diff options
Diffstat (limited to 'net/sunrpc/svc.c')
| -rw-r--r-- | net/sunrpc/svc.c | 278 |
1 files changed, 182 insertions, 96 deletions
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6359c42c494..5de6801cd92 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -30,7 +30,7 @@ #define RPCDBG_FACILITY RPCDBG_SVCDSP -static void svc_unregister(const struct svc_serv *serv); +static void svc_unregister(const struct svc_serv *serv, struct net *net); #define svc_serv_is_pooled(serv) ((serv)->sv_function) @@ -167,6 +167,7 @@ svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) fail_free: kfree(m->to_pool); + m->to_pool = NULL; fail: return -ENOMEM; } @@ -285,9 +286,10 @@ svc_pool_map_put(void) mutex_lock(&svc_pool_map_mutex); if (!--m->count) { - m->mode = SVC_POOL_DEFAULT; kfree(m->to_pool); + m->to_pool = NULL; kfree(m->pool_to); + m->pool_to = NULL; m->npools = 0; } @@ -295,6 +297,18 @@ svc_pool_map_put(void) } +static int svc_pool_map_get_node(unsigned int pidx) +{ + const struct svc_pool_map *m = &svc_pool_map; + + if (m->count) { + if (m->mode == SVC_POOL_PERCPU) + return cpu_to_node(m->pool_to[pidx]); + if (m->mode == SVC_POOL_PERNODE) + return m->pool_to[pidx]; + } + return NUMA_NO_NODE; +} /* * Set the given thread's cpus_allowed mask so that it * will only run on cpus in the given pool. @@ -309,7 +323,9 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) * The caller checks for sv_nrpools > 1, which * implies that we've been initialized. */ - BUG_ON(m->count == 0); + WARN_ON_ONCE(m->count == 0); + if (m->count == 0) + return; switch (m->mode) { case SVC_POOL_PERCPU: @@ -354,13 +370,58 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu) return &serv->sv_pools[pidx % serv->sv_nrpools]; } +int svc_rpcb_setup(struct svc_serv *serv, struct net *net) +{ + int err; + + err = rpcb_create_local(net); + if (err) + return err; + + /* Remove any stale portmap registrations */ + svc_unregister(serv, net); + return 0; +} +EXPORT_SYMBOL_GPL(svc_rpcb_setup); + +void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net) +{ + svc_unregister(serv, net); + rpcb_put_local(net); +} +EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); + +static int svc_uses_rpcbind(struct svc_serv *serv) +{ + struct svc_program *progp; + unsigned int i; + + 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 == 0) + return 1; + } + } + + return 0; +} + +int svc_bind(struct svc_serv *serv, struct net *net) +{ + if (!svc_uses_rpcbind(serv)) + return 0; + return svc_rpcb_setup(serv, net); +} +EXPORT_SYMBOL_GPL(svc_bind); /* * Create an RPC service */ 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 net *net)) { struct svc_serv *serv; unsigned int vers; @@ -419,15 +480,15 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, spin_lock_init(&pool->sp_lock); } - /* Remove any stale portmap registrations */ - svc_unregister(serv); + if (svc_uses_rpcbind(serv) && (!serv->sv_shutdown)) + serv->sv_shutdown = svc_rpcb_cleanup; 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, struct net *net)) { return __svc_create(prog, bufsize, /*npools*/1, shutdown); } @@ -435,7 +496,7 @@ EXPORT_SYMBOL_GPL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - void (*shutdown)(struct svc_serv *serv), + void (*shutdown)(struct svc_serv *serv, struct net *net), svc_thread_fn func, struct module *mod) { struct svc_serv *serv; @@ -452,6 +513,15 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize, } EXPORT_SYMBOL_GPL(svc_create_pooled); +void svc_shutdown_net(struct svc_serv *serv, struct net *net) +{ + svc_close_net(serv, net); + + if (serv->sv_shutdown) + serv->sv_shutdown(serv, net); +} +EXPORT_SYMBOL_GPL(svc_shutdown_net); + /* * Destroy an RPC service. Should be called with appropriate locking to * protect the sv_nrthreads, sv_permsocks and sv_tempsocks. @@ -473,13 +543,10 @@ svc_destroy(struct svc_serv *serv) del_timer_sync(&serv->sv_temptimer); - svc_close_all(&serv->sv_tempsocks); - - if (serv->sv_shutdown) - serv->sv_shutdown(serv); - - svc_close_all(&serv->sv_permsocks); - + /* + * The last user is gone and thus all sockets have to be destroyed to + * the point. Check this. + */ BUG_ON(!list_empty(&serv->sv_permsocks)); BUG_ON(!list_empty(&serv->sv_tempsocks)); @@ -488,11 +555,6 @@ svc_destroy(struct svc_serv *serv) 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); } @@ -503,7 +565,7 @@ EXPORT_SYMBOL_GPL(svc_destroy); * We allocate pages and place them in rq_argpages. */ static int -svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) +svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) { unsigned int pages, arghi; @@ -515,9 +577,11 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size) * We assume one is at most one page */ arghi = 0; - BUG_ON(pages > RPCSVC_MAXPAGES); + WARN_ON_ONCE(pages > RPCSVC_MAXPAGES); + if (pages > RPCSVC_MAXPAGES) + pages = RPCSVC_MAXPAGES; while (pages) { - struct page *p = alloc_page(GFP_KERNEL); + struct page *p = alloc_pages_node(node, GFP_KERNEL, 0); if (!p) break; rqstp->rq_pages[arghi++] = p; @@ -540,11 +604,11 @@ svc_release_buffer(struct svc_rqst *rqstp) } struct svc_rqst * -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool) +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; - rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL); + rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) goto out_enomem; @@ -558,15 +622,15 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool) rqstp->rq_server = serv; rqstp->rq_pool = pool; - rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL); + rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) goto out_thread; - rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL); + rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) goto out_thread; - if (!svc_init_buffer(rqstp, serv->sv_max_mesg)) + if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) goto out_thread; return rqstp; @@ -633,8 +697,8 @@ found_pool: * Create or destroy enough new threads to make the number * 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 or another lock to protect access to svc_serv fields. + * all pools. Caller must ensure that mutual exclusion between this and + * server startup or shutdown. * * Destroying threads relies on the service threads filling in * rqstp->rq_task, which only the nfs ones do. Assumes the serv @@ -651,6 +715,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) struct svc_pool *chosen_pool; int error = 0; unsigned int state = serv->sv_nrthreads-1; + int node; if (pool == NULL) { /* The -1 assumes caller has done a svc_get() */ @@ -666,14 +731,16 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) nrservs--; chosen_pool = choose_pool(serv, pool, &state); - rqstp = svc_prepare_thread(serv, chosen_pool); + node = svc_pool_map_get_node(chosen_pool->sp_id); + rqstp = svc_prepare_thread(serv, chosen_pool, node); if (IS_ERR(rqstp)) { error = PTR_ERR(rqstp); break; } __module_get(serv->sv_module); - task = kthread_create(serv->sv_function, rqstp, serv->sv_name); + task = kthread_create_on_node(serv->sv_function, rqstp, + node, "%s", serv->sv_name); if (IS_ERR(task)) { error = PTR_ERR(task); module_put(serv->sv_module); @@ -737,7 +804,8 @@ EXPORT_SYMBOL_GPL(svc_exit_thread); * Returns zero on success; a negative errno value is returned * if any error occurs. */ -static int __svc_rpcb_register4(const u32 program, const u32 version, +static int __svc_rpcb_register4(struct net *net, const u32 program, + const u32 version, const unsigned short protocol, const unsigned short port) { @@ -760,7 +828,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, return -ENOPROTOOPT; } - error = rpcb_v4_register(program, version, + error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin, netid); /* @@ -768,12 +836,12 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, * registration request with the legacy rpcbind v2 protocol. */ if (error == -EPROTONOSUPPORT) - error = rpcb_register(program, version, protocol, port); + error = rpcb_register(net, program, version, protocol, port); return error; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) /* * Register an "inet6" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. @@ -784,7 +852,8 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, * 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, +static int __svc_rpcb_register6(struct net *net, const u32 program, + const u32 version, const unsigned short protocol, const unsigned short port) { @@ -807,7 +876,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, return -ENOPROTOOPT; } - error = rpcb_v4_register(program, version, + error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin6, netid); /* @@ -819,7 +888,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, return error; } -#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ +#endif /* IS_ENABLED(CONFIG_IPV6) */ /* * Register a kernel RPC service via rpcbind version 4. @@ -827,7 +896,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, * Returns zero on success; a negative errno value is returned * if any error occurs. */ -static int __svc_register(const char *progname, +static int __svc_register(struct net *net, const char *progname, const u32 program, const u32 version, const int family, const unsigned short protocol, @@ -837,43 +906,46 @@ static int __svc_register(const char *progname, switch (family) { case PF_INET: - error = __svc_rpcb_register4(program, version, + error = __svc_rpcb_register4(net, program, version, protocol, port); break; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case PF_INET6: - error = __svc_rpcb_register6(program, version, + error = __svc_rpcb_register6(net, program, version, protocol, port); -#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ +#endif } - 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 + * @net: net namespace 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) +int svc_register(const struct svc_serv *serv, struct net *net, + const int family, const unsigned short proto, + const unsigned short port) { struct svc_program *progp; + struct svc_version *vers; unsigned int i; int error = 0; - BUG_ON(proto == 0 && port == 0); + WARN_ON_ONCE(proto == 0 && port == 0); + if (proto == 0 && port == 0) + return -EINVAL; for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { - if (progp->pg_vers[i] == NULL) + vers = progp->pg_vers[i]; + if (vers == NULL) continue; dprintk("svc: svc_register(%sv%d, %s, %u, %u)%s\n", @@ -882,16 +954,26 @@ int svc_register(const struct svc_serv *serv, const int family, proto == IPPROTO_UDP? "udp" : "tcp", port, family, - progp->pg_vers[i]->vs_hidden? - " (but not telling portmap)" : ""); + vers->vs_hidden ? + " (but not telling portmap)" : ""); - if (progp->pg_vers[i]->vs_hidden) + if (vers->vs_hidden) continue; - error = __svc_register(progp->pg_name, progp->pg_prog, + error = __svc_register(net, progp->pg_name, progp->pg_prog, i, family, proto, port); - if (error < 0) + + if (vers->vs_rpcb_optnl) { + error = 0; + continue; + } + + if (error < 0) { + printk(KERN_WARNING "svc: failed to register " + "%sv%u RPC service (errno %d).\n", + progp->pg_name, i, -error); break; + } } } @@ -905,19 +987,19 @@ int svc_register(const struct svc_serv *serv, const int family, * 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, +static void __svc_unregister(struct net *net, const u32 program, const u32 version, const char *progname) { int error; - error = rpcb_v4_register(program, version, NULL, ""); + error = rpcb_v4_register(net, 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); + error = rpcb_register(net, program, version, 0, 0); dprintk("svc: %s(%sv%u), error %d\n", __func__, progname, version, error); @@ -931,7 +1013,7 @@ static void __svc_unregister(const u32 program, const u32 version, * 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) +static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct svc_program *progp; unsigned long flags; @@ -946,7 +1028,9 @@ static void svc_unregister(const struct svc_serv *serv) if (progp->pg_vers[i]->vs_hidden) continue; - __svc_unregister(progp->pg_prog, i, progp->pg_name); + dprintk("svc: attempting to unregister %sv%u\n", + progp->pg_name, i); + __svc_unregister(net, progp->pg_prog, i, progp->pg_name); } } @@ -956,28 +1040,28 @@ static void svc_unregister(const struct svc_serv *serv) } /* - * Printk the given error with the address of the client that caused it. + * dprintk the given error with the address of the client that caused it. */ -static int -__attribute__ ((format (printf, 2, 3))) -svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) +#ifdef RPC_DEBUG +static __printf(2, 3) +void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { + struct va_format vaf; va_list args; - int r; char buf[RPC_MAX_ADDRBUFLEN]; - if (!net_ratelimit()) - return 0; + va_start(args, fmt); - printk(KERN_WARNING "svc: %s: ", - svc_print_addr(rqstp, buf, sizeof(buf))); + vaf.fmt = fmt; + vaf.va = &args; - va_start(args, fmt); - r = vprintk(fmt, args); - va_end(args); + dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); - return r; + va_end(args); } +#else +static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} +#endif /* * Common routine for processing the RPC request. @@ -1005,6 +1089,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) rqstp->rq_splice_ok = 1; /* Will be turned off only when NFSv4 Sessions are used */ rqstp->rq_usedeferral = 1; + rqstp->rq_dropme = false; /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); @@ -1028,8 +1113,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) rqstp->rq_vers = vers = svc_getnl(argv); /* version number */ rqstp->rq_proc = proc = svc_getnl(argv); /* procedure number */ - progp = serv->sv_program; - for (progp = serv->sv_program; progp; progp = progp->pg_next) if (prog == progp->pg_prog) break; @@ -1106,7 +1189,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); /* Encode reply */ - if (*statp == rpc_drop_reply) { + if (rqstp->rq_dropme) { if (procp->pc_release) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; @@ -1147,7 +1230,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); - svc_drop(rqstp); return 0; err_short_len: @@ -1218,13 +1300,12 @@ svc_process(struct svc_rqst *rqstp) 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; + rqstp->rq_next_page = &rqstp->rq_respages[1]; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; rqstp->rq_res.pages = rqstp->rq_respages + 1; @@ -1246,14 +1327,16 @@ svc_process(struct svc_rqst *rqstp) return 0; } - error = svc_process_common(rqstp, argv, resv); - if (error <= 0) - return error; - - return svc_send(rqstp); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) + return svc_send(rqstp); + else { + svc_drop(rqstp); + return 0; + } } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Process a backchannel RPC request that arrived over an existing * outbound connection @@ -1264,10 +1347,9 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, { 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_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; @@ -1292,15 +1374,19 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, 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); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) { + memcpy(&req->rq_snd_buf, &rqstp->rq_res, + sizeof(req->rq_snd_buf)); + return bc_send(req); + } else { + /* drop request */ + xprt_free_bc_request(req); + return 0; + } } -EXPORT_SYMBOL(bc_svc_process); -#endif /* CONFIG_NFS_V4_1 */ +EXPORT_SYMBOL_GPL(bc_svc_process); +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * Return (transport-specific) limit on the rpc payload. |
