* [PATCH 01/21] SUNRPC: Modify synopsis of rpc_client_register()
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 02/21] SUNRPC: Add a helper to switch the transport of an rpc_clnt Chuck Lever
` (19 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
The rpc_client_register() helper was added in commit e73f4cc0,
"SUNRPC: split client creation routine into setup and registration,"
Mon Jun 24 11:52:52 2013. In a subsequent patch, I'd like to invoke
rpc_client_register() from a context where a struct rpc_create_args
is not available.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
net/sunrpc/clnt.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7747960..1aa361b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -272,12 +272,13 @@ static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen);
}
-static int rpc_client_register(const struct rpc_create_args *args,
- struct rpc_clnt *clnt)
+static int rpc_client_register(struct rpc_clnt *clnt,
+ rpc_authflavor_t pseudoflavor,
+ const char *client_name)
{
struct rpc_auth_create_args auth_args = {
- .pseudoflavor = args->authflavor,
- .target_name = args->client_name,
+ .pseudoflavor = pseudoflavor,
+ .target_name = client_name,
};
struct rpc_auth *auth;
struct net *net = rpc_net_ns(clnt);
@@ -298,7 +299,7 @@ static int rpc_client_register(const struct rpc_create_args *args,
auth = rpcauth_create(&auth_args, clnt);
if (IS_ERR(auth)) {
dprintk("RPC: Couldn't create auth handle (flavor %u)\n",
- args->authflavor);
+ pseudoflavor);
err = PTR_ERR(auth);
goto err_auth;
}
@@ -398,7 +399,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
/* save the nodename */
rpc_clnt_set_nodename(clnt, utsname()->nodename);
- err = rpc_client_register(args, clnt);
+ err = rpc_client_register(clnt, args->authflavor, args->client_name);
if (err)
goto out_no_path;
if (parent)
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 02/21] SUNRPC: Add a helper to switch the transport of an rpc_clnt
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
2013-10-17 18:12 ` [PATCH 01/21] SUNRPC: Modify synopsis of rpc_client_register() Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 03/21] NFS: Add nfs4_update_server Chuck Lever
` (18 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Add an RPC client API to redirect an rpc_clnt's transport from a
source server to a destination server during a migration event.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
[ cel: forward ported to 3.12 ]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
include/linux/sunrpc/clnt.h | 4 ++
net/sunrpc/clnt.c | 107 ++++++++++++++++++++++++++++++++++++++++---
2 files changed, 104 insertions(+), 7 deletions(-)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6740801..e90c543 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -134,6 +134,10 @@ 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);
+int rpc_switch_client_transport(struct rpc_clnt *,
+ struct xprt_create *,
+ const struct rpc_timeout *);
+
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 1aa361b..d2c8091 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -25,6 +25,7 @@
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include <linux/utsname.h>
#include <linux/workqueue.h>
#include <linux/in.h>
@@ -264,6 +265,25 @@ void rpc_clients_notifier_unregister(void)
return rpc_pipefs_notifier_unregister(&rpc_clients_block);
}
+static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ const struct rpc_timeout *timeout)
+{
+ struct rpc_xprt *old;
+
+ spin_lock(&clnt->cl_lock);
+ old = clnt->cl_xprt;
+
+ if (!xprt_bound(xprt))
+ clnt->cl_autobind = 1;
+
+ clnt->cl_timeout = timeout;
+ rcu_assign_pointer(clnt->cl_xprt, xprt);
+ spin_unlock(&clnt->cl_lock);
+
+ return old;
+}
+
static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
{
clnt->cl_nodelen = strlen(nodename);
@@ -338,7 +358,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
{
const struct rpc_program *program = args->program;
const struct rpc_version *version;
- struct rpc_clnt *clnt = NULL;
+ struct rpc_clnt *clnt = NULL;
+ const struct rpc_timeout *timeout;
int err;
/* sanity check the name before trying to print it */
@@ -366,7 +387,6 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
if (err)
goto out_no_clid;
- rcu_assign_pointer(clnt->cl_xprt, xprt);
clnt->cl_procinfo = version->procs;
clnt->cl_maxproc = version->nrprocs;
clnt->cl_prog = args->prognumber ? : program->number;
@@ -381,16 +401,15 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
INIT_LIST_HEAD(&clnt->cl_tasks);
spin_lock_init(&clnt->cl_lock);
- if (!xprt_bound(xprt))
- clnt->cl_autobind = 1;
-
- clnt->cl_timeout = xprt->timeout;
+ timeout = xprt->timeout;
if (args->timeout != NULL) {
memcpy(&clnt->cl_timeout_default, args->timeout,
sizeof(clnt->cl_timeout_default));
- clnt->cl_timeout = &clnt->cl_timeout_default;
+ timeout = &clnt->cl_timeout_default;
}
+ rpc_clnt_set_transport(clnt, xprt, timeout);
+
clnt->cl_rtt = &clnt->cl_rtt_default;
rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval);
@@ -601,6 +620,80 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
}
EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth);
+/**
+ * rpc_switch_client_transport: switch the RPC transport on the fly
+ * @clnt: pointer to a struct rpc_clnt
+ * @args: pointer to the new transport arguments
+ * @timeout: pointer to the new timeout parameters
+ *
+ * This function allows the caller to switch the RPC transport for the
+ * rpc_clnt structure 'clnt' to allow it to connect to a mirrored NFS
+ * server, for instance. It assumes that the caller has ensured that
+ * there are no active RPC tasks by using some form of locking.
+ *
+ * Returns zero if "clnt" is now using the new xprt. Otherwise a
+ * negative errno is returned, and "clnt" continues to use the old
+ * xprt.
+ */
+int rpc_switch_client_transport(struct rpc_clnt *clnt,
+ struct xprt_create *args,
+ const struct rpc_timeout *timeout)
+{
+ const struct rpc_timeout *old_timeo;
+ rpc_authflavor_t pseudoflavor;
+ struct rpc_xprt *xprt, *old;
+ struct rpc_clnt *parent;
+ int err;
+
+ xprt = xprt_create_transport(args);
+ if (IS_ERR(xprt)) {
+ dprintk("RPC: failed to create new xprt for clnt %p\n",
+ clnt);
+ return PTR_ERR(xprt);
+ }
+
+ pseudoflavor = clnt->cl_auth->au_flavor;
+
+ old_timeo = clnt->cl_timeout;
+ old = rpc_clnt_set_transport(clnt, xprt, timeout);
+
+ rpc_unregister_client(clnt);
+ __rpc_clnt_remove_pipedir(clnt);
+
+ /*
+ * A new transport was created. "clnt" therefore
+ * becomes the root of a new cl_parent tree. clnt's
+ * children, if it has any, still point to the old xprt.
+ */
+ parent = clnt->cl_parent;
+ clnt->cl_parent = clnt;
+
+ /*
+ * The old rpc_auth cache cannot be re-used. GSS
+ * contexts in particular are between a single
+ * client and server.
+ */
+ err = rpc_client_register(clnt, pseudoflavor, NULL);
+ if (err)
+ goto out_revert;
+
+ synchronize_rcu();
+ if (parent != clnt)
+ rpc_release_client(parent);
+ xprt_put(old);
+ dprintk("RPC: replaced xprt for clnt %p\n", clnt);
+ return 0;
+
+out_revert:
+ rpc_clnt_set_transport(clnt, old, old_timeo);
+ clnt->cl_parent = parent;
+ rpc_client_register(clnt, pseudoflavor, NULL);
+ xprt_put(xprt);
+ dprintk("RPC: failed to switch xprt for clnt %p\n", clnt);
+ return err;
+}
+EXPORT_SYMBOL_GPL(rpc_switch_client_transport);
+
/*
* Kill all tasks for the given client.
* XXX: kill their descendants as well?
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 03/21] NFS: Add nfs4_update_server
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
2013-10-17 18:12 ` [PATCH 01/21] SUNRPC: Modify synopsis of rpc_client_register() Chuck Lever
2013-10-17 18:12 ` [PATCH 02/21] SUNRPC: Add a helper to switch the transport of an rpc_clnt Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 04/21] NFS: Add functions to swap transports during migration recovery Chuck Lever
` (17 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
New function nfs4_update_server() moves an nfs_server to a different
nfs_client. This is done as part of migration recovery.
Though it may be appealing to think of them as the same thing,
migration recovery is not the same as following a referral.
For a referral, the client has not descended into the file system
yet: it has no nfs_server, no super block, no inodes or open state.
It is enough to simply instantiate the nfs_server and super block,
and perform a referral mount.
For a migration, however, we have all of those things already, and
they have to be moved to a different nfs_client. No local namespace
changes are needed here.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/client.c | 3 +
fs/nfs/internal.h | 3 +
fs/nfs/nfs4client.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 113 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2dceee4..f2e870c 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -943,7 +943,7 @@ void nfs_server_insert_lists(struct nfs_server *server)
}
EXPORT_SYMBOL_GPL(nfs_server_insert_lists);
-static void nfs_server_remove_lists(struct nfs_server *server)
+void nfs_server_remove_lists(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
struct nfs_net *nn;
@@ -960,6 +960,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
synchronize_rcu();
}
+EXPORT_SYMBOL_GPL(nfs_server_remove_lists);
/*
* Allocate and initialise a server record
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 38da8c2..e5a6bd1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -154,6 +154,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
rpc_authflavor_t);
int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
void nfs_server_insert_lists(struct nfs_server *);
+void nfs_server_remove_lists(struct nfs_server *);
void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
rpc_authflavor_t);
@@ -174,6 +175,8 @@ extern struct nfs_server *nfs4_create_server(
struct nfs_subversion *);
extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
struct nfs_fh *);
+extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
+ struct sockaddr *sap, size_t salen);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index a860ab5..299cf6b 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1091,3 +1091,111 @@ error:
dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
return ERR_PTR(error);
}
+
+/*
+ * Grab the destination's particulars, including lease expiry time.
+ *
+ * Returns zero if probe succeeded and retrieved FSID matches the FSID
+ * we have cached.
+ */
+static int nfs_probe_destination(struct nfs_server *server)
+{
+ struct inode *inode = server->super->s_root->d_inode;
+ struct nfs_fattr *fattr;
+ int error;
+
+ fattr = nfs_alloc_fattr();
+ if (fattr == NULL)
+ return -ENOMEM;
+
+ /* Sanity: the probe won't work if the destination server
+ * does not recognize the migrated FH. */
+ error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr);
+
+ nfs_free_fattr(fattr);
+ return error;
+}
+
+/**
+ * nfs4_update_server - Move an nfs_server to a different nfs_client
+ *
+ * @server: represents FSID to be moved
+ * @hostname: new end-point's hostname
+ * @sap: new end-point's socket address
+ * @salen: size of "sap"
+ *
+ * The nfs_server must be quiescent before this function is invoked.
+ * Either its session is drained (NFSv4.1+), or its transport is
+ * plugged and drained (NFSv4.0).
+ *
+ * Returns zero on success, or a negative errno value.
+ */
+int nfs4_update_server(struct nfs_server *server, const char *hostname,
+ struct sockaddr *sap, size_t salen)
+{
+ struct nfs_client *clp = server->nfs_client;
+ struct rpc_clnt *clnt = server->client;
+ struct xprt_create xargs = {
+ .ident = clp->cl_proto,
+ .net = &init_net,
+ .dstaddr = sap,
+ .addrlen = salen,
+ .servername = hostname,
+ };
+ char buf[INET6_ADDRSTRLEN + 1];
+ struct sockaddr_storage address;
+ struct sockaddr *localaddr = (struct sockaddr *)&address;
+ int error;
+
+ dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__,
+ (unsigned long long)server->fsid.major,
+ (unsigned long long)server->fsid.minor,
+ hostname);
+
+ error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout);
+ if (error != 0) {
+ dprintk("<-- %s(): rpc_switch_client_transport returned %d\n",
+ __func__, error);
+ goto out;
+ }
+
+ error = rpc_localaddr(clnt, localaddr, sizeof(address));
+ if (error != 0) {
+ dprintk("<-- %s(): rpc_localaddr returned %d\n",
+ __func__, error);
+ goto out;
+ }
+
+ error = -EAFNOSUPPORT;
+ if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) {
+ dprintk("<-- %s(): rpc_ntop returned %d\n",
+ __func__, error);
+ goto out;
+ }
+
+ nfs_server_remove_lists(server);
+ error = nfs4_set_client(server, hostname, sap, salen, buf,
+ clp->cl_rpcclient->cl_auth->au_flavor,
+ clp->cl_proto, clnt->cl_timeout,
+ clp->cl_minorversion, clp->cl_net);
+ nfs_put_client(clp);
+ if (error != 0) {
+ nfs_server_insert_lists(server);
+ dprintk("<-- %s(): nfs4_set_client returned %d\n",
+ __func__, error);
+ goto out;
+ }
+
+ if (server->nfs_client->cl_hostname == NULL)
+ server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL);
+ nfs_server_insert_lists(server);
+
+ error = nfs_probe_destination(server);
+ if (error < 0)
+ goto out;
+
+ dprintk("<-- %s() succeeded\n", __func__);
+
+out:
+ return error;
+}
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 04/21] NFS: Add functions to swap transports during migration recovery
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (2 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 03/21] NFS: Add nfs4_update_server Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 05/21] NFS: Introduce a vector of migration recovery ops Chuck Lever
` (16 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
Introduce functions that can walk through an array of returned
fs_locations information and connect a transport to one of the
destination servers listed therein.
Note that NFS minor version 1 introduces "fs_locations_info" which
extends the locations array sorting criteria available to clients.
This is not supported yet.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 2 +
fs/nfs/nfs4namespace.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 103 insertions(+)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 28842ab..fcae728 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -217,6 +217,8 @@ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *,
struct nfs_fh *, struct nfs_fattr *);
+int nfs4_replace_transport(struct nfs_server *server,
+ const struct nfs4_fs_locations *locations);
/* nfs4proc.c */
extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 2288cd3..ebd8b06 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -400,3 +400,104 @@ out:
rpc_shutdown_client(client);
return mnt;
}
+
+/*
+ * Try one location from the fs_locations array.
+ *
+ * Returns zero on success, or a negative errno value.
+ */
+static int nfs4_try_replacing_one_location(struct nfs_server *server,
+ char *page, char *page2,
+ const struct nfs4_fs_location *location)
+{
+ const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct sockaddr *sap;
+ unsigned int s;
+ size_t salen;
+ int error;
+
+ sap = kmalloc(addr_bufsize, GFP_KERNEL);
+ if (sap == NULL)
+ return -ENOMEM;
+
+ error = -ENOENT;
+ for (s = 0; s < location->nservers; s++) {
+ const struct nfs4_string *buf = &location->servers[s];
+ char *hostname;
+
+ if (buf->len <= 0 || buf->len > PAGE_SIZE)
+ continue;
+
+ if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len) != NULL)
+ continue;
+
+ salen = nfs_parse_server_name(buf->data, buf->len,
+ sap, addr_bufsize, server);
+ if (salen == 0)
+ continue;
+ rpc_set_port(sap, NFS_PORT);
+
+ error = -ENOMEM;
+ hostname = kstrndup(buf->data, buf->len, GFP_KERNEL);
+ if (hostname == NULL)
+ break;
+
+ error = nfs4_update_server(server, hostname, sap, salen);
+ kfree(hostname);
+ if (error == 0)
+ break;
+ }
+
+ kfree(sap);
+ return error;
+}
+
+/**
+ * nfs4_replace_transport - set up transport to destination server
+ *
+ * @server: export being migrated
+ * @locations: fs_locations array
+ *
+ * Returns zero on success, or a negative errno value.
+ *
+ * The client tries all the entries in the "locations" array, in the
+ * order returned by the server, until one works or the end of the
+ * array is reached.
+ */
+int nfs4_replace_transport(struct nfs_server *server,
+ const struct nfs4_fs_locations *locations)
+{
+ char *page = NULL, *page2 = NULL;
+ int loc, error;
+
+ error = -ENOENT;
+ if (locations == NULL || locations->nlocations <= 0)
+ goto out;
+
+ error = -ENOMEM;
+ page = (char *) __get_free_page(GFP_USER);
+ if (!page)
+ goto out;
+ page2 = (char *) __get_free_page(GFP_USER);
+ if (!page2)
+ goto out;
+
+ for (loc = 0; loc < locations->nlocations; loc++) {
+ const struct nfs4_fs_location *location =
+ &locations->locations[loc];
+
+ if (location == NULL || location->nservers <= 0 ||
+ location->rootpath.ncomponents == 0)
+ continue;
+
+ error = nfs4_try_replacing_one_location(server, page,
+ page2, location);
+ if (error == 0)
+ break;
+ }
+
+out:
+ free_page((unsigned long)page);
+ free_page((unsigned long)page2);
+ return error;
+}
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 05/21] NFS: Introduce a vector of migration recovery ops
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (3 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 04/21] NFS: Add functions to swap transports during migration recovery Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 06/21] NFS: Export _nfs_display_fhandle() Chuck Lever
` (15 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
The differences between minor version 0 and minor version 1
migration will be abstracted by the addition of a set of migration
recovery ops.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 4 ++++
fs/nfs/nfs4proc.c | 10 ++++++++++
2 files changed, 14 insertions(+)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index fcae728..4f48000 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -50,6 +50,7 @@ struct nfs4_minor_version_ops {
const struct nfs4_state_recovery_ops *reboot_recovery_ops;
const struct nfs4_state_recovery_ops *nograce_recovery_ops;
const struct nfs4_state_maintenance_ops *state_renewal_ops;
+ const struct nfs4_mig_recovery_ops *mig_recovery_ops;
};
#define NFS_SEQID_CONFIRMED 1
@@ -203,6 +204,9 @@ struct nfs4_state_maintenance_ops {
int (*renew_lease)(struct nfs_client *, struct rpc_cred *);
};
+struct nfs4_mig_recovery_ops {
+};
+
extern const struct dentry_operations nfs4_dentry_operations;
/* dir.c */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d53d678..e4bd317 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7887,6 +7887,14 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
};
#endif
+static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
+};
+
+#if defined(CONFIG_NFS_V4_1)
+static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = {
+};
+#endif /* CONFIG_NFS_V4_1 */
+
static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
.minor_version = 0,
.init_caps = NFS_CAP_READDIRPLUS
@@ -7902,6 +7910,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
.state_renewal_ops = &nfs40_state_renewal_ops,
+ .mig_recovery_ops = &nfs40_mig_recovery_ops,
};
#if defined(CONFIG_NFS_V4_1)
@@ -7922,6 +7931,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
.state_renewal_ops = &nfs41_state_renewal_ops,
+ .mig_recovery_ops = &nfs41_mig_recovery_ops,
};
#endif
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 06/21] NFS: Export _nfs_display_fhandle()
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (4 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 05/21] NFS: Introduce a vector of migration recovery ops Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 07/21] NFS: Add method to retrieve fs_locations during migration recovery Chuck Lever
` (14 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
Allow code in nfsv4.ko to use _nfs_display_fhandle().
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/inode.c | 2 ++
fs/nfs/nfs4client.c | 2 +-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index eda8879..4bc7538 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1209,6 +1209,7 @@ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
* not on the result */
return nfs_fhandle_hash(fh);
}
+EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash);
/*
* _nfs_display_fhandle - display an NFS file handle on the console
@@ -1253,6 +1254,7 @@ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
}
}
}
+EXPORT_SYMBOL_GPL(_nfs_display_fhandle);
#endif
/**
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 299cf6b..b19c94f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -924,7 +924,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
dprintk("Server FSID: %llx:%llx\n",
(unsigned long long) server->fsid.major,
(unsigned long long) server->fsid.minor);
- dprintk("Mount FH: %d\n", mntfh->size);
+ nfs_display_fhandle(mntfh, "Pseudo-fs root FH");
nfs4_session_set_rwsize(server);
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 07/21] NFS: Add method to retrieve fs_locations during migration recovery
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (5 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 06/21] NFS: Export _nfs_display_fhandle() Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:12 ` [PATCH 08/21] NFS: Add a super_block backpointer to the nfs_server struct Chuck Lever
` (13 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
The nfs4_proc_fs_locations() function is invoked during referral
processing to perform a GETATTR(fs_locations) on an object's parent
directory in order to discover the target of the referral. It
performs a LOOKUP in the compound, so the client needs to know the
parent's file handle a priori.
Unfortunately this function is not adequate for handling migration
recovery. We need to probe fs_locations information on an FSID, but
there's no parent directory available for many operations that
can return NFS4ERR_MOVED.
Another subtlety: recovering from NFS4ERR_LEASE_MOVED is a process
of walking over a list of known FSIDs that reside on the server, and
probing whether they have migrated. Once the server has detected
that the client has probed all migrated file systems, it stops
returning NFS4ERR_LEASE_MOVED.
A minor version zero server needs to know what client ID is
requesting fs_locations information so it can clear the flag that
forces it to continue returning NFS4ERR_LEASE_MOVED. This flag is
set per client ID and per FSID. However, the client ID is not an
argument of either the PUTFH or GETATTR operations. Later minor
versions have client ID information embedded in the compound's
SEQUENCE operation.
Therefore, by convention, minor version zero clients send a RENEW
operation in the same compound as the GETATTR(fs_locations), since
RENEW's one argument is a clientid4. This allows a minor version
zero server to identify correctly the client that is probing for a
migration.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 4 +
fs/nfs/nfs4proc.c | 153 +++++++++++++++++++++++++++++++++++++++++++++++
fs/nfs/nfs4xdr.c | 46 +++++++++++---
include/linux/nfs_xdr.h | 4 +
4 files changed, 196 insertions(+), 11 deletions(-)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4f48000..e59d3b4 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -205,6 +205,8 @@ struct nfs4_state_maintenance_ops {
};
struct nfs4_mig_recovery_ops {
+ int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
+ struct page *, struct rpc_cred *);
};
extern const struct dentry_operations nfs4_dentry_operations;
@@ -237,6 +239,8 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
struct nfs4_fs_locations *, struct page *);
+extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
+ struct page *page, struct rpc_cred *);
extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *,
struct nfs_fh *, struct nfs_fattr *);
extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e4bd317..f507e54 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5990,6 +5990,157 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
return err;
}
+/*
+ * This operation also signals the server that this client is
+ * performing migration recovery. The server can stop returning
+ * NFS4ERR_LEASE_MOVED to this client. A RENEW operation is
+ * appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_get_locations(struct inode *inode,
+ struct nfs4_fs_locations *locations,
+ struct page *page, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct rpc_clnt *clnt = server->client;
+ u32 bitmask[2] = {
+ [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
+ };
+ struct nfs4_fs_locations_arg args = {
+ .clientid = server->nfs_client->cl_clientid,
+ .fh = NFS_FH(inode),
+ .page = page,
+ .bitmask = bitmask,
+ .migration = 1, /* skip LOOKUP */
+ .renew = 1, /* append RENEW */
+ };
+ struct nfs4_fs_locations_res res = {
+ .fs_locations = locations,
+ .migration = 1,
+ .renew = 1,
+ };
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ .rpc_cred = cred,
+ };
+ unsigned long now = jiffies;
+ int status;
+
+ nfs_fattr_init(&locations->fattr);
+ locations->server = server;
+ locations->nlocations = 0;
+
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+ nfs4_set_sequence_privileged(&args.seq_args);
+ status = nfs4_call_sync_sequence(clnt, server, &msg,
+ &args.seq_args, &res.seq_res);
+ if (status)
+ return status;
+
+ renew_lease(server, now);
+ return 0;
+}
+
+#ifdef CONFIG_NFS_V4_1
+
+/*
+ * This operation also signals the server that this client is
+ * performing migration recovery. The server can stop asserting
+ * SEQ4_STATUS_LEASE_MOVED for this client. The client ID
+ * performing this operation is identified in the SEQUENCE
+ * operation in this compound.
+ *
+ * When the client supports GETATTR(fs_locations_info), it can
+ * be plumbed in here.
+ */
+static int _nfs41_proc_get_locations(struct inode *inode,
+ struct nfs4_fs_locations *locations,
+ struct page *page, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct rpc_clnt *clnt = server->client;
+ u32 bitmask[2] = {
+ [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
+ };
+ struct nfs4_fs_locations_arg args = {
+ .fh = NFS_FH(inode),
+ .page = page,
+ .bitmask = bitmask,
+ .migration = 1, /* skip LOOKUP */
+ };
+ struct nfs4_fs_locations_res res = {
+ .fs_locations = locations,
+ .migration = 1,
+ };
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ .rpc_cred = cred,
+ };
+ int status;
+
+ nfs_fattr_init(&locations->fattr);
+ locations->server = server;
+ locations->nlocations = 0;
+
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+ nfs4_set_sequence_privileged(&args.seq_args);
+ status = nfs4_call_sync_sequence(clnt, server, &msg,
+ &args.seq_args, &res.seq_res);
+ if (status == NFS4_OK &&
+ res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED)
+ status = -NFS4ERR_LEASE_MOVED;
+ return status;
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+/**
+ * nfs4_proc_get_locations - discover locations for a migrated FSID
+ * @inode: inode on FSID that is migrating
+ * @locations: result of query
+ * @page: buffer
+ * @cred: credential to use for this operation
+ *
+ * Returns NFS4_OK on success, a negative NFS4ERR status code if the
+ * operation failed, or a negative errno if a local error occurred.
+ *
+ * On success, "locations" is filled in, but if the server has
+ * no locations information, NFS_ATTR_FATTR_V4_LOCATIONS is not
+ * asserted.
+ *
+ * -NFS4ERR_LEASE_MOVED is returned if the server still has leases
+ * from this client that require migration recovery.
+ */
+int nfs4_proc_get_locations(struct inode *inode,
+ struct nfs4_fs_locations *locations,
+ struct page *page, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct nfs_client *clp = server->nfs_client;
+ const struct nfs4_mig_recovery_ops *ops =
+ clp->cl_mvops->mig_recovery_ops;
+ struct nfs4_exception exception = { };
+ int status;
+
+ dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
+ (unsigned long long)server->fsid.major,
+ (unsigned long long)server->fsid.minor,
+ clp->cl_hostname);
+ nfs_display_fhandle(NFS_FH(inode), __func__);
+
+ do {
+ status = ops->get_locations(inode, locations, page, cred);
+ if (status != -NFS4ERR_DELAY)
+ break;
+ nfs4_handle_exception(server, status, &exception);
+ } while (exception.retry);
+ return status;
+}
+
/**
* If 'use_integrity' is true and the state managment nfs_client
* cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient
@@ -7888,10 +8039,12 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
#endif
static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
+ .get_locations = _nfs40_proc_get_locations,
};
#if defined(CONFIG_NFS_V4_1)
static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = {
+ .get_locations = _nfs41_proc_get_locations,
};
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 79210d2..1854b04 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -736,13 +736,15 @@ static int nfs4_stat_to_errno(int);
encode_sequence_maxsz + \
encode_putfh_maxsz + \
encode_lookup_maxsz + \
- encode_fs_locations_maxsz)
+ encode_fs_locations_maxsz + \
+ encode_renew_maxsz)
#define NFS4_dec_fs_locations_sz \
(compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_lookup_maxsz + \
- decode_fs_locations_maxsz)
+ decode_fs_locations_maxsz + \
+ decode_renew_maxsz)
#define NFS4_enc_secinfo_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -2687,11 +2689,20 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
- encode_putfh(xdr, args->dir_fh, &hdr);
- encode_lookup(xdr, args->name, &hdr);
- replen = hdr.replen; /* get the attribute into args->page */
- encode_fs_locations(xdr, args->bitmask, &hdr);
+ if (args->migration) {
+ encode_putfh(xdr, args->fh, &hdr);
+ replen = hdr.replen;
+ encode_fs_locations(xdr, args->bitmask, &hdr);
+ if (args->renew)
+ encode_renew(xdr, args->clientid, &hdr);
+ } else {
+ encode_putfh(xdr, args->dir_fh, &hdr);
+ encode_lookup(xdr, args->name, &hdr);
+ replen = hdr.replen;
+ encode_fs_locations(xdr, args->bitmask, &hdr);
+ }
+ /* Set up reply kvec to capture returned fs_locations array. */
xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page,
0, PAGE_SIZE);
encode_nops(&hdr);
@@ -6824,13 +6835,26 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
status = decode_putfh(xdr);
if (status)
goto out;
- status = decode_lookup(xdr);
- if (status)
- goto out;
- xdr_enter_page(xdr, PAGE_SIZE);
- status = decode_getfattr_generic(xdr, &res->fs_locations->fattr,
+ if (res->migration) {
+ xdr_enter_page(xdr, PAGE_SIZE);
+ status = decode_getfattr_generic(xdr,
+ &res->fs_locations->fattr,
NULL, res->fs_locations,
NULL, res->fs_locations->server);
+ if (status)
+ goto out;
+ if (res->renew)
+ status = decode_renew(xdr);
+ } else {
+ status = decode_lookup(xdr);
+ if (status)
+ goto out;
+ xdr_enter_page(xdr, PAGE_SIZE);
+ status = decode_getfattr_generic(xdr,
+ &res->fs_locations->fattr,
+ NULL, res->fs_locations,
+ NULL, res->fs_locations->server);
+ }
out:
return status;
}
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 49f52c8..405dfad 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1053,14 +1053,18 @@ struct nfs4_fs_locations {
struct nfs4_fs_locations_arg {
struct nfs4_sequence_args seq_args;
const struct nfs_fh *dir_fh;
+ const struct nfs_fh *fh;
const struct qstr *name;
struct page *page;
const u32 *bitmask;
+ clientid4 clientid;
+ unsigned char migration:1, renew:1;
};
struct nfs4_fs_locations_res {
struct nfs4_sequence_res seq_res;
struct nfs4_fs_locations *fs_locations;
+ unsigned char migration:1, renew:1;
};
struct nfs4_secinfo4 {
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 08/21] NFS: Add a super_block backpointer to the nfs_server struct
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (6 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 07/21] NFS: Add method to retrieve fs_locations during migration recovery Chuck Lever
@ 2013-10-17 18:12 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 09/21] NFS: Add basic migration support to state manager thread Chuck Lever
` (12 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:12 UTC (permalink / raw)
To: linux-nfs
NFS_SB() returns the pointer to an nfs_server struct, given a
pointer to a super_block. But we have no way to go back the other
way.
Add a super_block backpointer field so that, given an nfs_server
struct, it is easy to get to the filesystem's root dentry.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/super.c | 1 +
include/linux/nfs_fs_sb.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index a03b9c6..5edc613 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2530,6 +2530,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
mntroot = ERR_PTR(error);
goto error_splat_bdi;
}
+ server->super = s;
}
if (!s->s_root) {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b8cedce..a1c80a2 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -147,6 +147,7 @@ struct nfs_server {
__u64 maxfilesize; /* maximum file size */
struct timespec time_delta; /* smallest time granularity */
unsigned long mount_time; /* when this fs was mounted */
+ struct super_block *super; /* VFS super block */
dev_t s_dev; /* superblock dev numbers */
#ifdef CONFIG_NFS_FSCACHE
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 09/21] NFS: Add basic migration support to state manager thread
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (7 preceding siblings ...)
2013-10-17 18:12 ` [PATCH 08/21] NFS: Add a super_block backpointer to the nfs_server struct Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 10/21] NFS: Re-use exit code in nfs4_async_handle_error() Chuck Lever
` (11 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
Migration recovery and state recovery must be serialized, so handle
both in the state manager thread.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 2 +
fs/nfs/nfs4client.c | 1
fs/nfs/nfs4state.c | 161 ++++++++++++++++++++++++++++++++++++++++++++-
include/linux/nfs_fs_sb.h | 7 ++
4 files changed, 168 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e59d3b4..94e783f 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -29,6 +29,7 @@ enum nfs4_client_state {
NFS4CLNT_SERVER_SCOPE_MISMATCH,
NFS4CLNT_PURGE_STATE,
NFS4CLNT_BIND_CONN_TO_SESSION,
+ NFS4CLNT_MOVED,
};
#define NFS4_RENEW_TIMEOUT 0x01
@@ -421,6 +422,7 @@ extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
extern void nfs4_schedule_state_manager(struct nfs_client *);
extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
+extern int nfs4_schedule_migration_recovery(const struct nfs_server *);
extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
extern void nfs41_handle_server_scope(struct nfs_client *,
struct nfs41_server_scope **);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index b19c94f..b510f4f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -197,6 +197,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
clp->cl_minorversion = cl_init->minorversion;
clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
+ clp->cl_mig_gen = 1;
return clp;
error:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index cc14cbb..b66163f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -239,8 +239,6 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
}
}
-#if defined(CONFIG_NFS_V4_1)
-
static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
{
set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
@@ -270,6 +268,8 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
return nfs4_drain_slot_tbl(&ses->fc_slot_table);
}
+#if defined(CONFIG_NFS_V4_1)
+
static int nfs41_setup_state_renewal(struct nfs_client *clp)
{
int status;
@@ -1197,6 +1197,42 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
}
EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
+/**
+ * nfs4_schedule_migration_recovery - trigger migration recovery
+ *
+ * @server: FSID that is migrating
+ *
+ * Returns zero if recovery has started, otherwise a negative NFS4ERR
+ * value is returned.
+ */
+int nfs4_schedule_migration_recovery(const struct nfs_server *server)
+{
+ struct nfs_client *clp = server->nfs_client;
+
+ if (server->fh_expire_type != NFS4_FH_PERSISTENT) {
+ pr_err("NFS: volatile file handles not supported (server %s)\n",
+ clp->cl_hostname);
+ return -NFS4ERR_IO;
+ }
+
+ if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+ return -NFS4ERR_IO;
+
+ dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n",
+ __func__,
+ (unsigned long long)server->fsid.major,
+ (unsigned long long)server->fsid.minor,
+ clp->cl_hostname);
+
+ set_bit(NFS_MIG_IN_TRANSITION,
+ &((struct nfs_server *)server)->mig_status);
+ set_bit(NFS4CLNT_MOVED, &clp->cl_state);
+
+ nfs4_schedule_state_manager(clp);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery);
+
int nfs4_wait_clnt_recover(struct nfs_client *clp)
{
int res;
@@ -1829,6 +1865,119 @@ static int nfs4_purge_lease(struct nfs_client *clp)
return 0;
}
+/*
+ * Try remote migration of one FSID from a source server to a
+ * destination server. The source server provides a list of
+ * potential destinations.
+ *
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred)
+{
+ struct nfs_client *clp = server->nfs_client;
+ struct nfs4_fs_locations *locations = NULL;
+ struct inode *inode;
+ struct page *page;
+ int status, result;
+
+ dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__,
+ (unsigned long long)server->fsid.major,
+ (unsigned long long)server->fsid.minor,
+ clp->cl_hostname);
+
+ result = 0;
+ page = alloc_page(GFP_KERNEL);
+ locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
+ if (page == NULL || locations == NULL) {
+ dprintk("<-- %s: no memory\n", __func__);
+ goto out;
+ }
+
+ inode = server->super->s_root->d_inode;
+ result = nfs4_proc_get_locations(inode, locations, page, cred);
+ if (result) {
+ dprintk("<-- %s: failed to retrieve fs_locations: %d\n",
+ __func__, result);
+ goto out;
+ }
+
+ result = -NFS4ERR_NXIO;
+ if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+ dprintk("<-- %s: No fs_locations data, migration skipped\n",
+ __func__);
+ goto out;
+ }
+
+ nfs4_begin_drain_session(clp);
+
+ status = nfs4_replace_transport(server, locations);
+ if (status != 0) {
+ dprintk("<-- %s: failed to replace transport: %d\n",
+ __func__, status);
+ goto out;
+ }
+
+ result = 0;
+ dprintk("<-- %s: migration succeeded\n", __func__);
+
+out:
+ if (page != NULL)
+ __free_page(page);
+ kfree(locations);
+ if (result) {
+ pr_err("NFS: migration recovery failed (server %s)\n",
+ clp->cl_hostname);
+ set_bit(NFS_MIG_FAILED, &server->mig_status);
+ }
+ return result;
+}
+
+/*
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_handle_migration(struct nfs_client *clp)
+{
+ const struct nfs4_state_maintenance_ops *ops =
+ clp->cl_mvops->state_renewal_ops;
+ struct nfs_server *server;
+ struct rpc_cred *cred;
+
+ dprintk("%s: migration reported on \"%s\"\n", __func__,
+ clp->cl_hostname);
+
+ spin_lock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred_locked(clp);
+ spin_unlock(&clp->cl_lock);
+ if (cred == NULL)
+ return -NFS4ERR_NOENT;
+
+ clp->cl_mig_gen++;
+restart:
+ rcu_read_lock();
+ list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+ int status;
+
+ if (server->mig_gen == clp->cl_mig_gen)
+ continue;
+ server->mig_gen = clp->cl_mig_gen;
+
+ if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION,
+ &server->mig_status))
+ continue;
+
+ rcu_read_unlock();
+ status = nfs4_try_migration(server, cred);
+ if (status < 0) {
+ put_rpccred(cred);
+ return status;
+ }
+ goto restart;
+ }
+ rcu_read_unlock();
+ put_rpccred(cred);
+ return 0;
+}
+
/**
* nfs4_discover_server_trunking - Detect server IP address trunking
*
@@ -2157,7 +2306,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
status = nfs4_check_lease(clp);
if (status < 0)
goto out_error;
- continue;
+ }
+
+ if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
+ section = "migration";
+ status = nfs4_handle_migration(clp);
+ if (status < 0)
+ goto out_error;
}
/* First recover reboot state... */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a1c80a2..c7a11bc 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -78,6 +78,7 @@ struct nfs_client {
char cl_ipaddr[48];
u32 cl_cb_ident; /* v4.0 callback identifier */
const struct nfs4_minor_version_ops *cl_mvops;
+ unsigned long cl_mig_gen;
/* NFSv4.0 transport blocking */
struct nfs4_slot_table *cl_slot_tbl;
@@ -188,6 +189,12 @@ struct nfs_server {
struct list_head state_owners_lru;
struct list_head layouts;
struct list_head delegations;
+
+ unsigned long mig_gen;
+ unsigned long mig_status;
+#define NFS_MIG_IN_TRANSITION (1)
+#define NFS_MIG_FAILED (2)
+
void (*destroy)(struct nfs_server *);
atomic_t active; /* Keep trace of any activity to this server */
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 10/21] NFS: Re-use exit code in nfs4_async_handle_error()
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (8 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 09/21] NFS: Add basic migration support to state manager thread Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 11/21] NFS: Rename "stateid_invalid" label Chuck Lever
` (10 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
Clean up.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f507e54..297bdd0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4757,19 +4757,15 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
dprintk("%s ERROR %d, Reset session\n", __func__,
task->tk_status);
nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
- task->tk_status = 0;
- return -EAGAIN;
+ goto restart_call;
#endif /* CONFIG_NFS_V4_1 */
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
case -NFS4ERR_GRACE:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
- task->tk_status = 0;
- return -EAGAIN;
case -NFS4ERR_RETRY_UNCACHED_REP:
case -NFS4ERR_OLD_STATEID:
- task->tk_status = 0;
- return -EAGAIN;
+ goto restart_call;
}
task->tk_status = nfs4_map_errors(task->tk_status);
return 0;
@@ -4780,6 +4776,7 @@ wait_on_recovery:
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+restart_call:
task->tk_status = 0;
return -EAGAIN;
}
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 11/21] NFS: Rename "stateid_invalid" label
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (9 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 10/21] NFS: Re-use exit code in nfs4_async_handle_error() Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 12/21] NFS: Add migration recovery callouts in nfs4proc.c Chuck Lever
` (9 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
I'm going to use this exit label also for migration recovery
failures.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 297bdd0..c304ec1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4735,12 +4735,12 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
if (state == NULL)
break;
if (nfs4_schedule_stateid_recovery(server, state) < 0)
- goto stateid_invalid;
+ goto recovery_failed;
goto wait_on_recovery;
case -NFS4ERR_EXPIRED:
if (state != NULL) {
if (nfs4_schedule_stateid_recovery(server, state) < 0)
- goto stateid_invalid;
+ goto recovery_failed;
}
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
@@ -4769,7 +4769,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
}
task->tk_status = nfs4_map_errors(task->tk_status);
return 0;
-stateid_invalid:
+recovery_failed:
task->tk_status = -EIO;
return 0;
wait_on_recovery:
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 12/21] NFS: Add migration recovery callouts in nfs4proc.c
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (10 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 11/21] NFS: Rename "stateid_invalid" label Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 13/21] NFS: Handle NFS4ERR_MOVED during delegation recall Chuck Lever
` (8 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
When a server returns NFS4ERR_MOVED, trigger the new migration
recovery logic in the state manager.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c304ec1..25d42a8 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -384,6 +384,11 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
case -NFS4ERR_STALE_CLIENTID:
nfs4_schedule_lease_recovery(clp);
goto wait_on_recovery;
+ case -NFS4ERR_MOVED:
+ ret = nfs4_schedule_migration_recovery(server);
+ if (ret < 0)
+ break;
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
@@ -431,6 +436,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
return nfs4_map_errors(ret);
wait_on_recovery:
ret = nfs4_wait_clnt_recover(clp);
+ if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+ return -EIO;
if (ret == 0)
exception->retry = 1;
return ret;
@@ -2981,11 +2988,16 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
status = nfs4_proc_fs_locations(client, dir, name, locations, page);
if (status != 0)
goto out;
- /* Make sure server returned a different fsid for the referral */
+
+ /*
+ * If the fsid didn't change, this is a migration event, not a
+ * referral. Cause us to drop into the exception handler, which
+ * will kick off migration recovery.
+ */
if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) {
dprintk("%s: server did not return a different fsid for"
" a referral at %s\n", __func__, name->name);
- status = -EIO;
+ status = -NFS4ERR_MOVED;
goto out;
}
/* Fixup attributes for the nfs_lookup() call to nfs_fhget() */
@@ -4746,6 +4758,10 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
case -NFS4ERR_STALE_CLIENTID:
nfs4_schedule_lease_recovery(clp);
goto wait_on_recovery;
+ case -NFS4ERR_MOVED:
+ if (nfs4_schedule_migration_recovery(server) < 0)
+ goto recovery_failed;
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
@@ -4776,6 +4792,8 @@ wait_on_recovery:
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+ if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+ goto recovery_failed;
restart_call:
task->tk_status = 0;
return -EAGAIN;
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 13/21] NFS: Handle NFS4ERR_MOVED during delegation recall
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (11 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 12/21] NFS: Add migration recovery callouts in nfs4proc.c Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 14/21] NFS: Add method to detect whether an FSID is still on the server Chuck Lever
` (7 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
When a server returns NFS4ERR_MOVED during a delegation recall,
trigger the new migration recovery logic in the state manager.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 25d42a8..af8feba 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1582,6 +1582,9 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
/* Don't recall a delegation if it was lost */
nfs4_schedule_lease_recovery(server->nfs_client);
return -EAGAIN;
+ case -NFS4ERR_MOVED:
+ nfs4_schedule_migration_recovery(server);
+ return -EAGAIN;
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 14/21] NFS: Add method to detect whether an FSID is still on the server
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (12 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 13/21] NFS: Handle NFS4ERR_MOVED during delegation recall Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 15/21] NFS: Support NFS4ERR_LEASE_MOVED recovery in state manager Chuck Lever
` (6 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
Introduce a mechanism for probing a server to determine if an FSID
is present or absent.
The on-the-wire compound is different between minor version 0 and 1.
Minor version 0 appends a RENEW operation to identify which client
ID is probing. Minor version 1 has a SEQUENCE operation in the
compound which effectively carries the same information.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 2 +
fs/nfs/nfs4proc.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++
fs/nfs/nfs4xdr.c | 67 ++++++++++++++++++++++++-
include/linux/nfs4.h | 1
include/linux/nfs_xdr.h | 13 +++++
5 files changed, 209 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 94e783f..2f0f8c2 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -208,6 +208,7 @@ struct nfs4_state_maintenance_ops {
struct nfs4_mig_recovery_ops {
int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
struct page *, struct rpc_cred *);
+ int (*fsid_present)(struct inode *, struct rpc_cred *);
};
extern const struct dentry_operations nfs4_dentry_operations;
@@ -242,6 +243,7 @@ extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struc
struct nfs4_fs_locations *, struct page *);
extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
struct page *page, struct rpc_cred *);
+extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *);
extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *,
struct nfs_fh *, struct nfs_fattr *);
extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index af8feba..360e14e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6159,6 +6159,132 @@ int nfs4_proc_get_locations(struct inode *inode,
return status;
}
+/*
+ * This operation also signals the server that this client is
+ * performing "lease moved" recovery. The server can stop
+ * returning NFS4ERR_LEASE_MOVED to this client. A RENEW operation
+ * is appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+ struct rpc_clnt *clnt = server->client;
+ struct nfs4_fsid_present_arg args = {
+ .fh = NFS_FH(inode),
+ .clientid = clp->cl_clientid,
+ .renew = 1, /* append RENEW */
+ };
+ struct nfs4_fsid_present_res res = {
+ .renew = 1,
+ };
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ .rpc_cred = cred,
+ };
+ unsigned long now = jiffies;
+ int status;
+
+ res.fh = nfs_alloc_fhandle();
+ if (res.fh == NULL)
+ return -ENOMEM;
+
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+ nfs4_set_sequence_privileged(&args.seq_args);
+ status = nfs4_call_sync_sequence(clnt, server, &msg,
+ &args.seq_args, &res.seq_res);
+ nfs_free_fhandle(res.fh);
+ if (status)
+ return status;
+
+ do_renew_lease(clp, now);
+ return 0;
+}
+
+#ifdef CONFIG_NFS_V4_1
+
+/*
+ * This operation also signals the server that this client is
+ * performing "lease moved" recovery. The server can stop asserting
+ * SEQ4_STATUS_LEASE_MOVED for this client. The client ID performing
+ * this operation is identified in the SEQUENCE operation in this
+ * compound.
+ */
+static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct rpc_clnt *clnt = server->client;
+ struct nfs4_fsid_present_arg args = {
+ .fh = NFS_FH(inode),
+ };
+ struct nfs4_fsid_present_res res = {
+ };
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ .rpc_cred = cred,
+ };
+ int status;
+
+ res.fh = nfs_alloc_fhandle();
+ if (res.fh == NULL)
+ return -ENOMEM;
+
+ nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+ nfs4_set_sequence_privileged(&args.seq_args);
+ status = nfs4_call_sync_sequence(clnt, server, &msg,
+ &args.seq_args, &res.seq_res);
+ nfs_free_fhandle(res.fh);
+ if (status == NFS4_OK &&
+ res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED)
+ status = -NFS4ERR_LEASE_MOVED;
+ return status;
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+/**
+ * nfs4_proc_fsid_present - Is this FSID present or absent on server?
+ * @inode: inode on FSID to check
+ * @cred: credential to use for this operation
+ *
+ * Server indicates whether the FSID is present, moved, or not
+ * recognized. This operation is necessary to clear a LEASE_MOVED
+ * condition for this client ID.
+ *
+ * Returns NFS4_OK if the FSID is present on this server,
+ * -NFS4ERR_MOVED if the FSID is no longer present, a negative
+ * NFS4ERR code if some error occurred on the server, or a
+ * negative errno if a local failure occurred.
+ */
+int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct nfs_client *clp = server->nfs_client;
+ const struct nfs4_mig_recovery_ops *ops =
+ clp->cl_mvops->mig_recovery_ops;
+ struct nfs4_exception exception = { };
+ int status;
+
+ dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
+ (unsigned long long)server->fsid.major,
+ (unsigned long long)server->fsid.minor,
+ clp->cl_hostname);
+ nfs_display_fhandle(NFS_FH(inode), __func__);
+
+ do {
+ status = ops->fsid_present(inode, cred);
+ if (status != -NFS4ERR_DELAY)
+ break;
+ nfs4_handle_exception(server, status, &exception);
+ } while (exception.retry);
+ return status;
+}
+
/**
* If 'use_integrity' is true and the state managment nfs_client
* cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient
@@ -8058,11 +8184,13 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
.get_locations = _nfs40_proc_get_locations,
+ .fsid_present = _nfs40_proc_fsid_present,
};
#if defined(CONFIG_NFS_V4_1)
static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = {
.get_locations = _nfs41_proc_get_locations,
+ .fsid_present = _nfs41_proc_fsid_present,
};
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1854b04..f903389 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -595,11 +595,13 @@ static int nfs4_stat_to_errno(int);
#define NFS4_enc_getattr_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
- encode_getattr_maxsz)
+ encode_getattr_maxsz + \
+ encode_renew_maxsz)
#define NFS4_dec_getattr_sz (compound_decode_hdr_maxsz + \
decode_sequence_maxsz + \
decode_putfh_maxsz + \
- decode_getattr_maxsz)
+ decode_getattr_maxsz + \
+ decode_renew_maxsz)
#define NFS4_enc_lookup_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -753,6 +755,18 @@ static int nfs4_stat_to_errno(int);
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_secinfo_maxsz)
+#define NFS4_enc_fsid_present_sz \
+ (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
+ encode_putfh_maxsz + \
+ encode_getfh_maxsz + \
+ encode_renew_maxsz)
+#define NFS4_dec_fsid_present_sz \
+ (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
+ decode_putfh_maxsz + \
+ decode_getfh_maxsz + \
+ decode_renew_maxsz)
#if defined(CONFIG_NFS_V4_1)
#define NFS4_enc_bind_conn_to_session_sz \
(compound_encode_hdr_maxsz + \
@@ -2726,6 +2740,26 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
encode_nops(&hdr);
}
+/*
+ * Encode FSID_PRESENT request
+ */
+static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ struct nfs4_fsid_present_arg *args)
+{
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+ };
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->seq_args, &hdr);
+ encode_putfh(xdr, args->fh, &hdr);
+ encode_getfh(xdr, &hdr);
+ if (args->renew)
+ encode_renew(xdr, args->clientid, &hdr);
+ encode_nops(&hdr);
+}
+
#if defined(CONFIG_NFS_V4_1)
/*
* BIND_CONN_TO_SESSION request
@@ -6883,6 +6917,34 @@ out:
return status;
}
+/*
+ * Decode FSID_PRESENT response
+ */
+static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ struct nfs4_fsid_present_res *res)
+{
+ struct compound_hdr hdr;
+ int status;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_getfh(xdr, res->fh);
+ if (status)
+ goto out;
+ if (res->renew)
+ status = decode_renew(xdr);
+out:
+ return status;
+}
+
#if defined(CONFIG_NFS_V4_1)
/*
* Decode BIND_CONN_TO_SESSION response
@@ -7397,6 +7459,7 @@ struct rpc_procinfo nfs4_procedures[] = {
PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations),
PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner),
PROC(SECINFO, enc_secinfo, dec_secinfo),
+ PROC(FSID_PRESENT, enc_fsid_present, dec_fsid_present),
#if defined(CONFIG_NFS_V4_1)
PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id),
PROC(CREATE_SESSION, enc_create_session, dec_create_session),
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e36dee5..c56fa8f 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -460,6 +460,7 @@ enum {
NFSPROC4_CLNT_FS_LOCATIONS,
NFSPROC4_CLNT_RELEASE_LOCKOWNER,
NFSPROC4_CLNT_SECINFO,
+ NFSPROC4_CLNT_FSID_PRESENT,
/* nfs41 */
NFSPROC4_CLNT_EXCHANGE_ID,
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 405dfad..8fe5b94 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1088,6 +1088,19 @@ struct nfs4_secinfo_res {
struct nfs4_secinfo_flavors *flavors;
};
+struct nfs4_fsid_present_arg {
+ struct nfs4_sequence_args seq_args;
+ const struct nfs_fh *fh;
+ clientid4 clientid;
+ unsigned char renew:1;
+};
+
+struct nfs4_fsid_present_res {
+ struct nfs4_sequence_res seq_res;
+ struct nfs_fh *fh;
+ unsigned char renew:1;
+};
+
#endif /* CONFIG_NFS_V4 */
struct nfstime4 {
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 15/21] NFS: Support NFS4ERR_LEASE_MOVED recovery in state manager
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (13 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 14/21] NFS: Add method to detect whether an FSID is still on the server Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 16/21] NFS: Implement support for NFS4ERR_LEASE_MOVED Chuck Lever
` (5 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
A migration on the FSID in play for the current NFS operation
is reported via the error status code NFS4ERR_MOVED.
"Lease moved" means that a migration has occurred on some other
FSID than the one for the current operation. It's a signal that
the client should take action immediately to handle a migration
that it may not have noticed otherwise. This is so that the
client's lease does not expire unnoticed on the destination server.
In NFSv4.0, a moved lease is reported with the NFS4ERR_LEASE_MOVED
error status code.
To recover from NFS4ERR_LEASE_MOVED, check each FSID for that server
to see if it is still present. Invoke nfs4_try_migration() if the
FSID is no longer present on the server.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4_fs.h | 2 +
fs/nfs/nfs4state.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 74 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 2f0f8c2..210e44e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -30,6 +30,7 @@ enum nfs4_client_state {
NFS4CLNT_PURGE_STATE,
NFS4CLNT_BIND_CONN_TO_SESSION,
NFS4CLNT_MOVED,
+ NFS4CLNT_LEASE_MOVED,
};
#define NFS4_RENEW_TIMEOUT 0x01
@@ -425,6 +426,7 @@ extern void nfs4_schedule_state_manager(struct nfs_client *);
extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
extern int nfs4_schedule_migration_recovery(const struct nfs_server *);
+extern void nfs4_schedule_lease_moved_recovery(struct nfs_client *);
extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
extern void nfs41_handle_server_scope(struct nfs_client *,
struct nfs41_server_scope **);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b66163f..3fbce1f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1233,6 +1233,22 @@ int nfs4_schedule_migration_recovery(const struct nfs_server *server)
}
EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery);
+/**
+ * nfs4_schedule_lease_moved_recovery - start lease-moved recovery
+ *
+ * @clp: server to check for moved leases
+ *
+ */
+void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp)
+{
+ dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n",
+ __func__, clp->cl_clientid, clp->cl_hostname);
+
+ set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state);
+ nfs4_schedule_state_manager(clp);
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery);
+
int nfs4_wait_clnt_recover(struct nfs_client *clp)
{
int res;
@@ -1664,7 +1680,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
nfs4_state_end_reclaim_reboot(clp);
break;
case -NFS4ERR_STALE_CLIENTID:
- case -NFS4ERR_LEASE_MOVED:
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
nfs4_state_clear_reclaim_reboot(clp);
nfs4_state_start_reclaim_reboot(clp);
@@ -1978,6 +1993,55 @@ restart:
return 0;
}
+/*
+ * Test each nfs_server on the clp's cl_superblocks list to see
+ * if it's moved to another server. Stop when the server no longer
+ * returns NFS4ERR_LEASE_MOVED.
+ */
+static int nfs4_handle_lease_moved(struct nfs_client *clp)
+{
+ const struct nfs4_state_maintenance_ops *ops =
+ clp->cl_mvops->state_renewal_ops;
+ struct nfs_server *server;
+ struct rpc_cred *cred;
+
+ dprintk("%s: lease moved reported on \"%s\"\n", __func__,
+ clp->cl_hostname);
+
+ spin_lock(&clp->cl_lock);
+ cred = ops->get_state_renewal_cred_locked(clp);
+ spin_unlock(&clp->cl_lock);
+ if (cred == NULL)
+ return -NFS4ERR_NOENT;
+
+ clp->cl_mig_gen++;
+restart:
+ rcu_read_lock();
+ list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+ struct inode *inode;
+ int status;
+
+ if (server->mig_gen == clp->cl_mig_gen)
+ continue;
+ server->mig_gen = clp->cl_mig_gen;
+
+ rcu_read_unlock();
+
+ inode = server->super->s_root->d_inode;
+ status = nfs4_proc_fsid_present(inode, cred);
+ if (status != -NFS4ERR_MOVED)
+ goto restart; /* wasn't this one */
+ if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED)
+ goto restart; /* there are more */
+ goto out;
+ }
+ rcu_read_unlock();
+
+out:
+ put_rpccred(cred);
+ return 0;
+}
+
/**
* nfs4_discover_server_trunking - Detect server IP address trunking
*
@@ -2315,6 +2379,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
goto out_error;
}
+ if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) {
+ section = "lease moved";
+ status = nfs4_handle_lease_moved(clp);
+ if (status < 0)
+ goto out_error;
+ }
+
/* First recover reboot state... */
if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
section = "reclaim reboot";
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 16/21] NFS: Implement support for NFS4ERR_LEASE_MOVED
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (14 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 15/21] NFS: Support NFS4ERR_LEASE_MOVED recovery in state manager Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 17/21] NFS: Migration support for RELEASE_LOCKOWNER Chuck Lever
` (4 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
Trigger lease-moved recovery when a request returns
NFS4ERR_LEASE_MOVED.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 360e14e..3a03cd6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -389,6 +389,9 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
if (ret < 0)
break;
goto wait_on_recovery;
+ case -NFS4ERR_LEASE_MOVED:
+ nfs4_schedule_lease_moved_recovery(clp);
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
@@ -1585,6 +1588,9 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
case -NFS4ERR_MOVED:
nfs4_schedule_migration_recovery(server);
return -EAGAIN;
+ case -NFS4ERR_LEASE_MOVED:
+ nfs4_schedule_lease_moved_recovery(server->nfs_client);
+ return -EAGAIN;
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
@@ -4765,6 +4771,9 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
if (nfs4_schedule_migration_recovery(server) < 0)
goto recovery_failed;
goto wait_on_recovery;
+ case -NFS4ERR_LEASE_MOVED:
+ nfs4_schedule_lease_moved_recovery(clp);
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 17/21] NFS: Migration support for RELEASE_LOCKOWNER
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (15 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 16/21] NFS: Implement support for NFS4ERR_LEASE_MOVED Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 18/21] NFS: Handle NFS4ERR_LEASE_MOVED during async RENEW Chuck Lever
` (3 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
Currently the Linux NFS client ignores the operation status code for
the RELEASE_LOCKOWNER operation. Like NFSv3's UMNT operation,
RELEASE_LOCKOWNER is a courtesy to help servers manage their
resources, and the outcome is not consequential for the client.
During a migration, a server may report NFS4ERR_LEASE_MOVED, in
which case the client really should retry, since typically
LEASE_MOVED has nothing to do with the current operation, but does
prevent it from going forward.
Also, it's important for a client to respond as soon as possible to
a moved lease condition, since the client's lease could expire on
the destination without further action by the client.
NFS4ERR_DELAY is not included in the list of valid status codes for
RELEASE_LOCKOWNER in RFC 3530bis. However, rfc3530-migration-update
does permit migration-capable servers to return DELAY to clients,
but only in the context of an ongoing migration. In this case the
server has frozen lock state in preparation for migration, and a
client retry would help the destination server purge unneeded state
once migration recovery is complete.
Interestly, NFS4ERR_MOVED is not valid for RELEASE_LOCKOWNER, even
though lock owners can be migrated with Transparent State Migration.
Note that RFC 3530bis section 9.5 includes RELEASE_LOCKOWNER in the
list of operations that renew a client's lease on the server if they
succeed. Now that our client pays attention to the operation's
status code, we can note that renewal appropriately.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3a03cd6..e743e1d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5806,6 +5806,7 @@ struct nfs_release_lockowner_data {
struct nfs_release_lockowner_args args;
struct nfs4_sequence_args seq_args;
struct nfs4_sequence_res seq_res;
+ unsigned long timestamp;
};
static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata)
@@ -5813,12 +5814,27 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
struct nfs_release_lockowner_data *data = calldata;
nfs40_setup_sequence(data->server,
&data->seq_args, &data->seq_res, task);
+ data->timestamp = jiffies;
}
static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
{
struct nfs_release_lockowner_data *data = calldata;
+ struct nfs_server *server = data->server;
+
nfs40_sequence_done(task, &data->seq_res);
+
+ switch (task->tk_status) {
+ case 0:
+ renew_lease(server, data->timestamp);
+ break;
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_LEASE_MOVED:
+ case -NFS4ERR_DELAY:
+ if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN)
+ rpc_restart_call_prepare(task);
+ }
}
static void nfs4_release_lockowner_release(void *calldata)
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 18/21] NFS: Handle NFS4ERR_LEASE_MOVED during async RENEW
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (16 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 17/21] NFS: Migration support for RELEASE_LOCKOWNER Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:13 ` [PATCH 19/21] NFS: Handle SEQ4_STATUS_LEASE_MOVED Chuck Lever
` (2 subsequent siblings)
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
With NFSv4 minor version 0, the asynchronous lease RENEW
heartbeat can return NFS4ERR_LEASE_MOVED. Error recovery logic for
async RENEW is a separate code path from the generic NFS proc paths,
so it must be updated to handle NFS4ERR_LEASE_MOVED as well.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4proc.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e743e1d..d9c38cd 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4242,7 +4242,13 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata)
unsigned long timestamp = data->timestamp;
trace_nfs4_renew_async(clp, task->tk_status);
- if (task->tk_status < 0) {
+ switch (task->tk_status) {
+ case 0:
+ break;
+ case -NFS4ERR_LEASE_MOVED:
+ nfs4_schedule_lease_moved_recovery(clp);
+ break;
+ default:
/* Unless we're shutting down, schedule state recovery! */
if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0)
return;
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 19/21] NFS: Handle SEQ4_STATUS_LEASE_MOVED
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (17 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 18/21] NFS: Handle NFS4ERR_LEASE_MOVED during async RENEW Chuck Lever
@ 2013-10-17 18:13 ` Chuck Lever
2013-10-17 18:14 ` [PATCH 20/21] NFS: Set EXCHGID4_FLAG_SUPP_MOVED_MIGR Chuck Lever
2013-10-17 18:14 ` [PATCH 21/21] NFS: Fix possible endless state recovery wait Chuck Lever
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:13 UTC (permalink / raw)
To: linux-nfs
With the advent of NFSv4 sessions in NFSv4.1 and following, a "lease
moved" condition is reported differently than it is in NFSv4.0.
NFSv4 minor version 0 servers return an error status code,
NFS4ERR_LEASE_MOVED, to signal that a lease has moved. This error
causes the whole compound operation to fail. Normal compounds
against this server continue to fail until the client performs
migration recovery on the migrated share.
Minor version 1 and later servers assert a bit flag in the reply to
a compound's SEQUENCE operation to signal LEASE_MOVED. This is not
a fatal condition: operations against this server continue normally.
The server asserts this flag until the client performs migration
recovery on the migrated share.
Note that servers MUST NOT return NFS4ERR_LEASE_MOVED to NFSv4
clients not using NFSv4.0.
After the server asserts any of the sr_status_flags in the SEQUENCE
operation in a typical compound, our client initiates standard lease
recovery. For NFSv4.1+, a stand-alone SEQUENCE operation is
performed to discover what recovery is needed.
If SEQ4_STATUS_LEASE_MOVED is asserted in this stand-alone SEQUENCE
operation, our client attempts to discover which FSIDs have been
migrated, and then performs migration recovery on each.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4state.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3fbce1f..6daa064 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2230,9 +2230,10 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
nfs41_handle_server_reboot(clp);
if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
- SEQ4_STATUS_ADMIN_STATE_REVOKED |
- SEQ4_STATUS_LEASE_MOVED))
+ SEQ4_STATUS_ADMIN_STATE_REVOKED))
nfs41_handle_state_revoked(clp);
+ if (flags & SEQ4_STATUS_LEASE_MOVED)
+ nfs4_schedule_lease_moved_recovery(clp);
if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
nfs41_handle_recallable_state_revoked(clp);
if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT)
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 20/21] NFS: Set EXCHGID4_FLAG_SUPP_MOVED_MIGR
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (18 preceding siblings ...)
2013-10-17 18:13 ` [PATCH 19/21] NFS: Handle SEQ4_STATUS_LEASE_MOVED Chuck Lever
@ 2013-10-17 18:14 ` Chuck Lever
2013-10-17 18:14 ` [PATCH 21/21] NFS: Fix possible endless state recovery wait Chuck Lever
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:14 UTC (permalink / raw)
To: linux-nfs
Broadly speaking, v4.1 migration is untested. There are no servers
in the wild that support NFSv4.1 migration. However, as server
implementations become available, we do want to enable testing by
developers, while leaving it disabled for environments for which
broken migration support would be an unpleasant surprise.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/Kconfig | 11 +++++++++++
fs/nfs/nfs4proc.c | 8 +++++++-
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index b5e80b0..38c1768 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -140,6 +140,17 @@ config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
If the NFS client is unchanged from the upstream kernel, this
option should be set to the default "kernel.org".
+config NFS_V4_1_MIGRATION
+ bool "NFSv4.1 client support for migration"
+ depends on NFS_V4_1
+ default n
+ help
+ This option makes the NFS client advertise to NFSv4.1 servers that
+ it can support NFSv4 migration.
+
+ The NFSv4.1 pieces of the Linux NFSv4 migration implementation are
+ still experimental. If you are not an NFSv4 developer, say N here.
+
config NFS_V4_SECURITY_LABEL
bool
depends on NFS_V4_2 && SECURITY
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d9c38cd..fbc925f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6602,8 +6602,14 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
struct nfs41_exchange_id_args args = {
.verifier = &verifier,
.client = clp,
+#ifdef CONFIG_NFS_V4_1_MIGRATION
.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
- EXCHGID4_FLAG_BIND_PRINC_STATEID,
+ EXCHGID4_FLAG_BIND_PRINC_STATEID |
+ EXCHGID4_FLAG_SUPP_MOVED_MIGR,
+#else
+ .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
+ EXCHGID4_FLAG_BIND_PRINC_STATEID,
+#endif
};
struct nfs41_exchange_id_res res = {
0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH 21/21] NFS: Fix possible endless state recovery wait
2013-10-17 18:12 [PATCH 00/21] Basic NFSv4 migration support Chuck Lever
` (19 preceding siblings ...)
2013-10-17 18:14 ` [PATCH 20/21] NFS: Set EXCHGID4_FLAG_SUPP_MOVED_MIGR Chuck Lever
@ 2013-10-17 18:14 ` Chuck Lever
20 siblings, 0 replies; 22+ messages in thread
From: Chuck Lever @ 2013-10-17 18:14 UTC (permalink / raw)
To: linux-nfs
In nfs4_wait_clnt_recover(), hold a reference to the clp being
waited on. The state manager can reduce clp->cl_count to 1, in
which case the nfs_put_client() in nfs4_run_state_manager() can
free *clp before wait_on_bit() returns and allows
nfs4_wait_clnt_recover() to run again.
The behavior at that point is non-deterministic. If the waited-on
bit still happens to be zero, wait_on_bit() will wake the waiter as
expected. If the bit is set again (say, if the memory was poisoned
when freed) wait_on_bit() can leave the waiter asleep.
This is a narrow fix which ensures the safety of accessing *clp in
nfs4_wait_clnt_recover(), but does not address the continued use
of a possibly freed *clp after nfs4_wait_clnt_recover() returns
(see nfs_end_delegation_return(), for example).
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfs/nfs4state.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6daa064..1a3cb26 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1255,14 +1255,16 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp)
might_sleep();
+ atomic_inc(&clp->cl_count);
res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
nfs_wait_bit_killable, TASK_KILLABLE);
if (res)
- return res;
-
+ goto out;
if (clp->cl_cons_state < 0)
- return clp->cl_cons_state;
- return 0;
+ res = clp->cl_cons_state;
+out:
+ nfs_put_client(clp);
+ return res;
}
int nfs4_client_recover_expired_lease(struct nfs_client *clp)
^ permalink raw reply related [flat|nested] 22+ messages in thread