block: Create bip slabs with embedded integrity vectors

This patch restores stacking ability to the block layer integrity
infrastructure by creating a set of dedicated bip slabs.  Each bip slab
has an embedded bio_vec array at the end.  This cuts down on memory
allocations and also simplifies the code compared to the original bvec
version.  Only the largest bip slab is backed by a mempool.  The pool is
contained in the bio_set so stacking drivers can ensure forward
progress.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@carl.(none)>

5 files changed, 152 insertions, 57 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index b06cf5c..345d99d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2365,7 +2365,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 		__bio_clone(bio, bio_src);
 
 		if (bio_integrity(bio_src) &&
-		    bio_integrity_clone(bio, bio_src, gfp_mask))
+		    bio_integrity_clone(bio, bio_src, gfp_mask, bs))
 			goto free_and_out;
 
 		if (bio_ctr && bio_ctr(bio, bio_src, data))
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c6d4ee..9acd54a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1017,7 +1017,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	clone->bi_flags |= 1 << BIO_CLONED;
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO);
+		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
 		bio_integrity_trim(clone,
 				   bio_sector_offset(bio, idx, offset), len);
 	}
@@ -1045,7 +1045,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 	clone->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO);
+		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
 
 		if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
 			bio_integrity_trim(clone,
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 31c46a2..49a34e7 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -1,7 +1,7 @@
 /*
  * bio-integrity.c - bio data integrity extensions
  *
- * Copyright (C) 2007, 2008 Oracle Corporation
+ * Copyright (C) 2007, 2008, 2009 Oracle Corporation
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
  *
  * This program is free software; you can redistribute it and/or
@@ -25,63 +25,121 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 
-static struct kmem_cache *bio_integrity_slab __read_mostly;
-static mempool_t *bio_integrity_pool;
-static struct bio_set *integrity_bio_set;
+struct integrity_slab {
+	struct kmem_cache *slab;
+	unsigned short nr_vecs;
+	char name[8];
+};
+
+#define IS(x) { .nr_vecs = x, .name = "bip-"__stringify(x) }
+struct integrity_slab bip_slab[BIOVEC_NR_POOLS] __read_mostly = {
+	IS(1), IS(4), IS(16), IS(64), IS(128), IS(BIO_MAX_PAGES),
+};
+#undef IS
+
 static struct workqueue_struct *kintegrityd_wq;
 
+static inline unsigned int vecs_to_idx(unsigned int nr)
+{
+	switch (nr) {
+	case 1:
+		return 0;
+	case 2 ... 4:
+		return 1;
+	case 5 ... 16:
+		return 2;
+	case 17 ... 64:
+		return 3;
+	case 65 ... 128:
+		return 4;
+	case 129 ... BIO_MAX_PAGES:
+		return 5;
+	default:
+		BUG();
+	}
+}
+
+static inline int use_bip_pool(unsigned int idx)
+{
+	if (idx == BIOVEC_NR_POOLS)
+		return 1;
+
+	return 0;
+}
+
 /**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
+ * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
  * @gfp_mask:	Memory allocation mask
  * @nr_vecs:	Number of integrity metadata scatter-gather elements
+ * @bs:		bio_set to allocate from
  *
  * Description: This function prepares a bio for attaching integrity
  * metadata.  nr_vecs specifies the maximum number of pages containing
  * integrity metadata that can be attached.
  */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
-						  gfp_t gfp_mask,
-						  unsigned int nr_vecs)
+struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
+							 gfp_t gfp_mask,
+							 unsigned int nr_vecs,
+							 struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip;
-	struct bio_vec *iv;
-	unsigned long idx;
+	unsigned int idx = vecs_to_idx(nr_vecs);
 
 	BUG_ON(bio == NULL);
+	bip = NULL;
 
-	bip = mempool_alloc(bio_integrity_pool, gfp_mask);
-	if (unlikely(bip == NULL)) {
-		printk(KERN_ERR "%s: could not alloc bip\n", __func__);
-		return NULL;
-	}
+	/* Lower order allocations come straight from slab */
+	if (!use_bip_pool(idx))
+		bip = kmem_cache_alloc(bip_slab[idx].slab, gfp_mask);
 
-	memset(bip, 0, sizeof(*bip));
+	/* Use mempool if lower order alloc failed or max vecs were requested */
+	if (bip == NULL) {
+		bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
 
-	iv = bvec_alloc_bs(gfp_mask, nr_vecs, &idx, integrity_bio_set);
-	if (unlikely(iv == NULL)) {
-		printk(KERN_ERR "%s: could not alloc bip_vec\n", __func__);
-		mempool_free(bip, bio_integrity_pool);
-		return NULL;
+		if (unlikely(bip == NULL)) {
+			printk(KERN_ERR "%s: could not alloc bip\n", __func__);
+			return NULL;
+		}
 	}
 
-	bip->bip_pool = idx;
-	bip->bip_vec = iv;
+	memset(bip, 0, sizeof(*bip));
+
+	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
 
 	return bip;
 }
+EXPORT_SYMBOL(bio_integrity_alloc_bioset);
+
+/**
+ * bio_integrity_alloc - Allocate integrity payload and attach it to bio
+ * @bio:	bio to attach integrity metadata to
+ * @gfp_mask:	Memory allocation mask
+ * @nr_vecs:	Number of integrity metadata scatter-gather elements
+ *
+ * Description: This function prepares a bio for attaching integrity
+ * metadata.  nr_vecs specifies the maximum number of pages containing
+ * integrity metadata that can be attached.
+ */
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
+						  gfp_t gfp_mask,
+						  unsigned int nr_vecs)
+{
+	return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set);
+}
 EXPORT_SYMBOL(bio_integrity_alloc);
 
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
+ * @bs:		bio_set this bio was allocated from
  *
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-void bio_integrity_free(struct bio *bio)
+void bio_integrity_free(struct bio *bio, struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 
@@ -92,8 +150,10 @@ void bio_integrity_free(struct bio *bio)
 	    && bip->bip_buf != NULL)
 		kfree(bip->bip_buf);
 
-	bvec_free_bs(integrity_bio_set, bip->bip_vec, bip->bip_pool);
-	mempool_free(bip, bio_integrity_pool);
+	if (use_bip_pool(bip->bip_slab))
+		mempool_free(bip, bs->bio_integrity_pool);
+	else
+		kmem_cache_free(bip_slab[bip->bip_slab].slab, bip);
 
 	bio->bi_integrity = NULL;
 }
@@ -114,7 +174,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct bio_vec *iv;
 
-	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_pool)) {
+	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
 		printk(KERN_ERR "%s: bip_vec full\n", __func__);
 		return 0;
 	}
@@ -647,8 +707,8 @@ void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors)
 	bp->iv1 = bip->bip_vec[0];
 	bp->iv2 = bip->bip_vec[0];
 
-	bp->bip1.bip_vec = &bp->iv1;
-	bp->bip2.bip_vec = &bp->iv2;
+	bp->bip1.bip_vec[0] = bp->iv1;
+	bp->bip2.bip_vec[0] = bp->iv2;
 
 	bp->iv1.bv_len = sectors * bi->tuple_size;
 	bp->iv2.bv_offset += sectors * bi->tuple_size;
@@ -667,17 +727,19 @@ EXPORT_SYMBOL(bio_integrity_split);
  * @bio:	New bio
  * @bio_src:	Original bio
  * @gfp_mask:	Memory allocation mask
+ * @bs:		bio_set to allocate bip from
  *
  * Description:	Called to allocate a bip when cloning a bio
  */
-int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask)
+int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
+			gfp_t gfp_mask, struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
+	bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
 
 	if (bip == NULL)
 		return -EIO;
@@ -693,25 +755,43 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(bio_integrity_clone);
 
-static int __init bio_integrity_init(void)
+int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
-	kintegrityd_wq = create_workqueue("kintegrityd");
+	unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES);
+
+	bs->bio_integrity_pool =
+		mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab);
 
+	if (!bs->bio_integrity_pool)
+		return -1;
+
+	return 0;
+}
+EXPORT_SYMBOL(bioset_integrity_create);
+
+void bioset_integrity_free(struct bio_set *bs)
+{
+	if (bs->bio_integrity_pool)
+		mempool_destroy(bs->bio_integrity_pool);
+}
+EXPORT_SYMBOL(bioset_integrity_free);
+
+void __init bio_integrity_init(void)
+{
+	unsigned int i;
+
+	kintegrityd_wq = create_workqueue("kintegrityd");
 	if (!kintegrityd_wq)
 		panic("Failed to create kintegrityd\n");
 
-	bio_integrity_slab = KMEM_CACHE(bio_integrity_payload,
-					SLAB_HWCACHE_ALIGN|SLAB_PANIC);
+	for (i = 0 ; i < BIOVEC_NR_POOLS ; i++) {
+		unsigned int size;
 
-	bio_integrity_pool = mempool_create_slab_pool(BIO_POOL_SIZE,
-						      bio_integrity_slab);
-	if (!bio_integrity_pool)
-		panic("bio_integrity: can't allocate bip pool\n");
+		size = sizeof(struct bio_integrity_payload)
+			+ bip_slab[i].nr_vecs * sizeof(struct bio_vec);
 
-	integrity_bio_set = bioset_create(BIO_POOL_SIZE, 0);
-	if (!integrity_bio_set)
-		panic("bio_integrity: can't allocate bio_set\n");
-
-	return 0;
+		bip_slab[i].slab =
+			kmem_cache_create(bip_slab[i].name, size, 0,
+					  SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	}
 }
-subsys_initcall(bio_integrity_init);
diff --git a/fs/bio.c b/fs/bio.c
index 24c9140..1486b19 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -238,7 +238,7 @@ void bio_free(struct bio *bio, struct bio_set *bs)
 		bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
 
 	if (bio_integrity(bio))
-		bio_integrity_free(bio);
+		bio_integrity_free(bio, bs);
 
 	/*
 	 * If we have front padding, adjust the bio pointer before freeing
@@ -341,7 +341,7 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
 static void bio_kmalloc_destructor(struct bio *bio)
 {
 	if (bio_integrity(bio))
-		bio_integrity_free(bio);
+		bio_integrity_free(bio, fs_bio_set);
 	kfree(bio);
 }
 
@@ -472,7 +472,7 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 	if (bio_integrity(bio)) {
 		int ret;
 
-		ret = bio_integrity_clone(b, bio, gfp_mask);
+		ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
 
 		if (ret < 0) {
 			bio_put(b);
@@ -1539,6 +1539,7 @@ void bioset_free(struct bio_set *bs)
 	if (bs->bio_pool)
 		mempool_destroy(bs->bio_pool);
 
+	bioset_integrity_free(bs);
 	biovec_free_pools(bs);
 	bio_put_slab(bs);
 
@@ -1579,6 +1580,9 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 	if (!bs->bio_pool)
 		goto bad;
 
+	if (bioset_integrity_create(bs, pool_size))
+		goto bad;
+
 	if (!biovec_create_pools(bs, pool_size))
 		return bs;
 
@@ -1616,6 +1620,7 @@ static int __init init_bio(void)
 	if (!bio_slabs)
 		panic("bio: can't allocate bios\n");
 
+	bio_integrity_init();
 	biovec_init_slabs();
 
 	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2a04eb5..2892b710 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -319,7 +319,6 @@ static inline int bio_has_allocated_vec(struct bio *bio)
  */
 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 */
 
@@ -328,11 +327,12 @@ struct bio_integrity_payload {
 
 	unsigned int		bip_size;
 
-	unsigned short		bip_pool;	/* pool the ivec came from */
+	unsigned short		bip_slab;	/* slab the bip 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 */
+	struct bio_vec		bip_vec[0];	/* embedded bvec array */
 };
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
@@ -430,6 +430,9 @@ struct bio_set {
 	unsigned int front_pad;
 
 	mempool_t *bio_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+#endif
 	mempool_t *bvec_pool;
 };
 
@@ -634,8 +637,9 @@ static inline struct bio *bio_list_get(struct bio_list *bl)
 
 #define bio_integrity(bio) (bio->bi_integrity != NULL)
 
+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 *);
+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);
@@ -645,21 +649,27 @@ 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 *, gfp_t);
+extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, 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(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 bio_integrity_free(a)		do { } while (0)
+#define bio_integrity_clone(a, b, c, d)	(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(a)		do { } while (0)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */