A caller that creates many listeners in one operation calls svc_register() once for each of them. Every call waits for the local rpcbind on its own, so a rpcbind that never answers costs the caller one timeout per listener. The caller has no way to learn that the first call already failed.
Split rpcb_register_call() failures by whether rpcbind answered: - answered: a FALSE reply, or an RPC-level rejection that rpc_decode_header() derives from the reply. -EACCES (FALSE reply or AUTH_ERROR), -EPROTONOSUPPORT, -EPFNOSUPPORT, -EOPNOTSUPP. - never sent: -ENOMEM, -EMSGSIZE, -ERESTARTSYS. - no answer: everything else, i.e. transport errors. Any no-answer error gets represented by -EIO, which is already what the RPC layer reports for most of it: rpc_check_timeout() returns -EIO for a soft timeout without RPC_TASK_TIMEOUT, and call_status() documents -EIO as "shutdown or soft timeout". Keep a count of the number of rpcbind failures in the serv. Later patches will use that to watch for hard rpcbind failures, and alter their behavior accordingly. Assisted-by: LLM Signed-off-by: Jeff Layton <[email protected]> --- include/linux/sunrpc/clnt.h | 3 ++- include/linux/sunrpc/svc.h | 7 +++++-- net/sunrpc/rpcb_clnt.c | 22 +++++++++++++++++++--- net/sunrpc/svc.c | 42 +++++++++++++++++++++++++++++++++++++++++- 4 files changed, 67 insertions(+), 7 deletions(-) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 3c2b8c355ab3..30344c0d6a9d 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -199,7 +199,8 @@ struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, int rpcb_create_local(struct net *); void rpcb_put_local(struct net *); -int rpcb_register(struct net *, u32, u32, int, unsigned short); +int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, + unsigned short port); int rpcb_v4_register(struct net *net, const u32 program, const u32 version, const struct sockaddr *address, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 2db1b9ec5658..5fa9417e034d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -78,6 +78,7 @@ struct svc_serv { unsigned int sv_max_payload; /* datagram payload size */ unsigned int sv_max_mesg; /* max_payload + 1 page for overheads */ unsigned int sv_xdrsize; /* XDR buffer size */ + atomic_t sv_rpcb_failures; /* unanswered rpcbind calls */ struct list_head sv_permsocks; /* all permanent sockets */ struct list_head sv_tempsocks; /* all temporary sockets */ int sv_tmpcnt; /* count of temporary "valid" sockets */ @@ -451,6 +452,7 @@ int sunrpc_set_pool_mode(const char *val); int sunrpc_get_pool_mode(char *val, size_t size); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); +unsigned int svc_rpcb_failure_count(struct svc_serv *serv); struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); bool svc_rqst_replace_page(struct svc_rqst *rqstp, @@ -471,8 +473,9 @@ unsigned int svc_serv_maxthreads(const struct svc_serv *serv); int svc_pool_stats_open(struct svc_info *si, struct file *file); void svc_process(struct svc_rqst *rqstp); void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp); -int svc_register(const struct svc_serv *, struct net *, const int, - const unsigned short, const unsigned short); +int svc_register(struct svc_serv *serv, struct net *net, + const int family, const unsigned short proto, + const unsigned short port); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 0aa376b82a52..7255c1e07eec 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -412,7 +412,8 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename, return rpc_create(&args); } -static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set) +static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, + struct rpc_message *msg, bool is_set) { int flags = RPC_TASK_NOCONNECT; int error, result = 0; @@ -422,8 +423,23 @@ static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, stru msg->rpc_resp = &result; error = rpc_call_sync(clnt, msg, flags); - if (error < 0) - return error; + if (error < 0) { + switch (error) { + /* rpcbind answered; the reply itself carries the error */ + case -EPROTONOSUPPORT: + case -EPFNOSUPPORT: + case -EOPNOTSUPP: + case -EACCES: + /* the call never made it onto the wire */ + case -ENOMEM: + case -EMSGSIZE: + /* the caller is going away; this says nothing about rpcbind */ + case -ERESTARTSYS: + return error; + } + /* anything else, we assume that rpcbind isn't functional */ + return -EIO; + } if (!result) return -EACCES; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4f402bbf97ba..ca6f90653327 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1179,10 +1179,40 @@ int svc_generic_rpcbind_set(struct net *net, error = svc_rpcbind_set_version(net, progp, version, family, proto, port); + /* -EIO means no answer, not a refusal, so vs_rpcb_optnl must keep it. */ + if (error == -EIO) + return error; + return (vers->vs_rpcb_optnl) ? 0 : error; } EXPORT_SYMBOL_GPL(svc_generic_rpcbind_set); +/** + * svc_rpcb_failure_count - local rpcbind calls for @serv that got no answer + * @serv: RPC service to query + * + * svc_register() adds one for each of its calls that got no answer. A reply + * that refuses one entry does not count, because rpcbind answered and the + * next entry may still succeed. + * + * The count is kept per serv rather than per net. The local rpcbind client + * is per-net and lockd shares it, but a count that another service can move + * says nothing about this serv's own calls. + * + * This is for callers that cannot see the svc_register() return, because a + * transport class sits in between. Such a caller reads the count before it + * starts and compares as it goes, so there is no state to reset between + * operations. The count never resets, and callers must not attach meaning + * to the value itself. + * + * Return: the number of unanswered calls since this serv was created. + */ +unsigned int svc_rpcb_failure_count(struct svc_serv *serv) +{ + return atomic_read(&serv->sv_rpcb_failures); +} +EXPORT_SYMBOL_GPL(svc_rpcb_failure_count); + /** * svc_register - register an RPC service with the local portmapper * @serv: svc_serv struct for the service to register @@ -1193,10 +1223,11 @@ EXPORT_SYMBOL_GPL(svc_generic_rpcbind_set); * * Service is registered for any address in the passed-in protocol family */ -int svc_register(const struct svc_serv *serv, struct net *net, +int svc_register(struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { + bool noanswer = false; unsigned int p, i; int error = 0; @@ -1208,10 +1239,16 @@ int svc_register(const struct svc_serv *serv, struct net *net, struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { + const struct svc_version *vers = progp->pg_vers[i]; int ret; ret = progp->pg_rpcbind_set(net, progp, i, family, proto, port); + if (ret == -EIO) { + noanswer = true; + if (vers && vers->vs_rpcb_optnl) + ret = 0; + } if (ret < 0) { printk(KERN_WARNING "svc: failed to register " "%sv%u RPC service (errno %d).\n", @@ -1223,6 +1260,9 @@ int svc_register(const struct svc_serv *serv, struct net *net, } } + if (noanswer) + atomic_inc(&serv->sv_rpcb_failures); + return error; } -- 2.55.0
