + struct intel_plane_state *plane_state; + struct intel_plane *plane; + enum plane_id plane_id; + int i, level; + unsigned int dirty = 0; + + for_each_intel_plane_in_state(state, plane, plane_state, i) { + const struct intel_plane_state *old_plane_state = + to_intel_plane_state(plane->base.state); + + if (plane_state->base.crtc != &crtc->base && + old_plane_state->base.crtc != &crtc->base) + continue; + + if (g4x_raw_plane_wm_compute(crtc_state, plane_state)) + dirty |= BIT(plane->id); + } + + if (!dirty) + return 0; + + level = G4X_WM_LEVEL_NORMAL; + if (!g4x_raw_crtc_wm_is_valid(crtc_state, level)) + goto out; + + raw = &crtc_state->wm.g4x.raw[level]; + for_each_plane_id_on_crtc(crtc, plane_id) + wm_state->wm.plane[plane_id] = raw->plane[plane_id]; + + level = G4X_WM_LEVEL_SR; + + if (!g4x_raw_crtc_wm_is_valid(crtc_state, level)) + goto out; + + raw = &crtc_state->wm.g4x.raw[level]; + wm_state->sr.plane = raw->plane[PLANE_PRIMARY]; + wm_state->sr.cursor = raw->plane[PLANE_CURSOR]; + wm_state->sr.fbc = raw->fbc; + + wm_state->cxsr = num_active_planes == BIT(PLANE_PRIMARY); + + level = G4X_WM_LEVEL_HPLL; + + if (!g4x_raw_crtc_wm_is_valid(crtc_state, level)) + goto out; + + raw = &crtc_state->wm.g4x.raw[level]; + wm_state->hpll.plane = raw->plane[PLANE_PRIMARY]; + wm_state->hpll.cursor = raw->plane[PLANE_CURSOR]; + wm_state->hpll.fbc = raw->fbc; + + wm_state->hpll_en = wm_state->cxsr; + + level++; + + out: + if (level == G4X_WM_LEVEL_NORMAL) + return -EINVAL; + + /* invalidate the higher levels */ + g4x_invalidate_wms(crtc, wm_state, level); + + /* + * Determine if the FBC watermark(s) can be used. IF + * this isn't the case we prefer to disable the FBC + ( watermark(s) rather than disable the SR/HPLL + * level(s) entirely. + */ + wm_state->fbc_en = level > G4X_WM_LEVEL_NORMAL; + + if (level >= G4X_WM_LEVEL_SR && + wm_state->sr.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_SR)) + wm_state->fbc_en = false; + else if (level >= G4X_WM_LEVEL_HPLL && + wm_state->hpll.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_HPLL)) + wm_state->fbc_en = false; + + return 0; +} + +static int g4x_compute_intermediate_wm(struct drm_device *dev, + struct intel_crtc *crtc, + struct intel_crtc_state *crtc_state) +{ + struct g4x_wm_state *intermediate = &crtc_state->wm.g4x.intermediate; + const struct g4x_wm_state *optimal = &crtc_state->wm.g4x.optimal; + const struct g4x_wm_state *active = &crtc->wm.active.g4x; + enum plane_id plane_id; + + intermediate->cxsr = optimal->cxsr && active->cxsr && + !crtc_state->disable_cxsr; + intermediate->hpll_en = optimal->hpll_en && active->hpll_en && + !crtc_state->disable_cxsr; + intermediate->fbc_en = optimal->fbc_en && active->fbc_en; + + for_each_plane_id_on_crtc(crtc, plane_id) { + intermediate->wm.plane[plane_id] = + max(optimal->wm.plane[plane_id], + active->wm.plane[plane_id]); + + WARN_ON(intermediate->wm.plane[plane_id] > + g4x_plane_fifo_size(plane_id, G4X_WM_LEVEL_NORMAL)); + } + + intermediate->sr.plane = max(optimal->sr.plane, + active->sr.plane); + intermediate->sr.cursor = max(optimal->sr.cursor, + active->sr.cursor); + intermediate->sr.fbc = max(optimal->sr.fbc, + active->sr.fbc); + + intermediate->hpll.plane = max(optimal->hpll.plane, + active->hpll.plane); + intermediate->hpll.cursor = max(optimal->hpll.cursor, + active->hpll.cursor); + intermediate->hpll.fbc = max(optimal->hpll.fbc, + active->hpll.fbc); + + WARN_ON((intermediate->sr.plane > + g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_SR) || + intermediate->sr.cursor > + g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_SR)) && + intermediate->cxsr); + WARN_ON((intermediate->sr.plane > + g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_HPLL) || + intermediate->sr.cursor > + g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_HPLL)) && + intermediate->hpll_en); + + WARN_ON(intermediate->sr.fbc > g4x_fbc_fifo_size(1) && + intermediate->fbc_en && intermediate->cxsr); + WARN_ON(intermediate->hpll.fbc > g4x_fbc_fifo_size(2) && + intermediate->fbc_en && intermediate->hpll_en); + + /* + * If our intermediate WM are identical to the final WM, then we can + * omit the post-vblank programming; only update if it's different. + */ + if (memcmp(intermediate, optimal, sizeof(*intermediate)) != 0) + crtc_state->wm.need_postvbl_update = true; + + return 0; +} + +static void g4x_merge_wm(struct drm_i915_private *dev_priv, + struct g4x_wm_values *wm) +{ + struct intel_crtc *crtc; + int num_active_crtcs = 0; + + wm->cxsr = true; + wm->hpll_en = true; + wm->fbc_en = true; + + for_each_intel_crtc(&dev_priv->drm, crtc) { + const struct g4x_wm_state *wm_state = &crtc->wm.active.g4x; + + if (!crtc->active) + continue; + + if (!wm_state->cxsr) + wm->cxsr = false; + if (!wm_state->hpll_en) + wm->hpll_en = false; + if (!wm_state->fbc_en) + wm->fbc_en = false; + + num_active_crtcs++; + } + + if (num_active_crtcs != 1) { + wm->cxsr = false; + wm->hpll_en = false; + wm->fbc_en = false; + } + + for_each_intel_crtc(&dev_priv->drm, crtc) { + const struct g4x_wm_state *wm_state = &crtc->wm.active.g4x; + enum pipe pipe = crtc->pipe; + + wm->pipe[pipe] = wm_state->wm; + if (crtc->active && wm->cxsr) + wm->sr = wm_state->sr; + if (crtc->active && wm->hpll_en) + wm->hpll = wm_state->hpll; + } +} + +static void g4x_program_watermarks(struct drm_i915_private *dev_priv) +{ + struct g4x_wm_values *old_wm = &dev_priv->wm.g4x; + struct g4x_wm_values new_wm = {}; + + g4x_merge_wm(dev_priv, &new_wm); + + if (memcmp(old_wm, &new_wm, sizeof(new_wm)) == 0) + return; + + if (is_disabling(old_wm->cxsr, new_wm.cxsr, true)) + _intel_set_memory_cxsr(dev_priv, false); + + g4x_write_wm_values(dev_priv, &new_wm); + + if (is_enabling(old_wm->cxsr, new_wm.cxsr, true)) + _intel_set_memory_cxsr(dev_priv, true); + + *old_wm = new_wm; +} + +static void g4x_initial_watermarks(struct intel_atomic_state *state, + struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + + mutex_lock(&dev_priv->wm.wm_mutex); + crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate; + g4x_program_watermarks(dev_priv); + mutex_unlock(&dev_priv->wm.wm_mutex); +} + +static void g4x_optimize_watermarks(struct intel_atomic_state *state, + struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); + + if (!crtc_state->wm.need_postvbl_update) + return; + + mutex_lock(&dev_priv->wm.wm_mutex); + intel_crtc->wm.active.g4x = crtc_state->wm.g4x.optimal; + g4x_program_watermarks(dev_priv); + mutex_unlock(&dev_priv->wm.wm_mutex); +} + /* latency must be in 0.1us units. */ static unsigned int vlv_wm_method2(unsigned int pixel_rate, - unsigned int pipe_htotal, - unsigned int horiz_pixels, + unsigned int htotal, + unsigned int width, unsigned int cpp, unsigned int latency) { unsigned int ret; - ret = (latency * pixel_rate) / (pipe_htotal * 10000); - ret = (ret + 1) * horiz_pixels * cpp; + ret = intel_wm_method2(pixel_rate, htotal, + width, cpp, latency); ret = DIV_ROUND_UP(ret, 64); return ret; @@ -1029,17 +1582,15 @@ static uint16_t vlv_compute_wm_level(const struct intel_crtc_state *crtc_state, if (dev_priv->wm.pri_latency[level] == 0) return USHRT_MAX; - if (!plane_state->base.visible) + if (!intel_wm_plane_visible(crtc_state, plane_state)) return 0; cpp = plane_state->base.fb->format->cpp[0]; clock = adjusted_mode->crtc_clock; htotal = adjusted_mode->crtc_htotal; width = crtc_state->pipe_src_w; - if (WARN_ON(htotal == 0)) - htotal = 1; - if (plane->base.type == DRM_PLANE_TYPE_CURSOR) { + if (plane->id == PLANE_CURSOR) { /* * FIXME the formula gives values that are * too big for the cursor FIFO, and hence we @@ -1064,7 +1615,7 @@ static bool vlv_need_sprite0_fifo_workaround(unsigned int active_planes) static int vlv_compute_fifo(struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - const struct vlv_pipe_wm *raw = + const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2]; struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state; unsigned int active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); @@ -1143,18 +1694,13 @@ static int vlv_compute_fifo(struct intel_crtc_state *crtc_state) return 0; } -static int vlv_num_wm_levels(struct drm_i915_private *dev_priv) -{ - return dev_priv->wm.max_level + 1; -} - /* mark all levels starting from 'level' as invalid */ static void vlv_invalidate_wms(struct intel_crtc *crtc, struct vlv_wm_state *wm_state, int level) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - for (; level < vlv_num_wm_levels(dev_priv); level++) { + for (; level < intel_wm_num_levels(dev_priv); level++) { enum plane_id plane_id; for_each_plane_id_on_crtc(crtc, plane_id) @@ -1181,11 +1727,11 @@ static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state, int level, enum plane_id plane_id, u16 value) { struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); - int num_levels = vlv_num_wm_levels(dev_priv); + int num_levels = intel_wm_num_levels(dev_priv); bool dirty = false; for (; level < num_levels; level++) { - struct vlv_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; + struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; dirty |= raw->plane[plane_id] != value; raw->plane[plane_id] = value; @@ -1194,22 +1740,22 @@ static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state, return dirty; } -static bool vlv_plane_wm_compute(struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->base.plane); enum plane_id plane_id = plane->id; - int num_levels = vlv_num_wm_levels(to_i915(plane->base.dev)); + int num_levels = intel_wm_num_levels(to_i915(plane->base.dev)); int level; bool dirty = false; - if (!plane_state->base.visible) { + if (!intel_wm_plane_visible(crtc_state, plane_state)) { dirty |= vlv_raw_plane_wm_set(crtc_state, 0, plane_id, 0); goto out; } for (level = 0; level < num_levels; level++) { - struct vlv_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; + struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; int wm = vlv_compute_wm_level(crtc_state, plane_state, level); int max_wm = plane_id == PLANE_CURSOR ? 63 : 511; @@ -1225,7 +1771,7 @@ static bool vlv_plane_wm_compute(struct intel_crtc_state *crtc_state, out: if (dirty) - DRM_DEBUG_KMS("%s wms: [0]=%d,[1]=%d,[2]=%d\n", + DRM_DEBUG_KMS("%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n", plane->base.name, crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id], crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id], @@ -1234,10 +1780,10 @@ static bool vlv_plane_wm_compute(struct intel_crtc_state *crtc_state, return dirty; } -static bool vlv_plane_wm_is_valid(const struct intel_crtc_state *crtc_state, - enum plane_id plane_id, int level) +static bool vlv_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state, + enum plane_id plane_id, int level) { - const struct vlv_pipe_wm *raw = + const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; const struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state; @@ -1245,12 +1791,12 @@ static bool vlv_plane_wm_is_valid(const struct intel_crtc_state *crtc_state, return raw->plane[plane_id] <= fifo_state->plane[plane_id]; } -static bool vlv_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, int level) +static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, int level) { - return vlv_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) && - vlv_plane_wm_is_valid(crtc_state, PLANE_SPRITE0, level) && - vlv_plane_wm_is_valid(crtc_state, PLANE_SPRITE1, level) && - vlv_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level); + return vlv_raw_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) && + vlv_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE0, level) && + vlv_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE1, level) && + vlv_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level); } static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state) @@ -1279,7 +1825,7 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state) old_plane_state->base.crtc != &crtc->base) continue; - if (vlv_plane_wm_compute(crtc_state, plane_state)) + if (vlv_raw_plane_wm_compute(crtc_state, plane_state)) dirty |= BIT(plane->id); } @@ -1313,7 +1859,7 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state) } /* initially allow all levels */ - wm_state->num_levels = vlv_num_wm_levels(dev_priv); + wm_state->num_levels = intel_wm_num_levels(dev_priv); /* * Note that enabling cxsr with no primary/sprite planes * enabled can wedge the pipe. Hence we only allow cxsr @@ -1322,10 +1868,10 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state) wm_state->cxsr = crtc->pipe != PIPE_C && num_active_planes == 1; for (level = 0; level < wm_state->num_levels; level++) { - const struct vlv_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; + const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; const int sr_fifo_size = INTEL_INFO(dev_priv)->num_pipes * 512 - 1; - if (!vlv_crtc_wm_is_valid(crtc_state, level)) + if (!vlv_raw_crtc_wm_is_valid(crtc_state, level)) break; for_each_plane_id_on_crtc(crtc, plane_id) { @@ -1539,16 +2085,6 @@ static void vlv_merge_wm(struct drm_i915_private *dev_priv, } } -static bool is_disabling(int old, int new, int threshold) -{ - return old >= threshold && new < threshold; -} - -static bool is_enabling(int old, int new, int threshold) -{ - return old < threshold && new >= threshold; -} - static void vlv_program_watermarks(struct drm_i915_private *dev_priv) { struct vlv_wm_values *old_wm = &dev_priv->wm.vlv; @@ -1609,65 +2145,6 @@ static void vlv_optimize_watermarks(struct intel_atomic_state *state, mutex_unlock(&dev_priv->wm.wm_mutex); } -#define single_plane_enabled(mask) is_power_of_2(mask) - -static void g4x_update_wm(struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - static const int sr_latency_ns = 12000; - int planea_wm, planeb_wm, cursora_wm, cursorb_wm; - int plane_sr, cursor_sr; - unsigned int enabled = 0; - bool cxsr_enabled; - - if (g4x_compute_wm0(dev_priv, PIPE_A, - &g4x_wm_info, pessimal_latency_ns, - &g4x_cursor_wm_info, pessimal_latency_ns, - &planea_wm, &cursora_wm)) - enabled |= 1 << PIPE_A; - - if (g4x_compute_wm0(dev_priv, PIPE_B, - &g4x_wm_info, pessimal_latency_ns, - &g4x_cursor_wm_info, pessimal_latency_ns, - &planeb_wm, &cursorb_wm)) - enabled |= 1 << PIPE_B; - - if (single_plane_enabled(enabled) && - g4x_compute_srwm(dev_priv, ffs(enabled) - 1, - sr_latency_ns, - &g4x_wm_info, - &g4x_cursor_wm_info, - &plane_sr, &cursor_sr)) { - cxsr_enabled = true; - } else { - cxsr_enabled = false; - intel_set_memory_cxsr(dev_priv, false); - plane_sr = cursor_sr = 0; - } - - DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, " - "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n", - planea_wm, cursora_wm, - planeb_wm, cursorb_wm, - plane_sr, cursor_sr); - - I915_WRITE(DSPFW1, - FW_WM(plane_sr, SR) | - FW_WM(cursorb_wm, CURSORB) | - FW_WM(planeb_wm, PLANEB) | - FW_WM(planea_wm, PLANEA)); - I915_WRITE(DSPFW2, - (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) | - FW_WM(cursora_wm, CURSORA)); - /* HPLL off in SR has some issues on G4x... disable it */ - I915_WRITE(DSPFW3, - (I915_READ(DSPFW3) & ~(DSPFW_HPLL_SR_EN | DSPFW_CURSOR_SR_MASK)) | - FW_WM(cursor_sr, CURSOR_SR)); - - if (cxsr_enabled) - intel_set_memory_cxsr(dev_priv, true); -} - static void i965_update_wm(struct intel_crtc *unused_crtc) { struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev); @@ -1689,14 +2166,10 @@ static void i965_update_wm(struct intel_crtc *unused_crtc) int htotal = adjusted_mode->crtc_htotal; int hdisplay = crtc->config->pipe_src_w; int cpp = fb->format->cpp[0]; - unsigned long line_time_us; int entries; - line_time_us = max(htotal * 1000 / clock, 1); - - /* Use ns/us then divide to preserve precision */ - entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - cpp * hdisplay; + entries = intel_wm_method2(clock, htotal, + hdisplay, cpp, sr_latency_ns / 100); entries = DIV_ROUND_UP(entries, I915_FIFO_LINE_SIZE); srwm = I965_FIFO_SIZE - entries; if (srwm < 0) @@ -1705,13 +2178,14 @@ static void i965_update_wm(struct intel_crtc *unused_crtc) DRM_DEBUG_KMS("self-refresh entries: %d, wm: %d\n", entries, srwm); - entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - cpp * crtc->base.cursor->state->crtc_w; + entries = intel_wm_method2(clock, htotal, + crtc->base.cursor->state->crtc_w, 4, + sr_latency_ns / 100); entries = DIV_ROUND_UP(entries, - i965_cursor_wm_info.cacheline_size); - cursor_sr = i965_cursor_wm_info.fifo_size - - (entries + i965_cursor_wm_info.guard_size); + i965_cursor_wm_info.cacheline_size) + + i965_cursor_wm_info.guard_size; + cursor_sr = i965_cursor_wm_info.fifo_size - entries; if (cursor_sr > i965_cursor_wm_info.max_wm) cursor_sr = i965_cursor_wm_info.max_wm; @@ -1848,7 +2322,6 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) int htotal = adjusted_mode->crtc_htotal; int hdisplay = enabled->config->pipe_src_w; int cpp; - unsigned long line_time_us; int entries; if (IS_I915GM(dev_priv) || IS_I945GM(dev_priv)) @@ -1856,11 +2329,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) else cpp = fb->format->cpp[0]; - line_time_us = max(htotal * 1000 / clock, 1); - - /* Use ns/us then divide to preserve precision */ - entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * - cpp * hdisplay; + entries = intel_wm_method2(clock, htotal, hdisplay, cpp, + sr_latency_ns / 100); entries = DIV_ROUND_UP(entries, wm_info->cacheline_size); DRM_DEBUG_KMS("self-refresh entries: %d\n", entries); srwm = wm_info->fifo_size - entries; @@ -1917,34 +2387,31 @@ static void i845_update_wm(struct intel_crtc *unused_crtc) } /* latency must be in 0.1us units. */ -static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latency) +static unsigned int ilk_wm_method1(unsigned int pixel_rate, + unsigned int cpp, + unsigned int latency) { - uint64_t ret; - - if (WARN(latency == 0, "Latency value missing\n")) - return UINT_MAX; + unsigned int ret; - ret = (uint64_t) pixel_rate * cpp * latency; - ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2; + ret = intel_wm_method1(pixel_rate, cpp, latency); + ret = DIV_ROUND_UP(ret, 64) + 2; return ret; } /* latency must be in 0.1us units. */ -static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, - uint32_t horiz_pixels, uint8_t cpp, - uint32_t latency) +static unsigned int ilk_wm_method2(unsigned int pixel_rate, + unsigned int htotal, + unsigned int width, + unsigned int cpp, + unsigned int latency) { - uint32_t ret; - - if (WARN(latency == 0, "Latency value missing\n")) - return UINT_MAX; - if (WARN_ON(!pipe_htotal)) - return UINT_MAX; + unsigned int ret; - ret = (latency * pixel_rate) / (pipe_htotal * 10000); - ret = (ret + 1) * horiz_pixels * cpp; + ret = intel_wm_method2(pixel_rate, htotal, + width, cpp, latency); ret = DIV_ROUND_UP(ret, 64) + 2; + return ret; } @@ -3360,26 +3827,27 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, * Return value is provided in 16.16 fixed point form to retain fractional part. * Caller should take care of dividing & rounding off the value. */ -static uint32_t +static uint_fixed_16_16_t skl_plane_downscale_amount(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate) { struct intel_plane *plane = to_intel_plane(pstate->base.plane); - uint32_t downscale_h, downscale_w; uint32_t src_w, src_h, dst_w, dst_h; + uint_fixed_16_16_t fp_w_ratio, fp_h_ratio; + uint_fixed_16_16_t downscale_h, downscale_w; if (WARN_ON(!intel_wm_plane_visible(cstate, pstate))) - return DRM_PLANE_HELPER_NO_SCALING; + return u32_to_fixed_16_16(0); /* n.b., src is 16.16 fixed point, dst is whole integer */ if (plane->id == PLANE_CURSOR) { - src_w = pstate->base.src_w; - src_h = pstate->base.src_h; + src_w = pstate->base.src_w >> 16; + src_h = pstate->base.src_h >> 16; dst_w = pstate->base.crtc_w; dst_h = pstate->base.crtc_h; } else { - src_w = drm_rect_width(&pstate->base.src); - src_h = drm_rect_height(&pstate->base.src); + src_w = drm_rect_width(&pstate->base.src) >> 16; + src_h = drm_rect_height(&pstate->base.src) >> 16; dst_w = drm_rect_width(&pstate->base.dst); dst_h = drm_rect_height(&pstate->base.dst); } @@ -3387,11 +3855,103 @@ skl_plane_downscale_amount(const struct intel_crtc_state *cstate, if (drm_rotation_90_or_270(pstate->base.rotation)) swap(dst_w, dst_h); - downscale_h = max(src_h / dst_h, (uint32_t)DRM_PLANE_HELPER_NO_SCALING); - downscale_w = max(src_w / dst_w, (uint32_t)DRM_PLANE_HELPER_NO_SCALING); + fp_w_ratio = fixed_16_16_div(src_w, dst_w); + fp_h_ratio = fixed_16_16_div(src_h, dst_h); + downscale_w = max_fixed_16_16(fp_w_ratio, u32_to_fixed_16_16(1)); + downscale_h = max_fixed_16_16(fp_h_ratio, u32_to_fixed_16_16(1)); - /* Provide result in 16.16 fixed point */ - return (uint64_t)downscale_w * downscale_h >> 16; + return mul_fixed16(downscale_w, downscale_h); +} + +static uint_fixed_16_16_t +skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state) +{ + uint_fixed_16_16_t pipe_downscale = u32_to_fixed_16_16(1); + + if (!crtc_state->base.enable) + return pipe_downscale; + + if (crtc_state->pch_pfit.enabled) { + uint32_t src_w, src_h, dst_w, dst_h; + uint32_t pfit_size = crtc_state->pch_pfit.size; + uint_fixed_16_16_t fp_w_ratio, fp_h_ratio; + uint_fixed_16_16_t downscale_h, downscale_w; + + src_w = crtc_state->pipe_src_w; + src_h = crtc_state->pipe_src_h; + dst_w = pfit_size >> 16; + dst_h = pfit_size & 0xffff; + + if (!dst_w || !dst_h) + return pipe_downscale; + + fp_w_ratio = fixed_16_16_div(src_w, dst_w); + fp_h_ratio = fixed_16_16_div(src_h, dst_h); + downscale_w = max_fixed_16_16(fp_w_ratio, u32_to_fixed_16_16(1)); + downscale_h = max_fixed_16_16(fp_h_ratio, u32_to_fixed_16_16(1)); + + pipe_downscale = mul_fixed16(downscale_w, downscale_h); + } + + return pipe_downscale; +} + +int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc, + struct intel_crtc_state *cstate) +{ + struct drm_crtc_state *crtc_state = &cstate->base; + struct drm_atomic_state *state = crtc_state->state; + struct drm_plane *plane; + const struct drm_plane_state *pstate; + struct intel_plane_state *intel_pstate; + int crtc_clock, dotclk; + uint32_t pipe_max_pixel_rate; + uint_fixed_16_16_t pipe_downscale; + uint_fixed_16_16_t max_downscale = u32_to_fixed_16_16(1); + + if (!cstate->base.enable) + return 0; + + drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) { + uint_fixed_16_16_t plane_downscale; + uint_fixed_16_16_t fp_9_div_8 = fixed_16_16_div(9, 8); + int bpp; + + if (!intel_wm_plane_visible(cstate, + to_intel_plane_state(pstate))) + continue; + + if (WARN_ON(!pstate->fb)) + return -EINVAL; + + intel_pstate = to_intel_plane_state(pstate); + plane_downscale = skl_plane_downscale_amount(cstate, + intel_pstate); + bpp = pstate->fb->format->cpp[0] * 8; + if (bpp == 64) + plane_downscale = mul_fixed16(plane_downscale, + fp_9_div_8); + + max_downscale = max_fixed_16_16(plane_downscale, max_downscale); + } + pipe_downscale = skl_pipe_downscale_amount(cstate); + + pipe_downscale = mul_fixed16(pipe_downscale, max_downscale); + + crtc_clock = crtc_state->adjusted_mode.crtc_clock; + dotclk = to_intel_atomic_state(state)->cdclk.logical.cdclk; + + if (IS_GEMINILAKE(to_i915(intel_crtc->base.dev))) + dotclk *= 2; + + pipe_max_pixel_rate = div_round_up_u32_fixed16(dotclk, pipe_downscale); + + if (pipe_max_pixel_rate < crtc_clock) { + DRM_DEBUG_KMS("Max supported pixel clock with scaling exceeded\n"); + return -EINVAL; + } + + return 0; } static unsigned int @@ -3401,10 +3961,11 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate, { struct intel_plane *plane = to_intel_plane(pstate->plane); struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate); - uint32_t down_scale_amount, data_rate; + uint32_t data_rate; uint32_t width = 0, height = 0; struct drm_framebuffer *fb; u32 format; + uint_fixed_16_16_t down_scale_amount; if (!intel_pstate->base.visible) return 0; @@ -3438,7 +3999,7 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate, down_scale_amount = skl_plane_downscale_amount(cstate, intel_pstate); - return (uint64_t)data_rate * down_scale_amount >> 16; + return mul_round_up_u32_fixed16(data_rate, down_scale_amount); } /* @@ -3565,17 +4126,45 @@ skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active, minimum[plane_id] = skl_ddb_min_alloc(pstate, 0); y_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1); } - - minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active); + + minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active); +} + +static void +skl_enable_plane_wm_levels(const struct drm_i915_private *dev_priv, + uint16_t plane_ddb, + uint16_t max_level, + struct skl_plane_wm *wm) +{ + int level; + /* + * Now enable all levels in WM structure which can be enabled + * using current DDB allocation + */ + for (level = ilk_wm_max_level(dev_priv); level >= 0; level--) { + struct skl_wm_level *level_wm = &wm->wm[level]; + + if (level > max_level || level_wm->plane_res_b == 0 + || level_wm->plane_res_l >= 31 + || level_wm->plane_res_b >= plane_ddb) { + level_wm->plane_en = false; + level_wm->plane_res_b = 0; + level_wm->plane_res_l = 0; + } else { + level_wm->plane_en = true; + } + } } static int skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, + struct skl_pipe_wm *pipe_wm, struct skl_ddb_allocation *ddb /* out */) { struct drm_atomic_state *state = cstate->base.state; struct drm_crtc *crtc = cstate->base.crtc; struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum pipe pipe = intel_crtc->pipe; struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb; @@ -3587,6 +4176,10 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, int num_active; unsigned plane_data_rate[I915_MAX_PLANES] = {}; unsigned plane_y_data_rate[I915_MAX_PLANES] = {}; + uint16_t total_min_blocks = 0; + uint16_t total_level_ddb; + uint16_t plane_blocks = 0; + int max_level, level; /* Clear the partitioning for disabled planes. */ memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); @@ -3602,10 +4195,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, skl_ddb_get_pipe_allocation_limits(dev, cstate, alloc, &num_active); alloc_size = skl_ddb_entry_size(alloc); - if (alloc_size == 0) { - memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); + if (alloc_size == 0) return 0; - } skl_ddb_calc_min(cstate, num_active, minimum, y_minimum); @@ -3616,13 +4207,59 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, */ for_each_plane_id_on_crtc(intel_crtc, plane_id) { - alloc_size -= minimum[plane_id]; - alloc_size -= y_minimum[plane_id]; + total_min_blocks += minimum[plane_id]; + total_min_blocks += y_minimum[plane_id]; } - ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR]; + if (total_min_blocks > alloc_size) { + DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations"); + DRM_DEBUG_KMS("minimum required %d/%d\n", total_min_blocks, + alloc_size); + return -EINVAL; + } + + alloc_size -= minimum[PLANE_CURSOR]; + ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - + minimum[PLANE_CURSOR]; ddb->plane[pipe][PLANE_CURSOR].end = alloc->end; + for (level = ilk_wm_max_level(dev_priv); level >= 0; level--) { + total_level_ddb = 0; + for_each_plane_id_on_crtc(intel_crtc, plane_id) { + /* + * TODO: We should calculate watermark values for Y/UV + * plane both in case of NV12 format and use both values + * for ddb calculation. NV12 is disabled as of now, So + * using only single/UV plane value here. + */ + struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + uint16_t plane_res_b = wm->wm[level].plane_res_b; + uint16_t min = minimum[plane_id] + y_minimum[plane_id]; + + if (plane_id == PLANE_CURSOR) + continue; + + total_level_ddb += max(plane_res_b, min); + } + + /* + * If This level can successfully be enabled with the + * pipe's current DDB allocation, then all lower levels are + * guaranteed to succeed as well. + */ + if (total_level_ddb <= alloc_size) + break; + } + + if ((level < 0) || (total_min_blocks > alloc_size)) { + DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations"); + DRM_DEBUG_KMS("minimum required %d/%d\n", (level < 0) ? + total_level_ddb : total_min_blocks, alloc_size); + return -EINVAL; + } + max_level = level; + alloc_size -= total_level_ddb; + /* * 2. Distribute the remaining space in proportion to the amount of * data each plane needs to fetch from memory. @@ -3632,13 +4269,24 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, total_data_rate = skl_get_total_relative_data_rate(cstate, plane_data_rate, plane_y_data_rate); + /* + * PLANE_CURSOR data rate is not included in total_data_rate. + * If only cursor plane is enabled we have to enable its WM levels + * explicitly before returning. Cursor has fixed ddb allocation, + * So it's ok to always check cursor WM enabling before return. + */ + plane_blocks = skl_ddb_entry_size(&ddb->plane[pipe][PLANE_CURSOR]); + skl_enable_plane_wm_levels(dev_priv, plane_blocks, max_level, + &pipe_wm->planes[PLANE_CURSOR]); if (total_data_rate == 0) return 0; start = alloc->start; for_each_plane_id_on_crtc(intel_crtc, plane_id) { unsigned int data_rate, y_data_rate; - uint16_t plane_blocks, y_plane_blocks = 0; + uint16_t plane_blocks = 0, y_plane_blocks = 0; + struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + uint16_t plane_res_b = wm->wm[max_level].plane_res_b; if (plane_id == PLANE_CURSOR) continue; @@ -3650,33 +4298,36 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, * promote the expression to 64 bits to avoid overflowing, the * result is < available as data_rate / total_data_rate < 1 */ - plane_blocks = minimum[plane_id]; - plane_blocks += div_u64((uint64_t)alloc_size * data_rate, - total_data_rate); /* Leave disabled planes at (0,0) */ if (data_rate) { + plane_blocks = max(minimum[plane_id], plane_res_b); + plane_blocks += div_u64((uint64_t)alloc_size * + data_rate, total_data_rate); ddb->plane[pipe][plane_id].start = start; ddb->plane[pipe][plane_id].end = start + plane_blocks; + start += plane_blocks; } - start += plane_blocks; - /* * allocation for y_plane part of planar format: + * TODO: Once we start calculating watermark values for Y/UV + * plane both consider it for initial allowed wm blocks. */ y_data_rate = plane_y_data_rate[plane_id]; - y_plane_blocks = y_minimum[plane_id]; - y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate, - total_data_rate); - if (y_data_rate) { + y_plane_blocks = y_minimum[plane_id]; + y_plane_blocks += div_u64((uint64_t)alloc_size * + y_data_rate, total_data_rate); ddb->y_plane[pipe][plane_id].start = start; ddb->y_plane[pipe][plane_id].end = start + y_plane_blocks; + start += y_plane_blocks; } - - start += y_plane_blocks; + skl_enable_plane_wm_levels(dev_priv, + plane_blocks, + max_level, + wm); } return 0; @@ -3698,7 +4349,7 @@ static uint_fixed_16_16_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp, return FP_16_16_MAX; wm_intermediate_val = latency * pixel_rate * cpp; - ret = fixed_16_16_div_round_up_u64(wm_intermediate_val, 1000 * 512); + ret = fixed_16_16_div_u64(wm_intermediate_val, 1000 * 512); return ret; } @@ -3720,12 +4371,33 @@ static uint_fixed_16_16_t skl_wm_method2(uint32_t pixel_rate, return ret; } -static uint32_t skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate, - struct intel_plane_state *pstate) +static uint_fixed_16_16_t +intel_get_linetime_us(struct intel_crtc_state *cstate) +{ + uint32_t pixel_rate; + uint32_t crtc_htotal; + uint_fixed_16_16_t linetime_us; + + if (!cstate->base.active) + return u32_to_fixed_16_16(0); + + pixel_rate = cstate->pixel_rate; + + if (WARN_ON(pixel_rate == 0)) + return u32_to_fixed_16_16(0); + + crtc_htotal = cstate->base.adjusted_mode.crtc_htotal; + linetime_us = fixed_16_16_div_u64(crtc_htotal * 1000, pixel_rate); + + return linetime_us; +} + +static uint32_t +skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate) { uint64_t adjusted_pixel_rate; - uint64_t downscale_amount; - uint64_t pixel_rate; + uint_fixed_16_16_t downscale_amount; /* Shouldn't reach here on disabled planes... */ if (WARN_ON(!intel_wm_plane_visible(cstate, pstate))) @@ -3738,24 +4410,20 @@ static uint32_t skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cst adjusted_pixel_rate = cstate->pixel_rate; downscale_amount = skl_plane_downscale_amount(cstate, pstate); - pixel_rate = adjusted_pixel_rate * downscale_amount >> 16; - WARN_ON(pixel_rate != clamp_t(uint32_t, pixel_rate, 0, ~0)); - - return pixel_rate; + return mul_round_up_u32_fixed16(adjusted_pixel_rate, + downscale_amount); } static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, struct intel_crtc_state *cstate, - struct intel_plane_state *intel_pstate, - uint16_t ddb_allocation, + const struct intel_plane_state *intel_pstate, int level, uint16_t *out_blocks, /* out */ - uint8_t *out_lines, /* out */ - bool *enabled /* out */) + uint8_t *out_lines /* out */) { struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane); - struct drm_plane_state *pstate = &intel_pstate->base; - struct drm_framebuffer *fb = pstate->fb; + const struct drm_plane_state *pstate = &intel_pstate->base; + const struct drm_framebuffer *fb = pstate->fb; uint32_t latency = dev_priv->wm.skl_latency[level]; uint_fixed_16_16_t method1, method2; uint_fixed_16_16_t plane_blocks_per_line; @@ -3774,10 +4442,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, bool y_tiled, x_tiled; if (latency == 0 || - !intel_wm_plane_visible(cstate, intel_pstate)) { - *enabled = false; + !intel_wm_plane_visible(cstate, intel_pstate)) return 0; - } y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED || fb->modifier == I915_FORMAT_MOD_Yf_TILED; @@ -3834,8 +4500,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, if (y_tiled) { interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line * y_min_scanlines, 512); - plane_blocks_per_line = - fixed_16_16_div_round_up(interm_pbpl, y_min_scanlines); + plane_blocks_per_line = fixed_16_16_div(interm_pbpl, + y_min_scanlines); } else if (x_tiled) { interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512); plane_blocks_per_line = u32_to_fixed_16_16(interm_pbpl); @@ -3856,19 +4522,22 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, if (y_tiled) { selected_result = max_fixed_16_16(method2, y_tile_minimum); } else { + uint32_t linetime_us; + + linetime_us = fixed_16_16_to_u32_round_up( + intel_get_linetime_us(cstate)); if ((cpp * cstate->base.adjusted_mode.crtc_htotal / 512 < 1) && (plane_bytes_per_line / 512 < 1)) selected_result = method2; - else if ((ddb_allocation / - fixed_16_16_to_u32_round_up(plane_blocks_per_line)) >= 1) + else if (latency >= linetime_us) selected_result = min_fixed_16_16(method1, method2); else selected_result = method1; } res_blocks = fixed_16_16_to_u32_round_up(selected_result) + 1; - res_lines = DIV_ROUND_UP(selected_result.val, - plane_blocks_per_line.val); + res_lines = div_round_up_fixed16(selected_result, + plane_blocks_per_line); if (level >= 1 && level <= 7) { if (y_tiled) { @@ -3879,82 +4548,45 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, } } - if (res_blocks >= ddb_allocation || res_lines > 31) { - *enabled = false; - - /* - * If there are no valid level 0 watermarks, then we can't - * support this display configuration. - */ - if (level) { - return 0; - } else { - struct drm_plane *plane = pstate->plane; + if (res_lines >= 31 && level == 0) { + struct drm_plane *plane = pstate->plane; - DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n"); - DRM_DEBUG_KMS("[PLANE:%d:%s] blocks required = %u/%u, lines required = %u/31\n", - plane->base.id, plane->name, - res_blocks, ddb_allocation, res_lines); - return -EINVAL; - } + DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n"); + DRM_DEBUG_KMS("[PLANE:%d:%s] lines required = %u/31\n", + plane->base.id, plane->name, res_lines); + return -EINVAL; } *out_blocks = res_blocks; *out_lines = res_lines; - *enabled = true; return 0; } static int -skl_compute_wm_level(const struct drm_i915_private *dev_priv, - struct skl_ddb_allocation *ddb, - struct intel_crtc_state *cstate, - struct intel_plane *intel_plane, - int level, - struct skl_wm_level *result) +skl_compute_wm_levels(const struct drm_i915_private *dev_priv, + struct intel_crtc_state *cstate, + const struct intel_plane_state *intel_pstate, + struct skl_plane_wm *wm) { - struct drm_atomic_state *state = cstate->base.state; - struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); - struct drm_plane *plane = &intel_plane->base; - struct intel_plane_state *intel_pstate = NULL; - uint16_t ddb_blocks; - enum pipe pipe = intel_crtc->pipe; + int level, max_level = ilk_wm_max_level(dev_priv); int ret; - if (state) - intel_pstate = - intel_atomic_get_existing_plane_state(state, - intel_plane); - - /* - * Note: If we start supporting multiple pending atomic commits against - * the same planes/CRTC's in the future, plane->state will no longer be - * the correct pre-state to use for the calculations here and we'll - * need to change where we get the 'unchanged' plane data from. - * - * For now this is fine because we only allow one queued commit against - * a CRTC. Even if the plane isn't modified by this transaction and we - * don't have a plane lock, we still have the CRTC's lock, so we know - * that no other transactions are racing with us to update it. - */ - if (!intel_pstate) - intel_pstate = to_intel_plane_state(plane->state); - - WARN_ON(!intel_pstate->base.fb); - - ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][intel_plane->id]); + if (WARN_ON(!intel_pstate->base.fb)) + return -EINVAL; - ret = skl_compute_plane_wm(dev_priv, - cstate, - intel_pstate, - ddb_blocks, - level, - &result->plane_res_b, - &result->plane_res_l, - &result->plane_en); - if (ret) - return ret; + for (level = 0; level <= max_level; level++) { + struct skl_wm_level *result = &wm->wm[level]; + + ret = skl_compute_plane_wm(dev_priv, + cstate, + intel_pstate, + level, + &result->plane_res_b, + &result->plane_res_l); + if (ret) + return ret; + } return 0; } @@ -3964,19 +4596,16 @@ skl_compute_linetime_wm(struct intel_crtc_state *cstate) { struct drm_atomic_state *state = cstate->base.state; struct drm_i915_private *dev_priv = to_i915(state->dev); - uint32_t pixel_rate; + uint_fixed_16_16_t linetime_us; uint32_t linetime_wm; - if (!cstate->base.active) - return 0; - - pixel_rate = cstate->pixel_rate; + linetime_us = intel_get_linetime_us(cstate); - if (WARN_ON(pixel_rate == 0)) + if (is_fixed16_zero(linetime_us)) return 0; - linetime_wm = DIV_ROUND_UP(8 * cstate->base.adjusted_mode.crtc_htotal * - 1000, pixel_rate); + linetime_wm = fixed_16_16_to_u32_round_up(mul_u32_fixed_16_16(8, + linetime_us)); /* Display WA #1135: bxt. */ if (IS_BROXTON(dev_priv) && dev_priv->ipc_enabled) @@ -4000,10 +4629,11 @@ static int skl_build_pipe_wm(struct intel_crtc_state *cstate, struct skl_pipe_wm *pipe_wm) { struct drm_device *dev = cstate->base.crtc->dev; + struct drm_crtc_state *crtc_state = &cstate->base; const struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane; + struct drm_plane *plane; + const struct drm_plane_state *pstate; struct skl_plane_wm *wm; - int level, max_level = ilk_wm_max_level(dev_priv); int ret; /* @@ -4012,18 +4642,16 @@ static int skl_build_pipe_wm(struct intel_crtc_state *cstate, */ memset(pipe_wm->planes, 0, sizeof(pipe_wm->planes)); - for_each_intel_plane_mask(&dev_priv->drm, - intel_plane, - cstate->base.plane_mask) { - wm = &pipe_wm->planes[intel_plane->id]; + drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) { + const struct intel_plane_state *intel_pstate = + to_intel_plane_state(pstate); + enum plane_id plane_id = to_intel_plane(plane)->id; - for (level = 0; level <= max_level; level++) { - ret = skl_compute_wm_level(dev_priv, ddb, cstate, - intel_plane, level, - &wm->wm[level]); - if (ret) - return ret; - } + wm = &pipe_wm->planes[plane_id]; + + ret = skl_compute_wm_levels(dev_priv, cstate, intel_pstate, wm); + if (ret) + return ret; skl_compute_transition_wm(cstate, &wm->trans_wm); } pipe_wm->linetime = skl_compute_linetime_wm(cstate); @@ -4134,6 +4762,45 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry **entries, return false; } +static int +skl_ddb_add_affected_planes(struct intel_crtc_state *cstate, + const struct skl_pipe_wm *old_pipe_wm, + const struct skl_pipe_wm *pipe_wm) +{ + struct drm_atomic_state *state = cstate->base.state; + struct drm_device *dev = state->dev; + struct drm_crtc *crtc = cstate->base.crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb; + struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb; + struct drm_plane_state *plane_state; + struct drm_plane *plane; + enum pipe pipe = intel_crtc->pipe; + + WARN_ON(!drm_atomic_get_existing_crtc_state(state, crtc)); + + drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) { + enum plane_id plane_id = to_intel_plane(plane)->id; + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + const struct skl_plane_wm *old_wm = &old_pipe_wm->planes[plane_id]; + + if ((skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id], + &new_ddb->plane[pipe][plane_id]) && + skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][plane_id], + &new_ddb->y_plane[pipe][plane_id])) && + !memcmp(wm, old_wm, sizeof(struct skl_plane_wm))) + continue; + + plane_state = drm_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + } + + return 0; +} + static int skl_update_pipe_wm(struct drm_crtc_state *cstate, const struct skl_pipe_wm *old_pipe_wm, struct skl_pipe_wm *pipe_wm, /* out */ @@ -4147,6 +4814,17 @@ static int skl_update_pipe_wm(struct drm_crtc_state *cstate, if (ret) return ret; + ret = skl_allocate_pipe_ddb(intel_cstate, pipe_wm, ddb); + if (ret) + return ret; + /* + * TODO: Planes are included in state to arm WM registers. + * Scope to optimize further, by just rewriting plane surf register. + */ + ret = skl_ddb_add_affected_planes(intel_cstate, old_pipe_wm, pipe_wm); + if (ret) + return ret; + if (!memcmp(old_pipe_wm, pipe_wm, sizeof(*pipe_wm))) *changed = false; else @@ -4169,41 +4847,7 @@ pipes_modified(struct drm_atomic_state *state) } static int -skl_ddb_add_affected_planes(struct intel_crtc_state *cstate) -{ - struct drm_atomic_state *state = cstate->base.state; - struct drm_device *dev = state->dev; - struct drm_crtc *crtc = cstate->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb; - struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb; - struct drm_plane_state *plane_state; - struct drm_plane *plane; - enum pipe pipe = intel_crtc->pipe; - - WARN_ON(!drm_atomic_get_existing_crtc_state(state, crtc)); - - drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) { - enum plane_id plane_id = to_intel_plane(plane)->id; - - if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id], - &new_ddb->plane[pipe][plane_id]) && - skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][plane_id], - &new_ddb->y_plane[pipe][plane_id])) - continue; - - plane_state = drm_atomic_get_plane_state(state, plane); - if (IS_ERR(plane_state)) - return PTR_ERR(plane_state); - } - - return 0; -} - -static int -skl_compute_ddb(struct drm_atomic_state *state) +skl_include_affected_crtcs(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; struct drm_i915_private *dev_priv = to_i915(dev); @@ -4267,14 +4911,6 @@ skl_compute_ddb(struct drm_atomic_state *state) cstate = intel_atomic_get_crtc_state(state, intel_crtc); if (IS_ERR(cstate)) return PTR_ERR(cstate); - - ret = skl_allocate_pipe_ddb(cstate, ddb); - if (ret) - return ret; - - ret = skl_ddb_add_affected_planes(cstate); - if (ret) - return ret; } return 0; @@ -4335,10 +4971,18 @@ skl_compute_wm(struct drm_atomic_state *state) struct drm_crtc_state *cstate; struct intel_atomic_state *intel_state = to_intel_atomic_state(state); struct skl_wm_values *results = &intel_state->wm_results; + struct drm_device *dev = state->dev; struct skl_pipe_wm *pipe_wm; bool changed = false; int ret, i; + /* + * When we distrust bios wm we always need to recompute to set the + * expected DDB allocations for each CRTC. + */ + if (to_i915(dev)->wm.distrust_bios_wm) + changed = true; + /* * If this transaction isn't actually touching any CRTC's, don't * bother with watermark calculation. Note that if we pass this @@ -4349,13 +4993,14 @@ skl_compute_wm(struct drm_atomic_state *state) */ for_each_new_crtc_in_state(state, crtc, cstate, i) changed = true; + if (!changed) return 0; /* Clear all dirty flags */ results->dirty_pipes = 0; - ret = skl_compute_ddb(state); + ret = skl_include_affected_crtcs(state); if (ret) return ret; @@ -4654,6 +5299,32 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) #define _FW_WM_VLV(value, plane) \ (((value) & DSPFW_ ## plane ## _MASK_VLV) >> DSPFW_ ## plane ## _SHIFT) +static void g4x_read_wm_values(struct drm_i915_private *dev_priv, + struct g4x_wm_values *wm) +{ + uint32_t tmp; + + tmp = I915_READ(DSPFW1); + wm->sr.plane = _FW_WM(tmp, SR); + wm->pipe[PIPE_B].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORB); + wm->pipe[PIPE_B].plane[PLANE_PRIMARY] = _FW_WM(tmp, PLANEB); + wm->pipe[PIPE_A].plane[PLANE_PRIMARY] = _FW_WM(tmp, PLANEA); + + tmp = I915_READ(DSPFW2); + wm->fbc_en = tmp & DSPFW_FBC_SR_EN; + wm->sr.fbc = _FW_WM(tmp, FBC_SR); + wm->hpll.fbc = _FW_WM(tmp, FBC_HPLL_SR); + wm->pipe[PIPE_B].plane[PLANE_SPRITE0] = _FW_WM(tmp, SPRITEB); + wm->pipe[PIPE_A].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORA); + wm->pipe[PIPE_A].plane[PLANE_SPRITE0] = _FW_WM(tmp, SPRITEA); + + tmp = I915_READ(DSPFW3); + wm->hpll_en = tmp & DSPFW_HPLL_SR_EN; + wm->sr.cursor = _FW_WM(tmp, CURSOR_SR); + wm->hpll.cursor = _FW_WM(tmp, HPLL_CURSOR); + wm->hpll.plane = _FW_WM(tmp, HPLL_SR); +} + static void vlv_read_wm_values(struct drm_i915_private *dev_priv, struct vlv_wm_values *wm) { @@ -4730,6 +5401,147 @@ static void vlv_read_wm_values(struct drm_i915_private *dev_priv, #undef _FW_WM #undef _FW_WM_VLV +void g4x_wm_get_hw_state(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct g4x_wm_values *wm = &dev_priv->wm.g4x; + struct intel_crtc *crtc; + + g4x_read_wm_values(dev_priv, wm); + + wm->cxsr = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN; + + for_each_intel_crtc(dev, crtc) { + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct g4x_wm_state *active = &crtc->wm.active.g4x; + struct g4x_pipe_wm *raw; + enum pipe pipe = crtc->pipe; + enum plane_id plane_id; + int level, max_level; + + active->cxsr = wm->cxsr; + active->hpll_en = wm->hpll_en; + active->fbc_en = wm->fbc_en; + + active->sr = wm->sr; + active->hpll = wm->hpll; + + for_each_plane_id_on_crtc(crtc, plane_id) { + active->wm.plane[plane_id] = + wm->pipe[pipe].plane[plane_id]; + } + + if (wm->cxsr && wm->hpll_en) + max_level = G4X_WM_LEVEL_HPLL; + else if (wm->cxsr) + max_level = G4X_WM_LEVEL_SR; + else + max_level = G4X_WM_LEVEL_NORMAL; + + level = G4X_WM_LEVEL_NORMAL; + raw = &crtc_state->wm.g4x.raw[level]; + for_each_plane_id_on_crtc(crtc, plane_id) + raw->plane[plane_id] = active->wm.plane[plane_id]; + + if (++level > max_level) + goto out; + + raw = &crtc_state->wm.g4x.raw[level]; + raw->plane[PLANE_PRIMARY] = active->sr.plane; + raw->plane[PLANE_CURSOR] = active->sr.cursor; + raw->plane[PLANE_SPRITE0] = 0; + raw->fbc = active->sr.fbc; + + if (++level > max_level) + goto out; + + raw = &crtc_state->wm.g4x.raw[level]; + raw->plane[PLANE_PRIMARY] = active->hpll.plane; + raw->plane[PLANE_CURSOR] = active->hpll.cursor; + raw->plane[PLANE_SPRITE0] = 0; + raw->fbc = active->hpll.fbc; + + out: + for_each_plane_id_on_crtc(crtc, plane_id) + g4x_raw_plane_wm_set(crtc_state, level, + plane_id, USHRT_MAX); + g4x_raw_fbc_wm_set(crtc_state, level, USHRT_MAX); + + crtc_state->wm.g4x.optimal = *active; + crtc_state->wm.g4x.intermediate = *active; + + DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n", + pipe_name(pipe), + wm->pipe[pipe].plane[PLANE_PRIMARY], + wm->pipe[pipe].plane[PLANE_CURSOR], + wm->pipe[pipe].plane[PLANE_SPRITE0]); + } + + DRM_DEBUG_KMS("Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n", + wm->sr.plane, wm->sr.cursor, wm->sr.fbc); + DRM_DEBUG_KMS("Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n", + wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc); + DRM_DEBUG_KMS("Initial SR=%s HPLL=%s FBC=%s\n", + yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en)); +} + +void g4x_wm_sanitize(struct drm_i915_private *dev_priv) +{ + struct intel_plane *plane; + struct intel_crtc *crtc; + + mutex_lock(&dev_priv->wm.wm_mutex); + + for_each_intel_plane(&dev_priv->drm, plane) { + struct intel_crtc *crtc = + intel_get_crtc_for_pipe(dev_priv, plane->pipe); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal; + enum plane_id plane_id = plane->id; + int level; + + if (plane_state->base.visible) + continue; + + for (level = 0; level < 3; level++) { + struct g4x_pipe_wm *raw = + &crtc_state->wm.g4x.raw[level]; + + raw->plane[plane_id] = 0; + wm_state->wm.plane[plane_id] = 0; + } + + if (plane_id == PLANE_PRIMARY) { + for (level = 0; level < 3; level++) { + struct g4x_pipe_wm *raw = + &crtc_state->wm.g4x.raw[level]; + raw->fbc = 0; + } + + wm_state->sr.fbc = 0; + wm_state->hpll.fbc = 0; + wm_state->fbc_en = false; + } + } + + for_each_intel_crtc(&dev_priv->drm, crtc) { + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + + crtc_state->wm.g4x.intermediate = + crtc_state->wm.g4x.optimal; + crtc->wm.active.g4x = crtc_state->wm.g4x.optimal; + } + + g4x_program_watermarks(dev_priv); + + mutex_unlock(&dev_priv->wm.wm_mutex); +} + void vlv_wm_get_hw_state(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -4792,7 +5604,7 @@ void vlv_wm_get_hw_state(struct drm_device *dev) active->cxsr = wm->cxsr; for (level = 0; level < active->num_levels; level++) { - struct vlv_pipe_wm *raw = + struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; active->sr[level].plane = wm->sr.plane; @@ -4852,7 +5664,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) continue; for (level = 0; level < wm_state->num_levels; level++) { - struct vlv_pipe_wm *raw = + struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level]; raw->plane[plane_id] = 0; @@ -8036,6 +8848,12 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->display.initial_watermarks = vlv_initial_watermarks; dev_priv->display.optimize_watermarks = vlv_optimize_watermarks; dev_priv->display.atomic_update_watermarks = vlv_atomic_update_fifo; + } else if (IS_G4X(dev_priv)) { + g4x_setup_wm_latency(dev_priv); + dev_priv->display.compute_pipe_wm = g4x_compute_pipe_wm; + dev_priv->display.compute_intermediate_wm = g4x_compute_intermediate_wm; + dev_priv->display.initial_watermarks = g4x_initial_watermarks; + dev_priv->display.optimize_watermarks = g4x_optimize_watermarks; } else if (IS_PINEVIEW(dev_priv)) { if (!intel_get_cxsr_latency(IS_PINEVIEW_G(dev_priv), dev_priv->is_ddr3, @@ -8051,8 +8869,6 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->display.update_wm = NULL; } else dev_priv->display.update_wm = pineview_update_wm; - } else if (IS_G4X(dev_priv)) { - dev_priv->display.update_wm = g4x_update_wm; } else if (IS_GEN4(dev_priv)) { dev_priv->display.update_wm = i965_update_wm; } else if (IS_GEN3(dev_priv)) { @@ -8135,9 +8951,9 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val I915_WRITE_FW(GEN6_PCODE_DATA1, 0); I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox); - if (intel_wait_for_register_fw(dev_priv, - GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0, - 500)) { + if (__intel_wait_for_register_fw(dev_priv, + GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0, + 500, 0, NULL)) { DRM_ERROR("timeout waiting for pcode read (%d) to finish\n", mbox); return -ETIMEDOUT; } @@ -8180,9 +8996,9 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, I915_WRITE_FW(GEN6_PCODE_DATA1, 0); I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox); - if (intel_wait_for_register_fw(dev_priv, - GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0, - 500)) { + if (__intel_wait_for_register_fw(dev_priv, + GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0, + 500, 0, NULL)) { DRM_ERROR("timeout waiting for pcode write (%d) to finish\n", mbox); return -ETIMEDOUT; } diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index c3780d0d2baf75..559f1ab42bfc23 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -435,8 +435,9 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp) } /* PSR2 is restricted to work with panel resolutions upto 3200x2000 */ - if (intel_crtc->config->pipe_src_w > 3200 || - intel_crtc->config->pipe_src_h > 2000) { + if (dev_priv->psr.psr2_support && + (intel_crtc->config->pipe_src_w > 3200 || + intel_crtc->config->pipe_src_h > 2000)) { dev_priv->psr.psr2_support = false; return false; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 66a2b8b8397269..acd1da9b62a3f2 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -39,17 +39,27 @@ */ #define LEGACY_REQUEST_SIZE 200 -static int __intel_ring_space(int head, int tail, int size) +static unsigned int __intel_ring_space(unsigned int head, + unsigned int tail, + unsigned int size) { - int space = head - tail; - if (space <= 0) - space += size; - return space - I915_RING_FREE_SPACE; + /* + * "If the Ring Buffer Head Pointer and the Tail Pointer are on the + * same cacheline, the Head Pointer must not be greater than the Tail + * Pointer." + */ + GEM_BUG_ON(!is_power_of_2(size)); + return (head - tail - CACHELINE_BYTES) & (size - 1); } -void intel_ring_update_space(struct intel_ring *ring) +unsigned int intel_ring_update_space(struct intel_ring *ring) { - ring->space = __intel_ring_space(ring->head, ring->tail, ring->size); + unsigned int space; + + space = __intel_ring_space(ring->head, ring->emit, ring->size); + + ring->space = space; + return space; } static int @@ -538,9 +548,9 @@ static int init_ring_common(struct intel_engine_cs *engine) I915_WRITE_CTL(engine, RING_CTL_SIZE(ring->size) | RING_VALID); /* If the head is still not zero, the ring is dead */ - if (intel_wait_for_register_fw(dev_priv, RING_CTL(engine->mmio_base), - RING_VALID, RING_VALID, - 50)) { + if (intel_wait_for_register(dev_priv, RING_CTL(engine->mmio_base), + RING_VALID, RING_VALID, + 50)) { DRM_ERROR("%s initialization failed " "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", engine->name, @@ -774,8 +784,8 @@ static void i9xx_submit_request(struct drm_i915_gem_request *request) i915_gem_request_submit(request); - assert_ring_tail_valid(request->ring, request->tail); - I915_WRITE_TAIL(request->engine, request->tail); + I915_WRITE_TAIL(request->engine, + intel_ring_set_tail(request->ring, request->tail)); } static void i9xx_emit_breadcrumb(struct drm_i915_gem_request *req, u32 *cs) @@ -1259,6 +1269,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + GEM_BUG_ON(engine->id != RCS); + dev_priv->status_page_dmah = drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE); if (!dev_priv->status_page_dmah) @@ -1270,17 +1282,18 @@ static int init_phys_status_page(struct intel_engine_cs *engine) return 0; } -int intel_ring_pin(struct intel_ring *ring, unsigned int offset_bias) +int intel_ring_pin(struct intel_ring *ring, + struct drm_i915_private *i915, + unsigned int offset_bias) { - unsigned int flags; - enum i915_map_type map; + enum i915_map_type map = HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC; struct i915_vma *vma = ring->vma; + unsigned int flags; void *addr; int ret; GEM_BUG_ON(ring->vaddr); - map = HAS_LLC(ring->engine->i915) ? I915_MAP_WB : I915_MAP_WC; flags = PIN_GLOBAL; if (offset_bias) @@ -1316,11 +1329,23 @@ int intel_ring_pin(struct intel_ring *ring, unsigned int offset_bias) return PTR_ERR(addr); } +void intel_ring_reset(struct intel_ring *ring, u32 tail) +{ + GEM_BUG_ON(!list_empty(&ring->request_list)); + ring->tail = tail; + ring->head = tail; + ring->emit = tail; + intel_ring_update_space(ring); +} + void intel_ring_unpin(struct intel_ring *ring) { GEM_BUG_ON(!ring->vma); GEM_BUG_ON(!ring->vaddr); + /* Discard any unused bytes beyond that submitted to hw. */ + intel_ring_reset(ring, ring->tail); + if (i915_vma_is_map_and_fenceable(ring->vma)) i915_vma_unpin_iomap(ring->vma); else @@ -1338,7 +1363,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) obj = i915_gem_object_create_stolen(dev_priv, size); if (!obj) - obj = i915_gem_object_create(dev_priv, size); + obj = i915_gem_object_create_internal(dev_priv, size); if (IS_ERR(obj)) return ERR_CAST(obj); @@ -1369,8 +1394,6 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size) if (!ring) return ERR_PTR(-ENOMEM); - ring->engine = engine; - INIT_LIST_HEAD(&ring->request_list); ring->size = size; @@ -1424,22 +1447,73 @@ static int context_pin(struct i915_gem_context *ctx) PIN_GLOBAL | PIN_HIGH); } -static int intel_ring_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static struct i915_vma * +alloc_context_vma(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + + obj = i915_gem_object_create(i915, engine->context_size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + /* + * Try to make the context utilize L3 as well as LLC. + * + * On VLV we don't have L3 controls in the PTEs so we + * shouldn't touch the cache level, especially as that + * would make the object snooped which might have a + * negative performance impact. + * + * Snooping is required on non-llc platforms in execlist + * mode, but since all GGTT accesses use PAT entry 0 we + * get snooping anyway regardless of cache_level. + * + * This is only applicable for Ivy Bridge devices since + * later platforms don't have L3 control bits in the PTE. + */ + if (IS_IVYBRIDGE(i915)) { + /* Ignore any error, regard it as a simple optimisation */ + i915_gem_object_set_cache_level(obj, I915_CACHE_L3_LLC); + } + + vma = i915_vma_instance(obj, &i915->ggtt.base, NULL); + if (IS_ERR(vma)) + i915_gem_object_put(obj); + + return vma; +} + +static struct intel_ring * +intel_ring_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { struct intel_context *ce = &ctx->engine[engine->id]; int ret; lockdep_assert_held(&ctx->i915->drm.struct_mutex); - if (ce->pin_count++) - return 0; + if (likely(ce->pin_count++)) + goto out; GEM_BUG_ON(!ce->pin_count); /* no overflow please! */ + if (!ce->state && engine->context_size) { + struct i915_vma *vma; + + vma = alloc_context_vma(engine); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err; + } + + ce->state = vma; + } + if (ce->state) { ret = context_pin(ctx); if (ret) - goto error; + goto err; ce->state->obj->mm.dirty = true; } @@ -1455,11 +1529,14 @@ static int intel_ring_context_pin(struct intel_engine_cs *engine, ce->initialised = true; i915_gem_context_get(ctx); - return 0; -error: +out: + /* One ringbuffer to rule them all */ + return engine->buffer; + +err: ce->pin_count = 0; - return ret; + return ERR_PTR(ret); } static void intel_ring_context_unpin(struct intel_engine_cs *engine, @@ -1481,78 +1558,70 @@ static void intel_ring_context_unpin(struct intel_engine_cs *engine, static int intel_init_ring_buffer(struct intel_engine_cs *engine) { - struct drm_i915_private *dev_priv = engine->i915; struct intel_ring *ring; - int ret; - - WARN_ON(engine->buffer); + int err; intel_engine_setup_common(engine); - ret = intel_engine_init_common(engine); - if (ret) - goto error; + err = intel_engine_init_common(engine); + if (err) + goto err; + + if (HWS_NEEDS_PHYSICAL(engine->i915)) + err = init_phys_status_page(engine); + else + err = init_status_page(engine); + if (err) + goto err; ring = intel_engine_create_ring(engine, 32 * PAGE_SIZE); if (IS_ERR(ring)) { - ret = PTR_ERR(ring); - goto error; - } - - if (HWS_NEEDS_PHYSICAL(dev_priv)) { - WARN_ON(engine->id != RCS); - ret = init_phys_status_page(engine); - if (ret) - goto error; - } else { - ret = init_status_page(engine); - if (ret) - goto error; + err = PTR_ERR(ring); + goto err_hws; } /* Ring wraparound at offset 0 sometimes hangs. No idea why. */ - ret = intel_ring_pin(ring, I915_GTT_PAGE_SIZE); - if (ret) { - intel_ring_free(ring); - goto error; - } + err = intel_ring_pin(ring, engine->i915, I915_GTT_PAGE_SIZE); + if (err) + goto err_ring; + + GEM_BUG_ON(engine->buffer); engine->buffer = ring; return 0; -error: - intel_engine_cleanup(engine); - return ret; +err_ring: + intel_ring_free(ring); +err_hws: + if (HWS_NEEDS_PHYSICAL(engine->i915)) + cleanup_phys_status_page(engine); + else + cleanup_status_page(engine); +err: + intel_engine_cleanup_common(engine); + return err; } void intel_engine_cleanup(struct intel_engine_cs *engine) { - struct drm_i915_private *dev_priv; - - dev_priv = engine->i915; + struct drm_i915_private *dev_priv = engine->i915; - if (engine->buffer) { - WARN_ON(INTEL_GEN(dev_priv) > 2 && - (I915_READ_MODE(engine) & MODE_IDLE) == 0); + WARN_ON(INTEL_GEN(dev_priv) > 2 && + (I915_READ_MODE(engine) & MODE_IDLE) == 0); - intel_ring_unpin(engine->buffer); - intel_ring_free(engine->buffer); - engine->buffer = NULL; - } + intel_ring_unpin(engine->buffer); + intel_ring_free(engine->buffer); if (engine->cleanup) engine->cleanup(engine); - if (HWS_NEEDS_PHYSICAL(dev_priv)) { - WARN_ON(engine->id != RCS); + if (HWS_NEEDS_PHYSICAL(dev_priv)) cleanup_phys_status_page(engine); - } else { + else cleanup_status_page(engine); - } intel_engine_cleanup_common(engine); - engine->i915 = NULL; dev_priv->engine[engine->id] = NULL; kfree(engine); } @@ -1562,8 +1631,9 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv) struct intel_engine_cs *engine; enum intel_engine_id id; + /* Restart from the beginning of the rings for convenience */ for_each_engine(engine, dev_priv, id) - engine->buffer->head = engine->buffer->tail; + intel_ring_reset(engine->buffer, 0); } static int ring_request_alloc(struct drm_i915_gem_request *request) @@ -1578,9 +1648,6 @@ static int ring_request_alloc(struct drm_i915_gem_request *request) */ request->reserved_space += LEGACY_REQUEST_SIZE; - GEM_BUG_ON(!request->engine->buffer); - request->ring = request->engine->buffer; - cs = intel_ring_begin(request, 0); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -1589,7 +1656,8 @@ static int ring_request_alloc(struct drm_i915_gem_request *request) return 0; } -static int wait_for_space(struct drm_i915_gem_request *req, int bytes) +static noinline int wait_for_space(struct drm_i915_gem_request *req, + unsigned int bytes) { struct intel_ring *ring = req->ring; struct drm_i915_gem_request *target; @@ -1597,8 +1665,7 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes) lockdep_assert_held(&req->i915->drm.struct_mutex); - intel_ring_update_space(ring); - if (ring->space >= bytes) + if (intel_ring_update_space(ring) >= bytes) return 0; /* @@ -1613,12 +1680,9 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes) GEM_BUG_ON(!req->reserved_space); list_for_each_entry(target, &ring->request_list, ring_link) { - unsigned space; - /* Would completion of this request free enough space? */ - space = __intel_ring_space(target->postfix, ring->tail, - ring->size); - if (space >= bytes) + if (bytes <= __intel_ring_space(target->postfix, + ring->emit, ring->size)) break; } @@ -1638,59 +1702,64 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes) return 0; } -u32 *intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords) +u32 *intel_ring_begin(struct drm_i915_gem_request *req, + unsigned int num_dwords) { struct intel_ring *ring = req->ring; - int remain_actual = ring->size - ring->tail; - int remain_usable = ring->effective_size - ring->tail; - int bytes = num_dwords * sizeof(u32); - int total_bytes, wait_bytes; - bool need_wrap = false; + const unsigned int remain_usable = ring->effective_size - ring->emit; + const unsigned int bytes = num_dwords * sizeof(u32); + unsigned int need_wrap = 0; + unsigned int total_bytes; u32 *cs; total_bytes = bytes + req->reserved_space; + GEM_BUG_ON(total_bytes > ring->effective_size); - if (unlikely(bytes > remain_usable)) { - /* - * Not enough space for the basic request. So need to flush - * out the remainder and then wait for base + reserved. - */ - wait_bytes = remain_actual + total_bytes; - need_wrap = true; - } else if (unlikely(total_bytes > remain_usable)) { - /* - * The base request will fit but the reserved space - * falls off the end. So we don't need an immediate wrap - * and only need to effectively wait for the reserved - * size space from the start of ringbuffer. - */ - wait_bytes = remain_actual + req->reserved_space; - } else { - /* No wrapping required, just waiting. */ - wait_bytes = total_bytes; + if (unlikely(total_bytes > remain_usable)) { + const int remain_actual = ring->size - ring->emit; + + if (bytes > remain_usable) { + /* + * Not enough space for the basic request. So need to + * flush out the remainder and then wait for + * base + reserved. + */ + total_bytes += remain_actual; + need_wrap = remain_actual | 1; + } else { + /* + * The base request will fit but the reserved space + * falls off the end. So we don't need an immediate + * wrap and only need to effectively wait for the + * reserved size from the start of ringbuffer. + */ + total_bytes = req->reserved_space + remain_actual; + } } - if (wait_bytes > ring->space) { - int ret = wait_for_space(req, wait_bytes); + if (unlikely(total_bytes > ring->space)) { + int ret = wait_for_space(req, total_bytes); if (unlikely(ret)) return ERR_PTR(ret); } if (unlikely(need_wrap)) { - GEM_BUG_ON(remain_actual > ring->space); - GEM_BUG_ON(ring->tail + remain_actual > ring->size); + need_wrap &= ~1; + GEM_BUG_ON(need_wrap > ring->space); + GEM_BUG_ON(ring->emit + need_wrap > ring->size); /* Fill the tail with MI_NOOP */ - memset(ring->vaddr + ring->tail, 0, remain_actual); - ring->tail = 0; - ring->space -= remain_actual; + memset(ring->vaddr + ring->emit, 0, need_wrap); + ring->emit = 0; + ring->space -= need_wrap; } - GEM_BUG_ON(ring->tail > ring->size - bytes); - cs = ring->vaddr + ring->tail; - ring->tail += bytes; + GEM_BUG_ON(ring->emit > ring->size - bytes); + GEM_BUG_ON(ring->space < bytes); + cs = ring->vaddr + ring->emit; + GEM_DEBUG_EXEC(memset(cs, POISON_INUSE, bytes)); + ring->emit += bytes; ring->space -= bytes; - GEM_BUG_ON(ring->space < 0); return cs; } @@ -1699,7 +1768,7 @@ u32 *intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords) int intel_ring_cacheline_align(struct drm_i915_gem_request *req) { int num_dwords = - (req->ring->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); + (req->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); u32 *cs; if (num_dwords == 0) @@ -1736,11 +1805,11 @@ static void gen6_bsd_submit_request(struct drm_i915_gem_request *request) I915_WRITE64_FW(GEN6_BSD_RNCID, 0x0); /* Wait for the ring not to be idle, i.e. for it to wake up. */ - if (intel_wait_for_register_fw(dev_priv, - GEN6_BSD_SLEEP_PSMI_CONTROL, - GEN6_BSD_SLEEP_INDICATOR, - 0, - 50)) + if (__intel_wait_for_register_fw(dev_priv, + GEN6_BSD_SLEEP_PSMI_CONTROL, + GEN6_BSD_SLEEP_INDICATOR, + 0, + 1000, 0, NULL)) DRM_ERROR("timed out waiting for the BSD ring to wake up\n"); /* Now that the ring is fully powered up, update the tail */ @@ -2182,20 +2251,6 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine) return intel_init_ring_buffer(engine); } -/** - * Initialize the second BSD ring (eg. Broadwell GT3, Skylake GT3) - */ -int intel_init_bsd2_ring_buffer(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - - intel_ring_default_vfuncs(dev_priv, engine); - - engine->emit_flush = gen6_bsd_ring_flush; - - return intel_init_ring_buffer(engine); -} - int intel_init_blt_ring_buffer(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index a82a0807f64dbd..6aa20ac8cde388 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -17,17 +17,6 @@ #define CACHELINE_BYTES 64 #define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(uint32_t)) -/* - * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use" - * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use" - * Gen4+ BSpec "vol1c Memory Interface and Command Stream" / 5.3.4.5 "Ring Buffer Use" - * - * "If the Ring Buffer Head Pointer and the Tail Pointer are on the same - * cacheline, the Head Pointer must not be greater than the Tail - * Pointer." - */ -#define I915_RING_FREE_SPACE 64 - struct intel_hw_status_page { struct i915_vma *vma; u32 *page_addr; @@ -139,16 +128,15 @@ struct intel_ring { struct i915_vma *vma; void *vaddr; - struct intel_engine_cs *engine; - struct list_head request_list; u32 head; u32 tail; + u32 emit; - int space; - int size; - int effective_size; + u32 space; + u32 size; + u32 effective_size; }; struct i915_gem_context; @@ -189,15 +177,28 @@ enum intel_engine_id { VECS }; +struct i915_priolist { + struct rb_node node; + struct list_head requests; + int priority; +}; + +#define INTEL_ENGINE_CS_MAX_NAME 8 + struct intel_engine_cs { struct drm_i915_private *i915; - const char *name; + char name[INTEL_ENGINE_CS_MAX_NAME]; enum intel_engine_id id; - unsigned int exec_id; + unsigned int uabi_id; unsigned int hw_id; unsigned int guc_id; - u32 mmio_base; + + u8 class; + u8 instance; + u32 context_size; + u32 mmio_base; unsigned int irq_shift; + struct intel_ring *buffer; struct intel_timeline *timeline; @@ -265,8 +266,8 @@ struct intel_engine_cs { void (*set_default_submission)(struct intel_engine_cs *engine); - int (*context_pin)(struct intel_engine_cs *engine, - struct i915_gem_context *ctx); + struct intel_ring *(*context_pin)(struct intel_engine_cs *engine, + struct i915_gem_context *ctx); void (*context_unpin)(struct intel_engine_cs *engine, struct i915_gem_context *ctx); int (*request_alloc)(struct drm_i915_gem_request *req); @@ -372,9 +373,18 @@ struct intel_engine_cs { /* Execlists */ struct tasklet_struct irq_tasklet; + struct i915_priolist default_priolist; + bool no_priolist; struct execlist_port { - struct drm_i915_gem_request *request; - unsigned int count; + struct drm_i915_gem_request *request_count; +#define EXECLIST_COUNT_BITS 2 +#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS) +#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS) +#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS) +#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS) +#define port_set(p, packed) ((p)->request_count = (packed)) +#define port_isset(p) ((p)->request_count) +#define port_index(p, e) ((p) - (e)->execlist_port) GEM_DEBUG_DECL(u32 context_id); } execlist_port[2]; struct rb_root execlist_queue; @@ -487,7 +497,11 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value) struct intel_ring * intel_engine_create_ring(struct intel_engine_cs *engine, int size); -int intel_ring_pin(struct intel_ring *ring, unsigned int offset_bias); +int intel_ring_pin(struct intel_ring *ring, + struct drm_i915_private *i915, + unsigned int offset_bias); +void intel_ring_reset(struct intel_ring *ring, u32 tail); +unsigned int intel_ring_update_space(struct intel_ring *ring); void intel_ring_unpin(struct intel_ring *ring); void intel_ring_free(struct intel_ring *ring); @@ -498,7 +512,8 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv); int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req); -u32 __must_check *intel_ring_begin(struct drm_i915_gem_request *req, int n); +u32 __must_check *intel_ring_begin(struct drm_i915_gem_request *req, + unsigned int n); static inline void intel_ring_advance(struct drm_i915_gem_request *req, u32 *cs) @@ -511,7 +526,7 @@ intel_ring_advance(struct drm_i915_gem_request *req, u32 *cs) * reserved for the command packet (i.e. the value passed to * intel_ring_begin()). */ - GEM_BUG_ON((req->ring->vaddr + req->ring->tail) != cs); + GEM_BUG_ON((req->ring->vaddr + req->ring->emit) != cs); } static inline u32 @@ -538,9 +553,40 @@ assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail) */ GEM_BUG_ON(!IS_ALIGNED(tail, 8)); GEM_BUG_ON(tail >= ring->size); + + /* + * "Ring Buffer Use" + * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 + * Gen3 BSpec "1c Memory Interface Functions" / 2.3.4.5 + * Gen4+ BSpec "1c Memory Interface and Command Stream" / 5.3.4.5 + * "If the Ring Buffer Head Pointer and the Tail Pointer are on the + * same cacheline, the Head Pointer must not be greater than the Tail + * Pointer." + * + * We use ring->head as the last known location of the actual RING_HEAD, + * it may have advanced but in the worst case it is equally the same + * as ring->head and so we should never program RING_TAIL to advance + * into the same cacheline as ring->head. + */ +#define cacheline(a) round_down(a, CACHELINE_BYTES) + GEM_BUG_ON(cacheline(tail) == cacheline(ring->head) && + tail < ring->head); +#undef cacheline } -void intel_ring_update_space(struct intel_ring *ring); +static inline unsigned int +intel_ring_set_tail(struct intel_ring *ring, unsigned int tail) +{ + /* Whilst writes to the tail are strictly order, there is no + * serialisation between readers and the writers. The tail may be + * read by i915_gem_request_retire() just as it is being updated + * by execlists, as although the breadcrumb is complete, the context + * switch hasn't been seen. + */ + assert_ring_tail_valid(ring, tail); + ring->tail = tail; + return tail; +} void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno); @@ -551,7 +597,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine); int intel_init_render_ring_buffer(struct intel_engine_cs *engine); int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine); -int intel_init_bsd2_ring_buffer(struct intel_engine_cs *engine); int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine); @@ -652,7 +697,8 @@ bool intel_engine_add_wait(struct intel_engine_cs *engine, struct intel_wait *wait); void intel_engine_remove_wait(struct intel_engine_cs *engine, struct intel_wait *wait); -void intel_engine_enable_signaling(struct drm_i915_gem_request *request); +void intel_engine_enable_signaling(struct drm_i915_gem_request *request, + bool wakeup); void intel_engine_cancel_signaling(struct drm_i915_gem_request *request); static inline bool intel_engine_has_waiter(const struct intel_engine_cs *engine) @@ -685,6 +731,7 @@ static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset) bool intel_engine_is_idle(struct intel_engine_cs *engine); bool intel_engines_are_idle(struct drm_i915_private *dev_priv); +void intel_engines_mark_idle(struct drm_i915_private *i915); void intel_engines_reset_default_submission(struct drm_i915_private *i915); #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 816a6f5a3fd948..f4329d20b6f6f0 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -99,18 +99,6 @@ struct intel_sdvo { */ uint16_t hotplug_active; - /** - * This is used to select the color range of RBG outputs in HDMI mode. - * It is only valid when using TMDS encoding and 8 bit per color mode. - */ - uint32_t color_range; - bool color_range_auto; - - /** - * HDMI user specified aspect ratio - */ - enum hdmi_picture_aspect aspect_ratio; - /** * This is set if we're going to treat the device as TV-out. * @@ -122,9 +110,6 @@ struct intel_sdvo { enum port port; - /* This is for current tv format name */ - int tv_format_index; - /** * This is set if we treat the device as HDMI, instead of DVI. */ @@ -159,8 +144,6 @@ struct intel_sdvo_connector { /* Mark the type of connector */ uint16_t output_flag; - enum hdmi_force_audio force_audio; - /* This contains all current supported TV format */ u8 tv_format_supported[TV_FORMAT_NUM]; int format_supported_num; @@ -187,24 +170,19 @@ struct intel_sdvo_connector { /* add the property for the SDVO-TV/LVDS */ struct drm_property *brightness; - /* Add variable to record current setting for the above property */ - u32 left_margin, right_margin, top_margin, bottom_margin; - /* this is to get the range of margin.*/ - u32 max_hscan, max_vscan; - u32 max_hpos, cur_hpos; - u32 max_vpos, cur_vpos; - u32 cur_brightness, max_brightness; - u32 cur_contrast, max_contrast; - u32 cur_saturation, max_saturation; - u32 cur_hue, max_hue; - u32 cur_sharpness, max_sharpness; - u32 cur_flicker_filter, max_flicker_filter; - u32 cur_flicker_filter_adaptive, max_flicker_filter_adaptive; - u32 cur_flicker_filter_2d, max_flicker_filter_2d; - u32 cur_tv_chroma_filter, max_tv_chroma_filter; - u32 cur_tv_luma_filter, max_tv_luma_filter; - u32 cur_dot_crawl, max_dot_crawl; + u32 max_hscan, max_vscan; +}; + +struct intel_sdvo_connector_state { + /* base.base: tv.saturation/contrast/hue/brightness */ + struct intel_digital_connector_state base; + + struct { + unsigned overscan_h, overscan_v, hpos, vpos, sharpness; + unsigned flicker_filter, flicker_filter_2d, flicker_filter_adaptive; + unsigned chroma_filter, luma_filter, dot_crawl; + } tv; }; static struct intel_sdvo *to_sdvo(struct intel_encoder *encoder) @@ -217,9 +195,16 @@ static struct intel_sdvo *intel_attached_sdvo(struct drm_connector *connector) return to_sdvo(intel_attached_encoder(connector)); } -static struct intel_sdvo_connector *to_intel_sdvo_connector(struct drm_connector *connector) +static struct intel_sdvo_connector * +to_intel_sdvo_connector(struct drm_connector *connector) +{ + return container_of(connector, struct intel_sdvo_connector, base.base); +} + +static struct intel_sdvo_connector_state * +to_intel_sdvo_connector_state(struct drm_connector_state *conn_state) { - return container_of(to_intel_connector(connector), struct intel_sdvo_connector, base); + return container_of(conn_state, struct intel_sdvo_connector_state, base.base); } static bool @@ -1035,12 +1020,13 @@ static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo, sdvo_data, sizeof(sdvo_data)); } -static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo) +static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo, + struct drm_connector_state *conn_state) { struct intel_sdvo_tv_format format; uint32_t format_map; - format_map = 1 << intel_sdvo->tv_format_index; + format_map = 1 << conn_state->tv.mode; memset(&format, 0, sizeof(format)); memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map))); @@ -1127,6 +1113,8 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, struct drm_connector_state *conn_state) { struct intel_sdvo *intel_sdvo = to_sdvo(encoder); + struct intel_sdvo_connector_state *intel_sdvo_state = + to_intel_sdvo_connector_state(conn_state); struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; struct drm_display_mode *mode = &pipe_config->base.mode; @@ -1165,9 +1153,14 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, pipe_config->pixel_multiplier = intel_sdvo_get_pixel_multiplier(adjusted_mode); - pipe_config->has_hdmi_sink = intel_sdvo->has_hdmi_monitor; + if (intel_sdvo_state->base.force_audio != HDMI_AUDIO_OFF_DVI) + pipe_config->has_hdmi_sink = intel_sdvo->has_hdmi_monitor; - if (intel_sdvo->color_range_auto) { + if (intel_sdvo_state->base.force_audio == HDMI_AUDIO_ON || + (intel_sdvo_state->base.force_audio == HDMI_AUDIO_AUTO && intel_sdvo->has_hdmi_audio)) + pipe_config->has_audio = true; + + if (intel_sdvo_state->base.broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ /* FIXME: This bit is only valid when using TMDS encoding and 8 * bit per color mode. */ @@ -1176,7 +1169,7 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, pipe_config->limited_color_range = true; } else { if (pipe_config->has_hdmi_sink && - intel_sdvo->color_range == HDMI_COLOR_RANGE_16_235) + intel_sdvo_state->base.broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED) pipe_config->limited_color_range = true; } @@ -1186,11 +1179,73 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, /* Set user selected PAR to incoming mode's member */ if (intel_sdvo->is_hdmi) - adjusted_mode->picture_aspect_ratio = intel_sdvo->aspect_ratio; + adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio; return true; } +#define UPDATE_PROPERTY(input, NAME) \ + do { \ + val = input; \ + intel_sdvo_set_value(intel_sdvo, SDVO_CMD_SET_##NAME, &val, sizeof(val)); \ + } while (0) + +static void intel_sdvo_update_props(struct intel_sdvo *intel_sdvo, + struct intel_sdvo_connector_state *sdvo_state) +{ + struct drm_connector_state *conn_state = &sdvo_state->base.base; + struct intel_sdvo_connector *intel_sdvo_conn = + to_intel_sdvo_connector(conn_state->connector); + uint16_t val; + + if (intel_sdvo_conn->left) + UPDATE_PROPERTY(sdvo_state->tv.overscan_h, OVERSCAN_H); + + if (intel_sdvo_conn->top) + UPDATE_PROPERTY(sdvo_state->tv.overscan_v, OVERSCAN_V); + + if (intel_sdvo_conn->hpos) + UPDATE_PROPERTY(sdvo_state->tv.hpos, HPOS); + + if (intel_sdvo_conn->vpos) + UPDATE_PROPERTY(sdvo_state->tv.vpos, VPOS); + + if (intel_sdvo_conn->saturation) + UPDATE_PROPERTY(conn_state->tv.saturation, SATURATION); + + if (intel_sdvo_conn->contrast) + UPDATE_PROPERTY(conn_state->tv.contrast, CONTRAST); + + if (intel_sdvo_conn->hue) + UPDATE_PROPERTY(conn_state->tv.hue, HUE); + + if (intel_sdvo_conn->brightness) + UPDATE_PROPERTY(conn_state->tv.brightness, BRIGHTNESS); + + if (intel_sdvo_conn->sharpness) + UPDATE_PROPERTY(sdvo_state->tv.sharpness, SHARPNESS); + + if (intel_sdvo_conn->flicker_filter) + UPDATE_PROPERTY(sdvo_state->tv.flicker_filter, FLICKER_FILTER); + + if (intel_sdvo_conn->flicker_filter_2d) + UPDATE_PROPERTY(sdvo_state->tv.flicker_filter_2d, FLICKER_FILTER_2D); + + if (intel_sdvo_conn->flicker_filter_adaptive) + UPDATE_PROPERTY(sdvo_state->tv.flicker_filter_adaptive, FLICKER_FILTER_ADAPTIVE); + + if (intel_sdvo_conn->tv_chroma_filter) + UPDATE_PROPERTY(sdvo_state->tv.chroma_filter, TV_CHROMA_FILTER); + + if (intel_sdvo_conn->tv_luma_filter) + UPDATE_PROPERTY(sdvo_state->tv.luma_filter, TV_LUMA_FILTER); + + if (intel_sdvo_conn->dot_crawl) + UPDATE_PROPERTY(sdvo_state->tv.dot_crawl, DOT_CRAWL); + +#undef UPDATE_PROPERTY +} + static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, struct intel_crtc_state *crtc_state, struct drm_connector_state *conn_state) @@ -1198,6 +1253,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev); struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode; + struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(conn_state); struct drm_display_mode *mode = &crtc_state->base.mode; struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder); u32 sdvox; @@ -1205,6 +1261,8 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, struct intel_sdvo_dtd input_dtd, output_dtd; int rate; + intel_sdvo_update_props(intel_sdvo, sdvo_state); + /* First, set the input mapping for the first input to our controlled * output. This is only correct if we're a single-input device, in * which case the first input is the output from the appropriate SDVO @@ -1246,7 +1304,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_DVI); if (intel_sdvo->is_tv && - !intel_sdvo_set_tv_format(intel_sdvo)) + !intel_sdvo_set_tv_format(intel_sdvo, conn_state)) return; intel_sdvo_get_dtd_from_mode(&input_dtd, adjusted_mode); @@ -1290,7 +1348,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, else sdvox |= SDVO_PIPE_SEL(crtc->pipe); - if (intel_sdvo->has_hdmi_audio) + if (crtc_state->has_audio) sdvox |= SDVO_AUDIO_ENABLE; if (INTEL_GEN(dev_priv) >= 4) { @@ -1699,12 +1757,6 @@ intel_sdvo_tmds_sink_detect(struct drm_connector *connector) kfree(edid); } - if (status == connector_status_connected) { - struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - if (intel_sdvo_connector->force_audio != HDMI_AUDIO_AUTO) - intel_sdvo->has_hdmi_audio = (intel_sdvo_connector->force_audio == HDMI_AUDIO_ON); - } - return status; } @@ -1884,6 +1936,7 @@ static const struct drm_display_mode sdvo_tv_modes[] = { static void intel_sdvo_get_tv_modes(struct drm_connector *connector) { struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector); + const struct drm_connector_state *conn_state = connector->state; struct intel_sdvo_sdtv_resolution_request tv_res; uint32_t reply = 0, format_map = 0; int i; @@ -1894,7 +1947,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector) /* Read the list of supported input resolutions for the selected TV * format. */ - format_map = 1 << intel_sdvo->tv_format_index; + format_map = 1 << conn_state->tv.mode; memcpy(&tv_res, &format_map, min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request))); @@ -1983,204 +2036,121 @@ static void intel_sdvo_destroy(struct drm_connector *connector) kfree(intel_sdvo_connector); } -static bool intel_sdvo_detect_hdmi_audio(struct drm_connector *connector) -{ - struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector); - struct edid *edid; - bool has_audio = false; - - if (!intel_sdvo->is_hdmi) - return false; - - edid = intel_sdvo_get_edid(connector); - if (edid != NULL && edid->input & DRM_EDID_INPUT_DIGITAL) - has_audio = drm_detect_monitor_audio(edid); - kfree(edid); - - return has_audio; -} - static int -intel_sdvo_set_property(struct drm_connector *connector, - struct drm_property *property, - uint64_t val) +intel_sdvo_connector_atomic_get_property(struct drm_connector *connector, + const struct drm_connector_state *state, + struct drm_property *property, + uint64_t *val) { - struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - struct drm_i915_private *dev_priv = to_i915(connector->dev); - uint16_t temp_value; - uint8_t cmd; - int ret; - - ret = drm_object_property_set_value(&connector->base, property, val); - if (ret) - return ret; - - if (property == dev_priv->force_audio_property) { - int i = val; - bool has_audio; - - if (i == intel_sdvo_connector->force_audio) - return 0; - - intel_sdvo_connector->force_audio = i; - - if (i == HDMI_AUDIO_AUTO) - has_audio = intel_sdvo_detect_hdmi_audio(connector); - else - has_audio = (i == HDMI_AUDIO_ON); - - if (has_audio == intel_sdvo->has_hdmi_audio) - return 0; - - intel_sdvo->has_hdmi_audio = has_audio; - goto done; - } - - if (property == dev_priv->broadcast_rgb_property) { - bool old_auto = intel_sdvo->color_range_auto; - uint32_t old_range = intel_sdvo->color_range; - - switch (val) { - case INTEL_BROADCAST_RGB_AUTO: - intel_sdvo->color_range_auto = true; - break; - case INTEL_BROADCAST_RGB_FULL: - intel_sdvo->color_range_auto = false; - intel_sdvo->color_range = 0; - break; - case INTEL_BROADCAST_RGB_LIMITED: - intel_sdvo->color_range_auto = false; - /* FIXME: this bit is only valid when using TMDS - * encoding and 8 bit per color mode. */ - intel_sdvo->color_range = HDMI_COLOR_RANGE_16_235; - break; - default: - return -EINVAL; - } - - if (old_auto == intel_sdvo->color_range_auto && - old_range == intel_sdvo->color_range) - return 0; - - goto done; - } - - if (property == connector->dev->mode_config.aspect_ratio_property) { - switch (val) { - case DRM_MODE_PICTURE_ASPECT_NONE: - intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; - break; - case DRM_MODE_PICTURE_ASPECT_4_3: - intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_4_3; - break; - case DRM_MODE_PICTURE_ASPECT_16_9: - intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_16_9; - break; - default: - return -EINVAL; - } - goto done; - } - -#define CHECK_PROPERTY(name, NAME) \ - if (intel_sdvo_connector->name == property) { \ - if (intel_sdvo_connector->cur_##name == temp_value) return 0; \ - if (intel_sdvo_connector->max_##name < temp_value) return -EINVAL; \ - cmd = SDVO_CMD_SET_##NAME; \ - intel_sdvo_connector->cur_##name = temp_value; \ - goto set_value; \ - } + const struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state((void *)state); if (property == intel_sdvo_connector->tv_format) { - if (val >= TV_FORMAT_NUM) - return -EINVAL; - - if (intel_sdvo->tv_format_index == - intel_sdvo_connector->tv_format_supported[val]) - return 0; - - intel_sdvo->tv_format_index = intel_sdvo_connector->tv_format_supported[val]; - goto done; - } else if (IS_TV_OR_LVDS(intel_sdvo_connector)) { - temp_value = val; - if (intel_sdvo_connector->left == property) { - drm_object_property_set_value(&connector->base, - intel_sdvo_connector->right, val); - if (intel_sdvo_connector->left_margin == temp_value) - return 0; + int i; - intel_sdvo_connector->left_margin = temp_value; - intel_sdvo_connector->right_margin = temp_value; - temp_value = intel_sdvo_connector->max_hscan - - intel_sdvo_connector->left_margin; - cmd = SDVO_CMD_SET_OVERSCAN_H; - goto set_value; - } else if (intel_sdvo_connector->right == property) { - drm_object_property_set_value(&connector->base, - intel_sdvo_connector->left, val); - if (intel_sdvo_connector->right_margin == temp_value) - return 0; + for (i = 0; i < intel_sdvo_connector->format_supported_num; i++) + if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) { + *val = i; - intel_sdvo_connector->left_margin = temp_value; - intel_sdvo_connector->right_margin = temp_value; - temp_value = intel_sdvo_connector->max_hscan - - intel_sdvo_connector->left_margin; - cmd = SDVO_CMD_SET_OVERSCAN_H; - goto set_value; - } else if (intel_sdvo_connector->top == property) { - drm_object_property_set_value(&connector->base, - intel_sdvo_connector->bottom, val); - if (intel_sdvo_connector->top_margin == temp_value) return 0; + } - intel_sdvo_connector->top_margin = temp_value; - intel_sdvo_connector->bottom_margin = temp_value; - temp_value = intel_sdvo_connector->max_vscan - - intel_sdvo_connector->top_margin; - cmd = SDVO_CMD_SET_OVERSCAN_V; - goto set_value; - } else if (intel_sdvo_connector->bottom == property) { - drm_object_property_set_value(&connector->base, - intel_sdvo_connector->top, val); - if (intel_sdvo_connector->bottom_margin == temp_value) - return 0; + WARN_ON(1); + *val = 0; + } else if (property == intel_sdvo_connector->top || + property == intel_sdvo_connector->bottom) + *val = intel_sdvo_connector->max_vscan - sdvo_state->tv.overscan_v; + else if (property == intel_sdvo_connector->left || + property == intel_sdvo_connector->right) + *val = intel_sdvo_connector->max_hscan - sdvo_state->tv.overscan_h; + else if (property == intel_sdvo_connector->hpos) + *val = sdvo_state->tv.hpos; + else if (property == intel_sdvo_connector->vpos) + *val = sdvo_state->tv.vpos; + else if (property == intel_sdvo_connector->saturation) + *val = state->tv.saturation; + else if (property == intel_sdvo_connector->contrast) + *val = state->tv.contrast; + else if (property == intel_sdvo_connector->hue) + *val = state->tv.hue; + else if (property == intel_sdvo_connector->brightness) + *val = state->tv.brightness; + else if (property == intel_sdvo_connector->sharpness) + *val = sdvo_state->tv.sharpness; + else if (property == intel_sdvo_connector->flicker_filter) + *val = sdvo_state->tv.flicker_filter; + else if (property == intel_sdvo_connector->flicker_filter_2d) + *val = sdvo_state->tv.flicker_filter_2d; + else if (property == intel_sdvo_connector->flicker_filter_adaptive) + *val = sdvo_state->tv.flicker_filter_adaptive; + else if (property == intel_sdvo_connector->tv_chroma_filter) + *val = sdvo_state->tv.chroma_filter; + else if (property == intel_sdvo_connector->tv_luma_filter) + *val = sdvo_state->tv.luma_filter; + else if (property == intel_sdvo_connector->dot_crawl) + *val = sdvo_state->tv.dot_crawl; + else + return intel_digital_connector_atomic_get_property(connector, state, property, val); - intel_sdvo_connector->top_margin = temp_value; - intel_sdvo_connector->bottom_margin = temp_value; - temp_value = intel_sdvo_connector->max_vscan - - intel_sdvo_connector->top_margin; - cmd = SDVO_CMD_SET_OVERSCAN_V; - goto set_value; - } - CHECK_PROPERTY(hpos, HPOS) - CHECK_PROPERTY(vpos, VPOS) - CHECK_PROPERTY(saturation, SATURATION) - CHECK_PROPERTY(contrast, CONTRAST) - CHECK_PROPERTY(hue, HUE) - CHECK_PROPERTY(brightness, BRIGHTNESS) - CHECK_PROPERTY(sharpness, SHARPNESS) - CHECK_PROPERTY(flicker_filter, FLICKER_FILTER) - CHECK_PROPERTY(flicker_filter_2d, FLICKER_FILTER_2D) - CHECK_PROPERTY(flicker_filter_adaptive, FLICKER_FILTER_ADAPTIVE) - CHECK_PROPERTY(tv_chroma_filter, TV_CHROMA_FILTER) - CHECK_PROPERTY(tv_luma_filter, TV_LUMA_FILTER) - CHECK_PROPERTY(dot_crawl, DOT_CRAWL) - } + return 0; +} - return -EINVAL; /* unknown property */ +static int +intel_sdvo_connector_atomic_set_property(struct drm_connector *connector, + struct drm_connector_state *state, + struct drm_property *property, + uint64_t val) +{ + struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); + struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state); -set_value: - if (!intel_sdvo_set_value(intel_sdvo, cmd, &temp_value, 2)) - return -EIO; + if (property == intel_sdvo_connector->tv_format) { + state->tv.mode = intel_sdvo_connector->tv_format_supported[val]; + if (state->crtc) { + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(state->state, state->crtc); -done: - if (intel_sdvo->base.base.crtc) - intel_crtc_restore_mode(intel_sdvo->base.base.crtc); + crtc_state->connectors_changed = true; + } + } else if (property == intel_sdvo_connector->top || + property == intel_sdvo_connector->bottom) + /* Cannot set these independent from each other */ + sdvo_state->tv.overscan_v = intel_sdvo_connector->max_vscan - val; + else if (property == intel_sdvo_connector->left || + property == intel_sdvo_connector->right) + /* Cannot set these independent from each other */ + sdvo_state->tv.overscan_h = intel_sdvo_connector->max_hscan - val; + else if (property == intel_sdvo_connector->hpos) + sdvo_state->tv.hpos = val; + else if (property == intel_sdvo_connector->vpos) + sdvo_state->tv.vpos = val; + else if (property == intel_sdvo_connector->saturation) + state->tv.saturation = val; + else if (property == intel_sdvo_connector->contrast) + state->tv.contrast = val; + else if (property == intel_sdvo_connector->hue) + state->tv.hue = val; + else if (property == intel_sdvo_connector->brightness) + state->tv.brightness = val; + else if (property == intel_sdvo_connector->sharpness) + sdvo_state->tv.sharpness = val; + else if (property == intel_sdvo_connector->flicker_filter) + sdvo_state->tv.flicker_filter = val; + else if (property == intel_sdvo_connector->flicker_filter_2d) + sdvo_state->tv.flicker_filter_2d = val; + else if (property == intel_sdvo_connector->flicker_filter_adaptive) + sdvo_state->tv.flicker_filter_adaptive = val; + else if (property == intel_sdvo_connector->tv_chroma_filter) + sdvo_state->tv.chroma_filter = val; + else if (property == intel_sdvo_connector->tv_luma_filter) + sdvo_state->tv.luma_filter = val; + else if (property == intel_sdvo_connector->dot_crawl) + sdvo_state->tv.dot_crawl = val; + else + return intel_digital_connector_atomic_set_property(connector, state, property, val); return 0; -#undef CHECK_PROPERTY } static int @@ -2208,22 +2178,61 @@ intel_sdvo_connector_unregister(struct drm_connector *connector) intel_connector_unregister(connector); } +static struct drm_connector_state * +intel_sdvo_connector_duplicate_state(struct drm_connector *connector) +{ + struct intel_sdvo_connector_state *state; + + state = kmemdup(connector->state, sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_connector_duplicate_state(connector, &state->base.base); + return &state->base.base; +} + static const struct drm_connector_funcs intel_sdvo_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .detect = intel_sdvo_detect, .fill_modes = drm_helper_probe_single_connector_modes, - .set_property = intel_sdvo_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, + .atomic_get_property = intel_sdvo_connector_atomic_get_property, + .atomic_set_property = intel_sdvo_connector_atomic_set_property, .late_register = intel_sdvo_connector_register, .early_unregister = intel_sdvo_connector_unregister, .destroy = intel_sdvo_destroy, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_duplicate_state = intel_sdvo_connector_duplicate_state, }; +static int intel_sdvo_atomic_check(struct drm_connector *conn, + struct drm_connector_state *new_conn_state) +{ + struct drm_atomic_state *state = new_conn_state->state; + struct drm_connector_state *old_conn_state = + drm_atomic_get_old_connector_state(state, conn); + struct intel_sdvo_connector_state *old_state = + to_intel_sdvo_connector_state(old_conn_state); + struct intel_sdvo_connector_state *new_state = + to_intel_sdvo_connector_state(new_conn_state); + + if (new_conn_state->crtc && + (memcmp(&old_state->tv, &new_state->tv, sizeof(old_state->tv)) || + memcmp(&old_conn_state->tv, &new_conn_state->tv, sizeof(old_conn_state->tv)))) { + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(new_conn_state->state, + new_conn_state->crtc); + + crtc_state->connectors_changed = true; + } + + return intel_digital_connector_atomic_check(conn, new_conn_state); +} + static const struct drm_connector_helper_funcs intel_sdvo_connector_helper_funcs = { .get_modes = intel_sdvo_get_modes, .mode_valid = intel_sdvo_mode_valid, + .atomic_check = intel_sdvo_atomic_check, }; static void intel_sdvo_enc_destroy(struct drm_encoder *encoder) @@ -2415,25 +2424,29 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo *intel_sdvo, intel_attach_force_audio_property(&connector->base.base); if (INTEL_GEN(dev_priv) >= 4 && IS_MOBILE(dev_priv)) { intel_attach_broadcast_rgb_property(&connector->base.base); - intel_sdvo->color_range_auto = true; } intel_attach_aspect_ratio_property(&connector->base.base); - intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; + connector->base.base.state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE; } static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void) { struct intel_sdvo_connector *sdvo_connector; + struct intel_sdvo_connector_state *conn_state; sdvo_connector = kzalloc(sizeof(*sdvo_connector), GFP_KERNEL); if (!sdvo_connector) return NULL; - if (intel_connector_init(&sdvo_connector->base) < 0) { + conn_state = kzalloc(sizeof(*conn_state), GFP_KERNEL); + if (!conn_state) { kfree(sdvo_connector); return NULL; } + __drm_atomic_helper_connector_reset(&sdvo_connector->base.base, + &conn_state->base.base); + return sdvo_connector; } @@ -2725,31 +2738,30 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo, intel_sdvo_connector->tv_format, i, i, tv_format_names[intel_sdvo_connector->tv_format_supported[i]]); - intel_sdvo->tv_format_index = intel_sdvo_connector->tv_format_supported[0]; - drm_object_attach_property(&intel_sdvo_connector->base.base.base, - intel_sdvo_connector->tv_format, 0); + intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0]; + drm_object_attach_property(&intel_sdvo_connector->base.base.base, 0, 0); return true; } -#define ENHANCEMENT(name, NAME) do { \ +#define _ENHANCEMENT(state_assignment, name, NAME) do { \ if (enhancements.name) { \ if (!intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_MAX_##NAME, &data_value, 4) || \ !intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_##NAME, &response, 2)) \ return false; \ - intel_sdvo_connector->max_##name = data_value[0]; \ - intel_sdvo_connector->cur_##name = response; \ intel_sdvo_connector->name = \ drm_property_create_range(dev, 0, #name, 0, data_value[0]); \ if (!intel_sdvo_connector->name) return false; \ + state_assignment = response; \ drm_object_attach_property(&connector->base, \ - intel_sdvo_connector->name, \ - intel_sdvo_connector->cur_##name); \ + intel_sdvo_connector->name, 0); \ DRM_DEBUG_KMS(#name ": max %d, default %d, current %d\n", \ data_value[0], data_value[1], response); \ } \ } while (0) +#define ENHANCEMENT(state, name, NAME) _ENHANCEMENT((state)->name, name, NAME) + static bool intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, struct intel_sdvo_connector *intel_sdvo_connector, @@ -2757,6 +2769,9 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, { struct drm_device *dev = intel_sdvo->base.base.dev; struct drm_connector *connector = &intel_sdvo_connector->base.base; + struct drm_connector_state *conn_state = connector->state; + struct intel_sdvo_connector_state *sdvo_state = + to_intel_sdvo_connector_state(conn_state); uint16_t response, data_value[2]; /* when horizontal overscan is supported, Add the left/right property */ @@ -2771,17 +2786,16 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, &response, 2)) return false; + sdvo_state->tv.overscan_h = response; + intel_sdvo_connector->max_hscan = data_value[0]; - intel_sdvo_connector->left_margin = data_value[0] - response; - intel_sdvo_connector->right_margin = intel_sdvo_connector->left_margin; intel_sdvo_connector->left = drm_property_create_range(dev, 0, "left_margin", 0, data_value[0]); if (!intel_sdvo_connector->left) return false; drm_object_attach_property(&connector->base, - intel_sdvo_connector->left, - intel_sdvo_connector->left_margin); + intel_sdvo_connector->left, 0); intel_sdvo_connector->right = drm_property_create_range(dev, 0, "right_margin", 0, data_value[0]); @@ -2789,8 +2803,7 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, return false; drm_object_attach_property(&connector->base, - intel_sdvo_connector->right, - intel_sdvo_connector->right_margin); + intel_sdvo_connector->right, 0); DRM_DEBUG_KMS("h_overscan: max %d, " "default %d, current %d\n", data_value[0], data_value[1], response); @@ -2807,9 +2820,9 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, &response, 2)) return false; + sdvo_state->tv.overscan_v = response; + intel_sdvo_connector->max_vscan = data_value[0]; - intel_sdvo_connector->top_margin = data_value[0] - response; - intel_sdvo_connector->bottom_margin = intel_sdvo_connector->top_margin; intel_sdvo_connector->top = drm_property_create_range(dev, 0, "top_margin", 0, data_value[0]); @@ -2817,8 +2830,7 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, return false; drm_object_attach_property(&connector->base, - intel_sdvo_connector->top, - intel_sdvo_connector->top_margin); + intel_sdvo_connector->top, 0); intel_sdvo_connector->bottom = drm_property_create_range(dev, 0, @@ -2827,40 +2839,37 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, return false; drm_object_attach_property(&connector->base, - intel_sdvo_connector->bottom, - intel_sdvo_connector->bottom_margin); + intel_sdvo_connector->bottom, 0); DRM_DEBUG_KMS("v_overscan: max %d, " "default %d, current %d\n", data_value[0], data_value[1], response); } - ENHANCEMENT(hpos, HPOS); - ENHANCEMENT(vpos, VPOS); - ENHANCEMENT(saturation, SATURATION); - ENHANCEMENT(contrast, CONTRAST); - ENHANCEMENT(hue, HUE); - ENHANCEMENT(sharpness, SHARPNESS); - ENHANCEMENT(brightness, BRIGHTNESS); - ENHANCEMENT(flicker_filter, FLICKER_FILTER); - ENHANCEMENT(flicker_filter_adaptive, FLICKER_FILTER_ADAPTIVE); - ENHANCEMENT(flicker_filter_2d, FLICKER_FILTER_2D); - ENHANCEMENT(tv_chroma_filter, TV_CHROMA_FILTER); - ENHANCEMENT(tv_luma_filter, TV_LUMA_FILTER); + ENHANCEMENT(&sdvo_state->tv, hpos, HPOS); + ENHANCEMENT(&sdvo_state->tv, vpos, VPOS); + ENHANCEMENT(&conn_state->tv, saturation, SATURATION); + ENHANCEMENT(&conn_state->tv, contrast, CONTRAST); + ENHANCEMENT(&conn_state->tv, hue, HUE); + ENHANCEMENT(&conn_state->tv, brightness, BRIGHTNESS); + ENHANCEMENT(&sdvo_state->tv, sharpness, SHARPNESS); + ENHANCEMENT(&sdvo_state->tv, flicker_filter, FLICKER_FILTER); + ENHANCEMENT(&sdvo_state->tv, flicker_filter_adaptive, FLICKER_FILTER_ADAPTIVE); + ENHANCEMENT(&sdvo_state->tv, flicker_filter_2d, FLICKER_FILTER_2D); + _ENHANCEMENT(sdvo_state->tv.chroma_filter, tv_chroma_filter, TV_CHROMA_FILTER); + _ENHANCEMENT(sdvo_state->tv.luma_filter, tv_luma_filter, TV_LUMA_FILTER); if (enhancements.dot_crawl) { if (!intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_DOT_CRAWL, &response, 2)) return false; - intel_sdvo_connector->max_dot_crawl = 1; - intel_sdvo_connector->cur_dot_crawl = response & 0x1; + sdvo_state->tv.dot_crawl = response & 0x1; intel_sdvo_connector->dot_crawl = drm_property_create_range(dev, 0, "dot_crawl", 0, 1); if (!intel_sdvo_connector->dot_crawl) return false; drm_object_attach_property(&connector->base, - intel_sdvo_connector->dot_crawl, - intel_sdvo_connector->cur_dot_crawl); + intel_sdvo_connector->dot_crawl, 0); DRM_DEBUG_KMS("dot crawl: current %d\n", response); } @@ -2876,11 +2885,12 @@ intel_sdvo_create_enhance_property_lvds(struct intel_sdvo *intel_sdvo, struct drm_connector *connector = &intel_sdvo_connector->base.base; uint16_t response, data_value[2]; - ENHANCEMENT(brightness, BRIGHTNESS); + ENHANCEMENT(&connector->state->tv, brightness, BRIGHTNESS); return true; } #undef ENHANCEMENT +#undef _ENHANCEMENT static bool intel_sdvo_create_enhance_property(struct intel_sdvo *intel_sdvo, struct intel_sdvo_connector *intel_sdvo_connector) @@ -2892,11 +2902,10 @@ static bool intel_sdvo_create_enhance_property(struct intel_sdvo *intel_sdvo, BUILD_BUG_ON(sizeof(enhancements) != 2); - enhancements.response = 0; - intel_sdvo_get_value(intel_sdvo, - SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS, - &enhancements, sizeof(enhancements)); - if (enhancements.response == 0) { + if (!intel_sdvo_get_value(intel_sdvo, + SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS, + &enhancements, sizeof(enhancements)) || + enhancements.response == 0) { DRM_DEBUG_KMS("No enhancement is supported\n"); return true; } diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 8c87c717c7cda9..c4bf19364e490c 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -210,16 +210,14 @@ void intel_pipe_update_end(struct intel_crtc *crtc, struct intel_flip_work *work } static void -skl_update_plane(struct drm_plane *drm_plane, +skl_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = drm_plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(drm_plane); - struct drm_framebuffer *fb = plane_state->base.fb; - enum plane_id plane_id = intel_plane->id; - enum pipe pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; u32 plane_ctl = plane_state->ctl; const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; u32 surf_addr = plane_state->main.offset; @@ -288,13 +286,11 @@ skl_update_plane(struct drm_plane *drm_plane, } static void -skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) +skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) { - struct drm_device *dev = dplane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(dplane); - enum plane_id plane_id = intel_plane->id; - enum pipe pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -308,10 +304,10 @@ skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) } static void -chv_update_csc(struct intel_plane *intel_plane, uint32_t format) +chv_update_csc(struct intel_plane *plane, uint32_t format) { - struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev); - enum plane_id plane_id = intel_plane->id; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum plane_id plane_id = plane->id; /* Seems RGB data bypasses the CSC always */ if (!format_is_yuv(format)) @@ -398,10 +394,10 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state, if (fb->modifier == I915_FORMAT_MOD_X_TILED) sprctl |= SP_TILED; - if (rotation & DRM_ROTATE_180) + if (rotation & DRM_MODE_ROTATE_180) sprctl |= SP_ROTATE_180; - if (rotation & DRM_REFLECT_X) + if (rotation & DRM_MODE_REFLECT_X) sprctl |= SP_MIRROR; if (key->flags & I915_SET_COLORKEY_SOURCE) @@ -411,16 +407,14 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state, } static void -vlv_update_plane(struct drm_plane *dplane, +vlv_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = dplane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(dplane); - struct drm_framebuffer *fb = plane_state->base.fb; - enum pipe pipe = intel_plane->pipe; - enum plane_id plane_id = intel_plane->id; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; + enum plane_id plane_id = plane->id; u32 sprctl = plane_state->ctl; u32 sprsurf_offset = plane_state->main.offset; u32 linear_offset; @@ -442,7 +436,7 @@ vlv_update_plane(struct drm_plane *dplane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) - chv_update_csc(intel_plane, fb->format->format); + chv_update_csc(plane, fb->format->format); if (key->flags) { I915_WRITE_FW(SPKEYMINVAL(pipe, plane_id), key->min_value); @@ -469,13 +463,11 @@ vlv_update_plane(struct drm_plane *dplane, } static void -vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) +vlv_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) { - struct drm_device *dev = dplane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(dplane); - enum pipe pipe = intel_plane->pipe; - enum plane_id plane_id = intel_plane->id; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + enum plane_id plane_id = plane->id; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -533,7 +525,7 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state, if (fb->modifier == I915_FORMAT_MOD_X_TILED) sprctl |= SPRITE_TILED; - if (rotation & DRM_ROTATE_180) + if (rotation & DRM_MODE_ROTATE_180) sprctl |= SPRITE_ROTATE_180; if (key->flags & I915_SET_COLORKEY_DESTINATION) @@ -545,15 +537,13 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state, } static void -ivb_update_plane(struct drm_plane *plane, +ivb_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(plane); - struct drm_framebuffer *fb = plane_state->base.fb; - enum pipe pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; u32 sprctl = plane_state->ctl, sprscale = 0; u32 sprsurf_offset = plane_state->main.offset; u32 linear_offset; @@ -600,7 +590,7 @@ ivb_update_plane(struct drm_plane *plane, I915_WRITE_FW(SPRLINOFF(pipe), linear_offset); I915_WRITE_FW(SPRSIZE(pipe), (crtc_h << 16) | crtc_w); - if (intel_plane->can_scale) + if (plane->can_scale) I915_WRITE_FW(SPRSCALE(pipe), sprscale); I915_WRITE_FW(SPRCTL(pipe), sprctl); I915_WRITE_FW(SPRSURF(pipe), @@ -611,19 +601,17 @@ ivb_update_plane(struct drm_plane *plane, } static void -ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) +ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) { - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(plane); - int pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); I915_WRITE_FW(SPRCTL(pipe), 0); /* Can't leave the scaler enabled... */ - if (intel_plane->can_scale) + if (plane->can_scale) I915_WRITE_FW(SPRSCALE(pipe), 0); I915_WRITE_FW(SPRSURF(pipe), 0); @@ -632,7 +620,7 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } -static u32 ilk_sprite_ctl(const struct intel_crtc_state *crtc_state, +static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = @@ -674,7 +662,7 @@ static u32 ilk_sprite_ctl(const struct intel_crtc_state *crtc_state, if (fb->modifier == I915_FORMAT_MOD_X_TILED) dvscntr |= DVS_TILED; - if (rotation & DRM_ROTATE_180) + if (rotation & DRM_MODE_ROTATE_180) dvscntr |= DVS_ROTATE_180; if (key->flags & I915_SET_COLORKEY_DESTINATION) @@ -686,15 +674,13 @@ static u32 ilk_sprite_ctl(const struct intel_crtc_state *crtc_state, } static void -ilk_update_plane(struct drm_plane *plane, +g4x_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(plane); - struct drm_framebuffer *fb = plane_state->base.fb; - int pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; u32 dvscntr = plane_state->ctl, dvsscale = 0; u32 dvssurf_offset = plane_state->main.offset; u32 linear_offset; @@ -747,12 +733,10 @@ ilk_update_plane(struct drm_plane *plane, } static void -ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) +g4x_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) { - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_plane *intel_plane = to_intel_plane(plane); - int pipe = intel_plane->pipe; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; unsigned long irqflags; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -768,14 +752,12 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) } static int -intel_check_sprite_plane(struct drm_plane *plane, +intel_check_sprite_plane(struct intel_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state) { - struct drm_i915_private *dev_priv = to_i915(plane->dev); - struct drm_crtc *crtc = state->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_plane *intel_plane = to_intel_plane(plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); struct drm_framebuffer *fb = state->base.fb; int crtc_x, crtc_y; unsigned int crtc_w, crtc_h; @@ -797,7 +779,7 @@ intel_check_sprite_plane(struct drm_plane *plane, } /* Don't modify another pipe's plane */ - if (intel_plane->pipe != intel_crtc->pipe) { + if (plane->pipe != crtc->pipe) { DRM_DEBUG_KMS("Wrong plane <-> crtc mapping\n"); return -EINVAL; } @@ -814,16 +796,16 @@ intel_check_sprite_plane(struct drm_plane *plane, if (state->ckey.flags == I915_SET_COLORKEY_NONE) { can_scale = 1; min_scale = 1; - max_scale = skl_max_scale(intel_crtc, crtc_state); + max_scale = skl_max_scale(crtc, crtc_state); } else { can_scale = 0; min_scale = DRM_PLANE_HELPER_NO_SCALING; max_scale = DRM_PLANE_HELPER_NO_SCALING; } } else { - can_scale = intel_plane->can_scale; - max_scale = intel_plane->max_downscale << 16; - min_scale = intel_plane->can_scale ? 1 : (1 << 16); + can_scale = plane->can_scale; + max_scale = plane->max_downscale << 16; + min_scale = plane->can_scale ? 1 : (1 << 16); } /* @@ -967,7 +949,7 @@ intel_check_sprite_plane(struct drm_plane *plane, if (ret) return ret; - state->ctl = ilk_sprite_ctl(crtc_state, state); + state->ctl = g4x_sprite_ctl(crtc_state, state); } return 0; @@ -1027,7 +1009,7 @@ int intel_sprite_set_colorkey(struct drm_device *dev, void *data, return ret; } -static const uint32_t ilk_plane_formats[] = { +static const uint32_t g4x_plane_formats[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_YUYV, DRM_FORMAT_YVYU, @@ -1131,29 +1113,29 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, intel_plane->can_scale = true; intel_plane->max_downscale = 16; - intel_plane->update_plane = ilk_update_plane; - intel_plane->disable_plane = ilk_disable_plane; + intel_plane->update_plane = g4x_update_plane; + intel_plane->disable_plane = g4x_disable_plane; if (IS_GEN6(dev_priv)) { plane_formats = snb_plane_formats; num_plane_formats = ARRAY_SIZE(snb_plane_formats); } else { - plane_formats = ilk_plane_formats; - num_plane_formats = ARRAY_SIZE(ilk_plane_formats); + plane_formats = g4x_plane_formats; + num_plane_formats = ARRAY_SIZE(g4x_plane_formats); } } if (INTEL_GEN(dev_priv) >= 9) { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_90 | - DRM_ROTATE_180 | DRM_ROTATE_270; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | + DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270; } else if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_180 | - DRM_REFLECT_X; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 | + DRM_MODE_REFLECT_X; } else { supported_rotations = - DRM_ROTATE_0 | DRM_ROTATE_180; + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180; } intel_plane->pipe = pipe; @@ -1180,7 +1162,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, goto fail; drm_plane_create_rotation_property(&intel_plane->base, - DRM_ROTATE_0, + DRM_MODE_ROTATE_0, supported_rotations); drm_plane_helper_add(&intel_plane->base, &intel_plane_helper_funcs); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index e077c2a9e69470..784df024e23056 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -48,41 +48,6 @@ struct intel_tv { struct intel_encoder base; int type; - const char *tv_format; - int margin[4]; - u32 save_TV_H_CTL_1; - u32 save_TV_H_CTL_2; - u32 save_TV_H_CTL_3; - u32 save_TV_V_CTL_1; - u32 save_TV_V_CTL_2; - u32 save_TV_V_CTL_3; - u32 save_TV_V_CTL_4; - u32 save_TV_V_CTL_5; - u32 save_TV_V_CTL_6; - u32 save_TV_V_CTL_7; - u32 save_TV_SC_CTL_1, save_TV_SC_CTL_2, save_TV_SC_CTL_3; - - u32 save_TV_CSC_Y; - u32 save_TV_CSC_Y2; - u32 save_TV_CSC_U; - u32 save_TV_CSC_U2; - u32 save_TV_CSC_V; - u32 save_TV_CSC_V2; - u32 save_TV_CLR_KNOBS; - u32 save_TV_CLR_LEVEL; - u32 save_TV_WIN_POS; - u32 save_TV_WIN_SIZE; - u32 save_TV_FILTER_CTL_1; - u32 save_TV_FILTER_CTL_2; - u32 save_TV_FILTER_CTL_3; - - u32 save_TV_H_LUMA[60]; - u32 save_TV_H_CHROMA[60]; - u32 save_TV_V_LUMA[43]; - u32 save_TV_V_CHROMA[43]; - - u32 save_TV_DAC; - u32 save_TV_CTL; }; struct video_levels { @@ -873,32 +838,18 @@ intel_disable_tv(struct intel_encoder *encoder, I915_WRITE(TV_CTL, I915_READ(TV_CTL) & ~TV_ENC_ENABLE); } -static const struct tv_mode * -intel_tv_mode_lookup(const char *tv_format) +static const struct tv_mode *intel_tv_mode_find(struct drm_connector_state *conn_state) { - int i; - - for (i = 0; i < ARRAY_SIZE(tv_modes); i++) { - const struct tv_mode *tv_mode = &tv_modes[i]; + int format = conn_state->tv.mode; - if (!strcmp(tv_format, tv_mode->name)) - return tv_mode; - } - return NULL; -} - -static const struct tv_mode * -intel_tv_mode_find(struct intel_tv *intel_tv) -{ - return intel_tv_mode_lookup(intel_tv->tv_format); + return &tv_modes[format]; } static enum drm_mode_status intel_tv_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { - struct intel_tv *intel_tv = intel_attached_tv(connector); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); + const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; if (mode->clock > max_dotclk) @@ -925,8 +876,7 @@ intel_tv_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { - struct intel_tv *intel_tv = enc_to_tv(encoder); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); + const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state); if (!tv_mode) return false; @@ -1032,7 +982,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); struct intel_tv *intel_tv = enc_to_tv(encoder); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); + const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state); u32 tv_ctl; u32 scctl1, scctl2, scctl3; int i, j; @@ -1135,12 +1085,12 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder, else ysize = 2*tv_mode->nbr_end + 1; - xpos += intel_tv->margin[TV_MARGIN_LEFT]; - ypos += intel_tv->margin[TV_MARGIN_TOP]; - xsize -= (intel_tv->margin[TV_MARGIN_LEFT] + - intel_tv->margin[TV_MARGIN_RIGHT]); - ysize -= (intel_tv->margin[TV_MARGIN_TOP] + - intel_tv->margin[TV_MARGIN_BOTTOM]); + xpos += conn_state->tv.margins.left; + ypos += conn_state->tv.margins.top; + xsize -= (conn_state->tv.margins.left + + conn_state->tv.margins.right); + ysize -= (conn_state->tv.margins.top + + conn_state->tv.margins.bottom); I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos); I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize); @@ -1288,7 +1238,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv, static void intel_tv_find_better_format(struct drm_connector *connector) { struct intel_tv *intel_tv = intel_attached_tv(connector); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); + const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); int i; if ((intel_tv->type == DRM_MODE_CONNECTOR_Component) == @@ -1304,9 +1254,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector) break; } - intel_tv->tv_format = tv_mode->name; - drm_object_property_set_value(&connector->base, - connector->dev->mode_config.tv_mode_property, i); + connector->state->tv.mode = i; } /** @@ -1347,16 +1295,15 @@ intel_tv_detect(struct drm_connector *connector, connector_status_connected; } else status = connector_status_unknown; - } else - return connector->status; - if (status != connector_status_connected) - return status; - - intel_tv->type = type; - intel_tv_find_better_format(connector); + if (status == connector_status_connected) { + intel_tv->type = type; + intel_tv_find_better_format(connector); + } - return connector_status_connected; + return status; + } else + return connector->status; } static const struct input_res { @@ -1376,12 +1323,9 @@ static const struct input_res { * Chose preferred mode according to line number of TV format */ static void -intel_tv_chose_preferred_modes(struct drm_connector *connector, +intel_tv_choose_preferred_modes(const struct tv_mode *tv_mode, struct drm_display_mode *mode_ptr) { - struct intel_tv *intel_tv = intel_attached_tv(connector); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); - if (tv_mode->nbr_end < 480 && mode_ptr->vdisplay == 480) mode_ptr->type |= DRM_MODE_TYPE_PREFERRED; else if (tv_mode->nbr_end > 480) { @@ -1404,8 +1348,7 @@ static int intel_tv_get_modes(struct drm_connector *connector) { struct drm_display_mode *mode_ptr; - struct intel_tv *intel_tv = intel_attached_tv(connector); - const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv); + const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); int j, count = 0; u64 tmp; @@ -1448,7 +1391,7 @@ intel_tv_get_modes(struct drm_connector *connector) mode_ptr->clock = (int) tmp; mode_ptr->type = DRM_MODE_TYPE_DRIVER; - intel_tv_chose_preferred_modes(connector, mode_ptr); + intel_tv_choose_preferred_modes(tv_mode, mode_ptr); drm_mode_probed_add(connector, mode_ptr); count++; } @@ -1463,74 +1406,47 @@ intel_tv_destroy(struct drm_connector *connector) kfree(connector); } - -static int -intel_tv_set_property(struct drm_connector *connector, struct drm_property *property, - uint64_t val) -{ - struct drm_device *dev = connector->dev; - struct intel_tv *intel_tv = intel_attached_tv(connector); - struct drm_crtc *crtc = intel_tv->base.base.crtc; - int ret = 0; - bool changed = false; - - ret = drm_object_property_set_value(&connector->base, property, val); - if (ret < 0) - goto out; - - if (property == dev->mode_config.tv_left_margin_property && - intel_tv->margin[TV_MARGIN_LEFT] != val) { - intel_tv->margin[TV_MARGIN_LEFT] = val; - changed = true; - } else if (property == dev->mode_config.tv_right_margin_property && - intel_tv->margin[TV_MARGIN_RIGHT] != val) { - intel_tv->margin[TV_MARGIN_RIGHT] = val; - changed = true; - } else if (property == dev->mode_config.tv_top_margin_property && - intel_tv->margin[TV_MARGIN_TOP] != val) { - intel_tv->margin[TV_MARGIN_TOP] = val; - changed = true; - } else if (property == dev->mode_config.tv_bottom_margin_property && - intel_tv->margin[TV_MARGIN_BOTTOM] != val) { - intel_tv->margin[TV_MARGIN_BOTTOM] = val; - changed = true; - } else if (property == dev->mode_config.tv_mode_property) { - if (val >= ARRAY_SIZE(tv_modes)) { - ret = -EINVAL; - goto out; - } - if (!strcmp(intel_tv->tv_format, tv_modes[val].name)) - goto out; - - intel_tv->tv_format = tv_modes[val].name; - changed = true; - } else { - ret = -EINVAL; - goto out; - } - - if (changed && crtc) - intel_crtc_restore_mode(crtc); -out: - return ret; -} - static const struct drm_connector_funcs intel_tv_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .late_register = intel_connector_register, .early_unregister = intel_connector_unregister, .destroy = intel_tv_destroy, - .set_property = intel_tv_set_property, - .atomic_get_property = intel_connector_atomic_get_property, + .set_property = drm_atomic_helper_connector_set_property, .fill_modes = drm_helper_probe_single_connector_modes, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, }; +static int intel_tv_atomic_check(struct drm_connector *connector, + struct drm_connector_state *new_state) +{ + struct drm_crtc_state *new_crtc_state; + struct drm_connector_state *old_state; + + if (!new_state->crtc) + return 0; + + old_state = drm_atomic_get_old_connector_state(new_state->state, connector); + new_crtc_state = drm_atomic_get_new_crtc_state(new_state->state, new_state->crtc); + + if (old_state->tv.mode != new_state->tv.mode || + old_state->tv.margins.left != new_state->tv.margins.left || + old_state->tv.margins.right != new_state->tv.margins.right || + old_state->tv.margins.top != new_state->tv.margins.top || + old_state->tv.margins.bottom != new_state->tv.margins.bottom) { + /* Force a modeset. */ + + new_crtc_state->connectors_changed = true; + } + + return 0; +} + static const struct drm_connector_helper_funcs intel_tv_connector_helper_funcs = { .detect_ctx = intel_tv_detect, .mode_valid = intel_tv_mode_valid, .get_modes = intel_tv_get_modes, + .atomic_check = intel_tv_atomic_check, }; static const struct drm_encoder_funcs intel_tv_enc_funcs = { @@ -1548,6 +1464,7 @@ intel_tv_init(struct drm_i915_private *dev_priv) u32 tv_dac_on, tv_dac_off, save_tv_dac; const char *tv_format_names[ARRAY_SIZE(tv_modes)]; int i, initial_mode = 0; + struct drm_connector_state *state; if ((I915_READ(TV_CTL) & TV_FUSE_STATE_MASK) == TV_FUSE_STATE_DISABLED) return; @@ -1593,6 +1510,7 @@ intel_tv_init(struct drm_i915_private *dev_priv) intel_encoder = &intel_tv->base; connector = &intel_connector->base; + state = connector->state; /* The documentation, for the older chipsets at least, recommend * using a polling method rather than hotplug detection for TVs. @@ -1630,12 +1548,12 @@ intel_tv_init(struct drm_i915_private *dev_priv) intel_tv->type = DRM_MODE_CONNECTOR_Unknown; /* BIOS margin values */ - intel_tv->margin[TV_MARGIN_LEFT] = 54; - intel_tv->margin[TV_MARGIN_TOP] = 36; - intel_tv->margin[TV_MARGIN_RIGHT] = 46; - intel_tv->margin[TV_MARGIN_BOTTOM] = 37; + state->tv.margins.left = 54; + state->tv.margins.top = 36; + state->tv.margins.right = 46; + state->tv.margins.bottom = 37; - intel_tv->tv_format = tv_modes[initial_mode].name; + state->tv.mode = initial_mode; drm_connector_helper_add(connector, &intel_tv_connector_helper_funcs); connector->interlace_allowed = false; @@ -1649,17 +1567,17 @@ intel_tv_init(struct drm_i915_private *dev_priv) tv_format_names); drm_object_attach_property(&connector->base, dev->mode_config.tv_mode_property, - initial_mode); + state->tv.mode); drm_object_attach_property(&connector->base, dev->mode_config.tv_left_margin_property, - intel_tv->margin[TV_MARGIN_LEFT]); + state->tv.margins.left); drm_object_attach_property(&connector->base, dev->mode_config.tv_top_margin_property, - intel_tv->margin[TV_MARGIN_TOP]); + state->tv.margins.top); drm_object_attach_property(&connector->base, dev->mode_config.tv_right_margin_property, - intel_tv->margin[TV_MARGIN_RIGHT]); + state->tv.margins.right); drm_object_attach_property(&connector->base, dev->mode_config.tv_bottom_margin_property, - intel_tv->margin[TV_MARGIN_BOTTOM]); + state->tv.margins.bottom); } diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c index c117424f1f50e1..7a7b07de28a3dd 100644 --- a/drivers/gpu/drm/i915/intel_uc.c +++ b/drivers/gpu/drm/i915/intel_uc.c @@ -94,12 +94,22 @@ void intel_uc_sanitize_options(struct drm_i915_private *dev_priv) i915.enable_guc_submission = HAS_GUC_SCHED(dev_priv); } +static void guc_write_irq_trigger(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + + I915_WRITE(GUC_SEND_INTERRUPT, GUC_SEND_TRIGGER); +} + void intel_uc_init_early(struct drm_i915_private *dev_priv) { struct intel_guc *guc = &dev_priv->guc; + intel_guc_ct_init_early(&guc->ct); + mutex_init(&guc->send_mutex); - guc->send = intel_guc_send_mmio; + guc->send = intel_guc_send_nop; + guc->notify = guc_write_irq_trigger; } static void fetch_uc_fw(struct drm_i915_private *dev_priv, @@ -252,13 +262,81 @@ void intel_uc_fini_fw(struct drm_i915_private *dev_priv) __intel_uc_fw_fini(&dev_priv->huc.fw); } +static inline i915_reg_t guc_send_reg(struct intel_guc *guc, u32 i) +{ + GEM_BUG_ON(!guc->send_regs.base); + GEM_BUG_ON(!guc->send_regs.count); + GEM_BUG_ON(i >= guc->send_regs.count); + + return _MMIO(guc->send_regs.base + 4 * i); +} + +static void guc_init_send_regs(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + enum forcewake_domains fw_domains = 0; + unsigned int i; + + guc->send_regs.base = i915_mmio_reg_offset(SOFT_SCRATCH(0)); + guc->send_regs.count = SOFT_SCRATCH_COUNT - 1; + + for (i = 0; i < guc->send_regs.count; i++) { + fw_domains |= intel_uncore_forcewake_for_reg(dev_priv, + guc_send_reg(guc, i), + FW_REG_READ | FW_REG_WRITE); + } + guc->send_regs.fw_domains = fw_domains; +} + +static void guc_capture_load_err_log(struct intel_guc *guc) +{ + if (!guc->log.vma || i915.guc_log_level < 0) + return; + + if (!guc->load_err_log) + guc->load_err_log = i915_gem_object_get(guc->log.vma->obj); + + return; +} + +static void guc_free_load_err_log(struct intel_guc *guc) +{ + if (guc->load_err_log) + i915_gem_object_put(guc->load_err_log); +} + +static int guc_enable_communication(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + + guc_init_send_regs(guc); + + if (HAS_GUC_CT(dev_priv)) + return intel_guc_enable_ct(guc); + + guc->send = intel_guc_send_mmio; + return 0; +} + +static void guc_disable_communication(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + + if (HAS_GUC_CT(dev_priv)) + intel_guc_disable_ct(guc); + + guc->send = intel_guc_send_nop; +} + int intel_uc_init_hw(struct drm_i915_private *dev_priv) { + struct intel_guc *guc = &dev_priv->guc; int ret, attempts; if (!i915.enable_guc_loading) return 0; + guc_disable_communication(guc); gen9_reset_guc_interrupts(dev_priv); /* We need to notify the guc whenever we change the GGTT */ @@ -274,6 +352,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv) goto err_guc; } + /* init WOPCM */ + I915_WRITE(GUC_WOPCM_SIZE, intel_guc_wopcm_size(dev_priv)); + I915_WRITE(DMA_GUC_WOPCM_OFFSET, + GUC_WOPCM_OFFSET_VALUE | HUC_LOADING_AGENT_GUC); + /* WaEnableuKernelHeaderValidFix:skl */ /* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */ if (IS_GEN9(dev_priv)) @@ -301,7 +384,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv) /* Did we succeded or run out of retries? */ if (ret) - goto err_submission; + goto err_log_capture; + + ret = guc_enable_communication(guc); + if (ret) + goto err_log_capture; intel_guc_auth_huc(dev_priv); if (i915.enable_guc_submission) { @@ -325,7 +412,10 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv) * marks the GPU as wedged until reset). */ err_interrupts: + guc_disable_communication(guc); gen9_disable_guc_interrupts(dev_priv); +err_log_capture: + guc_capture_load_err_log(guc); err_submission: if (i915.enable_guc_submission) i915_guc_submission_fini(dev_priv); @@ -351,25 +441,25 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv) if (!i915.enable_guc_loading) return; - if (i915.enable_guc_submission) { + guc_free_load_err_log(&dev_priv->guc); + + if (i915.enable_guc_submission) i915_guc_submission_disable(dev_priv); + + guc_disable_communication(&dev_priv->guc); + + if (i915.enable_guc_submission) { gen9_disable_guc_interrupts(dev_priv); i915_guc_submission_fini(dev_priv); } + i915_ggtt_disable_guc(dev_priv); } -/* - * Read GuC command/status register (SOFT_SCRATCH_0) - * Return true if it contains a response rather than a command - */ -static bool guc_recv(struct intel_guc *guc, u32 *status) +int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len) { - struct drm_i915_private *dev_priv = guc_to_i915(guc); - - u32 val = I915_READ(SOFT_SCRATCH(0)); - *status = val; - return INTEL_GUC_RECV_IS_RESPONSE(val); + WARN(1, "Unexpected send: action=%#x\n", *action); + return -ENODEV; } /* @@ -382,30 +472,33 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len) int i; int ret; - if (WARN_ON(len < 1 || len > 15)) - return -EINVAL; + GEM_BUG_ON(!len); + GEM_BUG_ON(len > guc->send_regs.count); - mutex_lock(&guc->send_mutex); - intel_uncore_forcewake_get(dev_priv, FORCEWAKE_BLITTER); + /* If CT is available, we expect to use MMIO only during init/fini */ + GEM_BUG_ON(HAS_GUC_CT(dev_priv) && + *action != INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER && + *action != INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER); - dev_priv->guc.action_count += 1; - dev_priv->guc.action_cmd = action[0]; + mutex_lock(&guc->send_mutex); + intel_uncore_forcewake_get(dev_priv, guc->send_regs.fw_domains); for (i = 0; i < len; i++) - I915_WRITE(SOFT_SCRATCH(i), action[i]); + I915_WRITE(guc_send_reg(guc, i), action[i]); - POSTING_READ(SOFT_SCRATCH(i - 1)); + POSTING_READ(guc_send_reg(guc, i - 1)); - I915_WRITE(GUC_SEND_INTERRUPT, GUC_SEND_TRIGGER); + intel_guc_notify(guc); /* - * Fast commands should complete in less than 10us, so sample quickly - * up to that length of time, then switch to a slower sleep-wait loop. - * No inte_guc_send command should ever take longer than 10ms. + * No GuC command should ever take longer than 10ms. + * Fast commands should still complete in 10us. */ - ret = wait_for_us(guc_recv(guc, &status), 10); - if (ret) - ret = wait_for(guc_recv(guc, &status), 10); + ret = __intel_wait_for_register_fw(dev_priv, + guc_send_reg(guc, 0), + INTEL_GUC_RECV_MASK, + INTEL_GUC_RECV_MASK, + 10, 10, &status); if (status != INTEL_GUC_STATUS_SUCCESS) { /* * Either the GuC explicitly returned an error (which @@ -418,13 +511,9 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len) DRM_WARN("INTEL_GUC_SEND: Action 0x%X failed;" " ret=%d status=0x%08X response=0x%08X\n", action[0], ret, status, I915_READ(SOFT_SCRATCH(15))); - - dev_priv->guc.action_fail += 1; - dev_priv->guc.action_err = ret; } - dev_priv->guc.action_status = status; - intel_uncore_forcewake_put(dev_priv, FORCEWAKE_BLITTER); + intel_uncore_forcewake_put(dev_priv, guc->send_regs.fw_domains); mutex_unlock(&guc->send_mutex); return ret; diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h index 4b7f73aeddac64..69daf4c01cd0ed 100644 --- a/drivers/gpu/drm/i915/intel_uc.h +++ b/drivers/gpu/drm/i915/intel_uc.h @@ -27,7 +27,7 @@ #include "intel_guc_fwif.h" #include "i915_guc_reg.h" #include "intel_ringbuffer.h" - +#include "intel_guc_ct.h" #include "i915_vma.h" struct drm_i915_gem_request; @@ -59,12 +59,6 @@ struct drm_i915_gem_request; * available in the work queue (note, the queue is shared, * not per-engine). It is OK for this to be nonzero, but * it should not be huge! - * q_fail: failed to enqueue a work item. This should never happen, - * because we check for space beforehand. - * b_fail: failed to ring the doorbell. This should never happen, unless - * somehow the hardware misbehaves, or maybe if the GuC firmware - * crashes? We probably need to reset the GPU to recover. - * retcode: errno from last guc_submit() */ struct i915_guc_client { struct i915_vma *vma; @@ -87,8 +81,6 @@ struct i915_guc_client { uint32_t wq_tail; uint32_t wq_rsvd; uint32_t no_wq_space; - uint32_t b_fail; - int retcode; /* Per-engine counts of GuC submissions */ uint64_t submissions[I915_NUM_ENGINES]; @@ -181,6 +173,10 @@ struct intel_guc_log { struct intel_guc { struct intel_uc_fw fw; struct intel_guc_log log; + struct intel_guc_ct ct; + + /* Log snapshot if GuC errors during load */ + struct drm_i915_gem_object *load_err_log; /* intel_guc_recv interrupt related state */ bool interrupts_enabled; @@ -195,21 +191,21 @@ struct intel_guc { DECLARE_BITMAP(doorbell_bitmap, GUC_NUM_DOORBELLS); uint32_t db_cacheline; /* Cyclic counter mod pagesize */ - /* Action status & statistics */ - uint64_t action_count; /* Total commands issued */ - uint32_t action_cmd; /* Last command word */ - uint32_t action_status; /* Last return status */ - uint32_t action_fail; /* Total number of failures */ - int32_t action_err; /* Last error code */ - - uint64_t submissions[I915_NUM_ENGINES]; - uint32_t last_seqno[I915_NUM_ENGINES]; + /* GuC's FW specific registers used in MMIO send */ + struct { + u32 base; + unsigned int count; + enum forcewake_domains fw_domains; + } send_regs; /* To serialize the intel_guc_send actions */ struct mutex send_mutex; /* GuC's FW specific send function */ int (*send)(struct intel_guc *guc, const u32 *data, u32 len); + + /* GuC's FW specific notify function */ + void (*notify)(struct intel_guc *guc); }; struct intel_huc { @@ -227,12 +223,19 @@ void intel_uc_fini_fw(struct drm_i915_private *dev_priv); int intel_uc_init_hw(struct drm_i915_private *dev_priv); void intel_uc_fini_hw(struct drm_i915_private *dev_priv); int intel_guc_sample_forcewake(struct intel_guc *guc); +int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len); int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len); + static inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len) { return guc->send(guc, action, len); } +static inline void intel_guc_notify(struct intel_guc *guc) +{ + guc->notify(guc); +} + /* intel_guc_loader.c */ int intel_guc_select_fw(struct intel_guc *guc); int intel_guc_init_hw(struct intel_guc *guc); @@ -266,7 +269,7 @@ static inline u32 guc_ggtt_offset(struct i915_vma *vma) /* intel_huc.c */ void intel_huc_select_fw(struct intel_huc *huc); -int intel_huc_init_hw(struct intel_huc *huc); +void intel_huc_init_hw(struct intel_huc *huc); void intel_guc_auth_huc(struct drm_i915_private *dev_priv); #endif diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 6d1ea26b2493ba..9882724bc2b69c 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -29,6 +29,7 @@ #include #define FORCEWAKE_ACK_TIMEOUT_MS 50 +#define GT_FIFO_TIMEOUT_MS 10 #define __raw_posting_read(dev_priv__, reg__) (void)__raw_i915_read32((dev_priv__), (reg__)) @@ -172,22 +173,6 @@ static void fw_domains_get_with_thread_status(struct drm_i915_private *dev_priv, __gen6_gt_wait_for_thread_c0(dev_priv); } -static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv) -{ - u32 gtfifodbg; - - gtfifodbg = __raw_i915_read32(dev_priv, GTFIFODBG); - if (WARN(gtfifodbg, "GT wake FIFO error 0x%x\n", gtfifodbg)) - __raw_i915_write32(dev_priv, GTFIFODBG, gtfifodbg); -} - -static void fw_domains_put_with_fifo(struct drm_i915_private *dev_priv, - enum forcewake_domains fw_domains) -{ - fw_domains_put(dev_priv, fw_domains); - gen6_gt_check_fifodbg(dev_priv); -} - static inline u32 fifo_free_entries(struct drm_i915_private *dev_priv) { u32 count = __raw_i915_read32(dev_priv, GTFIFOCTL); @@ -195,30 +180,27 @@ static inline u32 fifo_free_entries(struct drm_i915_private *dev_priv) return count & GT_FIFO_FREE_ENTRIES_MASK; } -static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) +static void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) { - int ret = 0; + u32 n; /* On VLV, FIFO will be shared by both SW and HW. * So, we need to read the FREE_ENTRIES everytime */ if (IS_VALLEYVIEW(dev_priv)) - dev_priv->uncore.fifo_count = fifo_free_entries(dev_priv); - - if (dev_priv->uncore.fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) { - int loop = 500; - u32 fifo = fifo_free_entries(dev_priv); - - while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) { - udelay(10); - fifo = fifo_free_entries(dev_priv); + n = fifo_free_entries(dev_priv); + else + n = dev_priv->uncore.fifo_count; + + if (n <= GT_FIFO_NUM_RESERVED_ENTRIES) { + if (wait_for_atomic((n = fifo_free_entries(dev_priv)) > + GT_FIFO_NUM_RESERVED_ENTRIES, + GT_FIFO_TIMEOUT_MS)) { + DRM_DEBUG("GT_FIFO timeout, entries: %u\n", n); + return; } - if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES)) - ++ret; - dev_priv->uncore.fifo_count = fifo; } - dev_priv->uncore.fifo_count--; - return ret; + dev_priv->uncore.fifo_count = n - 1; } static enum hrtimer_restart @@ -232,6 +214,9 @@ intel_uncore_fw_release_timer(struct hrtimer *timer) assert_rpm_device_not_suspended(dev_priv); + if (xchg(&domain->active, false)) + return HRTIMER_RESTART; + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); if (WARN_ON(domain->wake_count == 0)) domain->wake_count++; @@ -262,6 +247,7 @@ static void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, active_domains = 0; for_each_fw_domain(domain, dev_priv, tmp) { + smp_store_mb(domain->active, false); if (hrtimer_cancel(&domain->timer) == 0) continue; @@ -383,32 +369,45 @@ vlv_check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) return true; } +static bool +gen6_check_for_fifo_debug(struct drm_i915_private *dev_priv) +{ + u32 fifodbg; + + fifodbg = __raw_i915_read32(dev_priv, GTFIFODBG); + + if (unlikely(fifodbg)) { + DRM_DEBUG_DRIVER("GTFIFODBG = 0x08%x\n", fifodbg); + __raw_i915_write32(dev_priv, GTFIFODBG, fifodbg); + } + + return fifodbg; +} + static bool check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) { + bool ret = false; + if (HAS_FPGA_DBG_UNCLAIMED(dev_priv)) - return fpga_check_for_unclaimed_mmio(dev_priv); + ret |= fpga_check_for_unclaimed_mmio(dev_priv); if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - return vlv_check_for_unclaimed_mmio(dev_priv); + ret |= vlv_check_for_unclaimed_mmio(dev_priv); - return false; + if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) + ret |= gen6_check_for_fifo_debug(dev_priv); + + return ret; } static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, bool restore_forcewake) { - struct intel_device_info *info = mkwrite_device_info(dev_priv); - /* clear out unclaimed reg detection bit */ if (check_for_unclaimed_mmio(dev_priv)) DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n"); - /* clear out old GT FIFO errors */ - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) - __raw_i915_write32(dev_priv, GTFIFODBG, - __raw_i915_read32(dev_priv, GTFIFODBG)); - /* WaDisableShadowRegForCpd:chv */ if (IS_CHERRYVIEW(dev_priv)) { __raw_i915_write32(dev_priv, GTFIFOCTL, @@ -417,9 +416,6 @@ static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, GT_FIFO_CTL_RC6_POLICY_STALL); } - if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B_LAST)) - info->has_decoupled_mmio = false; - intel_uncore_forcewake_reset(dev_priv, restore_forcewake); } @@ -454,9 +450,12 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, fw_domains &= dev_priv->uncore.fw_domains; - for_each_fw_domain_masked(domain, fw_domains, dev_priv, tmp) - if (domain->wake_count++) + for_each_fw_domain_masked(domain, fw_domains, dev_priv, tmp) { + if (domain->wake_count++) { fw_domains &= ~domain->mask; + domain->active = true; + } + } if (fw_domains) dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); @@ -521,8 +520,10 @@ static void __intel_uncore_forcewake_put(struct drm_i915_private *dev_priv, if (WARN_ON(domain->wake_count == 0)) continue; - if (--domain->wake_count) + if (--domain->wake_count) { + domain->active = true; continue; + } fw_domain_arm_timer(domain); } @@ -804,66 +805,6 @@ unclaimed_reg_debug(struct drm_i915_private *dev_priv, __unclaimed_reg_debug(dev_priv, reg, read, before); } -static const enum decoupled_power_domain fw2dpd_domain[] = { - GEN9_DECOUPLED_PD_RENDER, - GEN9_DECOUPLED_PD_BLITTER, - GEN9_DECOUPLED_PD_ALL, - GEN9_DECOUPLED_PD_MEDIA, - GEN9_DECOUPLED_PD_ALL, - GEN9_DECOUPLED_PD_ALL, - GEN9_DECOUPLED_PD_ALL -}; - -/* - * Decoupled MMIO access for only 1 DWORD - */ -static void __gen9_decoupled_mmio_access(struct drm_i915_private *dev_priv, - u32 reg, - enum forcewake_domains fw_domain, - enum decoupled_ops operation) -{ - enum decoupled_power_domain dp_domain; - u32 ctrl_reg_data = 0; - - dp_domain = fw2dpd_domain[fw_domain - 1]; - - ctrl_reg_data |= reg; - ctrl_reg_data |= (operation << GEN9_DECOUPLED_OP_SHIFT); - ctrl_reg_data |= (dp_domain << GEN9_DECOUPLED_PD_SHIFT); - ctrl_reg_data |= GEN9_DECOUPLED_DW1_GO; - __raw_i915_write32(dev_priv, GEN9_DECOUPLED_REG0_DW1, ctrl_reg_data); - - if (wait_for_atomic((__raw_i915_read32(dev_priv, - GEN9_DECOUPLED_REG0_DW1) & - GEN9_DECOUPLED_DW1_GO) == 0, - FORCEWAKE_ACK_TIMEOUT_MS)) - DRM_ERROR("Decoupled MMIO wait timed out\n"); -} - -static inline u32 -__gen9_decoupled_mmio_read32(struct drm_i915_private *dev_priv, - u32 reg, - enum forcewake_domains fw_domain) -{ - __gen9_decoupled_mmio_access(dev_priv, reg, fw_domain, - GEN9_DECOUPLED_OP_READ); - - return __raw_i915_read32(dev_priv, GEN9_DECOUPLED_REG0_DW0); -} - -static inline void -__gen9_decoupled_mmio_write(struct drm_i915_private *dev_priv, - u32 reg, u32 data, - enum forcewake_domains fw_domain) -{ - - __raw_i915_write32(dev_priv, GEN9_DECOUPLED_REG0_DW0, data); - - __gen9_decoupled_mmio_access(dev_priv, reg, fw_domain, - GEN9_DECOUPLED_OP_WRITE); -} - - #define GEN2_READ_HEADER(x) \ u##x val = 0; \ assert_rpm_wakelock_held(dev_priv); @@ -960,28 +901,6 @@ func##_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { #define __gen6_read(x) __gen_read(gen6, x) #define __fwtable_read(x) __gen_read(fwtable, x) -#define __gen9_decoupled_read(x) \ -static u##x \ -gen9_decoupled_read##x(struct drm_i915_private *dev_priv, \ - i915_reg_t reg, bool trace) { \ - enum forcewake_domains fw_engine; \ - GEN6_READ_HEADER(x); \ - fw_engine = __fwtable_reg_read_fw_domains(offset); \ - if (fw_engine & ~dev_priv->uncore.fw_domains_active) { \ - unsigned i; \ - u32 *ptr_data = (u32 *) &val; \ - for (i = 0; i < x/32; i++, offset += sizeof(u32), ptr_data++) \ - *ptr_data = __gen9_decoupled_mmio_read32(dev_priv, \ - offset, \ - fw_engine); \ - } else { \ - val = __raw_i915_read##x(dev_priv, reg); \ - } \ - GEN6_READ_FOOTER; \ -} - -__gen9_decoupled_read(32) -__gen9_decoupled_read(64) __fwtable_read(8) __fwtable_read(16) __fwtable_read(32) @@ -1047,15 +966,10 @@ __gen2_write(32) #define __gen6_write(x) \ static void \ gen6_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ - u32 __fifo_ret = 0; \ GEN6_WRITE_HEADER; \ - if (NEEDS_FORCE_WAKE(offset)) { \ - __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ - } \ + if (NEEDS_FORCE_WAKE(offset)) \ + __gen6_gt_wait_for_fifo(dev_priv); \ __raw_i915_write##x(dev_priv, reg, val); \ - if (unlikely(__fifo_ret)) { \ - gen6_gt_check_fifodbg(dev_priv); \ - } \ GEN6_WRITE_FOOTER; \ } @@ -1073,25 +987,6 @@ func##_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, boo #define __gen8_write(x) __gen_write(gen8, x) #define __fwtable_write(x) __gen_write(fwtable, x) -#define __gen9_decoupled_write(x) \ -static void \ -gen9_decoupled_write##x(struct drm_i915_private *dev_priv, \ - i915_reg_t reg, u##x val, \ - bool trace) { \ - enum forcewake_domains fw_engine; \ - GEN6_WRITE_HEADER; \ - fw_engine = __fwtable_reg_write_fw_domains(offset); \ - if (fw_engine & ~dev_priv->uncore.fw_domains_active) \ - __gen9_decoupled_mmio_write(dev_priv, \ - offset, \ - val, \ - fw_engine); \ - else \ - __raw_i915_write##x(dev_priv, reg, val); \ - GEN6_WRITE_FOOTER; \ -} - -__gen9_decoupled_write(32) __fwtable_write(8) __fwtable_write(16) __fwtable_write(32) @@ -1108,19 +1003,19 @@ __gen6_write(32) #undef GEN6_WRITE_FOOTER #undef GEN6_WRITE_HEADER -#define ASSIGN_WRITE_MMIO_VFUNCS(x) \ +#define ASSIGN_WRITE_MMIO_VFUNCS(i915, x) \ do { \ - dev_priv->uncore.funcs.mmio_writeb = x##_write8; \ - dev_priv->uncore.funcs.mmio_writew = x##_write16; \ - dev_priv->uncore.funcs.mmio_writel = x##_write32; \ + (i915)->uncore.funcs.mmio_writeb = x##_write8; \ + (i915)->uncore.funcs.mmio_writew = x##_write16; \ + (i915)->uncore.funcs.mmio_writel = x##_write32; \ } while (0) -#define ASSIGN_READ_MMIO_VFUNCS(x) \ +#define ASSIGN_READ_MMIO_VFUNCS(i915, x) \ do { \ - dev_priv->uncore.funcs.mmio_readb = x##_read8; \ - dev_priv->uncore.funcs.mmio_readw = x##_read16; \ - dev_priv->uncore.funcs.mmio_readl = x##_read32; \ - dev_priv->uncore.funcs.mmio_readq = x##_read64; \ + (i915)->uncore.funcs.mmio_readb = x##_read8; \ + (i915)->uncore.funcs.mmio_readw = x##_read16; \ + (i915)->uncore.funcs.mmio_readl = x##_read32; \ + (i915)->uncore.funcs.mmio_readq = x##_read64; \ } while (0) @@ -1190,11 +1085,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) FORCEWAKE_MEDIA_GEN9, FORCEWAKE_ACK_MEDIA_GEN9); } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get; - if (!IS_CHERRYVIEW(dev_priv)) - dev_priv->uncore.funcs.force_wake_put = - fw_domains_put_with_fifo; - else - dev_priv->uncore.funcs.force_wake_put = fw_domains_put; + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_VLV, FORCEWAKE_ACK_VLV); fw_domain_init(dev_priv, FW_DOMAIN_ID_MEDIA, @@ -1202,11 +1093,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - if (IS_HASWELL(dev_priv)) - dev_priv->uncore.funcs.force_wake_put = - fw_domains_put_with_fifo; - else - dev_priv->uncore.funcs.force_wake_put = fw_domains_put; + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_ACK_HSW); } else if (IS_IVYBRIDGE(dev_priv)) { @@ -1223,8 +1110,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) */ dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - dev_priv->uncore.funcs.force_wake_put = - fw_domains_put_with_fifo; + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; /* We need to init first for ECOBUS access and then * determine later if we want to reinit, in case of MT access is @@ -1242,7 +1128,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) spin_lock_irq(&dev_priv->uncore.lock); fw_domains_get_with_thread_status(dev_priv, FORCEWAKE_RENDER); ecobus = __raw_i915_read32(dev_priv, ECOBUS); - fw_domains_put_with_fifo(dev_priv, FORCEWAKE_RENDER); + fw_domains_put(dev_priv, FORCEWAKE_RENDER); spin_unlock_irq(&dev_priv->uncore.lock); if (!(ecobus & FORCEWAKE_MT_ENABLE)) { @@ -1254,8 +1140,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) } else if (IS_GEN6(dev_priv)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - dev_priv->uncore.funcs.force_wake_put = - fw_domains_put_with_fifo; + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE, FORCEWAKE_ACK); } @@ -1310,42 +1195,34 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) i915_pmic_bus_access_notifier; if (IS_GEN(dev_priv, 2, 4) || intel_vgpu_active(dev_priv)) { - ASSIGN_WRITE_MMIO_VFUNCS(gen2); - ASSIGN_READ_MMIO_VFUNCS(gen2); + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen2); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen2); } else if (IS_GEN5(dev_priv)) { - ASSIGN_WRITE_MMIO_VFUNCS(gen5); - ASSIGN_READ_MMIO_VFUNCS(gen5); + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen5); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen5); } else if (IS_GEN(dev_priv, 6, 7)) { - ASSIGN_WRITE_MMIO_VFUNCS(gen6); + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen6); if (IS_VALLEYVIEW(dev_priv)) { ASSIGN_FW_DOMAINS_TABLE(__vlv_fw_ranges); - ASSIGN_READ_MMIO_VFUNCS(fwtable); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, fwtable); } else { - ASSIGN_READ_MMIO_VFUNCS(gen6); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen6); } } else if (IS_GEN8(dev_priv)) { if (IS_CHERRYVIEW(dev_priv)) { ASSIGN_FW_DOMAINS_TABLE(__chv_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(fwtable); - ASSIGN_READ_MMIO_VFUNCS(fwtable); + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, fwtable); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, fwtable); } else { - ASSIGN_WRITE_MMIO_VFUNCS(gen8); - ASSIGN_READ_MMIO_VFUNCS(gen6); + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen8); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen6); } } else { ASSIGN_FW_DOMAINS_TABLE(__gen9_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(fwtable); - ASSIGN_READ_MMIO_VFUNCS(fwtable); - if (HAS_DECOUPLED_MMIO(dev_priv)) { - dev_priv->uncore.funcs.mmio_readl = - gen9_decoupled_read32; - dev_priv->uncore.funcs.mmio_readq = - gen9_decoupled_read64; - dev_priv->uncore.funcs.mmio_writel = - gen9_decoupled_write32; - } + ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, fwtable); + ASSIGN_READ_MMIO_VFUNCS(dev_priv, fwtable); } iosf_mbi_register_pmic_bus_access_notifier( @@ -1353,8 +1230,6 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) i915_check_and_clear_faults(dev_priv); } -#undef ASSIGN_WRITE_MMIO_VFUNCS -#undef ASSIGN_READ_MMIO_VFUNCS void intel_uncore_fini(struct drm_i915_private *dev_priv) { @@ -1435,9 +1310,39 @@ int i915_reg_read_ioctl(struct drm_device *dev, return ret; } -static int i915_reset_complete(struct pci_dev *pdev) +static void gen3_stop_rings(struct drm_i915_private *dev_priv) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, dev_priv, id) { + const u32 base = engine->mmio_base; + const i915_reg_t mode = RING_MI_MODE(base); + + I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING)); + if (intel_wait_for_register_fw(dev_priv, + mode, + MODE_IDLE, + MODE_IDLE, + 500)) + DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", + engine->name); + + I915_WRITE_FW(RING_CTL(base), 0); + I915_WRITE_FW(RING_HEAD(base), 0); + I915_WRITE_FW(RING_TAIL(base), 0); + + /* Check acts as a post */ + if (I915_READ_FW(RING_HEAD(base)) != 0) + DRM_DEBUG_DRIVER("%s: ring head not parked\n", + engine->name); + } +} + +static bool i915_reset_complete(struct pci_dev *pdev) { u8 gdrst; + pci_read_config_byte(pdev, I915_GDRST, &gdrst); return (gdrst & GRDOM_RESET_STATUS) == 0; } @@ -1448,15 +1353,16 @@ static int i915_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask /* assert reset for at least 20 usec */ pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); - udelay(20); + usleep_range(50, 200); pci_write_config_byte(pdev, I915_GDRST, 0); return wait_for(i915_reset_complete(pdev), 500); } -static int g4x_reset_complete(struct pci_dev *pdev) +static bool g4x_reset_complete(struct pci_dev *pdev) { u8 gdrst; + pci_read_config_byte(pdev, I915_GDRST, &gdrst); return (gdrst & GRDOM_RESET_ENABLE) == 0; } @@ -1464,6 +1370,10 @@ static int g4x_reset_complete(struct pci_dev *pdev) static int g33_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask) { struct pci_dev *pdev = dev_priv->drm.pdev; + + /* Stop engines before we reset; see g4x_do_reset() below for why. */ + gen3_stop_rings(dev_priv); + pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); return wait_for(g4x_reset_complete(pdev), 500); } @@ -1473,29 +1383,41 @@ static int g4x_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask) struct pci_dev *pdev = dev_priv->drm.pdev; int ret; - pci_write_config_byte(pdev, I915_GDRST, - GRDOM_RENDER | GRDOM_RESET_ENABLE); - ret = wait_for(g4x_reset_complete(pdev), 500); - if (ret) - return ret; - /* WaVcpClkGateDisableForMediaReset:ctg,elk */ - I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE); + I915_WRITE(VDECCLK_GATE_D, + I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE); POSTING_READ(VDECCLK_GATE_D); + /* We stop engines, otherwise we might get failed reset and a + * dead gpu (on elk). + * WaMediaResetMainRingCleanup:ctg,elk (presumably) + */ + gen3_stop_rings(dev_priv); + pci_write_config_byte(pdev, I915_GDRST, GRDOM_MEDIA | GRDOM_RESET_ENABLE); ret = wait_for(g4x_reset_complete(pdev), 500); - if (ret) - return ret; + if (ret) { + DRM_DEBUG_DRIVER("Wait for media reset failed\n"); + goto out; + } - /* WaVcpClkGateDisableForMediaReset:ctg,elk */ - I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE); - POSTING_READ(VDECCLK_GATE_D); + pci_write_config_byte(pdev, I915_GDRST, + GRDOM_RENDER | GRDOM_RESET_ENABLE); + ret = wait_for(g4x_reset_complete(pdev), 500); + if (ret) { + DRM_DEBUG_DRIVER("Wait for render reset failed\n"); + goto out; + } +out: pci_write_config_byte(pdev, I915_GDRST, 0); - return 0; + I915_WRITE(VDECCLK_GATE_D, + I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE); + POSTING_READ(VDECCLK_GATE_D); + + return ret; } static int ironlake_do_reset(struct drm_i915_private *dev_priv, @@ -1503,41 +1425,51 @@ static int ironlake_do_reset(struct drm_i915_private *dev_priv, { int ret; - I915_WRITE(ILK_GDSR, - ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE); + I915_WRITE(ILK_GDSR, ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE); ret = intel_wait_for_register(dev_priv, ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0, 500); - if (ret) - return ret; + if (ret) { + DRM_DEBUG_DRIVER("Wait for render reset failed\n"); + goto out; + } - I915_WRITE(ILK_GDSR, - ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE); + I915_WRITE(ILK_GDSR, ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE); ret = intel_wait_for_register(dev_priv, ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0, 500); - if (ret) - return ret; + if (ret) { + DRM_DEBUG_DRIVER("Wait for media reset failed\n"); + goto out; + } +out: I915_WRITE(ILK_GDSR, 0); - - return 0; + POSTING_READ(ILK_GDSR); + return ret; } /* Reset the hardware domains (GENX_GRDOM_*) specified by mask */ static int gen6_hw_domain_reset(struct drm_i915_private *dev_priv, u32 hw_domain_mask) { + int err; + /* GEN6_GDRST is not in the gt power well, no need to check * for fifo space for the write or forcewake the chip for * the read */ __raw_i915_write32(dev_priv, GEN6_GDRST, hw_domain_mask); - /* Spin waiting for the device to ack the reset requests */ - return intel_wait_for_register_fw(dev_priv, + /* Wait for the device to ack the reset requests */ + err = intel_wait_for_register_fw(dev_priv, GEN6_GDRST, hw_domain_mask, 0, 500); + if (err) + DRM_DEBUG_DRIVER("Wait for 0x%08x engines reset failed\n", + hw_domain_mask); + + return err; } /** @@ -1585,19 +1517,23 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv, } /** - * intel_wait_for_register_fw - wait until register matches expected state + * __intel_wait_for_register_fw - wait until register matches expected state * @dev_priv: the i915 device * @reg: the register to read * @mask: mask to apply to register value * @value: expected value - * @timeout_ms: timeout in millisecond + * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait + * @slow_timeout_ms: slow timeout in millisecond + * @out_value: optional placeholder to hold registry value * * This routine waits until the target register @reg contains the expected * @value after applying the @mask, i.e. it waits until :: * * (I915_READ_FW(reg) & mask) == value * - * Otherwise, the wait will timeout after @timeout_ms milliseconds. + * Otherwise, the wait will timeout after @slow_timeout_ms milliseconds. + * For atomic context @slow_timeout_ms must be zero and @fast_timeout_us + * must be not larger than 20,0000 microseconds. * * Note that this routine assumes the caller holds forcewake asserted, it is * not suitable for very long waits. See intel_wait_for_register() if you @@ -1606,16 +1542,31 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv, * * Returns 0 if the register matches the desired condition, or -ETIMEOUT. */ -int intel_wait_for_register_fw(struct drm_i915_private *dev_priv, - i915_reg_t reg, - const u32 mask, - const u32 value, - const unsigned long timeout_ms) -{ -#define done ((I915_READ_FW(reg) & mask) == value) - int ret = wait_for_us(done, 2); - if (ret) - ret = wait_for(done, timeout_ms); +int __intel_wait_for_register_fw(struct drm_i915_private *dev_priv, + i915_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms, + u32 *out_value) +{ + u32 uninitialized_var(reg_value); +#define done (((reg_value = I915_READ_FW(reg)) & mask) == value) + int ret; + + /* Catch any overuse of this function */ + might_sleep_if(slow_timeout_ms); + GEM_BUG_ON(fast_timeout_us > 20000); + + ret = -ETIMEDOUT; + if (fast_timeout_us && fast_timeout_us <= 20000) + ret = _wait_for_atomic(done, fast_timeout_us, 0); + if (ret && slow_timeout_ms) + ret = wait_for(done, slow_timeout_ms); + + if (out_value) + *out_value = reg_value; + return ret; #undef done } @@ -1639,18 +1590,26 @@ int intel_wait_for_register_fw(struct drm_i915_private *dev_priv, */ int intel_wait_for_register(struct drm_i915_private *dev_priv, i915_reg_t reg, - const u32 mask, - const u32 value, - const unsigned long timeout_ms) + u32 mask, + u32 value, + unsigned int timeout_ms) { - unsigned fw = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ); int ret; - intel_uncore_forcewake_get(dev_priv, fw); - ret = wait_for_us((I915_READ_FW(reg) & mask) == value, 2); - intel_uncore_forcewake_put(dev_priv, fw); + might_sleep(); + + spin_lock_irq(&dev_priv->uncore.lock); + intel_uncore_forcewake_get__locked(dev_priv, fw); + + ret = __intel_wait_for_register_fw(dev_priv, + reg, mask, value, + 2, 0, NULL); + + intel_uncore_forcewake_put__locked(dev_priv, fw); + spin_unlock_irq(&dev_priv->uncore.lock); + if (ret) ret = wait_for((I915_READ_NOTRACE(reg) & mask) == value, timeout_ms); @@ -1658,7 +1617,7 @@ int intel_wait_for_register(struct drm_i915_private *dev_priv, return ret; } -static int gen8_request_engine_reset(struct intel_engine_cs *engine) +static int gen8_reset_engine_start(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; int ret; @@ -1677,7 +1636,7 @@ static int gen8_request_engine_reset(struct intel_engine_cs *engine) return ret; } -static void gen8_unrequest_engine_reset(struct intel_engine_cs *engine) +static void gen8_reset_engine_cancel(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; @@ -1692,14 +1651,14 @@ static int gen8_reset_engines(struct drm_i915_private *dev_priv, unsigned int tmp; for_each_engine_masked(engine, dev_priv, engine_mask, tmp) - if (gen8_request_engine_reset(engine)) + if (gen8_reset_engine_start(engine)) goto not_ready; return gen6_reset_engines(dev_priv, engine_mask); not_ready: for_each_engine_masked(engine, dev_priv, engine_mask, tmp) - gen8_unrequest_engine_reset(engine); + gen8_reset_engine_cancel(engine); return -EIO; } @@ -1730,8 +1689,11 @@ static reset_func intel_get_gpu_reset(struct drm_i915_private *dev_priv) int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask) { reset_func reset; + int retry; int ret; + might_sleep(); + reset = intel_get_gpu_reset(dev_priv); if (reset == NULL) return -ENODEV; @@ -1740,7 +1702,13 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask) * request may be dropped and never completes (causing -EIO). */ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - ret = reset(dev_priv, engine_mask); + for (retry = 0; retry < 3; retry++) { + ret = reset(dev_priv, engine_mask); + if (ret != -ETIMEDOUT) + break; + + cond_resched(); + } intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); return ret; @@ -1754,17 +1722,12 @@ bool intel_has_gpu_reset(struct drm_i915_private *dev_priv) int intel_guc_reset(struct drm_i915_private *dev_priv) { int ret; - unsigned long irqflags; if (!HAS_GUC(dev_priv)) return -EINVAL; intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - ret = gen6_hw_domain_reset(dev_priv, GEN9_GRDOM_GUC); - - spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); return ret; @@ -1873,5 +1836,6 @@ intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv, } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/mock_uncore.c" #include "selftests/intel_uncore.c" #endif diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h new file mode 100644 index 00000000000000..5f90278da46121 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -0,0 +1,170 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#ifndef __INTEL_UNCORE_H__ +#define __INTEL_UNCORE_H__ + +struct drm_i915_private; + +enum forcewake_domain_id { + FW_DOMAIN_ID_RENDER = 0, + FW_DOMAIN_ID_BLITTER, + FW_DOMAIN_ID_MEDIA, + + FW_DOMAIN_ID_COUNT +}; + +enum forcewake_domains { + FORCEWAKE_RENDER = BIT(FW_DOMAIN_ID_RENDER), + FORCEWAKE_BLITTER = BIT(FW_DOMAIN_ID_BLITTER), + FORCEWAKE_MEDIA = BIT(FW_DOMAIN_ID_MEDIA), + FORCEWAKE_ALL = (FORCEWAKE_RENDER | + FORCEWAKE_BLITTER | + FORCEWAKE_MEDIA) +}; + +struct intel_uncore_funcs { + void (*force_wake_get)(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); + void (*force_wake_put)(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); + + uint8_t (*mmio_readb)(struct drm_i915_private *dev_priv, + i915_reg_t r, bool trace); + uint16_t (*mmio_readw)(struct drm_i915_private *dev_priv, + i915_reg_t r, bool trace); + uint32_t (*mmio_readl)(struct drm_i915_private *dev_priv, + i915_reg_t r, bool trace); + uint64_t (*mmio_readq)(struct drm_i915_private *dev_priv, + i915_reg_t r, bool trace); + + void (*mmio_writeb)(struct drm_i915_private *dev_priv, + i915_reg_t r, uint8_t val, bool trace); + void (*mmio_writew)(struct drm_i915_private *dev_priv, + i915_reg_t r, uint16_t val, bool trace); + void (*mmio_writel)(struct drm_i915_private *dev_priv, + i915_reg_t r, uint32_t val, bool trace); +}; + +struct intel_forcewake_range { + u32 start; + u32 end; + + enum forcewake_domains domains; +}; + +struct intel_uncore { + spinlock_t lock; /** lock is also taken in irq contexts. */ + + const struct intel_forcewake_range *fw_domains_table; + unsigned int fw_domains_table_entries; + + struct notifier_block pmic_bus_access_nb; + struct intel_uncore_funcs funcs; + + unsigned int fifo_count; + + enum forcewake_domains fw_domains; + enum forcewake_domains fw_domains_active; + + u32 fw_set; + u32 fw_clear; + u32 fw_reset; + + struct intel_uncore_forcewake_domain { + enum forcewake_domain_id id; + enum forcewake_domains mask; + unsigned int wake_count; + bool active; + struct hrtimer timer; + i915_reg_t reg_set; + i915_reg_t reg_ack; + } fw_domain[FW_DOMAIN_ID_COUNT]; + + int unclaimed_mmio_check; +}; + +/* Iterate over initialised fw domains */ +#define for_each_fw_domain_masked(domain__, mask__, dev_priv__, tmp__) \ + for (tmp__ = (mask__); \ + tmp__ ? (domain__ = &(dev_priv__)->uncore.fw_domain[__mask_next_bit(tmp__)]), 1 : 0;) + +#define for_each_fw_domain(domain__, dev_priv__, tmp__) \ + for_each_fw_domain_masked(domain__, (dev_priv__)->uncore.fw_domains, dev_priv__, tmp__) + + +void intel_uncore_sanitize(struct drm_i915_private *dev_priv); +void intel_uncore_init(struct drm_i915_private *dev_priv); +bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv); +bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv); +void intel_uncore_fini(struct drm_i915_private *dev_priv); +void intel_uncore_suspend(struct drm_i915_private *dev_priv); +void intel_uncore_resume_early(struct drm_i915_private *dev_priv); + +u64 intel_uncore_edram_size(struct drm_i915_private *dev_priv); +void assert_forcewakes_inactive(struct drm_i915_private *dev_priv); +const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id); + +enum forcewake_domains +intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv, + i915_reg_t reg, unsigned int op); +#define FW_REG_READ (1) +#define FW_REG_WRITE (2) + +void intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); +void intel_uncore_forcewake_put(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); +/* Like above but the caller must manage the uncore.lock itself. + * Must be used with I915_READ_FW and friends. + */ +void intel_uncore_forcewake_get__locked(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); +void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv, + enum forcewake_domains domains); + +int intel_wait_for_register(struct drm_i915_private *dev_priv, + i915_reg_t reg, + u32 mask, + u32 value, + unsigned int timeout_ms); +int __intel_wait_for_register_fw(struct drm_i915_private *dev_priv, + i915_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms, + u32 *out_value); +static inline +int intel_wait_for_register_fw(struct drm_i915_private *dev_priv, + i915_reg_t reg, + u32 mask, + u32 value, + unsigned int timeout_ms) +{ + return __intel_wait_for_register_fw(dev_priv, reg, mask, value, + 2, timeout_ms, NULL); +} + +#endif /* !__INTEL_UNCORE_H__ */ diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c index f08d0179b3df2e..95d4aebc01817a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c @@ -138,10 +138,7 @@ static int wc_set(struct drm_i915_gem_object *obj, typeof(v) *map; int err; - /* XXX GTT write followed by WC write go missing */ - i915_gem_object_flush_gtt_write_domain(obj); - - err = i915_gem_object_set_to_gtt_domain(obj, true); + err = i915_gem_object_set_to_wc_domain(obj, true); if (err) return err; @@ -162,10 +159,7 @@ static int wc_get(struct drm_i915_gem_object *obj, typeof(v) map; int err; - /* XXX WC write followed by GTT write go missing */ - i915_gem_object_flush_gtt_write_domain(obj); - - err = i915_gem_object_set_to_gtt_domain(obj, false); + err = i915_gem_object_set_to_wc_domain(obj, false); if (err) return err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c index 817bef74bbcbc4..d15cc9d3a5cd19 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c @@ -271,6 +271,105 @@ static int igt_dmabuf_export_vmap(void *arg) return err; } +static int igt_dmabuf_export_kmap(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct drm_i915_gem_object *obj; + struct dma_buf *dmabuf; + void *ptr; + int err; + + obj = i915_gem_object_create(i915, 2*PAGE_SIZE); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + dmabuf = i915_gem_prime_export(&i915->drm, &obj->base, 0); + i915_gem_object_put(obj); + if (IS_ERR(dmabuf)) { + err = PTR_ERR(dmabuf); + pr_err("i915_gem_prime_export failed with err=%d\n", err); + return err; + } + + ptr = dma_buf_kmap(dmabuf, 0); + if (!ptr) { + pr_err("dma_buf_kmap failed\n"); + err = -ENOMEM; + goto err; + } + + if (memchr_inv(ptr, 0, PAGE_SIZE)) { + dma_buf_kunmap(dmabuf, 0, ptr); + pr_err("Exported page[0] not initialiased to zero!\n"); + err = -EINVAL; + goto err; + } + + memset(ptr, 0xc5, PAGE_SIZE); + dma_buf_kunmap(dmabuf, 0, ptr); + + ptr = i915_gem_object_pin_map(obj, I915_MAP_WB); + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + pr_err("i915_gem_object_pin_map failed with err=%d\n", err); + goto err; + } + memset(ptr + PAGE_SIZE, 0xaa, PAGE_SIZE); + i915_gem_object_unpin_map(obj); + + ptr = dma_buf_kmap(dmabuf, 1); + if (!ptr) { + pr_err("dma_buf_kmap failed\n"); + err = -ENOMEM; + goto err; + } + + if (memchr_inv(ptr, 0xaa, PAGE_SIZE)) { + dma_buf_kunmap(dmabuf, 1, ptr); + pr_err("Exported page[1] not set to 0xaa!\n"); + err = -EINVAL; + goto err; + } + + memset(ptr, 0xc5, PAGE_SIZE); + dma_buf_kunmap(dmabuf, 1, ptr); + + ptr = dma_buf_kmap(dmabuf, 0); + if (!ptr) { + pr_err("dma_buf_kmap failed\n"); + err = -ENOMEM; + goto err; + } + if (memchr_inv(ptr, 0xc5, PAGE_SIZE)) { + dma_buf_kunmap(dmabuf, 0, ptr); + pr_err("Exported page[0] did not retain 0xc5!\n"); + err = -EINVAL; + goto err; + } + dma_buf_kunmap(dmabuf, 0, ptr); + + ptr = dma_buf_kmap(dmabuf, 2); + if (ptr) { + pr_err("Erroneously kmapped beyond the end of the object!\n"); + dma_buf_kunmap(dmabuf, 2, ptr); + err = -EINVAL; + goto err; + } + + ptr = dma_buf_kmap(dmabuf, -1); + if (ptr) { + pr_err("Erroneously kmapped before the start of the object!\n"); + dma_buf_kunmap(dmabuf, -1, ptr); + err = -EINVAL; + goto err; + } + + err = 0; +err: + dma_buf_put(dmabuf); + return err; +} + int i915_gem_dmabuf_mock_selftests(void) { static const struct i915_subtest tests[] = { @@ -279,6 +378,7 @@ int i915_gem_dmabuf_mock_selftests(void) SUBTEST(igt_dmabuf_import), SUBTEST(igt_dmabuf_import_ownership), SUBTEST(igt_dmabuf_export_vmap), + SUBTEST(igt_dmabuf_export_kmap), }; struct drm_i915_private *i915; int err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index 67d82bf1407f00..8f011c447e4103 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -266,7 +266,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, if (offset >= obj->base.size) continue; - i915_gem_object_flush_gtt_write_domain(obj); + flush_write_domain(obj, ~I915_GEM_DOMAIN_CPU); p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT); cpu = kmap(p) + offset_in_page(offset); @@ -545,7 +545,9 @@ static int igt_mmap_offset_exhaustion(void *arg) } mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); err = make_obj_busy(obj); + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); if (err) { pr_err("[loop %d] Failed to busy the object\n", loop); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_request.c b/drivers/gpu/drm/i915/selftests/i915_gem_request.c index 98b7aac41eec7e..6664cb2eb0b8dd 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_request.c @@ -580,7 +580,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915) if (err) goto err; - err = i915_gem_object_set_to_gtt_domain(obj, true); + err = i915_gem_object_set_to_wc_domain(obj, true); if (err) goto err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c new file mode 100644 index 00000000000000..7a44dab631b8ec --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c @@ -0,0 +1,299 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include "../i915_selftest.h" +#include "i915_random.h" + +#include "mock_gem_device.h" +#include "mock_timeline.h" + +struct __igt_sync { + const char *name; + u32 seqno; + bool expected; + bool set; +}; + +static int __igt_sync(struct intel_timeline *tl, + u64 ctx, + const struct __igt_sync *p, + const char *name) +{ + int ret; + + if (__intel_timeline_sync_is_later(tl, ctx, p->seqno) != p->expected) { + pr_err("%s: %s(ctx=%llu, seqno=%u) expected passed %s but failed\n", + name, p->name, ctx, p->seqno, yesno(p->expected)); + return -EINVAL; + } + + if (p->set) { + ret = __intel_timeline_sync_set(tl, ctx, p->seqno); + if (ret) + return ret; + } + + return 0; +} + +static int igt_sync(void *arg) +{ + const struct __igt_sync pass[] = { + { "unset", 0, false, false }, + { "new", 0, false, true }, + { "0a", 0, true, true }, + { "1a", 1, false, true }, + { "1b", 1, true, true }, + { "0b", 0, true, false }, + { "2a", 2, false, true }, + { "4", 4, false, true }, + { "INT_MAX", INT_MAX, false, true }, + { "INT_MAX-1", INT_MAX-1, true, false }, + { "INT_MAX+1", (u32)INT_MAX+1, false, true }, + { "INT_MAX", INT_MAX, true, false }, + { "UINT_MAX", UINT_MAX, false, true }, + { "wrap", 0, false, true }, + { "unwrap", UINT_MAX, true, false }, + {}, + }, *p; + struct intel_timeline *tl; + int order, offset; + int ret; + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + for (p = pass; p->name; p++) { + for (order = 1; order < 64; order++) { + for (offset = -1; offset <= (order > 1); offset++) { + u64 ctx = BIT_ULL(order) + offset; + + ret = __igt_sync(tl, ctx, p, "1"); + if (ret) + goto out; + } + } + } + mock_timeline_destroy(tl); + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + for (order = 1; order < 64; order++) { + for (offset = -1; offset <= (order > 1); offset++) { + u64 ctx = BIT_ULL(order) + offset; + + for (p = pass; p->name; p++) { + ret = __igt_sync(tl, ctx, p, "2"); + if (ret) + goto out; + } + } + } + +out: + mock_timeline_destroy(tl); + return ret; +} + +static unsigned int random_engine(struct rnd_state *rnd) +{ + return ((u64)prandom_u32_state(rnd) * I915_NUM_ENGINES) >> 32; +} + +static int bench_sync(void *arg) +{ + struct rnd_state prng; + struct intel_timeline *tl; + unsigned long end_time, count; + u64 prng32_1M; + ktime_t kt; + int order, last_order; + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + /* Lookups from cache are very fast and so the random number generation + * and the loop itself becomes a significant factor in the per-iteration + * timings. We try to compensate the results by measuring the overhead + * of the prng and subtract it from the reported results. + */ + prandom_seed_state(&prng, i915_selftest.random_seed); + count = 0; + kt = ktime_get(); + end_time = jiffies + HZ/10; + do { + u32 x; + + /* Make sure the compiler doesn't optimise away the prng call */ + WRITE_ONCE(x, prandom_u32_state(&prng)); + + count++; + } while (!time_after(jiffies, end_time)); + kt = ktime_sub(ktime_get(), kt); + pr_debug("%s: %lu random evaluations, %lluns/prng\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + prng32_1M = div64_ul(ktime_to_ns(kt) << 20, count); + + /* Benchmark (only) setting random context ids */ + prandom_seed_state(&prng, i915_selftest.random_seed); + count = 0; + kt = ktime_get(); + end_time = jiffies + HZ/10; + do { + u64 id = i915_prandom_u64_state(&prng); + + __intel_timeline_sync_set(tl, id, 0); + count++; + } while (!time_after(jiffies, end_time)); + kt = ktime_sub(ktime_get(), kt); + kt = ktime_sub_ns(kt, (count * prng32_1M * 2) >> 20); + pr_info("%s: %lu random insertions, %lluns/insert\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + + /* Benchmark looking up the exact same context ids as we just set */ + prandom_seed_state(&prng, i915_selftest.random_seed); + end_time = count; + kt = ktime_get(); + while (end_time--) { + u64 id = i915_prandom_u64_state(&prng); + + if (!__intel_timeline_sync_is_later(tl, id, 0)) { + mock_timeline_destroy(tl); + pr_err("Lookup of %llu failed\n", id); + return -EINVAL; + } + } + kt = ktime_sub(ktime_get(), kt); + kt = ktime_sub_ns(kt, (count * prng32_1M * 2) >> 20); + pr_info("%s: %lu random lookups, %lluns/lookup\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + + mock_timeline_destroy(tl); + cond_resched(); + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + /* Benchmark setting the first N (in order) contexts */ + count = 0; + kt = ktime_get(); + end_time = jiffies + HZ/10; + do { + __intel_timeline_sync_set(tl, count++, 0); + } while (!time_after(jiffies, end_time)); + kt = ktime_sub(ktime_get(), kt); + pr_info("%s: %lu in-order insertions, %lluns/insert\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + + /* Benchmark looking up the exact same context ids as we just set */ + end_time = count; + kt = ktime_get(); + while (end_time--) { + if (!__intel_timeline_sync_is_later(tl, end_time, 0)) { + pr_err("Lookup of %lu failed\n", end_time); + mock_timeline_destroy(tl); + return -EINVAL; + } + } + kt = ktime_sub(ktime_get(), kt); + pr_info("%s: %lu in-order lookups, %lluns/lookup\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + + mock_timeline_destroy(tl); + cond_resched(); + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + /* Benchmark searching for a random context id and maybe changing it */ + prandom_seed_state(&prng, i915_selftest.random_seed); + count = 0; + kt = ktime_get(); + end_time = jiffies + HZ/10; + do { + u32 id = random_engine(&prng); + u32 seqno = prandom_u32_state(&prng); + + if (!__intel_timeline_sync_is_later(tl, id, seqno)) + __intel_timeline_sync_set(tl, id, seqno); + + count++; + } while (!time_after(jiffies, end_time)); + kt = ktime_sub(ktime_get(), kt); + kt = ktime_sub_ns(kt, (count * prng32_1M * 2) >> 20); + pr_info("%s: %lu repeated insert/lookups, %lluns/op\n", + __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); + mock_timeline_destroy(tl); + cond_resched(); + + /* Benchmark searching for a known context id and changing the seqno */ + for (last_order = 1, order = 1; order < 32; + ({ int tmp = last_order; last_order = order; order += tmp; })) { + unsigned int mask = BIT(order) - 1; + + tl = mock_timeline(0); + if (!tl) + return -ENOMEM; + + count = 0; + kt = ktime_get(); + end_time = jiffies + HZ/10; + do { + /* Without assuming too many details of the underlying + * implementation, try to identify its phase-changes + * (if any)! + */ + u64 id = (u64)(count & mask) << order; + + __intel_timeline_sync_is_later(tl, id, 0); + __intel_timeline_sync_set(tl, id, 0); + + count++; + } while (!time_after(jiffies, end_time)); + kt = ktime_sub(ktime_get(), kt); + pr_info("%s: %lu cyclic/%d insert/lookups, %lluns/op\n", + __func__, count, order, + (long long)div64_ul(ktime_to_ns(kt), count)); + mock_timeline_destroy(tl); + cond_resched(); + } + + return 0; +} + +int i915_gem_timeline_mock_selftests(void) +{ + static const struct i915_subtest tests[] = { + SUBTEST(igt_sync), + SUBTEST(bench_sync), + }; + + return i915_subtests(tests, NULL); +} diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h index be9a9ebf5692d8..fc74687501ba92 100644 --- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h @@ -9,9 +9,12 @@ * Tests are executed in order by igt/drv_selftest */ selftest(sanitycheck, i915_mock_sanitycheck) /* keep first (igt selfcheck) */ +selftest(fence, i915_sw_fence_mock_selftests) selftest(scatterlist, scatterlist_mock_selftests) +selftest(syncmap, i915_syncmap_mock_selftests) selftest(uncore, intel_uncore_mock_selftests) selftest(breadcrumbs, intel_breadcrumbs_mock_selftests) +selftest(timelines, i915_gem_timeline_mock_selftests) selftest(requests, i915_gem_request_mock_selftests) selftest(objects, i915_gem_object_mock_selftests) selftest(dmabuf, i915_gem_dmabuf_mock_selftests) diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c index c17c83c3063784..d044bf9a6feb37 100644 --- a/drivers/gpu/drm/i915/selftests/i915_random.c +++ b/drivers/gpu/drm/i915/selftests/i915_random.c @@ -30,6 +30,17 @@ #include "i915_random.h" +u64 i915_prandom_u64_state(struct rnd_state *rnd) +{ + u64 x; + + x = prandom_u32_state(rnd); + x <<= 32; + x |= prandom_u32_state(rnd); + + return x; +} + static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state) { return upper_32_bits((u64)prandom_u32_state(state) * ep_ro); diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h index b9c334ce6cd949..6c937987138494 100644 --- a/drivers/gpu/drm/i915/selftests/i915_random.h +++ b/drivers/gpu/drm/i915/selftests/i915_random.h @@ -41,6 +41,8 @@ #define I915_RND_SUBSTATE(name__, parent__) \ struct rnd_state name__ = I915_RND_STATE_INITIALIZER(prandom_u32_state(&(parent__))) +u64 i915_prandom_u64_state(struct rnd_state *rnd); + unsigned int *i915_random_order(unsigned int count, struct rnd_state *state); void i915_random_reorder(unsigned int *order, diff --git a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c new file mode 100644 index 00000000000000..19d145d6bf5238 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c @@ -0,0 +1,582 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include +#include + +#include "../i915_selftest.h" + +static int __i915_sw_fence_call +fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) +{ + switch (state) { + case FENCE_COMPLETE: + break; + + case FENCE_FREE: + /* Leave the fence for the caller to free it after testing */ + break; + } + + return NOTIFY_DONE; +} + +static struct i915_sw_fence *alloc_fence(void) +{ + struct i915_sw_fence *fence; + + fence = kmalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) + return NULL; + + i915_sw_fence_init(fence, fence_notify); + return fence; +} + +static void free_fence(struct i915_sw_fence *fence) +{ + i915_sw_fence_fini(fence); + kfree(fence); +} + +static int __test_self(struct i915_sw_fence *fence) +{ + if (i915_sw_fence_done(fence)) + return -EINVAL; + + i915_sw_fence_commit(fence); + if (!i915_sw_fence_done(fence)) + return -EINVAL; + + i915_sw_fence_wait(fence); + if (!i915_sw_fence_done(fence)) + return -EINVAL; + + return 0; +} + +static int test_self(void *arg) +{ + struct i915_sw_fence *fence; + int ret; + + /* Test i915_sw_fence signaling and completion testing */ + fence = alloc_fence(); + if (!fence) + return -ENOMEM; + + ret = __test_self(fence); + + free_fence(fence); + return ret; +} + +static int test_dag(void *arg) +{ + struct i915_sw_fence *A, *B, *C; + int ret = -EINVAL; + + /* Test detection of cycles within the i915_sw_fence graphs */ + if (!IS_ENABLED(CONFIG_DRM_I915_SW_FENCE_CHECK_DAG)) + return 0; + + A = alloc_fence(); + if (!A) + return -ENOMEM; + + if (i915_sw_fence_await_sw_fence_gfp(A, A, GFP_KERNEL) != -EINVAL) { + pr_err("recursive cycle not detected (AA)\n"); + goto err_A; + } + + B = alloc_fence(); + if (!B) { + ret = -ENOMEM; + goto err_A; + } + + i915_sw_fence_await_sw_fence_gfp(A, B, GFP_KERNEL); + if (i915_sw_fence_await_sw_fence_gfp(B, A, GFP_KERNEL) != -EINVAL) { + pr_err("single depth cycle not detected (BAB)\n"); + goto err_B; + } + + C = alloc_fence(); + if (!C) { + ret = -ENOMEM; + goto err_B; + } + + if (i915_sw_fence_await_sw_fence_gfp(B, C, GFP_KERNEL) == -EINVAL) { + pr_err("invalid cycle detected\n"); + goto err_C; + } + if (i915_sw_fence_await_sw_fence_gfp(C, B, GFP_KERNEL) != -EINVAL) { + pr_err("single depth cycle not detected (CBC)\n"); + goto err_C; + } + if (i915_sw_fence_await_sw_fence_gfp(C, A, GFP_KERNEL) != -EINVAL) { + pr_err("cycle not detected (BA, CB, AC)\n"); + goto err_C; + } + if (i915_sw_fence_await_sw_fence_gfp(A, C, GFP_KERNEL) == -EINVAL) { + pr_err("invalid cycle detected\n"); + goto err_C; + } + + i915_sw_fence_commit(A); + i915_sw_fence_commit(B); + i915_sw_fence_commit(C); + + ret = 0; + if (!i915_sw_fence_done(C)) { + pr_err("fence C not done\n"); + ret = -EINVAL; + } + if (!i915_sw_fence_done(B)) { + pr_err("fence B not done\n"); + ret = -EINVAL; + } + if (!i915_sw_fence_done(A)) { + pr_err("fence A not done\n"); + ret = -EINVAL; + } +err_C: + free_fence(C); +err_B: + free_fence(B); +err_A: + free_fence(A); + return ret; +} + +static int test_AB(void *arg) +{ + struct i915_sw_fence *A, *B; + int ret; + + /* Test i915_sw_fence (A) waiting on an event source (B) */ + A = alloc_fence(); + if (!A) + return -ENOMEM; + B = alloc_fence(); + if (!B) { + ret = -ENOMEM; + goto err_A; + } + + ret = i915_sw_fence_await_sw_fence_gfp(A, B, GFP_KERNEL); + if (ret < 0) + goto err_B; + if (ret == 0) { + pr_err("Incorrectly reported fence A was complete before await\n"); + ret = -EINVAL; + goto err_B; + } + + ret = -EINVAL; + i915_sw_fence_commit(A); + if (i915_sw_fence_done(A)) + goto err_B; + + i915_sw_fence_commit(B); + if (!i915_sw_fence_done(B)) { + pr_err("Fence B is not done\n"); + goto err_B; + } + + if (!i915_sw_fence_done(A)) { + pr_err("Fence A is not done\n"); + goto err_B; + } + + ret = 0; +err_B: + free_fence(B); +err_A: + free_fence(A); + return ret; +} + +static int test_ABC(void *arg) +{ + struct i915_sw_fence *A, *B, *C; + int ret; + + /* Test a chain of fences, A waits on B who waits on C */ + A = alloc_fence(); + if (!A) + return -ENOMEM; + + B = alloc_fence(); + if (!B) { + ret = -ENOMEM; + goto err_A; + } + + C = alloc_fence(); + if (!C) { + ret = -ENOMEM; + goto err_B; + } + + ret = i915_sw_fence_await_sw_fence_gfp(A, B, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + pr_err("Incorrectly reported fence B was complete before await\n"); + goto err_C; + } + + ret = i915_sw_fence_await_sw_fence_gfp(B, C, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + pr_err("Incorrectly reported fence C was complete before await\n"); + goto err_C; + } + + ret = -EINVAL; + i915_sw_fence_commit(A); + if (i915_sw_fence_done(A)) { + pr_err("Fence A completed early\n"); + goto err_C; + } + + i915_sw_fence_commit(B); + if (i915_sw_fence_done(B)) { + pr_err("Fence B completed early\n"); + goto err_C; + } + + if (i915_sw_fence_done(A)) { + pr_err("Fence A completed early (after signaling B)\n"); + goto err_C; + } + + i915_sw_fence_commit(C); + + ret = 0; + if (!i915_sw_fence_done(C)) { + pr_err("Fence C not done\n"); + ret = -EINVAL; + } + if (!i915_sw_fence_done(B)) { + pr_err("Fence B not done\n"); + ret = -EINVAL; + } + if (!i915_sw_fence_done(A)) { + pr_err("Fence A not done\n"); + ret = -EINVAL; + } +err_C: + free_fence(C); +err_B: + free_fence(B); +err_A: + free_fence(A); + return ret; +} + +static int test_AB_C(void *arg) +{ + struct i915_sw_fence *A, *B, *C; + int ret = -EINVAL; + + /* Test multiple fences (AB) waiting on a single event (C) */ + A = alloc_fence(); + if (!A) + return -ENOMEM; + + B = alloc_fence(); + if (!B) { + ret = -ENOMEM; + goto err_A; + } + + C = alloc_fence(); + if (!C) { + ret = -ENOMEM; + goto err_B; + } + + ret = i915_sw_fence_await_sw_fence_gfp(A, C, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + ret = -EINVAL; + goto err_C; + } + + ret = i915_sw_fence_await_sw_fence_gfp(B, C, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + ret = -EINVAL; + goto err_C; + } + + i915_sw_fence_commit(A); + i915_sw_fence_commit(B); + + ret = 0; + if (i915_sw_fence_done(A)) { + pr_err("Fence A completed early\n"); + ret = -EINVAL; + } + + if (i915_sw_fence_done(B)) { + pr_err("Fence B completed early\n"); + ret = -EINVAL; + } + + i915_sw_fence_commit(C); + if (!i915_sw_fence_done(C)) { + pr_err("Fence C not done\n"); + ret = -EINVAL; + } + + if (!i915_sw_fence_done(B)) { + pr_err("Fence B not done\n"); + ret = -EINVAL; + } + + if (!i915_sw_fence_done(A)) { + pr_err("Fence A not done\n"); + ret = -EINVAL; + } + +err_C: + free_fence(C); +err_B: + free_fence(B); +err_A: + free_fence(A); + return ret; +} + +static int test_C_AB(void *arg) +{ + struct i915_sw_fence *A, *B, *C; + int ret; + + /* Test multiple event sources (A,B) for a single fence (C) */ + A = alloc_fence(); + if (!A) + return -ENOMEM; + + B = alloc_fence(); + if (!B) { + ret = -ENOMEM; + goto err_A; + } + + C = alloc_fence(); + if (!C) { + ret = -ENOMEM; + goto err_B; + } + + ret = i915_sw_fence_await_sw_fence_gfp(C, A, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + ret = -EINVAL; + goto err_C; + } + + ret = i915_sw_fence_await_sw_fence_gfp(C, B, GFP_KERNEL); + if (ret < 0) + goto err_C; + if (ret == 0) { + ret = -EINVAL; + goto err_C; + } + + ret = 0; + i915_sw_fence_commit(C); + if (i915_sw_fence_done(C)) + ret = -EINVAL; + + i915_sw_fence_commit(A); + i915_sw_fence_commit(B); + + if (!i915_sw_fence_done(A)) { + pr_err("Fence A not done\n"); + ret = -EINVAL; + } + + if (!i915_sw_fence_done(B)) { + pr_err("Fence B not done\n"); + ret = -EINVAL; + } + + if (!i915_sw_fence_done(C)) { + pr_err("Fence C not done\n"); + ret = -EINVAL; + } + +err_C: + free_fence(C); +err_B: + free_fence(B); +err_A: + free_fence(A); + return ret; +} + +static int test_chain(void *arg) +{ + int nfences = 4096; + struct i915_sw_fence **fences; + int ret, i; + + /* Test a long chain of fences */ + fences = kmalloc_array(nfences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return -ENOMEM; + + for (i = 0; i < nfences; i++) { + fences[i] = alloc_fence(); + if (!fences[i]) { + nfences = i; + ret = -ENOMEM; + goto err; + } + + if (i > 0) { + ret = i915_sw_fence_await_sw_fence_gfp(fences[i], + fences[i - 1], + GFP_KERNEL); + if (ret < 0) { + nfences = i + 1; + goto err; + } + + i915_sw_fence_commit(fences[i]); + } + } + + ret = 0; + for (i = nfences; --i; ) { + if (i915_sw_fence_done(fences[i])) { + if (ret == 0) + pr_err("Fence[%d] completed early\n", i); + ret = -EINVAL; + } + } + i915_sw_fence_commit(fences[0]); + for (i = 0; ret == 0 && i < nfences; i++) { + if (!i915_sw_fence_done(fences[i])) { + pr_err("Fence[%d] is not done\n", i); + ret = -EINVAL; + } + } + +err: + for (i = 0; i < nfences; i++) + free_fence(fences[i]); + kfree(fences); + return ret; +} + +struct task_ipc { + struct work_struct work; + struct completion started; + struct i915_sw_fence *in, *out; + int value; +}; + +static void task_ipc(struct work_struct *work) +{ + struct task_ipc *ipc = container_of(work, typeof(*ipc), work); + + complete(&ipc->started); + + i915_sw_fence_wait(ipc->in); + smp_store_mb(ipc->value, 1); + i915_sw_fence_commit(ipc->out); +} + +static int test_ipc(void *arg) +{ + struct task_ipc ipc; + int ret = 0; + + /* Test use of i915_sw_fence as an interprocess signaling mechanism */ + ipc.in = alloc_fence(); + if (!ipc.in) + return -ENOMEM; + ipc.out = alloc_fence(); + if (!ipc.out) { + ret = -ENOMEM; + goto err_in; + } + + /* use a completion to avoid chicken-and-egg testing */ + init_completion(&ipc.started); + + ipc.value = 0; + INIT_WORK_ONSTACK(&ipc.work, task_ipc); + schedule_work(&ipc.work); + + wait_for_completion(&ipc.started); + + usleep_range(1000, 2000); + if (READ_ONCE(ipc.value)) { + pr_err("worker updated value before i915_sw_fence was signaled\n"); + ret = -EINVAL; + } + + i915_sw_fence_commit(ipc.in); + i915_sw_fence_wait(ipc.out); + + if (!READ_ONCE(ipc.value)) { + pr_err("worker signaled i915_sw_fence before value was posted\n"); + ret = -EINVAL; + } + + flush_work(&ipc.work); + destroy_work_on_stack(&ipc.work); + free_fence(ipc.out); +err_in: + free_fence(ipc.in); + return ret; +} + +int i915_sw_fence_mock_selftests(void) +{ + static const struct i915_subtest tests[] = { + SUBTEST(test_self), + SUBTEST(test_dag), + SUBTEST(test_AB), + SUBTEST(test_ABC), + SUBTEST(test_AB_C), + SUBTEST(test_C_AB), + SUBTEST(test_chain), + SUBTEST(test_ipc), + }; + + return i915_subtests(tests, NULL); +} diff --git a/drivers/gpu/drm/i915/selftests/i915_syncmap.c b/drivers/gpu/drm/i915/selftests/i915_syncmap.c new file mode 100644 index 00000000000000..bcab3d00a78596 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/i915_syncmap.c @@ -0,0 +1,616 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include "../i915_selftest.h" +#include "i915_random.h" + +static char * +__sync_print(struct i915_syncmap *p, + char *buf, unsigned long *sz, + unsigned int depth, + unsigned int last, + unsigned int idx) +{ + unsigned long len; + unsigned int i, X; + + if (depth) { + unsigned int d; + + for (d = 0; d < depth - 1; d++) { + if (last & BIT(depth - d - 1)) + len = scnprintf(buf, *sz, "| "); + else + len = scnprintf(buf, *sz, " "); + buf += len; + *sz -= len; + } + len = scnprintf(buf, *sz, "%x-> ", idx); + buf += len; + *sz -= len; + } + + /* We mark bits after the prefix as "X" */ + len = scnprintf(buf, *sz, "0x%016llx", p->prefix << p->height << SHIFT); + buf += len; + *sz -= len; + X = (p->height + SHIFT) / 4; + scnprintf(buf - X, *sz + X, "%*s", X, "XXXXXXXXXXXXXXXXX"); + + if (!p->height) { + for_each_set_bit(i, (unsigned long *)&p->bitmap, KSYNCMAP) { + len = scnprintf(buf, *sz, " %x:%x,", + i, __sync_seqno(p)[i]); + buf += len; + *sz -= len; + } + buf -= 1; + *sz += 1; + } + + len = scnprintf(buf, *sz, "\n"); + buf += len; + *sz -= len; + + if (p->height) { + for_each_set_bit(i, (unsigned long *)&p->bitmap, KSYNCMAP) { + buf = __sync_print(__sync_child(p)[i], buf, sz, + depth + 1, + last << 1 | !!(p->bitmap >> (i + 1)), + i); + } + } + + return buf; +} + +static bool +i915_syncmap_print_to_buf(struct i915_syncmap *p, char *buf, unsigned long sz) +{ + if (!p) + return false; + + while (p->parent) + p = p->parent; + + __sync_print(p, buf, &sz, 0, 1, 0); + return true; +} + +static int check_syncmap_free(struct i915_syncmap **sync) +{ + i915_syncmap_free(sync); + if (*sync) { + pr_err("sync not cleared after free\n"); + return -EINVAL; + } + + return 0; +} + +static int dump_syncmap(struct i915_syncmap *sync, int err) +{ + char *buf; + + if (!err) + return check_syncmap_free(&sync); + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + goto skip; + + if (i915_syncmap_print_to_buf(sync, buf, PAGE_SIZE)) + pr_err("%s", buf); + + kfree(buf); + +skip: + i915_syncmap_free(&sync); + return err; +} + +static int igt_syncmap_init(void *arg) +{ + struct i915_syncmap *sync = (void *)~0ul; + + /* + * Cursory check that we can initialise a random pointer and transform + * it into the root pointer of a syncmap. + */ + + i915_syncmap_init(&sync); + return check_syncmap_free(&sync); +} + +static int check_seqno(struct i915_syncmap *leaf, unsigned int idx, u32 seqno) +{ + if (leaf->height) { + pr_err("%s: not a leaf, height is %d\n", + __func__, leaf->height); + return -EINVAL; + } + + if (__sync_seqno(leaf)[idx] != seqno) { + pr_err("%s: seqno[%d], found %x, expected %x\n", + __func__, idx, __sync_seqno(leaf)[idx], seqno); + return -EINVAL; + } + + return 0; +} + +static int check_one(struct i915_syncmap **sync, u64 context, u32 seqno) +{ + int err; + + err = i915_syncmap_set(sync, context, seqno); + if (err) + return err; + + if ((*sync)->height) { + pr_err("Inserting first context=%llx did not return leaf (height=%d, prefix=%llx\n", + context, (*sync)->height, (*sync)->prefix); + return -EINVAL; + } + + if ((*sync)->parent) { + pr_err("Inserting first context=%llx created branches!\n", + context); + return -EINVAL; + } + + if (hweight32((*sync)->bitmap) != 1) { + pr_err("First bitmap does not contain a single entry, found %x (count=%d)!\n", + (*sync)->bitmap, hweight32((*sync)->bitmap)); + return -EINVAL; + } + + err = check_seqno((*sync), ilog2((*sync)->bitmap), seqno); + if (err) + return err; + + if (!i915_syncmap_is_later(sync, context, seqno)) { + pr_err("Lookup of first context=%llx/seqno=%x failed!\n", + context, seqno); + return -EINVAL; + } + + return 0; +} + +static int igt_syncmap_one(void *arg) +{ + I915_RND_STATE(prng); + IGT_TIMEOUT(end_time); + struct i915_syncmap *sync; + unsigned long max = 1; + int err; + + /* + * Check that inserting a new id, creates a leaf and only that leaf. + */ + + i915_syncmap_init(&sync); + + do { + u64 context = i915_prandom_u64_state(&prng); + unsigned long loop; + + err = check_syncmap_free(&sync); + if (err) + goto out; + + for (loop = 0; loop <= max; loop++) { + err = check_one(&sync, context, + prandom_u32_state(&prng)); + if (err) + goto out; + } + max++; + } while (!__igt_timeout(end_time, NULL)); + pr_debug("%s: Completed %lu single insertions\n", + __func__, max * (max - 1) / 2); +out: + return dump_syncmap(sync, err); +} + +static int check_leaf(struct i915_syncmap **sync, u64 context, u32 seqno) +{ + int err; + + err = i915_syncmap_set(sync, context, seqno); + if (err) + return err; + + if ((*sync)->height) { + pr_err("Inserting context=%llx did not return leaf (height=%d, prefix=%llx\n", + context, (*sync)->height, (*sync)->prefix); + return -EINVAL; + } + + if (hweight32((*sync)->bitmap) != 1) { + pr_err("First entry into leaf (context=%llx) does not contain a single entry, found %x (count=%d)!\n", + context, (*sync)->bitmap, hweight32((*sync)->bitmap)); + return -EINVAL; + } + + err = check_seqno((*sync), ilog2((*sync)->bitmap), seqno); + if (err) + return err; + + if (!i915_syncmap_is_later(sync, context, seqno)) { + pr_err("Lookup of first entry context=%llx/seqno=%x failed!\n", + context, seqno); + return -EINVAL; + } + + return 0; +} + +static int igt_syncmap_join_above(void *arg) +{ + struct i915_syncmap *sync; + unsigned int pass, order; + int err; + + i915_syncmap_init(&sync); + + /* + * When we have a new id that doesn't fit inside the existing tree, + * we need to add a new layer above. + * + * 1: 0x00000001 + * 2: 0x00000010 + * 3: 0x00000100 + * 4: 0x00001000 + * ... + * Each pass the common prefix shrinks and we have to insert a join. + * Each join will only contain two branches, the latest of which + * is always a leaf. + * + * If we then reuse the same set of contexts, we expect to build an + * identical tree. + */ + for (pass = 0; pass < 3; pass++) { + for (order = 0; order < 64; order += SHIFT) { + u64 context = BIT_ULL(order); + struct i915_syncmap *join; + + err = check_leaf(&sync, context, 0); + if (err) + goto out; + + join = sync->parent; + if (!join) /* very first insert will have no parents */ + continue; + + if (!join->height) { + pr_err("Parent with no height!\n"); + err = -EINVAL; + goto out; + } + + if (hweight32(join->bitmap) != 2) { + pr_err("Join does not have 2 children: %x (%d)\n", + join->bitmap, hweight32(join->bitmap)); + err = -EINVAL; + goto out; + } + + if (__sync_child(join)[__sync_branch_idx(join, context)] != sync) { + pr_err("Leaf misplaced in parent!\n"); + err = -EINVAL; + goto out; + } + } + } +out: + return dump_syncmap(sync, err); +} + +static int igt_syncmap_join_below(void *arg) +{ + struct i915_syncmap *sync; + unsigned int step, order, idx; + int err; + + i915_syncmap_init(&sync); + + /* + * Check that we can split a compacted branch by replacing it with + * a join. + */ + for (step = 0; step < KSYNCMAP; step++) { + for (order = 64 - SHIFT; order > 0; order -= SHIFT) { + u64 context = step * BIT_ULL(order); + + err = i915_syncmap_set(&sync, context, 0); + if (err) + goto out; + + if (sync->height) { + pr_err("Inserting context=%llx (order=%d, step=%d) did not return leaf (height=%d, prefix=%llx\n", + context, order, step, sync->height, sync->prefix); + err = -EINVAL; + goto out; + } + } + } + + for (step = 0; step < KSYNCMAP; step++) { + for (order = SHIFT; order < 64; order += SHIFT) { + u64 context = step * BIT_ULL(order); + + if (!i915_syncmap_is_later(&sync, context, 0)) { + pr_err("1: context %llx (order=%d, step=%d) not found\n", + context, order, step); + err = -EINVAL; + goto out; + } + + for (idx = 1; idx < KSYNCMAP; idx++) { + if (i915_syncmap_is_later(&sync, context + idx, 0)) { + pr_err("1: context %llx (order=%d, step=%d) should not exist\n", + context + idx, order, step); + err = -EINVAL; + goto out; + } + } + } + } + + for (order = SHIFT; order < 64; order += SHIFT) { + for (step = 0; step < KSYNCMAP; step++) { + u64 context = step * BIT_ULL(order); + + if (!i915_syncmap_is_later(&sync, context, 0)) { + pr_err("2: context %llx (order=%d, step=%d) not found\n", + context, order, step); + err = -EINVAL; + goto out; + } + } + } + +out: + return dump_syncmap(sync, err); +} + +static int igt_syncmap_neighbours(void *arg) +{ + I915_RND_STATE(prng); + IGT_TIMEOUT(end_time); + struct i915_syncmap *sync; + int err; + + /* + * Each leaf holds KSYNCMAP seqno. Check that when we create KSYNCMAP + * neighbouring ids, they all fit into the same leaf. + */ + + i915_syncmap_init(&sync); + do { + u64 context = i915_prandom_u64_state(&prng) & ~MASK; + unsigned int idx; + + if (i915_syncmap_is_later(&sync, context, 0)) /* Skip repeats */ + continue; + + for (idx = 0; idx < KSYNCMAP; idx++) { + err = i915_syncmap_set(&sync, context + idx, 0); + if (err) + goto out; + + if (sync->height) { + pr_err("Inserting context=%llx did not return leaf (height=%d, prefix=%llx\n", + context, sync->height, sync->prefix); + err = -EINVAL; + goto out; + } + + if (sync->bitmap != BIT(idx + 1) - 1) { + pr_err("Inserting neighbouring context=0x%llx+%d, did not fit into the same leaf bitmap=%x (%d), expected %lx (%d)\n", + context, idx, + sync->bitmap, hweight32(sync->bitmap), + BIT(idx + 1) - 1, idx + 1); + err = -EINVAL; + goto out; + } + } + } while (!__igt_timeout(end_time, NULL)); +out: + return dump_syncmap(sync, err); +} + +static int igt_syncmap_compact(void *arg) +{ + struct i915_syncmap *sync; + unsigned int idx, order; + int err; + + i915_syncmap_init(&sync); + + /* + * The syncmap are "space efficient" compressed radix trees - any + * branch with only one child is skipped and replaced by the child. + * + * If we construct a tree with ids that are neighbouring at a non-zero + * height, we form a join but each child of that join is directly a + * leaf holding the single id. + */ + for (order = SHIFT; order < 64; order += SHIFT) { + err = check_syncmap_free(&sync); + if (err) + goto out; + + /* Create neighbours in the parent */ + for (idx = 0; idx < KSYNCMAP; idx++) { + u64 context = idx * BIT_ULL(order) + idx; + + err = i915_syncmap_set(&sync, context, 0); + if (err) + goto out; + + if (sync->height) { + pr_err("Inserting context=%llx (order=%d, idx=%d) did not return leaf (height=%d, prefix=%llx\n", + context, order, idx, + sync->height, sync->prefix); + err = -EINVAL; + goto out; + } + } + + sync = sync->parent; + if (sync->parent) { + pr_err("Parent (join) of last leaf was not the sync!\n"); + err = -EINVAL; + goto out; + } + + if (sync->height != order) { + pr_err("Join does not have the expected height, found %d, expected %d\n", + sync->height, order); + err = -EINVAL; + goto out; + } + + if (sync->bitmap != BIT(KSYNCMAP) - 1) { + pr_err("Join is not full!, found %x (%d) expected %lx (%d)\n", + sync->bitmap, hweight32(sync->bitmap), + BIT(KSYNCMAP) - 1, KSYNCMAP); + err = -EINVAL; + goto out; + } + + /* Each of our children should be a leaf */ + for (idx = 0; idx < KSYNCMAP; idx++) { + struct i915_syncmap *leaf = __sync_child(sync)[idx]; + + if (leaf->height) { + pr_err("Child %d is a not leaf!\n", idx); + err = -EINVAL; + goto out; + } + + if (leaf->parent != sync) { + pr_err("Child %d is not attached to us!\n", + idx); + err = -EINVAL; + goto out; + } + + if (!is_power_of_2(leaf->bitmap)) { + pr_err("Child %d holds more than one id, found %x (%d)\n", + idx, leaf->bitmap, hweight32(leaf->bitmap)); + err = -EINVAL; + goto out; + } + + if (leaf->bitmap != BIT(idx)) { + pr_err("Child %d has wrong seqno idx, found %d, expected %d\n", + idx, ilog2(leaf->bitmap), idx); + err = -EINVAL; + goto out; + } + } + } +out: + return dump_syncmap(sync, err); +} + +static int igt_syncmap_random(void *arg) +{ + I915_RND_STATE(prng); + IGT_TIMEOUT(end_time); + struct i915_syncmap *sync; + unsigned long count, phase, i; + u32 seqno; + int err; + + i915_syncmap_init(&sync); + + /* + * Having tried to test the individual operations within i915_syncmap, + * run a smoketest exploring the entire u64 space with random + * insertions. + */ + + count = 0; + phase = jiffies + HZ/100 + 1; + do { + u64 context = i915_prandom_u64_state(&prng); + + err = i915_syncmap_set(&sync, context, 0); + if (err) + goto out; + + count++; + } while (!time_after(jiffies, phase)); + seqno = 0; + + phase = 0; + do { + I915_RND_STATE(ctx); + u32 last_seqno = seqno; + bool expect; + + seqno = prandom_u32_state(&prng); + expect = seqno_later(last_seqno, seqno); + + for (i = 0; i < count; i++) { + u64 context = i915_prandom_u64_state(&ctx); + + if (i915_syncmap_is_later(&sync, context, seqno) != expect) { + pr_err("context=%llu, last=%u this=%u did not match expectation (%d)\n", + context, last_seqno, seqno, expect); + err = -EINVAL; + goto out; + } + + err = i915_syncmap_set(&sync, context, seqno); + if (err) + goto out; + } + + phase++; + } while (!__igt_timeout(end_time, NULL)); + pr_debug("Completed %lu passes, each of %lu contexts\n", phase, count); +out: + return dump_syncmap(sync, err); +} + +int i915_syncmap_mock_selftests(void) +{ + static const struct i915_subtest tests[] = { + SUBTEST(igt_syncmap_init), + SUBTEST(igt_syncmap_one), + SUBTEST(igt_syncmap_join_above), + SUBTEST(igt_syncmap_join_below), + SUBTEST(igt_syncmap_neighbours), + SUBTEST(igt_syncmap_compact), + SUBTEST(igt_syncmap_random), + }; + + return i915_subtests(tests, NULL); +} diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c index 19860a372d9005..7276194c04f7fa 100644 --- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c @@ -117,7 +117,7 @@ static int igt_random_insert_remove(void *arg) mock_engine_reset(engine); - waiters = drm_malloc_gfp(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); if (!waiters) goto out_engines; @@ -169,7 +169,7 @@ static int igt_random_insert_remove(void *arg) out_bitmap: kfree(bitmap); out_waiters: - drm_free_large(waiters); + kvfree(waiters); out_engines: mock_engine_flush(engine); return err; @@ -187,7 +187,7 @@ static int igt_insert_complete(void *arg) mock_engine_reset(engine); - waiters = drm_malloc_gfp(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); if (!waiters) goto out_engines; @@ -254,7 +254,7 @@ static int igt_insert_complete(void *arg) out_bitmap: kfree(bitmap); out_waiters: - drm_free_large(waiters); + kvfree(waiters); out_engines: mock_engine_flush(engine); return err; @@ -368,7 +368,7 @@ static int igt_wakeup(void *arg) mock_engine_reset(engine); - waiters = drm_malloc_gfp(count, sizeof(*waiters), GFP_TEMPORARY); + waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY); if (!waiters) goto out_engines; @@ -454,7 +454,7 @@ static int igt_wakeup(void *arg) put_task_struct(waiters[n].tsk); } - drm_free_large(waiters); + kvfree(waiters); out_engines: mock_engine_flush(engine); return err; diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c index 0ad624a1db90a0..5b18a2dc19a87a 100644 --- a/drivers/gpu/drm/i915/selftests/mock_engine.c +++ b/drivers/gpu/drm/i915/selftests/mock_engine.c @@ -52,11 +52,12 @@ static void hw_delay_complete(unsigned long data) spin_unlock(&engine->hw_lock); } -static int mock_context_pin(struct intel_engine_cs *engine, - struct i915_gem_context *ctx) +static struct intel_ring * +mock_context_pin(struct intel_engine_cs *engine, + struct i915_gem_context *ctx) { i915_gem_context_get(ctx); - return 0; + return engine->buffer; } static void mock_context_unpin(struct intel_engine_cs *engine, @@ -72,7 +73,6 @@ static int mock_request_alloc(struct drm_i915_gem_request *request) INIT_LIST_HEAD(&mock->link); mock->delay = 0; - request->ring = request->engine->buffer; return 0; } @@ -112,7 +112,6 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) if (!ring) return NULL; - ring->engine = engine; ring->size = sz; ring->effective_size = sz; ring->vaddr = (void *)(ring + 1); @@ -141,7 +140,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, /* minimal engine setup for requests */ engine->base.i915 = i915; - engine->base.name = name; + snprintf(engine->base.name, sizeof(engine->base.name), "%s", name); engine->base.id = id++; engine->base.status_page.page_addr = (void *)(engine + 1); diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 9f24c5da3f8d3c..627e2aa097665f 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -30,6 +30,7 @@ #include "mock_gem_device.h" #include "mock_gem_object.h" #include "mock_gtt.h" +#include "mock_uncore.h" void mock_device_flush(struct drm_i915_private *i915) { @@ -73,6 +74,7 @@ static void mock_device_release(struct drm_device *dev) destroy_workqueue(i915->wq); + kmem_cache_destroy(i915->priorities); kmem_cache_destroy(i915->dependencies); kmem_cache_destroy(i915->requests); kmem_cache_destroy(i915->vmas); @@ -119,6 +121,7 @@ struct drm_i915_private *mock_gem_device(void) goto err; device_initialize(&pdev->dev); + pdev->class = PCI_BASE_CLASS_DISPLAY << 16; pdev->dev.release = release_dev; dev_set_name(&pdev->dev, "mock"); dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); @@ -143,6 +146,7 @@ struct drm_i915_private *mock_gem_device(void) mkwrite_device_info(i915)->gen = -1; spin_lock_init(&i915->mm.object_stat_lock); + mock_uncore_init(i915); init_waitqueue_head(&i915->gpu_error.wait_queue); init_waitqueue_head(&i915->gpu_error.reset_queue); @@ -184,12 +188,16 @@ struct drm_i915_private *mock_gem_device(void) if (!i915->dependencies) goto err_requests; + i915->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN); + if (!i915->priorities) + goto err_dependencies; + mutex_lock(&i915->drm.struct_mutex); INIT_LIST_HEAD(&i915->gt.timelines); err = i915_gem_timeline_init__global(i915); if (err) { mutex_unlock(&i915->drm.struct_mutex); - goto err_dependencies; + goto err_priorities; } mock_init_ggtt(i915); @@ -209,6 +217,8 @@ struct drm_i915_private *mock_gem_device(void) err_engine: for_each_engine(engine, i915, id) mock_engine_free(engine); +err_priorities: + kmem_cache_destroy(i915->priorities); err_dependencies: kmem_cache_destroy(i915->dependencies); err_requests: diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c new file mode 100644 index 00000000000000..47b1f47c5812f0 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c @@ -0,0 +1,45 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include "mock_timeline.h" + +struct intel_timeline *mock_timeline(u64 context) +{ + static struct lock_class_key class; + struct intel_timeline *tl; + + tl = kzalloc(sizeof(*tl), GFP_KERNEL); + if (!tl) + return NULL; + + __intel_timeline_init(tl, NULL, context, &class, "mock"); + + return tl; +} + +void mock_timeline_destroy(struct intel_timeline *tl) +{ + __intel_timeline_fini(tl); + kfree(tl); +} diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.h b/drivers/gpu/drm/i915/selftests/mock_timeline.h new file mode 100644 index 00000000000000..c27ff4639b8bc3 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/mock_timeline.h @@ -0,0 +1,33 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#ifndef __MOCK_TIMELINE__ +#define __MOCK_TIMELINE__ + +#include "../i915_gem_timeline.h" + +struct intel_timeline *mock_timeline(u64 context); +void mock_timeline_destroy(struct intel_timeline *tl); + +#endif /* !__MOCK_TIMELINE__ */ diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.c b/drivers/gpu/drm/i915/selftests/mock_uncore.c new file mode 100644 index 00000000000000..8ef14c7e5e3823 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/mock_uncore.c @@ -0,0 +1,46 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include "mock_uncore.h" + +#define __nop_write(x) \ +static void \ +nop_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { } +__nop_write(8) +__nop_write(16) +__nop_write(32) + +#define __nop_read(x) \ +static u##x \ +nop_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { return 0; } +__nop_read(8) +__nop_read(16) +__nop_read(32) +__nop_read(64) + +void mock_uncore_init(struct drm_i915_private *i915) +{ + ASSIGN_WRITE_MMIO_VFUNCS(i915, nop); + ASSIGN_READ_MMIO_VFUNCS(i915, nop); +} diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.h b/drivers/gpu/drm/i915/selftests/mock_uncore.h new file mode 100644 index 00000000000000..d79aa3ca4d5108 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/mock_uncore.h @@ -0,0 +1,30 @@ +/* + * Copyright © 2017 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#ifndef __MOCK_UNCORE_H +#define __MOCK_UNCORE_H + +void mock_uncore_init(struct drm_i915_private *i915); + +#endif /* !__MOCK_UNCORE_H */ diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index d63e853a030064..49546222c6d398 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -273,7 +273,7 @@ void ipu_plane_state_reset(struct drm_plane *plane) if (ipu_state) { ipu_state->base.plane = plane; - ipu_state->base.rotation = DRM_ROTATE_0; + ipu_state->base.rotation = DRM_MODE_ROTATE_0; } plane->state = &ipu_state->base; diff --git a/drivers/gpu/drm/mga/Makefile b/drivers/gpu/drm/mga/Makefile index 60684785c20387..49e972c2f7878f 100644 --- a/drivers/gpu/drm/mga/Makefile +++ b/drivers/gpu/drm/mga/Makefile @@ -2,7 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm mga-y := mga_drv.o mga_dma.o mga_state.o mga_warp.o mga_irq.o mga-$(CONFIG_COMPAT) += mga_ioc32.o diff --git a/drivers/gpu/drm/mgag200/Makefile b/drivers/gpu/drm/mgag200/Makefile index a9a0300f09fca4..3d91d1d6c45d11 100644 --- a/drivers/gpu/drm/mgag200/Makefile +++ b/drivers/gpu/drm/mgag200/Makefile @@ -1,4 +1,3 @@ -ccflags-y := -Iinclude/drm mgag200-y := mgag200_main.o mgag200_mode.o mgag200_cursor.o \ mgag200_drv.o mgag200_fb.o mgag200_i2c.o mgag200_ttm.o diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c index 565a217b46f251..3e7e1cd31395ee 100644 --- a/drivers/gpu/drm/mgag200/mgag200_ttm.c +++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c @@ -26,8 +26,9 @@ * Authors: Dave Airlie */ #include +#include + #include "mgag200_drv.h" -#include static inline struct mga_device * mgag200_bdev(struct ttm_bo_device *bd) diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 5241ac8803ba69..33008fa1be9b86 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -1,4 +1,4 @@ -ccflags-y := -Iinclude/drm -Idrivers/gpu/drm/msm +ccflags-y := -Idrivers/gpu/drm/msm ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi msm-y := \ diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 32369975d155bf..9e6017387efb99 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -17,9 +17,9 @@ #include #include -#include "drm_crtc.h" -#include "drm_mipi_dsi.h" -#include "drm_panel.h" +#include +#include +#include #include "msm_drv.h" diff --git a/drivers/gpu/drm/msm/edp/edp.h b/drivers/gpu/drm/msm/edp/edp.h index ba5bedde5241f1..e0f5818ec9ca49 100644 --- a/drivers/gpu/drm/msm/edp/edp.h +++ b/drivers/gpu/drm/msm/edp/edp.h @@ -18,9 +18,9 @@ #include #include #include +#include +#include -#include "drm_crtc.h" -#include "drm_dp_helper.h" #include "msm_drv.h" #define edp_read(offset) msm_readl((offset)) diff --git a/drivers/gpu/drm/msm/edp/edp_ctrl.c b/drivers/gpu/drm/msm/edp/edp_ctrl.c index 149bfe7ddd82de..e32a4a4f3797fc 100644 --- a/drivers/gpu/drm/msm/edp/edp_ctrl.c +++ b/drivers/gpu/drm/msm/edp/edp_ctrl.c @@ -14,10 +14,10 @@ #include #include #include +#include +#include +#include -#include "drm_crtc.h" -#include "drm_dp_helper.h" -#include "drm_edid.h" #include "edp.h" #include "edp.xml.h" diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c index f29194a74a19d9..698e514203c647 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c @@ -15,12 +15,12 @@ * this program. If not, see . */ -#include "mdp4_kms.h" - +#include +#include +#include #include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" -#include "drm_flip_work.h" + +#include "mdp4_kms.h" struct mdp4_crtc { struct drm_crtc base; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dsi_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dsi_encoder.c index 106f0e77259541..6a1ebdace391d9 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dsi_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dsi_encoder.c @@ -17,10 +17,10 @@ * this program. If not, see . */ -#include "mdp4_kms.h" +#include +#include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" +#include "mdp4_kms.h" struct mdp4_dsi_encoder { struct drm_encoder base; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c index 24258e3025e31a..ba8e587f734b3d 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c @@ -15,11 +15,10 @@ * this program. If not, see . */ -#include "mdp4_kms.h" - -#include "drm_crtc.h" -#include "drm_crtc_helper.h" +#include +#include +#include "mdp4_kms.h" struct mdp4_dtv_encoder { struct drm_encoder base; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h index 62712ca164ee16..c413779d488a9c 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h @@ -18,12 +18,14 @@ #ifndef __MDP4_KMS_H__ #define __MDP4_KMS_H__ +#include + #include "msm_drv.h" #include "msm_kms.h" #include "mdp/mdp_kms.h" #include "mdp4.xml.h" -#include "drm_panel.h" +struct device_node; struct mdp4_kms { struct mdp_kms base; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c index a06b064f86c197..4a645926edb7d1 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c @@ -16,10 +16,10 @@ * this program. If not, see . */ -#include "mdp4_kms.h" +#include +#include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" +#include "mdp4_kms.h" struct mdp4_lcdc_encoder { struct drm_encoder base; diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c index 8dafc7bdba4819..aa7402e03f676b 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c @@ -11,10 +11,10 @@ * GNU General Public License for more details. */ -#include "mdp5_kms.h" +#include +#include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" +#include "mdp5_kms.h" static struct mdp5_kms *get_kms(struct drm_encoder *encoder) { diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index 9217e0d6e93e0d..0764a6498110ed 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -16,13 +16,13 @@ * this program. If not, see . */ -#include "mdp5_kms.h" - #include #include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" -#include "drm_flip_work.h" +#include +#include +#include + +#include "mdp5_kms.h" #define CURSOR_WIDTH 64 #define CURSOR_HEIGHT 64 diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c index c2ab0f03303186..97f3294fbfc6f9 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c @@ -16,10 +16,10 @@ * this program. If not, see . */ -#include "mdp5_kms.h" +#include +#include -#include "drm_crtc.h" -#include "drm_crtc_helper.h" +#include "mdp5_kms.h" static struct mdp5_kms *get_kms(struct drm_encoder *encoder) { diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index d3d6b4cae1e6c8..e2b3346ead48fb 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -527,31 +527,28 @@ static struct drm_encoder *get_encoder_from_crtc(struct drm_crtc *crtc) return NULL; } -static int mdp5_get_scanoutpos(struct drm_device *dev, unsigned int pipe, - unsigned int flags, int *vpos, int *hpos, - ktime_t *stime, ktime_t *etime, - const struct drm_display_mode *mode) +static bool mdp5_get_scanoutpos(struct drm_device *dev, unsigned int pipe, + bool in_vblank_irq, int *vpos, int *hpos, + ktime_t *stime, ktime_t *etime, + const struct drm_display_mode *mode) { struct msm_drm_private *priv = dev->dev_private; struct drm_crtc *crtc; struct drm_encoder *encoder; int line, vsw, vbp, vactive_start, vactive_end, vfp_end; - int ret = 0; crtc = priv->crtcs[pipe]; if (!crtc) { DRM_ERROR("Invalid crtc %d\n", pipe); - return 0; + return false; } encoder = get_encoder_from_crtc(crtc); if (!encoder) { DRM_ERROR("no encoder found for crtc %d\n", pipe); - return 0; + return false; } - ret |= DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE; - vsw = mode->crtc_vsync_end - mode->crtc_vsync_start; vbp = mode->crtc_vtotal - mode->crtc_vsync_end; @@ -575,10 +572,8 @@ static int mdp5_get_scanoutpos(struct drm_device *dev, unsigned int pipe, if (line < vactive_start) { line -= vactive_start; - ret |= DRM_SCANOUTPOS_IN_VBLANK; } else if (line > vactive_end) { line = line - vfp_end - vactive_start; - ret |= DRM_SCANOUTPOS_IN_VBLANK; } else { line -= vactive_start; } @@ -589,31 +584,7 @@ static int mdp5_get_scanoutpos(struct drm_device *dev, unsigned int pipe, if (etime) *etime = ktime_get(); - return ret; -} - -static int mdp5_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags) -{ - struct msm_drm_private *priv = dev->dev_private; - struct drm_crtc *crtc; - - if (pipe < 0 || pipe >= priv->num_crtcs) { - DRM_ERROR("Invalid crtc %d\n", pipe); - return -EINVAL; - } - - crtc = priv->crtcs[pipe]; - if (!crtc) { - DRM_ERROR("Invalid crtc %d\n", pipe); - return -EINVAL; - } - - return drm_calc_vbltimestamp_from_scanoutpos(dev, pipe, max_error, - vblank_time, flags, - &crtc->mode); + return true; } static u32 mdp5_get_vblank_counter(struct drm_device *dev, unsigned int pipe) @@ -725,7 +696,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) dev->mode_config.max_width = 0xffff; dev->mode_config.max_height = 0xffff; - dev->driver->get_vblank_timestamp = mdp5_get_vblank_timestamp; + dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos; dev->driver->get_scanout_position = mdp5_get_scanoutpos; dev->driver->get_vblank_counter = mdp5_get_vblank_counter; dev->max_vblank_count = 0xffffffff; diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c index 7d374121538711..abaaac7fea1a97 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c @@ -67,11 +67,11 @@ static void mdp5_plane_install_rotation_property(struct drm_device *dev, struct drm_plane *plane) { drm_plane_create_rotation_property(plane, - DRM_ROTATE_0, - DRM_ROTATE_0 | - DRM_ROTATE_180 | - DRM_REFLECT_X | - DRM_REFLECT_Y); + DRM_MODE_ROTATE_0, + DRM_MODE_ROTATE_0 | + DRM_MODE_ROTATE_180 | + DRM_MODE_REFLECT_X | + DRM_MODE_REFLECT_Y); } /* helper to install properties which are common to planes and crtcs */ @@ -370,14 +370,14 @@ static int mdp5_plane_atomic_check_with_state(struct drm_crtc_state *crtc_state, caps |= MDP_PIPE_CAP_SCALE; rotation = drm_rotation_simplify(state->rotation, - DRM_ROTATE_0 | - DRM_REFLECT_X | - DRM_REFLECT_Y); + DRM_MODE_ROTATE_0 | + DRM_MODE_REFLECT_X | + DRM_MODE_REFLECT_Y); - if (rotation & DRM_REFLECT_X) + if (rotation & DRM_MODE_REFLECT_X) caps |= MDP_PIPE_CAP_HFLIP; - if (rotation & DRM_REFLECT_Y) + if (rotation & DRM_MODE_REFLECT_Y) caps |= MDP_PIPE_CAP_VFLIP; if (plane->type == DRM_PLANE_TYPE_CURSOR) @@ -975,11 +975,11 @@ static int mdp5_plane_mode_set(struct drm_plane *plane, DBG("scale config = %x", config); rotation = drm_rotation_simplify(pstate->rotation, - DRM_ROTATE_0 | - DRM_REFLECT_X | - DRM_REFLECT_Y); - hflip = !!(rotation & DRM_REFLECT_X); - vflip = !!(rotation & DRM_REFLECT_Y); + DRM_MODE_ROTATE_0 | + DRM_MODE_REFLECT_X | + DRM_MODE_REFLECT_Y); + hflip = !!(rotation & DRM_MODE_REFLECT_X); + vflip = !!(rotation & DRM_MODE_REFLECT_Y); spin_lock_irqsave(&mdp5_plane->pipe_lock, flags); diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index 5cf165c9c3a9fe..ba2733a95a4f03 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -15,12 +15,12 @@ * this program. If not, see . */ +#include +#include + #include "msm_drv.h" #include "msm_kms.h" -#include "drm_crtc.h" -#include "drm_crtc_helper.h" - struct msm_framebuffer { struct drm_framebuffer base; const struct msm_format *format; diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 951e40faf6e8dd..feea8ba4e05b2e 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -15,10 +15,10 @@ * this program. If not, see . */ -#include "msm_drv.h" +#include +#include -#include "drm_crtc.h" -#include "drm_fb_helper.h" +#include "msm_drv.h" #include "msm_gem.h" extern int msm_gem_mmap_obj(struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 50289a23baf8df..be77a35a7a8e5c 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -50,13 +50,13 @@ static struct page **get_pages_vram(struct drm_gem_object *obj, struct page **p; int ret, i; - p = drm_malloc_ab(npages, sizeof(struct page *)); + p = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); ret = drm_mm_insert_node(&priv->vram.mm, msm_obj->vram_node, npages); if (ret) { - drm_free_large(p); + kvfree(p); return ERR_PTR(ret); } @@ -127,7 +127,7 @@ static void put_pages(struct drm_gem_object *obj) drm_gem_put_pages(obj, msm_obj->pages, true, false); else { drm_mm_remove_node(msm_obj->vram_node); - drm_free_large(msm_obj->pages); + kvfree(msm_obj->pages); } msm_obj->pages = NULL; @@ -707,7 +707,7 @@ void msm_gem_free_object(struct drm_gem_object *obj) * ours, just free the array we allocated: */ if (msm_obj->pages) - drm_free_large(msm_obj->pages); + kvfree(msm_obj->pages); drm_prime_gem_destroy(obj, msm_obj->sgt); } else { @@ -869,7 +869,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, msm_obj = to_msm_bo(obj); msm_obj->sgt = sgt; - msm_obj->pages = drm_malloc_ab(npages, sizeof(struct page *)); + msm_obj->pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!msm_obj->pages) { ret = -ENOMEM; goto fail; diff --git a/drivers/gpu/drm/nouveau/Kbuild b/drivers/gpu/drm/nouveau/Kbuild index fde6e3656636f4..2e9ce53ae3a8ca 100644 --- a/drivers/gpu/drm/nouveau/Kbuild +++ b/drivers/gpu/drm/nouveau/Kbuild @@ -1,4 +1,3 @@ -ccflags-y := -Iinclude/drm ccflags-y += -I$(src)/include ccflags-y += -I$(src)/include/nvkm ccflags-y += -I$(src)/nvkm diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 549763f5e17d8f..8d1df5678eaaa7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -98,7 +98,7 @@ calc(int blanks, int blanke, int total, int line) return line; } -static int +static bool nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime) { @@ -111,16 +111,16 @@ nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos, }; struct nouveau_display *disp = nouveau_display(crtc->dev); struct drm_vblank_crtc *vblank = &crtc->dev->vblank[drm_crtc_index(crtc)]; - int ret, retry = 20; + int retry = 20; + bool ret = false; do { ret = nvif_mthd(&disp->disp, 0, &args, sizeof(args)); if (ret != 0) - return 0; + return false; if (args.scan.vline) { - ret |= DRM_SCANOUTPOS_ACCURATE; - ret |= DRM_SCANOUTPOS_VALID; + ret = true; break; } @@ -133,14 +133,12 @@ nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos, if (stime) *stime = ns_to_ktime(args.scan.time[0]); if (etime) *etime = ns_to_ktime(args.scan.time[1]); - if (*vpos < 0) - ret |= DRM_SCANOUTPOS_IN_VBLANK; return ret; } -int +bool nouveau_display_scanoutpos(struct drm_device *dev, unsigned int pipe, - unsigned int flags, int *vpos, int *hpos, + bool in_vblank_irq, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime, const struct drm_display_mode *mode) { @@ -153,28 +151,7 @@ nouveau_display_scanoutpos(struct drm_device *dev, unsigned int pipe, } } - return 0; -} - -int -nouveau_display_vblstamp(struct drm_device *dev, unsigned int pipe, - int *max_error, struct timeval *time, unsigned flags) -{ - struct drm_crtc *crtc; - - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - if (nouveau_crtc(crtc)->index == pipe) { - struct drm_display_mode *mode; - if (drm_drv_uses_atomic_modeset(dev)) - mode = &crtc->state->adjusted_mode; - else - mode = &crtc->hwmode; - return drm_calc_vbltimestamp_from_scanoutpos(dev, - pipe, max_error, time, flags, mode); - } - } - - return -EINVAL; + return false; } static void diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index e1d772d394887e..201aec2ea5b81c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -68,11 +68,9 @@ int nouveau_display_suspend(struct drm_device *dev, bool runtime); void nouveau_display_resume(struct drm_device *dev, bool runtime); int nouveau_display_vblank_enable(struct drm_device *, unsigned int); void nouveau_display_vblank_disable(struct drm_device *, unsigned int); -int nouveau_display_scanoutpos(struct drm_device *, unsigned int, - unsigned int, int *, int *, ktime_t *, - ktime_t *, const struct drm_display_mode *); -int nouveau_display_vblstamp(struct drm_device *, unsigned int, int *, - struct timeval *, unsigned); +bool nouveau_display_scanoutpos(struct drm_device *, unsigned int, + bool, int *, int *, ktime_t *, + ktime_t *, const struct drm_display_mode *); int nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event, diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 36268e1802b5af..6844372366d341 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -29,8 +29,8 @@ #include #include -#include "drmP.h" -#include "drm_crtc_helper.h" +#include +#include #include #include @@ -881,7 +881,7 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) } static void -nouveau_drm_preclose(struct drm_device *dev, struct drm_file *fpriv) +nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv) { struct nouveau_cli *cli = nouveau_cli(fpriv); struct nouveau_drm *drm = nouveau_drm(dev); @@ -897,12 +897,6 @@ nouveau_drm_preclose(struct drm_device *dev, struct drm_file *fpriv) list_del(&cli->head); mutex_unlock(&drm->client.mutex); -} - -static void -nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv) -{ - struct nouveau_cli *cli = nouveau_cli(fpriv); nouveau_cli_fini(cli); kfree(cli); pm_runtime_mark_last_busy(dev->dev); @@ -974,7 +968,6 @@ driver_stub = { .load = nouveau_drm_load, .unload = nouveau_drm_unload, .open = nouveau_drm_open, - .preclose = nouveau_drm_preclose, .postclose = nouveau_drm_postclose, .lastclose = nouveau_vga_lastclose, @@ -985,7 +978,7 @@ driver_stub = { .enable_vblank = nouveau_display_vblank_enable, .disable_vblank = nouveau_display_vblank_disable, .get_scanout_position = nouveau_display_scanoutpos, - .get_vblank_timestamp = nouveau_display_vblstamp, + .get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos, .ioctls = nouveau_ioctls, .num_ioctls = ARRAY_SIZE(nouveau_ioctls), diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index eadec2f49ad318..aaa25641fed601 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -43,7 +43,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index 13e5cc5f07fe02..999c35a25498f8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -28,7 +28,7 @@ #include "nouveau_ttm.h" #include "nouveau_gem.h" -#include "drm_legacy.h" +#include #include diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index a7663249b3baf2..9303daa79aba1f 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -1033,7 +1033,7 @@ nv50_wndw_reset(struct drm_plane *plane) plane->funcs->atomic_destroy_state(plane, plane->state); plane->state = &asyw->state; plane->state->plane = plane; - plane->state->rotation = DRM_ROTATE_0; + plane->state->rotation = DRM_MODE_ROTATE_0; } static void diff --git a/drivers/gpu/drm/omapdrm/Makefile b/drivers/gpu/drm/omapdrm/Makefile index 48b7b750c05c88..b391be7ecb6c3a 100644 --- a/drivers/gpu/drm/omapdrm/Makefile +++ b/drivers/gpu/drm/omapdrm/Makefile @@ -6,7 +6,6 @@ obj-y += dss/ obj-y += displays/ -ccflags-y := -Iinclude/drm omapdrm-y := omap_drv.o \ omap_irq.o \ omap_debugfs.o \ diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index e1f47f0b3ccfd3..663e930a7b0f6f 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -577,7 +577,7 @@ static void dev_lastclose(struct drm_device *dev) drm_object_property_set_value(&crtc->base, crtc->primary->rotation_property, - DRM_ROTATE_0); + DRM_MODE_ROTATE_0); } for (i = 0; i < priv->num_planes; i++) { @@ -588,7 +588,7 @@ static void dev_lastclose(struct drm_device *dev) drm_object_property_set_value(&plane->base, plane->rotation_property, - DRM_ROTATE_0); + DRM_MODE_ROTATE_0); } if (priv->fbdev) { diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c index 29dc677dd4d3e7..5ca0537bb4271a 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.c +++ b/drivers/gpu/drm/omapdrm/omap_fb.c @@ -167,30 +167,30 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, uint32_t w = win->src_w; uint32_t h = win->src_h; - switch (win->rotation & DRM_ROTATE_MASK) { + switch (win->rotation & DRM_MODE_ROTATE_MASK) { default: dev_err(fb->dev->dev, "invalid rotation: %02x", (uint32_t)win->rotation); /* fallthru to default to no rotation */ case 0: - case DRM_ROTATE_0: + case DRM_MODE_ROTATE_0: orient = 0; break; - case DRM_ROTATE_90: + case DRM_MODE_ROTATE_90: orient = MASK_XY_FLIP | MASK_X_INVERT; break; - case DRM_ROTATE_180: + case DRM_MODE_ROTATE_180: orient = MASK_X_INVERT | MASK_Y_INVERT; break; - case DRM_ROTATE_270: + case DRM_MODE_ROTATE_270: orient = MASK_XY_FLIP | MASK_Y_INVERT; break; } - if (win->rotation & DRM_REFLECT_X) + if (win->rotation & DRM_MODE_REFLECT_X) orient ^= MASK_X_INVERT; - if (win->rotation & DRM_REFLECT_Y) + if (win->rotation & DRM_MODE_REFLECT_Y) orient ^= MASK_Y_INVERT; /* adjust x,y offset for flip/invert: */ @@ -205,9 +205,9 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb, info->rotation_type = OMAP_DSS_ROT_TILER; info->screen_width = omap_gem_tiled_stride(plane->bo, orient); } else { - switch (win->rotation & DRM_ROTATE_MASK) { + switch (win->rotation & DRM_MODE_ROTATE_MASK) { case 0: - case DRM_ROTATE_0: + case DRM_MODE_ROTATE_0: /* OK */ break; diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 9168154d749e42..d3d6818c68f823 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -141,7 +141,7 @@ static void omap_plane_atomic_disable(struct drm_plane *plane, struct omap_plane_state *omap_state = to_omap_plane_state(plane->state); struct omap_plane *omap_plane = to_omap_plane(plane); - plane->state->rotation = DRM_ROTATE_0; + plane->state->rotation = DRM_MODE_ROTATE_0; omap_state->zorder = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : omap_plane->id; @@ -177,7 +177,7 @@ static int omap_plane_atomic_check(struct drm_plane *plane, if (state->crtc_y + state->crtc_h > crtc_state->adjusted_mode.vdisplay) return -EINVAL; - if (state->rotation != DRM_ROTATE_0 && + if (state->rotation != DRM_MODE_ROTATE_0 && !omap_framebuffer_supports_rotation(state->fb)) return -EINVAL; @@ -213,15 +213,15 @@ void omap_plane_install_properties(struct drm_plane *plane, if (priv->has_dmm) { if (!plane->rotation_property) drm_plane_create_rotation_property(plane, - DRM_ROTATE_0, - DRM_ROTATE_0 | DRM_ROTATE_90 | - DRM_ROTATE_180 | DRM_ROTATE_270 | - DRM_REFLECT_X | DRM_REFLECT_Y); + DRM_MODE_ROTATE_0, + DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | + DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270 | + DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y); /* Attach the rotation property also to the crtc object */ if (plane->rotation_property && obj != &plane->base) drm_object_attach_property(obj, plane->rotation_property, - DRM_ROTATE_0); + DRM_MODE_ROTATE_0); } drm_object_attach_property(obj, priv->zorder_prop, 0); @@ -273,7 +273,7 @@ static void omap_plane_reset(struct drm_plane *plane) */ omap_state->zorder = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : omap_plane->id; - omap_state->base.rotation = DRM_ROTATE_0; + omap_state->base.rotation = DRM_MODE_ROTATE_0; plane->state = &omap_state->base; plane->state->plane = plane; diff --git a/drivers/gpu/drm/pl111/Kconfig b/drivers/gpu/drm/pl111/Kconfig new file mode 100644 index 00000000000000..309f4fd52de780 --- /dev/null +++ b/drivers/gpu/drm/pl111/Kconfig @@ -0,0 +1,13 @@ +config DRM_PL111 + tristate "DRM Support for PL111 CLCD Controller" + depends on DRM + depends on ARM || ARM64 || COMPILE_TEST + depends on COMMON_CLK + select DRM_KMS_HELPER + select DRM_KMS_CMA_HELPER + select DRM_GEM_CMA_HELPER + select VT_HW_CONSOLE_BINDING if FRAMEBUFFER_CONSOLE + help + Choose this option for DRM support for the PL111 CLCD controller. + If M is selected the module will be called pl111_drm. + diff --git a/drivers/gpu/drm/pl111/Makefile b/drivers/gpu/drm/pl111/Makefile new file mode 100644 index 00000000000000..59483d610ef5cd --- /dev/null +++ b/drivers/gpu/drm/pl111/Makefile @@ -0,0 +1,7 @@ +pl111_drm-y += pl111_connector.o \ + pl111_display.o \ + pl111_drv.o + +pl111_drm-$(CONFIG_DEBUG_FS) += pl111_debugfs.o + +obj-$(CONFIG_DRM_PL111) += pl111_drm.o diff --git a/drivers/gpu/drm/pl111/pl111_connector.c b/drivers/gpu/drm/pl111/pl111_connector.c new file mode 100644 index 00000000000000..3f213d7e7692d3 --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_connector.c @@ -0,0 +1,127 @@ +/* + * (C) COPYRIGHT 2012-2013 ARM Limited. All rights reserved. + * + * Parts of this file were based on sources as follows: + * + * Copyright (c) 2006-2008 Intel Corporation + * Copyright (c) 2007 Dave Airlie + * Copyright (C) 2011 Texas Instruments + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms of + * such GNU licence. + * + */ + +/** + * pl111_drm_connector.c + * Implementation of the connector functions for PL111 DRM + */ +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "pl111_drm.h" + +static void pl111_connector_destroy(struct drm_connector *connector) +{ + struct pl111_drm_connector *pl111_connector = + to_pl111_connector(connector); + + if (pl111_connector->panel) + drm_panel_detach(pl111_connector->panel); + + drm_connector_unregister(connector); + drm_connector_cleanup(connector); +} + +static enum drm_connector_status pl111_connector_detect(struct drm_connector + *connector, bool force) +{ + struct pl111_drm_connector *pl111_connector = + to_pl111_connector(connector); + + return (pl111_connector->panel ? + connector_status_connected : + connector_status_disconnected); +} + +static int pl111_connector_helper_get_modes(struct drm_connector *connector) +{ + struct pl111_drm_connector *pl111_connector = + to_pl111_connector(connector); + + if (!pl111_connector->panel) + return 0; + + return drm_panel_get_modes(pl111_connector->panel); +} + +const struct drm_connector_funcs connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = pl111_connector_destroy, + .detect = pl111_connector_detect, + .dpms = drm_atomic_helper_connector_dpms, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +const struct drm_connector_helper_funcs connector_helper_funcs = { + .get_modes = pl111_connector_helper_get_modes, +}; + +/* Walks the OF graph to find the panel node and then asks DRM to look + * up the panel. + */ +static struct drm_panel *pl111_get_panel(struct device *dev) +{ + struct device_node *endpoint, *panel_node; + struct device_node *np = dev->of_node; + struct drm_panel *panel; + + endpoint = of_graph_get_next_endpoint(np, NULL); + if (!endpoint) { + dev_err(dev, "no endpoint to fetch panel\n"); + return NULL; + } + + /* don't proceed if we have an endpoint but no panel_node tied to it */ + panel_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + if (!panel_node) { + dev_err(dev, "no valid panel node\n"); + return NULL; + } + + panel = of_drm_find_panel(panel_node); + of_node_put(panel_node); + + return panel; +} + +int pl111_connector_init(struct drm_device *dev) +{ + struct pl111_drm_dev_private *priv = dev->dev_private; + struct pl111_drm_connector *pl111_connector = &priv->connector; + struct drm_connector *connector = &pl111_connector->connector; + + drm_connector_init(dev, connector, &connector_funcs, + DRM_MODE_CONNECTOR_DPI); + drm_connector_helper_add(connector, &connector_helper_funcs); + + pl111_connector->panel = pl111_get_panel(dev->dev); + if (pl111_connector->panel) + drm_panel_attach(pl111_connector->panel, connector); + + return 0; +} + diff --git a/drivers/gpu/drm/pl111/pl111_debugfs.c b/drivers/gpu/drm/pl111/pl111_debugfs.c new file mode 100644 index 00000000000000..0d9dee199b2cc9 --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_debugfs.c @@ -0,0 +1,55 @@ +/* + * Copyright © 2017 Broadcom + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include "pl111_drm.h" + +#define REGDEF(reg) { reg, #reg } +static const struct { + u32 reg; + const char *name; +} pl111_reg_defs[] = { + REGDEF(CLCD_TIM0), + REGDEF(CLCD_TIM1), + REGDEF(CLCD_TIM2), + REGDEF(CLCD_TIM3), + REGDEF(CLCD_UBAS), + REGDEF(CLCD_PL111_CNTL), + REGDEF(CLCD_PL111_IENB), +}; + +int pl111_debugfs_regs(struct seq_file *m, void *unused) +{ + struct drm_info_node *node = (struct drm_info_node *)m->private; + struct drm_device *dev = node->minor->dev; + struct pl111_drm_dev_private *priv = dev->dev_private; + int i; + + for (i = 0; i < ARRAY_SIZE(pl111_reg_defs); i++) { + seq_printf(m, "%s (0x%04x): 0x%08x\n", + pl111_reg_defs[i].name, pl111_reg_defs[i].reg, + readl(priv->regs + pl111_reg_defs[i].reg)); + } + + return 0; +} + +static const struct drm_info_list pl111_debugfs_list[] = { + {"regs", pl111_debugfs_regs, 0}, +}; + +int +pl111_debugfs_init(struct drm_minor *minor) +{ + return drm_debugfs_create_files(pl111_debugfs_list, + ARRAY_SIZE(pl111_debugfs_list), + minor->debugfs_root, minor); +} diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c new file mode 100644 index 00000000000000..3e0a4fa73ddbc3 --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -0,0 +1,476 @@ +/* + * (C) COPYRIGHT 2012-2013 ARM Limited. All rights reserved. + * + * Parts of this file were based on sources as follows: + * + * Copyright (c) 2006-2008 Intel Corporation + * Copyright (c) 2007 Dave Airlie + * Copyright (C) 2011 Texas Instruments + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms of + * such GNU licence. + * + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include "pl111_drm.h" + +irqreturn_t pl111_irq(int irq, void *data) +{ + struct pl111_drm_dev_private *priv = data; + u32 irq_stat; + irqreturn_t status = IRQ_NONE; + + irq_stat = readl(priv->regs + CLCD_PL111_MIS); + + if (!irq_stat) + return IRQ_NONE; + + if (irq_stat & CLCD_IRQ_NEXTBASE_UPDATE) { + drm_crtc_handle_vblank(&priv->pipe.crtc); + + status = IRQ_HANDLED; + } + + /* Clear the interrupt once done */ + writel(irq_stat, priv->regs + CLCD_PL111_ICR); + + return status; +} + +static u32 pl111_get_fb_offset(struct drm_plane_state *pstate) +{ + struct drm_framebuffer *fb = pstate->fb; + struct drm_gem_cma_object *obj = drm_fb_cma_get_gem_obj(fb, 0); + + return (obj->paddr + + fb->offsets[0] + + fb->format->cpp[0] * pstate->src_x + + fb->pitches[0] * pstate->src_y); +} + +static int pl111_display_check(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *pstate, + struct drm_crtc_state *cstate) +{ + const struct drm_display_mode *mode = &cstate->mode; + struct drm_framebuffer *old_fb = pipe->plane.state->fb; + struct drm_framebuffer *fb = pstate->fb; + + if (mode->hdisplay % 16) + return -EINVAL; + + if (fb) { + u32 offset = pl111_get_fb_offset(pstate); + + /* FB base address must be dword aligned. */ + if (offset & 3) + return -EINVAL; + + /* There's no pitch register -- the mode's hdisplay + * controls it. + */ + if (fb->pitches[0] != mode->hdisplay * fb->format->cpp[0]) + return -EINVAL; + + /* We can't change the FB format in a flicker-free + * manner (and only update it during CRTC enable). + */ + if (old_fb && old_fb->format != fb->format) + cstate->mode_changed = true; + } + + return 0; +} + +static void pl111_display_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *cstate) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_plane *plane = &pipe->plane; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + const struct drm_display_mode *mode = &cstate->mode; + struct drm_framebuffer *fb = plane->state->fb; + struct drm_connector *connector = &priv->connector.connector; + u32 cntl; + u32 ppl, hsw, hfp, hbp; + u32 lpp, vsw, vfp, vbp; + u32 cpl, tim2; + int ret; + + ret = clk_set_rate(priv->clk, mode->clock * 1000); + if (ret) { + dev_err(drm->dev, + "Failed to set pixel clock rate to %d: %d\n", + mode->clock * 1000, ret); + } + + clk_prepare_enable(priv->clk); + + ppl = (mode->hdisplay / 16) - 1; + hsw = mode->hsync_end - mode->hsync_start - 1; + hfp = mode->hsync_start - mode->hdisplay - 1; + hbp = mode->htotal - mode->hsync_end - 1; + + lpp = mode->vdisplay - 1; + vsw = mode->vsync_end - mode->vsync_start - 1; + vfp = mode->vsync_start - mode->vdisplay; + vbp = mode->vtotal - mode->vsync_end; + + cpl = mode->hdisplay - 1; + + writel((ppl << 2) | + (hsw << 8) | + (hfp << 16) | + (hbp << 24), + priv->regs + CLCD_TIM0); + writel(lpp | + (vsw << 10) | + (vfp << 16) | + (vbp << 24), + priv->regs + CLCD_TIM1); + + spin_lock(&priv->tim2_lock); + + tim2 = readl(priv->regs + CLCD_TIM2); + tim2 &= (TIM2_BCD | TIM2_PCD_LO_MASK | TIM2_PCD_HI_MASK); + + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + tim2 |= TIM2_IHS; + + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + tim2 |= TIM2_IVS; + + if (connector->display_info.bus_flags & DRM_BUS_FLAG_DE_LOW) + tim2 |= TIM2_IOE; + + if (connector->display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE) + tim2 |= TIM2_IPC; + + tim2 |= cpl << 16; + writel(tim2, priv->regs + CLCD_TIM2); + spin_unlock(&priv->tim2_lock); + + writel(0, priv->regs + CLCD_TIM3); + + drm_panel_prepare(priv->connector.panel); + + /* Enable and Power Up */ + cntl = CNTL_LCDEN | CNTL_LCDTFT | CNTL_LCDPWR | CNTL_LCDVCOMP(1); + + /* Note that the the hardware's format reader takes 'r' from + * the low bit, while DRM formats list channels from high bit + * to low bit as you read left to right. + */ + switch (fb->format->format) { + case DRM_FORMAT_ABGR8888: + case DRM_FORMAT_XBGR8888: + cntl |= CNTL_LCDBPP24; + break; + case DRM_FORMAT_ARGB8888: + case DRM_FORMAT_XRGB8888: + cntl |= CNTL_LCDBPP24 | CNTL_BGR; + break; + case DRM_FORMAT_BGR565: + cntl |= CNTL_LCDBPP16_565; + break; + case DRM_FORMAT_RGB565: + cntl |= CNTL_LCDBPP16_565 | CNTL_BGR; + break; + case DRM_FORMAT_ABGR1555: + case DRM_FORMAT_XBGR1555: + cntl |= CNTL_LCDBPP16; + break; + case DRM_FORMAT_ARGB1555: + case DRM_FORMAT_XRGB1555: + cntl |= CNTL_LCDBPP16 | CNTL_BGR; + break; + case DRM_FORMAT_ABGR4444: + case DRM_FORMAT_XBGR4444: + cntl |= CNTL_LCDBPP16_444; + break; + case DRM_FORMAT_ARGB4444: + case DRM_FORMAT_XRGB4444: + cntl |= CNTL_LCDBPP16_444 | CNTL_BGR; + break; + default: + WARN_ONCE(true, "Unknown FB format 0x%08x\n", + fb->format->format); + break; + } + + writel(cntl, priv->regs + CLCD_PL111_CNTL); + + drm_panel_enable(priv->connector.panel); + + drm_crtc_vblank_on(crtc); +} + +void pl111_display_disable(struct drm_simple_display_pipe *pipe) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + + drm_crtc_vblank_off(crtc); + + drm_panel_disable(priv->connector.panel); + + /* Disable and Power Down */ + writel(0, priv->regs + CLCD_PL111_CNTL); + + drm_panel_unprepare(priv->connector.panel); + + clk_disable_unprepare(priv->clk); +} + +static void pl111_display_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_pstate) +{ + struct drm_crtc *crtc = &pipe->crtc; + struct drm_device *drm = crtc->dev; + struct pl111_drm_dev_private *priv = drm->dev_private; + struct drm_pending_vblank_event *event = crtc->state->event; + struct drm_plane *plane = &pipe->plane; + struct drm_plane_state *pstate = plane->state; + struct drm_framebuffer *fb = pstate->fb; + + if (fb) { + u32 addr = pl111_get_fb_offset(pstate); + + writel(addr, priv->regs + CLCD_UBAS); + } + + if (event) { + crtc->state->event = NULL; + + spin_lock_irq(&crtc->dev->event_lock); + if (crtc->state->active && drm_crtc_vblank_get(crtc) == 0) + drm_crtc_arm_vblank_event(crtc, event); + else + drm_crtc_send_vblank_event(crtc, event); + spin_unlock_irq(&crtc->dev->event_lock); + } +} + +int pl111_enable_vblank(struct drm_device *drm, unsigned int crtc) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + + writel(CLCD_IRQ_NEXTBASE_UPDATE, priv->regs + CLCD_PL111_IENB); + + return 0; +} + +void pl111_disable_vblank(struct drm_device *drm, unsigned int crtc) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + + writel(0, priv->regs + CLCD_PL111_IENB); +} + +static int pl111_display_prepare_fb(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state) +{ + return drm_fb_cma_prepare_fb(&pipe->plane, plane_state); +} + +static const struct drm_simple_display_pipe_funcs pl111_display_funcs = { + .check = pl111_display_check, + .enable = pl111_display_enable, + .disable = pl111_display_disable, + .update = pl111_display_update, + .prepare_fb = pl111_display_prepare_fb, +}; + +static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, bool set_parent) +{ + int best_div = 1, div; + struct clk_hw *parent = clk_hw_get_parent(hw); + unsigned long best_prate = 0; + unsigned long best_diff = ~0ul; + int max_div = (1 << (TIM2_PCD_LO_BITS + TIM2_PCD_HI_BITS)) - 1; + + for (div = 1; div < max_div; div++) { + unsigned long this_prate, div_rate, diff; + + if (set_parent) + this_prate = clk_hw_round_rate(parent, rate * div); + else + this_prate = *prate; + div_rate = DIV_ROUND_UP_ULL(this_prate, div); + diff = abs(rate - div_rate); + + if (diff < best_diff) { + best_div = div; + best_diff = diff; + best_prate = this_prate; + } + } + + *prate = best_prate; + return best_div; +} + +static long pl111_clk_div_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + int div = pl111_clk_div_choose_div(hw, rate, prate, true); + + return DIV_ROUND_UP_ULL(*prate, div); +} + +static unsigned long pl111_clk_div_recalc_rate(struct clk_hw *hw, + unsigned long prate) +{ + struct pl111_drm_dev_private *priv = + container_of(hw, struct pl111_drm_dev_private, clk_div); + u32 tim2 = readl(priv->regs + CLCD_TIM2); + int div; + + if (tim2 & TIM2_BCD) + return prate; + + div = tim2 & TIM2_PCD_LO_MASK; + div |= (tim2 & TIM2_PCD_HI_MASK) >> + (TIM2_PCD_HI_SHIFT - TIM2_PCD_LO_BITS); + div += 2; + + return DIV_ROUND_UP_ULL(prate, div); +} + +static int pl111_clk_div_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long prate) +{ + struct pl111_drm_dev_private *priv = + container_of(hw, struct pl111_drm_dev_private, clk_div); + int div = pl111_clk_div_choose_div(hw, rate, &prate, false); + u32 tim2; + + spin_lock(&priv->tim2_lock); + tim2 = readl(priv->regs + CLCD_TIM2); + tim2 &= ~(TIM2_BCD | TIM2_PCD_LO_MASK | TIM2_PCD_HI_MASK); + + if (div == 1) { + tim2 |= TIM2_BCD; + } else { + div -= 2; + tim2 |= div & TIM2_PCD_LO_MASK; + tim2 |= (div >> TIM2_PCD_LO_BITS) << TIM2_PCD_HI_SHIFT; + } + + writel(tim2, priv->regs + CLCD_TIM2); + spin_unlock(&priv->tim2_lock); + + return 0; +} + +static const struct clk_ops pl111_clk_div_ops = { + .recalc_rate = pl111_clk_div_recalc_rate, + .round_rate = pl111_clk_div_round_rate, + .set_rate = pl111_clk_div_set_rate, +}; + +static int +pl111_init_clock_divider(struct drm_device *drm) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + struct clk *parent = devm_clk_get(drm->dev, "clcdclk"); + struct clk_hw *div = &priv->clk_div; + const char *parent_name; + struct clk_init_data init = { + .name = "pl111_div", + .ops = &pl111_clk_div_ops, + .parent_names = &parent_name, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + }; + int ret; + + if (IS_ERR(parent)) { + dev_err(drm->dev, "CLCD: unable to get clcdclk.\n"); + return PTR_ERR(parent); + } + parent_name = __clk_get_name(parent); + + spin_lock_init(&priv->tim2_lock); + div->init = &init; + + ret = devm_clk_hw_register(drm->dev, div); + + priv->clk = div->clk; + return ret; +} + +int pl111_display_init(struct drm_device *drm) +{ + struct pl111_drm_dev_private *priv = drm->dev_private; + struct device *dev = drm->dev; + struct device_node *endpoint; + u32 tft_r0b0g0[3]; + int ret; + static const u32 formats[] = { + DRM_FORMAT_ABGR8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_BGR565, + DRM_FORMAT_RGB565, + DRM_FORMAT_ABGR1555, + DRM_FORMAT_XBGR1555, + DRM_FORMAT_ARGB1555, + DRM_FORMAT_XRGB1555, + DRM_FORMAT_ABGR4444, + DRM_FORMAT_XBGR4444, + DRM_FORMAT_ARGB4444, + DRM_FORMAT_XRGB4444, + }; + + endpoint = of_graph_get_next_endpoint(dev->of_node, NULL); + if (!endpoint) + return -ENODEV; + + if (of_property_read_u32_array(endpoint, + "arm,pl11x,tft-r0g0b0-pads", + tft_r0b0g0, + ARRAY_SIZE(tft_r0b0g0)) != 0) { + dev_err(dev, "arm,pl11x,tft-r0g0b0-pads should be 3 ints\n"); + of_node_put(endpoint); + return -ENOENT; + } + of_node_put(endpoint); + + if (tft_r0b0g0[0] != 0 || + tft_r0b0g0[1] != 8 || + tft_r0b0g0[2] != 16) { + dev_err(dev, "arm,pl11x,tft-r0g0b0-pads != [0,8,16] not yet supported\n"); + return -EINVAL; + } + + ret = pl111_init_clock_divider(drm); + if (ret) + return ret; + + ret = drm_simple_display_pipe_init(drm, &priv->pipe, + &pl111_display_funcs, + formats, ARRAY_SIZE(formats), + &priv->connector.connector); + if (ret) + return ret; + + return 0; +} diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h new file mode 100644 index 00000000000000..5c685bfc8fdc52 --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_drm.h @@ -0,0 +1,67 @@ +/* + * + * (C) COPYRIGHT 2012-2013 ARM Limited. All rights reserved. + * + * + * Parts of this file were based on sources as follows: + * + * Copyright (c) 2006-2008 Intel Corporation + * Copyright (c) 2007 Dave Airlie + * Copyright (C) 2011 Texas Instruments + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms of + * such GNU licence. + * + */ + +#ifndef _PL111_DRM_H_ +#define _PL111_DRM_H_ + +#include +#include +#include + +#define CLCD_IRQ_NEXTBASE_UPDATE BIT(2) + +struct drm_minor; + +struct pl111_drm_connector { + struct drm_connector connector; + struct drm_panel *panel; +}; + +struct pl111_drm_dev_private { + struct drm_device *drm; + + struct pl111_drm_connector connector; + struct drm_simple_display_pipe pipe; + struct drm_fbdev_cma *fbdev; + + void *regs; + /* The pixel clock (a reference to our clock divider off of CLCDCLK). */ + struct clk *clk; + /* pl111's internal clock divider. */ + struct clk_hw clk_div; + /* Lock to sync access to CLCD_TIM2 between the common clock + * subsystem and pl111_display_enable(). + */ + spinlock_t tim2_lock; +}; + +#define to_pl111_connector(x) \ + container_of(x, struct pl111_drm_connector, connector) + +int pl111_display_init(struct drm_device *dev); +int pl111_enable_vblank(struct drm_device *drm, unsigned int crtc); +void pl111_disable_vblank(struct drm_device *drm, unsigned int crtc); +irqreturn_t pl111_irq(int irq, void *data); +int pl111_connector_init(struct drm_device *dev); +int pl111_encoder_init(struct drm_device *dev); +int pl111_dumb_create(struct drm_file *file_priv, + struct drm_device *dev, + struct drm_mode_create_dumb *args); +int pl111_debugfs_init(struct drm_minor *minor); + +#endif /* _PL111_DRM_H_ */ diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c new file mode 100644 index 00000000000000..e96efad37d274f --- /dev/null +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -0,0 +1,269 @@ +/* + * (C) COPYRIGHT 2012-2013 ARM Limited. All rights reserved. + * + * Parts of this file were based on sources as follows: + * + * Copyright (c) 2006-2008 Intel Corporation + * Copyright (c) 2007 Dave Airlie + * Copyright (C) 2011 Texas Instruments + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms of + * such GNU licence. + * + */ + +/** + * DOC: ARM PrimeCell PL111 CLCD Driver + * + * The PL111 is a simple LCD controller that can support TFT and STN + * displays. This driver exposes a standard KMS interface for them. + * + * This driver uses the same Device Tree binding as the fbdev CLCD + * driver. While the fbdev driver supports panels that may be + * connected to the CLCD internally to the CLCD driver, in DRM the + * panels get split out to drivers/gpu/drm/panels/. This means that, + * in converting from using fbdev to using DRM, you also need to write + * a panel driver (which may be as simple as an entry in + * panel-simple.c). + * + * The driver currently doesn't expose the cursor. The DRM API for + * cursors requires support for 64x64 ARGB8888 cursor images, while + * the hardware can only support 64x64 monochrome with masking + * cursors. While one could imagine trying to hack something together + * to look at the ARGB8888 and program reasonable in monochrome, we + * just don't expose the cursor at all instead, and leave cursor + * support to the X11 software cursor layer. + * + * TODO: + * + * - Fix race between setting plane base address and getting IRQ for + * vsync firing the pageflip completion. + * + * - Expose the correct set of formats we can support based on the + * "arm,pl11x,tft-r0g0b0-pads" DT property. + * + * - Use the "max-memory-bandwidth" DT property to filter the + * supported formats. + * + * - Read back hardware state at boot to skip reprogramming the + * hardware when doing a no-op modeset. + * + * - Use the CLKSEL bit to support switching between the two external + * clock parents. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "pl111_drm.h" + +#define DRIVER_DESC "DRM module for PL111" + +static struct drm_mode_config_funcs mode_config_funcs = { + .fb_create = drm_fb_cma_create, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static int pl111_modeset_init(struct drm_device *dev) +{ + struct drm_mode_config *mode_config; + struct pl111_drm_dev_private *priv = dev->dev_private; + int ret = 0; + + drm_mode_config_init(dev); + mode_config = &dev->mode_config; + mode_config->funcs = &mode_config_funcs; + mode_config->min_width = 1; + mode_config->max_width = 1024; + mode_config->min_height = 1; + mode_config->max_height = 768; + + ret = pl111_connector_init(dev); + if (ret) { + dev_err(dev->dev, "Failed to create pl111_drm_connector\n"); + goto out_config; + } + + /* Don't actually attach if we didn't find a drm_panel + * attached to us. This will allow a kernel to include both + * the fbdev pl111 driver and this one, and choose between + * them based on which subsystem has support for the panel. + */ + if (!priv->connector.panel) { + dev_info(dev->dev, + "Disabling due to lack of DRM panel device.\n"); + ret = -ENODEV; + goto out_config; + } + + ret = pl111_display_init(dev); + if (ret != 0) { + dev_err(dev->dev, "Failed to init display\n"); + goto out_config; + } + + ret = drm_vblank_init(dev, 1); + if (ret != 0) { + dev_err(dev->dev, "Failed to init vblank\n"); + goto out_config; + } + + drm_mode_config_reset(dev); + + priv->fbdev = drm_fbdev_cma_init(dev, 32, + dev->mode_config.num_connector); + + drm_kms_helper_poll_init(dev); + + goto finish; + +out_config: + drm_mode_config_cleanup(dev); +finish: + return ret; +} + +DEFINE_DRM_GEM_CMA_FOPS(drm_fops); + +static void pl111_lastclose(struct drm_device *dev) +{ + struct pl111_drm_dev_private *priv = dev->dev_private; + + drm_fbdev_cma_restore_mode(priv->fbdev); +} + +static struct drm_driver pl111_drm_driver = { + .driver_features = + DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME | DRIVER_ATOMIC, + .lastclose = pl111_lastclose, + .ioctls = NULL, + .fops = &drm_fops, + .name = "pl111", + .desc = DRIVER_DESC, + .date = "20170317", + .major = 1, + .minor = 0, + .patchlevel = 0, + .dumb_create = drm_gem_cma_dumb_create, + .dumb_destroy = drm_gem_dumb_destroy, + .dumb_map_offset = drm_gem_cma_dumb_map_offset, + .gem_free_object = drm_gem_cma_free_object, + .gem_vm_ops = &drm_gem_cma_vm_ops, + + .enable_vblank = pl111_enable_vblank, + .disable_vblank = pl111_disable_vblank, + + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_get_sg_table = drm_gem_cma_prime_get_sg_table, + +#if defined(CONFIG_DEBUG_FS) + .debugfs_init = pl111_debugfs_init, +#endif +}; + +#ifdef CONFIG_ARM_AMBA +static int pl111_amba_probe(struct amba_device *amba_dev, + const struct amba_id *id) +{ + struct device *dev = &amba_dev->dev; + struct pl111_drm_dev_private *priv; + struct drm_device *drm; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + drm = drm_dev_alloc(&pl111_drm_driver, dev); + if (IS_ERR(drm)) + return PTR_ERR(drm); + amba_set_drvdata(amba_dev, drm); + priv->drm = drm; + drm->dev_private = priv; + + priv->regs = devm_ioremap_resource(dev, &amba_dev->res); + if (IS_ERR(priv->regs)) { + dev_err(dev, "%s failed mmio\n", __func__); + return PTR_ERR(priv->regs); + } + + /* turn off interrupts before requesting the irq */ + writel(0, priv->regs + CLCD_PL111_IENB); + + ret = devm_request_irq(dev, amba_dev->irq[0], pl111_irq, 0, + "pl111", priv); + if (ret != 0) { + dev_err(dev, "%s failed irq %d\n", __func__, ret); + return ret; + } + + ret = pl111_modeset_init(drm); + if (ret != 0) + goto dev_unref; + + ret = drm_dev_register(drm, 0); + if (ret < 0) + goto dev_unref; + + return 0; + +dev_unref: + drm_dev_unref(drm); + return ret; +} + +static int pl111_amba_remove(struct amba_device *amba_dev) +{ + struct drm_device *drm = amba_get_drvdata(amba_dev); + struct pl111_drm_dev_private *priv = drm->dev_private; + + drm_dev_unregister(drm); + if (priv->fbdev) + drm_fbdev_cma_fini(priv->fbdev); + drm_mode_config_cleanup(drm); + drm_dev_unref(drm); + + return 0; +} + +static struct amba_id pl111_id_table[] = { + { + .id = 0x00041111, + .mask = 0x000fffff, + }, + {0, 0}, +}; + +static struct amba_driver pl111_amba_driver = { + .drv = { + .name = "drm-clcd-pl111", + }, + .probe = pl111_amba_probe, + .remove = pl111_amba_remove, + .id_table = pl111_id_table, +}; + +module_amba_driver(pl111_amba_driver); +#endif /* CONFIG_ARM_AMBA */ + +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_AUTHOR("ARM Ltd."); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/qxl/Makefile b/drivers/gpu/drm/qxl/Makefile index bacc4aff120107..33a7d0c434b7f6 100644 --- a/drivers/gpu/drm/qxl/Makefile +++ b/drivers/gpu/drm/qxl/Makefile @@ -2,8 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm - qxl-y := qxl_drv.o qxl_kms.o qxl_display.o qxl_ttm.o qxl_fb.o qxl_object.o qxl_gem.o qxl_cmd.o qxl_image.o qxl_draw.o qxl_debugfs.o qxl_irq.o qxl_dumb.o qxl_ioctl.o qxl_release.o qxl_prime.o obj-$(CONFIG_DRM_QXL)+= qxl.o diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index ffe821b61f7d75..15c84068d3fb56 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -30,7 +30,7 @@ #include -#include "drmP.h" +#include #include "qxl_drv.h" #include "qxl_object.h" diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 4a340efd8ba67a..03fe182203ce91 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -23,16 +23,15 @@ * Alon Levy */ - #include - -#include "qxl_drv.h" -#include "qxl_object.h" -#include "drm_crtc_helper.h" +#include #include #include #include +#include "qxl_drv.h" +#include "qxl_object.h" + static bool qxl_head_enabled(struct qxl_head *head) { return head->width && head->height; diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index abf7b8360361b8..c2fc201d9e1ba8 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -31,9 +31,9 @@ #include #include -#include "drmP.h" -#include "drm/drm.h" -#include "drm_crtc_helper.h" +#include +#include +#include #include "qxl_drv.h" #include "qxl_object.h" diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 5ea290a33a6897..3591d2330a09d8 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -36,20 +36,18 @@ #include #include -#include "drmP.h" -#include "drm_crtc.h" -#include -#include -#include -#include - +#include #include #include - +#include +#include +#include /* just for ttm_validate_buffer */ -#include - +#include +#include +#include #include + #include "qxl_dev.h" #define DRIVER_AUTHOR "Dave Airlie" diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index 14e2a49a4dcf3f..573e7e9a5f986e 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -25,14 +25,15 @@ */ #include -#include "drmP.h" -#include "drm/drm.h" -#include "drm/drm_crtc.h" -#include "drm/drm_crtc_helper.h" +#include +#include +#include +#include +#include + #include "qxl_drv.h" #include "qxl_object.h" -#include "drm_fb_helper.h" #define QXL_DIRTY_DELAY (HZ / 30) diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c index 3f185c4da5b7d5..85f546719adb07 100644 --- a/drivers/gpu/drm/qxl/qxl_gem.c +++ b/drivers/gpu/drm/qxl/qxl_gem.c @@ -23,8 +23,9 @@ * Alon Levy */ -#include "drmP.h" -#include "drm/drm.h" +#include +#include + #include "qxl_drv.h" #include "qxl_object.h" diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 0fdedee4509ddb..87fc1dbd0a2fcf 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -23,11 +23,11 @@ * Alon Levy */ -#include -#include -#include -#include -#include +#include +#include +#include +#include +#include #include #include #include diff --git a/drivers/gpu/drm/r128/Makefile b/drivers/gpu/drm/r128/Makefile index 1cc72ae3a88076..1a6700ebaf09f3 100644 --- a/drivers/gpu/drm/r128/Makefile +++ b/drivers/gpu/drm/r128/Makefile @@ -2,7 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm r128-y := r128_drv.o r128_cce.o r128_state.o r128_irq.o r128-$(CONFIG_COMPAT) += r128_ioc32.o diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile index 08bd17d3925cef..a5d3cd3ecb5f67 100644 --- a/drivers/gpu/drm/radeon/Makefile +++ b/drivers/gpu/drm/radeon/Makefile @@ -2,7 +2,7 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y := -Iinclude/drm -Idrivers/gpu/drm/amd/include +ccflags-y := -Idrivers/gpu/drm/amd/include hostprogs-y := mkregtable clean-files := rn50_reg_safe.h r100_reg_safe.h r200_reg_safe.h rv515_reg_safe.h r300_reg_safe.h r420_reg_safe.h rs600_reg_safe.h r600_reg_safe.h evergreen_reg_safe.h cayman_reg_safe.h diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c index 38e5123708e74e..95652e643da132 100644 --- a/drivers/gpu/drm/radeon/btc_dpm.c +++ b/drivers/gpu/drm/radeon/btc_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "btcd.h" diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index ea36dc4dd5d22e..c97fbb2ab48b45 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -22,7 +22,7 @@ */ #include -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "radeon_ucode.h" diff --git a/drivers/gpu/drm/radeon/ci_smc.c b/drivers/gpu/drm/radeon/ci_smc.c index 24760ee3063ed8..3356a21d97ec2d 100644 --- a/drivers/gpu/drm/radeon/ci_smc.c +++ b/drivers/gpu/drm/radeon/ci_smc.c @@ -23,7 +23,7 @@ */ #include -#include "drmP.h" +#include #include "radeon.h" #include "cikd.h" #include "ppsmc.h" diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 008c145b7f29f6..258912132b629d 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -24,7 +24,7 @@ #include #include #include -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "radeon_audio.h" diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c index a4edd07027186d..3eb7899a4035ba 100644 --- a/drivers/gpu/drm/radeon/cypress_dpm.c +++ b/drivers/gpu/drm/radeon/cypress_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "evergreend.h" diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c index a7e9786779378f..ae1529b0ef6f41 100644 --- a/drivers/gpu/drm/radeon/kv_dpm.c +++ b/drivers/gpu/drm/radeon/kv_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "cikd.h" #include "r600_dpm.h" diff --git a/drivers/gpu/drm/radeon/kv_smc.c b/drivers/gpu/drm/radeon/kv_smc.c index 0000b59a6d0599..af60bd32a28737 100644 --- a/drivers/gpu/drm/radeon/kv_smc.c +++ b/drivers/gpu/drm/radeon/kv_smc.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "cikd.h" #include "kv_dpm.h" diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index 4a601f99056259..9416e72f86aafc 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "nid.h" diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index c7fc1dbfd192f1..31d1b471084468 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "r600d.h" diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index c1c8e2208a21b4..342e3b1fb9c7e1 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -68,11 +68,11 @@ #include #include -#include -#include -#include -#include -#include +#include +#include +#include +#include +#include #include diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 3ac671f6c8e1f0..00b22af70f5c09 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -87,7 +87,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->dma_reloc_idx = 0; /* FIXME: we assume that each relocs use 4 dwords */ p->nrelocs = chunk->length_dw / 4; - p->relocs = drm_calloc_large(p->nrelocs, sizeof(struct radeon_bo_list)); + p->relocs = kvmalloc_array(p->nrelocs, sizeof(struct radeon_bo_list), + GFP_KERNEL | __GFP_ZERO); if (p->relocs == NULL) { return -ENOMEM; } @@ -341,7 +342,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) continue; } - p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t)); + p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), GFP_KERNEL); size *= sizeof(uint32_t); if (p->chunks[i].kdata == NULL) { return -ENOMEM; @@ -440,10 +441,10 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo } } kfree(parser->track); - drm_free_large(parser->relocs); - drm_free_large(parser->vm_bos); + kvfree(parser->relocs); + kvfree(parser->vm_bos); for (i = 0; i < parser->nchunks; i++) - drm_free_large(parser->chunks[i].kdata); + kvfree(parser->chunks[i].kdata); kfree(parser->chunks); kfree(parser->chunks_array); radeon_ib_free(parser->rdev, &parser->ib); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 93d45aa5c3d4f7..6f906abd612b76 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -41,7 +41,7 @@ #include #include -#include "drm_crtc_helper.h" +#include #include "radeon_kfd.h" /* @@ -115,10 +115,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon); u32 radeon_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe); int radeon_enable_vblank_kms(struct drm_device *dev, unsigned int pipe); void radeon_disable_vblank_kms(struct drm_device *dev, unsigned int pipe); -int radeon_get_vblank_timestamp_kms(struct drm_device *dev, unsigned int pipe, - int *max_error, - struct timeval *vblank_time, - unsigned flags); void radeon_driver_irq_preinstall_kms(struct drm_device *dev); int radeon_driver_irq_postinstall_kms(struct drm_device *dev); void radeon_driver_irq_uninstall_kms(struct drm_device *dev); @@ -530,6 +526,16 @@ static const struct file_operations radeon_driver_kms_fops = { #endif }; +static bool +radeon_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, + bool in_vblank_irq, int *vpos, int *hpos, + ktime_t *stime, ktime_t *etime, + const struct drm_display_mode *mode) +{ + return radeon_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos, + stime, etime, mode); +} + static struct drm_driver kms_driver = { .driver_features = DRIVER_USE_AGP | @@ -544,8 +550,8 @@ static struct drm_driver kms_driver = { .get_vblank_counter = radeon_get_vblank_counter_kms, .enable_vblank = radeon_enable_vblank_kms, .disable_vblank = radeon_disable_vblank_kms, - .get_vblank_timestamp = radeon_get_vblank_timestamp_kms, - .get_scanout_position = radeon_get_crtc_scanoutpos, + .get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos, + .get_scanout_position = radeon_get_crtc_scanout_position, .irq_preinstall = radeon_driver_irq_preinstall_kms, .irq_postinstall = radeon_driver_irq_postinstall_kms, .irq_uninstall = radeon_driver_irq_uninstall_kms, diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index dddb372de2b9de..574bf7e6b1186f 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -587,7 +587,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, ttm_eu_backoff_reservation(&ticket, &list); error_free: - drm_free_large(vm_bos); + kvfree(vm_bos); if (r && r != -ERESTARTSYS) DRM_ERROR("Couldn't update BO_VA (%d)\n", r); diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 4761f27f2ca2a0..d0ad03674250e9 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -858,43 +858,6 @@ void radeon_disable_vblank_kms(struct drm_device *dev, int crtc) spin_unlock_irqrestore(&rdev->irq.lock, irqflags); } -/** - * radeon_get_vblank_timestamp_kms - get vblank timestamp - * - * @dev: drm dev pointer - * @crtc: crtc to get the timestamp for - * @max_error: max error - * @vblank_time: time value - * @flags: flags passed to the driver - * - * Gets the timestamp on the requested crtc based on the - * scanout position. (all asics). - * Returns postive status flags on success, negative error on failure. - */ -int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc, - int *max_error, - struct timeval *vblank_time, - unsigned flags) -{ - struct drm_crtc *drmcrtc; - struct radeon_device *rdev = dev->dev_private; - - if (crtc < 0 || crtc >= dev->num_crtcs) { - DRM_ERROR("Invalid crtc %d\n", crtc); - return -EINVAL; - } - - /* Get associated drm_crtc: */ - drmcrtc = &rdev->mode_info.crtcs[crtc]->base; - if (!drmcrtc) - return -EINVAL; - - /* Helper routine in DRM core does all the work: */ - return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error, - vblank_time, flags, - &drmcrtc->hwmode); -} - const struct drm_ioctl_desc radeon_ioctls_kms[] = { DRM_IOCTL_DEF_DRV(RADEON_CP_INIT, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(RADEON_CP_START, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index ad282648fc8b1e..00f5ec5c12c7af 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -691,6 +691,9 @@ struct atom_voltage_table }; /* Driver internal use only flags of radeon_get_crtc_scanoutpos() */ +#define DRM_SCANOUTPOS_VALID (1 << 0) +#define DRM_SCANOUTPOS_IN_VBLANK (1 << 1) +#define DRM_SCANOUTPOS_ACCURATE (1 << 2) #define USE_REAL_VBLANKSTART (1 << 30) #define GET_DISTANCE_TO_VBLANKSTART (1 << 31) diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 8c7872339c2a6f..84802b201beff8 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -314,7 +314,7 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring } /* and then save the content of the ring */ - *data = drm_malloc_ab(size, sizeof(uint32_t)); + *data = kvmalloc_array(size, sizeof(uint32_t), GFP_KERNEL); if (!*data) { mutex_unlock(&rdev->ring_lock); return 0; @@ -356,7 +356,7 @@ int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring, } radeon_ring_unlock_commit(rdev, ring, false); - drm_free_large(data); + kvfree(data); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 8b7623b5a62424..faa021396da342 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -29,11 +29,11 @@ * Thomas Hellstrom * Dave Airlie */ -#include -#include -#include -#include -#include +#include +#include +#include +#include +#include #include #include #include diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index a1358748cea56d..5f68245579a3b4 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -132,8 +132,8 @@ struct radeon_bo_list *radeon_vm_get_bos(struct radeon_device *rdev, struct radeon_bo_list *list; unsigned i, idx; - list = drm_malloc_ab(vm->max_pde_used + 2, - sizeof(struct radeon_bo_list)); + list = kvmalloc_array(vm->max_pde_used + 2, + sizeof(struct radeon_bo_list), GFP_KERNEL); if (!list) return NULL; diff --git a/drivers/gpu/drm/radeon/rs780_dpm.c b/drivers/gpu/drm/radeon/rs780_dpm.c index 94b48fc1e266c7..b5e4e09a899616 100644 --- a/drivers/gpu/drm/radeon/rs780_dpm.c +++ b/drivers/gpu/drm/radeon/rs780_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "rs780d.h" diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c index 25e29303b119b9..d91aa394459331 100644 --- a/drivers/gpu/drm/radeon/rv6xx_dpm.c +++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "rv6xxd.h" diff --git a/drivers/gpu/drm/radeon/rv730_dpm.c b/drivers/gpu/drm/radeon/rv730_dpm.c index d37ba2cb886e90..38fdb4152e2a0a 100644 --- a/drivers/gpu/drm/radeon/rv730_dpm.c +++ b/drivers/gpu/drm/radeon/rv730_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "rv730d.h" #include "r600_dpm.h" diff --git a/drivers/gpu/drm/radeon/rv740_dpm.c b/drivers/gpu/drm/radeon/rv740_dpm.c index 4b850824fe06c9..afd597ec508586 100644 --- a/drivers/gpu/drm/radeon/rv740_dpm.c +++ b/drivers/gpu/drm/radeon/rv740_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "rv740d.h" #include "r600_dpm.h" diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c index a010decf59af44..cb2a7ec4e2176f 100644 --- a/drivers/gpu/drm/radeon/rv770_dpm.c +++ b/drivers/gpu/drm/radeon/rv770_dpm.c @@ -22,7 +22,7 @@ * Authors: Alex Deucher */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "rv770d.h" diff --git a/drivers/gpu/drm/radeon/rv770_smc.c b/drivers/gpu/drm/radeon/rv770_smc.c index b2a224407365da..2b7ddee3984ccf 100644 --- a/drivers/gpu/drm/radeon/rv770_smc.c +++ b/drivers/gpu/drm/radeon/rv770_smc.c @@ -23,7 +23,7 @@ */ #include -#include "drmP.h" +#include #include "radeon.h" #include "rv770d.h" #include "rv770_dpm.h" diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index c7af9fdd20c729..ee3e74266a1332 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "sid.h" diff --git a/drivers/gpu/drm/radeon/si_smc.c b/drivers/gpu/drm/radeon/si_smc.c index e5bb92f1677529..51155abda8d8ef 100644 --- a/drivers/gpu/drm/radeon/si_smc.c +++ b/drivers/gpu/drm/radeon/si_smc.c @@ -23,7 +23,7 @@ */ #include -#include "drmP.h" +#include #include "radeon.h" #include "sid.h" #include "ppsmc.h" diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index f0d5c1724f55cf..fd4804829e46a8 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "sumod.h" diff --git a/drivers/gpu/drm/radeon/sumo_smc.c b/drivers/gpu/drm/radeon/sumo_smc.c index fb081d2ae37477..cc051be4236228 100644 --- a/drivers/gpu/drm/radeon/sumo_smc.c +++ b/drivers/gpu/drm/radeon/sumo_smc.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "sumod.h" #include "sumo_dpm.h" diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 6730367ac2289d..2ef7c4e5e49508 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "radeon_asic.h" #include "trinityd.h" diff --git a/drivers/gpu/drm/radeon/trinity_smc.c b/drivers/gpu/drm/radeon/trinity_smc.c index 99dd0455334d1a..0310e36e3159ca 100644 --- a/drivers/gpu/drm/radeon/trinity_smc.c +++ b/drivers/gpu/drm/radeon/trinity_smc.c @@ -21,7 +21,7 @@ * */ -#include "drmP.h" +#include #include "radeon.h" #include "trinityd.h" #include "trinity_dpm.h" diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index d8fa7a9c9240bd..9606121fa185aa 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -104,26 +104,18 @@ static void analogix_dp_psr_work(struct work_struct *work) { struct rockchip_dp_device *dp = container_of(work, typeof(*dp), psr_work); - struct drm_crtc *crtc = dp->encoder.crtc; - int psr_state = dp->psr_state; - int vact_end; int ret; unsigned long flags; - if (!crtc) - return; - - vact_end = crtc->mode.vtotal - crtc->mode.vsync_start + crtc->mode.vdisplay; - - ret = rockchip_drm_wait_line_flag(dp->encoder.crtc, vact_end, - PSR_WAIT_LINE_FLAG_TIMEOUT_MS); + ret = rockchip_drm_wait_vact_end(dp->encoder.crtc, + PSR_WAIT_LINE_FLAG_TIMEOUT_MS); if (ret) { dev_err(dp->dev, "line flag interrupt did not arrive\n"); return; } spin_lock_irqsave(&dp->psr_lock, flags); - if (psr_state == EDP_VSC_PSR_STATE_ACTIVE) + if (dp->psr_state == EDP_VSC_PSR_STATE_ACTIVE) analogix_dp_enable_psr(dp->dev); else analogix_dp_disable_psr(dp->dev); @@ -245,8 +237,6 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder, struct drm_connector_state *conn_state) { struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state); - struct rockchip_dp_device *dp = to_dp(encoder); - int ret; /* * The hardware IC designed that VOP must output the RGB10 video @@ -258,16 +248,6 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder, s->output_mode = ROCKCHIP_OUT_MODE_AAAA; s->output_type = DRM_MODE_CONNECTOR_eDP; - if (dp->data->chip_type == RK3399_EDP) { - /* - * For RK3399, VOP Lit must code the out mode to RGB888, - * VOP Big must code the out mode to RGB10. - */ - ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, - encoder); - if (ret > 0) - s->output_mode = ROCKCHIP_OUT_MODE_P888; - } return 0; } diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index a2169dd3d26b91..14fa1f8351e8df 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -615,7 +615,6 @@ static void cdn_dp_encoder_enable(struct drm_encoder *encoder) { struct cdn_dp_device *dp = encoder_to_dp(encoder); int ret, val; - struct rockchip_crtc_state *state; ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder); if (ret < 0) { @@ -625,14 +624,10 @@ static void cdn_dp_encoder_enable(struct drm_encoder *encoder) DRM_DEV_DEBUG_KMS(dp->dev, "vop %s output to cdn-dp\n", (ret) ? "LIT" : "BIG"); - state = to_rockchip_crtc_state(encoder->crtc->state); - if (ret) { + if (ret) val = DP_SEL_VOP_LIT | (DP_SEL_VOP_LIT << 16); - state->output_mode = ROCKCHIP_OUT_MODE_P888; - } else { + else val = DP_SEL_VOP_LIT << 16; - state->output_mode = ROCKCHIP_OUT_MODE_AAAA; - } ret = cdn_dp_grf_write(dp, GRF_SOC_CON9, val); if (ret) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index a48fcce3f5f65e..c7e96b82cf6397 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -45,13 +45,13 @@ struct rockchip_crtc_state { * * @crtc: array of enabled CRTCs, used to map from "pipe" to drm_crtc. * @num_pipe: number of pipes for this device. + * @mm_lock: protect drm_mm on multi-threads. */ struct rockchip_drm_private { struct drm_fb_helper fbdev_helper; struct drm_gem_object *fbdev_bo; struct drm_atomic_state *state; struct iommu_domain *domain; - /* protect drm_mm on multi-threads */ struct mutex mm_lock; struct drm_mm mm; struct list_head psr_list; @@ -62,8 +62,7 @@ int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, struct device *dev); void rockchip_drm_dma_detach_device(struct drm_device *drm_dev, struct device *dev); -int rockchip_drm_wait_line_flag(struct drm_crtc *crtc, unsigned int line_num, - unsigned int mstimeout); +int rockchip_drm_wait_vact_end(struct drm_crtc *crtc, unsigned int mstimeout); extern struct platform_driver cdn_dp_driver; extern struct platform_driver dw_hdmi_rockchip_pltfm_driver; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index df9e57064f1983..b74ac717e56a50 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -29,12 +29,11 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) ssize_t ret; mutex_lock(&private->mm_lock); - ret = drm_mm_insert_node_generic(&private->mm, &rk_obj->mm, rk_obj->base.size, PAGE_SIZE, 0, 0); - mutex_unlock(&private->mm_lock); + if (ret < 0) { DRM_ERROR("out of I/O virtual memory: %zd\n", ret); return ret; @@ -56,7 +55,9 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) return 0; err_remove_node: + mutex_lock(&private->mm_lock); drm_mm_remove_node(&rk_obj->mm); + mutex_unlock(&private->mm_lock); return ret; } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 3f7a82d1e0956e..c83f481a21c88b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -468,7 +468,7 @@ static bool vop_line_flag_irq_is_enabled(struct vop *vop) return !!line_flag_irq; } -static void vop_line_flag_irq_enable(struct vop *vop, int line_num) +static void vop_line_flag_irq_enable(struct vop *vop) { unsigned long flags; @@ -477,7 +477,6 @@ static void vop_line_flag_irq_enable(struct vop *vop, int line_num) spin_lock_irqsave(&vop->irq_lock, flags); - VOP_CTRL_SET(vop, line_flag_num[0], line_num); VOP_INTR_SET_TYPE(vop, clear, LINE_FLAG_INTR, 1); VOP_INTR_SET_TYPE(vop, enable, LINE_FLAG_INTR, 1); @@ -875,6 +874,7 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc, static void vop_crtc_enable(struct drm_crtc *crtc) { struct vop *vop = to_vop(crtc); + const struct vop_data *vop_data = vop->data; struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc->state); struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode; u16 hsync_len = adjusted_mode->hsync_end - adjusted_mode->hsync_start; @@ -967,6 +967,13 @@ static void vop_crtc_enable(struct drm_crtc *crtc) DRM_DEV_ERROR(vop->dev, "unsupported connector_type [%d]\n", s->output_type); } + + /* + * if vop is not support RGB10 output, need force RGB10 to RGB888. + */ + if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && + !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10)) + s->output_mode = ROCKCHIP_OUT_MODE_P888; VOP_CTRL_SET(vop, out_mode, s->output_mode); VOP_CTRL_SET(vop, htotal_pw, (htotal << 16) | hsync_len); @@ -981,6 +988,8 @@ static void vop_crtc_enable(struct drm_crtc *crtc) VOP_CTRL_SET(vop, vact_st_end, val); VOP_CTRL_SET(vop, vpost_st_end, val); + VOP_CTRL_SET(vop, line_flag_num[0], vact_end); + clk_set_rate(vop->dclk, adjusted_mode->clock * 1000); VOP_CTRL_SET(vop, standby, 0); @@ -1507,19 +1516,16 @@ static void vop_win_init(struct vop *vop) } /** - * rockchip_drm_wait_line_flag - acqiure the give line flag event + * rockchip_drm_wait_vact_end * @crtc: CRTC to enable line flag - * @line_num: interested line number * @mstimeout: millisecond for timeout * - * Driver would hold here until the interested line flag interrupt have - * happened or timeout to wait. + * Wait for vact_end line flag irq or timeout. * * Returns: * Zero on success, negative errno on failure. */ -int rockchip_drm_wait_line_flag(struct drm_crtc *crtc, unsigned int line_num, - unsigned int mstimeout) +int rockchip_drm_wait_vact_end(struct drm_crtc *crtc, unsigned int mstimeout) { struct vop *vop = to_vop(crtc); unsigned long jiffies_left; @@ -1527,14 +1533,14 @@ int rockchip_drm_wait_line_flag(struct drm_crtc *crtc, unsigned int line_num, if (!crtc || !vop->is_enabled) return -ENODEV; - if (line_num > crtc->mode.vtotal || mstimeout <= 0) + if (mstimeout <= 0) return -EINVAL; if (vop_line_flag_irq_is_enabled(vop)) return -EBUSY; reinit_completion(&vop->line_flag_completion); - vop_line_flag_irq_enable(vop, line_num); + vop_line_flag_irq_enable(vop); jiffies_left = wait_for_completion_timeout(&vop->line_flag_completion, msecs_to_jiffies(mstimeout)); @@ -1547,7 +1553,7 @@ int rockchip_drm_wait_line_flag(struct drm_crtc *crtc, unsigned int line_num, return 0; } -EXPORT_SYMBOL(rockchip_drm_wait_line_flag); +EXPORT_SYMBOL(rockchip_drm_wait_vact_end); static int vop_bind(struct device *dev, struct device *master, void *data) { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 5a4faa85dbd29d..9979fd0c22821d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -142,6 +142,9 @@ struct vop_data { const struct vop_intr *intr; const struct vop_win_data *win; unsigned int win_size; + +#define VOP_FEATURE_OUTPUT_RGB10 BIT(0) + u64 feature; }; /* interrupt define */ diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c index 0da44442aab097..bafd698a28b1b4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c @@ -275,6 +275,7 @@ static const struct vop_intr rk3288_vop_intr = { static const struct vop_data rk3288_vop = { .init_table = rk3288_init_reg_table, .table_size = ARRAY_SIZE(rk3288_init_reg_table), + .feature = VOP_FEATURE_OUTPUT_RGB10, .intr = &rk3288_vop_intr, .ctrl = &rk3288_ctrl_data, .win = rk3288_vop_win_data, @@ -343,6 +344,7 @@ static const struct vop_reg_data rk3399_init_reg_table[] = { static const struct vop_data rk3399_vop_big = { .init_table = rk3399_init_reg_table, .table_size = ARRAY_SIZE(rk3399_init_reg_table), + .feature = VOP_FEATURE_OUTPUT_RGB10, .intr = &rk3399_vop_intr, .ctrl = &rk3399_ctrl_data, /* diff --git a/drivers/gpu/drm/savage/Makefile b/drivers/gpu/drm/savage/Makefile index d8f84ac7bb2606..cfd436bb28e4d7 100644 --- a/drivers/gpu/drm/savage/Makefile +++ b/drivers/gpu/drm/savage/Makefile @@ -2,7 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y = -Iinclude/drm savage-y := savage_drv.o savage_bci.o savage_state.o obj-$(CONFIG_DRM_SAVAGE)+= savage.o diff --git a/drivers/gpu/drm/selftests/test-drm_mm.c b/drivers/gpu/drm/selftests/test-drm_mm.c index fa356f5dae27d3..dfdd858eda0a06 100644 --- a/drivers/gpu/drm/selftests/test-drm_mm.c +++ b/drivers/gpu/drm/selftests/test-drm_mm.c @@ -514,6 +514,8 @@ static int igt_reserve(void *ignored) ret = __igt_reserve(count, size + 1); if (ret) return ret; + + cond_resched(); } return 0; @@ -712,6 +714,10 @@ static int igt_insert(void *ignored) return ret; ret = __igt_insert(count, size + 1, false); + if (ret) + return ret; + + cond_resched(); } return 0; @@ -741,6 +747,10 @@ static int igt_replace(void *ignored) return ret; ret = __igt_insert(count, size + 1, true); + if (ret) + return ret; + + cond_resched(); } return 0; @@ -1011,6 +1021,8 @@ static int igt_insert_range(void *ignored) ret = __igt_insert_range(count, size, max/4+1, 3*max/4-1); if (ret) return ret; + + cond_resched(); } return 0; @@ -1056,6 +1068,7 @@ static int igt_align(void *ignored) drm_mm_for_each_node_safe(node, next, &mm) drm_mm_remove_node(node); DRM_MM_BUG_ON(!drm_mm_clean(&mm)); + cond_resched(); } ret = 0; @@ -1097,6 +1110,8 @@ static int igt_align_pot(int max) align, bit); goto out; } + + cond_resched(); } ret = 0; @@ -1471,6 +1486,8 @@ static int igt_evict(void *ignored) goto out; } } + + cond_resched(); } ret = 0; @@ -1566,6 +1583,8 @@ static int igt_evict_range(void *ignored) goto out; } } + + cond_resched(); } ret = 0; @@ -1683,6 +1702,7 @@ static int igt_topdown(void *ignored) drm_mm_for_each_node_safe(node, next, &mm) drm_mm_remove_node(node); DRM_MM_BUG_ON(!drm_mm_clean(&mm)); + cond_resched(); } ret = 0; @@ -1783,6 +1803,7 @@ static int igt_bottomup(void *ignored) drm_mm_for_each_node_safe(node, next, &mm) drm_mm_remove_node(node); DRM_MM_BUG_ON(!drm_mm_clean(&mm)); + cond_resched(); } ret = 0; @@ -1970,6 +1991,8 @@ static int igt_color(void *ignored) drm_mm_remove_node(node); kfree(node); } + + cond_resched(); } ret = 0; @@ -2047,6 +2070,7 @@ static int evict_color(struct drm_mm *mm, } } + cond_resched(); return 0; } @@ -2132,6 +2156,8 @@ static int igt_color_evict(void *ignored) goto out; } } + + cond_resched(); } ret = 0; @@ -2231,6 +2257,8 @@ static int igt_color_evict_range(void *ignored) goto out; } } + + cond_resched(); } ret = 0; diff --git a/drivers/gpu/drm/sis/Makefile b/drivers/gpu/drm/sis/Makefile index 441c061c3ad02e..7bf4c130c8fd90 100644 --- a/drivers/gpu/drm/sis/Makefile +++ b/drivers/gpu/drm/sis/Makefile @@ -2,7 +2,6 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -ccflags-y = -Iinclude/drm sis-y := sis_drv.o sis_mm.o obj-$(CONFIG_DRM_SIS) += sis.o diff --git a/drivers/gpu/drm/sti/sti_compositor.c b/drivers/gpu/drm/sti/sti_compositor.c index 11d4e885893abb..6e4bf68262db1b 100644 --- a/drivers/gpu/drm/sti/sti_compositor.c +++ b/drivers/gpu/drm/sti/sti_compositor.c @@ -129,7 +129,7 @@ static int sti_compositor_bind(struct device *dev, } break; default: - DRM_ERROR("Unknown subdev compoment type\n"); + DRM_ERROR("Unknown subdev component type\n"); return 1; } diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c index cca75bddb9ad1a..5b3a41f74f21b2 100644 --- a/drivers/gpu/drm/sti/sti_cursor.c +++ b/drivers/gpu/drm/sti/sti_cursor.c @@ -33,7 +33,7 @@ #define STI_CURS_MAX_SIZE 128 /* - * pixmap dma buffer stucture + * pixmap dma buffer structure * * @paddr: physical address * @size: buffer size @@ -121,8 +121,7 @@ static int cursor_dbg_show(struct seq_file *s, void *data) cursor_dbg_cml(s, cursor, readl(cursor->regs + CUR_CML)); DBGFS_DUMP(CUR_AWS); DBGFS_DUMP(CUR_AWE); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index bb23318a44b714..24ebc6b2f34d1d 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -186,8 +186,7 @@ static int dvo_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP(DVO_LUT_PROG_MID); DBGFS_DUMP(DVO_LUT_PROG_HIGH); dvo_dbg_awg_microcode(s, dvo->regs + DVO_DIGSYNC_INSTR_I); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index 88f16cdf6a4bce..5ee0503945c8bf 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -149,7 +149,7 @@ static void gdp_dbg_ctl(struct seq_file *s, int val) seq_puts(s, "\tColor:"); for (i = 0; i < ARRAY_SIZE(gdp_format_to_str); i++) { if (gdp_format_to_str[i].format == (val & 0x1F)) { - seq_printf(s, gdp_format_to_str[i].name); + seq_puts(s, gdp_format_to_str[i].name); break; } } @@ -266,8 +266,7 @@ static void gdp_node_dump_node(struct seq_file *s, struct sti_gdp_node *node) seq_printf(s, "\n\tKEY2 0x%08X", node->gam_gdp_key2); seq_printf(s, "\n\tPPT 0x%08X", node->gam_gdp_ppt); gdp_dbg_ppt(s, node->gam_gdp_ppt); - seq_printf(s, "\n\tCML 0x%08X", node->gam_gdp_cml); - seq_puts(s, "\n"); + seq_printf(s, "\n\tCML 0x%08X\n", node->gam_gdp_cml); } static int gdp_node_dbg_show(struct seq_file *s, void *arg) diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 0c0a75bc8bc3f6..d6ed909d9d75ff 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -320,8 +320,7 @@ static void hda_dbg_awg_microcode(struct seq_file *s, void __iomem *reg) { unsigned int i; - seq_puts(s, "\n\n"); - seq_puts(s, " HDA AWG microcode:"); + seq_puts(s, "\n\n HDA AWG microcode:"); for (i = 0; i < AWG_MAX_INST; i++) { if (i % 8 == 0) seq_printf(s, "\n %04X:", i); @@ -333,8 +332,7 @@ static void hda_dbg_video_dacs_ctrl(struct seq_file *s, void __iomem *reg) { u32 val = readl(reg); - seq_puts(s, "\n"); - seq_printf(s, "\n %-25s 0x%08X", "VIDEO_DACS_CONTROL", val); + seq_printf(s, "\n\n %-25s 0x%08X", "VIDEO_DACS_CONTROL", val); seq_puts(s, "\tHD DACs "); seq_puts(s, val & DAC_CFG_HD_HZUVW_OFF_MASK ? "disabled" : "enabled"); } @@ -356,8 +354,7 @@ static int hda_dbg_show(struct seq_file *s, void *data) hda_dbg_awg_microcode(s, hda->regs + HDA_SYNC_AWGI); if (hda->video_dacs_ctrl) hda_dbg_video_dacs_ctrl(s, hda->video_dacs_ctrl); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 243905b6ae5903..a59c95a8081b7a 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -592,7 +592,7 @@ static void hdmi_dbg_cfg(struct seq_file *s, int val) { int tmp; - seq_puts(s, "\t"); + seq_putc(s, '\t'); tmp = val & HDMI_CFG_HDMI_NOT_DVI; DBGFS_PRINT_STR("mode:", tmp ? "HDMI" : "DVI"); seq_puts(s, "\t\t\t\t\t"); @@ -616,7 +616,7 @@ static void hdmi_dbg_sta(struct seq_file *s, int val) { int tmp; - seq_puts(s, "\t"); + seq_putc(s, '\t'); tmp = (val & HDMI_STA_DLL_LCK); DBGFS_PRINT_STR("pll:", tmp ? "locked" : "not locked"); seq_puts(s, "\t\t\t\t\t"); @@ -632,7 +632,7 @@ static void hdmi_dbg_sw_di_cfg(struct seq_file *s, int val) "once every field", "once every frame"}; - seq_puts(s, "\t"); + seq_putc(s, '\t'); tmp = (val & HDMI_IFRAME_CFG_DI_N(HDMI_IFRAME_MASK, 1)); DBGFS_PRINT_STR("Data island 1:", en_di[tmp]); seq_puts(s, "\t\t\t\t\t"); @@ -664,16 +664,16 @@ static int hdmi_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP("\n", HDMI_STA); hdmi_dbg_sta(s, hdmi_read(hdmi, HDMI_STA)); DBGFS_DUMP("", HDMI_ACTIVE_VID_XMIN); - seq_puts(s, "\t"); + seq_putc(s, '\t'); DBGFS_PRINT_INT("Xmin:", hdmi_read(hdmi, HDMI_ACTIVE_VID_XMIN)); DBGFS_DUMP("", HDMI_ACTIVE_VID_XMAX); - seq_puts(s, "\t"); + seq_putc(s, '\t'); DBGFS_PRINT_INT("Xmax:", hdmi_read(hdmi, HDMI_ACTIVE_VID_XMAX)); DBGFS_DUMP("", HDMI_ACTIVE_VID_YMIN); - seq_puts(s, "\t"); + seq_putc(s, '\t'); DBGFS_PRINT_INT("Ymin:", hdmi_read(hdmi, HDMI_ACTIVE_VID_YMIN)); DBGFS_DUMP("", HDMI_ACTIVE_VID_YMAX); - seq_puts(s, "\t"); + seq_putc(s, '\t'); DBGFS_PRINT_INT("Ymax:", hdmi_read(hdmi, HDMI_ACTIVE_VID_YMAX)); DBGFS_DUMP("", HDMI_SW_DI_CFG); hdmi_dbg_sw_di_cfg(s, hdmi_read(hdmi, HDMI_SW_DI_CFG)); @@ -692,8 +692,7 @@ static int hdmi_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD4, HDMI_IFRAME_SLOT_AVI); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD5, HDMI_IFRAME_SLOT_AVI); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD6, HDMI_IFRAME_SLOT_AVI); - seq_puts(s, "\n"); - seq_printf(s, "\n AUDIO Infoframe (Data Island slot N=%d):", + seq_printf(s, "\n\n AUDIO Infoframe (Data Island slot N=%d):", HDMI_IFRAME_SLOT_AUDIO); DBGFS_DUMP_DI(HDMI_SW_DI_N_HEAD_WORD, HDMI_IFRAME_SLOT_AUDIO); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD0, HDMI_IFRAME_SLOT_AUDIO); @@ -703,8 +702,7 @@ static int hdmi_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD4, HDMI_IFRAME_SLOT_AUDIO); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD5, HDMI_IFRAME_SLOT_AUDIO); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD6, HDMI_IFRAME_SLOT_AUDIO); - seq_puts(s, "\n"); - seq_printf(s, "\n VENDOR SPECIFIC Infoframe (Data Island slot N=%d):", + seq_printf(s, "\n\n VENDOR SPECIFIC Infoframe (Data Island slot N=%d):", HDMI_IFRAME_SLOT_VENDOR); DBGFS_DUMP_DI(HDMI_SW_DI_N_HEAD_WORD, HDMI_IFRAME_SLOT_VENDOR); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD0, HDMI_IFRAME_SLOT_VENDOR); @@ -714,8 +712,7 @@ static int hdmi_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD4, HDMI_IFRAME_SLOT_VENDOR); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD5, HDMI_IFRAME_SLOT_VENDOR); DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD6, HDMI_IFRAME_SLOT_VENDOR); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 66f843148ef7f5..a1c161f7780442 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -625,8 +625,7 @@ static int hqvdp_dbg_show(struct seq_file *s, void *data) hqvdp_dbg_dump_cmd(s, (struct sti_hqvdp_cmd *)virt); } - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } @@ -1357,12 +1356,12 @@ static int sti_hqvdp_probe(struct platform_device *pdev) /* Get Memory resources */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res == NULL) { + if (!res) { DRM_ERROR("Get memory resource failed\n"); return -ENXIO; } hqvdp->regs = devm_ioremap(dev, res->start, resource_size(res)); - if (hqvdp->regs == NULL) { + if (!hqvdp->regs) { DRM_ERROR("Register mapping failed\n"); return -ENXIO; } diff --git a/drivers/gpu/drm/sti/sti_mixer.c b/drivers/gpu/drm/sti/sti_mixer.c index 4ddc58f7fe2e98..2bd1d46fe1cd32 100644 --- a/drivers/gpu/drm/sti/sti_mixer.c +++ b/drivers/gpu/drm/sti/sti_mixer.c @@ -162,8 +162,7 @@ static int mixer_dbg_show(struct seq_file *s, void *arg) DBGFS_DUMP(GAM_MIXER_MBP); DBGFS_DUMP(GAM_MIXER_MX0); mixer_dbg_mxn(s, mixer->regs + GAM_MIXER_MX0); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c index 8b8ea717c121f0..8959fcc743a8ed 100644 --- a/drivers/gpu/drm/sti/sti_tvout.c +++ b/drivers/gpu/drm/sti/sti_tvout.c @@ -459,7 +459,7 @@ static void tvout_dbg_vip(struct seq_file *s, int val) "Aux (color matrix by-passed)", "", "", "", "", "", "Force value"}; - seq_puts(s, "\t"); + seq_putc(s, '\t'); mask = TVO_VIP_REORDER_MASK << TVO_VIP_REORDER_R_SHIFT; r = (val & mask) >> TVO_VIP_REORDER_R_SHIFT; mask = TVO_VIP_REORDER_MASK << TVO_VIP_REORDER_G_SHIFT; @@ -558,8 +558,7 @@ static int tvout_dbg_show(struct seq_file *s, void *data) DBGFS_DUMP(TVO_CSC_AUX_M6); DBGFS_DUMP(TVO_CSC_AUX_M7); DBGFS_DUMP(TVO_AUX_IN_VID_FORMAT); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } @@ -847,7 +846,7 @@ static int sti_tvout_probe(struct platform_device *pdev) tvout->dev = dev; - /* get Memory ressources */ + /* get memory resources */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tvout-reg"); if (!res) { DRM_ERROR("Invalid glue resource\n"); diff --git a/drivers/gpu/drm/sti/sti_vid.c b/drivers/gpu/drm/sti/sti_vid.c index 2ad59892b57e25..577a3341d3c13f 100644 --- a/drivers/gpu/drm/sti/sti_vid.c +++ b/drivers/gpu/drm/sti/sti_vid.c @@ -61,7 +61,7 @@ static void vid_dbg_ctl(struct seq_file *s, int val) { val = val >> 30; - seq_puts(s, "\t"); + seq_putc(s, '\t'); if (!(val & 1)) seq_puts(s, "NOT "); @@ -114,8 +114,7 @@ static int vid_dbg_show(struct seq_file *s, void *arg) DBGFS_DUMP(VID_BC); DBGFS_DUMP(VID_TINT); DBGFS_DUMP(VID_CSAT); - seq_puts(s, "\n"); - + seq_putc(s, '\n'); return 0; } diff --git a/drivers/gpu/drm/stm/Kconfig b/drivers/gpu/drm/stm/Kconfig new file mode 100644 index 00000000000000..2c4817fb089024 --- /dev/null +++ b/drivers/gpu/drm/stm/Kconfig @@ -0,0 +1,16 @@ +config DRM_STM + tristate "DRM Support for STMicroelectronics SoC Series" + depends on DRM && (ARCH_STM32 || ARCH_MULTIPLATFORM) + select DRM_KMS_HELPER + select DRM_GEM_CMA_HELPER + select DRM_KMS_CMA_HELPER + select DRM_PANEL + select VIDEOMODE_HELPERS + select FB_PROVIDE_GET_FB_UNMAPPED_AREA + default y + + help + Enable support for the on-chip display controller on + STMicroelectronics STM32 MCUs. + To compile this driver as a module, choose M here: the module + will be called stm-drm. diff --git a/drivers/gpu/drm/stm/Makefile b/drivers/gpu/drm/stm/Makefile new file mode 100644 index 00000000000000..a09ecf45021845 --- /dev/null +++ b/drivers/gpu/drm/stm/Makefile @@ -0,0 +1,5 @@ +stm-drm-y := \ + drv.o \ + ltdc.o + +obj-$(CONFIG_DRM_STM) += stm-drm.o diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c new file mode 100644 index 00000000000000..83ab48f1fd0087 --- /dev/null +++ b/drivers/gpu/drm/stm/drv.c @@ -0,0 +1,221 @@ +/* + * Copyright (C) STMicroelectronics SA 2017 + * + * Authors: Philippe Cornu + * Yannick Fertre + * Fabien Dessenne + * Mickael Reulier + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#include +#include + +#include +#include +#include +#include +#include + +#include "ltdc.h" + +#define DRIVER_NAME "stm" +#define DRIVER_DESC "STMicroelectronics SoC DRM" +#define DRIVER_DATE "20170330" +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 0 +#define DRIVER_PATCH_LEVEL 0 + +#define STM_MAX_FB_WIDTH 2048 +#define STM_MAX_FB_HEIGHT 2048 /* same as width to handle orientation */ + +static void drv_output_poll_changed(struct drm_device *ddev) +{ + struct ltdc_device *ldev = ddev->dev_private; + + drm_fbdev_cma_hotplug_event(ldev->fbdev); +} + +static const struct drm_mode_config_funcs drv_mode_config_funcs = { + .fb_create = drm_fb_cma_create, + .output_poll_changed = drv_output_poll_changed, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static void drv_lastclose(struct drm_device *ddev) +{ + struct ltdc_device *ldev = ddev->dev_private; + + DRM_DEBUG("%s\n", __func__); + + drm_fbdev_cma_restore_mode(ldev->fbdev); +} + +DEFINE_DRM_GEM_CMA_FOPS(drv_driver_fops); + +static struct drm_driver drv_driver = { + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME | + DRIVER_ATOMIC, + .lastclose = drv_lastclose, + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + .patchlevel = DRIVER_PATCH_LEVEL, + .fops = &drv_driver_fops, + .dumb_create = drm_gem_cma_dumb_create, + .dumb_map_offset = drm_gem_cma_dumb_map_offset, + .dumb_destroy = drm_gem_dumb_destroy, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_free_object_unlocked = drm_gem_cma_free_object, + .gem_vm_ops = &drm_gem_cma_vm_ops, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_get_sg_table = drm_gem_cma_prime_get_sg_table, + .gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table, + .gem_prime_vmap = drm_gem_cma_prime_vmap, + .gem_prime_vunmap = drm_gem_cma_prime_vunmap, + .gem_prime_mmap = drm_gem_cma_prime_mmap, + .enable_vblank = ltdc_crtc_enable_vblank, + .disable_vblank = ltdc_crtc_disable_vblank, +}; + +static int drv_load(struct drm_device *ddev) +{ + struct platform_device *pdev = to_platform_device(ddev->dev); + struct drm_fbdev_cma *fbdev; + struct ltdc_device *ldev; + int ret; + + DRM_DEBUG("%s\n", __func__); + + ldev = devm_kzalloc(ddev->dev, sizeof(*ldev), GFP_KERNEL); + if (!ldev) + return -ENOMEM; + + ddev->dev_private = (void *)ldev; + + drm_mode_config_init(ddev); + + /* + * set max width and height as default value. + * this value would be used to check framebuffer size limitation + * at drm_mode_addfb(). + */ + ddev->mode_config.min_width = 0; + ddev->mode_config.min_height = 0; + ddev->mode_config.max_width = STM_MAX_FB_WIDTH; + ddev->mode_config.max_height = STM_MAX_FB_HEIGHT; + ddev->mode_config.funcs = &drv_mode_config_funcs; + + ret = ltdc_load(ddev); + if (ret) + goto err; + + drm_mode_config_reset(ddev); + drm_kms_helper_poll_init(ddev); + + if (ddev->mode_config.num_connector) { + ldev = ddev->dev_private; + fbdev = drm_fbdev_cma_init(ddev, 16, + ddev->mode_config.num_connector); + if (IS_ERR(fbdev)) { + DRM_DEBUG("Warning: fails to create fbdev\n"); + fbdev = NULL; + } + ldev->fbdev = fbdev; + } + + platform_set_drvdata(pdev, ddev); + + return 0; +err: + drm_mode_config_cleanup(ddev); + return ret; +} + +static void drv_unload(struct drm_device *ddev) +{ + struct ltdc_device *ldev = ddev->dev_private; + + DRM_DEBUG("%s\n", __func__); + + if (ldev->fbdev) { + drm_fbdev_cma_fini(ldev->fbdev); + ldev->fbdev = NULL; + } + drm_kms_helper_poll_fini(ddev); + ltdc_unload(ddev); + drm_mode_config_cleanup(ddev); +} + +static int stm_drm_platform_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct drm_device *ddev; + int ret; + + DRM_DEBUG("%s\n", __func__); + + dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + + ddev = drm_dev_alloc(&drv_driver, dev); + if (IS_ERR(ddev)) + return PTR_ERR(ddev); + + ret = drv_load(ddev); + if (ret) + goto err_unref; + + ret = drm_dev_register(ddev, 0); + if (ret) + goto err_unref; + + return 0; + +err_unref: + drm_dev_unref(ddev); + + return ret; +} + +static int stm_drm_platform_remove(struct platform_device *pdev) +{ + struct drm_device *ddev = platform_get_drvdata(pdev); + + DRM_DEBUG("%s\n", __func__); + + drm_dev_unregister(ddev); + drv_unload(ddev); + drm_dev_unref(ddev); + + return 0; +} + +static const struct of_device_id drv_dt_ids[] = { + { .compatible = "st,stm32-ltdc"}, + { /* end node */ }, +}; +MODULE_DEVICE_TABLE(of, drv_dt_ids); + +static struct platform_driver stm_drm_platform_driver = { + .probe = stm_drm_platform_probe, + .remove = stm_drm_platform_remove, + .driver = { + .name = DRIVER_NAME, + .of_match_table = drv_dt_ids, + }, +}; + +module_platform_driver(stm_drm_platform_driver); + +MODULE_AUTHOR("Philippe Cornu "); +MODULE_AUTHOR("Yannick Fertre "); +MODULE_AUTHOR("Fabien Dessenne "); +MODULE_AUTHOR("Mickael Reulier "); +MODULE_DESCRIPTION("STMicroelectronics ST DRM LTDC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c new file mode 100644 index 00000000000000..700cc0800e512d --- /dev/null +++ b/drivers/gpu/drm/stm/ltdc.c @@ -0,0 +1,1160 @@ +/* + * Copyright (C) STMicroelectronics SA 2017 + * + * Authors: Philippe Cornu + * Yannick Fertre + * Fabien Dessenne + * Mickael Reulier + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include