nfsd: Support the server resetting the boot verifier

Add support to allow the server to reset the boot verifier in order to
force clients to resend I/O after a timeout failure.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

5 files changed, 48 insertions, 15 deletions

diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index bdfe5bcb3dcd..9a4ef815fb8c 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -104,6 +104,7 @@ struct nfsd_net {
 
 	/* Time of server startup */
 	struct timespec64 nfssvc_boot;
+	seqlock_t boot_lock;
 
 	/*
 	 * Max number of connections this nfsd container will allow. Defaults
@@ -179,4 +180,7 @@ struct nfsd_net {
 extern void nfsd_netns_free_versions(struct nfsd_net *nn);
 
 extern unsigned int nfsd_net_id;
+
+void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn);
+void nfsd_reset_boot_verifier(struct nfsd_net *nn);
 #endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index fcf31822c74c..86e5658651f1 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -27,6 +27,7 @@ static u32	nfs3_ftypes[] = {
 	NF3SOCK, NF3BAD,  NF3LNK, NF3BAD,
 };
 
+
 /*
  * XDR functions for basic NFS types
  */
@@ -751,14 +752,16 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
 		*p++ = htonl(resp->committed);
 		/* unique identifier, y2038 overflow can be ignored */
-		*p++ = htonl((u32)nn->nfssvc_boot.tv_sec);
-		*p++ = htonl(nn->nfssvc_boot.tv_nsec);
+		nfsd_copy_boot_verifier(verf, nn);
+		*p++ = verf[0];
+		*p++ = verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }
@@ -1125,13 +1128,15 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	/* Write verifier */
 	if (resp->status == 0) {
 		/* unique identifier, y2038 overflow can be ignored */
-		*p++ = htonl((u32)nn->nfssvc_boot.tv_sec);
-		*p++ = htonl(nn->nfssvc_boot.tv_nsec);
+		nfsd_copy_boot_verifier(verf, nn);
+		*p++ = verf[0];
+		*p++ = verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index cb51893ec1cd..4e3e77b76411 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -568,17 +568,11 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
 {
-	__be32 verf[2];
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	__be32 *verf = (__be32 *)verifier->data;
 
-	/*
-	 * This is opaque to client, so no need to byte-swap. Use
-	 * __force to keep sparse happy. y2038 time_t overflow is
-	 * irrelevant in this usage.
-	 */
-	verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec;
-	verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec;
-	memcpy(verifier->data, verf, sizeof(verifier->data));
+	BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data));
+
+	nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id));
 }
 
 static __be32
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3cf4f6aa48d6..33cbe2e5d937 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1477,6 +1477,7 @@ static __net_init int nfsd_init_net(struct net *net)
 
 	atomic_set(&nn->ntf_refcnt, 0);
 	init_waitqueue_head(&nn->ntf_wq);
+	seqlock_init(&nn->boot_lock);
 
 	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
 	if (IS_ERR(mnt)) {
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index b944553c6927..3caaf5675259 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -344,6 +344,35 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
 	return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST);
 }
 
+void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn)
+{
+	int seq = 0;
+
+	do {
+		read_seqbegin_or_lock(&nn->boot_lock, &seq);
+		/*
+		 * This is opaque to client, so no need to byte-swap. Use
+		 * __force to keep sparse happy. y2038 time_t overflow is
+		 * irrelevant in this usage
+		 */
+		verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec;
+		verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec;
+	} while (need_seqretry(&nn->boot_lock, seq));
+	done_seqretry(&nn->boot_lock, seq);
+}
+
+void nfsd_reset_boot_verifier_locked(struct nfsd_net *nn)
+{
+	ktime_get_real_ts64(&nn->nfssvc_boot);
+}
+
+void nfsd_reset_boot_verifier(struct nfsd_net *nn)
+{
+	write_seqlock(&nn->boot_lock);
+	nfsd_reset_boot_verifier_locked(nn);
+	write_sequnlock(&nn->boot_lock);
+}
+
 static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -596,7 +625,7 @@ int nfsd_create_serv(struct net *net)
 #endif
 	}
 	atomic_inc(&nn->ntf_refcnt);
-	ktime_get_real_ts64(&nn->nfssvc_boot); /* record boot time */
+	nfsd_reset_boot_verifier(nn);
 	return 0;
 }