[PATCH 00/10] 3.7 candidates

[PATCH 00/10] 3.7 candidates

[Chuck Lever]

Hi-

Please consider these patches for 3.7.  This series adds support for
uniform client strings and server trunking detection, in addition to
addressing the "rpcauth_create() returns EEXIST" issue, as discussed.
While the UCS work has seen some light testing, more review is
welcome.

Instead of changing the documented name for the new
nfs.nfs4_unique_id module parameter as we discussed, I moved the
parameter to the super.c module with most of the other parameters,
so it's name remains without the nfs4. prefix.  I haven't had a
chance to test this final change.

---

Chuck Lever (10):
      NFS: Add nfs4_unique_id boot parameter
      NFS: Discover NFSv4 server trunking when mounting
      NFS: Use the same nfs_client_id4 for every server
      NFS: Introduce "migration" mount option
      SUNRPC: Introduce rpc_clone_client_set_auth()
      SUNRPC: Refactor rpc_clone_client()
      SUNRPC: Use __func__ in dprintk() in auth_gss.c
      SUNRPC: Clean up dprintk messages in rpc_pipe.c
      NFS: Slow down state manager after an unhandled error
      NFS: nfs_parsed_mount_options can use unsigned int


 Documentation/filesystems/nfs/nfs.txt |   44 +++++-
 Documentation/kernel-parameters.txt   |    5 +
 fs/nfs/client.c                       |   18 +-
 fs/nfs/internal.h                     |   14 +-
 fs/nfs/nfs4_fs.h                      |   11 +
 fs/nfs/nfs4client.c                   |  253 +++++++++++++++++++++++++++++++++
 fs/nfs/nfs4namespace.c                |   14 --
 fs/nfs/nfs4proc.c                     |   59 ++++++--
 fs/nfs/nfs4state.c                    |  183 ++++++++++++++++++++++++
 fs/nfs/super.c                        |   25 +++
 include/linux/nfs_fs_sb.h             |    3 
 include/linux/sunrpc/clnt.h           |    2 
 net/sunrpc/auth_gss/auth_gss.c        |   58 ++++----
 net/sunrpc/clnt.c                     |  105 ++++++++------
 net/sunrpc/rpc_pipe.c                 |    8 +
 15 files changed, 684 insertions(+), 118 deletions(-)

-- 
Chuck Lever

[PATCH 01/10] NFS: nfs_parsed_mount_options can use unsigned int

[Chuck Lever]

fs/nfs/super.c: In function ‘nfs_compare_remount_data’:
fs/nfs/super.c:2042:18: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2043:18: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2044:20: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2046:21: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2047:21: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2048:21: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2049:21: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]
fs/nfs/super.c:2050:18: warning: comparison between signed and
    unsigned integer expressions [-Wsign-compare]

Seen with gcc (GCC) 4.6.3 20120306 (Red Hat 4.6.3-2).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 fs/nfs/internal.h |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 31fdb03..89560be 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -101,11 +101,11 @@ struct nfs_client_initdata {
  */
 struct nfs_parsed_mount_data {
 	int			flags;
-	int			rsize, wsize;
-	int			timeo, retrans;
-	int			acregmin, acregmax,
+	unsigned int		rsize, wsize;
+	unsigned int		timeo, retrans;
+	unsigned int		acregmin, acregmax,
 				acdirmin, acdirmax;
-	int			namlen;
+	unsigned int		namlen;
 	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;

[PATCH 02/10] NFS: Slow down state manager after an unhandled error

[Chuck Lever]

If the state manager thread is not actually able to fully recover from
some situation, it wakes up waiters, who kick off a new state manager
thread.  Quite often the fresh invocation of the state manager is just
as successful.

This results in a livelock as the client dumps thousands of NFS
requests a second on the network in a vain attempt to recover.  Not
very friendly.

To mitigate this situation, add a delay in the state manager after
an unhandled error, so that the client sends just a few requests
every second in this case.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 fs/nfs/nfs4state.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 55148de..d6e0d63 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2008,6 +2008,7 @@ out_error:
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
+	ssleep(1);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }

[PATCH 03/10] SUNRPC: Clean up dprintk messages in rpc_pipe.c

[Chuck Lever]

Clean up: The blank space in front of the message must be spaces.
Tabs show up on the console as a graphical character.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 net/sunrpc/rpc_pipe.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 21fde99..80f5dd2 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1119,8 +1119,8 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
 		return -ENOMEM;
-	dprintk("RPC:	sending pipefs MOUNT notification for net %p%s\n", net,
-								NET_NAME(net));
+	dprintk("RPC:       sending pipefs MOUNT notification for net %p%s\n",
+		net, NET_NAME(net));
 	sn->pipefs_sb = sb;
 	err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_MOUNT,
@@ -1155,8 +1155,8 @@ static void rpc_kill_sb(struct super_block *sb)
 	sn->pipefs_sb = NULL;
 	mutex_unlock(&sn->pipefs_sb_lock);
 	put_net(net);
-	dprintk("RPC:	sending pipefs UMOUNT notification for net %p%s\n", net,
-								NET_NAME(net));
+	dprintk("RPC:       sending pipefs UMOUNT notification for net %p%s\n",
+		net, NET_NAME(net));
 	blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_UMOUNT,
 					   sb);

[PATCH 04/10] SUNRPC: Use __func__ in dprintk() in auth_gss.c

[Chuck Lever]

Clean up: Some function names have changed, but debugging messages
were never updated.  Automate the construction of the function name
in debugging messages.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 net/sunrpc/auth_gss/auth_gss.c |   58 ++++++++++++++++++++--------------------
 1 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 34c5220..909dc0c 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -239,7 +239,7 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct
 	}
 	return q;
 err:
-	dprintk("RPC:       gss_fill_context returning %ld\n", -PTR_ERR(p));
+	dprintk("RPC:       %s returning %ld\n", __func__, -PTR_ERR(p));
 	return p;
 }
 
@@ -301,10 +301,10 @@ __gss_find_upcall(struct rpc_pipe *pipe, uid_t uid)
 		if (pos->uid != uid)
 			continue;
 		atomic_inc(&pos->count);
-		dprintk("RPC:       gss_find_upcall found msg %p\n", pos);
+		dprintk("RPC:       %s found msg %p\n", __func__, pos);
 		return pos;
 	}
-	dprintk("RPC:       gss_find_upcall found nothing\n");
+	dprintk("RPC:       %s found nothing\n", __func__);
 	return NULL;
 }
 
@@ -507,8 +507,8 @@ gss_refresh_upcall(struct rpc_task *task)
 	struct rpc_pipe *pipe;
 	int err = 0;
 
-	dprintk("RPC: %5u gss_refresh_upcall for uid %u\n", task->tk_pid,
-								cred->cr_uid);
+	dprintk("RPC: %5u %s for uid %u\n",
+		task->tk_pid, __func__, cred->cr_uid);
 	gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		/* XXX: warning on the first, under the assumption we
@@ -539,8 +539,8 @@ gss_refresh_upcall(struct rpc_task *task)
 	spin_unlock(&pipe->lock);
 	gss_release_msg(gss_msg);
 out:
-	dprintk("RPC: %5u gss_refresh_upcall for uid %u result %d\n",
-			task->tk_pid, cred->cr_uid, err);
+	dprintk("RPC: %5u %s for uid %u result %d\n",
+		task->tk_pid, __func__, cred->cr_uid, err);
 	return err;
 }
 
@@ -553,7 +553,7 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 	DEFINE_WAIT(wait);
 	int err = 0;
 
-	dprintk("RPC:       gss_upcall for uid %u\n", cred->cr_uid);
+	dprintk("RPC:       %s for uid %u\n", __func__, cred->cr_uid);
 retry:
 	gss_msg = gss_setup_upcall(gss_auth->client, gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
@@ -594,8 +594,8 @@ out_intr:
 	finish_wait(&gss_msg->waitqueue, &wait);
 	gss_release_msg(gss_msg);
 out:
-	dprintk("RPC:       gss_create_upcall for uid %u result %d\n",
-			cred->cr_uid, err);
+	dprintk("RPC:       %s for uid %u result %d\n",
+		__func__, cred->cr_uid, err);
 	return err;
 }
 
@@ -681,7 +681,7 @@ err_put_ctx:
 err:
 	kfree(buf);
 out:
-	dprintk("RPC:       gss_pipe_downcall returning %Zd\n", err);
+	dprintk("RPC:       %s returning %Zd\n", __func__, err);
 	return err;
 }
 
@@ -747,8 +747,8 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 	struct gss_upcall_msg *gss_msg = container_of(msg, struct gss_upcall_msg, msg);
 
 	if (msg->errno < 0) {
-		dprintk("RPC:       gss_pipe_destroy_msg releasing msg %p\n",
-				gss_msg);
+		dprintk("RPC:       %s releasing msg %p\n",
+			__func__, gss_msg);
 		atomic_inc(&gss_msg->count);
 		gss_unhash_msg(gss_msg);
 		if (msg->errno == -ETIMEDOUT)
@@ -976,7 +976,7 @@ gss_destroying_context(struct rpc_cred *cred)
 static void
 gss_do_free_ctx(struct gss_cl_ctx *ctx)
 {
-	dprintk("RPC:       gss_free_ctx\n");
+	dprintk("RPC:       %s\n", __func__);
 
 	gss_delete_sec_context(&ctx->gc_gss_ctx);
 	kfree(ctx->gc_wire_ctx.data);
@@ -999,7 +999,7 @@ gss_free_ctx(struct gss_cl_ctx *ctx)
 static void
 gss_free_cred(struct gss_cred *gss_cred)
 {
-	dprintk("RPC:       gss_free_cred %p\n", gss_cred);
+	dprintk("RPC:       %s cred=%p\n", __func__, gss_cred);
 	kfree(gss_cred);
 }
 
@@ -1049,8 +1049,8 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	struct gss_cred	*cred = NULL;
 	int err = -ENOMEM;
 
-	dprintk("RPC:       gss_create_cred for uid %d, flavor %d\n",
-		acred->uid, auth->au_flavor);
+	dprintk("RPC:       %s for uid %d, flavor %d\n",
+		__func__, acred->uid, auth->au_flavor);
 
 	if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS)))
 		goto out_err;
@@ -1069,7 +1069,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	return &cred->gc_base;
 
 out_err:
-	dprintk("RPC:       gss_create_cred failed with error %d\n", err);
+	dprintk("RPC:       %s failed with error %d\n", __func__, err);
 	return ERR_PTR(err);
 }
 
@@ -1127,7 +1127,7 @@ gss_marshal(struct rpc_task *task, __be32 *p)
 	struct kvec	iov;
 	struct xdr_buf	verf_buf;
 
-	dprintk("RPC: %5u gss_marshal\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 
 	*p++ = htonl(RPC_AUTH_GSS);
 	cred_len = p++;
@@ -1253,7 +1253,7 @@ gss_validate(struct rpc_task *task, __be32 *p)
 	u32		flav,len;
 	u32		maj_stat;
 
-	dprintk("RPC: %5u gss_validate\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 
 	flav = ntohl(*p++);
 	if ((len = ntohl(*p++)) > RPC_MAX_AUTH_SIZE)
@@ -1271,20 +1271,20 @@ gss_validate(struct rpc_task *task, __be32 *p)
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat) {
-		dprintk("RPC: %5u gss_validate: gss_verify_mic returned "
-				"error 0x%08x\n", task->tk_pid, maj_stat);
+		dprintk("RPC: %5u %s: gss_verify_mic returned error 0x%08x\n",
+			task->tk_pid, __func__, maj_stat);
 		goto out_bad;
 	}
 	/* We leave it to unwrap to calculate au_rslack. For now we just
 	 * calculate the length of the verifier: */
 	cred->cr_auth->au_verfsize = XDR_QUADLEN(len) + 2;
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_validate: gss_verify_mic succeeded.\n",
-			task->tk_pid);
+	dprintk("RPC: %5u %s: gss_verify_mic succeeded.\n",
+			task->tk_pid, __func__);
 	return p + XDR_QUADLEN(len);
 out_bad:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_validate failed.\n", task->tk_pid);
+	dprintk("RPC: %5u %s failed.\n", task->tk_pid, __func__);
 	return NULL;
 }
 
@@ -1466,7 +1466,7 @@ gss_wrap_req(struct rpc_task *task,
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
 	int             status = -EIO;
 
-	dprintk("RPC: %5u gss_wrap_req\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 	if (ctx->gc_proc != RPC_GSS_PROC_DATA) {
 		/* The spec seems a little ambiguous here, but I think that not
 		 * wrapping context destruction requests makes the most sense.
@@ -1489,7 +1489,7 @@ gss_wrap_req(struct rpc_task *task,
 	}
 out:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_wrap_req returning %d\n", task->tk_pid, status);
+	dprintk("RPC: %5u %s returning %d\n", task->tk_pid, __func__, status);
 	return status;
 }
 
@@ -1604,8 +1604,8 @@ out_decode:
 	status = gss_unwrap_req_decode(decode, rqstp, p, obj);
 out:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_unwrap_resp returning %d\n", task->tk_pid,
-			status);
+	dprintk("RPC: %5u %s returning %d\n",
+		task->tk_pid, __func__, status);
 	return status;
 }
 

[PATCH 05/10] SUNRPC: Refactor rpc_clone_client()

[Chuck Lever]

rpc_clone_client() does most of the same tasks as rpc_new_client(),
so there is an opportunity for code re-use.  Create a generic helper
that makes it easy to clone an RPC client while replacing any of the
clnt's parameters.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 net/sunrpc/clnt.c |   83 +++++++++++++++++++++++++++--------------------------
 1 files changed, 43 insertions(+), 40 deletions(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index fa48c60..afbeefa 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -490,59 +490,62 @@ EXPORT_SYMBOL_GPL(rpc_create);
  * same transport while varying parameters such as the authentication
  * flavour.
  */
-struct rpc_clnt *
-rpc_clone_client(struct rpc_clnt *clnt)
+static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
+					   struct rpc_clnt *clnt)
 {
-	struct rpc_clnt *new;
 	struct rpc_xprt *xprt;
-	int err = -ENOMEM;
+	struct rpc_clnt *new;
+	int err;
 
-	new = kmemdup(clnt, sizeof(*new), GFP_KERNEL);
-	if (!new)
-		goto out_no_clnt;
-	new->cl_parent = clnt;
-	/* Turn off autobind on clones */
-	new->cl_autobind = 0;
-	INIT_LIST_HEAD(&new->cl_tasks);
-	spin_lock_init(&new->cl_lock);
-	rpc_init_rtt(&new->cl_rtt_default, clnt->cl_timeout->to_initval);
-	new->cl_metrics = rpc_alloc_iostats(clnt);
-	if (new->cl_metrics == NULL)
-		goto out_no_stats;
-	if (clnt->cl_principal) {
-		new->cl_principal = kstrdup(clnt->cl_principal, GFP_KERNEL);
-		if (new->cl_principal == NULL)
-			goto out_no_principal;
-	}
+	err = -ENOMEM;
 	rcu_read_lock();
 	xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
 	rcu_read_unlock();
 	if (xprt == NULL)
-		goto out_no_transport;
-	rcu_assign_pointer(new->cl_xprt, xprt);
-	atomic_set(&new->cl_count, 1);
-	err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name);
-	if (err != 0)
-		goto out_no_path;
-	rpc_clnt_set_nodename(new, utsname()->nodename);
-	if (new->cl_auth)
-		atomic_inc(&new->cl_auth->au_count);
+		goto out_err;
+	args->servername = xprt->servername;
+
+	new = rpc_new_client(args, xprt);
+	if (IS_ERR(new)) {
+		err = PTR_ERR(new);
+		goto out_put;
+	}
+
 	atomic_inc(&clnt->cl_count);
-	rpc_register_client(new);
-	rpciod_up();
+	new->cl_parent = clnt;
+
+	/* Turn off autobind on clones */
+	new->cl_autobind = 0;
+	new->cl_softrtry = clnt->cl_softrtry;
+	new->cl_discrtry = clnt->cl_discrtry;
+	new->cl_chatty = clnt->cl_chatty;
 	return new;
-out_no_path:
+
+out_put:
 	xprt_put(xprt);
-out_no_transport:
-	kfree(new->cl_principal);
-out_no_principal:
-	rpc_free_iostats(new->cl_metrics);
-out_no_stats:
-	kfree(new);
-out_no_clnt:
+out_err:
 	dprintk("RPC:       %s: returned error %d\n", __func__, err);
 	return ERR_PTR(err);
 }
+
+/**
+ * rpc_clone_client - Clone an RPC client structure
+ *
+ * @clnt: RPC client whose parameters are copied
+ *
+ * Returns a fresh RPC client or an ERR_PTR.
+ */
+struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt)
+{
+	struct rpc_create_args args = {
+		.program	= clnt->cl_program,
+		.prognumber	= clnt->cl_prog,
+		.version	= clnt->cl_vers,
+		.authflavor	= clnt->cl_auth->au_flavor,
+		.client_name	= clnt->cl_principal,
+	};
+	return __rpc_clone_client(&args, clnt);
+}
 EXPORT_SYMBOL_GPL(rpc_clone_client);
 
 /*

[PATCH 06/10] SUNRPC: Introduce rpc_clone_client_set_auth()

[Chuck Lever]

An ULP is supposed to be able to replace a GSS rpc_auth object with
another GSS rpc_auth object using rpcauth_create().  However,
rpcauth_create() in 3.5 reliably fails with -EEXIST in this case.
This is because when gss_create() attempts to create the upcall pipes,
sometimes they are already there.  For example if a pipe FS mount
event occurs, or a previous GSS flavor was in use for this rpc_clnt.

It turns out that's not the only problem here.  While working on a
fix for the above problem, we noticed that replacing an rpc_clnt's
rpc_auth is not safe, since dereferencing the cl_auth field is not
protected in any way.

So we're deprecating the ability of rpcauth_create() to switch an
rpc_clnt's security flavor during normal operation.  Instead, let's
add a fresh API that clones an rpc_clnt and gives the clone a new
flavor before it's used.

This makes immediate use of the new __rpc_clone_client() helper.

This can be used in a similar fashion to rpcauth_create() when a
client is hunting for the correct security flavor.  Instead of
replacing an rpc_clnt's security flavor in a loop, the ULP replaces
the whole rpc_clnt.

To fix the -EEXIST problem, any ULP logic that relies on replacing
an rpc_clnt's rpc_auth with rpcauth_create() must be changed to use
this API instead.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 fs/nfs/client.c             |   13 ++-----------
 fs/nfs/nfs4namespace.c      |   14 +-------------
 include/linux/sunrpc/clnt.h |    2 ++
 net/sunrpc/clnt.c           |   22 ++++++++++++++++++++++
 4 files changed, 27 insertions(+), 24 deletions(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9969444..143149d 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -668,7 +668,8 @@ int nfs_init_server_rpcclient(struct nfs_server *server,
 {
 	struct nfs_client *clp = server->nfs_client;
 
-	server->client = rpc_clone_client(clp->cl_rpcclient);
+	server->client = rpc_clone_client_set_auth(clp->cl_rpcclient,
+							pseudoflavour);
 	if (IS_ERR(server->client)) {
 		dprintk("%s: couldn't create rpc_client!\n", __func__);
 		return PTR_ERR(server->client);
@@ -678,16 +679,6 @@ int nfs_init_server_rpcclient(struct nfs_server *server,
 			timeo,
 			sizeof(server->client->cl_timeout_default));
 	server->client->cl_timeout = &server->client->cl_timeout_default;
-
-	if (pseudoflavour != clp->cl_rpcclient->cl_auth->au_flavor) {
-		struct rpc_auth *auth;
-
-		auth = rpcauth_create(pseudoflavour, server->client);
-		if (IS_ERR(auth)) {
-			dprintk("%s: couldn't create credcache!\n", __func__);
-			return PTR_ERR(auth);
-		}
-	}
 	server->client->cl_softrtry = 0;
 	if (server->flags & NFS_MOUNT_SOFT)
 		server->client->cl_softrtry = 1;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 017b4b0..5ce7024 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -192,25 +192,13 @@ out:
 struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode,
 					struct qstr *name)
 {
-	struct rpc_clnt *clone;
-	struct rpc_auth *auth;
 	rpc_authflavor_t flavor;
 
 	flavor = nfs4_negotiate_security(inode, name);
 	if ((int)flavor < 0)
 		return ERR_PTR(flavor);
 
-	clone = rpc_clone_client(clnt);
-	if (IS_ERR(clone))
-		return clone;
-
-	auth = rpcauth_create(flavor, clone);
-	if (!auth) {
-		rpc_shutdown_client(clone);
-		clone = ERR_PTR(-EIO);
-	}
-
-	return clone;
+	return rpc_clone_client_set_auth(clnt, flavor);
 }
 
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 523547e..34206b8 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -130,6 +130,8 @@ struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
+struct rpc_clnt *rpc_clone_client_set_auth(struct rpc_clnt *,
+				rpc_authflavor_t);
 void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
 void		rpc_task_release_client(struct rpc_task *);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index afbeefa..cdc7564 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -548,6 +548,28 @@ struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_clone_client);
 
+/**
+ * rpc_clone_client_set_auth - Clone an RPC client structure and set its auth
+ *
+ * @clnt: RPC client whose parameters are copied
+ * @auth: security flavor for new client
+ *
+ * Returns a fresh RPC client or an ERR_PTR.
+ */
+struct rpc_clnt *
+rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
+{
+	struct rpc_create_args args = {
+		.program	= clnt->cl_program,
+		.prognumber	= clnt->cl_prog,
+		.version	= clnt->cl_vers,
+		.authflavor	= flavor,
+		.client_name	= clnt->cl_principal,
+	};
+	return __rpc_clone_client(&args, clnt);
+}
+EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth);
+
 /*
  * Kill all tasks for the given client.
  * XXX: kill their descendants as well?

[PATCH 07/10] NFS: Introduce "migration" mount option

[Chuck Lever]

Currently, the Linux client uses a unique nfs_client_id4.id string
when identifying itself to distinct NFS servers.

To support transparent state migration, the Linux client will have to
use the same nfs_client_id4 string for all servers it communicates
with (also known as the "uniform client string" approach).  Otherwise
NFS servers can not recognize that open and lock state need to be
merged after a file system transition.

Unfortunately, there are some NFSv4.0 servers currently in the field
that do not tolerate the uniform client string approach.

Thus, by default, our NFSv4.0 mounts will continue to use the current
approach, and we introduce a mount option that switches them to use
the uniform model.  Client administrators must identify which servers
can be mounted with this option.  Eventually most NFSv4.0 servers will
be able to handle the uniform approach, and we can change the default.

The first mount of a server controls the behavior for all subsequent
mounts for the lifetime of that set of mounts of that server.  After
the last mount of that server is gone, the client erases the data
structure that tracks the lease.  A subsequent lease may then honor
a different "migration" setting.

This patch adds only the infrastructure for parsing the new mount
option.  Support for uniform client strings is added in a subsequent
patch.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---

 fs/nfs/client.c           |    2 ++
 fs/nfs/super.c            |   20 ++++++++++++++++++++
 include/linux/nfs_fs_sb.h |    2 ++
 3 files changed, 24 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 143149d..92aed2e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -752,6 +752,8 @@ static int nfs_init_server(struct nfs_server *server,
 			data->timeo, data->retrans);
 	if (data->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (server->options & NFS_OPTION_MIGRATION)
+		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 239aff7..4aabf19 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -88,6 +88,7 @@ enum {
 	Opt_sharecache, Opt_nosharecache,
 	Opt_resvport, Opt_noresvport,
 	Opt_fscache, Opt_nofscache,
+	Opt_migration, Opt_nomigration,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -147,6 +148,8 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_noresvport, "noresvport" },
 	{ Opt_fscache, "fsc" },
 	{ Opt_nofscache, "nofsc" },
+	{ Opt_migration, "migration" },
+	{ Opt_nomigration, "nomigration" },
 
 	{ Opt_port, "port=%s" },
 	{ Opt_rsize, "rsize=%s" },
@@ -676,6 +679,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (nfss->options & NFS_OPTION_FSCACHE)
 		seq_printf(m, ",fsc");
 
+	if (nfss->options & NFS_OPTION_MIGRATION)
+		seq_printf(m, ",migration");
+
 	if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
 		if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
 			seq_printf(m, ",lookupcache=none");
@@ -1243,6 +1249,12 @@ static int nfs_parse_mount_options(char *raw,
 			kfree(mnt->fscache_uniq);
 			mnt->fscache_uniq = NULL;
 			break;
+		case Opt_migration:
+			mnt->options |= NFS_OPTION_MIGRATION;
+			break;
+		case Opt_nomigration:
+			mnt->options &= NFS_OPTION_MIGRATION;
+			break;
 
 		/*
 		 * options that take numeric values
@@ -1535,6 +1547,10 @@ static int nfs_parse_mount_options(char *raw,
 	if (mnt->minorversion && mnt->version != 4)
 		goto out_minorversion_mismatch;
 
+	if (mnt->options & NFS_OPTION_MIGRATION &&
+	    mnt->version != 4 && mnt->minorversion != 0)
+		goto out_migration_misuse;
+
 	/*
 	 * verify that any proto=/mountproto= options match the address
 	 * familiies in the addr=/mountaddr= options.
@@ -1572,6 +1588,10 @@ out_minorversion_mismatch:
 	printk(KERN_INFO "NFS: mount option vers=%u does not support "
 			 "minorversion=%u\n", mnt->version, mnt->minorversion);
 	return 0;
+out_migration_misuse:
+	printk(KERN_INFO
+		"NFS: 'migration' not supported for this NFS version\n");
+	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
 	return 0;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 310c63c..2e22fc7 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -39,6 +39,7 @@ struct nfs_client {
 	unsigned long		cl_flags;	/* behavior switches */
 #define NFS_CS_NORESVPORT	0		/* - use ephemeral src port */
 #define NFS_CS_DISCRTRY		1		/* - disconnect on RPC retry */
+#define NFS_CS_MIGRATION	2		/* - transparent state migr */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -125,6 +126,7 @@ struct nfs_server {
 	unsigned int		namelen;
 	unsigned int		options;	/* extra options enabled by mount */
 #define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
+#define NFS_OPTION_MIGRATION	0x00000002	/* - NFSv4 migration enabled */
 
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */

[PATCH 08/10] NFS: Use the same nfs_client_id4 for every server

[Chuck Lever]

Currently, when identifying itself to NFS servers, the Linux NFS
client uses a unique nfs_client_id4.id string for each server IP
address it talks with.  For example, when client A talks to server X,
the client identifies itself using a string like "AX".  The
requirements for these strings are specified in detail by RFC 3530
(and bis).

This form of client identification presents a problem for Transparent
State Migration.  When client A's state on server X is migrated to
server Y, it continues to be associated with string "AX."  But,
according to the rules of client string construction above, client
A will present string "AY" when communicating with server Y.

Server Y thus has no way to know that client A should be associated
with the state migrated from server X.  "AX" is all but abandoned,
interfering with establishing fresh state for client A on server Y.

To support transparent state migration, then, NFSv4.0 clients must
instead use the same nfs_client_id4.id string to identify themselves
to every NFS server; something like "A".

Now a client identifies itself as "A" to server X.  When a file
system on server X transitions to server Y, and client A identifies
itself as "A" to server Y, Y will know immediately that the state
associated with "A," whether it is native or migrated, is owned by
the client, and can merge both into a single lease.

As a pre-requisite to adding support for NFSv4 migration to the Linux
NFS client, this patch changes the way Linux identifies itself to NFS
servers via the SETCLIENTID (NFSv4 minor version 0) and EXCHANGE_ID
(NFSv4 minor version 1) operations.

In addition to removing the server's IP address from nfs_client_id4,
the Linux NFS client will also no longer use its own source IP address
as part of the nfs_client_id4 string.  On multi-homed clients, the
value of this address depends on the address family and network
routing used to contact the server, thus it can be different for each
server.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---

 fs/nfs/nfs4proc.c |   51 +++++++++++++++++++++++++++++++++++++++------------
 1 files changed, 39 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6352741..80aadcc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4012,6 +4012,32 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+static unsigned int
+nfs4_init_nonuniform_client_string(const struct nfs_client *clp,
+				   char *buf, size_t len)
+{
+	unsigned int result;
+
+	rcu_read_lock();
+	result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s",
+				clp->cl_ipaddr,
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_ADDR),
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_PROTO));
+	rcu_read_unlock();
+	return result;
+}
+
+static unsigned int
+nfs4_init_uniform_client_string(const struct nfs_client *clp,
+				char *buf, size_t len)
+{
+	return scnprintf(buf, len, "Linux NFSv%u.%u %s",
+				clp->rpc_ops->version, clp->cl_minorversion,
+				clp->cl_rpcclient->cl_nodename);
+}
+
 /**
  * nfs4_proc_setclientid - Negotiate client ID
  * @clp: state data structure
@@ -4042,15 +4068,18 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 
 	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
-	rcu_read_lock();
-	setclientid.sc_name_len = scnprintf(setclientid.sc_name,
-			sizeof(setclientid.sc_name), "%s/%s %s",
-			clp->cl_ipaddr,
-			rpc_peeraddr2str(clp->cl_rpcclient,
-						RPC_DISPLAY_ADDR),
-			rpc_peeraddr2str(clp->cl_rpcclient,
-						RPC_DISPLAY_PROTO));
+	if (test_bit(NFS_CS_MIGRATION, &clp->cl_flags))
+		setclientid.sc_name_len =
+				nfs4_init_uniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
+	else
+		setclientid.sc_name_len =
+				nfs4_init_nonuniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
 	/* cb_client4 */
+	rcu_read_lock();
 	setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
 				sizeof(setclientid.sc_netid),
 				rpc_peeraddr2str(clp->cl_rpcclient,
@@ -5272,10 +5301,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	};
 
 	nfs4_init_boot_verifier(clp, &verifier);
-	args.id_len = scnprintf(args.id, sizeof(args.id),
-				"%s/%s",
-				clp->cl_ipaddr,
-				clp->cl_rpcclient->cl_nodename);
+	args.id_len = nfs4_init_uniform_client_string(clp, args.id,
+							sizeof(args.id));
 	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
 		clp->cl_rpcclient->cl_auth->au_ops->au_name,
 		args.id_len, args.id);

[PATCH 09/10] NFS: Discover NFSv4 server trunking when mounting

[Chuck Lever]

"Server trunking" is a fancy named for a multi-homed NFS server.
Trunking might occur if a client sends NFS requests for a single
workload to multiple network interfaces on the same server.  There
are some implications for NFSv4 state management that make it useful
for a client to know if a single NFSv4 server instance is
multi-homed.  (Note this is only a consideration for NFSv4, not for
legacy versions of NFS, which are stateless).

If a client cares about server trunking, no NFSv4 operations can
proceed until that client determines who it is talking to.  Thus
server IP trunking discovery must be done when the client first
encounters an unfamiliar server IP address.

The nfs_get_client() function walks the nfs_client_list and matches
on server IP address.  The outcome of that walk tells us immediately
if we have an unfamiliar server IP address.  It invokes
nfs_init_client() in this case.  Thus, nfs4_init_client() is a good
spot to perform trunking discovery.

Discovery requires a client to establish a fresh client ID, so our
client will now send SETCLIENTID or EXCHANGE_ID as the first NFS
operation after a successful ping, rather than waiting for an
application to perform an operation that requires NFSv4 state.

The exact process for detecting trunking is different for NFSv4.0 and
NFSv4.1, so a minorversion-specific init_client callout method is
introduced.

CLID_INUSE recovery is important for the trunking discovery process.
CLID_INUSE is a sign the server recognizes the client's nfs_client_id4
id string, but the client is using the wrong principal this time for
the SETCLIENTID operation.  The SETCLIENTID must be retried with a
series of different principals until one works, and then the rest of
trunking discovery can proceed.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 fs/nfs/client.c           |    3 -
 fs/nfs/internal.h         |    6 +
 fs/nfs/nfs4_fs.h          |    8 +
 fs/nfs/nfs4client.c       |  253 +++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4proc.c         |    4 +
 fs/nfs/nfs4state.c        |  182 ++++++++++++++++++++++++++++++++
 include/linux/nfs_fs_sb.h |    1 
 7 files changed, 455 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 92aed2e..57d2a5c 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -498,7 +498,8 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
-			list_add(&new->cl_share_link, &nn->nfs_client_list);
+			list_add_tail(&new->cl_share_link,
+					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
 			return rpc_ops->init_client(new, timeparms, ip_addr,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 89560be..89a795d 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -483,6 +483,12 @@ extern int _nfs4_call_sync_session(struct rpc_clnt *clnt,
 				   struct nfs4_sequence_args *args,
 				   struct nfs4_sequence_res *res,
 				   int cache_reply);
+extern int nfs40_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
+extern int nfs41_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
 
 /*
  * Determine the device name as a string
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index da0618a..c8e0998 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -191,6 +191,8 @@ struct nfs4_state_recovery_ops {
 	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
 	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
 	int (*reclaim_complete)(struct nfs_client *);
+	int (*detect_trunking)(struct nfs_client *, struct nfs_client **,
+		struct rpc_cred *);
 };
 
 struct nfs4_state_maintenance_ops {
@@ -320,9 +322,15 @@ extern void nfs4_renew_state(struct work_struct *);
 /* nfs4state.c */
 struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **);
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 #if defined(CONFIG_NFS_V4_1)
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 24eb663..739b328 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -185,6 +185,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 				    rpc_authflavor_t authflavour)
 {
 	char buf[INET6_ADDRSTRLEN + 1];
+	struct nfs_client *old;
 	int error;
 
 	if (clp->cl_cons_state == NFS_CS_READY) {
@@ -230,6 +231,17 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 
 	if (!nfs4_has_session(clp))
 		nfs_mark_client_ready(clp, NFS_CS_READY);
+
+	error = nfs4_discover_server_trunking(clp, &old);
+	if (error < 0)
+		goto error;
+	if (clp != old) {
+		clp->cl_preserve_clid = true;
+		nfs_put_client(clp);
+		clp = old;
+		atomic_inc(&clp->cl_count);
+	}
+
 	return clp;
 
 error:
@@ -239,6 +251,247 @@ error:
 	return ERR_PTR(error);
 }
 
+/*
+ * Returns true if the client IDs match
+ */
+static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b)
+{
+	if (a->cl_clientid != b->cl_clientid) {
+		dprintk("NFS: --> %s client ID %llx does not match %llx\n",
+			__func__, a->cl_clientid, b->cl_clientid);
+		return false;
+	}
+	dprintk("NFS: --> %s client ID %llx matches %llx\n",
+		__func__, a->cl_clientid, b->cl_clientid);
+	return true;
+}
+
+/*
+ * SETCLIENTID just did a callback update with the callback ident in
+ * "drop," but server trunking discovery claims "drop" and "keep" are
+ * actually the same server.  Swap the callback IDs so that "keep"
+ * will continue to use the callback ident the server now knows about,
+ * and so that "keep"'s original callback ident is destroyed when
+ * "drop" is freed.
+ */
+static void nfs4_swap_callback_idents(struct nfs_client *keep,
+				      struct nfs_client *drop)
+{
+	struct nfs_net *nn = net_generic(keep->cl_net, nfs_net_id);
+	unsigned int save = keep->cl_cb_ident;
+
+	if (keep->cl_cb_ident == drop->cl_cb_ident)
+		return;
+
+	dprintk("%s: keeping callback ident %u and dropping ident %u\n",
+		__func__, keep->cl_cb_ident, drop->cl_cb_ident);
+
+	spin_lock(&nn->nfs_client_lock);
+
+	idr_replace(&nn->cb_ident_idr, keep, drop->cl_cb_ident);
+	keep->cl_cb_ident = drop->cl_cb_ident;
+
+	idr_replace(&nn->cb_ident_idr, drop, save);
+	drop->cl_cb_ident = save;
+
+	spin_unlock(&nn->nfs_client_lock);
+}
+
+/**
+ * nfs40_walk_client_list - Find server that recognizes a client ID
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs40_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs40_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	struct nfs4_setclientid_res clid = {
+		.clientid	= new->cl_clientid,
+		.confirm	= new->cl_confirm,
+	};
+	int status;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos" */
+		if (pos->cl_cons_state < NFS_CS_READY)
+			continue;
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (pos->cl_clientid != new->cl_clientid)
+			continue;
+
+		atomic_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+
+		if (prev)
+			nfs_put_client(prev);
+
+		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
+		if (status == 0) {
+			nfs4_swap_callback_idents(pos, new);
+
+			nfs_put_client(pos);
+			*result = pos;
+			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+				__func__, pos, atomic_read(&pos->cl_count));
+			return 0;
+		}
+		if (status != -NFS4ERR_STALE_CLIENTID) {
+			nfs_put_client(pos);
+			dprintk("NFS: <-- %s status = %d, no result\n",
+				__func__, status);
+			return status;
+		}
+
+		spin_lock(&nn->nfs_client_lock);
+		prev = pos;
+	}
+
+	/*
+	 * No matching nfs_client found.  This should be impossible,
+	 * because the new nfs_client has already been added to
+	 * nfs_client_list by nfs_get_client().
+	 *
+	 * Don't BUG(), since the caller is holding a mutex.
+	 */
+	if (prev)
+		nfs_put_client(prev);
+	spin_unlock(&nn->nfs_client_lock);
+	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
+	return -NFS4ERR_STALE_CLIENTID;
+}
+
+#ifdef CONFIG_NFS_V4_1
+/*
+ * Returns true if the server owners match
+ */
+static bool
+nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b)
+{
+	struct nfs41_server_owner *o1 = a->cl_serverowner;
+	struct nfs41_server_owner *o2 = b->cl_serverowner;
+
+	if (o1->minor_id != o2->minor_id) {
+		dprintk("NFS: --> %s server owner minor IDs do not match\n",
+			__func__);
+		return false;
+	}
+
+	if (o1->major_id_sz != o2->major_id_sz)
+		goto out_major_mismatch;
+	if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
+		goto out_major_mismatch;
+
+	dprintk("NFS: --> %s server owners match\n", __func__);
+	return true;
+
+out_major_mismatch:
+	dprintk("NFS: --> %s server owner major IDs do not match\n",
+		__func__);
+	return false;
+}
+
+/**
+ * nfs41_walk_client_list - Find nfs_client that matches a client/server owner
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs41_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs41_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	int error;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos", especially the client
+		 * ID and serverowner fields.  Wait for CREATE_SESSION
+		 * to finish. */
+		if (pos->cl_cons_state < NFS_CS_READY) {
+			atomic_inc(&pos->cl_count);
+			spin_unlock(&nn->nfs_client_lock);
+
+			if (prev)
+				nfs_put_client(prev);
+			prev = pos;
+
+			error = nfs_wait_client_init_complete(pos);
+			if (error < 0) {
+				nfs_put_client(pos);
+				continue;
+			}
+
+			spin_lock(&nn->nfs_client_lock);
+		}
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (!nfs4_match_clientids(pos, new))
+			continue;
+
+		if (!nfs4_match_serverowners(pos, new))
+			continue;
+
+		spin_unlock(&nn->nfs_client_lock);
+		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+			__func__, pos, atomic_read(&pos->cl_count));
+
+		*result = pos;
+		return 0;
+	}
+
+	/*
+	 * No matching nfs_client found.  This should be impossible,
+	 * because the new nfs_client has already been added to
+	 * nfs_client_list by nfs_get_client().
+	 *
+	 * Don't BUG(), since the caller is holding a mutex.
+	 */
+	spin_unlock(&nn->nfs_client_lock);
+	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
+	return -NFS4ERR_STALE_CLIENTID;
+}
+#endif	/* CONFIG_NFS_V4_1 */
+
 static void nfs4_destroy_server(struct nfs_server *server)
 {
 	nfs_server_return_all_delegations(server);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 80aadcc..e344f13 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5423,6 +5423,8 @@ int nfs4_destroy_clientid(struct nfs_client *clp)
 		goto out;
 	if (clp->cl_exchange_flags == 0)
 		goto out;
+	if (clp->cl_preserve_clid)
+		goto out;
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_destroy_clientid(clp, cred);
 	if (cred)
@@ -6832,6 +6834,7 @@ static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
 	.recover_lock	= nfs4_lock_reclaim,
 	.establish_clid = nfs4_init_clientid,
 	.get_clid_cred	= nfs4_get_setclientid_cred,
+	.detect_trunking = nfs40_discover_server_trunking,
 };
 
 #if defined(CONFIG_NFS_V4_1)
@@ -6843,6 +6846,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 	.establish_clid = nfs41_init_clientid,
 	.get_clid_cred	= nfs4_get_exchange_id_cred,
 	.reclaim_complete = nfs41_proc_reclaim_complete,
+	.detect_trunking = nfs41_discover_server_trunking,
 };
 #endif /* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d6e0d63..2893a87 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -51,6 +51,8 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
+#include <linux/sunrpc/clnt.h>
+
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
@@ -62,7 +64,7 @@
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
-
+static DEFINE_MUTEX(nfs_clid_init_mutex);
 static LIST_HEAD(nfs4_clientid_list);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
@@ -96,6 +98,55 @@ out:
 	return status;
 }
 
+/**
+ * nfs40_discover_server_trunking - Detect server IP address trunking (mv0)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	struct nfs4_setclientid_res clid = {
+		.clientid = clp->cl_clientid,
+		.confirm = clp->cl_confirm,
+	};
+	unsigned short port;
+	int status;
+
+	port = nfs_callback_tcpport;
+	if (clp->cl_addr.ss_family == AF_INET6)
+		port = nfs_callback_tcpport6;
+
+	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
+	if (status != 0)
+		goto out;
+	clp->cl_clientid = clid.clientid;
+	clp->cl_confirm = clid.confirm;
+
+	status = nfs40_walk_client_list(clp, result, cred);
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	case 0:
+		/* Sustain the lease, even if it's empty.  If the clientid4
+		 * goes stale it's of no use for trunking discovery. */
+		nfs4_schedule_state_renewal(*result);
+		break;
+	}
+
+out:
+	return status;
+}
+
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
 {
 	struct rpc_cred *cred = NULL;
@@ -275,6 +326,32 @@ out:
 	return status;
 }
 
+/**
+ * nfs41_discover_server_trunking - Detect server IP address trunking (mv1)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns NFS4_OK, a negative errno, or a negative NFS4ERR status.
+ * If NFS4_OK is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	int status;
+
+	status = nfs4_proc_exchange_id(clp, cred);
+	if (status != NFS4_OK)
+		return status;
+
+	return nfs41_walk_client_list(clp, result, cred);
+}
+
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
@@ -1698,6 +1775,109 @@ static int nfs4_purge_lease(struct nfs_client *clp)
 	return 0;
 }
 
+/**
+ * nfs4_discover_server_trunking - Detect server IP address trunking
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ *
+ * Returns zero or a negative errno.  If zero is returned,
+ * an nfs_client pointer is planted in "result".
+ *
+ * Note: since we are invoked in process context, and
+ * not from inside the state manager, we cannot use
+ * nfs4_handle_reclaim_lease_error().
+ */
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+				  struct nfs_client **result)
+{
+	const struct nfs4_state_recovery_ops *ops =
+				clp->cl_mvops->reboot_recovery_ops;
+	rpc_authflavor_t *flavors, flav, save;
+	struct rpc_clnt *clnt;
+	struct rpc_cred *cred;
+	int i, len, status;
+
+	dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
+
+	len = NFS_MAX_SECFLAVORS;
+	flavors = kcalloc(len, sizeof(*flavors), GFP_KERNEL);
+	if (flavors == NULL) {
+		status = -ENOMEM;
+		goto out;
+	}
+	len = rpcauth_list_flavors(flavors, len);
+	if (len < 0) {
+		status = len;
+		goto out_free;
+	}
+	clnt = clp->cl_rpcclient;
+	save = clnt->cl_auth->au_flavor;
+	i = 0;
+
+	mutex_lock(&nfs_clid_init_mutex);
+	status  = -ENOENT;
+again:
+	cred = ops->get_clid_cred(clp);
+	if (cred == NULL)
+		goto out_unlock;
+
+	status = ops->detect_trunking(clp, result, cred);
+	put_rpccred(cred);
+	switch (status) {
+	case 0:
+		break;
+
+	case -EACCES:
+		if (clp->cl_machine_cred == NULL)
+			break;
+		/* Handle case where the user hasn't set up machine creds */
+		nfs4_clear_machine_cred(clp);
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EAGAIN:
+		ssleep(1);
+		dprintk("NFS: %s after status %d, retrying\n",
+			__func__, status);
+		goto again;
+
+	case -NFS4ERR_CLID_INUSE:
+	case -NFS4ERR_WRONGSEC:
+		status = -EPERM;
+		if (i >= len)
+			break;
+
+		flav = flavors[i++];
+		if (flav == save)
+			flav = flavors[i++];
+		clnt = rpc_clone_client_set_auth(clnt, flav);
+		if (IS_ERR(clnt)) {
+			status = PTR_ERR(clnt);
+			break;
+		}
+		clp->cl_rpcclient = clnt;
+		goto again;
+
+	case -NFS4ERR_MINOR_VERS_MISMATCH:
+		status = -EPROTONOSUPPORT;
+		break;
+
+	case -EKEYEXPIRED:
+		nfs4_warn_keyexpired(clp->cl_hostname);
+	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+				 * in nfs4_exchange_id */
+		status = -EKEYEXPIRED;
+	}
+
+out_unlock:
+	mutex_unlock(&nfs_clid_init_mutex);
+out_free:
+	kfree(flavors);
+out:
+	dprintk("NFS: %s: status = %d\n", __func__, status);
+	return status;
+}
+
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 2e22fc7..a9e76ee 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -82,6 +82,7 @@ struct nfs_client {
 	/* The flags used for obtaining the clientid during EXCHANGE_ID */
 	u32			cl_exchange_flags;
 	struct nfs4_session	*cl_session;	/* shared session */
+	bool			cl_preserve_clid;
 	struct nfs41_server_owner *cl_serverowner;
 	struct nfs41_server_scope *cl_serverscope;
 	struct nfs41_impl_id	*cl_implid;

[PATCH 10/10] NFS: Add nfs4_unique_id boot parameter

[Chuck Lever]

An optional boot parameter is introduced to allow client
administrators to specify a string that the Linux NFS client can
insert into its nfs_client_id4 id string, to make it both more
globally unique, and to ensure that it doesn't change even if the
client's nodename changes.

If this boot parameter is not specified, the client's nodename is
used, as before.

Client installation procedures can create a unique string (typically,
a UUID) which remains unchanged during the lifetime of that client
instance.  This works just like creating a UUID for the label of the
system's root and boot volumes.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---

 Documentation/filesystems/nfs/nfs.txt |   44 +++++++++++++++++++++++++++++++--
 Documentation/kernel-parameters.txt   |    5 ++++
 fs/nfs/nfs4_fs.h                      |    3 ++
 fs/nfs/nfs4proc.c                     |    6 ++++-
 fs/nfs/super.c                        |    5 ++++
 5 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/Documentation/filesystems/nfs/nfs.txt b/Documentation/filesystems/nfs/nfs.txt
index f50f26c..f2571c8 100644
--- a/Documentation/filesystems/nfs/nfs.txt
+++ b/Documentation/filesystems/nfs/nfs.txt
@@ -12,9 +12,47 @@ and work is in progress on adding support for minor version 1 of the NFSv4
 protocol.
 
 The purpose of this document is to provide information on some of the
-upcall interfaces that are used in order to provide the NFS client with
-some of the information that it requires in order to fully comply with
-the NFS spec.
+special features of the NFS client that can be configured by system
+administrators.
+
+
+The nfs4_unique_id parameter
+============================
+
+NFSv4 requires clients to identify themselves to servers with a unique
+string.  File open and lock state shared between one client and one server
+is associated with this identity.  To support robust NFSv4 state recovery
+and transparent state migration, this identity string must not change
+across client reboots.
+
+Without any other intervention, the Linux client uses a string that contains
+the local system's node name.  System administrators, however, often do not
+take care to ensure that node names are fully qualified and do not change
+over the lifetime of a client system.  Node names can have other
+administrative requirements that require particular behavior that does not
+work well as part of an nfs_client_id4 string.
+
+The nfs.nfs4_unique_id boot parameter specifies a unique string that can be
+used instead of a system's node name when an NFS client identifies itself to
+a server.  Thus, if the system's node name is not unique, or it changes, its
+nfs.nfs4_unique_id stays the same, preventing collision with other clients
+or loss of state during NFS reboot recovery or transparent state migration.
+
+The nfs.nfs4_unique_id string is typically a UUID, though it can contain
+anything that is believed to be unique across all NFS clients.  An
+nfs4_unique_id string should be chosen when a client system is installed,
+just as a system's root file system gets a fresh UUID in its label at
+install time.
+
+The string should remain fixed for the lifetime of the client.  It can be
+changed safely if care is taken that the client shuts down cleanly and all
+outstanding NFSv4 state has expired, to prevent loss of NFSv4 state.
+
+This string can be stored in an NFS client's grub.conf, or it can be provided
+via a net boot facility such as PXE.  It may also be specified as an nfs.ko
+module parameter.  Specifying a uniquifier string is not support for NFS
+clients running in containers.
+
 
 The DNS resolver
 ================
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index ad7e2e5..396a1e6 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1719,6 +1719,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			will be autodetected by the client, and it will fall
 			back to using the idmapper.
 			To turn off this behaviour, set the value to '0'.
+	nfs.nfs4_unique_id=
+			[NFS4] Specify an additional fixed unique ident-
+			ification string that NFSv4 clients can insert into
+			their nfs_client_id4 string.  This is typically a
+			UUID that is generated at system install time.
 
 	nfs.send_implementation_id =
 			[NFSv4.1] Send client implementation identification
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index c8e0998..bf54671 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -380,6 +380,9 @@ extern bool nfs4_disable_idmapping;
 extern unsigned short max_session_slots;
 extern unsigned short send_implementation_id;
 
+#define NFS4_CLIENT_ID_UNIQ_LEN		(64)
+extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN];
+
 /* nfs4sysctl.c */
 #ifdef CONFIG_SYSCTL
 int nfs4_register_sysctl(void);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e344f13..f456f5f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4033,9 +4033,13 @@ static unsigned int
 nfs4_init_uniform_client_string(const struct nfs_client *clp,
 				char *buf, size_t len)
 {
+	char *nodename = clp->cl_rpcclient->cl_nodename;
+
+	if (nfs4_client_id_uniquifier[0] != '\0')
+		nodename = nfs4_client_id_uniquifier;
 	return scnprintf(buf, len, "Linux NFSv%u.%u %s",
 				clp->rpc_ops->version, clp->cl_minorversion,
-				clp->cl_rpcclient->cl_nodename);
+				nodename);
 }
 
 /**
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4aabf19..77d95d0 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2660,6 +2660,7 @@ unsigned int nfs_idmap_cache_timeout = 600;
 bool nfs4_disable_idmapping = true;
 unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
 unsigned short send_implementation_id = 1;
+char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = "";
 
 EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport);
 EXPORT_SYMBOL_GPL(nfs_callback_tcpport);
@@ -2667,6 +2668,7 @@ EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout);
 EXPORT_SYMBOL_GPL(nfs4_disable_idmapping);
 EXPORT_SYMBOL_GPL(max_session_slots);
 EXPORT_SYMBOL_GPL(send_implementation_id);
+EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier);
 
 #define NFS_CALLBACK_MAXPORTNR (65535U)
 
@@ -2692,6 +2694,8 @@ static struct kernel_param_ops param_ops_portnr = {
 module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 module_param(nfs_idmap_cache_timeout, int, 0644);
 module_param(nfs4_disable_idmapping, bool, 0644);
+module_param_string(nfs4_unique_id, nfs4_client_id_uniquifier,
+			NFS4_CLIENT_ID_UNIQ_LEN, 0600);
 MODULE_PARM_DESC(nfs4_disable_idmapping,
 		"Turn off NFSv4 idmapping when using 'sec=sys'");
 module_param(max_session_slots, ushort, 0644);
@@ -2700,6 +2704,7 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
 module_param(send_implementation_id, ushort, 0644);
 MODULE_PARM_DESC(send_implementation_id,
 		"Send implementation ID with NFSv4.1 exchange_id");
+MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
 MODULE_ALIAS("nfs4");
 
 #endif /* CONFIG_NFS_V4 */