[ Upstream commit c34fae003c79570b6c930b425fea3f0b7b1e7056 ]
If the server returns with EAGAIN when we're trying to recover from
a server reboot, we currently delay for 1 second, but then mark the
stateid as needing recovery after the grace period has expired.
Instead, we should just retry the same recovery process immediately
after the 1 second delay. Break out of the loop after 10 retries.
Fixes: 35a61606a612 ("NFS: Reduce indentation of the switch statement...")
Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
fs/nfs/nfs4state.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e2e3c4f04d3e0..556ec916846f0 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1606,6 +1606,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
{
struct nfs4_state *state;
+ unsigned int loop = 0;
int status = 0;
/* Note: we rely on the sp->so_states list being ordered
@@ -1632,8 +1633,10 @@ restart:
switch (status) {
default:
- if (status >= 0)
+ if (status >= 0) {
+ loop = 0;
break;
+ }
printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
/* Fall through */
case -ENOENT:
@@ -1647,6 +1650,10 @@ restart:
break;
case -EAGAIN:
ssleep(1);
+ if (loop++ < 10) {
+ set_bit(ops->state_flag_bit, &state->flags);
+ break;
+ }
/* Fall through */
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
--
2.20.1
