bio: allow individual slabs in the bio_set

Instead of having a global bio slab cache, add a reference to one
in each bio_set that is created. This allows for personalized slabs
in each bio_set, so that they can have bios of different sizes.

This means we can personalize the bios we return. File systems may
want to embed the bio inside another structure, to avoid allocation
more items (and stuffing them in ->bi_private) after the get a bio.
Or we may want to embed a number of bio_vecs directly at the end
of a bio, to avoid doing two allocations to return a bio. This is now
possible.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 9340098d75dc..4b80d3537f97 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -334,7 +334,7 @@ struct bio_pair {
 extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
 extern void bio_pair_release(struct bio_pair *dbio);
 
-extern struct bio_set *bioset_create(int, int);
+extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 
 extern struct bio *bio_alloc(gfp_t, int);
@@ -379,6 +379,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 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 void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
@@ -401,6 +402,8 @@ static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
 
 struct bio_set {
         struct kmem_cache *bio_slab;
+        unsigned int front_pad;
+
         mempool_t *bio_pool;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
         mempool_t *bio_integrity_pool;
@@ -415,6 +418,7 @@ struct biovec_slab {
 };
 
 extern struct bio_set *fs_bio_set;
+extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly;
 
 /*
  * a small number of entries is fine, not going to be performance critical.