NFS: fix writeback in presence of errors

After running xfstest generic/751, in certain conditions, can have
a writeback IO stuck while experiencing one of the two patterns.

Pattern#1: writeback IO experiences ENOSPC on an offset smaller
than the filesize. Example,
write offset=0 len=4096 how=unstable OK
write offset=8192 len=4096 how=unstable OK
write offset=12288 len=4096 how=unstable ENOSPC
write offset=4096 len=4096 how=unstable ENOSPC
client sends a commit and receives a verifier which is different
from the last successful write. It marks pages dirty and writeback
retries. But it again send writes unstable and gets into the same
pattern, running into the ENOSPC error and sending a commit because
writes were sent at unstable.

Pattern#2: an unstable write followed by a short write and ENOSPC.
write offset=0 len=4096 how=unstable OK
write offset=4096 len=4096 how=unstable returns OK but count=100
write offset=4197 len=3996 how=stable returns ENOSPC
client send a commit and receives a verifier different from
the last unstable write. The same behaviour is retried in a loop.

Instead, this patch proposes to identify those conditions and mark
requests to be done synchronously instead. Previous solution tried
to mark it in the nfs_page, however that's not persistent thus
instead mark it in the nfs_open_context.

Furthermore, the same problem occurs during localio code path so
recognize that IO needs to be done sync in that case as well.

Signed-off-by: Olga Kornievskaia <okorniev@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

4 files changed, 27 insertions, 1 deletions

diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 4c7d16a99ed6..e55c5977fcc3 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -865,6 +865,8 @@ static void nfs_local_call_write(struct work_struct *work)
 	file_start_write(filp);
 	n_iters = atomic_read(&iocb->n_iters);
 	for (int i = 0; i < n_iters ; i++) {
+		size_t icount;
+
 		if (iocb->iter_is_dio_aligned[i]) {
 			iocb->kiocb.ki_flags |= IOCB_DIRECT;
 			/* Only use AIO completion if DIO-aligned segment is last */
@@ -881,8 +883,16 @@ static void nfs_local_call_write(struct work_struct *work)
 		if (status == -EIOCBQUEUED)
 			continue;
 		/* Break on completion, errors, or short writes */
+		icount = iov_iter_count(&iocb->iters[i]);
 		if (nfs_local_pgio_done(iocb, status) || status < 0 ||
-		    (size_t)status < iov_iter_count(&iocb->iters[i])) {
+		    (size_t)status < icount) {
+			if ((size_t)status < icount) {
+				struct nfs_lock_context *ctx =
+					iocb->hdr->req->wb_lock_context;
+
+				set_bit(NFS_CONTEXT_WRITE_SYNC,
+					&ctx->open_context->flags);
+			}
 			nfs_local_write_iocb_done(iocb);
 			break;
 		}
@@ -901,6 +911,9 @@ static void nfs_local_do_write(struct nfs_local_kiocb *iocb,
 		__func__, hdr->args.count, hdr->args.offset,
 		(hdr->args.stable == NFS_UNSTABLE) ?  "unstable" : "stable");
 
+	if (test_bit(NFS_CONTEXT_WRITE_SYNC,
+		     &hdr->req->wb_lock_context->open_context->flags))
+		hdr->args.stable = NFS_FILE_SYNC;
 	switch (hdr->args.stable) {
 	default:
 		break;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index a9373de891c9..4a87b2fdb2e6 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1186,6 +1186,9 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 
 	nfs_page_group_lock(req);
 
+	if (test_bit(NFS_CONTEXT_WRITE_SYNC,
+		     &req->wb_lock_context->open_context->flags))
+		desc->pg_ioflags |= FLUSH_STABLE;
 	subreq = req;
 	subreq_size = subreq->wb_bytes;
 	for(;;) {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f1f62787dd74..f224b73fa30e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -927,9 +927,13 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			goto remove_req;
 		}
 		if (nfs_write_need_commit(hdr)) {
+			struct nfs_open_context *ctx =
+				hdr->req->wb_lock_context->open_context;
+
 			/* Reset wb_nio, since the write was successful. */
 			req->wb_nio = 0;
 			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
+			clear_bit(NFS_CONTEXT_WRITE_SYNC, &ctx->flags);
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
 				hdr->ds_commit_idx);
 			goto next;
@@ -1553,7 +1557,10 @@ static void nfs_writeback_result(struct rpc_task *task,
 
 	if (resp->count < argp->count && !list_empty(&hdr->pages)) {
 		static unsigned long    complain;
+		struct nfs_open_context *ctx =
+			hdr->req->wb_lock_context->open_context;
 
+		set_bit(NFS_CONTEXT_WRITE_SYNC, &ctx->flags);
 		/* This a short write! */
 		nfs_inc_stats(hdr->inode, NFSIOS_SHORTWRITE);
 
@@ -1837,6 +1844,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* We have a mismatch. Write the page again */
 		dprintk(" mismatch\n");
 		nfs_mark_request_dirty(req);
+		set_bit(NFS_CONTEXT_WRITE_SYNC,
+			&req->wb_lock_context->open_context->flags);
 		atomic_long_inc(&NFS_I(data->inode)->redirtied_pages);
 	next:
 		nfs_unlock_and_release_request(req);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 8dd79a3f3d66..4623262da3c0 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -109,6 +109,7 @@ struct nfs_open_context {
 #define NFS_CONTEXT_BAD			(2)
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
+#define NFS_CONTEXT_WRITE_SYNC		(5)
 
 	struct nfs4_threshold	*mdsthreshold;
 	struct list_head list;