summaryrefslogtreecommitdiff
path: root/fs/btrfs/file.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-09-21 20:15:26 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-09-21 20:15:26 +0300
commitb5cbe7c00aa0f7a81ec40c007f81a3e9c84581e3 (patch)
treef7b08cac9b3b80326948a6b13411213dde379d46 /fs/btrfs/file.c
parent7bdfc1af0a5af34b3c9620a2023d2ea00fd77b57 (diff)
parent647aa768281f38cb1002edb3a1f673c3d66a8d81 (diff)
downloadlinux-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/btrfs/file.c')
-rw-r--r--fs/btrfs/file.c24
1 files changed, 20 insertions, 4 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 87a5c128f716..361535c71c0f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1106,6 +1106,25 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode)
btrfs_drew_write_unlock(&inode->root->snapshot_lock);
}
+static void update_time_for_write(struct inode *inode)
+{
+ struct timespec64 now, ctime;
+
+ if (IS_NOCMTIME(inode))
+ return;
+
+ now = current_time(inode);
+ if (!timespec64_equal(&inode->i_mtime, &now))
+ inode->i_mtime = now;
+
+ ctime = inode_get_ctime(inode);
+ if (!timespec64_equal(&ctime, &now))
+ inode_set_ctime_to_ts(inode, now);
+
+ if (IS_I_VERSION(inode))
+ inode_inc_iversion(inode);
+}
+
static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
size_t count)
{
@@ -1137,10 +1156,7 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
* need to start yet another transaction to update the inode as we will
* update the inode when we finish writing whatever data we write.
*/
- if (!IS_NOCMTIME(inode)) {
- inode->i_mtime = inode_set_ctime_current(inode);
- inode_inc_iversion(inode);
- }
+ update_time_for_write(inode);
start_pos = round_down(pos, fs_info->sectorsize);
oldsize = i_size_read(inode);