summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c29
-rw-r--r--net/core/devlink.c4
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/filter.c1
-rw-r--r--net/core/neighbour.c1
-rw-r--r--net/core/net_namespace.c20
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/skbuff.c4
-rw-r--r--net/core/sock.c24
9 files changed, 65 insertions, 24 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 222b1d322c96..ef8cf7619baf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
if (q->flags & TCQ_F_NOLOCK) {
rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
- qdisc_run(q);
+ if (likely(!netif_xmit_frozen_or_stopped(txq)))
+ qdisc_run(q);
if (unlikely(to_free))
kfree_skb_list(to_free);
@@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
+ rcu_read_lock();
+
while (head) {
struct Qdisc *q = head;
spinlock_t *root_lock = NULL;
head = head->next_sched;
- if (!(q->flags & TCQ_F_NOLOCK)) {
- root_lock = qdisc_lock(q);
- spin_lock(root_lock);
- }
/* We need to make sure head->next_sched is read
* before clearing __QDISC_STATE_SCHED
*/
smp_mb__before_atomic();
+
+ if (!(q->flags & TCQ_F_NOLOCK)) {
+ root_lock = qdisc_lock(q);
+ spin_lock(root_lock);
+ } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+ &q->state))) {
+ /* There is a synchronize_net() between
+ * STATE_DEACTIVATED flag being set and
+ * qdisc_reset()/some_qdisc_is_busy() in
+ * dev_deactivate(), so we can safely bail out
+ * early here to avoid data race between
+ * qdisc_deactivate() and some_qdisc_is_busy()
+ * for lockless qdisc.
+ */
+ clear_bit(__QDISC_STATE_SCHED, &q->state);
+ continue;
+ }
+
clear_bit(__QDISC_STATE_SCHED, &q->state);
qdisc_run(q);
if (root_lock)
spin_unlock(root_lock);
}
+
+ rcu_read_unlock();
}
xfrm_dev_backlog(sd);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4eb969518ee0..051432ea4f69 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -705,7 +705,6 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
attrs->phys.port_number))
return -EMSGSIZE;
@@ -8631,7 +8630,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
switch (attrs->flavour) {
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
if (!attrs->split)
n = snprintf(name, len, "p%u", attrs->phys.port_number);
else
@@ -8679,6 +8677,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
attrs->pci_sf.sf);
break;
+ case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+ return -EOPNOTSUPP;
}
if (n >= len)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index cd80ffed6d26..a9f937975080 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -1168,7 +1168,7 @@ static void notify_rule_change(int event, struct fib_rule *rule,
{
struct net *net;
struct sk_buff *skb;
- int err = -ENOBUFS;
+ int err = -ENOMEM;
net = ops->fro_net;
skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..65ab4e21c087 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
__skb_push(skb, head_room);
memset(skb->data, 0, head_room);
skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
}
return ret;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 98f20efbfadf..bf774575ad71 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -238,6 +238,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
write_lock(&n->lock);
if ((n->nud_state == NUD_FAILED) ||
+ (n->nud_state == NUD_NOARP) ||
(tbl->is_multicast &&
tbl->is_multicast(n->primary_key)) ||
time_after(tref, n->updated))
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 43b6ac4c4439..9b5a767eddd5 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -641,6 +641,18 @@ void __put_net(struct net *net)
}
EXPORT_SYMBOL_GPL(__put_net);
+/**
+ * get_net_ns - increment the refcount of the network namespace
+ * @ns: common namespace (net)
+ *
+ * Returns the net's common namespace.
+ */
+struct ns_common *get_net_ns(struct ns_common *ns)
+{
+ return &get_net(container_of(ns, struct net, ns))->ns;
+}
+EXPORT_SYMBOL_GPL(get_net_ns);
+
struct net *get_net_ns_by_fd(int fd)
{
struct file *file;
@@ -660,14 +672,8 @@ struct net *get_net_ns_by_fd(int fd)
fput(file);
return net;
}
-
-#else
-struct net *get_net_ns_by_fd(int fd)
-{
- return ERR_PTR(-EINVAL);
-}
-#endif
EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
+#endif
struct net *get_net_ns_by_pid(pid_t pid)
{
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 714d5fa38546..ec931b080156 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4842,6 +4842,10 @@ static int rtnl_bridge_notify(struct net_device *dev)
if (err < 0)
goto errout;
+ /* Notification info is only filled for bridge ports, not the bridge
+ * device itself. Therefore, a zero notification length is valid and
+ * should not result in an error.
+ */
if (!skb->len)
goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3ad22870298c..bbc3b4b62032 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1253,6 +1253,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg)
struct sock *sk = skb->sk;
struct sk_buff_head *q;
unsigned long flags;
+ bool is_zerocopy;
u32 lo, hi;
u16 len;
@@ -1267,6 +1268,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg)
len = uarg->len;
lo = uarg->id;
hi = uarg->id + len - 1;
+ is_zerocopy = uarg->zerocopy;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
@@ -1274,7 +1276,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg)
serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY;
serr->ee.ee_data = hi;
serr->ee.ee_info = lo;
- if (!uarg->zerocopy)
+ if (!is_zerocopy)
serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED;
q = &sk->sk_error_queue;
diff --git a/net/core/sock.c b/net/core/sock.c
index c761c4a0b66b..946888afef88 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -815,10 +815,18 @@ void sock_set_rcvbuf(struct sock *sk, int val)
}
EXPORT_SYMBOL(sock_set_rcvbuf);
+static void __sock_set_mark(struct sock *sk, u32 val)
+{
+ if (val != sk->sk_mark) {
+ sk->sk_mark = val;
+ sk_dst_reset(sk);
+ }
+}
+
void sock_set_mark(struct sock *sk, u32 val)
{
lock_sock(sk);
- sk->sk_mark = val;
+ __sock_set_mark(sk, val);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_mark);
@@ -1126,10 +1134,10 @@ set_sndbuf:
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
- } else if (val != sk->sk_mark) {
- sk->sk_mark = val;
- sk_dst_reset(sk);
+ break;
}
+
+ __sock_set_mark(sk, val);
break;
case SO_RXQ_OVFL:
@@ -2132,10 +2140,10 @@ void skb_orphan_partial(struct sk_buff *skb)
if (skb_is_tcp_pure_ack(skb))
return;
- if (can_skb_orphan_partial(skb))
- skb_set_owner_sk_safe(skb, skb->sk);
- else
- skb_orphan(skb);
+ if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk))
+ return;
+
+ skb_orphan(skb);
}
EXPORT_SYMBOL(skb_orphan_partial);