diff options
Diffstat (limited to 'net/sunrpc')
-rw-r--r-- | net/sunrpc/auth.c | 28 | ||||
-rw-r--r-- | net/sunrpc/auth_gss/auth_gss.c | 44 | ||||
-rw-r--r-- | net/sunrpc/auth_gss/gss_krb5_crypto.c | 2 | ||||
-rw-r--r-- | net/sunrpc/auth_gss/svcauth_gss.c | 2 | ||||
-rw-r--r-- | net/sunrpc/bc_svc.c | 2 | ||||
-rw-r--r-- | net/sunrpc/cache.c | 54 | ||||
-rw-r--r-- | net/sunrpc/clnt.c | 21 | ||||
-rw-r--r-- | net/sunrpc/rpc_pipe.c | 2 | ||||
-rw-r--r-- | net/sunrpc/rpcb_clnt.c | 147 | ||||
-rw-r--r-- | net/sunrpc/svc.c | 39 | ||||
-rw-r--r-- | net/sunrpc/svc_xprt.c | 97 | ||||
-rw-r--r-- | net/sunrpc/svcauth.c | 1 | ||||
-rw-r--r-- | net/sunrpc/svcauth_unix.c | 17 | ||||
-rw-r--r-- | net/sunrpc/svcsock.c | 126 | ||||
-rw-r--r-- | net/sunrpc/xdr.c | 155 | ||||
-rw-r--r-- | net/sunrpc/xprt.c | 5 | ||||
-rw-r--r-- | net/sunrpc/xprtsock.c | 34 |
17 files changed, 486 insertions, 290 deletions
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index afe67849269..67e31276682 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -563,8 +563,17 @@ rpcauth_checkverf(struct rpc_task *task, __be32 *p) return cred->cr_ops->crvalidate(task, p); } +static void rpcauth_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, data); + encode(rqstp, &xdr, obj); +} + int -rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, +rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -574,11 +583,22 @@ rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, if (cred->cr_ops->crwrap_req) return cred->cr_ops->crwrap_req(task, encode, rqstp, data, obj); /* By default, we encode the arguments normally. */ - return encode(rqstp, data, obj); + rpcauth_wrap_req_encode(encode, rqstp, data, obj); + return 0; +} + +static int +rpcauth_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, data); + return decode(rqstp, &xdr, obj); } int -rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, +rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -589,7 +609,7 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, return cred->cr_ops->crunwrap_resp(task, decode, rqstp, data, obj); /* By default, we decode the arguments normally. */ - return decode(rqstp, data, obj); + return rpcauth_unwrap_req_decode(decode, rqstp, data, obj); } int diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 3835ce35e22..45dbf1521b9 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1231,9 +1231,19 @@ out_bad: return NULL; } +static void gss_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, p); + encode(rqstp, &xdr, obj); +} + static inline int gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; struct xdr_buf integ_buf; @@ -1249,9 +1259,7 @@ gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); if (xdr_buf_subsegment(snd_buf, &integ_buf, offset, snd_buf->len - offset)) @@ -1325,7 +1333,8 @@ out: static inline int gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; u32 offset; @@ -1342,9 +1351,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); status = alloc_enc_pages(rqstp); if (status) @@ -1394,7 +1401,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static int gss_wrap_req(struct rpc_task *task, - kxdrproc_t encode, void *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1407,12 +1414,14 @@ gss_wrap_req(struct rpc_task *task, /* The spec seems a little ambiguous here, but I think that not * wrapping context destruction requests makes the most sense. */ - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; goto out; } switch (gss_cred->gc_service) { case RPC_GSS_SVC_NONE: - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; break; case RPC_GSS_SVC_INTEGRITY: status = gss_wrap_req_integ(cred, ctx, encode, @@ -1494,10 +1503,19 @@ gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, return 0; } +static int +gss_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + return decode(rqstp, &xdr, obj); +} static int gss_unwrap_resp(struct rpc_task *task, - kxdrproc_t decode, void *rqstp, __be32 *p, void *obj) + kxdrdproc_t decode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1528,7 +1546,7 @@ gss_unwrap_resp(struct rpc_task *task, cred->cr_auth->au_rslack = cred->cr_auth->au_verfsize + (p - savedp) + (savedlen - head->iov_len); out_decode: - status = decode(rqstp, p, obj); + status = gss_unwrap_req_decode(decode, rqstp, p, obj); out: gss_put_ctx(ctx); dprintk("RPC: %5u gss_unwrap_resp returning %d\n", task->tk_pid, diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 75ee993ea05..9576f35ab70 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -137,7 +137,7 @@ arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4]) ms_usage = 13; break; default: - return EINVAL;; + return -EINVAL; } salt[0] = (ms_usage >> 0) & 0xff; salt[1] = (ms_usage >> 8) & 0xff; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index dec2a6fc7c1..bcdae78fdfc 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -67,7 +67,6 @@ static int netobj_equal(struct xdr_netobj *a, struct xdr_netobj *b) #define RSI_HASHBITS 6 #define RSI_HASHMAX (1<<RSI_HASHBITS) -#define RSI_HASHMASK (RSI_HASHMAX-1) struct rsi { struct cache_head h; @@ -319,7 +318,6 @@ static struct rsi *rsi_update(struct rsi *new, struct rsi *old) #define RSC_HASHBITS 10 #define RSC_HASHMAX (1<<RSC_HASHBITS) -#define RSC_HASHMASK (RSC_HASHMAX-1) #define GSS_SEQ_WIN 128 diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 7dcfe0cc350..1dd1a689000 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -59,8 +59,8 @@ int bc_send(struct rpc_rqst *req) ret = task->tk_status; rpc_put_task(task); } - return ret; dprintk("RPC: bc_send ret= %d\n", ret); + return ret; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index e433e7580e2..72ad836e4fe 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -37,7 +37,7 @@ #define RPCDBG_FACILITY RPCDBG_CACHE -static void cache_defer_req(struct cache_req *req, struct cache_head *item); +static bool cache_defer_req(struct cache_req *req, struct cache_head *item); static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h) @@ -128,6 +128,7 @@ static void cache_fresh_locked(struct cache_head *head, time_t expiry) { head->expiry_time = expiry; head->last_refresh = seconds_since_boot(); + smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */ set_bit(CACHE_VALID, &head->flags); } @@ -208,11 +209,36 @@ static inline int cache_is_valid(struct cache_detail *detail, struct cache_head /* entry is valid */ if (test_bit(CACHE_NEGATIVE, &h->flags)) return -ENOENT; - else + else { + /* + * In combination with write barrier in + * sunrpc_cache_update, ensures that anyone + * using the cache entry after this sees the + * updated contents: + */ + smp_rmb(); return 0; + } } } +static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h) +{ + int rv; + + write_lock(&detail->hash_lock); + rv = cache_is_valid(detail, h); + if (rv != -EAGAIN) { + write_unlock(&detail->hash_lock); + return rv; + } + set_bit(CACHE_NEGATIVE, &h->flags); + cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY); + write_unlock(&detail->hash_lock); + cache_fresh_unlocked(h, detail); + return -ENOENT; +} + /* * This is the generic cache management routine for all * the authentication caches. @@ -251,14 +277,8 @@ int cache_check(struct cache_detail *detail, case -EINVAL: clear_bit(CACHE_PENDING, &h->flags); cache_revisit_request(h); - if (rv == -EAGAIN) { - set_bit(CACHE_NEGATIVE, &h->flags); - cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY); - cache_fresh_unlocked(h, detail); - rv = -ENOENT; - } + rv = try_to_negate_entry(detail, h); break; - case -EAGAIN: clear_bit(CACHE_PENDING, &h->flags); cache_revisit_request(h); @@ -268,9 +288,11 @@ int cache_check(struct cache_detail *detail, } if (rv == -EAGAIN) { - cache_defer_req(rqstp, h); - if (!test_bit(CACHE_PENDING, &h->flags)) { - /* Request is not deferred */ + if (!cache_defer_req(rqstp, h)) { + /* + * Request was not deferred; handle it as best + * we can ourselves: + */ rv = cache_is_valid(detail, h); if (rv == -EAGAIN) rv = -ETIMEDOUT; @@ -618,18 +640,19 @@ static void cache_limit_defers(void) discard->revisit(discard, 1); } -static void cache_defer_req(struct cache_req *req, struct cache_head *item) +/* Return true if and only if a deferred request is queued. */ +static bool cache_defer_req(struct cache_req *req, struct cache_head *item) { struct cache_deferred_req *dreq; if (req->thread_wait) { cache_wait_req(req, item); if (!test_bit(CACHE_PENDING, &item->flags)) - return; + return false; } dreq = req->defer(req); if (dreq == NULL) - return; + return false; setup_deferral(dreq, item, 1); if (!test_bit(CACHE_PENDING, &item->flags)) /* Bit could have been cleared before we managed to @@ -638,6 +661,7 @@ static void cache_defer_req(struct cache_req *req, struct cache_head *item) cache_revisit_request(item); cache_limit_defers(); + return true; } static void cache_revisit_request(struct cache_head *item) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 92ce94f5146..57d344cf225 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1095,7 +1095,7 @@ static void rpc_xdr_encode(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t encode; + kxdreproc_t encode; __be32 *p; dprint_status(task); @@ -1535,7 +1535,7 @@ call_decode(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t decode = task->tk_msg.rpc_proc->p_decode; + kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; __be32 *p; dprintk("RPC: %5u call_decode (status %d)\n", @@ -1776,12 +1776,11 @@ out_overflow: goto out_garbage; } -static int rpcproc_encode_null(void *rqstp, __be32 *data, void *obj) +static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { - return 0; } -static int rpcproc_decode_null(void *rqstp, __be32 *data, void *obj) +static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { return 0; } @@ -1830,23 +1829,15 @@ static void rpc_show_task(const struct rpc_clnt *clnt, const struct rpc_task *task) { const char *rpc_waitq = "none"; - char *p, action[KSYM_SYMBOL_LEN]; if (RPC_IS_QUEUED(task)) rpc_waitq = rpc_qname(task->tk_waitqueue); - /* map tk_action pointer to a function name; then trim off - * the "+0x0 [sunrpc]" */ - sprint_symbol(action, (unsigned long)task->tk_action); - p = strchr(action, '+'); - if (p) - *p = '\0'; - - printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%s q:%s\n", + printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%ps q:%s\n", task->tk_pid, task->tk_flags, task->tk_status, clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops, clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task), - action, rpc_waitq); + task->tk_action, rpc_waitq); } void rpc_show_tasks(void) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 09f01f41e55..72bc5368396 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -474,7 +474,7 @@ static int __rpc_create_common(struct inode *dir, struct dentry *dentry, { struct inode *inode; - BUG_ON(!d_unhashed(dentry)); + d_drop(dentry); inode = rpc_get_inode(dir->i_sb, mode); if (!inode) goto out_err; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index fa6d7ca2c85..c652e4cc9fe 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -57,10 +57,6 @@ enum { RPCBPROC_GETSTAT, }; -#define RPCB_HIGHPROC_2 RPCBPROC_CALLIT -#define RPCB_HIGHPROC_3 RPCBPROC_TADDR2UADDR -#define RPCB_HIGHPROC_4 RPCBPROC_GETSTAT - /* * r_owner * @@ -693,46 +689,37 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); - if (unlikely(p == NULL)) - return -EIO; - - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); - *p++ = htonl(rpcb->r_prot); - *p = htonl(rpcb->r_port); - - return 0; + p = xdr_reserve_space(xdr, RPCB_mappingargs_sz << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p++ = cpu_to_be32(rpcb->r_vers); + *p++ = cpu_to_be32(rpcb->r_prot); + *p = cpu_to_be32(rpcb->r_port); } -static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; unsigned long port; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; rpcb->r_port = 0; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; - port = ntohl(*p); + port = be32_to_cpup(p); dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, port); if (unlikely(port > USHRT_MAX)) @@ -742,20 +729,18 @@ static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, unsigned int *boolp) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; *boolp = 0; - if (*p) + if (*p != xdr_zero) *boolp = 1; dprintk("RPC: %5u RPCB_%s call %s\n", @@ -764,73 +749,53 @@ static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, return 0; } -static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, - const u32 maxstrlen) +static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - u32 len; __be32 *p; + u32 len; - if (unlikely(string == NULL)) - return -EIO; len = strlen(string); - if (unlikely(len > maxstrlen)) - return -EIO; - - p = xdr_reserve_space(xdr, sizeof(__be32) + len); - if (unlikely(p == NULL)) - return -EIO; + BUG_ON(len > maxstrlen); + p = xdr_reserve_space(xdr, 4 + len); xdr_encode_opaque(p, string, len); - - return 0; } -static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_netid, rpcb->r_addr); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, - sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); - if (unlikely(p == NULL)) - return -EIO; - *p++ = htonl(rpcb->r_prog); - *p = htonl(rpcb->r_vers); - - if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) - return -EIO; + p = xdr_reserve_space(xdr, (RPCB_program_sz + RPCB_version_sz) << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p = cpu_to_be32(rpcb->r_vers); - return 0; + encode_rpcb_string(xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN); + encode_rpcb_string(xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN); + encode_rpcb_string(xdr, rpcb->r_owner, RPCB_MAXOWNERLEN); } -static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; u32 len; rpcb->r_port = 0; - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); - - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) goto out_fail; - len = ntohl(*p); + len = be32_to_cpup(p); /* * If the returned universal address is a null string, @@ -845,7 +810,7 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, if (unlikely(len > RPCBIND_MAXUADDRLEN)) goto out_fail; - p = xdr_inline_decode(&xdr, len); + p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, @@ -871,8 +836,8 @@ out_fail: static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -881,8 +846,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -891,8 +856,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -904,8 +869,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -914,8 +879,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -924,8 +889,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -937,8 +902,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -947,8 +912,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -957,8 +922,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -993,19 +958,19 @@ static struct rpcb_info rpcb_next_version6[] = { static struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, - .nrprocs = RPCB_HIGHPROC_2, + .nrprocs = ARRAY_SIZE(rpcb_procedures2), .procs = rpcb_procedures2 }; static struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, - .nrprocs = RPCB_HIGHPROC_3, + .nrprocs = ARRAY_SIZE(rpcb_procedures3), .procs = rpcb_procedures3 }; static struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, - .nrprocs = RPCB_HIGHPROC_4, + .nrprocs = ARRAY_SIZE(rpcb_procedures4), .procs = rpcb_procedures4 }; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6359c42c494..08e05a8ce02 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -488,10 +488,6 @@ 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); @@ -1005,6 +1001,7 @@ 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); @@ -1106,7 +1103,7 @@ 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 +1144,6 @@ 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: @@ -1218,7 +1214,6 @@ 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. @@ -1246,11 +1241,13 @@ 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) @@ -1264,10 +1261,9 @@ 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; @@ -1292,12 +1288,15 @@ 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 { + /* Nothing to do to drop request */ + return 0; + } } EXPORT_SYMBOL(bc_svc_process); #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 3f2c5559ca1..ab86b7927f8 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -13,6 +13,7 @@ #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/svcsock.h> +#include <linux/sunrpc/xprt.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -128,6 +129,9 @@ static void svc_xprt_free(struct kref *kref) if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) svcauth_unix_info_release(xprt); put_net(xprt->xpt_net); + /* See comment on corresponding get in xs_setup_bc_tcp(): */ + if (xprt->xpt_bc_xprt) + xprt_put(xprt->xpt_bc_xprt); xprt->xpt_ops->xpo_free(xprt); module_put(owner); } @@ -303,6 +307,15 @@ static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp) list_del(&rqstp->rq_list); } +static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) +{ + if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE))) + return true; + if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) + return xprt->xpt_ops->xpo_has_wspace(xprt); + return false; +} + /* * Queue up a transport with data pending. If there are idle nfsd * processes, wake 'em up. @@ -315,8 +328,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_rqst *rqstp; int cpu; - if (!(xprt->xpt_flags & - ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED)))) + if (!svc_xprt_has_something_to_do(xprt)) return; cpu = get_cpu(); @@ -343,28 +355,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) dprintk("svc: transport %p busy, not enqueued\n", xprt); goto out_unlock; } - BUG_ON(xprt->xpt_pool != NULL); - xprt->xpt_pool = pool; - - /* Handle pending connection */ - if (test_bit(XPT_CONN, &xprt->xpt_flags)) - goto process; - - /* Handle close in-progress */ - if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) - goto process; - - /* Check if we have space to reply to a request */ - if (!xprt->xpt_ops->xpo_has_wspace(xprt)) { - /* Don't enqueue while not enough space for reply */ - dprintk("svc: no write space, transport %p not enqueued\n", - xprt); - xprt->xpt_pool = NULL; - clear_bit(XPT_BUSY, &xprt->xpt_flags); - goto out_unlock; - } - process: if (!list_empty(&pool->sp_threads)) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, @@ -381,13 +372,11 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); pool->sp_stats.threads_woken++; - BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); } else { dprintk("svc: transport %p put into queue\n", xprt); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); pool->sp_stats.sockets_queued++; - BUG_ON(xprt->xpt_pool != pool); } out_unlock: @@ -426,7 +415,6 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool) void svc_xprt_received(struct svc_xprt *xprt) { BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags)); - xprt->xpt_pool = NULL; /* As soon as we clear busy, the xprt could be closed and * 'put', so we need a reference to call svc_xprt_enqueue with: */ @@ -722,7 +710,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) { dprintk("svc_recv: found XPT_CLOSE\n"); svc_delete_xprt(xprt); - } else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { + /* Leave XPT_BUSY set on the dead xprt: */ + goto out; + } + if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { struct svc_xprt *newxpt; newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) { @@ -747,28 +738,23 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) spin_unlock_bh(&serv->sv_lock); svc_xprt_received(newxpt); } - svc_xprt_received(xprt); - } else { + } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) { dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, pool->sp_id, xprt, atomic_read(&xprt->xpt_ref.refcount)); rqstp->rq_deferred = svc_deferred_dequeue(xprt); - if (rqstp->rq_deferred) { - svc_xprt_received(xprt); + if (rqstp->rq_deferred) len = svc_deferred_recv(rqstp); - } else { + else len = xprt->xpt_ops->xpo_recvfrom(rqstp); - svc_xprt_received(xprt); - } dprintk("svc: got len=%d\n", len); } + svc_xprt_received(xprt); /* No data, incomplete (TCP) read, or accept() */ - if (len == 0 || len == -EAGAIN) { - rqstp->rq_res.len = 0; - svc_xprt_release(rqstp); - return -EAGAIN; - } + if (len == 0 || len == -EAGAIN) + goto out; + clear_bit(XPT_OLD, &xprt->xpt_flags); rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp)); @@ -777,6 +763,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (serv->sv_stats) serv->sv_stats->netcnt++; return len; +out: + rqstp->rq_res.len = 0; + svc_xprt_release(rqstp); + return -EAGAIN; } EXPORT_SYMBOL_GPL(svc_recv); @@ -935,7 +925,12 @@ void svc_close_xprt(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) /* someone else will have to effect the close */ return; - + /* + * We expect svc_close_xprt() to work even when no threads are + * running (e.g., while configuring the server before starting + * any threads), so if the transport isn't busy, we delete + * it ourself: + */ svc_delete_xprt(xprt); } EXPORT_SYMBOL_GPL(svc_close_xprt); @@ -945,16 +940,16 @@ void svc_close_all(struct list_head *xprt_list) struct svc_xprt *xprt; struct svc_xprt *tmp; + /* + * The server is shutting down, and no more threads are running. + * svc_xprt_enqueue() might still be running, but at worst it + * will re-add the xprt to sp_sockets, which will soon get + * freed. So we don't bother with any more locking, and don't + * leave the close to the (nonexistent) server threads: + */ list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) { set_bit(XPT_CLOSE, &xprt->xpt_flags); - if (test_bit(XPT_BUSY, &xprt->xpt_flags)) { - /* Waiting to be processed, but no threads left, - * So just remove it from the waiting list - */ - list_del_init(&xprt->xpt_ready); - clear_bit(XPT_BUSY, &xprt->xpt_flags); - } - svc_close_xprt(xprt); + svc_delete_xprt(xprt); } } @@ -1028,6 +1023,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) } svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; + rqstp->rq_dropme = true; dr->handle.revisit = svc_revisit; return &dr->handle; @@ -1065,14 +1061,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) if (!test_bit(XPT_DEFERRED, &xprt->xpt_flags)) return NULL; spin_lock(&xprt->xpt_lock); - clear_bit(XPT_DEFERRED, &xprt->xpt_flags); if (!list_empty(&xprt->xpt_deferred)) { dr = list_entry(xprt->xpt_deferred.next, struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); - set_bit(XPT_DEFERRED, &xprt->xpt_flags); - } + } else + clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); return dr; } diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 4e9393c2468..7963569fc04 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -118,7 +118,6 @@ EXPORT_SYMBOL_GPL(svc_auth_unregister); #define DN_HASHBITS 6 #define DN_HASHMAX (1<<DN_HASHBITS) -#define DN_HASHMASK (DN_HASHMAX-1) static struct hlist_head auth_domain_table[DN_HASHMAX]; static spinlock_t auth_domain_lock = diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 560677d187f..30916b06c12 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -30,7 +30,9 @@ struct unix_domain { struct auth_domain h; +#ifdef CONFIG_NFSD_DEPRECATED int addr_changes; +#endif /* CONFIG_NFSD_DEPRECATED */ /* other stuff later */ }; @@ -64,7 +66,9 @@ struct auth_domain *unix_domain_find(char *name) return NULL; } new->h.flavour = &svcauth_unix; +#ifdef CONFIG_NFSD_DEPRECATED new->addr_changes = 0; +#endif /* CONFIG_NFSD_DEPRECATED */ rv = auth_domain_lookup(name, &new->h); } } @@ -85,14 +89,15 @@ static void svcauth_unix_domain_release(struct auth_domain *dom) */ #define IP_HASHBITS 8 #define IP_HASHMAX (1<<IP_HASHBITS) -#define IP_HASHMASK (IP_HASHMAX-1) struct ip_map { struct cache_head h; char m_class[8]; /* e.g. "nfsd" */ struct in6_addr m_addr; struct unix_domain *m_client; +#ifdef CONFIG_NFSD_DEPRECATED int m_add_change; +#endif /* CONFIG_NFSD_DEPRECATED */ }; static void ip_map_put(struct kref *kref) @@ -146,7 +151,9 @@ static void update(struct cache_head *cnew, struct cache_head *citem) kref_get(&item->m_client->h.ref); new->m_client = item->m_client; +#ifdef CONFIG_NFSD_DEPRECATED new->m_add_change = item->m_add_change; +#endif /* CONFIG_NFSD_DEPRECATED */ } static struct cache_head *ip_map_alloc(void) { @@ -331,6 +338,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, ip.h.flags = 0; if (!udom) set_bit(CACHE_NEGATIVE, &ip.h.flags); +#ifdef CONFIG_NFSD_DEPRECATED else { ip.m_add_change = udom->addr_changes; /* if this is from the legacy set_client system call, @@ -339,6 +347,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, if (expiry == NEVER) ip.m_add_change++; } +#endif /* CONFIG_NFSD_DEPRECATED */ ip.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ip.h, &ipm->h, hash_str(ipm->m_class, IP_HASHBITS) ^ @@ -358,6 +367,7 @@ static inline int ip_map_update(struct net *net, struct ip_map *ipm, return __ip_map_update(sn->ip_map_cache, ipm, udom, expiry); } +#ifdef CONFIG_NFSD_DEPRECATED int auth_unix_add_addr(struct net *net, struct in6_addr *addr, struct auth_domain *dom) { struct unix_domain *udom; @@ -402,8 +412,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr) return NULL; if ((ipm->m_client->addr_changes - ipm->m_add_change) >0) { - if (test_and_set_bit(CACHE_NEGATIVE, &ipm->h.flags) == 0) - auth_domain_put(&ipm->m_client->h); + sunrpc_invalidate(&ipm->h, sn->ip_map_cache); rv = NULL; } else { rv = &ipm->m_client->h; @@ -413,6 +422,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr) return rv; } EXPORT_SYMBOL_GPL(auth_unix_lookup); +#endif /* CONFIG_NFSD_DEPRECATED */ void svcauth_unix_purge(void) { @@ -497,7 +507,6 @@ svcauth_unix_info_release(struct svc_xprt *xpt) */ #define GID_HASHBITS 8 #define GID_HASHMAX (1<<GID_HASHBITS) -#define GID_HASHMASK (GID_HASHMAX - 1) struct unix_gid { struct cache_head h; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 07919e16be3..7bd3bbba471 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -66,6 +66,13 @@ static void svc_sock_free(struct svc_xprt *); static struct svc_xprt *svc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); +#endif /* CONFIG_NFS_V4_1 */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key svc_key[2]; static struct lock_class_key svc_slock_key[2]; @@ -324,19 +331,21 @@ int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen, len = onelen; break; } - if (toclose && strcmp(toclose, buf + len) == 0) + if (toclose && strcmp(toclose, buf + len) == 0) { closesk = svsk; - else + svc_xprt_get(&closesk->sk_xprt); + } else len += onelen; } spin_unlock_bh(&serv->sv_lock); - if (closesk) + if (closesk) { /* Should unregister with portmap, but you cannot * unregister just one protocol... */ svc_close_xprt(&closesk->sk_xprt); - else if (toclose) + svc_xprt_put(&closesk->sk_xprt); + } else if (toclose) return -ENOENT; return len; } @@ -985,15 +994,17 @@ static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp, vec[0] = rqstp->rq_arg.head[0]; } else { /* REPLY */ - if (svsk->sk_bc_xprt) - req = xprt_lookup_rqst(svsk->sk_bc_xprt, xid); + struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt; + + if (bc_xprt) + req = xprt_lookup_rqst(bc_xprt, xid); if (!req) { printk(KERN_NOTICE "%s: Got unrecognized reply: " - "calldir 0x%x sk_bc_xprt %p xid %08x\n", + "calldir 0x%x xpt_bc_xprt %p xid %08x\n", __func__, ntohl(calldir), - svsk->sk_bc_xprt, xid); + bc_xprt, xid); vec[0] = rqstp->rq_arg.head[0]; goto out; } @@ -1184,6 +1195,57 @@ static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); } +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); + +static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv, + struct net *net, + struct sockaddr *sa, int salen, + int flags) +{ + return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); +} + +static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt) +{ +} + +static struct svc_xprt_ops svc_tcp_bc_ops = { + .xpo_create = svc_bc_tcp_create, + .xpo_detach = svc_bc_tcp_sock_detach, + .xpo_free = svc_bc_sock_free, + .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, +}; + +static struct svc_xprt_class svc_tcp_bc_class = { + .xcl_name = "tcp-bc", + .xcl_owner = THIS_MODULE, + .xcl_ops = &svc_tcp_bc_ops, + .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, +}; + +static void svc_init_bc_xprt_sock(void) +{ + svc_reg_xprt_class(&svc_tcp_bc_class); +} + +static void svc_cleanup_bc_xprt_sock(void) +{ + svc_unreg_xprt_class(&svc_tcp_bc_class); +} +#else /* CONFIG_NFS_V4_1 */ +static void svc_init_bc_xprt_sock(void) +{ +} + +static void svc_cleanup_bc_xprt_sock(void) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + static struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, @@ -1207,12 +1269,14 @@ void svc_init_xprt_sock(void) { svc_reg_xprt_class(&svc_tcp_class); svc_reg_xprt_class(&svc_udp_class); + svc_init_bc_xprt_sock(); } void svc_cleanup_xprt_sock(void) { svc_unreg_xprt_class(&svc_tcp_class); svc_unreg_xprt_class(&svc_udp_class); + svc_cleanup_bc_xprt_sock(); } static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1509,41 +1573,45 @@ static void svc_sock_free(struct svc_xprt *xprt) kfree(svsk); } +#if defined(CONFIG_NFS_V4_1) /* - * Create a svc_xprt. - * - * For internal use only (e.g. nfsv4.1 backchannel). - * Callers should typically use the xpo_create() method. + * Create a back channel svc_xprt which shares the fore channel socket. */ -struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, + int protocol, + struct net *net, + struct sockaddr *sin, int len, + int flags) { struct svc_sock *svsk; - struct svc_xprt *xprt = NULL; + struct svc_xprt *xprt; + + if (protocol != IPPROTO_TCP) { + printk(KERN_WARNING "svc: only TCP sockets" + " supported on shared back channel\n"); + return ERR_PTR(-EINVAL); + } - dprintk("svc: %s\n", __func__); svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); if (!svsk) - goto out; + return ERR_PTR(-ENOMEM); xprt = &svsk->sk_xprt; - if (prot == IPPROTO_TCP) - svc_xprt_init(&svc_tcp_class, xprt, serv); - else if (prot == IPPROTO_UDP) - svc_xprt_init(&svc_udp_class, xprt, serv); - else - BUG(); -out: - dprintk("svc: %s return %p\n", __func__, xprt); + svc_xprt_init(&svc_tcp_bc_class, xprt, serv); + + serv->sv_bc_xprt = xprt; + return xprt; } -EXPORT_SYMBOL_GPL(svc_sock_create); /* - * Destroy a svc_sock. + * Free a back channel svc_sock. */ -void svc_sock_destroy(struct svc_xprt *xprt) +static void svc_bc_sock_free(struct svc_xprt *xprt) { - if (xprt) + if (xprt) { + kfree(xprt->xpt_bc_sid); kfree(container_of(xprt, struct svc_sock, sk_xprt)); + } } -EXPORT_SYMBOL_GPL(svc_sock_destroy); +#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index cd9e841e749..679cd674b81 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -552,6 +552,74 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b } EXPORT_SYMBOL_GPL(xdr_write_pages); +static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov, + __be32 *p, unsigned int len) +{ + if (len > iov->iov_len) + len = iov->iov_len; + if (p == NULL) + p = (__be32*)iov->iov_base; + xdr->p = p; + xdr->end = (__be32*)(iov->iov_base + len); + xdr->iov = iov; + xdr->page_ptr = NULL; +} + +static int xdr_set_page_base(struct xdr_stream *xdr, + unsigned int base, unsigned int len) +{ + unsigned int pgnr; + unsigned int maxlen; + unsigned int pgoff; + unsigned int pgend; + void *kaddr; + + maxlen = xdr->buf->page_len; + if (base >= maxlen) + return -EINVAL; + maxlen -= base; + if (len > maxlen) + len = maxlen; + + base += xdr->buf->page_base; + + pgnr = base >> PAGE_SHIFT; + xdr->page_ptr = &xdr->buf->pages[pgnr]; + kaddr = page_address(*xdr->page_ptr); + + pgoff = base & ~PAGE_MASK; + xdr->p = (__be32*)(kaddr + pgoff); + + pgend = pgoff + len; + if (pgend > PAGE_SIZE) + pgend = PAGE_SIZE; + xdr->end = (__be32*)(kaddr + pgend); + xdr->iov = NULL; + return 0; +} + +static void xdr_set_next_page(struct xdr_stream *xdr) +{ + unsigned int newbase; + + newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT; + newbase -= xdr->buf->page_base; + + if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); +} + +static bool xdr_set_next_buffer(struct xdr_stream *xdr) +{ + if (xdr->page_ptr != NULL) + xdr_set_next_page(xdr); + else if (xdr->iov == xdr->buf->head) { + if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + } + return xdr->p != xdr->end; +} + /** * xdr_init_decode - Initialize an xdr_stream for decoding data. * @xdr: pointer to xdr_stream struct @@ -560,41 +628,67 @@ EXPORT_SYMBOL_GPL(xdr_write_pages); */ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) { - struct kvec *iov = buf->head; - unsigned int len = iov->iov_len; - - if (len > buf->len) - len = buf->len; xdr->buf = buf; - xdr->iov = iov; - xdr->p = p; - xdr->end = (__be32 *)((char *)iov->iov_base + len); + xdr->scratch.iov_base = NULL; + xdr->scratch.iov_len = 0; + if (buf->head[0].iov_len != 0) + xdr_set_iov(xdr, buf->head, p, buf->len); + else if (buf->page_len != 0) + xdr_set_page_base(xdr, 0, buf->len); } EXPORT_SYMBOL_GPL(xdr_init_decode); -/** - * xdr_inline_peek - Allow read-ahead in the XDR data stream - * @xdr: pointer to xdr_stream struct - * @nbytes: number of bytes of data to decode - * - * Check if the input buffer is long enough to enable us to decode - * 'nbytes' more bytes of data starting at the current position. - * If so return the current pointer without updating the current - * pointer position. - */ -__be32 * xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes) +static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { __be32 *p = xdr->p; __be32 *q = p + XDR_QUADLEN(nbytes); if (unlikely(q > xdr->end || q < p)) return NULL; + xdr->p = q; return p; } -EXPORT_SYMBOL_GPL(xdr_inline_peek); /** - * xdr_inline_decode - Retrieve non-page XDR data to decode + * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data. + * @xdr: pointer to xdr_stream struct + * @buf: pointer to an empty buffer + * @buflen: size of 'buf' + * + * The scratch buffer is used when decoding from an array of pages. + * If an xdr_inline_decode() call spans across page boundaries, then + * we copy the data into the scratch buffer in order to allow linear + * access. + */ +void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen) +{ + xdr->scratch.iov_base = buf; + xdr->scratch.iov_len = buflen; +} +EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer); + +static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p; + void *cpdest = xdr->scratch.iov_base; + size_t cplen = (char *)xdr->end - (char *)xdr->p; + + if (nbytes > xdr->scratch.iov_len) + return NULL; + memcpy(cpdest, xdr->p, cplen); + cpdest += cplen; + nbytes -= cplen; + if (!xdr_set_next_buffer(xdr)) + return NULL; + p = __xdr_inline_decode(xdr, nbytes); + if (p == NULL) + return NULL; + memcpy(cpdest, p, nbytes); + return xdr->scratch.iov_base; +} + +/** + * xdr_inline_decode - Retrieve XDR data to decode * @xdr: pointer to xdr_stream struct * @nbytes: number of bytes of data to decode * @@ -605,13 +699,16 @@ EXPORT_SYMBOL_GPL(xdr_inline_peek); */ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { - __be32 *p = xdr->p; - __be32 *q = p + XDR_QUADLEN(nbytes); + __be32 *p; - if (unlikely(q > xdr->end || q < p)) + if (nbytes == 0) + return xdr->p; + if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr)) return NULL; - xdr->p = q; - return p; + p = __xdr_inline_decode(xdr, nbytes); + if (p != NULL) + return p; + return xdr_copy_to_scratch(xdr, nbytes); } EXPORT_SYMBOL_GPL(xdr_inline_decode); @@ -671,16 +768,12 @@ EXPORT_SYMBOL_GPL(xdr_read_pages); */ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) { - char * kaddr = page_address(xdr->buf->pages[0]); xdr_read_pages(xdr, len); /* * Position current pointer at beginning of tail, and * set remaining message length. */ - if (len > PAGE_CACHE_SIZE - xdr->buf->page_base) - len = PAGE_CACHE_SIZE - xdr->buf->page_base; - xdr->p = (__be32 *)(kaddr + xdr->buf->page_base); - xdr->end = (__be32 *)((char *)xdr->p + len); + xdr_set_page_base(xdr, 0, len); } EXPORT_SYMBOL_GPL(xdr_enter_page); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 4c8f18aff7c..856274d7e85 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -965,6 +965,7 @@ struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req) xprt = kzalloc(size, GFP_KERNEL); if (xprt == NULL) goto out; + kref_init(&xprt->kref); xprt->max_reqs = max_req; xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL); @@ -1101,8 +1102,10 @@ found: -PTR_ERR(xprt)); return xprt; } + if (test_and_set_bit(XPRT_INITIALIZED, &xprt->state)) + /* ->setup returned a pre-initialized xprt: */ + return xprt; - kref_init(&xprt->kref); spin_lock_init(&xprt->transport_lock); spin_lock_init(&xprt->reserve_lock); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 96549df836e..c431f5a5796 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2359,6 +2359,15 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) struct svc_sock *bc_sock; struct rpc_xprt *ret; + if (args->bc_xprt->xpt_bc_xprt) { + /* + * This server connection already has a backchannel + * export; we can't create a new one, as we wouldn't be + * able to match replies based on xid any more. So, + * reuse the already-existing one: + */ + return args->bc_xprt->xpt_bc_xprt; + } xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; @@ -2375,16 +2384,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->reestablish_timeout = 0; xprt->idle_timeout = 0; - /* - * The backchannel uses the same socket connection as the - * forechannel - */ - xprt->bc_xprt = args->bc_xprt; - bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); - bc_sock->sk_bc_xprt = xprt; - transport->sock = bc_sock->sk_sock; - transport->inet = bc_sock->sk_sk; - xprt->ops = &bc_tcp_ops; switch (addr->sa_family) { @@ -2407,6 +2406,20 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->address_strings[RPC_DISPLAY_PROTO]); /* + * Once we've associated a backchannel xprt with a connection, + * we want to keep it around as long as long as the connection + * lasts, in case we need to start using it for a backchannel + * again; this reference won't be dropped until bc_xprt is + * destroyed. + */ + xprt_get(xprt); + args->bc_xprt->xpt_bc_xprt = xprt; + xprt->bc_xprt = args->bc_xprt; + bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); + transport->sock = bc_sock->sk_sock; + transport->inet = bc_sock->sk_sk; + + /* * Since we don't want connections for the backchannel, we set * the xprt status to connected */ @@ -2415,6 +2428,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) if (try_module_get(THIS_MODULE)) return xprt; + xprt_put(xprt); ret = ERR_PTR(-EINVAL); out_err: xprt_free(xprt); |