1 files changed, 65 insertions, 49 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 39695b59dfcc..dc91973c0b4f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -118,6 +118,54 @@ xfs_dir_fsync(
 	return xfs_log_force_inode(ip);
 }
 
+static xfs_lsn_t
+xfs_fsync_lsn(
+	struct xfs_inode	*ip,
+	bool			datasync)
+{
+	if (!xfs_ipincount(ip))
+		return 0;
+	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+		return 0;
+	return ip->i_itemp->ili_last_lsn;
+}
+
+/*
+ * All metadata updates are logged, which means that we just have to flush the
+ * log up to the latest LSN that touched the inode.
+ *
+ * If we have concurrent fsync/fdatasync() calls, we need them to all block on
+ * the log force before we clear the ili_fsync_fields field. This ensures that
+ * we don't get a racing sync operation that does not wait for the metadata to
+ * hit the journal before returning.  If we race with clearing ili_fsync_fields,
+ * then all that will happen is the log force will do nothing as the lsn will
+ * already be on disk.  We can't race with setting ili_fsync_fields because that
+ * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock
+ * shared until after the ili_fsync_fields is cleared.
+ */
+static  int
+xfs_fsync_flush_log(
+	struct xfs_inode	*ip,
+	bool			datasync,
+	int			*log_flushed)
+{
+	int			error = 0;
+	xfs_lsn_t		lsn;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	lsn = xfs_fsync_lsn(ip, datasync);
+	if (lsn) {
+		error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC,
+					  log_flushed);
+
+		spin_lock(&ip->i_itemp->ili_lock);
+		ip->i_itemp->ili_fsync_fields = 0;
+		spin_unlock(&ip->i_itemp->ili_lock);
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return error;
+}
+
 STATIC int
 xfs_file_fsync(
 	struct file		*file,
@@ -125,13 +173,10 @@ xfs_file_fsync(
 	loff_t			end,
 	int			datasync)
 {
-	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_inode	*ip = XFS_I(file->f_mapping->host);
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error = 0;
 	int			log_flushed = 0;
-	xfs_lsn_t		lsn = 0;
 
 	trace_xfs_file_fsync(ip);
 
@@ -156,32 +201,13 @@ xfs_file_fsync(
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
 	/*
-	 * All metadata updates are logged, which means that we just have to
-	 * flush the log up to the latest LSN that touched the inode. If we have
-	 * concurrent fsync/fdatasync() calls, we need them to all block on the
-	 * log force before we clear the ili_fsync_fields field. This ensures
-	 * that we don't get a racing sync operation that does not wait for the
-	 * metadata to hit the journal before returning. If we race with
-	 * clearing the ili_fsync_fields, then all that will happen is the log
-	 * force will do nothing as the lsn will already be on disk. We can't
-	 * race with setting ili_fsync_fields because that is done under
-	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
-	 * until after the ili_fsync_fields is cleared.
+	 * Any inode that has dirty modifications in the log is pinned.  The
+	 * racy check here for a pinned inode while not catch modifications
+	 * that happen concurrently to the fsync call, but fsync semantics
+	 * only require to sync previously completed I/O.
 	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_ipincount(ip)) {
-		if (!datasync ||
-		    (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);
-		spin_lock(&iip->ili_lock);
-		iip->ili_fsync_fields = 0;
-		spin_unlock(&iip->ili_lock);
-	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	if (xfs_ipincount(ip))
+		error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
 
 	/*
 	 * If we only have a single device, and the log force about was
@@ -408,12 +434,6 @@ restart:
 	} else
 		spin_unlock(&ip->i_flags_lock);
 
-	/*
-	 * Updating the timestamps will grab the ilock again from
-	 * xfs_fs_dirty_inode, so we have to call it after dropping the
-	 * lock above.  Eventually we should look into a way to avoid
-	 * the pointless lock roundtrip.
-	 */
 	return file_modified(file);
 }
 
@@ -693,7 +713,7 @@ xfs_file_buffered_write(
 	struct inode		*inode = mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
-	int			enospc = 0;
+	bool			cleared_space = false;
 	int			iolock;
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
@@ -723,27 +743,23 @@ write_retry:
 	 * metadata space. This reduces the chances that the eofblocks scan
 	 * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
 	 * also behaves as a filter to prevent too many eofblocks scans from
-	 * running at the same time.
+	 * running at the same time.  Use a synchronous scan to increase the
+	 * effectiveness of the scan.
 	 */
-	if (ret == -EDQUOT && !enospc) {
+	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		enospc = xfs_inode_free_quota_eofblocks(ip);
-		if (enospc)
-			goto write_retry;
-		enospc = xfs_inode_free_quota_cowblocks(ip);
-		if (enospc)
-			goto write_retry;
-		iolock = 0;
-	} else if (ret == -ENOSPC && !enospc) {
+		xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC);
+		cleared_space = true;
+		goto write_retry;
+	} else if (ret == -ENOSPC && !cleared_space) {
 		struct xfs_eofblocks eofb = {0};
 
-		enospc = 1;
+		cleared_space = true;
 		xfs_flush_inodes(ip->i_mount);
 
 		xfs_iunlock(ip, iolock);
 		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
-		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
-		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
+		xfs_blockgc_free_space(ip->i_mount, &eofb);
 		goto write_retry;
 	}