* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
+#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/freezer.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
+#include <net/ipv6.h>
#include <net/tcp_states.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/sunrpc/types.h>
+#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/stats.h>
/* SMP locking strategy:
*
- * svc_serv->sv_lock protects most stuff for that service.
+ * svc_pool->sp_lock protects most of the fields of that pool.
+ * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
+ * when both need to be taken (rare), svc_serv->sv_lock is first.
+ * BKL protects svc_serv->sv_nrthread.
+ * svc_sock->sk_lock protects the svc_sock->sk_deferred list
+ * and the ->sk_info_authunix cache.
+ * svc_sock->sk_xprt.xpt_flags.XPT_BUSY prevents a svc_sock being
+ * enqueued multiply.
*
* Some flags can be set to certain values at any time
* providing that certain rules are followed:
*
- * SK_BUSY can be set to 0 at any time.
- * svc_sock_enqueue must be called afterwards
- * SK_CONN, SK_DATA, can be set or cleared at any time.
- * after a set, svc_sock_enqueue must be called.
+ * XPT_CONN, XPT_DATA, can be set or cleared at any time.
+ * after a set, svc_sock_enqueue must be called.
* after a clear, the socket must be read/accepted
* if this succeeds, it must be set again.
- * SK_CLOSE can set at any time. It is never cleared.
+ * XPT_CLOSE can set at any time. It is never cleared.
+ * xpt_ref contains a bias of '1' until XPT_DEAD is set.
+ * so when xprt_ref hits zero, we know the transport is dead
+ * and no-one is using it.
+ * XPT_DEAD can only be set while XPT_BUSY is held which ensures
+ * no other thread will be using the socket or will try to
+ * set XPT_DEAD.
*
*/
-#define RPCDBG_FACILITY RPCDBG_SVCSOCK
+#define RPCDBG_FACILITY RPCDBG_SVCXPRT
static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
- int *errp, int pmap_reg);
+ int *errp, int flags);
+static void svc_delete_xprt(struct svc_xprt *xprt);
static void svc_udp_data_ready(struct sock *, int);
static int svc_udp_recvfrom(struct svc_rqst *);
static int svc_udp_sendto(struct svc_rqst *);
+static void svc_close_xprt(struct svc_xprt *xprt);
+static void svc_sock_detach(struct svc_xprt *);
+static void svc_sock_free(struct svc_xprt *);
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
+static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
+ struct sockaddr *, int, int);
+
+/* apparently the "standard" is that clients close
+ * idle connections after 5 minutes, servers after
+ * 6 minutes
+ * http://www.connectathon.org/talks96/nfstcp.pdf
+ */
+static int svc_conn_age_period = 6*60;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key svc_key[2];
+static struct lock_class_key svc_slock_key[2];
+
+static inline void svc_reclassify_socket(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ BUG_ON(sock_owned_by_user(sk));
+ switch (sk->sk_family) {
+ case AF_INET:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
+ &svc_slock_key[0], "sk_lock-AF_INET-NFSD", &svc_key[0]);
+ break;
+
+ case AF_INET6:
+ sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
+ &svc_slock_key[1], "sk_lock-AF_INET6-NFSD", &svc_key[1]);
+ break;
+
+ default:
+ BUG();
+ }
+}
+#else
+static inline void svc_reclassify_socket(struct socket *sock)
+{
+}
+#endif
+
+static char *__svc_print_addr(struct sockaddr *addr, char *buf, size_t len)
+{
+ switch (addr->sa_family) {
+ case AF_INET:
+ snprintf(buf, len, "%u.%u.%u.%u, port=%u",
+ NIPQUAD(((struct sockaddr_in *) addr)->sin_addr),
+ ntohs(((struct sockaddr_in *) addr)->sin_port));
+ break;
+
+ case AF_INET6:
+ snprintf(buf, len, "%x:%x:%x:%x:%x:%x:%x:%x, port=%u",
+ NIP6(((struct sockaddr_in6 *) addr)->sin6_addr),
+ ntohs(((struct sockaddr_in6 *) addr)->sin6_port));
+ break;
+
+ default:
+ snprintf(buf, len, "unknown address type: %d", addr->sa_family);
+ break;
+ }
+ return buf;
+}
+
+/**
+ * svc_print_addr - Format rq_addr field for printing
+ * @rqstp: svc_rqst struct containing address to print
+ * @buf: target buffer for formatted address
+ * @len: length of target buffer
+ *
+ */
+char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
+{
+ return __svc_print_addr(svc_addr(rqstp), buf, len);
+}
+EXPORT_SYMBOL_GPL(svc_print_addr);
/*
- * Queue up an idle server thread. Must have serv->sv_lock held.
+ * Queue up an idle server thread. Must have pool->sp_lock held.
* Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't polute
+ * use as many different threads as we need, and the rest don't pollute
* the cache.
*/
static inline void
-svc_serv_enqueue(struct svc_serv *serv, struct svc_rqst *rqstp)
+svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
- list_add(&rqstp->rq_list, &serv->sv_threads);
+ list_add(&rqstp->rq_list, &pool->sp_threads);
}
/*
- * Dequeue an nfsd thread. Must have serv->sv_lock held.
+ * Dequeue an nfsd thread. Must have pool->sp_lock held.
*/
static inline void
-svc_serv_dequeue(struct svc_serv *serv, struct svc_rqst *rqstp)
+svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
list_del(&rqstp->rq_list);
}
/*
* Release an skbuff after use
*/
-static inline void
-svc_release_skb(struct svc_rqst *rqstp)
+static void svc_release_skb(struct svc_rqst *rqstp)
{
- struct sk_buff *skb = rqstp->rq_skbuff;
+ struct sk_buff *skb = rqstp->rq_xprt_ctxt;
struct svc_deferred_req *dr = rqstp->rq_deferred;
if (skb) {
- rqstp->rq_skbuff = NULL;
+ rqstp->rq_xprt_ctxt = NULL;
dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
skb_free_datagram(rqstp->rq_sock->sk_sk, skb);
}
/*
- * Any space to write?
- */
-static inline unsigned long
-svc_sock_wspace(struct svc_sock *svsk)
-{
- int wspace;
-
- if (svsk->sk_sock->type == SOCK_STREAM)
- wspace = sk_stream_wspace(svsk->sk_sk);
- else
- wspace = sock_wspace(svsk->sk_sk);
-
- return wspace;
-}
-
-/*
* Queue up a socket with data pending. If there are idle nfsd
* processes, wake 'em up.
*
static void
svc_sock_enqueue(struct svc_sock *svsk)
{
- struct svc_serv *serv = svsk->sk_server;
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
+ struct svc_pool *pool;
struct svc_rqst *rqstp;
+ int cpu;
- if (!(svsk->sk_flags &
- ( (1<<SK_CONN)|(1<<SK_DATA)|(1<<SK_CLOSE)|(1<<SK_DEFERRED)) ))
+ if (!(svsk->sk_xprt.xpt_flags &
+ ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
return;
- if (test_bit(SK_DEAD, &svsk->sk_flags))
+ if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags))
return;
- spin_lock_bh(&serv->sv_lock);
+ cpu = get_cpu();
+ pool = svc_pool_for_cpu(svsk->sk_xprt.xpt_server, cpu);
+ put_cpu();
- if (!list_empty(&serv->sv_threads) &&
- !list_empty(&serv->sv_sockets))
+ spin_lock_bh(&pool->sp_lock);
+
+ if (!list_empty(&pool->sp_threads) &&
+ !list_empty(&pool->sp_sockets))
printk(KERN_ERR
"svc_sock_enqueue: threads and sockets both waiting??\n");
- if (test_bit(SK_DEAD, &svsk->sk_flags)) {
+ if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags)) {
/* Don't enqueue dead sockets */
dprintk("svc: socket %p is dead, not enqueued\n", svsk->sk_sk);
goto out_unlock;
}
- if (test_bit(SK_BUSY, &svsk->sk_flags)) {
- /* Don't enqueue socket while daemon is receiving */
+ /* Mark socket as busy. It will remain in this state until the
+ * server has processed all pending data and put the socket back
+ * on the idle list. We update XPT_BUSY atomically because
+ * it also guards against trying to enqueue the svc_sock twice.
+ */
+ if (test_and_set_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)) {
+ /* Don't enqueue socket while already enqueued */
dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk);
goto out_unlock;
}
+ BUG_ON(svsk->sk_xprt.xpt_pool != NULL);
+ svsk->sk_xprt.xpt_pool = pool;
- set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
- if (((svsk->sk_reserved + serv->sv_bufsz)*2
- > svc_sock_wspace(svsk))
- && !test_bit(SK_CLOSE, &svsk->sk_flags)
- && !test_bit(SK_CONN, &svsk->sk_flags)) {
+ /* Handle pending connection */
+ if (test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags))
+ goto process;
+
+ /* Handle close in-progress */
+ if (test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags))
+ goto process;
+
+ /* Check if we have space to reply to a request */
+ if (!svsk->sk_xprt.xpt_ops->xpo_has_wspace(&svsk->sk_xprt)) {
/* Don't enqueue while not enough space for reply */
- dprintk("svc: socket %p no space, %d*2 > %ld, not enqueued\n",
- svsk->sk_sk, svsk->sk_reserved+serv->sv_bufsz,
- svc_sock_wspace(svsk));
+ dprintk("svc: no write space, socket %p not enqueued\n", svsk);
+ svsk->sk_xprt.xpt_pool = NULL;
+ clear_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags);
goto out_unlock;
}
- clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
- /* Mark socket as busy. It will remain in this state until the
- * server has processed all pending data and put the socket back
- * on the idle list.
- */
- set_bit(SK_BUSY, &svsk->sk_flags);
-
- if (!list_empty(&serv->sv_threads)) {
- rqstp = list_entry(serv->sv_threads.next,
+ process:
+ if (!list_empty(&pool->sp_threads)) {
+ rqstp = list_entry(pool->sp_threads.next,
struct svc_rqst,
rq_list);
dprintk("svc: socket %p served by daemon %p\n",
svsk->sk_sk, rqstp);
- svc_serv_dequeue(serv, rqstp);
+ svc_thread_dequeue(pool, rqstp);
if (rqstp->rq_sock)
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_sock_enqueue: server %p, rq_sock=%p!\n",
rqstp, rqstp->rq_sock);
rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
- rqstp->rq_reserved = serv->sv_bufsz;
- svsk->sk_reserved += rqstp->rq_reserved;
+ svc_xprt_get(&svsk->sk_xprt);
+ rqstp->rq_reserved = serv->sv_max_mesg;
+ atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
+ BUG_ON(svsk->sk_xprt.xpt_pool != pool);
wake_up(&rqstp->rq_wait);
} else {
dprintk("svc: socket %p put into queue\n", svsk->sk_sk);
- list_add_tail(&svsk->sk_ready, &serv->sv_sockets);
+ list_add_tail(&svsk->sk_xprt.xpt_ready, &pool->sp_sockets);
+ BUG_ON(svsk->sk_xprt.xpt_pool != pool);
}
out_unlock:
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&pool->sp_lock);
}
/*
- * Dequeue the first socket. Must be called with the serv->sv_lock held.
+ * Dequeue the first socket. Must be called with the pool->sp_lock held.
*/
static inline struct svc_sock *
-svc_sock_dequeue(struct svc_serv *serv)
+svc_sock_dequeue(struct svc_pool *pool)
{
struct svc_sock *svsk;
- if (list_empty(&serv->sv_sockets))
+ if (list_empty(&pool->sp_sockets))
return NULL;
- svsk = list_entry(serv->sv_sockets.next,
- struct svc_sock, sk_ready);
- list_del_init(&svsk->sk_ready);
+ svsk = list_entry(pool->sp_sockets.next,
+ struct svc_sock, sk_xprt.xpt_ready);
+ list_del_init(&svsk->sk_xprt.xpt_ready);
dprintk("svc: socket %p dequeued, inuse=%d\n",
- svsk->sk_sk, svsk->sk_inuse);
+ svsk->sk_sk, atomic_read(&svsk->sk_xprt.xpt_ref.refcount));
return svsk;
}
/*
* Having read something from a socket, check whether it
* needs to be re-enqueued.
- * Note: SK_DATA only gets cleared when a read-attempt finds
+ * Note: XPT_DATA only gets cleared when a read-attempt finds
* no (or insufficient) data.
*/
static inline void
svc_sock_received(struct svc_sock *svsk)
{
- clear_bit(SK_BUSY, &svsk->sk_flags);
+ svsk->sk_xprt.xpt_pool = NULL;
+ clear_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
}
if (space < rqstp->rq_reserved) {
struct svc_sock *svsk = rqstp->rq_sock;
- spin_lock_bh(&svsk->sk_server->sv_lock);
- svsk->sk_reserved -= (rqstp->rq_reserved - space);
+ atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved);
rqstp->rq_reserved = space;
- spin_unlock_bh(&svsk->sk_server->sv_lock);
svc_sock_enqueue(svsk);
}
}
-/*
- * Release a socket after use.
- */
-static inline void
-svc_sock_put(struct svc_sock *svsk)
-{
- struct svc_serv *serv = svsk->sk_server;
-
- spin_lock_bh(&serv->sv_lock);
- if (!--(svsk->sk_inuse) && test_bit(SK_DEAD, &svsk->sk_flags)) {
- spin_unlock_bh(&serv->sv_lock);
- dprintk("svc: releasing dead socket\n");
- sock_release(svsk->sk_sock);
- kfree(svsk);
- }
- else
- spin_unlock_bh(&serv->sv_lock);
-}
-
static void
svc_sock_release(struct svc_rqst *rqstp)
{
struct svc_sock *svsk = rqstp->rq_sock;
- svc_release_skb(rqstp);
+ rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
- svc_free_allpages(rqstp);
+ svc_free_res_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
svc_reserve(rqstp, 0);
rqstp->rq_sock = NULL;
- svc_sock_put(svsk);
+ svc_xprt_put(&svsk->sk_xprt);
}
/*
* External function to wake up a server waiting for data
+ * This really only makes sense for services like lockd
+ * which have exactly one thread anyway.
*/
void
svc_wake_up(struct svc_serv *serv)
{
struct svc_rqst *rqstp;
+ unsigned int i;
+ struct svc_pool *pool;
+
+ for (i = 0; i < serv->sv_nrpools; i++) {
+ pool = &serv->sv_pools[i];
+
+ spin_lock_bh(&pool->sp_lock);
+ if (!list_empty(&pool->sp_threads)) {
+ rqstp = list_entry(pool->sp_threads.next,
+ struct svc_rqst,
+ rq_list);
+ dprintk("svc: daemon %p woken up.\n", rqstp);
+ /*
+ svc_thread_dequeue(pool, rqstp);
+ rqstp->rq_sock = NULL;
+ */
+ wake_up(&rqstp->rq_wait);
+ }
+ spin_unlock_bh(&pool->sp_lock);
+ }
+}
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&serv->sv_threads)) {
- rqstp = list_entry(serv->sv_threads.next,
- struct svc_rqst,
- rq_list);
- dprintk("svc: daemon %p woken up.\n", rqstp);
- /*
- svc_serv_dequeue(serv, rqstp);
- rqstp->rq_sock = NULL;
- */
- wake_up(&rqstp->rq_wait);
+union svc_pktinfo_u {
+ struct in_pktinfo pkti;
+ struct in6_pktinfo pkti6;
+};
+#define SVC_PKTINFO_SPACE \
+ CMSG_SPACE(sizeof(union svc_pktinfo_u))
+
+static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
+{
+ switch (rqstp->rq_sock->sk_sk->sk_family) {
+ case AF_INET: {
+ struct in_pktinfo *pki = CMSG_DATA(cmh);
+
+ cmh->cmsg_level = SOL_IP;
+ cmh->cmsg_type = IP_PKTINFO;
+ pki->ipi_ifindex = 0;
+ pki->ipi_spec_dst.s_addr = rqstp->rq_daddr.addr.s_addr;
+ cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
+ }
+ break;
+
+ case AF_INET6: {
+ struct in6_pktinfo *pki = CMSG_DATA(cmh);
+
+ cmh->cmsg_level = SOL_IPV6;
+ cmh->cmsg_type = IPV6_PKTINFO;
+ pki->ipi6_ifindex = 0;
+ ipv6_addr_copy(&pki->ipi6_addr,
+ &rqstp->rq_daddr.addr6);
+ cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
+ }
+ break;
}
- spin_unlock_bh(&serv->sv_lock);
+ return;
}
/*
struct svc_sock *svsk = rqstp->rq_sock;
struct socket *sock = svsk->sk_sock;
int slen;
- char buffer[CMSG_SPACE(sizeof(struct in_pktinfo))];
- struct cmsghdr *cmh = (struct cmsghdr *)buffer;
- struct in_pktinfo *pki = (struct in_pktinfo *)CMSG_DATA(cmh);
+ union {
+ struct cmsghdr hdr;
+ long all[SVC_PKTINFO_SPACE / sizeof(long)];
+ } buffer;
+ struct cmsghdr *cmh = &buffer.hdr;
int len = 0;
int result;
int size;
size_t base = xdr->page_base;
unsigned int pglen = xdr->page_len;
unsigned int flags = MSG_MORE;
+ char buf[RPC_MAX_ADDRBUFLEN];
slen = xdr->len;
if (rqstp->rq_prot == IPPROTO_UDP) {
- /* set the source and destination */
- struct msghdr msg;
- msg.msg_name = &rqstp->rq_addr;
- msg.msg_namelen = sizeof(rqstp->rq_addr);
- msg.msg_iov = NULL;
- msg.msg_iovlen = 0;
- msg.msg_flags = MSG_MORE;
-
- msg.msg_control = cmh;
- msg.msg_controllen = sizeof(buffer);
- cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
- cmh->cmsg_level = SOL_IP;
- cmh->cmsg_type = IP_PKTINFO;
- pki->ipi_ifindex = 0;
- pki->ipi_spec_dst.s_addr = rqstp->rq_daddr;
+ struct msghdr msg = {
+ .msg_name = &rqstp->rq_addr,
+ .msg_namelen = rqstp->rq_addrlen,
+ .msg_control = cmh,
+ .msg_controllen = sizeof(buffer),
+ .msg_flags = MSG_MORE,
+ };
+
+ svc_set_cmsg_data(rqstp, cmh);
if (sock_sendmsg(sock, &msg, 0) < 0)
goto out;
/* send head */
if (slen == xdr->head[0].iov_len)
flags = 0;
- len = sock->ops->sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags);
+ len = kernel_sendpage(sock, rqstp->rq_respages[0], 0,
+ xdr->head[0].iov_len, flags);
if (len != xdr->head[0].iov_len)
goto out;
slen -= xdr->head[0].iov_len;
while (pglen > 0) {
if (slen == size)
flags = 0;
- result = sock->ops->sendpage(sock, *ppage, base, size, flags);
+ result = kernel_sendpage(sock, *ppage, base, size, flags);
if (result > 0)
len += result;
if (result != size)
}
/* send tail */
if (xdr->tail[0].iov_len) {
- result = sock->ops->sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage],
- ((unsigned long)xdr->tail[0].iov_base)& (PAGE_SIZE-1),
+ result = kernel_sendpage(sock, rqstp->rq_respages[0],
+ ((unsigned long)xdr->tail[0].iov_base)
+ & (PAGE_SIZE-1),
xdr->tail[0].iov_len, 0);
if (result > 0)
len += result;
}
out:
- dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %x)\n",
- rqstp->rq_sock, xdr->head[0].iov_base, xdr->head[0].iov_len, xdr->len, len,
- rqstp->rq_addr.sin_addr.s_addr);
+ dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n",
+ rqstp->rq_sock, xdr->head[0].iov_base, xdr->head[0].iov_len,
+ xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));
return len;
}
/*
+ * Report socket names for nfsdfs
+ */
+static int one_sock_name(char *buf, struct svc_sock *svsk)
+{
+ int len;
+
+ switch(svsk->sk_sk->sk_family) {
+ case AF_INET:
+ len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n",
+ svsk->sk_sk->sk_protocol==IPPROTO_UDP?
+ "udp" : "tcp",
+ NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr),
+ inet_sk(svsk->sk_sk)->num);
+ break;
+ default:
+ len = sprintf(buf, "*unknown-%d*\n",
+ svsk->sk_sk->sk_family);
+ }
+ return len;
+}
+
+int
+svc_sock_names(char *buf, struct svc_serv *serv, char *toclose)
+{
+ struct svc_sock *svsk, *closesk = NULL;
+ int len = 0;
+
+ if (!serv)
+ return 0;
+ spin_lock_bh(&serv->sv_lock);
+ list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list) {
+ int onelen = one_sock_name(buf+len, svsk);
+ if (toclose && strcmp(toclose, buf+len) == 0)
+ closesk = svsk;
+ else
+ len += onelen;
+ }
+ spin_unlock_bh(&serv->sv_lock);
+ if (closesk)
+ /* Should unregister with portmap, but you cannot
+ * unregister just one protocol...
+ */
+ svc_close_xprt(&closesk->sk_xprt);
+ else if (toclose)
+ return -ENOENT;
+ return len;
+}
+EXPORT_SYMBOL(svc_sock_names);
+
+/*
* Check input queue length
*/
static int
svc_recv_available(struct svc_sock *svsk)
{
- mm_segment_t oldfs;
struct socket *sock = svsk->sk_sock;
int avail, err;
- oldfs = get_fs(); set_fs(KERNEL_DS);
- err = sock->ops->ioctl(sock, TIOCINQ, (unsigned long) &avail);
- set_fs(oldfs);
+ err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);
return (err >= 0)? avail : err;
}
static int
svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
{
- struct msghdr msg;
- struct socket *sock;
- int len, alen;
-
- rqstp->rq_addrlen = sizeof(rqstp->rq_addr);
- sock = rqstp->rq_sock->sk_sock;
+ struct svc_sock *svsk = rqstp->rq_sock;
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT,
+ };
+ struct sockaddr *sin;
+ int len;
- msg.msg_name = &rqstp->rq_addr;
- msg.msg_namelen = sizeof(rqstp->rq_addr);
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
-
- msg.msg_flags = MSG_DONTWAIT;
-
- len = kernel_recvmsg(sock, &msg, iov, nr, buflen, MSG_DONTWAIT);
+ len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
+ msg.msg_flags);
/* sock_recvmsg doesn't fill in the name/namelen, so we must..
- * possibly we should cache this in the svc_sock structure
- * at accept time. FIXME
*/
- alen = sizeof(rqstp->rq_addr);
- sock->ops->getname(sock, (struct sockaddr *)&rqstp->rq_addr, &alen, 1);
+ memcpy(&rqstp->rq_addr, &svsk->sk_remote, svsk->sk_remotelen);
+ rqstp->rq_addrlen = svsk->sk_remotelen;
+
+ /* Destination address in request is needed for binding the
+ * source address in RPC callbacks later.
+ */
+ sin = (struct sockaddr *)&svsk->sk_local;
+ switch (sin->sa_family) {
+ case AF_INET:
+ rqstp->rq_daddr.addr = ((struct sockaddr_in *)sin)->sin_addr;
+ break;
+ case AF_INET6:
+ rqstp->rq_daddr.addr6 = ((struct sockaddr_in6 *)sin)->sin6_addr;
+ break;
+ }
dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
- rqstp->rq_sock, iov[0].iov_base, iov[0].iov_len, len);
+ svsk, iov[0].iov_base, iov[0].iov_len, len);
return len;
}
if (svsk) {
dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
- svsk, sk, count, test_bit(SK_BUSY, &svsk->sk_flags));
- set_bit(SK_DATA, &svsk->sk_flags);
+ svsk, sk, count,
+ test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
}
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
if (svsk) {
dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
- svsk, sk, test_bit(SK_BUSY, &svsk->sk_flags));
+ svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
svc_sock_enqueue(svsk);
}
}
}
+static inline void svc_udp_get_dest_address(struct svc_rqst *rqstp,
+ struct cmsghdr *cmh)
+{
+ switch (rqstp->rq_sock->sk_sk->sk_family) {
+ case AF_INET: {
+ struct in_pktinfo *pki = CMSG_DATA(cmh);
+ rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
+ break;
+ }
+ case AF_INET6: {
+ struct in6_pktinfo *pki = CMSG_DATA(cmh);
+ ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr);
+ break;
+ }
+ }
+}
+
/*
* Receive a datagram from a UDP socket.
*/
svc_udp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk = rqstp->rq_sock;
- struct svc_serv *serv = svsk->sk_server;
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct sk_buff *skb;
+ union {
+ struct cmsghdr hdr;
+ long all[SVC_PKTINFO_SPACE / sizeof(long)];
+ } buffer;
+ struct cmsghdr *cmh = &buffer.hdr;
int err, len;
-
- if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
+ struct msghdr msg = {
+ .msg_name = svc_addr(rqstp),
+ .msg_control = cmh,
+ .msg_controllen = sizeof(buffer),
+ .msg_flags = MSG_DONTWAIT,
+ };
+
+ if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
/* udp sockets need large rcvbuf as all pending
* requests are still in that buffer. sndbuf must
* also be large enough that there is enough space
- * for one reply per thread.
+ * for one reply per thread. We count all threads
+ * rather than threads in a particular pool, which
+ * provides an upper bound on the number of threads
+ * which will access the socket.
*/
svc_sock_setbufsize(svsk->sk_sock,
- (serv->sv_nrthreads+3) * serv->sv_bufsz,
- (serv->sv_nrthreads+3) * serv->sv_bufsz);
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg,
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg);
if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
svc_sock_received(svsk);
return svc_deferred_recv(rqstp);
}
- clear_bit(SK_DATA, &svsk->sk_flags);
- while ((skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err)) == NULL) {
- if (err == -EAGAIN) {
- svc_sock_received(svsk);
- return err;
+ clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ skb = NULL;
+ err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
+ 0, 0, MSG_PEEK | MSG_DONTWAIT);
+ if (err >= 0)
+ skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err);
+
+ if (skb == NULL) {
+ if (err != -EAGAIN) {
+ /* possibly an icmp error */
+ dprintk("svc: recvfrom returned error %d\n", -err);
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
}
- /* possibly an icmp error */
- dprintk("svc: recvfrom returned error %d\n", -err);
+ svc_sock_received(svsk);
+ return -EAGAIN;
}
- if (skb->tstamp.off_sec == 0) {
- struct timeval tv;
-
- tv.tv_sec = xtime.tv_sec;
- tv.tv_usec = xtime.tv_nsec / NSEC_PER_USEC;
- skb_set_timestamp(skb, &tv);
- /* Don't enable netstamp, sunrpc doesn't
+ rqstp->rq_addrlen = sizeof(rqstp->rq_addr);
+ if (skb->tstamp.tv64 == 0) {
+ skb->tstamp = ktime_get_real();
+ /* Don't enable netstamp, sunrpc doesn't
need that much accuracy */
}
- skb_get_timestamp(skb, &svsk->sk_sk->sk_stamp);
- set_bit(SK_DATA, &svsk->sk_flags); /* there may be more data... */
+ svsk->sk_sk->sk_stamp = skb->tstamp;
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
/*
* Maybe more packets - kick another thread ASAP.
len = skb->len - sizeof(struct udphdr);
rqstp->rq_arg.len = len;
- rqstp->rq_prot = IPPROTO_UDP;
+ rqstp->rq_prot = IPPROTO_UDP;
- /* Get sender address */
- rqstp->rq_addr.sin_family = AF_INET;
- rqstp->rq_addr.sin_port = skb->h.uh->source;
- rqstp->rq_addr.sin_addr.s_addr = skb->nh.iph->saddr;
- rqstp->rq_daddr = skb->nh.iph->daddr;
+ if (cmh->cmsg_level != IPPROTO_IP ||
+ cmh->cmsg_type != IP_PKTINFO) {
+ if (net_ratelimit())
+ printk("rpcsvc: received unknown control message:"
+ "%d/%d\n",
+ cmh->cmsg_level, cmh->cmsg_type);
+ skb_free_datagram(svsk->sk_sk, skb);
+ return 0;
+ }
+ svc_udp_get_dest_address(rqstp, cmh);
if (skb_is_nonlinear(skb)) {
/* we have to copy */
return 0;
}
local_bh_enable();
- skb_free_datagram(svsk->sk_sk, skb);
+ skb_free_datagram(svsk->sk_sk, skb);
} else {
/* we can use it in-place */
rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr);
skb_free_datagram(svsk->sk_sk, skb);
return 0;
}
- rqstp->rq_skbuff = skb;
+ rqstp->rq_xprt_ctxt = skb;
}
rqstp->rq_arg.page_base = 0;
if (len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = len;
rqstp->rq_arg.page_len = 0;
+ rqstp->rq_respages = rqstp->rq_pages+1;
} else {
rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
- rqstp->rq_argused += (rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE;
+ rqstp->rq_respages = rqstp->rq_pages + 1 +
+ DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
}
if (serv->sv_stats)
return error;
}
-static void
-svc_udp_init(struct svc_sock *svsk)
+static void svc_udp_prep_reply_hdr(struct svc_rqst *rqstp)
+{
+}
+
+static int svc_udp_has_wspace(struct svc_xprt *xprt)
+{
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+ struct svc_serv *serv = xprt->xpt_server;
+ unsigned long required;
+
+ /*
+ * Set the SOCK_NOSPACE flag before checking the available
+ * sock space.
+ */
+ set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
+ required = atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg;
+ if (required*2 > sock_wspace(svsk->sk_sk))
+ return 0;
+ clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
+ return 1;
+}
+
+static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
{
+ BUG();
+ return NULL;
+}
+
+static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
+ struct sockaddr *sa, int salen,
+ int flags)
+{
+ return svc_create_socket(serv, IPPROTO_UDP, sa, salen, flags);
+}
+
+static struct svc_xprt_ops svc_udp_ops = {
+ .xpo_create = svc_udp_create,
+ .xpo_recvfrom = svc_udp_recvfrom,
+ .xpo_sendto = svc_udp_sendto,
+ .xpo_release_rqst = svc_release_skb,
+ .xpo_detach = svc_sock_detach,
+ .xpo_free = svc_sock_free,
+ .xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
+ .xpo_has_wspace = svc_udp_has_wspace,
+ .xpo_accept = svc_udp_accept,
+};
+
+static struct svc_xprt_class svc_udp_class = {
+ .xcl_name = "udp",
+ .xcl_owner = THIS_MODULE,
+ .xcl_ops = &svc_udp_ops,
+ .xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
+};
+
+static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
+{
+ int one = 1;
+ mm_segment_t oldfs;
+
+ svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv);
svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
svsk->sk_sk->sk_write_space = svc_write_space;
- svsk->sk_recvfrom = svc_udp_recvfrom;
- svsk->sk_sendto = svc_udp_sendto;
/* initialise setting must have enough space to
- * receive and respond to one request.
+ * receive and respond to one request.
* svc_udp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk->sk_sock,
- 3 * svsk->sk_server->sv_bufsz,
- 3 * svsk->sk_server->sv_bufsz);
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
+
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* might have come in before data_ready set up */
+ set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
- set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */
- set_bit(SK_CHNGBUF, &svsk->sk_flags);
+ oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ /* make sure we get destination address info */
+ svsk->sk_sock->ops->setsockopt(svsk->sk_sock, IPPROTO_IP, IP_PKTINFO,
+ (char __user *)&one, sizeof(one));
+ set_fs(oldfs);
}
/*
*/
if (sk->sk_state == TCP_LISTEN) {
if (svsk) {
- set_bit(SK_CONN, &svsk->sk_flags);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
} else
printk("svc: socket %p: no user data\n", sk);
if (!svsk)
printk("svc: socket %p: no user data\n", sk);
else {
- set_bit(SK_CLOSE, &svsk->sk_flags);
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
}
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
dprintk("svc: socket %p TCP data ready (svsk %p)\n",
sk, sk->sk_user_data);
if (svsk) {
- set_bit(SK_DATA, &svsk->sk_flags);
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
}
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep);
}
+static inline int svc_port_is_privileged(struct sockaddr *sin)
+{
+ switch (sin->sa_family) {
+ case AF_INET:
+ return ntohs(((struct sockaddr_in *)sin)->sin_port)
+ < PROT_SOCK;
+ case AF_INET6:
+ return ntohs(((struct sockaddr_in6 *)sin)->sin6_port)
+ < PROT_SOCK;
+ default:
+ return 0;
+ }
+}
+
/*
* Accept a TCP connection
*/
-static void
-svc_tcp_accept(struct svc_sock *svsk)
+static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
{
- struct sockaddr_in sin;
- struct svc_serv *serv = svsk->sk_server;
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+ struct sockaddr_storage addr;
+ struct sockaddr *sin = (struct sockaddr *) &addr;
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct socket *sock = svsk->sk_sock;
struct socket *newsock;
- const struct proto_ops *ops;
struct svc_sock *newsvsk;
int err, slen;
+ char buf[RPC_MAX_ADDRBUFLEN];
dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
if (!sock)
- return;
+ return NULL;
- err = sock_create_lite(PF_INET, SOCK_STREAM, IPPROTO_TCP, &newsock);
- if (err) {
+ clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+ err = kernel_accept(sock, &newsock, O_NONBLOCK);
+ if (err < 0) {
if (err == -ENOMEM)
printk(KERN_WARNING "%s: no more sockets!\n",
serv->sv_name);
- return;
- }
-
- dprintk("svc: tcp_accept %p allocated\n", newsock);
- newsock->ops = ops = sock->ops;
-
- clear_bit(SK_CONN, &svsk->sk_flags);
- if ((err = ops->accept(sock, newsock, O_NONBLOCK)) < 0) {
- if (err != -EAGAIN && net_ratelimit())
+ else if (err != -EAGAIN && net_ratelimit())
printk(KERN_WARNING "%s: accept failed (err %d)!\n",
serv->sv_name, -err);
- goto failed; /* aborted connection or whatever */
+ return NULL;
}
- set_bit(SK_CONN, &svsk->sk_flags);
- svc_sock_enqueue(svsk);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
- slen = sizeof(sin);
- err = ops->getname(newsock, (struct sockaddr *) &sin, &slen, 1);
+ err = kernel_getpeername(newsock, sin, &slen);
if (err < 0) {
if (net_ratelimit())
printk(KERN_WARNING "%s: peername failed (err %d)!\n",
}
/* Ideally, we would want to reject connections from unauthorized
- * hosts here, but when we get encription, the IP of the host won't
- * tell us anything. For now just warn about unpriv connections.
+ * hosts here, but when we get encryption, the IP of the host won't
+ * tell us anything. For now just warn about unpriv connections.
*/
- if (ntohs(sin.sin_port) >= 1024) {
+ if (!svc_port_is_privileged(sin)) {
dprintk(KERN_WARNING
- "%s: connect from unprivileged port: %u.%u.%u.%u:%d\n",
- serv->sv_name,
- NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
+ "%s: connect from unprivileged port: %s\n",
+ serv->sv_name,
+ __svc_print_addr(sin, buf, sizeof(buf)));
}
-
- dprintk("%s: connect from %u.%u.%u.%u:%04x\n", serv->sv_name,
- NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
+ dprintk("%s: connect from %s\n", serv->sv_name,
+ __svc_print_addr(sin, buf, sizeof(buf)));
/* make sure that a write doesn't block forever when
* low on memory
*/
newsock->sk->sk_sndtimeo = HZ*30;
- if (!(newsvsk = svc_setup_socket(serv, newsock, &err, 0)))
+ if (!(newsvsk = svc_setup_socket(serv, newsock, &err,
+ (SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY))))
goto failed;
-
-
- /* make sure that we don't have too many active connections.
- * If we have, something must be dropped.
- *
- * There's no point in trying to do random drop here for
- * DoS prevention. The NFS clients does 1 reconnect in 15
- * seconds. An attacker can easily beat that.
- *
- * The only somewhat efficient mechanism would be if drop
- * old connections from the same IP first. But right now
- * we don't even record the client IP in svc_sock.
- */
- if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
- struct svc_sock *svsk = NULL;
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&serv->sv_tempsocks)) {
- if (net_ratelimit()) {
- /* Try to help the admin */
- printk(KERN_NOTICE "%s: too many open TCP "
- "sockets, consider increasing the "
- "number of nfsd threads\n",
- serv->sv_name);
- printk(KERN_NOTICE "%s: last TCP connect from "
- "%u.%u.%u.%u:%d\n",
- serv->sv_name,
- NIPQUAD(sin.sin_addr.s_addr),
- ntohs(sin.sin_port));
- }
- /*
- * Always select the oldest socket. It's not fair,
- * but so is life
- */
- svsk = list_entry(serv->sv_tempsocks.prev,
- struct svc_sock,
- sk_list);
- set_bit(SK_CLOSE, &svsk->sk_flags);
- svsk->sk_inuse ++;
- }
- spin_unlock_bh(&serv->sv_lock);
-
- if (svsk) {
- svc_sock_enqueue(svsk);
- svc_sock_put(svsk);
- }
-
+ memcpy(&newsvsk->sk_remote, sin, slen);
+ newsvsk->sk_remotelen = slen;
+ err = kernel_getsockname(newsock, sin, &slen);
+ if (unlikely(err < 0)) {
+ dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
+ slen = offsetof(struct sockaddr, sa_data);
}
+ memcpy(&newsvsk->sk_local, sin, slen);
+
+ svc_sock_received(newsvsk);
if (serv->sv_stats)
serv->sv_stats->nettcpconn++;
- return;
+ return &newsvsk->sk_xprt;
failed:
sock_release(newsock);
- return;
+ return NULL;
}
/*
svc_tcp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk = rqstp->rq_sock;
- struct svc_serv *serv = svsk->sk_server;
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
int len;
- struct kvec vec[RPCSVC_MAXPAGES];
+ struct kvec *vec;
int pnum, vlen;
dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
- svsk, test_bit(SK_DATA, &svsk->sk_flags),
- test_bit(SK_CONN, &svsk->sk_flags),
- test_bit(SK_CLOSE, &svsk->sk_flags));
+ svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
+ test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
+ test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
svc_sock_received(svsk);
return svc_deferred_recv(rqstp);
}
- if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
- svc_delete_socket(svsk);
- return 0;
- }
-
- if (test_bit(SK_CONN, &svsk->sk_flags)) {
- svc_tcp_accept(svsk);
- svc_sock_received(svsk);
- return 0;
- }
-
- if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
+ if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
/* sndbuf needs to have room for one request
* per thread, otherwise we can stall even when the
* network isn't a bottleneck.
+ *
+ * We count all threads rather than threads in a
+ * particular pool, which provides an upper bound
+ * on the number of threads which will access the socket.
+ *
* rcvbuf just needs to be able to hold a few requests.
- * Normally they will be removed from the queue
+ * Normally they will be removed from the queue
* as soon a a complete request arrives.
*/
svc_sock_setbufsize(svsk->sk_sock,
- (serv->sv_nrthreads+3) * serv->sv_bufsz,
- 3 * serv->sv_bufsz);
+ (serv->sv_nrthreads+3) * serv->sv_max_mesg,
+ 3 * serv->sv_max_mesg);
- clear_bit(SK_DATA, &svsk->sk_flags);
+ clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
/* Receive data. If we haven't got the record length yet, get
* the next four bytes. Otherwise try to gobble up as much as
if (len < want) {
dprintk("svc: short recvfrom while reading record length (%d of %lu)\n",
- len, want);
+ len, want);
svc_sock_received(svsk);
return -EAGAIN; /* record header not complete */
}
* bit set in the fragment length header.
* But apparently no known nfs clients send fragmented
* records. */
- printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx (non-terminal)\n",
- (unsigned long) svsk->sk_reclen);
+ if (net_ratelimit())
+ printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
+ " (non-terminal)\n",
+ (unsigned long) svsk->sk_reclen);
goto err_delete;
}
svsk->sk_reclen &= 0x7fffffff;
dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
- if (svsk->sk_reclen > serv->sv_bufsz) {
- printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx (large)\n",
- (unsigned long) svsk->sk_reclen);
+ if (svsk->sk_reclen > serv->sv_max_mesg) {
+ if (net_ratelimit())
+ printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
+ " (large)\n",
+ (unsigned long) svsk->sk_reclen);
goto err_delete;
}
}
return -EAGAIN; /* record not complete */
}
len = svsk->sk_reclen;
- set_bit(SK_DATA, &svsk->sk_flags);
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ vec = rqstp->rq_vec;
vec[0] = rqstp->rq_arg.head[0];
vlen = PAGE_SIZE;
pnum = 1;
while (vlen < len) {
- vec[pnum].iov_base = page_address(rqstp->rq_argpages[rqstp->rq_argused++]);
+ vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]);
vec[pnum].iov_len = PAGE_SIZE;
pnum++;
vlen += PAGE_SIZE;
}
+ rqstp->rq_respages = &rqstp->rq_pages[pnum];
/* Now receive data */
len = svc_recvfrom(rqstp, vec, pnum, len);
rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
}
- rqstp->rq_skbuff = NULL;
+ rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
/* Reset TCP read info */
return len;
err_delete:
- svc_delete_socket(svsk);
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
return -EAGAIN;
error:
svc_sock_received(svsk);
} else {
printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
- svsk->sk_server->sv_name, -len);
- svc_sock_received(svsk);
+ svsk->sk_xprt.xpt_server->sv_name, -len);
+ goto err_delete;
}
return len;
{
struct xdr_buf *xbufp = &rqstp->rq_res;
int sent;
- u32 reclen;
+ __be32 reclen;
/* Set up the first element of the reply kvec.
* Any other kvecs that may be in use have been taken
reclen = htonl(0x80000000|((xbufp->len ) - 4));
memcpy(xbufp->head[0].iov_base, &reclen, 4);
- if (test_bit(SK_DEAD, &rqstp->rq_sock->sk_flags))
+ if (test_bit(XPT_DEAD, &rqstp->rq_sock->sk_xprt.xpt_flags))
return -ENOTCONN;
sent = svc_sendto(rqstp, &rqstp->rq_res);
if (sent != xbufp->len) {
printk(KERN_NOTICE "rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
- rqstp->rq_sock->sk_server->sv_name,
+ rqstp->rq_sock->sk_xprt.xpt_server->sv_name,
(sent<0)?"got error":"sent only",
sent, xbufp->len);
- svc_delete_socket(rqstp->rq_sock);
+ set_bit(XPT_CLOSE, &rqstp->rq_sock->sk_xprt.xpt_flags);
+ svc_sock_enqueue(rqstp->rq_sock);
sent = -EAGAIN;
}
return sent;
}
-static void
-svc_tcp_init(struct svc_sock *svsk)
+/*
+ * Setup response header. TCP has a 4B record length field.
+ */
+static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+{
+ struct kvec *resv = &rqstp->rq_res.head[0];
+
+ /* tcp needs a space for the record length... */
+ svc_putnl(resv, 0);
+}
+
+static int svc_tcp_has_wspace(struct svc_xprt *xprt)
+{
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+ struct svc_serv *serv = svsk->sk_xprt.xpt_server;
+ int required;
+ int wspace;
+
+ /*
+ * Set the SOCK_NOSPACE flag before checking the available
+ * sock space.
+ */
+ set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
+ required = atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg;
+ wspace = sk_stream_wspace(svsk->sk_sk);
+
+ if (wspace < sk_stream_min_wspace(svsk->sk_sk))
+ return 0;
+ if (required * 2 > wspace)
+ return 0;
+
+ clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
+ return 1;
+}
+
+static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
+ struct sockaddr *sa, int salen,
+ int flags)
+{
+ return svc_create_socket(serv, IPPROTO_TCP, sa, salen, flags);
+}
+
+static struct svc_xprt_ops svc_tcp_ops = {
+ .xpo_create = svc_tcp_create,
+ .xpo_recvfrom = svc_tcp_recvfrom,
+ .xpo_sendto = svc_tcp_sendto,
+ .xpo_release_rqst = svc_release_skb,
+ .xpo_detach = svc_sock_detach,
+ .xpo_free = svc_sock_free,
+ .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
+ .xpo_has_wspace = svc_tcp_has_wspace,
+ .xpo_accept = svc_tcp_accept,
+};
+
+static struct svc_xprt_class svc_tcp_class = {
+ .xcl_name = "tcp",
+ .xcl_owner = THIS_MODULE,
+ .xcl_ops = &svc_tcp_ops,
+ .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+};
+
+void svc_init_xprt_sock(void)
+{
+ svc_reg_xprt_class(&svc_tcp_class);
+ svc_reg_xprt_class(&svc_udp_class);
+}
+
+void svc_cleanup_xprt_sock(void)
+{
+ svc_unreg_xprt_class(&svc_tcp_class);
+ svc_unreg_xprt_class(&svc_udp_class);
+}
+
+static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
struct sock *sk = svsk->sk_sk;
struct tcp_sock *tp = tcp_sk(sk);
- svsk->sk_recvfrom = svc_tcp_recvfrom;
- svsk->sk_sendto = svc_tcp_sendto;
+ svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt, serv);
if (sk->sk_state == TCP_LISTEN) {
dprintk("setting up TCP socket for listening\n");
+ set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
sk->sk_data_ready = svc_tcp_listen_data_ready;
- set_bit(SK_CONN, &svsk->sk_flags);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
} else {
dprintk("setting up TCP socket for reading\n");
sk->sk_state_change = svc_tcp_state_change;
tp->nonagle = 1; /* disable Nagle's algorithm */
/* initialise setting must have enough space to
- * receive and respond to one request.
+ * receive and respond to one request.
* svc_tcp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk->sk_sock,
- 3 * svsk->sk_server->sv_bufsz,
- 3 * svsk->sk_server->sv_bufsz);
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
+ 3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
- set_bit(SK_CHNGBUF, &svsk->sk_flags);
- set_bit(SK_DATA, &svsk->sk_flags);
- if (sk->sk_state != TCP_ESTABLISHED)
- set_bit(SK_CLOSE, &svsk->sk_flags);
+ set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
+ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+ if (sk->sk_state != TCP_ESTABLISHED)
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
}
}
spin_lock_bh(&serv->sv_lock);
list_for_each(le, &serv->sv_permsocks) {
- struct svc_sock *svsk =
- list_entry(le, struct svc_sock, sk_list);
- set_bit(SK_CHNGBUF, &svsk->sk_flags);
+ struct svc_sock *svsk =
+ list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+ set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
}
list_for_each(le, &serv->sv_tempsocks) {
struct svc_sock *svsk =
- list_entry(le, struct svc_sock, sk_list);
- set_bit(SK_CHNGBUF, &svsk->sk_flags);
+ list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+ set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
}
spin_unlock_bh(&serv->sv_lock);
}
/*
- * Receive the next request on any socket.
+ * Make sure that we don't have too many active connections. If we
+ * have, something must be dropped.
+ *
+ * There's no point in trying to do random drop here for DoS
+ * prevention. The NFS clients does 1 reconnect in 15 seconds. An
+ * attacker can easily beat that.
+ *
+ * The only somewhat efficient mechanism would be if drop old
+ * connections from the same IP first. But right now we don't even
+ * record the client IP in svc_sock.
+ */
+static void svc_check_conn_limits(struct svc_serv *serv)
+{
+ if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
+ struct svc_sock *svsk = NULL;
+ spin_lock_bh(&serv->sv_lock);
+ if (!list_empty(&serv->sv_tempsocks)) {
+ if (net_ratelimit()) {
+ /* Try to help the admin */
+ printk(KERN_NOTICE "%s: too many open TCP "
+ "sockets, consider increasing the "
+ "number of nfsd threads\n",
+ serv->sv_name);
+ }
+ /*
+ * Always select the oldest socket. It's not fair,
+ * but so is life
+ */
+ svsk = list_entry(serv->sv_tempsocks.prev,
+ struct svc_sock,
+ sk_xprt.xpt_list);
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+ svc_xprt_get(&svsk->sk_xprt);
+ }
+ spin_unlock_bh(&serv->sv_lock);
+
+ if (svsk) {
+ svc_sock_enqueue(svsk);
+ svc_xprt_put(&svsk->sk_xprt);
+ }
+ }
+}
+
+/*
+ * Receive the next request on any socket. This code is carefully
+ * organised not to touch any cachelines in the shared svc_serv
+ * structure, only cachelines in the local svc_pool.
*/
int
-svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
+svc_recv(struct svc_rqst *rqstp, long timeout)
{
- struct svc_sock *svsk =NULL;
- int len;
+ struct svc_sock *svsk = NULL;
+ struct svc_serv *serv = rqstp->rq_server;
+ struct svc_pool *pool = rqstp->rq_pool;
+ int len, i;
int pages;
struct xdr_buf *arg;
DECLARE_WAITQUEUE(wait, current);
rqstp, timeout);
if (rqstp->rq_sock)
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_recv: service %p, socket not NULL!\n",
rqstp);
if (waitqueue_active(&rqstp->rq_wait))
- printk(KERN_ERR
+ printk(KERN_ERR
"svc_recv: service %p, wait queue active!\n",
rqstp);
- /* Initialize the buffers */
- /* first reclaim pages that were moved to response list */
- svc_pushback_allpages(rqstp);
/* now allocate needed pages. If we get a failure, sleep briefly */
- pages = 2 + (serv->sv_bufsz + PAGE_SIZE -1) / PAGE_SIZE;
- while (rqstp->rq_arghi < pages) {
- struct page *p = alloc_page(GFP_KERNEL);
- if (!p) {
- schedule_timeout_uninterruptible(msecs_to_jiffies(500));
- continue;
+ pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE;
+ for (i=0; i < pages ; i++)
+ while (rqstp->rq_pages[i] == NULL) {
+ struct page *p = alloc_page(GFP_KERNEL);
+ if (!p)
+ schedule_timeout_uninterruptible(msecs_to_jiffies(500));
+ rqstp->rq_pages[i] = p;
}
- rqstp->rq_argpages[rqstp->rq_arghi++] = p;
- }
+ rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
+ BUG_ON(pages >= RPCSVC_MAXPAGES);
/* Make arg->head point to first page and arg->pages point to rest */
arg = &rqstp->rq_arg;
- arg->head[0].iov_base = page_address(rqstp->rq_argpages[0]);
+ arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
arg->head[0].iov_len = PAGE_SIZE;
- rqstp->rq_argused = 1;
- arg->pages = rqstp->rq_argpages + 1;
+ arg->pages = rqstp->rq_pages + 1;
arg->page_base = 0;
/* save at least one page for response */
arg->page_len = (pages-2)*PAGE_SIZE;
if (signalled())
return -EINTR;
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&serv->sv_tempsocks)) {
- svsk = list_entry(serv->sv_tempsocks.next,
- struct svc_sock, sk_list);
- /* apparently the "standard" is that clients close
- * idle connections after 5 minutes, servers after
- * 6 minutes
- * http://www.connectathon.org/talks96/nfstcp.pdf
- */
- if (get_seconds() - svsk->sk_lastrecv < 6*60
- || test_bit(SK_BUSY, &svsk->sk_flags))
- svsk = NULL;
- }
- if (svsk) {
- set_bit(SK_BUSY, &svsk->sk_flags);
- set_bit(SK_CLOSE, &svsk->sk_flags);
- rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
- } else if ((svsk = svc_sock_dequeue(serv)) != NULL) {
+ spin_lock_bh(&pool->sp_lock);
+ if ((svsk = svc_sock_dequeue(pool)) != NULL) {
rqstp->rq_sock = svsk;
- svsk->sk_inuse++;
- rqstp->rq_reserved = serv->sv_bufsz;
- svsk->sk_reserved += rqstp->rq_reserved;
+ svc_xprt_get(&svsk->sk_xprt);
+ rqstp->rq_reserved = serv->sv_max_mesg;
+ atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
} else {
/* No data pending. Go to sleep */
- svc_serv_enqueue(serv, rqstp);
+ svc_thread_enqueue(pool, rqstp);
/*
* We have to be able to interrupt this wait
*/
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&rqstp->rq_wait, &wait);
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock_bh(&pool->sp_lock);
schedule_timeout(timeout);
try_to_freeze();
- spin_lock_bh(&serv->sv_lock);
+ spin_lock_bh(&pool->sp_lock);
remove_wait_queue(&rqstp->rq_wait, &wait);
if (!(svsk = rqstp->rq_sock)) {
- svc_serv_dequeue(serv, rqstp);
- spin_unlock_bh(&serv->sv_lock);
+ svc_thread_dequeue(pool, rqstp);
+ spin_unlock_bh(&pool->sp_lock);
dprintk("svc: server %p, no data yet\n", rqstp);
return signalled()? -EINTR : -EAGAIN;
}
}
- spin_unlock_bh(&serv->sv_lock);
-
- dprintk("svc: server %p, socket %p, inuse=%d\n",
- rqstp, svsk, svsk->sk_inuse);
- len = svsk->sk_recvfrom(rqstp);
- dprintk("svc: got len=%d\n", len);
+ spin_unlock_bh(&pool->sp_lock);
+
+ len = 0;
+ if (test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)) {
+ dprintk("svc_recv: found XPT_CLOSE\n");
+ svc_delete_xprt(&svsk->sk_xprt);
+ } else if (test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags)) {
+ struct svc_xprt *newxpt;
+ newxpt = svsk->sk_xprt.xpt_ops->xpo_accept(&svsk->sk_xprt);
+ if (newxpt) {
+ /*
+ * We know this module_get will succeed because the
+ * listener holds a reference too
+ */
+ __module_get(newxpt->xpt_class->xcl_owner);
+ svc_check_conn_limits(svsk->sk_xprt.xpt_server);
+ }
+ svc_sock_received(svsk);
+ } else {
+ dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
+ rqstp, pool->sp_id, svsk,
+ atomic_read(&svsk->sk_xprt.xpt_ref.refcount));
+ len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
+ dprintk("svc: got len=%d\n", len);
+ }
/* No data, incomplete (TCP) read, or accept() */
if (len == 0 || len == -EAGAIN) {
return -EAGAIN;
}
svsk->sk_lastrecv = get_seconds();
- if (test_bit(SK_TEMP, &svsk->sk_flags)) {
- /* push active sockets to end of list */
- spin_lock_bh(&serv->sv_lock);
- if (!list_empty(&svsk->sk_list))
- list_move_tail(&svsk->sk_list, &serv->sv_tempsocks);
- spin_unlock_bh(&serv->sv_lock);
- }
+ clear_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags);
- rqstp->rq_secure = ntohs(rqstp->rq_addr.sin_port) < 1024;
+ rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
rqstp->rq_chandle.defer = svc_defer;
if (serv->sv_stats)
return len;
}
-/*
+/*
* Drop request
*/
void
}
/* release the receive skb before sending the reply */
- svc_release_skb(rqstp);
+ rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
/* calculate over-all length */
xb = & rqstp->rq_res;
xb->page_len +
xb->tail[0].iov_len;
- /* Grab svsk->sk_sem to serialize outgoing data. */
- down(&svsk->sk_sem);
- if (test_bit(SK_DEAD, &svsk->sk_flags))
+ /* Grab svsk->sk_mutex to serialize outgoing data. */
+ mutex_lock(&svsk->sk_mutex);
+ if (test_bit(XPT_DEAD, &svsk->sk_xprt.xpt_flags))
len = -ENOTCONN;
else
- len = svsk->sk_sendto(rqstp);
- up(&svsk->sk_sem);
+ len = svsk->sk_xprt.xpt_ops->xpo_sendto(rqstp);
+ mutex_unlock(&svsk->sk_mutex);
svc_sock_release(rqstp);
if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
}
/*
+ * Timer function to close old temporary sockets, using
+ * a mark-and-sweep algorithm.
+ */
+static void
+svc_age_temp_sockets(unsigned long closure)
+{
+ struct svc_serv *serv = (struct svc_serv *)closure;
+ struct svc_sock *svsk;
+ struct list_head *le, *next;
+ LIST_HEAD(to_be_aged);
+
+ dprintk("svc_age_temp_sockets\n");
+
+ if (!spin_trylock_bh(&serv->sv_lock)) {
+ /* busy, try again 1 sec later */
+ dprintk("svc_age_temp_sockets: busy\n");
+ mod_timer(&serv->sv_temptimer, jiffies + HZ);
+ return;
+ }
+
+ list_for_each_safe(le, next, &serv->sv_tempsocks) {
+ svsk = list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+
+ if (!test_and_set_bit(XPT_OLD, &svsk->sk_xprt.xpt_flags))
+ continue;
+ if (atomic_read(&svsk->sk_xprt.xpt_ref.refcount) > 1
+ || test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags))
+ continue;
+ svc_xprt_get(&svsk->sk_xprt);
+ list_move(le, &to_be_aged);
+ set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+ set_bit(XPT_DETACHED, &svsk->sk_xprt.xpt_flags);
+ }
+ spin_unlock_bh(&serv->sv_lock);
+
+ while (!list_empty(&to_be_aged)) {
+ le = to_be_aged.next;
+ /* fiddling the sk_xprt.xpt_list node is safe 'cos we're XPT_DETACHED */
+ list_del_init(le);
+ svsk = list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+
+ dprintk("queuing svsk %p for closing, %lu seconds old\n",
+ svsk, get_seconds() - svsk->sk_lastrecv);
+
+ /* a thread will dequeue and close it soon */
+ svc_sock_enqueue(svsk);
+ svc_xprt_put(&svsk->sk_xprt);
+ }
+
+ mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
+}
+
+/*
* Initialize socket for RPC use and create svc_sock struct
* XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF.
*/
-static struct svc_sock *
-svc_setup_socket(struct svc_serv *serv, struct socket *sock,
- int *errp, int pmap_register)
+static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
+ struct socket *sock,
+ int *errp, int flags)
{
struct svc_sock *svsk;
struct sock *inet;
+ int pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+ int is_temporary = flags & SVC_SOCK_TEMPORARY;
dprintk("svc: svc_setup_socket %p\n", sock);
- if (!(svsk = kmalloc(sizeof(*svsk), GFP_KERNEL))) {
+ if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) {
*errp = -ENOMEM;
return NULL;
}
- memset(svsk, 0, sizeof(*svsk));
inet = sock->sk;
return NULL;
}
- set_bit(SK_BUSY, &svsk->sk_flags);
+ set_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags);
inet->sk_user_data = svsk;
svsk->sk_sock = sock;
svsk->sk_sk = inet;
svsk->sk_ostate = inet->sk_state_change;
svsk->sk_odata = inet->sk_data_ready;
svsk->sk_owspace = inet->sk_write_space;
- svsk->sk_server = serv;
svsk->sk_lastrecv = get_seconds();
+ spin_lock_init(&svsk->sk_lock);
INIT_LIST_HEAD(&svsk->sk_deferred);
- INIT_LIST_HEAD(&svsk->sk_ready);
- sema_init(&svsk->sk_sem, 1);
+ mutex_init(&svsk->sk_mutex);
/* Initialize the socket */
if (sock->type == SOCK_DGRAM)
- svc_udp_init(svsk);
+ svc_udp_init(svsk, serv);
else
- svc_tcp_init(svsk);
+ svc_tcp_init(svsk, serv);
spin_lock_bh(&serv->sv_lock);
- if (!pmap_register) {
- set_bit(SK_TEMP, &svsk->sk_flags);
- list_add(&svsk->sk_list, &serv->sv_tempsocks);
+ if (is_temporary) {
+ set_bit(XPT_TEMP, &svsk->sk_xprt.xpt_flags);
+ list_add(&svsk->sk_xprt.xpt_list, &serv->sv_tempsocks);
serv->sv_tmpcnt++;
+ if (serv->sv_temptimer.function == NULL) {
+ /* setup timer to age temp sockets */
+ setup_timer(&serv->sv_temptimer, svc_age_temp_sockets,
+ (unsigned long)serv);
+ mod_timer(&serv->sv_temptimer,
+ jiffies + svc_conn_age_period * HZ);
+ }
} else {
- clear_bit(SK_TEMP, &svsk->sk_flags);
- list_add(&svsk->sk_list, &serv->sv_permsocks);
+ clear_bit(XPT_TEMP, &svsk->sk_xprt.xpt_flags);
+ list_add(&svsk->sk_xprt.xpt_list, &serv->sv_permsocks);
}
spin_unlock_bh(&serv->sv_lock);
dprintk("svc: svc_setup_socket created %p (inet %p)\n",
svsk, svsk->sk_sk);
- clear_bit(SK_BUSY, &svsk->sk_flags);
- svc_sock_enqueue(svsk);
return svsk;
}
+int svc_addsock(struct svc_serv *serv,
+ int fd,
+ char *name_return,
+ int *proto)
+{
+ int err = 0;
+ struct socket *so = sockfd_lookup(fd, &err);
+ struct svc_sock *svsk = NULL;
+
+ if (!so)
+ return err;
+ if (so->sk->sk_family != AF_INET)
+ err = -EAFNOSUPPORT;
+ else if (so->sk->sk_protocol != IPPROTO_TCP &&
+ so->sk->sk_protocol != IPPROTO_UDP)
+ err = -EPROTONOSUPPORT;
+ else if (so->state > SS_UNCONNECTED)
+ err = -EISCONN;
+ else {
+ svsk = svc_setup_socket(serv, so, &err, SVC_SOCK_DEFAULTS);
+ if (svsk) {
+ svc_sock_received(svsk);
+ err = 0;
+ }
+ }
+ if (err) {
+ sockfd_put(so);
+ return err;
+ }
+ if (proto) *proto = so->sk->sk_protocol;
+ return one_sock_name(name_return, svsk);
+}
+EXPORT_SYMBOL_GPL(svc_addsock);
+
/*
* Create socket for RPC service.
*/
-static int
-svc_create_socket(struct svc_serv *serv, int protocol, struct sockaddr_in *sin)
+static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
+ int protocol,
+ struct sockaddr *sin, int len,
+ int flags)
{
struct svc_sock *svsk;
struct socket *sock;
int error;
int type;
+ char buf[RPC_MAX_ADDRBUFLEN];
- dprintk("svc: svc_create_socket(%s, %d, %u.%u.%u.%u:%d)\n",
- serv->sv_program->pg_name, protocol,
- NIPQUAD(sin->sin_addr.s_addr),
- ntohs(sin->sin_port));
+ dprintk("svc: svc_create_socket(%s, %d, %s)\n",
+ serv->sv_program->pg_name, protocol,
+ __svc_print_addr(sin, buf, sizeof(buf)));
if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) {
printk(KERN_WARNING "svc: only UDP and TCP "
"sockets supported\n");
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM;
- if ((error = sock_create_kern(PF_INET, type, protocol, &sock)) < 0)
- return error;
+ error = sock_create_kern(sin->sa_family, type, protocol, &sock);
+ if (error < 0)
+ return ERR_PTR(error);
- if (sin != NULL) {
- if (type == SOCK_STREAM)
- sock->sk->sk_reuse = 1; /* allow address reuse */
- error = sock->ops->bind(sock, (struct sockaddr *) sin,
- sizeof(*sin));
- if (error < 0)
- goto bummer;
- }
+ svc_reclassify_socket(sock);
+
+ if (type == SOCK_STREAM)
+ sock->sk->sk_reuse = 1; /* allow address reuse */
+ error = kernel_bind(sock, sin, len);
+ if (error < 0)
+ goto bummer;
if (protocol == IPPROTO_TCP) {
- if ((error = sock->ops->listen(sock, 64)) < 0)
+ if ((error = kernel_listen(sock, 64)) < 0)
goto bummer;
}
- if ((svsk = svc_setup_socket(serv, sock, &error, 1)) != NULL)
- return 0;
+ if ((svsk = svc_setup_socket(serv, sock, &error, flags)) != NULL) {
+ svc_sock_received(svsk);
+ return (struct svc_xprt *)svsk;
+ }
bummer:
dprintk("svc: svc_create_socket error = %d\n", -error);
sock_release(sock);
- return error;
+ return ERR_PTR(error);
}
/*
- * Remove a dead socket
+ * Detach the svc_sock from the socket so that no
+ * more callbacks occur.
*/
-void
-svc_delete_socket(struct svc_sock *svsk)
+static void svc_sock_detach(struct svc_xprt *xprt)
{
- struct svc_serv *serv;
- struct sock *sk;
-
- dprintk("svc: svc_delete_socket(%p)\n", svsk);
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+ struct sock *sk = svsk->sk_sk;
- serv = svsk->sk_server;
- sk = svsk->sk_sk;
+ dprintk("svc: svc_sock_detach(%p)\n", svsk);
+ /* put back the old socket callbacks */
sk->sk_state_change = svsk->sk_ostate;
sk->sk_data_ready = svsk->sk_odata;
sk->sk_write_space = svsk->sk_owspace;
+}
- spin_lock_bh(&serv->sv_lock);
-
- list_del_init(&svsk->sk_list);
- list_del_init(&svsk->sk_ready);
- if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags))
- if (test_bit(SK_TEMP, &svsk->sk_flags))
- serv->sv_tmpcnt--;
+/*
+ * Free the svc_sock's socket resources and the svc_sock itself.
+ */
+static void svc_sock_free(struct svc_xprt *xprt)
+{
+ struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+ dprintk("svc: svc_sock_free(%p)\n", svsk);
- if (!svsk->sk_inuse) {
- spin_unlock_bh(&serv->sv_lock);
+ if (svsk->sk_info_authunix != NULL)
+ svcauth_unix_info_release(svsk->sk_info_authunix);
+ if (svsk->sk_sock->file)
+ sockfd_put(svsk->sk_sock);
+ else
sock_release(svsk->sk_sock);
- kfree(svsk);
- } else {
- spin_unlock_bh(&serv->sv_lock);
- dprintk(KERN_NOTICE "svc: server socket destroy delayed\n");
- /* svsk->sk_server = NULL; */
- }
+ kfree(svsk);
}
/*
- * Make a socket for nfsd and lockd
+ * Remove a dead transport
*/
-int
-svc_makesock(struct svc_serv *serv, int protocol, unsigned short port)
+static void svc_delete_xprt(struct svc_xprt *xprt)
{
- struct sockaddr_in sin;
+ struct svc_serv *serv = xprt->xpt_server;
+
+ dprintk("svc: svc_delete_xprt(%p)\n", xprt);
+ xprt->xpt_ops->xpo_detach(xprt);
- dprintk("svc: creating socket proto = %d\n", protocol);
- sin.sin_family = AF_INET;
- sin.sin_addr.s_addr = INADDR_ANY;
- sin.sin_port = htons(port);
- return svc_create_socket(serv, protocol, &sin);
+ spin_lock_bh(&serv->sv_lock);
+ if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
+ list_del_init(&xprt->xpt_list);
+ /*
+ * We used to delete the transport from whichever list
+ * it's sk_xprt.xpt_ready node was on, but we don't actually
+ * need to. This is because the only time we're called
+ * while still attached to a queue, the queue itself
+ * is about to be destroyed (in svc_destroy).
+ */
+ if (!test_and_set_bit(XPT_DEAD, &xprt->xpt_flags)) {
+ BUG_ON(atomic_read(&xprt->xpt_ref.refcount) < 2);
+ if (test_bit(XPT_TEMP, &xprt->xpt_flags))
+ serv->sv_tmpcnt--;
+ svc_xprt_put(xprt);
+ }
+ spin_unlock_bh(&serv->sv_lock);
+}
+
+static void svc_close_xprt(struct svc_xprt *xprt)
+{
+ set_bit(XPT_CLOSE, &xprt->xpt_flags);
+ if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
+ /* someone else will have to effect the close */
+ return;
+
+ svc_xprt_get(xprt);
+ svc_delete_xprt(xprt);
+ clear_bit(XPT_BUSY, &xprt->xpt_flags);
+ svc_xprt_put(xprt);
+}
+
+void svc_close_all(struct list_head *xprt_list)
+{
+ struct svc_xprt *xprt;
+ struct svc_xprt *tmp;
+
+ 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);
+ }
}
/*
- * Handle defer and revisit of requests
+ * Handle defer and revisit of requests
*/
static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
{
struct svc_deferred_req *dr = container_of(dreq, struct svc_deferred_req, handle);
- struct svc_serv *serv = dreq->owner;
struct svc_sock *svsk;
if (too_many) {
- svc_sock_put(dr->svsk);
+ svc_xprt_put(&dr->svsk->sk_xprt);
kfree(dr);
return;
}
dprintk("revisit queued\n");
svsk = dr->svsk;
dr->svsk = NULL;
- spin_lock_bh(&serv->sv_lock);
+ spin_lock(&svsk->sk_lock);
list_add(&dr->handle.recent, &svsk->sk_deferred);
- spin_unlock_bh(&serv->sv_lock);
- set_bit(SK_DEFERRED, &svsk->sk_flags);
+ spin_unlock(&svsk->sk_lock);
+ set_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
svc_sock_enqueue(svsk);
- svc_sock_put(svsk);
+ svc_xprt_put(&svsk->sk_xprt);
}
static struct cache_deferred_req *
dr->handle.owner = rqstp->rq_server;
dr->prot = rqstp->rq_prot;
- dr->addr = rqstp->rq_addr;
+ memcpy(&dr->addr, &rqstp->rq_addr, rqstp->rq_addrlen);
+ dr->addrlen = rqstp->rq_addrlen;
+ dr->daddr = rqstp->rq_daddr;
dr->argslen = rqstp->rq_arg.len >> 2;
memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2);
}
- spin_lock_bh(&rqstp->rq_server->sv_lock);
- rqstp->rq_sock->sk_inuse++;
+ svc_xprt_get(rqstp->rq_xprt);
dr->svsk = rqstp->rq_sock;
- spin_unlock_bh(&rqstp->rq_server->sv_lock);
dr->handle.revisit = svc_revisit;
return &dr->handle;
rqstp->rq_arg.page_len = 0;
rqstp->rq_arg.len = dr->argslen<<2;
rqstp->rq_prot = dr->prot;
- rqstp->rq_addr = dr->addr;
+ memcpy(&rqstp->rq_addr, &dr->addr, dr->addrlen);
+ rqstp->rq_addrlen = dr->addrlen;
+ rqstp->rq_daddr = dr->daddr;
+ rqstp->rq_respages = rqstp->rq_pages;
return dr->argslen<<2;
}
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
{
struct svc_deferred_req *dr = NULL;
- struct svc_serv *serv = svsk->sk_server;
-
- if (!test_bit(SK_DEFERRED, &svsk->sk_flags))
+
+ if (!test_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags))
return NULL;
- spin_lock_bh(&serv->sv_lock);
- clear_bit(SK_DEFERRED, &svsk->sk_flags);
+ spin_lock(&svsk->sk_lock);
+ clear_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
if (!list_empty(&svsk->sk_deferred)) {
dr = list_entry(svsk->sk_deferred.next,
struct svc_deferred_req,
handle.recent);
list_del_init(&dr->handle.recent);
- set_bit(SK_DEFERRED, &svsk->sk_flags);
+ set_bit(XPT_DEFERRED, &svsk->sk_xprt.xpt_flags);
}
- spin_unlock_bh(&serv->sv_lock);
+ spin_unlock(&svsk->sk_lock);
return dr;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff