summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c6
-rw-r--r--net/core/dev.c48
-rw-r--r--net/core/drop_monitor.c12
-rw-r--r--net/core/neighbour.c1
-rw-r--r--net/core/rtnetlink.c30
-rw-r--r--net/core/skbuff.c1
-rw-r--r--net/core/sock.c52
7 files changed, 109 insertions, 41 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index e0097531417a..f5b6f43a4c2e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -229,15 +229,17 @@ EXPORT_SYMBOL(skb_free_datagram);
void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
{
+ bool slow;
+
if (likely(atomic_read(&skb->users) == 1))
smp_rmb();
else if (likely(!atomic_dec_and_test(&skb->users)))
return;
- lock_sock_bh(sk);
+ slow = lock_sock_fast(sk);
skb_orphan(skb);
sk_mem_reclaim_partial(sk);
- unlock_sock_bh(sk);
+ unlock_sock_fast(sk, slow);
/* skb is now orphaned, can be freed outside of locked section */
__kfree_skb(skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index d273e4e3ecdc..1845b08c624e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -954,18 +954,22 @@ int dev_alloc_name(struct net_device *dev, const char *name)
}
EXPORT_SYMBOL(dev_alloc_name);
-static int dev_get_valid_name(struct net *net, const char *name, char *buf,
- bool fmt)
+static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt)
{
+ struct net *net;
+
+ BUG_ON(!dev_net(dev));
+ net = dev_net(dev);
+
if (!dev_valid_name(name))
return -EINVAL;
if (fmt && strchr(name, '%'))
- return __dev_alloc_name(net, name, buf);
+ return dev_alloc_name(dev, name);
else if (__dev_get_by_name(net, name))
return -EEXIST;
- else if (buf != name)
- strlcpy(buf, name, IFNAMSIZ);
+ else if (dev->name != name)
+ strlcpy(dev->name, name, IFNAMSIZ);
return 0;
}
@@ -997,7 +1001,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
memcpy(oldname, dev->name, IFNAMSIZ);
- err = dev_get_valid_name(net, newname, dev->name, 1);
+ err = dev_get_valid_name(dev, newname, 1);
if (err < 0)
return err;
@@ -2421,10 +2425,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
-#ifdef CONFIG_RPS
- *qtail = sd->input_queue_head +
- skb_queue_len(&sd->input_pkt_queue);
-#endif
+ input_queue_tail_incr_save(sd, qtail);
rps_unlock(sd);
local_irq_restore(flags);
return NET_RX_SUCCESS;
@@ -2959,7 +2960,7 @@ static void flush_backlog(void *arg)
if (skb->dev == dev) {
__skb_unlink(skb, &sd->input_pkt_queue);
kfree_skb(skb);
- input_queue_head_add(sd, 1);
+ input_queue_head_incr(sd);
}
}
rps_unlock(sd);
@@ -2968,6 +2969,7 @@ static void flush_backlog(void *arg)
if (skb->dev == dev) {
__skb_unlink(skb, &sd->process_queue);
kfree_skb(skb);
+ input_queue_head_incr(sd);
}
}
}
@@ -3323,18 +3325,20 @@ static int process_backlog(struct napi_struct *napi, int quota)
while ((skb = __skb_dequeue(&sd->process_queue))) {
local_irq_enable();
__netif_receive_skb(skb);
- if (++work >= quota)
- return work;
local_irq_disable();
+ input_queue_head_incr(sd);
+ if (++work >= quota) {
+ local_irq_enable();
+ return work;
+ }
}
rps_lock(sd);
qlen = skb_queue_len(&sd->input_pkt_queue);
- if (qlen) {
- input_queue_head_add(sd, qlen);
+ if (qlen)
skb_queue_splice_tail_init(&sd->input_pkt_queue,
&sd->process_queue);
- }
+
if (qlen < quota - work) {
/*
* Inline a custom version of __napi_complete().
@@ -4960,7 +4964,7 @@ int register_netdevice(struct net_device *dev)
}
}
- ret = dev_get_valid_name(net, dev->name, dev->name, 0);
+ ret = dev_get_valid_name(dev, dev->name, 0);
if (ret)
goto err_uninit;
@@ -5558,7 +5562,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (dev_get_valid_name(net, pat, dev->name, 1))
+ if (dev_get_valid_name(dev, pat, 1))
goto out;
}
@@ -5661,12 +5665,14 @@ static int dev_cpu_callback(struct notifier_block *nfb,
local_irq_enable();
/* Process offline CPU's input_pkt_queue */
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = __skb_dequeue(&oldsd->process_queue))) {
netif_rx(skb);
- input_queue_head_add(oldsd, 1);
+ input_queue_head_incr(oldsd);
}
- while ((skb = __skb_dequeue(&oldsd->process_queue)))
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
+ input_queue_head_incr(oldsd);
+ }
return NOTIFY_OK;
}
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index cf208d8042b1..ad41529fb60f 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -172,12 +172,12 @@ out:
return;
}
-static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
{
trace_drop_common(skb, location);
}
-static void trace_napi_poll_hit(struct napi_struct *napi)
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
{
struct dm_hw_stat_delta *new_stat;
@@ -225,12 +225,12 @@ static int set_all_monitor_traces(int state)
switch (state) {
case TRACE_ON:
- rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
- rc |= register_trace_napi_poll(trace_napi_poll_hit);
+ rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+ rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
break;
case TRACE_OFF:
- rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
- rc |= unregister_trace_napi_poll(trace_napi_poll_hit);
+ rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+ rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
tracepoint_synchronize_unregister();
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bff37908bd55..6ba1c0eece03 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -934,6 +934,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
kfree_skb(buff);
NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
}
+ skb_dst_force(skb);
__skb_queue_tail(&neigh->arp_queue, skb);
}
rc = 1;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e4b9870e4706..1a2af24e9e3d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -650,11 +650,12 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev)
if (dev->dev.parent && dev_is_pci(dev->dev.parent)) {
int num_vfs = dev_num_vf(dev->dev.parent);
- size_t size = nlmsg_total_size(sizeof(struct nlattr));
- size += nlmsg_total_size(num_vfs * sizeof(struct nlattr));
- size += num_vfs * (sizeof(struct ifla_vf_mac) +
- sizeof(struct ifla_vf_vlan) +
- sizeof(struct ifla_vf_tx_rate));
+ size_t size = nla_total_size(sizeof(struct nlattr));
+ size += nla_total_size(num_vfs * sizeof(struct nlattr));
+ size += num_vfs *
+ (nla_total_size(sizeof(struct ifla_vf_mac)) +
+ nla_total_size(sizeof(struct ifla_vf_vlan)) +
+ nla_total_size(sizeof(struct ifla_vf_tx_rate)));
return size;
} else
return 0;
@@ -722,14 +723,13 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
vf_port = nla_nest_start(skb, IFLA_VF_PORT);
- if (!vf_port) {
- nla_nest_cancel(skb, vf_ports);
- return -EMSGSIZE;
- }
+ if (!vf_port)
+ goto nla_put_failure;
NLA_PUT_U32(skb, IFLA_PORT_VF, vf);
err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
+ if (err == -EMSGSIZE)
+ goto nla_put_failure;
if (err) {
-nla_put_failure:
nla_nest_cancel(skb, vf_port);
continue;
}
@@ -739,6 +739,10 @@ nla_put_failure:
nla_nest_end(skb, vf_ports);
return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, vf_ports);
+ return -EMSGSIZE;
}
static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
@@ -753,7 +757,7 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb);
if (err) {
nla_nest_cancel(skb, port_self);
- return err;
+ return (err == -EMSGSIZE) ? err : 0;
}
nla_nest_end(skb, port_self);
@@ -1199,8 +1203,10 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
struct nlattr *attr;
int rem;
nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
- if (nla_type(attr) != IFLA_VF_INFO)
+ if (nla_type(attr) != IFLA_VF_INFO) {
+ err = -EINVAL;
goto errout;
+ }
err = do_setvfinfo(dev, attr);
if (err < 0)
goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 66d9c416851e..f8abf68e3988 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2722,6 +2722,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
*NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p);
skb_shinfo(nskb)->frag_list = p;
skb_shinfo(nskb)->gso_size = pinfo->gso_size;
+ pinfo->gso_size = 0;
skb_header_release(p);
nskb->prev = p;
diff --git a/net/core/sock.c b/net/core/sock.c
index bf88a167c8f2..2cf7f9f7e775 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -123,6 +123,7 @@
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
+#include <net/cls_cgroup.h>
#include <linux/filter.h>
@@ -217,6 +218,11 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
+#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+int net_cls_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_cls_subsys_id);
+#endif
+
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
struct timeval tv;
@@ -1050,6 +1056,17 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
+#ifdef CONFIG_CGROUPS
+void sock_update_classid(struct sock *sk)
+{
+ u32 classid = task_cls_classid(current);
+
+ if (classid && classid != sk->sk_classid)
+ sk->sk_classid = classid;
+}
+EXPORT_SYMBOL(sock_update_classid);
+#endif
+
/**
* sk_alloc - All socket objects are allocated here
* @net: the applicable net namespace
@@ -1073,6 +1090,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sock_lock_init(sk);
sock_net_set(sk, get_net(net));
atomic_set(&sk->sk_wmem_alloc, 1);
+
+ sock_update_classid(sk);
}
return sk;
@@ -1988,6 +2007,39 @@ void release_sock(struct sock *sk)
}
EXPORT_SYMBOL(release_sock);
+/**
+ * lock_sock_fast - fast version of lock_sock
+ * @sk: socket
+ *
+ * This version should be used for very small section, where process wont block
+ * return false if fast path is taken
+ * sk_lock.slock locked, owned = 0, BH disabled
+ * return true if slow path is taken
+ * sk_lock.slock unlocked, owned = 1, BH enabled
+ */
+bool lock_sock_fast(struct sock *sk)
+{
+ might_sleep();
+ spin_lock_bh(&sk->sk_lock.slock);
+
+ if (!sk->sk_lock.owned)
+ /*
+ * Note : We must disable BH
+ */
+ return false;
+
+ __lock_sock(sk);
+ sk->sk_lock.owned = 1;
+ spin_unlock(&sk->sk_lock.slock);
+ /*
+ * The sk_lock has mutex_lock() semantics here:
+ */
+ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+ local_bh_enable();
+ return true;
+}
+EXPORT_SYMBOL(lock_sock_fast);
+
int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
struct timeval tv;
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2024-12-29 02:35:33 +0000