block: Block layer data integrity support

Some block devices support verifying the integrity of requests by way
of checksums or other protection information that is submitted along
with the I/O.

This patch implements support for generating and verifying integrity
metadata, as well as correctly merging, splitting and cloning bios and
requests that have this extra information attached.

See Documentation/block/data-integrity.txt for more information.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

block/Kconfig

@@ -81,6 +81,18 @@ config BLK_DEV_BSG
 
 	  If unsure, say N.
 
+config BLK_DEV_INTEGRITY
+	bool "Block layer data integrity support"
+	---help---
+	Some storage devices allow extra information to be
+	stored/retrieved to help protect the data.  The block layer
+	data integrity option provides hooks which can be used by
+	filesystems to ensure better data integrity.
+
+	Say yes here if you have a storage device that provides the
+	T10/SCSI Data Integrity Field or the T13/ATA External Path
+	Protection.  If in doubt, say N.
+
 endif # BLOCK
 
 config BLOCK_COMPAT

block/Makefile

@@ -14,3 +14,4 @@ obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o

block/blk-core.c

@@ -143,6 +143,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 		bio->bi_size -= nbytes;
 		bio->bi_sector += (nbytes >> 9);
+
+		if (bio_integrity(bio))
+			bio_integrity_advance(bio, nbytes);
+
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
@@ -1381,6 +1385,9 @@ static inline void __generic_make_request(struct bio *bio)
 		 */
 		blk_partition_remap(bio);
 
+		if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
+			goto end_io;
+
 		if (old_sector != -1)
 			blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
 					    old_sector);

block/blk-merge.c

@@ -441,6 +441,9 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	    || next->special)
 		return 0;
 
+	if (blk_integrity_rq(req) != blk_integrity_rq(next))
+		return 0;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn

block/blk.h

@@ -51,4 +51,12 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
 	return q->nr_congestion_off;
 }
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define rq_for_each_integrity_segment(bvl, _rq, _iter)		\
+	__rq_for_each_bio(_iter.bio, _rq)			\
+		bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
+
+#endif /* BLK_DEV_INTEGRITY */
+
 #endif

block/elevator.c

@@ -86,6 +86,12 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
 		return 0;
 
+	/*
+	 * only merge integrity protected bio into ditto rq
+	 */
+	if (bio_integrity(bio) != blk_integrity_rq(rq))
+		return 0;
+
 	if (!elv_iosched_allow_merge(rq, bio))
 		return 0;
 

fs/Makefile

@@ -19,6 +19,7 @@ else
 obj-y +=	no-block.o
 endif
 
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
 obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o

fs/bio.c

@@ -50,6 +50,11 @@ static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
  */
 struct bio_set *fs_bio_set;
 
+unsigned int bvec_nr_vecs(unsigned short idx)
+{
+	return bvec_slabs[idx].nr_vecs;
+}
+
 struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
 {
 	struct bio_vec *bvl;
@@ -91,6 +96,9 @@ void bio_free(struct bio *bio, struct bio_set *bio_set)
 		mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
 	}
 
+	if (bio_integrity(bio))
+		bio_integrity_free(bio, bio_set);
+
 	mempool_free(bio, bio_set->bio_pool);
 }
 
@@ -249,9 +257,19 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 {
 	struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
 
-	if (b) {
-		b->bi_destructor = bio_fs_destructor;
-		__bio_clone(b, bio);
+	if (!b)
+		return NULL;
+
+	b->bi_destructor = bio_fs_destructor;
+	__bio_clone(b, bio);
+
+	if (bio_integrity(bio)) {
+		int ret;
+
+		ret = bio_integrity_clone(b, bio, fs_bio_set);
+
+		if (ret < 0)
+			return NULL;
 	}
 
 	return b;
@@ -1223,6 +1241,9 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
 	bp->bio1.bi_private = bi;
 	bp->bio2.bi_private = pool;
 
+	if (bio_integrity(bi))
+		bio_integrity_split(bi, bp, first_sectors);
+
 	return bp;
 }
 
@@ -1264,6 +1285,7 @@ void bioset_free(struct bio_set *bs)
 	if (bs->bio_pool)
 		mempool_destroy(bs->bio_pool);
 
+	bioset_integrity_free(bs);
 	biovec_free_pools(bs);
 
 	kfree(bs);
@@ -1280,6 +1302,9 @@ struct bio_set *bioset_create(int bio_pool_size, int bvec_pool_size)
 	if (!bs->bio_pool)
 		goto bad;
 
+	if (bioset_integrity_create(bs, bio_pool_size))
+		goto bad;
+
 	if (!biovec_create_pools(bs, bvec_pool_size))
 		return bs;
 
@@ -1306,6 +1331,7 @@ static int __init init_bio(void)
 {
 	bio_slab = KMEM_CACHE(bio, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
+	bio_integrity_init_slab();
 	biovec_init_slabs();
 
 	fs_bio_set = bioset_create(BIO_POOL_SIZE, 2);

include/linux/bio.h

@@ -64,6 +64,7 @@ struct bio_vec {
 
 struct bio_set;
 struct bio;
+struct bio_integrity_payload;
 typedef void (bio_end_io_t) (struct bio *, int);
 typedef void (bio_destructor_t) (struct bio *);
 
@@ -112,6 +113,9 @@ struct bio {
 	atomic_t		bi_cnt;		/* pin count */
 
 	void			*bi_private;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload *bi_integrity;  /* data integrity */
+#endif
 
 	bio_destructor_t	*bi_destructor;	/* destructor */
 };
@@ -271,6 +275,29 @@ static inline void *bio_data(struct bio *bio)
  */
 #define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+/*
+ * bio integrity payload
+ */
+struct bio_integrity_payload {
+	struct bio		*bip_bio;	/* parent bio */
+	struct bio_vec		*bip_vec;	/* integrity data vector */
+
+	sector_t		bip_sector;	/* virtual start sector */
+
+	void			*bip_buf;	/* generated integrity data */
+	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
+
+	int			bip_error;	/* saved I/O error */
+	unsigned int		bip_size;
+
+	unsigned short		bip_pool;	/* pool the ivec came from */
+	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
+	unsigned short		bip_idx;	/* current bip_vec index */
+
+	struct work_struct	bip_work;	/* I/O completion */
+};
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
  * A bio_pair is used when we need to split a bio.
@@ -283,10 +310,14 @@ static inline void *bio_data(struct bio *bio)
  *   in bio2.bi_private
  */
 struct bio_pair {
-	struct bio	bio1, bio2;
-	struct bio_vec	bv1, bv2;
-	atomic_t	cnt;
-	int		error;
+	struct bio			bio1, bio2;
+	struct bio_vec			bv1, bv2;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload	bip1, bip2;
+	struct bio_vec			iv1, iv2;
+#endif
+	atomic_t			cnt;
+	int				error;
 };
 extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool,
 				  int first_sectors);
@@ -334,6 +365,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *,
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
+extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
  * bio_set is used to allow other portions of the IO system to
@@ -346,6 +378,9 @@ extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set
 
 struct bio_set {
 	mempool_t *bio_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+#endif
 	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
 };
 
@@ -410,5 +445,56 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
 	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
 #define bio_kunmap_irq(buf,flags)	__bio_kunmap_irq(buf, flags)
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
+#define bip_vec(bip)		bip_vec_idx(bip, 0)
+
+#define __bip_for_each_vec(bvl, bip, i, start_idx)			\
+	for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx);	\
+	     i < (bip)->bip_vcnt;					\
+	     bvl++, i++)
+
+#define bip_for_each_vec(bvl, bip, i)					\
+	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)
+
+#define bio_integrity(bio)	((bio)->bi_integrity ? 1 : 0)
+
+extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
+extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
+extern void bio_integrity_free(struct bio *, struct bio_set *);
+extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
+extern int bio_integrity_enabled(struct bio *bio);
+extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
+extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
+extern int bio_integrity_prep(struct bio *);
+extern void bio_integrity_endio(struct bio *, int);
+extern void bio_integrity_advance(struct bio *, unsigned int);
+extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
+extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
+extern int bio_integrity_clone(struct bio *, struct bio *, struct bio_set *);
+extern int bioset_integrity_create(struct bio_set *, int);
+extern void bioset_integrity_free(struct bio_set *);
+extern void bio_integrity_init_slab(void);
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+
+#define bio_integrity(a)		(0)
+#define bioset_integrity_create(a, b)	(0)
+#define bio_integrity_prep(a)		(0)
+#define bio_integrity_enabled(a)	(0)
+#define bio_integrity_clone(a, b, c)	(0)
+#define bioset_integrity_free(a)	do { } while (0)
+#define bio_integrity_free(a, b)	do { } while (0)
+#define bio_integrity_endio(a, b)	do { } while (0)
+#define bio_integrity_advance(a, b)	do { } while (0)
+#define bio_integrity_trim(a, b, c)	do { } while (0)
+#define bio_integrity_split(a, b, c)	do { } while (0)
+#define bio_integrity_set_tag(a, b, c)	do { } while (0)
+#define bio_integrity_get_tag(a, b, c)	do { } while (0)
+#define bio_integrity_init_slab(a)	do { } while (0)
+
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
 #endif /* CONFIG_BLOCK */
 #endif /* __LINUX_BIO_H */

include/linux/blkdev.h

@@ -112,6 +112,7 @@ enum rq_flag_bits {
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
+	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -134,6 +135,7 @@ enum rq_flag_bits {
 #define REQ_ALLOCED	(1 << __REQ_ALLOCED)
 #define REQ_RW_META	(1 << __REQ_RW_META)
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
+#define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 
 #define BLK_MAX_CDB	16
 
@@ -865,6 +867,109 @@ void kblockd_flush_work(struct work_struct *work);
 	MODULE_ALIAS("block-major-" __stringify(major) "-*")
 
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+#define INTEGRITY_FLAG_READ	1	/* verify data integrity on read */
+#define INTEGRITY_FLAG_WRITE	2	/* generate data integrity on write */
+
+struct blk_integrity_exchg {
+	void			*prot_buf;
+	void			*data_buf;
+	sector_t		sector;
+	unsigned int		data_size;
+	unsigned short		sector_size;
+	const char		*disk_name;
+};
+
+typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
+typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
+typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
+typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);
+
+struct blk_integrity {
+	integrity_gen_fn	*generate_fn;
+	integrity_vrfy_fn	*verify_fn;
+	integrity_set_tag_fn	*set_tag_fn;
+	integrity_get_tag_fn	*get_tag_fn;
+
+	unsigned short		flags;
+	unsigned short		tuple_size;
+	unsigned short		sector_size;
+	unsigned short		tag_size;
+
+	const char		*name;
+
+	struct kobject		kobj;
+};
+
+extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
+extern void blk_integrity_unregister(struct gendisk *);
+extern int blk_integrity_compare(struct block_device *, struct block_device *);
+extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
+extern int blk_rq_count_integrity_sg(struct request *);
+
+static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
+{
+	if (bi)
+		return bi->tuple_size;
+
+	return 0;
+}
+
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
+{
+	return bdev->bd_disk->integrity;
+}
+
+static inline unsigned int bdev_get_tag_size(struct block_device *bdev)
+{
+	struct blk_integrity *bi = bdev_get_integrity(bdev);
+
+	if (bi)
+		return bi->tag_size;
+
+	return 0;
+}
+
+static inline 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 &&
+	    test_bit(INTEGRITY_FLAG_READ, &bi->flags))
+		return 1;
+
+	if (rw == WRITE && bi->generate_fn != NULL &&
+	    test_bit(INTEGRITY_FLAG_WRITE, &bi->flags))
+		return 1;
+
+	return 0;
+}
+
+static inline int blk_integrity_rq(struct request *rq)
+{
+	BUG_ON(rq->bio == NULL);
+
+	return bio_integrity(rq->bio);
+}
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+
+#define blk_integrity_rq(rq)			(0)
+#define blk_rq_count_integrity_sg(a)		(0)
+#define blk_rq_map_integrity_sg(a, b)		(0)
+#define bdev_get_integrity(a)			(0)
+#define bdev_get_tag_size(a)			(0)
+#define blk_integrity_compare(a, b)		(0)
+#define blk_integrity_register(a, b)		(0)
+#define blk_integrity_unregister(a)		do { } while (0);
+
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
+
 #else /* CONFIG_BLOCK */
 /*
  * stubs for when the block layer is configured out

include/linux/genhd.h

@@ -141,6 +141,9 @@ struct gendisk {
 	struct disk_stats dkstats;
 #endif
 	struct work_struct async_notify;
+#ifdef  CONFIG_BLK_DEV_INTEGRITY
+	struct blk_integrity *integrity;
+#endif
 };
 
 /*