aboutsummaryrefslogtreecommitdiff
path: root/net/sunrpc
diff options
context:
space:
mode:
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/clnt.c6
-rw-r--r--net/sunrpc/rpcb_clnt.c121
-rw-r--r--net/sunrpc/svc.c251
-rw-r--r--net/sunrpc/svc_xprt.c39
-rw-r--r--net/sunrpc/svcsock.c17
-rw-r--r--net/sunrpc/xprt.c12
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c33
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_recvfrom.c187
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c255
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c364
-rw-r--r--net/sunrpc/xprtrdma/transport.c41
-rw-r--r--net/sunrpc/xprtrdma/verbs.c741
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h17
-rw-r--r--net/sunrpc/xprtsock.c4
14 files changed, 1609 insertions, 479 deletions
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 76739e928d0..4895c341e46 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -174,7 +174,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru
clnt->cl_procinfo = version->procs;
clnt->cl_maxproc = version->nrprocs;
clnt->cl_protname = program->name;
- clnt->cl_prog = program->number;
+ clnt->cl_prog = args->prognumber ? : program->number;
clnt->cl_vers = version->number;
clnt->cl_stats = program->stats;
clnt->cl_metrics = rpc_alloc_iostats(clnt);
@@ -213,10 +213,10 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru
}
/* save the nodename */
- clnt->cl_nodelen = strlen(utsname()->nodename);
+ clnt->cl_nodelen = strlen(init_utsname()->nodename);
if (clnt->cl_nodelen > UNX_MAXNODENAME)
clnt->cl_nodelen = UNX_MAXNODENAME;
- memcpy(clnt->cl_nodename, utsname()->nodename, clnt->cl_nodelen);
+ memcpy(clnt->cl_nodename, init_utsname()->nodename, clnt->cl_nodelen);
rpc_register_client(clnt);
return clnt;
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 24db2b4d12d..41013dd66ac 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -20,6 +20,7 @@
#include <linux/in6.h>
#include <linux/kernel.h>
#include <linux/errno.h>
+#include <net/ipv6.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/sched.h>
@@ -176,13 +177,12 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
}
static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
- u32 version, struct rpc_message *msg,
- int *result)
+ u32 version, struct rpc_message *msg)
{
struct rpc_clnt *rpcb_clnt;
- int error = 0;
+ int result, error = 0;
- *result = 0;
+ msg->rpc_resp = &result;
rpcb_clnt = rpcb_create_local(addr, addrlen, version);
if (!IS_ERR(rpcb_clnt)) {
@@ -191,12 +191,15 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
} else
error = PTR_ERR(rpcb_clnt);
- if (error < 0)
+ if (error < 0) {
printk(KERN_WARNING "RPC: failed to contact local rpcbind "
"server (errno %d).\n", -error);
- dprintk("RPC: registration status %d/%d\n", error, *result);
+ return error;
+ }
- return error;
+ if (!result)
+ return -EACCES;
+ return 0;
}
/**
@@ -205,7 +208,11 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
* @vers: RPC version number to bind
* @prot: transport protocol to register
* @port: port value to register
- * @okay: OUT: result code
+ *
+ * Returns zero if the registration request was dispatched successfully
+ * and the rpcbind daemon returned success. Otherwise, returns an errno
+ * value that reflects the nature of the error (request could not be
+ * dispatched, timed out, or rpcbind returned an error).
*
* RPC services invoke this function to advertise their contact
* information via the system's rpcbind daemon. RPC services
@@ -217,15 +224,6 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
* all registered transports for [program, version] from the local
* rpcbind database.
*
- * Returns zero if the registration request was dispatched
- * successfully and a reply was received. The rpcbind daemon's
- * boolean result code is stored in *okay.
- *
- * Returns an errno value and sets *result to zero if there was
- * some problem that prevented the rpcbind request from being
- * dispatched, or if the rpcbind daemon did not respond within
- * the timeout.
- *
* This function uses rpcbind protocol version 2 to contact the
* local rpcbind daemon.
*
@@ -236,7 +234,7 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
* IN6ADDR_ANY (ie available for all AF_INET and AF_INET6
* addresses).
*/
-int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
+int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port)
{
struct rpcbind_args map = {
.r_prog = prog,
@@ -246,7 +244,6 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
};
struct rpc_message msg = {
.rpc_argp = &map,
- .rpc_resp = okay,
};
dprintk("RPC: %sregistering (%u, %u, %d, %u) with local "
@@ -259,7 +256,7 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
sizeof(rpcb_inaddr_loopback),
- RPCBVERS_2, &msg, okay);
+ RPCBVERS_2, &msg);
}
/*
@@ -290,7 +287,7 @@ static int rpcb_register_netid4(struct sockaddr_in *address_to_register,
return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
sizeof(rpcb_inaddr_loopback),
- RPCBVERS_4, msg, msg->rpc_resp);
+ RPCBVERS_4, msg);
}
/*
@@ -304,10 +301,13 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
char buf[64];
/* Construct AF_INET6 universal address */
- snprintf(buf, sizeof(buf),
- NIP6_FMT".%u.%u",
- NIP6(address_to_register->sin6_addr),
- port >> 8, port & 0xff);
+ if (ipv6_addr_any(&address_to_register->sin6_addr))
+ snprintf(buf, sizeof(buf), "::.%u.%u",
+ port >> 8, port & 0xff);
+ else
+ snprintf(buf, sizeof(buf), NIP6_FMT".%u.%u",
+ NIP6(address_to_register->sin6_addr),
+ port >> 8, port & 0xff);
map->r_addr = buf;
dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with "
@@ -321,7 +321,7 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback,
sizeof(rpcb_in6addr_loopback),
- RPCBVERS_4, msg, msg->rpc_resp);
+ RPCBVERS_4, msg);
}
/**
@@ -330,7 +330,11 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
* @version: RPC version number of service to (un)register
* @address: address family, IP address, and port to (un)register
* @netid: netid of transport protocol to (un)register
- * @result: result code from rpcbind RPC call
+ *
+ * Returns zero if the registration request was dispatched successfully
+ * and the rpcbind daemon returned success. Otherwise, returns an errno
+ * value that reflects the nature of the error (request could not be
+ * dispatched, timed out, or rpcbind returned an error).
*
* RPC services invoke this function to advertise their contact
* information via the system's rpcbind daemon. RPC services
@@ -342,15 +346,6 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
* to zero. Callers pass a netid of "" to unregister all
* transport netids associated with [program, version, address].
*
- * Returns zero if the registration request was dispatched
- * successfully and a reply was received. The rpcbind daemon's
- * result code is stored in *result.
- *
- * Returns an errno value and sets *result to zero if there was
- * some problem that prevented the rpcbind request from being
- * dispatched, or if the rpcbind daemon did not respond within
- * the timeout.
- *
* This function uses rpcbind protocol version 4 to contact the
* local rpcbind daemon. The local rpcbind daemon must support
* version 4 of the rpcbind protocol in order for these functions
@@ -372,8 +367,7 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
* advertises the service on all IPv4 and IPv6 addresses.
*/
int rpcb_v4_register(const u32 program, const u32 version,
- const struct sockaddr *address, const char *netid,
- int *result)
+ const struct sockaddr *address, const char *netid)
{
struct rpcbind_args map = {
.r_prog = program,
@@ -383,11 +377,8 @@ int rpcb_v4_register(const u32 program, const u32 version,
};
struct rpc_message msg = {
.rpc_argp = &map,
- .rpc_resp = result,
};
- *result = 0;
-
switch (address->sa_family) {
case AF_INET:
return rpcb_register_netid4((struct sockaddr_in *)address,
@@ -469,6 +460,28 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi
return rpc_run_task(&task_setup_data);
}
+/*
+ * In the case where rpc clients have been cloned, we want to make
+ * sure that we use the program number/version etc of the actual
+ * owner of the xprt. To do so, we walk back up the tree of parents
+ * to find whoever created the transport and/or whoever has the
+ * autobind flag set.
+ */
+static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt)
+{
+ struct rpc_clnt *parent = clnt->cl_parent;
+
+ while (parent != clnt) {
+ if (parent->cl_xprt != clnt->cl_xprt)
+ break;
+ if (clnt->cl_autobind)
+ break;
+ clnt = parent;
+ parent = parent->cl_parent;
+ }
+ return clnt;
+}
+
/**
* rpcb_getport_async - obtain the port for a given RPC service on a given host
* @task: task that is waiting for portmapper request
@@ -478,10 +491,10 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi
*/
void rpcb_getport_async(struct rpc_task *task)
{
- struct rpc_clnt *clnt = task->tk_client;
+ struct rpc_clnt *clnt;
struct rpc_procinfo *proc;
u32 bind_version;
- struct rpc_xprt *xprt = task->tk_xprt;
+ struct rpc_xprt *xprt;
struct rpc_clnt *rpcb_clnt;
static struct rpcbind_args *map;
struct rpc_task *child;
@@ -490,13 +503,13 @@ void rpcb_getport_async(struct rpc_task *task)
size_t salen;
int status;
+ clnt = rpcb_find_transport_owner(task->tk_client);
+ xprt = clnt->cl_xprt;
+
dprintk("RPC: %5u %s(%s, %u, %u, %d)\n",
task->tk_pid, __func__,
clnt->cl_server, clnt->cl_prog, clnt->cl_vers, xprt->prot);
- /* Autobind on cloned rpc clients is discouraged */
- BUG_ON(clnt->cl_parent != clnt);
-
/* Put self on the wait queue to ensure we get notified if
* some other task is already attempting to bind the port */
rpc_sleep_on(&xprt->binding, task, NULL);
@@ -558,7 +571,7 @@ void rpcb_getport_async(struct rpc_task *task)
status = -ENOMEM;
dprintk("RPC: %5u %s: no memory available\n",
task->tk_pid, __func__);
- goto bailout_nofree;
+ goto bailout_release_client;
}
map->r_prog = clnt->cl_prog;
map->r_vers = clnt->cl_vers;
@@ -578,11 +591,13 @@ void rpcb_getport_async(struct rpc_task *task)
task->tk_pid, __func__);
return;
}
- rpc_put_task(child);
- task->tk_xprt->stat.bind_count++;
+ xprt->stat.bind_count++;
+ rpc_put_task(child);
return;
+bailout_release_client:
+ rpc_release_client(rpcb_clnt);
bailout_nofree:
rpcb_wake_rpcbind_waiters(xprt, status);
task->tk_status = status;
@@ -633,7 +648,7 @@ static void rpcb_getport_done(struct rpc_task *child, void *data)
static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p,
struct rpcbind_args *rpcb)
{
- dprintk("RPC: rpcb_encode_mapping(%u, %u, %d, %u)\n",
+ dprintk("RPC: encoding rpcb request (%u, %u, %d, %u)\n",
rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port);
*p++ = htonl(rpcb->r_prog);
*p++ = htonl(rpcb->r_vers);
@@ -648,7 +663,7 @@ static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p,
unsigned short *portp)
{
*portp = (unsigned short) ntohl(*p++);
- dprintk("RPC: rpcb_decode_getport result %u\n",
+ dprintk("RPC: rpcb getport result: %u\n",
*portp);
return 0;
}
@@ -657,7 +672,7 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p,
unsigned int *boolp)
{
*boolp = (unsigned int) ntohl(*p++);
- dprintk("RPC: rpcb_decode_set: call %s\n",
+ dprintk("RPC: rpcb set/unset call %s\n",
(*boolp ? "succeeded" : "failed"));
return 0;
}
@@ -665,7 +680,7 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p,
static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p,
struct rpcbind_args *rpcb)
{
- dprintk("RPC: rpcb_encode_getaddr(%u, %u, %s)\n",
+ dprintk("RPC: encoding rpcb request (%u, %u, %s)\n",
rpcb->r_prog, rpcb->r_vers, rpcb->r_addr);
*p++ = htonl(rpcb->r_prog);
*p++ = htonl(rpcb->r_vers);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 5a32cb7c4bb..54c98d87684 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -28,6 +28,8 @@
#define RPCDBG_FACILITY RPCDBG_SVCDSP
+static void svc_unregister(const struct svc_serv *serv);
+
#define svc_serv_is_pooled(serv) ((serv)->sv_function)
/*
@@ -357,7 +359,7 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu)
*/
static struct svc_serv *
__svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
- void (*shutdown)(struct svc_serv *serv))
+ sa_family_t family, void (*shutdown)(struct svc_serv *serv))
{
struct svc_serv *serv;
unsigned int vers;
@@ -366,6 +368,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
return NULL;
+ serv->sv_family = family;
serv->sv_name = prog->pg_name;
serv->sv_program = prog;
serv->sv_nrthreads = 1;
@@ -416,30 +419,29 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
spin_lock_init(&pool->sp_lock);
}
-
/* Remove any stale portmap registrations */
- svc_register(serv, 0, 0);
+ svc_unregister(serv);
return serv;
}
struct svc_serv *
svc_create(struct svc_program *prog, unsigned int bufsize,
- void (*shutdown)(struct svc_serv *serv))
+ sa_family_t family, void (*shutdown)(struct svc_serv *serv))
{
- return __svc_create(prog, bufsize, /*npools*/1, shutdown);
+ return __svc_create(prog, bufsize, /*npools*/1, family, shutdown);
}
EXPORT_SYMBOL(svc_create);
struct svc_serv *
svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
- void (*shutdown)(struct svc_serv *serv),
+ sa_family_t family, void (*shutdown)(struct svc_serv *serv),
svc_thread_fn func, struct module *mod)
{
struct svc_serv *serv;
unsigned int npools = svc_pool_map_get();
- serv = __svc_create(prog, bufsize, npools, shutdown);
+ serv = __svc_create(prog, bufsize, npools, family, shutdown);
if (serv != NULL) {
serv->sv_function = func;
@@ -486,8 +488,7 @@ svc_destroy(struct svc_serv *serv)
if (svc_serv_is_pooled(serv))
svc_pool_map_put();
- /* Unregister service with the portmapper */
- svc_register(serv, 0, 0);
+ svc_unregister(serv);
kfree(serv->sv_pools);
kfree(serv);
}
@@ -718,55 +719,245 @@ svc_exit_thread(struct svc_rqst *rqstp)
}
EXPORT_SYMBOL(svc_exit_thread);
+#ifdef CONFIG_SUNRPC_REGISTER_V4
+
/*
- * Register an RPC service with the local portmapper.
- * To unregister a service, call this routine with
- * proto and port == 0.
+ * Register an "inet" protocol family netid with the local
+ * rpcbind daemon via an rpcbind v4 SET request.
+ *
+ * No netconfig infrastructure is available in the kernel, so
+ * we map IP_ protocol numbers to netids by hand.
+ *
+ * Returns zero on success; a negative errno value is returned
+ * if any error occurs.
*/
-int
-svc_register(struct svc_serv *serv, int proto, unsigned short port)
+static int __svc_rpcb_register4(const u32 program, const u32 version,
+ const unsigned short protocol,
+ const unsigned short port)
+{
+ struct sockaddr_in sin = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
+ .sin_port = htons(port),
+ };
+ char *netid;
+
+ switch (protocol) {
+ case IPPROTO_UDP:
+ netid = RPCBIND_NETID_UDP;
+ break;
+ case IPPROTO_TCP:
+ netid = RPCBIND_NETID_TCP;
+ break;
+ default:
+ return -EPROTONOSUPPORT;
+ }
+
+ return rpcb_v4_register(program, version,
+ (struct sockaddr *)&sin, netid);
+}
+
+/*
+ * Register an "inet6" protocol family netid with the local
+ * rpcbind daemon via an rpcbind v4 SET request.
+ *
+ * No netconfig infrastructure is available in the kernel, so
+ * we map IP_ protocol numbers to netids by hand.
+ *
+ * Returns zero on success; a negative errno value is returned
+ * if any error occurs.
+ */
+static int __svc_rpcb_register6(const u32 program, const u32 version,
+ const unsigned short protocol,
+ const unsigned short port)
+{
+ struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = htons(port),
+ };
+ char *netid;
+
+ switch (protocol) {
+ case IPPROTO_UDP:
+ netid = RPCBIND_NETID_UDP6;
+ break;
+ case IPPROTO_TCP:
+ netid = RPCBIND_NETID_TCP6;
+ break;
+ default:
+ return -EPROTONOSUPPORT;
+ }
+
+ return rpcb_v4_register(program, version,
+ (struct sockaddr *)&sin6, netid);
+}
+
+/*
+ * Register a kernel RPC service via rpcbind version 4.
+ *
+ * Returns zero on success; a negative errno value is returned
+ * if any error occurs.
+ */
+static int __svc_register(const u32 program, const u32 version,
+ const sa_family_t family,
+ const unsigned short protocol,
+ const unsigned short port)
+{
+ int error;
+
+ switch (family) {
+ case AF_INET:
+ return __svc_rpcb_register4(program, version,
+ protocol, port);
+ case AF_INET6:
+ error = __svc_rpcb_register6(program, version,
+ protocol, port);
+ if (error < 0)
+ return error;
+
+ /*
+ * Work around bug in some versions of Linux rpcbind
+ * which don't allow registration of both inet and
+ * inet6 netids.
+ *
+ * Error return ignored for now.
+ */
+ __svc_rpcb_register4(program, version,
+ protocol, port);
+ return 0;
+ }
+
+ return -EAFNOSUPPORT;
+}
+
+#else /* CONFIG_SUNRPC_REGISTER_V4 */
+
+/*
+ * Register a kernel RPC service via rpcbind version 2.
+ *
+ * Returns zero on success; a negative errno value is returned
+ * if any error occurs.
+ */
+static int __svc_register(const u32 program, const u32 version,
+ sa_family_t family,
+ const unsigned short protocol,
+ const unsigned short port)
+{
+ if (family != AF_INET)
+ return -EAFNOSUPPORT;
+
+ return rpcb_register(program, version, protocol, port);
+}
+
+#endif /* CONFIG_SUNRPC_REGISTER_V4 */
+
+/**
+ * svc_register - register an RPC service with the local portmapper
+ * @serv: svc_serv struct for the service to register
+ * @proto: transport protocol number to advertise
+ * @port: port to advertise
+ *
+ * Service is registered for any address in serv's address family
+ */
+int svc_register(const struct svc_serv *serv, const unsigned short proto,
+ const unsigned short port)
{
struct svc_program *progp;
- unsigned long flags;
unsigned int i;
- int error = 0, dummy;
+ int error = 0;
- if (!port)
- clear_thread_flag(TIF_SIGPENDING);
+ BUG_ON(proto == 0 && port == 0);
for (progp = serv->sv_program; progp; progp = progp->pg_next) {
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
- dprintk("svc: svc_register(%s, %s, %d, %d)%s\n",
+ dprintk("svc: svc_register(%sv%d, %s, %u, %u)%s\n",
progp->pg_name,
+ i,
proto == IPPROTO_UDP? "udp" : "tcp",
port,
- i,
+ serv->sv_family,
progp->pg_vers[i]->vs_hidden?
" (but not telling portmap)" : "");
if (progp->pg_vers[i]->vs_hidden)
continue;
- error = rpcb_register(progp->pg_prog, i, proto, port, &dummy);
+ error = __svc_register(progp->pg_prog, i,
+ serv->sv_family, proto, port);
if (error < 0)
break;
- if (port && !dummy) {
- error = -EACCES;
- break;
- }
}
}
- if (!port) {
- spin_lock_irqsave(&current->sighand->siglock, flags);
- recalc_sigpending();
- spin_unlock_irqrestore(&current->sighand->siglock, flags);
+ return error;
+}
+
+#ifdef CONFIG_SUNRPC_REGISTER_V4
+
+static void __svc_unregister(const u32 program, const u32 version,
+ const char *progname)
+{
+ struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = 0,
+ };
+ int error;
+
+ error = rpcb_v4_register(program, version,
+ (struct sockaddr *)&sin6, "");
+ dprintk("svc: %s(%sv%u), error %d\n",
+ __func__, progname, version, error);
+}
+
+#else /* CONFIG_SUNRPC_REGISTER_V4 */
+
+static void __svc_unregister(const u32 program, const u32 version,
+ const char *progname)
+{
+ int error;
+
+ error = rpcb_register(program, version, 0, 0);
+ dprintk("svc: %s(%sv%u), error %d\n",
+ __func__, progname, version, error);
+}
+
+#endif /* CONFIG_SUNRPC_REGISTER_V4 */
+
+/*
+ * All netids, bind addresses and ports registered for [program, version]
+ * are removed from the local rpcbind database (if the service is not
+ * hidden) to make way for a new instance of the service.
+ *
+ * The result of unregistration is reported via dprintk for those who want
+ * verification of the result, but is otherwise not important.
+ */
+static void svc_unregister(const struct svc_serv *serv)
+{
+ struct svc_program *progp;
+ unsigned long flags;
+ unsigned int i;
+
+ clear_thread_flag(TIF_SIGPENDING);
+
+ for (progp = serv->sv_program; progp; progp = progp->pg_next) {
+ for (i = 0; i < progp->pg_nvers; i++) {
+ if (progp->pg_vers[i] == NULL)
+ continue;
+ if (progp->pg_vers[i]->vs_hidden)
+ continue;
+
+ __svc_unregister(progp->pg_prog, i, progp->pg_name);
+ }
}
- return error;
+ spin_lock_irqsave(&current->sighand->siglock, flags);
+ recalc_sigpending();
+ spin_unlock_irqrestore(&current->sighand->siglock, flags);
}
/*
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index e46c825f495..bf5b5cdafeb 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -159,15 +159,44 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
-int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
- int flags)
+static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
+ struct svc_serv *serv,
+ unsigned short port, int flags)
{
- struct svc_xprt_class *xcl;
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
+ struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = htons(port),
+ };
+ struct sockaddr *sap;
+ size_t len;
+
+ switch (serv->sv_family) {
+ case AF_INET:
+ sap = (struct sockaddr *)&sin;
+ len = sizeof(sin);
+ break;
+ case AF_INET6:
+ sap = (struct sockaddr *)&sin6;
+ len = sizeof(sin6);
+ break;
+ default:
+ return ERR_PTR(-EAFNOSUPPORT);
+ }
+
+ return xcl->xcl_ops->xpo_create(serv, sap, len, flags);
+}
+
+int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
+ int flags)
+{
+ struct svc_xprt_class *xcl;
+
dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
@@ -180,9 +209,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
goto err;
spin_unlock(&svc_xprt_class_lock);
- newxprt = xcl->xcl_ops->
- xpo_create(serv, (struct sockaddr *)&sin, sizeof(sin),
- flags);
+ newxprt = __svc_xpo_create(xcl, serv, port, flags);
if (IS_ERR(newxprt)) {
module_put(xcl->xcl_owner);
return PTR_ERR(newxprt);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 3e65719f1ef..95293f549e9 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1114,6 +1114,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
struct svc_sock *svsk;
struct sock *inet;
int pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+ int val;
dprintk("svc: svc_setup_socket %p\n", sock);
if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) {
@@ -1146,6 +1147,18 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
else
svc_tcp_init(svsk, serv);
+ /*
+ * We start one listener per sv_serv. We want AF_INET
+ * requests to be automatically shunted to our AF_INET6
+ * listener using a mapped IPv4 address. Make sure
+ * no-one starts an equivalent IPv4 listener, which
+ * would steal our incoming connections.
+ */
+ val = 0;
+ if (serv->sv_family == AF_INET6)
+ kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
+ (char *)&val, sizeof(val));
+
dprintk("svc: svc_setup_socket created %p (inet %p)\n",
svsk, svsk->sk_sk);
@@ -1154,8 +1167,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
int svc_addsock(struct svc_serv *serv,
int fd,
- char *name_return,
- int *proto)
+ char *name_return)
{
int err = 0;
struct socket *so = sockfd_lookup(fd, &err);
@@ -1190,7 +1202,6 @@ int svc_addsock(struct svc_serv *serv,
sockfd_put(so);
return err;
}
- if (proto) *proto = so->sk->sk_protocol;
return one_sock_name(name_return, svsk);
}
EXPORT_SYMBOL_GPL(svc_addsock);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 99a52aabe33..29e401bb612 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -108,13 +108,10 @@ int xprt_register_transport(struct xprt_class *transport)
goto out;
}
- result = -EINVAL;
- if (try_module_get(THIS_MODULE)) {
- list_add_tail(&transport->list, &xprt_list);
- printk(KERN_INFO "RPC: Registered %s transport module.\n",
- transport->name);
- result = 0;
- }
+ list_add_tail(&transport->list, &xprt_list);
+ printk(KERN_INFO "RPC: Registered %s transport module.\n",
+ transport->name);
+ result = 0;
out:
spin_unlock(&xprt_list_lock);
@@ -143,7 +140,6 @@ int xprt_unregister_transport(struct xprt_class *transport)
"RPC: Unregistered %s transport module.\n",
transport->name);
list_del_init(&transport->list);
- module_put(THIS_MODULE);
goto out;
}
}
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e55427f73df..14106d26bb9 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -118,6 +118,10 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
}
if (xdrbuf->tail[0].iov_len) {
+ /* the rpcrdma protocol allows us to omit any trailing
+ * xdr pad bytes, saving the server an RDMA operation. */
+ if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
+ return n;
if (n == nsegs)
return 0;
seg[n].mr_page = NULL;
@@ -508,8 +512,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
if (hdrlen == 0)
return -1;
- dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd\n"
- " headerp 0x%p base 0x%p lkey 0x%x\n",
+ dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd"
+ " headerp 0x%p base 0x%p lkey 0x%x\n",
__func__, transfertypes[wtype], hdrlen, rpclen, padlen,
headerp, base, req->rl_iov.lkey);
@@ -594,7 +598,7 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
* Scatter inline received data back into provided iov's.
*/
static void
-rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len)
+rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
{
int i, npages, curlen, olen;
char *destp;
@@ -660,6 +664,13 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len)
} else
rqst->rq_rcv_buf.tail[0].iov_len = 0;
+ if (pad) {
+ /* implicit padding on terminal chunk */
+ unsigned char *p = rqst->rq_rcv_buf.tail[0].iov_base;
+ while (pad--)
+ p[rqst->rq_rcv_buf.tail[0].iov_len++] = 0;
+ }
+
if (copy_len)
dprintk("RPC: %s: %d bytes in"
" %d extra segments (%d lost)\n",
@@ -681,12 +692,14 @@ rpcrdma_conn_func(struct rpcrdma_ep *ep)
struct rpc_xprt *xprt = ep->rep_xprt;
spin_lock_bh(&xprt->transport_lock);
+ if (++xprt->connect_cookie == 0) /* maintain a reserved value */
+ ++xprt->connect_cookie;
if (ep->rep_connected > 0) {
if (!xprt_test_and_set_connected(xprt))
xprt_wake_pending_tasks(xprt, 0);
} else {
if (xprt_test_and_clear_connected(xprt))
- xprt_wake_pending_tasks(xprt, ep->rep_connected);
+ xprt_wake_pending_tasks(xprt, -ENOTCONN);
}
spin_unlock_bh(&xprt->transport_lock);
}
@@ -769,7 +782,7 @@ repost:
/* check for expected message types */
/* The order of some of these tests is important. */
switch (headerp->rm_type) {
- case __constant_htonl(RDMA_MSG):
+ case htonl(RDMA_MSG):
/* never expect read chunks */
/* never expect reply chunks (two ways to check) */
/* never expect write chunks without having offered RDMA */
@@ -792,17 +805,23 @@ repost:
((unsigned char *)iptr - (unsigned char *)headerp);
status = rep->rr_len + rdmalen;
r_xprt->rx_stats.total_rdma_reply += rdmalen;
+ /* special case - last chunk may omit padding */
+ if (rdmalen &= 3) {
+ rdmalen = 4 - rdmalen;
+ status += rdmalen;
+ }
} else {
/* else ordinary inline */
+ rdmalen = 0;
iptr = (__be32 *)((unsigned char *)headerp + 28);
rep->rr_len -= 28; /*sizeof *headerp;*/
status = rep->rr_len;
}
/* Fix up the rpc results for upper layer */
- rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len);
+ rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen);
break;
- case __constant_htonl(RDMA_NOMSG):
+ case htonl(RDMA_NOMSG):
/* never expect read or write chunks, always reply chunks */
if (headerp->rm_body.rm_chunks[0] != xdr_zero ||
headerp->rm_body.rm_chunks[1] != xdr_zero ||
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 74de31a0661..a4756576d68 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -116,7 +116,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
*
* Assumptions:
* - chunk[0]->position points to pages[0] at an offset of 0
- * - pages[] is not physically or virtually contigous and consists of
+ * - pages[] is not physically or virtually contiguous and consists of
* PAGE_SIZE elements.
*
* Output:
@@ -125,7 +125,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
* chunk in the read list
*
*/
-static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt,
+static int map_read_chunks(struct svcxprt_rdma *xprt,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head,
struct rpcrdma_msg *rmsgp,
@@ -211,26 +211,128 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt,
return sge_no;
}
-static void rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
- struct svc_rdma_op_ctxt *ctxt,
- struct kvec *vec,
- u64 *sgl_offset,
- int count)
+/* Map a read-chunk-list to an XDR and fast register the page-list.
+ *
+ * Assumptions:
+ * - chunk[0] position points to pages[0] at an offset of 0
+ * - pages[] will be made physically contiguous by creating a one-off memory
+ * region using the fastreg verb.
+ * - byte_count is # of bytes in read-chunk-list
+ * - ch_count is # of chunks in read-chunk-list
+ *
+ * Output:
+ * - sge array pointing into pages[] array.
+ * - chunk_sge array specifying sge index and count for each
+ * chunk in the read list
+ */
+static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
+ struct svc_rqst *rqstp,
+ struct svc_rdma_op_ctxt *head,
+ struct rpcrdma_msg *rmsgp,
+ struct svc_rdma_req_map *rpl_map,
+ struct svc_rdma_req_map *chl_map,
+ int ch_count,
+ int byte_count)
+{
+ int page_no;
+ int ch_no;
+ u32 offset;
+ struct rpcrdma_read_chunk *ch;
+ struct svc_rdma_fastreg_mr *frmr;
+ int ret = 0;
+
+ frmr = svc_rdma_get_frmr(xprt);
+ if (IS_ERR(frmr))
+ return -ENOMEM;
+
+ head->frmr = frmr;
+ head->arg