NFS: swap-out must always use STABLE writes.

[ 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>

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 28afc31..c220810 100644 (file)
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -793,7 +793,7 @@ 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;
@@ -801,7 +801,7 @@ 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);
@@ -947,11 +947,13 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
        pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode);
 
        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,