summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2018-06-07 17:46:42 +0300
committerDarrick J. Wong <darrick.wong@oracle.com>2018-06-08 20:07:51 +0300
commit4a2d01b076d231afebbea04647373644e767b453 (patch)
treecbc2479bf4ca80dc56e6b67beb77a28d3415eae0 /fs/xfs
parentef215e394eeb960ea0e8a0fd37ba2fa30260e05b (diff)
downloadlinux-4a2d01b076d231afebbea04647373644e767b453.tar.xz
xfs: xfs_reflink_convert_cow() memory allocation deadlock
xfs_reflink_convert_cow() manipulates the incore extent list in GFP_KERNEL context in the IO submission path whilst holding locked pages under writeback. This is a memory reclaim deadlock vector. This code is not in a transaction, so any memory allocations it makes aren't protected via the memalloc_nofs_save() context that transactions carry. Hence we need to run this call under memalloc_nofs_save() context to prevent potential memory allocations from being run as GFP_KERNEL and deadlocking. Signed-Off-By: Dave Chinner <dchinner@redhat.com> Reviewed-by: Allison Henderson <allison.henderson@oracle.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')
-rw-r--r--fs/xfs/xfs_aops.c11
-rw-r--r--fs/xfs/xfs_buf.c1
-rw-r--r--fs/xfs/xfs_linux.h1
3 files changed, 12 insertions, 1 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 767d53222f31..1eb625fdcb1e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -531,8 +531,19 @@ xfs_submit_ioend(
{
/* Convert CoW extents to regular */
if (!status && ioend->io_type == XFS_IO_COW) {
+ /*
+ * Yuk. This can do memory allocation, but is not a
+ * transactional operation so everything is done in GFP_KERNEL
+ * context. That can deadlock, because we hold pages in
+ * writeback state and GFP_KERNEL allocations can block on them.
+ * Hence we must operate in nofs conditions here.
+ */
+ unsigned nofs_flag;
+
+ nofs_flag = memalloc_nofs_save();
status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
ioend->io_offset, ioend->io_size);
+ memalloc_nofs_restore(nofs_flag);
}
/* Reserve log space if we might write beyond the on-disk inode size. */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 980bc48979e9..e9c058e3761c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -21,7 +21,6 @@
#include <linux/migrate.h>
#include <linux/backing-dev.h>
#include <linux/freezer.h>
-#include <linux/sched/mm.h>
#include "xfs_format.h"
#include "xfs_log_format.h"
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index ae1e66fa3f61..1631cf4546f2 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -26,6 +26,7 @@ typedef __u32 xfs_nlink_t;
#include <linux/semaphore.h>
#include <linux/mm.h>
+#include <linux/sched/mm.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/slab.h>