#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/kthread.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/bc_xprt.h>
#define RPCDBG_FACILITY RPCDBG_SVCDSP
-#define RPC_PARANOIA 1
+
+static void svc_unregister(const struct svc_serv *serv);
+
+#define svc_serv_is_pooled(serv) ((serv)->sv_function)
/*
* Mode for mapping cpus to pools.
*/
enum {
- SVC_POOL_NONE = -1, /* uninitialised, choose one of the others */
+ SVC_POOL_AUTO = -1, /* choose one of the others */
SVC_POOL_GLOBAL, /* no mapping, just a single global pool
* (legacy & UP mode) */
SVC_POOL_PERCPU, /* one pool per cpu */
SVC_POOL_PERNODE /* one pool per numa node */
};
+#define SVC_POOL_DEFAULT SVC_POOL_GLOBAL
/*
* Structure for mapping cpus to pools and vice versa.
* Setup once during sunrpc initialisation.
*/
static struct svc_pool_map {
+ int count; /* How many svc_servs use us */
int mode; /* Note: int not enum to avoid
* warnings about "enumeration value
* not handled in switch" */
unsigned int *pool_to; /* maps pool id to cpu or node */
unsigned int *to_pool; /* maps cpu or node to pool id */
} svc_pool_map = {
- .mode = SVC_POOL_NONE
+ .count = 0,
+ .mode = SVC_POOL_DEFAULT
};
+static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
+static int
+param_set_pool_mode(const char *val, struct kernel_param *kp)
+{
+ int *ip = (int *)kp->arg;
+ struct svc_pool_map *m = &svc_pool_map;
+ int err;
+
+ mutex_lock(&svc_pool_map_mutex);
+
+ err = -EBUSY;
+ if (m->count)
+ goto out;
+
+ err = 0;
+ if (!strncmp(val, "auto", 4))
+ *ip = SVC_POOL_AUTO;
+ else if (!strncmp(val, "global", 6))
+ *ip = SVC_POOL_GLOBAL;
+ else if (!strncmp(val, "percpu", 6))
+ *ip = SVC_POOL_PERCPU;
+ else if (!strncmp(val, "pernode", 7))
+ *ip = SVC_POOL_PERNODE;
+ else
+ err = -EINVAL;
+
+out:
+ mutex_unlock(&svc_pool_map_mutex);
+ return err;
+}
+
+static int
+param_get_pool_mode(char *buf, struct kernel_param *kp)
+{
+ int *ip = (int *)kp->arg;
+
+ switch (*ip)
+ {
+ case SVC_POOL_AUTO:
+ return strlcpy(buf, "auto", 20);
+ case SVC_POOL_GLOBAL:
+ return strlcpy(buf, "global", 20);
+ case SVC_POOL_PERCPU:
+ return strlcpy(buf, "percpu", 20);
+ case SVC_POOL_PERNODE:
+ return strlcpy(buf, "pernode", 20);
+ default:
+ return sprintf(buf, "%d", *ip);
+ }
+}
+
+module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode,
+ &svc_pool_map.mode, 0644);
/*
* Detect best pool mapping mode heuristically,
{
unsigned int node;
- if (num_online_nodes() > 1) {
+ if (nr_online_nodes > 1) {
/*
* Actually have multiple NUMA nodes,
* so split pools on NUMA node boundaries
static int
svc_pool_map_init_percpu(struct svc_pool_map *m)
{
- unsigned int maxpools = highest_possible_processor_id()+1;
+ unsigned int maxpools = nr_cpu_ids;
unsigned int pidx = 0;
unsigned int cpu;
int err;
static int
svc_pool_map_init_pernode(struct svc_pool_map *m)
{
- unsigned int maxpools = highest_possible_node_id()+1;
+ unsigned int maxpools = nr_node_ids;
unsigned int pidx = 0;
unsigned int node;
int err;
/*
- * Build the global map of cpus to pools and vice versa.
+ * Add a reference to the global map of cpus to pools (and
+ * vice versa). Initialise the map if we're the first user.
+ * Returns the number of pools.
*/
static unsigned int
-svc_pool_map_init(void)
+svc_pool_map_get(void)
{
struct svc_pool_map *m = &svc_pool_map;
int npools = -1;
- if (m->mode != SVC_POOL_NONE)
+ mutex_lock(&svc_pool_map_mutex);
+
+ if (m->count++) {
+ mutex_unlock(&svc_pool_map_mutex);
return m->npools;
+ }
- m->mode = svc_pool_map_choose_mode();
+ if (m->mode == SVC_POOL_AUTO)
+ m->mode = svc_pool_map_choose_mode();
switch (m->mode) {
case SVC_POOL_PERCPU:
}
m->npools = npools;
+ mutex_unlock(&svc_pool_map_mutex);
return m->npools;
}
+
+/*
+ * Drop a reference to the global map of cpus to pools.
+ * When the last reference is dropped, the map data is
+ * freed; this allows the sysadmin to change the pool
+ * mode using the pool_mode module option without
+ * rebooting or re-loading sunrpc.ko.
+ */
+static void
+svc_pool_map_put(void)
+{
+ struct svc_pool_map *m = &svc_pool_map;
+
+ mutex_lock(&svc_pool_map_mutex);
+
+ if (!--m->count) {
+ m->mode = SVC_POOL_DEFAULT;
+ kfree(m->to_pool);
+ kfree(m->pool_to);
+ m->npools = 0;
+ }
+
+ mutex_unlock(&svc_pool_map_mutex);
+}
+
+
/*
- * Set the current thread's cpus_allowed mask so that it
+ * Set the given thread's cpus_allowed mask so that it
* will only run on cpus in the given pool.
- *
- * Returns 1 and fills in oldmask iff a cpumask was applied.
*/
-static inline int
-svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask)
+static inline void
+svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
{
struct svc_pool_map *m = &svc_pool_map;
- unsigned int node; /* or cpu */
+ unsigned int node = m->pool_to[pidx];
/*
* The caller checks for sv_nrpools > 1, which
- * implies that we've been initialized and the
- * map mode is not NONE.
+ * implies that we've been initialized.
*/
- BUG_ON(m->mode == SVC_POOL_NONE);
+ BUG_ON(m->count == 0);
- switch (m->mode)
- {
- default:
- return 0;
+ switch (m->mode) {
case SVC_POOL_PERCPU:
- node = m->pool_to[pidx];
- *oldmask = current->cpus_allowed;
- set_cpus_allowed(current, cpumask_of_cpu(node));
- return 1;
+ {
+ set_cpus_allowed_ptr(task, cpumask_of(node));
+ break;
+ }
case SVC_POOL_PERNODE:
- node = m->pool_to[pidx];
- *oldmask = current->cpus_allowed;
- set_cpus_allowed(current, node_to_cpumask(node));
- return 1;
+ {
+ set_cpus_allowed_ptr(task, cpumask_of_node(node));
+ break;
+ }
}
}
unsigned int pidx = 0;
/*
- * SVC_POOL_NONE happens in a pure client when
+ * An uninitialised map happens in a pure client when
* lockd is brought up, so silently treat it the
* same as SVC_POOL_GLOBAL.
*/
-
- switch (m->mode) {
- case SVC_POOL_PERCPU:
- pidx = m->to_pool[cpu];
- break;
- case SVC_POOL_PERNODE:
- pidx = m->to_pool[cpu_to_node(cpu)];
- break;
+ if (svc_serv_is_pooled(serv)) {
+ switch (m->mode) {
+ case SVC_POOL_PERCPU:
+ pidx = m->to_pool[cpu];
+ break;
+ case SVC_POOL_PERNODE:
+ pidx = m->to_pool[cpu_to_node(cpu)];
+ break;
+ }
}
return &serv->sv_pools[pidx % serv->sv_nrpools];
}
*/
static struct svc_serv *
__svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
- void (*shutdown)(struct svc_serv *serv))
+ void (*shutdown)(struct svc_serv *serv))
{
struct svc_serv *serv;
- int vers;
+ unsigned int vers;
unsigned int xdrsize;
unsigned int i;
serv->sv_nrpools = npools;
serv->sv_pools =
- kcalloc(sizeof(struct svc_pool), serv->sv_nrpools,
+ kcalloc(serv->sv_nrpools, sizeof(struct svc_pool),
GFP_KERNEL);
if (!serv->sv_pools) {
kfree(serv);
for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_pool *pool = &serv->sv_pools[i];
- dprintk("initialising pool %u for %s\n",
+ dprintk("svc: initialising pool %u for %s\n",
i, serv->sv_name);
pool->sp_id = i;
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))
+ void (*shutdown)(struct svc_serv *serv))
{
return __svc_create(prog, bufsize, /*npools*/1, shutdown);
}
+EXPORT_SYMBOL_GPL(svc_create);
struct svc_serv *
svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
- void (*shutdown)(struct svc_serv *serv),
- svc_thread_fn func, int sig, struct module *mod)
+ void (*shutdown)(struct svc_serv *serv),
+ svc_thread_fn func, struct module *mod)
{
struct svc_serv *serv;
- unsigned int npools = svc_pool_map_init();
+ unsigned int npools = svc_pool_map_get();
serv = __svc_create(prog, bufsize, npools, shutdown);
if (serv != NULL) {
serv->sv_function = func;
- serv->sv_kill_signal = sig;
serv->sv_module = mod;
}
return serv;
}
+EXPORT_SYMBOL_GPL(svc_create_pooled);
/*
- * Destroy an RPC service. Should be called with the BKL held
+ * Destroy an RPC service. Should be called with appropriate locking to
+ * protect the sv_nrthreads, sv_permsocks and sv_tempsocks.
*/
void
svc_destroy(struct svc_serv *serv)
{
- struct svc_sock *svsk;
-
- dprintk("RPC: svc_destroy(%s, %d)\n",
+ dprintk("svc: svc_destroy(%s, %d)\n",
serv->sv_program->pg_name,
serv->sv_nrthreads);
del_timer_sync(&serv->sv_temptimer);
- while (!list_empty(&serv->sv_tempsocks)) {
- svsk = list_entry(serv->sv_tempsocks.next,
- struct svc_sock,
- sk_list);
- svc_delete_socket(svsk);
- }
+ svc_close_all(&serv->sv_tempsocks);
+
if (serv->sv_shutdown)
serv->sv_shutdown(serv);
- while (!list_empty(&serv->sv_permsocks)) {
- svsk = list_entry(serv->sv_permsocks.next,
- struct svc_sock,
- sk_list);
- svc_delete_socket(svsk);
- }
-
+ svc_close_all(&serv->sv_permsocks);
+
+ BUG_ON(!list_empty(&serv->sv_permsocks));
+ BUG_ON(!list_empty(&serv->sv_tempsocks));
+
cache_clean_deferred(serv);
- /* Unregister service with the portmapper */
- svc_register(serv, 0, 0);
+ if (svc_serv_is_pooled(serv))
+ svc_pool_map_put();
+
+#if defined(CONFIG_NFS_V4_1)
+ svc_sock_destroy(serv->bc_xprt);
+#endif /* CONFIG_NFS_V4_1 */
+
+ svc_unregister(serv);
kfree(serv->sv_pools);
kfree(serv);
}
+EXPORT_SYMBOL_GPL(svc_destroy);
/*
* Allocate an RPC server's buffer space.
static int
svc_init_buffer(struct svc_rqst *rqstp, unsigned int size)
{
- int pages;
- int arghi;
-
+ unsigned int pages, arghi;
+
pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply.
* We assume one is at most one page
*/
rqstp->rq_pages[arghi++] = p;
pages--;
}
- return ! pages;
+ return pages == 0;
}
/*
static void
svc_release_buffer(struct svc_rqst *rqstp)
{
- int i;
- for (i=0; i<ARRAY_SIZE(rqstp->rq_pages); i++)
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++)
if (rqstp->rq_pages[i])
put_page(rqstp->rq_pages[i]);
}
-/*
- * Create a thread in the given pool. Caller must hold BKL.
- * On a NUMA or SMP machine, with a multi-pool serv, the thread
- * will be restricted to run on the cpus belonging to the pool.
- */
-static int
-__svc_create_thread(svc_thread_fn func, struct svc_serv *serv,
- struct svc_pool *pool)
+struct svc_rqst *
+svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool)
{
struct svc_rqst *rqstp;
- int error = -ENOMEM;
- int have_oldmask = 0;
- cpumask_t oldmask;
rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
- goto out;
+ goto out_enomem;
init_waitqueue_head(&rqstp->rq_wait);
- if (!(rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
- || !(rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
- || !svc_init_buffer(rqstp, serv->sv_max_mesg))
- goto out_thread;
-
serv->sv_nrthreads++;
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads++;
rqstp->rq_server = serv;
rqstp->rq_pool = pool;
- if (serv->sv_nrpools > 1)
- have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask);
-
- error = kernel_thread((int (*)(void *)) func, rqstp, 0);
+ rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
+ if (!rqstp->rq_argp)
+ goto out_thread;
- if (have_oldmask)
- set_cpus_allowed(current, oldmask);
+ rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
+ if (!rqstp->rq_resp)
+ goto out_thread;
- if (error < 0)
+ if (!svc_init_buffer(rqstp, serv->sv_max_mesg))
goto out_thread;
- svc_sock_update_bufs(serv);
- error = 0;
-out:
- return error;
+ return rqstp;
out_thread:
svc_exit_thread(rqstp);
- goto out;
-}
-
-/*
- * Create a thread in the default pool. Caller must hold BKL.
- */
-int
-svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
-{
- return __svc_create_thread(func, serv, &serv->sv_pools[0]);
+out_enomem:
+ return ERR_PTR(-ENOMEM);
}
+EXPORT_SYMBOL_GPL(svc_prepare_thread);
/*
* Choose a pool in which to create a new thread, for svc_set_num_threads
if (pool != NULL)
return pool;
- return &serv->sv_pools[(*state)++ % serv->sv_nrpools];
+ return &serv->sv_pools[(*state)++ % serv->sv_nrpools];
}
/*
spin_lock_bh(&pool->sp_lock);
} else {
/* choose a pool in round-robin fashion */
- for (i = 0; i < serv->sv_nrpools; i++) {
- pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&pool->sp_all_threads))
- goto found_pool;
+ if (!list_empty(&pool->sp_all_threads))
+ goto found_pool;
spin_unlock_bh(&pool->sp_lock);
- }
+ }
return NULL;
}
rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
list_del_init(&rqstp->rq_all);
task = rqstp->rq_task;
- }
+ }
spin_unlock_bh(&pool->sp_lock);
return task;
* of threads the given number. If `pool' is non-NULL, applies
* only to threads in that pool, otherwise round-robins between
* all pools. Must be called with a svc_get() reference and
- * the BKL held.
+ * the BKL or another lock to protect access to svc_serv fields.
*
* Destroying threads relies on the service threads filling in
* rqstp->rq_task, which only the nfs ones do. Assumes the serv
int
svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
- struct task_struct *victim;
+ struct svc_rqst *rqstp;
+ struct task_struct *task;
+ struct svc_pool *chosen_pool;
int error = 0;
unsigned int state = serv->sv_nrthreads-1;
/* create new threads */
while (nrservs > 0) {
nrservs--;
+ chosen_pool = choose_pool(serv, pool, &state);
+
+ rqstp = svc_prepare_thread(serv, chosen_pool);
+ if (IS_ERR(rqstp)) {
+ error = PTR_ERR(rqstp);
+ break;
+ }
+
__module_get(serv->sv_module);
- error = __svc_create_thread(serv->sv_function, serv,
- choose_pool(serv, pool, &state));
- if (error < 0) {
+ task = kthread_create(serv->sv_function, rqstp, serv->sv_name);
+ if (IS_ERR(task)) {
+ error = PTR_ERR(task);
module_put(serv->sv_module);
+ svc_exit_thread(rqstp);
break;
}
+
+ rqstp->rq_task = task;
+ if (serv->sv_nrpools > 1)
+ svc_pool_map_set_cpumask(task, chosen_pool->sp_id);
+
+ svc_sock_update_bufs(serv);
+ wake_up_process(task);
}
/* destroy old threads */
while (nrservs < 0 &&
- (victim = choose_victim(serv, pool, &state)) != NULL) {
- send_sig(serv->sv_kill_signal, victim, 1);
+ (task = choose_victim(serv, pool, &state)) != NULL) {
+ send_sig(SIGINT, task, 1);
nrservs++;
}
return error;
}
+EXPORT_SYMBOL_GPL(svc_set_num_threads);
/*
- * Called from a server thread as it's exiting. Caller must hold BKL.
+ * Called from a server thread as it's exiting. Caller must hold the BKL or
+ * the "service mutex", whichever is appropriate for the service.
*/
void
svc_exit_thread(struct svc_rqst *rqstp)
if (serv)
svc_destroy(serv);
}
+EXPORT_SYMBOL_GPL(svc_exit_thread);
/*
- * 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)
+{
+ const struct sockaddr_in sin = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_ANY),
+ .sin_port = htons(port),
+ };
+ const char *netid;
+ int error;
+
+ switch (protocol) {
+ case IPPROTO_UDP:
+ netid = RPCBIND_NETID_UDP;
+ break;
+ case IPPROTO_TCP:
+ netid = RPCBIND_NETID_TCP;
+ break;
+ default:
+ return -ENOPROTOOPT;
+ }
+
+ error = rpcb_v4_register(program, version,
+ (const struct sockaddr *)&sin, netid);
+
+ /*
+ * User space didn't support rpcbind v4, so retry this
+ * registration request with the legacy rpcbind v2 protocol.
+ */
+ if (error == -EPROTONOSUPPORT)
+ error = rpcb_register(program, version, protocol, port);
+
+ return error;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+/*
+ * 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)
+{
+ const struct sockaddr_in6 sin6 = {
+ .sin6_family = AF_INET6,
+ .sin6_addr = IN6ADDR_ANY_INIT,
+ .sin6_port = htons(port),
+ };
+ const char *netid;
+ int error;
+
+ switch (protocol) {
+ case IPPROTO_UDP:
+ netid = RPCBIND_NETID_UDP6;
+ break;
+ case IPPROTO_TCP:
+ netid = RPCBIND_NETID_TCP6;
+ break;
+ default:
+ return -ENOPROTOOPT;
+ }
+
+ error = rpcb_v4_register(program, version,
+ (const struct sockaddr *)&sin6, netid);
+
+ /*
+ * User space didn't support rpcbind version 4, so we won't
+ * use a PF_INET6 listener.
+ */
+ if (error == -EPROTONOSUPPORT)
+ error = -EAFNOSUPPORT;
+
+ return error;
+}
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+
+/*
+ * 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 char *progname,
+ const u32 program, const u32 version,
+ const int family,
+ const unsigned short protocol,
+ const unsigned short port)
+{
+ int error = -EAFNOSUPPORT;
+
+ switch (family) {
+ case PF_INET:
+ error = __svc_rpcb_register4(program, version,
+ protocol, port);
+ break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case PF_INET6:
+ error = __svc_rpcb_register6(program, version,
+ protocol, port);
+#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+ }
+
+ if (error < 0)
+ printk(KERN_WARNING "svc: failed to register %sv%u RPC "
+ "service (errno %d).\n", progname, version, -error);
+ return error;
+}
+
+/**
+ * svc_register - register an RPC service with the local portmapper
+ * @serv: svc_serv struct for the service to register
+ * @family: protocol family of service's listener socket
+ * @proto: transport protocol number to advertise
+ * @port: port to advertise
+ *
+ * Service is registered for any address in the passed-in protocol family
+ */
+int svc_register(const struct svc_serv *serv, const int family,
+ const unsigned short proto, const unsigned short port)
{
struct svc_program *progp;
- unsigned long flags;
- int i, error = 0, dummy;
+ unsigned int i;
+ 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("RPC: 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,
+ family,
progp->pg_vers[i]->vs_hidden?
" (but not telling portmap)" : "");
if (progp->pg_vers[i]->vs_hidden)
continue;
- error = rpc_register(progp->pg_prog, i, proto, port, &dummy);
+ error = __svc_register(progp->pg_name, progp->pg_prog,
+ i, family, proto, port);
if (error < 0)
break;
- if (port && !dummy) {
- error = -EACCES;
- break;
- }
}
}
- if (!port) {
- spin_lock_irqsave(¤t->sighand->siglock, flags);
- recalc_sigpending();
- spin_unlock_irqrestore(¤t->sighand->siglock, flags);
+ return error;
+}
+
+/*
+ * If user space is running rpcbind, it should take the v4 UNSET
+ * and clear everything for this [program, version]. If user space
+ * is running portmap, it will reject the v4 UNSET, but won't have
+ * any "inet6" entries anyway. So a PMAP_UNSET should be sufficient
+ * in this case to clear all existing entries for [program, version].
+ */
+static void __svc_unregister(const u32 program, const u32 version,
+ const char *progname)
+{
+ int error;
+
+ error = rpcb_v4_register(program, version, NULL, "");
+
+ /*
+ * User space didn't support rpcbind v4, so retry this
+ * request with the legacy rpcbind v2 protocol.
+ */
+ if (error == -EPROTONOSUPPORT)
+ error = rpcb_register(program, version, 0, 0);
+
+ dprintk("svc: %s(%sv%u), error %d\n",
+ __func__, progname, version, error);
+}
+
+/*
+ * 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(¤t->sighand->siglock, flags);
+ recalc_sigpending();
+ spin_unlock_irqrestore(¤t->sighand->siglock, flags);
}
/*
- * Process the RPC request.
+ * Printk the given error with the address of the client that caused it.
*/
-int
-svc_process(struct svc_rqst *rqstp)
+static int
+__attribute__ ((format (printf, 2, 3)))
+svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
+{
+ va_list args;
+ int r;
+ char buf[RPC_MAX_ADDRBUFLEN];
+
+ if (!net_ratelimit())
+ return 0;
+
+ printk(KERN_WARNING "svc: %s: ",
+ svc_print_addr(rqstp, buf, sizeof(buf)));
+
+ va_start(args, fmt);
+ r = vprintk(fmt, args);
+ va_end(args);
+
+ return r;
+}
+
+/*
+ * Common routine for processing the RPC request.
+ */
+static int
+svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
{
struct svc_program *progp;
struct svc_version *versp = NULL; /* compiler food */
struct svc_procedure *procp = NULL;
- struct kvec * argv = &rqstp->rq_arg.head[0];
- struct kvec * resv = &rqstp->rq_res.head[0];
struct svc_serv *serv = rqstp->rq_server;
kxdrproc_t xdr;
__be32 *statp;
- u32 dir, prog, vers, proc;
+ u32 prog, vers, proc;
__be32 auth_stat, rpc_stat;
int auth_res;
__be32 *reply_statp;
if (argv->iov_len < 6*4)
goto err_short_len;
- /* setup response xdr_buf.
- * Initially it has just one page
- */
- rqstp->rq_resused = 1;
- resv->iov_base = page_address(rqstp->rq_respages[0]);
- resv->iov_len = 0;
- rqstp->rq_res.pages = rqstp->rq_respages + 1;
- rqstp->rq_res.len = 0;
- rqstp->rq_res.page_base = 0;
- rqstp->rq_res.page_len = 0;
- rqstp->rq_res.buflen = PAGE_SIZE;
- rqstp->rq_res.tail[0].iov_base = NULL;
- rqstp->rq_res.tail[0].iov_len = 0;
/* Will be turned off only in gss privacy case: */
- rqstp->rq_sendfile_ok = 1;
- /* tcp needs a space for the record length... */
- if (rqstp->rq_prot == IPPROTO_TCP)
- svc_putnl(resv, 0);
+ rqstp->rq_splice_ok = 1;
+ /* Will be turned off only when NFSv4 Sessions are used */
+ rqstp->rq_usedeferral = 1;
+
+ /* Setup reply header */
+ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
- rqstp->rq_xid = svc_getu32(argv);
svc_putu32(resv, rqstp->rq_xid);
- dir = svc_getnl(argv);
vers = svc_getnl(argv);
/* First words of reply: */
svc_putnl(resv, 1); /* REPLY */
- if (dir != 0) /* direction != CALL */
- goto err_bad_dir;
if (vers != 2) /* RPC version number */
goto err_bad_rpc;
case SVC_OK:
break;
case SVC_GARBAGE:
- rpc_stat = rpc_garbage_args;
- goto err_bad;
+ goto err_garbage;
case SVC_SYSERR:
rpc_stat = rpc_system_err;
goto err_bad;
procp = versp->vs_proc + proc;
if (proc >= versp->vs_nproc || !procp->pc_func)
goto err_bad_proc;
- rqstp->rq_server = serv;
rqstp->rq_procinfo = procp;
/* Syntactic check complete */
memset(rqstp->rq_argp, 0, procp->pc_argsize);
memset(rqstp->rq_resp, 0, procp->pc_ressize);
- /* un-reserve some of the out-queue now that we have a
+ /* un-reserve some of the out-queue now that we have a
* better idea of reply size
*/
if (procp->pc_xdrressize)
- svc_reserve(rqstp, procp->pc_xdrressize<<2);
+ svc_reserve_auth(rqstp, procp->pc_xdrressize<<2);
/* Call the function that processes the request. */
if (!versp->vs_dispatch) {
sendit:
if (svc_authorise(rqstp))
goto dropit;
- return svc_send(rqstp);
+ return 1; /* Caller can now send it */
dropit:
svc_authorise(rqstp); /* doesn't hurt to call this twice */
return 0;
err_short_len:
-#ifdef RPC_PARANOIA
- printk("svc: short len %Zd, dropping request\n", argv->iov_len);
-#endif
- goto dropit; /* drop request */
+ svc_printk(rqstp, "short len %Zd, dropping request\n",
+ argv->iov_len);
-err_bad_dir:
-#ifdef RPC_PARANOIA
- printk("svc: bad direction %d, dropping request\n", dir);
-#endif
- serv->sv_stats->rpcbadfmt++;
goto dropit; /* drop request */
err_bad_rpc:
goto sendit;
err_bad_vers:
-#ifdef RPC_PARANOIA
- printk("svc: unknown version (%d)\n", vers);
-#endif
+ svc_printk(rqstp, "unknown version (%d for prog %d, %s)\n",
+ vers, prog, progp->pg_name);
+
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, RPC_PROG_MISMATCH);
svc_putnl(resv, progp->pg_lovers);
goto sendit;
err_bad_proc:
-#ifdef RPC_PARANOIA
- printk("svc: unknown procedure (%d)\n", proc);
-#endif
+ svc_printk(rqstp, "unknown procedure (%d)\n", proc);
+
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, RPC_PROC_UNAVAIL);
goto sendit;
err_garbage:
-#ifdef RPC_PARANOIA
- printk("svc: failed to decode args\n");
-#endif
+ svc_printk(rqstp, "failed to decode args\n");
+
rpc_stat = rpc_garbage_args;
err_bad:
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, ntohl(rpc_stat));
goto sendit;
}
+EXPORT_SYMBOL_GPL(svc_process);
+
+/*
+ * Process the RPC request.
+ */
+int
+svc_process(struct svc_rqst *rqstp)
+{
+ struct kvec *argv = &rqstp->rq_arg.head[0];
+ struct kvec *resv = &rqstp->rq_res.head[0];
+ struct svc_serv *serv = rqstp->rq_server;
+ u32 dir;
+ int error;
+
+ /*
+ * Setup response xdr_buf.
+ * Initially it has just one page
+ */
+ rqstp->rq_resused = 1;
+ resv->iov_base = page_address(rqstp->rq_respages[0]);
+ resv->iov_len = 0;
+ rqstp->rq_res.pages = rqstp->rq_respages + 1;
+ rqstp->rq_res.len = 0;
+ rqstp->rq_res.page_base = 0;
+ rqstp->rq_res.page_len = 0;
+ rqstp->rq_res.buflen = PAGE_SIZE;
+ rqstp->rq_res.tail[0].iov_base = NULL;
+ rqstp->rq_res.tail[0].iov_len = 0;
+
+ rqstp->rq_xid = svc_getu32(argv);
+
+ dir = svc_getnl(argv);
+ if (dir != 0) {
+ /* direction != CALL */
+ svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
+ serv->sv_stats->rpcbadfmt++;
+ svc_drop(rqstp);
+ return 0;
+ }
+
+ error = svc_process_common(rqstp, argv, resv);
+ if (error <= 0)
+ return error;
+
+ return svc_send(rqstp);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * Process a backchannel RPC request that arrived over an existing
+ * outbound connection
+ */
+int
+bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
+ struct svc_rqst *rqstp)
+{
+ struct kvec *argv = &rqstp->rq_arg.head[0];
+ struct kvec *resv = &rqstp->rq_res.head[0];
+ int error;
+
+ /* Build the svc_rqst used by the common processing routine */
+ rqstp->rq_xprt = serv->bc_xprt;
+ rqstp->rq_xid = req->rq_xid;
+ rqstp->rq_prot = req->rq_xprt->prot;
+ rqstp->rq_server = serv;
+
+ rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
+ memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
+ memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg));
+ memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res));
+
+ /* reset result send buffer "put" position */
+ resv->iov_len = 0;
+
+ if (rqstp->rq_prot != IPPROTO_TCP) {
+ printk(KERN_ERR "No support for Non-TCP transports!\n");
+ BUG();
+ }
+
+ /*
+ * Skip the next two words because they've already been
+ * processed in the trasport
+ */
+ svc_getu32(argv); /* XID */
+ svc_getnl(argv); /* CALLDIR */
+
+ error = svc_process_common(rqstp, argv, resv);
+ if (error <= 0)
+ return error;
+
+ memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
+ return bc_send(req);
+}
+EXPORT_SYMBOL(bc_svc_process);
+#endif /* CONFIG_NFS_V4_1 */
/*
* Return (transport-specific) limit on the rpc payload.
*/
u32 svc_max_payload(const struct svc_rqst *rqstp)
{
- int max = RPCSVC_MAXPAYLOAD_TCP;
+ u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload;
- if (rqstp->rq_sock->sk_sock->type == SOCK_DGRAM)
- max = RPCSVC_MAXPAYLOAD_UDP;
if (rqstp->rq_server->sv_max_payload < max)
max = rqstp->rq_server->sv_max_payload;
return max;