[GIT PULL] block device inode syncing improvements

Makefile

@@ -1115,7 +1115,8 @@ export MODORDER := $(extmod_prefix)modules.order
 export MODULES_NSDEPS := $(extmod_prefix)modules.nsdeps
 
 ifeq ($(KBUILD_EXTMOD),)
-core-y		+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
+core-y			+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/
+core-$(CONFIG_BLOCK)	+= block/
 
 vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, \
 		     $(core-y) $(core-m) $(drivers-y) $(drivers-m) \

arch/m68k/emu/nfblock.c

@@ -58,7 +58,7 @@ struct nfhd_device {
 	struct gendisk *disk;
 };
 
-static blk_qc_t nfhd_submit_bio(struct bio *bio)
+static void nfhd_submit_bio(struct bio *bio)
 {
 	struct nfhd_device *dev = bio->bi_bdev->bd_disk->private_data;
 	struct bio_vec bvec;
@@ -76,7 +76,6 @@ static blk_qc_t nfhd_submit_bio(struct bio *bio)
 		sec += len;
 	}
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)

arch/mips/rb532/prom.c

@@ -16,7 +16,6 @@
 #include <linux/console.h>
 #include <linux/memblock.h>
 #include <linux/ioport.h>
-#include <linux/blkdev.h>
 
 #include <asm/bootinfo.h>
 #include <asm/mach-rc32434/ddr.h>

arch/mips/sibyte/common/cfe.c

@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 #include <linux/linkage.h>
 #include <linux/mm.h>
-#include <linux/blkdev.h>
 #include <linux/memblock.h>
 #include <linux/pm.h>
 #include <linux/smp.h>

arch/mips/sibyte/swarm/setup.c

@@ -11,7 +11,6 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/memblock.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/screen_info.h>

arch/openrisc/mm/init.c

@@ -25,7 +25,6 @@
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/blkdev.h>	/* for initrd_* */
 #include <linux/pagemap.h>
 
 #include <asm/pgalloc.h>

arch/powerpc/platforms/cell/spufs/inode.c

@@ -21,6 +21,7 @@
 #include <linux/namei.h>
 #include <linux/pagemap.h>
 #include <linux/poll.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 
 #include <asm/prom.h>

arch/um/drivers/ubd_kern.c

@@ -27,6 +27,7 @@
 #include <linux/blk-mq.h>
 #include <linux/ata.h>
 #include <linux/hdreg.h>
+#include <linux/major.h>
 #include <linux/cdrom.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>

arch/xtensa/platforms/iss/simdisk.c

@@ -100,7 +100,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 	spin_unlock(&dev->lock);
 }
 
-static blk_qc_t simdisk_submit_bio(struct bio *bio)
+static void simdisk_submit_bio(struct bio *bio)
 {
 	struct simdisk *dev = bio->bi_bdev->bd_disk->private_data;
 	struct bio_vec bvec;
@@ -118,7 +118,6 @@ static blk_qc_t simdisk_submit_bio(struct bio *bio)
 	}
 
 	bio_endio(bio);
-	return BLK_QC_T_NONE;
 }
 
 static int simdisk_open(struct block_device *bdev, fmode_t mode)

block/Kconfig

@@ -73,7 +73,7 @@ config BLK_DEV_ZONED
 
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
-	depends on BLK_CGROUP=y
+	depends on BLK_CGROUP
 	select BLK_CGROUP_RWSTAT
 	help
 	Block layer bio throttling support. It can be used to limit
@@ -112,7 +112,7 @@ config BLK_WBT_MQ
 
 config BLK_CGROUP_IOLATENCY
 	bool "Enable support for latency based cgroup IO protection"
-	depends on BLK_CGROUP=y
+	depends on BLK_CGROUP
 	help
 	Enabling this option enables the .latency interface for IO throttling.
 	The IO controller will attempt to maintain average IO latencies below
@@ -132,7 +132,7 @@ config BLK_CGROUP_FC_APPID
 
 config BLK_CGROUP_IOCOST
 	bool "Enable support for cost model based cgroup IO controller"
-	depends on BLK_CGROUP=y
+	depends on BLK_CGROUP
 	select BLK_RQ_IO_DATA_LEN
 	select BLK_RQ_ALLOC_TIME
 	help
@@ -190,39 +190,31 @@ config BLK_INLINE_ENCRYPTION_FALLBACK
 	  by falling back to the kernel crypto API when inline
 	  encryption hardware is not present.
 
-menu "Partition Types"
-
 source "block/partitions/Kconfig"
 
-endmenu
-
-endif # BLOCK
-
 config BLOCK_COMPAT
-	bool
-	depends on BLOCK && COMPAT
-	default y
+	def_bool COMPAT
 
 config BLK_MQ_PCI
-	bool
-	depends on BLOCK && PCI
-	default y
+	def_bool PCI
 
 config BLK_MQ_VIRTIO
 	bool
-	depends on BLOCK && VIRTIO
+	depends on VIRTIO
 	default y
 
 config BLK_MQ_RDMA
 	bool
-	depends on BLOCK && INFINIBAND
+	depends on INFINIBAND
 	default y
 
 config BLK_PM
-	def_bool BLOCK && PM
+	def_bool PM
 
 # do not use in new code
 config BLOCK_HOLDER_DEPRECATED
 	bool
 
 source "block/Kconfig.iosched"
+
+endif # BLOCK

block/Kconfig.iosched

@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-if BLOCK
-
 menu "IO Schedulers"
 
 config MQ_IOSCHED_DEADLINE
@@ -45,5 +43,3 @@ config BFQ_CGROUP_DEBUG
 	files in a cgroup which can be useful for debugging.
 
 endmenu
-
-endif

block/Makefile

@@ -3,7 +3,7 @@
 # Makefile for the kernel block layer
 #
 
-obj-$(CONFIG_BLOCK) := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
+obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
@@ -36,6 +36,6 @@ obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
 obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
-obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= keyslot-manager.o blk-crypto.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= blk-crypto.o blk-crypto-profile.o
 obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK)	+= blk-crypto-fallback.o
 obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED)	+= holder.o

block/bdev.c

@@ -12,6 +12,7 @@
 #include <linux/major.h>
 #include <linux/device_cgroup.h>
 #include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/backing-dev.h>
 #include <linux/module.h>
 #include <linux/blkpg.h>
@@ -184,22 +185,23 @@ int sb_min_blocksize(struct super_block *sb, int size)
 
 EXPORT_SYMBOL(sb_min_blocksize);
 
-int __sync_blockdev(struct block_device *bdev, int wait)
+int sync_blockdev_nowait(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	if (!wait)
-		return filemap_flush(bdev->bd_inode->i_mapping);
-	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+	return filemap_flush(bdev->bd_inode->i_mapping);
 }
+EXPORT_SYMBOL_GPL(sync_blockdev_nowait);
 
 /*
  * Write out and wait upon all the dirty data associated with a block
  * device via its mapping.  Does not take the superblock lock.
  */
 int sync_blockdev(struct block_device *bdev)
 {
-	return __sync_blockdev(bdev, 1);
+	if (!bdev)
+		return 0;
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
@@ -326,12 +328,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return result;
 
-	result = blk_queue_enter(bdev->bd_disk->queue, 0);
+	result = blk_queue_enter(bdev_get_queue(bdev), 0);
 	if (result)
 		return result;
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
 			      REQ_OP_READ);
-	blk_queue_exit(bdev->bd_disk->queue);
+	blk_queue_exit(bdev_get_queue(bdev));
 	return result;
 }
 
@@ -362,7 +364,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
-	result = blk_queue_enter(bdev->bd_disk->queue, 0);
+	result = blk_queue_enter(bdev_get_queue(bdev), 0);
 	if (result)
 		return result;
 
@@ -375,7 +377,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		clean_page_buffers(page);
 		unlock_page(page);
 	}
-	blk_queue_exit(bdev->bd_disk->queue);
+	blk_queue_exit(bdev_get_queue(bdev));
 	return result;
 }
 
@@ -492,6 +494,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	spin_lock_init(&bdev->bd_size_lock);
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
+	bdev->bd_queue = disk->queue;
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
 	if (!bdev->bd_stats) {
 		iput(inode);
@@ -962,9 +965,11 @@ EXPORT_SYMBOL(blkdev_put);
  * @pathname:	special file representing the block device
  * @dev:	return value of the block device's dev_t
  *
- * Get a reference to the blockdevice at @pathname in the current
- * namespace if possible and return it.  Return ERR_PTR(error)
- * otherwise.
+ * Lookup the block device's dev_t at @pathname in the current
+ * namespace if possible and return it by @dev.
+ *
+ * RETURNS:
+ * 0 if succeeded, errno otherwise.
  */
 int lookup_bdev(const char *pathname, dev_t *dev)
 {
@@ -1016,7 +1021,7 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty)
 }
 EXPORT_SYMBOL(__invalidate_device);
 
-void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+void sync_bdevs(bool wait)
 {
 	struct inode *inode, *old_inode = NULL;
 
@@ -1047,8 +1052,19 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 		bdev = I_BDEV(inode);
 
 		mutex_lock(&bdev->bd_disk->open_mutex);
-		if (bdev->bd_openers)
-			func(bdev, arg);
+		if (!bdev->bd_openers) {
+			; /* skip */
+		} else if (wait) {
+			/*
+			 * We keep the error status of individual mapping so
+			 * that applications can catch the writeback error using
+			 * fsync(2). See filemap_fdatawait_keep_errors() for
+			 * details.
+			 */
+			filemap_fdatawait_keep_errors(inode->i_mapping);
+		} else {
+			filemap_fdatawrite(inode->i_mapping);
+		}
 		mutex_unlock(&bdev->bd_disk->open_mutex);
 
 		spin_lock(&blockdev_superblock->s_inode_list_lock);

block/bfq-cgroup.c

@@ -6,13 +6,13 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/cgroup.h>
-#include <linux/elevator.h>
 #include <linux/ktime.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/sbitmap.h>
 #include <linux/delay.h>
 
+#include "elevator.h"
 #include "bfq-iosched.h"
 
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
@@ -463,7 +463,7 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
 	if (blkg_rwstat_init(&stats->bytes, gfp) ||
 	    blkg_rwstat_init(&stats->ios, gfp))
-		return -ENOMEM;
+		goto error;
 
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
@@ -476,13 +476,15 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 	    bfq_stat_init(&stats->dequeue, gfp) ||
 	    bfq_stat_init(&stats->group_wait_time, gfp) ||
 	    bfq_stat_init(&stats->idle_time, gfp) ||
-	    bfq_stat_init(&stats->empty_time, gfp)) {
-		bfqg_stats_exit(stats);
-		return -ENOMEM;
-	}
+	    bfq_stat_init(&stats->empty_time, gfp))
+		goto error;
 #endif
 
 	return 0;
+
+error:
+	bfqg_stats_exit(stats);
+	return -ENOMEM;
 }
 
 static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)

block/bfq-iosched.c

@@ -117,7 +117,6 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/cgroup.h>
-#include <linux/elevator.h>
 #include <linux/ktime.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
@@ -127,6 +126,7 @@
 
 #include <trace/events/block.h>
 
+#include "elevator.h"
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
@@ -6884,8 +6884,8 @@ static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct blk_mq_tags *tags = hctx->sched_tags;
 	unsigned int min_shallow;
 
-	min_shallow = bfq_update_depths(bfqd, tags->bitmap_tags);
-	sbitmap_queue_min_shallow_depth(tags->bitmap_tags, min_shallow);
+	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
+	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
 }
 
 static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)