From b74c02a37987d3ea755f96119c527f5e91950592 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 13 Mar 2024 08:15:03 +0000 Subject: [PATCH] afs: Fix occasional rmdir-then-VNOVNODE with generic/011 Sometimes generic/011 causes kafs to follow up an FS.RemoveDir RPC call by spending around a second sending a slew of FS.FetchStatus RPC calls to the directory just deleted that then abort with VNOVNODE, indicating deletion of the target directory. This seems to stem from userspace attempting to stat the directory or something in it: afs_select_fileserver+0x46d/0xaa2 afs_wait_for_operation+0x12/0x17e afs_fetch_status+0x56/0x75 afs_validate+0xfb/0x240 afs_permission+0xef/0x1b0 inode_permission+0x90/0x139 link_path_walk.part.0.constprop.0+0x6f/0x2f0 path_lookupat+0x4c/0xfa filename_lookup+0x63/0xd7 vfs_statx+0x62/0x13f vfs_fstatat+0x72/0x8a The issue appears to be that afs_dir_remove_subdir() marks the callback promise as being cancelled by setting the expiry time to AFS_NO_CB_PROMISE - which then confuses afs_validate() which sends the FetchStatus to try and get a new one before it checks for the AFS_VNODE_DELETED flag which indicates that we know the directory got deleted. Fix this by: (1) Make afs_check_validity() return true if AFS_VNODE_DELETED is set, and then tweak the return from afs_validate() if the DELETED flag is set. (2) Move the AFS_VNODE_DELETED check in afs_validate() up above the expiration check to immediately after we've grabbed the validate_lock. Fixes: 453924de6212 ("afs: Overhaul invalidation handling to better support RO volumes") Signed-off-by: David Howells Link: https://lore.kernel.org/r/20240313081505.3060173-3-dhowells@redhat.com Reviewed-by: Marc Dionne cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: Christian Brauner --- fs/afs/validation.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/afs/validation.c b/fs/afs/validation.c index 46b37f2cce7d..32a53fc8dfb2 100644 --- a/fs/afs/validation.c +++ b/fs/afs/validation.c @@ -122,6 +122,9 @@ bool afs_check_validity(const struct afs_vnode *vnode) const struct afs_volume *volume = vnode->volume; time64_t deadline = ktime_get_real_seconds() + 10; + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) + return true; + if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) || atomic64_read(&vnode->cb_expires_at) <= deadline || volume->cb_expires_at <= deadline || @@ -389,12 +392,17 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) key_serial(key)); if (afs_check_validity(vnode)) - return 0; + return test_bit(AFS_VNODE_DELETED, &vnode->flags) ? -ESTALE : 0; ret = down_write_killable(&vnode->validate_lock); if (ret < 0) goto error; + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + ret = -ESTALE; + goto error_unlock; + } + /* Validate a volume after the v_break has changed or the volume * callback expired. We only want to do this once per volume per * v_break change. The actual work will be done when parsing the @@ -448,12 +456,6 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->cb_ro_snapshot = cb_ro_snapshot; vnode->cb_scrub = cb_scrub; - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - _debug("file already deleted"); - ret = -ESTALE; - goto error_unlock; - } - /* if the vnode's data version number changed then its contents are * different */ zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);