summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c4
-rw-r--r--net/core/dev.c238
-rw-r--r--net/core/drop_monitor.c4
-rw-r--r--net/core/dst.c2
-rw-r--r--net/core/ethtool.c24
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/gen_estimator.c12
-rw-r--r--net/core/gen_stats.c22
-rw-r--r--net/core/link_watch.c3
-rw-r--r--net/core/neighbour.c34
-rw-r--r--net/core/net-procfs.c16
-rw-r--r--net/core/netpoll.c16
-rw-r--r--net/core/netprio_cgroup.c2
-rw-r--r--net/core/pktgen.c81
-rw-r--r--net/core/rtnetlink.c32
-rw-r--r--net/core/skbuff.c68
-rw-r--r--net/core/sock.c26
-rw-r--r--net/core/sysctl_net_core.c139
18 files changed, 554 insertions, 173 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b71423db7785..9cbaba98ce4c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -56,6 +56,7 @@
#include <net/sock.h>
#include <net/tcp_states.h>
#include <trace/events/skb.h>
+#include <net/ll_poll.h>
/*
* Is a socket 'connection oriented' ?
@@ -207,6 +208,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
}
spin_unlock_irqrestore(&queue->lock, cpu_flags);
+ if (sk_valid_ll(sk) && sk_poll_ll(sk, flags & MSG_DONTWAIT))
+ continue;
+
/* User doesn't want to wait */
error = -EAGAIN;
if (!timeo)
diff --git a/net/core/dev.c b/net/core/dev.c
index faebb398fb46..560dafd83adf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -129,6 +129,8 @@
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
+#include <linux/hashtable.h>
+#include <linux/vmalloc.h>
#include "net-sysfs.h"
@@ -166,6 +168,12 @@ static struct list_head offload_base __read_mostly;
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+/* protects napi_hash addition/deletion and napi_gen_id */
+static DEFINE_SPINLOCK(napi_hash_lock);
+
+static unsigned int napi_gen_id;
+static DEFINE_HASHTABLE(napi_hash, 8);
+
seqcount_t devnet_rename_seq;
static inline void dev_base_seq_inc(struct net *net)
@@ -1232,9 +1240,7 @@ static int __dev_open(struct net_device *dev)
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
@@ -1343,9 +1349,7 @@ static int __dev_close(struct net_device *dev)
LIST_HEAD(single);
/* Temporarily disable netpoll until the interface is down */
- retval = netpoll_rx_disable(dev);
- if (retval)
- return retval;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
@@ -1387,14 +1391,11 @@ static int dev_close_many(struct list_head *head)
*/
int dev_close(struct net_device *dev)
{
- int ret = 0;
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
/* Block netpoll rx while the interface is going down */
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
@@ -1402,7 +1403,7 @@ int dev_close(struct net_device *dev)
netpoll_rx_enable(dev);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL(dev_close);
@@ -1432,6 +1433,14 @@ void dev_disable_lro(struct net_device *dev)
}
EXPORT_SYMBOL(dev_disable_lro);
+static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
+ struct net_device *dev)
+{
+ struct netdev_notifier_info info;
+
+ netdev_notifier_info_init(&info, dev);
+ return nb->notifier_call(nb, val, &info);
+}
static int dev_boot_phase = 1;
@@ -1464,7 +1473,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
goto unlock;
for_each_net(net) {
for_each_netdev(net, dev) {
- err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
err = notifier_to_errno(err);
if (err)
goto rollback;
@@ -1472,7 +1481,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
if (!(dev->flags & IFF_UP))
continue;
- nb->notifier_call(nb, NETDEV_UP, dev);
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
}
}
@@ -1488,10 +1497,11 @@ rollback:
goto outroll;
if (dev->flags & IFF_UP) {
- nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
- nb->notifier_call(nb, NETDEV_DOWN, dev);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
@@ -1529,10 +1539,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev->flags & IFF_UP) {
- nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
- nb->notifier_call(nb, NETDEV_DOWN, dev);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
unlock:
@@ -1542,6 +1553,25 @@ unlock:
EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
+ * call_netdevice_notifiers_info - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @dev: net_device pointer passed unmodified to notifier function
+ * @info: notifier information data
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for raw_notifier_call_chain().
+ */
+
+int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
+ struct netdev_notifier_info *info)
+{
+ ASSERT_RTNL();
+ netdev_notifier_info_init(info, dev);
+ return raw_notifier_call_chain(&netdev_chain, val, info);
+}
+EXPORT_SYMBOL(call_netdevice_notifiers_info);
+
+/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @dev: net_device pointer passed unmodified to notifier function
@@ -1552,8 +1582,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- ASSERT_RTNL();
- return raw_notifier_call_chain(&netdev_chain, val, dev);
+ struct netdev_notifier_info info;
+
+ return call_netdevice_notifiers_info(val, dev, &info);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
@@ -1655,23 +1686,19 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
}
}
- skb_orphan(skb);
-
if (unlikely(!is_skb_forwardable(dev, skb))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
- skb->skb_iif = 0;
- skb->dev = dev;
- skb_dst_drop(skb);
- skb->tstamp.tv64 = 0;
- skb->pkt_type = PACKET_HOST;
+ skb_scrub_packet(skb);
skb->protocol = eth_type_trans(skb, dev);
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
- nf_reset_trace(skb);
+
+ /* eth_type_trans() can set pkt_type.
+ * clear pkt_type _after_ calling eth_type_trans()
+ */
+ skb->pkt_type = PACKET_HOST;
+
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1736,7 +1763,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb2);
if (skb_network_header(skb2) < skb2->data ||
- skb2->network_header > skb2->tail) {
+ skb_network_header(skb2) > skb_tail_pointer(skb2)) {
net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
ntohs(skb2->protocol),
dev->name);
@@ -3099,6 +3126,46 @@ static int rps_ipi_queued(struct softnet_data *sd)
return 0;
}
+#ifdef CONFIG_NET_FLOW_LIMIT
+int netdev_flow_limit_table_len __read_mostly = (1 << 12);
+#endif
+
+static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
+{
+#ifdef CONFIG_NET_FLOW_LIMIT
+ struct sd_flow_limit *fl;
+ struct softnet_data *sd;
+ unsigned int old_flow, new_flow;
+
+ if (qlen < (netdev_max_backlog >> 1))
+ return false;
+
+ sd = &__get_cpu_var(softnet_data);
+
+ rcu_read_lock();
+ fl = rcu_dereference(sd->flow_limit);
+ if (fl) {
+ new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ old_flow = fl->history[fl->history_head];
+ fl->history[fl->history_head] = new_flow;
+
+ fl->history_head++;
+ fl->history_head &= FLOW_LIMIT_HISTORY - 1;
+
+ if (likely(fl->buckets[old_flow]))
+ fl->buckets[old_flow]--;
+
+ if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
+ fl->count++;
+ rcu_read_unlock();
+ return true;
+ }
+ }
+ rcu_read_unlock();
+#endif
+ return false;
+}
+
/*
* enqueue_to_backlog is called to queue an skb to a per CPU backlog
* queue (may be a remote CPU queue).
@@ -3108,13 +3175,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
{
struct softnet_data *sd;
unsigned long flags;
+ unsigned int qlen;
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
rps_lock(sd);
- if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -3862,7 +3931,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
- if (skb->mac_header == skb->tail &&
+ if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
pinfo->nr_frags &&
!PageHighMem(skb_frag_page(frag0))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
@@ -4106,6 +4175,58 @@ void napi_complete(struct napi_struct *n)
}
EXPORT_SYMBOL(napi_complete);
+/* must be called under rcu_read_lock(), as we dont take a reference */
+struct napi_struct *napi_by_id(unsigned int napi_id)
+{
+ unsigned int hash = napi_id % HASH_SIZE(napi_hash);
+ struct napi_struct *napi;
+
+ hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node)
+ if (napi->napi_id == napi_id)
+ return napi;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(napi_by_id);
+
+void napi_hash_add(struct napi_struct *napi)
+{
+ if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+
+ spin_lock(&napi_hash_lock);
+
+ /* 0 is not a valid id, we also skip an id that is taken
+ * we expect both events to be extremely rare
+ */
+ napi->napi_id = 0;
+ while (!napi->napi_id) {
+ napi->napi_id = ++napi_gen_id;
+ if (napi_by_id(napi->napi_id))
+ napi->napi_id = 0;
+ }
+
+ hlist_add_head_rcu(&napi->napi_hash_node,
+ &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+
+ spin_unlock(&napi_hash_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(napi_hash_add);
+
+/* Warning : caller is responsible to make sure rcu grace period
+ * is respected before freeing memory containing @napi
+ */
+void napi_hash_del(struct napi_struct *napi)
+{
+ spin_lock(&napi_hash_lock);
+
+ if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
+ hlist_del_rcu(&napi->napi_hash_node);
+
+ spin_unlock(&napi_hash_lock);
+}
+EXPORT_SYMBOL_GPL(napi_hash_del);
+
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
@@ -4404,7 +4525,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
else
list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
dev_hold(upper_dev);
-
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
return 0;
}
@@ -4464,6 +4585,7 @@ void netdev_upper_dev_unlink(struct net_device *dev,
list_del_rcu(&upper->list);
dev_put(upper_dev);
kfree_rcu(upper, rcu);
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -4734,8 +4856,13 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
}
if (dev->flags & IFF_UP &&
- (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE)))
- call_netdevice_notifiers(NETDEV_CHANGE, dev);
+ (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
+ struct netdev_notifier_change_info change_info;
+
+ change_info.flags_changed = changes;
+ call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+ &change_info.info);
+ }
}
/**
@@ -5158,17 +5285,28 @@ static void netdev_init_one_queue(struct net_device *dev,
#endif
}
+static void netif_free_tx_queues(struct net_device *dev)
+{
+ if (is_vmalloc_addr(dev->_tx))
+ vfree(dev->_tx);
+ else
+ kfree(dev->_tx);
+}
+
static int netif_alloc_netdev_queues(struct net_device *dev)
{
unsigned int count = dev->num_tx_queues;
struct netdev_queue *tx;
+ size_t sz = count * sizeof(*tx);
- BUG_ON(count < 1);
-
- tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
- if (!tx)
- return -ENOMEM;
+ BUG_ON(count < 1 || count > 0xffff);
+ tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!tx) {
+ tx = vzalloc(sz);
+ if (!tx)
+ return -ENOMEM;
+ }
dev->_tx = tx;
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
@@ -5269,6 +5407,10 @@ int register_netdevice(struct net_device *dev)
*/
dev->hw_enc_features |= NETIF_F_SG;
+ /* Make NETIF_F_SG inheritable to MPLS.
+ */
+ dev->mpls_features |= NETIF_F_SG;
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
@@ -5712,7 +5854,7 @@ free_all:
free_pcpu:
free_percpu(dev->pcpu_refcnt);
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
@@ -5737,7 +5879,7 @@ void free_netdev(struct net_device *dev)
release_net(dev_net(dev));
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
@@ -6048,7 +6190,7 @@ netdev_features_t netdev_increment_features(netdev_features_t all,
}
EXPORT_SYMBOL(netdev_increment_features);
-static struct hlist_head *netdev_create_hash(void)
+static struct hlist_head * __net_init netdev_create_hash(void)
{
int i;
struct hlist_head *hash;
@@ -6304,6 +6446,10 @@ static int __init net_dev_init(void)
sd->backlog.weight = weight_p;
sd->backlog.gro_list = NULL;
sd->backlog.gro_count = 0;
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+ sd->flow_limit = NULL;
+#endif
}
dev_boot_phase = 0;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index d23b6682f4e9..5e78d44333b9 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -295,9 +295,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb,
}
static int dropmon_net_event(struct notifier_block *ev_block,
- unsigned long event, void *ptr)
+ unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *tmp;
diff --git a/net/core/dst.c b/net/core/dst.c
index df9cc810ec8e..ca4231ec7347 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -372,7 +372,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static int dst_dev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dst_entry *dst, *last = NULL;
switch (event) {
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index ce91766eeca9..ab5fa6336c84 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
+ [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
@@ -1319,10 +1320,19 @@ static int ethtool_get_dump_data(struct net_device *dev,
if (ret)
return ret;
- len = (tmp.len > dump.len) ? dump.len : tmp.len;
+ len = min(tmp.len, dump.len);
if (!len)
return -EFAULT;
+ /* Don't ever let the driver think there's more space available
+ * than it requested with .get_dump_flag().
+ */
+ dump.len = len;
+
+ /* Always allocate enough space to hold the whole thing so that the
+ * driver does not need to check the length and bother with partial
+ * dumping.
+ */
data = vzalloc(tmp.len);
if (!data)
return -ENOMEM;
@@ -1330,6 +1340,16 @@ static int ethtool_get_dump_data(struct net_device *dev,
if (ret)
goto out;
+ /* There are two sane possibilities:
+ * 1. The driver's .get_dump_data() does not touch dump.len.
+ * 2. Or it may set dump.len to how much it really writes, which
+ * should be tmp.len (or len if it can do a partial dump).
+ * In any case respond to userspace with the actual length of data
+ * it's receiving.
+ */
+ WARN_ON(dump.len != len && dump.len != tmp.len);
+ dump.len = len;
+
if (copy_to_user(useraddr, &dump, sizeof(dump))) {
ret = -EFAULT;
goto out;
@@ -1413,7 +1433,7 @@ static int ethtool_get_module_eeprom(struct net_device *dev,
modinfo.eeprom_len);
}
-/* The main entry point in this file. Called from net/core/dev.c */
+/* The main entry point in this file. Called from net/core/dev_ioctl.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
{
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d5a9f8ead0d8..21735440c44a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -705,9 +705,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
static int fib_rules_event(struct notifier_block *this, unsigned long event,
- void *ptr)
+ void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct fib_rules_ops *ops;
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index d9d198aa9fed..6b5b6e7013ca 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -82,7 +82,7 @@ struct gen_estimator
{
struct list_head list;
struct gnet_stats_basic_packed *bstats;
- struct gnet_stats_rate_est *rate_est;
+ struct gnet_stats_rate_est64 *rate_est;
spinlock_t *stats_lock;
int ewma_log;
u64 last_bytes;
@@ -167,7 +167,7 @@ static void gen_add_node(struct gen_estimator *est)
static
struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats,
- const struct gnet_stats_rate_est *rate_est)
+ const struct gnet_stats_rate_est64 *rate_est)
{
struct rb_node *p = est_root.rb_node;
@@ -203,7 +203,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
*
*/
int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est,
+ struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock,
struct nlattr *opt)
{
@@ -258,7 +258,7 @@ EXPORT_SYMBOL(gen_new_estimator);
* Note : Caller should respect an RCU grace period before freeing stats_lock
*/
void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est)
+ struct gnet_stats_rate_est64 *rate_est)
{
struct gen_estimator *e;
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(gen_kill_estimator);
* Returns 0 on success or a negative error code.
*/
int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
- struct gnet_stats_rate_est *rate_est,
+ struct gnet_stats_rate_est64 *rate_est,
spinlock_t *stats_lock, struct nlattr *opt)
{
gen_kill_estimator(bstats, rate_est);
@@ -306,7 +306,7 @@ EXPORT_SYMBOL(gen_replace_estimator);
* Returns true if estimator is active, and false if not.
*/
bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
- const struct gnet_stats_rate_est *rate_est)
+ const struct gnet_stats_rate_est64 *rate_est)
{
bool res;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index ddedf211e588..9d3d9e78397b 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -143,18 +143,30 @@ EXPORT_SYMBOL(gnet_stats_copy_basic);
int
gnet_stats_copy_rate_est(struct gnet_dump *d,
const struct gnet_stats_basic_packed *b,
- struct gnet_stats_rate_est *r)
+ struct gnet_stats_rate_est64 *r)
{
+ struct gnet_stats_rate_est est;
+ int res;
+
if (b && !gen_estimator_active(b, r))
return 0;
+ est.bps = min_t(u64, UINT_MAX, r->bps);
+ /* we have some time before reaching 2^32 packets per second */
+ est.pps = r->pps;
+
if (d->compat_tc_stats) {
- d->tc_stats.bps = r->bps;
- d->tc_stats.pps = r->pps;
+ d->tc_stats.bps = est.bps;
+ d->tc_stats.pps = est.pps;
}
- if (d->tail)
- return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r));
+ if (d->tail) {
+ res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est));
+ if (res < 0 || est.bps == r->bps)
+ return res;
+ /* emit 64bit stats only if needed */
+ return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r));
+ }
return 0;
}
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 8f82a5cc3851..9c3a839322ba 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -92,6 +92,9 @@ static bool linkwatch_urgent_event(struct net_device *dev)
if (dev->ifindex != dev->iflink)
return true;
+ if (dev->priv_flags & IFF_TEAM_PORT)
+ return true;
+
return netif_carrier_ok(dev) && qdisc_tx_changing(dev);
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5c56b217b999..b7de821f98df 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -231,7 +231,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
we must kill timers etc. and move
it to safe state.
*/
- skb_queue_purge(&n->arp_queue);
+ __skb_queue_purge(&n->arp_queue);
n->arp_queue_len_bytes = 0;
n->output = neigh_blackhole;
if (n->nud_state & NUD_VALID)
@@ -286,7 +286,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
if (!n)
goto out_entries;
- skb_queue_head_init(&n->arp_queue);
+ __skb_queue_head_init(&n->arp_queue);
rwlock_init(&n->lock);
seqlock_init(&n->ha_lock);
n->updated = n->used = now;
@@ -708,7 +708,9 @@ void neigh_destroy(struct neighbour *neigh)
if (neigh_del_timer(neigh))
pr_warn("Impossible event\n");
- skb_queue_purge(&neigh->arp_queue);
+ write_lock_bh(&neigh->lock);
+ __skb_queue_purge(&neigh->arp_queue);
+ write_unlock_bh(&neigh->lock);
neigh->arp_queue_len_bytes = 0;
if (dev->netdev_ops->ndo_neigh_destroy)
@@ -858,7 +860,7 @@ static void neigh_invalidate(struct neighbour *neigh)
neigh->ops->error_report(neigh, skb);
write_lock(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
@@ -1210,7 +1212,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
write_lock_bh(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
out:
@@ -1419,7 +1421,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
for (p = &tbl->parms; p; p = p->next) {
if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
- (!p->dev && !ifindex))
+ (!p->dev && !ifindex && net_eq(net, &init_net)))
return p;
}
@@ -1429,15 +1431,11 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
struct neigh_table *tbl)
{
- struct neigh_parms *p, *ref;
+ struct neigh_parms *p;
struct net *net = dev_net(dev);
const struct net_device_ops *ops = dev->netdev_ops;
- ref = lookup_neigh_parms(tbl, net, 0);
- if (!ref)
- return NULL;
-
- p = kmemdup(ref, sizeof(*p), GFP_KERNEL);
+ p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);
if (p) {
p->tbl = tbl;
atomic_set(&p->refcnt, 1);
@@ -2053,6 +2051,12 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
}
}
+ err = -ENOENT;
+ if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] ||
+ tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) &&
+ !net_eq(net, &init_net))
+ goto errout_tbl_lock;
+
if (tb[NDTA_THRESH1])
tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]);
@@ -2765,11 +2769,11 @@ EXPORT_SYMBOL(neigh_app_ns);
static int zero;
static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
-static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_unres_qlen(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
{
int size, ret;
- ctl_table tmp = *ctl;
+ struct ctl_table tmp = *ctl;
tmp.extra1 = &zero;
tmp.extra2 = &unres_qlen_max;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 569d355fec3e..2bf83299600a 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -146,11 +146,23 @@ static void softnet_seq_stop(struct seq_file *seq, void *v)
static int softnet_seq_show(struct seq_file *seq, void *v)
{
struct softnet_data *sd = v;
+ unsigned int flow_limit_count = 0;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+#ifdef CONFIG_NET_FLOW_LIMIT
+ struct sd_flow_limit *fl;
+
+ rcu_read_lock();
+ fl = rcu_dereference(sd->flow_limit);
+ if (fl)
+ flow_limit_count = fl->count;
+ rcu_read_unlock();
+#endif
+
+ seq_printf(seq,
+ "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
sd->processed, sd->dropped, sd->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- sd->cpu_collision, sd->received_rps);
+ sd->cpu_collision, sd->received_rps, flow_limit_count);
return 0;
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index cec074be8c43..03c8ec3edc72 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -247,7 +247,7 @@ static void netpoll_poll_dev(struct net_device *dev)
zap_completion_queue();
}
-int netpoll_rx_disable(struct net_device *dev)
+void netpoll_rx_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
@@ -257,7 +257,6 @@ int netpoll_rx_disable(struct net_device *dev)
if (ni)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
- return 0;
}
EXPORT_SYMBOL(netpoll_rx_disable);
@@ -690,25 +689,20 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
send_skb->dev = skb->dev;
skb_reset_network_header(send_skb);
- skb_put(send_skb, sizeof(struct ipv6hdr));
- hdr = ipv6_hdr(send_skb);
-
+ hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
*(__be32*)hdr = htonl(0x60000000);
-
hdr->payload_len = htons(size);
hdr->nexthdr = IPPROTO_ICMPV6;
hdr->hop_limit = 255;
hdr->saddr = *saddr;
hdr->daddr = *daddr;
- send_skb->transport_header = send_skb->tail;
- skb_put(send_skb, size);
-
- icmp6h = (struct icmp6hdr *)skb_transport_header(skb);
+ icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
icmp6h->icmp6_router = 0;
icmp6h->icmp6_solicited = 1;
- target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr));
+
+ target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
*target = msg->target;
icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
IPPROTO_ICMPV6,
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0777d0aa18c3..e533259dce3c 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -261,7 +261,7 @@ struct cgroup_subsys net_prio_subsys = {
static int netprio_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct netprio_map *old;
/*
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 11f2704c3810..9640972ec50e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1921,7 +1921,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
static int pktgen_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id);
if (pn->pktgen_exiting)
@@ -2627,6 +2627,29 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
pgh->tv_usec = htonl(timestamp.tv_usec);
}
+static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
+ struct pktgen_dev *pkt_dev,
+ unsigned int extralen)
+{
+ struct sk_buff *skb = NULL;
+ unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen +
+ pkt_dev->pkt_overhead;
+
+ if (pkt_dev->flags & F_NODE) {
+ int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id();
+
+ skb = __alloc_skb(NET_SKB_PAD + size, GFP_NOWAIT, 0, node);
+ if (likely(skb)) {
+ skb_reserve(skb, NET_SKB_PAD);
+ skb->dev = dev;
+ }
+ } else {
+ skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
+ }
+
+ return skb;
+}
+
static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
struct pktgen_dev *pkt_dev)
{
@@ -2657,32 +2680,13 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
datalen = (odev->hard_header_len + 16) & ~0xf;
- if (pkt_dev->flags & F_NODE) {
- int node;
-
- if (pkt_dev->node >= 0)
- node = pkt_dev->node;
- else
- node = numa_node_id();
-
- skb = __alloc_skb(NET_SKB_PAD + pkt_dev->cur_pkt_size + 64
- + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT, 0, node);
- if (likely(skb)) {
- skb_reserve(skb, NET_SKB_PAD);
- skb->dev = odev;
- }
- }
- else
- skb = __netdev_alloc_skb(odev,
- pkt_dev->cur_pkt_size + 64
- + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT);
-
+ skb = pktgen_alloc_skb(odev, pkt_dev, datalen);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
}
- prefetchw(skb->data);
+ prefetchw(skb->data);
skb_reserve(skb, datalen);
/* Reserve for ethernet and IP header */
@@ -2708,15 +2712,15 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
*vlan_encapsulated_proto = htons(ETH_P_IP);
}
- skb->network_header = skb->tail;
- skb->transport_header = skb->network_header + sizeof(struct iphdr);
- skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr));
+ skb_set_mac_header(skb, 0);
+ skb_set_network_header(skb, skb->len);
+ iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr));
+
+ skb_set_transport_header(skb, skb->len);
+ udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
skb->priority = pkt_dev->skb_priority;
- iph = ip_hdr(skb);
- udph = udp_hdr(skb);
-
memcpy(eth, pkt_dev->hh, 12);
*(__be16 *) & eth[12] = protocol;
@@ -2746,8 +2750,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
iph->check = 0;
iph->check = ip_fast_csum((void *)iph, iph->ihl);
skb->protocol = protocol;
- skb->mac_header = (skb->network_header - ETH_HLEN -
- pkt_dev->pkt_overhead);
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
pktgen_finalize_skb(pkt_dev, skb, datalen);
@@ -2788,15 +2790,13 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
mod_cur_headers(pkt_dev);
queue_map = pkt_dev->cur_queue_map;
- skb = __netdev_alloc_skb(odev,
- pkt_dev->cur_pkt_size + 64
- + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT);
+ skb = pktgen_alloc_skb(odev, pkt_dev, 16);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
}
- prefetchw(skb->data);
+ prefetchw(skb->data);
skb_reserve(skb, 16);
/* Reserve for ethernet and IP header */
@@ -2822,13 +2822,14 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
*vlan_encapsulated_proto = htons(ETH_P_IPV6);
}
- skb->network_header = skb->tail;
- skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
- skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr));
+ skb_set_mac_header(skb, 0);
+ skb_set_network_header(skb, skb->len);
+ iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr));
+
+ skb_set_transport_header(skb, skb->len);
+ udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
skb->priority = pkt_dev->skb_priority;
- iph = ipv6_hdr(skb);
- udph = udp_hdr(skb);
memcpy(eth, pkt_dev->hh, 12);
*(__be16 *) &eth[12] = protocol;
@@ -2863,8 +2864,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
iph->daddr = pkt_dev->cur_in6_daddr;
iph->saddr = pkt_dev->cur_in6_saddr;
- skb->mac_header = (skb->network_header - ETH_HLEN -
- pkt_dev->pkt_overhead);
skb->protocol = protocol;
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a08bd2b7fe3f..3de740834d1f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -947,6 +947,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_vlan vf_vlan;
struct ifla_vf_tx_rate vf_tx_rate;
struct ifla_vf_spoofchk vf_spoofchk;
+ struct ifla_vf_link_state vf_linkstate;
/*
* Not all SR-IOV capable drivers support the
@@ -956,18 +957,24 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
*/
ivi.spoofchk = -1;
memset(ivi.mac, 0, sizeof(ivi.mac));
+ /* The default value for VF link state is "auto"
+ * IFLA_VF_LINK_STATE_AUTO which equals zero
+ */
+ ivi.linkstate = 0;
if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
break;
vf_mac.vf =
vf_vlan.vf =
vf_tx_rate.vf =
- vf_spoofchk.vf = ivi.vf;
+ vf_spoofchk.vf =
+ vf_linkstate.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
vf_tx_rate.rate = ivi.tx_rate;
vf_spoofchk.setting = ivi.spoofchk;
+ vf_linkstate.link_state = ivi.linkstate;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
@@ -978,7 +985,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
&vf_tx_rate) ||
nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
- &vf_spoofchk))
+ &vf_spoofchk) ||
+ nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
+ &vf_linkstate))
goto nla_put_failure;
nla_nest_end(skb, vf);
}
@@ -1238,6 +1247,15 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
ivs->setting);
break;
}
+ case IFLA_VF_LINK_STATE: {
+ struct ifla_vf_link_state *ivl;
+ ivl = nla_data(vf);
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_link_state)
+ err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+ ivl->link_state);
+ break;
+ }
default:
err = -EINVAL;
break;
@@ -2091,10 +2109,6 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (is_zero_ether_addr(addr)) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
- return -EINVAL;
- }
err = -EOPNOTSUPP;
@@ -2192,10 +2206,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (is_zero_ether_addr(addr)) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n");
- return -EINVAL;
- }
err = -EOPNOTSUPP;
@@ -2667,7 +2677,7 @@ static void rtnetlink_rcv(struct sk_buff *skb)
static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
switch (event) {
case NETDEV_UP:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1c1738cc4538..77971a35d6e1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -199,9 +199,7 @@ struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node)
skb->truesize = sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
out:
return skb;
}
@@ -275,10 +273,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->data = data;
skb_reset_tail_pointer(skb);
skb->end = skb->tail + size;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
- skb->transport_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb->transport_header = (typeof(skb->transport_header))~0U;
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
@@ -344,10 +340,8 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
skb->data = data;
skb_reset_tail_pointer(skb);
skb->end = skb->tail + size;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->mac_header = ~0U;
- skb->transport_header = ~0U;
-#endif
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb->transport_header = (typeof(skb->transport_header))~0U;
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
@@ -743,6 +737,10 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->vlan_tci = old->vlan_tci;
skb_copy_secmark(new, old);
+
+#ifdef CONFIG_NET_LL_RX_POLL
+ new->napi_id = old->napi_id;
+#endif
}
/*
@@ -915,18 +913,8 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off)
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
-#ifndef NET_SKBUFF_DATA_USES_OFFSET
- /*
- * Shift between the two data areas in bytes
- */
- unsigned long offset = new->data - old->data;
-#endif
-
__copy_skb_header(new, old);
-#ifndef NET_SKBUFF_DATA_USES_OFFSET
- skb_headers_offset_update(new, offset);
-#endif
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
@@ -1118,7 +1106,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb->end = skb->head + size;
#endif
skb->tail += off;
- skb_headers_offset_update(skb, off);
+ skb_headers_offset_update(skb, nhead);
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += nhead;
@@ -1213,9 +1201,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
off = newheadroom - oldheadroom;
if (n->ip_summed == CHECKSUM_PARTIAL)
n->csum_start += off;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
+
skb_headers_offset_update(n, off);
-#endif
return n;
}
@@ -2558,8 +2545,13 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
unsigned int block_limit, abs_offset = consumed + st->lower_offset;
skb_frag_t *frag;
- if (unlikely(abs_offset >= st->upper_offset))
+ if (unlikely(abs_offset >= st->upper_offset)) {
+ if (st->frag_data) {
+ kunmap_atomic(st->frag_data);
+ st->frag_data = NULL;
+ }
return 0;
+ }
next_skb:
block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
@@ -2857,7 +2849,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
doffset + tnl_hlen);
if (fskb != skb_shinfo(skb)->frag_list)
- continue;
+ goto perform_csum_check;
if (!sg) {
nskb->ip_summed = CHECKSUM_NONE;
@@ -2921,6 +2913,7 @@ skip_fraglist:
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
+perform_csum_check:
if (!csum) {
nskb->csum = skb_checksum(nskb, doffset,
nskb->len - doffset, 0);
@@ -3503,3 +3496,26 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
return true;
}
EXPORT_SYMBOL(skb_try_coalesce);
+
+/**
+ * skb_scrub_packet - scrub an skb before sending it to another netns
+ *
+ * @skb: buffer to clean
+ *
+ * skb_scrub_packet can be used to clean an skb before injecting it in
+ * another namespace. We have to clear all information in the skb that
+ * could impact namespace isolation.
+ */
+void skb_scrub_packet(struct sk_buff *skb)
+{
+ skb_orphan(skb);
+ skb->tstamp.tv64 = 0;
+ skb->pkt_type = PACKET_HOST;
+ skb->skb_iif = 0;
+ skb_dst_drop(skb);
+ skb->mark = 0;
+ secpath_reset(skb);
+ nf_reset(skb);
+ nf_reset_trace(skb);
+}
+EXPORT_SYMBOL_GPL(skb_scrub_packet);
diff --git a/net/core/sock.c b/net/core/sock.c
index d6d024cfaaaf..ab06b719f5b1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -139,6 +139,8 @@
#include <net/tcp.h>
#endif
+#include <net/ll_poll.h>
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
@@ -898,6 +900,19 @@ set_rcvbuf:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
+#ifdef CONFIG_NET_LL_RX_POLL
+ case SO_LL:
+ /* allow unprivileged users to decrease the value */
+ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ else {
+ if (val < 0)
+ ret = -EINVAL;
+ else
+ sk->sk_ll_usec = val;
+ }
+ break;
+#endif
default:
ret = -ENOPROTOOPT;
break;
@@ -1155,6 +1170,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
break;
+#ifdef CONFIG_NET_LL_RX_POLL
+ case SO_LL:
+ v.val = sk->sk_ll_usec;
+ break;
+#endif
+
default:
return -ENOPROTOOPT;
}
@@ -2271,6 +2292,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_stamp = ktime_set(-1L, 0);
+#ifdef CONFIG_NET_LL_RX_POLL
+ sk->sk_napi_id = 0;
+ sk->sk_ll_usec = sysctl_net_ll_read;
+#endif
+
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cfdb46ab3a7f..afc677eadd93 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -19,16 +19,17 @@
#include <net/ip.h>
#include <net/sock.h>
#include <net/net_ratelimit.h>
+#include <net/ll_poll.h>
static int one = 1;
#ifdef CONFIG_RPS
-static int rps_sock_flow_sysctl(ctl_table *table, int write,
+static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int orig_size, size;
int ret, i;
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &size,
.maxlen = sizeof(size),
.mode = table->mode
@@ -87,6 +88,109 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
}
#endif /* CONFIG_RPS */
+#ifdef CONFIG_NET_FLOW_LIMIT
+static DEFINE_MUTEX(flow_limit_update_mutex);
+
+static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct sd_flow_limit *cur;
+ struct softnet_data *sd;
+ cpumask_var_t mask;
+ int i, len, ret = 0;
+
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ if (write) {
+ ret = cpumask_parse_user(buffer, *lenp, mask);
+ if (ret)
+ goto done;
+
+ mutex_lock(&flow_limit_update_mutex);
+ len = sizeof(*cur) + netdev_flow_limit_table_len;
+ for_each_possible_cpu(i) {
+ sd = &per_cpu(softnet_data, i);
+ cur = rcu_dereference_protected(sd->flow_limit,
+ lockdep_is_held(&flow_limit_update_mutex));
+ if (cur && !cpumask_test_cpu(i, mask)) {
+ RCU_INIT_POINTER(sd->flow_limit, NULL);
+ synchronize_rcu();
+ kfree(cur);
+ } else if (!cur && cpumask_test_cpu(i, mask)) {
+ cur = kzalloc(len, GFP_KERNEL);
+ if (!cur) {
+ /* not unwinding previous changes */
+ ret = -ENOMEM;
+ goto write_unlock;
+ }
+ cur->num_buckets = netdev_flow_limit_table_len;
+ rcu_assign_pointer(sd->flow_limit, cur);
+ }
+ }
+write_unlock:
+ mutex_unlock(&flow_limit_update_mutex);
+ } else {
+ char kbuf[128];
+
+ if (*ppos || !*lenp) {
+ *lenp = 0;
+ goto done;
+ }
+
+ cpumask_clear(mask);
+ rcu_read_lock();
+ for_each_possible_cpu(i) {
+ sd = &per_cpu(softnet_data, i);
+ if (rcu_dereference(sd->flow_limit))
+ cpumask_set_cpu(i, mask);
+ }
+ rcu_read_unlock();
+
+ len = min(sizeof(kbuf) - 1, *lenp);
+ len = cpumask_scnprintf(kbuf, len, mask);
+ if (!len) {
+ *lenp = 0;
+ goto done;
+ }
+ if (len < *lenp)
+ kbuf[len++] = '\n';
+ if (copy_to_user(buffer, kbuf, len)) {
+ ret = -EFAULT;
+ goto done;
+ }
+ *lenp = len;
+ *ppos += len;
+ }
+
+done:
+ free_cpumask_var(mask);
+ return ret;
+}
+
+static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ unsigned int old, *ptr;
+ int ret;
+
+ mutex_lock(&flow_limit_update_mutex);
+
+ ptr = table->data;
+ old = *ptr;
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ if (!ret && write && !is_power_of_2(*ptr)) {
+ *ptr = old;
+ ret = -EINVAL;
+ }
+
+ mutex_unlock(&flow_limit_update_mutex);
+ return ret;
+}
+#endif /* CONFIG_NET_FLOW_LIMIT */
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -180,6 +284,37 @@ static struct ctl_table net_core_table[] = {
.proc_handler = rps_sock_flow_sysctl
},
#endif
+#ifdef CONFIG_NET_FLOW_LIMIT
+ {
+ .procname = "flow_limit_cpu_bitmap",
+ .mode = 0644,
+ .proc_handler = flow_limit_cpu_sysctl
+ },
+ {
+ .procname = "flow_limit_table_len",
+ .data = &netdev_flow_limit_table_len,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = flow_limit_table_len_sysctl
+ },
+#endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_LL_RX_POLL
+ {
+ .procname = "low_latency_poll",
+ .data = &sysctl_net_ll_poll,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "low_latency_read",
+ .data = &sysctl_net_ll_read,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+#
+#endif
#endif /* CONFIG_NET */
{
.procname = "netdev_budget",
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-26 12:57:24 +0300