[PATCH 09/19] XFS: ensure xfs_file_*_read cannot deadlock in memory allocation.

[NeilBrown]

xfs_file_*_read holds an inode lock while calling a generic 'read'
function.  These functions perform read-ahead and are quite likely to
allocate memory.
So set PF_FSTRANS to ensure they avoid __GFP_FS and so don't recurse
into a filesystem to free memory.

This can be a problem with loop-back NFS mounts, if free_pages ends up
wating in nfs_release_page(), and nfsd is blocked waiting for the lock
that this code holds.

This was found both by lockdep and as a real deadlock during testing.

Signed-off-by: NeilBrown <neilb@xxxxxxx>
---
 fs/xfs/xfs_file.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 64b48eade91d..88b33ef64668 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -243,6 +243,7 @@ xfs_file_aio_read(
 	ssize_t			ret = 0;
 	int			ioflags = 0;
 	xfs_fsize_t		n;
+	unsigned int		pflags;
 
 	XFS_STATS_INC(xs_read_calls);
 
@@ -290,6 +291,10 @@ xfs_file_aio_read(
 	 * proceeed concurrently without serialisation.
 	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	/* As we hold a lock, we must ensure that any allocation
+	 * in generic_file_aio_read avoid __GFP_FS
+	 */
+	current_set_flags_nested(&pflags, PF_FSTRANS);
 	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
 		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
@@ -313,6 +318,7 @@ xfs_file_aio_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
+	current_restore_flags_nested(&pflags, PF_FSTRANS);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
@@ -328,6 +334,7 @@ xfs_file_splice_read(
 	struct xfs_inode	*ip = XFS_I(infilp->f_mapping->host);
 	int			ioflags = 0;
 	ssize_t			ret;
+	unsigned int		pflags;
 
 	XFS_STATS_INC(xs_read_calls);
 
@@ -338,6 +345,10 @@ xfs_file_splice_read(
 		return -EIO;
 
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	/* As we hold a lock, we must ensure that any allocation
+	 * in generic_file_splice_read avoid __GFP_FS
+	 */
+	current_set_flags_nested(&pflags, PF_FSTRANS);
 
 	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
 
@@ -345,6 +356,7 @@ xfs_file_splice_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
+	current_restore_flags_nested(&pflags, PF_FSTRANS);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/