aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c3
-rw-r--r--net/bluetooth/sco.c3
-rw-r--r--net/core/skbuff.c6
-rw-r--r--net/core/sock.c5
-rw-r--r--net/decnet/af_decnet.c3
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/fou.c3
-rw-r--r--net/ipv4/tcp_ipv4.c5
-rw-r--r--net/ipv6/af_inet6.c3
-rw-r--r--net/ipv6/ip6_gre.c8
-rw-r--r--net/ipv6/tcp_ipv6.c3
-rw-r--r--net/irda/af_irda.c3
-rw-r--r--net/rds/send.c4
-rw-r--r--net/sctp/ipv6.c8
-rw-r--r--net/sctp/sm_make_chunk.c4
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/unix/af_unix.c196
17 files changed, 216 insertions, 48 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c35c3f48fc0f..1428c3ff3341 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -806,6 +806,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
struct sock *sk;
ax25_cb *ax25;
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (!net_eq(net, &init_net))
return -EAFNOSUPPORT;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 7ee9e4ab00f8..b3ef78a644ed 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -520,6 +520,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ if (addr_len < sizeof(struct sockaddr_sco))
+ return -EINVAL;
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ea0bcc4a9657..b2921c0d5608 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3599,7 +3599,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
serr->ee.ee_info = tstype;
if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
- if (sk->sk_protocol == IPPROTO_TCP)
+ if (sk->sk_protocol == IPPROTO_TCP &&
+ sk->sk_type == SOCK_STREAM)
serr->ee.ee_data -= sk->sk_tskey;
}
@@ -4108,7 +4109,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
return NULL;
}
- memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+ memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
+ 2 * ETH_ALEN);
skb->mac_header += VLAN_HLEN;
return skb;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e5130de31b6..b1a6ff0a9041 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -422,8 +422,6 @@ static void sock_warn_obsolete_bsdism(const char *name)
}
}
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
@@ -861,7 +859,8 @@ set_rcvbuf:
}
if (val & SOF_TIMESTAMPING_OPT_ID &&
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
- if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_protocol == IPPROTO_TCP &&
+ sk->sk_type == SOCK_STREAM) {
if (sk->sk_state != TCP_ESTABLISHED) {
ret = -EINVAL;
break;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 25733d538147..2aeeb4f22e9d 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
{
struct sock *sk;
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (!net_eq(net, &init_net))
return -EAFNOSUPPORT;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9a173577a790..6cf020ea4f46 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -259,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 606c520ffd5a..8ce8e82d1abb 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -25,6 +25,7 @@ struct fou {
u16 port;
struct udp_offload udp_offloads;
struct list_head list;
+ struct rcu_head rcu;
};
struct fou_cfg {
@@ -287,7 +288,7 @@ static void fou_release(struct fou *fou)
sock_release(sock);
- kfree(fou);
+ kfree_rcu(fou, rcu);
}
static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6cd9f696d9c6..5d5390299277 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1553,7 +1553,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
if (likely(sk->sk_rx_dst))
skb_dst_drop(skb);
else
- skb_dst_force(skb);
+ skb_dst_force_safe(skb);
__skb_queue_tail(&tp->ucopy.prequeue, skb);
tp->ucopy.memory += skb->truesize;
@@ -1758,8 +1758,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- if (dst) {
- dst_hold(dst);
+ if (dst && dst_hold_safe(dst)) {
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 05417c330f4e..ad95905e7a70 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 28d7a245ea34..25cd22c1ddee 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1563,13 +1563,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
return -EEXIST;
} else {
t = nt;
-
- ip6gre_tunnel_unlink(ign, t);
- ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
- ip6gre_tunnel_link(ign, t);
- netdev_state_change(dev);
}
+ ip6gre_tunnel_unlink(ign, t);
+ ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link(ign, t);
return 0;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 26feadd0b763..b5a4ac8ce4b1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- if (dst) {
+ if (dst && dst_hold_safe(dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
- dst_hold(dst);
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
if (rt->rt6i_node)
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 3f3a6cbdceb7..b3f6ec0df426 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1100,6 +1100,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
IRDA_DEBUG(2, "%s()\n", __func__);
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (net != &init_net)
return -EAFNOSUPPORT;
diff --git a/net/rds/send.c b/net/rds/send.c
index 0a64541020b0..0bae8d43b012 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -958,11 +958,13 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
release_sock(sk);
}
- /* racing with another thread binding seems ok here */
+ lock_sock(sk);
if (daddr == 0 || rs->rs_bound_addr == 0) {
+ release_sock(sk);
ret = -ENOTCONN; /* XXX not a great errno */
goto out;
}
+ release_sock(sk);
/* size of rm including all sgs */
ret = rds_rm_size(msg, payload_len);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0e4198ee2370..3267a5cbb3e8 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -634,6 +634,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
struct sock *newsk;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct sctp6_sock *newsctp6sk;
+ struct ipv6_txoptions *opt;
newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot);
if (!newsk)
@@ -653,6 +654,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+ rcu_read_lock();
+ opt = rcu_dereference(np->opt);
+ if (opt)
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ rcu_read_unlock();
+
/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
* and getpeername().
*/
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 371a152d9759..642c11570285 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
/* Set an expiration time for the cookie. */
cookie->c.expiration = ktime_add(asoc->cookie_life,
- ktime_get());
+ ktime_get_real());
/* Copy the peer's init packet. */
memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr,
@@ -1780,7 +1780,7 @@ no_hmac:
if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
kt = skb_get_ktime(skb);
else
- kt = ktime_get();
+ kt = ktime_get_real();
if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
/*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fb082aa4d656..4130c1b87dd6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7181,6 +7181,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
newsk->sk_type = sk->sk_type;
newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
newsk->sk_flags = sk->sk_flags;
+ newsk->sk_tsflags = sk->sk_tsflags;
newsk->sk_no_check_tx = sk->sk_no_check_tx;
newsk->sk_no_check_rx = sk->sk_no_check_rx;
newsk->sk_reuse = sk->sk_reuse;
@@ -7213,6 +7214,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
newinet->mc_ttl = 1;
newinet->mc_index = 0;
newinet->mc_list = NULL;
+
+ if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+ net_enable_timestamp();
}
static inline void sctp_copy_descendant(struct sock *sk_to,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2ae4a5915aa7..7229794c1419 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -316,6 +316,118 @@ found:
return s;
}
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+ void *key)
+{
+ struct unix_sock *u;
+ wait_queue_head_t *u_sleep;
+
+ u = container_of(q, struct unix_sock, peer_wake);
+
+ __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+ q);
+ u->peer_wake.private = NULL;
+
+ /* relaying can only happen while the wq still exists */
+ u_sleep = sk_sleep(&u->sk);
+ if (u_sleep)
+ wake_up_interruptible_poll(u_sleep, key);
+
+ return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+ int rc;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ rc = 0;
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (!u->peer_wake.private) {
+ u->peer_wake.private = other;
+ __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+ rc = 1;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+ return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+ struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (u->peer_wake.private == other) {
+ __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+ u->peer_wake.private = NULL;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+ struct sock *other)
+{
+ unix_dgram_peer_wake_disconnect(sk, other);
+ wake_up_interruptible_poll(sk_sleep(sk),
+ POLLOUT |
+ POLLWRNORM |
+ POLLWRBAND);
+}
+
+/* preconditions:
+ * - unix_peer(sk) == other
+ * - association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+ int connected;
+
+ connected = unix_dgram_peer_wake_connect(sk, other);
+
+ if (unix_recvq_full(other))
+ return 1;
+
+ if (connected)
+ unix_dgram_peer_wake_disconnect(sk, other);
+
+ return 0;
+}
+
static inline int unix_writable(struct sock *sk)
{
return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -420,6 +532,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
skpair->sk_state_change(skpair);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
}
+
+ unix_dgram_peer_wake_disconnect(sk, skpair);
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
}
@@ -653,6 +767,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
+ init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -1020,6 +1135,8 @@ restart:
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
unix_peer(sk) = other;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
unix_state_double_unlock(sk, other);
if (other != old_peer)
@@ -1459,6 +1576,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct scm_cookie tmp_scm;
int max_level;
int data_len = 0;
+ int sk_locked;
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
@@ -1540,12 +1658,14 @@ restart:
goto out_free;
}
+ sk_locked = 0;
unix_state_lock(other);
+restart_locked:
err = -EPERM;
if (!unix_may_send(sk, other))
goto out_unlock;
- if (sock_flag(other, SOCK_DEAD)) {
+ if (unlikely(sock_flag(other, SOCK_DEAD))) {
/*
* Check with 1003.1g - what should
* datagram error
@@ -1553,10 +1673,14 @@ restart:
unix_state_unlock(other);
sock_put(other);
+ if (!sk_locked)
+ unix_state_lock(sk);
+
err = 0;
- unix_state_lock(sk);
if (unix_peer(sk) == other) {
unix_peer(sk) = NULL;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
unix_state_unlock(sk);
unix_dgram_disconnected(sk, other);
@@ -1582,21 +1706,38 @@ restart:
goto out_unlock;
}
- if (unix_peer(other) != sk && unix_recvq_full(other)) {
- if (!timeo) {
- err = -EAGAIN;
- goto out_unlock;
+ if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+ if (timeo) {
+ timeo = unix_wait_for_peer(other, timeo);
+
+ err = sock_intr_errno(timeo);
+ if (signal_pending(current))
+ goto out_free;
+
+ goto restart;
}
- timeo = unix_wait_for_peer(other, timeo);
+ if (!sk_locked) {
+ unix_state_unlock(other);
+ unix_state_double_lock(sk, other);
+ }
- err = sock_intr_errno(timeo);
- if (signal_pending(current))
- goto out_free;
+ if (unix_peer(sk) != other ||
+ unix_dgram_peer_wake_me(sk, other)) {
+ err = -EAGAIN;
+ sk_locked = 1;
+ goto out_unlock;
+ }
- goto restart;
+ if (!sk_locked) {
+ sk_locked = 1;
+ goto restart_locked;
+ }
}
+ if (unlikely(sk_locked))
+ unix_state_unlock(sk);
+
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
maybe_add_creds(skb, sock, other);
@@ -1610,6 +1751,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -1953,14 +2096,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
memset(&tmp_scm, 0, sizeof(tmp_scm));
}
- err = mutex_lock_interruptible(&u->readlock);
- if (unlikely(err)) {
- /* recvmsg() in non blocking mode is supposed to return -EAGAIN
- * sk_rcvtimeo is not honored by mutex_lock_interruptible()
- */
- err = noblock ? -EAGAIN : -ERESTARTSYS;
- goto out;
- }
+ mutex_lock(&u->readlock);
if (flags & MSG_PEEK)
skip = sk_peek_offset(sk, flags);
@@ -2001,12 +2137,12 @@ again:
timeo = unix_stream_data_wait(sk, timeo, last);
- if (signal_pending(current)
- || mutex_lock_interruptible(&u->readlock)) {
+ if (signal_pending(current)) {
err = sock_intr_errno(timeo);
goto out;
}
+ mutex_lock(&u->readlock);
continue;
unlock:
unix_state_unlock(sk);
@@ -2269,14 +2405,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
return mask;
writable = unix_writable(sk);
- other = unix_peer_get(sk);
- if (other) {
- if (unix_peer(other) != sk) {
- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
- if (unix_recvq_full(other))
- writable = 0;
- }
- sock_put(other);
+ if (writable) {
+ unix_state_lock(sk);
+
+ other = unix_peer(sk);
+ if (other && unix_peer(other) != sk &&
+ unix_recvq_full(other) &&
+ unix_dgram_peer_wake_me(sk, other))
+ writable = 0;
+
+ unix_state_unlock(sk);
}
if (writable)
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-01 05:51:52 +0000