diff mbox series

[5.4,415/475] NFS: swap-out must always use STABLE writes.

Message ID 20220414110906.677442214@linuxfoundation.org
State Superseded
Headers show
Series None | expand

Commit Message

Greg KH April 14, 2022, 1:13 p.m. UTC
From: NeilBrown <neilb@suse.de>

[ Upstream commit c265de257f558a05c1859ee9e3fed04883b9ec0e ]

The commit handling code is not safe against memory-pressure deadlocks
when writing to swap.  In particular, nfs_commitdata_alloc() blocks
indefinitely waiting for memory, and this can consume all available
workqueue threads.

swap-out most likely uses STABLE writes anyway as COND_STABLE indicates
that a stable write should be used if the write fits in a single
request, and it normally does.  However if we ever swap with a small
wsize, or gather unusually large numbers of pages for a single write,
this might change.

For safety, make it explicit in the code that direct writes used for swap
must always use FLUSH_STABLE.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/direct.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0e2aa3f8bcab..0682037f972b 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -855,7 +855,7 @@  static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
  */
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 					       struct iov_iter *iter,
-					       loff_t pos)
+					       loff_t pos, int ioflags)
 {
 	struct nfs_pageio_descriptor desc;
 	struct inode *inode = dreq->inode;
@@ -863,7 +863,7 @@  static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	size_t requested_bytes = 0;
 	size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
 
-	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
+	nfs_pageio_init_write(&desc, inode, ioflags, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
@@ -1008,11 +1008,13 @@  ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 		dreq->iocb = iocb;
 
 	if (swap) {
-		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+							    FLUSH_STABLE);
 	} else {
 		nfs_start_io_direct(inode);
 
-		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+							    FLUSH_COND_STABLE);
 
 		if (mapping->nrpages) {
 			invalidate_inode_pages2_range(mapping,