summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c1
-rw-r--r--net/core/dev.c128
-rw-r--r--net/core/dst.c35
-rw-r--r--net/core/ethtool.c45
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/flow_dissector.c5
-rw-r--r--net/core/neighbour.c31
-rw-r--r--net/core/net-sysfs.c74
-rw-r--r--net/core/netpoll.c105
-rw-r--r--net/core/netprio_cgroup.c49
-rw-r--r--net/core/rtnetlink.c74
-rw-r--r--net/core/scm.c26
-rw-r--r--net/core/skbuff.c195
-rw-r--r--net/core/sock.c75
-rw-r--r--net/core/sock_diag.c42
16 files changed, 610 insertions, 287 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ae6acf6a3de..0337e2b7686 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -248,7 +248,6 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
unlock_sock_fast(sk, slow);
/* skb is now orphaned, can be freed outside of locked section */
- trace_kfree_skb(skb, skb_free_datagram_locked);
__kfree_skb(skb);
}
EXPORT_SYMBOL(skb_free_datagram_locked);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1cb0d8a6aa6..83988362805 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1055,6 +1055,8 @@ rollback:
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
+ char *new_ifalias;
+
ASSERT_RTNL();
if (len >= IFALIASZ)
@@ -1068,9 +1070,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
return 0;
}
- dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
- if (!dev->ifalias)
+ new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+ if (!new_ifalias)
return -ENOMEM;
+ dev->ifalias = new_ifalias;
strlcpy(dev->ifalias, alias, len+1);
return len;
@@ -1172,6 +1175,7 @@ static int __dev_open(struct net_device *dev)
net_dmaengine_get();
dev_set_rx_mode(dev);
dev_activate(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
@@ -1632,10 +1636,25 @@ static inline int deliver_skb(struct sk_buff *skb,
struct packet_type *pt_prev,
struct net_device *orig_dev)
{
+ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+ return -ENOMEM;
atomic_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
+static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
+{
+ if (ptype->af_packet_priv == NULL)
+ return false;
+
+ if (ptype->id_match)
+ return ptype->id_match(ptype, skb->sk);
+ else if ((struct sock *)ptype->af_packet_priv == skb->sk)
+ return true;
+
+ return false;
+}
+
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
@@ -1653,8 +1672,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if ((ptype->dev == dev || !ptype->dev) &&
- (ptype->af_packet_priv == NULL ||
- (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ (!skb_loop_sk(ptype, skb))) {
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
@@ -1691,7 +1709,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
rcu_read_unlock();
}
-/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
+/**
+ * netif_setup_tc - Handle tc mappings on real_num_tx_queues change
* @dev: Network device
* @txq: number of queues available
*
@@ -1793,6 +1812,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
#endif
+/**
+ * netif_get_num_default_rss_queues - default number of RSS queues
+ *
+ * This routine should set an upper limit on the number of RSS queues
+ * used by default by multiqueue devices.
+ */
+int netif_get_num_default_rss_queues(void)
+{
+ return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+}
+EXPORT_SYMBOL(netif_get_num_default_rss_queues);
+
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
@@ -2118,6 +2149,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
__be16 protocol = skb->protocol;
netdev_features_t features = skb->dev->features;
+ if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ features &= ~NETIF_F_GSO_MASK;
+
if (protocol == htons(ETH_P_8021Q)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
@@ -2459,6 +2493,23 @@ static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 10
/**
+ * dev_loopback_xmit - loop back @skb
+ * @skb: buffer to transmit
+ */
+int dev_loopback_xmit(struct sk_buff *skb)
+{
+ skb_reset_mac_header(skb);
+ __skb_pull(skb, skb_network_offset(skb));
+ skb->pkt_type = PACKET_LOOPBACK;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ WARN_ON(!skb_dst(skb));
+ skb_dst_force(skb);
+ netif_rx_ni(skb);
+ return 0;
+}
+EXPORT_SYMBOL(dev_loopback_xmit);
+
+/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
*
@@ -3123,6 +3174,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_ARP):
+ case __constant_htons(ETH_P_IP):
+ case __constant_htons(ETH_P_IPV6):
+ case __constant_htons(ETH_P_8021Q):
+ return true;
+ default:
+ return false;
+ }
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -3132,17 +3200,28 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ current->flags |= PF_MEMALLOC;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ goto out;
- if (!skb->skb_iif)
- skb->skb_iif = skb->dev->ifindex;
orig_dev = skb->dev;
skb_reset_network_header(skb);
@@ -3154,13 +3233,14 @@ static int __netif_receive_skb(struct sk_buff *skb)
rcu_read_lock();
another_round:
+ skb->skb_iif = skb->dev->ifindex;
__this_cpu_inc(softnet_data.processed);
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto out;
+ goto unlock;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3170,6 +3250,9 @@ another_round:
}
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
@@ -3178,13 +3261,18 @@ another_round:
}
}
+skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto out;
+ goto unlock;
ncls:
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+ && !skb_pfmemalloc_protocol(skb))
+ goto drop;
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
@@ -3194,7 +3282,7 @@ ncls:
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
- goto out;
+ goto unlock;
}
if (rx_handler) {
@@ -3204,7 +3292,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
- goto out;
+ goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3232,8 +3320,12 @@ ncls:
}
if (pt_prev) {
- ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+ ret = -ENOMEM;
+ else
+ ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+drop:
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
@@ -3242,8 +3334,10 @@ ncls:
ret = NET_RX_DROP;
}
-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
@@ -4767,6 +4861,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
err = ops->ndo_set_mac_address(dev, sa);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
return err;
}
EXPORT_SYMBOL(dev_set_mac_address);
@@ -5545,6 +5640,7 @@ int register_netdevice(struct net_device *dev)
dev_init_scheduler(dev);
dev_hold(dev);
list_netdevice(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -5646,8 +5742,9 @@ int netdev_refcnt_read(const struct net_device *dev)
}
EXPORT_SYMBOL(netdev_refcnt_read);
-/*
+/**
* netdev_wait_allrefs - wait until all references are gone.
+ * @dev: target net_device
*
* This is called when unregistering network devices.
*
@@ -5908,6 +6005,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net);
dev->gso_max_size = GSO_MAX_SIZE;
+ dev->gso_max_segs = GSO_MAX_SEGS;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
diff --git a/net/core/dst.c b/net/core/dst.c
index 43d94cedbf7..56d63612e1e 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -94,7 +94,7 @@ loop:
* But we do not have state "obsoleted, but
* referenced by parent", so it is right.
*/
- if (dst->obsolete > 1)
+ if (dst->obsolete > 0)
continue;
___dst_free(dst);
@@ -149,10 +149,18 @@ int dst_discard(struct sk_buff *skb)
}
EXPORT_SYMBOL(dst_discard);
-const u32 dst_default_metrics[RTAX_MAX];
+const u32 dst_default_metrics[RTAX_MAX + 1] = {
+ /* This initializer is needed to force linker to place this variable
+ * into const section. Otherwise it might end into bss section.
+ * We really want to avoid false sharing on this variable, and catch
+ * any writes on it.
+ */
+ [RTAX_MAX] = 0xdeadbeef,
+};
+
void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
- int initial_ref, int initial_obsolete, int flags)
+ int initial_ref, int initial_obsolete, unsigned short flags)
{
struct dst_entry *dst;
@@ -171,7 +179,6 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
dst_init_metrics(dst, dst_default_metrics, true);
dst->expires = 0UL;
dst->path = dst;
- RCU_INIT_POINTER(dst->_neighbour, NULL);
#ifdef CONFIG_XFRM
dst->xfrm = NULL;
#endif
@@ -188,6 +195,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
dst->__use = 0;
dst->lastuse = jiffies;
dst->flags = flags;
+ dst->pending_confirm = 0;
dst->next = NULL;
if (!(flags & DST_NOCOUNT))
dst_entries_add(ops, 1);
@@ -202,7 +210,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP))
dst->input = dst->output = dst_discard;
- dst->obsolete = 2;
+ dst->obsolete = DST_OBSOLETE_DEAD;
}
void __dst_free(struct dst_entry *dst)
@@ -224,19 +232,12 @@ EXPORT_SYMBOL(__dst_free);
struct dst_entry *dst_destroy(struct dst_entry * dst)
{
struct dst_entry *child;
- struct neighbour *neigh;
smp_rmb();
again:
- neigh = rcu_dereference_protected(dst->_neighbour, 1);
child = dst->child;
- if (neigh) {
- RCU_INIT_POINTER(dst->_neighbour, NULL);
- neigh_release(neigh);
- }
-
if (!(dst->flags & DST_NOCOUNT))
dst_entries_add(dst->ops, -1);
@@ -360,19 +361,9 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
if (!unregister) {
dst->input = dst->output = dst_discard;
} else {
- struct neighbour *neigh;
-
dst->dev = dev_net(dst->dev)->loopback_dev;
dev_hold(dst->dev);
dev_put(dev);
- rcu_read_lock();
- neigh = dst_get_neighbour_noref(dst);
- if (neigh && neigh->dev == dev) {
- neigh->dev = dst->dev;
- dev_hold(dst->dev);
- dev_put(dev);
- }
- rcu_read_unlock();
}
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9c2afb48027..cbf033dcaf1 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -729,6 +729,40 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
return dev->ethtool_ops->set_wol(dev, &wol);
}
+static int ethtool_get_eee(struct net_device *dev, char __user *useraddr)
+{
+ struct ethtool_eee edata;
+ int rc;
+
+ if (!dev->ethtool_ops->get_eee)
+ return -EOPNOTSUPP;
+
+ memset(&edata, 0, sizeof(struct ethtool_eee));
+ edata.cmd = ETHTOOL_GEEE;
+ rc = dev->ethtool_ops->get_eee(dev, &edata);
+
+ if (rc)
+ return rc;
+
+ if (copy_to_user(useraddr, &edata, sizeof(edata)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_set_eee(struct net_device *dev, char __user *useraddr)
+{
+ struct ethtool_eee edata;
+
+ if (!dev->ethtool_ops->set_eee)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&edata, useraddr, sizeof(edata)))
+ return -EFAULT;
+
+ return dev->ethtool_ops->set_eee(dev, &edata);
+}
+
static int ethtool_nway_reset(struct net_device *dev)
{
if (!dev->ethtool_ops->nway_reset)
@@ -1409,6 +1443,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GSET:
case ETHTOOL_GDRVINFO:
case ETHTOOL_GMSGLVL:
+ case ETHTOOL_GLINK:
case ETHTOOL_GCOALESCE:
case ETHTOOL_GRINGPARAM:
case ETHTOOL_GPAUSEPARAM:
@@ -1417,6 +1452,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GSG:
case ETHTOOL_GSSET_INFO:
case ETHTOOL_GSTRINGS:
+ case ETHTOOL_GSTATS:
case ETHTOOL_GTSO:
case ETHTOOL_GPERMADDR:
case ETHTOOL_GUFO:
@@ -1429,8 +1465,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
+ case ETHTOOL_GRXFHINDIR:
case ETHTOOL_GFEATURES:
+ case ETHTOOL_GCHANNELS:
case ETHTOOL_GET_TS_INFO:
+ case ETHTOOL_GEEE:
break;
default:
if (!capable(CAP_NET_ADMIN))
@@ -1471,6 +1510,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
rc = ethtool_set_value_void(dev, useraddr,
dev->ethtool_ops->set_msglevel);
break;
+ case ETHTOOL_GEEE:
+ rc = ethtool_get_eee(dev, useraddr);
+ break;
+ case ETHTOOL_SEEE:
+ rc = ethtool_set_eee(dev, useraddr);
+ break;
case ETHTOOL_NWAY_RST:
rc = ethtool_nway_reset(dev);
break;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 72cceb79d0d..ab7db83236c 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -151,6 +151,8 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) {
list_del_rcu(&rule->list);
+ if (ops->delete)
+ ops->delete(rule);
fib_rule_put(rule);
}
}
@@ -499,6 +501,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).pid);
+ if (ops->delete)
+ ops->delete(rule);
fib_rule_put(rule);
flush_route_cache(ops);
rules_ops_put(ops);
diff --git a/net/core/filter.c b/net/core/filter.c
index d4ce2dc712e..907efd27ec7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
int err;
struct sk_filter *filter;
+ /*
+ * If the skb was allocated from pfmemalloc reserves, only
+ * allow SOCK_MEMALLOC sockets to use it as this socket is
+ * helping free memory
+ */
+ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+ return -ENOMEM;
+
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a225089df5b..466820b6e34 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -4,6 +4,7 @@
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <net/ip.h>
+#include <net/ipv6.h>
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
@@ -55,8 +56,8 @@ ipv6:
return false;
ip_proto = iph->nexthdr;
- flow->src = iph->saddr.s6_addr32[3];
- flow->dst = iph->daddr.s6_addr32[3];
+ flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
+ flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
nhoff += sizeof(struct ipv6hdr);
break;
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index d81d026138f..117afaf5126 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -474,8 +474,8 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
}
EXPORT_SYMBOL(neigh_lookup_nodev);
-struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
- struct net_device *dev)
+struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
+ struct net_device *dev, bool want_ref)
{
u32 hash_val;
int key_len = tbl->key_len;
@@ -535,14 +535,16 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
n1 = rcu_dereference_protected(n1->next,
lockdep_is_held(&tbl->lock))) {
if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
- neigh_hold(n1);
+ if (want_ref)
+ neigh_hold(n1);
rc = n1;
goto out_tbl_unlock;
}
}
n->dead = 0;
- neigh_hold(n);
+ if (want_ref)
+ neigh_hold(n);
rcu_assign_pointer(n->next,
rcu_dereference_protected(nht->hash_buckets[hash_val],
lockdep_is_held(&tbl->lock)));
@@ -558,7 +560,7 @@ out_neigh_release:
neigh_release(n);
goto out;
}
-EXPORT_SYMBOL(neigh_create);
+EXPORT_SYMBOL(__neigh_create);
static u32 pneigh_hash(const void *pkey, int key_len)
{
@@ -1199,10 +1201,23 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
write_unlock_bh(&neigh->lock);
rcu_read_lock();
- /* On shaper/eql skb->dst->neighbour != neigh :( */
- if (dst && (n2 = dst_get_neighbour_noref(dst)) != NULL)
- n1 = n2;
+
+ /* Why not just use 'neigh' as-is? The problem is that
+ * things such as shaper, eql, and sch_teql can end up
+ * using alternative, different, neigh objects to output
+ * the packet in the output path. So what we need to do
+ * here is re-lookup the top-level neigh in the path so
+ * we can reinject the packet there.
+ */
+ n2 = NULL;
+ if (dst) {
+ n2 = dst_neigh_lookup_skb(dst, skb);
+ if (n2)
+ n1 = n2;
+ }
n1->output(n1, skb);
+ if (n2)
+ neigh_release(n2);
rcu_read_unlock();
write_lock_bh(&neigh->lock);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index fdf9e61d065..72607174ea5 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -417,72 +417,6 @@ static struct attribute_group netstat_group = {
.name = "statistics",
.attrs = netstat_attrs,
};
-
-#ifdef CONFIG_WIRELESS_EXT_SYSFS
-/* helper function that does all the locking etc for wireless stats */
-static ssize_t wireless_show(struct device *d, char *buf,
- ssize_t (*format)(const struct iw_statistics *,
- char *))
-{
- struct net_device *dev = to_net_dev(d);
- const struct iw_statistics *iw;
- ssize_t ret = -EINVAL;
-
- if (!rtnl_trylock())
- return restart_syscall();
- if (dev_isalive(dev)) {
- iw = get_wireless_stats(dev);
- if (iw)
- ret = (*format)(iw, buf);
- }
- rtnl_unlock();
-
- return ret;
-}
-
-/* show function template for wireless fields */
-#define WIRELESS_SHOW(name, field, format_string) \
-static ssize_t format_iw_##name(const struct iw_statistics *iw, char *buf) \
-{ \
- return sprintf(buf, format_string, iw->field); \
-} \
-static ssize_t show_iw_##name(struct device *d, \
- struct device_attribute *attr, char *buf) \
-{ \
- return wireless_show(d, buf, format_iw_##name); \
-} \
-static DEVICE_ATTR(name, S_IRUGO, show_iw_##name, NULL)
-
-WIRELESS_SHOW(status, status, fmt_hex);
-WIRELESS_SHOW(link, qual.qual, fmt_dec);
-WIRELESS_SHOW(level, qual.level, fmt_dec);
-WIRELESS_SHOW(noise, qual.noise, fmt_dec);
-WIRELESS_SHOW(nwid, discard.nwid, fmt_dec);
-WIRELESS_SHOW(crypt, discard.code, fmt_dec);
-WIRELESS_SHOW(fragment, discard.fragment, fmt_dec);
-WIRELESS_SHOW(misc, discard.misc, fmt_dec);
-WIRELESS_SHOW(retries, discard.retries, fmt_dec);
-WIRELESS_SHOW(beacon, miss.beacon, fmt_dec);
-
-static struct attribute *wireless_attrs[] = {
- &dev_attr_status.attr,
- &dev_attr_link.attr,
- &dev_attr_level.attr,
- &dev_attr_noise.attr,
- &dev_attr_nwid.attr,
- &dev_attr_crypt.attr,
- &dev_attr_fragment.attr,
- &dev_attr_retries.attr,
- &dev_attr_misc.attr,
- &dev_attr_beacon.attr,
- NULL
-};
-
-static struct attribute_group wireless_group = {
- .name = "wireless",
- .attrs = wireless_attrs,
-};
-#endif
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_RPS
@@ -1463,14 +1397,6 @@ int netdev_register_kobject(struct net_device *net)
groups++;
*groups++ = &netstat_group;
-#ifdef CONFIG_WIRELESS_EXT_SYSFS
- if (net->ieee80211_ptr)
- *groups++ = &wireless_group;
-#ifdef CONFIG_WIRELESS_EXT
- else if (net->wireless_handlers)
- *groups++ = &wireless_group;
-#endif
-#endif
#endif /* CONFIG_SYSFS */
error = device_add(dev);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index f9f40b932e4..e4ba3e70c17 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -26,6 +26,7 @@
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/if_vlan.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <asm/unaligned.h>
@@ -54,7 +55,7 @@ static atomic_t trapped;
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void arp_reply(struct sk_buff *skb);
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);
@@ -170,7 +171,8 @@ static void poll_napi(struct net_device *dev)
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(dev->npinfo, napi, budget);
+ budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
+ napi, budget);
spin_unlock(&napi->poll_lock);
if (!budget)
@@ -185,13 +187,14 @@ static void service_arp_queue(struct netpoll_info *npi)
struct sk_buff *skb;
while ((skb = skb_dequeue(&npi->arp_tx)))
- arp_reply(skb);
+ netpoll_arp_reply(skb, npi);
}
}
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
+ struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
if (!dev || !netif_running(dev))
return;
@@ -206,17 +209,18 @@ static void netpoll_poll_dev(struct net_device *dev)
poll_napi(dev);
if (dev->flags & IFF_SLAVE) {
- if (dev->npinfo) {
+ if (ni) {
struct net_device *bond_dev = dev->master;
struct sk_buff *skb;
- while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) {
+ struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo);
+ while ((skb = skb_dequeue(&ni->arp_tx))) {
skb->dev = bond_dev;
- skb_queue_tail(&bond_dev->npinfo->arp_tx, skb);
+ skb_queue_tail(&bond_ni->arp_tx, skb);
}
}
}
- service_arp_queue(dev->npinfo);
+ service_arp_queue(ni);
zap_completion_queue();
}
@@ -302,6 +306,7 @@ static int netpoll_owner_active(struct net_device *dev)
return 0;
}
+/* call with IRQ disabled */
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev)
{
@@ -309,8 +314,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
unsigned long tries;
const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
- struct netpoll_info *npinfo = np->dev->npinfo;
+ struct netpoll_info *npinfo;
+
+ WARN_ON_ONCE(!irqs_disabled());
+ npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
__kfree_skb(skb);
return;
@@ -319,16 +327,22 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* don't get messages out of order, and no recursion */
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
struct netdev_queue *txq;
- unsigned long flags;
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
- local_irq_save(flags);
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
if (__netif_tx_trylock(txq)) {
if (!netif_xmit_stopped(txq)) {
+ if (vlan_tx_tag_present(skb) &&
+ !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) {
+ skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+ if (unlikely(!skb))
+ break;
+ skb->vlan_tci = 0;
+ }
+
status = ops->ndo_start_xmit(skb, dev);
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
@@ -347,10 +361,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
WARN_ONCE(!irqs_disabled(),
- "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n",
+ "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
dev->name, ops->ndo_start_xmit);
- local_irq_restore(flags);
}
if (status != NETDEV_TX_OK) {
@@ -423,9 +436,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void arp_reply(struct sk_buff *skb)
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
{
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct arphdr *arp;
unsigned char *arp_ptr;
int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
@@ -543,13 +555,12 @@ static void arp_reply(struct sk_buff *skb)
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
-int __netpoll_rx(struct sk_buff *skb)
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
{
int proto, len, ulen;
int hits = 0;
const struct iphdr *iph;
struct udphdr *uh;
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct netpoll *np, *tmp;
if (list_empty(&npinfo->rx_np))
@@ -565,6 +576,12 @@ int __netpoll_rx(struct sk_buff *skb)
return 1;
}
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ goto out;
+ }
+
proto = ntohs(eth_hdr(skb)->h_proto);
if (proto != ETH_P_IP)
goto out;
@@ -715,14 +732,16 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
{
- struct net_device *ndev = np->dev;
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
unsigned long flags;
int err;
+ np->dev = ndev;
+ strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
+
if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
!ndev->netdev_ops->ndo_poll_controller) {
np_err(np, "%s doesn't support polling, aborting\n",
@@ -732,7 +751,7 @@ int __netpoll_setup(struct netpoll *np)
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+ npinfo = kmalloc(sizeof(*npinfo), gfp);
if (!npinfo) {
err = -ENOMEM;
goto out;
@@ -750,7 +769,7 @@ int __netpoll_setup(struct netpoll *np)
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo);
+ err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
if (err)
goto free_npinfo;
}
@@ -851,13 +870,11 @@ int netpoll_setup(struct netpoll *np)
np_info(np, "local IP %pI4\n", &np->local_ip);
}
- np->dev = ndev;
-
/* fill up the skb queue */
refill_skbs();
rtnl_lock();
- err = __netpoll_setup(np);
+ err = __netpoll_setup(np, ndev, GFP_KERNEL);
rtnl_unlock();
if (err)
@@ -878,6 +895,24 @@ static int __init netpoll_init(void)
}
core_initcall(netpoll_init);
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+ struct netpoll_info *npinfo =
+ container_of(rcu_head, struct netpoll_info, rcu);
+
+ skb_queue_purge(&npinfo->arp_tx);
+ skb_queue_purge(&npinfo->txq);
+
+ /* we can't call cancel_delayed_work_sync here, as we are in softirq */
+ cancel_delayed_work(&npinfo->tx_work);
+
+ /* clean after last, unfinished work */
+ __skb_queue_purge(&npinfo->txq);
+ /* now cancel it again */
+ cancel_delayed_work(&npinfo->tx_work);
+ kfree(npinfo);
+}
+
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
@@ -903,20 +938,24 @@ void __netpoll_cleanup(struct netpoll *np)
ops->ndo_netpoll_cleanup(np->dev);
RCU_INIT_POINTER(np->dev->npinfo, NULL);
+ call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+ }
+}
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
- /* avoid racing with NAPI reading npinfo */
- synchronize_rcu_bh();
+static void rcu_cleanup_netpoll(struct rcu_head *rcu_head)
+{
+ struct netpoll *np = container_of(rcu_head, struct netpoll, rcu);
- skb_queue_purge(&npinfo->arp_tx);
- skb_queue_purge(&npinfo->txq);
- cancel_delayed_work_sync(&npinfo->tx_work);
+ __netpoll_cleanup(np);
+ kfree(np);
+}
- /* clean after last, unfinished work */
- __skb_queue_purge(&npinfo->txq);
- kfree(npinfo);
- }
+void __netpoll_free_rcu(struct netpoll *np)
+{
+ call_rcu_bh(&np->rcu, rcu_cleanup_netpoll);
}
-EXPORT_SYMBOL_GPL(__netpoll_cleanup);
+EXPORT_SYMBOL_GPL(__netpoll_free_rcu);
void netpoll_cleanup(struct netpoll *np)
{
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index b2e9caa1ad1..c75e3f9d060 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -25,6 +25,8 @@
#include <net/sock.h>
#include <net/netprio_cgroup.h>
+#include <linux/fdtable.h>
+
#define PRIOIDX_SZ 128
static unsigned long prioidx_map[PRIOIDX_SZ];
@@ -99,12 +101,10 @@ static int write_update_netdev_table(struct net_device *dev)
u32 max_len;
struct netprio_map *map;
- rtnl_lock();
max_len = atomic_read(&max_prioidx) + 1;
map = rtnl_dereference(dev->priomap);
if (!map || map->priomap_len < max_len)
ret = extend_netdev_table(dev, max_len);
- rtnl_unlock();
return ret;
}
@@ -232,7 +232,7 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
/*
*Separate the devname from the associated priority
- *and advance the priostr poitner to the priority value
+ *and advance the priostr pointer to the priority value
*/
*priostr = '\0';
priostr++;
@@ -254,17 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
if (!dev)
goto out_free_devname;
+ rtnl_lock();
ret = write_update_netdev_table(dev);
if (ret < 0)
goto out_put_dev;
- rcu_read_lock();
- map = rcu_dereference(dev->priomap);
+ map = rtnl_dereference(dev->priomap);
if (map)
map->priomap[prioidx] = priority;
- rcu_read_unlock();
out_put_dev:
+ rtnl_unlock();
dev_put(dev);
out_free_devname:
@@ -272,6 +272,42 @@ out_free_devname:
return ret;
}
+void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+ struct task_struct *p;
+
+ cgroup_taskset_for_each(p, cgrp, tset) {
+ unsigned int fd;
+ struct fdtable *fdt;
+ struct files_struct *files;
+
+ task_lock(p);
+ files = p->files;
+ if (!files) {
+ task_unlock(p);
+ continue;
+ }
+
+ spin_lock(&files->file_lock);
+ fdt = files_fdtable(files);
+ for (fd = 0; fd < fdt->max_fds; fd++) {
+ struct file *file;
+ struct socket *sock;
+ int err;
+
+ file = fcheck_files(files, fd);
+ if (!file)
+ continue;
+
+ sock = sock_from_file(file, &err);
+ if (sock)
+ sock_update_netprioidx(sock->sk, p);
+ }
+ spin_unlock(&files->file_lock);
+ task_unlock(p);
+ }
+}
+
static struct cftype ss_files[] = {
{
.name = "prioidx",
@@ -289,6 +325,7 @@ struct cgroup_subsys net_prio_subsys = {
.name = "net_prio",
.create = cgrp_create,
.destroy = cgrp_destroy,
+ .attach = net_prio_attach,
#ifdef CONFIG_NETPRIO_CGROUP
.subsys_id = net_prio_subsys_id,
#endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 21318d15bbc..2c5a0a06c4c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -541,19 +541,6 @@ static const int rta_max[RTM_NR_FAMILIES] =
[RTM_FAM(RTM_NEWACTION)] = TCAA_MAX,
};
-void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
-{
- struct rtattr *rta;
- int size = RTA_LENGTH(attrlen);
-
- rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size));
- rta->rta_type = attrtype;
- rta->rta_len = size;
- memcpy(RTA_DATA(rta), data, attrlen);
- memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size);
-}
-EXPORT_SYMBOL(__rta_fill);
-
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
struct sock *rtnl = net->rtnl;
@@ -628,7 +615,7 @@ nla_put_failure:
EXPORT_SYMBOL(rtnetlink_put_metrics);
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
- u32 ts, u32 tsage, long expires, u32 error)
+ long expires, u32 error)
{
struct rta_cacheinfo ci = {
.rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse),
@@ -636,13 +623,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
.rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
- .rta_ts = ts,
- .rta_tsage = tsage,
};
- if (expires)
- ci.rta_expires = jiffies_to_clock_t(expires);
+ if (expires) {
+ unsigned long clock;
+ clock = jiffies_to_clock_t(abs(expires));
+ clock = min_t(unsigned long, clock, INT_MAX);
+ ci.rta_expires = (expires > 0) ? clock : -clock;
+ }
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
@@ -674,6 +663,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
}
}
+static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
+{
+ return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) |
+ (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI));
+}
+
static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
const struct ifinfomsg *ifm)
{
@@ -682,7 +677,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
/* bugwards compatibility: ifi_change == 0 is treated as ~0 */
if (ifm->ifi_change)
flags = (flags & ifm->ifi_change) |
- (dev->flags & ~ifm->ifi_change);
+ (rtnl_dev_get_flags(dev) & ~ifm->ifi_change);
return flags;
}
@@ -786,6 +781,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(4) /* IFLA_PROMISCUITY */
+ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */
+ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(ext_filter_mask
@@ -904,6 +901,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
nla_put_u32(skb, IFLA_GROUP, dev->group) ||
nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) ||
+ nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) ||
+#ifdef CONFIG_RPS
+ nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
+#endif
(dev->ifindex != dev->iflink &&
nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
(dev->master &&
@@ -1121,6 +1122,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_AF_SPEC] = { .type = NLA_NESTED },
[IFLA_EXT_MASK] = { .type = NLA_U32 },
[IFLA_PROMISCUITY] = { .type = NLA_U32 },
+ [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
+ [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
};
EXPORT_SYMBOL(ifla_policy);
@@ -1378,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
goto errout;
send_addr_notify = 1;
modified = 1;
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
if (tb[IFLA_MTU]) {
@@ -1639,17 +1643,22 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
{
int err;
struct net_device *dev;
- unsigned int num_queues = 1;
+ unsigned int num_tx_queues = 1;
+ unsigned int num_rx_queues = 1;
- if (ops->get_tx_queues) {
- err = ops->get_tx_queues(src_net, tb);
- if (err < 0)
- goto err;
- num_queues = err;
- }
+ if (tb[IFLA_NUM_TX_QUEUES])
+ num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
+ else if (ops->get_num_tx_queues)
+ num_tx_queues = ops->get_num_tx_queues();
+
+ if (tb[IFLA_NUM_RX_QUEUES])
+ num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]);
+ else if (ops->get_num_rx_queues)
+ num_rx_queues = ops->get_num_rx_queues();
err = -ENOMEM;
- dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues);
+ dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup,
+ num_tx_queues, num_rx_queues);
if (!dev)
goto err;
@@ -2189,7 +2198,7 @@ skip:
}
/**
- * ndo_dflt_fdb_dump: default netdevice operation to dump an FDB table.
+ * ndo_dflt_fdb_dump - default netdevice operation to dump an FDB table.
* @nlh: netlink message header
* @dev: netdevice
*
@@ -2366,8 +2375,13 @@ static struct notifier_block rtnetlink_dev_notifier = {
static int __net_init rtnetlink_net_init(struct net *net)
{
struct sock *sk;
- sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX,
- rtnetlink_rcv, &rtnl_mutex, THIS_MODULE);
+ struct netlink_kernel_cfg cfg = {
+ .groups = RTNLGRP_MAX,
+ .input = rtnetlink_rcv,
+ .cb_mutex = &rtnl_mutex,
+ };
+
+ sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg);
if (!sk)
return -ENOMEM;
net->rtnl = sk;
diff --git a/net/core/scm.c b/net/core/scm.c
index 611c5efd4cb..040cebeed45 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -109,25 +109,9 @@ void __scm_destroy(struct scm_cookie *scm)
if (fpl) {
scm->fp = NULL;
- if (current->scm_work_list) {
- list_add_tail(&fpl->list, current->scm_work_list);
- } else {
- LIST_HEAD(work_list);
-
- current->scm_work_list = &work_list;
-
- list_add(&fpl->list, &work_list);
- while (!list_empty(&work_list)) {
- fpl = list_first_entry(&work_list, struct scm_fp_list, list);
-
- list_del(&fpl->list);
- for (i=fpl->count-1; i>=0; i--)
- fput(fpl->fp[i]);
- kfree(fpl);
- }
-
- current->scm_work_list = NULL;
- }
+ for (i=fpl->count-1; i>=0; i--)
+ fput(fpl->fp[i]);
+ kfree(fpl);
}
}
EXPORT_SYMBOL(__scm_destroy);
@@ -281,6 +265,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
i++, cmfptr++)
{
+ struct socket *sock;
int new_fd;
err = security_file_receive(fp[i]);
if (err)
@@ -297,6 +282,9 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
}
/* Bump the usage count and install the file. */
get_file(fp[i]);
+ sock = sock_from_file(fp[i], &err);
+ if (sock)
+ sock_update_netprioidx(sock->sk, current);
fd_install(new_fd, fp[i]);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d124306b81f..fe00d120816 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
BUG();
}
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+ bool *pfmemalloc)
+{
+ void *obj;
+ bool ret_pfmemalloc = false;
+
+ /*
+ * Try a regular allocation, when that fails and we're not entitled
+ * to the reserves, fail.
+ */
+ obj = kmalloc_node_track_caller(size,
+ flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+ node);
+ if (obj || !(gfp_pfmemalloc_allowed(flags)))
+ goto out;
+
+ /* Try again but now we are using pfmemalloc reserves */
+ ret_pfmemalloc = true;
+ obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+ if (pfmemalloc)
+ *pfmemalloc = ret_pfmemalloc;
+
+ return obj;
+}
+
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
@@ -155,26 +192,33 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
- * @fclone: allocate from fclone cache instead of head cache
- * and allocate a cloned (child) skb
+ * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ * instead of head cache and allocate a cloned (child) skb.
+ * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ * allocations in case the data is required for writeback
* @node: numa node to allocate memory on
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
- * tail room of size bytes. The object has a reference count of one.
- * The return is the buffer. On a failure the return is %NULL.
+ * tail room of at least size bytes. The object has a reference count
+ * of one. The return is the buffer. On a failure the return is %NULL.
*
* Buffers may only be allocated from interrupts using a @gfp_mask of
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
- int fclone, int node)
+ int flags, int node)
{
struct kmem_cache *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
+ bool pfmemalloc;
- cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+ cache = (flags & SKB_ALLOC_FCLONE)
+ ? skbuff_fclone_cache : skbuff_head_cache;
+
+ if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+ gfp_mask |= __GFP_MEMALLOC;
/* Get the HEAD */
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
@@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
*/
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- data = kmalloc_node_track_caller(size, gfp_mask, node);
+ data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
if (!data)
goto nodata;
/* kmalloc(size) might give us more room than requested.
@@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
memset(skb, 0, offsetof(struct sk_buff, tail));
/* Account for allocated memory : skb + skb->head */
skb->truesize = SKB_TRUESIZE(size);
+ skb->pfmemalloc = pfmemalloc;
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(&shinfo->dataref, 1);
kmemcheck_annotate_variable(shinfo->destructor_arg);
- if (fclone) {
+ if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
@@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
+ child->pfmemalloc = pfmemalloc;
}
out:
return skb;
@@ -296,17 +342,13 @@ EXPORT_SYMBOL(build_skb);
struct netdev_alloc_cache {
struct page *page;
unsigned int offset;
+ unsigned int pagecnt_bias;
};
static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
+
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
struct netdev_alloc_cache *nc;
void *data = NULL;
@@ -316,21 +358,42 @@ void *netdev_alloc_frag(unsigned int fragsz)
nc = &__get_cpu_var(netdev_alloc_cache);
if (unlikely(!nc->page)) {
refill:
- nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ nc->page = alloc_page(gfp_mask);
+ if (unlikely(!nc->page))
+ goto end;
+recycle:
+ atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS);
+ nc->pagecnt_bias = NETDEV_PAGECNT_BIAS;
nc->offset = 0;
}
- if (likely(nc->page)) {
- if (nc->offset + fragsz > PAGE_SIZE) {
- put_page(nc->page);
- goto refill;
- }
- data = page_address(nc->page) + nc->offset;
- nc->offset += fragsz;
- get_page(nc->page);
+
+ if (nc->offset + fragsz > PAGE_SIZE) {
+ /* avoid unnecessary locked operations if possible */
+ if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) ||
+ atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count))
+ goto recycle;
+ goto refill;
}
+
+ data = page_address(nc->page) + nc->offset;
+ nc->offset += fragsz;
+ nc->pagecnt_bias--;
+end:
local_irq_restore(flags);
return data;
}
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+ return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
EXPORT_SYMBOL(netdev_alloc_frag);
/**
@@ -354,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
- void *data = netdev_alloc_frag(fragsz);
+ void *data;
+
+ if (sk_memalloc_socks())
+ gfp_mask |= __GFP_MEMALLOC;
+
+ data = __netdev_alloc_frag(fragsz, gfp_mask);
if (likely(data)) {
skb = build_skb(data, fragsz);
@@ -362,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
put_page(virt_to_head_page(data));
}
} else {
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+ SKB_ALLOC_RX, NUMA_NO_NODE);
}
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
@@ -644,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#if IS_ENABLED(CONFIG_IP_VS)
new->ipvs_property = old->ipvs_property;
#endif
+ new->pfmemalloc = old->pfmemalloc;
new->protocol = old->protocol;
new->mark = old->mark;
new->skb_iif = old->skb_iif;
@@ -713,7 +783,8 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
-/* skb_copy_ubufs - copy userspace skb frags buffers to kernel
+/**
+ * skb_copy_ubufs - copy userspace skb frags buffers to kernel
* @skb: the skb to modify
* @gfp_mask: allocation priority
*
@@ -738,7 +809,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
u8 *vaddr;
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
- page = alloc_page(GFP_ATOMIC);
+ page = alloc_page(gfp_mask);
if (!page) {
while (head) {
struct page *next = (struct page *)head->private;
@@ -756,22 +827,22 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
}
/* skb frags release userspace buffers */
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ for (i = 0; i < num_frags; i++)
skb_frag_unref(skb, i);
uarg->callback(uarg);
/* skb frags point to kernel buffers */
- for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) {
- __skb_fill_page_desc(skb, i-1, head, 0,
- skb_shinfo(skb)->frags[i - 1].size);
+ for (i = num_frags - 1; i >= 0; i--) {
+ __skb_fill_page_desc(skb, i, head, 0,
+ skb_shinfo(skb)->frags[i].size);
head = (struct page *)head->private;
}
skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
return 0;
}
-
+EXPORT_SYMBOL_GPL(skb_copy_ubufs);
/**
* skb_clone - duplicate an sk_buff
@@ -791,10 +862,8 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff *n;
- if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
- if (skb_copy_ubufs(skb, gfp_mask))
- return NULL;
- }
+ if (skb_orphan_frags(skb, gfp_mask))
+ return NULL;
n = skb + 1;
if (skb->fclone == SKB_FCLONE_ORIG &&
@@ -803,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
n->fclone = SKB_FCLONE_CLONE;
atomic_inc(fclone_ref);
} else {
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+
n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
if (!n)
return NULL;
@@ -839,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+ if (skb_pfmemalloc(skb))
+ return SKB_ALLOC_RX;
+ return 0;
+}
+
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
@@ -860,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
unsigned int size = skb_end_offset(skb) + skb->data_len;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
@@ -895,7 +975,8 @@ EXPORT_SYMBOL(skb_copy);
struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
{
unsigned int size = skb_headlen(skb) + headroom;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
goto out;
@@ -914,12 +995,10 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
if (skb_shinfo(skb)->nr_frags) {
int i;
- if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
- if (skb_copy_ubufs(skb, gfp_mask)) {
- kfree_skb(n);
- n = NULL;
- goto out;
- }
+ if (skb_orphan_frags(skb, gfp_mask)) {
+ kfree_skb(n);
+ n = NULL;
+ goto out;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
@@ -970,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
size = SKB_DATA_ALIGN(size);
- data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
- gfp_mask);
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+ data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+ gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
goto nodata;
size = SKB_WITH_OVERHEAD(ksize(data));
@@ -992,10 +1073,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
*/
if (skb_cloned(skb)) {
/* copy this zero copy skb frags */
- if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
- if (skb_copy_ubufs(skb, gfp_mask))
- goto nofrags;
- }
+ if (skb_orphan_frags(skb, gfp_mask))
+ goto nofrags;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i);
@@ -1085,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
/*
* Allocate the copy buffer
*/
- struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
- gfp_mask);
+ struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
int off;
@@ -2614,7 +2694,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
EXPORT_SYMBOL(skb_find_text);
/**
- * skb_append_datato_frags: - append the user data to a skb
+ * skb_append_datato_frags - append the user data to a skb
* @sk: sock structure
* @skb: skb structure to be appened with user data.
* @getfrag: call back function to be used for getting the user data
@@ -2768,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
- nskb = alloc_skb(hsize + doffset + headroom,
- GFP_ATOMIC);
+ nskb = __alloc_skb(hsize + doffset + headroom,
+ GFP_ATOMIC, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
if (unlikely(!nskb))
goto err;
diff --git a/net/core/sock.c b/net/core/sock.c
index 9e5b71fda6e..8f67ced8d6a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,7 +142,7 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
@@ -271,6 +271,61 @@ __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);
+struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(memalloc_socks);
+
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+ sock_set_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation |= __GFP_MEMALLOC;
+ static_key_slow_inc(&memalloc_socks);
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+ sock_reset_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation &= ~__GFP_MEMALLOC;
+ static_key_slow_dec(&memalloc_socks);
+
+ /*
+ * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+ * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+ * it has rmem allocations there is a risk that the user of the
+ * socket cannot make forward progress due to exceeding the rmem
+ * limits. By rights, sk_clear_memalloc() should only be called
+ * on sockets being torn down but warn and reset the accounting if
+ * that assumption breaks.
+ */
+ if (WARN_ON(sk->sk_forward_alloc))
+ sk_mem_reclaim(sk);
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+ unsigned long pflags = current->flags;
+
+ /* these should have been dropped before queueing */
+ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+ current->flags |= PF_MEMALLOC;
+ ret = sk->sk_backlog_rcv(sk, skb);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+ return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
#if defined(CONFIG_CGROUPS)
#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
@@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize)) {
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
}
@@ -1180,12 +1235,12 @@ void sock_update_classid(struct sock *sk)
}
EXPORT_SYMBOL(sock_update_classid);
-void sock_update_netprioidx(struct sock *sk)
+void sock_update_netprioidx(struct sock *sk, struct task_struct *task)
{
if (in_interrupt())
return;
- sk->sk_cgrp_prioidx = task_netprioidx(current);
+ sk->sk_cgrp_prioidx = task_netprioidx(task);
}
EXPORT_SYMBOL_GPL(sock_update_netprioidx);
#endif
@@ -1215,7 +1270,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
atomic_set(&sk->sk_wmem_alloc, 1);
sock_update_classid(sk);
- sock_update_netprioidx(sk);
+ sock_update_netprioidx(sk, current);
}
return sk;
@@ -1403,6 +1458,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
} else {
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
sk->sk_gso_max_size = dst->dev->gso_max_size;
+ sk->sk_gso_max_segs = dst->dev->gso_max_segs;
}
}
}
@@ -1465,6 +1521,11 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+void sock_edemux(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
int sock_i_uid(struct sock *sk)
{
@@ -2154,6 +2215,10 @@ void release_sock(struct sock *sk)
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_backlog.tail)
__release_sock(sk);
+
+ if (sk->sk_prot->release_cb)
+ sk->sk_prot->release_cb(sk);
+
sk->sk_lock.owned = 0;
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 5fd146720f3..9d8755e4a7a 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -4,7 +4,6 @@
#include <net/netlink.h>
#include <net/net_namespace.h>
#include <linux/module.h>
-#include <linux/rtnetlink.h>
#include <net/sock.h>
#include <linux/inet_diag.h>
@@ -35,9 +34,7 @@ EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
{
- __u32 *mem;
-
- mem = RTA_DATA(__RTA_PUT(skb, attrtype, SK_MEMINFO_VARS * sizeof(__u32)));
+ u32 mem[SK_MEMINFO_VARS];
mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
@@ -46,11 +43,9 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+ mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
- return 0;
-
-rtattr_failure:
- return -EMSGSIZE;
+ return nla_put(skb, attrtype, sizeof(mem), &mem);
}
EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
@@ -120,7 +115,7 @@ static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h)
static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
- struct sock_diag_req *req = NLMSG_DATA(nlh);
+ struct sock_diag_req *req = nlmsg_data(nlh);
const struct sock_diag_handler *hndl;
if (nlmsg_len(nlh) < sizeof(*req))
@@ -171,19 +166,36 @@ static void sock_diag_rcv(struct sk_buff *skb)
mutex_unlock(&sock_diag_mutex);
}
-struct sock *sock_diag_nlsk;
-EXPORT_SYMBOL_GPL(sock_diag_nlsk);
+static int __net_init diag_net_init(struct net *net)
+{
+ struct netlink_kernel_cfg cfg = {
+ .input = sock_diag_rcv,
+ };
+
+ net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG,
+ THIS_MODULE, &cfg);
+ return net->diag_nlsk == NULL ? -ENOMEM : 0;
+}
+
+static void __net_exit diag_net_exit(struct net *net)
+{
+ netlink_kernel_release(net->diag_nlsk);
+ net->diag_nlsk = NULL;
+}
+
+static struct pernet_operations diag_net_ops = {
+ .init = diag_net_init,
+ .exit = diag_net_exit,
+};
static int __init sock_diag_init(void)
{
- sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0,
- sock_diag_rcv, NULL, THIS_MODULE);
- return sock_diag_nlsk == NULL ? -ENOMEM : 0;
+ return register_pernet_subsys(&diag_net_ops);
}
static void __exit sock_diag_exit(void)
{
- netlink_kernel_release(sock_diag_nlsk);
+ unregister_pernet_subsys(&diag_net_ops);
}
module_init(sock_diag_init);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-02-01 06:46:36 +0000