1 files changed, 45 insertions, 25 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3c0749ab9e40..cc3cfb12df53 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -119,8 +119,8 @@ xfs_dir_fsync(
 	return xfs_log_force_inode(ip);
 }
 
-static xfs_lsn_t
-xfs_fsync_lsn(
+static xfs_csn_t
+xfs_fsync_seq(
 	struct xfs_inode	*ip,
 	bool			datasync)
 {
@@ -128,7 +128,7 @@ xfs_fsync_lsn(
 		return 0;
 	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 		return 0;
-	return ip->i_itemp->ili_last_lsn;
+	return ip->i_itemp->ili_commit_seq;
 }
 
 /*
@@ -151,12 +151,12 @@ xfs_fsync_flush_log(
 	int			*log_flushed)
 {
 	int			error = 0;
-	xfs_lsn_t		lsn;
+	xfs_csn_t		seq;
 
 	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,
+	seq = xfs_fsync_seq(ip, datasync);
+	if (seq) {
+		error = xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC,
 					  log_flushed);
 
 		spin_lock(&ip->i_itemp->ili_lock);
@@ -197,9 +197,9 @@ xfs_file_fsync(
 	 * inode size in case of an extending write.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_blkdev_issue_flush(mp->m_rtdev_targp);
+		blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
-		xfs_blkdev_issue_flush(mp->m_ddev_targp);
+		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
 
 	/*
 	 * Any inode that has dirty modifications in the log is pinned.  The
@@ -219,7 +219,7 @@ xfs_file_fsync(
 	 */
 	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
 	    mp->m_logdev_targp == mp->m_ddev_targp)
-		xfs_blkdev_issue_flush(mp->m_ddev_targp);
+		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
 
 	return error;
 }
@@ -384,21 +384,30 @@ restart:
 		}
 		goto restart;
 	}
+
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
-	 * write.  If zeroing is needed and we are currently holding the
-	 * iolock shared, we need to update it to exclusive which implies
-	 * having to redo all checks before.
+	 * write.  If zeroing is needed and we are currently holding the iolock
+	 * shared, we need to update it to exclusive which implies having to
+	 * redo all checks before.
+	 *
+	 * We need to serialise against EOF updates that occur in IO completions
+	 * here. We want to make sure that nobody is changing the size while we
+	 * do this check until we have placed an IO barrier (i.e.  hold the
+	 * XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.  The
+	 * spinlock effectively forms a memory barrier once we have the
+	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value and
+	 * hence be able to correctly determine if we need to run zeroing.
 	 *
-	 * We need to serialise against EOF updates that occur in IO
-	 * completions here. We want to make sure that nobody is changing the
-	 * size while we do this check until we have placed an IO barrier (i.e.
-	 * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
-	 * The spinlock effectively forms a memory barrier once we have the
-	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
-	 * and hence be able to correctly determine if we need to run zeroing.
+	 * We can do an unlocked check here safely as IO completion can only
+	 * extend EOF. Truncate is locked out at this point, so the EOF can
+	 * not move backwards, only forwards. Hence we only need to take the
+	 * slow path and spin locks when we are at or beyond the current EOF.
 	 */
+	if (iocb->ki_pos <= i_size_read(inode))
+		goto out;
+
 	spin_lock(&ip->i_flags_lock);
 	isize = i_size_read(inode);
 	if (iocb->ki_pos > isize) {
@@ -426,7 +435,7 @@ restart:
 			drained_dio = true;
 			goto restart;
 		}
-	
+
 		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
 		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
 				NULL, &xfs_buffered_write_iomap_ops);
@@ -435,6 +444,7 @@ restart:
 	} else
 		spin_unlock(&ip->i_flags_lock);
 
+out:
 	return file_modified(file);
 }
 
@@ -500,7 +510,17 @@ xfs_dio_write_end_io(
 	 * other IO completions here to update the EOF. Failing to serialise
 	 * here can result in EOF moving backwards and Bad Things Happen when
 	 * that occurs.
+	 *
+	 * As IO completion only ever extends EOF, we can do an unlocked check
+	 * here to avoid taking the spinlock. If we land within the current EOF,
+	 * then we do not need to do an extending update at all, and we don't
+	 * need to take the lock to check this. If we race with an update moving
+	 * EOF, then we'll either still be beyond EOF and need to take the lock,
+	 * or we'll be within EOF and we don't need to take it at all.
 	 */
+	if (offset + size <= i_size_read(inode))
+		goto out;
+
 	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode)) {
 		i_size_write(inode, offset + size);
@@ -749,18 +769,18 @@ write_retry:
 	 */
 	if (ret == -EDQUOT && !cleared_space) {
 		xfs_iunlock(ip, iolock);
-		xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC);
+		xfs_blockgc_free_quota(ip, XFS_ICWALK_FLAG_SYNC);
 		cleared_space = true;
 		goto write_retry;
 	} else if (ret == -ENOSPC && !cleared_space) {
-		struct xfs_eofblocks eofb = {0};
+		struct xfs_icwalk	icw = {0};
 
 		cleared_space = true;
 		xfs_flush_inodes(ip->i_mount);
 
 		xfs_iunlock(ip, iolock);
-		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
-		xfs_blockgc_free_space(ip->i_mount, &eofb);
+		icw.icw_flags = XFS_ICWALK_FLAG_SYNC;
+		xfs_blockgc_free_space(ip->i_mount, &icw);
 		goto write_retry;
 	}