Merge branch 'for-3.18/core' of git://git.kernel.dk/linux-block

Pull core block layer changes from Jens Axboe:
 "This is the core block IO pull request for 3.18.  Apart from the new
  and improved flush machinery for blk-mq, this is all mostly bug fixes
  and cleanups.

   - blk-mq timeout updates and fixes from Christoph.

   - Removal of REQ_END, also from Christoph.  We pass it through the
     ->queue_rq() hook for blk-mq instead, freeing up one of the request
     bits.  The space was overly tight on 32-bit, so Martin also killed
     REQ_KERNEL since it's no longer used.

   - blk integrity updates and fixes from Martin and Gu Zheng.

   - Update to the flush machinery for blk-mq from Ming Lei.  Now we
     have a per hardware context flush request, which both cleans up the
     code should scale better for flush intensive workloads on blk-mq.

   - Improve the error printing, from Rob Elliott.

   - Backing device improvements and cleanups from Tejun.

   - Fixup of a misplaced rq_complete() tracepoint from Hannes.

   - Make blk_get_request() return error pointers, fixing up issues
     where we NULL deref when a device goes bad or missing.  From Joe
     Lawrence.

   - Prep work for drastically reducing the memory consumption of dm
     devices from Junichi Nomura.  This allows creating clone bio sets
     without preallocating a lot of memory.

   - Fix a blk-mq hang on certain combinations of queue depths and
     hardware queues from me.

   - Limit memory consumption for blk-mq devices for crash dump
     scenarios and drivers that use crazy high depths (certain SCSI
     shared tag setups).  We now just use a single queue and limited
     depth for that"

* 'for-3.18/core' of git://git.kernel.dk/linux-block: (58 commits)
  block: Remove REQ_KERNEL
  blk-mq: allocate cpumask on the home node
  bio-integrity: remove the needless fail handle of bip_slab creating
  block: include func name in __get_request prints
  block: make blk_update_request print prefix match ratelimited prefix
  blk-merge: don't compute bi_phys_segments from bi_vcnt for cloned bio
  block: fix alignment_offset math that assumes io_min is a power-of-2
  blk-mq: Make bt_clear_tag() easier to read
  blk-mq: fix potential hang if rolling wakeup depth is too high
  block: add bioset_create_nobvec()
  block: use bio_clone_fast() in blk_rq_prep_clone()
  block: misplaced rq_complete tracepoint
  sd: Honor block layer integrity handling flags
  block: Replace strnicmp with strncasecmp
  block: Add T10 Protection Information functions
  block: Don't merge requests if integrity flags differ
  block: Integrity checksum flag
  block: Relocate bio integrity flags
  block: Add a disk flag to block integrity profile
  block: Add prefix to block integrity profile flags
  ...

24 files changed, 791 insertions, 607 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 2429515c05c2..161491d0a879 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,7 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
+	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
diff --git a/block/Makefile b/block/Makefile
index a2ce6ac935ec..00ecc97629db 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -20,6 +20,6 @@ obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
+
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f14b4abbebd8..0984232e429f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -79,6 +79,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
+	bio->bi_rw |= REQ_INTEGRITY;
 
 	return bip;
 err:
@@ -96,11 +97,12 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  */
 void bio_integrity_free(struct bio *bio)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
-	if (bip->bip_owns_buf)
-		kfree(bip->bip_buf);
+	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
+		kfree(page_address(bip->bip_vec->bv_page) +
+		      bip->bip_vec->bv_offset);
 
 	if (bs) {
 		if (bip->bip_slab != BIO_POOL_NONE)
@@ -128,7 +130,7 @@ EXPORT_SYMBOL(bio_integrity_free);
 int bio_integrity_add_page(struct bio *bio, struct page *page,
 			   unsigned int len, unsigned int offset)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_vec *iv;
 
 	if (bip->bip_vcnt >= bip->bip_max_vcnt) {
@@ -147,24 +149,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-static int bdev_integrity_enabled(struct block_device *bdev, int rw)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bdev);
-
-	if (bi == NULL)
-		return 0;
-
-	if (rw == READ && bi->verify_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_READ))
-		return 1;
-
-	if (rw == WRITE && bi->generate_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_WRITE))
-		return 1;
-
-	return 0;
-}
-
 /**
  * bio_integrity_enabled - Check whether integrity can be passed
  * @bio:	bio to check
@@ -174,171 +158,86 @@ static int bdev_integrity_enabled(struct block_device *bdev, int rw)
  * set prior to calling.  The functions honors the write_generate and
  * read_verify flags in sysfs.
  */
-int bio_integrity_enabled(struct bio *bio)
+bool bio_integrity_enabled(struct bio *bio)
 {
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
+
 	if (!bio_is_rw(bio))
-		return 0;
+		return false;
 
 	/* Already protected? */
 	if (bio_integrity(bio))
-		return 0;
+		return false;
+
+	if (bi == NULL)
+		return false;
+
+	if (bio_data_dir(bio) == READ && bi->verify_fn != NULL &&
+	    (bi->flags & BLK_INTEGRITY_VERIFY))
+		return true;
+
+	if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL &&
+	    (bi->flags & BLK_INTEGRITY_GENERATE))
+		return true;
 
-	return bdev_integrity_enabled(bio->bi_bdev, bio_data_dir(bio));
+	return false;
 }
 EXPORT_SYMBOL(bio_integrity_enabled);
 
 /**
- * bio_integrity_hw_sectors - Convert 512b sectors to hardware ditto
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
  * @bi:		blk_integrity profile for device
- * @sectors:	Number of 512 sectors to convert
+ * @sectors:	Size of the bio in 512-byte sectors
  *
  * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the hardware
- * sector size of the storage device.  Convert the block layer sectors
- * to physical sectors.
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
  */
-static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
-						    unsigned int sectors)
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
 {
-	/* At this point there are only 512b or 4096b DIF/EPP devices */
-	if (bi->sector_size == 4096)
-		return sectors >>= 3;
-
-	return sectors;
+	return sectors >> (ilog2(bi->interval) - 9);
 }
 
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
 }
 
 /**
- * bio_integrity_tag_size - Retrieve integrity tag space
- * @bio:	bio to inspect
- *
- * Description: Returns the maximum number of tag bytes that can be
- * attached to this bio. Filesystems can use this to determine how
- * much metadata to attach to an I/O.
- */
-unsigned int bio_integrity_tag_size(struct bio *bio)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
-	BUG_ON(bio->bi_iter.bi_size == 0);
-
-	return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
-}
-EXPORT_SYMBOL(bio_integrity_tag_size);
-
-static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
-			     int set)
-{
-	struct bio_integrity_payload *bip = bio->bi_integrity;
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	unsigned int nr_sectors;
-
-	BUG_ON(bip->bip_buf == NULL);
-
-	if (bi->tag_size == 0)
-		return -1;
-
-	nr_sectors = bio_integrity_hw_sectors(bi,
-					DIV_ROUND_UP(len, bi->tag_size));
-
-	if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
-		printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
-		       nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
-		return -1;
-	}
-
-	if (set)
-		bi->set_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-	else
-		bi->get_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-
-	return 0;
-}
-
-/**
- * bio_integrity_set_tag - Attach a tag buffer to a bio
- * @bio:	bio to attach buffer to
- * @tag_buf:	Pointer to a buffer containing tag data
- * @len:	Length of the included buffer
- *
- * Description: Use this function to tag a bio by leveraging the extra
- * space provided by devices formatted with integrity protection.  The
- * size of the integrity buffer must be <= to the size reported by
- * bio_integrity_tag_size().
- */
-int bio_integrity_set_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != WRITE);
-
-	return bio_integrity_tag(bio, tag_buf, len, 1);
-}
-EXPORT_SYMBOL(bio_integrity_set_tag);
-
-/**
- * bio_integrity_get_tag - Retrieve a tag buffer from a bio
- * @bio:	bio to retrieve buffer from
- * @tag_buf:	Pointer to a buffer for the tag data
- * @len:	Length of the target buffer
- *
- * Description: Use this function to retrieve the tag buffer from a
- * completed I/O. The size of the integrity buffer must be <= to the
- * size reported by bio_integrity_tag_size().
- */
-int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != READ);
-
-	return bio_integrity_tag(bio, tag_buf, len, 0);
-}
-EXPORT_SYMBOL(bio_integrity_get_tag);
-
-/**
- * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
+ * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
- * @operate:	operate number, 1 for generate, 0 for verify
+ * @proc_fn:	Pointer to the relevant processing function
  */
-static int bio_integrity_generate_verify(struct bio *bio, int operate)
+static int bio_integrity_process(struct bio *bio,
+				 integrity_processing_fn *proc_fn)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	struct blk_integrity_exchg bix;
+	struct blk_integrity_iter iter;
 	struct bio_vec *bv;
-	sector_t sector;
-	unsigned int sectors, ret = 0, i;
-	void *prot_buf = bio->bi_integrity->bip_buf;
-
-	if (operate)
-		sector = bio->bi_iter.bi_sector;
-	else
-		sector = bio->bi_integrity->bip_iter.bi_sector;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	unsigned int i, ret = 0;
+	void *prot_buf = page_address(bip->bip_vec->bv_page) +
+		bip->bip_vec->bv_offset;
 
-	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	bix.sector_size = bi->sector_size;
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = bi->interval;
+	iter.seed = bip_get_seed(bip);
+	iter.prot_buf = prot_buf;
 
 	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
-		bix.data_buf = kaddr + bv->bv_offset;
-		bix.data_size = bv->bv_len;
-		bix.prot_buf = prot_buf;
-		bix.sector = sector;
-
-		if (operate)
-			bi->generate_fn(&bix);
-		else {
-			ret = bi->verify_fn(&bix);
-			if (ret) {
-				kunmap_atomic(kaddr);
-				return ret;
-			}
-		}
 
-		sectors = bv->bv_len / bi->sector_size;
-		sector += sectors;
-		prot_buf += sectors * bi->tuple_size;
+		iter.data_buf = kaddr + bv->bv_offset;
+		iter.data_size = bv->bv_len;
+
+		ret = proc_fn(&iter);
+		if (ret) {
+			kunmap_atomic(kaddr);
+			return ret;
+		}
 
 		kunmap_atomic(kaddr);
 	}
@@ -346,28 +245,6 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 }
 
 /**
- * bio_integrity_generate - Generate integrity metadata for a bio
- * @bio:	bio to generate integrity metadata for
- *
- * Description: Generates integrity metadata for a bio by calling the
- * block device's generation callback function.  The bio must have a
- * bip attached with enough room to accommodate the generated
- * integrity metadata.
- */
-static void bio_integrity_generate(struct bio *bio)
-{
-	bio_integrity_generate_verify(bio, 1);
-}
-
-static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
-{
-	if (bi)
-		return bi->tuple_size;
-
-	return 0;
-}
-
-/**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
  *
@@ -387,17 +264,17 @@ int bio_integrity_prep(struct bio *bio)
 	unsigned long start, end;
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
-	unsigned int sectors;
+	unsigned int intervals;
 
 	bi = bdev_get_integrity(bio->bi_bdev);
 	q = bdev_get_queue(bio->bi_bdev);
 	BUG_ON(bi == NULL);
 	BUG_ON(bio_integrity(bio));
 
-	sectors = bio_integrity_hw_sectors(bi, bio_sectors(bio));
+	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = sectors * blk_integrity_tuple_size(bi);
+	len = intervals * bi->tuple_size;
 	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
@@ -416,10 +293,12 @@ int bio_integrity_prep(struct bio *bio)
 		return -EIO;
 	}
 
-	bip->bip_owns_buf = 1;
-	bip->bip_buf = buf;
+	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip->bip_iter.bi_size = len;
-	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
+	bip_set_seed(bip, bio->bi_iter.bi_sector);
+
+	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+		bip->bip_flags |= BIP_IP_CHECKSUM;
 
 	/* Map it */
 	offset = offset_in_page(buf);
@@ -455,26 +334,13 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE)
-		bio_integrity_generate(bio);
+		bio_integrity_process(bio, bi->generate_fn);
 
 	return 0;
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
 /**
- * bio_integrity_verify - Verify integrity metadata for a bio
- * @bio:	bio to verify
- *
- * Description: This function is called to verify the integrity of a
- * bio.	 The data in the bio io_vec is compared to the integrity
- * metadata returned by the HBA.
- */
-static int bio_integrity_verify(struct bio *bio)
-{
-	return bio_integrity_generate_verify(bio, 0);
-}
-
-/**
  * bio_integrity_verify_fn - Integrity I/O completion worker
  * @work:	Work struct stored in bio to be verified
  *
@@ -487,9 +353,10 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	int error;
 
-	error = bio_integrity_verify(bio);
+	error = bio_integrity_process(bio, bi->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
@@ -510,7 +377,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 void bio_integrity_endio(struct bio *bio, int error)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	BUG_ON(bip->bip_bio != bio);
 
@@ -541,7 +408,7 @@ EXPORT_SYMBOL(bio_integrity_endio);
  */
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
 
@@ -563,7 +430,7 @@ EXPORT_SYMBOL(bio_integrity_advance);
 void bio_integrity_trim(struct bio *bio, unsigned int offset,
 			unsigned int sectors)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
 	bio_integrity_advance(bio, offset << 9);
@@ -582,7 +449,7 @@ EXPORT_SYMBOL(bio_integrity_trim);
 int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 			gfp_t gfp_mask)
 {
-	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
+	struct bio_integrity_payload *bip_src = bio_integrity(bio_src);
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
@@ -646,6 +513,4 @@ void __init bio_integrity_init(void)
 				     sizeof(struct bio_integrity_payload) +
 				     sizeof(struct bio_vec) * BIP_INLINE_VECS,
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	if (!bip_slab)
-		panic("Failed to create slab\n");
 }
diff --git a/block/bio.c b/block/bio.c
index 3e6331d25d90..3e6e1986a5b2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -428,6 +428,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		front_pad = 0;
 		inline_vecs = nr_iovecs;
 	} else {
+		/* should not use nobvec bioset for nr_iovecs > 0 */
+		if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
+			return NULL;
 		/*
 		 * generic_make_request() converts recursion to iteration; this
 		 * means if we're running beneath it, any bios we allocate and
@@ -1900,20 +1903,9 @@ void bioset_free(struct bio_set *bs)
 }
 EXPORT_SYMBOL(bioset_free);
 
-/**
- * bioset_create  - Create a bio_set
- * @pool_size:	Number of bio and bio_vecs to cache in the mempool
- * @front_pad:	Number of bytes to allocate in front of the returned bio
- *
- * Description:
- *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- *    to ask for a number of bytes to be allocated in front of the bio.
- *    Front pad allocation is useful for embedding the bio inside
- *    another structure, to avoid allocating extra data to go with the bio.
- *    Note that the bio must be embedded at the END of that structure always,
- *    or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+static struct bio_set *__bioset_create(unsigned int pool_size,
+				       unsigned int front_pad,
+				       bool create_bvec_pool)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
 	struct bio_set *bs;
@@ -1938,9 +1930,11 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 	if (!bs->bio_pool)
 		goto bad;
 
-	bs->bvec_pool = biovec_create_pool(pool_size);
-	if (!bs->bvec_pool)
-		goto bad;
+	if (create_bvec_pool) {
+		bs->bvec_pool = biovec_create_pool(pool_size);
+		if (!bs->bvec_pool)
+			goto bad;
+	}
 
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
@@ -1951,8 +1945,41 @@ bad:
 	bioset_free(bs);
 	return NULL;
 }
+
+/**
+ * bioset_create  - Create a bio_set
+ * @pool_size:	Number of bio and bio_vecs to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ *    to ask for a number of bytes to be allocated in front of the bio.
+ *    Front pad allocation is useful for embedding the bio inside
+ *    another structure, to avoid allocating extra data to go with the bio.
+ *    Note that the bio must be embedded at the END of that structure always,
+ *    or things will break badly.
+ */
+struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, true);
+}
 EXPORT_SYMBOL(bioset_create);
 
+/**
+ * bioset_create_nobvec  - Create a bio_set without bio_vec mempool
+ * @pool_size:	Number of bio to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Same functionality as bioset_create() except that mempool is not
+ *    created for bio_vecs. Saving some memory for bio_clone_fast() users.
+ */
+struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, false);
+}
+EXPORT_SYMBOL(bioset_create_nobvec);
+
 #ifdef CONFIG_BLK_CGROUP
 /**
  * bio_associate_current - associate a bio with %current
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e17da947f6bd..0ac817b750db 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -822,7 +822,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 static struct cgroup_subsys_state *
 blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
-	static atomic64_t id_seq = ATOMIC64_INIT(0);
 	struct blkcg *blkcg;
 
 	if (!parent_css) {
@@ -836,7 +835,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT;
 	blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT;
-	blkcg->id = atomic64_inc_return(&id_seq); /* root is 0, start from 1 */
 done:
 	spin_lock_init(&blkcg->lock);
 	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index d3fd7aa3d2a3..c567865b5f1d 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -50,9 +50,6 @@ struct blkcg {
 	struct blkcg_gq			*blkg_hint;
 	struct hlist_head		blkg_list;
 
-	/* for policies to test whether associated blkcg has changed */
-	uint64_t			id;
-
 	/* TODO: per-policy storage in blkcg */
 	unsigned int			cfq_weight;	/* belongs to cfq */
 	unsigned int			cfq_leaf_weight;
diff --git a/block/blk-core.c b/block/blk-core.c
index 9c888bd22b00..0421b53e6431 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -83,18 +83,14 @@ void blk_queue_congestion_threshold(struct request_queue *q)
  * @bdev:	device
  *
  * Locates the passed device's request queue and returns the address of its
- * backing_dev_info
- *
- * Will return NULL if the request queue cannot be located.
+ * backing_dev_info.  This function can only be called if @bdev is opened
+ * and the return value is never NULL.
  */
 struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 {
-	struct backing_dev_info *ret = NULL;
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q)
-		ret = &q->backing_dev_info;
-	return ret;
+	return &q->backing_dev_info;
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
@@ -394,11 +390,13 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 		 * be drained.  Check all the queues and counters.
 		 */
 		if (drain_all) {
+			struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 			drain |= !list_empty(&q->queue_head);
 			for (i = 0; i < 2; i++) {
 				drain |= q->nr_rqs[i];
 				drain |= q->in_flight[i];
-				drain |= !list_empty(&q->flush_queue[i]);
+				if (fq)
+				    drain |= !list_empty(&fq->flush_queue[i]);
 			}
 		}
 
@@ -604,9 +602,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 #ifdef CONFIG_BLK_CGROUP
 	INIT_LIST_HEAD(&q->blkg_list);
 #endif
-	INIT_LIST_HEAD(&q->flush_queue[0]);
-	INIT_LIST_HEAD(&q->flush_queue[1]);
-	INIT_LIST_HEAD(&q->flush_data_in_flight);
 	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -709,8 +704,8 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!q->flush_rq)
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
+	if (!q->fq)
 		return NULL;
 
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
@@ -746,7 +741,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	return q;
 
 fail:
-	kfree(q->flush_rq);
+	blk_free_flush_queue(q->fq);
 	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -934,8 +929,8 @@ static struct io_context *rq_ioc(struct bio *bio)
  * pressure or if @q is dead.
  *
  * Must be called with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *__get_request(struct request_list *rl, int rw_flags,
 				     struct bio *bio, gfp_t gfp_mask)
@@ -949,7 +944,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
@@ -974,7 +969,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 					 * process is not a "batcher", and not
 					 * exempted by the IO scheduler
 					 */
-					return NULL;
+					return ERR_PTR(-ENOMEM);
 				}
 			}
 		}
@@ -992,7 +987,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	 * allocated with any setting of ->nr_requests
 	 */
 	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	q->nr_rqs[is_sync]++;
 	rl->count[is_sync]++;
@@ -1065,8 +1060,8 @@ fail_elvpriv:
 	 * shouldn't stall IO.  Treat this request as !elvpriv.  This will
 	 * disturb iosched and blkcg but weird is bettern than dead.
 	 */
-	printk_ratelimited(KERN_WARNING "%s: request aux data allocation failed, iosched may be disturbed\n",
-			   dev_name(q->backing_dev_info.dev));
+	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
+			   __func__, dev_name(q->backing_dev_info.dev));
 
 	rq->cmd_flags &= ~REQ_ELVPRIV;
 	rq->elv.icq = NULL;
@@ -1097,7 +1092,7 @@ fail_alloc:
 rq_starved:
 	if (unlikely(rl->count[is_sync] == 0))
 		rl->starved[is_sync] = 1;
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
@@ -1111,8 +1106,8 @@ rq_starved:
  * function keeps retrying under memory pressure and fails iff @q is dead.
  *
  * Must be called with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *get_request(struct request_queue *q, int rw_flags,
 				   struct bio *bio, gfp_t gfp_mask)
@@ -1125,12 +1120,12 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
 	rq = __get_request(rl, rw_flags, bio, gfp_mask);
-	if (rq)
+	if (!IS_ERR(rq))
 		return rq;
 
 	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
-		return NULL;
+		return rq;
 	}
 
 	/* wait on @rl and retry */
@@ -1167,7 +1162,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 
 	spin_lock_irq(q->queue_lock);
 	rq = get_request(q, rw, NULL, gfp_mask);
-	if (!rq)
+	if (IS_ERR(rq))
 		spin_unlock_irq(q->queue_lock);
 	/* q->queue_lock is unlocked at this point */
 
@@ -1219,8 +1214,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 {
 	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
 
-	if (unlikely(!rq))
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(rq))
+		return rq;
 
 	blk_rq_set_block_pc(rq);
 
@@ -1614,8 +1609,8 @@ get_rq:
 	 * Returns with the queue unlocked.
 	 */
 	req = get_request(q, rw_flags, bio, GFP_NOIO);
-	if (unlikely(!req)) {
-		bio_endio(bio, -ENODEV);	/* @q is dead */
+	if (IS_ERR(req)) {
+		bio_endio(bio, PTR_ERR(req));	/* @q is dead */
 		goto out_unlock;
 	}
 
@@ -2405,11 +2400,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes;
 
+	trace_block_rq_complete(req->q, req, nr_bytes);
+
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req, nr_bytes);
-
 	/*
 	 * For fs requests, rq is just carrie