dm: store dm_target_io in bio front_pad
Use the recently-added bio front_pad field to allocate struct dm_target_io.
Prior to this patch, dm_target_io was allocated from a mempool. For each
dm_target_io, there is exactly one bio allocated from a bioset.
This patch merges these two allocations into one allocation: we create a
bioset with front_pad equal to the size of dm_target_io so that every
bio allocated from the bioset has sizeof(struct dm_target_io) bytes
before it. We allocate a bio and use the bytes before the bio as
dm_target_io.
_tio_cache is removed and the tio_pool mempool is now only used for
request-based devices.
This idea was introduced by Kent Overstreet.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: tj@kernel.org
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Bill Pemberton <wfp5p@viridian.itc.virginia.edu>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 66ceaff..02db9183 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -71,6 +71,7 @@
struct dm_io *io;
struct dm_target *ti;
union map_info info;
+ struct bio clone;
};
/*
@@ -214,7 +215,6 @@
#define MIN_IOS 256
static struct kmem_cache *_io_cache;
-static struct kmem_cache *_tio_cache;
static struct kmem_cache *_rq_tio_cache;
/*
@@ -232,14 +232,9 @@
if (!_io_cache)
return r;
- /* allocate a slab for the target ios */
- _tio_cache = KMEM_CACHE(dm_target_io, 0);
- if (!_tio_cache)
- goto out_free_io_cache;
-
_rq_tio_cache = KMEM_CACHE(dm_rq_target_io, 0);
if (!_rq_tio_cache)
- goto out_free_tio_cache;
+ goto out_free_io_cache;
_rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0);
if (!_rq_bio_info_cache)
@@ -265,8 +260,6 @@
kmem_cache_destroy(_rq_bio_info_cache);
out_free_rq_tio_cache:
kmem_cache_destroy(_rq_tio_cache);
-out_free_tio_cache:
- kmem_cache_destroy(_tio_cache);
out_free_io_cache:
kmem_cache_destroy(_io_cache);
@@ -277,7 +270,6 @@
{
kmem_cache_destroy(_rq_bio_info_cache);
kmem_cache_destroy(_rq_tio_cache);
- kmem_cache_destroy(_tio_cache);
kmem_cache_destroy(_io_cache);
unregister_blkdev(_major, _name);
dm_uevent_exit();
@@ -463,7 +455,7 @@
static void free_tio(struct mapped_device *md, struct dm_target_io *tio)
{
- mempool_free(tio, md->tio_pool);
+ bio_put(&tio->clone);
}
static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md,
@@ -682,7 +674,6 @@
}
free_tio(md, tio);
- bio_put(bio);
dec_pending(io, error);
}
@@ -1002,12 +993,12 @@
}
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
-static void __map_bio(struct dm_target *ti, struct bio *clone,
- struct dm_target_io *tio)
+static void __map_bio(struct dm_target *ti, struct dm_target_io *tio)
{
int r;
sector_t sector;
struct mapped_device *md;
+ struct bio *clone = &tio->clone;
clone->bi_end_io = clone_endio;
clone->bi_private = tio;
@@ -1031,7 +1022,6 @@
/* error the io and bail out, or requeue it if needed */
md = tio->io->md;
dec_pending(tio->io, r);
- bio_put(clone);
free_tio(md, tio);
} else if (r) {
DMWARN("unimplemented target map return value: %d", r);
@@ -1052,14 +1042,13 @@
/*
* Creates a little bio that just does part of a bvec.
*/
-static struct bio *split_bvec(struct bio *bio, sector_t sector,
- unsigned short idx, unsigned int offset,
- unsigned int len, struct bio_set *bs)
+static void split_bvec(struct dm_target_io *tio, struct bio *bio,
+ sector_t sector, unsigned short idx, unsigned int offset,
+ unsigned int len, struct bio_set *bs)
{
- struct bio *clone;
+ struct bio *clone = &tio->clone;
struct bio_vec *bv = bio->bi_io_vec + idx;
- clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
*clone->bi_io_vec = *bv;
clone->bi_sector = sector;
@@ -1076,20 +1065,18 @@
bio_integrity_trim(clone,
bio_sector_offset(bio, idx, offset), len);
}
-
- return clone;
}
/*
* Creates a bio that consists of range of complete bvecs.
*/
-static struct bio *clone_bio(struct bio *bio, sector_t sector,
- unsigned short idx, unsigned short bv_count,
- unsigned int len, struct bio_set *bs)
+static void clone_bio(struct dm_target_io *tio, struct bio *bio,
+ sector_t sector, unsigned short idx,
+ unsigned short bv_count, unsigned int len,
+ struct bio_set *bs)
{
- struct bio *clone;
+ struct bio *clone = &tio->clone;
- clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
__bio_clone(clone, bio);
clone->bi_sector = sector;
clone->bi_idx = idx;
@@ -1104,14 +1091,16 @@
bio_integrity_trim(clone,
bio_sector_offset(bio, idx, 0), len);
}
-
- return clone;
}
static struct dm_target_io *alloc_tio(struct clone_info *ci,
- struct dm_target *ti)
+ struct dm_target *ti, int nr_iovecs)
{
- struct dm_target_io *tio = mempool_alloc(ci->md->tio_pool, GFP_NOIO);
+ struct dm_target_io *tio;
+ struct bio *clone;
+
+ clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, ci->md->bs);
+ tio = container_of(clone, struct dm_target_io, clone);
tio->io = ci->io;
tio->ti = ti;
@@ -1123,8 +1112,8 @@
static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
unsigned request_nr, sector_t len)
{
- struct dm_target_io *tio = alloc_tio(ci, ti);
- struct bio *clone;
+ struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs);
+ struct bio *clone = &tio->clone;
tio->info.target_request_nr = request_nr;
@@ -1133,14 +1122,14 @@
* ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
* and discard, so no need for concern about wasted bvec allocations.
*/
- clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs);
+ __bio_clone(clone, ci->bio);
if (len) {
clone->bi_sector = ci->sector;
clone->bi_size = to_bytes(len);
}
- __map_bio(ti, clone, tio);
+ __map_bio(ti, tio);
}
static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti,
@@ -1169,14 +1158,13 @@
*/
static void __clone_and_map_simple(struct clone_info *ci, struct dm_target *ti)
{
- struct bio *clone, *bio = ci->bio;
+ struct bio *bio = ci->bio;
struct dm_target_io *tio;
- tio = alloc_tio(ci, ti);
- clone = clone_bio(bio, ci->sector, ci->idx,
- bio->bi_vcnt - ci->idx, ci->sector_count,
- ci->md->bs);
- __map_bio(ti, clone, tio);
+ tio = alloc_tio(ci, ti, bio->bi_max_vecs);
+ clone_bio(tio, bio, ci->sector, ci->idx, bio->bi_vcnt - ci->idx,
+ ci->sector_count, ci->md->bs);
+ __map_bio(ti, tio);
ci->sector_count = 0;
}
@@ -1214,7 +1202,7 @@
static int __clone_and_map(struct clone_info *ci)
{
- struct bio *clone, *bio = ci->bio;
+ struct bio *bio = ci->bio;
struct dm_target *ti;
sector_t len = 0, max;
struct dm_target_io *tio;
@@ -1254,10 +1242,10 @@
len += bv_len;
}
- tio = alloc_tio(ci, ti);
- clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
- ci->md->bs);
- __map_bio(ti, clone, tio);
+ tio = alloc_tio(ci, ti, bio->bi_max_vecs);
+ clone_bio(tio, bio, ci->sector, ci->idx, i - ci->idx, len,
+ ci->md->bs);
+ __map_bio(ti, tio);
ci->sector += len;
ci->sector_count -= len;
@@ -1282,12 +1270,11 @@
len = min(remaining, max);
- tio = alloc_tio(ci, ti);
- clone = split_bvec(bio, ci->sector, ci->idx,
- bv->bv_offset + offset, len,
- ci->md->bs);
+ tio = alloc_tio(ci, ti, 1);
+ split_bvec(tio, bio, ci->sector, ci->idx,
+ bv->bv_offset + offset, len, ci->md->bs);
- __map_bio(ti, clone, tio);
+ __map_bio(ti, tio);
ci->sector += len;
ci->sector_count -= len;
@@ -1955,7 +1942,7 @@
{
struct dm_md_mempools *p;
- if (md->io_pool && md->tio_pool && md->bs)
+ if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs)
/* the md already has necessary mempools */
goto out;
@@ -2732,14 +2719,16 @@
if (!pools->io_pool)
goto free_pools_and_out;
- pools->tio_pool = (type == DM_TYPE_BIO_BASED) ?
- mempool_create_slab_pool(MIN_IOS, _tio_cache) :
- mempool_create_slab_pool(MIN_IOS, _rq_tio_cache);
- if (!pools->tio_pool)
- goto free_io_pool_and_out;
+ pools->tio_pool = NULL;
+ if (type == DM_TYPE_REQUEST_BASED) {
+ pools->tio_pool = mempool_create_slab_pool(MIN_IOS, _rq_tio_cache);
+ if (!pools->tio_pool)
+ goto free_io_pool_and_out;
+ }
pools->bs = (type == DM_TYPE_BIO_BASED) ?
- bioset_create(pool_size, 0) :
+ bioset_create(pool_size,
+ offsetof(struct dm_target_io, clone)) :
bioset_create(pool_size,
offsetof(struct dm_rq_clone_bio_info, clone));
if (!pools->bs)
@@ -2754,7 +2743,8 @@
bioset_free(pools->bs);
free_tio_pool_and_out:
- mempool_destroy(pools->tio_pool);
+ if (pools->tio_pool)
+ mempool_destroy(pools->tio_pool);
free_io_pool_and_out:
mempool_destroy(pools->io_pool);
