From db7e68b522c01eb666cfe1f31637775f18997811 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 24 Sep 2024 16:50:22 -0400 Subject: btrfs: drop the backref cache during relocation if we commit Since the inception of relocation we have maintained the backref cache across transaction commits, updating the backref cache with the new bytenr whenever we COWed blocks that were in the cache, and then updating their bytenr once we detected a transaction id change. This works as long as we're only ever modifying blocks, not changing the structure of the tree. However relocation does in fact change the structure of the tree. For example, if we are relocating a data extent, we will look up all the leaves that point to this data extent. We will then call do_relocation() on each of these leaves, which will COW down to the leaf and then update the file extent location. But, a key feature of do_relocation() is the pending list. This is all the pending nodes that we modified when we updated the file extent item. We will then process all of these blocks via finish_pending_nodes, which calls do_relocation() on all of the nodes that led up to that leaf. The purpose of this is to make sure we don't break sharing unless we absolutely have to. Consider the case that we have 3 snapshots that all point to this leaf through the same nodes, the initial COW would have created a whole new path. If we did this for all 3 snapshots we would end up with 3x the number of nodes we had originally. To avoid this we will cycle through each of the snapshots that point to each of these nodes and update their pointers to point at the new nodes. Once we update the pointer to the new node we will drop the node we removed the link for and all of its children via btrfs_drop_subtree(). This is essentially just btrfs_drop_snapshot(), but for an arbitrary point in the snapshot. The problem with this is that we will never reflect this in the backref cache. If we do this btrfs_drop_snapshot() for a node that is in the backref tree, we will leave the node in the backref tree. This becomes a problem when we change the transid, as now the backref cache has entire subtrees that no longer exist, but exist as if they still are pointed to by the same roots. In the best case scenario you end up with "adding refs to an existing tree ref" errors from insert_inline_extent_backref(), where we attempt to link in nodes on roots that are no longer valid. Worst case you will double free some random block and re-use it when there's still references to the block. This is extremely subtle, and the consequences are quite bad. There isn't a way to make sure our backref cache is consistent between transid's. In order to fix this we need to simply evict the entire backref cache anytime we cross transid's. This reduces performance in that we have to rebuild this backref cache every time we change transid's, but fixes the bug. This has existed since relocation was added, and is a pretty critical bug. There's a lot more cleanup that can be done now that this functionality is going away, but this patch is as small as possible in order to fix the problem and make it easy for us to backport it to all the kernels it needs to be backported to. Followup series will dismantle more of this code and simplify relocation drastically to remove this functionality. We have a reproducer that reproduced the corruption within a few minutes of running. With this patch it survives several iterations/hours of running the reproducer. Fixes: 3fd0a5585eb9 ("Btrfs: Metadata ENOSPC handling for balance") CC: stable@vger.kernel.org Reviewed-by: Boris Burkov Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 75 +++------------------------------------------------ 1 file changed, 3 insertions(+), 72 deletions(-) (limited to 'fs/btrfs/relocation.c') diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ea4ed85919ec..cf1dfeaaf2d8 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -232,70 +232,6 @@ static struct btrfs_backref_node *walk_down_backref( return NULL; } -static void update_backref_node(struct btrfs_backref_cache *cache, - struct btrfs_backref_node *node, u64 bytenr) -{ - struct rb_node *rb_node; - rb_erase(&node->rb_node, &cache->rb_root); - node->bytenr = bytenr; - rb_node = rb_simple_insert(&cache->rb_root, node->bytenr, &node->rb_node); - if (rb_node) - btrfs_backref_panic(cache->fs_info, bytenr, -EEXIST); -} - -/* - * update backref cache after a transaction commit - */ -static int update_backref_cache(struct btrfs_trans_handle *trans, - struct btrfs_backref_cache *cache) -{ - struct btrfs_backref_node *node; - int level = 0; - - if (cache->last_trans == 0) { - cache->last_trans = trans->transid; - return 0; - } - - if (cache->last_trans == trans->transid) - return 0; - - /* - * detached nodes are used to avoid unnecessary backref - * lookup. transaction commit changes the extent tree. - * so the detached nodes are no longer useful. - */ - while (!list_empty(&cache->detached)) { - node = list_entry(cache->detached.next, - struct btrfs_backref_node, list); - btrfs_backref_cleanup_node(cache, node); - } - - while (!list_empty(&cache->changed)) { - node = list_entry(cache->changed.next, - struct btrfs_backref_node, list); - list_del_init(&node->list); - BUG_ON(node->pending); - update_backref_node(cache, node, node->new_bytenr); - } - - /* - * some nodes can be left in the pending list if there were - * errors during processing the pending nodes. - */ - for (level = 0; level < BTRFS_MAX_LEVEL; level++) { - list_for_each_entry(node, &cache->pending[level], list) { - BUG_ON(!node->pending); - if (node->bytenr == node->new_bytenr) - continue; - update_backref_node(cache, node, node->new_bytenr); - } - } - - cache->last_trans = 0; - return 1; -} - static bool reloc_root_is_dead(const struct btrfs_root *root) { /* @@ -551,9 +487,6 @@ static int clone_backref_node(struct btrfs_trans_handle *trans, struct btrfs_backref_edge *new_edge; struct rb_node *rb_node; - if (cache->last_trans > 0) - update_backref_cache(trans, cache); - rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start); if (rb_node) { node = rb_entry(rb_node, struct btrfs_backref_node, rb_node); @@ -3698,11 +3631,9 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) break; } restart: - if (update_backref_cache(trans, &rc->backref_cache)) { - btrfs_end_transaction(trans); - trans = NULL; - continue; - } + if (rc->backref_cache.last_trans != trans->transid) + btrfs_backref_release_cache(&rc->backref_cache); + rc->backref_cache.last_trans = trans->transid; ret = find_next_extent(rc, path, &key); if (ret < 0) -- cgit v1.2.3 From c3b47f49e83197e8dffd023ec568403bcdbb774b Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sat, 28 Sep 2024 08:05:58 +0930 Subject: btrfs: fix a NULL pointer dereference when failed to start a new trasacntion [BUG] Syzbot reported a NULL pointer dereference with the following crash: FAULT_INJECTION: forcing a failure. start_transaction+0x830/0x1670 fs/btrfs/transaction.c:676 prepare_to_relocate+0x31f/0x4c0 fs/btrfs/relocation.c:3642 relocate_block_group+0x169/0xd20 fs/btrfs/relocation.c:3678 ... BTRFS info (device loop0): balance: ended with status: -12 Oops: general protection fault, probably for non-canonical address 0xdffffc00000000cc: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000660-0x0000000000000667] RIP: 0010:btrfs_update_reloc_root+0x362/0xa80 fs/btrfs/relocation.c:926 Call Trace: commit_fs_roots+0x2ee/0x720 fs/btrfs/transaction.c:1496 btrfs_commit_transaction+0xfaf/0x3740 fs/btrfs/transaction.c:2430 del_balance_item fs/btrfs/volumes.c:3678 [inline] reset_balance_state+0x25e/0x3c0 fs/btrfs/volumes.c:3742 btrfs_balance+0xead/0x10c0 fs/btrfs/volumes.c:4574 btrfs_ioctl_balance+0x493/0x7c0 fs/btrfs/ioctl.c:3673 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [CAUSE] The allocation failure happens at the start_transaction() inside prepare_to_relocate(), and during the error handling we call unset_reloc_control(), which makes fs_info->balance_ctl to be NULL. Then we continue the error path cleanup in btrfs_balance() by calling reset_balance_state() which will call del_balance_item() to fully delete the balance item in the root tree. However during the small window between set_reloc_contrl() and unset_reloc_control(), we can have a subvolume tree update and created a reloc_root for that subvolume. Then we go into the final btrfs_commit_transaction() of del_balance_item(), and into btrfs_update_reloc_root() inside commit_fs_roots(). That function checks if fs_info->reloc_ctl is in the merge_reloc_tree stage, but since fs_info->reloc_ctl is NULL, it results a NULL pointer dereference. [FIX] Just add extra check on fs_info->reloc_ctl inside btrfs_update_reloc_root(), before checking fs_info->reloc_ctl->merge_reloc_tree. That DEAD_RELOC_TREE handling is to prevent further modification to the reloc tree during merge stage, but since there is no reloc_ctl at all, we do not need to bother that. Reported-by: syzbot+283673dbc38527ef9f3d@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/66f6bfa7.050a0220.38ace9.0019.GAE@google.com/ CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/relocation.c') diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index cf1dfeaaf2d8..f3834f8d26b4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -856,7 +856,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, btrfs_grab_root(reloc_root); /* root->reloc_root will stay until current relocation finished */ - if (fs_info->reloc_ctl->merge_reloc_tree && + if (fs_info->reloc_ctl && fs_info->reloc_ctl->merge_reloc_tree && btrfs_root_refs(root_item) == 0) { set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); /* -- cgit v1.2.3