From 05b36b04d74a517d6675bf2f90829ff1ac7e28dc Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 13 Nov 2024 18:16:48 +0100 Subject: [PATCH 1/7] btrfs: fix use-after-free in btrfs_encoded_read_endio() Shinichiro reported the following use-after free that sometimes is happening in our CI system when running fstests' btrfs/284 on a TCMU runner device: BUG: KASAN: slab-use-after-free in lock_release+0x708/0x780 Read of size 8 at addr ffff888106a83f18 by task kworker/u80:6/219 CPU: 8 UID: 0 PID: 219 Comm: kworker/u80:6 Not tainted 6.12.0-rc6-kts+ #15 Hardware name: Supermicro Super Server/X11SPi-TF, BIOS 3.3 02/21/2020 Workqueue: btrfs-endio btrfs_end_bio_work [btrfs] Call Trace: dump_stack_lvl+0x6e/0xa0 ? lock_release+0x708/0x780 print_report+0x174/0x505 ? lock_release+0x708/0x780 ? __virt_addr_valid+0x224/0x410 ? lock_release+0x708/0x780 kasan_report+0xda/0x1b0 ? lock_release+0x708/0x780 ? __wake_up+0x44/0x60 lock_release+0x708/0x780 ? __pfx_lock_release+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? lock_is_held_type+0x9a/0x110 _raw_spin_unlock_irqrestore+0x1f/0x60 __wake_up+0x44/0x60 btrfs_encoded_read_endio+0x14b/0x190 [btrfs] btrfs_check_read_bio+0x8d9/0x1360 [btrfs] ? lock_release+0x1b0/0x780 ? trace_lock_acquire+0x12f/0x1a0 ? __pfx_btrfs_check_read_bio+0x10/0x10 [btrfs] ? process_one_work+0x7e3/0x1460 ? lock_acquire+0x31/0xc0 ? process_one_work+0x7e3/0x1460 process_one_work+0x85c/0x1460 ? __pfx_process_one_work+0x10/0x10 ? assign_work+0x16c/0x240 worker_thread+0x5e6/0xfc0 ? __pfx_worker_thread+0x10/0x10 kthread+0x2c3/0x3a0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 Allocated by task 3661: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 btrfs_encoded_read_regular_fill_pages+0x16c/0x6d0 [btrfs] send_extent_data+0xf0f/0x24a0 [btrfs] process_extent+0x48a/0x1830 [btrfs] changed_cb+0x178b/0x2ea0 [btrfs] btrfs_ioctl_send+0x3bf9/0x5c20 [btrfs] _btrfs_ioctl_send+0x117/0x330 [btrfs] btrfs_ioctl+0x184a/0x60a0 [btrfs] __x64_sys_ioctl+0x12e/0x1a0 do_syscall_64+0x95/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 3661: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x70 __kasan_slab_free+0x4f/0x70 kfree+0x143/0x490 btrfs_encoded_read_regular_fill_pages+0x531/0x6d0 [btrfs] send_extent_data+0xf0f/0x24a0 [btrfs] process_extent+0x48a/0x1830 [btrfs] changed_cb+0x178b/0x2ea0 [btrfs] btrfs_ioctl_send+0x3bf9/0x5c20 [btrfs] _btrfs_ioctl_send+0x117/0x330 [btrfs] btrfs_ioctl+0x184a/0x60a0 [btrfs] __x64_sys_ioctl+0x12e/0x1a0 do_syscall_64+0x95/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e The buggy address belongs to the object at ffff888106a83f00 which belongs to the cache kmalloc-rnd-07-96 of size 96 The buggy address is located 24 bytes inside of freed 96-byte region [ffff888106a83f00, ffff888106a83f60) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888106a83800 pfn:0x106a83 flags: 0x17ffffc0000000(node=0|zone=2|lastcpupid=0x1fffff) page_type: f5(slab) raw: 0017ffffc0000000 ffff888100053680 ffffea0004917200 0000000000000004 raw: ffff888106a83800 0000000080200019 00000001f5000000 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888106a83e00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888106a83e80: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc >ffff888106a83f00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888106a83f80: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888106a84000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== Further analyzing the trace and the crash dump's vmcore file shows that the wake_up() call in btrfs_encoded_read_endio() is calling wake_up() on the wait_queue that is in the private data passed to the end_io handler. Commit 4ff47df40447 ("btrfs: move priv off stack in btrfs_encoded_read_regular_fill_pages()") moved 'struct btrfs_encoded_read_private' off the stack. Before that commit one can see a corruption of the private data when analyzing the vmcore after a crash: *(struct btrfs_encoded_read_private *)0xffff88815626eec8 = { .wait = (wait_queue_head_t){ .lock = (spinlock_t){ .rlock = (struct raw_spinlock){ .raw_lock = (arch_spinlock_t){ .val = (atomic_t){ .counter = (int)-2005885696, }, .locked = (u8)0, .pending = (u8)157, .locked_pending = (u16)40192, .tail = (u16)34928, }, .magic = (unsigned int)536325682, .owner_cpu = (unsigned int)29, .owner = (void *)__SCT__tp_func_btrfs_transaction_commit+0x0 = 0x0, .dep_map = (struct lockdep_map){ .key = (struct lock_class_key *)0xffff8881575a3b6c, .class_cache = (struct lock_class *[2]){ 0xffff8882a71985c0, 0xffffea00066f5d40 }, .name = (const char *)0xffff88815626f100 = "", .wait_type_outer = (u8)37, .wait_type_inner = (u8)178, .lock_type = (u8)154, }, }, .__padding = (u8 [24]){ 0, 157, 112, 136, 50, 174, 247, 31, 29 }, .dep_map = (struct lockdep_map){ .key = (struct lock_class_key *)0xffff8881575a3b6c, .class_cache = (struct lock_class *[2]){ 0xffff8882a71985c0, 0xffffea00066f5d40 }, .name = (const char *)0xffff88815626f100 = "", .wait_type_outer = (u8)37, .wait_type_inner = (u8)178, .lock_type = (u8)154, }, }, .head = (struct list_head){ .next = (struct list_head *)0x112cca, .prev = (struct list_head *)0x47, }, }, .pending = (atomic_t){ .counter = (int)-1491499288, }, .status = (blk_status_t)130, } Here we can see several indicators of in-memory data corruption, e.g. the large negative atomic values of ->pending or ->wait->lock->rlock->raw_lock->val, as well as the bogus spinlock magic 0x1ff7ae32 (decimal 536325682 above) instead of 0xdead4ead or the bogus pointer values for ->wait->head. To fix this, change atomic_dec_return() to atomic_dec_and_test() to fix the corruption, as atomic_dec_return() is defined as two instructions on x86_64, whereas atomic_dec_and_test() is defined as a single atomic operation. This can lead to a situation where counter value is already decremented but the if statement in btrfs_encoded_read_endio() is not completely processed, i.e. the 0 test has not completed. If another thread continues executing btrfs_encoded_read_regular_fill_pages() the atomic_dec_return() there can see an already updated ->pending counter and continues by freeing the private data. Continuing in the endio handler the test for 0 succeeds and the wait_queue is woken up, resulting in a use-after-free. Reported-by: Shinichiro Kawasaki Suggested-by: Damien Le Moal Fixes: 1881fba89bd5 ("btrfs: add BTRFS_IOC_ENCODED_READ ioctl") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Filipe Manana Reviewed-by: Qu Wenruo Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 22b8e2764619..fdad1adee1a3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9089,7 +9089,7 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (atomic_dec_return(&priv->pending) == 0) { + if (atomic_dec_and_test(&priv->pending)) { int err = blk_status_to_errno(READ_ONCE(priv->status)); if (priv->uring_ctx) { From 7d6872ccbd56c310d2b9658ecaeafeda258727b6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 14 Nov 2024 12:11:26 +0000 Subject: [PATCH 2/7] btrfs: fix deadlock between transaction commits and extent locks When running a workload with fsstress and duperemove (generic/561) we can hit a deadlock related to transaction commits and locking extent ranges, as described below. Task A hanging during a transaction commit, waiting for all other writers to complete: [178317.334817] INFO: task fsstress:555623 blocked for more than 120 seconds. [178317.335693] Not tainted 6.12.0-rc6-btrfs-next-179+ #1 [178317.336528] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [178317.337673] task:fsstress state:D stack:0 pid:555623 tgid:555623 ppid:555620 flags:0x00004002 [178317.337679] Call Trace: [178317.337681] [178317.337685] __schedule+0x364/0xbe0 [178317.337691] schedule+0x26/0xa0 [178317.337695] btrfs_commit_transaction+0x5c5/0x1050 [btrfs] [178317.337769] ? start_transaction+0xc4/0x800 [btrfs] [178317.337815] ? __pfx_autoremove_wake_function+0x10/0x10 [178317.337819] btrfs_mksubvol+0x381/0x640 [btrfs] [178317.337878] btrfs_mksnapshot+0x7a/0xb0 [btrfs] [178317.337935] __btrfs_ioctl_snap_create+0x1bb/0x1d0 [btrfs] [178317.337995] btrfs_ioctl_snap_create_v2+0x103/0x130 [btrfs] [178317.338053] btrfs_ioctl+0x29b/0x2a90 [btrfs] [178317.338118] ? kmem_cache_alloc_noprof+0x5f/0x2c0 [178317.338126] ? getname_flags+0x45/0x1f0 [178317.338133] ? _raw_spin_unlock+0x15/0x30 [178317.338145] ? __x64_sys_ioctl+0x88/0xc0 [178317.338149] __x64_sys_ioctl+0x88/0xc0 [178317.338152] do_syscall_64+0x4a/0x110 [178317.338160] entry_SYSCALL_64_after_hwframe+0x76/0x7e [178317.338190] RIP: 0033:0x7f13c28e271b Which corresponds to line 2361 of transaction.c: $ cat -n fs/btrfs/transaction.c (...) 2162 int btrfs_commit_transaction(struct btrfs_trans_handle *trans) 2163 { (...) 2349 spin_lock(&fs_info->trans_lock); 2350 add_pending_snapshot(trans); 2351 cur_trans->state = TRANS_STATE_COMMIT_DOING; 2352 spin_unlock(&fs_info->trans_lock); 2353 2354 /* 2355 * The thread has started/joined the transaction thus it holds the 2356 * lockdep map as a reader. It has to release it before acquiring the 2357 * lockdep map as a writer. 2358 */ 2359 btrfs_lockdep_release(fs_info, btrfs_trans_num_writers); 2360 btrfs_might_wait_for_event(fs_info, btrfs_trans_num_writers); 2361 wait_event(cur_trans->writer_wait, 2362 atomic_read(&cur_trans->num_writers) == 1); (...) The transaction is in the TRANS_STATE_COMMIT_DOING state and so it's waiting for all other existing writers to complete and release their transaction handle. Task B is running ordered extent completion and blocked waiting to lock an extent range in an inode's io tree: [178317.327411] INFO: task kworker/u48:8:554545 blocked for more than 120 seconds. [178317.328630] Not tainted 6.12.0-rc6-btrfs-next-179+ #1 [178317.329635] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [178317.330872] task:kworker/u48:8 state:D stack:0 pid:554545 tgid:554545 ppid:2 flags:0x00004000 [178317.330878] Workqueue: btrfs-endio-write btrfs_work_helper [btrfs] [178317.330944] Call Trace: [178317.330945] [178317.330947] __schedule+0x364/0xbe0 [178317.330952] schedule+0x26/0xa0 [178317.330955] __lock_extent+0x337/0x3a0 [btrfs] [178317.331014] ? __pfx_autoremove_wake_function+0x10/0x10 [178317.331017] btrfs_finish_one_ordered+0x47a/0xaa0 [btrfs] [178317.331074] ? psi_group_change+0x132/0x2d0 [178317.331078] btrfs_work_helper+0xbd/0x370 [btrfs] [178317.331140] process_scheduled_works+0xd3/0x460 [178317.331144] ? __pfx_worker_thread+0x10/0x10 [178317.331146] worker_thread+0x121/0x250 [178317.331149] ? __pfx_worker_thread+0x10/0x10 [178317.331151] kthread+0xe9/0x120 [178317.331154] ? __pfx_kthread+0x10/0x10 [178317.331157] ret_from_fork+0x2d/0x50 [178317.331159] ? __pfx_kthread+0x10/0x10 [178317.331162] ret_from_fork_asm+0x1a/0x30 This extent range locking happens after joining the current transaction, so task A is waiting for task B to release its transaction handle (decrementing the transaction's num_writers counter). Task C while doing a fiemap it tries to join the current transaction: [242682.812815] task:pool state:D stack:0 pid:560767 tgid:560724 ppid:555622 flags:0x00004006 [242682.812827] Call Trace: [242682.812856] [242682.812864] __schedule+0x364/0xbe0 [242682.812879] ? _raw_spin_unlock_irqrestore+0x23/0x40 [242682.812897] schedule+0x26/0xa0 [242682.812909] wait_current_trans+0xd6/0x130 [btrfs] [242682.813148] ? __pfx_autoremove_wake_function+0x10/0x10 [242682.813162] start_transaction+0x3d4/0x800 [btrfs] [242682.813399] btrfs_is_data_extent_shared+0xd2/0x440 [btrfs] [242682.813723] fiemap_process_hole+0x2a2/0x300 [btrfs] [242682.813995] extent_fiemap+0x9b8/0xb80 [btrfs] [242682.814249] btrfs_fiemap+0x78/0xc0 [btrfs] [242682.814501] do_vfs_ioctl+0x2db/0xa50 [242682.814519] __x64_sys_ioctl+0x6a/0xc0 [242682.814531] do_syscall_64+0x4a/0x110 [242682.814544] entry_SYSCALL_64_after_hwframe+0x76/0x7e [242682.814556] RIP: 0033:0x7efff595e71b It tries to join the current transaction, but it can't because the transaction is in the TRANS_STATE_COMMIT_DOING state, so join_transaction() returns -EBUSY to start_transaction() and makes it wait for the current transaction to complete. And while it's waiting for the transaction to complete, it's holding an extent range locked in the same inode that task B is operating, which causes a deadlock between these 3 tasks. The extent range for the inode was locked at the start of the fiemap operation, early at extent_fiemap(). In short these tasks deadlock because: 1) Task A is waiting for task B to release its transaction handle; 2) Task B is waiting to lock an extent range for an inode while holding a transaction handle open; 3) Task C is waiting for the current transaction to complete (for task A to finish the transaction commit) while holding the extent range for the inode locked, so task B can't progress and release its transaction handle. This results in an ABBA deadlock involving transaction commits and extent locks. Extent locks are higher level locks, like inode VFS locks, and should always be acquired before joining or starting a transaction, but recently commit 2206265f41e9 ("btrfs: remove code duplication in ordered extent finishing") accidentally changed btrfs_finish_one_ordered() to do the transaction join before locking the extent range. Fix this by making sure that btrfs_finish_one_ordered() always locks the extent before joining a transaction and add an explicit comment about the need for this order. Fixes: 2206265f41e9 ("btrfs: remove code duplication in ordered extent finishing") Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/inode.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index fdad1adee1a3..659a5940a5b2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3063,6 +3063,19 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) goto out; } + /* + * If it's a COW write we need to lock the extent range as we will be + * inserting/replacing file extent items and unpinning an extent map. + * This must be taken before joining a transaction, as it's a higher + * level lock (like the inode's VFS lock), otherwise we can run into an + * ABBA deadlock with other tasks (transactions work like a lock, + * depending on their current state). + */ + if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { + clear_bits |= EXTENT_LOCKED; + lock_extent(io_tree, start, end, &cached_state); + } + if (freespace_inode) trans = btrfs_join_transaction_spacecache(root); else @@ -3099,9 +3112,6 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) goto out; } - clear_bits |= EXTENT_LOCKED; - lock_extent(io_tree, start, end, &cached_state); - if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags)) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { From b188ad7791899da8afe937e439e3086ffddd84a8 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 14 Nov 2024 15:38:27 +0000 Subject: [PATCH 3/7] btrfs: sysfs: advertise experimental features only if CONFIG_BTRFS_EXPERIMENTAL=y We are advertising experimental features through sysfs if CONFIG_BTRFS_DEBUG is set, without looking if CONFIG_BTRFS_EXPERIMENTAL is set. This is wrong as it will result in reporting experimental features as supported when CONFIG_BTRFS_EXPERIMENTAL is not set but CONFIG_BTRFS_DEBUG is set. Fix this by checking for CONFIG_BTRFS_EXPERIMENTAL instead of CONFIG_BTRFS_DEBUG. Fixes: 67cd3f221769 ("btrfs: split out CONFIG_BTRFS_EXPERIMENTAL from CONFIG_BTRFS_DEBUG") Reviewed-by: Neal Gompa Reviewed-by: Qu Wenruo Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index b843308e2bc6..fdcbf650ac31 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -295,7 +295,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(simple_quota, SIMPLE_QUOTA); #ifdef CONFIG_BLK_DEV_ZONED BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED); #endif -#ifdef CONFIG_BTRFS_DEBUG +#ifdef CONFIG_BTRFS_EXPERIMENTAL /* Remove once support for extent tree v2 is feature complete */ BTRFS_FEAT_ATTR_INCOMPAT(extent_tree_v2, EXTENT_TREE_V2); /* Remove once support for raid stripe tree is feature complete. */ @@ -329,7 +329,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { #ifdef CONFIG_BLK_DEV_ZONED BTRFS_FEAT_ATTR_PTR(zoned), #endif -#ifdef CONFIG_BTRFS_DEBUG +#ifdef CONFIG_BTRFS_EXPERIMENTAL BTRFS_FEAT_ATTR_PTR(extent_tree_v2), BTRFS_FEAT_ATTR_PTR(raid_stripe_tree), #endif From ed67f2a913a4f0fc505db29805c41dd07d3cb356 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 15 Nov 2024 15:46:13 +0000 Subject: [PATCH 4/7] btrfs: don't loop for nowait writes when checking for cross references When checking for delayed refs when verifying if there are cross references for a data extent, we stop if the path has nowait set and we can't try lock the delayed ref head's mutex, returning -EAGAIN with the goal of making a write fallback to a blocking context. However we ignore the -EAGAIN at btrfs_cross_ref_exist() when check_delayed_ref() returns it, and keep looping instead of immediately returning the -EAGAIN to the caller. Fix this by not looping if we get -EAGAIN and we have a nowait path. Fixes: 26ce91144631 ("btrfs: make can_nocow_extent nowait compatible") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 412e318e4a22..bd09dd3ad1a0 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2422,7 +2422,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, goto out; ret = check_delayed_ref(root, path, objectid, offset, bytenr); - } while (ret == -EAGAIN); + } while (ret == -EAGAIN && !path->nowait); out: btrfs_release_path(path); From 3ed51857a50f530ac7a1482e069dfbd1298558d4 Mon Sep 17 00:00:00 2001 From: Lizhi Xu Date: Fri, 25 Oct 2024 12:55:53 +0800 Subject: [PATCH 5/7] btrfs: add a sanity check for btrfs root in btrfs_search_slot() Syzbot reports a null-ptr-deref in btrfs_search_slot(). The reproducer is using rescue=ibadroots, and the extent tree root is corrupted thus the extent tree is NULL. When scrub tries to search the extent tree to gather the needed extent info, btrfs_search_slot() doesn't check if the target root is NULL or not, resulting the null-ptr-deref. Add sanity check for btrfs root before using it in btrfs_search_slot(). Reported-by: syzbot+3030e17bd57a73d39bd7@syzkaller.appspotmail.com Fixes: 42437a6386ff ("btrfs: introduce mount option rescue=ignorebadroots") Link: https://syzkaller.appspot.com/bug?extid=3030e17bd57a73d39bd7 CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Qu Wenruo Tested-by: syzbot+3030e17bd57a73d39bd7@syzkaller.appspotmail.com Signed-off-by: Lizhi Xu Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 148648ea1c8b..693dc27ffb89 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2046,7 +2046,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info; struct extent_buffer *b; int slot; int ret; @@ -2059,6 +2059,10 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, int min_write_lock_level; int prev_cmp; + if (!root) + return -EINVAL; + + fs_info = root->fs_info; might_sleep(); lowest_level = p->lowest_level; From 7c4e39f9d2af4abaf82ca0e315d1fd340456620f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 15 Nov 2024 11:29:21 +0000 Subject: [PATCH 6/7] btrfs: ref-verify: fix use-after-free after invalid ref action At btrfs_ref_tree_mod() after we successfully inserted the new ref entry (local variable 'ref') into the respective block entry's rbtree (local variable 'be'), if we find an unexpected action of BTRFS_DROP_DELAYED_REF, we error out and free the ref entry without removing it from the block entry's rbtree. Then in the error path of btrfs_ref_tree_mod() we call btrfs_free_ref_cache(), which iterates over all block entries and then calls free_block_entry() for each one, and there we will trigger a use-after-free when we are called against the block entry to which we added the freed ref entry to its rbtree, since the rbtree still points to the block entry, as we didn't remove it from the rbtree before freeing it in the error path at btrfs_ref_tree_mod(). Fix this by removing the new ref entry from the rbtree before freeing it. Syzbot report this with the following stack traces: BTRFS error (device loop0 state EA): Ref action 2, root 5, ref_root 0, parent 8564736, owner 0, offset 0, num_refs 18446744073709551615 __btrfs_mod_ref+0x7dd/0xac0 fs/btrfs/extent-tree.c:2523 update_ref_for_cow+0x9cd/0x11f0 fs/btrfs/ctree.c:512 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_insert_empty_items+0x9c/0x1a0 fs/btrfs/ctree.c:4314 btrfs_insert_empty_item fs/btrfs/ctree.h:669 [inline] btrfs_insert_orphan_item+0x1f1/0x320 fs/btrfs/orphan.c:23 btrfs_orphan_add+0x6d/0x1a0 fs/btrfs/inode.c:3482 btrfs_unlink+0x267/0x350 fs/btrfs/inode.c:4293 vfs_unlink+0x365/0x650 fs/namei.c:4469 do_unlinkat+0x4ae/0x830 fs/namei.c:4533 __do_sys_unlinkat fs/namei.c:4576 [inline] __se_sys_unlinkat fs/namei.c:4569 [inline] __x64_sys_unlinkat+0xcc/0xf0 fs/namei.c:4569 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 BTRFS error (device loop0 state EA): Ref action 1, root 5, ref_root 5, parent 0, owner 260, offset 0, num_refs 1 __btrfs_mod_ref+0x76b/0xac0 fs/btrfs/extent-tree.c:2521 update_ref_for_cow+0x96a/0x11f0 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:411 __btrfs_update_delayed_inode+0x1e7/0xb90 fs/btrfs/delayed-inode.c:1030 btrfs_update_delayed_inode fs/btrfs/delayed-inode.c:1114 [inline] __btrfs_commit_inode_delayed_items+0x2318/0x24a0 fs/btrfs/delayed-inode.c:1137 __btrfs_run_delayed_items+0x213/0x490 fs/btrfs/delayed-inode.c:1171 btrfs_commit_transaction+0x8a8/0x3740 fs/btrfs/transaction.c:2313 prepare_to_relocate+0x3c4/0x4c0 fs/btrfs/relocation.c:3586 relocate_block_group+0x16c/0xd40 fs/btrfs/relocation.c:3611 btrfs_relocate_block_group+0x77d/0xd90 fs/btrfs/relocation.c:4081 btrfs_relocate_chunk+0x12c/0x3b0 fs/btrfs/volumes.c:3377 __btrfs_balance+0x1b0f/0x26b0 fs/btrfs/volumes.c:4161 btrfs_balance+0xbdc/0x10c0 fs/btrfs/volumes.c:4538 BTRFS error (device loop0 state EA): Ref action 2, root 5, ref_root 0, parent 8564736, owner 0, offset 0, num_refs 18446744073709551615 __btrfs_mod_ref+0x7dd/0xac0 fs/btrfs/extent-tree.c:2523 update_ref_for_cow+0x9cd/0x11f0 fs/btrfs/ctree.c:512 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:411 __btrfs_update_delayed_inode+0x1e7/0xb90 fs/btrfs/delayed-inode.c:1030 btrfs_update_delayed_inode fs/btrfs/delayed-inode.c:1114 [inline] __btrfs_commit_inode_delayed_items+0x2318/0x24a0 fs/btrfs/delayed-inode.c:1137 __btrfs_run_delayed_items+0x213/0x490 fs/btrfs/delayed-inode.c:1171 btrfs_commit_transaction+0x8a8/0x3740 fs/btrfs/transaction.c:2313 prepare_to_relocate+0x3c4/0x4c0 fs/btrfs/relocation.c:3586 relocate_block_group+0x16c/0xd40 fs/btrfs/relocation.c:3611 btrfs_relocate_block_group+0x77d/0xd90 fs/btrfs/relocation.c:4081 btrfs_relocate_chunk+0x12c/0x3b0 fs/btrfs/volumes.c:3377 __btrfs_balance+0x1b0f/0x26b0 fs/btrfs/volumes.c:4161 btrfs_balance+0xbdc/0x10c0 fs/btrfs/volumes.c:4538 ================================================================== BUG: KASAN: slab-use-after-free in rb_first+0x69/0x70 lib/rbtree.c:473 Read of size 8 at addr ffff888042d1af38 by task syz.0.0/5329 CPU: 0 UID: 0 PID: 5329 Comm: syz.0.0 Not tainted 6.12.0-rc7-syzkaller #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 rb_first+0x69/0x70 lib/rbtree.c:473 free_block_entry+0x78/0x230 fs/btrfs/ref-verify.c:248 btrfs_free_ref_cache+0xa3/0x100 fs/btrfs/ref-verify.c:917 btrfs_ref_tree_mod+0x139f/0x15e0 fs/btrfs/ref-verify.c:898 btrfs_free_extent+0x33c/0x380 fs/btrfs/extent-tree.c:3544 __btrfs_mod_ref+0x7dd/0xac0 fs/btrfs/extent-tree.c:2523 update_ref_for_cow+0x9cd/0x11f0 fs/btrfs/ctree.c:512 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:411 __btrfs_update_delayed_inode+0x1e7/0xb90 fs/btrfs/delayed-inode.c:1030 btrfs_update_delayed_inode fs/btrfs/delayed-inode.c:1114 [inline] __btrfs_commit_inode_delayed_items+0x2318/0x24a0 fs/btrfs/delayed-inode.c:1137 __btrfs_run_delayed_items+0x213/0x490 fs/btrfs/delayed-inode.c:1171 btrfs_commit_transaction+0x8a8/0x3740 fs/btrfs/transaction.c:2313 prepare_to_relocate+0x3c4/0x4c0 fs/btrfs/relocation.c:3586 relocate_block_group+0x16c/0xd40 fs/btrfs/relocation.c:3611 btrfs_relocate_block_group+0x77d/0xd90 fs/btrfs/relocation.c:4081 btrfs_relocate_chunk+0x12c/0x3b0 fs/btrfs/volumes.c:3377 __btrfs_balance+0x1b0f/0x26b0 fs/btrfs/volumes.c:4161 btrfs_balance+0xbdc/0x10c0 fs/btrfs/volumes.c:4538 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 RIP: 0033:0x7f996df7e719 RSP: 002b:00007f996ede7038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f996e135f80 RCX: 00007f996df7e719 RDX: 0000000020000180 RSI: 00000000c4009420 RDI: 0000000000000004 RBP: 00007f996dff139e R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f996e135f80 R15: 00007fff79f32e68 Allocated by task 5329: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:257 [inline] __kmalloc_cache_noprof+0x19c/0x2c0 mm/slub.c:4295 kmalloc_noprof include/linux/slab.h:878 [inline] kzalloc_noprof include/linux/slab.h:1014 [inline] btrfs_ref_tree_mod+0x264/0x15e0 fs/btrfs/ref-verify.c:701 btrfs_free_extent+0x33c/0x380 fs/btrfs/extent-tree.c:3544 __btrfs_mod_ref+0x7dd/0xac0 fs/btrfs/extent-tree.c:2523 update_ref_for_cow+0x9cd/0x11f0 fs/btrfs/ctree.c:512 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:411 __btrfs_update_delayed_inode+0x1e7/0xb90 fs/btrfs/delayed-inode.c:1030 btrfs_update_delayed_inode fs/btrfs/delayed-inode.c:1114 [inline] __btrfs_commit_inode_delayed_items+0x2318/0x24a0 fs/btrfs/delayed-inode.c:1137 __btrfs_run_delayed_items+0x213/0x490 fs/btrfs/delayed-inode.c:1171 btrfs_commit_transaction+0x8a8/0x3740 fs/btrfs/transaction.c:2313 prepare_to_relocate+0x3c4/0x4c0 fs/btrfs/relocation.c:3586 relocate_block_group+0x16c/0xd40 fs/btrfs/relocation.c:3611 btrfs_relocate_block_group+0x77d/0xd90 fs/btrfs/relocation.c:4081 btrfs_relocate_chunk+0x12c/0x3b0 fs/btrfs/volumes.c:3377 __btrfs_balance+0x1b0f/0x26b0 fs/btrfs/volumes.c:4161 btrfs_balance+0xbdc/0x10c0 fs/btrfs/volumes.c:4538 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 Freed by task 5329: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:2342 [inline] slab_free mm/slub.c:4579 [inline] kfree+0x1a0/0x440 mm/slub.c:4727 btrfs_ref_tree_mod+0x136c/0x15e0 btrfs_free_extent+0x33c/0x380 fs/btrfs/extent-tree.c:3544 __btrfs_mod_ref+0x7dd/0xac0 fs/btrfs/extent-tree.c:2523 update_ref_for_cow+0x9cd/0x11f0 fs/btrfs/ctree.c:512 btrfs_force_cow_block+0x9f6/0x1da0 fs/btrfs/ctree.c:594 btrfs_cow_block+0x35e/0xa40 fs/btrfs/ctree.c:754 btrfs_search_slot+0xbdd/0x30d0 fs/btrfs/ctree.c:2116 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:411 __btrfs_update_delayed_inode+0x1e7/0xb90 fs/btrfs/delayed-inode.c:1030 btrfs_update_delayed_inode fs/btrfs/delayed-inode.c:1114 [inline] __btrfs_commit_inode_delayed_items+0x2318/0x24a0 fs/btrfs/delayed-inode.c:1137 __btrfs_run_delayed_items+0x213/0x490 fs/btrfs/delayed-inode.c:1171 btrfs_commit_transaction+0x8a8/0x3740 fs/btrfs/transaction.c:2313 prepare_to_relocate+0x3c4/0x4c0 fs/btrfs/relocation.c:3586 relocate_block_group+0x16c/0xd40 fs/btrfs/relocation.c:3611 btrfs_relocate_block_group+0x77d/0xd90 fs/btrfs/relocation.c:4081 btrfs_relocate_chunk+0x12c/0x3b0 fs/btrfs/volumes.c:3377 __btrfs_balance+0x1b0f/0x26b0 fs/btrfs/volumes.c:4161 btrfs_balance+0xbdc/0x10c0 fs/btrfs/volumes.c:4538 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 The buggy address belongs to the object at ffff888042d1af00 which belongs to the cache kmalloc-64 of size 64 The buggy address is located 56 bytes inside of freed 64-byte region [ffff888042d1af00, ffff888042d1af40) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x42d1a anon flags: 0x4fff00000000000(node=1|zone=1|lastcpupid=0x7ff) page_type: f5(slab) raw: 04fff00000000000 ffff88801ac418c0 0000000000000000 dead000000000001 raw: 0000000000000000 0000000000200020 00000001f5000000 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x52c40(GFP_NOFS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP), pid 5055, tgid 5055 (dhcpcd-run-hook), ts 40377240074, free_ts 40376848335 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1541 prep_new_page mm/page_alloc.c:1549 [inline] get_page_from_freelist+0x3649/0x3790 mm/page_alloc.c:3459 __alloc_pages_noprof+0x292/0x710 mm/page_alloc.c:4735 alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265 alloc_slab_page+0x6a/0x140 mm/slub.c:2412 allocate_slab+0x5a/0x2f0 mm/slub.c:2578 new_slab mm/slub.c:2631 [inline] ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3818 __slab_alloc+0x58/0xa0 mm/slub.c:3908 __slab_alloc_node mm/slub.c:3961 [inline] slab_alloc_node mm/slub.c:4122 [inline] __do_kmalloc_node mm/slub.c:4263 [inline] __kmalloc_noprof+0x25a/0x400 mm/slub.c:4276 kmalloc_noprof include/linux/slab.h:882 [inline] kzalloc_noprof include/linux/slab.h:1014 [inline] tomoyo_encode2 security/tomoyo/realpath.c:45 [inline] tomoyo_encode+0x26f/0x540 security/tomoyo/realpath.c:80 tomoyo_realpath_from_path+0x59e/0x5e0 security/tomoyo/realpath.c:283 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_check_open_permission+0x255/0x500 security/tomoyo/file.c:771 security_file_open+0x777/0x990 security/security.c:3109 do_dentry_open+0x369/0x1460 fs/open.c:945 vfs_open+0x3e/0x330 fs/open.c:1088 do_open fs/namei.c:3774 [inline] path_openat+0x2c84/0x3590 fs/namei.c:3933 page last free pid 5055 tgid 5055 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] free_pages_prepare mm/page_alloc.c:1112 [inline] free_unref_page+0xcfb/0xf20 mm/page_alloc.c:2642 free_pipe_info+0x300/0x390 fs/pipe.c:860 put_pipe_info fs/pipe.c:719 [inline] pipe_release+0x245/0x320 fs/pipe.c:742 __fput+0x23f/0x880 fs/file_table.c:431 __do_sys_close fs/open.c:1567 [inline] __se_sys_close fs/open.c:1552 [inline] __x64_sys_close+0x7f/0x110 fs/open.c:1552 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 Memory state around the buggy address: ffff888042d1ae00: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff888042d1ae80: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc >ffff888042d1af00: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ^ ffff888042d1af80: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc ffff888042d1b000: 00 00 00 00 00 fc fc 00 00 00 00 00 fc fc 00 00 Reported-by: syzbot+7325f164162e200000c1@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/673723eb.050a0220.1324f8.00a8.GAE@google.com/T/#u Fixes: fd708b81d972 ("Btrfs: add a extent ref verify tool") CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ref-verify.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 9522a8b79d22..2928abf7eb82 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -857,6 +857,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + rb_erase(&ref->node, &be->refs); kfree(ref); kfree(ra); goto out_unlock; From 22d2e48e318564f8c9b09faf03ecb4f03fb44dd5 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Fri, 15 Nov 2024 15:49:17 +0000 Subject: [PATCH 7/7] btrfs: fix lockdep warnings on io_uring encoded reads Lockdep doesn't like the fact that btrfs_uring_read_extent() returns to userspace still holding the inode lock, even though we release it once the I/O finishes. Add calls to rwsem_release() and rwsem_acquire_read() to work round this. Reported-by: Johannes Thumshirn 34310c442e17 ("btrfs: add io_uring command for encoded reads (ENCODED_READ ioctl)") Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 10 ++++++++++ fs/btrfs/locking.h | 10 ++++++++++ 2 files changed, 20 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1fdeb216bf6c..f8680e7cc974 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4752,6 +4752,9 @@ static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int iss size_t page_offset; ssize_t ret; + /* The inode lock has already been acquired in btrfs_uring_read_extent. */ + btrfs_lockdep_inode_acquire(inode, i_rwsem); + if (priv->err) { ret = priv->err; goto out; @@ -4860,6 +4863,13 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter, * and inode and freeing the allocations. */ + /* + * We're returning to userspace with the inode lock held, and that's + * okay - it'll get unlocked in a worker thread. Call + * btrfs_lockdep_inode_release() to avoid confusing lockdep. + */ + btrfs_lockdep_inode_release(inode, i_rwsem); + return -EIOCBQUEUED; out_fail: diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 46c8be2afab1..35036b151bf5 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -128,6 +128,16 @@ enum btrfs_lockdep_trans_states { #define btrfs_lockdep_release(owner, lock) \ rwsem_release(&owner->lock##_map, _THIS_IP_) +/* + * Used to account for the fact that when doing io_uring encoded I/O, we can + * return to userspace with the inode lock still held. + */ +#define btrfs_lockdep_inode_acquire(owner, lock) \ + rwsem_acquire_read(&owner->vfs_inode.lock.dep_map, 0, 0, _THIS_IP_) + +#define btrfs_lockdep_inode_release(owner, lock) \ + rwsem_release(&owner->vfs_inode.lock.dep_map, _THIS_IP_) + /* * Macros for the transaction states wait events, similar to the generic wait * event macros.