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/scm.c2
-rw-r--r--net/core/sock.c2
-rw-r--r--net/decnet/af_decnet.c3
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/ipmr.c15
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c3
-rw-r--r--net/ipv6/af_inet6.c3
-rw-r--r--net/ipv6/ip6_gre.c8
-rw-r--r--net/ipv6/ip6mr.c15
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c5
-rw-r--r--net/ipv6/reassembly.c10
-rw-r--r--net/irda/af_irda.c3
-rw-r--r--net/sctp/auth.c4
-rw-r--r--net/sctp/ipv6.c8
-rw-r--r--net/sctp/socket.c12
-rw-r--r--net/unix/af_unix.c196
20 files changed, 240 insertions, 61 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ba6db78a0..69940a723 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 de9c955b2..a31d0b9f1 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -459,6 +459,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ if (alen < sizeof(sa))
+ return -EINVAL;
+
memset(&sa, 0, sizeof(sa));
len = min_t(unsigned int, sizeof(sa), alen);
memcpy(&sa, addr, len);
diff --git a/net/core/scm.c b/net/core/scm.c
index b4da80b1c..dbc6bfcdf 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -306,6 +306,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
err = put_user(cmlen, &cm->cmsg_len);
if (!err) {
cmlen = CMSG_SPACE(i*sizeof(int));
+ if (msg->msg_controllen < cmlen)
+ cmlen = msg->msg_controllen;
msg->msg_control += cmlen;
msg->msg_controllen -= cmlen;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index d19cf53df..218da1249 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -423,8 +423,6 @@ 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) {
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index c21f200ee..ca6106562 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -677,6 +677,9 @@ 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 f022e0e97..14ad21e2f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -304,6 +304,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
build_ehash_secret();
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6f5f943ff..b31553d38 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -136,7 +136,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -348,7 +348,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
static void ipmr_free_table(struct mr_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -1199,7 +1199,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1208,8 +1208,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
/* Shut down all active vif entries */
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif_table[i].flags & VIFF_STATIC))
- vif_delete(mrt, i, 0, &list);
+ if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+ continue;
+ vif_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
@@ -1217,7 +1218,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
for (i = 0; i < MFC_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
list_del_rcu(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1252,7 +1253,7 @@ static void mrtsock_destruct(struct sock *sk)
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
}
}
rtnl_unlock();
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6df001f5d..d1749cb10 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5610,6 +5610,7 @@ discard:
}
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 23f97a0cf..be8f79c08 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1015,7 +1015,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
}
md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
+ sock_owned_by_user(sk) ||
+ lockdep_is_held(&sk->sk_lock.slock));
if (!md5sig) {
md5sig = kmalloc(sizeof(*md5sig), gfp);
if (!md5sig)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d29ae19ae..72aa1a135 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -131,6 +131,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
!inet_ehash_secret)
build_ehash_secret();
+ 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 bf6233cdb..7eb726786 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1541,13 +1541,11 @@ 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/ip6mr.c b/net/ipv6/ip6mr.c
index 57dd3e7d8..9ec416552 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -120,7 +120,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
int cmd);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -337,7 +337,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
static void ip6mr_free_table(struct mr6_table *mrt)
{
del_timer(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -1537,7 +1537,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1547,8 +1547,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
* Shut down all active vif entries
*/
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(mrt, i, &list);
+ if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+ continue;
+ mif6_delete(mrt, i, &list);
}
unregister_netdevice_many(&list);
@@ -1557,7 +1558,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
*/
for (i = 0; i < MFC6_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
write_lock_bh(&mrt_lock);
list_del(&c->list);
@@ -1620,7 +1621,7 @@ int ip6mr_sk_done(struct sock *sk)
net->ipv6.devconf_all);
write_unlock_bh(&mrt_lock);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
err = 0;
break;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 734aec059..7ba6180ff 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1441,7 +1441,6 @@ out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
} else {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
}
@@ -1805,7 +1804,6 @@ out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
} else
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 253566a8d..7cd623588 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -172,7 +172,7 @@ static void nf_ct_frag6_expire(unsigned long data)
/* Creation primitives. */
static inline struct frag_queue *fq_find(struct net *net, __be32 id,
u32 user, struct in6_addr *src,
- struct in6_addr *dst, u8 ecn)
+ struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -182,6 +182,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
arg.user = user;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
read_lock_bh(&nf_frags.lock);
@@ -590,7 +591,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
local_bh_enable();
fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1aeb473b2..a1fb511da 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -111,7 +111,10 @@ bool ip6_frag_match(struct inet_frag_queue *q, void *a)
return fq->id == arg->id &&
fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst);
+ ipv6_addr_equal(&fq->daddr, arg->dst) &&
+ (arg->iif == fq->iif ||
+ !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)));
}
EXPORT_SYMBOL(ip6_frag_match);
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
static __inline__ struct frag_queue *
fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, u8 ecn)
+ const struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
read_lock(&ip6_frags.lock);
@@ -558,7 +562,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
IPSTATS_MIB_REASMFAILS, evicted);
fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq != NULL) {
int ret;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index a5e62ef57..f8133ff5b 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1105,6 +1105,9 @@ 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/sctp/auth.c b/net/sctp/auth.c
index bc2fae7e6..62433f797 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -812,8 +812,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
if (!has_sha1)
return -EINVAL;
- memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
- hmacs->shmac_num_idents * sizeof(__u16));
+ for (i = 0; i < hmacs->shmac_num_idents; i++)
+ ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
hmacs->shmac_num_idents * sizeof(__u16));
return 0;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 422d8bdac..bee032a70 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -639,6 +639,7 @@ 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)
@@ -658,6 +659,13 @@ 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/socket.c b/net/sctp/socket.c
index ec5766dc3..80bd61ae5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6969,6 +6969,9 @@ 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,
@@ -7149,6 +7152,13 @@ struct proto sctp_prot = {
#if IS_ENABLED(CONFIG_IPV6)
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+ sctp_destroy_sock(sk);
+ inet6_destroy_sock(sk);
+}
+
struct proto sctpv6_prot = {
.name = "SCTPv6",
.owner = THIS_MODULE,
@@ -7158,7 +7168,7 @@ struct proto sctpv6_prot = {
.accept = sctp_accept,
.ioctl = sctp_ioctl,
.init = sctp_init_sock,
- .destroy = sctp_destroy_sock,
+ .destroy = sctp_v6_destroy_sock,
.shutdown = sctp_shutdown,
.setsockopt = sctp_setsockopt,
.getsockopt = sctp_getsockopt,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5a82d12a9..8246d5ee8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -334,6 +334,118 @@ 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;
@@ -440,6 +552,8 @@ 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;
}
@@ -674,6 +788,7 @@ 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)
@@ -1044,6 +1159,8 @@ 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)
@@ -1504,6 +1621,7 @@ 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;
@@ -1580,12 +1698,14 @@ 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
@@ -1593,10 +1713,14 @@ 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);
@@ -1622,21 +1746,38 @@ 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);
@@ -1651,6 +1792,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -1870,14 +2013,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
if (flags&MSG_OOB)
goto out;
- 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);
skip = sk_peek_offset(sk, flags);
@@ -2111,12 +2247,12 @@ again:
}
- 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);
@@ -2387,14 +2523,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
}
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 2.39.1) at 2026-03-14 17:37:46 +0000