From 6416954ca75baed71640bf3828625bf165fb9b5e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 14 May 2021 10:03:40 +0100 Subject: btrfs: release path before starting transaction when cloning inline extent When cloning an inline extent there are a few cases, such as when we have an implicit hole at file offset 0, where we start a transaction while holding a read lock on a leaf. Starting the transaction results in a call to sb_start_intwrite(), which results in doing a read lock on a percpu semaphore. Lockdep doesn't like this and complains about it: [46.580704] ====================================================== [46.580752] WARNING: possible circular locking dependency detected [46.580799] 5.13.0-rc1 #28 Not tainted [46.580832] ------------------------------------------------------ [46.580877] cloner/3835 is trying to acquire lock: [46.580918] c00000001301d638 (sb_internal#2){.+.+}-{0:0}, at: clone_copy_inline_extent+0xe4/0x5a0 [46.581167] [46.581167] but task is already holding lock: [46.581217] c000000007fa2550 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x70/0x1d0 [46.581293] [46.581293] which lock already depends on the new lock. [46.581293] [46.581351] [46.581351] the existing dependency chain (in reverse order) is: [46.581410] [46.581410] -> #1 (btrfs-tree-00){++++}-{3:3}: [46.581464] down_read_nested+0x68/0x200 [46.581536] __btrfs_tree_read_lock+0x70/0x1d0 [46.581577] btrfs_read_lock_root_node+0x88/0x200 [46.581623] btrfs_search_slot+0x298/0xb70 [46.581665] btrfs_set_inode_index+0xfc/0x260 [46.581708] btrfs_new_inode+0x26c/0x950 [46.581749] btrfs_create+0xf4/0x2b0 [46.581782] lookup_open.isra.57+0x55c/0x6a0 [46.581855] path_openat+0x418/0xd20 [46.581888] do_filp_open+0x9c/0x130 [46.581920] do_sys_openat2+0x2ec/0x430 [46.581961] do_sys_open+0x90/0xc0 [46.581993] system_call_exception+0x3d4/0x410 [46.582037] system_call_common+0xec/0x278 [46.582078] [46.582078] -> #0 (sb_internal#2){.+.+}-{0:0}: [46.582135] __lock_acquire+0x1e90/0x2c50 [46.582176] lock_acquire+0x2b4/0x5b0 [46.582263] start_transaction+0x3cc/0x950 [46.582308] clone_copy_inline_extent+0xe4/0x5a0 [46.582353] btrfs_clone+0x5fc/0x880 [46.582388] btrfs_clone_files+0xd8/0x1c0 [46.582434] btrfs_remap_file_range+0x3d8/0x590 [46.582481] do_clone_file_range+0x10c/0x270 [46.582558] vfs_clone_file_range+0x1b0/0x310 [46.582605] ioctl_file_clone+0x90/0x130 [46.582651] do_vfs_ioctl+0x874/0x1ac0 [46.582697] sys_ioctl+0x6c/0x120 [46.582733] system_call_exception+0x3d4/0x410 [46.582777] system_call_common+0xec/0x278 [46.582822] [46.582822] other info that might help us debug this: [46.582822] [46.582888] Possible unsafe locking scenario: [46.582888] [46.582942] CPU0 CPU1 [46.582984] ---- ---- [46.583028] lock(btrfs-tree-00); [46.583062] lock(sb_internal#2); [46.583119] lock(btrfs-tree-00); [46.583174] lock(sb_internal#2); [46.583212] [46.583212] *** DEADLOCK *** [46.583212] [46.583266] 6 locks held by cloner/3835: [46.583299] #0: c00000001301d448 (sb_writers#12){.+.+}-{0:0}, at: ioctl_file_clone+0x90/0x130 [46.583382] #1: c00000000f6d3768 (&sb->s_type->i_mutex_key#15){+.+.}-{3:3}, at: lock_two_nondirectories+0x58/0xc0 [46.583477] #2: c00000000f6d72a8 (&sb->s_type->i_mutex_key#15/4){+.+.}-{3:3}, at: lock_two_nondirectories+0x9c/0xc0 [46.583574] #3: c00000000f6d7138 (&ei->i_mmap_lock){+.+.}-{3:3}, at: btrfs_remap_file_range+0xd0/0x590 [46.583657] #4: c00000000f6d35f8 (&ei->i_mmap_lock/1){+.+.}-{3:3}, at: btrfs_remap_file_range+0xe0/0x590 [46.583743] #5: c000000007fa2550 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x70/0x1d0 [46.583828] [46.583828] stack backtrace: [46.583872] CPU: 1 PID: 3835 Comm: cloner Not tainted 5.13.0-rc1 #28 [46.583931] Call Trace: [46.583955] [c0000000167c7200] [c000000000c1ee78] dump_stack+0xec/0x144 (unreliable) [46.584052] [c0000000167c7240] [c000000000274058] print_circular_bug.isra.32+0x3a8/0x400 [46.584123] [c0000000167c72e0] [c0000000002741f4] check_noncircular+0x144/0x190 [46.584191] [c0000000167c73b0] [c000000000278fc0] __lock_acquire+0x1e90/0x2c50 [46.584259] [c0000000167c74f0] [c00000000027aa94] lock_acquire+0x2b4/0x5b0 [46.584317] [c0000000167c75e0] [c000000000a0d6cc] start_transaction+0x3cc/0x950 [46.584388] [c0000000167c7690] [c000000000af47a4] clone_copy_inline_extent+0xe4/0x5a0 [46.584457] [c0000000167c77c0] [c000000000af525c] btrfs_clone+0x5fc/0x880 [46.584514] [c0000000167c7990] [c000000000af5698] btrfs_clone_files+0xd8/0x1c0 [46.584583] [c0000000167c7a00] [c000000000af5b58] btrfs_remap_file_range+0x3d8/0x590 [46.584652] [c0000000167c7ae0] [c0000000005d81dc] do_clone_file_range+0x10c/0x270 [46.584722] [c0000000167c7b40] [c0000000005d84f0] vfs_clone_file_range+0x1b0/0x310 [46.584793] [c0000000167c7bb0] [c00000000058bf80] ioctl_file_clone+0x90/0x130 [46.584861] [c0000000167c7c10] [c00000000058c894] do_vfs_ioctl+0x874/0x1ac0 [46.584922] [c0000000167c7d10] [c00000000058db4c] sys_ioctl+0x6c/0x120 [46.584978] [c0000000167c7d60] [c0000000000364a4] system_call_exception+0x3d4/0x410 [46.585046] [c0000000167c7e10] [c00000000000d45c] system_call_common+0xec/0x278 [46.585114] --- interrupt: c00 at 0x7ffff7e22990 [46.585160] NIP: 00007ffff7e22990 LR: 00000001000010ec CTR: 0000000000000000 [46.585224] REGS: c0000000167c7e80 TRAP: 0c00 Not tainted (5.13.0-rc1) [46.585280] MSR: 800000000280f033 CR: 28000244 XER: 00000000 [46.585374] IRQMASK: 0 [46.585374] GPR00: 0000000000000036 00007fffffffdec0 00007ffff7f17100 0000000000000004 [46.585374] GPR04: 000000008020940d 00007fffffffdf40 0000000000000000 0000000000000000 [46.585374] GPR08: 0000000000000004 0000000000000000 0000000000000000 0000000000000000 [46.585374] GPR12: 0000000000000000 00007ffff7ffa940 0000000000000000 0000000000000000 [46.585374] GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [46.585374] GPR20: 0000000000000000 000000009123683e 00007fffffffdf40 0000000000000000 [46.585374] GPR24: 0000000000000000 0000000000000000 0000000000000000 0000000000000004 [46.585374] GPR28: 0000000100030260 0000000100030280 0000000000000003 000000000000005f [46.585919] NIP [00007ffff7e22990] 0x7ffff7e22990 [46.585964] LR [00000001000010ec] 0x1000010ec [46.586010] --- interrupt: c00 This should be a false positive, as both locks are acquired in read mode. Nevertheless, we don't need to hold a leaf locked when we start the transaction, so just release the leaf (path) before starting it. Reported-by: Ritesh Harjani Link: https://lore.kernel.org/linux-btrfs/20210513214404.xks77p566fglzgum@riteshh-domain/ Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/reflink.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index f4ec06b53aa0..06682128d8fa 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -285,6 +285,11 @@ copy_inline_extent: ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end); out: if (!ret && !trans) { + /* + * Release path before starting a new transaction so we don't + * hold locks that would confuse lockdep. + */ + btrfs_release_path(path); /* * No transaction here means we copied the inline extent into a * page of the destination inode. -- cgit v1.2.3 From 91df99a6eb50d5a1bc70fff4a09a0b7ae6aab96d Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 14 May 2021 10:56:16 -0400 Subject: btrfs: do not BUG_ON in link_to_fixup_dir While doing error injection testing I got the following panic kernel BUG at fs/btrfs/tree-log.c:1862! invalid opcode: 0000 [#1] SMP NOPTI CPU: 1 PID: 7836 Comm: mount Not tainted 5.13.0-rc1+ #305 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 RIP: 0010:link_to_fixup_dir+0xd5/0xe0 RSP: 0018:ffffb5800180fa30 EFLAGS: 00010216 RAX: fffffffffffffffb RBX: 00000000fffffffb RCX: ffff8f595287faf0 RDX: ffffb5800180fa37 RSI: ffff8f5954978800 RDI: 0000000000000000 RBP: ffff8f5953af9450 R08: 0000000000000019 R09: 0000000000000001 R10: 000151f408682970 R11: 0000000120021001 R12: ffff8f5954978800 R13: ffff8f595287faf0 R14: ffff8f5953c77dd0 R15: 0000000000000065 FS: 00007fc5284c8c40(0000) GS:ffff8f59bbd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc5287f47c0 CR3: 000000011275e002 CR4: 0000000000370ee0 Call Trace: replay_one_buffer+0x409/0x470 ? btree_read_extent_buffer_pages+0xd0/0x110 walk_up_log_tree+0x157/0x1e0 walk_log_tree+0xa6/0x1d0 btrfs_recover_log_trees+0x1da/0x360 ? replay_one_extent+0x7b0/0x7b0 open_ctree+0x1486/0x1720 btrfs_mount_root.cold+0x12/0xea ? __kmalloc_track_caller+0x12f/0x240 legacy_get_tree+0x24/0x40 vfs_get_tree+0x22/0xb0 vfs_kern_mount.part.0+0x71/0xb0 btrfs_mount+0x10d/0x380 ? vfs_parse_fs_string+0x4d/0x90 legacy_get_tree+0x24/0x40 vfs_get_tree+0x22/0xb0 path_mount+0x433/0xa10 __x64_sys_mount+0xe3/0x120 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae We can get -EIO or any number of legitimate errors from btrfs_search_slot(), panicing here is not the appropriate response. The error path for this code handles errors properly, simply return the error. Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fd6b1f13112e..c17d6b827b42 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1858,8 +1858,6 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); } else if (ret == -EEXIST) { ret = 0; - } else { - BUG(); /* Logic Error */ } iput(inode); -- cgit v1.2.3 From e380adfc213a13677993c0e35cb48f5a8e61ebb0 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 19 May 2021 00:40:27 +0900 Subject: btrfs: zoned: pass start block to btrfs_use_zone_append btrfs_use_zone_append only needs the passed in extent_map's block_start member, so there's no need to pass in the full extent map. This also enables the use of btrfs_use_zone_append in places where we only have a start byte but no extent_map. Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 2 +- fs/btrfs/inode.c | 2 +- fs/btrfs/zoned.c | 4 ++-- fs/btrfs/zoned.h | 5 ++--- 4 files changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 360d997c7226..d9f20ca3ac7d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3762,7 +3762,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, /* Note that em_end from extent_map_end() is exclusive */ iosize = min(em_end, end + 1) - cur; - if (btrfs_use_zone_append(inode, em)) + if (btrfs_use_zone_append(inode, em->block_start)) opf = REQ_OP_ZONE_APPEND; free_extent_map(em); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 095e452f59f0..bb4ab408d670 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7796,7 +7796,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->bdev = fs_info->fs_devices->latest_bdev; iomap->length = len; - if (write && btrfs_use_zone_append(BTRFS_I(inode), em)) + if (write && btrfs_use_zone_append(BTRFS_I(inode), em->block_start)) iomap->flags |= IOMAP_F_ZONE_APPEND; free_extent_map(em); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 304ce64c70a4..1bb8ee97aae0 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1278,7 +1278,7 @@ void btrfs_free_redirty_list(struct btrfs_transaction *trans) spin_unlock(&trans->releasing_ebs_lock); } -bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) +bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_block_group *cache; @@ -1293,7 +1293,7 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) if (!is_data_inode(&inode->vfs_inode)) return false; - cache = btrfs_lookup_block_group(fs_info, em->block_start); + cache = btrfs_lookup_block_group(fs_info, start); ASSERT(cache); if (!cache) return false; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 5e41a74a9cb2..e55d32595c2c 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -53,7 +53,7 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb); void btrfs_free_redirty_list(struct btrfs_transaction *trans); -bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em); +bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start); void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, struct bio *bio); void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); @@ -152,8 +152,7 @@ static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb) { } static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } -static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, - struct extent_map *em) +static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) { return false; } -- cgit v1.2.3 From 764c7c9a464b68f7c6a5a9ec0b923176a05e8e8f Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 19 May 2021 00:40:28 +0900 Subject: btrfs: zoned: fix parallel compressed writes When multiple processes write data to the same block group on a compressed zoned filesystem, the underlying device could report I/O errors and data corruption is possible. This happens because on a zoned file system, compressed data writes where sent to the device via a REQ_OP_WRITE instead of a REQ_OP_ZONE_APPEND operation. But with REQ_OP_WRITE and parallel submission it cannot be guaranteed that the data is always submitted aligned to the underlying zone's write pointer. The change to using REQ_OP_ZONE_APPEND instead of REQ_OP_WRITE on a zoned filesystem is non intrusive on a regular file system or when submitting to a conventional zone on a zoned filesystem, as it is guarded by btrfs_use_zone_append. Reported-by: David Sterba Fixes: 9d294a685fbc ("btrfs: zoned: enable to mount ZONED incompat flag") CC: stable@vger.kernel.org # 5.12.x: e380adfc213a13: btrfs: zoned: pass start block to btrfs_use_zone_append CC: stable@vger.kernel.org # 5.12.x Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/compression.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 17f93fd28f7e..91743a0b34c5 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -28,6 +28,7 @@ #include "compression.h" #include "extent_io.h" #include "extent_map.h" +#include "zoned.h" static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" }; @@ -349,6 +350,7 @@ static void end_compressed_bio_write(struct bio *bio) */ inode = cb->inode; cb->compressed_pages[0]->mapping = cb->inode->i_mapping; + btrfs_record_physical_zoned(inode, cb->start, bio); btrfs_writepage_endio_finish_ordered(cb->compressed_pages[0], cb->start, cb->start + cb->len - 1, bio->bi_status == BLK_STS_OK); @@ -401,6 +403,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, u64 first_byte = disk_start; blk_status_t ret; int skip_sum = inode->flags & BTRFS_INODE_NODATASUM; + const bool use_append = btrfs_use_zone_append(inode, disk_start); + const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE; WARN_ON(!PAGE_ALIGNED(start)); cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); @@ -418,10 +422,31 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->nr_pages = nr_pages; bio = btrfs_bio_alloc(first_byte); - bio->bi_opf = REQ_OP_WRITE | write_flags; + bio->bi_opf = bio_op | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; + if (use_append) { + struct extent_map *em; + struct map_lookup *map; + struct block_device *bdev; + + em = btrfs_get_chunk_map(fs_info, disk_start, PAGE_SIZE); + if (IS_ERR(em)) { + kfree(cb); + bio_put(bio); + return BLK_STS_NOTSUPP; + } + + map = em->map_lookup; + /* We only support single profile for now */ + ASSERT(map->num_stripes == 1); + bdev = map->stripes[0].dev->bdev; + + bio_set_dev(bio, bdev); + free_extent_map(em); + } + if (blkcg_css) { bio->bi_opf |= REQ_CGROUP_PUNT; kthread_associate_blkcg(blkcg_css); @@ -432,6 +457,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bytes_left = compressed_len; for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { int submit = 0; + int len; page = compressed_pages[pg_index]; page->mapping = inode->vfs_inode.i_mapping; @@ -439,9 +465,13 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); + if (pg_index == 0 && use_append) + len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0); + else + len = bio_add_page(bio, page, PAGE_SIZE, 0); + page->mapping = NULL; - if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < - PAGE_SIZE) { + if (submit || len < PAGE_SIZE) { /* * inc the count before we submit the bio so * we know the end IO handler won't happen before @@ -465,11 +495,15 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, } bio = btrfs_bio_alloc(first_byte); - bio->bi_opf = REQ_OP_WRITE | write_flags; + bio->bi_opf = bio_op | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; if (blkcg_css) bio->bi_opf |= REQ_CGROUP_PUNT; + /* + * Use bio_add_page() to ensure the bio has at least one + * page. + */ bio_add_page(bio, page, PAGE_SIZE, 0); } if (bytes_left < PAGE_SIZE) { -- cgit v1.2.3