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
  ...

65 files changed, 1210 insertions, 1172 deletions

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 279da08f7541..8df003963d99 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -53,6 +53,14 @@ Description:
 		512 bytes of data.
 
 
+What:		/sys/block/<disk>/integrity/device_is_integrity_capable
+Date:		July 2014
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether a storage device is capable of storing
+		integrity metadata. Set if the device is T10 PI-capable.
+
+
 What:		/sys/block/<disk>/integrity/write_generate
 Date:		June 2008
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index 2d735b0ae383..f56ec97f0d14 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -129,11 +129,11 @@ interface for this is being worked on.
 4.1 BIO
 
 The data integrity patches add a new field to struct bio when
-CONFIG_BLK_DEV_INTEGRITY is enabled.  bio->bi_integrity is a pointer
-to a struct bip which contains the bio integrity payload.  Essentially
-a bip is a trimmed down struct bio which holds a bio_vec containing
-the integrity metadata and the required housekeeping information (bvec
-pool, vector count, etc.)
+CONFIG_BLK_DEV_INTEGRITY is enabled.  bio_integrity(bio) returns a
+pointer to a struct bip which contains the bio integrity payload.
+Essentially a bip is a trimmed down struct bio which holds a bio_vec
+containing the integrity metadata and the required housekeeping
+information (bvec pool, vector count, etc.)
 
 A kernel subsystem can enable data integrity protection on a bio by
 calling bio_integrity_alloc(bio).  This will allocate and attach the
@@ -192,16 +192,6 @@ will require extra work due to the application tag.
     supported by the block device.
 
 
-    int bdev_integrity_enabled(block_device, int rw);
-
-      bdev_integrity_enabled() will return 1 if the block device
-      supports integrity metadata transfer for the data direction
-      specified in 'rw'.
-
-      bdev_integrity_enabled() honors the write_generate and
-      read_verify flags in sysfs and will respond accordingly.
-
-
     int bio_integrity_prep(bio);
 
       To generate IMD for WRITE and to set up buffers for READ, the
@@ -216,36 +206,6 @@ will require extra work due to the application tag.
       bio_integrity_enabled() returned 1.
 
 
-    int bio_integrity_tag_size(bio);
-
-      If the filesystem wants to use the application tag space it will
-      first have to find out how much storage space is available.
-      Because tag space is generally limited (usually 2 bytes per
-      sector regardless of sector size), the integrity framework
-      supports interleaving the information between the sectors in an
-      I/O.
-
-      Filesystems can call bio_integrity_tag_size(bio) to find out how
-      many bytes of storage are available for that particular bio.
-
-      Another option is bdev_get_tag_size(block_device) which will
-      return the number of available bytes per hardware sector.
-
-
-    int bio_integrity_set_tag(bio, void *tag_buf, len);
-
-      After a successful return from bio_integrity_prep(),
-      bio_integrity_set_tag() can be used to attach an opaque tag
-      buffer to a bio.  Obviously this only makes sense if the I/O is
-      a WRITE.
-
-
-    int bio_integrity_get_tag(bio, void *tag_buf, len);
-
-      Similarly, at READ I/O completion time the filesystem can
-      retrieve the tag buffer using bio_integrity_get_tag().
-
-
 5.3 PASSING EXISTING INTEGRITY METADATA
 
     Filesystems that either generate their own integrity metadata or
@@ -298,8 +258,6 @@ will require extra work due to the application tag.
             .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
             .generate_fn            = my_generate_fn,
        	    .verify_fn              = my_verify_fn,
-       	    .get_tag_fn             = my_get_tag_fn,
-       	    .set_tag_fn             = my_set_tag_fn,
 	    .tuple_size             = sizeof(struct my_tuple_size),
 	    .tag_size               = <tag bytes per hw sector>,
         };
@@ -321,7 +279,5 @@ will require extra work due to the application tag.
       are available per hardware sector.  For DIF this is either 2 or
       0 depending on the value of the Control Mode Page ATO bit.
 
-      See 6.2 for a description of get_tag_fn and set_tag_fn.
-
 ----------------------------------------------------------------------
 2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>
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)