netfs: when subreq is marked for retry, do not check if it faced an error

The *_subreq_terminated functions today only process the NEED_RETRY
flag when the subreq was successful or failed with EAGAIN error.
However, there could be other retriable errors for network filesystems.

Avoid this by processing the NEED_RETRY irrespective of the error
code faced by the subreq. If it was specifically marked for retry,
the error code must not matter.

Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>

4 files changed, 17 insertions, 6 deletions

diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index 7a0ffa675fb1..137f0e28a44c 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -546,6 +546,15 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq)
 		}
 	}
 
+	/* If need retry is set, error should not matter unless we hit too many
+	 * retries. Pause the generation of new subreqs
+	 */
+	if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_set_pause);
+		set_bit(NETFS_RREQ_PAUSE, &rreq->flags);
+		goto skip_error_checks;
+	}
+
 	if (unlikely(subreq->error < 0)) {
 		trace_netfs_failure(rreq, subreq, subreq->error, netfs_fail_read);
 		if (subreq->source == NETFS_READ_FROM_CACHE) {
@@ -559,6 +568,7 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq)
 		set_bit(NETFS_RREQ_PAUSE, &rreq->flags);
 	}
 
+skip_error_checks:
 	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
 	netfs_subreq_clear_in_progress(subreq);
 	netfs_put_subrequest(subreq, netfs_sreq_trace_put_terminated);
diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index b99e84a8170a..7793ba5e3e8f 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -12,6 +12,7 @@
 static void netfs_reissue_read(struct netfs_io_request *rreq,
 			       struct netfs_io_subrequest *subreq)
 {
+	subreq->error = 0;
 	__clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
 	__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
 	netfs_stat(&netfs_n_rh_retry_read_subreq);
@@ -242,8 +243,7 @@ abandon_after:
 	subreq = list_next_entry(subreq, rreq_link);
 abandon:
 	list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) {
-		if (!subreq->error &&
-		    !test_bit(NETFS_SREQ_FAILED, &subreq->flags) &&
+		if (!test_bit(NETFS_SREQ_FAILED, &subreq->flags) &&
 		    !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags))
 			continue;
 		subreq->error = -ENOMEM;
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index cbf3d9194c7b..61eab34ea67e 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -492,11 +492,11 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error)
 
 	if (IS_ERR_VALUE(transferred_or_error)) {
 		subreq->error = transferred_or_error;
-		if (subreq->error == -EAGAIN)
-			set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
-		else
+		/* if need retry is set, error should not matter */
+		if (!test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
 			set_bit(NETFS_SREQ_FAILED, &subreq->flags);
-		trace_netfs_failure(wreq, subreq, transferred_or_error, netfs_fail_write);
+			trace_netfs_failure(wreq, subreq, transferred_or_error, netfs_fail_write);
+		}
 
 		switch (subreq->source) {
 		case NETFS_WRITE_TO_CACHE:
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index dd8743bc8d7f..34894da5a23e 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -250,6 +250,7 @@ void netfs_reissue_write(struct netfs_io_stream *stream,
 	iov_iter_truncate(&subreq->io_iter, size);
 
 	subreq->retry_count++;
+	subreq->error = 0;
 	__clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
 	__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
 	netfs_stat(&netfs_n_wh_retry_write_subreq);