summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_file.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2020-06-30 00:48:46 +0300
committerDarrick J. Wong <darrick.wong@oracle.com>2020-07-06 20:46:58 +0300
commit1319ebefd6ed7a9988b7b4bc9317fbcf61a28bfc (patch)
treef55ab46d6a6476679a7dd7f12bed8c3580821dd9 /fs/xfs/xfs_file.c
parent1dfde687a65fec73e6914c184ecf8e9e54ccfe74 (diff)
downloadlinux-1319ebefd6ed7a9988b7b4bc9317fbcf61a28bfc.tar.xz
xfs: add an inode item lock
The inode log item is kind of special in that it can be aggregating new changes in memory at the same time time existing changes are being written back to disk. This means there are fields in the log item that are accessed concurrently from contexts that don't share any locking at all. e.g. updating ili_last_fields occurs at flush time under the ILOCK_EXCL and flush lock at flush time, under the flush lock at IO completion time, and is read under the ILOCK_EXCL when the inode is logged. Hence there is no actual serialisation between reading the field during logging of the inode in transactions vs clearing the field in IO completion. We currently get away with this by the fact that we are only clearing fields in IO completion, and nothing bad happens if we accidentally log more of the inode than we actually modify. Worst case is we consume a tiny bit more memory and log bandwidth. However, if we want to do more complex state manipulations on the log item that requires updates at all three of these potential locations, we need to have some mechanism of serialising those operations. To do this, introduce a spinlock into the log item to serialise internal state. This could be done via the xfs_inode i_flags_lock, but this then leads to potential lock inversion issues where inode flag updates need to occur inside locks that best nest inside the inode log item locks (e.g. marking inodes stale during inode cluster freeing). Using a separate spinlock avoids these sorts of problems and simplifies future code. This does not touch the use of ili_fields in the item formatting code - that is entirely protected by the ILOCK_EXCL at this point in time, so it remains untouched. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Diffstat (limited to 'fs/xfs/xfs_file.c')
-rw-r--r--fs/xfs/xfs_file.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index cc6528726187..01c098834c4b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -94,6 +94,7 @@ xfs_file_fsync(
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
@@ -137,13 +138,15 @@ xfs_file_fsync(
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
- (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
- lsn = ip->i_itemp->ili_last_lsn;
+ (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+ lsn = iip->ili_last_lsn;
}
if (lsn) {
error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
- ip->i_itemp->ili_fsync_fields = 0;
+ spin_lock(&iip->ili_lock);
+ iip->ili_fsync_fields = 0;
+ spin_unlock(&iip->ili_lock);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);