summaryrefslogtreecommitdiff
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c126
1 files changed, 101 insertions, 25 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 1180a0cb0110..2ff40dd0a7a6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -141,9 +141,14 @@
#include <linux/ethtool.h>
+#include "dev.h"
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
+static void sock_def_write_space_wfree(struct sock *sk);
+static void sock_def_write_space(struct sock *sk);
+
/**
* sk_ns_capable - General socket capability test
* @sk: Socket to use a capability on or through
@@ -503,17 +508,35 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(__sock_queue_rcv_skb);
-int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
+ enum skb_drop_reason *reason)
{
+ enum skb_drop_reason drop_reason;
int err;
err = sk_filter(sk, skb);
- if (err)
- return err;
-
- return __sock_queue_rcv_skb(sk, skb);
+ if (err) {
+ drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+ goto out;
+ }
+ err = __sock_queue_rcv_skb(sk, skb);
+ switch (err) {
+ case -ENOMEM:
+ drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
+ break;
+ case -ENOBUFS:
+ drop_reason = SKB_DROP_REASON_PROTO_MEM;
+ break;
+ default:
+ drop_reason = SKB_NOT_DROPPED_YET;
+ break;
+ }
+out:
+ if (reason)
+ *reason = drop_reason;
+ return err;
}
-EXPORT_SYMBOL(sock_queue_rcv_skb);
+EXPORT_SYMBOL(sock_queue_rcv_skb_reason);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
const int nested, unsigned int trim_cap, bool refcounted)
@@ -612,7 +635,9 @@ static int sock_bindtoindex_locked(struct sock *sk, int ifindex)
if (ifindex < 0)
goto out;
- sk->sk_bound_dev_if = ifindex;
+ /* Paired with all READ_ONCE() done locklessly. */
+ WRITE_ONCE(sk->sk_bound_dev_if, ifindex);
+
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
@@ -690,10 +715,11 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
+ int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
- if (sk->sk_bound_dev_if == 0) {
+ if (bound_dev_if == 0) {
len = 0;
goto zero;
}
@@ -702,7 +728,7 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
if (len < IFNAMSIZ)
goto out;
- ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
+ ret = netdev_get_name(net, devname, bound_dev_if);
if (ret)
goto out;
@@ -1291,6 +1317,15 @@ set_sndbuf:
__sock_set_mark(sk, val);
break;
+ case SO_RCVMARK:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+ !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ break;
+ }
+
+ sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
+ break;
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
@@ -1717,6 +1752,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_mark;
break;
+ case SO_RCVMARK:
+ v.val = sock_flag(sk, SOCK_RCVMARK);
+ break;
+
case SO_RXQ_OVFL:
v.val = sock_flag(sk, SOCK_RXQ_OVFL);
break;
@@ -1825,7 +1864,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_BINDTOIFINDEX:
- v.val = sk->sk_bound_dev_if;
+ v.val = READ_ONCE(sk->sk_bound_dev_if);
break;
case SO_NETNS_COOKIE:
@@ -2062,9 +2101,6 @@ void sk_destruct(struct sock *sk)
{
bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
- WARN_ON_ONCE(!llist_empty(&sk->defer_list));
- sk_defer_free_flush(sk);
-
if (rcu_access_pointer(sk->sk_reuseport_cb)) {
reuseport_detach_sock(sk);
use_call_rcu = true;
@@ -2260,6 +2296,19 @@ void sk_free_unlock_clone(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
+static void sk_trim_gso_size(struct sock *sk)
+{
+ if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
+ return;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6 &&
+ sk_is_tcp(sk) &&
+ !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ return;
+#endif
+ sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
+}
+
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
@@ -2279,6 +2328,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
+ sk_trim_gso_size(sk);
sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
@@ -2300,8 +2350,20 @@ void sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
+ bool free;
if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
+ if (sock_flag(sk, SOCK_RCU_FREE) &&
+ sk->sk_write_space == sock_def_write_space) {
+ rcu_read_lock();
+ free = refcount_sub_and_test(len, &sk->sk_wmem_alloc);
+ sock_def_write_space_wfree(sk);
+ rcu_read_unlock();
+ if (unlikely(free))
+ __sk_free(sk);
+ return;
+ }
+
/*
* Keep a reference on sk_wmem_alloc, this will be released
* after sk_write_space() call
@@ -2611,13 +2673,6 @@ failure:
}
EXPORT_SYMBOL(sock_alloc_send_pskb);
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
- int noblock, int *errcode)
-{
- return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
-}
-EXPORT_SYMBOL(sock_alloc_send_skb);
-
int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc)
{
@@ -3174,20 +3229,42 @@ static void sock_def_write_space(struct sock *sk)
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
- if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
+ if (sock_writeable(sk)) {
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
EPOLLWRNORM | EPOLLWRBAND);
/* Should agree with poll, otherwise some programs break */
- if (sock_writeable(sk))
- sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+ sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
rcu_read_unlock();
}
+/* An optimised version of sock_def_write_space(), should only be called
+ * for SOCK_RCU_FREE sockets under RCU read section and after putting
+ * ->sk_wmem_alloc.
+ */
+static void sock_def_write_space_wfree(struct sock *sk)
+{
+ /* Do not wake up a writer until he can make "significant"
+ * progress. --DaveM
+ */
+ if (sock_writeable(sk)) {
+ struct socket_wq *wq = rcu_dereference(sk->sk_wq);
+
+ /* rely on refcount_sub from sock_wfree() */
+ smp_mb__after_atomic();
+ if (wq && waitqueue_active(&wq->wait))
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
+
+ /* Should agree with poll, otherwise some programs break */
+ sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+ }
+}
+
static void sock_def_destruct(struct sock *sk)
{
}
@@ -3486,8 +3563,7 @@ int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int addr_len = 0;
int err;
- err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
- flags & ~MSG_DONTWAIT, &addr_len);
+ err = sk->sk_prot->recvmsg(sk, msg, size, flags, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-22 22:37:38 +0300