nfscl: Fix NFSv4.1/4.2 mount recovery from an expired lease

The most difficult NFSv4 client recovery case happens when the
lease has expired on the server.  For NFSv4.0, the client will
receive a NFSERR_EXPIRED reply from the server to indicate this
has happened.
For NFSv4.1/4.2, most RPCs have a Sequence operation and, as such,
the client will receive a NFSERR_BADSESSION reply when the lease
has expired for these RPCs.  The client will then call nfscl_recover()
to handle the NFSERR_BADSESSION reply.  However, for the expired lease
case, the first reclaim Open will fail with NFSERR_NOGRACE.

This patch recognizes this case and calls nfscl_expireclient()
to handle the recovery from an expired lease.

This patch only affects NFSv4.1/4.2 mounts when the lease
expires on the server, due to a network partitioning that
exceeds the lease duration or similar.

MFC after:	2 weeks
This commit is contained in:
Rick Macklem 2021-05-19 14:52:56 -07:00
parent fe815b88b5
commit c28cb257dd

View File

@ -1996,6 +1996,7 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
u_int32_t delegtype = NFSV4OPEN_DELEGATEWRITE, mode;
int i, igotlock = 0, error, trycnt, firstlock;
struct nfscllayout *lyp, *nlyp;
bool recovered_one;
/*
* First, lock the client structure, so everyone else will
@ -2077,6 +2078,7 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
* Now traverse the state lists, doing Open and Lock Reclaims.
*/
tcred = newnfs_getcred();
recovered_one = false;
owp = LIST_FIRST(&clp->nfsc_owner);
while (owp != NULL) {
nowp = LIST_NEXT(owp, nfsow_list);
@ -2110,6 +2112,7 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
op->nfso_mode, op, NULL, 0, &ndp, 1, delegtype,
tcred, p);
if (!error) {
recovered_one = true;
/* Handle any replied delegation */
if (ndp != NULL && ((ndp->nfsdl_flags & NFSCLDL_WRITE)
|| NFSMNT_RDONLY(nmp->nm_mountp))) {
@ -2168,6 +2171,21 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
nfscl_freelockowner(lp, 0);
lp = nlp;
}
} else if (error == NFSERR_NOGRACE && !recovered_one &&
NFSHASNFSV4N(nmp)) {
/*
* For NFSv4.1/4.2, the NFSERR_EXPIRED case will
* actually end up here, since the client will do
* a recovery for NFSERR_BADSESSION, but will get
* an NFSERR_NOGRACE reply for the first "reclaim"
* attempt.
* So, call nfscl_expireclient() to recover the
* opens as best we can and then do a reclaim
* complete and return.
*/
nfsrpc_reclaimcomplete(nmp, cred, p);
nfscl_expireclient(clp, nmp, tcred, p);
goto out;
}
}
if (error != 0 && error != NFSERR_BADSESSION)
@ -2254,6 +2272,23 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
if (error) {
if (nop != NULL)
free(nop, M_NFSCLOPEN);
if (error == NFSERR_NOGRACE && !recovered_one &&
NFSHASNFSV4N(nmp)) {
/*
* For NFSv4.1/4.2, the NFSERR_EXPIRED case will
* actually end up here, since the client will do
* a recovery for NFSERR_BADSESSION, but will get
* an NFSERR_NOGRACE reply for the first "reclaim"
* attempt.
* So, call nfscl_expireclient() to recover the
* opens as best we can and then do a reclaim
* complete and return.
*/
nfsrpc_reclaimcomplete(nmp, cred, p);
nfscl_expireclient(clp, nmp, tcred, p);
free(nowp, M_NFSCLOWNER);
goto out;
}
/*
* Couldn't reclaim it, so throw the state
* away. Ouch!!
@ -2261,6 +2296,7 @@ nfscl_recover(struct nfsclclient *clp, bool *retokp, struct ucred *cred,
nfscl_cleandeleg(dp);
nfscl_freedeleg(&clp->nfsc_deleg, dp, true);
} else {
recovered_one = true;
LIST_INSERT_HEAD(&extra_open, nop, nfso_list);
}
}