From 580c079b5766ac706f56eec5c79aee4bf929fef6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 13 Jul 2020 15:11:56 +0100 Subject: btrfs: fix double free on ulist after backref resolution failure At btrfs_find_all_roots_safe() we allocate a ulist and set the **roots argument to point to it. However if later we fail due to an error returned by find_parent_nodes(), we free that ulist but leave a dangling pointer in the **roots argument. Upon receiving the error, a caller of this function can attempt to free the same ulist again, resulting in an invalid memory access. One such scenario is during qgroup accounting: btrfs_qgroup_account_extents() --> calls btrfs_find_all_roots() passes &new_roots (a stack allocated pointer) to btrfs_find_all_roots() --> btrfs_find_all_roots() just calls btrfs_find_all_roots_safe() passing &new_roots to it --> allocates ulist and assigns its address to **roots (which points to new_roots from btrfs_qgroup_account_extents()) --> find_parent_nodes() returns an error, so we free the ulist and leave **roots pointing to it after returning --> btrfs_qgroup_account_extents() sees btrfs_find_all_roots() returned an error and jumps to the label 'cleanup', which just tries to free again the same ulist Stack trace example: ------------[ cut here ]------------ BTRFS: tree first key check failed WARNING: CPU: 1 PID: 1763215 at fs/btrfs/disk-io.c:422 btrfs_verify_level_key+0xe0/0x180 [btrfs] Modules linked in: dm_snapshot dm_thin_pool (...) CPU: 1 PID: 1763215 Comm: fsstress Tainted: G W 5.8.0-rc3-btrfs-next-64 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:btrfs_verify_level_key+0xe0/0x180 [btrfs] Code: 28 5b 5d (...) RSP: 0018:ffffb89b473779a0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff90397759bf08 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000027 RDI: 00000000ffffffff RBP: ffff9039a419c000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffffb89b43301000 R12: 000000000000005e R13: ffffb89b47377a2e R14: ffffb89b473779af R15: 0000000000000000 FS: 00007fc47e1e1000(0000) GS:ffff9039ac200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc47e1df000 CR3: 00000003d9e4e001 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: read_block_for_search+0xf6/0x350 [btrfs] btrfs_next_old_leaf+0x242/0x650 [btrfs] resolve_indirect_refs+0x7cf/0x9e0 [btrfs] find_parent_nodes+0x4ea/0x12c0 [btrfs] btrfs_find_all_roots_safe+0xbf/0x130 [btrfs] btrfs_qgroup_account_extents+0x9d/0x390 [btrfs] btrfs_commit_transaction+0x4f7/0xb20 [btrfs] btrfs_sync_file+0x3d4/0x4d0 [btrfs] do_fsync+0x38/0x70 __x64_sys_fdatasync+0x13/0x20 do_syscall_64+0x5c/0xe0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fc47e2d72e3 Code: Bad RIP value. RSP: 002b:00007fffa32098c8 EFLAGS: 00000246 ORIG_RAX: 000000000000004b RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fc47e2d72e3 RDX: 00007fffa3209830 RSI: 00007fffa3209830 RDI: 0000000000000003 RBP: 000000000000072e R08: 0000000000000001 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000000003e8 R13: 0000000051eb851f R14: 00007fffa3209970 R15: 00005607c4ac8b50 irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [] copy_process+0x755/0x1eb0 softirqs last enabled at (0): [] copy_process+0x755/0x1eb0 softirqs last disabled at (0): [<0000000000000000>] 0x0 ---[ end trace 8639237550317b48 ]--- BTRFS error (device sdc): tree first key mismatch detected, bytenr=62324736 parent_transid=94 key expected=(262,108,1351680) has=(259,108,1921024) general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI CPU: 2 PID: 1763215 Comm: fsstress Tainted: G W 5.8.0-rc3-btrfs-next-64 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:ulist_release+0x14/0x60 [btrfs] Code: c7 07 00 (...) RSP: 0018:ffffb89b47377d60 EFLAGS: 00010282 RAX: 6b6b6b6b6b6b6b6b RBX: ffff903959b56b90 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000270024 RDI: ffff9036e2adc840 RBP: ffff9036e2adc848 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9036e2adc840 R13: 0000000000000015 R14: ffff9039a419ccf8 R15: ffff90395d605840 FS: 00007fc47e1e1000(0000) GS:ffff9039ac600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8c1c0a51c8 CR3: 00000003d9e4e004 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ulist_free+0x13/0x20 [btrfs] btrfs_qgroup_account_extents+0xf3/0x390 [btrfs] btrfs_commit_transaction+0x4f7/0xb20 [btrfs] btrfs_sync_file+0x3d4/0x4d0 [btrfs] do_fsync+0x38/0x70 __x64_sys_fdatasync+0x13/0x20 do_syscall_64+0x5c/0xe0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fc47e2d72e3 Code: Bad RIP value. RSP: 002b:00007fffa32098c8 EFLAGS: 00000246 ORIG_RAX: 000000000000004b RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fc47e2d72e3 RDX: 00007fffa3209830 RSI: 00007fffa3209830 RDI: 0000000000000003 RBP: 000000000000072e R08: 0000000000000001 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000000003e8 R13: 0000000051eb851f R14: 00007fffa3209970 R15: 00005607c4ac8b50 Modules linked in: dm_snapshot dm_thin_pool (...) ---[ end trace 8639237550317b49 ]--- RIP: 0010:ulist_release+0x14/0x60 [btrfs] Code: c7 07 00 (...) RSP: 0018:ffffb89b47377d60 EFLAGS: 00010282 RAX: 6b6b6b6b6b6b6b6b RBX: ffff903959b56b90 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000270024 RDI: ffff9036e2adc840 RBP: ffff9036e2adc848 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9036e2adc840 R13: 0000000000000015 R14: ffff9039a419ccf8 R15: ffff90395d605840 FS: 00007fc47e1e1000(0000) GS:ffff9039ad200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6a776f7d40 CR3: 00000003d9e4e002 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fix this by making btrfs_find_all_roots_safe() set *roots to NULL after it frees the ulist. Fixes: 8da6d5815c592b ("Btrfs: added btrfs_find_all_roots()") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/backref.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d888e71e66b6..ea10f7bc99ab 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1461,6 +1461,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); + *roots = NULL; return ret; } node = ulist_next(tmp, &uiter); -- cgit v1.2.3 From fa91e4aa1716004ea8096d5185ec0451e206aea0 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 17 Jul 2020 15:12:05 +0800 Subject: btrfs: qgroup: fix data leak caused by race between writeback and truncate [BUG] When running tests like generic/013 on test device with btrfs quota enabled, it can normally lead to data leak, detected at unmount time: BTRFS warning (device dm-3): qgroup 0/5 has unreleased space, type 0 rsv 4096 ------------[ cut here ]------------ WARNING: CPU: 11 PID: 16386 at fs/btrfs/disk-io.c:4142 close_ctree+0x1dc/0x323 [btrfs] RIP: 0010:close_ctree+0x1dc/0x323 [btrfs] Call Trace: btrfs_put_super+0x15/0x17 [btrfs] generic_shutdown_super+0x72/0x110 kill_anon_super+0x18/0x30 btrfs_kill_super+0x17/0x30 [btrfs] deactivate_locked_super+0x3b/0xa0 deactivate_super+0x40/0x50 cleanup_mnt+0x135/0x190 __cleanup_mnt+0x12/0x20 task_work_run+0x64/0xb0 __prepare_exit_to_usermode+0x1bc/0x1c0 __syscall_return_slowpath+0x47/0x230 do_syscall_64+0x64/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace caf08beafeca2392 ]--- BTRFS error (device dm-3): qgroup reserved space leaked [CAUSE] In the offending case, the offending operations are: 2/6: writev f2X[269 1 0 0 0 0] [1006997,67,288] 0 2/7: truncate f2X[269 1 0 0 48 1026293] 18388 0 The following sequence of events could happen after the writev(): CPU1 (writeback) | CPU2 (truncate) ----------------------------------------------------------------- btrfs_writepages() | |- extent_write_cache_pages() | |- Got page for 1003520 | | 1003520 is Dirty, no writeback | | So (!clear_page_dirty_for_io()) | | gets called for it | |- Now page 1003520 is Clean. | | | btrfs_setattr() | | |- btrfs_setsize() | | |- truncate_setsize() | | New i_size is 18388 |- __extent_writepage() | | |- page_offset() > i_size | |- btrfs_invalidatepage() | |- Page is clean, so no qgroup | callback executed This means, the qgroup reserved data space is not properly released in btrfs_invalidatepage() as the page is Clean. [FIX] Instead of checking the dirty bit of a page, call btrfs_qgroup_free_data() unconditionally in btrfs_invalidatepage(). As qgroup rsv are completely bound to the QGROUP_RESERVED bit of io_tree, not bound to page status, thus we won't cause double freeing anyway. Fixes: 0b34c261e235 ("btrfs: qgroup: Prevent qgroup->reserved from going subzero") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/inode.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 11f81a148350..b7dd5124941e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8136,20 +8136,17 @@ again: /* * Qgroup reserved space handler * Page here will be either - * 1) Already written to disk - * In this case, its reserved space is released from data rsv map - * and will be freed by delayed_ref handler finally. - * So even we call qgroup_free_data(), it won't decrease reserved - * space. - * 2) Not written to disk - * This means the reserved space should be freed here. However, - * if a truncate invalidates the page (by clearing PageDirty) - * and the page is accounted for while allocating extent - * in btrfs_check_data_free_space() we let delayed_ref to - * free the entire extent. + * 1) Already written to disk or ordered extent already submitted + * Then its QGROUP_RESERVED bit in io_tree is already cleaned. + * Qgroup will be handled by its qgroup_record then. + * btrfs_qgroup_free_data() call will do nothing here. + * + * 2) Not written to disk yet + * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED + * bit of its io_tree, and free the qgroup reserved data space. + * Since the IO will never happen for this page. */ - if (PageDirty(page)) - btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | -- cgit v1.2.3 From 5909ca110b29aa16b23b52b8de8d3bb1035fd738 Mon Sep 17 00:00:00 2001 From: Robbie Ko Date: Mon, 20 Jul 2020 09:42:09 +0800 Subject: btrfs: fix page leaks after failure to lock page for delalloc When locking pages for delalloc, we check if it's dirty and mapping still matches. If it does not match, we need to return -EAGAIN and release all pages. Only the current page was put though, iterate over all the remaining pages too. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Filipe Manana Reviewed-by: Nikolay Borisov Signed-off-by: Robbie Ko Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 95313bb7fe40..72c836b54efc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1999,7 +1999,8 @@ static int __process_pages_contig(struct address_space *mapping, if (!PageDirty(pages[i]) || pages[i]->mapping != mapping) { unlock_page(pages[i]); - put_page(pages[i]); + for (; i < ret; i++) + put_page(pages[i]); err = -EAGAIN; goto out; } -- cgit v1.2.3 From 48cfa61b58a1fee0bc49eef04f8ccf31493b7cdd Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Thu, 16 Jul 2020 13:29:46 -0700 Subject: btrfs: fix mount failure caused by race with umount It is possible to cause a btrfs mount to fail by racing it with a slow umount. The crux of the sequence is generic_shutdown_super not yet calling sop->put_super before btrfs_mount_root calls btrfs_open_devices. If that occurs, btrfs_open_devices will decide the opened counter is non-zero, increment it, and skip resetting fs_devices->total_rw_bytes to 0. From here, mount will call sget which will result in grab_super trying to take the super block umount semaphore. That semaphore will be held by the slow umount, so mount will block. Before up-ing the semaphore, umount will delete the super block, resulting in mount's sget reliably allocating a new one, which causes the mount path to dutifully fill it out, and increment total_rw_bytes a second time, which causes the mount to fail, as we see double the expected bytes. Here is the sequence laid out in greater detail: CPU0 CPU1 down_write sb->s_umount btrfs_kill_super kill_anon_super(sb) generic_shutdown_super(sb); shrink_dcache_for_umount(sb); sync_filesystem(sb); evict_inodes(sb); // SLOW btrfs_mount_root btrfs_scan_one_device fs_devices = device->fs_devices fs_info->fs_devices = fs_devices // fs_devices-opened makes this a no-op btrfs_open_devices(fs_devices, mode, fs_type) s = sget(fs_type, test, set, flags, fs_info); find sb in s_instances grab_super(sb); down_write(&s->s_umount); // blocks sop->put_super(sb) // sb->fs_devices->opened == 2; no-op spin_lock(&sb_lock); hlist_del_init(&sb->s_instances); spin_unlock(&sb_lock); up_write(&sb->s_umount); return 0; retry lookup don't find sb in s_instances (deleted by CPU0) s = alloc_super return s; btrfs_fill_super(s, fs_devices, data) open_ctree // fs_devices total_rw_bytes improperly set! btrfs_read_chunk_tree read_one_dev // increment total_rw_bytes again!! super_total_bytes < fs_devices->total_rw_bytes // ERROR!!! To fix this, we clear total_rw_bytes from within btrfs_read_chunk_tree before the calls to read_one_dev, while holding the sb umount semaphore and the uuid mutex. To reproduce, it is sufficient to dirty a decent number of inodes, then quickly umount and mount. for i in $(seq 0 500) do dd if=/dev/zero of="/mnt/foo/$i" bs=1M count=1 done umount /mnt/foo& mount /mnt/foo does the trick for me. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0d6e785bcb98..f403fb1e6d37 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7051,6 +7051,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) mutex_lock(&uuid_mutex); mutex_lock(&fs_info->chunk_mutex); + /* + * It is possible for mount and umount to race in such a way that + * we execute this code path, but open_fs_devices failed to clear + * total_rw_bytes. We certainly want it cleared before reading the + * device items, so clear it here. + */ + fs_info->fs_devices->total_rw_bytes = 0; + /* * Read all device items, and then all the chunk items. All * device items are found before any chunk item (their object id -- cgit v1.2.3