From 395c72a707d966b36d5a42fe12c3a237ded3a0d9 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 6 Sep 2012 15:34:55 -0700 Subject: block: Generalized bio pool freeing With the old code, when you allocate a bio from a bio pool you have to implement your own destructor that knows how to find the bio pool the bio was originally allocated from. This adds a new field to struct bio (bi_pool) and changes bio_alloc_bioset() to use it. This makes various bio destructors unnecessary, so they're then deleted. v6: Explain the temporary if statement in bio_put Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown CC: Alasdair Kergon CC: Nicholas Bellinger CC: Lars Ellenberg Acked-by: Tejun Heo Acked-by: Nicholas Bellinger Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_main.c | 13 +------------ drivers/md/dm-crypt.c | 9 --------- drivers/md/dm-io.c | 11 ----------- drivers/md/dm.c | 20 -------------------- drivers/md/md.c | 28 ++++------------------------ drivers/target/target_core_iblock.c | 9 --------- 6 files changed, 5 insertions(+), 85 deletions(-) (limited to 'drivers') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index f93a0320e952..f55683ad4ffa 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -162,23 +162,12 @@ static const struct block_device_operations drbd_ops = { .release = drbd_release, }; -static void bio_destructor_drbd(struct bio *bio) -{ - bio_free(bio, drbd_md_io_bio_set); -} - struct bio *bio_alloc_drbd(gfp_t gfp_mask) { - struct bio *bio; - if (!drbd_md_io_bio_set) return bio_alloc(gfp_mask, 1); - bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set); - if (!bio) - return NULL; - bio->bi_destructor = bio_destructor_drbd; - return bio; + return bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set); } #ifdef __CHECKER__ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 664743d6a6cd..3c0acba042b6 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -798,14 +798,6 @@ static int crypt_convert(struct crypt_config *cc, return 0; } -static void dm_crypt_bio_destructor(struct bio *bio) -{ - struct dm_crypt_io *io = bio->bi_private; - struct crypt_config *cc = io->cc; - - bio_free(bio, cc->bs); -} - /* * Generate a new unfragmented bio with the given size * This should never violate the device limitations @@ -974,7 +966,6 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) clone->bi_end_io = crypt_endio; clone->bi_bdev = cc->dev->bdev; clone->bi_rw = io->base_bio->bi_rw; - clone->bi_destructor = dm_crypt_bio_destructor; } static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index ea5dd289fe2a..1c46f97d6664 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -249,16 +249,6 @@ static void vm_dp_init(struct dpages *dp, void *data) dp->context_ptr = data; } -static void dm_bio_destructor(struct bio *bio) -{ - unsigned region; - struct io *io; - - retrieve_io_and_region_from_bio(bio, &io, ®ion); - - bio_free(bio, io->client->bios); -} - /* * Functions for getting the pages from kernel memory. */ @@ -317,7 +307,6 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, bio->bi_sector = where->sector + (where->count - remaining); bio->bi_bdev = where->bdev; bio->bi_end_io = endio; - bio->bi_destructor = dm_bio_destructor; store_io_and_region_in_bio(bio, io, region); if (rw & REQ_DISCARD) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4e09b6ff5b49..0c3d6dd51897 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -681,11 +681,6 @@ static void clone_endio(struct bio *bio, int error) } } - /* - * Store md for cleanup instead of tio which is about to get freed. - */ - bio->bi_private = md->bs; - free_tio(md, tio); bio_put(bio); dec_pending(io, error); @@ -1032,11 +1027,6 @@ static void __map_bio(struct dm_target *ti, struct bio *clone, /* error the io and bail out, or requeue it if needed */ md = tio->io->md; dec_pending(tio->io, r); - /* - * Store bio_set for cleanup. - */ - clone->bi_end_io = NULL; - clone->bi_private = md->bs; bio_put(clone); free_tio(md, tio); } else if (r) { @@ -1055,13 +1045,6 @@ struct clone_info { unsigned short idx; }; -static void dm_bio_destructor(struct bio *bio) -{ - struct bio_set *bs = bio->bi_private; - - bio_free(bio, bs); -} - /* * Creates a little bio that just does part of a bvec. */ @@ -1073,7 +1056,6 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector, struct bio_vec *bv = bio->bi_io_vec + idx; clone = bio_alloc_bioset(GFP_NOIO, 1, bs); - clone->bi_destructor = dm_bio_destructor; *clone->bi_io_vec = *bv; clone->bi_sector = sector; @@ -1105,7 +1087,6 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs); __bio_clone(clone, bio); - clone->bi_destructor = dm_bio_destructor; clone->bi_sector = sector; clone->bi_idx = idx; clone->bi_vcnt = idx + bv_count; @@ -1150,7 +1131,6 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti, */ clone = bio_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs); __bio_clone(clone, ci->bio); - clone->bi_destructor = dm_bio_destructor; if (len) { clone->bi_sector = ci->sector; clone->bi_size = to_bytes(len); diff --git a/drivers/md/md.c b/drivers/md/md.c index 3f6203a4c7ea..b8eebe357b2b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -155,32 +155,17 @@ static int start_readonly; * like bio_clone, but with a local bio set */ -static void mddev_bio_destructor(struct bio *bio) -{ - struct mddev *mddev, **mddevp; - - mddevp = (void*)bio; - mddev = mddevp[-1]; - - bio_free(bio, mddev->bio_set); -} - struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev) { struct bio *b; - struct mddev **mddevp; if (!mddev || !mddev->bio_set) return bio_alloc(gfp_mask, nr_iovecs); - b = bio_alloc_bioset(gfp_mask, nr_iovecs, - mddev->bio_set); + b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set); if (!b) return NULL; - mddevp = (void*)b; - mddevp[-1] = mddev; - b->bi_destructor = mddev_bio_destructor; return b; } EXPORT_SYMBOL_GPL(bio_alloc_mddev); @@ -189,18 +174,14 @@ struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, struct mddev *mddev) { struct bio *b; - struct mddev **mddevp; if (!mddev || !mddev->bio_set) return bio_clone(bio, gfp_mask); - b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, - mddev->bio_set); + b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, mddev->bio_set); if (!b) return NULL; - mddevp = (void*)b; - mddevp[-1] = mddev; - b->bi_destructor = mddev_bio_destructor; + __bio_clone(b, bio); if (bio_integrity(bio)) { int ret; @@ -5006,8 +4987,7 @@ int md_run(struct mddev *mddev) } if (mddev->bio_set == NULL) - mddev->bio_set = bioset_create(BIO_POOL_SIZE, - sizeof(struct mddev *)); + mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0); spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 76db75e836ed..e58cd7d2fce4 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -543,14 +543,6 @@ static void iblock_complete_cmd(struct se_cmd *cmd) kfree(ibr); } -static void iblock_bio_destructor(struct bio *bio) -{ - struct se_cmd *cmd = bio->bi_private; - struct iblock_dev *ib_dev = cmd->se_dev->dev_ptr; - - bio_free(bio, ib_dev->ibd_bio_set); -} - static struct bio * iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num) { @@ -572,7 +564,6 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num) bio->bi_bdev = ib_dev->ibd_bd; bio->bi_private = cmd; - bio->bi_destructor = iblock_bio_destructor; bio->bi_end_io = &iblock_bio_done; bio->bi_sector = lba; return bio; -- cgit v1.2.1 From 1e2a410ff71504a64d1af2e354287ac51aeac1b0 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 6 Sep 2012 15:34:56 -0700 Subject: block: Ues bi_pool for bio_integrity_alloc() Now that bios keep track of where they were allocated from, bio_integrity_alloc_bioset() becomes redundant. Remove bio_integrity_alloc_bioset() and drop bio_set argument from the related functions and make them use bio->bi_pool. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/md/dm.c | 4 ++-- drivers/md/md.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 0c3d6dd51897..f43aaf689bd0 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1068,7 +1068,7 @@ 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, bs); + bio_integrity_clone(clone, bio, GFP_NOIO); bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len); } @@ -1094,7 +1094,7 @@ 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, bs); + bio_integrity_clone(clone, bio, GFP_NOIO); if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) bio_integrity_trim(clone, diff --git a/drivers/md/md.c b/drivers/md/md.c index b8eebe357b2b..457ca8451ddb 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -186,7 +186,7 @@ struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, if (bio_integrity(bio)) { int ret; - ret = bio_integrity_clone(b, bio, gfp_mask, mddev->bio_set); + ret = bio_integrity_clone(b, bio, gfp_mask); if (ret < 0) { bio_put(b); -- cgit v1.2.1 From 94818742316e27d01506240cf8b07d69844d31af Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 7 Sep 2012 13:44:01 -0700 Subject: dm: Use bioset's front_pad for dm_rq_clone_bio_info Previously, dm_rq_clone_bio_info needed to be freed by the bio's destructor to avoid a memory leak in the blk_rq_prep_clone() error path. This gets rid of a memory allocation and means we can kill dm_rq_bio_destructor. The _rq_bio_info_cache kmem cache is unused now and needs to be deleted, but due to the way io_pool is used and overloaded this looks not quite trivial so I'm leaving it for a later patch. v6: Fix comment on struct dm_rq_clone_bio_info, per Tejun Signed-off-by: Kent Overstreet CC: Alasdair Kergon Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/md/dm.c | 46 ++++++++++++++++++---------------------------- 1 file changed, 18 insertions(+), 28 deletions(-) (limited to 'drivers') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f43aaf689bd0..33470f01ea5e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -86,12 +86,17 @@ struct dm_rq_target_io { }; /* - * For request-based dm. - * One of these is allocated per bio. + * For request-based dm - the bio clones we allocate are embedded in these + * structs. + * + * We allocate these with bio_alloc_bioset, using the front_pad parameter when + * the bioset is created - this means the bio has to come at the end of the + * struct. */ struct dm_rq_clone_bio_info { struct bio *orig; struct dm_rq_target_io *tio; + struct bio clone; }; union map_info *dm_get_mapinfo(struct bio *bio) @@ -211,6 +216,11 @@ struct dm_md_mempools { static struct kmem_cache *_io_cache; static struct kmem_cache *_tio_cache; static struct kmem_cache *_rq_tio_cache; + +/* + * Unused now, and needs to be deleted. But since io_pool is overloaded and it's + * still used for _io_cache, I'm leaving this for a later cleanup + */ static struct kmem_cache *_rq_bio_info_cache; static int __init local_init(void) @@ -467,16 +477,6 @@ static void free_rq_tio(struct dm_rq_target_io *tio) mempool_free(tio, tio->md->tio_pool); } -static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md) -{ - return mempool_alloc(md->io_pool, GFP_ATOMIC); -} - -static void free_bio_info(struct dm_rq_clone_bio_info *info) -{ - mempool_free(info, info->tio->md->io_pool); -} - static int md_in_flight(struct mapped_device *md) { return atomic_read(&md->pending[READ]) + @@ -1460,30 +1460,17 @@ void dm_dispatch_request(struct request *rq) } EXPORT_SYMBOL_GPL(dm_dispatch_request); -static void dm_rq_bio_destructor(struct bio *bio) -{ - struct dm_rq_clone_bio_info *info = bio->bi_private; - struct mapped_device *md = info->tio->md; - - free_bio_info(info); - bio_free(bio, md->bs); -} - static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig, void *data) { struct dm_rq_target_io *tio = data; - struct mapped_device *md = tio->md; - struct dm_rq_clone_bio_info *info = alloc_bio_info(md); - - if (!info) - return -ENOMEM; + struct dm_rq_clone_bio_info *info = + container_of(bio, struct dm_rq_clone_bio_info, clone); info->orig = bio_orig; info->tio = tio; bio->bi_end_io = end_clone_bio; bio->bi_private = info; - bio->bi_destructor = dm_rq_bio_destructor; return 0; } @@ -2718,7 +2705,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity) if (!pools->tio_pool) goto free_io_pool_and_out; - pools->bs = bioset_create(pool_size, 0); + pools->bs = (type == DM_TYPE_BIO_BASED) ? + bioset_create(pool_size, 0) : + bioset_create(pool_size, + offsetof(struct dm_rq_clone_bio_info, clone)); if (!pools->bs) goto free_tio_pool_and_out; -- cgit v1.2.1 From ccc5c9ca6aac08218b1ba52afd07a1a9864c8c5d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 7 Sep 2012 13:44:02 -0700 Subject: pktcdvd: Switch to bio_kmalloc() This is prep work for killing bi_destructor - previously, pktcdvd had its own pkt_bio_alloc which was basically duplication bio_kmalloc(), necessitating its own bi_destructor implementation. v5: Un-reorder some functions, to make the patch easier to review Signed-off-by: Kent Overstreet Acked-by: Jiri Kosina Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 52 +++++++------------------------------------------ 1 file changed, 7 insertions(+), 45 deletions(-) (limited to 'drivers') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index ba66e4445f41..2e7de7a59bfc 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -522,38 +522,6 @@ static void pkt_bio_finished(struct pktcdvd_device *pd) } } -static void pkt_bio_destructor(struct bio *bio) -{ - kfree(bio->bi_io_vec); - kfree(bio); -} - -static struct bio *pkt_bio_alloc(int nr_iovecs) -{ - struct bio_vec *bvl = NULL; - struct bio *bio; - - bio = kmalloc(sizeof(struct bio), GFP_KERNEL); - if (!bio) - goto no_bio; - bio_init(bio); - - bvl = kcalloc(nr_iovecs, sizeof(struct bio_vec), GFP_KERNEL); - if (!bvl) - goto no_bvl; - - bio->bi_max_vecs = nr_iovecs; - bio->bi_io_vec = bvl; - bio->bi_destructor = pkt_bio_destructor; - - return bio; - - no_bvl: - kfree(bio); - no_bio: - return NULL; -} - /* * Allocate a packet_data struct */ @@ -567,7 +535,7 @@ static struct packet_data *pkt_alloc_packet_data(int frames) goto no_pkt; pkt->frames = frames; - pkt->w_bio = pkt_bio_alloc(frames); + pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames); if (!pkt->w_bio) goto no_bio; @@ -581,9 +549,10 @@ static struct packet_data *pkt_alloc_packet_data(int frames) bio_list_init(&pkt->orig_bios); for (i = 0; i < frames; i++) { - struct bio *bio = pkt_bio_alloc(1); + struct bio *bio = bio_kmalloc(GFP_KERNEL, 1); if (!bio) goto no_rd_bio; + pkt->r_bios[i] = bio; } @@ -1111,21 +1080,17 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) * Schedule reads for missing parts of the packet. */ for (f = 0; f < pkt->frames; f++) { - struct bio_vec *vec; - int p, offset; + if (written[f]) continue; + bio = pkt->r_bios[f]; - vec = bio->bi_io_vec; - bio_init(bio); - bio->bi_max_vecs = 1; + bio_reset(bio); bio->bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); bio->bi_bdev = pd->bdev; bio->bi_end_io = pkt_end_io_read; bio->bi_private = pkt; - bio->bi_io_vec = vec; - bio->bi_destructor = pkt_bio_destructor; p = (f * CD_FRAMESIZE) / PAGE_SIZE; offset = (f * CD_FRAMESIZE) % PAGE_SIZE; @@ -1418,14 +1383,11 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) } /* Start the write request */ - bio_init(pkt->w_bio); - pkt->w_bio->bi_max_vecs = PACKET_MAX_SIZE; + bio_reset(pkt->w_bio); pkt->w_bio->bi_sector = pkt->sector; pkt->w_bio->bi_bdev = pd->bdev; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; - pkt->w_bio->bi_io_vec = bvec; - pkt->w_bio->bi_destructor = pkt_bio_destructor; for (f = 0; f < pkt->frames; f++) if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset)) BUG(); -- cgit v1.2.1 From bf800ef1816b4283a885e55ad38068aec9711e4d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 6 Sep 2012 15:35:02 -0700 Subject: block: Add bio_clone_bioset(), bio_clone_kmalloc() Previously, there was bio_clone() but it only allocated from the fs bio set; as a result various users were open coding it and using __bio_clone(). This changes bio_clone() to become bio_clone_bioset(), and then we add bio_clone() and bio_clone_kmalloc() as wrappers around it, making use of the functionality the last patch adedd. This will also help in a later patch changing how bio cloning works. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown CC: Alasdair Kergon CC: Boaz Harrosh CC: Jeff Garzik Acked-by: Jeff Garzik Signed-off-by: Jens Axboe --- drivers/block/osdblk.c | 3 +-- drivers/md/dm-crypt.c | 7 +------ drivers/md/dm.c | 4 ++-- drivers/md/md.c | 20 +------------------- 4 files changed, 5 insertions(+), 29 deletions(-) (limited to 'drivers') diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 87311ebac0db..1bbc681688e4 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -266,11 +266,10 @@ static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask) struct bio *tmp, *new_chain = NULL, *tail = NULL; while (old_chain) { - tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs); + tmp = bio_clone_kmalloc(old_chain, gfpmask); if (!tmp) goto err_out; - __bio_clone(tmp, old_chain); tmp->bi_bdev = NULL; gfpmask &= ~__GFP_WAIT; tmp->bi_next = NULL; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3c0acba042b6..bbf459bca61d 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -979,19 +979,14 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) * copy the required bvecs because we need the original * one in order to decrypt the whole bio data *afterwards*. */ - clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs); + clone = bio_clone_bioset(base_bio, gfp, cc->bs); if (!clone) return 1; crypt_inc_pending(io); clone_init(io, clone); - clone->bi_idx = 0; - clone->bi_vcnt = bio_segments(base_bio); - clone->bi_size = base_bio->bi_size; clone->bi_sector = cc->start + io->sector; - memcpy(clone->bi_io_vec, bio_iovec(base_bio), - sizeof(struct bio_vec) * clone->bi_vcnt); generic_make_request(clone); return 0; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 33470f01ea5e..837879716889 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1129,8 +1129,8 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti, * 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_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs); - __bio_clone(clone, ci->bio); + clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs); + if (len) { clone->bi_sector = ci->sector; clone->bi_size = to_bytes(len); diff --git a/drivers/md/md.c b/drivers/md/md.c index 457ca8451ddb..7a2b0793f66e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -173,28 +173,10 @@ EXPORT_SYMBOL_GPL(bio_alloc_mddev); struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, struct mddev *mddev) { - struct bio *b; - if (!mddev || !mddev->bio_set) return bio_clone(bio, gfp_mask); - b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, mddev->bio_set); - if (!b) - return NULL; - - __bio_clone(b, bio); - if (bio_integrity(bio)) { - int ret; - - ret = bio_integrity_clone(b, bio, gfp_mask); - - if (ret < 0) { - bio_put(b); - return NULL; - } - } - - return b; + return bio_clone_bioset(bio, gfp_mask, mddev->bio_set); } EXPORT_SYMBOL_GPL(bio_clone_mddev); -- cgit v1.2.1 From 4363ac7c13a9a4b763c6e8d9fdbfc2468f3b8ca4 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 18 Sep 2012 12:19:27 -0400 Subject: block: Implement support for WRITE SAME The WRITE SAME command supported on some SCSI devices allows the same block to be efficiently replicated throughout a block range. Only a single logical block is transferred from the host and the storage device writes the same data to all blocks described by the I/O. This patch implements support for WRITE SAME in the block layer. The blkdev_issue_write_same() function can be used by filesystems and block drivers to replicate a buffer across a block range. This can be used to efficiently initialize software RAID devices, etc. Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- drivers/md/raid0.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index de63a1fc3737..a9e4fa95dfaa 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -422,6 +422,7 @@ static int raid0_run(struct mddev *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { -- cgit v1.2.1 From b87570f5d349661814b262dd5fc40787700f80d6 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 26 Sep 2012 07:46:40 +0200 Subject: Fix a crash when block device is read and block size is changed at the same time The kernel may crash when block size is changed and I/O is issued simultaneously. Because some subsystems (udev or lvm) may read any block device anytime, the bug actually puts any code that changes a block device size in jeopardy. The crash can be reproduced if you place "msleep(1000)" to blkdev_get_blocks just before "bh->b_size = max_blocks << inode->i_blkbits;". Then, run "dd if=/dev/ram0 of=/dev/null bs=4k count=1 iflag=direct" While it is waiting in msleep, run "blockdev --setbsz 2048 /dev/ram0" You get a BUG. The direct and non-direct I/O is written with the assumption that block size does not change. It doesn't seem practical to fix these crashes one-by-one there may be many crash possibilities when block size changes at a certain place and it is impossible to find them all and verify the code. This patch introduces a new rw-lock bd_block_size_semaphore. The lock is taken for read during I/O. It is taken for write when changing block size. Consequently, block size can't be changed while I/O is being submitted. For asynchronous I/O, the patch only prevents block size change while the I/O is being submitted. The block size can change when the I/O is in progress or when the I/O is being finished. This is acceptable because there are no accesses to block size when asynchronous I/O is being finished. The patch prevents block size changing while the device is mapped with mmap. Signed-off-by: Mikulas Patocka Signed-off-by: Jens Axboe --- drivers/char/raw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 54a3a6d09819..0bb207eaef2f 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -285,7 +285,7 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd, static const struct file_operations raw_fops = { .read = do_sync_read, - .aio_read = generic_file_aio_read, + .aio_read = blkdev_aio_read, .write = do_sync_write, .aio_write = blkdev_aio_write, .fsync = blkdev_fsync, -- cgit v1.2.1