diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-09-21 20:15:26 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-09-21 20:15:26 +0300 |
commit | b5cbe7c00aa0f7a81ec40c007f81a3e9c84581e3 (patch) | |
tree | f7b08cac9b3b80326948a6b13411213dde379d46 /fs/inode.c | |
parent | 7bdfc1af0a5af34b3c9620a2023d2ea00fd77b57 (diff) | |
parent | 647aa768281f38cb1002edb3a1f673c3d66a8d81 (diff) | |
download | linux-b5cbe7c00aa0f7a81ec40c007f81a3e9c84581e3.tar.xz |
Merge tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull finegrained timestamp reverts from Christian Brauner:
"Earlier this week we sent a few minor fixes for the multi-grained
timestamp work in [1]. While we were polishing those up after Linus
realized that there might be a nicer way to fix them we received a
regression report in [2] that fine grained timestamps break gnulib
tests and thus possibly other tools.
The kernel will elide fine-grain timestamp updates when no one is
actively querying for them to avoid performance impacts. So a sequence
like write(f1) stat(f2) write(f2) stat(f2) write(f1) stat(f1) may
result in timestamp f1 to be older than the final f2 timestamp even
though f1 was last written too but the second write didn't update the
timestamp.
Such plotholes can lead to subtle bugs when programs compare
timestamps. For example, the nap() function in [2] will estimate that
it needs to wait one ns on a fine-grain timestamp enabled filesytem
between subsequent calls to observe a timestamp change. But in general
we don't update timestamps with more than one jiffie if we think that
no one is actively querying for fine-grain timestamps to avoid
performance impacts.
While discussing various fixes the decision was to go back to the
drawing board and ultimately to explore a solution that involves only
exposing such fine-grained timestamps to nfs internally and never to
userspace.
As there are multiple solutions discussed the honest thing to do here
is not to fix this up or disable it but to cleanly revert. The general
infrastructure will probably come back but there is no reason to keep
this code in mainline.
The general changes to timestamp handling are valid and a good cleanup
that will stay. The revert is fully bisectable"
Link: https://lore.kernel.org/all/20230918-hirte-neuzugang-4c2324e7bae3@brauner [1]
Link: https://lore.kernel.org/all/bf0524debb976627693e12ad23690094e4514303.camel@linuxfromscratch.org [2]
* tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
Revert "fs: add infrastructure for multigrain timestamps"
Revert "btrfs: convert to multigrain timestamps"
Revert "ext4: switch to multigrain timestamps"
Revert "xfs: switch to multigrain timestamps"
Revert "tmpfs: add support for multigrain timestamps"
Diffstat (limited to 'fs/inode.c')
-rw-r--r-- | fs/inode.c | 82 |
1 files changed, 3 insertions, 79 deletions
diff --git a/fs/inode.c b/fs/inode.c index 35fd688168c5..84bc3c76e5cc 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2102,52 +2102,10 @@ int file_remove_privs(struct file *file) } EXPORT_SYMBOL(file_remove_privs); -/** - * current_mgtime - Return FS time (possibly fine-grained) - * @inode: inode. - * - * Return the current time truncated to the time granularity supported by - * the fs, as suitable for a ctime/mtime change. If the ctime is flagged - * as having been QUERIED, get a fine-grained timestamp. - */ -struct timespec64 current_mgtime(struct inode *inode) -{ - struct timespec64 now, ctime; - atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec; - long nsec = atomic_long_read(pnsec); - - if (nsec & I_CTIME_QUERIED) { - ktime_get_real_ts64(&now); - return timestamp_truncate(now, inode); - } - - ktime_get_coarse_real_ts64(&now); - now = timestamp_truncate(now, inode); - - /* - * If we've recently fetched a fine-grained timestamp - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime = inode_get_ctime(inode); - if (timespec64_compare(&ctime, &now) > 0) - now = ctime; - - return now; -} -EXPORT_SYMBOL(current_mgtime); - -static struct timespec64 current_ctime(struct inode *inode) -{ - if (is_mgtime(inode)) - return current_mgtime(inode); - return current_time(inode); -} - static int inode_needs_update_time(struct inode *inode) { int sync_it = 0; - struct timespec64 now = current_ctime(inode); + struct timespec64 now = current_time(inode); struct timespec64 ctime; /* First try to exhaust all avenues to not sync */ @@ -2578,43 +2536,9 @@ EXPORT_SYMBOL(current_time); */ struct timespec64 inode_set_ctime_current(struct inode *inode) { - struct timespec64 now; - struct timespec64 ctime; - - ctime.tv_nsec = READ_ONCE(inode->__i_ctime.tv_nsec); - if (!(ctime.tv_nsec & I_CTIME_QUERIED)) { - now = current_time(inode); + struct timespec64 now = current_time(inode); - /* Just copy it into place if it's not multigrain */ - if (!is_mgtime(inode)) { - inode_set_ctime_to_ts(inode, now); - return now; - } - - /* - * If we've recently updated with a fine-grained timestamp, - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime.tv_sec = inode->__i_ctime.tv_sec; - if (timespec64_compare(&ctime, &now) > 0) - return ctime; - - /* - * Ctime updates are usually protected by the inode_lock, but - * we can still race with someone setting the QUERIED flag. - * Try to swap the new nsec value into place. If it's changed - * in the interim, then just go with a fine-grained timestamp. - */ - if (cmpxchg(&inode->__i_ctime.tv_nsec, ctime.tv_nsec, - now.tv_nsec) != ctime.tv_nsec) - goto fine_grained; - inode->__i_ctime.tv_sec = now.tv_sec; - return now; - } -fine_grained: - ktime_get_real_ts64(&now); - inode_set_ctime_to_ts(inode, timestamp_truncate(now, inode)); + inode_set_ctime(inode, now.tv_sec, now.tv_nsec); return now; } EXPORT_SYMBOL(inode_set_ctime_current); |