From 8226e37d82f43657da34dd770e2b38f20242ada7 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 13 Jan 2023 19:52:10 +0800 Subject: fscache: Use wait_on_bit() to wait for the freeing of relinquished volume The freeing of relinquished volume will wake up the pending volume acquisition by using wake_up_bit(), however it is mismatched with wait_var_event() used in fscache_wait_on_volume_collision() and it will never wake up the waiter in the wait-queue because these two functions operate on different wait-queues. According to the implementation in fscache_wait_on_volume_collision(), if the wake-up of pending acquisition is delayed longer than 20 seconds (e.g., due to the delay of on-demand fd closing), the first wait_var_event_timeout() will timeout and the following wait_var_event() will hang forever as shown below: FS-Cache: Potential volume collision new=00000024 old=00000022 ...... INFO: task mount:1148 blocked for more than 122 seconds. Not tainted 6.1.0-rc6+ #1 task:mount state:D stack:0 pid:1148 ppid:1 Call Trace: __schedule+0x2f6/0xb80 schedule+0x67/0xe0 fscache_wait_on_volume_collision.cold+0x80/0x82 __fscache_acquire_volume+0x40d/0x4e0 erofs_fscache_register_volume+0x51/0xe0 [erofs] erofs_fscache_register_fs+0x19c/0x240 [erofs] erofs_fc_fill_super+0x746/0xaf0 [erofs] vfs_get_super+0x7d/0x100 get_tree_nodev+0x16/0x20 erofs_fc_get_tree+0x20/0x30 [erofs] vfs_get_tree+0x24/0xb0 path_mount+0x2fa/0xa90 do_mount+0x7c/0xa0 __x64_sys_mount+0x8b/0xe0 do_syscall_64+0x30/0x60 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Considering that wake_up_bit() is more selective, so fix it by using wait_on_bit() instead of wait_var_event() to wait for the freeing of relinquished volume. In addition because waitqueue_active() is used in wake_up_bit() and clear_bit() doesn't imply any memory barrier, use clear_and_wake_up_bit() to add the missing memory barrier between cursor->flags and waitqueue_active(). Fixes: 62ab63352350 ("fscache: Implement volume registration") Reviewed-by: Jingbo Xu Signed-off-by: Hou Tao Signed-off-by: David Howells Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/20230113115211.2895845-2-houtao@huaweicloud.com/ # v3 --- fs/fscache/volume.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index ab8ceddf9efa..903af9d85f8b 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -141,13 +141,14 @@ static bool fscache_is_acquire_pending(struct fscache_volume *volume) static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, unsigned int collidee_debug_id) { - wait_var_event_timeout(&candidate->flags, - !fscache_is_acquire_pending(candidate), 20 * HZ); + wait_on_bit_timeout(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE, 20 * HZ); if (fscache_is_acquire_pending(candidate)) { pr_notice("Potential volume collision new=%08x old=%08x", candidate->debug_id, collidee_debug_id); fscache_stat(&fscache_n_volumes_collision); - wait_var_event(&candidate->flags, !fscache_is_acquire_pending(candidate)); + wait_on_bit(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE); } } @@ -347,8 +348,8 @@ static void fscache_wake_pending_volume(struct fscache_volume *volume, hlist_bl_for_each_entry(cursor, p, h, hash_link) { if (fscache_volume_same(cursor, volume)) { fscache_see_volume(cursor, fscache_volume_see_hash_wake); - clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); - wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + clear_and_wake_up_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, + &cursor->flags); return; } } -- cgit v1.2.3