diff --git a/.github/workflows/cmake-linux.yml b/.github/workflows/cmake-linux.yml index 7864a04a..5acc5186 100644 --- a/.github/workflows/cmake-linux.yml +++ b/.github/workflows/cmake-linux.yml @@ -30,7 +30,7 @@ jobs: - uses: actions/checkout@v4 - name: Install build tools - run: apk add --no-cache --update clang cmake lld ninja lowdown + run: apk add --no-cache --update clang cmake lld ninja lowdown linux-headers - name: Configure run: CXX=clang++ LDFLAGS=-fuse-ld=lld cmake -B build -G Ninja -DBTOP_STATIC=ON diff --git a/.github/workflows/continuous-build-gpu.yml b/.github/workflows/continuous-build-gpu.yml index 34c3e117..1dca7662 100644 --- a/.github/workflows/continuous-build-gpu.yml +++ b/.github/workflows/continuous-build-gpu.yml @@ -40,7 +40,7 @@ jobs: - uses: actions/checkout@v4 - name: Install build tools - run: apk add --no-cache --update gcc g++ make + run: apk add --no-cache --update gcc g++ make linux-headers - name: Compile run: make CXX=g++ GPU_SUPPORT=true diff --git a/CMakeLists.txt b/CMakeLists.txt index 0ed93b2a..f3db9b6d 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -13,7 +13,7 @@ endif() project("btop" DESCRIPTION "A monitor of resources" HOMEPAGE_URL "https://github.com/aristocratos/btop" - LANGUAGES CXX + LANGUAGES CXX C ) include(CheckCXXCompilerFlag) @@ -70,6 +70,14 @@ elseif(CMAKE_SYSTEM_NAME STREQUAL "NetBSD") target_sources(btop PRIVATE src/netbsd/btop_collect.cpp) elseif(LINUX) target_sources(btop PRIVATE src/linux/btop_collect.cpp) + if(BTOP_GPU) + target_sources(btop PRIVATE + src/linux/intel_gpu_top/intel_gpu_top.c + src/linux/intel_gpu_top/igt_perf.c + src/linux/intel_gpu_top/intel_device_info.c + src/linux/intel_gpu_top/intel_name_lookup_shim.c + ) + endif() else() message(FATAL_ERROR "${CMAKE_SYSTEM_NAME} is not supported") endif() diff --git a/Makefile b/Makefile index 7fdec40d..0f8aef61 100644 --- a/Makefile +++ b/Makefile @@ -40,6 +40,7 @@ override PLATFORM_LC := $(shell echo $(PLATFORM) | tr '[:upper:]' '[:lower:]') ifeq ($(PLATFORM_LC)$(ARCH),linuxx86_64) ifneq ($(STATIC),true) GPU_SUPPORT := true + INTEL_GPU_SUPPORT := true endif endif ifneq ($(GPU_SUPPORT),true) @@ -208,13 +209,22 @@ endif SOURCES := $(sort $(shell find $(SRCDIR) -maxdepth 1 -type f -name *.$(SRCEXT))) -SOURCES += $(sort $(shell find $(SRCDIR)/$(PLATFORM_DIR) -type f -name *.$(SRCEXT))) - -#? Setup percentage progress -SOURCE_COUNT := $(words $(SOURCES)) +SOURCES += $(sort $(shell find $(SRCDIR)/$(PLATFORM_DIR) -maxdepth 1 -type f -name *.$(SRCEXT))) OBJECTS := $(patsubst $(SRCDIR)/%,$(BUILDDIR)/%,$(SOURCES:.$(SRCEXT)=.$(OBJEXT))) +ifeq ($(GPU_SUPPORT)$(INTEL_GPU_SUPPORT),truetrue) + IGT_OBJECTS := $(BUILDDIR)/igt_perf.c.o $(BUILDDIR)/intel_device_info.c.o $(BUILDDIR)/intel_name_lookup_shim.c.o $(BUILDDIR)/intel_gpu_top.c.o + OBJECTS += $(IGT_OBJECTS) + SHOW_CC_INFO = false + CC_VERSION := $(shell $(CC) -dumpfullversion -dumpversion || echo 0) +else + SHOW_CC_INFO = true +endif + +#? Setup percentage progress +SOURCE_COUNT := $(words $(OBJECTS)) + ifeq ($(shell find $(BUILDDIR) -type f -newermt "$(DATESTAMP)" -name *.o >/dev/null 2>&1; echo $$?),0) ifneq ($(wildcard $(BUILDDIR)/.*),) SKIPPED_SOURCES := $(foreach fname,$(SOURCES),$(shell find $(BUILDDIR) -type f -newer $(fname) -name *.o | grep "$(basename $(notdir $(fname))).o" 2>/dev/null)) @@ -248,7 +258,8 @@ info: @printf "\033[1;96mARCH \033[1;93m?| \033[0m$(ARCH)\n" @printf "\033[1;95mGPU_SUPPORT \033[1;94m:| \033[0m$(GPU_SUPPORT)\n" @printf "\033[1;93mCXX \033[1;93m?| \033[0m$(CXX) \033[1;93m(\033[97m$(CXX_VERSION)\033[93m)\n" - @printf "\033[1;94mTHREADS \033[1;94m:| \033[0m$(THREADS)\n" + @$(SHOW_CC_INFO) || printf "\033[1;93mCC \033[1;93m?| \033[0m$(CC) \033[1;93m(\033[97m$(CC_VERSION)\033[93m)\n" + @printf "\033[1;94mTHREADS \033[1;94m:| \033[0m$(THREADS)\n" gcc -dumpfullversion -dumpversion @printf "\033[1;92mREQFLAGS \033[1;91m!| \033[0m$(REQFLAGS)\n" @printf "\033[1;91mWARNFLAGS \033[1;94m:| \033[0m$(WARNFLAGS)\n" @printf "\033[1;94mOPTFLAGS \033[1;94m:| \033[0m$(OPTFLAGS)\n" @@ -409,5 +420,16 @@ $(BUILDDIR)/%.$(OBJEXT): $(SRCDIR)/%.$(SRCEXT) | rocm_smi directories config.h @$(CXX) $(CXXFLAGS) $(INC) -MMD -c -o $@ $< || exit 1 @printf "\033[1;92m$$($(PROGRESS))$(P)\033[10D\033[5C-> \033[1;37m$@ \033[100D\033[38C\033[1;93m(\033[1;97m$$(du -ah $@ | cut -f1)iB\033[1;93m) \033[92m(\033[97m$$($(DATE_CMD) -d @$$(expr $$($(DATE_CMD) +%s 2>/dev/null || echo "0") - $${TSTAMP} 2>/dev/null) -u +%Mm:%Ss 2>/dev/null | sed 's/^00m://' || echo '')\033[92m)\033[0m\n" +#? Compile intel_gpu_top C sources for Intel GPU support +.ONESHELL: +$(BUILDDIR)/%.c.o: $(SRCDIR)/$(PLATFORM_DIR)/intel_gpu_top/%.c | directories + @sleep 0.3 2>/dev/null || true + @TSTAMP=$$(date +%s 2>/dev/null || echo "0") + @$(QUIET) || printf "\033[1;97mCompiling $<\033[0m\n" + @$(VERBOSE) || printf "$(CC) $(INC) -c -o $@ $<\n" + @$(CC) $(INC) -w -c -o $@ $< || exit 1 + @printf "\033[1;92m$$($(PROGRESS))$(P)\033[10D\033[5C-> \033[1;37m$@ \033[100D\033[38C\033[1;93m(\033[1;97m$$(du -ah $@ | cut -f1)iB\033[1;93m) \033[92m(\033[97m$$($(DATE_CMD) -d @$$(expr $$($(DATE_CMD) +%s 2>/dev/null || echo "0") - $${TSTAMP} 2>/dev/null) -u +%Mm:%Ss 2>/dev/null | sed 's/^00m://' || echo '')\033[92m)\033[0m\n" + + #? Non-File Targets .PHONY: all config.h msg help pre diff --git a/src/linux/btop_collect.cpp b/src/linux/btop_collect.cpp index 0541357a..7ddedd47 100644 --- a/src/linux/btop_collect.cpp +++ b/src/linux/btop_collect.cpp @@ -47,6 +47,14 @@ tab-size = 4 #include "../btop_config.hpp" #include "../btop_tools.hpp" +#if defined(GPU_SUPPORT) + #define class class_ +extern "C" { + #include "./intel_gpu_top/intel_gpu_top.h" +} + #undef class +#endif + using std::clamp; using std::cmp_greater; using std::cmp_less; @@ -210,6 +218,19 @@ namespace Gpu { template bool collect(gpu_info* gpus_slice); uint32_t device_count = 0; } + + + //? Intel data collection + namespace Intel { + const char* device = "i915"; + struct engines *engines = nullptr; + + bool initialized = false; + bool init(); + bool shutdown(); + template bool collect(gpu_info* gpus_slice); + uint32_t device_count = 0; + } #endif } @@ -276,6 +297,7 @@ namespace Shared { #ifdef GPU_SUPPORT Gpu::Nvml::init(); Gpu::Rsmi::init(); + Gpu::Intel::init(); if (not Gpu::gpu_names.empty()) { for (auto const& [key, _] : Gpu::gpus[0].gpu_percent) Cpu::available_fields.push_back(key); @@ -1570,7 +1592,117 @@ namespace Gpu { } } - // TODO: Intel + namespace Intel { + bool init() { + if (initialized) return false; + + char *gpu_path = find_intel_gpu_dir(); + if (!gpu_path) { + Logger::debug("Failed to find Intel GPU sysfs path, Intel GPUs will not be detected"); + return false; + } + + char *gpu_device_id = get_intel_device_id(gpu_path); + if (!gpu_device_id) { + Logger::debug("Failed to find Intel GPU device ID, Intel GPUs will not be detected"); + return false; + } + + char *gpu_device_name = get_intel_device_name(gpu_device_id); + if (!gpu_device_name) { + Logger::warning("Failed to find Intel GPU device name in internal database"); + } + + free(gpu_device_id); + + engines = discover_engines(device); + if (!engines) { + Logger::debug("Failed to find Intel GPU engines, Intel GPUs will not be detected"); + return false; + } + + int ret = pmu_init(engines); + if (ret) { + Logger::warning("Intel GPU: Failed to initialize PMU"); + return false; + } + + pmu_sample(engines); + + device_count = 1; + + gpus.resize(gpus.size() + device_count); + gpu_names.resize(gpus.size() + device_count); + + if (gpu_device_name) { + gpu_names[Nvml::device_count + Rsmi::device_count] = string(gpu_device_name); + } else { + gpu_names[Nvml::device_count + Rsmi::device_count] = "Intel GPU"; + } + + free(gpu_device_name); + + initialized = true; + Intel::collect<1>(gpus.data() + Nvml::device_count + Rsmi::device_count); + + return true; + } + + bool shutdown() { + if (!initialized) return false; + if (engines) { + free_engines(engines); + engines = nullptr; + } + initialized = false; + return true; + } + + template bool collect(gpu_info* gpus_slice) { + if (!initialized) return false; + + if constexpr(is_init) { + gpus_slice->supported_functions = { + .gpu_utilization = true, + .mem_utilization = false, + .gpu_clock = true, + .mem_clock = false, + .pwr_usage = true, + .pwr_state = false, + .temp_info = false, + .mem_total = false, + .mem_used = false, + .pcie_txrx = false + }; + } + + pmu_sample(engines); + double t = (double)(engines->ts.cur - engines->ts.prev) / 1e9; + + double max_util = 0; + for (unsigned int i = 0; i < engines->num_engines; i++) { + struct engine *engine = &(&engines->engine)[i]; + double util = pmu_calc(&engine->busy.val, 1e9, t, 100); + if (util > max_util) { + max_util = util; + } + } + gpus_slice->gpu_percent.at("gpu-totals").push_back((long long)round(max_util)); + + double pwr = pmu_calc(&engines->r_gpu.val, 1, t, engines->r_gpu.scale); // in Watts + gpus_slice->pwr_usage = (long long)round(pwr * 1000); + if (gpus_slice->pwr_usage > 0) { + gpus_slice->gpu_percent.at("gpu-pwr-totals").push_back(100); + } else { + gpus_slice->gpu_percent.at("gpu-pwr-totals").push_back(0); + } + + double freq = pmu_calc(&engines->freq_act.val, 1, t, 1); // in MHz + gpus_slice->gpu_clock_speed = (unsigned int)round(freq); + + return true; + } + } //? Collect data from GPU-specific libraries auto collect(bool no_update) -> vector& { @@ -1581,6 +1713,7 @@ namespace Gpu { //* Collect data Nvml::collect<0>(gpus.data()); // raw pointer to vector data, size == Nvml::device_count Rsmi::collect<0>(gpus.data() + Nvml::device_count); // size = Rsmi::device_count + Intel::collect<0>(gpus.data() + Nvml::device_count + Rsmi::device_count); // size = Intel::device_count //* Calculate average usage long long avg = 0; diff --git a/src/linux/intel_gpu_top/drm.h b/src/linux/intel_gpu_top/drm.h new file mode 100644 index 00000000..02540248 --- /dev/null +++ b/src/linux/intel_gpu_top/drm.h @@ -0,0 +1,1318 @@ +/* + * Header for the Direct Rendering Manager + * + * Author: Rickard E. (Rik) Faith + * + * Acknowledgments: + * Dec 1999, Richard Henderson , move to generic cmpxchg. + */ + +/* + * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas. + * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California. + * All rights reserved. + * + * 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 + * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS 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 _DRM_H_ +#define _DRM_H_ + +#if defined(__linux__) + +#include +#include +typedef unsigned int drm_handle_t; + +#else /* One of the BSDs */ + +#include +#include +#include +typedef int8_t __s8; +typedef uint8_t __u8; +typedef int16_t __s16; +typedef uint16_t __u16; +typedef int32_t __s32; +typedef uint32_t __u32; +typedef int64_t __s64; +typedef uint64_t __u64; +typedef size_t __kernel_size_t; +typedef unsigned long drm_handle_t; + +#endif + +#if defined(__cplusplus) +extern "C" { +#endif + +#define DRM_NAME "drm" /**< Name in kernel, /dev, and /proc */ +#define DRM_MIN_ORDER 5 /**< At least 2^5 bytes = 32 bytes */ +#define DRM_MAX_ORDER 22 /**< Up to 2^22 bytes = 4MB */ +#define DRM_RAM_PERCENT 10 /**< How much system ram can we lock? */ + +#define _DRM_LOCK_HELD 0x80000000U /**< Hardware lock is held */ +#define _DRM_LOCK_CONT 0x40000000U /**< Hardware lock is contended */ +#define _DRM_LOCK_IS_HELD(lock) ((lock) & _DRM_LOCK_HELD) +#define _DRM_LOCK_IS_CONT(lock) ((lock) & _DRM_LOCK_CONT) +#define _DRM_LOCKING_CONTEXT(lock) ((lock) & ~(_DRM_LOCK_HELD|_DRM_LOCK_CONT)) + +typedef unsigned int drm_context_t; +typedef unsigned int drm_drawable_t; +typedef unsigned int drm_magic_t; + +/* + * Cliprect. + * + * \warning: If you change this structure, make sure you change + * XF86DRIClipRectRec in the server as well + * + * \note KW: Actually it's illegal to change either for + * backwards-compatibility reasons. + */ +struct drm_clip_rect { + unsigned short x1; + unsigned short y1; + unsigned short x2; + unsigned short y2; +}; + +/* + * Drawable information. + */ +struct drm_drawable_info { + unsigned int num_rects; + struct drm_clip_rect *rects; +}; + +/* + * Texture region, + */ +struct drm_tex_region { + unsigned char next; + unsigned char prev; + unsigned char in_use; + unsigned char padding; + unsigned int age; +}; + +/* + * Hardware lock. + * + * The lock structure is a simple cache-line aligned integer. To avoid + * processor bus contention on a multiprocessor system, there should not be any + * other data stored in the same cache line. + */ +struct drm_hw_lock { + __volatile__ unsigned int lock; /**< lock variable */ + char padding[60]; /**< Pad to cache line */ +}; + +/* + * DRM_IOCTL_VERSION ioctl argument type. + * + * \sa drmGetVersion(). + */ +struct drm_version { + int version_major; /**< Major version */ + int version_minor; /**< Minor version */ + int version_patchlevel; /**< Patch level */ + __kernel_size_t name_len; /**< Length of name buffer */ + char *name; /**< Name of driver */ + __kernel_size_t date_len; /**< Length of date buffer */ + char *date; /**< User-space buffer to hold date */ + __kernel_size_t desc_len; /**< Length of desc buffer */ + char *desc; /**< User-space buffer to hold desc */ +}; + +/* + * DRM_IOCTL_GET_UNIQUE ioctl argument type. + * + * \sa drmGetBusid() and drmSetBusId(). + */ +struct drm_unique { + __kernel_size_t unique_len; /**< Length of unique */ + char *unique; /**< Unique name for driver instantiation */ +}; + +struct drm_list { + int count; /**< Length of user-space structures */ + struct drm_version *version; +}; + +struct drm_block { + int unused; +}; + +/* + * DRM_IOCTL_CONTROL ioctl argument type. + * + * \sa drmCtlInstHandler() and drmCtlUninstHandler(). + */ +struct drm_control { + enum { + DRM_ADD_COMMAND, + DRM_RM_COMMAND, + DRM_INST_HANDLER, + DRM_UNINST_HANDLER + } func; + int irq; +}; + +/* + * Type of memory to map. + */ +enum drm_map_type { + _DRM_FRAME_BUFFER = 0, /**< WC (no caching), no core dump */ + _DRM_REGISTERS = 1, /**< no caching, no core dump */ + _DRM_SHM = 2, /**< shared, cached */ + _DRM_AGP = 3, /**< AGP/GART */ + _DRM_SCATTER_GATHER = 4, /**< Scatter/gather memory for PCI DMA */ + _DRM_CONSISTENT = 5 /**< Consistent memory for PCI DMA */ +}; + +/* + * Memory mapping flags. + */ +enum drm_map_flags { + _DRM_RESTRICTED = 0x01, /**< Cannot be mapped to user-virtual */ + _DRM_READ_ONLY = 0x02, + _DRM_LOCKED = 0x04, /**< shared, cached, locked */ + _DRM_KERNEL = 0x08, /**< kernel requires access */ + _DRM_WRITE_COMBINING = 0x10, /**< use write-combining if available */ + _DRM_CONTAINS_LOCK = 0x20, /**< SHM page that contains lock */ + _DRM_REMOVABLE = 0x40, /**< Removable mapping */ + _DRM_DRIVER = 0x80 /**< Managed by driver */ +}; + +struct drm_ctx_priv_map { + unsigned int ctx_id; /**< Context requesting private mapping */ + void *handle; /**< Handle of map */ +}; + +/* + * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls + * argument type. + * + * \sa drmAddMap(). + */ +struct drm_map { + unsigned long offset; /**< Requested physical address (0 for SAREA)*/ + unsigned long size; /**< Requested physical size (bytes) */ + enum drm_map_type type; /**< Type of memory to map */ + enum drm_map_flags flags; /**< Flags */ + void *handle; /**< User-space: "Handle" to pass to mmap() */ + /**< Kernel-space: kernel-virtual address */ + int mtrr; /**< MTRR slot used */ + /* Private data */ +}; + +/* + * DRM_IOCTL_GET_CLIENT ioctl argument type. + */ +struct drm_client { + int idx; /**< Which client desired? */ + int auth; /**< Is client authenticated? */ + unsigned long pid; /**< Process ID */ + unsigned long uid; /**< User ID */ + unsigned long magic; /**< Magic */ + unsigned long iocs; /**< Ioctl count */ +}; + +enum drm_stat_type { + _DRM_STAT_LOCK, + _DRM_STAT_OPENS, + _DRM_STAT_CLOSES, + _DRM_STAT_IOCTLS, + _DRM_STAT_LOCKS, + _DRM_STAT_UNLOCKS, + _DRM_STAT_VALUE, /**< Generic value */ + _DRM_STAT_BYTE, /**< Generic byte counter (1024bytes/K) */ + _DRM_STAT_COUNT, /**< Generic non-byte counter (1000/k) */ + + _DRM_STAT_IRQ, /**< IRQ */ + _DRM_STAT_PRIMARY, /**< Primary DMA bytes */ + _DRM_STAT_SECONDARY, /**< Secondary DMA bytes */ + _DRM_STAT_DMA, /**< DMA */ + _DRM_STAT_SPECIAL, /**< Special DMA (e.g., priority or polled) */ + _DRM_STAT_MISSED /**< Missed DMA opportunity */ + /* Add to the *END* of the list */ +}; + +/* + * DRM_IOCTL_GET_STATS ioctl argument type. + */ +struct drm_stats { + unsigned long count; + struct { + unsigned long value; + enum drm_stat_type type; + } data[15]; +}; + +/* + * Hardware locking flags. + */ +enum drm_lock_flags { + _DRM_LOCK_READY = 0x01, /**< Wait until hardware is ready for DMA */ + _DRM_LOCK_QUIESCENT = 0x02, /**< Wait until hardware quiescent */ + _DRM_LOCK_FLUSH = 0x04, /**< Flush this context's DMA queue first */ + _DRM_LOCK_FLUSH_ALL = 0x08, /**< Flush all DMA queues first */ + /* These *HALT* flags aren't supported yet + -- they will be used to support the + full-screen DGA-like mode. */ + _DRM_HALT_ALL_QUEUES = 0x10, /**< Halt all current and future queues */ + _DRM_HALT_CUR_QUEUES = 0x20 /**< Halt all current queues */ +}; + +/* + * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type. + * + * \sa drmGetLock() and drmUnlock(). + */ +struct drm_lock { + int context; + enum drm_lock_flags flags; +}; + +/* + * DMA flags + * + * \warning + * These values \e must match xf86drm.h. + * + * \sa drm_dma. + */ +enum drm_dma_flags { + /* Flags for DMA buffer dispatch */ + _DRM_DMA_BLOCK = 0x01, /**< + * Block until buffer dispatched. + * + * \note The buffer may not yet have + * been processed by the hardware -- + * getting a hardware lock with the + * hardware quiescent will ensure + * that the buffer has been + * processed. + */ + _DRM_DMA_WHILE_LOCKED = 0x02, /**< Dispatch while lock held */ + _DRM_DMA_PRIORITY = 0x04, /**< High priority dispatch */ + + /* Flags for DMA buffer request */ + _DRM_DMA_WAIT = 0x10, /**< Wait for free buffers */ + _DRM_DMA_SMALLER_OK = 0x20, /**< Smaller-than-requested buffers OK */ + _DRM_DMA_LARGER_OK = 0x40 /**< Larger-than-requested buffers OK */ +}; + +/* + * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type. + * + * \sa drmAddBufs(). + */ +struct drm_buf_desc { + int count; /**< Number of buffers of this size */ + int size; /**< Size in bytes */ + int low_mark; /**< Low water mark */ + int high_mark; /**< High water mark */ + enum { + _DRM_PAGE_ALIGN = 0x01, /**< Align on page boundaries for DMA */ + _DRM_AGP_BUFFER = 0x02, /**< Buffer is in AGP space */ + _DRM_SG_BUFFER = 0x04, /**< Scatter/gather memory buffer */ + _DRM_FB_BUFFER = 0x08, /**< Buffer is in frame buffer */ + _DRM_PCI_BUFFER_RO = 0x10 /**< Map PCI DMA buffer read-only */ + } flags; + unsigned long agp_start; /**< + * Start address of where the AGP buffers are + * in the AGP aperture + */ +}; + +/* + * DRM_IOCTL_INFO_BUFS ioctl argument type. + */ +struct drm_buf_info { + int count; /**< Entries in list */ + struct drm_buf_desc *list; +}; + +/* + * DRM_IOCTL_FREE_BUFS ioctl argument type. + */ +struct drm_buf_free { + int count; + int *list; +}; + +/* + * Buffer information + * + * \sa drm_buf_map. + */ +struct drm_buf_pub { + int idx; /**< Index into the master buffer list */ + int total; /**< Buffer size */ + int used; /**< Amount of buffer in use (for DMA) */ + void *address; /**< Address of buffer */ +}; + +/* + * DRM_IOCTL_MAP_BUFS ioctl argument type. + */ +struct drm_buf_map { + int count; /**< Length of the buffer list */ +#ifdef __cplusplus + void *virt; +#else + void *virtual; /**< Mmap'd area in user-virtual */ +#endif + struct drm_buf_pub *list; /**< Buffer information */ +}; + +/* + * DRM_IOCTL_DMA ioctl argument type. + * + * Indices here refer to the offset into the buffer list in drm_buf_get. + * + * \sa drmDMA(). + */ +struct drm_dma { + int context; /**< Context handle */ + int send_count; /**< Number of buffers to send */ + int *send_indices; /**< List of handles to buffers */ + int *send_sizes; /**< Lengths of data to send */ + enum drm_dma_flags flags; /**< Flags */ + int request_count; /**< Number of buffers requested */ + int request_size; /**< Desired size for buffers */ + int *request_indices; /**< Buffer information */ + int *request_sizes; + int granted_count; /**< Number of buffers granted */ +}; + +enum drm_ctx_flags { + _DRM_CONTEXT_PRESERVED = 0x01, + _DRM_CONTEXT_2DONLY = 0x02 +}; + +/* + * DRM_IOCTL_ADD_CTX ioctl argument type. + * + * \sa drmCreateContext() and drmDestroyContext(). + */ +struct drm_ctx { + drm_context_t handle; + enum drm_ctx_flags flags; +}; + +/* + * DRM_IOCTL_RES_CTX ioctl argument type. + */ +struct drm_ctx_res { + int count; + struct drm_ctx *contexts; +}; + +/* + * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type. + */ +struct drm_draw { + drm_drawable_t handle; +}; + +/* + * DRM_IOCTL_UPDATE_DRAW ioctl argument type. + */ +typedef enum { + DRM_DRAWABLE_CLIPRECTS +} drm_drawable_info_type_t; + +struct drm_update_draw { + drm_drawable_t handle; + unsigned int type; + unsigned int num; + unsigned long long data; +}; + +/* + * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type. + */ +struct drm_auth { + drm_magic_t magic; +}; + +/* + * DRM_IOCTL_IRQ_BUSID ioctl argument type. + * + * \sa drmGetInterruptFromBusID(). + */ +struct drm_irq_busid { + int irq; /**< IRQ number */ + int busnum; /**< bus number */ + int devnum; /**< device number */ + int funcnum; /**< function number */ +}; + +enum drm_vblank_seq_type { + _DRM_VBLANK_ABSOLUTE = 0x0, /**< Wait for specific vblank sequence number */ + _DRM_VBLANK_RELATIVE = 0x1, /**< Wait for given number of vblanks */ + /* bits 1-6 are reserved for high crtcs */ + _DRM_VBLANK_HIGH_CRTC_MASK = 0x0000003e, + _DRM_VBLANK_EVENT = 0x4000000, /**< Send event instead of blocking */ + _DRM_VBLANK_FLIP = 0x8000000, /**< Scheduled buffer swap should flip */ + _DRM_VBLANK_NEXTONMISS = 0x10000000, /**< If missed, wait for next vblank */ + _DRM_VBLANK_SECONDARY = 0x20000000, /**< Secondary display controller */ + _DRM_VBLANK_SIGNAL = 0x40000000 /**< Send signal instead of blocking, unsupported */ +}; +#define _DRM_VBLANK_HIGH_CRTC_SHIFT 1 + +#define _DRM_VBLANK_TYPES_MASK (_DRM_VBLANK_ABSOLUTE | _DRM_VBLANK_RELATIVE) +#define _DRM_VBLANK_FLAGS_MASK (_DRM_VBLANK_EVENT | _DRM_VBLANK_SIGNAL | \ + _DRM_VBLANK_SECONDARY | _DRM_VBLANK_NEXTONMISS) + +struct drm_wait_vblank_request { + enum drm_vblank_seq_type type; + unsigned int sequence; + unsigned long signal; +}; + +struct drm_wait_vblank_reply { + enum drm_vblank_seq_type type; + unsigned int sequence; + long tval_sec; + long tval_usec; +}; + +/* + * DRM_IOCTL_WAIT_VBLANK ioctl argument type. + * + * \sa drmWaitVBlank(). + */ +union drm_wait_vblank { + struct drm_wait_vblank_request request; + struct drm_wait_vblank_reply reply; +}; + +#define _DRM_PRE_MODESET 1 +#define _DRM_POST_MODESET 2 + +/* + * DRM_IOCTL_MODESET_CTL ioctl argument type + * + * \sa drmModesetCtl(). + */ +struct drm_modeset_ctl { + __u32 crtc; + __u32 cmd; +}; + +/* + * DRM_IOCTL_AGP_ENABLE ioctl argument type. + * + * \sa drmAgpEnable(). + */ +struct drm_agp_mode { + unsigned long mode; /**< AGP mode */ +}; + +/* + * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type. + * + * \sa drmAgpAlloc() and drmAgpFree(). + */ +struct drm_agp_buffer { + unsigned long size; /**< In bytes -- will round to page boundary */ + unsigned long handle; /**< Used for binding / unbinding */ + unsigned long type; /**< Type of memory to allocate */ + unsigned long physical; /**< Physical used by i810 */ +}; + +/* + * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type. + * + * \sa drmAgpBind() and drmAgpUnbind(). + */ +struct drm_agp_binding { + unsigned long handle; /**< From drm_agp_buffer */ + unsigned long offset; /**< In bytes -- will round to page boundary */ +}; + +/* + * DRM_IOCTL_AGP_INFO ioctl argument type. + * + * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(), + * drmAgpBase(), drmAgpSize(), drmAgpMemoryUsed(), drmAgpMemoryAvail(), + * drmAgpVendorId() and drmAgpDeviceId(). + */ +struct drm_agp_info { + int agp_version_major; + int agp_version_minor; + unsigned long mode; + unsigned long aperture_base; /* physical address */ + unsigned long aperture_size; /* bytes */ + unsigned long memory_allowed; /* bytes */ + unsigned long memory_used; + + /* PCI information */ + unsigned short id_vendor; + unsigned short id_device; +}; + +/* + * DRM_IOCTL_SG_ALLOC ioctl argument type. + */ +struct drm_scatter_gather { + unsigned long size; /**< In bytes -- will round to page boundary */ + unsigned long handle; /**< Used for mapping / unmapping */ +}; + +/* + * DRM_IOCTL_SET_VERSION ioctl argument type. + */ +struct drm_set_version { + int drm_di_major; + int drm_di_minor; + int drm_dd_major; + int drm_dd_minor; +}; + +/* DRM_IOCTL_GEM_CLOSE ioctl argument type */ +struct drm_gem_close { + /** Handle of the object to be closed. */ + __u32 handle; + __u32 pad; +}; + +/* DRM_IOCTL_GEM_FLINK ioctl argument type */ +struct drm_gem_flink { + /** Handle for the object being named */ + __u32 handle; + + /** Returned global name */ + __u32 name; +}; + +/* DRM_IOCTL_GEM_OPEN ioctl argument type */ +struct drm_gem_open { + /** Name of object being opened */ + __u32 name; + + /** Returned handle for the object */ + __u32 handle; + + /** Returned size of the object */ + __u64 size; +}; + +/** + * DRM_CAP_DUMB_BUFFER + * + * If set to 1, the driver supports creating dumb buffers via the + * &DRM_IOCTL_MODE_CREATE_DUMB ioctl. + */ +#define DRM_CAP_DUMB_BUFFER 0x1 +/** + * DRM_CAP_VBLANK_HIGH_CRTC + * + * If set to 1, the kernel supports specifying a :ref:`CRTC index` + * in the high bits of &drm_wait_vblank_request.type. + * + * Starting kernel version 2.6.39, this capability is always set to 1. + */ +#define DRM_CAP_VBLANK_HIGH_CRTC 0x2 +/** + * DRM_CAP_DUMB_PREFERRED_DEPTH + * + * The preferred bit depth for dumb buffers. + * + * The bit depth is the number of bits used to indicate the color of a single + * pixel excluding any padding. This is different from the number of bits per + * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per + * pixel. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ +#define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3 +/** + * DRM_CAP_DUMB_PREFER_SHADOW + * + * If set to 1, the driver prefers userspace to render to a shadow buffer + * instead of directly rendering to a dumb buffer. For best speed, userspace + * should do streaming ordered memory copies into the dumb buffer and never + * read from it. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ +#define DRM_CAP_DUMB_PREFER_SHADOW 0x4 +/** + * DRM_CAP_PRIME + * + * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT + * and &DRM_PRIME_CAP_EXPORT. + * + * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and + * &DRM_PRIME_CAP_EXPORT are always advertised. + * + * PRIME buffers are exposed as dma-buf file descriptors. + * See :ref:`prime_buffer_sharing`. + */ +#define DRM_CAP_PRIME 0x5 +/** + * DRM_PRIME_CAP_IMPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME + * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. + */ +#define DRM_PRIME_CAP_IMPORT 0x1 +/** + * DRM_PRIME_CAP_EXPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME + * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. + */ +#define DRM_PRIME_CAP_EXPORT 0x2 +/** + * DRM_CAP_TIMESTAMP_MONOTONIC + * + * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in + * struct drm_event_vblank. If set to 1, the kernel will report timestamps with + * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these + * clocks. + * + * Starting from kernel version 2.6.39, the default value for this capability + * is 1. Starting kernel version 4.15, this capability is always set to 1. + */ +#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 +/** + * DRM_CAP_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + */ +#define DRM_CAP_ASYNC_PAGE_FLIP 0x7 +/** + * DRM_CAP_CURSOR_WIDTH + * + * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid + * width x height combination for the hardware cursor. The intention is that a + * hardware agnostic userspace can query a cursor plane size to use. + * + * Note that the cross-driver contract is to merely return a valid size; + * drivers are free to attach another meaning on top, eg. i915 returns the + * maximum plane size. + */ +#define DRM_CAP_CURSOR_WIDTH 0x8 +/** + * DRM_CAP_CURSOR_HEIGHT + * + * See &DRM_CAP_CURSOR_WIDTH. + */ +#define DRM_CAP_CURSOR_HEIGHT 0x9 +/** + * DRM_CAP_ADDFB2_MODIFIERS + * + * If set to 1, the driver supports supplying modifiers in the + * &DRM_IOCTL_MODE_ADDFB2 ioctl. + */ +#define DRM_CAP_ADDFB2_MODIFIERS 0x10 +/** + * DRM_CAP_PAGE_FLIP_TARGET + * + * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and + * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in + * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP + * ioctl. + */ +#define DRM_CAP_PAGE_FLIP_TARGET 0x11 +/** + * DRM_CAP_CRTC_IN_VBLANK_EVENT + * + * If set to 1, the kernel supports reporting the CRTC ID in + * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and + * &DRM_EVENT_FLIP_COMPLETE events. + * + * Starting kernel version 4.12, this capability is always set to 1. + */ +#define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 +/** + * DRM_CAP_SYNCOBJ + * + * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`. + */ +#define DRM_CAP_SYNCOBJ 0x13 +/** + * DRM_CAP_SYNCOBJ_TIMELINE + * + * If set to 1, the driver supports timeline operations on sync objects. See + * :ref:`drm_sync_objects`. + */ +#define DRM_CAP_SYNCOBJ_TIMELINE 0x14 + +/* DRM_IOCTL_GET_CAP ioctl argument type */ +struct drm_get_cap { + __u64 capability; + __u64 value; +}; + +/** + * DRM_CLIENT_CAP_STEREO_3D + * + * If set to 1, the DRM core will expose the stereo 3D capabilities of the + * monitor by advertising the supported 3D layouts in the flags of struct + * drm_mode_modeinfo. See ``DRM_MODE_FLAG_3D_*``. + * + * This capability is always supported for all drivers starting from kernel + * version 3.13. + */ +#define DRM_CLIENT_CAP_STEREO_3D 1 + +/** + * DRM_CLIENT_CAP_UNIVERSAL_PLANES + * + * If set to 1, the DRM core will expose all planes (overlay, primary, and + * cursor) to userspace. + * + * This capability has been introduced in kernel version 3.15. Starting from + * kernel version 3.17, this capability is always supported for all drivers. + */ +#define DRM_CLIENT_CAP_UNIVERSAL_PLANES 2 + +/** + * DRM_CLIENT_CAP_ATOMIC + * + * If set to 1, the DRM core will expose atomic properties to userspace. This + * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and + * &DRM_CLIENT_CAP_ASPECT_RATIO. + * + * If the driver doesn't support atomic mode-setting, enabling this capability + * will fail with -EOPNOTSUPP. + * + * This capability has been introduced in kernel version 4.0. Starting from + * kernel version 4.2, this capability is always supported for atomic-capable + * drivers. + */ +#define DRM_CLIENT_CAP_ATOMIC 3 + +/** + * DRM_CLIENT_CAP_ASPECT_RATIO + * + * If set to 1, the DRM core will provide aspect ratio information in modes. + * See ``DRM_MODE_FLAG_PIC_AR_*``. + * + * This capability is always supported for all drivers starting from kernel + * version 4.18. + */ +#define DRM_CLIENT_CAP_ASPECT_RATIO 4 + +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. The client must enable + * &DRM_CLIENT_CAP_ATOMIC first. + * + * This capability is always supported for atomic-capable drivers starting from + * kernel version 4.19. + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + +/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ +struct drm_set_client_cap { + __u64 capability; + __u64 value; +}; + +#define DRM_RDWR O_RDWR +#define DRM_CLOEXEC O_CLOEXEC +struct drm_prime_handle { + __u32 handle; + + /** Flags.. only applicable for handle->fd */ + __u32 flags; + + /** Returned dmabuf file descriptor */ + __s32 fd; +}; + +struct drm_syncobj_create { + __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) + __u32 flags; +}; + +struct drm_syncobj_destroy { + __u32 handle; + __u32 pad; +}; + +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +struct drm_syncobj_handle { + __u32 handle; + __u32 flags; + + __s32 fd; + __u32 pad; +}; + +struct drm_syncobj_transfer { + __u32 src_handle; + __u32 dst_handle; + __u64 src_point; + __u64 dst_point; + __u32 flags; + __u32 pad; +}; + +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */ +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_timeline_wait { + __u64 handles; + /* wait on specific timeline point for every handles*/ + __u64 points; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +/** + * struct drm_syncobj_eventfd + * @handle: syncobj handle. + * @flags: Zero to wait for the point to be signalled, or + * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be + * available for the point. + * @point: syncobj timeline point (set to zero for binary syncobjs). + * @fd: Existing eventfd to sent events to. + * @pad: Must be zero. + * + * Register an eventfd to be signalled by a syncobj. The eventfd counter will + * be incremented by one. + */ +struct drm_syncobj_eventfd { + __u32 handle; + __u32 flags; + __u64 point; + __s32 fd; + __u32 pad; +}; + + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + +#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */ +struct drm_syncobj_timeline_array { + __u64 handles; + __u64 points; + __u32 count_handles; + __u32 flags; +}; + + +/* Query current scanout sequence number */ +struct drm_crtc_get_sequence { + __u32 crtc_id; /* requested crtc_id */ + __u32 active; /* return: crtc output is active */ + __u64 sequence; /* return: most recent vblank sequence */ + __s64 sequence_ns; /* return: most recent time of first pixel out */ +}; + +/* Queue event to be delivered at specified sequence. Time stamp marks + * when the first pixel of the refresh cycle leaves the display engine + * for the display + */ +#define DRM_CRTC_SEQUENCE_RELATIVE 0x00000001 /* sequence is relative to current */ +#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS 0x00000002 /* Use next sequence if we've missed */ + +struct drm_crtc_queue_sequence { + __u32 crtc_id; + __u32 flags; + __u64 sequence; /* on input, target sequence. on output, actual sequence */ + __u64 user_data; /* user data passed to event */ +}; + +#if defined(__cplusplus) +} +#endif + +#include "drm_mode.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +#define DRM_IOCTL_BASE 'd' +#define DRM_IO(nr) _IO(DRM_IOCTL_BASE,nr) +#define DRM_IOR(nr,type) _IOR(DRM_IOCTL_BASE,nr,type) +#define DRM_IOW(nr,type) _IOW(DRM_IOCTL_BASE,nr,type) +#define DRM_IOWR(nr,type) _IOWR(DRM_IOCTL_BASE,nr,type) + +#define DRM_IOCTL_VERSION DRM_IOWR(0x00, struct drm_version) +#define DRM_IOCTL_GET_UNIQUE DRM_IOWR(0x01, struct drm_unique) +#define DRM_IOCTL_GET_MAGIC DRM_IOR( 0x02, struct drm_auth) +#define DRM_IOCTL_IRQ_BUSID DRM_IOWR(0x03, struct drm_irq_busid) +#define DRM_IOCTL_GET_MAP DRM_IOWR(0x04, struct drm_map) +#define DRM_IOCTL_GET_CLIENT DRM_IOWR(0x05, struct drm_client) +#define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) +#define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) +#define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ +#define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) +#define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) +#define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) +#define DRM_IOCTL_GET_CAP DRM_IOWR(0x0c, struct drm_get_cap) +#define DRM_IOCTL_SET_CLIENT_CAP DRM_IOW( 0x0d, struct drm_set_client_cap) + +#define DRM_IOCTL_SET_UNIQUE DRM_IOW( 0x10, struct drm_unique) +#define DRM_IOCTL_AUTH_MAGIC DRM_IOW( 0x11, struct drm_auth) +#define DRM_IOCTL_BLOCK DRM_IOWR(0x12, struct drm_block) +#define DRM_IOCTL_UNBLOCK DRM_IOWR(0x13, struct drm_block) +#define DRM_IOCTL_CONTROL DRM_IOW( 0x14, struct drm_control) +#define DRM_IOCTL_ADD_MAP DRM_IOWR(0x15, struct drm_map) +#define DRM_IOCTL_ADD_BUFS DRM_IOWR(0x16, struct drm_buf_desc) +#define DRM_IOCTL_MARK_BUFS DRM_IOW( 0x17, struct drm_buf_desc) +#define DRM_IOCTL_INFO_BUFS DRM_IOWR(0x18, struct drm_buf_info) +#define DRM_IOCTL_MAP_BUFS DRM_IOWR(0x19, struct drm_buf_map) +#define DRM_IOCTL_FREE_BUFS DRM_IOW( 0x1a, struct drm_buf_free) + +#define DRM_IOCTL_RM_MAP DRM_IOW( 0x1b, struct drm_map) + +#define DRM_IOCTL_SET_SAREA_CTX DRM_IOW( 0x1c, struct drm_ctx_priv_map) +#define DRM_IOCTL_GET_SAREA_CTX DRM_IOWR(0x1d, struct drm_ctx_priv_map) + +#define DRM_IOCTL_SET_MASTER DRM_IO(0x1e) +#define DRM_IOCTL_DROP_MASTER DRM_IO(0x1f) + +#define DRM_IOCTL_ADD_CTX DRM_IOWR(0x20, struct drm_ctx) +#define DRM_IOCTL_RM_CTX DRM_IOWR(0x21, struct drm_ctx) +#define DRM_IOCTL_MOD_CTX DRM_IOW( 0x22, struct drm_ctx) +#define DRM_IOCTL_GET_CTX DRM_IOWR(0x23, struct drm_ctx) +#define DRM_IOCTL_SWITCH_CTX DRM_IOW( 0x24, struct drm_ctx) +#define DRM_IOCTL_NEW_CTX DRM_IOW( 0x25, struct drm_ctx) +#define DRM_IOCTL_RES_CTX DRM_IOWR(0x26, struct drm_ctx_res) +#define DRM_IOCTL_ADD_DRAW DRM_IOWR(0x27, struct drm_draw) +#define DRM_IOCTL_RM_DRAW DRM_IOWR(0x28, struct drm_draw) +#define DRM_IOCTL_DMA DRM_IOWR(0x29, struct drm_dma) +#define DRM_IOCTL_LOCK DRM_IOW( 0x2a, struct drm_lock) +#define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) +#define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) + +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ +#define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ +#define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) + +#define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) +#define DRM_IOCTL_AGP_RELEASE DRM_IO( 0x31) +#define DRM_IOCTL_AGP_ENABLE DRM_IOW( 0x32, struct drm_agp_mode) +#define DRM_IOCTL_AGP_INFO DRM_IOR( 0x33, struct drm_agp_info) +#define DRM_IOCTL_AGP_ALLOC DRM_IOWR(0x34, struct drm_agp_buffer) +#define DRM_IOCTL_AGP_FREE DRM_IOW( 0x35, struct drm_agp_buffer) +#define DRM_IOCTL_AGP_BIND DRM_IOW( 0x36, struct drm_agp_binding) +#define DRM_IOCTL_AGP_UNBIND DRM_IOW( 0x37, struct drm_agp_binding) + +#define DRM_IOCTL_SG_ALLOC DRM_IOWR(0x38, struct drm_scatter_gather) +#define DRM_IOCTL_SG_FREE DRM_IOW( 0x39, struct drm_scatter_gather) + +#define DRM_IOCTL_WAIT_VBLANK DRM_IOWR(0x3a, union drm_wait_vblank) + +#define DRM_IOCTL_CRTC_GET_SEQUENCE DRM_IOWR(0x3b, struct drm_crtc_get_sequence) +#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE DRM_IOWR(0x3c, struct drm_crtc_queue_sequence) + +#define DRM_IOCTL_UPDATE_DRAW DRM_IOW(0x3f, struct drm_update_draw) + +#define DRM_IOCTL_MODE_GETRESOURCES DRM_IOWR(0xA0, struct drm_mode_card_res) +#define DRM_IOCTL_MODE_GETCRTC DRM_IOWR(0xA1, struct drm_mode_crtc) +#define DRM_IOCTL_MODE_SETCRTC DRM_IOWR(0xA2, struct drm_mode_crtc) +#define DRM_IOCTL_MODE_CURSOR DRM_IOWR(0xA3, struct drm_mode_cursor) +#define DRM_IOCTL_MODE_GETGAMMA DRM_IOWR(0xA4, struct drm_mode_crtc_lut) +#define DRM_IOCTL_MODE_SETGAMMA DRM_IOWR(0xA5, struct drm_mode_crtc_lut) +#define DRM_IOCTL_MODE_GETENCODER DRM_IOWR(0xA6, struct drm_mode_get_encoder) +#define DRM_IOCTL_MODE_GETCONNECTOR DRM_IOWR(0xA7, struct drm_mode_get_connector) +#define DRM_IOCTL_MODE_ATTACHMODE DRM_IOWR(0xA8, struct drm_mode_mode_cmd) /* deprecated (never worked) */ +#define DRM_IOCTL_MODE_DETACHMODE DRM_IOWR(0xA9, struct drm_mode_mode_cmd) /* deprecated (never worked) */ + +#define DRM_IOCTL_MODE_GETPROPERTY DRM_IOWR(0xAA, struct drm_mode_get_property) +#define DRM_IOCTL_MODE_SETPROPERTY DRM_IOWR(0xAB, struct drm_mode_connector_set_property) +#define DRM_IOCTL_MODE_GETPROPBLOB DRM_IOWR(0xAC, struct drm_mode_get_blob) +#define DRM_IOCTL_MODE_GETFB DRM_IOWR(0xAD, struct drm_mode_fb_cmd) +#define DRM_IOCTL_MODE_ADDFB DRM_IOWR(0xAE, struct drm_mode_fb_cmd) +/** + * DRM_IOCTL_MODE_RMFB - Remove a framebuffer. + * + * This removes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL + * argument is a framebuffer object ID. + * + * Warning: removing a framebuffer currently in-use on an enabled plane will + * disable that plane. The CRTC the plane is linked to may also be disabled + * (depending on driver capabilities). + */ +#define DRM_IOCTL_MODE_RMFB DRM_IOWR(0xAF, unsigned int) +#define DRM_IOCTL_MODE_PAGE_FLIP DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip) +#define DRM_IOCTL_MODE_DIRTYFB DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd) + +#define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb) +#define DRM_IOCTL_MODE_MAP_DUMB DRM_IOWR(0xB3, struct drm_mode_map_dumb) +#define DRM_IOCTL_MODE_DESTROY_DUMB DRM_IOWR(0xB4, struct drm_mode_destroy_dumb) +#define DRM_IOCTL_MODE_GETPLANERESOURCES DRM_IOWR(0xB5, struct drm_mode_get_plane_res) +#define DRM_IOCTL_MODE_GETPLANE DRM_IOWR(0xB6, struct drm_mode_get_plane) +#define DRM_IOCTL_MODE_SETPLANE DRM_IOWR(0xB7, struct drm_mode_set_plane) +#define DRM_IOCTL_MODE_ADDFB2 DRM_IOWR(0xB8, struct drm_mode_fb_cmd2) +#define DRM_IOCTL_MODE_OBJ_GETPROPERTIES DRM_IOWR(0xB9, struct drm_mode_obj_get_properties) +#define DRM_IOCTL_MODE_OBJ_SETPROPERTY DRM_IOWR(0xBA, struct drm_mode_obj_set_property) +#define DRM_IOCTL_MODE_CURSOR2 DRM_IOWR(0xBB, struct drm_mode_cursor2) +#define DRM_IOCTL_MODE_ATOMIC DRM_IOWR(0xBC, struct drm_mode_atomic) +#define DRM_IOCTL_MODE_CREATEPROPBLOB DRM_IOWR(0xBD, struct drm_mode_create_blob) +#define DRM_IOCTL_MODE_DESTROYPROPBLOB DRM_IOWR(0xBE, struct drm_mode_destroy_blob) + +#define DRM_IOCTL_SYNCOBJ_CREATE DRM_IOWR(0xBF, struct drm_syncobj_create) +#define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) +#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) + +#define DRM_IOCTL_MODE_CREATE_LEASE DRM_IOWR(0xC6, struct drm_mode_create_lease) +#define DRM_IOCTL_MODE_LIST_LESSEES DRM_IOWR(0xC7, struct drm_mode_list_lessees) +#define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease) +#define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease) + +#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait) +#define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) +#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) + +/** + * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata. + * + * This queries metadata about a framebuffer. User-space fills + * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the + * struct as the output. + * + * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. + * + * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid + * until one has a zero &drm_mode_fb_cmd2.pitches. + * + * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set + * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the + * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. + */ +#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) + +#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) + +/* + * Device specific ioctls should only be in their respective headers + * The device specific ioctl range is from 0x40 to 0x9f. + * Generic IOCTLS restart at 0xA0. + * + * \sa drmCommandNone(), drmCommandRead(), drmCommandWrite(), and + * drmCommandReadWrite(). + */ +#define DRM_COMMAND_BASE 0x40 +#define DRM_COMMAND_END 0xA0 + +/** + * struct drm_event - Header for DRM events + * @type: event type. + * @length: total number of payload bytes (including header). + * + * This struct is a header for events written back to user-space on the DRM FD. + * A read on the DRM FD will always only return complete events: e.g. if the + * read buffer is 100 bytes large and there are two 64 byte events pending, + * only one will be returned. + * + * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and + * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK, + * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE. + */ +struct drm_event { + __u32 type; + __u32 length; +}; + +/** + * DRM_EVENT_VBLANK - vertical blanking event + * + * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the + * &_DRM_VBLANK_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ +#define DRM_EVENT_VBLANK 0x01 +/** + * DRM_EVENT_FLIP_COMPLETE - page-flip completion event + * + * This event is sent in response to an atomic commit or legacy page-flip with + * the &DRM_MODE_PAGE_FLIP_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ +#define DRM_EVENT_FLIP_COMPLETE 0x02 +/** + * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event + * + * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE. + * + * The event payload is a struct drm_event_crtc_sequence. + */ +#define DRM_EVENT_CRTC_SEQUENCE 0x03 + +struct drm_event_vblank { + struct drm_event base; + __u64 user_data; + __u32 tv_sec; + __u32 tv_usec; + __u32 sequence; + __u32 crtc_id; /* 0 on older kernels that do not support this */ +}; + +/* Event delivered at sequence. Time stamp marks when the first pixel + * of the refresh cycle leaves the display engine for the display + */ +struct drm_event_crtc_sequence { + struct drm_event base; + __u64 user_data; + __s64 time_ns; + __u64 sequence; +}; + +/* typedef area */ +typedef struct drm_clip_rect drm_clip_rect_t; +typedef struct drm_drawable_info drm_drawable_info_t; +typedef struct drm_tex_region drm_tex_region_t; +typedef struct drm_hw_lock drm_hw_lock_t; +typedef struct drm_version drm_version_t; +typedef struct drm_unique drm_unique_t; +typedef struct drm_list drm_list_t; +typedef struct drm_block drm_block_t; +typedef struct drm_control drm_control_t; +typedef enum drm_map_type drm_map_type_t; +typedef enum drm_map_flags drm_map_flags_t; +typedef struct drm_ctx_priv_map drm_ctx_priv_map_t; +typedef struct drm_map drm_map_t; +typedef struct drm_client drm_client_t; +typedef enum drm_stat_type drm_stat_type_t; +typedef struct drm_stats drm_stats_t; +typedef enum drm_lock_flags drm_lock_flags_t; +typedef struct drm_lock drm_lock_t; +typedef enum drm_dma_flags drm_dma_flags_t; +typedef struct drm_buf_desc drm_buf_desc_t; +typedef struct drm_buf_info drm_buf_info_t; +typedef struct drm_buf_free drm_buf_free_t; +typedef struct drm_buf_pub drm_buf_pub_t; +typedef struct drm_buf_map drm_buf_map_t; +typedef struct drm_dma drm_dma_t; +typedef union drm_wait_vblank drm_wait_vblank_t; +typedef struct drm_agp_mode drm_agp_mode_t; +typedef enum drm_ctx_flags drm_ctx_flags_t; +typedef struct drm_ctx drm_ctx_t; +typedef struct drm_ctx_res drm_ctx_res_t; +typedef struct drm_draw drm_draw_t; +typedef struct drm_update_draw drm_update_draw_t; +typedef struct drm_auth drm_auth_t; +typedef struct drm_irq_busid drm_irq_busid_t; +typedef enum drm_vblank_seq_type drm_vblank_seq_type_t; + +typedef struct drm_agp_buffer drm_agp_buffer_t; +typedef struct drm_agp_binding drm_agp_binding_t; +typedef struct drm_agp_info drm_agp_info_t; +typedef struct drm_scatter_gather drm_scatter_gather_t; +typedef struct drm_set_version drm_set_version_t; + +#if defined(__cplusplus) +} +#endif + +#endif diff --git a/src/linux/intel_gpu_top/drm_mode.h b/src/linux/intel_gpu_top/drm_mode.h new file mode 100644 index 00000000..ea1b639b --- /dev/null +++ b/src/linux/intel_gpu_top/drm_mode.h @@ -0,0 +1,1318 @@ +/* + * Copyright (c) 2007 Dave Airlie + * Copyright (c) 2007 Jakob Bornecrantz + * Copyright (c) 2008 Red Hat Inc. + * Copyright (c) 2007-2008 Tungsten Graphics, Inc., Cedar Park, TX., USA + * Copyright (c) 2007-2008 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 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 _DRM_MODE_H +#define _DRM_MODE_H + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: overview + * + * DRM exposes many UAPI and structure definition to have a consistent + * and standardized interface with user. + * Userspace can refer to these structure definitions and UAPI formats + * to communicate to driver + */ + +#define DRM_CONNECTOR_NAME_LEN 32 +#define DRM_DISPLAY_MODE_LEN 32 +#define DRM_PROP_NAME_LEN 32 + +#define DRM_MODE_TYPE_BUILTIN (1<<0) /* deprecated */ +#define DRM_MODE_TYPE_CLOCK_C ((1<<1) | DRM_MODE_TYPE_BUILTIN) /* deprecated */ +#define DRM_MODE_TYPE_CRTC_C ((1<<2) | DRM_MODE_TYPE_BUILTIN) /* deprecated */ +#define DRM_MODE_TYPE_PREFERRED (1<<3) +#define DRM_MODE_TYPE_DEFAULT (1<<4) /* deprecated */ +#define DRM_MODE_TYPE_USERDEF (1<<5) +#define DRM_MODE_TYPE_DRIVER (1<<6) + +#define DRM_MODE_TYPE_ALL (DRM_MODE_TYPE_PREFERRED | \ + DRM_MODE_TYPE_USERDEF | \ + DRM_MODE_TYPE_DRIVER) + +/* Video mode flags */ +/* bit compatible with the xrandr RR_ definitions (bits 0-13) + * + * ABI warning: Existing userspace really expects + * the mode flags to match the xrandr definitions. Any + * changes that don't match the xrandr definitions will + * likely need a new client cap or some other mechanism + * to avoid breaking existing userspace. This includes + * allocating new flags in the previously unused bits! + */ +#define DRM_MODE_FLAG_PHSYNC (1<<0) +#define DRM_MODE_FLAG_NHSYNC (1<<1) +#define DRM_MODE_FLAG_PVSYNC (1<<2) +#define DRM_MODE_FLAG_NVSYNC (1<<3) +#define DRM_MODE_FLAG_INTERLACE (1<<4) +#define DRM_MODE_FLAG_DBLSCAN (1<<5) +#define DRM_MODE_FLAG_CSYNC (1<<6) +#define DRM_MODE_FLAG_PCSYNC (1<<7) +#define DRM_MODE_FLAG_NCSYNC (1<<8) +#define DRM_MODE_FLAG_HSKEW (1<<9) /* hskew provided */ +#define DRM_MODE_FLAG_BCAST (1<<10) /* deprecated */ +#define DRM_MODE_FLAG_PIXMUX (1<<11) /* deprecated */ +#define DRM_MODE_FLAG_DBLCLK (1<<12) +#define DRM_MODE_FLAG_CLKDIV2 (1<<13) + /* + * When adding a new stereo mode don't forget to adjust DRM_MODE_FLAGS_3D_MAX + * (define not exposed to user space). + */ +#define DRM_MODE_FLAG_3D_MASK (0x1f<<14) +#define DRM_MODE_FLAG_3D_NONE (0<<14) +#define DRM_MODE_FLAG_3D_FRAME_PACKING (1<<14) +#define DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE (2<<14) +#define DRM_MODE_FLAG_3D_LINE_ALTERNATIVE (3<<14) +#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL (4<<14) +#define DRM_MODE_FLAG_3D_L_DEPTH (5<<14) +#define DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH (6<<14) +#define DRM_MODE_FLAG_3D_TOP_AND_BOTTOM (7<<14) +#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF (8<<14) + +/* Picture aspect ratio options */ +#define DRM_MODE_PICTURE_ASPECT_NONE 0 +#define DRM_MODE_PICTURE_ASPECT_4_3 1 +#define DRM_MODE_PICTURE_ASPECT_16_9 2 +#define DRM_MODE_PICTURE_ASPECT_64_27 3 +#define DRM_MODE_PICTURE_ASPECT_256_135 4 + +/* Content type options */ +#define DRM_MODE_CONTENT_TYPE_NO_DATA 0 +#define DRM_MODE_CONTENT_TYPE_GRAPHICS 1 +#define DRM_MODE_CONTENT_TYPE_PHOTO 2 +#define DRM_MODE_CONTENT_TYPE_CINEMA 3 +#define DRM_MODE_CONTENT_TYPE_GAME 4 + +/* Aspect ratio flag bitmask (4 bits 22:19) */ +#define DRM_MODE_FLAG_PIC_AR_MASK (0x0F<<19) +#define DRM_MODE_FLAG_PIC_AR_NONE \ + (DRM_MODE_PICTURE_ASPECT_NONE<<19) +#define DRM_MODE_FLAG_PIC_AR_4_3 \ + (DRM_MODE_PICTURE_ASPECT_4_3<<19) +#define DRM_MODE_FLAG_PIC_AR_16_9 \ + (DRM_MODE_PICTURE_ASPECT_16_9<<19) +#define DRM_MODE_FLAG_PIC_AR_64_27 \ + (DRM_MODE_PICTURE_ASPECT_64_27<<19) +#define DRM_MODE_FLAG_PIC_AR_256_135 \ + (DRM_MODE_PICTURE_ASPECT_256_135<<19) + +#define DRM_MODE_FLAG_ALL (DRM_MODE_FLAG_PHSYNC | \ + DRM_MODE_FLAG_NHSYNC | \ + DRM_MODE_FLAG_PVSYNC | \ + DRM_MODE_FLAG_NVSYNC | \ + DRM_MODE_FLAG_INTERLACE | \ + DRM_MODE_FLAG_DBLSCAN | \ + DRM_MODE_FLAG_CSYNC | \ + DRM_MODE_FLAG_PCSYNC | \ + DRM_MODE_FLAG_NCSYNC | \ + DRM_MODE_FLAG_HSKEW | \ + DRM_MODE_FLAG_DBLCLK | \ + DRM_MODE_FLAG_CLKDIV2 | \ + DRM_MODE_FLAG_3D_MASK) + +/* DPMS flags */ +/* bit compatible with the xorg definitions. */ +#define DRM_MODE_DPMS_ON 0 +#define DRM_MODE_DPMS_STANDBY 1 +#define DRM_MODE_DPMS_SUSPEND 2 +#define DRM_MODE_DPMS_OFF 3 + +/* Scaling mode options */ +#define DRM_MODE_SCALE_NONE 0 /* Unmodified timing (display or + software can still scale) */ +#define DRM_MODE_SCALE_FULLSCREEN 1 /* Full screen, ignore aspect */ +#define DRM_MODE_SCALE_CENTER 2 /* Centered, no scaling */ +#define DRM_MODE_SCALE_ASPECT 3 /* Full screen, preserve aspect */ + +/* Dithering mode options */ +#define DRM_MODE_DITHERING_OFF 0 +#define DRM_MODE_DITHERING_ON 1 +#define DRM_MODE_DITHERING_AUTO 2 + +/* Dirty info options */ +#define DRM_MODE_DIRTY_OFF 0 +#define DRM_MODE_DIRTY_ON 1 +#define DRM_MODE_DIRTY_ANNOTATE 2 + +/* Link Status options */ +#define DRM_MODE_LINK_STATUS_GOOD 0 +#define DRM_MODE_LINK_STATUS_BAD 1 + +/* + * DRM_MODE_ROTATE_ + * + * Signals that a drm plane is been rotated degrees in counter + * clockwise direction. + * + * This define is provided as a convenience, looking up the property id + * using the name->prop id lookup is the preferred method. + */ +#define DRM_MODE_ROTATE_0 (1<<0) +#define DRM_MODE_ROTATE_90 (1<<1) +#define DRM_MODE_ROTATE_180 (1<<2) +#define DRM_MODE_ROTATE_270 (1<<3) + +/* + * DRM_MODE_ROTATE_MASK + * + * Bitmask used to look for drm plane rotations. + */ +#define DRM_MODE_ROTATE_MASK (\ + DRM_MODE_ROTATE_0 | \ + DRM_MODE_ROTATE_90 | \ + DRM_MODE_ROTATE_180 | \ + DRM_MODE_ROTATE_270) + +/* + * DRM_MODE_REFLECT_ + * + * Signals that the contents of a drm plane is reflected along the axis, + * in the same way as mirroring. + * See kerneldoc chapter "Plane Composition Properties" for more details. + * + * This define is provided as a convenience, looking up the property id + * using the name->prop id lookup is the preferred method. + */ +#define DRM_MODE_REFLECT_X (1<<4) +#define DRM_MODE_REFLECT_Y (1<<5) + +/* + * DRM_MODE_REFLECT_MASK + * + * Bitmask used to look for drm plane reflections. + */ +#define DRM_MODE_REFLECT_MASK (\ + DRM_MODE_REFLECT_X | \ + DRM_MODE_REFLECT_Y) + +/* Content Protection Flags */ +#define DRM_MODE_CONTENT_PROTECTION_UNDESIRED 0 +#define DRM_MODE_CONTENT_PROTECTION_DESIRED 1 +#define DRM_MODE_CONTENT_PROTECTION_ENABLED 2 + +/** + * struct drm_mode_modeinfo - Display mode information. + * @clock: pixel clock in kHz + * @hdisplay: horizontal display size + * @hsync_start: horizontal sync start + * @hsync_end: horizontal sync end + * @htotal: horizontal total size + * @hskew: horizontal skew + * @vdisplay: vertical display size + * @vsync_start: vertical sync start + * @vsync_end: vertical sync end + * @vtotal: vertical total size + * @vscan: vertical scan + * @vrefresh: approximate vertical refresh rate in Hz + * @flags: bitmask of misc. flags, see DRM_MODE_FLAG_* defines + * @type: bitmask of type flags, see DRM_MODE_TYPE_* defines + * @name: string describing the mode resolution + * + * This is the user-space API display mode information structure. For the + * kernel version see struct drm_display_mode. + */ +struct drm_mode_modeinfo { + __u32 clock; + __u16 hdisplay; + __u16 hsync_start; + __u16 hsync_end; + __u16 htotal; + __u16 hskew; + __u16 vdisplay; + __u16 vsync_start; + __u16 vsync_end; + __u16 vtotal; + __u16 vscan; + + __u32 vrefresh; + + __u32 flags; + __u32 type; + char name[DRM_DISPLAY_MODE_LEN]; +}; + +struct drm_mode_card_res { + __u64 fb_id_ptr; + __u64 crtc_id_ptr; + __u64 connector_id_ptr; + __u64 encoder_id_ptr; + __u32 count_fbs; + __u32 count_crtcs; + __u32 count_connectors; + __u32 count_encoders; + __u32 min_width; + __u32 max_width; + __u32 min_height; + __u32 max_height; +}; + +struct drm_mode_crtc { + __u64 set_connectors_ptr; + __u32 count_connectors; + + __u32 crtc_id; /**< Id */ + __u32 fb_id; /**< Id of framebuffer */ + + __u32 x; /**< x Position on the framebuffer */ + __u32 y; /**< y Position on the framebuffer */ + + __u32 gamma_size; + __u32 mode_valid; + struct drm_mode_modeinfo mode; +}; + +#define DRM_MODE_PRESENT_TOP_FIELD (1<<0) +#define DRM_MODE_PRESENT_BOTTOM_FIELD (1<<1) + +/* Planes blend with or override other bits on the CRTC */ +struct drm_mode_set_plane { + __u32 plane_id; + __u32 crtc_id; + __u32 fb_id; /* fb object contains surface format type */ + __u32 flags; /* see above flags */ + + /* Signed dest location allows it to be partially off screen */ + __s32 crtc_x; + __s32 crtc_y; + __u32 crtc_w; + __u32 crtc_h; + + /* Source values are 16.16 fixed point */ + __u32 src_x; + __u32 src_y; + __u32 src_h; + __u32 src_w; +}; + +/** + * struct drm_mode_get_plane - Get plane metadata. + * + * Userspace can perform a GETPLANE ioctl to retrieve information about a + * plane. + * + * To retrieve the number of formats supported, set @count_format_types to zero + * and call the ioctl. @count_format_types will be updated with the value. + * + * To retrieve these formats, allocate an array with the memory needed to store + * @count_format_types formats. Point @format_type_ptr to this array and call + * the ioctl again (with @count_format_types still set to the value returned in + * the first ioctl call). + */ +struct drm_mode_get_plane { + /** + * @plane_id: Object ID of the plane whose information should be + * retrieved. Set by caller. + */ + __u32 plane_id; + + /** @crtc_id: Object ID of the current CRTC. */ + __u32 crtc_id; + /** @fb_id: Object ID of the current fb. */ + __u32 fb_id; + + /** + * @possible_crtcs: Bitmask of CRTC's compatible with the plane. CRTC's + * are created and they receive an index, which corresponds to their + * position in the bitmask. Bit N corresponds to + * :ref:`CRTC index` N. + */ + __u32 possible_crtcs; + /** @gamma_size: Never used. */ + __u32 gamma_size; + + /** @count_format_types: Number of formats. */ + __u32 count_format_types; + /** + * @format_type_ptr: Pointer to ``__u32`` array of formats that are + * supported by the plane. These formats do not require modifiers. + */ + __u64 format_type_ptr; +}; + +struct drm_mode_get_plane_res { + __u64 plane_id_ptr; + __u32 count_planes; +}; + +#define DRM_MODE_ENCODER_NONE 0 +#define DRM_MODE_ENCODER_DAC 1 +#define DRM_MODE_ENCODER_TMDS 2 +#define DRM_MODE_ENCODER_LVDS 3 +#define DRM_MODE_ENCODER_TVDAC 4 +#define DRM_MODE_ENCODER_VIRTUAL 5 +#define DRM_MODE_ENCODER_DSI 6 +#define DRM_MODE_ENCODER_DPMST 7 +#define DRM_MODE_ENCODER_DPI 8 + +struct drm_mode_get_encoder { + __u32 encoder_id; + __u32 encoder_type; + + __u32 crtc_id; /**< Id of crtc */ + + __u32 possible_crtcs; + __u32 possible_clones; +}; + +/* This is for connectors with multiple signal types. */ +/* Try to match DRM_MODE_CONNECTOR_X as closely as possible. */ +enum drm_mode_subconnector { + DRM_MODE_SUBCONNECTOR_Automatic = 0, /* DVI-I, TV */ + DRM_MODE_SUBCONNECTOR_Unknown = 0, /* DVI-I, TV, DP */ + DRM_MODE_SUBCONNECTOR_VGA = 1, /* DP */ + DRM_MODE_SUBCONNECTOR_DVID = 3, /* DVI-I DP */ + DRM_MODE_SUBCONNECTOR_DVIA = 4, /* DVI-I */ + DRM_MODE_SUBCONNECTOR_Composite = 5, /* TV */ + DRM_MODE_SUBCONNECTOR_SVIDEO = 6, /* TV */ + DRM_MODE_SUBCONNECTOR_Component = 8, /* TV */ + DRM_MODE_SUBCONNECTOR_SCART = 9, /* TV */ + DRM_MODE_SUBCONNECTOR_DisplayPort = 10, /* DP */ + DRM_MODE_SUBCONNECTOR_HDMIA = 11, /* DP */ + DRM_MODE_SUBCONNECTOR_Native = 15, /* DP */ + DRM_MODE_SUBCONNECTOR_Wireless = 18, /* DP */ +}; + +#define DRM_MODE_CONNECTOR_Unknown 0 +#define DRM_MODE_CONNECTOR_VGA 1 +#define DRM_MODE_CONNECTOR_DVII 2 +#define DRM_MODE_CONNECTOR_DVID 3 +#define DRM_MODE_CONNECTOR_DVIA 4 +#define DRM_MODE_CONNECTOR_Composite 5 +#define DRM_MODE_CONNECTOR_SVIDEO 6 +#define DRM_MODE_CONNECTOR_LVDS 7 +#define DRM_MODE_CONNECTOR_Component 8 +#define DRM_MODE_CONNECTOR_9PinDIN 9 +#define DRM_MODE_CONNECTOR_DisplayPort 10 +#define DRM_MODE_CONNECTOR_HDMIA 11 +#define DRM_MODE_CONNECTOR_HDMIB 12 +#define DRM_MODE_CONNECTOR_TV 13 +#define DRM_MODE_CONNECTOR_eDP 14 +#define DRM_MODE_CONNECTOR_VIRTUAL 15 +#define DRM_MODE_CONNECTOR_DSI 16 +#define DRM_MODE_CONNECTOR_DPI 17 +#define DRM_MODE_CONNECTOR_WRITEBACK 18 +#define DRM_MODE_CONNECTOR_SPI 19 +#define DRM_MODE_CONNECTOR_USB 20 + +/** + * struct drm_mode_get_connector - Get connector metadata. + * + * User-space can perform a GETCONNECTOR ioctl to retrieve information about a + * connector. User-space is expected to retrieve encoders, modes and properties + * by performing this ioctl at least twice: the first time to retrieve the + * number of elements, the second time to retrieve the elements themselves. + * + * To retrieve the number of elements, set @count_props and @count_encoders to + * zero, set @count_modes to 1, and set @modes_ptr to a temporary struct + * drm_mode_modeinfo element. + * + * To retrieve the elements, allocate arrays for @encoders_ptr, @modes_ptr, + * @props_ptr and @prop_values_ptr, then set @count_modes, @count_props and + * @count_encoders to their capacity. + * + * Performing the ioctl only twice may be racy: the number of elements may have + * changed with a hotplug event in-between the two ioctls. User-space is + * expected to retry the last ioctl until the number of elements stabilizes. + * The kernel won't fill any array which doesn't have the expected length. + * + * **Force-probing a connector** + * + * If the @count_modes field is set to zero and the DRM client is the current + * DRM master, the kernel will perform a forced probe on the connector to + * refresh the connector status, modes and EDID. A forced-probe can be slow, + * might cause flickering and the ioctl will block. + * + * User-space needs to force-probe connectors to ensure their metadata is + * up-to-date at startup and after receiving a hot-plug event. User-space + * may perform a forced-probe when the user explicitly requests it. User-space + * shouldn't perform a forced-probe in other situations. + */ +struct drm_mode_get_connector { + /** @encoders_ptr: Pointer to ``__u32`` array of object IDs. */ + __u64 encoders_ptr; + /** @modes_ptr: Pointer to struct drm_mode_modeinfo array. */ + __u64 modes_ptr; + /** @props_ptr: Pointer to ``__u32`` array of property IDs. */ + __u64 props_ptr; + /** @prop_values_ptr: Pointer to ``__u64`` array of property values. */ + __u64 prop_values_ptr; + + /** @count_modes: Number of modes. */ + __u32 count_modes; + /** @count_props: Number of properties. */ + __u32 count_props; + /** @count_encoders: Number of encoders. */ + __u32 count_encoders; + + /** @encoder_id: Object ID of the current encoder. */ + __u32 encoder_id; + /** @connector_id: Object ID of the connector. */ + __u32 connector_id; + /** + * @connector_type: Type of the connector. + * + * See DRM_MODE_CONNECTOR_* defines. + */ + __u32 connector_type; + /** + * @connector_type_id: Type-specific connector number. + * + * This is not an object ID. This is a per-type connector number. Each + * (type, type_id) combination is unique across all connectors of a DRM + * device. + * + * The (type, type_id) combination is not a stable identifier: the + * type_id can change depending on the driver probe order. + */ + __u32 connector_type_id; + + /** + * @connection: Status of the connector. + * + * See enum drm_connector_status. + */ + __u32 connection; + /** @mm_width: Width of the connected sink in millimeters. */ + __u32 mm_width; + /** @mm_height: Height of the connected sink in millimeters. */ + __u32 mm_height; + /** + * @subpixel: Subpixel order of the connected sink. + * + * See enum subpixel_order. + */ + __u32 subpixel; + + /** @pad: Padding, must be zero. */ + __u32 pad; +}; + +#define DRM_MODE_PROP_PENDING (1<<0) /* deprecated, do not use */ +#define DRM_MODE_PROP_RANGE (1<<1) +#define DRM_MODE_PROP_IMMUTABLE (1<<2) +#define DRM_MODE_PROP_ENUM (1<<3) /* enumerated type with text strings */ +#define DRM_MODE_PROP_BLOB (1<<4) +#define DRM_MODE_PROP_BITMASK (1<<5) /* bitmask of enumerated types */ + +/* non-extended types: legacy bitmask, one bit per type: */ +#define DRM_MODE_PROP_LEGACY_TYPE ( \ + DRM_MODE_PROP_RANGE | \ + DRM_MODE_PROP_ENUM | \ + DRM_MODE_PROP_BLOB | \ + DRM_MODE_PROP_BITMASK) + +/* extended-types: rather than continue to consume a bit per type, + * grab a chunk of the bits to use as integer type id. + */ +#define DRM_MODE_PROP_EXTENDED_TYPE 0x0000ffc0 +#define DRM_MODE_PROP_TYPE(n) ((n) << 6) +#define DRM_MODE_PROP_OBJECT DRM_MODE_PROP_TYPE(1) +#define DRM_MODE_PROP_SIGNED_RANGE DRM_MODE_PROP_TYPE(2) + +/* the PROP_ATOMIC flag is used to hide properties from userspace that + * is not aware of atomic properties. This is mostly to work around + * older userspace (DDX drivers) that read/write each prop they find, + * witout being aware that this could be triggering a lengthy modeset. + */ +#define DRM_MODE_PROP_ATOMIC 0x80000000 + +/** + * struct drm_mode_property_enum - Description for an enum/bitfield entry. + * @value: numeric value for this enum entry. + * @name: symbolic name for this enum entry. + * + * See struct drm_property_enum for details. + */ +struct drm_mode_property_enum { + __u64 value; + char name[DRM_PROP_NAME_LEN]; +}; + +/** + * struct drm_mode_get_property - Get property metadata. + * + * User-space can perform a GETPROPERTY ioctl to retrieve information about a + * property. The same property may be attached to multiple objects, see + * "Modeset Base Object Abstraction". + * + * The meaning of the @values_ptr field changes depending on the property type. + * See &drm_property.flags for more details. + * + * The @enum_blob_ptr and @count_enum_blobs fields are only meaningful when the + * property has the type &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK. For + * backwards compatibility, the kernel will always set @count_enum_blobs to + * zero when the property has the type &DRM_MODE_PROP_BLOB. User-space must + * ignore these two fields if the property has a different type. + * + * User-space is expected to retrieve values and enums by performing this ioctl + * at least twice: the first time to retrieve the number of elements, the + * second time to retrieve the elements themselves. + * + * To retrieve the number of elements, set @count_values and @count_enum_blobs + * to zero, then call the ioctl. @count_values will be updated with the number + * of elements. If the property has the type &DRM_MODE_PROP_ENUM or + * &DRM_MODE_PROP_BITMASK, @count_enum_blobs will be updated as well. + * + * To retrieve the elements themselves, allocate an array for @values_ptr and + * set @count_values to its capacity. If the property has the type + * &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK, allocate an array for + * @enum_blob_ptr and set @count_enum_blobs to its capacity. Calling the ioctl + * again will fill the arrays. + */ +struct drm_mode_get_property { + /** @values_ptr: Pointer to a ``__u64`` array. */ + __u64 values_ptr; + /** @enum_blob_ptr: Pointer to a struct drm_mode_property_enum array. */ + __u64 enum_blob_ptr; + + /** + * @prop_id: Object ID of the property which should be retrieved. Set + * by the caller. + */ + __u32 prop_id; + /** + * @flags: ``DRM_MODE_PROP_*`` bitfield. See &drm_property.flags for + * a definition of the flags. + */ + __u32 flags; + /** + * @name: Symbolic property name. User-space should use this field to + * recognize properties. + */ + char name[DRM_PROP_NAME_LEN]; + + /** @count_values: Number of elements in @values_ptr. */ + __u32 count_values; + /** @count_enum_blobs: Number of elements in @enum_blob_ptr. */ + __u32 count_enum_blobs; +}; + +struct drm_mode_connector_set_property { + __u64 value; + __u32 prop_id; + __u32 connector_id; +}; + +#define DRM_MODE_OBJECT_CRTC 0xcccccccc +#define DRM_MODE_OBJECT_CONNECTOR 0xc0c0c0c0 +#define DRM_MODE_OBJECT_ENCODER 0xe0e0e0e0 +#define DRM_MODE_OBJECT_MODE 0xdededede +#define DRM_MODE_OBJECT_PROPERTY 0xb0b0b0b0 +#define DRM_MODE_OBJECT_FB 0xfbfbfbfb +#define DRM_MODE_OBJECT_BLOB 0xbbbbbbbb +#define DRM_MODE_OBJECT_PLANE 0xeeeeeeee +#define DRM_MODE_OBJECT_ANY 0 + +struct drm_mode_obj_get_properties { + __u64 props_ptr; + __u64 prop_values_ptr; + __u32 count_props; + __u32 obj_id; + __u32 obj_type; +}; + +struct drm_mode_obj_set_property { + __u64 value; + __u32 prop_id; + __u32 obj_id; + __u32 obj_type; +}; + +struct drm_mode_get_blob { + __u32 blob_id; + __u32 length; + __u64 data; +}; + +struct drm_mode_fb_cmd { + __u32 fb_id; + __u32 width; + __u32 height; + __u32 pitch; + __u32 bpp; + __u32 depth; + /* driver specific handle */ + __u32 handle; +}; + +#define DRM_MODE_FB_INTERLACED (1<<0) /* for interlaced framebuffers */ +#define DRM_MODE_FB_MODIFIERS (1<<1) /* enables ->modifer[] */ + +/** + * struct drm_mode_fb_cmd2 - Frame-buffer metadata. + * + * This struct holds frame-buffer metadata. There are two ways to use it: + * + * - User-space can fill this struct and perform a &DRM_IOCTL_MODE_ADDFB2 + * ioctl to register a new frame-buffer. The new frame-buffer object ID will + * be set by the kernel in @fb_id. + * - User-space can set @fb_id and perform a &DRM_IOCTL_MODE_GETFB2 ioctl to + * fetch metadata about an existing frame-buffer. + * + * In case of planar formats, this struct allows up to 4 buffer objects with + * offsets and pitches per plane. The pitch and offset order are dictated by + * the format FourCC as defined by ``drm_fourcc.h``, e.g. NV12 is described as: + * + * YUV 4:2:0 image with a plane of 8-bit Y samples followed by an + * interleaved U/V plane containing 8-bit 2x2 subsampled colour difference + * samples. + * + * So it would consist of a Y plane at ``offsets[0]`` and a UV plane at + * ``offsets[1]``. + * + * To accommodate tiled, compressed, etc formats, a modifier can be specified. + * For more information see the "Format Modifiers" section. Note that even + * though it looks like we have a modifier per-plane, we in fact do not. The + * modifier for each plane must be identical. Thus all combinations of + * different data layouts for multi-plane formats must be enumerated as + * separate modifiers. + * + * All of the entries in @handles, @pitches, @offsets and @modifier must be + * zero when unused. Warning, for @offsets and @modifier zero can't be used to + * figure out whether the entry is used or not since it's a valid value (a zero + * offset is common, and a zero modifier is &DRM_FORMAT_MOD_LINEAR). + */ +struct drm_mode_fb_cmd2 { + /** @fb_id: Object ID of the frame-buffer. */ + __u32 fb_id; + /** @width: Width of the frame-buffer. */ + __u32 width; + /** @height: Height of the frame-buffer. */ + __u32 height; + /** + * @pixel_format: FourCC format code, see ``DRM_FORMAT_*`` constants in + * ``drm_fourcc.h``. + */ + __u32 pixel_format; + /** + * @flags: Frame-buffer flags (see &DRM_MODE_FB_INTERLACED and + * &DRM_MODE_FB_MODIFIERS). + */ + __u32 flags; + + /** + * @handles: GEM buffer handle, one per plane. Set to 0 if the plane is + * unused. The same handle can be used for multiple planes. + */ + __u32 handles[4]; + /** @pitches: Pitch (aka. stride) in bytes, one per plane. */ + __u32 pitches[4]; + /** @offsets: Offset into the buffer in bytes, one per plane. */ + __u32 offsets[4]; + /** + * @modifier: Format modifier, one per plane. See ``DRM_FORMAT_MOD_*`` + * constants in ``drm_fourcc.h``. All planes must use the same + * modifier. Ignored unless &DRM_MODE_FB_MODIFIERS is set in @flags. + */ + __u64 modifier[4]; +}; + +#define DRM_MODE_FB_DIRTY_ANNOTATE_COPY 0x01 +#define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02 +#define DRM_MODE_FB_DIRTY_FLAGS 0x03 + +#define DRM_MODE_FB_DIRTY_MAX_CLIPS 256 + +/* + * Mark a region of a framebuffer as dirty. + * + * Some hardware does not automatically update display contents + * as a hardware or software draw to a framebuffer. This ioctl + * allows userspace to tell the kernel and the hardware what + * regions of the framebuffer have changed. + * + * The kernel or hardware is free to update more then just the + * region specified by the clip rects. The kernel or hardware + * may also delay and/or coalesce several calls to dirty into a + * single update. + * + * Userspace may annotate the updates, the annotates are a + * promise made by the caller that the change is either a copy + * of pixels or a fill of a single color in the region specified. + * + * If the DRM_MODE_FB_DIRTY_ANNOTATE_COPY flag is given then + * the number of updated regions are half of num_clips given, + * where the clip rects are paired in src and dst. The width and + * height of each one of the pairs must match. + * + * If the DRM_MODE_FB_DIRTY_ANNOTATE_FILL flag is given the caller + * promises that the region specified of the clip rects is filled + * completely with a single color as given in the color argument. + */ + +struct drm_mode_fb_dirty_cmd { + __u32 fb_id; + __u32 flags; + __u32 color; + __u32 num_clips; + __u64 clips_ptr; +}; + +struct drm_mode_mode_cmd { + __u32 connector_id; + struct drm_mode_modeinfo mode; +}; + +#define DRM_MODE_CURSOR_BO 0x01 +#define DRM_MODE_CURSOR_MOVE 0x02 +#define DRM_MODE_CURSOR_FLAGS 0x03 + +/* + * depending on the value in flags different members are used. + * + * CURSOR_BO uses + * crtc_id + * width + * height + * handle - if 0 turns the cursor off + * + * CURSOR_MOVE uses + * crtc_id + * x + * y + */ +struct drm_mode_cursor { + __u32 flags; + __u32 crtc_id; + __s32 x; + __s32 y; + __u32 width; + __u32 height; + /* driver specific handle */ + __u32 handle; +}; + +struct drm_mode_cursor2 { + __u32 flags; + __u32 crtc_id; + __s32 x; + __s32 y; + __u32 width; + __u32 height; + /* driver specific handle */ + __u32 handle; + __s32 hot_x; + __s32 hot_y; +}; + +struct drm_mode_crtc_lut { + __u32 crtc_id; + __u32 gamma_size; + + /* pointers to arrays */ + __u64 red; + __u64 green; + __u64 blue; +}; + +struct drm_color_ctm { + /* + * Conversion matrix in S31.32 sign-magnitude + * (not two's complement!) format. + * + * out matrix in + * |R| |0 1 2| |R| + * |G| = |3 4 5| x |G| + * |B| |6 7 8| |B| + */ + __u64 matrix[9]; +}; + +struct drm_color_lut { + /* + * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and + * 0xffff == 1.0. + */ + __u16 red; + __u16 green; + __u16 blue; + __u16 reserved; +}; + +/** + * struct hdr_metadata_infoframe - HDR Metadata Infoframe Data. + * + * HDR Metadata Infoframe as per CTA 861.G spec. This is expected + * to match exactly with the spec. + * + * Userspace is expected to pass the metadata information as per + * the format described in this structure. + */ +struct hdr_metadata_infoframe { + /** + * @eotf: Electro-Optical Transfer Function (EOTF) + * used in the stream. + */ + __u8 eotf; + /** + * @metadata_type: Static_Metadata_Descriptor_ID. + */ + __u8 metadata_type; + /** + * @display_primaries: Color Primaries of the Data. + * These are coded as unsigned 16-bit values in units of + * 0.00002, where 0x0000 represents zero and 0xC350 + * represents 1.0000. + * @display_primaries.x: X cordinate of color primary. + * @display_primaries.y: Y cordinate of color primary. + */ + struct { + __u16 x, y; + } display_primaries[3]; + /** + * @white_point: White Point of Colorspace Data. + * These are coded as unsigned 16-bit values in units of + * 0.00002, where 0x0000 represents zero and 0xC350 + * represents 1.0000. + * @white_point.x: X cordinate of whitepoint of color primary. + * @white_point.y: Y cordinate of whitepoint of color primary. + */ + struct { + __u16 x, y; + } white_point; + /** + * @max_display_mastering_luminance: Max Mastering Display Luminance. + * This value is coded as an unsigned 16-bit value in units of 1 cd/m2, + * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2. + */ + __u16 max_display_mastering_luminance; + /** + * @min_display_mastering_luminance: Min Mastering Display Luminance. + * This value is coded as an unsigned 16-bit value in units of + * 0.0001 cd/m2, where 0x0001 represents 0.0001 cd/m2 and 0xFFFF + * represents 6.5535 cd/m2. + */ + __u16 min_display_mastering_luminance; + /** + * @max_cll: Max Content Light Level. + * This value is coded as an unsigned 16-bit value in units of 1 cd/m2, + * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2. + */ + __u16 max_cll; + /** + * @max_fall: Max Frame Average Light Level. + * This value is coded as an unsigned 16-bit value in units of 1 cd/m2, + * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2. + */ + __u16 max_fall; +}; + +/** + * struct hdr_output_metadata - HDR output metadata + * + * Metadata Information to be passed from userspace + */ +struct hdr_output_metadata { + /** + * @metadata_type: Static_Metadata_Descriptor_ID. + */ + __u32 metadata_type; + /** + * @hdmi_metadata_type1: HDR Metadata Infoframe. + */ + union { + struct hdr_metadata_infoframe hdmi_metadata_type1; + }; +}; + +/** + * DRM_MODE_PAGE_FLIP_EVENT + * + * Request that the kernel sends back a vblank event (see + * struct drm_event_vblank) with the &DRM_EVENT_FLIP_COMPLETE type when the + * page-flip is done. + */ +#define DRM_MODE_PAGE_FLIP_EVENT 0x01 +/** + * DRM_MODE_PAGE_FLIP_ASYNC + * + * Request that the page-flip is performed as soon as possible, ie. with no + * delay due to waiting for vblank. This may cause tearing to be visible on + * the screen. + */ +#define DRM_MODE_PAGE_FLIP_ASYNC 0x02 +#define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4 +#define DRM_MODE_PAGE_FLIP_TARGET_RELATIVE 0x8 +#define DRM_MODE_PAGE_FLIP_TARGET (DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE | \ + DRM_MODE_PAGE_FLIP_TARGET_RELATIVE) +/** + * DRM_MODE_PAGE_FLIP_FLAGS + * + * Bitmask of flags suitable for &drm_mode_crtc_page_flip_target.flags. + */ +#define DRM_MODE_PAGE_FLIP_FLAGS (DRM_MODE_PAGE_FLIP_EVENT | \ + DRM_MODE_PAGE_FLIP_ASYNC | \ + DRM_MODE_PAGE_FLIP_TARGET) + +/* + * Request a page flip on the specified crtc. + * + * This ioctl will ask KMS to schedule a page flip for the specified + * crtc. Once any pending rendering targeting the specified fb (as of + * ioctl time) has completed, the crtc will be reprogrammed to display + * that fb after the next vertical refresh. The ioctl returns + * immediately, but subsequent rendering to the current fb will block + * in the execbuffer ioctl until the page flip happens. If a page + * flip is already pending as the ioctl is called, EBUSY will be + * returned. + * + * Flag DRM_MODE_PAGE_FLIP_EVENT requests that drm sends back a vblank + * event (see drm.h: struct drm_event_vblank) when the page flip is + * done. The user_data field passed in with this ioctl will be + * returned as the user_data field in the vblank event struct. + * + * Flag DRM_MODE_PAGE_FLIP_ASYNC requests that the flip happen + * 'as soon as possible', meaning that it not delay waiting for vblank. + * This may cause tearing on the screen. + * + * The reserved field must be zero. + */ + +struct drm_mode_crtc_page_flip { + __u32 crtc_id; + __u32 fb_id; + __u32 flags; + __u32 reserved; + __u64 user_data; +}; + +/* + * Request a page flip on the specified crtc. + * + * Same as struct drm_mode_crtc_page_flip, but supports new flags and + * re-purposes the reserved field: + * + * The sequence field must be zero unless either of the + * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is specified. When + * the ABSOLUTE flag is specified, the sequence field denotes the absolute + * vblank sequence when the flip should take effect. When the RELATIVE + * flag is specified, the sequence field denotes the relative (to the + * current one when the ioctl is called) vblank sequence when the flip + * should take effect. NOTE: DRM_IOCTL_WAIT_VBLANK must still be used to + * make sure the vblank sequence before the target one has passed before + * calling this ioctl. The purpose of the + * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is merely to clarify + * the target for when code dealing with a page flip runs during a + * vertical blank period. + */ + +struct drm_mode_crtc_page_flip_target { + __u32 crtc_id; + __u32 fb_id; + __u32 flags; + __u32 sequence; + __u64 user_data; +}; + +/* create a dumb scanout buffer */ +struct drm_mode_create_dumb { + __u32 height; + __u32 width; + __u32 bpp; + __u32 flags; + /* handle, pitch, size will be returned */ + __u32 handle; + __u32 pitch; + __u64 size; +}; + +/* set up for mmap of a dumb scanout buffer */ +struct drm_mode_map_dumb { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; +}; + +struct drm_mode_destroy_dumb { + __u32 handle; +}; + +/** + * DRM_MODE_ATOMIC_TEST_ONLY + * + * Do not apply the atomic commit, instead check whether the hardware supports + * this configuration. + * + * See &drm_mode_config_funcs.atomic_check for more details on test-only + * commits. + */ +#define DRM_MODE_ATOMIC_TEST_ONLY 0x0100 +/** + * DRM_MODE_ATOMIC_NONBLOCK + * + * Do not block while applying the atomic commit. The &DRM_IOCTL_MODE_ATOMIC + * IOCTL returns immediately instead of waiting for the changes to be applied + * in hardware. Note, the driver will still check that the update can be + * applied before retuning. + */ +#define DRM_MODE_ATOMIC_NONBLOCK 0x0200 +/** + * DRM_MODE_ATOMIC_ALLOW_MODESET + * + * Allow the update to result in temporary or transient visible artifacts while + * the update is being applied. Applying the update may also take significantly + * more time than a page flip. All visual artifacts will disappear by the time + * the update is completed, as signalled through the vblank event's timestamp + * (see struct drm_event_vblank). + * + * This flag must be set when the KMS update might cause visible artifacts. + * Without this flag such KMS update will return a EINVAL error. What kind of + * update may cause visible artifacts depends on the driver and the hardware. + * User-space that needs to know beforehand if an update might cause visible + * artifacts can use &DRM_MODE_ATOMIC_TEST_ONLY without + * &DRM_MODE_ATOMIC_ALLOW_MODESET to see if it fails. + * + * To the best of the driver's knowledge, visual artifacts are guaranteed to + * not appear when this flag is not set. Some sinks might display visual + * artifacts outside of the driver's control. + */ +#define DRM_MODE_ATOMIC_ALLOW_MODESET 0x0400 + +/** + * DRM_MODE_ATOMIC_FLAGS + * + * Bitfield of flags accepted by the &DRM_IOCTL_MODE_ATOMIC IOCTL in + * &drm_mode_atomic.flags. + */ +#define DRM_MODE_ATOMIC_FLAGS (\ + DRM_MODE_PAGE_FLIP_EVENT |\ + DRM_MODE_PAGE_FLIP_ASYNC |\ + DRM_MODE_ATOMIC_TEST_ONLY |\ + DRM_MODE_ATOMIC_NONBLOCK |\ + DRM_MODE_ATOMIC_ALLOW_MODESET) + +struct drm_mode_atomic { + __u32 flags; + __u32 count_objs; + __u64 objs_ptr; + __u64 count_props_ptr; + __u64 props_ptr; + __u64 prop_values_ptr; + __u64 reserved; + __u64 user_data; +}; + +struct drm_format_modifier_blob { +#define FORMAT_BLOB_CURRENT 1 + /* Version of this blob format */ + __u32 version; + + /* Flags */ + __u32 flags; + + /* Number of fourcc formats supported */ + __u32 count_formats; + + /* Where in this blob the formats exist (in bytes) */ + __u32 formats_offset; + + /* Number of drm_format_modifiers */ + __u32 count_modifiers; + + /* Where in this blob the modifiers exist (in bytes) */ + __u32 modifiers_offset; + + /* __u32 formats[] */ + /* struct drm_format_modifier modifiers[] */ +}; + +struct drm_format_modifier { + /* Bitmask of formats in get_plane format list this info applies to. The + * offset allows a sliding window of which 64 formats (bits). + * + * Some examples: + * In today's world with < 65 formats, and formats 0, and 2 are + * supported + * 0x0000000000000005 + * ^-offset = 0, formats = 5 + * + * If the number formats grew to 128, and formats 98-102 are + * supported with the modifier: + * + * 0x0000007c00000000 0000000000000000 + * ^ + * |__offset = 64, formats = 0x7c00000000 + * + */ + __u64 formats; + __u32 offset; + __u32 pad; + + /* The modifier that applies to the >get_plane format list bitmask. */ + __u64 modifier; +}; + +/** + * struct drm_mode_create_blob - Create New blob property + * + * Create a new 'blob' data property, copying length bytes from data pointer, + * and returning new blob ID. + */ +struct drm_mode_create_blob { + /** @data: Pointer to data to copy. */ + __u64 data; + /** @length: Length of data to copy. */ + __u32 length; + /** @blob_id: Return: new property ID. */ + __u32 blob_id; +}; + +/** + * struct drm_mode_destroy_blob - Destroy user blob + * @blob_id: blob_id to destroy + * + * Destroy a user-created blob property. + * + * User-space can release blobs as soon as they do not need to refer to them by + * their blob object ID. For instance, if you are using a MODE_ID blob in an + * atomic commit and you will not make another commit re-using the same ID, you + * can destroy the blob as soon as the commit has been issued, without waiting + * for it to complete. + */ +struct drm_mode_destroy_blob { + __u32 blob_id; +}; + +/** + * struct drm_mode_create_lease - Create lease + * + * Lease mode resources, creating another drm_master. + * + * The @object_ids array must reference at least one CRTC, one connector and + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively, + * the lease can be completely empty. + */ +struct drm_mode_create_lease { + /** @object_ids: Pointer to array of object ids (__u32) */ + __u64 object_ids; + /** @object_count: Number of object ids */ + __u32 object_count; + /** @flags: flags for new FD (O_CLOEXEC, etc) */ + __u32 flags; + + /** @lessee_id: Return: unique identifier for lessee. */ + __u32 lessee_id; + /** @fd: Return: file descriptor to new drm_master file */ + __u32 fd; +}; + +/** + * struct drm_mode_list_lessees - List lessees + * + * List lesses from a drm_master. + */ +struct drm_mode_list_lessees { + /** + * @count_lessees: Number of lessees. + * + * On input, provides length of the array. + * On output, provides total number. No + * more than the input number will be written + * back, so two calls can be used to get + * the size and then the data. + */ + __u32 count_lessees; + /** @pad: Padding. */ + __u32 pad; + + /** + * @lessees_ptr: Pointer to lessees. + * + * Pointer to __u64 array of lessee ids + */ + __u64 lessees_ptr; +}; + +/** + * struct drm_mode_get_lease - Get Lease + * + * Get leased objects. + */ +struct drm_mode_get_lease { + /** + * @count_objects: Number of leased objects. + * + * On input, provides length of the array. + * On output, provides total number. No + * more than the input number will be written + * back, so two calls can be used to get + * the size and then the data. + */ + __u32 count_objects; + /** @pad: Padding. */ + __u32 pad; + + /** + * @objects_ptr: Pointer to objects. + * + * Pointer to __u32 array of object ids. + */ + __u64 objects_ptr; +}; + +/** + * struct drm_mode_revoke_lease - Revoke lease + */ +struct drm_mode_revoke_lease { + /** @lessee_id: Unique ID of lessee */ + __u32 lessee_id; +}; + +/** + * struct drm_mode_rect - Two dimensional rectangle. + * @x1: Horizontal starting coordinate (inclusive). + * @y1: Vertical starting coordinate (inclusive). + * @x2: Horizontal ending coordinate (exclusive). + * @y2: Vertical ending coordinate (exclusive). + * + * With drm subsystem using struct drm_rect to manage rectangular area this + * export it to user-space. + * + * Currently used by drm_mode_atomic blob property FB_DAMAGE_CLIPS. + */ +struct drm_mode_rect { + __s32 x1; + __s32 y1; + __s32 x2; + __s32 y2; +}; + +#if defined(__cplusplus) +} +#endif + +#endif diff --git a/src/linux/intel_gpu_top/i915_drm.h b/src/linux/intel_gpu_top/i915_drm.h new file mode 100644 index 00000000..fe3cf9bc --- /dev/null +++ b/src/linux/intel_gpu_top/i915_drm.h @@ -0,0 +1,3860 @@ +/* + * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas. + * All Rights Reserved. + * + * 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 TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS 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_DRM_H_ +#define _I915_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/* Please note that modifications to all structs defined here are + * subject to backwards-compatibility constraints. + */ + +/** + * DOC: uevents generated by i915 on its device node + * + * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch + * event from the GPU L3 cache. Additional information supplied is ROW, + * BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep + * track of these events, and if a specific cache-line seems to have a + * persistent error, remap it with the L3 remapping tool supplied in + * intel-gpu-tools. The value supplied with the event is always 1. + * + * I915_ERROR_UEVENT - Generated upon error detection, currently only via + * hangcheck. The error detection event is a good indicator of when things + * began to go badly. The value supplied with the event is a 1 upon error + * detection, and a 0 upon reset completion, signifying no more error + * exists. NOTE: Disabling hangcheck or reset via module parameter will + * cause the related events to not be seen. + * + * I915_RESET_UEVENT - Event is generated just before an attempt to reset the + * GPU. The value supplied with the event is always 1. NOTE: Disable + * reset via module parameter will cause this event to not be seen. + */ +#define I915_L3_PARITY_UEVENT "L3_PARITY_ERROR" +#define I915_ERROR_UEVENT "ERROR" +#define I915_RESET_UEVENT "RESET" + +/** + * struct i915_user_extension - Base class for defining a chain of extensions + * + * Many interfaces need to grow over time. In most cases we can simply + * extend the struct and have userspace pass in more data. Another option, + * as demonstrated by Vulkan's approach to providing extensions for forward + * and backward compatibility, is to use a list of optional structs to + * provide those extra details. + * + * The key advantage to using an extension chain is that it allows us to + * redefine the interface more easily than an ever growing struct of + * increasing complexity, and for large parts of that interface to be + * entirely optional. The downside is more pointer chasing; chasing across + * the boundary with pointers encapsulated inside u64. + * + * Example chaining: + * + * .. code-block:: C + * + * struct i915_user_extension ext3 { + * .next_extension = 0, // end + * .name = ..., + * }; + * struct i915_user_extension ext2 { + * .next_extension = (uintptr_t)&ext3, + * .name = ..., + * }; + * struct i915_user_extension ext1 { + * .next_extension = (uintptr_t)&ext2, + * .name = ..., + * }; + * + * Typically the struct i915_user_extension would be embedded in some uAPI + * struct, and in this case we would feed it the head of the chain(i.e ext1), + * which would then apply all of the above extensions. + * + */ +struct i915_user_extension { + /** + * @next_extension: + * + * Pointer to the next struct i915_user_extension, or zero if the end. + */ + __u64 next_extension; + /** + * @name: Name of the extension. + * + * Note that the name here is just some integer. + * + * Also note that the name space for this is not global for the whole + * driver, but rather its scope/meaning is limited to the specific piece + * of uAPI which has embedded the struct i915_user_extension. + */ + __u32 name; + /** + * @flags: MBZ + * + * All undefined bits must be zero. + */ + __u32 flags; + /** + * @rsvd: MBZ + * + * Reserved for future use; must be zero. + */ + __u32 rsvd[4]; +}; + +/* + * MOCS indexes used for GPU surfaces, defining the cacheability of the + * surface data and the coherency for this data wrt. CPU vs. GPU accesses. + */ +enum i915_mocs_table_index { + /* + * Not cached anywhere, coherency between CPU and GPU accesses is + * guaranteed. + */ + I915_MOCS_UNCACHED, + /* + * Cacheability and coherency controlled by the kernel automatically + * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current + * usage of the surface (used for display scanout or not). + */ + I915_MOCS_PTE, + /* + * Cached in all GPU caches available on the platform. + * Coherency between CPU and GPU accesses to the surface is not + * guaranteed without extra synchronization. + */ + I915_MOCS_CACHED, +}; + +/** + * enum drm_i915_gem_engine_class - uapi engine type enumeration + * + * Different engines serve different roles, and there may be more than one + * engine serving each role. This enum provides a classification of the role + * of the engine, which may be used when requesting operations to be performed + * on a certain subset of engines, or for providing information about that + * group. + */ +enum drm_i915_gem_engine_class { + /** + * @I915_ENGINE_CLASS_RENDER: + * + * Render engines support instructions used for 3D, Compute (GPGPU), + * and programmable media workloads. These instructions fetch data and + * dispatch individual work items to threads that operate in parallel. + * The threads run small programs (called "kernels" or "shaders") on + * the GPU's execution units (EUs). + */ + I915_ENGINE_CLASS_RENDER = 0, + + /** + * @I915_ENGINE_CLASS_COPY: + * + * Copy engines (also referred to as "blitters") support instructions + * that move blocks of data from one location in memory to another, + * or that fill a specified location of memory with fixed data. + * Copy engines can perform pre-defined logical or bitwise operations + * on the source, destination, or pattern data. + */ + I915_ENGINE_CLASS_COPY = 1, + + /** + * @I915_ENGINE_CLASS_VIDEO: + * + * Video engines (also referred to as "bit stream decode" (BSD) or + * "vdbox") support instructions that perform fixed-function media + * decode and encode. + */ + I915_ENGINE_CLASS_VIDEO = 2, + + /** + * @I915_ENGINE_CLASS_VIDEO_ENHANCE: + * + * Video enhancement engines (also referred to as "vebox") support + * instructions related to image enhancement. + */ + I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + + /** + * @I915_ENGINE_CLASS_COMPUTE: + * + * Compute engines support a subset of the instructions available + * on render engines: compute engines support Compute (GPGPU) and + * programmable media workloads, but do not support the 3D pipeline. + */ + I915_ENGINE_CLASS_COMPUTE = 4, + + /* Values in this enum should be kept compact. */ + + /** + * @I915_ENGINE_CLASS_INVALID: + * + * Placeholder value to represent an invalid engine class assignment. + */ + I915_ENGINE_CLASS_INVALID = -1 +}; + +/** + * struct i915_engine_class_instance - Engine class/instance identifier + * + * There may be more than one engine fulfilling any role within the system. + * Each engine of a class is given a unique instance number and therefore + * any engine can be specified by its class:instance tuplet. APIs that allow + * access to any engine in the system will use struct i915_engine_class_instance + * for this identification. + */ +struct i915_engine_class_instance { + /** + * @engine_class: + * + * Engine class from enum drm_i915_gem_engine_class + */ + __u16 engine_class; +#define I915_ENGINE_CLASS_INVALID_NONE -1 +#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 + + /** + * @engine_instance: + * + * Engine instance. + */ + __u16 engine_instance; +}; + +/** + * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 + * + */ + +enum drm_i915_pmu_engine_sample { + I915_SAMPLE_BUSY = 0, + I915_SAMPLE_WAIT = 1, + I915_SAMPLE_SEMA = 2 +}; + +#define I915_PMU_SAMPLE_BITS (4) +#define I915_PMU_SAMPLE_MASK (0xf) +#define I915_PMU_SAMPLE_INSTANCE_BITS (8) +#define I915_PMU_CLASS_SHIFT \ + (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS) + +#define __I915_PMU_ENGINE(class, instance, sample) \ + ((class) << I915_PMU_CLASS_SHIFT | \ + (instance) << I915_PMU_SAMPLE_BITS | \ + (sample)) + +#define I915_PMU_ENGINE_BUSY(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY) + +#define I915_PMU_ENGINE_WAIT(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT) + +#define I915_PMU_ENGINE_SEMA(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) + +/* + * Top 4 bits of every non-engine counter are GT id. + */ +#define __I915_PMU_GT_SHIFT (60) + +#define ___I915_PMU_OTHER(gt, x) \ + (((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \ + ((__u64)(gt) << __I915_PMU_GT_SHIFT)) + +#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x) + +#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) +#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) +#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) +#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) +#define I915_PMU_SOFTWARE_GT_AWAKE_TIME __I915_PMU_OTHER(4) + +#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY + +#define __I915_PMU_ACTUAL_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 0) +#define __I915_PMU_REQUESTED_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 1) +#define __I915_PMU_INTERRUPTS(gt) ___I915_PMU_OTHER(gt, 2) +#define __I915_PMU_RC6_RESIDENCY(gt) ___I915_PMU_OTHER(gt, 3) +#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt) ___I915_PMU_OTHER(gt, 4) + +/* Each region is a minimum of 16k, and there are at most 255 of them. + */ +#define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use + * of chars for next/prev indices */ +#define I915_LOG_MIN_TEX_REGION_SIZE 14 + +typedef struct _drm_i915_init { + enum { + I915_INIT_DMA = 0x01, + I915_CLEANUP_DMA = 0x02, + I915_RESUME_DMA = 0x03 + } func; + unsigned int mmio_offset; + int sarea_priv_offset; + unsigned int ring_start; + unsigned int ring_end; + unsigned int ring_size; + unsigned int front_offset; + unsigned int back_offset; + unsigned int depth_offset; + unsigned int w; + unsigned int h; + unsigned int pitch; + unsigned int pitch_bits; + unsigned int back_pitch; + unsigned int depth_pitch; + unsigned int cpp; + unsigned int chipset; +} drm_i915_init_t; + +typedef struct _drm_i915_sarea { + struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1]; + int last_upload; /* last time texture was uploaded */ + int last_enqueue; /* last time a buffer was enqueued */ + int last_dispatch; /* age of the most recently dispatched buffer */ + int ctxOwner; /* last context to upload state */ + int texAge; + int pf_enabled; /* is pageflipping allowed? */ + int pf_active; + int pf_current_page; /* which buffer is being displayed? */ + int perf_boxes; /* performance boxes to be displayed */ + int width, height; /* screen size in pixels */ + + drm_handle_t front_handle; + int front_offset; + int front_size; + + drm_handle_t back_handle; + int back_offset; + int back_size; + + drm_handle_t depth_handle; + int depth_offset; + int depth_size; + + drm_handle_t tex_handle; + int tex_offset; + int tex_size; + int log_tex_granularity; + int pitch; + int rotation; /* 0, 90, 180 or 270 */ + int rotated_offset; + int rotated_size; + int rotated_pitch; + int virtualX, virtualY; + + unsigned int front_tiled; + unsigned int back_tiled; + unsigned int depth_tiled; + unsigned int rotated_tiled; + unsigned int rotated2_tiled; + + int pipeA_x; + int pipeA_y; + int pipeA_w; + int pipeA_h; + int pipeB_x; + int pipeB_y; + int pipeB_w; + int pipeB_h; + + /* fill out some space for old userspace triple buffer */ + drm_handle_t unused_handle; + __u32 unused1, unused2, unused3; + + /* buffer object handles for static buffers. May change + * over the lifetime of the client. + */ + __u32 front_bo_handle; + __u32 back_bo_handle; + __u32 unused_bo_handle; + __u32 depth_bo_handle; + +} drm_i915_sarea_t; + +/* due to userspace building against these headers we need some compat here */ +#define planeA_x pipeA_x +#define planeA_y pipeA_y +#define planeA_w pipeA_w +#define planeA_h pipeA_h +#define planeB_x pipeB_x +#define planeB_y pipeB_y +#define planeB_w pipeB_w +#define planeB_h pipeB_h + +/* Flags for perf_boxes + */ +#define I915_BOX_RING_EMPTY 0x1 +#define I915_BOX_FLIP 0x2 +#define I915_BOX_WAIT 0x4 +#define I915_BOX_TEXTURE_LOAD 0x8 +#define I915_BOX_LOST_CONTEXT 0x10 + +/* + * i915 specific ioctls. + * + * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie + * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset + * against DRM_COMMAND_BASE and should be between [0x0, 0x60). + */ +#define DRM_I915_INIT 0x00 +#define DRM_I915_FLUSH 0x01 +#define DRM_I915_FLIP 0x02 +#define DRM_I915_BATCHBUFFER 0x03 +#define DRM_I915_IRQ_EMIT 0x04 +#define DRM_I915_IRQ_WAIT 0x05 +#define DRM_I915_GETPARAM 0x06 +#define DRM_I915_SETPARAM 0x07 +#define DRM_I915_ALLOC 0x08 +#define DRM_I915_FREE 0x09 +#define DRM_I915_INIT_HEAP 0x0a +#define DRM_I915_CMDBUFFER 0x0b +#define DRM_I915_DESTROY_HEAP 0x0c +#define DRM_I915_SET_VBLANK_PIPE 0x0d +#define DRM_I915_GET_VBLANK_PIPE 0x0e +#define DRM_I915_VBLANK_SWAP 0x0f +#define DRM_I915_HWS_ADDR 0x11 +#define DRM_I915_GEM_INIT 0x13 +#define DRM_I915_GEM_EXECBUFFER 0x14 +#define DRM_I915_GEM_PIN 0x15 +#define DRM_I915_GEM_UNPIN 0x16 +#define DRM_I915_GEM_BUSY 0x17 +#define DRM_I915_GEM_THROTTLE 0x18 +#define DRM_I915_GEM_ENTERVT 0x19 +#define DRM_I915_GEM_LEAVEVT 0x1a +#define DRM_I915_GEM_CREATE 0x1b +#define DRM_I915_GEM_PREAD 0x1c +#define DRM_I915_GEM_PWRITE 0x1d +#define DRM_I915_GEM_MMAP 0x1e +#define DRM_I915_GEM_SET_DOMAIN 0x1f +#define DRM_I915_GEM_SW_FINISH 0x20 +#define DRM_I915_GEM_SET_TILING 0x21 +#define DRM_I915_GEM_GET_TILING 0x22 +#define DRM_I915_GEM_GET_APERTURE 0x23 +#define DRM_I915_GEM_MMAP_GTT 0x24 +#define DRM_I915_GET_PIPE_FROM_CRTC_ID 0x25 +#define DRM_I915_GEM_MADVISE 0x26 +#define DRM_I915_OVERLAY_PUT_IMAGE 0x27 +#define DRM_I915_OVERLAY_ATTRS 0x28 +#define DRM_I915_GEM_EXECBUFFER2 0x29 +#define DRM_I915_GEM_EXECBUFFER2_WR DRM_I915_GEM_EXECBUFFER2 +#define DRM_I915_GET_SPRITE_COLORKEY 0x2a +#define DRM_I915_SET_SPRITE_COLORKEY 0x2b +#define DRM_I915_GEM_WAIT 0x2c +#define DRM_I915_GEM_CONTEXT_CREATE 0x2d +#define DRM_I915_GEM_CONTEXT_DESTROY 0x2e +#define DRM_I915_GEM_SET_CACHING 0x2f +#define DRM_I915_GEM_GET_CACHING 0x30 +#define DRM_I915_REG_READ 0x31 +#define DRM_I915_GET_RESET_STATS 0x32 +#define DRM_I915_GEM_USERPTR 0x33 +#define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 +#define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 +#define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 +#define DRM_I915_QUERY 0x39 +#define DRM_I915_GEM_VM_CREATE 0x3a +#define DRM_I915_GEM_VM_DESTROY 0x3b +#define DRM_I915_GEM_CREATE_EXT 0x3c +/* Must be kept compact -- no holes */ + +#define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) +#define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) +#define DRM_IOCTL_I915_FLIP DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP) +#define DRM_IOCTL_I915_BATCHBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t) +#define DRM_IOCTL_I915_IRQ_EMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t) +#define DRM_IOCTL_I915_IRQ_WAIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t) +#define DRM_IOCTL_I915_GETPARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t) +#define DRM_IOCTL_I915_SETPARAM DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t) +#define DRM_IOCTL_I915_ALLOC DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t) +#define DRM_IOCTL_I915_FREE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t) +#define DRM_IOCTL_I915_INIT_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t) +#define DRM_IOCTL_I915_CMDBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t) +#define DRM_IOCTL_I915_DESTROY_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t) +#define DRM_IOCTL_I915_SET_VBLANK_PIPE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t) +#define DRM_IOCTL_I915_GET_VBLANK_PIPE DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t) +#define DRM_IOCTL_I915_VBLANK_SWAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t) +#define DRM_IOCTL_I915_HWS_ADDR DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init) +#define DRM_IOCTL_I915_GEM_INIT DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init) +#define DRM_IOCTL_I915_GEM_EXECBUFFER DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer) +#define DRM_IOCTL_I915_GEM_EXECBUFFER2 DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2) +#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2) +#define DRM_IOCTL_I915_GEM_PIN DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin) +#define DRM_IOCTL_I915_GEM_UNPIN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin) +#define DRM_IOCTL_I915_GEM_BUSY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy) +#define DRM_IOCTL_I915_GEM_SET_CACHING DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching) +#define DRM_IOCTL_I915_GEM_GET_CACHING DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching) +#define DRM_IOCTL_I915_GEM_THROTTLE DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE) +#define DRM_IOCTL_I915_GEM_ENTERVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT) +#define DRM_IOCTL_I915_GEM_LEAVEVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT) +#define DRM_IOCTL_I915_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create) +#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext) +#define DRM_IOCTL_I915_GEM_PREAD DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread) +#define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) +#define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) +#define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt) +#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset) +#define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain) +#define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish) +#define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling) +#define DRM_IOCTL_I915_GEM_GET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling) +#define DRM_IOCTL_I915_GEM_GET_APERTURE DRM_IOR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture) +#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id) +#define DRM_IOCTL_I915_GEM_MADVISE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise) +#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image) +#define DRM_IOCTL_I915_OVERLAY_ATTRS DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs) +#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) +#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) +#define DRM_IOCTL_I915_GEM_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait) +#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create) +#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext) +#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy) +#define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read) +#define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats) +#define DRM_IOCTL_I915_GEM_USERPTR DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr) +#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) +#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) +#define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) +#define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query) +#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control) +#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control) + +/* Allow drivers to submit batchbuffers directly to hardware, relying + * on the security mechanisms provided by hardware. + */ +typedef struct drm_i915_batchbuffer { + int start; /* agp offset */ + int used; /* nr bytes in use */ + int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */ + int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */ + int num_cliprects; /* mulitpass with multiple cliprects? */ + struct drm_clip_rect *cliprects; /* pointer to userspace cliprects */ +} drm_i915_batchbuffer_t; + +/* As above, but pass a pointer to userspace buffer which can be + * validated by the kernel prior to sending to hardware. + */ +typedef struct _drm_i915_cmdbuffer { + char *buf; /* pointer to userspace command buffer */ + int sz; /* nr bytes in buf */ + int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */ + int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */ + int num_cliprects; /* mulitpass with multiple cliprects? */ + struct drm_clip_rect *cliprects; /* pointer to userspace cliprects */ +} drm_i915_cmdbuffer_t; + +/* Userspace can request & wait on irq's: + */ +typedef struct drm_i915_irq_emit { + int *irq_seq; +} drm_i915_irq_emit_t; + +typedef struct drm_i915_irq_wait { + int irq_seq; +} drm_i915_irq_wait_t; + +/* + * Different modes of per-process Graphics Translation Table, + * see I915_PARAM_HAS_ALIASING_PPGTT + */ +#define I915_GEM_PPGTT_NONE 0 +#define I915_GEM_PPGTT_ALIASING 1 +#define I915_GEM_PPGTT_FULL 2 + +/* Ioctl to query kernel params: + */ +#define I915_PARAM_IRQ_ACTIVE 1 +#define I915_PARAM_ALLOW_BATCHBUFFER 2 +#define I915_PARAM_LAST_DISPATCH 3 +#define I915_PARAM_CHIPSET_ID 4 +#define I915_PARAM_HAS_GEM 5 +#define I915_PARAM_NUM_FENCES_AVAIL 6 +#define I915_PARAM_HAS_OVERLAY 7 +#define I915_PARAM_HAS_PAGEFLIPPING 8 +#define I915_PARAM_HAS_EXECBUF2 9 +#define I915_PARAM_HAS_BSD 10 +#define I915_PARAM_HAS_BLT 11 +#define I915_PARAM_HAS_RELAXED_FENCING 12 +#define I915_PARAM_HAS_COHERENT_RINGS 13 +#define I915_PARAM_HAS_EXEC_CONSTANTS 14 +#define I915_PARAM_HAS_RELAXED_DELTA 15 +#define I915_PARAM_HAS_GEN7_SOL_RESET 16 +#define I915_PARAM_HAS_LLC 17 +#define I915_PARAM_HAS_ALIASING_PPGTT 18 +#define I915_PARAM_HAS_WAIT_TIMEOUT 19 +#define I915_PARAM_HAS_SEMAPHORES 20 +#define I915_PARAM_HAS_PRIME_VMAP_FLUSH 21 +#define I915_PARAM_HAS_VEBOX 22 +#define I915_PARAM_HAS_SECURE_BATCHES 23 +#define I915_PARAM_HAS_PINNED_BATCHES 24 +#define I915_PARAM_HAS_EXEC_NO_RELOC 25 +#define I915_PARAM_HAS_EXEC_HANDLE_LUT 26 +#define I915_PARAM_HAS_WT 27 +#define I915_PARAM_CMD_PARSER_VERSION 28 +#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29 +#define I915_PARAM_MMAP_VERSION 30 +#define I915_PARAM_HAS_BSD2 31 +#define I915_PARAM_REVISION 32 +#define I915_PARAM_SUBSLICE_TOTAL 33 +#define I915_PARAM_EU_TOTAL 34 +#define I915_PARAM_HAS_GPU_RESET 35 +#define I915_PARAM_HAS_RESOURCE_STREAMER 36 +#define I915_PARAM_HAS_EXEC_SOFTPIN 37 +#define I915_PARAM_HAS_POOLED_EU 38 +#define I915_PARAM_MIN_EU_IN_POOL 39 +#define I915_PARAM_MMAP_GTT_VERSION 40 + +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution + * priorities and the driver will attempt to execute batches in priority order. + * The param returns a capability bitmask, nonzero implies that the scheduler + * is enabled, with different features present according to the mask. + * + * The initial priority for each batch is supplied by the context and is + * controlled via I915_CONTEXT_PARAM_PRIORITY. + */ +#define I915_PARAM_HAS_SCHEDULER 41 +#define I915_SCHEDULER_CAP_ENABLED (1ul << 0) +#define I915_SCHEDULER_CAP_PRIORITY (1ul << 1) +#define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2) +#define I915_SCHEDULER_CAP_SEMAPHORES (1ul << 3) +#define I915_SCHEDULER_CAP_ENGINE_BUSY_STATS (1ul << 4) +/* + * Indicates the 2k user priority levels are statically mapped into 3 buckets as + * follows: + * + * -1k to -1 Low priority + * 0 Normal priority + * 1 to 1k Highest priority + */ +#define I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP (1ul << 5) + +/* + * Query the status of HuC load. + * + * The query can fail in the following scenarios with the listed error codes: + * -ENODEV if HuC is not present on this platform, + * -EOPNOTSUPP if HuC firmware usage is disabled, + * -ENOPKG if HuC firmware fetch failed, + * -ENOEXEC if HuC firmware is invalid or mismatched, + * -ENOMEM if i915 failed to prepare the FW objects for transfer to the uC, + * -EIO if the FW transfer or the FW authentication failed. + * + * If the IOCTL is successful, the returned parameter will be set to one of the + * following values: + * * 0 if HuC firmware load is not complete, + * * 1 if HuC firmware is loaded and fully authenticated, + * * 2 if HuC firmware is loaded and authenticated for clear media only + */ +#define I915_PARAM_HUC_STATUS 42 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of + * synchronisation with implicit fencing on individual objects. + * See EXEC_OBJECT_ASYNC. + */ +#define I915_PARAM_HAS_EXEC_ASYNC 43 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support - + * both being able to pass in a sync_file fd to wait upon before executing, + * and being able to return a new sync_file fd that is signaled when the + * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT. + */ +#define I915_PARAM_HAS_EXEC_FENCE 44 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture + * user-specified buffers for post-mortem debugging of GPU hangs. See + * EXEC_OBJECT_CAPTURE. + */ +#define I915_PARAM_HAS_EXEC_CAPTURE 45 + +#define I915_PARAM_SLICE_MASK 46 + +/* Assuming it's uniform for each slice, this queries the mask of subslices + * per-slice for this system. + */ +#define I915_PARAM_SUBSLICE_MASK 47 + +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer + * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST. + */ +#define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + +/* + * Query whether every context (both per-file default and user created) is + * isolated (insofar as HW supports). If this parameter is not true, then + * freshly created contexts may inherit values from an existing context, + * rather than default HW values. If true, it also ensures (insofar as HW + * supports) that all state set by this context will not leak to any other + * context. + * + * As not every engine across every gen support contexts, the returned + * value reports the support of context isolation for individual engines by + * returning a bitmask of each engine class set to true if that class supports + * isolation. + */ +#define I915_PARAM_HAS_CONTEXT_ISOLATION 50 + +/* Frequency of the command streamer timestamps given by the *_TIMESTAMP + * registers. This used to be fixed per platform but from CNL onwards, this + * might vary depending on the parts. + */ +#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 + +/* + * Once upon a time we supposed that writes through the GGTT would be + * immediately in physical memory (once flushed out of the CPU path). However, + * on a few different processors and chipsets, this is not necessarily the case + * as the writes appear to be buffered internally. Thus a read of the backing + * storage (physical memory) via a different path (with different physical tags + * to the indirect write via the GGTT) will see stale values from before + * the GGTT write. Inside the kernel, we can for the most part keep track of + * the different read/write domains in use (e.g. set-domain), but the assumption + * of coherency is baked into the ABI, hence reporting its true state in this + * parameter. + * + * Reports true when writes via mmap_gtt are immediately visible following an + * lfence to flush the WCB. + * + * Reports false when writes via mmap_gtt are indeterminately delayed in an in + * internal buffer and are _not_ immediately visible to third parties accessing + * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC + * communications channel when reporting false is strongly disadvised. + */ +#define I915_PARAM_MMAP_GTT_COHERENT 52 + +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel + * execution through use of explicit fence support. + * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. + */ +#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 + +/* + * Revision of the i915-perf uAPI. The value returned helps determine what + * i915-perf features are available. See drm_i915_perf_property_id. + */ +#define I915_PARAM_PERF_REVISION 54 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See + * I915_EXEC_USE_EXTENSIONS. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + +/* Query if the kernel supports the I915_USERPTR_PROBE flag. */ +#define I915_PARAM_HAS_USERPTR_PROBE 56 + +/* + * Frequency of the timestamps in OA reports. This used to be the same as the CS + * timestamp frequency, but differs on some platforms. + */ +#define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57 + +/* + * Query the status of PXP support in i915. + * + * The query can fail in the following scenarios with the listed error codes: + * -ENODEV = PXP support is not available on the GPU device or in the + * kernel due to missing component drivers or kernel configs. + * + * If the IOCTL is successful, the returned parameter will be set to one of + * the following values: + * 1 = PXP feature is supported and is ready for use. + * 2 = PXP feature is supported but should be ready soon (pending + * initialization of non-i915 system dependencies). + * + * NOTE: When param is supported (positive return values), user space should + * still refer to the GEM PXP context-creation UAPI header specs to be + * aware of possible failure due to system state machine at the time. + */ +#define I915_PARAM_PXP_STATUS 58 + +/* Must be kept compact -- no holes and well documented */ + +/** + * struct drm_i915_getparam - Driver parameter query structure. + */ +struct drm_i915_getparam { + /** @param: Driver parameter to query. */ + __s32 param; + + /** + * @value: Address of memory where queried value should be put. + * + * WARNING: Using pointers instead of fixed-size u64 means we need to write + * compat32 code. Don't repeat this mistake. + */ + int *value; +}; + +/** + * typedef drm_i915_getparam_t - Driver parameter query structure. + * See struct drm_i915_getparam. + */ +typedef struct drm_i915_getparam drm_i915_getparam_t; + +/* Ioctl to set kernel params: + */ +#define I915_SETPARAM_USE_MI_BATCHBUFFER_START 1 +#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2 +#define I915_SETPARAM_ALLOW_BATCHBUFFER 3 +#define I915_SETPARAM_NUM_USED_FENCES 4 +/* Must be kept compact -- no holes */ + +typedef struct drm_i915_setparam { + int param; + int value; +} drm_i915_setparam_t; + +/* A memory manager for regions of shared memory: + */ +#define I915_MEM_REGION_AGP 1 + +typedef struct drm_i915_mem_alloc { + int region; + int alignment; + int size; + int *region_offset; /* offset from start of fb or agp */ +} drm_i915_mem_alloc_t; + +typedef struct drm_i915_mem_free { + int region; + int region_offset; +} drm_i915_mem_free_t; + +typedef struct drm_i915_mem_init_heap { + int region; + int size; + int start; +} drm_i915_mem_init_heap_t; + +/* Allow memory manager to be torn down and re-initialized (eg on + * rotate): + */ +typedef struct drm_i915_mem_destroy_heap { + int region; +} drm_i915_mem_destroy_heap_t; + +/* Allow X server to configure which pipes to monitor for vblank signals + */ +#define DRM_I915_VBLANK_PIPE_A 1 +#define DRM_I915_VBLANK_PIPE_B 2 + +typedef struct drm_i915_vblank_pipe { + int pipe; +} drm_i915_vblank_pipe_t; + +/* Schedule buffer swap at given vertical blank: + */ +typedef struct drm_i915_vblank_swap { + drm_drawable_t drawable; + enum drm_vblank_seq_type seqtype; + unsigned int sequence; +} drm_i915_vblank_swap_t; + +typedef struct drm_i915_hws_addr { + __u64 addr; +} drm_i915_hws_addr_t; + +struct drm_i915_gem_init { + /** + * Beginning offset in the GTT to be managed by the DRM memory + * manager. + */ + __u64 gtt_start; + /** + * Ending offset in the GTT to be managed by the DRM memory + * manager. + */ + __u64 gtt_end; +}; + +struct drm_i915_gem_create { + /** + * Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + */ + __u64 size; + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + __u32 pad; +}; + +struct drm_i915_gem_pread { + /** Handle for the object being read. */ + __u32 handle; + __u32 pad; + /** Offset into the object to read from */ + __u64 offset; + /** Length of data to read */ + __u64 size; + /** + * Pointer to write the data into. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 data_ptr; +}; + +struct drm_i915_gem_pwrite { + /** Handle for the object being written to. */ + __u32 handle; + __u32 pad; + /** Offset into the object to write to */ + __u64 offset; + /** Length of data to write */ + __u64 size; + /** + * Pointer to read the data from. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 data_ptr; +}; + +struct drm_i915_gem_mmap { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** Offset in the object to map. */ + __u64 offset; + /** + * Length of data to map. + * + * The value will be page-aligned. + */ + __u64 size; + /** + * Returned pointer the data was mapped at. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 addr_ptr; + + /** + * Flags for extended behaviour. + * + * Added in version 2. + */ + __u64 flags; +#define I915_MMAP_WC 0x1 +}; + +struct drm_i915_gem_mmap_gtt { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; +}; + +/** + * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object. + * + * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl, + * and is used to retrieve the fake offset to mmap an object specified by &handle. + * + * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+. + * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave + * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`. + */ +struct drm_i915_gem_mmap_offset { + /** @handle: Handle for the object being mapped. */ + __u32 handle; + /** @pad: Must be zero */ + __u32 pad; + /** + * @offset: The fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; + + /** + * @flags: Flags for extended behaviour. + * + * It is mandatory that one of the `MMAP_OFFSET` types + * should be included: + * + * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined) + * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching. + * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching. + * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching. + * + * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid + * type. On devices without local memory, this caching mode is invalid. + * + * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will + * be used, depending on the object placement on creation. WB will be used + * when the object can only exist in system memory, WC otherwise. + */ + __u64 flags; + +#define I915_MMAP_OFFSET_GTT 0 +#define I915_MMAP_OFFSET_WC 1 +#define I915_MMAP_OFFSET_WB 2 +#define I915_MMAP_OFFSET_UC 3 +#define I915_MMAP_OFFSET_FIXED 4 + + /** + * @extensions: Zero-terminated chain of extensions. + * + * No current extensions defined; mbz. + */ + __u64 extensions; +}; + +/** + * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in + * preparation for accessing the pages via some CPU domain. + * + * Specifying a new write or read domain will flush the object out of the + * previous domain(if required), before then updating the objects domain + * tracking with the new domain. + * + * Note this might involve waiting for the object first if it is still active on + * the GPU. + * + * Supported values for @read_domains and @write_domain: + * + * - I915_GEM_DOMAIN_WC: Uncached write-combined domain + * - I915_GEM_DOMAIN_CPU: CPU cache domain + * - I915_GEM_DOMAIN_GTT: Mappable aperture domain + * + * All other domains are rejected. + * + * Note that for discrete, starting from DG1, this is no longer supported, and + * is instead rejected. On such platforms the CPU domain is effectively static, + * where we also only support a single &drm_i915_gem_mmap_offset cache mode, + * which can't be set explicitly and instead depends on the object placements, + * as per the below. + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. + * + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + */ +struct drm_i915_gem_set_domain { + /** @handle: Handle for the object. */ + __u32 handle; + + /** @read_domains: New read domains. */ + __u32 read_domains; + + /** + * @write_domain: New write domain. + * + * Note that having something in the write domain implies it's in the + * read domain, and only that read domain. + */ + __u32 write_domain; +}; + +struct drm_i915_gem_sw_finish { + /** Handle for the object */ + __u32 handle; +}; + +struct drm_i915_gem_relocation_entry { + /** + * Handle of the buffer being pointed to by this relocation entry. + * + * It's appealing to make this be an index into the mm_validate_entry + * list to refer to the buffer, but this allows the driver to create + * a relocation list for state buffers and not re-write it per + * exec using the buffer. + */ + __u32 target_handle; + + /** + * Value to be added to the offset of the target buffer to make up + * the relocation entry. + */ + __u32 delta; + + /** Offset in the buffer the relocation entry will be written into */ + __u64 offset; + + /** + * Offset value of the target buffer that the relocation entry was last + * written as. + * + * If the buffer has the same offset as last time, we can skip syncing + * and writing the relocation. This value is written back out by + * the execbuffer ioctl when the relocation is written. + */ + __u64 presumed_offset; + + /** + * Target memory domains read by this operation. + */ + __u32 read_domains; + + /** + * Target memory domains written by this operation. + * + * Note that only one domain may be written by the whole + * execbuffer operation, so that where there are conflicts, + * the application will get -EINVAL back. + */ + __u32 write_domain; +}; + +/** @{ + * Intel memory domains + * + * Most of these just align with the various caches in + * the system and are used to flush and invalidate as + * objects end up cached in different domains. + */ +/** CPU cache */ +#define I915_GEM_DOMAIN_CPU 0x00000001 +/** Render cache, used by 2D and 3D drawing */ +#define I915_GEM_DOMAIN_RENDER 0x00000002 +/** Sampler cache, used by texture engine */ +#define I915_GEM_DOMAIN_SAMPLER 0x00000004 +/** Command queue, used to load batch buffers */ +#define I915_GEM_DOMAIN_COMMAND 0x00000008 +/** Instruction cache, used by shader programs */ +#define I915_GEM_DOMAIN_INSTRUCTION 0x00000010 +/** Vertex address cache */ +#define I915_GEM_DOMAIN_VERTEX 0x00000020 +/** GTT domain - aperture and scanout */ +#define I915_GEM_DOMAIN_GTT 0x00000040 +/** WC domain - uncached access */ +#define I915_GEM_DOMAIN_WC 0x00000080 +/** @} */ + +struct drm_i915_gem_exec_object { + /** + * User's handle for a buffer to be bound into the GTT for this + * operation. + */ + __u32 handle; + + /** Number of relocations to be performed on this buffer */ + __u32 relocation_count; + /** + * Pointer to array of struct drm_i915_gem_relocation_entry containing + * the relocations to be performed in this buffer. + */ + __u64 relocs_ptr; + + /** Required alignment in graphics aperture */ + __u64 alignment; + + /** + * Returned value of the updated offset of the object, for future + * presumed_offset writes. + */ + __u64 offset; +}; + +/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */ +struct drm_i915_gem_execbuffer { + /** + * List of buffers to be validated with their relocations to be + * performend on them. + * + * This is a pointer to an array of struct drm_i915_gem_validate_entry. + * + * These buffers must be listed in an order such that all relocations + * a buffer is performing refer to buffers that have already appeared + * in the validate list. + */ + __u64 buffers_ptr; + __u32 buffer_count; + + /** Offset in the batchbuffer to start execution from. */ + __u32 batch_start_offset; + /** Bytes used in batchbuffer from batch_start_offset */ + __u32 batch_len; + __u32 DR1; + __u32 DR4; + __u32 num_cliprects; + /** This is a struct drm_clip_rect *cliprects */ + __u64 cliprects_ptr; +}; + +struct drm_i915_gem_exec_object2 { + /** + * User's handle for a buffer to be bound into the GTT for this + * operation. + */ + __u32 handle; + + /** Number of relocations to be performed on this buffer */ + __u32 relocation_count; + /** + * Pointer to array of struct drm_i915_gem_relocation_entry containing + * the relocations to be performed in this buffer. + */ + __u64 relocs_ptr; + + /** Required alignment in graphics aperture */ + __u64 alignment; + + /** + * When the EXEC_OBJECT_PINNED flag is specified this is populated by + * the user with the GTT offset at which this object will be pinned. + * + * When the I915_EXEC_NO_RELOC flag is specified this must contain the + * presumed_offset of the object. + * + * During execbuffer2 the kernel populates it with the value of the + * current GTT offset of the object, for future presumed_offset writes. + * + * See struct drm_i915_gem_create_ext for the rules when dealing with + * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with + * minimum page sizes, like DG2. + */ + __u64 offset; + +#define EXEC_OBJECT_NEEDS_FENCE (1<<0) +#define EXEC_OBJECT_NEEDS_GTT (1<<1) +#define EXEC_OBJECT_WRITE (1<<2) +#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3) +#define EXEC_OBJECT_PINNED (1<<4) +#define EXEC_OBJECT_PAD_TO_SIZE (1<<5) +/* The kernel implicitly tracks GPU activity on all GEM objects, and + * synchronises operations with outstanding rendering. This includes + * rendering on other devices if exported via dma-buf. However, sometimes + * this tracking is too coarse and the user knows better. For example, + * if the object is split into non-overlapping ranges shared between different + * clients or engines (i.e. suballocating objects), the implicit tracking + * by kernel assumes that each operation affects the whole object rather + * than an individual range, causing needless synchronisation between clients. + * The kernel will also forgo any CPU cache flushes prior to rendering from + * the object as the client is expected to be also handling such domain + * tracking. + * + * The kernel maintains the implicit tracking in order to manage resources + * used by the GPU - this flag only disables the synchronisation prior to + * rendering with this object in this execbuf. + * + * Opting out of implicit synhronisation requires the user to do its own + * explicit tracking to avoid rendering corruption. See, for example, + * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously. + */ +#define EXEC_OBJECT_ASYNC (1<<6) +/* Request that the contents of this execobject be copied into the error + * state upon a GPU hang involving this batch for post-mortem debugging. + * These buffers are recorded in no particular order as "user" in + * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see + * if the kernel supports this flag. + */ +#define EXEC_OBJECT_CAPTURE (1<<7) +/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */ +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1) + __u64 flags; + + union { + __u64 rsvd1; + __u64 pad_to_size; + }; + __u64 rsvd2; +}; + +/** + * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf + * ioctl. + * + * The request will wait for input fence to signal before submission. + * + * The returned output fence will be signaled after the completion of the + * request. + */ +struct drm_i915_gem_exec_fence { + /** @handle: User's handle for a drm_syncobj to wait on or signal. */ + __u32 handle; + + /** + * @flags: Supported flags are: + * + * I915_EXEC_FENCE_WAIT: + * Wait for the input fence before request submission. + * + * I915_EXEC_FENCE_SIGNAL: + * Return request completion fence as output + */ + __u32 flags; +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) +#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1)) +}; + +/** + * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences + * for execbuf ioctl. + * + * This structure describes an array of drm_syncobj and associated points for + * timeline variants of drm_syncobj. It is invalid to append this structure to + * the execbuf if I915_EXEC_FENCE_ARRAY is set. + */ +struct drm_i915_gem_execbuffer_ext_timeline_fences { +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + + /** + * @fence_count: Number of elements in the @handles_ptr & @value_ptr + * arrays. + */ + __u64 fence_count; + + /** + * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence + * of length @fence_count. + */ + __u64 handles_ptr; + + /** + * @values_ptr: Pointer to an array of u64 values of length + * @fence_count. + * Values must be 0 for a binary drm_syncobj. A Value of 0 for a + * timeline drm_syncobj is invalid as it turns a drm_syncobj into a + * binary one. + */ + __u64 values_ptr; +}; + +/** + * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2 + * ioctl. + */ +struct drm_i915_gem_execbuffer2 { + /** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */ + __u64 buffers_ptr; + + /** @buffer_count: Number of elements in @buffers_ptr array */ + __u32 buffer_count; + + /** + * @batch_start_offset: Offset in the batchbuffer to start execution + * from. + */ + __u32 batch_start_offset; + + /** + * @batch_len: Length in bytes of the batch buffer, starting from the + * @batch_start_offset. If 0, length is assumed to be the batch buffer + * object size. + */ + __u32 batch_len; + + /** @DR1: deprecated */ + __u32 DR1; + + /** @DR4: deprecated */ + __u32 DR4; + + /** @num_cliprects: See @cliprects_ptr */ + __u32 num_cliprects; + + /** + * @cliprects_ptr: Kernel clipping was a DRI1 misfeature. + * + * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or + * I915_EXEC_USE_EXTENSIONS flags are not set. + * + * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array + * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the + * array. + * + * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a + * single &i915_user_extension and num_cliprects is 0. + */ + __u64 cliprects_ptr; + + /** @flags: Execbuf flags */ + __u64 flags; +#define I915_EXEC_RING_MASK (0x3f) +#define I915_EXEC_DEFAULT (0<<0) +#define I915_EXEC_RENDER (1<<0) +#define I915_EXEC_BSD (2<<0) +#define I915_EXEC_BLT (3<<0) +#define I915_EXEC_VEBOX (4<<0) + +/* Used for switching the constants addressing mode on gen4+ RENDER ring. + * Gen6+ only supports relative addressing to dynamic state (default) and + * absolute addressing. + * + * These flags are ignored for the BSD and BLT rings. + */ +#define I915_EXEC_CONSTANTS_MASK (3<<6) +#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */ +#define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6) +#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */ + +/** Resets the SO write offset registers for transform feedback on gen7. */ +#define I915_EXEC_GEN7_SOL_RESET (1<<8) + +/** Request a privileged ("secure") batch buffer. Note only available for + * DRM_ROOT_ONLY | DRM_MASTER processes. + */ +#define I915_EXEC_SECURE (1<<9) + +/** Inform the kernel that the batch is and will always be pinned. This + * negates the requirement for a workaround to be performed to avoid + * an incoherent CS (such as can be found on 830/845). If this flag is + * not passed, the kernel will endeavour to make sure the batch is + * coherent with the CS before execution. If this flag is passed, + * userspace assumes the responsibility for ensuring the same. + */ +#define I915_EXEC_IS_PINNED (1<<10) + +/** Provide a hint to the kernel that the command stream and auxiliary + * state buffers already holds the correct presumed addresses and so the + * relocation process may be skipped if no buffers need to be moved in + * preparation for the execbuffer. + */ +#define I915_EXEC_NO_RELOC (1<<11) + +/** Use the reloc.handle as an index into the exec object array rather + * than as the per-file handle. + */ +#define I915_EXEC_HANDLE_LUT (1<<12) + +/** Used for switching BSD rings on the platforms with two BSD rings */ +#define I915_EXEC_BSD_SHIFT (13) +#define I915_EXEC_BSD_MASK (3 << I915_EXEC_BSD_SHIFT) +/* default ping-pong mode */ +#define I915_EXEC_BSD_DEFAULT (0 << I915_EXEC_BSD_SHIFT) +#define I915_EXEC_BSD_RING1 (1 << I915_EXEC_BSD_SHIFT) +#define I915_EXEC_BSD_RING2 (2 << I915_EXEC_BSD_SHIFT) + +/** Tell the kernel that the batchbuffer is processed by + * the resource streamer. + */ +#define I915_EXEC_RESOURCE_STREAMER (1<<15) + +/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_IN (1<<16) + +/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd + * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given + * to the caller, and it should be close() after use. (The fd is a regular + * file descriptor and will be cleaned up on process termination. It holds + * a reference to the request, but nothing else.) + * + * The sync_file fd can be combined with other sync_file and passed either + * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip + * will only occur after this request completes), or to other devices. + * + * Using I915_EXEC_FENCE_OUT requires use of + * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written + * back to userspace. Failure to do so will cause the out-fence to always + * be reported as zero, and the real fence fd to be leaked. + */ +#define I915_EXEC_FENCE_OUT (1<<17) + +/* + * Traditionally the execbuf ioctl has only considered the final element in + * the execobject[] to be the executable batch. Often though, the client + * will known the batch object prior to construction and being able to place + * it into the execobject[] array first can simplify the relocation tracking. + * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the + * execobject[] as the * batch instead (the default is to use the last + * element). + */ +#define I915_EXEC_BATCH_FIRST (1<<18) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +/* + * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_SUBMIT (1 << 20) + +/* + * Setting I915_EXEC_USE_EXTENSIONS implies that + * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked + * list of i915_user_extension. Each i915_user_extension node is the base of a + * larger structure. The list of supported structures are listed in the + * drm_i915_gem_execbuffer_ext enum. + */ +#define I915_EXEC_USE_EXTENSIONS (1 << 21) +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) + + /** @rsvd1: Context id */ + __u64 rsvd1; + + /** + * @rsvd2: in and out sync_file file descriptors. + * + * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the + * lower 32 bits of this field will have the in sync_file fd (input). + * + * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this + * field will have the out sync_file fd (output). + */ + __u64 rsvd2; +}; + +#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) +#define i915_execbuffer2_set_context_id(eb2, context) \ + (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK +#define i915_execbuffer2_get_context_id(eb2) \ + ((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK) + +struct drm_i915_gem_pin { + /** Handle of the buffer to be pinned. */ + __u32 handle; + __u32 pad; + + /** alignment required within the aperture */ + __u64 alignment; + + /** Returned GTT offset of the buffer. */ + __u64 offset; +}; + +struct drm_i915_gem_unpin { + /** Handle of the buffer to be unpinned. */ + __u32 handle; + __u32 pad; +}; + +struct drm_i915_gem_busy { + /** Handle of the buffer to check for busy */ + __u32 handle; + + /** Return busy status + * + * A return of 0 implies that the object is idle (after + * having flushed any pending activity), and a non-zero return that + * the object is still in-flight on the GPU. (The GPU has not yet + * signaled completion for all pending requests that reference the + * object.) An object is guaranteed to become idle eventually (so + * long as no new GPU commands are executed upon it). Due to the + * asynchronous nature of the hardware, an object reported + * as busy may become idle before the ioctl is completed. + * + * Furthermore, if the object is busy, which engine is busy is only + * provided as a guide and only indirectly by reporting its class + * (there may be more than one engine in each class). There are race + * conditions which prevent the report of which engines are busy from + * being always accurate. However, the converse is not true. If the + * object is idle, the result of the ioctl, that all engines are idle, + * is accurate. + * + * The returned dword is split into two fields to indicate both + * the engine classes on which the object is being read, and the + * engine class on which it is currently being written (if any). + * + * The low word (bits 0:15) indicate if the object is being written + * to by any engine (there can only be one, as the GEM implicit + * synchronisation rules force writes to be serialised). Only the + * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as + * 1 not 0 etc) for the last write is reported. + * + * The high word (bits 16:31) are a bitmask of which engines classes + * are currently reading from the object. Multiple engines may be + * reading from the object simultaneously. + * + * The value of each engine class is the same as specified in the + * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e. + * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc. + * Some hardware may have parallel execution engines, e.g. multiple + * media engines, which are mapped to the same class identifier and so + * are not separately reported for busyness. + * + * Caveat emptor: + * Only the boolean result of this query is reliable; that is whether + * the object is idle or busy. The report of which engines are busy + * should be only used as a heuristic. + */ + __u32 busy; +}; + +/** + * struct drm_i915_gem_caching - Set or get the caching for given object + * handle. + * + * Allow userspace to control the GTT caching bits for a given object when the + * object is later mapped through the ppGTT(or GGTT on older platforms lacking + * ppGTT support, or if the object is used for scanout). Note that this might + * require unbinding the object from the GTT first, if its current caching value + * doesn't match. + * + * Note that this all changes on discrete platforms, starting from DG1, the + * set/get caching is no longer supported, and is now rejected. Instead the CPU + * caching attributes(WB vs WC) will become an immutable creation time property + * for the object, along with the GTT caching level. For now we don't expose any + * new uAPI for this, instead on DG1 this is all implicit, although this largely + * shouldn't matter since DG1 is coherent by default(without any way of + * controlling it). + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. + * + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + * + * Side note: Part of the reason for this is that changing the at-allocation-time CPU + * caching attributes for the pages might be required(and is expensive) if we + * need to then CPU map the pages later with different caching attributes. This + * inconsistent caching behaviour, while supported on x86, is not universally + * supported on other architectures. So for simplicity we opt for setting + * everything at creation time, whilst also making it immutable, on discrete + * platforms. + */ +struct drm_i915_gem_caching { + /** + * @handle: Handle of the buffer to set/get the caching level. + */ + __u32 handle; + + /** + * @caching: The GTT caching level to apply or possible return value. + * + * The supported @caching values: + * + * I915_CACHING_NONE: + * + * GPU access is not coherent with CPU caches. Default for machines + * without an LLC. This means manual flushing might be needed, if we + * want GPU access to be coherent. + * + * I915_CACHING_CACHED: + * + * GPU access is coherent with CPU caches and furthermore the data is + * cached in last-level caches shared between CPU cores and the GPU GT. + * + * I915_CACHING_DISPLAY: + * + * Special GPU caching mode which is coherent with the scanout engines. + * Transparently falls back to I915_CACHING_NONE on platforms where no + * special cache mode (like write-through or gfdt flushing) is + * available. The kernel automatically sets this mode when using a + * buffer as a scanout target. Userspace can manually set this mode to + * avoid a costly stall and clflush in the hotpath of drawing the first + * frame. + */ +#define I915_CACHING_NONE 0 +#define I915_CACHING_CACHED 1 +#define I915_CACHING_DISPLAY 2 + __u32 caching; +}; + +#define I915_TILING_NONE 0 +#define I915_TILING_X 1 +#define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ +#define I915_TILING_LAST I915_TILING_Y + +#define I915_BIT_6_SWIZZLE_NONE 0 +#define I915_BIT_6_SWIZZLE_9 1 +#define I915_BIT_6_SWIZZLE_9_10 2 +#define I915_BIT_6_SWIZZLE_9_11 3 +#define I915_BIT_6_SWIZZLE_9_10_11 4 +/* Not seen by userland */ +#define I915_BIT_6_SWIZZLE_UNKNOWN 5 +/* Seen by userland. */ +#define I915_BIT_6_SWIZZLE_9_17 6 +#define I915_BIT_6_SWIZZLE_9_10_17 7 + +struct drm_i915_gem_set_tiling { + /** Handle of the buffer to have its tiling state updated */ + __u32 handle; + + /** + * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X, + * I915_TILING_Y). + * + * This value is to be set on request, and will be updated by the + * kernel on successful return with the actual chosen tiling layout. + * + * The tiling mode may be demoted to I915_TILING_NONE when the system + * has bit 6 swizzling that can't be managed correctly by GEM. + * + * Buffer contents become undefined when changing tiling_mode. + */ + __u32 tiling_mode; + + /** + * Stride in bytes for the object when in I915_TILING_X or + * I915_TILING_Y. + */ + __u32 stride; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping. + */ + __u32 swizzle_mode; +}; + +struct drm_i915_gem_get_tiling { + /** Handle of the buffer to get tiling state for. */ + __u32 handle; + + /** + * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X, + * I915_TILING_Y). + */ + __u32 tiling_mode; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping. + */ + __u32 swizzle_mode; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping whilst bound. + */ + __u32 phys_swizzle_mode; +}; + +struct drm_i915_gem_get_aperture { + /** Total size of the aperture used by i915_gem_execbuffer, in bytes */ + __u64 aper_size; + + /** + * Available space in the aperture used by i915_gem_execbuffer, in + * bytes + */ + __u64 aper_available_size; +}; + +struct drm_i915_get_pipe_from_crtc_id { + /** ID of CRTC being requested **/ + __u32 crtc_id; + + /** pipe of requested CRTC **/ + __u32 pipe; +}; + +#define I915_MADV_WILLNEED 0 +#define I915_MADV_DONTNEED 1 +#define __I915_MADV_PURGED 2 /* internal state */ + +struct drm_i915_gem_madvise { + /** Handle of the buffer to change the backing store advice */ + __u32 handle; + + /* Advice: either the buffer will be needed again in the near future, + * or won't be and could be discarded under memory pressure. + */ + __u32 madv; + + /** Whether the backing store still exists. */ + __u32 retained; +}; + +/* flags */ +#define I915_OVERLAY_TYPE_MASK 0xff +#define I915_OVERLAY_YUV_PLANAR 0x01 +#define I915_OVERLAY_YUV_PACKED 0x02 +#define I915_OVERLAY_RGB 0x03 + +#define I915_OVERLAY_DEPTH_MASK 0xff00 +#define I915_OVERLAY_RGB24 0x1000 +#define I915_OVERLAY_RGB16 0x2000 +#define I915_OVERLAY_RGB15 0x3000 +#define I915_OVERLAY_YUV422 0x0100 +#define I915_OVERLAY_YUV411 0x0200 +#define I915_OVERLAY_YUV420 0x0300 +#define I915_OVERLAY_YUV410 0x0400 + +#define I915_OVERLAY_SWAP_MASK 0xff0000 +#define I915_OVERLAY_NO_SWAP 0x000000 +#define I915_OVERLAY_UV_SWAP 0x010000 +#define I915_OVERLAY_Y_SWAP 0x020000 +#define I915_OVERLAY_Y_AND_UV_SWAP 0x030000 + +#define I915_OVERLAY_FLAGS_MASK 0xff000000 +#define I915_OVERLAY_ENABLE 0x01000000 + +struct drm_intel_overlay_put_image { + /* various flags and src format description */ + __u32 flags; + /* source picture description */ + __u32 bo_handle; + /* stride values and offsets are in bytes, buffer relative */ + __u16 stride_Y; /* stride for packed formats */ + __u16 stride_UV; + __u32 offset_Y; /* offset for packet formats */ + __u32 offset_U; + __u32 offset_V; + /* in pixels */ + __u16 src_width; + __u16 src_height; + /* to compensate the scaling factors for partially covered surfaces */ + __u16 src_scan_width; + __u16 src_scan_height; + /* output crtc description */ + __u32 crtc_id; + __u16 dst_x; + __u16 dst_y; + __u16 dst_width; + __u16 dst_height; +}; + +/* flags */ +#define I915_OVERLAY_UPDATE_ATTRS (1<<0) +#define I915_OVERLAY_UPDATE_GAMMA (1<<1) +#define I915_OVERLAY_DISABLE_DEST_COLORKEY (1<<2) +struct drm_intel_overlay_attrs { + __u32 flags; + __u32 color_key; + __s32 brightness; + __u32 contrast; + __u32 saturation; + __u32 gamma0; + __u32 gamma1; + __u32 gamma2; + __u32 gamma3; + __u32 gamma4; + __u32 gamma5; +}; + +/* + * Intel sprite handling + * + * Color keying works with a min/mask/max tuple. Both source and destination + * color keying is allowed. + * + * Source keying: + * Sprite pixels within the min & max values, masked against the color channels + * specified in the mask field, will be transparent. All other pixels will + * be displayed on top of the primary plane. For RGB surfaces, only the min + * and mask fields will be used; ranged compares are not allowed. + * + * Destination keying: + * Primary plane pixels that match the min value, masked against the color + * channels specified in the mask field, will be replaced by corresponding + * pixels from the sprite plane. + * + * Note that source & destination keying are exclusive; only one can be + * active on a given plane. + */ + +#define I915_SET_COLORKEY_NONE (1<<0) /* Deprecated. Instead set + * flags==0 to disable colorkeying. + */ +#define I915_SET_COLORKEY_DESTINATION (1<<1) +#define I915_SET_COLORKEY_SOURCE (1<<2) +struct drm_intel_sprite_colorkey { + __u32 plane_id; + __u32 min_value; + __u32 channel_mask; + __u32 max_value; + __u32 flags; +}; + +struct drm_i915_gem_wait { + /** Handle of BO we shall wait on */ + __u32 bo_handle; + __u32 flags; + /** Number of nanoseconds to wait, Returns time remaining. */ + __s64 timeout_ns; +}; + +struct drm_i915_gem_context_create { + __u32 ctx_id; /* output: id of new context*/ + __u32 pad; +}; + +/** + * struct drm_i915_gem_context_create_ext - Structure for creating contexts. + */ +struct drm_i915_gem_context_create_ext { + /** @ctx_id: Id of the created context (output) */ + __u32 ctx_id; + + /** + * @flags: Supported flags are: + * + * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS: + * + * Extensions may be appended to this structure and driver must check + * for those. See @extensions. + * + * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE + * + * Created context will have single timeline. + */ + __u32 flags; +#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) +#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) +#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ + (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) + + /** + * @extensions: Zero-terminated chain of extensions. + * + * I915_CONTEXT_CREATE_EXT_SETPARAM: + * Context parameter to set or query during context creation. + * See struct drm_i915_gem_context_create_ext_setparam. + * + * I915_CONTEXT_CREATE_EXT_CLONE: + * This extension has been removed. On the off chance someone somewhere + * has attempted to use it, never re-use this extension number. + */ + __u64 extensions; +#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 +#define I915_CONTEXT_CREATE_EXT_CLONE 1 +}; + +/** + * struct drm_i915_gem_context_param - Context parameter to set or query. + */ +struct drm_i915_gem_context_param { + /** @ctx_id: Context id */ + __u32 ctx_id; + + /** @size: Size of the parameter @value */ + __u32 size; + + /** @param: Parameter to set or query */ + __u64 param; +#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 +/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance + * someone somewhere has attempted to use it, never re-use this context + * param number. + */ +#define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 +#define I915_CONTEXT_PARAM_GTT_SIZE 0x3 +#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 +#define I915_CONTEXT_PARAM_BANNABLE 0x5 +#define I915_CONTEXT_PARAM_PRIORITY 0x6 +#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ +#define I915_CONTEXT_DEFAULT_PRIORITY 0 +#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ + /* + * When using the following param, value should be a pointer to + * drm_i915_gem_context_param_sseu. + */ +#define I915_CONTEXT_PARAM_SSEU 0x7 + +/* + * Not all clients may want to attempt automatic recover of a context after + * a hang (for example, some clients may only submit very small incremental + * batches relying on known logical state of previous batches which will never + * recover correctly and each attempt will hang), and so would prefer that + * the context is forever banned instead. + * + * If set to false (0), after a reset, subsequent (and in flight) rendering + * from this context is discarded, and the client will need to create a new + * context to use instead. + * + * If set to true (1), the kernel will automatically attempt to recover the + * context by skipping the hanging batch and executing the next batch starting + * from the default context state (discarding the incomplete logical context + * state lost due to the reset). + * + * On creation, all new contexts are marked as recoverable. + */ +#define I915_CONTEXT_PARAM_RECOVERABLE 0x8 + + /* + * The id of the associated virtual memory address space (ppGTT) of + * this context. Can be retrieved and passed to another context + * (on the same fd) for both to use the same ppGTT and so share + * address layouts, and avoid reloading the page tables on context + * switches between themselves. + * + * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY. + */ +#define I915_CONTEXT_PARAM_VM 0x9 + +/* + * I915_CONTEXT_PARAM_ENGINES: + * + * Bind this context to operate on this subset of available engines. Henceforth, + * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as + * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0] + * and upwards. Slots 0...N are filled in using the specified (class, instance). + * Use + * engine_class: I915_ENGINE_CLASS_INVALID, + * engine_instance: I915_ENGINE_CLASS_INVALID_NONE + * to specify a gap in the array that can be filled in later, e.g. by a + * virtual engine used for load balancing. + * + * Setting the number of engines bound to the context to 0, by passing a zero + * sized argument, will revert back to default settings. + * + * See struct i915_context_param_engines. + * + * Extensions: + * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) + * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) + */ +#define I915_CONTEXT_PARAM_ENGINES 0xa + +/* + * I915_CONTEXT_PARAM_PERSISTENCE: + * + * Allow the context and active rendering to survive the process until + * completion. Persistence allows fire-and-forget clients to queue up a + * bunch of work, hand the output over to a display server and then quit. + * If the context is marked as not persistent, upon closing (either via + * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure + * or process termination), the context and any outstanding requests will be + * cancelled (and exported fences for cancelled requests marked as -EIO). + * + * By default, new contexts allow persistence. + */ +#define I915_CONTEXT_PARAM_PERSISTENCE 0xb + +/* This API has been removed. On the off chance someone somewhere has + * attempted to use it, never re-use this context param number. + */ +#define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + * -ENXIO: A dependency such as a component driver or firmware is not yet + * loaded so user space may need to attempt again. Depending on the + * device, this error may be reported if protected context creation is + * attempted very early after kernel start because the internal timeout + * waiting for such dependencies is not guaranteed to be larger than + * required (numbers differ depending on system and kernel config): + * - ADL/RPL: dependencies may take up to 3 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * - MTL: dependencies may take up to 8 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * NOTE: such dependencies happen once, so a subsequent call to create a + * protected context after a prior successful call will not experience + * such timeouts and will not return -ENXIO (unless the driver is reloaded, + * or, depending on the device, resumes from a suspended state). + * -EIO: The firmware did not succeed in creating the protected context. + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd +/* Must be kept compact -- no holes and well documented */ + + /** @value: Context parameter value to be set or queried */ + __u64 value; +}; + +/* + * Context SSEU programming + * + * It may be necessary for either functional or performance reason to configure + * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ + * Sub-slice/EU). + * + * This is done by configuring SSEU configuration using the below + * @struct drm_i915_gem_context_param_sseu for every supported engine which + * userspace intends to use. + * + * Not all GPUs or engines support this functionality in which case an error + * code -ENODEV will be returned. + * + * Also, flexibility of possible SSEU configuration permutations varies between + * GPU generations and software imposed limitations. Requesting such a + * combination will return an error code of -EINVAL. + * + * NOTE: When perf/OA is active the context's SSEU configuration is ignored in + * favour of a single global setting. + */ +struct drm_i915_gem_context_param_sseu { + /* + * Engine class & instance to be configured or queried. + */ + struct i915_engine_class_instance engine; + + /* + * Unknown flags must be cleared to zero. + */ + __u32 flags; +#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0) + + /* + * Mask of slices to enable for the context. Valid values are a subset + * of the bitmask value returned for I915_PARAM_SLICE_MASK. + */ + __u64 slice_mask; + + /* + * Mask of subslices to enable for the context. Valid values are a + * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK. + */ + __u64 subslice_mask; + + /* + * Minimum/Maximum number of EUs to enable per subslice for the + * context. min_eus_per_subslice must be inferior or equal to + * max_eus_per_subslice. + */ + __u16 min_eus_per_subslice; + __u16 max_eus_per_subslice; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 rsvd; +}; + +/** + * DOC: Virtual Engine uAPI + * + * Virtual engine is a concept where userspace is able to configure a set of + * physical engines, submit a batch buffer, and let the driver execute it on any + * engine from the set as it sees fit. + * + * This is primarily useful on parts which have multiple instances of a same + * class engine, like for example GT3+ Skylake parts with their two VCS engines. + * + * For instance userspace can enumerate all engines of a certain class using the + * previously described `Engine Discovery uAPI`_. After that userspace can + * create a GEM context with a placeholder slot for the virtual engine (using + * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class + * and instance respectively) and finally using the + * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in + * the same reserved slot. + * + * Example of creating a virtual engine and submitting a batch buffer to it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = { + * .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE, + * .engine_index = 0, // Place this virtual engine into engine map slot 0 + * .num_siblings = 2, + * .engines = { { I915_ENGINE_CLASS_VIDEO, 0 }, + * { I915_ENGINE_CLASS_VIDEO, 1 }, }, + * }; + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = { + * .engines = { { I915_ENGINE_CLASS_INVALID, + * I915_ENGINE_CLASS_INVALID_NONE } }, + * .extensions = to_user_pointer(&virtual), // Chains after load_balance extension + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // Now we have created a GEM context with its engine map containing a + * // single virtual engine. Submissions to this slot can go either to + * // vcs0 or vcs1, depending on the load balancing algorithm used inside + * // the driver. The load balancing is dynamic from one batch buffer to + * // another and transparent to userspace. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0 which is the virtual engine + * gem_execbuf(drm_fd, &execbuf); + */ + +/* + * i915_context_engines_load_balance: + * + * Enable load balancing across this set of engines. + * + * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when + * used will proxy the execbuffer request onto one of the set of engines + * in such a way as to distribute the load evenly across the set. + * + * The set of engines must be compatible (e.g. the same HW class) as they + * will share the same logical GPU context and ring. + * + * To intermix rendering with the virtual engine and direct rendering onto + * the backing engines (bypassing the load balancing proxy), the context must + * be defined to use a single timeline for all engines. + */ +struct i915_context_engines_load_balance { + struct i915_user_extension base; + + __u16 engine_index; + __u16 num_siblings; + __u32 flags; /* all undefined flags must be zero */ + + __u64 mbz64; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 num_siblings; \ + __u32 flags; \ + __u64 mbz64; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/* + * i915_context_engines_bond: + * + * Constructed bonded pairs for execution within a virtual engine. + * + * All engines are equal, but some are more equal than others. Given + * the distribution of resources in the HW, it may be preferable to run + * a request on a given subset of engines in parallel to a request on a + * specific engine. We enable this selection of engines within a virtual + * engine by specifying bonding pairs, for any given master engine we will + * only execute on one of the corresponding siblings within the virtual engine. + * + * To execute a request in parallel on the master engine and a sibling requires + * coordination with a I915_EXEC_FENCE_SUBMIT. + */ +struct i915_context_engines_bond { + struct i915_user_extension base; + + struct i915_engine_class_instance master; + + __u16 virtual_index; /* index of virtual engine in ctx->engines[] */ + __u16 num_bonds; + + __u64 flags; /* all undefined flags must be zero */ + __u64 mbz64[4]; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ + struct i915_user_extension base; \ + struct i915_engine_class_instance master; \ + __u16 virtual_index; \ + __u16 num_bonds; \ + __u64 flags; \ + __u64 mbz64[4]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[]; + +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** + * DOC: Context Engine Map uAPI + * + * Context engine map is a new way of addressing engines when submitting batch- + * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT` + * inside the flags field of `struct drm_i915_gem_execbuffer2`. + * + * To use it created GEM contexts need to be configured with a list of engines + * the user is intending to submit to. This is accomplished using the + * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct + * i915_context_param_engines`. + * + * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the + * configured map. + * + * Example of creating such context and submitting against it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = { + * .engines = { { I915_ENGINE_CLASS_RENDER, 0 }, + * { I915_ENGINE_CLASS_COPY, 0 } } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // We have now created a GEM context with two engines in the map: + * // Index 0 points to rcs0 while index 1 points to bcs0. Other engines + * // will not be accessible from this context. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + */ + +struct i915_context_param_engines { + __u64 extensions; /* linked chain of extension blocks, 0 terminates */ +#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ +#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ + struct i915_engine_class_instance engines[]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ + __u64 extensions; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** + * struct drm_i915_gem_context_create_ext_setparam - Context parameter + * to set or query during context creation. + */ +struct drm_i915_gem_context_create_ext_setparam { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + + /** + * @param: Context parameter to set or query. + * See struct drm_i915_gem_context_param. + */ + struct drm_i915_gem_context_param param; +}; + +struct drm_i915_gem_context_destroy { + __u32 ctx_id; + __u32 pad; +}; + +/** + * struct drm_i915_gem_vm_control - Structure to create or destroy VM. + * + * DRM_I915_GEM_VM_CREATE - + * + * Create a new virtual memory address space (ppGTT) for use within a context + * on the same file. Extensions can be provided to configure exactly how the + * address space is setup upon creation. + * + * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is + * returned in the outparam @id. + * + * An extension chain maybe provided, starting with @extensions, and terminated + * by the @next_extension being 0. Currently, no extensions are defined. + * + * DRM_I915_GEM_VM_DESTROY - + * + * Destroys a previously created VM id, specified in @vm_id. + * + * No extensions or flags are allowed currently, and so must be zero. + */ +struct drm_i915_gem_vm_control { + /** @extensions: Zero-terminated chain of extensions. */ + __u64 extensions; + + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; + + /** @vm_id: Id of the VM created or to be destroyed */ + __u32 vm_id; +}; + +struct drm_i915_reg_read { + /* + * Register offset. + * For 64bit wide registers where the upper 32bits don't immediately + * follow the lower 32bits, the offset of the lower 32bits must + * be specified + */ + __u64 offset; +#define I915_REG_READ_8B_WA (1ul << 0) + + __u64 val; /* Return value */ +}; + +/* Known registers: + * + * Render engine timestamp - 0x2358 + 64bit - gen7+ + * - Note this register returns an invalid value if using the default + * single instruction 8byte read, in order to workaround that pass + * flag I915_REG_READ_8B_WA in offset field. + * + */ + +struct drm_i915_reset_stats { + __u32 ctx_id; + __u32 flags; + + /* All resets since boot/module reload, for all contexts */ + __u32 reset_count; + + /* Number of batches lost when active in GPU, for this context */ + __u32 batch_active; + + /* Number of batches lost pending for execution, for this context */ + __u32 batch_pending; + + __u32 pad; +}; + +/** + * struct drm_i915_gem_userptr - Create GEM object from user allocated memory. + * + * Userptr objects have several restrictions on what ioctls can be used with the + * object handle. + */ +struct drm_i915_gem_userptr { + /** + * @user_ptr: The pointer to the allocated memory. + * + * Needs to be aligned to PAGE_SIZE. + */ + __u64 user_ptr; + + /** + * @user_size: + * + * The size in bytes for the allocated memory. This will also become the + * object size. + * + * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE, + * or larger. + */ + __u64 user_size; + + /** + * @flags: + * + * Supported flags: + * + * I915_USERPTR_READ_ONLY: + * + * Mark the object as readonly, this also means GPU access can only be + * readonly. This is only supported on HW which supports readonly access + * through the GTT. If the HW can't support readonly access, an error is + * returned. + * + * I915_USERPTR_PROBE: + * + * Probe the provided @user_ptr range and validate that the @user_ptr is + * indeed pointing to normal memory and that the range is also valid. + * For example if some garbage address is given to the kernel, then this + * should complain. + * + * Returns -EFAULT if the probe failed. + * + * Note that this doesn't populate the backing pages, and also doesn't + * guarantee that the object will remain valid when the object is + * eventually used. + * + * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE + * returns a non-zero value. + * + * I915_USERPTR_UNSYNCHRONIZED: + * + * NOT USED. Setting this flag will result in an error. + */ + __u32 flags; +#define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_PROBE 0x2 +#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; +}; + +enum drm_i915_oa_format { + I915_OA_FORMAT_A13 = 1, /* HSW only */ + I915_OA_FORMAT_A29, /* HSW only */ + I915_OA_FORMAT_A13_B8_C8, /* HSW only */ + I915_OA_FORMAT_B4_C8, /* HSW only */ + I915_OA_FORMAT_A45_B8_C8, /* HSW only */ + I915_OA_FORMAT_B4_C8_A16, /* HSW only */ + I915_OA_FORMAT_C4_B8, /* HSW+ */ + + /* Gen8+ */ + I915_OA_FORMAT_A12, + I915_OA_FORMAT_A12_B8_C8, + I915_OA_FORMAT_A32u40_A4u32_B8_C8, + + /* DG2 */ + I915_OAR_FORMAT_A32u40_A4u32_B8_C8, + I915_OA_FORMAT_A24u40_A14u32_B8_C8, + + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + + I915_OA_FORMAT_MAX /* non-ABI */ +}; + +enum drm_i915_perf_property_id { + /** + * Open the stream for a specific context handle (as used with + * execbuffer2). A stream opened for a specific context this way + * won't typically require root privileges. + * + * This property is available in perf revision 1. + */ + DRM_I915_PERF_PROP_CTX_HANDLE = 1, + + /** + * A value of 1 requests the inclusion of raw OA unit reports as + * part of stream samples. + * + * This property is available in perf revision 1. + */ + DRM_I915_PERF_PROP_SAMPLE_OA, + + /** + * The value specifies which set of OA unit metrics should be + * configured, defining the contents of any OA unit reports. + * + * This property is available in perf revision 1. + */ + DRM_I915_PERF_PROP_OA_METRICS_SET, + + /** + * The value specifies the size and layout of OA unit reports. + * + * This property is available in perf revision 1. + */ + DRM_I915_PERF_PROP_OA_FORMAT, + + /** + * Specifying this property implicitly requests periodic OA unit + * sampling and (at least on Haswell) the sampling frequency is derived + * from this exponent as follows: + * + * 80ns * 2^(period_exponent + 1) + * + * This property is available in perf revision 1. + */ + DRM_I915_PERF_PROP_OA_EXPONENT, + + /** + * Specifying this property is only valid when specify a context to + * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property + * will hold preemption of the particular context we want to gather + * performance data about. The execbuf2 submissions must include a + * drm_i915_gem_execbuffer_ext_perf parameter for this to apply. + * + * This property is available in perf revision 3. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + + /** + * Specifying this pins all contexts to the specified SSEU power + * configuration for the duration of the recording. + * + * This parameter's value is a pointer to a struct + * drm_i915_gem_context_param_sseu. + * + * This property is available in perf revision 4. + */ + DRM_I915_PERF_PROP_GLOBAL_SSEU, + + /** + * This optional parameter specifies the timer interval in nanoseconds + * at which the i915 driver will check the OA buffer for available data. + * Minimum allowed value is 100 microseconds. A default value is used by + * the driver if this parameter is not specified. Note that larger timer + * values will reduce cpu consumption during OA perf captures. However, + * excessively large values would potentially result in OA buffer + * overwrites as captures reach end of the OA buffer. + * + * This property is available in perf revision 5. + */ + DRM_I915_PERF_PROP_POLL_OA_PERIOD, + + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + + DRM_I915_PERF_PROP_MAX /* non-ABI */ +}; + +struct drm_i915_perf_open_param { + __u32 flags; +#define I915_PERF_FLAG_FD_CLOEXEC (1<<0) +#define I915_PERF_FLAG_FD_NONBLOCK (1<<1) +#define I915_PERF_FLAG_DISABLED (1<<2) + + /** The number of u64 (id, value) pairs */ + __u32 num_properties; + + /** + * Pointer to array of u64 (id, value) pairs configuring the stream + * to open. + */ + __u64 properties_ptr; +}; + +/* + * Enable data capture for a stream that was either opened in a disabled state + * via I915_PERF_FLAG_DISABLED or was later disabled via + * I915_PERF_IOCTL_DISABLE. + * + * It is intended to be cheaper to disable and enable a stream than it may be + * to close and re-open a stream with the same configuration. + * + * It's undefined whether any pending data for the stream will be lost. + * + * This ioctl is available in perf revision 1. + */ +#define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) + +/* + * Disable data capture for a stream. + * + * It is an error to try and read a stream that is disabled. + * + * This ioctl is available in perf revision 1. + */ +#define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) + +/* + * Change metrics_set captured by a stream. + * + * If the stream is bound to a specific context, the configuration change + * will performed __inline__ with that context such that it takes effect before + * the next execbuf submission. + * + * Returns the previously bound metrics set id, or a negative error code. + * + * This ioctl is available in perf revision 2. + */ +#define I915_PERF_IOCTL_CONFIG _IO('i', 0x2) + +/* + * Common to all i915 perf records + */ +struct drm_i915_perf_record_header { + __u32 type; + __u16 pad; + __u16 size; +}; + +enum drm_i915_perf_record_type { + + /** + * Samples are the work horse record type whose contents are extensible + * and defined when opening an i915 perf stream based on the given + * properties. + * + * Boolean properties following the naming convention + * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in + * every sample. + * + * The order of these sample properties given by userspace has no + * affect on the ordering of data within a sample. The order is + * documented here. + * + * struct { + * struct drm_i915_perf_record_header header; + * + * { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA + * }; + */ + DRM_I915_PERF_RECORD_SAMPLE = 1, + + /* + * Indicates that one or more OA reports were not written by the + * hardware. This can happen for example if an MI_REPORT_PERF_COUNT + * command collides with periodic sampling - which would be more likely + * at higher sampling frequencies. + */ + DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2, + + /** + * An error occurred that resulted in all pending OA reports being lost. + */ + DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3, + + DRM_I915_PERF_RECORD_MAX /* non-ABI */ +}; + +/** + * struct drm_i915_perf_oa_config + * + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** + * @uuid: + * + * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x" + */ + char uuid[36]; + + /** + * @n_mux_regs: + * + * Number of mux regs in &mux_regs_ptr. + */ + __u32 n_mux_regs; + + /** + * @n_boolean_regs: + * + * Number of boolean regs in &boolean_regs_ptr. + */ + __u32 n_boolean_regs; + + /** + * @n_flex_regs: + * + * Number of flex regs in &flex_regs_ptr. + */ + __u32 n_flex_regs; + + /** + * @mux_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_mux_regs). + */ + __u64 mux_regs_ptr; + + /** + * @boolean_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_boolean_regs). + */ + __u64 boolean_regs_ptr; + + /** + * @flex_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_flex_regs). + */ + __u64 flex_regs_ptr; +}; + +/** + * struct drm_i915_query_item - An individual query for the kernel to process. + * + * The behaviour is determined by the @query_id. Note that exactly what + * @data_ptr is also depends on the specific @query_id. + */ +struct drm_i915_query_item { + /** + * @query_id: + * + * The id for this query. Currently accepted query IDs are: + * - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info) + * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config) + * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) + * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) + * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version) + */ + __u64 query_id; +#define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 +#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_HWCONFIG_BLOB 5 +#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 +#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7 +/* Must be kept compact -- no holes and well documented */ + + /** + * @length: + * + * When set to zero by userspace, this is filled with the size of the + * data to be written at the @data_ptr pointer. The kernel sets this + * value to a negative value to signal an error on a particular query + * item. + */ + __s32 length; + + /** + * @flags: + * + * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * + * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the + * following: + * + * - %DRM_I915_QUERY_PERF_CONFIG_LIST + * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * + * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain + * a struct i915_engine_class_instance that references a render engine. + */ + __u32 flags; +#define DRM_I915_QUERY_PERF_CONFIG_LIST 1 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3 + + /** + * @data_ptr: + * + * Data will be written at the location pointed by @data_ptr when the + * value of @length matches the length of the data to be written by the + * kernel. + */ + __u64 data_ptr; +}; + +/** + * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the + * kernel to fill out. + * + * Note that this is generally a two step process for each struct + * drm_i915_query_item in the array: + * + * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct + * drm_i915_query_item, with &drm_i915_query_item.length set to zero. The + * kernel will then fill in the size, in bytes, which tells userspace how + * memory it needs to allocate for the blob(say for an array of properties). + * + * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the + * &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that + * the &drm_i915_query_item.length should still be the same as what the + * kernel previously set. At this point the kernel can fill in the blob. + * + * Note that for some query items it can make sense for userspace to just pass + * in a buffer/blob equal to or larger than the required size. In this case only + * a single ioctl call is needed. For some smaller query items this can work + * quite well. + * + */ +struct drm_i915_query { + /** @num_items: The number of elements in the @items_ptr array */ + __u32 num_items; + + /** + * @flags: Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /** + * @items_ptr: + * + * Pointer to an array of struct drm_i915_query_item. The number of + * array elements is @num_items. + */ + __u64 items_ptr; +}; + +/** + * struct drm_i915_query_topology_info + * + * Describes slice/subslice/EU information queried by + * %DRM_I915_QUERY_TOPOLOGY_INFO + */ +struct drm_i915_query_topology_info { + /** + * @flags: + * + * Unused for now. Must be cleared to zero. + */ + __u16 flags; + + /** + * @max_slices: + * + * The number of bits used to express the slice mask. + */ + __u16 max_slices; + + /** + * @max_subslices: + * + * The number of bits used to express the subslice mask. + */ + __u16 max_subslices; + + /** + * @max_eus_per_subslice: + * + * The number of bits in the EU mask that correspond to a single + * subslice's EUs. + */ + __u16 max_eus_per_subslice; + + /** + * @subslice_offset: + * + * Offset in data[] at which the subslice masks are stored. + */ + __u16 subslice_offset; + + /** + * @subslice_stride: + * + * Stride at which each of the subslice masks for each slice are + * stored. + */ + __u16 subslice_stride; + + /** + * @eu_offset: + * + * Offset in data[] at which the EU masks are stored. + */ + __u16 eu_offset; + + /** + * @eu_stride: + * + * Stride at which each of the EU masks for each subslice are stored. + */ + __u16 eu_stride; + + /** + * @data: + * + * Contains 3 pieces of information : + * + * - The slice mask with one bit per slice telling whether a slice is + * available. The availability of slice X can be queried with the + * following formula : + * + * .. code:: c + * + * (data[X / 8] >> (X % 8)) & 1 + * + * Starting with Xe_HP platforms, Intel hardware no longer has + * traditional slices so i915 will always report a single slice + * (hardcoded slicemask = 0x1) which contains all of the platform's + * subslices. I.e., the mask here does not reflect any of the newer + * hardware concepts such as "gslices" or "cslices" since userspace + * is capable of inferring those from the subslice mask. + * + * - The subslice mask for each slice with one bit per subslice telling + * whether a subslice is available. Starting with Gen12 we use the + * term "subslice" to refer to what the hardware documentation + * describes as a "dual-subslices." The availability of subslice Y + * in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1 + * + * - The EU mask for each subslice in each slice, with one bit per EU + * telling whether an EU is available. The availability of EU Z in + * subslice Y in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[eu_offset + + * (X * max_subslices + Y) * eu_stride + + * Z / 8 + * ] >> (Z % 8)) & 1 + */ + __u8 data[]; +}; + +/** + * DOC: Engine Discovery uAPI + * + * Engine discovery uAPI is a way of enumerating physical engines present in a + * GPU associated with an open i915 DRM file descriptor. This supersedes the old + * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like + * `I915_PARAM_HAS_BLT`. + * + * The need for this interface came starting with Icelake and newer GPUs, which + * started to establish a pattern of having multiple engines of a same class, + * where not all instances were always completely functionally equivalent. + * + * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the + * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id. + * + * Example for getting the list of engines: + * + * .. code-block:: C + * + * struct drm_i915_query_engine_info *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_ENGINE_INFO; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of engines. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * // + * // Alternatively a large buffer can be allocated straightaway enabling + * // querying in one pass, in which case item.length should contain the + * // length of the provided buffer. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with info on all engines. + * item.data_ptr = (uintptr_t)&info; + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each engine in the array + * for (i = 0; i < info->num_engines; i++) { + * struct drm_i915_engine_info einfo = info->engines[i]; + * u16 class = einfo.engine.class; + * u16 instance = einfo.engine.instance; + * .... + * } + * + * free(info); + * + * Each of the enumerated engines, apart from being defined by its class and + * instance (see `struct i915_engine_class_instance`), also can have flags and + * capabilities defined as documented in i915_drm.h. + * + * For instance video engines which support HEVC encoding will have the + * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set. + * + * Engine discovery only fully comes to its own when combined with the new way + * of addressing engines when submitting batch buffers using contexts with + * engine maps configured. + */ + +/** + * struct drm_i915_engine_info + * + * Describes one engine and its capabilities as known to the driver. + */ +struct drm_i915_engine_info { + /** @engine: Engine class and instance. */ + struct i915_engine_class_instance engine; + + /** @rsvd0: Reserved field. */ + __u32 rsvd0; + + /** @flags: Engine flags. */ + __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) + + /** @capabilities: Capabilities of this engine. */ + __u64 capabilities; +#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) +#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + + /** @rsvd1: Reserved fields. */ + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; +}; + +/** + * struct drm_i915_query_engine_info + * + * Engine info query enumerates all engines known to the driver by filling in + * an array of struct drm_i915_engine_info structures. + */ +struct drm_i915_query_engine_info { + /** @num_engines: Number of struct drm_i915_engine_info structs following. */ + __u32 num_engines; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @engines: Marker for drm_i915_engine_info structures. */ + struct drm_i915_engine_info engines[]; +}; + +/** + * struct drm_i915_query_perf_config + * + * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and + * %DRM_I915_QUERY_GEOMETRY_SUBSLICES. + */ +struct drm_i915_query_perf_config { + union { + /** + * @n_configs: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to + * the number of configurations available. + */ + __u64 n_configs; + + /** + * @config: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. + */ + __u64 config; + + /** + * @uuid: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. + * + * String formatted like "%08x-%04x-%04x-%04x-%012x" + */ + char uuid[36]; + }; + + /** + * @flags: + * + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /** + * @data: + * + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST, + * i915 will write an array of __u64 of configuration identifiers. + * + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA, + * i915 will write a struct drm_i915_perf_oa_config. If the following + * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will + * write into the associated pointers the values of submitted when the + * configuration was created : + * + * - &drm_i915_perf_oa_config.n_mux_regs + * - &drm_i915_perf_oa_config.n_boolean_regs + * - &drm_i915_perf_oa_config.n_flex_regs + */ + __u8 data[]; +}; + +/** + * enum drm_i915_gem_memory_class - Supported memory classes + */ +enum drm_i915_gem_memory_class { + /** @I915_MEMORY_CLASS_SYSTEM: System memory */ + I915_MEMORY_CLASS_SYSTEM = 0, + /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */ + I915_MEMORY_CLASS_DEVICE, +}; + +/** + * struct drm_i915_gem_memory_class_instance - Identify particular memory region + */ +struct drm_i915_gem_memory_class_instance { + /** @memory_class: See enum drm_i915_gem_memory_class */ + __u16 memory_class; + + /** @memory_instance: Which instance */ + __u16 memory_instance; +}; + +/** + * struct drm_i915_memory_region_info - Describes one region as known to the + * driver. + * + * Note this is using both struct drm_i915_query_item and struct drm_i915_query. + * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS + * at &drm_i915_query_item.query_id. + */ +struct drm_i915_memory_region_info { + /** @region: The class:instance pair encoding */ + struct drm_i915_gem_memory_class_instance region; + + /** @rsvd0: MBZ */ + __u32 rsvd0; + + /** + * @probed_size: Memory probed by the driver + * + * Note that it should not be possible to ever encounter a zero value + * here, also note that no current region type will ever return -1 here. + * Although for future region types, this might be a possibility. The + * same applies to the other size fields. + */ + __u64 probed_size; + + /** + * @unallocated_size: Estimate of memory remaining + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting. + * Without this (or if this is an older kernel) the value here will + * always equal the @probed_size. Note this is only currently tracked + * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here + * will always equal the @probed_size). + */ + __u64 unallocated_size; + + union { + /** @rsvd1: MBZ */ + __u64 rsvd1[8]; + struct { + /** + * @probed_cpu_visible_size: Memory probed by the driver + * that is CPU accessible. + * + * This will be always be <= @probed_size, and the + * remainder (if there is any) will not be CPU + * accessible. + * + * On systems without small BAR, the @probed_size will + * always equal the @probed_cpu_visible_size, since all + * of it will be CPU accessible. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the @probed_size). + * + * Note that if the value returned here is zero, then + * this must be an old kernel which lacks the relevant + * small-bar uAPI support (including + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on + * such systems we should never actually end up with a + * small BAR configuration, assuming we are able to load + * the kernel module. Hence it should be safe to treat + * this the same as when @probed_cpu_visible_size == + * @probed_size. + */ + __u64 probed_cpu_visible_size; + + /** + * @unallocated_cpu_visible_size: Estimate of CPU + * visible memory remaining. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the + * @probed_cpu_visible_size). + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always + * equal the @probed_cpu_visible_size. Note this is only + * currently tracked for I915_MEMORY_CLASS_DEVICE + * regions (for other types the value here will also + * always equal the @probed_cpu_visible_size). + * + * If this is an older kernel the value here will be + * zero, see also @probed_cpu_visible_size. + */ + __u64 unallocated_cpu_visible_size; + }; + }; +}; + +/** + * struct drm_i915_query_memory_regions + * + * The region info query enumerates all regions known to the driver by filling + * in an array of struct drm_i915_memory_region_info structures. + * + * Example for getting the list of supported regions: + * + * .. code-block:: C + * + * struct drm_i915_query_memory_regions *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_MEMORY_REGIONS; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of regions. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with the all the region info. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each region in the array + * for (i = 0; i < info->num_regions; i++) { + * struct drm_i915_memory_region_info mr = info->regions[i]; + * u16 class = mr.region.class; + * u16 instance = mr.region.instance; + * + * .... + * } + * + * free(info); + */ +struct drm_i915_query_memory_regions { + /** @num_regions: Number of supported regions */ + __u32 num_regions; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @regions: Info about each supported region */ + struct drm_i915_memory_region_info regions[]; +}; + +/** + * struct drm_i915_query_guc_submission_version - query GuC submission interface version + */ +struct drm_i915_query_guc_submission_version { + __u32 branch; + __u32 major; + __u32 minor; + __u32 patch; +}; + +/** + * DOC: GuC HWCONFIG blob uAPI + * + * The GuC produces a blob with information about the current device. + * i915 reads this blob from GuC and makes it available via this uAPI. + * + * The format and meaning of the blob content are documented in the + * Programmer's Reference Manual. + */ + +/** + * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added + * extension support using struct i915_user_extension. + * + * Note that new buffer flags should be added here, at least for the stuff that + * is immutable. Previously we would have two ioctls, one to create the object + * with gem_create, and another to apply various parameters, however this + * creates some ambiguity for the params which are considered immutable. Also in + * general we're phasing out the various SET/GET ioctls. + */ +struct drm_i915_gem_create_ext { + /** + * @size: Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + * + * On platforms like DG2/ATS the kernel will always use 64K or larger + * pages for I915_MEMORY_CLASS_DEVICE. The kernel also requires a + * minimum of 64K GTT alignment for such objects. + * + * NOTE: Previously the ABI here required a minimum GTT alignment of 2M + * on DG2/ATS, due to how the hardware implemented 64K GTT page support, + * where we had the following complications: + * + * 1) The entire PDE (which covers a 2MB virtual address range), must + * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same + * PDE is forbidden by the hardware. + * + * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM + * objects. + * + * However on actual production HW this was completely changed to now + * allow setting a TLB hint at the PTE level (see PS64), which is a lot + * more flexible than the above. With this the 2M restriction was + * dropped where we now only require 64K. + */ + __u64 size; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + + /** + * @flags: Optional flags. + * + * Supported values: + * + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that + * the object will need to be accessed via the CPU. + * + * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only + * strictly required on configurations where some subset of the device + * memory is directly visible/mappable through the CPU (which we also + * call small BAR), like on some DG2+ systems. Note that this is quite + * undesirable, but due to various factors like the client CPU, BIOS etc + * it's something we can expect to see in the wild. See + * &drm_i915_memory_region_info.probed_cpu_visible_size for how to + * determine if this system applies. + * + * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to + * ensure the kernel can always spill the allocation to system memory, + * if the object can't be allocated in the mappable part of + * I915_MEMORY_CLASS_DEVICE. + * + * Also note that since the kernel only supports flat-CCS on objects + * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore + * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with + * flat-CCS. + * + * Without this hint, the kernel will assume that non-mappable + * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the + * kernel can still migrate the object to the mappable part, as a last + * resort, if userspace ever CPU faults this object, but this might be + * expensive, and so ideally should be avoided. + * + * On older kernels which lack the relevant small-bar uAPI support (see + * also &drm_i915_memory_region_info.probed_cpu_visible_size), + * usage of the flag will result in an error, but it should NEVER be + * possible to end up with a small BAR configuration, assuming we can + * also successfully load the i915 kernel module. In such cases the + * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as + * such there are zero restrictions on where the object can be placed. + */ +#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0) + __u32 flags; + + /** + * @extensions: The chain of extensions to apply to this object. + * + * This will be useful in the future when we need to support several + * different extensions, and we need to apply more than one when + * creating the object. See struct i915_user_extension. + * + * If we don't supply any extensions then we get the same old gem_create + * behaviour. + * + * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see + * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. + * + * For I915_GEM_CREATE_EXT_SET_PAT usage see + * struct drm_i915_gem_create_ext_set_pat. + */ +#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 +#define I915_GEM_CREATE_EXT_SET_PAT 2 + __u64 extensions; +}; + +/** + * struct drm_i915_gem_create_ext_memory_regions - The + * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension. + * + * Set the object with the desired set of placements/regions in priority + * order. Each entry must be unique and supported by the device. + * + * This is provided as an array of struct drm_i915_gem_memory_class_instance, or + * an equivalent layout of class:instance pair encodings. See struct + * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to + * query the supported regions for a device. + * + * As an example, on discrete devices, if we wish to set the placement as + * device local-memory we can do something like: + * + * .. code-block:: C + * + * struct drm_i915_gem_memory_class_instance region_lmem = { + * .memory_class = I915_MEMORY_CLASS_DEVICE, + * .memory_instance = 0, + * }; + * struct drm_i915_gem_create_ext_memory_regions regions = { + * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS }, + * .regions = (uintptr_t)®ion_lmem, + * .num_regions = 1, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = 16 * PAGE_SIZE, + * .extensions = (uintptr_t)®ions, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + * + * At which point we get the object handle in &drm_i915_gem_create_ext.handle, + * along with the final object size in &drm_i915_gem_create_ext.size, which + * should account for any rounding up, if required. + * + * Note that userspace has no means of knowing the current backing region + * for objects where @num_regions is larger than one. The kernel will only + * ensure that the priority order of the @regions array is honoured, either + * when initially placing the object, or when moving memory around due to + * memory pressure + * + * On Flat-CCS capable HW, compression is supported for the objects residing + * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other + * memory class in @regions and migrated (by i915, due to memory + * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to + * decompress the content. But i915 doesn't have the required information to + * decompress the userspace compressed objects. + * + * So i915 supports Flat-CCS, on the objects which can reside only on + * I915_MEMORY_CLASS_DEVICE regions. + */ +struct drm_i915_gem_create_ext_memory_regions { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + + /** @pad: MBZ */ + __u32 pad; + /** @num_regions: Number of elements in the @regions array. */ + __u32 num_regions; + /** + * @regions: The regions/placements array. + * + * An array of struct drm_i915_gem_memory_class_instance. + */ + __u64 regions; +}; + +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + +/** + * struct drm_i915_gem_create_ext_set_pat - The + * I915_GEM_CREATE_EXT_SET_PAT extension. + * + * If this extension is provided, the specified caching policy (PAT index) is + * applied to the buffer object. + * + * Below is an example on how to create an object with specific caching policy: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_set_pat set_pat_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_SET_PAT }, + * .pat_index = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&set_pat_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_set_pat { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** + * @pat_index: PAT index to be set + * PAT index is a bit field in Page Table Entry to control caching + * behaviors for GPU accesses. The definition of PAT index is + * platform dependent and can be found in hardware specifications, + */ + __u32 pat_index; + /** @rsvd: reserved for future use */ + __u32 rsvd; +}; + +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + +#if defined(__cplusplus) +} +#endif + +#endif /* _I915_DRM_H_ */ diff --git a/src/linux/intel_gpu_top/i915_pciids.h b/src/linux/intel_gpu_top/i915_pciids.h new file mode 100644 index 00000000..3e39d644 --- /dev/null +++ b/src/linux/intel_gpu_top/i915_pciids.h @@ -0,0 +1,786 @@ +/* + * Copyright 2013 Intel Corporation + * All Rights Reserved. + * + * 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 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_PCIIDS_H +#define _I915_PCIIDS_H + +/* + * A pci_device_id struct { + * __u32 vendor, device; + * __u32 subvendor, subdevice; + * __u32 class, class_mask; + * kernel_ulong_t driver_data; + * }; + * Don't use C99 here because "class" is reserved and we want to + * give userspace flexibility. + */ +#define INTEL_VGA_DEVICE(id, info) { \ + 0x8086, id, \ + ~0, ~0, \ + 0x030000, 0xff0000, \ + (unsigned long) info } + +#define INTEL_QUANTA_VGA_DEVICE(info) { \ + 0x8086, 0x16a, \ + 0x152d, 0x8990, \ + 0x030000, 0xff0000, \ + (unsigned long) info } + +#define INTEL_I810_IDS(MACRO__, ...) \ + MACRO__(0x7121, ## __VA_ARGS__), /* I810 */ \ + MACRO__(0x7123, ## __VA_ARGS__), /* I810_DC100 */ \ + MACRO__(0x7125, ## __VA_ARGS__) /* I810_E */ + +#define INTEL_I815_IDS(MACRO__, ...) \ + MACRO__(0x1132, ## __VA_ARGS__) /* I815*/ + +#define INTEL_I830_IDS(MACRO__, ...) \ + MACRO__(0x3577, ## __VA_ARGS__) + +#define INTEL_I845G_IDS(MACRO__, ...) \ + MACRO__(0x2562, ## __VA_ARGS__) + +#define INTEL_I85X_IDS(MACRO__, ...) \ + MACRO__(0x3582, ## __VA_ARGS__), /* I855_GM */ \ + MACRO__(0x358e, ## __VA_ARGS__) + +#define INTEL_I865G_IDS(MACRO__, ...) \ + MACRO__(0x2572, ## __VA_ARGS__) /* I865_G */ + +#define INTEL_I915G_IDS(MACRO__, ...) \ + MACRO__(0x2582, ## __VA_ARGS__), /* I915_G */ \ + MACRO__(0x258a, ## __VA_ARGS__) /* E7221_G */ + +#define INTEL_I915GM_IDS(MACRO__, ...) \ + MACRO__(0x2592, ## __VA_ARGS__) /* I915_GM */ + +#define INTEL_I945G_IDS(MACRO__, ...) \ + MACRO__(0x2772, ## __VA_ARGS__) /* I945_G */ + +#define INTEL_I945GM_IDS(MACRO__, ...) \ + MACRO__(0x27a2, ## __VA_ARGS__), /* I945_GM */ \ + MACRO__(0x27ae, ## __VA_ARGS__) /* I945_GME */ + +#define INTEL_I965G_IDS(MACRO__, ...) \ + MACRO__(0x2972, ## __VA_ARGS__), /* I946_GZ */ \ + MACRO__(0x2982, ## __VA_ARGS__), /* G35_G */ \ + MACRO__(0x2992, ## __VA_ARGS__), /* I965_Q */ \ + MACRO__(0x29a2, ## __VA_ARGS__) /* I965_G */ + +#define INTEL_G33_IDS(MACRO__, ...) \ + MACRO__(0x29b2, ## __VA_ARGS__), /* Q35_G */ \ + MACRO__(0x29c2, ## __VA_ARGS__), /* G33_G */ \ + MACRO__(0x29d2, ## __VA_ARGS__) /* Q33_G */ + +#define INTEL_I965GM_IDS(MACRO__, ...) \ + MACRO__(0x2a02, ## __VA_ARGS__), /* I965_GM */ \ + MACRO__(0x2a12, ## __VA_ARGS__) /* I965_GME */ + +#define INTEL_GM45_IDS(MACRO__, ...) \ + MACRO__(0x2a42, ## __VA_ARGS__) /* GM45_G */ + +#define INTEL_G45_IDS(MACRO__, ...) \ + MACRO__(0x2e02, ## __VA_ARGS__), /* IGD_E_G */ \ + MACRO__(0x2e12, ## __VA_ARGS__), /* Q45_G */ \ + MACRO__(0x2e22, ## __VA_ARGS__), /* G45_G */ \ + MACRO__(0x2e32, ## __VA_ARGS__), /* G41_G */ \ + MACRO__(0x2e42, ## __VA_ARGS__), /* B43_G */ \ + MACRO__(0x2e92, ## __VA_ARGS__) /* B43_G.1 */ + +#define INTEL_PNV_G_IDS(MACRO__, ...) \ + MACRO__(0xa001, ## __VA_ARGS__) + +#define INTEL_PNV_M_IDS(MACRO__, ...) \ + MACRO__(0xa011, ## __VA_ARGS__) + +#define INTEL_PNV_IDS(MACRO__, ...) \ + INTEL_PNV_G_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_PNV_M_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_ILK_D_IDS(MACRO__, ...) \ + MACRO__(0x0042, ## __VA_ARGS__) + +#define INTEL_ILK_M_IDS(MACRO__, ...) \ + MACRO__(0x0046, ## __VA_ARGS__) + +#define INTEL_ILK_IDS(MACRO__, ...) \ + INTEL_ILK_D_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_ILK_M_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_SNB_D_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0102, ## __VA_ARGS__), \ + MACRO__(0x010A, ## __VA_ARGS__) + +#define INTEL_SNB_D_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0112, ## __VA_ARGS__), \ + MACRO__(0x0122, ## __VA_ARGS__) + +#define INTEL_SNB_D_IDS(MACRO__, ...) \ + INTEL_SNB_D_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SNB_D_GT2_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_SNB_M_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0106, ## __VA_ARGS__) + +#define INTEL_SNB_M_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0116, ## __VA_ARGS__), \ + MACRO__(0x0126, ## __VA_ARGS__) + +#define INTEL_SNB_M_IDS(MACRO__, ...) \ + INTEL_SNB_M_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SNB_M_GT2_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_SNB_IDS(MACRO__, ...) \ + INTEL_SNB_D_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SNB_M_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_IVB_M_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0156, ## __VA_ARGS__) /* GT1 mobile */ + +#define INTEL_IVB_M_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0166, ## __VA_ARGS__) /* GT2 mobile */ + +#define INTEL_IVB_M_IDS(MACRO__, ...) \ + INTEL_IVB_M_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_IVB_M_GT2_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_IVB_D_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0152, ## __VA_ARGS__), /* GT1 desktop */ \ + MACRO__(0x015a, ## __VA_ARGS__) /* GT1 server */ + +#define INTEL_IVB_D_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0162, ## __VA_ARGS__), /* GT2 desktop */ \ + MACRO__(0x016a, ## __VA_ARGS__) /* GT2 server */ + +#define INTEL_IVB_D_IDS(MACRO__, ...) \ + INTEL_IVB_D_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_IVB_D_GT2_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_IVB_IDS(MACRO__, ...) \ + INTEL_IVB_M_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_IVB_D_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_IVB_Q_IDS(MACRO__, ...) \ + INTEL_QUANTA_VGA_DEVICE(__VA_ARGS__) /* Quanta transcode */ + +#define INTEL_HSW_ULT_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0A02, ## __VA_ARGS__), /* ULT GT1 desktop */ \ + MACRO__(0x0A06, ## __VA_ARGS__), /* ULT GT1 mobile */ \ + MACRO__(0x0A0A, ## __VA_ARGS__), /* ULT GT1 server */ \ + MACRO__(0x0A0B, ## __VA_ARGS__) /* ULT GT1 reserved */ + +#define INTEL_HSW_ULX_GT1_IDS(MACRO__, ...) \ + MACRO__(0x0A0E, ## __VA_ARGS__) /* ULX GT1 mobile */ + +#define INTEL_HSW_GT1_IDS(MACRO__, ...) \ + INTEL_HSW_ULT_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_HSW_ULX_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x0402, ## __VA_ARGS__), /* GT1 desktop */ \ + MACRO__(0x0406, ## __VA_ARGS__), /* GT1 mobile */ \ + MACRO__(0x040A, ## __VA_ARGS__), /* GT1 server */ \ + MACRO__(0x040B, ## __VA_ARGS__), /* GT1 reserved */ \ + MACRO__(0x040E, ## __VA_ARGS__), /* GT1 reserved */ \ + MACRO__(0x0C02, ## __VA_ARGS__), /* SDV GT1 desktop */ \ + MACRO__(0x0C06, ## __VA_ARGS__), /* SDV GT1 mobile */ \ + MACRO__(0x0C0A, ## __VA_ARGS__), /* SDV GT1 server */ \ + MACRO__(0x0C0B, ## __VA_ARGS__), /* SDV GT1 reserved */ \ + MACRO__(0x0C0E, ## __VA_ARGS__), /* SDV GT1 reserved */ \ + MACRO__(0x0D02, ## __VA_ARGS__), /* CRW GT1 desktop */ \ + MACRO__(0x0D06, ## __VA_ARGS__), /* CRW GT1 mobile */ \ + MACRO__(0x0D0A, ## __VA_ARGS__), /* CRW GT1 server */ \ + MACRO__(0x0D0B, ## __VA_ARGS__), /* CRW GT1 reserved */ \ + MACRO__(0x0D0E, ## __VA_ARGS__) /* CRW GT1 reserved */ + +#define INTEL_HSW_ULT_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0A12, ## __VA_ARGS__), /* ULT GT2 desktop */ \ + MACRO__(0x0A16, ## __VA_ARGS__), /* ULT GT2 mobile */ \ + MACRO__(0x0A1A, ## __VA_ARGS__), /* ULT GT2 server */ \ + MACRO__(0x0A1B, ## __VA_ARGS__) /* ULT GT2 reserved */ \ + +#define INTEL_HSW_ULX_GT2_IDS(MACRO__, ...) \ + MACRO__(0x0A1E, ## __VA_ARGS__) /* ULX GT2 mobile */ \ + +#define INTEL_HSW_GT2_IDS(MACRO__, ...) \ + INTEL_HSW_ULT_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_HSW_ULX_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x0412, ## __VA_ARGS__), /* GT2 desktop */ \ + MACRO__(0x0416, ## __VA_ARGS__), /* GT2 mobile */ \ + MACRO__(0x041A, ## __VA_ARGS__), /* GT2 server */ \ + MACRO__(0x041B, ## __VA_ARGS__), /* GT2 reserved */ \ + MACRO__(0x041E, ## __VA_ARGS__), /* GT2 reserved */ \ + MACRO__(0x0C12, ## __VA_ARGS__), /* SDV GT2 desktop */ \ + MACRO__(0x0C16, ## __VA_ARGS__), /* SDV GT2 mobile */ \ + MACRO__(0x0C1A, ## __VA_ARGS__), /* SDV GT2 server */ \ + MACRO__(0x0C1B, ## __VA_ARGS__), /* SDV GT2 reserved */ \ + MACRO__(0x0C1E, ## __VA_ARGS__), /* SDV GT2 reserved */ \ + MACRO__(0x0D12, ## __VA_ARGS__), /* CRW GT2 desktop */ \ + MACRO__(0x0D16, ## __VA_ARGS__), /* CRW GT2 mobile */ \ + MACRO__(0x0D1A, ## __VA_ARGS__), /* CRW GT2 server */ \ + MACRO__(0x0D1B, ## __VA_ARGS__), /* CRW GT2 reserved */ \ + MACRO__(0x0D1E, ## __VA_ARGS__) /* CRW GT2 reserved */ + +#define INTEL_HSW_ULT_GT3_IDS(MACRO__, ...) \ + MACRO__(0x0A22, ## __VA_ARGS__), /* ULT GT3 desktop */ \ + MACRO__(0x0A26, ## __VA_ARGS__), /* ULT GT3 mobile */ \ + MACRO__(0x0A2A, ## __VA_ARGS__), /* ULT GT3 server */ \ + MACRO__(0x0A2B, ## __VA_ARGS__), /* ULT GT3 reserved */ \ + MACRO__(0x0A2E, ## __VA_ARGS__) /* ULT GT3 reserved */ + +#define INTEL_HSW_GT3_IDS(MACRO__, ...) \ + INTEL_HSW_ULT_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x0422, ## __VA_ARGS__), /* GT3 desktop */ \ + MACRO__(0x0426, ## __VA_ARGS__), /* GT3 mobile */ \ + MACRO__(0x042A, ## __VA_ARGS__), /* GT3 server */ \ + MACRO__(0x042B, ## __VA_ARGS__), /* GT3 reserved */ \ + MACRO__(0x042E, ## __VA_ARGS__), /* GT3 reserved */ \ + MACRO__(0x0C22, ## __VA_ARGS__), /* SDV GT3 desktop */ \ + MACRO__(0x0C26, ## __VA_ARGS__), /* SDV GT3 mobile */ \ + MACRO__(0x0C2A, ## __VA_ARGS__), /* SDV GT3 server */ \ + MACRO__(0x0C2B, ## __VA_ARGS__), /* SDV GT3 reserved */ \ + MACRO__(0x0C2E, ## __VA_ARGS__), /* SDV GT3 reserved */ \ + MACRO__(0x0D22, ## __VA_ARGS__), /* CRW GT3 desktop */ \ + MACRO__(0x0D26, ## __VA_ARGS__), /* CRW GT3 mobile */ \ + MACRO__(0x0D2A, ## __VA_ARGS__), /* CRW GT3 server */ \ + MACRO__(0x0D2B, ## __VA_ARGS__), /* CRW GT3 reserved */ \ + MACRO__(0x0D2E, ## __VA_ARGS__) /* CRW GT3 reserved */ + +#define INTEL_HSW_IDS(MACRO__, ...) \ + INTEL_HSW_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_HSW_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_HSW_GT3_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_VLV_IDS(MACRO__, ...) \ + MACRO__(0x0f30, ## __VA_ARGS__), \ + MACRO__(0x0f31, ## __VA_ARGS__), \ + MACRO__(0x0f32, ## __VA_ARGS__), \ + MACRO__(0x0f33, ## __VA_ARGS__) + +#define INTEL_BDW_ULT_GT1_IDS(MACRO__, ...) \ + MACRO__(0x1606, ## __VA_ARGS__), /* GT1 ULT */ \ + MACRO__(0x160B, ## __VA_ARGS__) /* GT1 Iris */ + +#define INTEL_BDW_ULX_GT1_IDS(MACRO__, ...) \ + MACRO__(0x160E, ## __VA_ARGS__) /* GT1 ULX */ + +#define INTEL_BDW_GT1_IDS(MACRO__, ...) \ + INTEL_BDW_ULT_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_ULX_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1602, ## __VA_ARGS__), /* GT1 ULT */ \ + MACRO__(0x160A, ## __VA_ARGS__), /* GT1 Server */ \ + MACRO__(0x160D, ## __VA_ARGS__) /* GT1 Workstation */ + +#define INTEL_BDW_ULT_GT2_IDS(MACRO__, ...) \ + MACRO__(0x1616, ## __VA_ARGS__), /* GT2 ULT */ \ + MACRO__(0x161B, ## __VA_ARGS__) /* GT2 ULT */ + +#define INTEL_BDW_ULX_GT2_IDS(MACRO__, ...) \ + MACRO__(0x161E, ## __VA_ARGS__) /* GT2 ULX */ + +#define INTEL_BDW_GT2_IDS(MACRO__, ...) \ + INTEL_BDW_ULT_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_ULX_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1612, ## __VA_ARGS__), /* GT2 Halo */ \ + MACRO__(0x161A, ## __VA_ARGS__), /* GT2 Server */ \ + MACRO__(0x161D, ## __VA_ARGS__) /* GT2 Workstation */ + +#define INTEL_BDW_ULT_GT3_IDS(MACRO__, ...) \ + MACRO__(0x1626, ## __VA_ARGS__), /* ULT */ \ + MACRO__(0x162B, ## __VA_ARGS__) /* Iris */ \ + +#define INTEL_BDW_ULX_GT3_IDS(MACRO__, ...) \ + MACRO__(0x162E, ## __VA_ARGS__) /* ULX */ + +#define INTEL_BDW_GT3_IDS(MACRO__, ...) \ + INTEL_BDW_ULT_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_ULX_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1622, ## __VA_ARGS__), /* ULT */ \ + MACRO__(0x162A, ## __VA_ARGS__), /* Server */ \ + MACRO__(0x162D, ## __VA_ARGS__) /* Workstation */ + +#define INTEL_BDW_ULT_RSVD_IDS(MACRO__, ...) \ + MACRO__(0x1636, ## __VA_ARGS__), /* ULT */ \ + MACRO__(0x163B, ## __VA_ARGS__) /* Iris */ + +#define INTEL_BDW_ULX_RSVD_IDS(MACRO__, ...) \ + MACRO__(0x163E, ## __VA_ARGS__) /* ULX */ + +#define INTEL_BDW_RSVD_IDS(MACRO__, ...) \ + INTEL_BDW_ULT_RSVD_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_ULX_RSVD_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1632, ## __VA_ARGS__), /* ULT */ \ + MACRO__(0x163A, ## __VA_ARGS__), /* Server */ \ + MACRO__(0x163D, ## __VA_ARGS__) /* Workstation */ + +#define INTEL_BDW_IDS(MACRO__, ...) \ + INTEL_BDW_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_BDW_RSVD_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_CHV_IDS(MACRO__, ...) \ + MACRO__(0x22b0, ## __VA_ARGS__), \ + MACRO__(0x22b1, ## __VA_ARGS__), \ + MACRO__(0x22b2, ## __VA_ARGS__), \ + MACRO__(0x22b3, ## __VA_ARGS__) + +#define INTEL_SKL_ULT_GT1_IDS(MACRO__, ...) \ + MACRO__(0x1906, ## __VA_ARGS__), /* ULT GT1 */ \ + MACRO__(0x1913, ## __VA_ARGS__) /* ULT GT1.5 */ + +#define INTEL_SKL_ULX_GT1_IDS(MACRO__, ...) \ + MACRO__(0x190E, ## __VA_ARGS__), /* ULX GT1 */ \ + MACRO__(0x1915, ## __VA_ARGS__) /* ULX GT1.5 */ + +#define INTEL_SKL_GT1_IDS(MACRO__, ...) \ + INTEL_SKL_ULT_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SKL_ULX_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1902, ## __VA_ARGS__), /* DT GT1 */ \ + MACRO__(0x190A, ## __VA_ARGS__), /* SRV GT1 */ \ + MACRO__(0x190B, ## __VA_ARGS__), /* Halo GT1 */ \ + MACRO__(0x1917, ## __VA_ARGS__) /* DT GT1.5 */ + +#define INTEL_SKL_ULT_GT2_IDS(MACRO__, ...) \ + MACRO__(0x1916, ## __VA_ARGS__), /* ULT GT2 */ \ + MACRO__(0x1921, ## __VA_ARGS__) /* ULT GT2F */ + +#define INTEL_SKL_ULX_GT2_IDS(MACRO__, ...) \ + MACRO__(0x191E, ## __VA_ARGS__) /* ULX GT2 */ + +#define INTEL_SKL_GT2_IDS(MACRO__, ...) \ + INTEL_SKL_ULT_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SKL_ULX_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x1912, ## __VA_ARGS__), /* DT GT2 */ \ + MACRO__(0x191A, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x191B, ## __VA_ARGS__), /* Halo GT2 */ \ + MACRO__(0x191D, ## __VA_ARGS__) /* WKS GT2 */ + +#define INTEL_SKL_ULT_GT3_IDS(MACRO__, ...) \ + MACRO__(0x1923, ## __VA_ARGS__), /* ULT GT3 */ \ + MACRO__(0x1926, ## __VA_ARGS__), /* ULT GT3e */ \ + MACRO__(0x1927, ## __VA_ARGS__) /* ULT GT3e */ + +#define INTEL_SKL_GT3_IDS(MACRO__, ...) \ + INTEL_SKL_ULT_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x192A, ## __VA_ARGS__), /* SRV GT3 */ \ + MACRO__(0x192B, ## __VA_ARGS__), /* Halo GT3e */ \ + MACRO__(0x192D, ## __VA_ARGS__) /* SRV GT3e */ + +#define INTEL_SKL_GT4_IDS(MACRO__, ...) \ + MACRO__(0x1932, ## __VA_ARGS__), /* DT GT4 */ \ + MACRO__(0x193A, ## __VA_ARGS__), /* SRV GT4e */ \ + MACRO__(0x193B, ## __VA_ARGS__), /* Halo GT4e */ \ + MACRO__(0x193D, ## __VA_ARGS__) /* WKS GT4e */ + +#define INTEL_SKL_IDS(MACRO__, ...) \ + INTEL_SKL_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SKL_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SKL_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_SKL_GT4_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_BXT_IDS(MACRO__, ...) \ + MACRO__(0x0A84, ## __VA_ARGS__), \ + MACRO__(0x1A84, ## __VA_ARGS__), \ + MACRO__(0x1A85, ## __VA_ARGS__), \ + MACRO__(0x5A84, ## __VA_ARGS__), /* APL HD Graphics 505 */ \ + MACRO__(0x5A85, ## __VA_ARGS__) /* APL HD Graphics 500 */ + +#define INTEL_GLK_IDS(MACRO__, ...) \ + MACRO__(0x3184, ## __VA_ARGS__), \ + MACRO__(0x3185, ## __VA_ARGS__) + +#define INTEL_KBL_ULT_GT1_IDS(MACRO__, ...) \ + MACRO__(0x5906, ## __VA_ARGS__), /* ULT GT1 */ \ + MACRO__(0x5913, ## __VA_ARGS__) /* ULT GT1.5 */ + +#define INTEL_KBL_ULX_GT1_IDS(MACRO__, ...) \ + MACRO__(0x590E, ## __VA_ARGS__), /* ULX GT1 */ \ + MACRO__(0x5915, ## __VA_ARGS__) /* ULX GT1.5 */ + +#define INTEL_KBL_GT1_IDS(MACRO__, ...) \ + INTEL_KBL_ULT_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_KBL_ULX_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x5902, ## __VA_ARGS__), /* DT GT1 */ \ + MACRO__(0x5908, ## __VA_ARGS__), /* Halo GT1 */ \ + MACRO__(0x590A, ## __VA_ARGS__), /* SRV GT1 */ \ + MACRO__(0x590B, ## __VA_ARGS__) /* Halo GT1 */ + +#define INTEL_KBL_ULT_GT2_IDS(MACRO__, ...) \ + MACRO__(0x5916, ## __VA_ARGS__), /* ULT GT2 */ \ + MACRO__(0x5921, ## __VA_ARGS__) /* ULT GT2F */ + +#define INTEL_KBL_ULX_GT2_IDS(MACRO__, ...) \ + MACRO__(0x591E, ## __VA_ARGS__) /* ULX GT2 */ + +#define INTEL_KBL_GT2_IDS(MACRO__, ...) \ + INTEL_KBL_ULT_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_KBL_ULX_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x5912, ## __VA_ARGS__), /* DT GT2 */ \ + MACRO__(0x5917, ## __VA_ARGS__), /* Mobile GT2 */ \ + MACRO__(0x591A, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x591B, ## __VA_ARGS__), /* Halo GT2 */ \ + MACRO__(0x591D, ## __VA_ARGS__) /* WKS GT2 */ + +#define INTEL_KBL_ULT_GT3_IDS(MACRO__, ...) \ + MACRO__(0x5926, ## __VA_ARGS__) /* ULT GT3 */ + +#define INTEL_KBL_GT3_IDS(MACRO__, ...) \ + INTEL_KBL_ULT_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x5923, ## __VA_ARGS__), /* ULT GT3 */ \ + MACRO__(0x5927, ## __VA_ARGS__) /* ULT GT3 */ + +#define INTEL_KBL_GT4_IDS(MACRO__, ...) \ + MACRO__(0x593B, ## __VA_ARGS__) /* Halo GT4 */ + +/* AML/KBL Y GT2 */ +#define INTEL_AML_KBL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x591C, ## __VA_ARGS__), /* ULX GT2 */ \ + MACRO__(0x87C0, ## __VA_ARGS__) /* ULX GT2 */ + +/* AML/CFL Y GT2 */ +#define INTEL_AML_CFL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x87CA, ## __VA_ARGS__) + +/* CML GT1 */ +#define INTEL_CML_GT1_IDS(MACRO__, ...) \ + MACRO__(0x9BA2, ## __VA_ARGS__), \ + MACRO__(0x9BA4, ## __VA_ARGS__), \ + MACRO__(0x9BA5, ## __VA_ARGS__), \ + MACRO__(0x9BA8, ## __VA_ARGS__) + +#define INTEL_CML_U_GT1_IDS(MACRO__, ...) \ + MACRO__(0x9B21, ## __VA_ARGS__), \ + MACRO__(0x9BAA, ## __VA_ARGS__), \ + MACRO__(0x9BAC, ## __VA_ARGS__) + +/* CML GT2 */ +#define INTEL_CML_GT2_IDS(MACRO__, ...) \ + MACRO__(0x9BC2, ## __VA_ARGS__), \ + MACRO__(0x9BC4, ## __VA_ARGS__), \ + MACRO__(0x9BC5, ## __VA_ARGS__), \ + MACRO__(0x9BC6, ## __VA_ARGS__), \ + MACRO__(0x9BC8, ## __VA_ARGS__), \ + MACRO__(0x9BE6, ## __VA_ARGS__), \ + MACRO__(0x9BF6, ## __VA_ARGS__) + +#define INTEL_CML_U_GT2_IDS(MACRO__, ...) \ + MACRO__(0x9B41, ## __VA_ARGS__), \ + MACRO__(0x9BCA, ## __VA_ARGS__), \ + MACRO__(0x9BCC, ## __VA_ARGS__) + +#define INTEL_CML_IDS(MACRO__, ...) \ + INTEL_CML_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CML_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CML_U_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CML_U_GT2_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_KBL_IDS(MACRO__, ...) \ + INTEL_KBL_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_KBL_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_KBL_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_KBL_GT4_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_AML_KBL_GT2_IDS(MACRO__, ## __VA_ARGS__) + +/* CFL S */ +#define INTEL_CFL_S_GT1_IDS(MACRO__, ...) \ + MACRO__(0x3E90, ## __VA_ARGS__), /* SRV GT1 */ \ + MACRO__(0x3E93, ## __VA_ARGS__), /* SRV GT1 */ \ + MACRO__(0x3E99, ## __VA_ARGS__) /* SRV GT1 */ + +#define INTEL_CFL_S_GT2_IDS(MACRO__, ...) \ + MACRO__(0x3E91, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x3E92, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x3E96, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x3E98, ## __VA_ARGS__), /* SRV GT2 */ \ + MACRO__(0x3E9A, ## __VA_ARGS__) /* SRV GT2 */ + +/* CFL H */ +#define INTEL_CFL_H_GT1_IDS(MACRO__, ...) \ + MACRO__(0x3E9C, ## __VA_ARGS__) + +#define INTEL_CFL_H_GT2_IDS(MACRO__, ...) \ + MACRO__(0x3E94, ## __VA_ARGS__), /* Halo GT2 */ \ + MACRO__(0x3E9B, ## __VA_ARGS__) /* Halo GT2 */ + +/* CFL U GT2 */ +#define INTEL_CFL_U_GT2_IDS(MACRO__, ...) \ + MACRO__(0x3EA9, ## __VA_ARGS__) + +/* CFL U GT3 */ +#define INTEL_CFL_U_GT3_IDS(MACRO__, ...) \ + MACRO__(0x3EA5, ## __VA_ARGS__), /* ULT GT3 */ \ + MACRO__(0x3EA6, ## __VA_ARGS__), /* ULT GT3 */ \ + MACRO__(0x3EA7, ## __VA_ARGS__), /* ULT GT3 */ \ + MACRO__(0x3EA8, ## __VA_ARGS__) /* ULT GT3 */ + +#define INTEL_CFL_IDS(MACRO__, ...) \ + INTEL_CFL_S_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CFL_S_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CFL_H_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CFL_H_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CFL_U_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_CFL_U_GT3_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_AML_CFL_GT2_IDS(MACRO__, ## __VA_ARGS__) + +/* WHL/CFL U GT1 */ +#define INTEL_WHL_U_GT1_IDS(MACRO__, ...) \ + MACRO__(0x3EA1, ## __VA_ARGS__), \ + MACRO__(0x3EA4, ## __VA_ARGS__) + +/* WHL/CFL U GT2 */ +#define INTEL_WHL_U_GT2_IDS(MACRO__, ...) \ + MACRO__(0x3EA0, ## __VA_ARGS__), \ + MACRO__(0x3EA3, ## __VA_ARGS__) + +/* WHL/CFL U GT3 */ +#define INTEL_WHL_U_GT3_IDS(MACRO__, ...) \ + MACRO__(0x3EA2, ## __VA_ARGS__) + +#define INTEL_WHL_IDS(MACRO__, ...) \ + INTEL_WHL_U_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_WHL_U_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_WHL_U_GT3_IDS(MACRO__, ## __VA_ARGS__) + +/* CNL */ +#define INTEL_CNL_PORT_F_IDS(MACRO__, ...) \ + MACRO__(0x5A44, ## __VA_ARGS__), \ + MACRO__(0x5A4C, ## __VA_ARGS__), \ + MACRO__(0x5A54, ## __VA_ARGS__), \ + MACRO__(0x5A5C, ## __VA_ARGS__) + +#define INTEL_CNL_IDS(MACRO__, ...) \ + INTEL_CNL_PORT_F_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x5A40, ## __VA_ARGS__), \ + MACRO__(0x5A41, ## __VA_ARGS__), \ + MACRO__(0x5A42, ## __VA_ARGS__), \ + MACRO__(0x5A49, ## __VA_ARGS__), \ + MACRO__(0x5A4A, ## __VA_ARGS__), \ + MACRO__(0x5A50, ## __VA_ARGS__), \ + MACRO__(0x5A51, ## __VA_ARGS__), \ + MACRO__(0x5A52, ## __VA_ARGS__), \ + MACRO__(0x5A59, ## __VA_ARGS__), \ + MACRO__(0x5A5A, ## __VA_ARGS__) + +/* ICL */ +#define INTEL_ICL_PORT_F_IDS(MACRO__, ...) \ + MACRO__(0x8A50, ## __VA_ARGS__), \ + MACRO__(0x8A52, ## __VA_ARGS__), \ + MACRO__(0x8A53, ## __VA_ARGS__), \ + MACRO__(0x8A54, ## __VA_ARGS__), \ + MACRO__(0x8A56, ## __VA_ARGS__), \ + MACRO__(0x8A57, ## __VA_ARGS__), \ + MACRO__(0x8A58, ## __VA_ARGS__), \ + MACRO__(0x8A59, ## __VA_ARGS__), \ + MACRO__(0x8A5A, ## __VA_ARGS__), \ + MACRO__(0x8A5B, ## __VA_ARGS__), \ + MACRO__(0x8A5C, ## __VA_ARGS__), \ + MACRO__(0x8A70, ## __VA_ARGS__), \ + MACRO__(0x8A71, ## __VA_ARGS__) + +#define INTEL_ICL_IDS(MACRO__, ...) \ + INTEL_ICL_PORT_F_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0x8A51, ## __VA_ARGS__), \ + MACRO__(0x8A5D, ## __VA_ARGS__) + +/* EHL */ +#define INTEL_EHL_IDS(MACRO__, ...) \ + MACRO__(0x4541, ## __VA_ARGS__), \ + MACRO__(0x4551, ## __VA_ARGS__), \ + MACRO__(0x4555, ## __VA_ARGS__), \ + MACRO__(0x4557, ## __VA_ARGS__), \ + MACRO__(0x4570, ## __VA_ARGS__), \ + MACRO__(0x4571, ## __VA_ARGS__) + +/* JSL */ +#define INTEL_JSL_IDS(MACRO__, ...) \ + MACRO__(0x4E51, ## __VA_ARGS__), \ + MACRO__(0x4E55, ## __VA_ARGS__), \ + MACRO__(0x4E57, ## __VA_ARGS__), \ + MACRO__(0x4E61, ## __VA_ARGS__), \ + MACRO__(0x4E71, ## __VA_ARGS__) + +/* TGL */ +#define INTEL_TGL_GT1_IDS(MACRO__, ...) \ + MACRO__(0x9A60, ## __VA_ARGS__), \ + MACRO__(0x9A68, ## __VA_ARGS__), \ + MACRO__(0x9A70, ## __VA_ARGS__) + +#define INTEL_TGL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x9A40, ## __VA_ARGS__), \ + MACRO__(0x9A49, ## __VA_ARGS__), \ + MACRO__(0x9A59, ## __VA_ARGS__), \ + MACRO__(0x9A78, ## __VA_ARGS__), \ + MACRO__(0x9AC0, ## __VA_ARGS__), \ + MACRO__(0x9AC9, ## __VA_ARGS__), \ + MACRO__(0x9AD9, ## __VA_ARGS__), \ + MACRO__(0x9AF8, ## __VA_ARGS__) + +#define INTEL_TGL_IDS(MACRO__, ...) \ + INTEL_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__) + +/* RKL */ +#define INTEL_RKL_IDS(MACRO__, ...) \ + MACRO__(0x4C80, ## __VA_ARGS__), \ + MACRO__(0x4C8A, ## __VA_ARGS__), \ + MACRO__(0x4C8B, ## __VA_ARGS__), \ + MACRO__(0x4C8C, ## __VA_ARGS__), \ + MACRO__(0x4C90, ## __VA_ARGS__), \ + MACRO__(0x4C9A, ## __VA_ARGS__) + +/* DG1 */ +#define INTEL_DG1_IDS(MACRO__, ...) \ + MACRO__(0x4905, ## __VA_ARGS__), \ + MACRO__(0x4906, ## __VA_ARGS__), \ + MACRO__(0x4907, ## __VA_ARGS__), \ + MACRO__(0x4908, ## __VA_ARGS__), \ + MACRO__(0x4909, ## __VA_ARGS__) + +/* ADL-S */ +#define INTEL_ADLS_IDS(MACRO__, ...) \ + MACRO__(0x4680, ## __VA_ARGS__), \ + MACRO__(0x4682, ## __VA_ARGS__), \ + MACRO__(0x4688, ## __VA_ARGS__), \ + MACRO__(0x468A, ## __VA_ARGS__), \ + MACRO__(0x468B, ## __VA_ARGS__), \ + MACRO__(0x4690, ## __VA_ARGS__), \ + MACRO__(0x4692, ## __VA_ARGS__), \ + MACRO__(0x4693, ## __VA_ARGS__) + +/* ADL-P */ +#define INTEL_ADLP_IDS(MACRO__, ...) \ + MACRO__(0x46A0, ## __VA_ARGS__), \ + MACRO__(0x46A1, ## __VA_ARGS__), \ + MACRO__(0x46A2, ## __VA_ARGS__), \ + MACRO__(0x46A3, ## __VA_ARGS__), \ + MACRO__(0x46A6, ## __VA_ARGS__), \ + MACRO__(0x46A8, ## __VA_ARGS__), \ + MACRO__(0x46AA, ## __VA_ARGS__), \ + MACRO__(0x462A, ## __VA_ARGS__), \ + MACRO__(0x4626, ## __VA_ARGS__), \ + MACRO__(0x4628, ## __VA_ARGS__), \ + MACRO__(0x46B0, ## __VA_ARGS__), \ + MACRO__(0x46B1, ## __VA_ARGS__), \ + MACRO__(0x46B2, ## __VA_ARGS__), \ + MACRO__(0x46B3, ## __VA_ARGS__), \ + MACRO__(0x46C0, ## __VA_ARGS__), \ + MACRO__(0x46C1, ## __VA_ARGS__), \ + MACRO__(0x46C2, ## __VA_ARGS__), \ + MACRO__(0x46C3, ## __VA_ARGS__) + +/* ADL-N */ +#define INTEL_ADLN_IDS(MACRO__, ...) \ + MACRO__(0x46D0, ## __VA_ARGS__), \ + MACRO__(0x46D1, ## __VA_ARGS__), \ + MACRO__(0x46D2, ## __VA_ARGS__), \ + MACRO__(0x46D3, ## __VA_ARGS__), \ + MACRO__(0x46D4, ## __VA_ARGS__) + +/* RPL-S */ +#define INTEL_RPLS_IDS(MACRO__, ...) \ + MACRO__(0xA780, ## __VA_ARGS__), \ + MACRO__(0xA781, ## __VA_ARGS__), \ + MACRO__(0xA782, ## __VA_ARGS__), \ + MACRO__(0xA783, ## __VA_ARGS__), \ + MACRO__(0xA788, ## __VA_ARGS__), \ + MACRO__(0xA789, ## __VA_ARGS__), \ + MACRO__(0xA78A, ## __VA_ARGS__), \ + MACRO__(0xA78B, ## __VA_ARGS__) + +/* RPL-U */ +#define INTEL_RPLU_IDS(MACRO__, ...) \ + MACRO__(0xA721, ## __VA_ARGS__), \ + MACRO__(0xA7A1, ## __VA_ARGS__), \ + MACRO__(0xA7A9, ## __VA_ARGS__), \ + MACRO__(0xA7AC, ## __VA_ARGS__), \ + MACRO__(0xA7AD, ## __VA_ARGS__) + +/* RPL-P */ +#define INTEL_RPLP_IDS(MACRO__, ...) \ + MACRO__(0xA720, ## __VA_ARGS__), \ + MACRO__(0xA7A0, ## __VA_ARGS__), \ + MACRO__(0xA7A8, ## __VA_ARGS__), \ + MACRO__(0xA7AA, ## __VA_ARGS__), \ + MACRO__(0xA7AB, ## __VA_ARGS__) + +/* DG2 */ +#define INTEL_DG2_G10_IDS(MACRO__, ...) \ + MACRO__(0x5690, ## __VA_ARGS__), \ + MACRO__(0x5691, ## __VA_ARGS__), \ + MACRO__(0x5692, ## __VA_ARGS__), \ + MACRO__(0x56A0, ## __VA_ARGS__), \ + MACRO__(0x56A1, ## __VA_ARGS__), \ + MACRO__(0x56A2, ## __VA_ARGS__), \ + MACRO__(0x56BE, ## __VA_ARGS__), \ + MACRO__(0x56BF, ## __VA_ARGS__) + +#define INTEL_DG2_G11_IDS(MACRO__, ...) \ + MACRO__(0x5693, ## __VA_ARGS__), \ + MACRO__(0x5694, ## __VA_ARGS__), \ + MACRO__(0x5695, ## __VA_ARGS__), \ + MACRO__(0x56A5, ## __VA_ARGS__), \ + MACRO__(0x56A6, ## __VA_ARGS__), \ + MACRO__(0x56B0, ## __VA_ARGS__), \ + MACRO__(0x56B1, ## __VA_ARGS__), \ + MACRO__(0x56BA, ## __VA_ARGS__), \ + MACRO__(0x56BB, ## __VA_ARGS__), \ + MACRO__(0x56BC, ## __VA_ARGS__), \ + MACRO__(0x56BD, ## __VA_ARGS__) + +#define INTEL_DG2_G12_IDS(MACRO__, ...) \ + MACRO__(0x5696, ## __VA_ARGS__), \ + MACRO__(0x5697, ## __VA_ARGS__), \ + MACRO__(0x56A3, ## __VA_ARGS__), \ + MACRO__(0x56A4, ## __VA_ARGS__), \ + MACRO__(0x56B2, ## __VA_ARGS__), \ + MACRO__(0x56B3, ## __VA_ARGS__) + +#define INTEL_DG2_IDS(MACRO__, ...) \ + INTEL_DG2_G10_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_DG2_G11_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_DG2_G12_IDS(MACRO__, ## __VA_ARGS__) + +#define INTEL_ATS_M150_IDS(MACRO__, ...) \ + MACRO__(0x56C0, ## __VA_ARGS__), \ + MACRO__(0x56C2, ## __VA_ARGS__) + +#define INTEL_ATS_M75_IDS(MACRO__, ...) \ + MACRO__(0x56C1, ## __VA_ARGS__) + +#define INTEL_ATS_M_IDS(MACRO__, ...) \ + INTEL_ATS_M150_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_ATS_M75_IDS(MACRO__, ## __VA_ARGS__) + +/* MTL */ +#define INTEL_MTL_IDS(MACRO__, ...) \ + MACRO__(0x7D40, ## __VA_ARGS__), \ + MACRO__(0x7D41, ## __VA_ARGS__), \ + MACRO__(0x7D45, ## __VA_ARGS__), \ + MACRO__(0x7D51, ## __VA_ARGS__), \ + MACRO__(0x7D55, ## __VA_ARGS__), \ + MACRO__(0x7D60, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__), \ + MACRO__(0x7DD1, ## __VA_ARGS__), \ + MACRO__(0x7DD5, ## __VA_ARGS__) + +#endif /* _I915_PCIIDS_H */ diff --git a/src/linux/intel_gpu_top/i915_pciids_local.h b/src/linux/intel_gpu_top/i915_pciids_local.h new file mode 100644 index 00000000..c404a51a --- /dev/null +++ b/src/linux/intel_gpu_top/i915_pciids_local.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ +#ifndef _I915_PCIIDS_LOCAL_H_ +#define _I915_PCIIDS_LOCAL_H_ + +#include "i915_pciids.h" + +/* MTL perf */ +#ifndef INTEL_MTL_M_IDS +#define INTEL_MTL_M_IDS(MACRO__, ...) \ + MACRO__(0x7D60, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__) +#endif + +#ifndef INTEL_MTL_P_GT2_IDS +#define INTEL_MTL_P_GT2_IDS(MACRO__, ...) \ + MACRO__(0x7D45, ## __VA_ARGS__) +#endif + +#ifndef INTEL_MTL_P_GT3_IDS +#define INTEL_MTL_P_GT3_IDS(MACRO__, ...) \ + MACRO__(0x7D55, ## __VA_ARGS__), \ + MACRO__(0x7DD5, ## __VA_ARGS__) +#endif + +#ifndef INTEL_MTL_P_IDS +#define INTEL_MTL_P_IDS(MACRO__, ...) \ + INTEL_MTL_P_GT2_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_MTL_P_GT3_IDS(MACRO__, ## __VA_ARGS__) +#endif + +#ifndef INTEL_ARL_GT1_IDS +#define INTEL_ARL_GT1_IDS(MACRO__, ...) \ + MACRO__(0x7D41, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__) +#endif + +#ifndef INTEL_ARL_GT2_IDS +#define INTEL_ARL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x7D51, ## __VA_ARGS__), \ + MACRO__(0x7DD1, ## __VA_ARGS__) +#endif + +#ifndef INTEL_ARL_IDS +#define INTEL_ARL_IDS(MACRO__, ...) \ + INTEL_ARL_GT1_IDS(MACRO__, ## __VA_ARGS__), \ + INTEL_ARL_GT2_IDS(MACRO__, ## __VA_ARGS__) +#endif + +/* PVC */ +#ifndef INTEL_PVC_IDS +#define INTEL_PVC_IDS(MACRO__, ...) \ + MACRO__(0x0BD0, ## __VA_ARGS__), \ + MACRO__(0x0BD1, ## __VA_ARGS__), \ + MACRO__(0x0BD2, ## __VA_ARGS__), \ + MACRO__(0x0BD5, ## __VA_ARGS__), \ + MACRO__(0x0BD6, ## __VA_ARGS__), \ + MACRO__(0x0BD7, ## __VA_ARGS__), \ + MACRO__(0x0BD8, ## __VA_ARGS__), \ + MACRO__(0x0BD9, ## __VA_ARGS__), \ + MACRO__(0x0BDA, ## __VA_ARGS__), \ + MACRO__(0x0BDB, ## __VA_ARGS__) +#endif + +#endif /* _I915_PCIIDS_LOCAL_H */ diff --git a/src/linux/intel_gpu_top/igt_perf.c b/src/linux/intel_gpu_top/igt_perf.c new file mode 100644 index 00000000..001d02ab --- /dev/null +++ b/src/linux/intel_gpu_top/igt_perf.c @@ -0,0 +1,210 @@ +#include +#include +#include +#include +#include +#include +#include +#ifdef __linux__ +#include +#include +#include +#endif +#include +#include +#include + +#include "igt_perf.h" + +static char *bus_address(int i915, char *path, int pathlen) +{ + struct stat st; + int len = -1; + int dir; + char *s; + + if (fstat(i915, &st) || !S_ISCHR(st.st_mode)) + return NULL; + + snprintf(path, pathlen, "/sys/dev/char/%d:%d", + major(st.st_rdev), minor(st.st_rdev)); + + dir = open(path, O_RDONLY); + if (dir != -1) { + len = readlinkat(dir, "device", path, pathlen - 1); + close(dir); + } + if (len < 0) + return NULL; + + path[len] = '\0'; + + /* strip off the relative path */ + s = strrchr(path, '/'); + if (s) + memmove(path, s + 1, len - (s - path) + 1); + + return path; +} + +const char *i915_perf_device(int i915, char *buf, int buflen) +{ + char *s; + +#define prefix "i915_" +#define plen strlen(prefix) + + if (!buf || buflen < plen) + return "i915"; + + memcpy(buf, prefix, plen); + + if (!bus_address(i915, buf + plen, buflen - plen) || + strcmp(buf + plen, "0000:00:02.0") == 0) /* legacy name for igfx */ + buf[plen - 1] = '\0'; + + /* Convert all colons in the address to '_', thanks perf! */ + for (s = buf; *s; s++) + if (*s == ':') + *s = '_'; + + return buf; +} + +const char *xe_perf_device(int xe, char *buf, int buflen) +{ + char *s; + char pref[] = "xe_"; + int len = strlen(pref); + + + if (!buf || buflen < len) + return "xe"; + + memcpy(buf, pref, len); + + if (!bus_address(xe, buf + len, buflen - len)) + buf[len - 1] = '\0'; + + /* Convert all colons in the address to '_', thanks perf! */ + for (s = buf; *s; s++) + if (*s == ':') + *s = '_'; + + return buf; +} + +uint64_t xe_perf_type_id(int xe) +{ + char buf[80]; + + return igt_perf_type_id(xe_perf_device(xe, buf, sizeof(buf))); +} + +uint64_t i915_perf_type_id(int i915) +{ + char buf[80]; + + return igt_perf_type_id(i915_perf_device(i915, buf, sizeof(buf))); +} + +uint64_t igt_perf_type_id(const char *device) +{ + char buf[64]; + ssize_t ret; + int fd; + + snprintf(buf, sizeof(buf), + "/sys/bus/event_source/devices/%s/type", device); + + fd = open(buf, O_RDONLY); + if (fd < 0) + return 0; + + ret = read(fd, buf, sizeof(buf) - 1); + close(fd); + if (ret < 1) + return 0; + + buf[ret] = '\0'; + + return strtoull(buf, NULL, 0); +} + +int igt_perf_events_dir(int i915) +{ + char buf[80]; + char path[PATH_MAX]; + + i915_perf_device(i915, buf, sizeof(buf)); + snprintf(path, sizeof(path), "/sys/bus/event_source/devices/%s/events", buf); + return open(path, O_RDONLY); +} + +static int +_perf_open(uint64_t type, uint64_t config, int group, uint64_t format) +{ + struct perf_event_attr attr = { }; + int nr_cpus = get_nprocs_conf(); + int cpu = 0, ret; + + attr.type = type; + if (attr.type == 0) + return -ENOENT; + + if (group >= 0) + format &= ~PERF_FORMAT_GROUP; + + attr.read_format = format; + attr.config = config; + attr.use_clockid = 1; + attr.clockid = CLOCK_MONOTONIC; + + do { + ret = perf_event_open(&attr, -1, cpu++, group, 0); + } while ((ret < 0 && errno == EINVAL) && (cpu < nr_cpus)); + + return ret; +} + +int perf_igfx_open(uint64_t config) +{ + return _perf_open(igt_perf_type_id("i915"), config, -1, + PERF_FORMAT_TOTAL_TIME_ENABLED); +} + +int perf_igfx_open_group(uint64_t config, int group) +{ + return _perf_open(igt_perf_type_id("i915"), config, group, + PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_GROUP); +} + +int perf_xe_open(int xe, uint64_t config) +{ + return _perf_open(xe_perf_type_id(xe), config, -1, + PERF_FORMAT_TOTAL_TIME_ENABLED); +} + +int perf_i915_open(int i915, uint64_t config) +{ + return _perf_open(i915_perf_type_id(i915), config, -1, + PERF_FORMAT_TOTAL_TIME_ENABLED); +} + +int perf_i915_open_group(int i915, uint64_t config, int group) +{ + return _perf_open(i915_perf_type_id(i915), config, group, + PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_GROUP); +} + +int igt_perf_open(uint64_t type, uint64_t config) +{ + return _perf_open(type, config, -1, + PERF_FORMAT_TOTAL_TIME_ENABLED); +} + +int igt_perf_open_group(uint64_t type, uint64_t config, int group) +{ + return _perf_open(type, config, group, + PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_GROUP); +} diff --git a/src/linux/intel_gpu_top/igt_perf.h b/src/linux/intel_gpu_top/igt_perf.h new file mode 100644 index 00000000..e2513ef0 --- /dev/null +++ b/src/linux/intel_gpu_top/igt_perf.h @@ -0,0 +1,75 @@ +/* + * 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_PERF_H +#define I915_PERF_H + +#include + +#ifdef __linux__ +#include +#endif + +//#include "igt_gt.h" + +static inline int +perf_event_open(struct perf_event_attr *attr, + pid_t pid, + int cpu, + int group_fd, + unsigned long flags) +{ +#ifndef __NR_perf_event_open +#if defined(__i386__) +#define __NR_perf_event_open 336 +#elif defined(__x86_64__) +#define __NR_perf_event_open 298 +#else +#define __NR_perf_event_open 0 +#endif +#endif + attr->size = sizeof(*attr); + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +uint64_t igt_perf_type_id(const char *device); +int igt_perf_events_dir(int i915); +int igt_perf_open(uint64_t type, uint64_t config); +int igt_perf_open_group(uint64_t type, uint64_t config, int group); + +const char *i915_perf_device(int i915, char *buf, int buflen); +uint64_t i915_perf_type_id(int i915); + +const char *xe_perf_device(int xe, char *buf, int buflen); +uint64_t xe_perf_type_id(int); + +int perf_igfx_open(uint64_t config); +int perf_igfx_open_group(uint64_t config, int group); + +int perf_i915_open(int i915, uint64_t config); +int perf_i915_open_group(int i915, uint64_t config, int group); + +int perf_xe_open(int xe, uint64_t config); + +#endif /* I915_PERF_H */ diff --git a/src/linux/intel_gpu_top/intel_chipset.h b/src/linux/intel_gpu_top/intel_chipset.h new file mode 100644 index 00000000..843d7650 --- /dev/null +++ b/src/linux/intel_gpu_top/intel_chipset.h @@ -0,0 +1,233 @@ +/* + * Copyright © 2007 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. + * + * Authors: + * Eric Anholt + * + */ + +#ifndef _INTEL_CHIPSET_H +#define _INTEL_CHIPSET_H + +#include +#include + +#define BIT(x) (1ul <<(x)) + +struct intel_device_info { + unsigned graphics_ver; + unsigned graphics_rel; + unsigned display_ver; + unsigned gt; /* 0 if unknown */ + bool has_4tile : 1; + bool has_flatccs : 1; + bool has_oam : 1; + bool is_mobile : 1; + bool is_whitney : 1; + bool is_almador : 1; + bool is_brookdale : 1; + bool is_montara : 1; + bool is_springdale : 1; + bool is_grantsdale : 1; + bool is_alviso : 1; + bool is_lakeport : 1; + bool is_calistoga : 1; + bool is_bearlake : 1; + bool is_pineview : 1; + bool is_broadwater : 1; + bool is_crestline : 1; + bool is_eaglelake : 1; + bool is_cantiga : 1; + bool is_ironlake : 1; + bool is_arrandale : 1; + bool is_sandybridge : 1; + bool is_ivybridge : 1; + bool is_valleyview : 1; + bool is_haswell : 1; + bool is_broadwell : 1; + bool is_cherryview : 1; + bool is_skylake : 1; + bool is_broxton : 1; + bool is_kabylake : 1; + bool is_geminilake : 1; + bool is_coffeelake : 1; + bool is_cometlake : 1; + bool is_cannonlake : 1; + bool is_icelake : 1; + bool is_elkhartlake : 1; + bool is_jasperlake : 1; + bool is_tigerlake : 1; + bool is_rocketlake : 1; + bool is_dg1 : 1; + bool is_dg2 : 1; + bool is_alderlake_s : 1; + bool is_raptorlake_s : 1; + bool is_alderlake_p : 1; + bool is_alderlake_n : 1; + bool is_meteorlake : 1; + bool is_pontevecchio : 1; + bool is_lunarlake : 1; + bool is_battlemage : 1; + const char *codename; +}; + +const struct intel_device_info *intel_get_device_info(uint16_t devid) __attribute__((pure)); + +extern enum pch_type intel_pch; + +enum pch_type { + PCH_NONE, + PCH_IBX, + PCH_CPT, + PCH_LPT, +}; + +void intel_check_pch(void); + +#define HAS_IBX (intel_pch == PCH_IBX) +#define HAS_CPT (intel_pch == PCH_CPT) +#define HAS_LPT (intel_pch == PCH_LPT) + +#define IP_VER(ver, rel) ((ver) << 8 | (rel)) + +/* Exclude chipset #defines, they just add noise */ +#ifndef __GTK_DOC_IGNORE__ + +#define PCI_CHIP_I810 0x7121 +#define PCI_CHIP_I810_DC100 0x7123 +#define PCI_CHIP_I810_E 0x7125 +#define PCI_CHIP_I815 0x1132 + +#define PCI_CHIP_I830_M 0x3577 +#define PCI_CHIP_845_G 0x2562 +#define PCI_CHIP_I854_G 0x358e +#define PCI_CHIP_I855_GM 0x3582 +#define PCI_CHIP_I865_G 0x2572 + +#define PCI_CHIP_I915_G 0x2582 +#define PCI_CHIP_E7221_G 0x258A +#define PCI_CHIP_I915_GM 0x2592 +#define PCI_CHIP_I945_G 0x2772 +#define PCI_CHIP_I945_GM 0x27A2 +#define PCI_CHIP_I945_GME 0x27AE + +#define PCI_CHIP_I965_G 0x29A2 +#define PCI_CHIP_I965_Q 0x2992 +#define PCI_CHIP_I965_G_1 0x2982 +#define PCI_CHIP_I946_GZ 0x2972 +#define PCI_CHIP_I965_GM 0x2A02 +#define PCI_CHIP_I965_GME 0x2A12 + +#define PCI_CHIP_GM45_GM 0x2A42 + +#define PCI_CHIP_Q45_G 0x2E12 +#define PCI_CHIP_G45_G 0x2E22 +#define PCI_CHIP_G41_G 0x2E32 + +#endif /* __GTK_DOC_IGNORE__ */ + +#define IS_915G(devid) (intel_get_device_info(devid)->is_grantsdale) +#define IS_915GM(devid) (intel_get_device_info(devid)->is_alviso) + +#define IS_915(devid) (IS_915G(devid) || IS_915GM(devid)) + +#define IS_945G(devid) (intel_get_device_info(devid)->is_lakeport) +#define IS_945GM(devid) (intel_get_device_info(devid)->is_calistoga) + +#define IS_945(devid) (IS_945G(devid) || \ + IS_945GM(devid) || \ + IS_G33(devid)) + +#define IS_PINEVIEW(devid) (intel_get_device_info(devid)->is_pineview) +#define IS_G33(devid) (intel_get_device_info(devid)->is_bearlake || \ + intel_get_device_info(devid)->is_pineview) + +#define IS_BROADWATER(devid) (intel_get_device_info(devid)->is_broadwater) +#define IS_CRESTLINE(devid) (intel_get_device_info(devid)->is_crestline) + +#define IS_GM45(devid) (intel_get_device_info(devid)->is_cantiga) +#define IS_G45(devid) (intel_get_device_info(devid)->is_eaglelake) +#define IS_G4X(devid) (IS_G45(devid) || IS_GM45(devid)) + +#define IS_IRONLAKE(devid) (intel_get_device_info(devid)->is_ironlake) +#define IS_ARRANDALE(devid) (intel_get_device_info(devid)->is_arrandale) +#define IS_SANDYBRIDGE(devid) (intel_get_device_info(devid)->is_sandybridge) +#define IS_IVYBRIDGE(devid) (intel_get_device_info(devid)->is_ivybridge) +#define IS_VALLEYVIEW(devid) (intel_get_device_info(devid)->is_valleyview) +#define IS_HASWELL(devid) (intel_get_device_info(devid)->is_haswell) +#define IS_BROADWELL(devid) (intel_get_device_info(devid)->is_broadwell) +#define IS_CHERRYVIEW(devid) (intel_get_device_info(devid)->is_cherryview) +#define IS_SKYLAKE(devid) (intel_get_device_info(devid)->is_skylake) +#define IS_BROXTON(devid) (intel_get_device_info(devid)->is_broxton) +#define IS_KABYLAKE(devid) (intel_get_device_info(devid)->is_kabylake) +#define IS_GEMINILAKE(devid) (intel_get_device_info(devid)->is_geminilake) +#define IS_COFFEELAKE(devid) (intel_get_device_info(devid)->is_coffeelake) +#define IS_COMETLAKE(devid) (intel_get_device_info(devid)->is_cometlake) +#define IS_CANNONLAKE(devid) (intel_get_device_info(devid)->is_cannonlake) +#define IS_ICELAKE(devid) (intel_get_device_info(devid)->is_icelake) +#define IS_TIGERLAKE(devid) (intel_get_device_info(devid)->is_tigerlake) +#define IS_ROCKETLAKE(devid) (intel_get_device_info(devid)->is_rocketlake) +#define IS_DG1(devid) (intel_get_device_info(devid)->is_dg1) +#define IS_DG2(devid) (intel_get_device_info(devid)->is_dg2) +#define IS_ALDERLAKE_S(devid) (intel_get_device_info(devid)->is_alderlake_s) +#define IS_RAPTORLAKE_S(devid) (intel_get_device_info(devid)->is_raptorlake_s) +#define IS_ALDERLAKE_P(devid) (intel_get_device_info(devid)->is_alderlake_p) +#define IS_ALDERLAKE_N(devid) (intel_get_device_info(devid)->is_alderlake_n) +#define IS_METEORLAKE(devid) (intel_get_device_info(devid)->is_meteorlake) +#define IS_PONTEVECCHIO(devid) (intel_get_device_info(devid)->is_pontevecchio) +#define IS_LUNARLAKE(devid) (intel_get_device_info(devid)->is_lunarlake) +#define IS_BATTLEMAGE(devid) (intel_get_device_info(devid)->is_battlemage) + +#define IS_GEN(devid, x) (intel_get_device_info(devid)->graphics_ver == x) +#define AT_LEAST_GEN(devid, x) (intel_get_device_info(devid)->graphics_ver >= x) +#define AT_LEAST_DISPLAY(devid, x) (intel_get_device_info(devid)->display_ver >= x) + +#define IS_GEN2(devid) IS_GEN(devid, 2) +#define IS_GEN3(devid) IS_GEN(devid, 3) +#define IS_GEN4(devid) IS_GEN(devid, 4) +#define IS_GEN5(devid) IS_GEN(devid, 5) +#define IS_GEN6(devid) IS_GEN(devid, 6) +#define IS_GEN7(devid) IS_GEN(devid, 7) +#define IS_GEN8(devid) IS_GEN(devid, 8) +#define IS_GEN9(devid) IS_GEN(devid, 9) +#define IS_GEN10(devid) IS_GEN(devid, 10) +#define IS_GEN11(devid) IS_GEN(devid, 11) +#define IS_GEN12(devid) IS_GEN(devid, 12) + +#define IS_MOBILE(devid) (intel_get_device_info(devid)->is_mobile) +#define IS_965(devid) AT_LEAST_GEN(devid, 4) + +#define HAS_BSD_RING(devid) AT_LEAST_GEN(devid, 5) +#define HAS_BLT_RING(devid) AT_LEAST_GEN(devid, 6) + +#define HAS_PCH_SPLIT(devid) (AT_LEAST_GEN(devid, 5) && \ + !(IS_VALLEYVIEW(devid) || \ + IS_CHERRYVIEW(devid) || \ + IS_BROXTON(devid))) + +#define HAS_4TILE(devid) (intel_get_device_info(devid)->has_4tile) + +#define HAS_FLATCCS(devid) (intel_get_device_info(devid)->has_flatccs) + +#define HAS_OAM(devid) (intel_get_device_info(devid)->has_oam) + +#endif /* _INTEL_CHIPSET_H */ diff --git a/src/linux/intel_gpu_top/intel_device_info.c b/src/linux/intel_gpu_top/intel_device_info.c new file mode 100644 index 00000000..aab04b78 --- /dev/null +++ b/src/linux/intel_gpu_top/intel_device_info.c @@ -0,0 +1,653 @@ +#include "intel_chipset.h" +#include "i915_pciids.h" +#include "i915_pciids_local.h" +#include "xe_pciids.h" + +#include /* ffs() */ + +// from pciaccess.h +#define PCI_MATCH_ANY (~0U) + +// from pciaccess.h +struct pci_id_match { + /** + * \name Device / vendor matching controls + * + * Control the search based on the device, vendor, subdevice, or subvendor + * IDs. Setting any of these fields to \c PCI_MATCH_ANY will cause the + * field to not be used in the comparison. + */ + /*@{*/ + uint32_t vendor_id; + uint32_t device_id; + uint32_t subvendor_id; + uint32_t subdevice_id; + /*@}*/ + + + /** + * \name Device class matching controls + * + */ + /*@{*/ + uint32_t device_class; + uint32_t device_class_mask; + /*@}*/ + + intptr_t match_data; +}; + +static const struct intel_device_info intel_generic_info = { + .graphics_ver = 0, + .display_ver = 0, +}; + +static const struct intel_device_info intel_i810_info = { + .graphics_ver = 1, + .display_ver = 1, + .is_whitney = true, + .codename = "solano" /* 815 == "whitney" ? or vice versa? */ +}; + +static const struct intel_device_info intel_i815_info = { + .graphics_ver = 1, + .display_ver = 1, + .is_whitney = true, + .codename = "whitney" +}; + +static const struct intel_device_info intel_i830_info = { + .graphics_ver = 2, + .display_ver = 2, + .is_almador = true, + .codename = "almador" +}; +static const struct intel_device_info intel_i845_info = { + .graphics_ver = 2, + .display_ver = 2, + .is_brookdale = true, + .codename = "brookdale" +}; +static const struct intel_device_info intel_i855_info = { + .graphics_ver = 2, + .display_ver = 2, + .is_mobile = true, + .is_montara = true, + .codename = "montara" +}; +static const struct intel_device_info intel_i865_info = { + .graphics_ver = 2, + .display_ver = 2, + .is_springdale = true, + .codename = "spingdale" +}; + +static const struct intel_device_info intel_i915_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_grantsdale = true, + .codename = "grantsdale" +}; +static const struct intel_device_info intel_i915m_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_mobile = true, + .is_alviso = true, + .codename = "alviso" +}; +static const struct intel_device_info intel_i945_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_lakeport = true, + .codename = "lakeport" +}; +static const struct intel_device_info intel_i945m_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_mobile = true, + .is_calistoga = true, + .codename = "calistoga" +}; + +static const struct intel_device_info intel_g33_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_bearlake = true, + .codename = "bearlake" +}; + +static const struct intel_device_info intel_pineview_g_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_pineview = true, + .codename = "pineview" +}; + +static const struct intel_device_info intel_pineview_m_info = { + .graphics_ver = 3, + .display_ver = 3, + .is_mobile = true, + .is_pineview = true, + .codename = "pineview" +}; + +static const struct intel_device_info intel_i965_info = { + .graphics_ver = 4, + .display_ver = 4, + .is_broadwater = true, + .codename = "broadwater" +}; + +static const struct intel_device_info intel_i965m_info = { + .graphics_ver = 4, + .display_ver = 4, + .is_mobile = true, + .is_crestline = true, + .codename = "crestline" +}; + +static const struct intel_device_info intel_g45_info = { + .graphics_ver = 4, + .display_ver = 4, + .is_eaglelake = true, + .codename = "eaglelake" +}; +static const struct intel_device_info intel_gm45_info = { + .graphics_ver = 4, + .display_ver = 4, + .is_mobile = true, + .is_cantiga = true, + .codename = "cantiga" +}; + +static const struct intel_device_info intel_ironlake_info = { + .graphics_ver = 5, + .display_ver = 5, + .is_ironlake = true, + .codename = "ironlake" /* clarkdale? */ +}; +static const struct intel_device_info intel_ironlake_m_info = { + .graphics_ver = 5, + .display_ver = 5, + .is_mobile = true, + .is_arrandale = true, + .codename = "arrandale" +}; + +static const struct intel_device_info intel_sandybridge_info = { + .graphics_ver = 6, + .display_ver = 6, + .is_sandybridge = true, + .codename = "sandybridge" +}; +static const struct intel_device_info intel_sandybridge_m_info = { + .graphics_ver = 6, + .display_ver = 6, + .is_mobile = true, + .is_sandybridge = true, + .codename = "sandybridge" +}; + +static const struct intel_device_info intel_ivybridge_info = { + .graphics_ver = 7, + .display_ver = 7, + .is_ivybridge = true, + .codename = "ivybridge" +}; +static const struct intel_device_info intel_ivybridge_m_info = { + .graphics_ver = 7, + .display_ver = 7, + .is_mobile = true, + .is_ivybridge = true, + .codename = "ivybridge" +}; + +static const struct intel_device_info intel_valleyview_info = { + .graphics_ver = 7, + .display_ver = 7, + .is_valleyview = true, + .codename = "valleyview" +}; + +#define HASWELL_FIELDS \ + .graphics_ver = 7, \ + .display_ver = 7, \ + .is_haswell = true, \ + .codename = "haswell" + +static const struct intel_device_info intel_haswell_gt1_info = { + HASWELL_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_haswell_gt2_info = { + HASWELL_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_haswell_gt3_info = { + HASWELL_FIELDS, + .gt = 3, +}; + +#define BROADWELL_FIELDS \ + .graphics_ver = 8, \ + .display_ver = 8, \ + .is_broadwell = true, \ + .codename = "broadwell" + +static const struct intel_device_info intel_broadwell_gt1_info = { + BROADWELL_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_broadwell_gt2_info = { + BROADWELL_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_broadwell_gt3_info = { + BROADWELL_FIELDS, + .gt = 3, +}; + +static const struct intel_device_info intel_broadwell_unknown_info = { + BROADWELL_FIELDS, +}; + +static const struct intel_device_info intel_cherryview_info = { + .graphics_ver = 8, + .display_ver = 8, + .is_cherryview = true, + .codename = "cherryview" +}; + +#define SKYLAKE_FIELDS \ + .graphics_ver = 9, \ + .display_ver = 9, \ + .codename = "skylake", \ + .is_skylake = true + +static const struct intel_device_info intel_skylake_gt1_info = { + SKYLAKE_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_skylake_gt2_info = { + SKYLAKE_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_skylake_gt3_info = { + SKYLAKE_FIELDS, + .gt = 3, +}; + +static const struct intel_device_info intel_skylake_gt4_info = { + SKYLAKE_FIELDS, + .gt = 4, +}; + +static const struct intel_device_info intel_broxton_info = { + .graphics_ver = 9, + .display_ver = 9, + .is_broxton = true, + .codename = "broxton" +}; + +#define KABYLAKE_FIELDS \ + .graphics_ver = 9, \ + .display_ver = 9, \ + .is_kabylake = true, \ + .codename = "kabylake" + +static const struct intel_device_info intel_kabylake_gt1_info = { + KABYLAKE_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_kabylake_gt2_info = { + KABYLAKE_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_kabylake_gt3_info = { + KABYLAKE_FIELDS, + .gt = 3, +}; + +static const struct intel_device_info intel_kabylake_gt4_info = { + KABYLAKE_FIELDS, + .gt = 4, +}; + +static const struct intel_device_info intel_geminilake_info = { + .graphics_ver = 9, + .display_ver = 9, + .is_geminilake = true, + .codename = "geminilake" +}; + +#define COFFEELAKE_FIELDS \ + .graphics_ver = 9, \ + .display_ver = 9, \ + .is_coffeelake = true, \ + .codename = "coffeelake" + +static const struct intel_device_info intel_coffeelake_gt1_info = { + COFFEELAKE_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_coffeelake_gt2_info = { + COFFEELAKE_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_coffeelake_gt3_info = { + COFFEELAKE_FIELDS, + .gt = 3, +}; + +#define COMETLAKE_FIELDS \ + .graphics_ver = 9, \ + .display_ver = 9, \ + .is_cometlake = true, \ + .codename = "cometlake" + +static const struct intel_device_info intel_cometlake_gt1_info = { + COMETLAKE_FIELDS, + .gt = 1, +}; + +static const struct intel_device_info intel_cometlake_gt2_info = { + COMETLAKE_FIELDS, + .gt = 2, +}; + +static const struct intel_device_info intel_cannonlake_info = { + .graphics_ver = 10, + .display_ver = 10, + .is_cannonlake = true, + .codename = "cannonlake" +}; + +static const struct intel_device_info intel_icelake_info = { + .graphics_ver = 11, + .display_ver = 11, + .is_icelake = true, + .codename = "icelake" +}; + +static const struct intel_device_info intel_elkhartlake_info = { + .graphics_ver = 11, + .display_ver = 11, + .is_elkhartlake = true, + .codename = "elkhartlake" +}; + +static const struct intel_device_info intel_jasperlake_info = { + .graphics_ver = 11, + .display_ver = 11, + .is_jasperlake = true, + .codename = "jasperlake" +}; + +static const struct intel_device_info intel_tigerlake_gt1_info = { + .graphics_ver = 12, + .display_ver = 12, + .is_tigerlake = true, + .codename = "tigerlake", + .gt = 1, +}; + +static const struct intel_device_info intel_tigerlake_gt2_info = { + .graphics_ver = 12, + .display_ver = 12, + .is_tigerlake = true, + .codename = "tigerlake", + .gt = 2, +}; + +static const struct intel_device_info intel_rocketlake_info = { + .graphics_ver = 12, + .display_ver = 12, + .is_rocketlake = true, + .codename = "rocketlake" +}; + +static const struct intel_device_info intel_dg1_info = { + .graphics_ver = 12, + .graphics_rel = 10, + .display_ver = 12, + .is_dg1 = true, + .codename = "dg1" +}; + +static const struct intel_device_info intel_dg2_info = { + .graphics_ver = 12, + .graphics_rel = 55, + .display_ver = 13, + .has_4tile = true, + .is_dg2 = true, + .codename = "dg2", + .has_flatccs = true, +}; + +static const struct intel_device_info intel_alderlake_s_info = { + .graphics_ver = 12, + .display_ver = 12, + .is_alderlake_s = true, + .codename = "alderlake_s" +}; + +static const struct intel_device_info intel_raptorlake_s_info = { + .graphics_ver = 12, + .display_ver = 12, + .is_raptorlake_s = true, + .codename = "raptorlake_s" +}; + +static const struct intel_device_info intel_alderlake_p_info = { + .graphics_ver = 12, + .display_ver = 13, + .is_alderlake_p = true, + .codename = "alderlake_p" +}; + +static const struct intel_device_info intel_alderlake_n_info = { + .graphics_ver = 12, + .display_ver = 13, + .is_alderlake_n = true, + .codename = "alderlake_n" +}; + +static const struct intel_device_info intel_ats_m_info = { + .graphics_ver = 12, + .graphics_rel = 55, + .display_ver = 0, /* no display support */ + .is_dg2 = true, + .has_4tile = true, + .codename = "ats_m", + .has_flatccs = true, +}; + +static const struct intel_device_info intel_meteorlake_info = { + .graphics_ver = 12, + .graphics_rel = 70, + .display_ver = 14, + .has_4tile = true, + .has_oam = true, + .is_meteorlake = true, + .codename = "meteorlake", +}; + +static const struct intel_device_info intel_pontevecchio_info = { + .graphics_ver = 12, + .graphics_rel = 60, + .is_pontevecchio = true, + .codename = "pontevecchio", +}; + +static const struct intel_device_info intel_lunarlake_info = { + .graphics_ver = 20, + .graphics_rel = 4, + .display_ver = 20, + .has_4tile = true, + .has_flatccs = true, + .has_oam = true, + .is_lunarlake = true, + .codename = "lunarlake", +}; + +static const struct intel_device_info intel_battlemage_info = { + .graphics_ver = 20, + .graphics_rel = 1, + .display_ver = 14, + .has_4tile = true, + .has_flatccs = true, + .is_battlemage = true, + .codename = "battlemage", +}; + +static const struct pci_id_match intel_device_match[] = { + INTEL_I810_IDS(INTEL_VGA_DEVICE, &intel_i810_info), + INTEL_I815_IDS(INTEL_VGA_DEVICE, &intel_i815_info), + + INTEL_I830_IDS(INTEL_VGA_DEVICE, &intel_i830_info), + INTEL_I845G_IDS(INTEL_VGA_DEVICE, &intel_i845_info), + INTEL_I85X_IDS(INTEL_VGA_DEVICE, &intel_i855_info), + INTEL_I865G_IDS(INTEL_VGA_DEVICE, &intel_i865_info), + + INTEL_I915G_IDS(INTEL_VGA_DEVICE, &intel_i915_info), + INTEL_I915GM_IDS(INTEL_VGA_DEVICE, &intel_i915m_info), + INTEL_I945G_IDS(INTEL_VGA_DEVICE, &intel_i945_info), + INTEL_I945GM_IDS(INTEL_VGA_DEVICE, &intel_i945m_info), + + INTEL_G33_IDS(INTEL_VGA_DEVICE, &intel_g33_info), + INTEL_PNV_G_IDS(INTEL_VGA_DEVICE, &intel_pineview_g_info), + INTEL_PNV_M_IDS(INTEL_VGA_DEVICE, &intel_pineview_m_info), + + INTEL_I965G_IDS(INTEL_VGA_DEVICE, &intel_i965_info), + INTEL_I965GM_IDS(INTEL_VGA_DEVICE, &intel_i965m_info), + + INTEL_G45_IDS(INTEL_VGA_DEVICE, &intel_g45_info), + INTEL_GM45_IDS(INTEL_VGA_DEVICE, &intel_gm45_info), + + INTEL_ILK_D_IDS(INTEL_VGA_DEVICE, &intel_ironlake_info), + INTEL_ILK_M_IDS(INTEL_VGA_DEVICE, &intel_ironlake_m_info), + + INTEL_SNB_D_IDS(INTEL_VGA_DEVICE, &intel_sandybridge_info), + INTEL_SNB_M_IDS(INTEL_VGA_DEVICE, &intel_sandybridge_m_info), + + INTEL_IVB_D_IDS(INTEL_VGA_DEVICE, &intel_ivybridge_info), + INTEL_IVB_M_IDS(INTEL_VGA_DEVICE, &intel_ivybridge_m_info), + + INTEL_HSW_GT1_IDS(INTEL_VGA_DEVICE, &intel_haswell_gt1_info), + INTEL_HSW_GT2_IDS(INTEL_VGA_DEVICE, &intel_haswell_gt2_info), + INTEL_HSW_GT3_IDS(INTEL_VGA_DEVICE, &intel_haswell_gt3_info), + + INTEL_VLV_IDS(INTEL_VGA_DEVICE, &intel_valleyview_info), + + INTEL_BDW_GT1_IDS(INTEL_VGA_DEVICE, &intel_broadwell_gt1_info), + INTEL_BDW_GT2_IDS(INTEL_VGA_DEVICE, &intel_broadwell_gt2_info), + INTEL_BDW_GT3_IDS(INTEL_VGA_DEVICE, &intel_broadwell_gt3_info), + INTEL_BDW_RSVD_IDS(INTEL_VGA_DEVICE, &intel_broadwell_unknown_info), + + INTEL_CHV_IDS(INTEL_VGA_DEVICE, &intel_cherryview_info), + + INTEL_SKL_GT1_IDS(INTEL_VGA_DEVICE, &intel_skylake_gt1_info), + INTEL_SKL_GT2_IDS(INTEL_VGA_DEVICE, &intel_skylake_gt2_info), + INTEL_SKL_GT3_IDS(INTEL_VGA_DEVICE, &intel_skylake_gt3_info), + INTEL_SKL_GT4_IDS(INTEL_VGA_DEVICE, &intel_skylake_gt4_info), + + INTEL_BXT_IDS(INTEL_VGA_DEVICE, &intel_broxton_info), + + INTEL_KBL_GT1_IDS(INTEL_VGA_DEVICE, &intel_kabylake_gt1_info), + INTEL_KBL_GT2_IDS(INTEL_VGA_DEVICE, &intel_kabylake_gt2_info), + INTEL_KBL_GT3_IDS(INTEL_VGA_DEVICE, &intel_kabylake_gt3_info), + INTEL_KBL_GT4_IDS(INTEL_VGA_DEVICE, &intel_kabylake_gt4_info), + INTEL_AML_KBL_GT2_IDS(INTEL_VGA_DEVICE, &intel_kabylake_gt2_info), + + INTEL_GLK_IDS(INTEL_VGA_DEVICE, &intel_geminilake_info), + + INTEL_CFL_S_GT1_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt1_info), + INTEL_CFL_S_GT2_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt2_info), + INTEL_CFL_H_GT1_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt1_info), + INTEL_CFL_H_GT2_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt2_info), + INTEL_CFL_U_GT2_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt2_info), + INTEL_CFL_U_GT3_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt3_info), + INTEL_WHL_U_GT1_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt1_info), + INTEL_WHL_U_GT2_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt2_info), + INTEL_WHL_U_GT3_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt3_info), + INTEL_AML_CFL_GT2_IDS(INTEL_VGA_DEVICE, &intel_coffeelake_gt2_info), + + INTEL_CML_GT1_IDS(INTEL_VGA_DEVICE, &intel_cometlake_gt1_info), + INTEL_CML_GT2_IDS(INTEL_VGA_DEVICE, &intel_cometlake_gt2_info), + INTEL_CML_U_GT1_IDS(INTEL_VGA_DEVICE, &intel_cometlake_gt1_info), + INTEL_CML_U_GT2_IDS(INTEL_VGA_DEVICE, &intel_cometlake_gt2_info), + + INTEL_CNL_IDS(INTEL_VGA_DEVICE, &intel_cannonlake_info), + + INTEL_ICL_IDS(INTEL_VGA_DEVICE, &intel_icelake_info), + + INTEL_EHL_IDS(INTEL_VGA_DEVICE, &intel_elkhartlake_info), + INTEL_JSL_IDS(INTEL_VGA_DEVICE, &intel_jasperlake_info), + + INTEL_TGL_GT1_IDS(INTEL_VGA_DEVICE, &intel_tigerlake_gt1_info), + INTEL_TGL_GT2_IDS(INTEL_VGA_DEVICE, &intel_tigerlake_gt2_info), + INTEL_RKL_IDS(INTEL_VGA_DEVICE, &intel_rocketlake_info), + + INTEL_DG1_IDS(INTEL_VGA_DEVICE, &intel_dg1_info), + INTEL_DG2_IDS(INTEL_VGA_DEVICE, &intel_dg2_info), + + INTEL_ADLS_IDS(INTEL_VGA_DEVICE, &intel_alderlake_s_info), + INTEL_RPLS_IDS(INTEL_VGA_DEVICE, &intel_raptorlake_s_info), + INTEL_ADLP_IDS(INTEL_VGA_DEVICE, &intel_alderlake_p_info), + INTEL_RPLU_IDS(INTEL_VGA_DEVICE, &intel_alderlake_p_info), + INTEL_RPLP_IDS(INTEL_VGA_DEVICE, &intel_alderlake_p_info), + INTEL_ADLN_IDS(INTEL_VGA_DEVICE, &intel_alderlake_n_info), + + INTEL_ATS_M_IDS(INTEL_VGA_DEVICE, &intel_ats_m_info), + + INTEL_MTL_IDS(INTEL_VGA_DEVICE, &intel_meteorlake_info), + + INTEL_PVC_IDS(INTEL_VGA_DEVICE, &intel_pontevecchio_info), + + XE_LNL_IDS(INTEL_VGA_DEVICE, &intel_lunarlake_info), + + XE_BMG_IDS(INTEL_VGA_DEVICE, &intel_battlemage_info), + + INTEL_VGA_DEVICE(PCI_MATCH_ANY, &intel_generic_info), +}; + +/** + * intel_get_device_info: + * @devid: pci device id + * + * Looks up the Intel GFX device info for the given device id. + * + * Returns: + * The associated intel_get_device_info + */ +const struct intel_device_info *intel_get_device_info(uint16_t devid) +{ + static const struct intel_device_info *cache = &intel_generic_info; + static uint16_t cached_devid; + int i; + + if (cached_devid == devid) + goto out; + + /* XXX Presort table and bsearch! */ + for (i = 0; intel_device_match[i].device_id != PCI_MATCH_ANY; i++) { + if (devid == intel_device_match[i].device_id) + break; + } + + cached_devid = devid; + cache = (void *)intel_device_match[i].match_data; + +out: + return cache; +} \ No newline at end of file diff --git a/src/linux/intel_gpu_top/intel_gpu_top.c b/src/linux/intel_gpu_top/intel_gpu_top.c new file mode 100644 index 00000000..eae1a178 --- /dev/null +++ b/src/linux/intel_gpu_top/intel_gpu_top.c @@ -0,0 +1,697 @@ +/* + * Copyright © 2007-2023 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "intel_gpu_top.h" +#include "i915_drm.h" +#include "igt_perf.h" + +#ifdef __clang__ //? Workaround for missing asprintf when compiling with clang, taken from https://stackoverflow.com/a/4899487 +int asprintf(char **ret, const char *format, ...) +{ + va_list ap; + + *ret = NULL; /* Ensure value can be passed to free() */ + + va_start(ap, format); + int count = vsnprintf(NULL, 0, format, ap); + va_end(ap); + + if (count >= 0) + { + char* buffer = malloc(count + 1); + if (buffer == NULL) + return -1; + + va_start(ap, format); + count = vsnprintf(buffer, count + 1, format, ap); + va_end(ap); + + if (count < 0) + { + free(buffer); + return count; + } + *ret = buffer; + } + + return count; +} +#endif + +__attribute__((format(scanf,3,4))) +static int igt_sysfs_scanf(int dir, const char *attr, const char *fmt, ...) +{ + FILE *file; + int fd; + int ret = -1; + + fd = openat(dir, attr, O_RDONLY); + if (fd < 0) + return -1; + + file = fdopen(fd, "r"); + if (file) { + va_list ap; + + va_start(ap, fmt); + ret = vfscanf(file, fmt, ap); + va_end(ap); + + fclose(file); + } else { + close(fd); + } + + return ret; +} + +static int pmu_parse(struct pmu_counter *pmu, const char *path, const char *str) +{ + locale_t locale, oldlocale; + bool result = true; + char buf[128] = {}; + int dir; + + dir = open(path, O_RDONLY); + if (dir < 0) + return -errno; + + /* Replace user environment with plain C to match kernel format */ + locale = newlocale(LC_ALL, "C", 0); + oldlocale = uselocale(locale); + + result &= igt_sysfs_scanf(dir, "type", "%"PRIu64, &pmu->type) == 1; + + snprintf(buf, sizeof(buf) - 1, "events/%s", str); + result &= igt_sysfs_scanf(dir, buf, "event=%"PRIx64, &pmu->config) == 1; + + snprintf(buf, sizeof(buf) - 1, "events/%s.scale", str); + result &= igt_sysfs_scanf(dir, buf, "%lf", &pmu->scale) == 1; + + snprintf(buf, sizeof(buf) - 1, "events/%s.unit", str); + result &= igt_sysfs_scanf(dir, buf, "%127s", buf) == 1; + pmu->units = strdup(buf); + + uselocale(oldlocale); + freelocale(locale); + + close(dir); + + if (!result) + return -EINVAL; + + if (isnan(pmu->scale) || !pmu->scale) + return -ERANGE; + + return 0; +} + +static int rapl_parse(struct pmu_counter *pmu, const char *str) +{ + const char *expected_units = "Joules"; + int err; + + err = pmu_parse(pmu, "/sys/devices/power", str); + if (err < 0) + return err; + + if (!pmu->units || strcmp(pmu->units, expected_units)) { + fprintf(stderr, + "Unexpected units for RAPL %s: found '%s', expected '%s'\n", + str, pmu->units, expected_units); + } + + return 0; +} + +static void +rapl_open(struct pmu_counter *pmu, + const char *domain, + struct engines *engines) +{ + int fd; + + if (rapl_parse(pmu, domain) < 0) + return; + + fd = igt_perf_open_group(pmu->type, pmu->config, engines->rapl_fd); + if (fd < 0) + return; + + if (engines->rapl_fd == -1) + engines->rapl_fd = fd; + + pmu->idx = engines->num_rapl++; + pmu->present = true; +} + +static void gpu_power_open(struct pmu_counter *pmu, + struct engines *engines) +{ + rapl_open(pmu, "energy-gpu", engines); +} + +static void pkg_power_open(struct pmu_counter *pmu, + struct engines *engines) +{ + rapl_open(pmu, "energy-pkg", engines); +} + +static uint64_t +get_pmu_config(int dirfd, const char *name, const char *counter) +{ + char buf[128], *p; + int fd, ret; + + ret = snprintf(buf, sizeof(buf), "%s-%s", name, counter); + if (ret < 0 || ret == sizeof(buf)) + return -1; + + fd = openat(dirfd, buf, O_RDONLY); + if (fd < 0) + return -1; + + ret = read(fd, buf, sizeof(buf)); + close(fd); + if (ret <= 0) + return -1; + + p = index(buf, '0'); + if (!p) + return -1; + + return strtoul(p, NULL, 0); +} + +#define engine_ptr(engines, n) (&engines->engine + (n)) + +static const char *class_display_name(unsigned int class) +{ + switch (class) { + case I915_ENGINE_CLASS_RENDER: + return "Render/3D"; + case I915_ENGINE_CLASS_COPY: + return "Blitter"; + case I915_ENGINE_CLASS_VIDEO: + return "Video"; + case I915_ENGINE_CLASS_VIDEO_ENHANCE: + return "VideoEnhance"; + case I915_ENGINE_CLASS_COMPUTE: + return "Compute"; + default: + return "[unknown]"; + } +} + +static const char *class_short_name(unsigned int class) +{ + switch (class) { + case I915_ENGINE_CLASS_RENDER: + return "RCS"; + case I915_ENGINE_CLASS_COPY: + return "BCS"; + case I915_ENGINE_CLASS_VIDEO: + return "VCS"; + case I915_ENGINE_CLASS_VIDEO_ENHANCE: + return "VECS"; + case I915_ENGINE_CLASS_COMPUTE: + return "CCS"; + default: + return "UNKN"; + } +} + +static int engine_cmp(const void *__a, const void *__b) +{ + const struct engine *a = (struct engine *)__a; + const struct engine *b = (struct engine *)__b; + + if (a->class != b->class) + return a->class - b->class; + else + return a->instance - b->instance; +} + +#define is_igpu(x) (strcmp(x, "i915") == 0) + +struct engines *discover_engines(const char *device) +{ + char sysfs_root[PATH_MAX]; + struct engines *engines; + struct dirent *dent; + int ret = 0; + DIR *d; + + snprintf(sysfs_root, sizeof(sysfs_root), + "/sys/devices/%s/events", device); + + engines = malloc(sizeof(struct engines)); + if (!engines) + return NULL; + + memset(engines, 0, sizeof(*engines)); + + engines->num_engines = 0; + engines->device = device; + engines->discrete = !is_igpu(device); + + d = opendir(sysfs_root); + if (!d) + goto err; + + while ((dent = readdir(d)) != NULL) { + const char *endswith = "-busy"; + const unsigned int endlen = strlen(endswith); + struct engine *engine = + engine_ptr(engines, engines->num_engines); + char buf[256]; + + if (dent->d_type != DT_REG) + continue; + + if (strlen(dent->d_name) >= sizeof(buf)) { + ret = ENAMETOOLONG; + break; + } + + strcpy(buf, dent->d_name); + + /* xxxN-busy */ + if (strlen(buf) < (endlen + 4)) + continue; + if (strcmp(&buf[strlen(buf) - endlen], endswith)) + continue; + + memset(engine, 0, sizeof(*engine)); + + buf[strlen(buf) - endlen] = 0; + engine->name = strdup(buf); + if (!engine->name) { + ret = errno; + break; + } + + engine->busy.config = get_pmu_config(dirfd(d), engine->name, + "busy"); + if (engine->busy.config == -1) { + ret = ENOENT; + break; + } + + /* Double check config is an engine config. */ + if (engine->busy.config >= __I915_PMU_OTHER(0)) { + free((void *)engine->name); + continue; + } + + engine->class = (engine->busy.config & + (__I915_PMU_OTHER(0) - 1)) >> + I915_PMU_CLASS_SHIFT; + + engine->instance = (engine->busy.config >> + I915_PMU_SAMPLE_BITS) & + ((1 << I915_PMU_SAMPLE_INSTANCE_BITS) - 1); + + ret = asprintf(&engine->display_name, "%s/%u", + class_display_name(engine->class), + engine->instance); + if (ret <= 0) { + ret = errno; + break; + } + + ret = asprintf(&engine->short_name, "%s/%u", + class_short_name(engine->class), + engine->instance); + if (ret <= 0) { + ret = errno; + break; + } + + engines->num_engines++; + engines = realloc(engines, sizeof(struct engines) + + engines->num_engines * sizeof(struct engine)); + if (!engines) { + ret = errno; + break; + } + + ret = 0; + } + + if (ret) { + errno = ret; + goto err; + } + + qsort(engine_ptr(engines, 0), engines->num_engines, + sizeof(struct engine), engine_cmp); + + engines->root = d; + + return engines; + +err: + free(engines); + + return NULL; +} + +void free_engines(struct engines *engines) +{ + struct pmu_counter **pmu, *free_list[] = { + &engines->r_gpu, + &engines->r_pkg, + &engines->imc_reads, + &engines->imc_writes, + NULL + }; + unsigned int i; + + if (!engines) + return; + + for (pmu = &free_list[0]; *pmu; pmu++) { + if ((*pmu)->present) + free((char *)(*pmu)->units); + } + + for (i = 0; i < engines->num_engines; i++) { + struct engine *engine = engine_ptr(engines, i); + + free((char *)engine->name); + free((char *)engine->short_name); + free((char *)engine->display_name); + } + + closedir(engines->root); + + free(engines->class); + free(engines); +} + +#define _open_pmu(type, cnt, pmu, fd) \ +({ \ + int fd__; \ +\ + fd__ = igt_perf_open_group((type), (pmu)->config, (fd)); \ + if (fd__ >= 0) { \ + if ((fd) == -1) \ + (fd) = fd__; \ + (pmu)->present = true; \ + (pmu)->idx = (cnt)++; \ + } \ +\ + fd__; \ +}) + +static int imc_parse(struct pmu_counter *pmu, const char *str) +{ + return pmu_parse(pmu, "/sys/devices/uncore_imc", str); +} + +static void +imc_open(struct pmu_counter *pmu, + const char *domain, + struct engines *engines) +{ + int fd; + + if (imc_parse(pmu, domain) < 0) + return; + + fd = igt_perf_open_group(pmu->type, pmu->config, engines->imc_fd); + if (fd < 0) + return; + + if (engines->imc_fd == -1) + engines->imc_fd = fd; + + pmu->idx = engines->num_imc++; + pmu->present = true; +} + +static void imc_writes_open(struct pmu_counter *pmu, struct engines *engines) +{ + imc_open(pmu, "data_writes", engines); +} + +static void imc_reads_open(struct pmu_counter *pmu, struct engines *engines) +{ + imc_open(pmu, "data_reads", engines); +} + +static int get_num_gts(uint64_t type) +{ + int fd, cnt; + + errno = 0; + for (cnt = 0; cnt < MAX_GTS; cnt++) { + fd = igt_perf_open(type, __I915_PMU_REQUESTED_FREQUENCY(cnt)); + if (fd < 0) + break; + + close(fd); + } + + if (!cnt || (errno && errno != ENOENT)) + cnt = -errno; + + return cnt; +} + +static void init_aggregate_counters(struct engines *engines) +{ + struct pmu_counter *pmu; + + pmu = &engines->freq_req; + pmu->type = igt_perf_type_id(engines->device); + pmu->config = I915_PMU_REQUESTED_FREQUENCY; + pmu->present = true; + + pmu = &engines->freq_act; + pmu->type = igt_perf_type_id(engines->device); + pmu->config = I915_PMU_ACTUAL_FREQUENCY; + pmu->present = true; + + pmu = &engines->rc6; + pmu->type = igt_perf_type_id(engines->device); + pmu->config = I915_PMU_RC6_RESIDENCY; + pmu->present = true; +} + +int pmu_init(struct engines *engines) +{ + unsigned int i; + int fd; + uint64_t type = igt_perf_type_id(engines->device); + + engines->fd = -1; + engines->num_counters = 0; + engines->num_gts = get_num_gts(type); + if (engines->num_gts <= 0) + return -1; + + engines->irq.config = I915_PMU_INTERRUPTS; + fd = _open_pmu(type, engines->num_counters, &engines->irq, engines->fd); + if (fd < 0) + return -1; + + init_aggregate_counters(engines); + + for (i = 0; i < engines->num_gts; i++) { + engines->freq_req_gt[i].config = __I915_PMU_REQUESTED_FREQUENCY(i); + _open_pmu(type, engines->num_counters, &engines->freq_req_gt[i], engines->fd); + + engines->freq_act_gt[i].config = __I915_PMU_ACTUAL_FREQUENCY(i); + _open_pmu(type, engines->num_counters, &engines->freq_act_gt[i], engines->fd); + + engines->rc6_gt[i].config = __I915_PMU_RC6_RESIDENCY(i); + _open_pmu(type, engines->num_counters, &engines->rc6_gt[i], engines->fd); + } + + for (i = 0; i < engines->num_engines; i++) { + struct engine *engine = engine_ptr(engines, i); + struct { + struct pmu_counter *pmu; + const char *counter; + } *cnt, counters[] = { + { .pmu = &engine->busy, .counter = "busy" }, + { .pmu = &engine->wait, .counter = "wait" }, + { .pmu = &engine->sema, .counter = "sema" }, + { .pmu = NULL, .counter = NULL }, + }; + + for (cnt = counters; cnt->pmu; cnt++) { + if (!cnt->pmu->config) + cnt->pmu->config = + get_pmu_config(dirfd(engines->root), + engine->name, + cnt->counter); + fd = _open_pmu(type, engines->num_counters, cnt->pmu, + engines->fd); + if (fd >= 0) + engine->num_counters++; + } + } + + engines->rapl_fd = -1; + if (!engines->discrete) { + gpu_power_open(&engines->r_gpu, engines); + pkg_power_open(&engines->r_pkg, engines); + } + + engines->imc_fd = -1; + imc_reads_open(&engines->imc_reads, engines); + imc_writes_open(&engines->imc_writes, engines); + + return 0; +} + +static uint64_t pmu_read_multi(int fd, unsigned int num, uint64_t *val) +{ + uint64_t buf[2 + num]; + unsigned int i; + ssize_t len; + + memset(buf, 0, sizeof(buf)); + + len = read(fd, buf, sizeof(buf)); + assert(len == sizeof(buf)); + + for (i = 0; i < num; i++) + val[i] = buf[2 + i]; + + return buf[1]; +} + +double pmu_calc(struct pmu_pair *p, double d, double t, double s) +{ + double v; + + v = p->cur - p->prev; + v /= d; + v /= t; + v *= s; + + if (s == 100.0 && v > 100.0) + v = 100.0; + + return v; +} + +static void __update_sample(struct pmu_counter *counter, uint64_t val) +{ + counter->val.prev = counter->val.cur; + counter->val.cur = val; +} + +static void update_sample(struct pmu_counter *counter, uint64_t *val) +{ + if (counter->present) + __update_sample(counter, val[counter->idx]); +} + +void pmu_sample(struct engines *engines) +{ + const int num_val = engines->num_counters; + uint64_t val[2 + num_val]; + unsigned int i; + + engines->ts.prev = engines->ts.cur; + engines->ts.cur = pmu_read_multi(engines->fd, num_val, val); + + engines->freq_req.val.cur = engines->freq_req.val.prev = 0; + engines->freq_act.val.cur = engines->freq_act.val.prev = 0; + engines->rc6.val.cur = engines->rc6.val.prev = 0; + + for (i = 0; i < engines->num_gts; i++) { + update_sample(&engines->freq_req_gt[i], val); + engines->freq_req.val.cur += engines->freq_req_gt[i].val.cur; + engines->freq_req.val.prev += engines->freq_req_gt[i].val.prev; + + update_sample(&engines->freq_act_gt[i], val); + engines->freq_act.val.cur += engines->freq_act_gt[i].val.cur; + engines->freq_act.val.prev += engines->freq_act_gt[i].val.prev; + + update_sample(&engines->rc6_gt[i], val); + engines->rc6.val.cur += engines->rc6_gt[i].val.cur; + engines->rc6.val.prev += engines->rc6_gt[i].val.prev; + } + + engines->freq_req.val.cur /= engines->num_gts; + engines->freq_req.val.prev /= engines->num_gts; + + engines->freq_act.val.cur /= engines->num_gts; + engines->freq_act.val.prev /= engines->num_gts; + + engines->rc6.val.cur /= engines->num_gts; + engines->rc6.val.prev /= engines->num_gts; + + update_sample(&engines->irq, val); + + for (i = 0; i < engines->num_engines; i++) { + struct engine *engine = engine_ptr(engines, i); + + update_sample(&engine->busy, val); + update_sample(&engine->sema, val); + update_sample(&engine->wait, val); + } + + if (engines->num_rapl) { + pmu_read_multi(engines->rapl_fd, engines->num_rapl, val); + update_sample(&engines->r_gpu, val); + update_sample(&engines->r_pkg, val); + } + + if (engines->num_imc) { + pmu_read_multi(engines->imc_fd, engines->num_imc, val); + update_sample(&engines->imc_reads, val); + update_sample(&engines->imc_writes, val); + } +} \ No newline at end of file diff --git a/src/linux/intel_gpu_top/intel_gpu_top.h b/src/linux/intel_gpu_top/intel_gpu_top.h new file mode 100644 index 00000000..0a2140c3 --- /dev/null +++ b/src/linux/intel_gpu_top/intel_gpu_top.h @@ -0,0 +1,95 @@ +#ifndef INTEL_GPU_TOP_H +#define INTEL_GPU_TOP_H + +#include +#include +#include + +struct pmu_pair { + uint64_t cur; + uint64_t prev; +}; + +struct pmu_counter { + uint64_t type; + uint64_t config; + unsigned int idx; + struct pmu_pair val; + double scale; + const char *units; + bool present; +}; + +struct engine_class { + unsigned int engine_class; + const char *name; + unsigned int num_engines; +}; + +struct engine { + const char *name; + char *display_name; + char *short_name; + + unsigned int class; + unsigned int instance; + + unsigned int num_counters; + + struct pmu_counter busy; + struct pmu_counter wait; + struct pmu_counter sema; +}; + +#define MAX_GTS 4 +struct engines { + unsigned int num_engines; + unsigned int num_classes; + struct engine_class *class; + unsigned int num_counters; + DIR *root; + int fd; + struct pmu_pair ts; + + int rapl_fd; + struct pmu_counter r_gpu, r_pkg; + unsigned int num_rapl; + + int imc_fd; + struct pmu_counter imc_reads; + struct pmu_counter imc_writes; + unsigned int num_imc; + + struct pmu_counter freq_req; + struct pmu_counter freq_req_gt[MAX_GTS]; + struct pmu_counter freq_act; + struct pmu_counter freq_act_gt[MAX_GTS]; + struct pmu_counter irq; + struct pmu_counter rc6; + struct pmu_counter rc6_gt[MAX_GTS]; + + bool discrete; + char *device; + + int num_gts; + + /* Do not edit below this line. + * This structure is reallocated every time a new engine is + * found and size is increased by sizeof (engine). + */ + + struct engine engine; + +}; + +struct engines *discover_engines(const char *device); +void free_engines(struct engines *engines); +int pmu_init(struct engines *engines); +void pmu_sample(struct engines *engines); +double pmu_calc(struct pmu_pair *p, double d, double t, double s); + +char* find_intel_gpu_dir(); +char* get_intel_device_id(const char* vendor_path); +char *get_intel_device_name(const char *device_id); + +#endif \ No newline at end of file diff --git a/src/linux/intel_gpu_top/intel_name_lookup_shim.c b/src/linux/intel_gpu_top/intel_name_lookup_shim.c new file mode 100644 index 00000000..e714f804 --- /dev/null +++ b/src/linux/intel_gpu_top/intel_name_lookup_shim.c @@ -0,0 +1,93 @@ +#include +#include +#include +#include +#include +#include + +#include "intel_gpu_top.h" +#include "intel_chipset.h" + +#define VENDOR_ID "0x8086" +#define SYSFS_PATH "/sys/class/drm" +#define VENDOR_FILE "vendor" +#define DEVICE_FILE "device" + +char* find_intel_gpu_dir() { + DIR *dir; + struct dirent *entry; + static char path[256]; + char vendor_path[256]; + char vendor_id[16]; + + if ((dir = opendir(SYSFS_PATH)) == NULL) { + perror("opendir"); + return NULL; + } + + while ((entry = readdir(dir)) != NULL) { + // Construct the path to the vendor file + snprintf(vendor_path, sizeof(vendor_path), "%s/%s/device/%s", SYSFS_PATH, entry->d_name, VENDOR_FILE); + + // Check if the vendor file exists + if (access(vendor_path, F_OK) != -1) { + FILE *file = fopen(vendor_path, "r"); + if (file) { + if (fgets(vendor_id, sizeof(vendor_id), file)) { + // Trim the newline character + vendor_id[strcspn(vendor_id, "\n")] = 0; + + if (strcmp(vendor_id, VENDOR_ID) == 0) { + fclose(file); + closedir(dir); + // Return the parent directory (i.e., /sys/class/drm/card*) + snprintf(path, sizeof(path), "%s/%s", SYSFS_PATH, entry->d_name); + return path; + } + } + fclose(file); + } + } + } + + closedir(dir); + return NULL; // Intel GPU not found +} + +char* get_intel_device_id(const char* gpu_dir) { + static char device_path[256]; + char device_id[16]; + + // Construct the path to the device file + snprintf(device_path, sizeof(device_path), "%s/device/%s", gpu_dir, DEVICE_FILE); + + FILE *file = fopen(device_path, "r"); + if (file) { + if (fgets(device_id, sizeof(device_id), file)) { + fclose(file); + // Trim the newline character + device_id[strcspn(device_id, "\n")] = 0; + // Return a copy of the device ID + return strdup(device_id); + } + fclose(file); + } else { + perror("fopen"); + } + + return NULL; +} + +char *get_intel_device_name(const char *device_id) { + uint16_t devid = strtol(device_id, NULL, 16); + char dev_name[256]; + char full_name[256]; + const struct intel_device_info *info = intel_get_device_info(devid); + if (info) { + strcpy(dev_name, info->codename); + dev_name[0] = toupper(dev_name[0]); + snprintf(full_name, sizeof(full_name), "Intel %s (Gen%u)", dev_name, info->graphics_ver); + return strdup(full_name); + } + return NULL; +} \ No newline at end of file diff --git a/src/linux/intel_gpu_top/source.txt b/src/linux/intel_gpu_top/source.txt new file mode 100644 index 00000000..1854916f --- /dev/null +++ b/src/linux/intel_gpu_top/source.txt @@ -0,0 +1,2 @@ +0f02dc176959e6296866b1bafd3982e277a5e44b +https://gitlab.freedesktop.org/drm/igt-gpu-tools.git \ No newline at end of file diff --git a/src/linux/intel_gpu_top/xe_pciids.h b/src/linux/intel_gpu_top/xe_pciids.h new file mode 100644 index 00000000..73d972a8 --- /dev/null +++ b/src/linux/intel_gpu_top/xe_pciids.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef _XE_PCIIDS_H_ +#define _XE_PCIIDS_H_ + +/* + * Lists below can be turned into initializers for a struct pci_device_id + * by defining INTEL_VGA_DEVICE: + * + * #define INTEL_VGA_DEVICE(id, info) { \ + * 0x8086, id, \ + * ~0, ~0, \ + * 0x030000, 0xff0000, \ + * (unsigned long) info } + * + * And then calling like: + * + * XE_TGL_12_GT1_IDS(INTEL_VGA_DEVICE, ## __VA_ARGS__) + * + * To turn them into something else, just provide a different macro passed as + * first argument. + */ + +/* TGL */ +#define XE_TGL_GT1_IDS(MACRO__, ...) \ + MACRO__(0x9A60, ## __VA_ARGS__), \ + MACRO__(0x9A68, ## __VA_ARGS__), \ + MACRO__(0x9A70, ## __VA_ARGS__) + +#define XE_TGL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x9A40, ## __VA_ARGS__), \ + MACRO__(0x9A49, ## __VA_ARGS__), \ + MACRO__(0x9A59, ## __VA_ARGS__), \ + MACRO__(0x9A78, ## __VA_ARGS__), \ + MACRO__(0x9AC0, ## __VA_ARGS__), \ + MACRO__(0x9AC9, ## __VA_ARGS__), \ + MACRO__(0x9AD9, ## __VA_ARGS__), \ + MACRO__(0x9AF8, ## __VA_ARGS__) + +#define XE_TGL_IDS(MACRO__, ...) \ + XE_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__),\ + XE_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__) + +/* RKL */ +#define XE_RKL_IDS(MACRO__, ...) \ + MACRO__(0x4C80, ## __VA_ARGS__), \ + MACRO__(0x4C8A, ## __VA_ARGS__), \ + MACRO__(0x4C8B, ## __VA_ARGS__), \ + MACRO__(0x4C8C, ## __VA_ARGS__), \ + MACRO__(0x4C90, ## __VA_ARGS__), \ + MACRO__(0x4C9A, ## __VA_ARGS__) + +/* DG1 */ +#define XE_DG1_IDS(MACRO__, ...) \ + MACRO__(0x4905, ## __VA_ARGS__), \ + MACRO__(0x4906, ## __VA_ARGS__), \ + MACRO__(0x4907, ## __VA_ARGS__), \ + MACRO__(0x4908, ## __VA_ARGS__), \ + MACRO__(0x4909, ## __VA_ARGS__) + +/* ADL-S */ +#define XE_ADLS_IDS(MACRO__, ...) \ + MACRO__(0x4680, ## __VA_ARGS__), \ + MACRO__(0x4682, ## __VA_ARGS__), \ + MACRO__(0x4688, ## __VA_ARGS__), \ + MACRO__(0x468A, ## __VA_ARGS__), \ + MACRO__(0x468B, ## __VA_ARGS__), \ + MACRO__(0x4690, ## __VA_ARGS__), \ + MACRO__(0x4692, ## __VA_ARGS__), \ + MACRO__(0x4693, ## __VA_ARGS__) + +/* ADL-P */ +#define XE_ADLP_IDS(MACRO__, ...) \ + MACRO__(0x46A0, ## __VA_ARGS__), \ + MACRO__(0x46A1, ## __VA_ARGS__), \ + MACRO__(0x46A2, ## __VA_ARGS__), \ + MACRO__(0x46A3, ## __VA_ARGS__), \ + MACRO__(0x46A6, ## __VA_ARGS__), \ + MACRO__(0x46A8, ## __VA_ARGS__), \ + MACRO__(0x46AA, ## __VA_ARGS__), \ + MACRO__(0x462A, ## __VA_ARGS__), \ + MACRO__(0x4626, ## __VA_ARGS__), \ + MACRO__(0x4628, ## __VA_ARGS__), \ + MACRO__(0x46B0, ## __VA_ARGS__), \ + MACRO__(0x46B1, ## __VA_ARGS__), \ + MACRO__(0x46B2, ## __VA_ARGS__), \ + MACRO__(0x46B3, ## __VA_ARGS__), \ + MACRO__(0x46C0, ## __VA_ARGS__), \ + MACRO__(0x46C1, ## __VA_ARGS__), \ + MACRO__(0x46C2, ## __VA_ARGS__), \ + MACRO__(0x46C3, ## __VA_ARGS__) + +/* ADL-N */ +#define XE_ADLN_IDS(MACRO__, ...) \ + MACRO__(0x46D0, ## __VA_ARGS__), \ + MACRO__(0x46D1, ## __VA_ARGS__), \ + MACRO__(0x46D2, ## __VA_ARGS__) + +/* RPL-S */ +#define XE_RPLS_IDS(MACRO__, ...) \ + MACRO__(0xA780, ## __VA_ARGS__), \ + MACRO__(0xA781, ## __VA_ARGS__), \ + MACRO__(0xA782, ## __VA_ARGS__), \ + MACRO__(0xA783, ## __VA_ARGS__), \ + MACRO__(0xA788, ## __VA_ARGS__), \ + MACRO__(0xA789, ## __VA_ARGS__), \ + MACRO__(0xA78A, ## __VA_ARGS__), \ + MACRO__(0xA78B, ## __VA_ARGS__) + +/* RPL-U */ +#define XE_RPLU_IDS(MACRO__, ...) \ + MACRO__(0xA721, ## __VA_ARGS__), \ + MACRO__(0xA7A1, ## __VA_ARGS__), \ + MACRO__(0xA7A9, ## __VA_ARGS__), \ + MACRO__(0xA7AC, ## __VA_ARGS__), \ + MACRO__(0xA7AD, ## __VA_ARGS__) + +/* RPL-P */ +#define XE_RPLP_IDS(MACRO__, ...) \ + XE_RPLU_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0xA720, ## __VA_ARGS__), \ + MACRO__(0xA7A0, ## __VA_ARGS__), \ + MACRO__(0xA7A8, ## __VA_ARGS__), \ + MACRO__(0xA7AA, ## __VA_ARGS__), \ + MACRO__(0xA7AB, ## __VA_ARGS__) + +/* DG2 */ +#define XE_DG2_G10_IDS(MACRO__, ...) \ + MACRO__(0x5690, ## __VA_ARGS__), \ + MACRO__(0x5691, ## __VA_ARGS__), \ + MACRO__(0x5692, ## __VA_ARGS__), \ + MACRO__(0x56A0, ## __VA_ARGS__), \ + MACRO__(0x56A1, ## __VA_ARGS__), \ + MACRO__(0x56A2, ## __VA_ARGS__), \ + MACRO__(0x56BE, ## __VA_ARGS__), \ + MACRO__(0x56BF, ## __VA_ARGS__) + +#define XE_DG2_G11_IDS(MACRO__, ...) \ + MACRO__(0x5693, ## __VA_ARGS__), \ + MACRO__(0x5694, ## __VA_ARGS__), \ + MACRO__(0x5695, ## __VA_ARGS__), \ + MACRO__(0x56A5, ## __VA_ARGS__), \ + MACRO__(0x56A6, ## __VA_ARGS__), \ + MACRO__(0x56B0, ## __VA_ARGS__), \ + MACRO__(0x56B1, ## __VA_ARGS__), \ + MACRO__(0x56BA, ## __VA_ARGS__), \ + MACRO__(0x56BB, ## __VA_ARGS__), \ + MACRO__(0x56BC, ## __VA_ARGS__), \ + MACRO__(0x56BD, ## __VA_ARGS__) + +#define XE_DG2_G12_IDS(MACRO__, ...) \ + MACRO__(0x5696, ## __VA_ARGS__), \ + MACRO__(0x5697, ## __VA_ARGS__), \ + MACRO__(0x56A3, ## __VA_ARGS__), \ + MACRO__(0x56A4, ## __VA_ARGS__), \ + MACRO__(0x56B2, ## __VA_ARGS__), \ + MACRO__(0x56B3, ## __VA_ARGS__) + +#define XE_DG2_IDS(MACRO__, ...) \ + XE_DG2_G10_IDS(MACRO__, ## __VA_ARGS__),\ + XE_DG2_G11_IDS(MACRO__, ## __VA_ARGS__),\ + XE_DG2_G12_IDS(MACRO__, ## __VA_ARGS__) + +#define XE_ATS_M150_IDS(MACRO__, ...) \ + MACRO__(0x56C0, ## __VA_ARGS__), \ + MACRO__(0x56C2, ## __VA_ARGS__) + +#define XE_ATS_M75_IDS(MACRO__, ...) \ + MACRO__(0x56C1, ## __VA_ARGS__) + +#define XE_ATS_M_IDS(MACRO__, ...) \ + XE_ATS_M150_IDS(MACRO__, ## __VA_ARGS__),\ + XE_ATS_M75_IDS(MACRO__, ## __VA_ARGS__) + +/* MTL / ARL */ +#define XE_MTL_IDS(MACRO__, ...) \ + MACRO__(0x7D40, ## __VA_ARGS__), \ + MACRO__(0x7D41, ## __VA_ARGS__), \ + MACRO__(0x7D45, ## __VA_ARGS__), \ + MACRO__(0x7D51, ## __VA_ARGS__), \ + MACRO__(0x7D55, ## __VA_ARGS__), \ + MACRO__(0x7D60, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__), \ + MACRO__(0x7DD1, ## __VA_ARGS__), \ + MACRO__(0x7DD5, ## __VA_ARGS__) + +/* PVC */ +#define XE_PVC_IDS(MACRO__, ...) \ + MACRO__(0x0B69, ## __VA_ARGS__), \ + MACRO__(0x0B6E, ## __VA_ARGS__), \ + MACRO__(0x0BD4, ## __VA_ARGS__), \ + MACRO__(0x0BD5, ## __VA_ARGS__), \ + MACRO__(0x0BD6, ## __VA_ARGS__), \ + MACRO__(0x0BD7, ## __VA_ARGS__), \ + MACRO__(0x0BD8, ## __VA_ARGS__), \ + MACRO__(0x0BD9, ## __VA_ARGS__), \ + MACRO__(0x0BDA, ## __VA_ARGS__), \ + MACRO__(0x0BDB, ## __VA_ARGS__), \ + MACRO__(0x0BE0, ## __VA_ARGS__), \ + MACRO__(0x0BE1, ## __VA_ARGS__), \ + MACRO__(0x0BE5, ## __VA_ARGS__) + +#define XE_LNL_IDS(MACRO__, ...) \ + MACRO__(0x6420, ## __VA_ARGS__), \ + MACRO__(0x64A0, ## __VA_ARGS__), \ + MACRO__(0x64B0, ## __VA_ARGS__) + +#define XE_BMG_IDS(MACRO__, ...) \ + MACRO__(0xE202, ## __VA_ARGS__), \ + MACRO__(0xE20B, ## __VA_ARGS__), \ + MACRO__(0xE20C, ## __VA_ARGS__), \ + MACRO__(0xE20D, ## __VA_ARGS__), \ + MACRO__(0xE212, ## __VA_ARGS__) + +#endif