summaryrefslogtreecommitdiff
path: root/fs/btrfs/ctree.c
AgeCommit message (Collapse)AuthorFilesLines
2021-03-16btrfs: fix race when cloning extent buffer during rewind of an old rootFilipe Manana1-0/+2
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 <ce3g8jdj@umail.furryterror.org> 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 <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-09btrfs: fix extent buffer leak on failure to copy rootFilipe Manana1-0/+2
At btrfs_copy_root(), if the call to btrfs_inc_ref() fails we end up returning without unlocking and releasing our reference on the extent buffer named "cow" we previously allocated with btrfs_alloc_tree_block(). So fix that by unlocking the extent buffer and dropping our reference on it before returning. Fixes: be20aa9dbadc8c ("Btrfs: Add mount option to turn off data cow") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-09btrfs: abort the transaction if we fail to inc ref in btrfs_copy_rootJosef Bacik1-2/+3
While testing my error handling patches, I added a error injection site at btrfs_inc_extent_ref, to validate the error handling I added was doing the correct thing. However I hit a pretty ugly corruption while doing this check, with the following error injection stack trace: btrfs_inc_extent_ref btrfs_copy_root create_reloc_root btrfs_init_reloc_root btrfs_record_root_in_trans btrfs_start_transaction btrfs_update_inode btrfs_update_time touch_atime file_accessed btrfs_file_mmap This is because we do not catch the error from btrfs_inc_extent_ref, which in practice would be ENOMEM, which means we lose the extent references for a root that has already been allocated and inserted, which is the problem. Fix this by aborting the transaction if we fail to do the reference modification. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-09btrfs: allow error injection for btrfs_search_slot and btrfs_cow_blockJosef Bacik1-0/+2
The following patches are going to address error handling in relocation, in order to test those patches I need to be able to inject errors in btrfs_search_slot and btrfs_cow_block, as we call both of these pretty often in different cases during relocation. Reviewed-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-18btrfs: correctly calculate item size used when item key collision happensethanwu1-2/+22
Item key collision is allowed for some item types, like dir item and inode refs, but the overall item size is limited by the nodesize. item size(ins_len) passed from btrfs_insert_empty_items to btrfs_search_slot already contains size of btrfs_item. When btrfs_search_slot reaches leaf, we'll see if we need to split leaf. The check incorrectly reports that split leaf is required, because it treats the space required by the newly inserted item as btrfs_item + item data. But in item key collision case, only item data is actually needed, the newly inserted item could merge into the existing one. No new btrfs_item will be inserted. And split_leaf return EOVERFLOW from following code: if (extend && data_size + btrfs_item_size_nr(l, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(fs_info)) return -EOVERFLOW; In most cases, when callers receive EOVERFLOW, they either return this error or handle in different ways. For example, in normal dir item creation the userspace will get errno EOVERFLOW; in inode ref case INODE_EXTREF is used instead. However, this is not the case for rename. To avoid the unrecoverable situation in rename, btrfs_check_dir_item_collision is called in early phase of rename. In this function, when item key collision is detected leaf space is checked: data_size = sizeof(*di) + name_len; if (data_size + btrfs_item_size_nr(leaf, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(root->fs_info)) the sizeof(struct btrfs_item) + btrfs_item_size_nr(leaf, slot) here refers to existing item size, the condition here correctly calculates the needed size for collision case rather than the wrong case above. The consequence of inconsistent condition check between btrfs_check_dir_item_collision and btrfs_search_slot when item key collision happens is that we might pass check here but fail later at btrfs_search_slot. Rename fails and volume is forced readonly [436149.586170] ------------[ cut here ]------------ [436149.586173] BTRFS: Transaction aborted (error -75) [436149.586196] WARNING: CPU: 0 PID: 16733 at fs/btrfs/inode.c:9870 btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586227] CPU: 0 PID: 16733 Comm: python Tainted: G D 4.18.0-rc5+ #1 [436149.586228] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/05/2016 [436149.586238] RIP: 0010:btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586254] RSP: 0018:ffffa327043a7ce0 EFLAGS: 00010286 [436149.586255] RAX: 0000000000000000 RBX: ffff8d8a17d13340 RCX: 0000000000000006 [436149.586256] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff8d8a7fc164b0 [436149.586257] RBP: ffffa327043a7da0 R08: 0000000000000560 R09: 7265282064657472 [436149.586258] R10: 0000000000000000 R11: 6361736e61725420 R12: ffff8d8a0d4c8b08 [436149.586258] R13: ffff8d8a17d13340 R14: ffff8d8a33e0a540 R15: 00000000000001fe [436149.586260] FS: 00007fa313933740(0000) GS:ffff8d8a7fc00000(0000) knlGS:0000000000000000 [436149.586261] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [436149.586262] CR2: 000055d8d9c9a720 CR3: 000000007aae0003 CR4: 00000000003606f0 [436149.586295] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [436149.586296] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [436149.586296] Call Trace: [436149.586311] vfs_rename+0x383/0x920 [436149.586313] ? vfs_rename+0x383/0x920 [436149.586315] do_renameat2+0x4ca/0x590 [436149.586317] __x64_sys_rename+0x20/0x30 [436149.586324] do_syscall_64+0x5a/0x120 [436149.586330] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [436149.586332] RIP: 0033:0x7fa3133b1d37 [436149.586348] RSP: 002b:00007fffd3e43908 EFLAGS: 00000246 ORIG_RAX: 0000000000000052 [436149.586349] RAX: ffffffffffffffda RBX: 00007fa3133b1d30 RCX: 00007fa3133b1d37 [436149.586350] RDX: 000055d8da06b5e0 RSI: 000055d8da225d60 RDI: 000055d8da2c4da0 [436149.586351] RBP: 000055d8da2252f0 R08: 00007fa313782000 R09: 00000000000177e0 [436149.586351] R10: 000055d8da010680 R11: 0000000000000246 R12: 00007fa313840b00 Thanks to Hans van Kranenburg for information about crc32 hash collision tools, I was able to reproduce the dir item collision with following python script. https://github.com/wutzuchieh/misc_tools/blob/master/crc32_forge.py Run it under a btrfs volume will trigger the abort transaction. It simply creates files and rename them to forged names that leads to hash collision. There are two ways to fix this. One is to simply revert the patch 878f2d2cb355 ("Btrfs: fix max dir item size calculation") to make the condition consistent although that patch is correct about the size. The other way is to handle the leaf space check correctly when collision happens. I prefer the second one since it correct leaf space check in collision case. This fix will not account sizeof(struct btrfs_item) when the item already exists. There are two places where ins_len doesn't contain sizeof(struct btrfs_item), however. 1. extent-tree.c: lookup_inline_extent_backref 2. file-item.c: btrfs_csum_file_blocks to make the logic of btrfs_search_slot more clear, we add a flag search_for_extension in btrfs_path. This flag indicates that ins_len passed to btrfs_search_slot doesn't contain sizeof(struct btrfs_item). When key exists, btrfs_search_slot will use the actual size needed to calculate the required leaf space. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: ethanwu <ethanwu@synology.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-09btrfs: handle sectorsize < PAGE_SIZE case for extent buffer accessorsQu Wenruo1-1/+2
To support sectorsize < PAGE_SIZE case, we need to take extra care of extent buffer accessors. Since sectorsize is smaller than PAGE_SIZE, one page can contain multiple tree blocks, we must use eb->start to determine the real offset to read/write for extent buffer accessors. This patch introduces two helpers to do this: - get_eb_page_index() This is to calculate the index to access extent_buffer::pages. It's just a simple wrapper around "start >> PAGE_SHIFT". For sectorsize == PAGE_SIZE case, nothing is changed. For sectorsize < PAGE_SIZE case, we always get index as 0, and the existing page shift also works. - get_eb_offset_in_page() This is to calculate the offset to access extent_buffer::pages. This needs to take extent_buffer::start into consideration. For sectorsize == PAGE_SIZE case, extent_buffer::start is always aligned to PAGE_SIZE, thus adding extent_buffer::start to offset_in_page() won't change the result. For sectorsize < PAGE_SIZE case, adding extent_buffer::start gives us the correct offset to access. This patch will touch the following parts to cover all extent buffer accessors: - BTRFS_SETGET_HEADER_FUNCS() - read_extent_buffer() - read_extent_buffer_to_user() - memcmp_extent_buffer() - write_extent_buffer_chunk_tree_uuid() - write_extent_buffer_fsid() - write_extent_buffer() - memzero_extent_buffer() - copy_extent_buffer_full() - copy_extent_buffer() - memcpy_extent_buffer() - memmove_extent_buffer() - btrfs_get_token_##bits() - btrfs_get_##bits() - btrfs_set_token_##bits() - btrfs_set_##bits() - generic_bin_search() Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: simplify return values in setup_nodes_for_searchNikolay Borisov1-22/+8
The function is needlessly convoluted. Fix that by: * removing redundant sret variable definition in both if arms * replace the again/done labels with direct return statements, the function is short enough and doesn't do anything special upon exit * remove BUG_ON on split_node returning a positive number - it can't happen as split_node returns either 0 or a negative error code. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: remove useless return value statement in split_nodeNikolay Borisov1-2/+1
At the point when we set 'ret = 0' it's guaranteed that the function is going to return 0 so directly return 0. No functional changes. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: use btrfs_tree_read_lock in btrfs_search_slotJosef Bacik1-1/+1
We no longer use recursion, so __btrfs_tree_read_lock(BTRFS_NESTING_NORMAL) == btrfs_tree_read_lock. Replace this call with the simple helper. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: merge back btrfs_read_lock_root_node helpersJosef Bacik1-1/+1
We no longer have recursive locking and there's no need for separate helpers that allowed the transition to rwsem with minimal code changes. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: remove btrfs_path::recurseJosef Bacik1-3/+2
With my async free space cache loading patches ("btrfs: load free space cache asynchronously") we no longer have a user of path->recurse and can remove it. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: unlock to current level in btrfs_next_old_leafJosef Bacik1-15/+17
Filipe reported the following lockdep splat ====================================================== WARNING: possible circular locking dependency detected 5.10.0-rc2-btrfs-next-71 #1 Not tainted ------------------------------------------------------ find/324157 is trying to acquire lock: ffff8ebc48d293a0 (btrfs-tree-01#2/3){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] but task is already holding lock: ffff8eb9932c5088 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-tree-00){++++}-{3:3}: lock_acquire+0xd8/0x490 down_write_nested+0x44/0x120 __btrfs_tree_lock+0x27/0x120 [btrfs] btrfs_search_slot+0x2a3/0xc50 [btrfs] btrfs_insert_empty_items+0x58/0xa0 [btrfs] insert_with_overflow+0x44/0x110 [btrfs] btrfs_insert_xattr_item+0xb8/0x1d0 [btrfs] btrfs_setxattr+0xd6/0x4c0 [btrfs] btrfs_setxattr_trans+0x68/0x100 [btrfs] __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x70/0x200 vfs_setxattr+0x6b/0x120 setxattr+0x125/0x240 path_setxattr+0xba/0xd0 __x64_sys_setxattr+0x27/0x30 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #0 (btrfs-tree-01#2/3){++++}-{3:3}: check_prev_add+0x91/0xc60 __lock_acquire+0x1689/0x3130 lock_acquire+0xd8/0x490 down_read_nested+0x45/0x220 __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] btrfs_next_old_leaf+0x27d/0x580 [btrfs] btrfs_real_readdir+0x1e3/0x4b0 [btrfs] iterate_dir+0x170/0x1c0 __x64_sys_getdents64+0x83/0x140 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(btrfs-tree-00); lock(btrfs-tree-01#2/3); lock(btrfs-tree-00); lock(btrfs-tree-01#2/3); *** DEADLOCK *** 5 locks held by find/324157: #0: ffff8ebc502c6e00 (&f->f_pos_lock){+.+.}-{3:3}, at: __fdget_pos+0x4d/0x60 #1: ffff8eb97f689980 (&type->i_mutex_dir_key#10){++++}-{3:3}, at: iterate_dir+0x52/0x1c0 #2: ffff8ebaec00ca58 (btrfs-tree-02#2){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] #3: ffff8eb98f986f78 (btrfs-tree-01#2){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] #4: ffff8eb9932c5088 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] stack backtrace: CPU: 2 PID: 324157 Comm: find Not tainted 5.10.0-rc2-btrfs-next-71 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x8d/0xb5 check_noncircular+0xff/0x110 ? mark_lock.part.0+0x468/0xe90 check_prev_add+0x91/0xc60 __lock_acquire+0x1689/0x3130 ? kvm_clock_read+0x14/0x30 ? kvm_sched_clock_read+0x5/0x10 lock_acquire+0xd8/0x490 ? __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] down_read_nested+0x45/0x220 ? __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] __btrfs_tree_read_lock+0x32/0x1a0 [btrfs] btrfs_next_old_leaf+0x27d/0x580 [btrfs] btrfs_real_readdir+0x1e3/0x4b0 [btrfs] iterate_dir+0x170/0x1c0 __x64_sys_getdents64+0x83/0x140 ? filldir+0x1d0/0x1d0 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 This happens because btrfs_next_old_leaf searches down to our current key, and then walks up the path until we can move to the next slot, and then reads back down the path so we get the next leaf. However it doesn't unlock any lower levels until it replaces them with the new extent buffer. This is technically fine, but of course causes lockdep to complain, because we could be holding locks on lower levels while locking upper levels. Fix this by dropping all nodes below the level that we use as our new starting point before we start reading back down the path. This also allows us to drop the nested/recursive locking magic, because we're no longer locking two nodes at the same level anymore. Reported-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: cleanup the locking in btrfs_next_old_leafJosef Bacik1-10/+4
We are carrying around this next_rw_lock from when we would do spinning vs blocking read locks. Now that we have the rwsem locking we can simply use the read lock flag unconditionally and the read lock helpers. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: pass root owner to read_tree_blockJosef Bacik1-3/+5
In order to properly set the lockdep class of a newly allocated block we need to know the owner of the block. For non-refcounted trees this is straightforward, we always know in advance what tree we're reading from. For refcounted trees we don't necessarily know, however all refcounted trees share the same lockdep class name, tree-<level>. Fix all the callers of read_tree_block() to pass in the root objectid we're using. In places like relocation and backref we could probably unconditionally use 0, but just in case use the root when we have it, otherwise use 0 in the cases we don't have the root as it's going to be a refcounted tree anyway. This is a preparation patch for further changes. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: use btrfs_read_node_slot in btrfs_realloc_nodeJosef Bacik1-33/+3
We have this open-coded nightmare in btrfs_realloc_node that does the same thing that the normal read path does, which is to see if we have the eb in memory already, and if not read it, and verify the eb is uptodate. Delete this open coding and simply use btrfs_read_node_slot. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: cleanup extent buffer readaheadJosef Bacik1-36/+9
We're going to pass around more information when we allocate extent buffers, in order to make that cleaner how we do readahead. Most of the callers have the parent node that we're getting our blockptr from, with the sole exception of relocation which simply has the bytenr it wants to read. Add a helper that takes the current arguments that we need (bytenr and gen), and add another helper for simply reading the slot out of a node. In followup patches the helper that takes all the extra arguments will be expanded, and the simpler helper won't need to have it's arguments adjusted. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: locking: rip out path->leave_spinningJosef Bacik1-3/+0
We no longer distinguish between blocking and spinning, so rip out all this code. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-08btrfs: locking: remove all the blocking helpersJosef Bacik1-79/+12
Now that we're using a rw_semaphore we no longer need to indicate if a lock is blocking or not, nor do we need to flip the entire path from blocking to spinning. Remove these helpers and all the places they are called. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: cleanup cow block on errorJosef Bacik1-0/+6
In fstest btrfs/064 a transaction abort in __btrfs_cow_block could lead to a system lockup. It gets stuck trying to write back inodes, and the write back thread was trying to lock an extent buffer: $ cat /proc/2143497/stack [<0>] __btrfs_tree_lock+0x108/0x250 [<0>] lock_extent_buffer_for_io+0x35e/0x3a0 [<0>] btree_write_cache_pages+0x15a/0x3b0 [<0>] do_writepages+0x28/0xb0 [<0>] __writeback_single_inode+0x54/0x5c0 [<0>] writeback_sb_inodes+0x1e8/0x510 [<0>] wb_writeback+0xcc/0x440 [<0>] wb_workfn+0xd7/0x650 [<0>] process_one_work+0x236/0x560 [<0>] worker_thread+0x55/0x3c0 [<0>] kthread+0x13a/0x150 [<0>] ret_from_fork+0x1f/0x30 This is because we got an error while COWing a block, specifically here if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (ret) { btrfs_abort_transaction(trans, ret); return ret; } } [16402.241552] BTRFS: Transaction aborted (error -2) [16402.242362] WARNING: CPU: 1 PID: 2563188 at fs/btrfs/ctree.c:1074 __btrfs_cow_block+0x376/0x540 [16402.249469] CPU: 1 PID: 2563188 Comm: fsstress Not tainted 5.9.0-rc6+ #8 [16402.249936] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 [16402.250525] RIP: 0010:__btrfs_cow_block+0x376/0x540 [16402.252417] RSP: 0018:ffff9cca40e578b0 EFLAGS: 00010282 [16402.252787] RAX: 0000000000000025 RBX: 0000000000000002 RCX: ffff9132bbd19388 [16402.253278] RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff9132bbd19380 [16402.254063] RBP: ffff9132b41a49c0 R08: 0000000000000000 R09: 0000000000000000 [16402.254887] R10: 0000000000000000 R11: ffff91324758b080 R12: ffff91326ef17ce0 [16402.255694] R13: ffff91325fc0f000 R14: ffff91326ef176b0 R15: ffff9132815e2000 [16402.256321] FS: 00007f542c6d7b80(0000) GS:ffff9132bbd00000(0000) knlGS:0000000000000000 [16402.256973] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [16402.257374] CR2: 00007f127b83f250 CR3: 0000000133480002 CR4: 0000000000370ee0 [16402.257867] Call Trace: [16402.258072] btrfs_cow_block+0x109/0x230 [16402.258356] btrfs_search_slot+0x530/0x9d0 [16402.258655] btrfs_lookup_file_extent+0x37/0x40 [16402.259155] __btrfs_drop_extents+0x13c/0xd60 [16402.259628] ? btrfs_block_rsv_migrate+0x4f/0xb0 [16402.259949] btrfs_replace_file_extents+0x190/0x820 [16402.260873] btrfs_clone+0x9ae/0xc00 [16402.261139] btrfs_extent_same_range+0x66/0x90 [16402.261771] btrfs_remap_file_range+0x353/0x3b1 [16402.262333] vfs_dedupe_file_range_one.part.0+0xd5/0x140 [16402.262821] vfs_dedupe_file_range+0x189/0x220 [16402.263150] do_vfs_ioctl+0x552/0x700 [16402.263662] __x64_sys_ioctl+0x62/0xb0 [16402.264023] do_syscall_64+0x33/0x40 [16402.264364] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [16402.264862] RIP: 0033:0x7f542c7d15cb [16402.266901] RSP: 002b:00007ffd35944ea8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [16402.267627] RAX: ffffffffffffffda RBX: 00000000009d1968 RCX: 00007f542c7d15cb [16402.268298] RDX: 00000000009d2490 RSI: 00000000c0189436 RDI: 0000000000000003 [16402.268958] RBP: 00000000009d2520 R08: 0000000000000036 R09: 00000000009d2e64 [16402.269726] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000002 [16402.270659] R13: 000000000001f000 R14: 00000000009d1970 R15: 00000000009d2e80 [16402.271498] irq event stamp: 0 [16402.271846] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [16402.272497] hardirqs last disabled at (0): [<ffffffff910dbf59>] copy_process+0x6b9/0x1ba0 [16402.273343] softirqs last enabled at (0): [<ffffffff910dbf59>] copy_process+0x6b9/0x1ba0 [16402.273905] softirqs last disabled at (0): [<0000000000000000>] 0x0 [16402.274338] ---[ end trace 737874a5a41a8236 ]--- [16402.274669] BTRFS: error (device dm-9) in __btrfs_cow_block:1074: errno=-2 No such entry [16402.276179] BTRFS info (device dm-9): forced readonly [16402.277046] BTRFS: error (device dm-9) in btrfs_replace_file_extents:2723: errno=-2 No such entry [16402.278744] BTRFS: error (device dm-9) in __btrfs_cow_block:1074: errno=-2 No such entry [16402.279968] BTRFS: error (device dm-9) in __btrfs_cow_block:1074: errno=-2 No such entry [16402.280582] BTRFS info (device dm-9): balance: ended with status: -30 The problem here is that as soon as we allocate the new block it is locked and marked dirty in the btree inode. This means that we could attempt to writeback this block and need to lock the extent buffer. However we're not unlocking it here and thus we deadlock. Fix this by unlocking the cow block if we have any errors inside of __btrfs_cow_block, and also free it so we do not leak it. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: improve error message in setup_items_for_insertNikolay Borisov1-1/+2
Reword and update formats to match variable types. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> [ update formats ] Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: add kerneldoc for setup_items_for_insertNikolay Borisov1-4/+10
Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: sink total_data parameter in setup_items_for_insertNikolay Borisov1-4/+9
That parameter can easily be derived based on the "data_size" and "nr" parameters exploit this fact to simply the function's signature. No functional changes. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: eliminate total_size parameter from setup_items_for_insertNikolay Borisov1-6/+4
The value of this argument can be derived from the total_data as it's simply the value of the data size + size of btrfs_items being touched. Move the parameter calculation inside the function. This results in a simpler interface and also a minor size reduction: ./scripts/bloat-o-meter ctree.original fs/btrfs/ctree.o add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-34 (-34) Function old new delta btrfs_duplicate_item 260 259 -1 setup_items_for_insert 1200 1190 -10 btrfs_insert_empty_items 177 154 -23 Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: re-arrange statements in setup_items_for_insertNikolay Borisov1-1/+1
Rearrange statements calculating the offset of the newly added items so that the calculation has to be done only once. No functional change. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: use BTRFS_NESTED_NEW_ROOT for double splitsJosef Bacik1-1/+11
I've made this change separate since it requires both of the newly added NESTED flags and I didn't want to slip it into one of those changes. If we do a double split of a node we can end up doing a BTRFS_NESTED_SPLIT on level 0, which throws lockdep off because it appears as a double lock. Since we're maxed out on subclasses, use BTRFS_NESTED_NEW_ROOT if we had to do a double split. This is OK because we won't have to do a double split if we had to insert a new root, and the new root would be at a higher level anyway. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce BTRFS_NESTING_NEW_ROOT for adding new rootsJosef Bacik1-2/+3
The way we add new roots is confusing from a locking perspective for lockdep. We generally have the rule that we lock things in order from highest level to lowest, but in the case of adding a new level to the tree we actually allocate a new block for the root, which makes the locking go in reverse. A similar issue exists for snapshotting, we cow the original root for the root of a new tree, however they're at the same level. Address this by using BTRFS_NESTING_NEW_ROOT for these operations. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce BTRFS_NESTING_SPLIT for split blocksJosef Bacik1-2/+2
If we are splitting a leaf/node, we could do something like the following lock(leaf) BTRFS_NESTING_NORMAL lock(left) BTRFS_NESTING_LEFT + BTRFS_NESTING_COW push from leaf -> left reset path to point to left split left allocate new block, lock block BTRFS_NESTING_SPLIT at the new block point we need to have a different nesting level, because we have already used either BTRFS_NESTING_LEFT or BTRFS_NESTING_RIGHT when pushing items from the original leaf into the adjacent leaves. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce BTRFS_NESTING_LEFT/RIGHT_COWJosef Bacik1-6/+6
For similar reasons as BTRFS_NESTING_COW, we need BTRFS_NESTING_LEFT/RIGHT_COW. The pattern is this lock leaf -> BTRFS_NESTING_NORMAL cow leaf -> BTRFS_NESTING_COW split leaf lock left -> BTRFS_NESTING_LEFT cow left -> BTRFS_NESTING_LEFT_COW We need this in order to indicate to lockdep that these locks are discrete and are being taken in a safe order. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce BTRFS_NESTING_LEFT/BTRFS_NESTING_RIGHTJosef Bacik1-8/+8
Our lockdep maps are based on rootid+level, however in some cases we will lock adjacent blocks on the same level, namely in searching forward or in split/balance. Because of this lockdep will complain, so we need a separate subclass to indicate to lockdep that these are different locks. lock leaf -> BTRFS_NESTING_NORMAL cow leaf -> BTRFS_NESTING_COW split leaf lock left -> BTRFS_NESTING_LEFT lock right -> BTRFS_NESTING_RIGHT The above graph illustrates the need for this new nesting subclass. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce BTRFS_NESTING_COW for cow'ing blocksJosef Bacik1-20/+32
When we COW a block we are holding a lock on the original block, and then we lock the new COW block. Because our lockdep maps are based on root + level, this will make lockdep complain. We need a way to indicate a subclass for locking the COW'ed block, so plumb through our btrfs_lock_nesting from btrfs_cow_block down to the btrfs_init_buffer, and then introduce BTRFS_NESTING_COW to be used for cow'ing blocks. The reason I've added all this extra infrastructure is because there will be need of different nesting classes in follow up patches. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: add nesting tags to the locking helpersJosef Bacik1-3/+8
We will need these when we switch to an rwsem, so plumb in the infrastructure here to use later on. I violate the 80 character limit some here because it'll be cleaned up later. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: introduce btrfs_path::recurseJosef Bacik1-4/+4
Our current tree locking stuff allows us to recurse with read locks if we're already holding the write lock. This is necessary for the space cache inode, as we could be holding a lock on the root_tree root when we need to cache a block group, and thus need to be able to read down the root_tree to read in the inode cache. We can get away with this in our current locking, but we won't be able to with a rwsem. Handle this by purposefully annotating the places where we require recursion, so that in the future we can maybe come up with a way to avoid the recursion. In the case of the free space inode, this will be superseded by the free space tree. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: ctree: check key order before merging tree blocksQu Wenruo1-0/+74
[BUG] With a crafted image, btrfs can panic at btrfs_del_csums(): kernel BUG at fs/btrfs/ctree.c:3188! invalid opcode: 0000 [#1] SMP PTI CPU: 0 PID: 1156 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9 RIP: 0010:btrfs_set_item_key_safe+0x16c/0x180 RSP: 0018:ffff976141257ab8 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffff898a6b890930 RCX: 0000000004b70000 RDX: 0000000000000000 RSI: ffff976141257bae RDI: ffff976141257acf RBP: ffff976141257b10 R08: 0000000000001000 R09: ffff9761412579a8 R10: 0000000000000000 R11: 0000000000000000 R12: ffff976141257abe R13: 0000000000000003 R14: ffff898a6a8be578 R15: ffff976141257bae FS: 0000000000000000(0000) GS:ffff898a77a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f779d9cd624 CR3: 000000022b2b4006 CR4: 00000000000206f0 Call Trace: truncate_one_csum+0xac/0xf0 btrfs_del_csums+0x24f/0x3a0 __btrfs_free_extent.isra.72+0x5a7/0xbe0 __btrfs_run_delayed_refs+0x539/0x1120 btrfs_run_delayed_refs+0xdb/0x1b0 btrfs_commit_transaction+0x52/0x950 ? start_transaction+0x94/0x450 transaction_kthread+0x163/0x190 kthread+0x105/0x140 ? btrfs_cleanup_transaction+0x560/0x560 ? kthread_destroy_worker+0x50/0x50 ret_from_fork+0x35/0x40 Modules linked in: ---[ end trace 93bf9db00e6c374e ]--- [CAUSE] This crafted image has a tricky key order corruption: checksum tree key (CSUM_TREE ROOT_ITEM 0) node 29741056 level 1 items 14 free 107 generation 19 owner CSUM_TREE ... key (EXTENT_CSUM EXTENT_CSUM 73785344) block 29757440 gen 19 key (EXTENT_CSUM EXTENT_CSUM 77594624) block 29753344 gen 19 ... leaf 29757440 items 5 free space 150 generation 19 owner CSUM_TREE item 0 key (EXTENT_CSUM EXTENT_CSUM 73785344) itemoff 2323 itemsize 1672 range start 73785344 end 75497472 length 1712128 item 1 key (EXTENT_CSUM EXTENT_CSUM 75497472) itemoff 2319 itemsize 4 range start 75497472 end 75501568 length 4096 item 2 key (EXTENT_CSUM EXTENT_CSUM 75501568) itemoff 579 itemsize 1740 range start 75501568 end 77283328 length 1781760 item 3 key (EXTENT_CSUM EXTENT_CSUM 77283328) itemoff 575 itemsize 4 range start 77283328 end 77287424 length 4096 item 4 key (EXTENT_CSUM EXTENT_CSUM 4120596480) itemoff 275 itemsize 300 <<< range start 4120596480 end 4120903680 length 307200 leaf 29753344 items 3 free space 1936 generation 19 owner CSUM_TREE item 0 key (18446744073457893366 EXTENT_CSUM 77594624) itemoff 2323 itemsize 1672 range start 77594624 end 79306752 length 1712128 ... Note the item 4 key of leaf 29757440, which is obviously too large, and even larger than the first key of the next leaf. However it still follows the key order in that tree block, thus tree checker is unable to detect it at read time, since tree checker can only work inside one leaf, thus such complex corruption can't be detected in advance. [FIX] The next time to detect such problem is at tree block merge time, which is in push_node_left(), balance_node_right(), push_leaf_left() or push_leaf_right(). Now we check if the key order of the right-most key of the left node is larger than the left-most key of the right node. By this we don't need to call the full tree-checker, while still keeping the key order correct as key order in each node is already checked by tree checker thus we only need to check the above two slots. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202833 Reviewed-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07btrfs: delete duplicated words + other fixes in commentsRandy Dunlap1-1/+1
Delete repeated words in fs/btrfs/. {to, the, a, and old} and change "into 2 part" to "into 2 parts". Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-27btrfs: set the lockdep class for log tree extent buffersJosef Bacik1-1/+5
These are special extent buffers that get rewound in order to lookup the state of the tree at a specific point in time. As such they do not go through the normal initialization paths that set their lockdep class, so handle them appropriately when they are created and before they are locked. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19btrfs: use the correct const function attribute for btrfs_get_num_csumsDavid Sterba1-1/+1
The build robot reports compiler: h8300-linux-gcc (GCC) 9.3.0 In file included from fs/btrfs/tests/extent-map-tests.c:8: >> fs/btrfs/tests/../ctree.h:2166:8: warning: type qualifiers ignored on function return type [-Wignored-qualifiers] 2166 | size_t __const btrfs_get_num_csums(void); | ^~~~~~~ The function attribute for const does not follow the expected scheme and in this case is confused with a const type qualifier. Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-27btrfs: add little-endian optimized key helpersDavid Sterba1-0/+17
The CPU and on-disk keys are mapped to two different structures because of the endianness. There's an intermediate buffer used to do the conversion, but this is not necessary when CPU and on-disk endianness match. Add optimized versions of helpers that take disk_key and use the buffer directly for CPU keys or drop the intermediate buffer and conversion. This saves a lot of stack space accross many functions and removes about 6K of generated binary code: text data bss dec hex filename 1090439 17468 14912 1122819 112203 pre/btrfs.ko 1084613 17456 14912 1116981 110b35 post/btrfs.ko Delta: -5826 Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-02btrfs: convert comments to fallthrough annotationsMarcos Paulo de Souza1-1/+1
Convert fall through comments to the pseudo-keyword which is now the preferred way. Signed-off-by: Marcos Paulo de Souza <mpdesouza@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-28btrfs: remove redundant local variable in read_block_for_searchNikolay Borisov1-5/+4
The local 'b' variable is only used to directly read values from passed extent buffer. So eliminate it and directly use the input parameter. Furthermore this shrinks the size of the following functions: ./scripts/bloat-o-meter ctree.orig fs/btrfs/ctree.o add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-73 (-73) Function old new delta read_block_for_search.isra 876 871 -5 push_node_left 1112 1044 -68 Total: Before=50348, After=50275, chg -0.14% Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-28btrfs: open code key_searchNikolay Borisov1-23/+18
This function wraps the optimisation implemented by d7396f07358a ("Btrfs: optimize key searches in btrfs_search_slot") however this optimisation is really used in only one place - btrfs_search_slot. Just open code the optimisation and also add a comment explaining how it works since it's not clear just by looking at the code - the key point here is it depends on an internal invariant that BTRFS' btree provides, namely intermediate pointers always contain the key at slot0 at the child node. So in the case of exact match we can safely assume that the given key will always be in slot 0 on lower levels. Furthermore this results in a reduction of btrfs_search_slot's size: ./scripts/bloat-o-meter ctree.orig fs/btrfs/ctree.o add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-75 (-75) Function old new delta btrfs_search_slot 2783 2708 -75 Total: Before=50423, After=50348, chg -0.15% Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-25btrfs: rename BTRFS_ROOT_REF_COWS to BTRFS_ROOT_SHAREABLEQu Wenruo1-13/+13
The name BTRFS_ROOT_REF_COWS is not very clear about the meaning. In fact, that bit can only be set to those trees: - Subvolume roots - Data reloc root - Reloc roots for above roots All other trees won't get this bit set. So just by the result, it is obvious that, roots with this bit set can have tree blocks shared with other trees. Either shared by snapshots, or by reloc roots (an special snapshot created by relocation). This patch will rename BTRFS_ROOT_REF_COWS to BTRFS_ROOT_SHAREABLE to make it easier to understand, and update all comment mentioning "reference counted" to follow the rename. Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-25btrfs: speed up and simplify generic_bin_searchDavid Sterba1-28/+15
The bin search jumps over the extent buffer item keys, comparing directly the bytes if the key is in one page, or storing it in a temporary buffer in case it spans two pages. The mapping start and length are obtained from map_private_extent_buffer, which is heavy weight compared to what we need. We know the key size and can find out the eb page in a simple way. For keys spanning two pages the fallback read_extent_buffer is used. The temporary variables are reduced and moved to the scope of use. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-25btrfs: don't use set/get token in leaf_space_usedDavid Sterba1-5/+3
The token is supposed to cache the last page used by the set/get helpers. In leaf_space_used the first and last items are accessed, it's not likely they'd be on the same page so there's some overhead caused updating the token address but not using it. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-25btrfs: drop eb parameter from set/get token helpersDavid Sterba1-30/+23
Now that all set/get helpers use the eb from the token, we don't need to pass it to many btrfs_token_*/btrfs_set_token_* helpers, saving some stack space. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-25btrfs: remove the redundant parameter level in btrfs_bin_search()Qu Wenruo1-7/+7
All callers pass the eb::level so we can get read it directly inside the btrfs_bin_search and key_search. This is inspired by the work of Marek in U-boot. CC: Marek Behun <marek.behun@nic.cz> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-03-23btrfs: inline checksum name and driver definitionsDavid Sterba1-3/+4
There's an unnecessary indirection in the checksum definition table, pointer and the string itself. The strings are short and the overall size of one entry is now 24 bytes. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-03-23btrfs: simplify parameters of btrfs_set_disk_extent_flagsDavid Sterba1-3/+1
All callers pass extent buffer start and length so the extent buffer itself should work fine. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-03-23btrfs: move root node locking helpers to locking.cDavid Sterba1-38/+0
The helpers are related to locking so move them there, update comments. Reviewed-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-03-23Btrfs: don't iterate mod seq list when putting a tree mod seqFilipe Manana1-12/+13
Each new element added to the mod seq list is always appended to the list, and each one gets a sequence number coming from a counter which gets incremented everytime a new element is added to the list (or a new node is added to the tree mod log rbtree). Therefore the element with the lowest sequence number is always the first element in the list. So just remove the list iteration at btrfs_put_tree_mod_seq() that computes the minimum sequence number in the list and replace it with a check for the first element's sequence number. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-31Btrfs: fix race between adding and putting tree mod seq elements and nodesFilipe Manana1-6/+2
There is a race between adding and removing elements to the tree mod log list and rbtree that can lead to use-after-free problems. Consider the following example that explains how/why the problems happens: 1) Task A has mod log element with sequence number 200. It currently is the only element in the mod log list; 2) Task A calls btrfs_put_tree_mod_seq() because it no longer needs to access the tree mod log. When it enters the function, it initializes 'min_seq' to (u64)-1. Then it acquires the lock 'tree_mod_seq_lock' before checking if there are other elements in the mod seq list. Since the list it empty, 'min_seq' remains set to (u64)-1. Then it unlocks the lock 'tree_mod_seq_lock'; 3) Before task A acquires the lock 'tree_mod_log_lock', task B adds itself to the mod seq list through btrfs_get_tree_mod_seq() and gets a sequence number of 201; 4) Some other task, name it task C, modifies a btree and because there elements in the mod seq list, it adds a tree mod elem to the tree mod log rbtree. That node added to the mod log rbtree is assigned a sequence number of 202; 5) Task B, which is doing fiemap and resolving indirect back references, calls btrfs get_old_root(), with 'time_seq' == 201, which in turn calls tree_mod_log_search() - the search returns the mod log node from the rbtree with sequence number 202, created by task C; 6) Task A now acquires the lock 'tree_mod_log_lock', starts iterating the mod log rbtree and finds the node with sequence number 202. Since 202 is less than the previously computed 'min_seq', (u64)-1, it removes the node and frees it; 7) Task B still has a pointer to the node with sequence number 202, and it dereferences the pointer itself and through the call to __tree_mod_log_rewind(), resulting in a use-after-free problem. This issue can be triggered sporadically with the test case generic/561 from fstests, and it happens more frequently with a higher number of duperemove processes. When it happens to me, it either freezes the VM or it produces a trace like the following before crashing: [ 1245.321140] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [ 1245.321200] CPU: 1 PID: 26997 Comm: pool Not tainted 5.5.0-rc6-btrfs-next-52 #1 [ 1245.321235] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014 [ 1245.321287] RIP: 0010:rb_next+0x16/0x50 [ 1245.321307] Code: .... [ 1245.321372] RSP: 0018:ffffa151c4d039b0 EFLAGS: 00010202 [ 1245.321388] RAX: 6b6b6b6b6b6b6b6b RBX: ffff8ae221363c80 RCX: 6b6b6b6b6b6b6b6b [ 1245.321409] RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff8ae221363c80 [ 1245.321439] RBP: ffff8ae20fcc4688 R08: 0000000000000002 R09: 0000000000000000 [ 1245.321475] R10: ffff8ae20b120910 R11: 00000000243f8bb1 R12: 0000000000000038 [ 1245.321506] R13: ffff8ae221363c80 R14: 000000000000075f R15: ffff8ae223f762b8 [ 1245.321539] FS: 00007fdee1ec7700(0000) GS:ffff8ae236c80000(0000) knlGS:0000000000000000 [ 1245.321591] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1245.321614] CR2: 00007fded4030c48 CR3: 000000021da16003 CR4: 00000000003606e0 [ 1245.321642] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1245.321668] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1245.321706] Call Trace: [ 1245.321798] __tree_mod_log_rewind+0xbf/0x280 [btrfs] [ 1245.321841] btrfs_search_old_slot+0x105/0xd00 [btrfs] [ 1245.321877] resolve_indirect_refs+0x1eb/0xc60 [btrfs] [ 1245.321912] find_parent_nodes+0x3dc/0x11b0 [btrfs] [ 1245.321947] btrfs_check_shared+0x115/0x1c0 [btrfs] [ 1245.321980] ? extent_fiemap+0x59d/0x6d0 [btrfs] [ 1245.322029] extent_fiemap+0x59d/0x6d0 [btrfs] [ 1245.322066] do_vfs_ioctl+0x45a/0x750 [ 1245.322081] ksys_ioctl+0x70/0x80 [ 1245.322092] ? trace_hardirqs_off_thunk+0x1a/0x1c [ 1245.322113] __x64_sys_ioctl+0x16/0x20 [ 1245.322126] do_syscall_64+0x5c/0x280 [ 1245.322139] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1245.322155] RIP: 0033:0x7fdee3942dd7 [ 1245.322177] Code: .... [ 1245.322258] RSP: 002b:00007fdee1ec6c88 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 1245.322294] RAX: ffffffffffffffda RBX: 00007fded40210d8 RCX: 00007fdee3942dd7 [ 1245.322314] RDX: 00007fded40210d8 RSI: 00000000c020660b RDI: 0000000000000004 [ 1245.322337] RBP: 0000562aa89e7510 R08: 0000000000000000 R09: 00007fdee1ec6d44 [ 1245.322369] R10: 0000000000000073 R11: 0000000000000246 R12: 00007fdee1ec6d48 [ 1245.322390] R13: 00007fdee1ec6d40 R14: 00007fded40210d0 R15: 00007fdee1ec6d50 [ 1245.322423] Modules linked in: .... [ 1245.323443] ---[ end trace 01de1e9ec5dff3cd ]--- Fix this by ensuring that btrfs_put_tree_mod_seq() computes the minimum sequence number and iterates the rbtree while holding the lock 'tree_mod_log_lock' in write mode. Also get rid of the 'tree_mod_seq_lock' lock, since it is now redundant. Fixes: bd989ba359f2ac ("Btrfs: add tree modification log functions") Fixes: 097b8a7c9e48e2 ("Btrfs: join tree mod log code with the code holding back delayed refs") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
generated by cgit v1.2.3 (git 2.39.0) at 2024-10-20 02:52:15 +0300