From 038ec2c13e0d1f7b9d45a081786f18f75b65f11b Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 25 Mar 2019 14:31:21 +0200 Subject: btrfs: Honour FITRIM range constraints during free space trim commit c2d1b3aae33605a61cbab445d8ae1c708ccd2698 upstream. Up until now trimming the freespace was done irrespective of what the arguments of the FITRIM ioctl were. For example fstrim's -o/-l arguments will be entirely ignored. Fix it by correctly handling those paramter. This requires breaking if the found freespace extent is after the end of the passed range as well as completing trim after trimming fstrim_range::len bytes. Fixes: 499f377f49f0 ("btrfs: iterate over unused chunk space in FITRIM") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent-tree.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7938c48c72ff..6b29165f766f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11150,9 +11150,9 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) * transaction. */ static int btrfs_trim_free_extents(struct btrfs_device *device, - u64 minlen, u64 *trimmed) + struct fstrim_range *range, u64 *trimmed) { - u64 start = 0, len = 0; + u64 start = range->start, len = 0; int ret; *trimmed = 0; @@ -11188,8 +11188,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, atomic_inc(&trans->use_count); spin_unlock(&fs_info->trans_lock); - ret = find_free_dev_extent_start(trans, device, minlen, start, - &start, &len); + ret = find_free_dev_extent_start(trans, device, range->minlen, + start, &start, &len); if (trans) btrfs_put_transaction(trans); @@ -11201,6 +11201,16 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, break; } + /* If we are out of the passed range break */ + if (start > range->start + range->len - 1) { + mutex_unlock(&fs_info->chunk_mutex); + ret = 0; + break; + } + + start = max(range->start, start); + len = min(range->len, len); + ret = btrfs_issue_discard(device->bdev, start, len, &bytes); up_read(&fs_info->commit_root_sem); mutex_unlock(&fs_info->chunk_mutex); @@ -11211,6 +11221,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; + /* We've trimmed enough */ + if (*trimmed >= range->len) + break; + if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11295,8 +11309,7 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range->minlen, - &group_trimmed); + ret = btrfs_trim_free_extents(device, range, &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; -- cgit v1.2.3 From abc261c8b99de79b7a249cfe05760565eab08e5f Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 29 May 2019 19:25:45 +0200 Subject: Revert "btrfs: Honour FITRIM range constraints during free space trim" This reverts commit 038ec2c13e0d1f7b9d45a081786f18f75b65f11b. There is currently no corresponding patch in master due to additional changes that would be significantly different from plain revert in the respective stable branch. The range argument was not handled correctly and could cause trim to overlap allocated areas or reach beyond the end of the device. The address space that fitrim normally operates on is in logical coordinates, while the discards are done on the physical device extents. This distinction cannot be made with the current ioctl interface and caused the confusion. The bug depends on the layout of block groups and does not always happen. The whole-fs trim (run by default by the fstrim tool) is not affected. Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent-tree.c | 25 ++++++------------------- 1 file changed, 6 insertions(+), 19 deletions(-) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6b29165f766f..7938c48c72ff 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11150,9 +11150,9 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) * transaction. */ static int btrfs_trim_free_extents(struct btrfs_device *device, - struct fstrim_range *range, u64 *trimmed) + u64 minlen, u64 *trimmed) { - u64 start = range->start, len = 0; + u64 start = 0, len = 0; int ret; *trimmed = 0; @@ -11188,8 +11188,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, atomic_inc(&trans->use_count); spin_unlock(&fs_info->trans_lock); - ret = find_free_dev_extent_start(trans, device, range->minlen, - start, &start, &len); + ret = find_free_dev_extent_start(trans, device, minlen, start, + &start, &len); if (trans) btrfs_put_transaction(trans); @@ -11201,16 +11201,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, break; } - /* If we are out of the passed range break */ - if (start > range->start + range->len - 1) { - mutex_unlock(&fs_info->chunk_mutex); - ret = 0; - break; - } - - start = max(range->start, start); - len = min(range->len, len); - ret = btrfs_issue_discard(device->bdev, start, len, &bytes); up_read(&fs_info->commit_root_sem); mutex_unlock(&fs_info->chunk_mutex); @@ -11221,10 +11211,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; - /* We've trimmed enough */ - if (*trimmed >= range->len) - break; - if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11309,7 +11295,8 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range, &group_trimmed); + ret = btrfs_trim_free_extents(device, range->minlen, + &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; -- cgit v1.2.3 From d43c355a7c19630ab99aeab0477eaeab8a1f6fa5 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 16 Jul 2019 17:00:33 +0800 Subject: btrfs: extent-tree: Make sure we only allocate extents from block groups with the same type [ Upstream commit 2a28468e525f3924efed7f29f2bc5a2926e7e19a ] [BUG] With fuzzed image and MIXED_GROUPS super flag, we can hit the following BUG_ON(): kernel BUG at fs/btrfs/delayed-ref.c:491! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 1849 Comm: sync Tainted: G O 5.2.0-custom #27 RIP: 0010:update_existing_head_ref.cold+0x44/0x46 [btrfs] Call Trace: add_delayed_ref_head+0x20c/0x2d0 [btrfs] btrfs_add_delayed_tree_ref+0x1fc/0x490 [btrfs] btrfs_free_tree_block+0x123/0x380 [btrfs] __btrfs_cow_block+0x435/0x500 [btrfs] btrfs_cow_block+0x110/0x240 [btrfs] btrfs_search_slot+0x230/0xa00 [btrfs] ? __lock_acquire+0x105e/0x1e20 btrfs_insert_empty_items+0x67/0xc0 [btrfs] alloc_reserved_file_extent+0x9e/0x340 [btrfs] __btrfs_run_delayed_refs+0x78e/0x1240 [btrfs] ? kvm_clock_read+0x18/0x30 ? __sched_clock_gtod_offset+0x21/0x50 btrfs_run_delayed_refs.part.0+0x4e/0x180 [btrfs] btrfs_run_delayed_refs+0x23/0x30 [btrfs] btrfs_commit_transaction+0x53/0x9f0 [btrfs] btrfs_sync_fs+0x7c/0x1c0 [btrfs] ? __ia32_sys_fdatasync+0x20/0x20 sync_fs_one_sb+0x23/0x30 iterate_supers+0x95/0x100 ksys_sync+0x62/0xb0 __ia32_sys_sync+0xe/0x20 do_syscall_64+0x65/0x240 entry_SYSCALL_64_after_hwframe+0x49/0xbe [CAUSE] This situation is caused by several factors: - Fuzzed image The extent tree of this fs missed one backref for extent tree root. So we can allocated space from that slot. - MIXED_BG feature Super block has MIXED_BG flag. - No mixed block groups exists All block groups are just regular ones. This makes data space_info->block_groups[] contains metadata block groups. And when we reserve space for data, we can use space in metadata block group. Then we hit the following file operations: - fallocate We need to allocate data extents. find_free_extent() choose to use the metadata block to allocate space from, and choose the space of extent tree root, since its backref is missing. This generate one delayed ref head with is_data = 1. - extent tree update We need to update extent tree at run_delayed_ref time. This generate one delayed ref head with is_data = 0, for the same bytenr of old extent tree root. Then we trigger the BUG_ON(). [FIX] The quick fix here is to check block_group->flags before using it. The problem can only happen for MIXED_GROUPS fs. Regular filesystems won't have space_info with DATA|METADATA flag, and no way to hit the bug. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203255 Reported-by: Jungyeon Yoon Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/extent-tree.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7938c48c72ff..f3a251234474 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7571,6 +7571,14 @@ search: */ if ((flags & extra) && !(block_group->flags & extra)) goto loop; + + /* + * This block group has different flags than we want. + * It's possible that we have MIXED_GROUP flag but no + * block group is mixed. Just skip such block group. + */ + btrfs_release_block_group(block_group, delalloc); + continue; } have_block_group: -- cgit v1.2.3 From 615e9f196d9e829a734a8a78aa0c52dcd4657557 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 10 Oct 2019 10:39:26 +0800 Subject: btrfs: block-group: Fix a memory leak due to missing btrfs_put_block_group() commit 4b654acdae850f48b8250b9a578a4eaa518c7a6f upstream. In btrfs_read_block_groups(), if we have an invalid block group which has mixed type (DATA|METADATA) while the fs doesn't have MIXED_GROUPS feature, we error out without freeing the block group cache. This patch will add the missing btrfs_put_block_group() to prevent memory leak. Note for stable backports: the file to patch in versions <= 5.3 is fs/btrfs/extent-tree.c Fixes: 49303381f19a ("Btrfs: bail out if block group has different mixed flag") CC: stable@vger.kernel.org # 4.9+ Reviewed-by: Anand Jain Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent-tree.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f3a251234474..538f378eea52 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10325,6 +10325,7 @@ int btrfs_read_block_groups(struct btrfs_root *root) btrfs_err(info, "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", cache->key.objectid); + btrfs_put_block_group(cache); ret = -EINVAL; goto error; } -- cgit v1.2.3