aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/rfcomm/sock.c18
-rw-r--r--net/ipv4/ip_forward.c3
-rw-r--r--net/ipv4/netfilter/arp_tables.c41
-rw-r--r--net/ipv4/netfilter/ip_tables.c46
-rw-r--r--net/ipv4/route.c5
-rw-r--r--net/ipv4/udp.c6
-rw-r--r--net/ipv6/ndisc.c9
-rw-r--r--net/ipv6/netfilter/ip6_tables.c46
-rw-r--r--net/ipv6/udp.c6
-rw-r--r--net/socket.c38
-rw-r--r--net/unix/af_unix.c183
11 files changed, 279 insertions, 122 deletions
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 216068f4af1..ef5e3a2bd4c 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -346,15 +346,19 @@ static int rfcomm_sock_create(struct net *net, struct socket *sock,
static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
- struct sockaddr_rc *sa = (struct sockaddr_rc *) addr;
+ struct sockaddr_rc sa;
struct sock *sk = sock->sk;
- int err = 0;
-
- BT_DBG("sk %p %s", sk, batostr(&sa->rc_bdaddr));
+ int len, err = 0;
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ memset(&sa, 0, sizeof(sa));
+ len = min_t(unsigned int, sizeof(sa), addr_len);
+ memcpy(&sa, addr, len);
+
+ BT_DBG("sk %p %s", sk, batostr(&sa.rc_bdaddr));
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
@@ -369,12 +373,12 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr
write_lock_bh(&rfcomm_sk_list.lock);
- if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) {
+ if (sa.rc_channel && __rfcomm_get_sock_by_addr(sa.rc_channel, &sa.rc_bdaddr)) {
err = -EADDRINUSE;
} else {
/* Save source address */
- bacpy(&bt_sk(sk)->src, &sa->rc_bdaddr);
- rfcomm_pi(sk)->channel = sa->rc_channel;
+ bacpy(&bt_sk(sk)->src, &sa.rc_bdaddr);
+ rfcomm_pi(sk)->channel = sa.rc_channel;
sk->sk_state = BT_BOUND;
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 29a07b6c716..0ee2d50c634 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -107,7 +107,8 @@ int ip_forward(struct sk_buff *skb)
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
- if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+ if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+ !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index fd7a3f68917..f4865d2958f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -350,11 +350,12 @@ unsigned int arpt_do_table(struct sk_buff *skb,
}
/* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
{
static const struct arpt_arp uncond;
- return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct arpt_entry) &&
+ memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
}
/* Figures out from what hook each rule can be called: returns 0 if
@@ -393,11 +394,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct arpt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->arp)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -465,14 +465,12 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
return 1;
}
-static inline int check_entry(const struct arpt_entry *e, const char *name)
+static inline int check_entry(const struct arpt_entry *e)
{
const struct xt_entry_target *t;
- if (!arp_checkentry(&e->arp)) {
- duprintf("arp_tables: arp check failed %p %s.\n", e, name);
+ if (!arp_checkentry(&e->arp))
return -EINVAL;
- }
if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
return -EINVAL;
@@ -513,10 +511,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
struct xt_target *target;
int ret;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
t = arpt_get_target(e);
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
t->u.user.revision);
@@ -542,7 +536,7 @@ static bool check_underflow(const struct arpt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->arp))
+ if (!unconditional(e))
return false;
t = arpt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -561,9 +555,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -575,6 +571,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
return -EINVAL;
}
+ err = check_entry(e);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -583,9 +583,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -1217,7 +1217,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1230,7 +1231,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
}
/* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct arpt_entry *)e, name);
+ ret = check_entry((struct arpt_entry *)e);
if (ret)
return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 24e556e83a3..d0f907567e1 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
/* All zeroes == unconditional rule. */
/* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
{
static const struct ipt_ip uncond;
- return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct ipt_entry) &&
+ memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
#undef FWINV
}
@@ -230,11 +231,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
} else if (s == e) {
(*rulenum)++;
- if (s->target_offset == sizeof(struct ipt_entry) &&
+ if (unconditional(s) &&
strcmp(t->target.u.kernel.target->name,
XT_STANDARD_TARGET) == 0 &&
- t->verdict < 0 &&
- unconditional(&s->ip)) {
+ t->verdict < 0) {
/* Tail of chains: STANDARD target (return/policy) */
*comment = *chainname == hookname
? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -468,11 +468,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct ipt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->ip)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -561,14 +560,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
}
static int
-check_entry(const struct ipt_entry *e, const char *name)
+check_entry(const struct ipt_entry *e)
{
const struct xt_entry_target *t;
- if (!ip_checkentry(&e->ip)) {
- duprintf("ip check failed %p %s.\n", e, name);
+ if (!ip_checkentry(&e->ip))
return -EINVAL;
- }
if (e->target_offset + sizeof(struct xt_entry_target) >
e->next_offset)
@@ -658,10 +655,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
j = 0;
mtpar.net = net;
mtpar.table = name;
@@ -705,7 +698,7 @@ static bool check_underflow(const struct ipt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->ip))
+ if (!unconditional(e))
return false;
t = ipt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -725,9 +718,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -739,6 +734,10 @@ check_entry_size_and_hooks(struct ipt_entry *e,
return -EINVAL;
}
+ err = check_entry(e);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_INET_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -747,9 +746,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -1484,7 +1483,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1497,7 +1497,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
}
/* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct ipt_entry *)e, name);
+ ret = check_entry((struct ipt_entry *)e);
if (ret)
return ret;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3097eca70fd..12e7474d6e3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2156,9 +2156,10 @@ static int __mkroute_input(struct sk_buff *skb,
flags |= RTCF_DIRECTSRC;
if (out_dev == in_dev && err &&
+ skb->protocol == htons(ETH_P_IP) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
- flags |= RTCF_DOREDIRECT;
+ IPCB(skb)->flags |= IPSKB_DOREDIRECT;
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
@@ -2987,6 +2988,8 @@ static int rt_fill_info(struct net *net,
r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
+ if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+ r->rtm_flags |= RTCF_DOREDIRECT;
NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4d844344f26..18c43ad0620 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1253,10 +1253,8 @@ csum_copy_err:
UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 176b469322a..882525464a0 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1266,7 +1266,14 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (rt)
rt6_set_expires(rt, jiffies + (HZ * lifetime));
if (ra_msg->icmph.icmp6_hop_limit) {
- in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ /* Only set hop_limit on the interface if it is higher than
+ * the current hop_limit.
+ */
+ if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+ in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ } else {
+ ND_PRINTK2(KERN_WARNING, "RA: Got route advertisement with lower hop_limit than current\n");
+ }
if (rt)
dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e641f8fa748..4b570b06fdb 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -195,11 +195,12 @@ get_entry(const void *base, unsigned int offset)
/* All zeroes == unconditional rule. */
/* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ip6t_ip6 *ipv6)
+static inline bool unconditional(const struct ip6t_entry *e)
{
static const struct ip6t_ip6 uncond;
- return memcmp(ipv6, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct ip6t_entry) &&
+ memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0;
}
static inline const struct xt_entry_target *
@@ -256,11 +257,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e,
} else if (s == e) {
(*rulenum)++;
- if (s->target_offset == sizeof(struct ip6t_entry) &&
+ if (unconditional(s) &&
strcmp(t->target.u.kernel.target->name,
XT_STANDARD_TARGET) == 0 &&
- t->verdict < 0 &&
- unconditional(&s->ipv6)) {
+ t->verdict < 0) {
/* Tail of chains: STANDARD target (return/policy) */
*comment = *chainname == hookname
? comments[NF_IP6_TRACE_COMMENT_POLICY]
@@ -477,11 +477,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct ip6t_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 &&
- unconditional(&e->ipv6)) || visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -570,14 +569,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
}
static int
-check_entry(const struct ip6t_entry *e, const char *name)
+check_entry(const struct ip6t_entry *e)
{
const struct xt_entry_target *t;
- if (!ip6_checkentry(&e->ipv6)) {
- duprintf("ip_tables: ip check failed %p %s.\n", e, name);
+ if (!ip6_checkentry(&e->ipv6))
return -EINVAL;
- }
if (e->target_offset + sizeof(struct xt_entry_target) >
e->next_offset)
@@ -668,10 +665,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
j = 0;
mtpar.net = net;
mtpar.table = name;
@@ -715,7 +708,7 @@ static bool check_underflow(const struct ip6t_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->ipv6))
+ if (!unconditional(e))
return false;
t = ip6t_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -735,9 +728,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 ||
- (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct ip6t_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -749,6 +744,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
return -EINVAL;
}
+ err = check_entry(e);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_INET_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -757,9 +756,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -1495,7 +1494,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1508,7 +1508,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
}
/* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct ip6t_entry *)e, name);
+ ret = check_entry((struct ip6t_entry *)e);
if (ret)
return ret;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 101d2ba8df2..1f8f1177ea3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -454,10 +454,8 @@ csum_copy_err:
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
diff --git a/net/socket.c b/net/socket.c
index 9d4b212ae2d..b3e305287bf 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2290,31 +2290,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
break;
}
-out_put:
- fput_light(sock->file, fput_needed);
-
if (err == 0)
- return datagrams;
+ goto out_put;
- if (datagrams != 0) {
+ if (datagrams == 0) {
+ datagrams = err;
+ goto out_put;
+ }
+
+ /*
+ * We may return less entries than requested (vlen) if the
+ * sock is non block and there aren't enough datagrams...
+ */
+ if (err != -EAGAIN) {
/*
- * We may return less entries than requested (vlen) if the
- * sock is non block and there aren't enough datagrams...
+ * ... or if recvmsg returns an error after we
+ * received some datagrams, where we record the
+ * error to return on the next call or if the
+ * app asks about it using getsockopt(SO_ERROR).
*/
- if (err != -EAGAIN) {
- /*
- * ... or if recvmsg returns an error after we
- * received some datagrams, where we record the
- * error to return on the next call or if the
- * app asks about it using getsockopt(SO_ERROR).
- */
- sock->sk->sk_err = -err;
- }
-
- return datagrams;
+ sock->sk->sk_err = -err;
}
+out_put:
+ fput_light(sock->file, fput_needed);
- return err;
+ return datagrams;
}
SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8d932a5c534..5266f779fd4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -307,6 +307,118 @@ 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;
@@ -411,6 +523,8 @@ static int 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;
}
@@ -645,6 +759,7 @@ 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);
out:
if (sk == NULL)
@@ -1014,6 +1129,8 @@ 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)
@@ -1443,6 +1560,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
long timeo;
struct scm_cookie tmp_scm;
int max_level;
+ int sk_locked;
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
@@ -1511,12 +1629,14 @@ 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
@@ -1524,10 +1644,14 @@ 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);
@@ -1553,21 +1677,38 @@ 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);
@@ -1581,6 +1722,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -2211,14 +2354,16 @@ 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 2025-12-20 18:50:10 +0000