[PATCH 2/2] NFSv4/pnfs: Allow layoutget to return EAGAIN for softerr mounts

[trondmy@xxxxxxxxx]

From: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>

If we're using the 'softerr' mount option, we may want to allow
layoutget to return EAGAIN to allow knfsd server threads to return a
JUKEBOX/DELAY error to the client instead of busy waiting.

Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
---
 fs/nfs/nfs4proc.c | 18 ++++++++++--------
 fs/nfs/pnfs.c     |  8 ++++++--
 fs/nfs/pnfs.h     |  5 ++++-
 fs/nfs/write.c    |  2 ++
 4 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 99c054a6c7b5..5deeaea8026e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9651,6 +9651,9 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 
 	nfs4_sequence_free_slot(&lgp->res.seq_res);
 
+	exception->state = NULL;
+	exception->stateid = NULL;
+
 	switch (nfs4err) {
 	case 0:
 		goto out;
@@ -9746,7 +9749,8 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 };
 
 struct pnfs_layout_segment *
-nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp,
+		    struct nfs4_exception *exception)
 {
 	struct inode *inode = lgp->args.inode;
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -9766,13 +9770,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 			 RPC_TASK_MOVEABLE,
 	};
 	struct pnfs_layout_segment *lseg = NULL;
-	struct nfs4_exception exception = {
-		.inode = inode,
-		.timeout = *timeout,
-	};
 	int status = 0;
 
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
+	exception->retry = 0;
 
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
@@ -9783,11 +9784,12 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 		goto out;
 
 	if (task->tk_status < 0) {
-		status = nfs4_layoutget_handle_exception(task, lgp, &exception);
-		*timeout = exception.timeout;
+		exception->retry = 1;
+		status = nfs4_layoutget_handle_exception(task, lgp, exception);
 	} else if (lgp->res.layoutp->len == 0) {
+		exception->retry = 1;
 		status = -EAGAIN;
-		*timeout = nfs4_update_delay(&exception.timeout);
+		nfs4_update_delay(&exception->timeout);
 	} else
 		lseg = pnfs_layout_process(lgp);
 out:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 306cba0b9e69..63904a372b2f 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1980,7 +1980,9 @@ pnfs_update_layout(struct inode *ino,
 	struct pnfs_layout_segment *lseg = NULL;
 	struct nfs4_layoutget *lgp;
 	nfs4_stateid stateid;
-	long timeout = 0;
+	struct nfs4_exception exception = {
+		.inode = ino,
+	};
 	unsigned long giveup = jiffies + (clp->cl_lease_time << 1);
 	bool first;
 
@@ -2144,7 +2146,7 @@ pnfs_update_layout(struct inode *ino,
 	lgp->lo = lo;
 	pnfs_get_layout_hdr(lo);
 
-	lseg = nfs4_proc_layoutget(lgp, &timeout);
+	lseg = nfs4_proc_layoutget(lgp, &exception);
 	trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
 	nfs_layoutget_end(lo);
@@ -2171,6 +2173,8 @@ pnfs_update_layout(struct inode *ino,
 			goto out_put_layout_hdr;
 		}
 		if (lseg) {
+			if (!exception.retry)
+				goto out_put_layout_hdr;
 			if (first)
 				pnfs_clear_first_layoutget(lo);
 			trace_pnfs_update_layout(ino, pos, count,
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index d886c8226d8f..db57a85500ee 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -35,6 +35,7 @@
 #include <linux/nfs_page.h>
 #include <linux/workqueue.h>
 
+struct nfs4_exception;
 struct nfs4_opendata;
 
 enum {
@@ -245,7 +246,9 @@ extern size_t max_response_pages(struct nfs_server *server);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev,
 				   const struct cred *cred);
-extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout);
+extern struct pnfs_layout_segment *
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp,
+		    struct nfs4_exception *exception);
 extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
 
 /* pnfs.c */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8c1ee1a1a28f..59478a32e19f 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -739,6 +739,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 					&pgio);
 		pgio.pg_error = 0;
 		nfs_pageio_complete(&pgio);
+		if (err == -EAGAIN && mntflags & NFS_MOUNT_SOFTERR)
+			break;
 	} while (err < 0 && !nfs_error_is_fatal(err));
 	nfs_io_completion_put(ioc);
 
-- 
2.41.0