From f82c458a2c3ffb94b431fc6ad791a79df1b3713e Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Wed, 19 Nov 2014 10:25:09 -0800 Subject: btrfs: fix lockups from btrfs_clear_path_blocking The fair reader/writer locks mean that btrfs_clear_path_blocking needs to strictly follow lock ordering rules even when we already have blocking locks on a given path. Before we can clear a blocking lock on the path, we need to make sure all of the locks have been converted to blocking. This will remove lock inversions against anyone spinning in write_lock() against the buffers we're trying to get read locks on. These inversions didn't exist before the fair read/writer locks, but now we need to be more careful. We papered over this deadlock in the past by changing btrfs_try_read_lock() to be a true trylock against both the spinlock and the blocking lock. This was slower, and not sufficient to fix all the deadlocks. This patch adds a btrfs_tree_read_lock_atomic(), which basically means get the spinlock but trylock on the blocking lock. Signed-off-by: Chris Mason Signed-off-by: Josef Bacik Reported-by: Patrick Schmid cc: stable@vger.kernel.org #v3.15+ --- fs/btrfs/ctree.c | 14 ++------------ fs/btrfs/locking.c | 24 +++++++++++++++++++++--- fs/btrfs/locking.h | 2 ++ 3 files changed, 25 insertions(+), 15 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 19bc6162fb8e..150822ee0a0b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -80,13 +80,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, { int i; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - /* lockdep really cares that we take all of these spinlocks - * in the right order. If any of the locks in the path are not - * currently blocking, it is going to complain. So, make really - * really sure by forcing the path to blocking before we clear - * the path blocking. - */ if (held) { btrfs_set_lock_blocking_rw(held, held_rw); if (held_rw == BTRFS_WRITE_LOCK) @@ -95,7 +88,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, held_rw = BTRFS_READ_LOCK_BLOCKING; } btrfs_set_path_blocking(p); -#endif for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) { if (p->nodes[i] && p->locks[i]) { @@ -107,10 +99,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, } } -#ifdef CONFIG_DEBUG_LOCK_ALLOC if (held) btrfs_clear_lock_blocking_rw(held, held_rw); -#endif } /* this also releases the path */ @@ -2893,7 +2883,7 @@ cow_done: } p->locks[level] = BTRFS_WRITE_LOCK; } else { - err = btrfs_try_tree_read_lock(b); + err = btrfs_tree_read_lock_atomic(b); if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); @@ -3025,7 +3015,7 @@ again: } level = btrfs_header_level(b); - err = btrfs_try_tree_read_lock(b); + err = btrfs_tree_read_lock_atomic(b); if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 5665d2149249..f8229ef1b46d 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -127,6 +127,26 @@ again: atomic_inc(&eb->spinning_readers); } +/* + * take a spinning read lock. + * returns 1 if we get the read lock and 0 if we don't + * this won't wait for blocking writers + */ +int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) +{ + if (atomic_read(&eb->blocking_writers)) + return 0; + + read_lock(&eb->lock); + if (atomic_read(&eb->blocking_writers)) { + read_unlock(&eb->lock); + return 0; + } + atomic_inc(&eb->read_locks); + atomic_inc(&eb->spinning_readers); + return 1; +} + /* * returns 1 if we get the read lock and 0 if we don't * this won't wait for blocking writers @@ -158,9 +178,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) atomic_read(&eb->blocking_readers)) return 0; - if (!write_trylock(&eb->lock)) - return 0; - + write_lock(&eb->lock); if (atomic_read(&eb->blocking_writers) || atomic_read(&eb->blocking_readers)) { write_unlock(&eb->lock); diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index b81e0e9a4894..c44a9d5f5362 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -35,6 +35,8 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw); void btrfs_assert_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_read_lock(struct extent_buffer *eb); int btrfs_try_tree_write_lock(struct extent_buffer *eb); +int btrfs_tree_read_lock_atomic(struct extent_buffer *eb); + static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw) { -- cgit v1.2.3 From f90523d1aa3c414031094ff2284d47791f0c0a05 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Thu, 13 Nov 2014 11:45:39 +0800 Subject: Btrfs: remove noused bbio_ret in __btrfs_map_block in condition bbio_ret in this condition is always !NULL because previous code already have a check-and-skip: 4908 if (!bbio_ret) 4909 goto out; Signed-off-by: Zhao Lei Signed-off-by: Miao Xie Reviewed-by: David Sterba --- fs/btrfs/volumes.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d47289c715c8..20160aa44655 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5161,8 +5161,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, BTRFS_BLOCK_GROUP_RAID6)) { u64 tmp; - if (bbio_ret && ((rw & REQ_WRITE) || mirror_num > 1) - && raid_map_ret) { + if (raid_map_ret && ((rw & REQ_WRITE) || mirror_num > 1)) { int i, rot; /* push stripe_nr back to the start of the full stripe */ -- cgit v1.2.3 From 6de65650758e819d3dfdc621010dcd6117e8d186 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Thu, 13 Nov 2014 11:45:40 +0800 Subject: Btrfs: remove unnecessary code of stripe_index assignment in __btrfs_map_block stripe_index's value was set again in latter line: stripe_index = 0; Signed-off-by: Zhao Lei Signed-off-by: Miao Xie Reviewed-by: David Sterba --- fs/btrfs/volumes.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 20160aa44655..6f5b302a08cf 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5166,9 +5166,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, /* push stripe_nr back to the start of the full stripe */ stripe_nr = raid56_full_stripe_start; - do_div(stripe_nr, stripe_len); - - stripe_index = do_div(stripe_nr, nr_data_stripes(map)); + do_div(stripe_nr, stripe_len * nr_data_stripes(map)); /* RAID[56] write or recovery. Return all stripes */ num_stripes = map->num_stripes; -- cgit v1.2.3 From b89e1b012c7f81123344058d5f245b844464d30c Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Wed, 15 Oct 2014 11:18:44 +0800 Subject: Btrfs, raid56: don't change bbio and raid_map Because we will reuse bbio and raid_map during the scrub later, it is better that we don't change any variant of bbio and don't free it at the end of IO request. So we introduced similar variants into the raid bio, and don't access those bbio's variants any more. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 6a41631cb959..c54b0e64c590 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -58,7 +58,6 @@ */ #define RBIO_CACHE_READY_BIT 3 - #define RBIO_CACHE_SIZE 1024 struct btrfs_raid_bio { @@ -146,6 +145,10 @@ struct btrfs_raid_bio { atomic_t refs; + + atomic_t stripes_pending; + + atomic_t error; /* * these are two arrays of pointers. We allocate the * rbio big enough to hold them both and setup their @@ -858,13 +861,13 @@ static void raid_write_end_io(struct bio *bio, int err) bio_put(bio); - if (!atomic_dec_and_test(&rbio->bbio->stripes_pending)) + if (!atomic_dec_and_test(&rbio->stripes_pending)) return; err = 0; /* OK, we have read all the stripes we need to. */ - if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors) + if (atomic_read(&rbio->error) > rbio->bbio->max_errors) err = -EIO; rbio_orig_end_io(rbio, err, 0); @@ -949,6 +952,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, rbio->faila = -1; rbio->failb = -1; atomic_set(&rbio->refs, 1); + atomic_set(&rbio->error, 0); + atomic_set(&rbio->stripes_pending, 0); /* * the stripe_pages and bio_pages array point to the extra @@ -1169,7 +1174,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags); spin_unlock_irq(&rbio->bio_list_lock); - atomic_set(&rbio->bbio->error, 0); + atomic_set(&rbio->error, 0); /* * now that we've set rmw_locked, run through the @@ -1245,8 +1250,8 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) } } - atomic_set(&bbio->stripes_pending, bio_list_size(&bio_list)); - BUG_ON(atomic_read(&bbio->stripes_pending) == 0); + atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list)); + BUG_ON(atomic_read(&rbio->stripes_pending) == 0); while (1) { bio = bio_list_pop(&bio_list); @@ -1331,11 +1336,11 @@ static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed) if (rbio->faila == -1) { /* first failure on this rbio */ rbio->faila = failed; - atomic_inc(&rbio->bbio->error); + atomic_inc(&rbio->error); } else if (rbio->failb == -1) { /* second failure on this rbio */ rbio->failb = failed; - atomic_inc(&rbio->bbio->error); + atomic_inc(&rbio->error); } else { ret = -EIO; } @@ -1394,11 +1399,11 @@ static void raid_rmw_end_io(struct bio *bio, int err) bio_put(bio); - if (!atomic_dec_and_test(&rbio->bbio->stripes_pending)) + if (!atomic_dec_and_test(&rbio->stripes_pending)) return; err = 0; - if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors) + if (atomic_read(&rbio->error) > rbio->bbio->max_errors) goto cleanup; /* @@ -1439,7 +1444,6 @@ static void async_read_rebuild(struct btrfs_raid_bio *rbio) static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) { int bios_to_read = 0; - struct btrfs_bio *bbio = rbio->bbio; struct bio_list bio_list; int ret; int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE); @@ -1455,7 +1459,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) index_rbio_pages(rbio); - atomic_set(&rbio->bbio->error, 0); + atomic_set(&rbio->error, 0); /* * build a list of bios to read all the missing parts of this * stripe @@ -1503,7 +1507,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) * the bbio may be freed once we submit the last bio. Make sure * not to touch it after that */ - atomic_set(&bbio->stripes_pending, bios_to_read); + atomic_set(&rbio->stripes_pending, bios_to_read); while (1) { bio = bio_list_pop(&bio_list); if (!bio) @@ -1917,10 +1921,10 @@ static void raid_recover_end_io(struct bio *bio, int err) set_bio_pages_uptodate(bio); bio_put(bio); - if (!atomic_dec_and_test(&rbio->bbio->stripes_pending)) + if (!atomic_dec_and_test(&rbio->stripes_pending)) return; - if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors) + if (atomic_read(&rbio->error) > rbio->bbio->max_errors) rbio_orig_end_io(rbio, -EIO, 0); else __raid_recover_end_io(rbio); @@ -1951,7 +1955,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) if (ret) goto cleanup; - atomic_set(&rbio->bbio->error, 0); + atomic_set(&rbio->error, 0); /* * read everything that hasn't failed. Thanks to the @@ -1960,7 +1964,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) */ for (stripe = 0; stripe < bbio->num_stripes; stripe++) { if (rbio->faila == stripe || rbio->failb == stripe) { - atomic_inc(&rbio->bbio->error); + atomic_inc(&rbio->error); continue; } @@ -1990,7 +1994,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) * were up to date, or we might have no bios to read because * the devices were gone. */ - if (atomic_read(&rbio->bbio->error) <= rbio->bbio->max_errors) { + if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) { __raid_recover_end_io(rbio); goto out; } else { @@ -2002,7 +2006,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) * the bbio may be freed once we submit the last bio. Make sure * not to touch it after that */ - atomic_set(&bbio->stripes_pending, bios_to_read); + atomic_set(&rbio->stripes_pending, bios_to_read); while (1) { bio = bio_list_pop(&bio_list); if (!bio) -- cgit v1.2.3 From af8e2d1df9848b39dd86b1e696bf8781d2020a88 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 23 Oct 2014 14:42:50 +0800 Subject: Btrfs, scrub: repair the common data on RAID5/6 if it is corrupted This patch implement the RAID5/6 common data repair function, the implementation is similar to the scrub on the other RAID such as RAID1, the differentia is that we don't read the data from the mirror, we use the data repair function of RAID5/6. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 52 ++++++++++---- fs/btrfs/raid56.h | 2 +- fs/btrfs/scrub.c | 194 ++++++++++++++++++++++++++++++++++++++++++++++++----- fs/btrfs/volumes.c | 16 ++++- fs/btrfs/volumes.h | 4 ++ 5 files changed, 235 insertions(+), 33 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index c54b0e64c590..95053a903474 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -58,6 +58,15 @@ */ #define RBIO_CACHE_READY_BIT 3 +/* + * bbio and raid_map is managed by the caller, so we shouldn't free + * them here. And besides that, all rbios with this flag should not + * be cached, because we need raid_map to check the rbios' stripe + * is the same or not, but it is very likely that the caller has + * free raid_map, so don't cache those rbios. + */ +#define RBIO_HOLD_BBIO_MAP_BIT 4 + #define RBIO_CACHE_SIZE 1024 struct btrfs_raid_bio { @@ -799,6 +808,21 @@ done_nolock: remove_rbio_from_cache(rbio); } +static inline void +__free_bbio_and_raid_map(struct btrfs_bio *bbio, u64 *raid_map, int need) +{ + if (need) { + kfree(raid_map); + kfree(bbio); + } +} + +static inline void free_bbio_and_raid_map(struct btrfs_raid_bio *rbio) +{ + __free_bbio_and_raid_map(rbio->bbio, rbio->raid_map, + !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags)); +} + static void __free_raid_bio(struct btrfs_raid_bio *rbio) { int i; @@ -817,8 +841,9 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio) rbio->stripe_pages[i] = NULL; } } - kfree(rbio->raid_map); - kfree(rbio->bbio); + + free_bbio_and_raid_map(rbio); + kfree(rbio); } @@ -933,11 +958,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2, GFP_NOFS); - if (!rbio) { - kfree(raid_map); - kfree(bbio); + if (!rbio) return ERR_PTR(-ENOMEM); - } bio_list_init(&rbio->bio_list); INIT_LIST_HEAD(&rbio->plug_list); @@ -1692,8 +1714,10 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct blk_plug_cb *cb; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); - if (IS_ERR(rbio)) + if (IS_ERR(rbio)) { + __free_bbio_and_raid_map(bbio, raid_map, 1); return PTR_ERR(rbio); + } bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_iter.bi_size; @@ -1888,7 +1912,8 @@ cleanup: cleanup_io: if (rbio->read_rebuild) { - if (err == 0) + if (err == 0 && + !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags)) cache_rbio_pages(rbio); else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); @@ -2038,15 +2063,19 @@ cleanup: */ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, - u64 stripe_len, int mirror_num) + u64 stripe_len, int mirror_num, int hold_bbio) { struct btrfs_raid_bio *rbio; int ret; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); - if (IS_ERR(rbio)) + if (IS_ERR(rbio)) { + __free_bbio_and_raid_map(bbio, raid_map, !hold_bbio); return PTR_ERR(rbio); + } + if (hold_bbio) + set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags); rbio->read_rebuild = 1; bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_iter.bi_size; @@ -2054,8 +2083,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, rbio->faila = find_logical_bio_stripe(rbio, bio); if (rbio->faila == -1) { BUG(); - kfree(raid_map); - kfree(bbio); + __free_bbio_and_raid_map(bbio, raid_map, !hold_bbio); kfree(rbio); return -EIO; } diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h index ea5d73bfdfbe..b310e8c830d1 100644 --- a/fs/btrfs/raid56.h +++ b/fs/btrfs/raid56.h @@ -41,7 +41,7 @@ static inline int nr_data_stripes(struct map_lookup *map) int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, - u64 stripe_len, int mirror_num); + u64 stripe_len, int mirror_num, int hold_bbio); int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, u64 stripe_len); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index efa083113827..ca4b9eb8b5da 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -63,6 +63,13 @@ struct scrub_ctx; */ #define SCRUB_MAX_PAGES_PER_BLOCK 16 /* 64k per node/leaf/sector */ +struct scrub_recover { + atomic_t refs; + struct btrfs_bio *bbio; + u64 *raid_map; + u64 map_length; +}; + struct scrub_page { struct scrub_block *sblock; struct page *page; @@ -79,6 +86,8 @@ struct scrub_page { unsigned int io_error:1; }; u8 csum[BTRFS_CSUM_SIZE]; + + struct scrub_recover *recover; }; struct scrub_bio { @@ -196,7 +205,7 @@ static int scrub_setup_recheck_block(struct scrub_ctx *sctx, static void scrub_recheck_block(struct btrfs_fs_info *fs_info, struct scrub_block *sblock, int is_metadata, int have_csum, u8 *csum, u64 generation, - u16 csum_size); + u16 csum_size, int retry_failed_mirror); static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, struct scrub_block *sblock, int is_metadata, int have_csum, @@ -790,6 +799,20 @@ out: scrub_pending_trans_workers_dec(sctx); } +static inline void scrub_get_recover(struct scrub_recover *recover) +{ + atomic_inc(&recover->refs); +} + +static inline void scrub_put_recover(struct scrub_recover *recover) +{ + if (atomic_dec_and_test(&recover->refs)) { + kfree(recover->bbio); + kfree(recover->raid_map); + kfree(recover); + } +} + /* * scrub_handle_errored_block gets called when either verification of the * pages failed or the bio failed to read, e.g. with EIO. In the latter @@ -906,7 +929,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) /* build and submit the bios for the failed mirror, check checksums */ scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum, - csum, generation, sctx->csum_size); + csum, generation, sctx->csum_size, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) { @@ -1019,7 +1042,7 @@ nodatasum_case: /* build and submit the bios, check checksums */ scrub_recheck_block(fs_info, sblock_other, is_metadata, have_csum, csum, generation, - sctx->csum_size); + sctx->csum_size, 0); if (!sblock_other->header_error && !sblock_other->checksum_error && @@ -1169,7 +1192,7 @@ nodatasum_case: */ scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum, csum, - generation, sctx->csum_size); + generation, sctx->csum_size, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) @@ -1201,11 +1224,18 @@ out: mirror_index++) { struct scrub_block *sblock = sblocks_for_recheck + mirror_index; + struct scrub_recover *recover; int page_index; for (page_index = 0; page_index < sblock->page_count; page_index++) { sblock->pagev[page_index]->sblock = NULL; + recover = sblock->pagev[page_index]->recover; + if (recover) { + scrub_put_recover(recover); + sblock->pagev[page_index]->recover = + NULL; + } scrub_page_put(sblock->pagev[page_index]); } } @@ -1215,14 +1245,63 @@ out: return 0; } +static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio, u64 *raid_map) +{ + if (raid_map) { + if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE) + return 3; + else + return 2; + } else { + return (int)bbio->num_stripes; + } +} + +static inline void scrub_stripe_index_and_offset(u64 logical, u64 *raid_map, + u64 mapped_length, + int nstripes, int mirror, + int *stripe_index, + u64 *stripe_offset) +{ + int i; + + if (raid_map) { + /* RAID5/6 */ + for (i = 0; i < nstripes; i++) { + if (raid_map[i] == RAID6_Q_STRIPE || + raid_map[i] == RAID5_P_STRIPE) + continue; + + if (logical >= raid_map[i] && + logical < raid_map[i] + mapped_length) + break; + } + + *stripe_index = i; + *stripe_offset = logical - raid_map[i]; + } else { + /* The other RAID type */ + *stripe_index = mirror; + *stripe_offset = 0; + } +} + static int scrub_setup_recheck_block(struct scrub_ctx *sctx, struct btrfs_fs_info *fs_info, struct scrub_block *original_sblock, u64 length, u64 logical, struct scrub_block *sblocks_for_recheck) { + struct scrub_recover *recover; + struct btrfs_bio *bbio; + u64 *raid_map; + u64 sublen; + u64 mapped_length; + u64 stripe_offset; + int stripe_index; int page_index; int mirror_index; + int nmirrors; int ret; /* @@ -1233,23 +1312,39 @@ static int scrub_setup_recheck_block(struct scrub_ctx *sctx, page_index = 0; while (length > 0) { - u64 sublen = min_t(u64, length, PAGE_SIZE); - u64 mapped_length = sublen; - struct btrfs_bio *bbio = NULL; + sublen = min_t(u64, length, PAGE_SIZE); + mapped_length = sublen; + bbio = NULL; + raid_map = NULL; /* * with a length of PAGE_SIZE, each returned stripe * represents one mirror */ - ret = btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS, logical, - &mapped_length, &bbio, 0); + ret = btrfs_map_sblock(fs_info, REQ_GET_READ_MIRRORS, logical, + &mapped_length, &bbio, 0, &raid_map); if (ret || !bbio || mapped_length < sublen) { kfree(bbio); + kfree(raid_map); return -EIO; } + recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS); + if (!recover) { + kfree(bbio); + kfree(raid_map); + return -ENOMEM; + } + + atomic_set(&recover->refs, 1); + recover->bbio = bbio; + recover->raid_map = raid_map; + recover->map_length = mapped_length; + BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO); - for (mirror_index = 0; mirror_index < (int)bbio->num_stripes; + + nmirrors = scrub_nr_raid_mirrors(bbio, raid_map); + for (mirror_index = 0; mirror_index < nmirrors; mirror_index++) { struct scrub_block *sblock; struct scrub_page *page; @@ -1265,26 +1360,38 @@ leave_nomem: spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; spin_unlock(&sctx->stat_lock); - kfree(bbio); + scrub_put_recover(recover); return -ENOMEM; } scrub_page_get(page); sblock->pagev[page_index] = page; page->logical = logical; - page->physical = bbio->stripes[mirror_index].physical; + + scrub_stripe_index_and_offset(logical, raid_map, + mapped_length, + bbio->num_stripes, + mirror_index, + &stripe_index, + &stripe_offset); + page->physical = bbio->stripes[stripe_index].physical + + stripe_offset; + page->dev = bbio->stripes[stripe_index].dev; + BUG_ON(page_index >= original_sblock->page_count); page->physical_for_dev_replace = original_sblock->pagev[page_index]-> physical_for_dev_replace; /* for missing devices, dev->bdev is NULL */ - page->dev = bbio->stripes[mirror_index].dev; page->mirror_num = mirror_index + 1; sblock->page_count++; page->page = alloc_page(GFP_NOFS); if (!page->page) goto leave_nomem; + + scrub_get_recover(recover); + page->recover = recover; } - kfree(bbio); + scrub_put_recover(recover); length -= sublen; logical += sublen; page_index++; @@ -1293,6 +1400,51 @@ leave_nomem: return 0; } +struct scrub_bio_ret { + struct completion event; + int error; +}; + +static void scrub_bio_wait_endio(struct bio *bio, int error) +{ + struct scrub_bio_ret *ret = bio->bi_private; + + ret->error = error; + complete(&ret->event); +} + +static inline int scrub_is_page_on_raid56(struct scrub_page *page) +{ + return page->recover && page->recover->raid_map; +} + +static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, + struct bio *bio, + struct scrub_page *page) +{ + struct scrub_bio_ret done; + int ret; + + init_completion(&done.event); + done.error = 0; + bio->bi_iter.bi_sector = page->logical >> 9; + bio->bi_private = &done; + bio->bi_end_io = scrub_bio_wait_endio; + + ret = raid56_parity_recover(fs_info->fs_root, bio, page->recover->bbio, + page->recover->raid_map, + page->recover->map_length, + page->mirror_num, 1); + if (ret) + return ret; + + wait_for_completion(&done.event); + if (done.error) + return -EIO; + + return 0; +} + /* * this function will check the on disk data for checksum errors, header * errors and read I/O errors. If any I/O errors happen, the exact pages @@ -1303,7 +1455,7 @@ leave_nomem: static void scrub_recheck_block(struct btrfs_fs_info *fs_info, struct scrub_block *sblock, int is_metadata, int have_csum, u8 *csum, u64 generation, - u16 csum_size) + u16 csum_size, int retry_failed_mirror) { int page_num; @@ -1329,11 +1481,17 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, continue; } bio->bi_bdev = page->dev->bdev; - bio->bi_iter.bi_sector = page->physical >> 9; bio_add_page(bio, page->page, PAGE_SIZE, 0); - if (btrfsic_submit_bio_wait(READ, bio)) - sblock->no_io_error_seen = 0; + if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) { + if (scrub_submit_raid56_bio_wait(fs_info, bio, page)) + sblock->no_io_error_seen = 0; + } else { + bio->bi_iter.bi_sector = page->physical >> 9; + + if (btrfsic_submit_bio_wait(READ, bio)) + sblock->no_io_error_seen = 0; + } bio_put(bio); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6f5b302a08cf..217c42ea90b0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5161,7 +5161,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, BTRFS_BLOCK_GROUP_RAID6)) { u64 tmp; - if (raid_map_ret && ((rw & REQ_WRITE) || mirror_num > 1)) { + if (raid_map_ret && + ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) || + mirror_num > 1)) { int i, rot; /* push stripe_nr back to the start of the full stripe */ @@ -5440,6 +5442,16 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, mirror_num, NULL); } +/* For Scrub/replace */ +int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw, + u64 logical, u64 *length, + struct btrfs_bio **bbio_ret, int mirror_num, + u64 **raid_map_ret) +{ + return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret, + mirror_num, raid_map_ret); +} + int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, u64 chunk_start, u64 physical, u64 devid, u64 **logical, int *naddrs, int *stripe_len) @@ -5809,7 +5821,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, } else { ret = raid56_parity_recover(root, bio, bbio, raid_map, map_length, - mirror_num); + mirror_num, 0); } /* * FIXME, replace dosen't support raid56 yet, please fix diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 08980fa23039..01094bb804c7 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -393,6 +393,10 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, u64 logical, u64 *length, struct btrfs_bio **bbio_ret, int mirror_num); +int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw, + u64 logical, u64 *length, + struct btrfs_bio **bbio_ret, int mirror_num, + u64 **raid_map_ret); int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, u64 chunk_start, u64 physical, u64 devid, u64 **logical, int *naddrs, int *stripe_len); -- cgit v1.2.3 From 1b94b5567e9c70ad3b24bd5e576a422246875c2a Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 6 Nov 2014 16:14:21 +0800 Subject: Btrfs, raid56: use a variant to record the operation type We will introduce new operation type later, if we still use integer variant as bool variant to record the operation type, we would add new variant and increase the size of raid bio structure. It is not good, by this patch, we define different number for different operation, and we can just use a variant to record the operation type. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 95053a903474..0600bf69199e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -69,6 +69,11 @@ #define RBIO_CACHE_SIZE 1024 +enum btrfs_rbio_ops { + BTRFS_RBIO_WRITE = 0, + BTRFS_RBIO_READ_REBUILD = 1, +}; + struct btrfs_raid_bio { struct btrfs_fs_info *fs_info; struct btrfs_bio *bbio; @@ -131,7 +136,7 @@ struct btrfs_raid_bio { * differently from a parity rebuild as part of * rmw */ - int read_rebuild; + enum btrfs_rbio_ops operation; /* first bad stripe */ int faila; @@ -154,7 +159,6 @@ struct btrfs_raid_bio { atomic_t refs; - atomic_t stripes_pending; atomic_t error; @@ -590,8 +594,7 @@ static int rbio_can_merge(struct btrfs_raid_bio *last, return 0; /* reads can't merge with writes */ - if (last->read_rebuild != - cur->read_rebuild) { + if (last->operation != cur->operation) { return 0; } @@ -784,9 +787,9 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio) spin_unlock(&rbio->bio_list_lock); spin_unlock_irqrestore(&h->lock, flags); - if (next->read_rebuild) + if (next->operation == BTRFS_RBIO_READ_REBUILD) async_read_rebuild(next); - else { + else if (next->operation == BTRFS_RBIO_WRITE){ steal_rbio(rbio, next); async_rmw_stripe(next); } @@ -1720,6 +1723,7 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, } bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_iter.bi_size; + rbio->operation = BTRFS_RBIO_WRITE; /* * don't plug on full rbios, just get them out the door @@ -1768,7 +1772,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) faila = rbio->faila; failb = rbio->failb; - if (rbio->read_rebuild) { + if (rbio->operation == BTRFS_RBIO_READ_REBUILD) { spin_lock_irq(&rbio->bio_list_lock); set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags); spin_unlock_irq(&rbio->bio_list_lock); @@ -1785,7 +1789,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) * if we're rebuilding a read, we have to use * pages from the bio list */ - if (rbio->read_rebuild && + if (rbio->operation == BTRFS_RBIO_READ_REBUILD && (stripe == faila || stripe == failb)) { page = page_in_rbio(rbio, stripe, pagenr, 0); } else { @@ -1878,7 +1882,7 @@ pstripe: * know they can be trusted. If this was a read reconstruction, * other endio functions will fiddle the uptodate bits */ - if (!rbio->read_rebuild) { + if (rbio->operation == BTRFS_RBIO_WRITE) { for (i = 0; i < nr_pages; i++) { if (faila != -1) { page = rbio_stripe_page(rbio, faila, i); @@ -1895,7 +1899,7 @@ pstripe: * if we're rebuilding a read, we have to use * pages from the bio list */ - if (rbio->read_rebuild && + if (rbio->operation == BTRFS_RBIO_READ_REBUILD && (stripe == faila || stripe == failb)) { page = page_in_rbio(rbio, stripe, pagenr, 0); } else { @@ -1910,8 +1914,7 @@ cleanup: kfree(pointers); cleanup_io: - - if (rbio->read_rebuild) { + if (rbio->operation == BTRFS_RBIO_READ_REBUILD) { if (err == 0 && !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags)) cache_rbio_pages(rbio); @@ -2050,7 +2053,7 @@ out: return 0; cleanup: - if (rbio->read_rebuild) + if (rbio->operation == BTRFS_RBIO_READ_REBUILD) rbio_orig_end_io(rbio, -EIO, 0); return -EIO; } @@ -2076,7 +2079,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, if (hold_bbio) set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags); - rbio->read_rebuild = 1; + rbio->operation = BTRFS_RBIO_READ_REBUILD; bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_iter.bi_size; -- cgit v1.2.3 From 5a6ac9eacb49143cbad3bbfda72263101cb1f3df Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 6 Nov 2014 17:20:58 +0800 Subject: Btrfs, raid56: support parity scrub on raid56 The implementation is: - Read and check all the data with checksum in the same stripe. All the data which has checksum is COW data, and we are sure that it is not changed though we don't lock the stripe. because the space of that data just can be reclaimed after the current transction is committed, and then the fs can use it to store the other data, but when doing scrub, we hold the current transaction, that is that data can not be recovered, it is safe that read and check it out of the stripe lock. - Lock the stripe - Read out all the data without checksum and parity The data without checksum and the parity may be changed if we don't lock the stripe, so we need read it in the stripe lock context. - Check the parity - Re-calculate the new parity and write back it if the old parity is not right - Unlock the stripe If we can not read out the data or the data we read is corrupted, we will try to repair it. If the repair fails. we will mark the horizontal sub-stripe(pages on the same horizontal) as corrupted sub-stripe, and we will skip the parity check and repair of that horizontal sub-stripe. And in order to skip the horizontal sub-stripe that has no data, we introduce a bitmap. If there is some data on the horizontal sub-stripe, we will the relative bit to 1, and when we check and repair the parity, we will skip those horizontal sub-stripes that the relative bits is 0. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 514 ++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/raid56.h | 12 ++ fs/btrfs/scrub.c | 609 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 1115 insertions(+), 20 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0600bf69199e..b85d68f721b8 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -72,6 +72,7 @@ enum btrfs_rbio_ops { BTRFS_RBIO_WRITE = 0, BTRFS_RBIO_READ_REBUILD = 1, + BTRFS_RBIO_PARITY_SCRUB = 2, }; struct btrfs_raid_bio { @@ -130,6 +131,7 @@ struct btrfs_raid_bio { /* number of data stripes (no p/q) */ int nr_data; + int stripe_npages; /* * set if we're doing a parity rebuild * for a read from higher up, which is handled @@ -144,6 +146,7 @@ struct btrfs_raid_bio { /* second bad stripe (for raid6 use) */ int failb; + int scrubp; /* * number of pages needed to represent the full * stripe @@ -178,6 +181,11 @@ struct btrfs_raid_bio { * here for faster lookup */ struct page **bio_pages; + + /* + * bitmap to record which horizontal stripe has data + */ + unsigned long *dbitmap; }; static int __raid56_parity_recover(struct btrfs_raid_bio *rbio); @@ -192,6 +200,10 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio); static void index_rbio_pages(struct btrfs_raid_bio *rbio); static int alloc_rbio_pages(struct btrfs_raid_bio *rbio); +static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, + int need_check); +static void async_scrub_parity(struct btrfs_raid_bio *rbio); + /* * the stripe hash table is used for locking, and to collect * bios in hopes of making a full stripe @@ -593,10 +605,20 @@ static int rbio_can_merge(struct btrfs_raid_bio *last, cur->raid_map[0]) return 0; - /* reads can't merge with writes */ - if (last->operation != cur->operation) { + /* we can't merge with different operations */ + if (last->operation != cur->operation) + return 0; + /* + * We've need read the full stripe from the drive. + * check and repair the parity and write the new results. + * + * We're not allowed to add any new bios to the + * bio list here, anyone else that wants to + * change this stripe needs to do their own rmw. + */ + if (last->operation == BTRFS_RBIO_PARITY_SCRUB || + cur->operation == BTRFS_RBIO_PARITY_SCRUB) return 0; - } return 1; } @@ -789,9 +811,12 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio) if (next->operation == BTRFS_RBIO_READ_REBUILD) async_read_rebuild(next); - else if (next->operation == BTRFS_RBIO_WRITE){ + else if (next->operation == BTRFS_RBIO_WRITE) { steal_rbio(rbio, next); async_rmw_stripe(next); + } else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) { + steal_rbio(rbio, next); + async_scrub_parity(next); } goto done_nolock; @@ -957,9 +982,11 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, struct btrfs_raid_bio *rbio; int nr_data = 0; int num_pages = rbio_nr_pages(stripe_len, bbio->num_stripes); + int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE); void *p; - rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2, + rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 + + DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8), GFP_NOFS); if (!rbio) return ERR_PTR(-ENOMEM); @@ -974,6 +1001,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, rbio->fs_info = root->fs_info; rbio->stripe_len = stripe_len; rbio->nr_pages = num_pages; + rbio->stripe_npages = stripe_npages; rbio->faila = -1; rbio->failb = -1; atomic_set(&rbio->refs, 1); @@ -987,6 +1015,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, p = rbio + 1; rbio->stripe_pages = p; rbio->bio_pages = p + sizeof(struct page *) * num_pages; + rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2; if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE) nr_data = bbio->num_stripes - 2; @@ -1781,6 +1810,14 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) index_rbio_pages(rbio); for (pagenr = 0; pagenr < nr_pages; pagenr++) { + /* + * Now we just use bitmap to mark the horizontal stripes in + * which we have data when doing parity scrub. + */ + if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB && + !test_bit(pagenr, rbio->dbitmap)) + continue; + /* setup our array of pointers with pages * from each stripe */ @@ -1925,7 +1962,13 @@ cleanup_io: } else if (err == 0) { rbio->faila = -1; rbio->failb = -1; - finish_rmw(rbio); + + if (rbio->operation == BTRFS_RBIO_WRITE) + finish_rmw(rbio); + else if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) + finish_parity_scrub(rbio, 0); + else + BUG(); } else { rbio_orig_end_io(rbio, err, 0); } @@ -2133,3 +2176,462 @@ static void read_rebuild_work(struct btrfs_work *work) rbio = container_of(work, struct btrfs_raid_bio, work); __raid56_parity_recover(rbio); } + +/* + * The following code is used to scrub/replace the parity stripe + * + * Note: We need make sure all the pages that add into the scrub/replace + * raid bio are correct and not be changed during the scrub/replace. That + * is those pages just hold metadata or file data with checksum. + */ + +struct btrfs_raid_bio * +raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio, + struct btrfs_bio *bbio, u64 *raid_map, + u64 stripe_len, struct btrfs_device *scrub_dev, + unsigned long *dbitmap, int stripe_nsectors) +{ + struct btrfs_raid_bio *rbio; + int i; + + rbio = alloc_rbio(root, bbio, raid_map, stripe_len); + if (IS_ERR(rbio)) + return NULL; + bio_list_add(&rbio->bio_list, bio); + /* + * This is a special bio which is used to hold the completion handler + * and make the scrub rbio is similar to the other types + */ + ASSERT(!bio->bi_iter.bi_size); + rbio->operation = BTRFS_RBIO_PARITY_SCRUB; + + for (i = 0; i < bbio->num_stripes; i++) { + if (bbio->stripes[i].dev == scrub_dev) { + rbio->scrubp = i; + break; + } + } + + /* Now we just support the sectorsize equals to page size */ + ASSERT(root->sectorsize == PAGE_SIZE); + ASSERT(rbio->stripe_npages == stripe_nsectors); + bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors); + + return rbio; +} + +void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio, + struct page *page, u64 logical) +{ + int stripe_offset; + int index; + + ASSERT(logical >= rbio->raid_map[0]); + ASSERT(logical + PAGE_SIZE <= rbio->raid_map[0] + + rbio->stripe_len * rbio->nr_data); + stripe_offset = (int)(logical - rbio->raid_map[0]); + index = stripe_offset >> PAGE_CACHE_SHIFT; + rbio->bio_pages[index] = page; +} + +/* + * We just scrub the parity that we have correct data on the same horizontal, + * so we needn't allocate all pages for all the stripes. + */ +static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) +{ + int i; + int bit; + int index; + struct page *page; + + for_each_set_bit(bit, rbio->dbitmap, rbio->stripe_npages) { + for (i = 0; i < rbio->bbio->num_stripes; i++) { + index = i * rbio->stripe_npages + bit; + if (rbio->stripe_pages[index]) + continue; + + page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (!page) + return -ENOMEM; + rbio->stripe_pages[index] = page; + ClearPageUptodate(page); + } + } + return 0; +} + +/* + * end io function used by finish_rmw. When we finally + * get here, we've written a full stripe + */ +static void raid_write_parity_end_io(struct bio *bio, int err) +{ + struct btrfs_raid_bio *rbio = bio->bi_private; + + if (err) + fail_bio_stripe(rbio, bio); + + bio_put(bio); + + if (!atomic_dec_and_test(&rbio->stripes_pending)) + return; + + err = 0; + + if (atomic_read(&rbio->error)) + err = -EIO; + + rbio_orig_end_io(rbio, err, 0); +} + +static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, + int need_check) +{ + struct btrfs_bio *bbio = rbio->bbio; + void *pointers[bbio->num_stripes]; + int nr_data = rbio->nr_data; + int stripe; + int pagenr; + int p_stripe = -1; + int q_stripe = -1; + struct page *p_page = NULL; + struct page *q_page = NULL; + struct bio_list bio_list; + struct bio *bio; + int ret; + + bio_list_init(&bio_list); + + if (bbio->num_stripes - rbio->nr_data == 1) { + p_stripe = bbio->num_stripes - 1; + } else if (bbio->num_stripes - rbio->nr_data == 2) { + p_stripe = bbio->num_stripes - 2; + q_stripe = bbio->num_stripes - 1; + } else { + BUG(); + } + + /* + * Because the higher layers(scrubber) are unlikely to + * use this area of the disk again soon, so don't cache + * it. + */ + clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); + + if (!need_check) + goto writeback; + + p_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (!p_page) + goto cleanup; + SetPageUptodate(p_page); + + if (q_stripe != -1) { + q_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (!q_page) { + __free_page(p_page); + goto cleanup; + } + SetPageUptodate(q_page); + } + + atomic_set(&rbio->error, 0); + + for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { + struct page *p; + void *parity; + /* first collect one page from each data stripe */ + for (stripe = 0; stripe < nr_data; stripe++) { + p = page_in_rbio(rbio, stripe, pagenr, 0); + pointers[stripe] = kmap(p); + } + + /* then add the parity stripe */ + pointers[stripe++] = kmap(p_page); + + if (q_stripe != -1) { + + /* + * raid6, add the qstripe and call the + * library function to fill in our p/q + */ + pointers[stripe++] = kmap(q_page); + + raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE, + pointers); + } else { + /* raid5 */ + memcpy(pointers[nr_data], pointers[0], PAGE_SIZE); + run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE); + } + + /* Check scrubbing pairty and repair it */ + p = rbio_stripe_page(rbio, rbio->scrubp, pagenr); + parity = kmap(p); + if (memcmp(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE)) + memcpy(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE); + else + /* Parity is right, needn't writeback */ + bitmap_clear(rbio->dbitmap, pagenr, 1); + kunmap(p); + + for (stripe = 0; stripe < bbio->num_stripes; stripe++) + kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); + } + + __free_page(p_page); + if (q_page) + __free_page(q_page); + +writeback: + /* + * time to start writing. Make bios for everything from the + * higher layers (the bio_list in our rbio) and our p/q. Ignore + * everything else. + */ + for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { + struct page *page; + + page = rbio_stripe_page(rbio, rbio->scrubp, pagenr); + ret = rbio_add_io_page(rbio, &bio_list, + page, rbio->scrubp, pagenr, rbio->stripe_len); + if (ret) + goto cleanup; + } + + nr_data = bio_list_size(&bio_list); + if (!nr_data) { + /* Every parity is right */ + rbio_orig_end_io(rbio, 0, 0); + return; + } + + atomic_set(&rbio->stripes_pending, nr_data); + + while (1) { + bio = bio_list_pop(&bio_list); + if (!bio) + break; + + bio->bi_private = rbio; + bio->bi_end_io = raid_write_parity_end_io; + BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); + submit_bio(WRITE, bio); + } + return; + +cleanup: + rbio_orig_end_io(rbio, -EIO, 0); +} + +static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe) +{ + if (stripe >= 0 && stripe < rbio->nr_data) + return 1; + return 0; +} + +/* + * While we're doing the parity check and repair, we could have errors + * in reading pages off the disk. This checks for errors and if we're + * not able to read the page it'll trigger parity reconstruction. The + * parity scrub will be finished after we've reconstructed the failed + * stripes + */ +static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio) +{ + if (atomic_read(&rbio->error) > rbio->bbio->max_errors) + goto cleanup; + + if (rbio->faila >= 0 || rbio->failb >= 0) { + int dfail = 0, failp = -1; + + if (is_data_stripe(rbio, rbio->faila)) + dfail++; + else if (is_parity_stripe(rbio->faila)) + failp = rbio->faila; + + if (is_data_stripe(rbio, rbio->failb)) + dfail++; + else if (is_parity_stripe(rbio->failb)) + failp = rbio->failb; + + /* + * Because we can not use a scrubbing parity to repair + * the data, so the capability of the repair is declined. + * (In the case of RAID5, we can not repair anything) + */ + if (dfail > rbio->bbio->max_errors - 1) + goto cleanup; + + /* + * If all data is good, only parity is correctly, just + * repair the parity. + */ + if (dfail == 0) { + finish_parity_scrub(rbio, 0); + return; + } + + /* + * Here means we got one corrupted data stripe and one + * corrupted parity on RAID6, if the corrupted parity + * is scrubbing parity, luckly, use the other one to repair + * the data, or we can not repair the data stripe. + */ + if (failp != rbio->scrubp) + goto cleanup; + + __raid_recover_end_io(rbio); + } else { + finish_parity_scrub(rbio, 1); + } + return; + +cleanup: + rbio_orig_end_io(rbio, -EIO, 0); +} + +/* + * end io for the read phase of the rmw cycle. All the bios here are physical + * stripe bios we've read from the disk so we can recalculate the parity of the + * stripe. + * + * This will usually kick off finish_rmw once all the bios are read in, but it + * may trigger parity reconstruction if we had any errors along the way + */ +static void raid56_parity_scrub_end_io(struct bio *bio, int err) +{ + struct btrfs_raid_bio *rbio = bio->bi_private; + + if (err) + fail_bio_stripe(rbio, bio); + else + set_bio_pages_uptodate(bio); + + bio_put(bio); + + if (!atomic_dec_and_test(&rbio->stripes_pending)) + return; + + /* + * this will normally call finish_rmw to start our write + * but if there are any failed stripes we'll reconstruct + * from parity first + */ + validate_rbio_for_parity_scrub(rbio); +} + +static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) +{ + int bios_to_read = 0; + struct btrfs_bio *bbio = rbio->bbio; + struct bio_list bio_list; + int ret; + int pagenr; + int stripe; + struct bio *bio; + + ret = alloc_rbio_essential_pages(rbio); + if (ret) + goto cleanup; + + bio_list_init(&bio_list); + + atomic_set(&rbio->error, 0); + /* + * build a list of bios to read all the missing parts of this + * stripe + */ + for (stripe = 0; stripe < bbio->num_stripes; stripe++) { + for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { + struct page *page; + /* + * we want to find all the pages missing from + * the rbio and read them from the disk. If + * page_in_rbio finds a page in the bio list + * we don't need to read it off the stripe. + */ + page = page_in_rbio(rbio, stripe, pagenr, 1); + if (page) + continue; + + page = rbio_stripe_page(rbio, stripe, pagenr); + /* + * the bio cache may have handed us an uptodate + * page. If so, be happy and use it + */ + if (PageUptodate(page)) + continue; + + ret = rbio_add_io_page(rbio, &bio_list, page, + stripe, pagenr, rbio->stripe_len); + if (ret) + goto cleanup; + } + } + + bios_to_read = bio_list_size(&bio_list); + if (!bios_to_read) { + /* + * this can happen if others have merged with + * us, it means there is nothing left to read. + * But if there are missing devices it may not be + * safe to do the full stripe write yet. + */ + goto finish; + } + + /* + * the bbio may be freed once we submit the last bio. Make sure + * not to touch it after that + */ + atomic_set(&rbio->stripes_pending, bios_to_read); + while (1) { + bio = bio_list_pop(&bio_list); + if (!bio) + break; + + bio->bi_private = rbio; + bio->bi_end_io = raid56_parity_scrub_end_io; + + btrfs_bio_wq_end_io(rbio->fs_info, bio, + BTRFS_WQ_ENDIO_RAID56); + + BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); + submit_bio(READ, bio); + } + /* the actual write will happen once the reads are done */ + return; + +cleanup: + rbio_orig_end_io(rbio, -EIO, 0); + return; + +finish: + validate_rbio_for_parity_scrub(rbio); +} + +static void scrub_parity_work(struct btrfs_work *work) +{ + struct btrfs_raid_bio *rbio; + + rbio = container_of(work, struct btrfs_raid_bio, work); + raid56_parity_scrub_stripe(rbio); +} + +static void async_scrub_parity(struct btrfs_raid_bio *rbio) +{ + btrfs_init_work(&rbio->work, btrfs_rmw_helper, + scrub_parity_work, NULL, NULL); + + btrfs_queue_work(rbio->fs_info->rmw_workers, + &rbio->work); +} + +void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio) +{ + if (!lock_stripe_add(rbio)) + async_scrub_parity(rbio); +} diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h index b310e8c830d1..3d4ddb3d861d 100644 --- a/fs/btrfs/raid56.h +++ b/fs/btrfs/raid56.h @@ -39,6 +39,9 @@ static inline int nr_data_stripes(struct map_lookup *map) #define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \ ((x) == RAID6_Q_STRIPE)) +struct btrfs_raid_bio; +struct btrfs_device; + int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, u64 stripe_len, int mirror_num, int hold_bbio); @@ -46,6 +49,15 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, u64 stripe_len); +struct btrfs_raid_bio * +raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio, + struct btrfs_bio *bbio, u64 *raid_map, + u64 stripe_len, struct btrfs_device *scrub_dev, + unsigned long *dbitmap, int stripe_nsectors); +void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio, + struct page *page, u64 logical); +void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio); + int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info); void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info); #endif diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ca4b9eb8b5da..7f95afcf9fd3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -74,6 +74,7 @@ struct scrub_page { struct scrub_block *sblock; struct page *page; struct btrfs_device *dev; + struct list_head list; u64 flags; /* extent flags */ u64 generation; u64 logical; @@ -114,14 +115,52 @@ struct scrub_block { atomic_t outstanding_pages; atomic_t ref_count; /* free mem on transition to zero */ struct scrub_ctx *sctx; + struct scrub_parity *sparity; struct { unsigned int header_error:1; unsigned int checksum_error:1; unsigned int no_io_error_seen:1; unsigned int generation_error:1; /* also sets header_error */ + + /* The following is for the data used to check parity */ + /* It is for the data with checksum */ + unsigned int data_corrected:1; }; }; +/* Used for the chunks with parity stripe such RAID5/6 */ +struct scrub_parity { + struct scrub_ctx *sctx; + + struct btrfs_device *scrub_dev; + + u64 logic_start; + + u64 logic_end; + + int nsectors; + + int stripe_len; + + atomic_t ref_count; + + struct list_head spages; + + /* Work of parity check and repair */ + struct btrfs_work work; + + /* Mark the parity blocks which have data */ + unsigned long *dbitmap; + + /* + * Mark the parity blocks which have data, but errors happen when + * read data or check data + */ + unsigned long *ebitmap; + + unsigned long bitmap[0]; +}; + struct scrub_wr_ctx { struct scrub_bio *wr_curr_bio; struct btrfs_device *tgtdev; @@ -227,6 +266,8 @@ static void scrub_block_get(struct scrub_block *sblock); static void scrub_block_put(struct scrub_block *sblock); static void scrub_page_get(struct scrub_page *spage); static void scrub_page_put(struct scrub_page *spage); +static void scrub_parity_get(struct scrub_parity *sparity); +static void scrub_parity_put(struct scrub_parity *sparity); static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx, struct scrub_page *spage); static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len, @@ -943,6 +984,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) */ spin_lock(&sctx->stat_lock); sctx->stat.unverified_errors++; + sblock_to_check->data_corrected = 1; spin_unlock(&sctx->stat_lock); if (sctx->is_dev_replace) @@ -1203,6 +1245,7 @@ nodatasum_case: corrected_error: spin_lock(&sctx->stat_lock); sctx->stat.corrected_errors++; + sblock_to_check->data_corrected = 1; spin_unlock(&sctx->stat_lock); printk_ratelimited_in_rcu(KERN_ERR "BTRFS: fixed up error at logical %llu on dev %s\n", @@ -1644,6 +1687,13 @@ static void scrub_write_block_to_dev_replace(struct scrub_block *sblock) { int page_num; + /* + * This block is used for the check of the parity on the source device, + * so the data needn't be written into the destination device. + */ + if (sblock->sparity) + return; + for (page_num = 0; page_num < sblock->page_count; page_num++) { int ret; @@ -2025,6 +2075,9 @@ static void scrub_block_put(struct scrub_block *sblock) if (atomic_dec_and_test(&sblock->ref_count)) { int i; + if (sblock->sparity) + scrub_parity_put(sblock->sparity); + for (i = 0; i < sblock->page_count; i++) scrub_page_put(sblock->pagev[i]); kfree(sblock); @@ -2282,9 +2335,51 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) scrub_pending_bio_dec(sctx); } +static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, + unsigned long *bitmap, + u64 start, u64 len) +{ + int offset; + int nsectors; + int sectorsize = sparity->sctx->dev_root->sectorsize; + + if (len >= sparity->stripe_len) { + bitmap_set(bitmap, 0, sparity->nsectors); + return; + } + + start -= sparity->logic_start; + offset = (int)do_div(start, sparity->stripe_len); + offset /= sectorsize; + nsectors = (int)len / sectorsize; + + if (offset + nsectors <= sparity->nsectors) { + bitmap_set(bitmap, offset, nsectors); + return; + } + + bitmap_set(bitmap, offset, sparity->nsectors - offset); + bitmap_set(bitmap, 0, nsectors - (sparity->nsectors - offset)); +} + +static inline void scrub_parity_mark_sectors_error(struct scrub_parity *sparity, + u64 start, u64 len) +{ + __scrub_mark_bitmap(sparity, sparity->ebitmap, start, len); +} + +static inline void scrub_parity_mark_sectors_data(struct scrub_parity *sparity, + u64 start, u64 len) +{ + __scrub_mark_bitmap(sparity, sparity->dbitmap, start, len); +} + static void scrub_block_complete(struct scrub_block *sblock) { + int corrupted = 0; + if (!sblock->no_io_error_seen) { + corrupted = 1; scrub_handle_errored_block(sblock); } else { /* @@ -2292,9 +2387,19 @@ static void scrub_block_complete(struct scrub_block *sblock) * dev replace case, otherwise write here in dev replace * case. */ - if (!scrub_checksum(sblock) && sblock->sctx->is_dev_replace) + corrupted = scrub_checksum(sblock); + if (!corrupted && sblock->sctx->is_dev_replace) scrub_write_block_to_dev_replace(sblock); } + + if (sblock->sparity && corrupted && !sblock->data_corrected) { + u64 start = sblock->pagev[0]->logical; + u64 end = sblock->pagev[sblock->page_count - 1]->logical + + PAGE_SIZE; + + scrub_parity_mark_sectors_error(sblock->sparity, + start, end - start); + } } static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len, @@ -2386,6 +2491,132 @@ behind_scrub_pages: return 0; } +static int scrub_pages_for_parity(struct scrub_parity *sparity, + u64 logical, u64 len, + u64 physical, struct btrfs_device *dev, + u64 flags, u64 gen, int mirror_num, u8 *csum) +{ + struct scrub_ctx *sctx = sparity->sctx; + struct scrub_block *sblock; + int index; + + sblock = kzalloc(sizeof(*sblock), GFP_NOFS); + if (!sblock) { + spin_lock(&sctx->stat_lock); + sctx->stat.malloc_errors++; + spin_unlock(&sctx->stat_lock); + return -ENOMEM; + } + + /* one ref inside this function, plus one for each page added to + * a bio later on */ + atomic_set(&sblock->ref_count, 1); + sblock->sctx = sctx; + sblock->no_io_error_seen = 1; + sblock->sparity = sparity; + scrub_parity_get(sparity); + + for (index = 0; len > 0; index++) { + struct scrub_page *spage; + u64 l = min_t(u64, len, PAGE_SIZE); + + spage = kzalloc(sizeof(*spage), GFP_NOFS); + if (!spage) { +leave_nomem: + spin_lock(&sctx->stat_lock); + sctx->stat.malloc_errors++; + spin_unlock(&sctx->stat_lock); + scrub_block_put(sblock); + return -ENOMEM; + } + BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK); + /* For scrub block */ + scrub_page_get(spage); + sblock->pagev[index] = spage; + /* For scrub parity */ + scrub_page_get(spage); + list_add_tail(&spage->list, &sparity->spages); + spage->sblock = sblock; + spage->dev = dev; + spage->flags = flags; + spage->generation = gen; + spage->logical = logical; + spage->physical = physical; + spage->mirror_num = mirror_num; + if (csum) { + spage->have_csum = 1; + memcpy(spage->csum, csum, sctx->csum_size); + } else { + spage->have_csum = 0; + } + sblock->page_count++; + spage->page = alloc_page(GFP_NOFS); + if (!spage->page) + goto leave_nomem; + len -= l; + logical += l; + physical += l; + } + + WARN_ON(sblock->page_count == 0); + for (index = 0; index < sblock->page_count; index++) { + struct scrub_page *spage = sblock->pagev[index]; + int ret; + + ret = scrub_add_page_to_rd_bio(sctx, spage); + if (ret) { + scrub_block_put(sblock); + return ret; + } + } + + /* last one frees, either here or in bio completion for last page */ + scrub_block_put(sblock); + return 0; +} + +static int scrub_extent_for_parity(struct scrub_parity *sparity, + u64 logical, u64 len, + u64 physical, struct btrfs_device *dev, + u64 flags, u64 gen, int mirror_num) +{ + struct scrub_ctx *sctx = sparity->sctx; + int ret; + u8 csum[BTRFS_CSUM_SIZE]; + u32 blocksize; + + if (flags & BTRFS_EXTENT_FLAG_DATA) { + blocksize = sctx->sectorsize; + } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { + blocksize = sctx->nodesize; + } else { + blocksize = sctx->sectorsize; + WARN_ON(1); + } + + while (len) { + u64 l = min_t(u64, len, blocksize); + int have_csum = 0; + + if (flags & BTRFS_EXTENT_FLAG_DATA) { + /* push csums to sbio */ + have_csum = scrub_find_csum(sctx, logical, l, csum); + if (have_csum == 0) + goto skip; + } + ret = scrub_pages_for_parity(sparity, logical, l, physical, dev, + flags, gen, mirror_num, + have_csum ? csum : NULL); +skip: + if (ret) + return ret; + len -= l; + logical += l; + physical += l; + } + return 0; +} + /* * Given a physical address, this will calculate it's * logical offset. if this is a parity stripe, it will return @@ -2394,7 +2625,8 @@ behind_scrub_pages: * return 0 if it is a data stripe, 1 means parity stripe. */ static int get_raid56_logic_offset(u64 physical, int num, - struct map_lookup *map, u64 *offset) + struct map_lookup *map, u64 *offset, + u64 *stripe_start) { int i; int j = 0; @@ -2405,6 +2637,9 @@ static int get_raid56_logic_offset(u64 physical, int num, last_offset = (physical - map->stripes[num].physical) * nr_data_stripes(map); + if (stripe_start) + *stripe_start = last_offset; + *offset = last_offset; for (i = 0; i < nr_data_stripes(map); i++) { *offset = last_offset + i * map->stripe_len; @@ -2427,13 +2662,330 @@ static int get_raid56_logic_offset(u64 physical, int num, return 1; } +static void scrub_free_parity(struct scrub_parity *sparity) +{ + struct scrub_ctx *sctx = sparity->sctx; + struct scrub_page *curr, *next; + int nbits; + + nbits = bitmap_weight(sparity->ebitmap, sparity->nsectors); + if (nbits) { + spin_lock(&sctx->stat_lock); + sctx->stat.read_errors += nbits; + sctx->stat.uncorrectable_errors += nbits; + spin_unlock(&sctx->stat_lock); + } + + list_for_each_entry_safe(curr, next, &sparity->spages, list) { + list_del_init(&curr->list); + scrub_page_put(curr); + } + + kfree(sparity); +} + +static void scrub_parity_bio_endio(struct bio *bio, int error) +{ + struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private; + struct scrub_ctx *sctx = sparity->sctx; + + if (error) + bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap, + sparity->nsectors); + + scrub_free_parity(sparity); + scrub_pending_bio_dec(sctx); + bio_put(bio); +} + +static void scrub_parity_check_and_repair(struct scrub_parity *sparity) +{ + struct scrub_ctx *sctx = sparity->sctx; + struct bio *bio; + struct btrfs_raid_bio *rbio; + struct scrub_page *spage; + struct btrfs_bio *bbio = NULL; + u64 *raid_map = NULL; + u64 length; + int ret; + + if (!bitmap_andnot(sparity->dbitmap, sparity->dbitmap, sparity->ebitmap, + sparity->nsectors)) + goto out; + + length = sparity->logic_end - sparity->logic_start + 1; + ret = btrfs_map_sblock(sctx->dev_root->fs_info, REQ_GET_READ_MIRRORS, + sparity->logic_start, + &length, &bbio, 0, &raid_map); + if (ret || !bbio || !raid_map) + goto bbio_out; + + bio = btrfs_io_bio_alloc(GFP_NOFS, 0); + if (!bio) + goto bbio_out; + + bio->bi_iter.bi_sector = sparity->logic_start >> 9; + bio->bi_private = sparity; + bio->bi_end_io = scrub_parity_bio_endio; + + rbio = raid56_parity_alloc_scrub_rbio(sctx->dev_root, bio, bbio, + raid_map, length, + sparity->scrub_dev, + sparity->dbitmap, + sparity->nsectors); + if (!rbio) + goto rbio_out; + + list_for_each_entry(spage, &sparity->spages, list) + raid56_parity_add_scrub_pages(rbio, spage->page, + spage->logical); + + scrub_pending_bio_inc(sctx); + raid56_parity_submit_scrub_rbio(rbio); + return; + +rbio_out: + bio_put(bio); +bbio_out: + kfree(bbio); + kfree(raid_map); + bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap, + sparity->nsectors); + spin_lock(&sctx->stat_lock); + sctx->stat.malloc_errors++; + spin_unlock(&sctx->stat_lock); +out: + scrub_free_parity(sparity); +} + +static inline int scrub_calc_parity_bitmap_len(int nsectors) +{ + return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8); +} + +static void scrub_parity_get(struct scrub_parity *sparity) +{ + atomic_inc(&sparity->ref_count); +} + +static void scrub_parity_put(struct scrub_parity *sparity) +{ + if (!atomic_dec_and_test(&sparity->ref_count)) + return; + + scrub_parity_check_and_repair(sparity); +} + +static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, + struct map_lookup *map, + struct btrfs_device *sdev, + struct btrfs_path *path, + u64 logic_start, + u64 logic_end) +{ + struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; + struct btrfs_root *root = fs_info->extent_root; + struct btrfs_root *csum_root = fs_info->csum_root; + struct btrfs_extent_item *extent; + u64 flags; + int ret; + int slot; + struct extent_buffer *l; + struct btrfs_key key; + u64 generation; + u64 extent_logical; + u64 extent_physical; + u64 extent_len; + struct btrfs_device *extent_dev; + struct scrub_parity *sparity; + int nsectors; + int bitmap_len; + int extent_mirror_num; + int stop_loop = 0; + + nsectors = map->stripe_len / root->sectorsize; + bitmap_len = scrub_calc_parity_bitmap_len(nsectors); + sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len, + GFP_NOFS); + if (!sparity) { + spin_lock(&sctx->stat_lock); + sctx->stat.malloc_errors++; + spin_unlock(&sctx->stat_lock); + return -ENOMEM; + } + + sparity->stripe_len = map->stripe_len; + sparity->nsectors = nsectors; + sparity->sctx = sctx; + sparity->scrub_dev = sdev; + sparity->logic_start = logic_start; + sparity->logic_end = logic_end; + atomic_set(&sparity->ref_count, 1); + INIT_LIST_HEAD(&sparity->spages); + sparity->dbitmap = sparity->bitmap; + sparity->ebitmap = (void *)sparity->bitmap + bitmap_len; + + ret = 0; + while (logic_start < logic_end) { + if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) + key.type = BTRFS_METADATA_ITEM_KEY; + else + key.type = BTRFS_EXTENT_ITEM_KEY; + key.objectid = logic_start; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + if (ret > 0) { + ret = btrfs_previous_extent_item(root, path, 0); + if (ret < 0) + goto out; + if (ret > 0) { + btrfs_release_path(path); + ret = btrfs_search_slot(NULL, root, &key, + path, 0, 0); + if (ret < 0) + goto out; + } + } + + stop_loop = 0; + while (1) { + u64 bytes; + + l = path->nodes[0]; + slot = path->slots[0]; + if (slot >= btrfs_header_nritems(l)) { + ret = btrfs_next_leaf(root, path); + if (ret == 0) + continue; + if (ret < 0) + goto out; + + stop_loop = 1; + break; + } + btrfs_item_key_to_cpu(l, &key, slot); + + if (key.type == BTRFS_METADATA_ITEM_KEY) + bytes = root->nodesize; + else + bytes = key.offset; + + if (key.objectid + bytes <= logic_start) + goto next; + + if (key.type != BTRFS_EXTENT_ITEM_KEY && + key.type != BTRFS_METADATA_ITEM_KEY) + goto next; + + if (key.objectid > logic_end) { + stop_loop = 1; + break; + } + + while (key.objectid >= logic_start + map->stripe_len) + logic_start += map->stripe_len; + + extent = btrfs_item_ptr(l, slot, + struct btrfs_extent_item); + flags = btrfs_extent_flags(l, extent); + generation = btrfs_extent_generation(l, extent); + + if (key.objectid < logic_start && + (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) { + btrfs_err(fs_info, + "scrub: tree block %llu spanning stripes, ignored. logical=%llu", + key.objectid, logic_start); + goto next; + } +again: + extent_logical = key.objectid; + extent_len = bytes; + + if (extent_logical < logic_start) { + extent_len -= logic_start - extent_logical; + extent_logical = logic_start; + } + + if (extent_logical + extent_len > + logic_start + map->stripe_len) + extent_len = logic_start + map->stripe_len - + extent_logical; + + scrub_parity_mark_sectors_data(sparity, extent_logical, + extent_len); + + scrub_remap_extent(fs_info, extent_logical, + extent_len, &extent_physical, + &extent_dev, + &extent_mirror_num); + + ret = btrfs_lookup_csums_range(csum_root, + extent_logical, + extent_logical + extent_len - 1, + &sctx->csum_list, 1); + if (ret) + goto out; + + ret = scrub_extent_for_parity(sparity, extent_logical, + extent_len, + extent_physical, + extent_dev, flags, + generation, + extent_mirror_num); + if (ret) + goto out; + + scrub_free_csums(sctx); + if (extent_logical + extent_len < + key.objectid + bytes) { + logic_start += map->stripe_len; + + if (logic_start >= logic_end) { + stop_loop = 1; + break; + } + + if (logic_start < key.objectid + bytes) { + cond_resched(); + goto again; + } + } +next: + path->slots[0]++; + } + + btrfs_release_path(path); + + if (stop_loop) + break; + + logic_start += map->stripe_len; + } +out: + if (ret < 0) + scrub_parity_mark_sectors_error(sparity, logic_start, + logic_end - logic_start + 1); + scrub_parity_put(sparity); + scrub_submit(sctx); + mutex_lock(&sctx->wr_ctx.wr_lock); + scrub_wr_submit(sctx); + mutex_unlock(&sctx->wr_ctx.wr_lock); + + btrfs_release_path(path); + return ret < 0 ? ret : 0; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, int num, u64 base, u64 length, int is_dev_replace) { - struct btrfs_path *path; + struct btrfs_path *path, *ppath; struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; struct btrfs_root *root = fs_info->extent_root; struct btrfs_root *csum_root = fs_info->csum_root; @@ -2460,6 +3012,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, u64 extent_logical; u64 extent_physical; u64 extent_len; + u64 stripe_logical; + u64 stripe_end; struct btrfs_device *extent_dev; int extent_mirror_num; int stop_loop = 0; @@ -2485,7 +3039,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, mirror_num = num % map->num_stripes + 1; } else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) { - get_raid56_logic_offset(physical, num, map, &offset); + get_raid56_logic_offset(physical, num, map, &offset, NULL); increment = map->stripe_len * nr_data_stripes(map); mirror_num = 1; } else { @@ -2497,6 +3051,12 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, if (!path) return -ENOMEM; + ppath = btrfs_alloc_path(); + if (!ppath) { + btrfs_free_path(ppath); + return -ENOMEM; + } + /* * work on commit root. The related disk blocks are static as * long as COW is applied. This means, it is save to rewrite @@ -2515,7 +3075,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) { get_raid56_logic_offset(physical_end, num, - map, &logic_end); + map, &logic_end, NULL); logic_end += base; } else { logic_end = logical + increment * nstripes; @@ -2562,10 +3122,18 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) { ret = get_raid56_logic_offset(physical, num, - map, &logical); + map, &logical, &stripe_logical); logical += base; - if (ret) + if (ret) { + stripe_logical += base; + stripe_end = stripe_logical + increment - 1; + ret = scrub_raid56_parity(sctx, map, scrub_dev, + ppath, stripe_logical, + stripe_end); + if (ret) + goto out; goto skip; + } } /* * canceled? @@ -2716,13 +3284,25 @@ again: * loop until we find next data stripe * or we have finished all stripes. */ - do { - physical += map->stripe_len; - ret = get_raid56_logic_offset( - physical, num, - map, &logical); - logical += base; - } while (physical < physical_end && ret); +loop: + physical += map->stripe_len; + ret = get_raid56_logic_offset(physical, + num, map, &logical, + &stripe_logical); + logical += base; + + if (ret && physical < physical_end) { + stripe_logical += base; + stripe_end = stripe_logical + + increment - 1; + ret = scrub_raid56_parity(sctx, + map, scrub_dev, ppath, + stripe_logical, + stripe_end); + if (ret) + goto out; + goto loop; + } } else { physical += map->stripe_len; logical += increment; @@ -2763,6 +3343,7 @@ out: blk_finish_plug(&plug); btrfs_free_path(path); + btrfs_free_path(ppath); return ret < 0 ? ret : 0; } -- cgit v1.2.3 From 2c8cdd6ee4e7f637b0486c6798117e7859dee586 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 14 Nov 2014 16:06:25 +0800 Subject: Btrfs, replace: write dirty pages into the replace target device The implementation is simple: - In order to avoid changing the code logic of btrfs_map_bio and RAID56, we add the stripes of the replace target devices at the end of the stripe array in btrfs bio, and we sort those target device stripes in the array. And we keep the number of the target device stripes in the btrfs bio. - Except write operation on RAID56, all the other operation don't take the target device stripes into account. - When we do write operation, we read the data from the common devices and calculate the parity. Then write the dirty data and new parity out, at this time, we will find the relative replace target stripes and wirte the relative data into it. Note: The function that copying old data on the source device to the target device was implemented in the past, it is similar to the other RAID type. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 104 +++++++++++++++++++++++++++++++++-------------------- fs/btrfs/volumes.c | 26 ++++++++++++-- fs/btrfs/volumes.h | 10 ++++-- 3 files changed, 97 insertions(+), 43 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index b85d68f721b8..89a8486c34b3 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -131,6 +131,8 @@ struct btrfs_raid_bio { /* number of data stripes (no p/q) */ int nr_data; + int real_stripes; + int stripe_npages; /* * set if we're doing a parity rebuild @@ -638,7 +640,7 @@ static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index) */ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index) { - if (rbio->nr_data + 1 == rbio->bbio->num_stripes) + if (rbio->nr_data + 1 == rbio->real_stripes) return NULL; index += ((rbio->nr_data + 1) * rbio->stripe_len) >> @@ -981,7 +983,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, { struct btrfs_raid_bio *rbio; int nr_data = 0; - int num_pages = rbio_nr_pages(stripe_len, bbio->num_stripes); + int real_stripes = bbio->num_stripes - bbio->num_tgtdevs; + int num_pages = rbio_nr_pages(stripe_len, real_stripes); int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE); void *p; @@ -1001,6 +1004,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, rbio->fs_info = root->fs_info; rbio->stripe_len = stripe_len; rbio->nr_pages = num_pages; + rbio->real_stripes = real_stripes; rbio->stripe_npages = stripe_npages; rbio->faila = -1; rbio->failb = -1; @@ -1017,10 +1021,10 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, rbio->bio_pages = p + sizeof(struct page *) * num_pages; rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2; - if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE) - nr_data = bbio->num_stripes - 2; + if (raid_map[real_stripes - 1] == RAID6_Q_STRIPE) + nr_data = real_stripes - 2; else - nr_data = bbio->num_stripes - 1; + nr_data = real_stripes - 1; rbio->nr_data = nr_data; return rbio; @@ -1132,7 +1136,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) { if (rbio->faila >= 0 || rbio->failb >= 0) { - BUG_ON(rbio->faila == rbio->bbio->num_stripes - 1); + BUG_ON(rbio->faila == rbio->real_stripes - 1); __raid56_parity_recover(rbio); } else { finish_rmw(rbio); @@ -1193,7 +1197,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio) static noinline void finish_rmw(struct btrfs_raid_bio *rbio) { struct btrfs_bio *bbio = rbio->bbio; - void *pointers[bbio->num_stripes]; + void *pointers[rbio->real_stripes]; int stripe_len = rbio->stripe_len; int nr_data = rbio->nr_data; int stripe; @@ -1207,11 +1211,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) bio_list_init(&bio_list); - if (bbio->num_stripes - rbio->nr_data == 1) { - p_stripe = bbio->num_stripes - 1; - } else if (bbio->num_stripes - rbio->nr_data == 2) { - p_stripe = bbio->num_stripes - 2; - q_stripe = bbio->num_stripes - 1; + if (rbio->real_stripes - rbio->nr_data == 1) { + p_stripe = rbio->real_stripes - 1; + } else if (rbio->real_stripes - rbio->nr_data == 2) { + p_stripe = rbio->real_stripes - 2; + q_stripe = rbio->real_stripes - 1; } else { BUG(); } @@ -1268,7 +1272,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) SetPageUptodate(p); pointers[stripe++] = kmap(p); - raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE, + raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE, pointers); } else { /* raid5 */ @@ -1277,7 +1281,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) } - for (stripe = 0; stripe < bbio->num_stripes; stripe++) + for (stripe = 0; stripe < rbio->real_stripes; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); } @@ -1286,7 +1290,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) * higher layers (the bio_list in our rbio) and our p/q. Ignore * everything else. */ - for (stripe = 0; stripe < bbio->num_stripes; stripe++) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) { struct page *page; if (stripe < rbio->nr_data) { @@ -1304,6 +1308,32 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) } } + if (likely(!bbio->num_tgtdevs)) + goto write_data; + + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { + if (!bbio->tgtdev_map[stripe]) + continue; + + for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) { + struct page *page; + if (stripe < rbio->nr_data) { + page = page_in_rbio(rbio, stripe, pagenr, 1); + if (!page) + continue; + } else { + page = rbio_stripe_page(rbio, stripe, pagenr); + } + + ret = rbio_add_io_page(rbio, &bio_list, page, + rbio->bbio->tgtdev_map[stripe], + pagenr, rbio->stripe_len); + if (ret) + goto cleanup; + } + } + +write_data: atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list)); BUG_ON(atomic_read(&rbio->stripes_pending) == 0); @@ -1342,7 +1372,8 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, stripe = &rbio->bbio->stripes[i]; stripe_start = stripe->physical; if (physical >= stripe_start && - physical < stripe_start + rbio->stripe_len) { + physical < stripe_start + rbio->stripe_len && + bio->bi_bdev == stripe->dev->bdev) { return i; } } @@ -1791,7 +1822,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) int err; int i; - pointers = kzalloc(rbio->bbio->num_stripes * sizeof(void *), + pointers = kzalloc(rbio->real_stripes * sizeof(void *), GFP_NOFS); if (!pointers) { err = -ENOMEM; @@ -1821,7 +1852,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) /* setup our array of pointers with pages * from each stripe */ - for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { /* * if we're rebuilding a read, we have to use * pages from the bio list @@ -1836,7 +1867,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) } /* all raid6 handling here */ - if (rbio->raid_map[rbio->bbio->num_stripes - 1] == + if (rbio->raid_map[rbio->real_stripes - 1] == RAID6_Q_STRIPE) { /* @@ -1886,10 +1917,10 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) } if (rbio->raid_map[failb] == RAID5_P_STRIPE) { - raid6_datap_recov(rbio->bbio->num_stripes, + raid6_datap_recov(rbio->real_stripes, PAGE_SIZE, faila, pointers); } else { - raid6_2data_recov(rbio->bbio->num_stripes, + raid6_2data_recov(rbio->real_stripes, PAGE_SIZE, faila, failb, pointers); } @@ -1931,7 +1962,7 @@ pstripe: } } } - for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { /* * if we're rebuilding a read, we have to use * pages from the bio list @@ -2012,7 +2043,6 @@ static void raid_recover_end_io(struct bio *bio, int err) static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) { int bios_to_read = 0; - struct btrfs_bio *bbio = rbio->bbio; struct bio_list bio_list; int ret; int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE); @@ -2033,7 +2063,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) * stripe cache, it is possible that some or all of these * pages are going to be uptodate. */ - for (stripe = 0; stripe < bbio->num_stripes; stripe++) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { if (rbio->faila == stripe || rbio->failb == stripe) { atomic_inc(&rbio->error); continue; @@ -2139,7 +2169,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, * asking for mirror 3 */ if (mirror_num == 3) - rbio->failb = bbio->num_stripes - 2; + rbio->failb = rbio->real_stripes - 2; ret = lock_stripe_add(rbio); @@ -2205,7 +2235,7 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio, ASSERT(!bio->bi_iter.bi_size); rbio->operation = BTRFS_RBIO_PARITY_SCRUB; - for (i = 0; i < bbio->num_stripes; i++) { + for (i = 0; i < rbio->real_stripes; i++) { if (bbio->stripes[i].dev == scrub_dev) { rbio->scrubp = i; break; @@ -2246,7 +2276,7 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) struct page *page; for_each_set_bit(bit, rbio->dbitmap, rbio->stripe_npages) { - for (i = 0; i < rbio->bbio->num_stripes; i++) { + for (i = 0; i < rbio->real_stripes; i++) { index = i * rbio->stripe_npages + bit; if (rbio->stripe_pages[index]) continue; @@ -2288,8 +2318,7 @@ static void raid_write_parity_end_io(struct bio *bio, int err) static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) { - struct btrfs_bio *bbio = rbio->bbio; - void *pointers[bbio->num_stripes]; + void *pointers[rbio->real_stripes]; int nr_data = rbio->nr_data; int stripe; int pagenr; @@ -2303,11 +2332,11 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bio_list_init(&bio_list); - if (bbio->num_stripes - rbio->nr_data == 1) { - p_stripe = bbio->num_stripes - 1; - } else if (bbio->num_stripes - rbio->nr_data == 2) { - p_stripe = bbio->num_stripes - 2; - q_stripe = bbio->num_stripes - 1; + if (rbio->real_stripes - rbio->nr_data == 1) { + p_stripe = rbio->real_stripes - 1; + } else if (rbio->real_stripes - rbio->nr_data == 2) { + p_stripe = rbio->real_stripes - 2; + q_stripe = rbio->real_stripes - 1; } else { BUG(); } @@ -2358,7 +2387,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, */ pointers[stripe++] = kmap(q_page); - raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE, + raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE, pointers); } else { /* raid5 */ @@ -2376,7 +2405,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bitmap_clear(rbio->dbitmap, pagenr, 1); kunmap(p); - for (stripe = 0; stripe < bbio->num_stripes; stripe++) + for (stripe = 0; stripe < rbio->real_stripes; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); } @@ -2526,7 +2555,6 @@ static void raid56_parity_scrub_end_io(struct bio *bio, int err) static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) { int bios_to_read = 0; - struct btrfs_bio *bbio = rbio->bbio; struct bio_list bio_list; int ret; int pagenr; @@ -2544,7 +2572,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) * build a list of bios to read all the missing parts of this * stripe */ - for (stripe = 0; stripe < bbio->num_stripes; stripe++) { + for (stripe = 0; stripe < rbio->real_stripes; stripe++) { for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { struct page *page; /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 217c42ea90b0..6d8a5e8d8c39 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4881,13 +4881,15 @@ static inline int parity_smaller(u64 a, u64 b) static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map) { struct btrfs_bio_stripe s; + int real_stripes = bbio->num_stripes - bbio->num_tgtdevs; int i; u64 l; int again = 1; + int m; while (again) { again = 0; - for (i = 0; i < bbio->num_stripes - 1; i++) { + for (i = 0; i < real_stripes - 1; i++) { if (parity_smaller(raid_map[i], raid_map[i+1])) { s = bbio->stripes[i]; l = raid_map[i]; @@ -4895,6 +4897,14 @@ static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map) raid_map[i] = raid_map[i+1]; bbio->stripes[i+1] = s; raid_map[i+1] = l; + + if (bbio->tgtdev_map) { + m = bbio->tgtdev_map[i]; + bbio->tgtdev_map[i] = + bbio->tgtdev_map[i + 1]; + bbio->tgtdev_map[i + 1] = m; + } + again = 1; } } @@ -4923,6 +4933,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, int ret = 0; int num_stripes; int max_errors = 0; + int tgtdev_indexes = 0; struct btrfs_bio *bbio = NULL; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; int dev_replace_is_ongoing = 0; @@ -5234,14 +5245,19 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, num_alloc_stripes <<= 1; if (rw & REQ_GET_READ_MIRRORS) num_alloc_stripes++; + tgtdev_indexes = num_stripes; } - bbio = kzalloc(btrfs_bio_size(num_alloc_stripes), GFP_NOFS); + + bbio = kzalloc(btrfs_bio_size(num_alloc_stripes, tgtdev_indexes), + GFP_NOFS); if (!bbio) { kfree(raid_map); ret = -ENOMEM; goto out; } atomic_set(&bbio->error, 0); + if (dev_replace_is_ongoing) + bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes); if (rw & REQ_DISCARD) { int factor = 0; @@ -5326,6 +5342,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) max_errors = btrfs_chunk_max_errors(map); + tgtdev_indexes = 0; if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) && dev_replace->tgtdev != NULL) { int index_where_to_add; @@ -5354,8 +5371,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, new->physical = old->physical; new->length = old->length; new->dev = dev_replace->tgtdev; + bbio->tgtdev_map[i] = index_where_to_add; index_where_to_add++; max_errors++; + tgtdev_indexes++; } } num_stripes = index_where_to_add; @@ -5401,7 +5420,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, tgtdev_stripe->length = bbio->stripes[index_srcdev].length; tgtdev_stripe->dev = dev_replace->tgtdev; + bbio->tgtdev_map[index_srcdev] = num_stripes; + tgtdev_indexes++; num_stripes++; } } @@ -5411,6 +5432,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, bbio->num_stripes = num_stripes; bbio->max_errors = max_errors; bbio->mirror_num = mirror_num; + bbio->num_tgtdevs = tgtdev_indexes; /* * this is the case that REQ_READ && dev_replace_is_ongoing && diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 01094bb804c7..70be2571cedf 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -292,7 +292,7 @@ struct btrfs_bio_stripe { struct btrfs_bio; typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err); -#define BTRFS_BIO_ORIG_BIO_SUBMITTED 0x1 +#define BTRFS_BIO_ORIG_BIO_SUBMITTED (1 << 0) struct btrfs_bio { atomic_t stripes_pending; @@ -305,6 +305,8 @@ struct btrfs_bio { int max_errors; int num_stripes; int mirror_num; + int num_tgtdevs; + int *tgtdev_map; struct btrfs_bio_stripe stripes[]; }; @@ -387,8 +389,10 @@ struct btrfs_balance_control { int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, u64 end, u64 *length); -#define btrfs_bio_size(n) (sizeof(struct btrfs_bio) + \ - (sizeof(struct btrfs_bio_stripe) * (n))) +#define btrfs_bio_size(total_stripes, real_stripes) \ + (sizeof(struct btrfs_bio) + \ + (sizeof(struct btrfs_bio_stripe) * (total_stripes)) + \ + (sizeof(int) * (real_stripes))) int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, u64 logical, u64 *length, -- cgit v1.2.3 From 7603597690147a16b5cc77047d7570fa22a22673 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 14 Nov 2014 17:45:42 +0800 Subject: Btrfs, replace: write raid56 parity into the replace target device This function reused the code of parity scrub, and we just write the right parity or corrected parity into the target device before the parity scrub end. Signed-off-by: Miao Xie --- fs/btrfs/raid56.c | 23 +++++++++++++++++++++++ fs/btrfs/scrub.c | 2 +- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 89a8486c34b3..5ece565bc5f0 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2318,7 +2318,9 @@ static void raid_write_parity_end_io(struct bio *bio, int err) static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) { + struct btrfs_bio *bbio = rbio->bbio; void *pointers[rbio->real_stripes]; + DECLARE_BITMAP(pbitmap, rbio->stripe_npages); int nr_data = rbio->nr_data; int stripe; int pagenr; @@ -2328,6 +2330,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, struct page *q_page = NULL; struct bio_list bio_list; struct bio *bio; + int is_replace = 0; int ret; bio_list_init(&bio_list); @@ -2341,6 +2344,11 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, BUG(); } + if (bbio->num_tgtdevs && bbio->tgtdev_map[rbio->scrubp]) { + is_replace = 1; + bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_npages); + } + /* * Because the higher layers(scrubber) are unlikely to * use this area of the disk again soon, so don't cache @@ -2429,6 +2437,21 @@ writeback: goto cleanup; } + if (!is_replace) + goto submit_write; + + for_each_set_bit(pagenr, pbitmap, rbio->stripe_npages) { + struct page *page; + + page = rbio_stripe_page(rbio, rbio->scrubp, pagenr); + ret = rbio_add_io_page(rbio, &bio_list, page, + bbio->tgtdev_map[rbio->scrubp], + pagenr, rbio->stripe_len); + if (ret) + goto cleanup; + } + +submit_write: nr_data = bio_list_size(&bio_list); if (!nr_data) { /* Every parity is right */ diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 7f95afcf9fd3..0ae837fd676d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2714,7 +2714,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity) goto out; length = sparity->logic_end - sparity->logic_start + 1; - ret = btrfs_map_sblock(sctx->dev_root->fs_info, REQ_GET_READ_MIRRORS, + ret = btrfs_map_sblock(sctx->dev_root->fs_info, WRITE, sparity->logic_start, &length, &bbio, 0, &raid_map); if (ret || !bbio || !raid_map) -- cgit v1.2.3 From 4245215d6a8dba1a51c50533b6667919687c0b89 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 25 Nov 2014 16:39:28 +0800 Subject: Btrfs, raid56: fix use-after-free problem in the final device replace procedure on raid56 The commit c404e0dc (Btrfs: fix use-after-free in the finishing procedure of the device replace) fixed a use-after-free problem which happened when removing the source device at the end of device replace, but at that time, btrfs didn't support device replace on raid56, so we didn't fix the problem on the raid56 profile. Currently, we implemented device replace for raid56, so we need kick that problem out before we enable that function for raid56. The fix method is very simple, we just increase the bio per-cpu counter before we submit a raid56 io, and decrease the counter when the raid56 io ends. Signed-off-by: Miao Xie --- fs/btrfs/ctree.h | 7 ++++++- fs/btrfs/dev-replace.c | 4 ++-- fs/btrfs/raid56.c | 41 ++++++++++++++++++++++++++++++++--------- fs/btrfs/raid56.h | 4 ++-- fs/btrfs/scrub.c | 2 +- fs/btrfs/volumes.c | 7 ++----- 6 files changed, 45 insertions(+), 20 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe69edda11fb..470e3177a7e8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -4097,7 +4097,12 @@ int btrfs_scrub_progress(struct btrfs_root *root, u64 devid, /* dev-replace.c */ void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info); void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info); -void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info); +void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount); + +static inline void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info) +{ + btrfs_bio_counter_sub(fs_info, 1); +} /* reada.c */ struct reada_control { diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 6f662b34ba0e..fa27b4e3b6c8 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -920,9 +920,9 @@ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info) percpu_counter_inc(&fs_info->bio_counter); } -void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info) +void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount) { - percpu_counter_dec(&fs_info->bio_counter); + percpu_counter_sub(&fs_info->bio_counter, amount); if (waitqueue_active(&fs_info->replace_wait)) wake_up(&fs_info->replace_wait); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 5ece565bc5f0..8ab2a17bbba8 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -162,6 +162,8 @@ struct btrfs_raid_bio { */ int bio_list_bytes; + int generic_bio_cnt; + atomic_t refs; atomic_t stripes_pending; @@ -354,6 +356,7 @@ static void merge_rbio(struct btrfs_raid_bio *dest, { bio_list_merge(&dest->bio_list, &victim->bio_list); dest->bio_list_bytes += victim->bio_list_bytes; + dest->generic_bio_cnt += victim->generic_bio_cnt; bio_list_init(&victim->bio_list); } @@ -891,6 +894,10 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate) { struct bio *cur = bio_list_get(&rbio->bio_list); struct bio *next; + + if (rbio->generic_bio_cnt) + btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt); + free_raid_bio(rbio); while (cur) { @@ -1775,6 +1782,7 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct btrfs_raid_bio *rbio; struct btrfs_plug_cb *plug = NULL; struct blk_plug_cb *cb; + int ret; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); if (IS_ERR(rbio)) { @@ -1785,12 +1793,19 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, rbio->bio_list_bytes = bio->bi_iter.bi_size; rbio->operation = BTRFS_RBIO_WRITE; + btrfs_bio_counter_inc_noblocked(root->fs_info); + rbio->generic_bio_cnt = 1; + /* * don't plug on full rbios, just get them out the door * as quickly as we can */ - if (rbio_is_full(rbio)) - return full_stripe_write(rbio); + if (rbio_is_full(rbio)) { + ret = full_stripe_write(rbio); + if (ret) + btrfs_bio_counter_dec(root->fs_info); + return ret; + } cb = blk_check_plugged(btrfs_raid_unplug, root->fs_info, sizeof(*plug)); @@ -1801,10 +1816,13 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, INIT_LIST_HEAD(&plug->rbio_list); } list_add_tail(&rbio->plug_list, &plug->rbio_list); + ret = 0; } else { - return __raid56_parity_write(rbio); + ret = __raid56_parity_write(rbio); + if (ret) + btrfs_bio_counter_dec(root->fs_info); } - return 0; + return ret; } /* @@ -2139,19 +2157,17 @@ cleanup: */ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, - u64 stripe_len, int mirror_num, int hold_bbio) + u64 stripe_len, int mirror_num, int generic_io) { struct btrfs_raid_bio *rbio; int ret; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); if (IS_ERR(rbio)) { - __free_bbio_and_raid_map(bbio, raid_map, !hold_bbio); + __free_bbio_and_raid_map(bbio, raid_map, generic_io); return PTR_ERR(rbio); } - if (hold_bbio) - set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags); rbio->operation = BTRFS_RBIO_READ_REBUILD; bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_iter.bi_size; @@ -2159,11 +2175,18 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, rbio->faila = find_logical_bio_stripe(rbio, bio); if (rbio->faila == -1) { BUG(); - __free_bbio_and_raid_map(bbio, raid_map, !hold_bbio); + __free_bbio_and_raid_map(bbio, raid_map, generic_io); kfree(rbio); return -EIO; } + if (generic_io) { + btrfs_bio_counter_inc_noblocked(root->fs_info); + rbio->generic_bio_cnt = 1; + } else { + set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags); + } + /* * reconstruct from the q stripe if they are * asking for mirror 3 diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h index 3d4ddb3d861d..31d4a157b5e3 100644 --- a/fs/btrfs/raid56.h +++ b/fs/btrfs/raid56.h @@ -43,8 +43,8 @@ struct btrfs_raid_bio; struct btrfs_device; int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, - struct btrfs_bio *bbio, u64 *raid_map, - u64 stripe_len, int mirror_num, int hold_bbio); + struct btrfs_bio *bbio, u64 *raid_map, + u64 stripe_len, int mirror_num, int generic_io); int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct btrfs_bio *bbio, u64 *raid_map, u64 stripe_len); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0ae837fd676d..27f2e16cd259 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1477,7 +1477,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, ret = raid56_parity_recover(fs_info->fs_root, bio, page->recover->bbio, page->recover->raid_map, page->recover->map_length, - page->mirror_num, 1); + page->mirror_num, 0); if (ret) return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6d8a5e8d8c39..cbb766577f31 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5843,12 +5843,9 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, } else { ret = raid56_parity_recover(root, bio, bbio, raid_map, map_length, - mirror_num, 0); + mirror_num, 1); } - /* - * FIXME, replace dosen't support raid56 yet, please fix - * it in the future. - */ + btrfs_bio_counter_dec(root->fs_info); return ret; } -- cgit v1.2.3 From 5d3edd8f44aac94de7b16f4c54290e24f5e8c532 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Thu, 13 Nov 2014 11:45:38 +0800 Subject: Btrfs, replace: enable dev-replace for raid56 Signed-off-by: Zhao Lei Signed-off-by: Miao Xie --- fs/btrfs/dev-replace.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index fa27b4e3b6c8..0bf41f8b1e23 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -316,11 +316,6 @@ int btrfs_dev_replace_start(struct btrfs_root *root, struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; - if (btrfs_fs_incompat(fs_info, RAID56)) { - btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6"); - return -EOPNOTSUPP; - } - switch (args->start.cont_reading_from_srcdev_mode) { case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS: case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID: -- cgit v1.2.3