X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fsunrpc%2Fsvc.c;h=538ca433a56cc72e2bae671e2b74174cb8efb3a8;hb=3705e11a21bcdffe7422ee7870e1b23fe4ac70f4;hp=d43cf8ddff67c13bd0646c728b618f2b39863fc3;hpb=3f9b48a7584851997702cdc3f58e7811b5546397;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d43cf8d..538ca43 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -18,15 +18,19 @@ #include #include #include +#include #include #include #include #include #include +#include #define RPCDBG_FACILITY RPCDBG_SVCDSP +static void svc_unregister(const struct svc_serv *serv); + #define svc_serv_is_pooled(serv) ((serv)->sv_function) /* @@ -121,7 +125,7 @@ svc_pool_map_choose_mode(void) { 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 @@ -291,15 +295,14 @@ svc_pool_map_put(void) /* - * 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 = m->pool_to[pidx]; /* * The caller checks for sv_nrpools > 1, which @@ -307,26 +310,16 @@ svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) */ BUG_ON(m->count == 0); - switch (m->mode) - { - default: - return 0; + switch (m->mode) { case SVC_POOL_PERCPU: { - unsigned int cpu = m->pool_to[pidx]; - - *oldmask = current->cpus_allowed; - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - return 1; + set_cpus_allowed_ptr(task, cpumask_of(node)); + break; } case SVC_POOL_PERNODE: { - unsigned int node = m->pool_to[pidx]; - node_to_cpumask_ptr(nodecpumask, node); - - *oldmask = current->cpus_allowed; - set_cpus_allowed_ptr(current, nodecpumask); - return 1; + set_cpus_allowed_ptr(task, cpumask_of_node(node)); + break; } } } @@ -366,7 +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)) + void (*shutdown)(struct svc_serv *serv)) { struct svc_serv *serv; unsigned int vers; @@ -425,25 +418,24 @@ __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)) + void (*shutdown)(struct svc_serv *serv)) { return __svc_create(prog, bufsize, /*npools*/1, shutdown); } -EXPORT_SYMBOL(svc_create); +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_get(); @@ -452,16 +444,16 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize, if (serv != NULL) { serv->sv_function = func; - serv->sv_kill_signal = sig; serv->sv_module = mod; } return serv; } -EXPORT_SYMBOL(svc_create_pooled); +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) @@ -495,12 +487,15 @@ 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); +#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(svc_destroy); +EXPORT_SYMBOL_GPL(svc_destroy); /* * Allocate an RPC server's buffer space. @@ -575,47 +570,7 @@ out_thread: out_enomem: return ERR_PTR(-ENOMEM); } -EXPORT_SYMBOL(svc_prepare_thread); - -/* - * 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 *rqstp; - int error = -ENOMEM; - int have_oldmask = 0; - cpumask_t uninitialized_var(oldmask); - - rqstp = svc_prepare_thread(serv, pool); - if (IS_ERR(rqstp)) { - error = PTR_ERR(rqstp); - goto out; - } - - if (serv->sv_nrpools > 1) - have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask); - - error = kernel_thread((int (*)(void *)) func, rqstp, 0); - - if (have_oldmask) - set_cpus_allowed_ptr(current, &oldmask); - - if (error < 0) - goto out_thread; - svc_sock_update_bufs(serv); - error = 0; -out: - return error; - -out_thread: - svc_exit_thread(rqstp); - goto out; -} +EXPORT_SYMBOL_GPL(svc_prepare_thread); /* * Choose a pool in which to create a new thread, for svc_set_num_threads @@ -674,7 +629,7 @@ found_pool: * 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 @@ -686,7 +641,9 @@ found_pool: 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; @@ -702,27 +659,44 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) /* 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(svc_set_num_threads); +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) @@ -746,57 +720,234 @@ svc_exit_thread(struct svc_rqst *rqstp) if (serv) svc_destroy(serv); } -EXPORT_SYMBOL(svc_exit_thread); +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; 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, + 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_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); } /* @@ -824,20 +975,18 @@ svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) } /* - * Process the RPC request. + * Common routine for processing the RPC request. */ -int -svc_process(struct svc_rqst *rqstp) +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; @@ -847,36 +996,21 @@ svc_process(struct svc_rqst *rqstp) 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_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; @@ -932,7 +1066,6 @@ svc_process(struct svc_rqst *rqstp) 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 */ @@ -970,8 +1103,9 @@ svc_process(struct svc_rqst *rqstp) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; } - if (*statp == rpc_success && (xdr = procp->pc_encode) - && !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { + if (*statp == rpc_success && + (xdr = procp->pc_encode) && + !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { dprintk("svc: failed to encode reply\n"); /* serv->sv_stats->rpcsystemerr++; */ *statp = rpc_system_err; @@ -1000,7 +1134,7 @@ svc_process(struct svc_rqst *rqstp) 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 */ @@ -1014,12 +1148,6 @@ err_short_len: goto dropit; /* drop request */ -err_bad_dir: - svc_printk(rqstp, "bad direction %d, dropping request\n", dir); - - serv->sv_stats->rpcbadfmt++; - goto dropit; /* drop request */ - err_bad_rpc: serv->sv_stats->rpcbadfmt++; svc_putnl(resv, 1); /* REJECT */ @@ -1070,7 +1198,101 @@ err_bad: svc_putnl(resv, ntohl(rpc_stat)); goto sendit; } -EXPORT_SYMBOL(svc_process); +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.