From d2dcc8ed8ec650a793e81d8b2222146eb6ddd84f Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 8 Mar 2021 17:20:17 +0800 Subject: btrfs: fix wrong offset to zero out range beyond i_size [BUG] The test generic/091 fails , with the following output: fsx -N 10000 -o 128000 -l 500000 -r PSIZE -t BSIZE -w BSIZE -Z -W mapped writes DISABLED Seed set to 1 main: filesystem does not support fallocate mode FALLOC_FL_COLLAPSE_RANGE, disabling! main: filesystem does not support fallocate mode FALLOC_FL_INSERT_RANGE, disabling! skipping zero size read truncating to largest ever: 0xe400 copying to largest ever: 0x1f400 cloning to largest ever: 0x70000 cloning to largest ever: 0x77000 fallocating to largest ever: 0x7a120 Mapped Read: non-zero data past EOF (0x3a7ff) page offset 0x800 is 0xf2e1 <<< ... [CAUSE] In commit c28ea613fafa ("btrfs: subpage: fix the false data csum mismatch error") end_bio_extent_readpage() changes to only zero the range inside the bvec for incoming subpage support. But that commit is using incorrect offset to calculate the start. For subpage, we can have a case that the whole bvec is beyond isize, thus we need to calculate the correct offset. But the offending commit is using @end (bvec end), other than @start (bvec start) to calculate the start offset. This means, we only zero the last byte of the bvec, not from the isize. This stupid bug makes the range beyond isize is not properly zeroed, and failed above test. [FIX] Use correct @start to calculate the range start. Reported-by: kernel test robot Fixes: c28ea613fafa ("btrfs: subpage: fix the false data csum mismatch error") Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4671c99d468d..f3d7be975c3a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3020,7 +3020,7 @@ readpage_ok: */ if (page->index == end_index && i_size <= end) { u32 zero_start = max(offset_in_page(i_size), - offset_in_page(end)); + offset_in_page(start)); zero_user_segment(page, zero_start, offset_in_page(end) + 1); -- cgit v1.2.3 From fbf48bb0b197e6894a04c714728c952af7153bf3 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 3 Mar 2021 18:41:51 +0800 Subject: btrfs: track qgroup released data in own variable in insert_prealloc_file_extent There is a piece of weird code in insert_prealloc_file_extent(), which looks like: ret = btrfs_qgroup_release_data(inode, file_offset, len); if (ret < 0) return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, file_offset, &stack_fi, true, ret); ... } extent_info.is_new_extent = true; extent_info.qgroup_reserved = ret; ... Note how the variable @ret is abused here, and if anyone is adding code just after btrfs_qgroup_release_data() call, it's super easy to overwrite the @ret and cause tons of qgroup related bugs. Fix such abuse by introducing new variable @qgroup_released, so that we won't reuse the existing variable @ret. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c35b724a5611..77182be403c5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9873,6 +9873,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; + int qgroup_released; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9885,14 +9886,14 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - ret = btrfs_qgroup_release_data(inode, file_offset, len); - if (ret < 0) - return ERR_PTR(ret); + qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); + if (qgroup_released < 0) + return ERR_PTR(qgroup_released); if (trans) { ret = insert_reserved_file_extent(trans, inode, file_offset, &stack_fi, - true, ret); + true, qgroup_released); if (ret) return ERR_PTR(ret); return trans; @@ -9905,7 +9906,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( extent_info.file_offset = file_offset; extent_info.extent_buf = (char *)&stack_fi; extent_info.is_new_extent = true; - extent_info.qgroup_reserved = ret; + extent_info.qgroup_reserved = qgroup_released; extent_info.insertions = 0; path = btrfs_alloc_path(); -- cgit v1.2.3 From a3ee79bd8fe17812d2305ccc4bf81bfeab395576 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 3 Mar 2021 18:41:52 +0800 Subject: btrfs: fix qgroup data rsv leak caused by falloc failure [BUG] When running fsstress with only falloc workload, and a very low qgroup limit set, we can get qgroup data rsv leak at unmount time. BTRFS warning (device dm-0): qgroup 0/5 has unreleased space, type 0 rsv 20480 BTRFS error (device dm-0): qgroup reserved space leaked The minimal reproducer looks like: #!/bin/bash dev=/dev/test/test mnt="/mnt/btrfs" fsstress=~/xfstests-dev/ltp/fsstress runtime=8 workload() { umount $dev &> /dev/null umount $mnt &> /dev/null mkfs.btrfs -f $dev > /dev/null mount $dev $mnt btrfs quota en $mnt btrfs quota rescan -w $mnt btrfs qgroup limit 16m 0/5 $mnt $fsstress -w -z -f creat=10 -f fallocate=10 -p 2 -n 100 \ -d $mnt -v > /tmp/fsstress umount $mnt if dmesg | grep leak ; then echo "!!! FAILED !!!" exit 1 fi } for (( i=0; i < $runtime; i++)); do echo "=== $i/$runtime===" workload done Normally it would fail before round 4. [CAUSE] In function insert_prealloc_file_extent(), we first call btrfs_qgroup_release_data() to know how many bytes are reserved for qgroup data rsv. Then use that @qgroup_released number to continue our work. But after we call btrfs_qgroup_release_data(), we should either queue @qgroup_released to delayed ref or free them manually in error path. Unfortunately, we lack the error handling to free the released bytes, leaking qgroup data rsv. All the error handling function outside won't help at all, as we have released the range, meaning in inode io tree, the EXTENT_QGROUP_RESERVED bit is already cleared, thus all btrfs_qgroup_free_data() call won't free any data rsv. [FIX] Add free_qgroup tag to manually free the released qgroup data rsv. Reported-by: Nikolay Borisov Reported-by: David Sterba Fixes: 9729f10a608f ("btrfs: inode: move qgroup reserved space release to the callers of insert_reserved_file_extent()") CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 77182be403c5..ea5ede619220 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9895,7 +9895,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( file_offset, &stack_fi, true, qgroup_released); if (ret) - return ERR_PTR(ret); + goto free_qgroup; return trans; } @@ -9910,17 +9910,31 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( extent_info.insertions = 0; path = btrfs_alloc_path(); - if (!path) - return ERR_PTR(-ENOMEM); + if (!path) { + ret = -ENOMEM; + goto free_qgroup; + } ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset, file_offset + len - 1, &extent_info, &trans); btrfs_free_path(path); if (ret) - return ERR_PTR(ret); - + goto free_qgroup; return trans; + +free_qgroup: + /* + * We have released qgroup data range at the beginning of the function, + * and normally qgroup_released bytes will be freed when committing + * transaction. + * But if we error out early, we have to free what we have released + * or we leak qgroup data reservation. + */ + btrfs_qgroup_free_refroot(inode->root->fs_info, + inode->root->root_key.objectid, qgroup_released, + BTRFS_QGROUP_RSV_DATA); + return ERR_PTR(ret); } static int __btrfs_prealloc_file_range(struct inode *inode, int mode, -- cgit v1.2.3 From e3d3b4157610164b0ec43d968b0dfedfe7c68992 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 11 Mar 2021 15:13:30 +0000 Subject: btrfs: zoned: fix linked list corruption after log root tree allocation failure When using a zoned filesystem, while syncing the log, if we fail to allocate the root node for the log root tree, we are not removing the log context we allocated on stack from the list of log contexts of the log root tree. This means after the return from btrfs_sync_log() we get a corrupted linked list. Fix this by allocating the node before adding our stack allocated context to the list of log contexts of the log root tree. Fixes: 3ddebf27fcd3a9 ("btrfs: zoned: reorder log node allocation on zoned filesystem") Reviewed-by: Johannes Thumshirn Reviewed-by: Naohiro Aota Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2f1acc9aea9e..92a368627791 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3169,10 +3169,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_lock(&log_root_tree->log_mutex); - index2 = log_root_tree->log_transid % 2; - list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); - root_log_ctx.log_transid = log_root_tree->log_transid; - if (btrfs_is_zoned(fs_info)) { if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); @@ -3183,6 +3179,10 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } } + index2 = log_root_tree->log_transid % 2; + list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); + root_log_ctx.log_transid = log_root_tree->log_transid; + /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit -- cgit v1.2.3 From d9bb77d51e668a1a6d4530c1ea471574d0ce465f Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Mar 2021 13:39:14 +0800 Subject: btrfs: subpage: fix wild pointer access during metadata read failure [BUG] When running fstests for btrfs subpage read-write test, it has a very high chance to crash at generic/475 with the following stack: BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10 Unable to handle kernel paging request at virtual address ffff80001157e7c0 CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G WC 5.12.0-rc2-custom+ #5 Hardware name: Khadas VIM3 (DT) Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] pc : queued_spin_lock_slowpath+0x1a0/0x390 lr : do_raw_spin_lock+0xc4/0x11c Call trace: queued_spin_lock_slowpath+0x1a0/0x390 _raw_spin_lock+0x68/0x84 btree_readahead_hook+0x38/0xc0 [btrfs] end_bio_extent_readpage+0x504/0x5f4 [btrfs] bio_endio+0x170/0x1a4 end_workqueue_fn+0x3c/0x60 [btrfs] btrfs_work_helper+0x1b0/0x1b4 [btrfs] process_one_work+0x22c/0x430 worker_thread+0x70/0x3a0 kthread+0x13c/0x140 ret_from_fork+0x10/0x30 Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827) [CAUSE] In end_bio_extent_readpage(), if we hit an error during read, we will handle the error differently for data and metadata. For data we queue a repair, while for metadata, we record the error and let the caller choose what to do. But the code is still using page->private to grab extent buffer, which no longer points to extent buffer for subpage metadata pages. Thus this wild pointer access leads to above crash. [FIX] Introduce a helper, find_extent_buffer_readpage(), to grab extent buffer. The difference against find_extent_buffer_nospinlock() is: - Also handles regular sectorsize == PAGE_SIZE case - No extent buffer refs increase/decrease As extent buffer under IO must have non-zero refs, so this is safe Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f3d7be975c3a..0d00a9cd123a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2885,6 +2885,35 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) btrfs_subpage_end_reader(fs_info, page, start, len); } +/* + * Find extent buffer for a givne bytenr. + * + * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking + * in endio context. + */ +static struct extent_buffer *find_extent_buffer_readpage( + struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) +{ + struct extent_buffer *eb; + + /* + * For regular sectorsize, we can use page->private to grab extent + * buffer + */ + if (fs_info->sectorsize == PAGE_SIZE) { + ASSERT(PagePrivate(page) && page->private); + return (struct extent_buffer *)page->private; + } + + /* For subpage case, we need to lookup buffer radix tree */ + rcu_read_lock(); + eb = radix_tree_lookup(&fs_info->buffer_radix, + bytenr >> fs_info->sectorsize_bits); + rcu_read_unlock(); + ASSERT(eb); + return eb; +} + /* * after a readpage IO is done, we need to: * clear the uptodate bits on error @@ -2996,7 +3025,7 @@ static void end_bio_extent_readpage(struct bio *bio) } else { struct extent_buffer *eb; - eb = (struct extent_buffer *)page->private; + eb = find_extent_buffer_readpage(fs_info, page, start); set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = mirror; atomic_dec(&eb->io_pages); -- cgit v1.2.3 From 60484cd9d50117017cf53d5310c6cd629600dc69 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 15 Mar 2021 13:39:15 +0800 Subject: btrfs: subpage: make readahead work properly In readahead infrastructure, we are using a lot of hard coded PAGE_SHIFT while we're not doing anything specific to PAGE_SIZE. One of the most affected part is the radix tree operation of btrfs_fs_info::reada_tree. If using PAGE_SHIFT, subpage metadata readahead is broken and does no help reading metadata ahead. Fix the problem by using btrfs_fs_info::sectorsize_bits so that readahead could work for subpage. Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/reada.c | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 20fd4aa48a8c..06713a8fe26b 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -209,7 +209,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err) /* find extent */ spin_lock(&fs_info->reada_lock); re = radix_tree_lookup(&fs_info->reada_tree, - eb->start >> PAGE_SHIFT); + eb->start >> fs_info->sectorsize_bits); if (re) re->refcnt++; spin_unlock(&fs_info->reada_lock); @@ -240,7 +240,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, zone = NULL; spin_lock(&fs_info->reada_lock); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_SHIFT, 1); + logical >> fs_info->sectorsize_bits, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) { kref_get(&zone->refcnt); spin_unlock(&fs_info->reada_lock); @@ -283,13 +283,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&dev->reada_zones, - (unsigned long)(zone->end >> PAGE_SHIFT), - zone); + (unsigned long)(zone->end >> fs_info->sectorsize_bits), + zone); if (ret == -EEXIST) { kfree(zone); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_SHIFT, 1); + logical >> fs_info->sectorsize_bits, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) kref_get(&zone->refcnt); else @@ -315,7 +315,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, u64 length; int real_stripes; int nzones = 0; - unsigned long index = logical >> PAGE_SHIFT; + unsigned long index = logical >> fs_info->sectorsize_bits; int dev_replace_is_ongoing; int have_zone = 0; @@ -497,7 +497,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info, struct reada_extent *re) { int i; - unsigned long index = re->logical >> PAGE_SHIFT; + unsigned long index = re->logical >> fs_info->sectorsize_bits; spin_lock(&fs_info->reada_lock); if (--re->refcnt) { @@ -538,11 +538,12 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info, static void reada_zone_release(struct kref *kref) { struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt); + struct btrfs_fs_info *fs_info = zone->device->fs_info; - lockdep_assert_held(&zone->device->fs_info->reada_lock); + lockdep_assert_held(&fs_info->reada_lock); radix_tree_delete(&zone->device->reada_zones, - zone->end >> PAGE_SHIFT); + zone->end >> fs_info->sectorsize_bits); kfree(zone); } @@ -593,7 +594,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical, static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock) { int i; - unsigned long index = zone->end >> PAGE_SHIFT; + unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits; for (i = 0; i < zone->ndevs; ++i) { struct reada_zone *peer; @@ -628,7 +629,7 @@ static int reada_pick_zone(struct btrfs_device *dev) (void **)&zone, index, 1); if (ret == 0) break; - index = (zone->end >> PAGE_SHIFT) + 1; + index = (zone->end >> dev->fs_info->sectorsize_bits) + 1; if (zone->locked) { if (zone->elems > top_locked_elems) { top_locked_elems = zone->elems; @@ -709,7 +710,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev) * plugging to speed things up */ ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_SHIFT, 1); + dev->reada_next >> fs_info->sectorsize_bits, 1); if (ret == 0 || re->logical > dev->reada_curr_zone->end) { ret = reada_pick_zone(dev); if (!ret) { @@ -718,7 +719,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev) } re = NULL; ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_SHIFT, 1); + dev->reada_next >> fs_info->sectorsize_bits, 1); } if (ret == 0) { spin_unlock(&fs_info->reada_lock); @@ -885,7 +886,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) pr_cont(" curr off %llu", device->reada_next - zone->start); pr_cont("\n"); - index = (zone->end >> PAGE_SHIFT) + 1; + index = (zone->end >> fs_info->sectorsize_bits) + 1; } cnt = 0; index = 0; @@ -910,7 +911,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } pr_cont("\n"); - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; if (++cnt > 15) break; } @@ -926,7 +927,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) if (ret == 0) break; if (!re->scheduled) { - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; continue; } pr_debug("re: logical %llu size %u list empty %d scheduled %d", @@ -942,7 +943,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } pr_cont("\n"); - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; } spin_unlock(&fs_info->reada_lock); } -- cgit v1.2.3 From 34e49994d0dcdb2d31d4d2908d04f4e9ce57e4d7 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 15 Mar 2021 15:18:24 +0100 Subject: btrfs: fix slab cache flags for free space tree bitmap The free space tree bitmap slab cache is created with SLAB_RED_ZONE but that's a debugging flag and not always enabled. Also the other slabs are created with at least SLAB_MEM_SPREAD that we want as well to average the memory placement cost. Reported-by: Vlastimil Babka Fixes: 3acd48507dc4 ("btrfs: fix allocation of free space cache v1 bitmap pages") CC: stable@vger.kernel.org # 5.4+ Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ea5ede619220..5092dea21448 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9005,7 +9005,7 @@ int __init btrfs_init_cachep(void) btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap", PAGE_SIZE, PAGE_SIZE, - SLAB_RED_ZONE, NULL); + SLAB_MEM_SPREAD, NULL); if (!btrfs_free_space_bitmap_cachep) goto fail; -- cgit v1.2.3 From dbcc7d57bffc0c8cac9dac11bec548597d59a6a5 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 11 Mar 2021 14:31:05 +0000 Subject: btrfs: fix race when cloning extent buffer during rewind of an old root While resolving backreferences, as part of a logical ino ioctl call or fiemap, we can end up hitting a BUG_ON() when replaying tree mod log operations of a root, triggering a stack trace like the following: ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:1210! invalid opcode: 0000 [#1] SMP KASAN PTI CPU: 1 PID: 19054 Comm: crawl_335 Tainted: G W 5.11.0-2d11c0084b02-misc-next+ #89 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 RIP: 0010:__tree_mod_log_rewind+0x3b1/0x3c0 Code: 05 48 8d 74 10 (...) RSP: 0018:ffffc90001eb70b8 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffff88812344e400 RCX: ffffffffb28933b6 RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff88812344e42c RBP: ffffc90001eb7108 R08: 1ffff11020b60a20 R09: ffffed1020b60a20 R10: ffff888105b050f9 R11: ffffed1020b60a1f R12: 00000000000000ee R13: ffff8880195520c0 R14: ffff8881bc958500 R15: ffff88812344e42c FS: 00007fd1955e8700(0000) GS:ffff8881f5600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007efdb7928718 CR3: 000000010103a006 CR4: 0000000000170ee0 Call Trace: btrfs_search_old_slot+0x265/0x10d0 ? lock_acquired+0xbb/0x600 ? btrfs_search_slot+0x1090/0x1090 ? free_extent_buffer.part.61+0xd7/0x140 ? free_extent_buffer+0x13/0x20 resolve_indirect_refs+0x3e9/0xfc0 ? lock_downgrade+0x3d0/0x3d0 ? __kasan_check_read+0x11/0x20 ? add_prelim_ref.part.11+0x150/0x150 ? lock_downgrade+0x3d0/0x3d0 ? __kasan_check_read+0x11/0x20 ? lock_acquired+0xbb/0x600 ? __kasan_check_write+0x14/0x20 ? do_raw_spin_unlock+0xa8/0x140 ? rb_insert_color+0x30/0x360 ? prelim_ref_insert+0x12d/0x430 find_parent_nodes+0x5c3/0x1830 ? resolve_indirect_refs+0xfc0/0xfc0 ? lock_release+0xc8/0x620 ? fs_reclaim_acquire+0x67/0xf0 ? lock_acquire+0xc7/0x510 ? lock_downgrade+0x3d0/0x3d0 ? lockdep_hardirqs_on_prepare+0x160/0x210 ? lock_release+0xc8/0x620 ? fs_reclaim_acquire+0x67/0xf0 ? lock_acquire+0xc7/0x510 ? poison_range+0x38/0x40 ? unpoison_range+0x14/0x40 ? trace_hardirqs_on+0x55/0x120 btrfs_find_all_roots_safe+0x142/0x1e0 ? find_parent_nodes+0x1830/0x1830 ? btrfs_inode_flags_to_xflags+0x50/0x50 iterate_extent_inodes+0x20e/0x580 ? tree_backref_for_extent+0x230/0x230 ? lock_downgrade+0x3d0/0x3d0 ? read_extent_buffer+0xdd/0x110 ? lock_downgrade+0x3d0/0x3d0 ? __kasan_check_read+0x11/0x20 ? lock_acquired+0xbb/0x600 ? __kasan_check_write+0x14/0x20 ? _raw_spin_unlock+0x22/0x30 ? __kasan_check_write+0x14/0x20 iterate_inodes_from_logical+0x129/0x170 ? iterate_inodes_from_logical+0x129/0x170 ? btrfs_inode_flags_to_xflags+0x50/0x50 ? iterate_extent_inodes+0x580/0x580 ? __vmalloc_node+0x92/0xb0 ? init_data_container+0x34/0xb0 ? init_data_container+0x34/0xb0 ? kvmalloc_node+0x60/0x80 btrfs_ioctl_logical_to_ino+0x158/0x230 btrfs_ioctl+0x205e/0x4040 ? __might_sleep+0x71/0xe0 ? btrfs_ioctl_get_supported_features+0x30/0x30 ? getrusage+0x4b6/0x9c0 ? __kasan_check_read+0x11/0x20 ? lock_release+0xc8/0x620 ? __might_fault+0x64/0xd0 ? lock_acquire+0xc7/0x510 ? lock_downgrade+0x3d0/0x3d0 ? lockdep_hardirqs_on_prepare+0x210/0x210 ? lockdep_hardirqs_on_prepare+0x210/0x210 ? __kasan_check_read+0x11/0x20 ? do_vfs_ioctl+0xfc/0x9d0 ? ioctl_file_clone+0xe0/0xe0 ? lock_downgrade+0x3d0/0x3d0 ? lockdep_hardirqs_on_prepare+0x210/0x210 ? __kasan_check_read+0x11/0x20 ? lock_release+0xc8/0x620 ? __task_pid_nr_ns+0xd3/0x250 ? lock_acquire+0xc7/0x510 ? __fget_files+0x160/0x230 ? __fget_light+0xf2/0x110 __x64_sys_ioctl+0xc3/0x100 do_syscall_64+0x37/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fd1976e2427 Code: 00 00 90 48 8b 05 (...) RSP: 002b:00007fd1955e5cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fd1955e5f40 RCX: 00007fd1976e2427 RDX: 00007fd1955e5f48 RSI: 00000000c038943b RDI: 0000000000000004 RBP: 0000000001000000 R08: 0000000000000000 R09: 00007fd1955e6120 R10: 0000557835366b00 R11: 0000000000000246 R12: 0000000000000004 R13: 00007fd1955e5f48 R14: 00007fd1955e5f40 R15: 00007fd1955e5ef8 Modules linked in: ---[ end trace ec8931a1c36e57be ]--- (gdb) l *(__tree_mod_log_rewind+0x3b1) 0xffffffff81893521 is in __tree_mod_log_rewind (fs/btrfs/ctree.c:1210). 1205 * the modification. as we're going backwards, we do the 1206 * opposite of each operation here. 1207 */ 1208 switch (tm->op) { 1209 case MOD_LOG_KEY_REMOVE_WHILE_FREEING: 1210 BUG_ON(tm->slot < n); 1211 fallthrough; 1212 case MOD_LOG_KEY_REMOVE_WHILE_MOVING: 1213 case MOD_LOG_KEY_REMOVE: 1214 btrfs_set_node_key(eb, &tm->key, tm->slot); Here's what happens to hit that BUG_ON(): 1) We have one tree mod log user (through fiemap or the logical ino ioctl), with a sequence number of 1, so we have fs_info->tree_mod_seq == 1; 2) Another task is at ctree.c:balance_level() and we have eb X currently as the root of the tree, and we promote its single child, eb Y, as the new root. Then, at ctree.c:balance_level(), we call: tree_mod_log_insert_root(eb X, eb Y, 1); 3) At tree_mod_log_insert_root() we create tree mod log elements for each slot of eb X, of operation type MOD_LOG_KEY_REMOVE_WHILE_FREEING each with a ->logical pointing to ebX->start. These are placed in an array named tm_list. Lets assume there are N elements (N pointers in eb X); 4) Then, still at tree_mod_log_insert_root(), we create a tree mod log element of operation type MOD_LOG_ROOT_REPLACE, ->logical set to ebY->start, ->old_root.logical set to ebX->start, ->old_root.level set to the level of eb X and ->generation set to the generation of eb X; 5) Then tree_mod_log_insert_root() calls tree_mod_log_free_eb() with tm_list as argument. After that, tree_mod_log_free_eb() calls __tree_mod_log_insert() for each member of tm_list in reverse order, from highest slot in eb X, slot N - 1, to slot 0 of eb X; 6) __tree_mod_log_insert() sets the sequence number of each given tree mod log operation - it increments fs_info->tree_mod_seq and sets fs_info->tree_mod_seq as the sequence number of the given tree mod log operation. This means that for the tm_list created at tree_mod_log_insert_root(), the element corresponding to slot 0 of eb X has the highest sequence number (1 + N), and the element corresponding to the last slot has the lowest sequence number (2); 7) Then, after inserting tm_list's elements into the tree mod log rbtree, the MOD_LOG_ROOT_REPLACE element is inserted, which gets the highest sequence number, which is N + 2; 8) Back to ctree.c:balance_level(), we free eb X by calling btrfs_free_tree_block() on it. Because eb X was created in the current transaction, has no other references and writeback did not happen for it, we add it back to the free space cache/tree; 9) Later some other task T allocates the metadata extent from eb X, since it is marked as free space in the space cache/tree, and uses it as a node for some other btree; 10) The tree mod log user task calls btrfs_search_old_slot(), which calls get_old_root(), and finally that calls __tree_mod_log_oldest_root() with time_seq == 1 and eb_root == eb Y; 11) First iteration of the while loop finds the tree mod log element with sequence number N + 2, for the logical address of eb Y and of type MOD_LOG_ROOT_REPLACE; 12) Because the operation type is MOD_LOG_ROOT_REPLACE, we don't break out of the loop, and set root_logical to point to tm->old_root.logical which corresponds to the logical address of eb X; 13) On the next iteration of the while loop, the call to tree_mod_log_search_oldest() returns the smallest tree mod log element for the logical address of eb X, which has a sequence number of 2, an operation type of MOD_LOG_KEY_REMOVE_WHILE_FREEING and corresponds to the old slot N - 1 of eb X (eb X had N items in it before being freed); 14) We then break out of the while loop and return the tree mod log operation of type MOD_LOG_ROOT_REPLACE (eb Y), and not the one for slot N - 1 of eb X, to get_old_root(); 15) At get_old_root(), we process the MOD_LOG_ROOT_REPLACE operation and set "logical" to the logical address of eb X, which was the old root. We then call tree_mod_log_search() passing it the logical address of eb X and time_seq == 1; 16) Then before calling tree_mod_log_search(), task T adds a key to eb X, which results in adding a tree mod log operation of type MOD_LOG_KEY_ADD to the tree mod log - this is done at ctree.c:insert_ptr() - but after adding the tree mod log operation and before updating the number of items in eb X from 0 to 1... 17) The task at get_old_root() calls tree_mod_log_search() and gets the tree mod log operation of type MOD_LOG_KEY_ADD just added by task T. Then it enters the following if branch: if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) { (...) } (...) Calls read_tree_block() for eb X, which gets a reference on eb X but does not lock it - task T has it locked. Then it clones eb X while it has nritems set to 0 in its header, before task T sets nritems to 1 in eb X's header. From hereupon we use the clone of eb X which no other task has access to; 18) Then we call __tree_mod_log_rewind(), passing it the MOD_LOG_KEY_ADD mod log operation we just got from tree_mod_log_search() in the previous step and the cloned version of eb X; 19) At __tree_mod_log_rewind(), we set the local variable "n" to the number of items set in eb X's clone, which is 0. Then we enter the while loop, and in its first iteration we process the MOD_LOG_KEY_ADD operation, which just decrements "n" from 0 to (u32)-1, since "n" is declared with a type of u32. At the end of this iteration we call rb_next() to find the next tree mod log operation for eb X, that gives us the mod log operation of type MOD_LOG_KEY_REMOVE_WHILE_FREEING, for slot 0, with a sequence number of N + 1 (steps 3 to 6); 20) Then we go back to the top of the while loop and trigger the following BUG_ON(): (...) switch (tm->op) { case MOD_LOG_KEY_REMOVE_WHILE_FREEING: BUG_ON(tm->slot < n); fallthrough; (...) Because "n" has a value of (u32)-1 (4294967295) and tm->slot is 0. Fix this by taking a read lock on the extent buffer before cloning it at ctree.c:get_old_root(). This should be done regardless of the extent buffer having been freed and reused, as a concurrent task might be modifying it (while holding a write lock on it). Reported-by: Zygo Blaxell Link: https://lore.kernel.org/linux-btrfs/20210227155037.GN28049@hungrycats.org/ Fixes: 834328a8493079 ("Btrfs: tree mod log's old roots could still be part of the tree") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d56730a67885..34b929bd5c1a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1365,7 +1365,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) "failed to read tree block %llu from get_old_root", logical); } else { + btrfs_tree_read_lock(old); eb = btrfs_clone_extent_buffer(old); + btrfs_tree_read_unlock(old); free_extent_buffer(old); } } else if (old_root) { -- cgit v1.2.3 From 485df75554257e883d0ce39bb886e8212349748e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 11 Mar 2021 14:31:06 +0000 Subject: btrfs: always pin deleted leaves when there are active tree mod log users When freeing a tree block we may end up adding its extent back to the free space cache/tree, as long as there are no more references for it, it was created in the current transaction and writeback for it never happened. This is generally fine, however when we have tree mod log operations it can result in inconsistent versions of a btree after unwinding extent buffers with the recorded tree mod log operations. This is because: * We only log operations for nodes (adding and removing key/pointers), for leaves we don't do anything; * This means that we can log a MOD_LOG_KEY_REMOVE_WHILE_FREEING operation for a node that points to a leaf that was deleted; * Before we apply the logged operation to unwind a node, we can have that leaf's extent allocated again, either as a node or as a leaf, and possibly for another btree. This is possible if the leaf was created in the current transaction and writeback for it never started, in which case btrfs_free_tree_block() returns its extent back to the free space cache/tree; * Then, before applying the tree mod log operation, some task allocates the metadata extent just freed before, and uses it either as a leaf or as a node for some btree (can be the same or another one, it does not matter); * After applying the MOD_LOG_KEY_REMOVE_WHILE_FREEING operation we now get the target node with an item pointing to the metadata extent that now has content different from what it had before the leaf was deleted. It might now belong to a different btree and be a node and not a leaf anymore. As a consequence, the results of searches after the unwinding can be unpredictable and produce unexpected results. So make sure we pin extent buffers corresponding to leaves when there are tree mod log users. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 78ad31a59e59..36a3c973fda1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3323,6 +3323,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (last_ref && btrfs_header_generation(buf) == trans->transid) { struct btrfs_block_group *cache; + bool must_pin = false; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); @@ -3340,7 +3341,27 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } - if (btrfs_is_zoned(fs_info)) { + /* + * If this is a leaf and there are tree mod log users, we may + * have recorded mod log operations that point to this leaf. + * So we must make sure no one reuses this leaf's extent before + * mod log operations are applied to a node, otherwise after + * rewinding a node using the mod log operations we get an + * inconsistent btree, as the leaf's extent may now be used as + * a node or leaf for another different btree. + * We are safe from races here because at this point no other + * node or root points to this extent buffer, so if after this + * check a new tree mod log user joins, it will not be able to + * find a node pointing to this leaf and record operations that + * point to this leaf. + */ + if (btrfs_header_level(buf) == 0) { + read_lock(&fs_info->tree_mod_log_lock); + must_pin = !list_empty(&fs_info->tree_mod_seq_list); + read_unlock(&fs_info->tree_mod_log_lock); + } + + if (must_pin || btrfs_is_zoned(fs_info)) { btrfs_redirty_list_add(trans->transaction, buf); pin_down_extent(trans, cache, buf->start, buf->len, 1); btrfs_put_block_group(cache); -- cgit v1.2.3