aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/802/fddi.c2
-rw-r--r--net/802/tr.c3
-rw-r--r--net/8021q/vlan_core.c4
-rw-r--r--net/core/dev.c9
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/udp.c3
-rw-r--r--net/ipv6/ipv6_sockglue.c4
-rw-r--r--net/ipv6/udp.c6
-rw-r--r--net/ipv6/xfrm6_output.c1
-rw-r--r--net/packet/af_packet.c5
-rw-r--r--net/rose/af_rose.c10
-rw-r--r--net/sched/em_meta.c6
-rw-r--r--net/socket.c6
-rw-r--r--net/sunrpc/svc.c3
-rw-r--r--net/sunrpc/svc_xprt.c127
-rw-r--r--net/sunrpc/svcsock.c35
16 files changed, 159 insertions, 68 deletions
diff --git a/net/802/fddi.c b/net/802/fddi.c
index f1611a1e06a..539e6064e6d 100644
--- a/net/802/fddi.c
+++ b/net/802/fddi.c
@@ -215,3 +215,5 @@ struct net_device *alloc_fddidev(int sizeof_priv)
return alloc_netdev(sizeof_priv, "fddi%d", fddi_setup);
}
EXPORT_SYMBOL(alloc_fddidev);
+
+MODULE_LICENSE("GPL");
diff --git a/net/802/tr.c b/net/802/tr.c
index e7eb13084d7..e874447ad14 100644
--- a/net/802/tr.c
+++ b/net/802/tr.c
@@ -561,6 +561,9 @@ static int rif_seq_show(struct seq_file *seq, void *v)
}
seq_putc(seq, '\n');
}
+
+ if (dev)
+ dev_put(dev);
}
return 0;
}
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 654e45f5719..c67fe6f7565 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -121,8 +121,10 @@ int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
if (!skb)
return NET_RX_DROP;
- if (netpoll_rx_on(skb))
+ if (netpoll_rx_on(skb)) {
+ skb->protocol = eth_type_trans(skb, skb->dev);
return vlan_hwaccel_receive_skb(skb, grp, vlan_tci);
+ }
return napi_frags_finish(napi, skb,
vlan_gro_common(napi, grp, vlan_tci, skb));
diff --git a/net/core/dev.c b/net/core/dev.c
index 91d792d17e0..343883f65ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1430,7 +1430,7 @@ void netif_device_detach(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_stop_queue(dev);
+ netif_tx_stop_all_queues(dev);
}
}
EXPORT_SYMBOL(netif_device_detach);
@@ -1445,7 +1445,7 @@ void netif_device_attach(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_wake_queue(dev);
+ netif_tx_wake_all_queues(dev);
__netdev_watchdog_up(dev);
}
}
@@ -2328,8 +2328,10 @@ static int napi_gro_complete(struct sk_buff *skb)
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int err = -ENOENT;
- if (NAPI_GRO_CB(skb)->count == 1)
+ if (NAPI_GRO_CB(skb)->count == 1) {
+ skb_shinfo(skb)->gso_size = 0;
goto out;
+ }
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
@@ -2348,7 +2350,6 @@ static int napi_gro_complete(struct sk_buff *skb)
}
out:
- skb_shinfo(skb)->gso_size = 0;
return netif_receive_skb(skb);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2bc8e27a163..c96a6bb2543 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -928,6 +928,8 @@ static void tcp_init_metrics(struct sock *sk)
tcp_set_rto(sk);
if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
goto reset;
+
+cwnd:
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
tp->snd_cwnd_stamp = tcp_time_stamp;
return;
@@ -942,6 +944,7 @@ reset:
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
}
+ goto cwnd;
}
static void tcp_update_reordering(struct sock *sk, const int metric,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bda08a09357..7a1d1ce22e6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -222,7 +222,7 @@ fail:
return error;
}
-int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
@@ -1823,7 +1823,6 @@ EXPORT_SYMBOL(udp_lib_getsockopt);
EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);
EXPORT_SYMBOL(udp_lib_get_port);
-EXPORT_SYMBOL(ipv4_rcv_saddr_equal);
#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d31df0f4bc9..a7fdf9a27f1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -380,10 +380,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
default:
goto sticky_done;
}
-
- if ((rthdr->hdrlen & 1) ||
- (rthdr->hdrlen >> 1) != rthdr->segments_left)
- goto sticky_done;
}
retv = 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6842dd2edd5..8905712cfbb 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -53,6 +53,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
{
const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
+ __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr;
+ __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
int sk_ipv6only = ipv6_only_sock(sk);
int sk2_ipv6only = inet_v6_ipv6only(sk2);
int addr_type = ipv6_addr_type(sk_rcv_saddr6);
@@ -60,7 +62,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
/* if both are mapped, treat as IPv4 */
if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
- return ipv4_rcv_saddr_equal(sk, sk2);
+ return (!sk2_ipv6only &&
+ (!sk_rcv_saddr || !sk2_rcv_saddr ||
+ sk_rcv_saddr == sk2_rcv_saddr));
if (addr_type2 == IPV6_ADDR_ANY &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 0af823cf7f1..5ee5a031bc9 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -72,6 +72,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
#endif
skb->protocol = htons(ETH_P_IPV6);
+ skb->local_df = 1;
return x->outer_mode->output2(x, skb);
}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 74776de523e..f546e81acc4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1758,8 +1758,9 @@ static void free_pg_vec(char **pg_vec, unsigned int order, unsigned int len)
static inline char *alloc_one_pg_vec_page(unsigned long order)
{
- return (char *) __get_free_pages(GFP_KERNEL | __GFP_COMP | __GFP_ZERO,
- order);
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN;
+
+ return (char *) __get_free_pages(gfp_flags, order);
}
static char **alloc_pg_vec(struct tpacket_req *req, int order)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 0f36e8d59b2..877a7f65f70 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1072,10 +1072,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
unsigned char *asmptr;
int n, size, qbit = 0;
- /* ROSE empty frame has no meaning : don't send */
- if (len == 0)
- return 0;
-
if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_CMSG_COMPAT))
return -EINVAL;
@@ -1273,12 +1269,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
skb_reset_transport_header(skb);
copied = skb->len;
- /* ROSE empty frame has no meaning : ignore it */
- if (copied == 0) {
- skb_free_datagram(sk, skb);
- return copied;
- }
-
if (copied > size) {
copied = size;
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 72cf86e3c09..fad596bf32d 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -176,8 +176,10 @@ META_COLLECTOR(var_dev)
META_COLLECTOR(int_vlan_tag)
{
- unsigned short uninitialized_var(tag);
- if (vlan_get_tag(skb, &tag) < 0)
+ unsigned short tag;
+
+ tag = vlan_tx_tag_get(skb);
+ if (!tag && __vlan_get_tag(skb, &tag))
*err = -1;
else
dst->value = tag;
diff --git a/net/socket.c b/net/socket.c
index 91d0c0254ff..791d71a36a9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -493,8 +493,7 @@ static struct socket *sock_alloc(void)
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- get_cpu_var(sockets_in_use)++;
- put_cpu_var(sockets_in_use);
+ percpu_add(sockets_in_use, 1);
return sock;
}
@@ -536,8 +535,7 @@ void sock_release(struct socket *sock)
if (sock->fasync_list)
printk(KERN_ERR "sock_release: fasync list not empty!\n");
- get_cpu_var(sockets_in_use)--;
- put_cpu_var(sockets_in_use);
+ percpu_sub(sockets_in_use, 1);
if (!sock->file) {
iput(SOCK_INODE(sock));
return;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9b49a6ab8de..8847add6ca1 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1008,6 +1008,8 @@ svc_process(struct svc_rqst *rqstp)
rqstp->rq_res.tail[0].iov_len = 0;
/* Will be turned off only in gss privacy case: */
rqstp->rq_splice_ok = 1;
+ /* Will be turned off only when NFSv4 Sessions are used */
+ rqstp->rq_usedeferral = 1;
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1078,7 +1080,6 @@ svc_process(struct svc_rqst *rqstp)
procp = versp->vs_proc + proc;
if (proc >= versp->vs_nproc || !procp->pc_func)
goto err_bad_proc;
- rqstp->rq_server = serv;
rqstp->rq_procinfo = procp;
/* Syntactic check complete */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 2819ee093f3..c200d92e57e 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -14,6 +14,8 @@
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
+#define SVC_MAX_WAKING 5
+
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
@@ -301,6 +303,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
struct svc_pool *pool;
struct svc_rqst *rqstp;
int cpu;
+ int thread_avail;
if (!(xprt->xpt_flags &
((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
@@ -312,18 +315,14 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
spin_lock_bh(&pool->sp_lock);
- if (!list_empty(&pool->sp_threads) &&
- !list_empty(&pool->sp_sockets))
- printk(KERN_ERR
- "svc_xprt_enqueue: "
- "threads and transports both waiting??\n");
-
if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
/* Don't enqueue dead transports */
dprintk("svc: transport %p is dead, not enqueued\n", xprt);
goto out_unlock;
}
+ pool->sp_stats.packets++;
+
/* Mark transport as busy. It will remain in this state until
* the provider calls svc_xprt_received. We update XPT_BUSY
* atomically because it also guards against trying to enqueue
@@ -356,7 +355,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
}
process:
- if (!list_empty(&pool->sp_threads)) {
+ /* Work out whether threads are available */
+ thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */
+ if (pool->sp_nwaking >= SVC_MAX_WAKING) {
+ /* too many threads are runnable and trying to wake up */
+ thread_avail = 0;
+ pool->sp_stats.overloads_avoided++;
+ }
+
+ if (thread_avail) {
rqstp = list_entry(pool->sp_threads.next,
struct svc_rqst,
rq_list);
@@ -371,11 +378,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
svc_xprt_get(xprt);
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+ rqstp->rq_waking = 1;
+ pool->sp_nwaking++;
+ 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);
}
@@ -588,6 +599,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
int pages;
struct xdr_buf *arg;
DECLARE_WAITQUEUE(wait, current);
+ long time_left;
dprintk("svc: server %p waiting for data (to = %ld)\n",
rqstp, timeout);
@@ -636,6 +648,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
return -EINTR;
spin_lock_bh(&pool->sp_lock);
+ if (rqstp->rq_waking) {
+ rqstp->rq_waking = 0;
+ pool->sp_nwaking--;
+ BUG_ON(pool->sp_nwaking < 0);
+ }
xprt = svc_xprt_dequeue(pool);
if (xprt) {
rqstp->rq_xprt = xprt;
@@ -668,12 +685,14 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
add_wait_queue(&rqstp->rq_wait, &wait);
spin_unlock_bh(&pool->sp_lock);
- schedule_timeout(timeout);
+ time_left = schedule_timeout(timeout);
try_to_freeze();
spin_lock_bh(&pool->sp_lock);
remove_wait_queue(&rqstp->rq_wait, &wait);
+ if (!time_left)
+ pool->sp_stats.threads_timedout++;
xprt = rqstp->rq_xprt;
if (!xprt) {
@@ -958,7 +977,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
struct svc_deferred_req *dr;
- if (rqstp->rq_arg.page_len)
+ if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
return NULL; /* if more than a page, give up FIXME */
if (rqstp->rq_deferred) {
dr = rqstp->rq_deferred;
@@ -1112,3 +1131,93 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen)
return totlen;
}
EXPORT_SYMBOL_GPL(svc_xprt_names);
+
+
+/*----------------------------------------------------------------------------*/
+
+static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
+{
+ unsigned int pidx = (unsigned int)*pos;
+ struct svc_serv *serv = m->private;
+
+ dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
+
+ lock_kernel();
+ /* bump up the pseudo refcount while traversing */
+ svc_get(serv);
+ unlock_kernel();
+
+ if (!pidx)
+ return SEQ_START_TOKEN;
+ return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+}
+
+static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ struct svc_pool *pool = p;
+ struct svc_serv *serv = m->private;
+
+ dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
+
+ if (p == SEQ_START_TOKEN) {
+ pool = &serv->sv_pools[0];
+ } else {
+ unsigned int pidx = (pool - &serv->sv_pools[0]);
+ if (pidx < serv->sv_nrpools-1)
+ pool = &serv->sv_pools[pidx+1];
+ else
+ pool = NULL;
+ }
+ ++*pos;
+ return pool;
+}
+
+static void svc_pool_stats_stop(struct seq_file *m, void *p)
+{
+ struct svc_serv *serv = m->private;
+
+ lock_kernel();
+ /* this function really, really should have been called svc_put() */
+ svc_destroy(serv);
+ unlock_kernel();
+}
+
+static int svc_pool_stats_show(struct seq_file *m, void *p)
+{
+ struct svc_pool *pool = p;
+
+ if (p == SEQ_START_TOKEN) {
+ seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n");
+ return 0;
+ }
+
+ seq_printf(m, "%u %lu %lu %lu %lu %lu\n",
+ pool->sp_id,
+ pool->sp_stats.packets,
+ pool->sp_stats.sockets_queued,
+ pool->sp_stats.threads_woken,
+ pool->sp_stats.overloads_avoided,
+ pool->sp_stats.threads_timedout);
+
+ return 0;
+}
+
+static const struct seq_operations svc_pool_stats_seq_ops = {
+ .start = svc_pool_stats_start,
+ .next = svc_pool_stats_next,
+ .stop = svc_pool_stats_stop,
+ .show = svc_pool_stats_show,
+};
+
+int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+{
+ int err;
+
+ err = seq_open(file, &svc_pool_stats_seq_ops);
+ if (!err)
+ ((struct seq_file *) file->private_data)->private = serv;
+ return err;
+}
+EXPORT_SYMBOL(svc_pool_stats_open);
+
+/*----------------------------------------------------------------------------*/
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 9d504234af4..af3198814c1 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -345,7 +345,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
lock_sock(sock->sk);
sock->sk->sk_sndbuf = snd * 2;
sock->sk->sk_rcvbuf = rcv * 2;
- sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
release_sock(sock->sk);
#endif
}
@@ -797,23 +796,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_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
- * as soon a a complete request arrives.
- */
- svc_sock_setbufsize(svsk->sk_sock,
- (serv->sv_nrthreads+3) * serv->sv_max_mesg,
- 3 * serv->sv_max_mesg);
-
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
/* Receive data. If we haven't got the record length yet, get
@@ -1061,15 +1043,6 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
- /* initialise setting must have enough space to
- * receive and respond to one request.
- * svc_tcp_recvfrom will re-adjust if necessary
- */
- svc_sock_setbufsize(svsk->sk_sock,
- 3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
- 3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
-
- 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);
@@ -1139,8 +1112,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
/* Initialize the socket */
if (sock->type == SOCK_DGRAM)
svc_udp_init(svsk, serv);
- else
+ else {
+ /* initialise setting must have enough space to
+ * receive and respond to one request.
+ */
+ svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
+ 4 * serv->sv_max_mesg);
svc_tcp_init(svsk, serv);
+ }
dprintk("svc: svc_setup_socket created %p (inet %p)\n",
svsk, svsk->sk_sk);
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-15 09:25:09 +0000