Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933201Ab2HVRFp (ORCPT ); Wed, 22 Aug 2012 13:05:45 -0400 Received: from mail-pz0-f46.google.com ([209.85.210.46]:61272 "EHLO mail-pz0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964823Ab2HVREq (ORCPT ); Wed, 22 Aug 2012 13:04:46 -0400 From: Kent Overstreet To: linux-bcache@vger.kernel.org, linux-kernel@vger.kernel.org, dm-devel@redhat.com Cc: Kent Overstreet , tj@kernel.org, vgoyal@redhat.com, mpatocka@redhat.com, bharrosh@panasas.com, Jens Axboe , NeilBrown , Lars Ellenberg , Peter Osterlund , Sage Weil , "Martin K. Petersen" Subject: [PATCH v6 11/13] block: Rework bio_pair_split() Date: Wed, 22 Aug 2012 10:04:08 -0700 Message-Id: <1345655050-28199-12-git-send-email-koverstreet@google.com> X-Mailer: git-send-email 1.7.12 In-Reply-To: <1345655050-28199-1-git-send-email-koverstreet@google.com> References: <1345655050-28199-1-git-send-email-koverstreet@google.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 13862 Lines: 433 This changes bio_pair_split() to use the new bio_split() underneath, which gets rid of the single page bio limitation. The various callers are fixed up for the slightly different struct bio_pair, and to remove the unnecessary checks. v5: Move extern declaration to proper patch, per Boaz Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown CC: Lars Ellenberg CC: Peter Osterlund CC: Sage Weil CC: Martin K. Petersen --- drivers/block/drbd/drbd_req.c | 16 +------ drivers/block/pktcdvd.c | 4 +- drivers/block/rbd.c | 7 ++-- drivers/md/linear.c | 4 +- drivers/md/raid0.c | 6 +-- drivers/md/raid10.c | 21 ++-------- fs/bio-integrity.c | 44 -------------------- fs/bio.c | 97 +++++++++++++++++++------------------------ include/linux/bio.h | 22 ++++------ 9 files changed, 66 insertions(+), 155 deletions(-) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index fbb0471..7d3e662 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1122,18 +1122,6 @@ void drbd_make_request(struct request_queue *q, struct bio *bio) do { inc_ap_bio(mdev, 1); } while (drbd_make_request_common(mdev, bio, start_time)); - return; - } - - /* can this bio be split generically? - * Maybe add our own split-arbitrary-bios function. */ - if (bio->bi_vcnt != 1 || bio->bi_idx != 0 || bio->bi_size > DRBD_MAX_BIO_SIZE) { - /* rather error out here than BUG in bio_split */ - dev_err(DEV, "bio would need to, but cannot, be split: " - "(vcnt=%u,idx=%u,size=%u,sector=%llu)\n", - bio->bi_vcnt, bio->bi_idx, bio->bi_size, - (unsigned long long)bio->bi_sector); - bio_endio(bio, -EINVAL); } else { /* This bio crosses some boundary, so we have to split it. */ struct bio_pair *bp; @@ -1160,10 +1148,10 @@ void drbd_make_request(struct request_queue *q, struct bio *bio) D_ASSERT(e_enr == s_enr + 1); - while (drbd_make_request_common(mdev, &bp->bio1, start_time)) + while (drbd_make_request_common(mdev, &bp->split, start_time)) inc_ap_bio(mdev, 1); - while (drbd_make_request_common(mdev, &bp->bio2, start_time)) + while (drbd_make_request_common(mdev, bio, start_time)) inc_ap_bio(mdev, 1); dec_ap_bio(mdev); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 18393a1..6709c1d 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2471,8 +2471,8 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio) first_sectors = last_zone - bio->bi_sector; bp = bio_pair_split(bio, first_sectors); BUG_ON(!bp); - pkt_make_request(q, &bp->bio1); - pkt_make_request(q, &bp->bio2); + pkt_make_request(q, &bp->split); + pkt_make_request(q, bio); bio_pair_release(bp); return; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1f5b483..63e5852 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -751,14 +751,13 @@ static struct bio *bio_chain_clone(struct bio **old, struct bio **next, /* split the bio. We'll release it either in the next call, or it will have to be released outside */ - bp = bio_pair_split(old_chain, - (len - total) / SECTOR_SIZE); + bp = bio_pair_split(old_chain, (len - total) / SECTOR_SIZE); if (!bp) goto err_out; - __bio_clone(tmp, &bp->bio1); + __bio_clone(tmp, &bp->split); - *next = &bp->bio2; + *next = bp->orig; } else { __bio_clone(tmp, old_chain); *next = old_chain->bi_next; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index e860cb9..7c6cafd 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -316,8 +316,8 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio) bp = bio_pair_split(bio, end_sector - bio->bi_sector); - linear_make_request(mddev, &bp->bio1); - linear_make_request(mddev, &bp->bio2); + linear_make_request(mddev, &bp->split); + linear_make_request(mddev, bio); bio_pair_release(bp); return; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c89c8aa..3469adf 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -520,9 +520,9 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) (chunk_sects-1))); else bp = bio_pair_split(bio, chunk_sects - - sector_div(sector, chunk_sects)); - raid0_make_request(mddev, &bp->bio1); - raid0_make_request(mddev, &bp->bio2); + sector_div(sector, chunk_sects)); + raid0_make_request(mddev, &bp->split); + raid0_make_request(mddev, bio); bio_pair_release(bp); return; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 0f31ec4..9fa07c7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1080,15 +1080,9 @@ static void make_request(struct mddev *mddev, struct bio * bio) && (conf->geo.near_copies < conf->geo.raid_disks || conf->prev.near_copies < conf->prev.raid_disks))) { struct bio_pair *bp; - /* Sanity check -- queue functions should prevent this happening */ - if (bio->bi_vcnt != 1 || - bio->bi_idx != 0) - goto bad_map; - /* This is a one page bio that upper layers - * refuse to split for us, so we need to split it. - */ + bp = bio_pair_split(bio, - chunk_sects - (bio->bi_sector & (chunk_sects - 1)) ); + chunk_sects - (bio->bi_sector & (chunk_sects - 1))); /* Each of these 'make_request' calls will call 'wait_barrier'. * If the first succeeds but the second blocks due to the resync @@ -1102,8 +1096,8 @@ static void make_request(struct mddev *mddev, struct bio * bio) conf->nr_waiting++; spin_unlock_irq(&conf->resync_lock); - make_request(mddev, &bp->bio1); - make_request(mddev, &bp->bio2); + make_request(mddev, &bp->split); + make_request(mddev, bio); spin_lock_irq(&conf->resync_lock); conf->nr_waiting--; @@ -1112,13 +1106,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) bio_pair_release(bp); return; - bad_map: - printk("md/raid10:%s: make_request bug: can't convert block across chunks" - " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2, - (unsigned long long)bio->bi_sector, bio->bi_size >> 10); - - bio_io_error(bio); - return; } md_write_start(mddev, bio); diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 35ee3d4..08a9e12 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -681,50 +681,6 @@ void bio_integrity_trim(struct bio *bio, unsigned int offset, EXPORT_SYMBOL(bio_integrity_trim); /** - * bio_integrity_split - Split integrity metadata - * @bio: Protected bio - * @bp: Resulting bio_pair - * @sectors: Offset - * - * Description: Splits an integrity page into a bio_pair. - */ -void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors) -{ - struct blk_integrity *bi; - struct bio_integrity_payload *bip = bio->bi_integrity; - unsigned int nr_sectors; - - if (bio_integrity(bio) == 0) - return; - - bi = bdev_get_integrity(bio->bi_bdev); - BUG_ON(bi == NULL); - BUG_ON(bip->bip_vcnt != 1); - - nr_sectors = bio_integrity_hw_sectors(bi, sectors); - - bp->bio1.bi_integrity = &bp->bip1; - bp->bio2.bi_integrity = &bp->bip2; - - bp->iv1 = bip->bip_vec[0]; - bp->iv2 = bip->bip_vec[0]; - - 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; - bp->iv2.bv_len -= sectors * bi->tuple_size; - - bp->bip1.bip_sector = bio->bi_integrity->bip_sector; - bp->bip2.bip_sector = bio->bi_integrity->bip_sector + nr_sectors; - - bp->bip1.bip_vcnt = bp->bip2.bip_vcnt = 1; - bp->bip1.bip_idx = bp->bip2.bip_idx = 0; -} -EXPORT_SYMBOL(bio_integrity_split); - -/** * bio_integrity_clone - Callback for cloning bios with integrity metadata * @bio: New bio * @bio_src: Original bio diff --git a/fs/bio.c b/fs/bio.c index c079006..f50adbd 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -37,7 +37,7 @@ */ #define BIO_INLINE_VECS 4 -static mempool_t *bio_split_pool __read_mostly; +static struct bio_set *bio_split_pool __read_mostly; /* * if you change this list, also change bvec_alloc or things will @@ -1461,80 +1461,70 @@ void bio_endio(struct bio *bio, int error) } EXPORT_SYMBOL(bio_endio); +/** + * bio_pair_release - drop refcount on a bio_pair + * + * This is called by bio_pair_split's endio function, and also must be called by + * the caller of bio_pair_split(). + */ void bio_pair_release(struct bio_pair *bp) { if (atomic_dec_and_test(&bp->cnt)) { - struct bio *master = bp->bio1.bi_private; + bp->orig->bi_end_io = bp->bi_end_io; + bp->orig->bi_private = bp->bi_private; - bio_endio(master, bp->error); - mempool_free(bp, bp->bio2.bi_private); + bio_endio(bp->orig, 0); + bio_put(&bp->split); } } EXPORT_SYMBOL(bio_pair_release); -static void bio_pair_end_1(struct bio *bi, int err) +static void bio_pair_end(struct bio *bio, int error) { - struct bio_pair *bp = container_of(bi, struct bio_pair, bio1); + struct bio_pair *bp = bio->bi_private; - if (err) - bp->error = err; - - bio_pair_release(bp); -} - -static void bio_pair_end_2(struct bio *bi, int err) -{ - struct bio_pair *bp = container_of(bi, struct bio_pair, bio2); - - if (err) - bp->error = err; + if (error) + clear_bit(BIO_UPTODATE, &bp->orig->bi_flags); bio_pair_release(bp); } -/* - * split a bio - only worry about a bio with a single page in its iovec +/** + * bio_pair_split - split a bio, and chain the completions + * @bio: bio to split + * @sectors: number of sectors to split from the front of @bio + * + * This wraps bio_split(), and puts the split and the original bio in a struct + * bio_pair. It also hooks into the completions so the original bio will be + * completed once both splits have been completed. + * + * The caller will own a refcount on the returned bio_pair, which must be + * dropped with bio_pair_release(). */ -struct bio_pair *bio_pair_split(struct bio *bi, int first_sectors) +struct bio_pair *bio_pair_split(struct bio *bio, int sectors) { - struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO); + struct bio_pair *bp; + struct bio *split; - if (!bp) - return bp; - - trace_block_split(bdev_get_queue(bi->bi_bdev), bi, - bi->bi_sector + first_sectors); - - BUG_ON(bi->bi_vcnt != 1); - BUG_ON(bi->bi_idx != 0); - atomic_set(&bp->cnt, 3); - bp->error = 0; - bp->bio1 = *bi; - bp->bio2 = *bi; - bp->bio2.bi_sector += first_sectors; - bp->bio2.bi_size -= first_sectors << 9; - bp->bio1.bi_size = first_sectors << 9; + split = bio_split(bio, sectors, GFP_NOIO, bio_split_pool); + if (!split) + return NULL; - bp->bv1 = bi->bi_io_vec[0]; - bp->bv2 = bi->bi_io_vec[0]; - bp->bv2.bv_offset += first_sectors << 9; - bp->bv2.bv_len -= first_sectors << 9; - bp->bv1.bv_len = first_sectors << 9; + BUG_ON(split == bio); - bp->bio1.bi_io_vec = &bp->bv1; - bp->bio2.bi_io_vec = &bp->bv2; + bp = container_of(split, struct bio_pair, split); - bp->bio1.bi_max_vecs = 1; - bp->bio2.bi_max_vecs = 1; + atomic_set(&bp->cnt, 3); + bp->orig = bio; - bp->bio1.bi_end_io = bio_pair_end_1; - bp->bio2.bi_end_io = bio_pair_end_2; + bp->bi_end_io = bio->bi_end_io; + bp->bi_private = bio->bi_private; - bp->bio1.bi_private = bi; - bp->bio2.bi_private = bio_split_pool; + bio->bi_private = bp; + bio->bi_end_io = bio_pair_end; - if (bio_integrity(bi)) - bio_integrity_split(bi, bp, first_sectors); + split->bi_private = bp; + split->bi_end_io = bio_pair_end; return bp; } @@ -1856,8 +1846,7 @@ static int __init init_bio(void) if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE)) panic("bio: can't create integrity pool\n"); - bio_split_pool = mempool_create_kmalloc_pool(BIO_SPLIT_ENTRIES, - sizeof(struct bio_pair)); + bio_split_pool = bioset_create(BIO_POOL_SIZE, offsetof(struct bio_pair, split)); if (!bio_split_pool) panic("bio: can't create split pool\n"); diff --git a/include/linux/bio.h b/include/linux/bio.h index 1c3bb47..3ad3540 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -192,14 +192,13 @@ struct bio_integrity_payload { * in bio2.bi_private */ struct bio_pair { - 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; + atomic_t cnt; + + bio_end_io_t *bi_end_io; + void *bi_private; + + struct bio *orig; + struct bio split; }; extern struct bio *bio_split(struct bio *bio, int sectors, @@ -544,7 +543,6 @@ 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 *, gfp_t, struct bio_set *); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); @@ -588,12 +586,6 @@ static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, return 0; } -static inline void bio_integrity_split(struct bio *bio, struct bio_pair *bp, - int sectors) -{ - return; -} - static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { -- 1.7.12 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/