summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/dev.c189
-rw-r--r--net/core/dst.c120
-rw-r--r--net/core/ethtool.c2
-rw-r--r--net/core/fib_rules.c48
-rw-r--r--net/core/filter.c299
-rw-r--r--net/core/flow_dissector.c284
-rw-r--r--net/core/lwtunnel.c249
-rw-r--r--net/core/neighbour.c59
-rw-r--r--net/core/net-sysfs.c54
-rw-r--r--net/core/net-traces.c1
-rw-r--r--net/core/netpoll.c31
-rw-r--r--net/core/pktgen.c5
-rw-r--r--net/core/ptp_classifier.c16
-rw-r--r--net/core/request_sock.c88
-rw-r--r--net/core/rtnetlink.c112
-rw-r--r--net/core/skbuff.c13
-rw-r--r--net/core/sock.c89
-rw-r--r--net/core/sock_diag.c17
-rw-r--r--net/core/timestamping.c6
-rw-r--r--net/core/tso.c18
-rw-r--r--net/core/utils.c58
22 files changed, 1364 insertions, 395 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index fec0856dd6c0..086b01fbe1bd 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -23,3 +23,4 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
+obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
diff --git a/net/core/dev.c b/net/core/dev.c
index a8e4dd430285..8ce3f74cd6b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -99,6 +99,7 @@
#include <linux/rtnetlink.h>
#include <linux/stat.h>
#include <net/dst.h>
+#include <net/dst_metadata.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/xfrm.h>
@@ -682,6 +683,32 @@ int dev_get_iflink(const struct net_device *dev)
EXPORT_SYMBOL(dev_get_iflink);
/**
+ * dev_fill_metadata_dst - Retrieve tunnel egress information.
+ * @dev: targeted interface
+ * @skb: The packet.
+ *
+ * For better visibility of tunnel traffic OVS needs to retrieve
+ * egress tunnel information for a packet. Following API allows
+ * user to get this info.
+ */
+int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ip_tunnel_info *info;
+
+ if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst)
+ return -EINVAL;
+
+ info = skb_tunnel_info_unclone(skb);
+ if (!info)
+ return -ENOMEM;
+ if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX)))
+ return -EINVAL;
+
+ return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb);
+}
+EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
+
+/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
@@ -2915,9 +2942,11 @@ EXPORT_SYMBOL(xmit_recursion);
/**
* dev_loopback_xmit - loop back @skb
+ * @net: network namespace this loopback is happening in
+ * @sk: sk needed to be a netfilter okfn
* @skb: buffer to transmit
*/
-int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
+int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
@@ -2972,6 +3001,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
new_index = skb_tx_hash(dev, skb);
if (queue_index != new_index && sk &&
+ sk_fullsock(sk) &&
rcu_access_pointer(sk->sk_dst_cache))
sk_tx_queue_set(sk, new_index);
@@ -3061,6 +3091,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
else
skb_dst_force(skb);
+#ifdef CONFIG_NET_SWITCHDEV
+ /* Don't forward if offload device already forwarded */
+ if (skb->offload_fwd_mark &&
+ skb->offload_fwd_mark == dev->offload_fwd_mark) {
+ consume_skb(skb);
+ rc = NET_XMIT_SUCCESS;
+ goto out;
+ }
+#endif
+
txq = netdev_pick_tx(dev, skb, accel_priv);
q = rcu_dereference_bh(txq->qdisc);
@@ -3133,11 +3173,11 @@ out:
return rc;
}
-int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb)
+int dev_queue_xmit(struct sk_buff *skb)
{
return __dev_queue_xmit(skb, NULL);
}
-EXPORT_SYMBOL(dev_queue_xmit_sk);
+EXPORT_SYMBOL(dev_queue_xmit);
int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
{
@@ -3645,19 +3685,27 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
qdisc_skb_cb(skb)->pkt_len = skb->len;
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
- qdisc_bstats_update_cpu(cl->q, skb);
+ qdisc_bstats_cpu_update(cl->q, skb);
- switch (tc_classify(skb, cl, &cl_res)) {
+ switch (tc_classify(skb, cl, &cl_res, false)) {
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(cl_res.classid);
break;
case TC_ACT_SHOT:
- qdisc_qstats_drop_cpu(cl->q);
+ qdisc_qstats_cpu_drop(cl->q);
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
kfree_skb(skb);
return NULL;
+ case TC_ACT_REDIRECT:
+ /* skb_mac_header check was done by cls/act_bpf, so
+ * we can safely push the L2 header back before
+ * redirecting to another netdev
+ */
+ __skb_push(skb, skb->mac_len);
+ skb_do_redirect(skb);
+ return NULL;
default:
break;
}
@@ -3972,13 +4020,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
* NET_RX_SUCCESS: no congestion
* NET_RX_DROP: packet was dropped
*/
-int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb)
+int netif_receive_skb(struct sk_buff *skb)
{
trace_netif_receive_skb_entry(skb);
return netif_receive_skb_internal(skb);
}
-EXPORT_SYMBOL(netif_receive_skb_sk);
+EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending
* Called with irqs disabled.
@@ -4703,6 +4751,8 @@ void napi_disable(struct napi_struct *n)
while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
msleep(1);
+ while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state))
+ msleep(1);
hrtimer_cancel(&n->timer);
@@ -4845,8 +4895,7 @@ struct netdev_adjacent {
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
- struct net_device *adj_dev,
+static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
struct list_head *adj_list)
{
struct netdev_adjacent *adj;
@@ -4872,7 +4921,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper);
+ return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -4985,7 +5034,7 @@ EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
* Gets the next netdev_adjacent->private from the dev's lower neighbour
* list, starting from iter position. The caller must hold either hold the
* RTNL lock or its own locking that guarantees that the neighbour lower
- * list will remain unchainged.
+ * list will remain unchanged.
*/
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter)
@@ -5040,7 +5089,7 @@ EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
* Gets the next netdev_adjacent from the dev's lower neighbour
* list, starting from iter position. The caller must hold RTNL lock or
* its own locking that guarantees that the neighbour lower
- * list will remain unchainged.
+ * list will remain unchanged.
*/
void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
{
@@ -5134,7 +5183,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct netdev_adjacent *adj;
int ret;
- adj = __netdev_find_adj(dev, adj_dev, dev_list);
+ adj = __netdev_find_adj(adj_dev, dev_list);
if (adj) {
adj->ref_nr++;
@@ -5190,7 +5239,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
{
struct netdev_adjacent *adj;
- adj = __netdev_find_adj(dev, adj_dev, dev_list);
+ adj = __netdev_find_adj(adj_dev, dev_list);
if (!adj) {
pr_err("tried to remove device %s from %s\n",
@@ -5301,6 +5350,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
void *private)
{
+ struct netdev_notifier_changeupper_info changeupper_info;
struct netdev_adjacent *i, *j, *to_i, *to_j;
int ret = 0;
@@ -5310,15 +5360,25 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
+ if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper))
return -EBUSY;
- if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
+ if (__netdev_find_adj(upper_dev, &dev->adj_list.upper))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
return -EBUSY;
+ changeupper_info.upper_dev = upper_dev;
+ changeupper_info.master = master;
+ changeupper_info.linking = true;
+
+ ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ &changeupper_info.info);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ return ret;
+
ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
master);
if (ret)
@@ -5357,7 +5417,8 @@ static int __netdev_upper_dev_link(struct net_device *dev,
goto rollback_lower_mesh;
}
- call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
+ call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ &changeupper_info.info);
return 0;
rollback_lower_mesh:
@@ -5452,9 +5513,17 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_notifier_changeupper_info changeupper_info;
struct netdev_adjacent *i, *j;
ASSERT_RTNL();
+ changeupper_info.upper_dev = upper_dev;
+ changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
+ changeupper_info.linking = false;
+
+ call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ &changeupper_info.info);
+
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
/* Here is the tricky part. We must remove all dev's lower
@@ -5474,7 +5543,8 @@ void netdev_upper_dev_unlink(struct net_device *dev,
list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
__netdev_adjacent_dev_unlink(dev, i->dev);
- call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
+ call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ &changeupper_info.info);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -5580,7 +5650,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
if (!lower_dev)
return NULL;
- lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower);
+ lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower);
if (!lower)
return NULL;
@@ -6075,6 +6145,26 @@ int dev_get_phys_port_name(struct net_device *dev,
EXPORT_SYMBOL(dev_get_phys_port_name);
/**
+ * dev_change_proto_down - update protocol port state information
+ * @dev: device
+ * @proto_down: new value
+ *
+ * This info can be used by switch drivers to set the phys state of the
+ * port.
+ */
+int dev_change_proto_down(struct net_device *dev, bool proto_down)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_change_proto_down)
+ return -EOPNOTSUPP;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return ops->ndo_change_proto_down(dev, proto_down);
+}
+EXPORT_SYMBOL(dev_change_proto_down);
+
+/**
* dev_new_index - allocate an ifindex
* @net: the applicable net namespace
*
@@ -6198,6 +6288,48 @@ static void rollback_registered(struct net_device *dev)
list_del(&single);
}
+static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
+ struct net_device *upper, netdev_features_t features)
+{
+ netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES;
+ netdev_features_t feature;
+ int feature_bit;
+
+ for_each_netdev_feature(&upper_disables, feature_bit) {
+ feature = __NETIF_F_BIT(feature_bit);
+ if (!(upper->wanted_features & feature)
+ && (features & feature)) {
+ netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n",
+ &feature, upper->name);
+ features &= ~feature;
+ }
+ }
+
+ return features;
+}
+
+static void netdev_sync_lower_features(struct net_device *upper,
+ struct net_device *lower, netdev_features_t features)
+{
+ netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES;
+ netdev_features_t feature;
+ int feature_bit;
+
+ for_each_netdev_feature(&upper_disables, feature_bit) {
+ feature = __NETIF_F_BIT(feature_bit);
+ if (!(features & feature) && (lower->features & feature)) {
+ netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
+ &feature, lower->name);
+ lower->wanted_features &= ~feature;
+ netdev_update_features(lower);
+
+ if (unlikely(lower->features & feature))
+ netdev_WARN(upper, "failed to disable %pNF on %s!\n",
+ &feature, lower->name);
+ }
+ }
+}
+
static netdev_features_t netdev_fix_features(struct net_device *dev,
netdev_features_t features)
{
@@ -6267,7 +6399,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
int __netdev_update_features(struct net_device *dev)
{
+ struct net_device *upper, *lower;
netdev_features_t features;
+ struct list_head *iter;
int err = 0;
ASSERT_RTNL();
@@ -6280,6 +6414,10 @@ int __netdev_update_features(struct net_device *dev)
/* driver might be less strict about feature dependencies */
features = netdev_fix_features(dev, features);
+ /* some features can't be enabled if they're off an an upper device */
+ netdev_for_each_upper_dev_rcu(dev, upper, iter)
+ features = netdev_sync_upper_features(dev, upper, features);
+
if (dev->features == features)
return 0;
@@ -6296,6 +6434,12 @@ int __netdev_update_features(struct net_device *dev)
return -1;
}
+ /* some features must be disabled on lower devices when disabled
+ * on an upper device (think: bonding master or bridge)
+ */
+ netdev_for_each_lower_dev(dev, lower, iter)
+ netdev_sync_lower_features(dev, lower, features);
+
if (!err)
dev->features = features;
@@ -6967,6 +7111,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
setup(dev);
+ if (!dev->tx_queue_len)
+ dev->priv_flags |= IFF_NO_QUEUE;
+
dev->num_tx_queues = txqs;
dev->real_num_tx_queues = txqs;
if (netif_alloc_netdev_queues(dev))
@@ -7639,7 +7786,7 @@ static int __init net_dev_init(void)
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
- dst_init();
+ dst_subsys_init();
rc = 0;
out:
return rc;
diff --git a/net/core/dst.c b/net/core/dst.c
index 002144bea935..2a1818065e12 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -20,8 +20,10 @@
#include <net/net_namespace.h>
#include <linux/sched.h>
#include <linux/prefetch.h>
+#include <net/lwtunnel.h>
#include <net/dst.h>
+#include <net/dst_metadata.h>
/*
* Theory of operations:
@@ -142,12 +144,12 @@ loop:
mutex_unlock(&dst_gc_mutex);
}
-int dst_discard_sk(struct sock *sk, struct sk_buff *skb)
+int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
return 0;
}
-EXPORT_SYMBOL(dst_discard_sk);
+EXPORT_SYMBOL(dst_discard_out);
const u32 dst_default_metrics[RTAX_MAX + 1] = {
/* This initializer is needed to force linker to place this variable
@@ -158,19 +160,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = {
[RTAX_MAX] = 0xdeadbeef,
};
-
-void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
- int initial_ref, int initial_obsolete, unsigned short flags)
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags)
{
- struct dst_entry *dst;
-
- if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
- if (ops->gc(ops))
- return NULL;
- }
- dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
- if (!dst)
- return NULL;
dst->child = NULL;
dst->dev = dev;
if (dev)
@@ -184,7 +177,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
dst->xfrm = NULL;
#endif
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
dst->error = 0;
dst->obsolete = initial_obsolete;
dst->header_len = 0;
@@ -192,6 +185,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = 0;
#endif
+ dst->lwtstate = NULL;
atomic_set(&dst->__refcnt, initial_ref);
dst->__use = 0;
dst->lastuse = jiffies;
@@ -200,6 +194,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
dst->next = NULL;
if (!(flags & DST_NOCOUNT))
dst_entries_add(ops, 1);
+}
+EXPORT_SYMBOL(dst_init);
+
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
+ int initial_ref, int initial_obsolete, unsigned short flags)
+{
+ struct dst_entry *dst;
+
+ if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
+ if (ops->gc(ops))
+ return NULL;
+ }
+
+ dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
+ if (!dst)
+ return NULL;
+
+ dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags);
+
return dst;
}
EXPORT_SYMBOL(dst_alloc);
@@ -211,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
}
dst->obsolete = DST_OBSOLETE_DEAD;
}
@@ -248,7 +261,13 @@ again:
dst->ops->destroy(dst);
if (dst->dev)
dev_put(dst->dev);
- kmem_cache_free(dst->ops->kmem_cachep, dst);
+
+ lwtstate_put(dst->lwtstate);
+
+ if (dst->flags & DST_METADATA)
+ kfree(dst);
+ else
+ kmem_cache_free(dst->ops->kmem_cachep, dst);
dst = child;
if (dst) {
@@ -329,6 +348,69 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
}
EXPORT_SYMBOL(__dst_destroy_metrics_generic);
+static struct dst_ops md_dst_ops = {
+ .family = AF_UNSPEC,
+};
+
+static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ WARN_ONCE(1, "Attempting to call output on metadata dst\n");
+ kfree_skb(skb);
+ return 0;
+}
+
+static int dst_md_discard(struct sk_buff *skb)
+{
+ WARN_ONCE(1, "Attempting to call input on metadata dst\n");
+ kfree_skb(skb);
+ return 0;
+}
+
+static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
+{
+ struct dst_entry *dst;
+
+ dst = &md_dst->dst;
+ dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+ DST_METADATA | DST_NOCACHE | DST_NOCOUNT);
+
+ dst->input = dst_md_discard;
+ dst->output = dst_md_discard_out;
+
+ memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
+}
+
+struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
+{
+ struct metadata_dst *md_dst;
+
+ md_dst = kmalloc(sizeof(*md_dst) + optslen, flags);
+ if (!md_dst)
+ return NULL;
+
+ __metadata_dst_init(md_dst, optslen);
+
+ return md_dst;
+}
+EXPORT_SYMBOL_GPL(metadata_dst_alloc);
+
+struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
+{
+ int cpu;
+ struct metadata_dst __percpu *md_dst;
+
+ md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen,
+ __alignof__(struct metadata_dst), flags);
+ if (!md_dst)
+ return NULL;
+
+ for_each_possible_cpu(cpu)
+ __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen);
+
+ return md_dst;
+}
+EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
+
/* Dirty hack. We did it in 2.2 (in __dst_free),
* we have _very_ good reasons not to repeat
* this mistake in 2.3, but we have no choice
@@ -348,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
if (!unregister) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
} else {
dst->dev = dev_net(dst->dev)->loopback_dev;
dev_hold(dst->dev);
@@ -393,7 +475,7 @@ static struct notifier_block dst_dev_notifier = {
.priority = -10, /* must be called after other network notifiers */
};
-void __init dst_init(void)
+void __init dst_subsys_init(void)
{
register_netdevice_notifier(&dst_dev_notifier);
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b495ab1797fa..29edf74846fc 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
gstrings.len = ret;
- data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+ data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
if (!data)
return -ENOMEM;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a12668f7d62..365de66436ac 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -16,6 +16,7 @@
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/fib_rules.h>
+#include <net/ip_tunnels.h>
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
@@ -43,7 +44,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
}
EXPORT_SYMBOL(fib_default_rule_add);
-u32 fib_default_rule_pref(struct fib_rules_ops *ops)
+static u32 fib_default_rule_pref(struct fib_rules_ops *ops)
{
struct list_head *pos;
struct fib_rule *rule;
@@ -59,7 +60,6 @@ u32 fib_default_rule_pref(struct fib_rules_ops *ops)
return 0;
}
-EXPORT_SYMBOL(fib_default_rule_pref);
static void notify_rule_change(int event, struct fib_rule *rule,
struct fib_rules_ops *ops, struct nlmsghdr *nlh,
@@ -186,6 +186,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
goto out;
+ if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -295,8 +298,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
}
rule->fr_net = net;
- if (tb[FRA_PRIORITY])
- rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
+ rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY])
+ : fib_default_rule_pref(ops);
if (tb[FRA_IIFNAME]) {
struct net_device *dev;
@@ -330,6 +333,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
if (tb[FRA_FWMASK])
rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]);
+ if (tb[FRA_TUN_ID])
+ rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
+
rule->action = frh->action;
rule->flags = frh->flags;
rule->table = frh_get_table(frh, tb);
@@ -343,9 +349,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
else
rule->suppress_ifgroup = -1;
- if (!tb[FRA_PRIORITY] && ops->default_pref)
- rule->pref = ops->default_pref(ops);
-
err = -EINVAL;
if (tb[FRA_GOTO]) {
if (rule->action != FR_ACT_GOTO)
@@ -407,6 +410,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
if (unresolved)
ops->unresolved_rules++;
+ if (rule->tun_id)
+ ip_tunnel_need_metadata();
+
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
flush_route_cache(ops);
rules_ops_put(ops);
@@ -473,6 +479,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
(rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
continue;
+ if (tb[FRA_TUN_ID] &&
+ (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -487,6 +497,9 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
goto errout;
}
+ if (rule->tun_id)
+ ip_tunnel_unneed_metadata();
+
list_del_rcu(&rule->list);
if (rule->action == FR_ACT_GOTO) {
@@ -535,7 +548,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
+ nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
+ nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+ nla_total_size(4) /* FRA_FWMARK */
- + nla_total_size(4); /* FRA_FWMASK */
+ + nla_total_size(4) /* FRA_FWMASK */
+ + nla_total_size(8); /* FRA_TUN_ID */
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -591,7 +605,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
((rule->mark_mask || rule->mark) &&
nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
(rule->target &&
- nla_put_u32(skb, FRA_GOTO, rule->target)))
+ nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+ (rule->tun_id &&
+ nla_put_be64(skb, FRA_TUN_ID, rule->tun_id)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
@@ -615,15 +631,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
{
int idx = 0;
struct fib_rule *rule;
+ int err = 0;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
if (idx < cb->args[1])
goto skip;
- if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, RTM_NEWRULE,
- NLM_F_MULTI, ops) < 0)
+ err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWRULE,
+ NLM_F_MULTI, ops);
+ if (err)
break;
skip:
idx++;
@@ -632,7 +650,7 @@ skip:
cb->args[1] = idx;
rules_ops_put(ops);
- return skb->len;
+ return err;
}
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -648,7 +666,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
if (ops == NULL)
return -EAFNOSUPPORT;
- return dump_rules(skb, cb, ops);
+ dump_rules(skb, cb, ops);
+
+ return skb->len;
}
rcu_read_lock();
diff --git a/net/core/filter.c b/net/core/filter.c
index be3098fb65e4..672eefbfbe99 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -47,16 +47,19 @@
#include <linux/if_vlan.h>
#include <linux/bpf.h>
#include <net/sch_generic.h>
+#include <net/cls_cgroup.h>
+#include <net/dst_metadata.h>
+#include <net/dst.h>
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
- * Run the filter code and then cut skb->data to correct size returned by
- * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller
+ * Run the eBPF program and then cut skb->data to correct size returned by
+ * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to SK_RUN_FILTER. It returns 0 if the packet should
+ * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
@@ -80,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
+ unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
@@ -146,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
return raw_smp_processor_id();
}
-/* note that this only generates 32-bit random numbers */
-static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
-{
- return prandom_u32();
-}
-
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
@@ -310,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
- *insn = BPF_EMIT_CALL(__get_random_u32);
+ *insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
+ bpf_user_rnd_init_once();
break;
}
break;
@@ -476,9 +474,9 @@ do_pass:
bpf_src = BPF_X;
} else {
insn->dst_reg = BPF_REG_A;
- insn->src_reg = BPF_REG_X;
insn->imm = fp->k;
bpf_src = BPF_SRC(fp->code);
+ insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0;
}
/* Common case where 'jump_false' is next insn. */
@@ -999,7 +997,7 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
int err;
fp->bpf_func = NULL;
- fp->jited = false;
+ fp->jited = 0;
err = bpf_check_classic(fp->insns, fp->len);
if (err) {
@@ -1081,16 +1079,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create);
* @pfp: the unattached filter that is created
* @fprog: the filter program
* @trans: post-classic verifier transformation handler
+ * @save_orig: save classic BPF program
*
* This function effectively does the same as bpf_prog_create(), only
* that it builds up its insns buffer from user space provided buffer.
* It also allows for passing a bpf_aux_classic_check_t handler.
*/
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
- bpf_aux_classic_check_t trans)
+ bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
+ int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
@@ -1106,12 +1106,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
}
fp->len = fprog->len;
- /* Since unattached filters are not copied back to user
- * space through sk_get_filter(), we do not need to hold
- * a copy here, and can spare us the work.
- */
fp->orig_prog = NULL;
+ if (save_orig) {
+ err = bpf_prog_store_orig_filter(fp, fprog);
+ if (err) {
+ __bpf_prog_free(fp);
+ return -ENOMEM;
+ }
+ }
+
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
@@ -1122,6 +1126,7 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
*pfp = fp;
return 0;
}
+EXPORT_SYMBOL_GPL(bpf_prog_create_from_user);
void bpf_prog_destroy(struct bpf_prog *fp)
{
@@ -1346,7 +1351,7 @@ const struct bpf_func_proto bpf_l3_csum_replace_proto = {
static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
- u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags);
+ bool is_pseudo = !!BPF_IS_PSEUDO_HEADER(flags);
int offset = (int) r2;
__sum16 sum, *ptr;
@@ -1401,9 +1406,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
if (unlikely(!dev))
return -EINVAL;
- if (unlikely(!(dev->flags & IFF_UP)))
- return -EINVAL;
-
skb2 = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!skb2))
return -ENOMEM;
@@ -1412,6 +1414,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
return dev_forward_skb(dev, skb2);
skb2->dev = dev;
+ skb_sender_cpu_clear(skb2);
return dev_queue_xmit(skb2);
}
@@ -1424,6 +1427,201 @@ const struct bpf_func_proto bpf_clone_redirect_proto = {
.arg3_type = ARG_ANYTHING,
};
+struct redirect_info {
+ u32 ifindex;
+ u32 flags;
+};
+
+static DEFINE_PER_CPU(struct redirect_info, redirect_info);
+static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+
+ ri->ifindex = ifindex;
+ ri->flags = flags;
+ return TC_ACT_REDIRECT;
+}
+
+int skb_do_redirect(struct sk_buff *skb)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ struct net_device *dev;
+
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex);
+ ri->ifindex = 0;
+ if (unlikely(!dev)) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ if (BPF_IS_REDIRECT_INGRESS(ri->flags))
+ return dev_forward_skb(dev, skb);
+
+ skb->dev = dev;
+ skb_sender_cpu_clear(skb);
+ return dev_queue_xmit(skb);
+}
+
+const struct bpf_func_proto bpf_redirect_proto = {
+ .func = bpf_redirect,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_ANYTHING,
+};
+
+static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ return task_get_classid((struct sk_buff *) (unsigned long) r1);
+}
+
+static const struct bpf_func_proto bpf_get_cgroup_classid_proto = {
+ .func = bpf_get_cgroup_classid,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ const struct dst_entry *dst;
+
+ dst = skb_dst((struct sk_buff *) (unsigned long) r1);
+ if (dst)
+ return dst->tclassid;
+#endif
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_route_realm_proto = {
+ .func = bpf_get_route_realm,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ __be16 vlan_proto = (__force __be16) r2;
+
+ if (unlikely(vlan_proto != htons(ETH_P_8021Q) &&
+ vlan_proto != htons(ETH_P_8021AD)))
+ vlan_proto = htons(ETH_P_8021Q);
+
+ return skb_vlan_push(skb, vlan_proto, vlan_tci);
+}
+
+const struct bpf_func_proto bpf_skb_vlan_push_proto = {
+ .func = bpf_skb_vlan_push,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto);
+
+static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+
+ return skb_vlan_pop(skb);
+}
+
+const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
+ .func = bpf_skb_vlan_pop,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
+
+bool bpf_helper_changes_skb_data(void *func)
+{
+ if (func == bpf_skb_vlan_push)
+ return true;
+ if (func == bpf_skb_vlan_pop)
+ return true;
+ return false;
+}
+
+static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2;
+ struct ip_tunnel_info *info = skb_tunnel_info(skb);
+
+ if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags || !info))
+ return -EINVAL;
+ if (ip_tunnel_info_af(info) != AF_INET)
+ return -EINVAL;
+
+ to->tunnel_id = be64_to_cpu(info->key.tun_id);
+ to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src);
+
+ return 0;
+}
+
+const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = {
+ .func = bpf_skb_get_tunnel_key,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_STACK,
+ .arg3_type = ARG_CONST_STACK_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+static struct metadata_dst __percpu *md_dst;
+
+static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *) (long) r1;
+ struct bpf_tunnel_key *from = (struct bpf_tunnel_key *) (long) r2;
+ struct metadata_dst *md = this_cpu_ptr(md_dst);
+ struct ip_tunnel_info *info;
+
+ if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags))
+ return -EINVAL;
+
+ skb_dst_drop(skb);
+ dst_hold((struct dst_entry *) md);
+ skb_dst_set(skb, (struct dst_entry *) md);
+
+ info = &md->u.tun_info;
+ info->mode = IP_TUNNEL_INFO_TX;
+ info->key.tun_flags = TUNNEL_KEY;
+ info->key.tun_id = cpu_to_be64(from->tunnel_id);
+ info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
+
+ return 0;
+}
+
+const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = {
+ .func = bpf_skb_set_tunnel_key,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_STACK,
+ .arg3_type = ARG_CONST_STACK_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void)
+{
+ if (!md_dst) {
+ /* race is not possible, since it's called from
+ * verifier that is holding verifier mutex
+ */
+ md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL);
+ if (!md_dst)
+ return NULL;
+ }
+ return &bpf_skb_set_tunnel_key_proto;
+}
+
static const struct bpf_func_proto *
sk_filter_func_proto(enum bpf_func_id func_id)
{
@@ -1443,7 +1641,8 @@ sk_filter_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_trace_printk:
- return bpf_get_trace_printk_proto();
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
@@ -1461,6 +1660,20 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_l4_csum_replace_proto;
case BPF_FUNC_clone_redirect:
return &bpf_clone_redirect_proto;
+ case BPF_FUNC_get_cgroup_classid:
+ return &bpf_get_cgroup_classid_proto;
+ case BPF_FUNC_skb_vlan_push:
+ return &bpf_skb_vlan_push_proto;
+ case BPF_FUNC_skb_vlan_pop:
+ return &bpf_skb_vlan_pop_proto;
+ case BPF_FUNC_skb_get_tunnel_key:
+ return &bpf_skb_get_tunnel_key_proto;
+ case BPF_FUNC_skb_set_tunnel_key:
+ return bpf_get_skb_set_tunnel_key_proto();
+ case BPF_FUNC_redirect:
+ return &bpf_redirect_proto;
+ case BPF_FUNC_get_route_realm:
+ return &bpf_get_route_realm_proto;
default:
return sk_filter_func_proto(func_id);
}
@@ -1486,6 +1699,9 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type)
static bool sk_filter_is_valid_access(int off, int size,
enum bpf_access_type type)
{
+ if (off == offsetof(struct __sk_buff, tc_classid))
+ return false;
+
if (type == BPF_WRITE) {
switch (off) {
case offsetof(struct __sk_buff, cb[0]) ...
@@ -1502,10 +1718,14 @@ static bool sk_filter_is_valid_access(int off, int size,
static bool tc_cls_act_is_valid_access(int off, int size,
enum bpf_access_type type)
{
+ if (off == offsetof(struct __sk_buff, tc_classid))
+ return type == BPF_WRITE ? true : false;
+
if (type == BPF_WRITE) {
switch (off) {
case offsetof(struct __sk_buff, mark):
case offsetof(struct __sk_buff, tc_index):
+ case offsetof(struct __sk_buff, priority):
case offsetof(struct __sk_buff, cb[0]) ...
offsetof(struct __sk_buff, cb[4]):
break;
@@ -1518,7 +1738,8 @@ static bool tc_cls_act_is_valid_access(int off, int size,
static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
- struct bpf_insn *insn_buf)
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog)
{
struct bpf_insn *insn = insn_buf;
@@ -1547,8 +1768,12 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
case offsetof(struct __sk_buff, priority):
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);
- *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
- offsetof(struct sk_buff, priority));
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
break;
case offsetof(struct __sk_buff, ingress_ifindex):
@@ -1569,6 +1794,13 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
offsetof(struct net_device, ifindex));
break;
+ case offsetof(struct __sk_buff, hash):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, hash));
+ break;
+
case offsetof(struct __sk_buff, mark):
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
@@ -1598,6 +1830,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
offsetof(struct __sk_buff, cb[4]):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);
+ prog->cb_access = 1;
ctx_off -= offsetof(struct __sk_buff, cb[0]);
ctx_off += offsetof(struct sk_buff, cb);
ctx_off += offsetof(struct qdisc_skb_cb, data);
@@ -1607,6 +1840,14 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
break;
+ case offsetof(struct __sk_buff, tc_classid):
+ ctx_off -= offsetof(struct __sk_buff, tc_classid);
+ ctx_off += offsetof(struct sk_buff, cb);
+ ctx_off += offsetof(struct qdisc_skb_cb, tc_classid);
+ WARN_ON(type != BPF_WRITE);
+ *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off);
+ break;
+
case offsetof(struct __sk_buff, tc_index):
#ifdef CONFIG_NET_SCHED
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2);
@@ -1701,9 +1942,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
goto out;
/* We're copying the filter that has been originally attached,
- * so no conversion/decode needed anymore.
+ * so no conversion/decode needed anymore. eBPF programs that
+ * have no original program cannot be dumped through this.
*/
+ ret = -EACCES;
fprog = filter->prog->orig_prog;
+ if (!fprog)
+ goto out;
ret = fprog->len;
if (!len)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2a834c6179b9..d79699c9d1b9 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -19,14 +19,14 @@
#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>
-static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector,
- enum flow_dissector_key_id key_id)
+static bool dissector_uses_key(const struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id)
{
return flow_dissector->used_keys & (1 << key_id);
}
-static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector,
- enum flow_dissector_key_id key_id)
+static void dissector_set_key(struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id)
{
flow_dissector->used_keys |= (1 << key_id);
}
@@ -51,20 +51,20 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
* boundaries of unsigned short.
*/
BUG_ON(key->offset > USHRT_MAX);
- BUG_ON(skb_flow_dissector_uses_key(flow_dissector,
- key->key_id));
+ BUG_ON(dissector_uses_key(flow_dissector,
+ key->key_id));
- skb_flow_dissector_set_key(flow_dissector, key->key_id);
+ dissector_set_key(flow_dissector, key->key_id);
flow_dissector->offset[key->key_id] = key->offset;
}
/* Ensure that the dissector always includes control and basic key.
* That way we are able to avoid handling lack of these in fast path.
*/
- BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_CONTROL));
- BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_BASIC));
+ BUG_ON(!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_CONTROL));
+ BUG_ON(!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_BASIC));
}
EXPORT_SYMBOL(skb_flow_dissector_init);
@@ -121,7 +121,8 @@ EXPORT_SYMBOL(__skb_flow_get_ports);
bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container,
- void *data, __be16 proto, int nhoff, int hlen)
+ void *data, __be16 proto, int nhoff, int hlen,
+ unsigned int flags)
{
struct flow_dissector_key_control *key_control;
struct flow_dissector_key_basic *key_basic;
@@ -130,6 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_keyid *key_keyid;
u8 ip_proto = 0;
+ bool ret = false;
if (!data) {
data = skb->data;
@@ -152,8 +154,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct ethhdr *eth = eth_hdr(skb);
struct flow_dissector_key_eth_addrs *key_eth_addrs;
@@ -171,15 +173,13 @@ again:
ip:
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph || iph->ihl < 5)
- return false;
+ goto out_bad;
nhoff += iph->ihl * 4;
ip_proto = iph->protocol;
- if (ip_is_fragment(iph))
- ip_proto = 0;
- if (!skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS))
+ if (!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS))
break;
key_addrs = skb_flow_dissector_target(flow_dissector,
@@ -187,6 +187,22 @@ ip:
memcpy(&key_addrs->v4addrs, &iph->saddr,
sizeof(key_addrs->v4addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+
+ if (ip_is_fragment(iph)) {
+ key_control->flags |= FLOW_DIS_IS_FRAGMENT;
+
+ if (iph->frag_off & htons(IP_OFFSET)) {
+ goto out_good;
+ } else {
+ key_control->flags |= FLOW_DIS_FIRST_FRAG;
+ if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG))
+ goto out_good;
+ }
+ }
+
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_L3)
+ goto out_good;
+
break;
}
case htons(ETH_P_IPV6): {
@@ -197,13 +213,13 @@ ip:
ipv6:
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph)
- return false;
+ goto out_bad;
ip_proto = iph->nexthdr;
nhoff += sizeof(struct ipv6hdr);
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs;
key_ipv6_addrs = skb_flow_dissector_target(flow_dissector,
@@ -216,15 +232,20 @@ ipv6:
flow_label = ip6_flowlabel(iph);
if (flow_label) {
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
key_tags = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_FLOW_LABEL,
target_container);
key_tags->flow_label = ntohl(flow_label);
}
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)
+ goto out_good;
}
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_L3)
+ goto out_good;
+
break;
}
case htons(ETH_P_8021AD):
@@ -234,10 +255,10 @@ ipv6:
vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
if (!vlan)
- return false;
+ goto out_bad;
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_VLANID)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_VLANID)) {
key_tags = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_VLANID,
target_container);
@@ -256,7 +277,7 @@ ipv6:
} *hdr, _hdr;
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
- return false;
+ goto out_bad;
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
@@ -265,7 +286,7 @@ ipv6:
case htons(PPP_IPV6):
goto ipv6;
default:
- return false;
+ goto out_bad;
}
}
case htons(ETH_P_TIPC): {
@@ -275,19 +296,17 @@ ipv6:
} *hdr, _hdr;
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
- return false;
- key_basic->n_proto = proto;
- key_control->thoff = (u16)nhoff;
+ goto out_bad;
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_TIPC_ADDRS)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_TIPC_ADDRS)) {
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_TIPC_ADDRS,
target_container);
key_addrs->tipcaddrs.srcnode = hdr->srcnode;
key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS;
}
- return true;
+ goto out_good;
}
case htons(ETH_P_MPLS_UC):
@@ -297,12 +316,12 @@ mpls:
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
hlen, &_hdr);
if (!hdr)
- return false;
+ goto out_bad;
if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
key_keyid = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
target_container);
@@ -310,21 +329,17 @@ mpls:
htonl(MPLS_LS_LABEL_MASK);
}
- key_basic->n_proto = proto;
- key_basic->ip_proto = ip_proto;
- key_control->thoff = (u16)nhoff;
-
- return true;
+ goto out_good;
}
- return true;
+ goto out_good;
}
case htons(ETH_P_FCOE):
key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
/* fall through */
default:
- return false;
+ goto out_bad;
}
ip_proto_again:
@@ -337,7 +352,7 @@ ip_proto_again:
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
- return false;
+ goto out_bad;
/*
* Only look inside GRE if version zero and no
* routing
@@ -357,10 +372,10 @@ ip_proto_again:
data, hlen, &_keyid);
if (!keyid)
- return false;
+ goto out_bad;
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_GRE_KEYID)) {
key_keyid = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_GRE_KEYID,
target_container);
@@ -378,10 +393,15 @@ ip_proto_again:
sizeof(_eth),
data, hlen, &_eth);
if (!eth)
- return false;
+ goto out_bad;
proto = eth->h_proto;
nhoff += sizeof(*eth);
}
+
+ key_control->flags |= FLOW_DIS_ENCAPSULATION;
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ goto out_good;
+
goto again;
}
case NEXTHDR_HOP:
@@ -395,18 +415,53 @@ ip_proto_again:
opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr),
data, hlen, &_opthdr);
if (!opthdr)
- return false;
+ goto out_bad;
ip_proto = opthdr[0];
nhoff += (opthdr[1] + 1) << 3;
goto ip_proto_again;
}
+ case NEXTHDR_FRAGMENT: {
+ struct frag_hdr _fh, *fh;
+
+ if (proto != htons(ETH_P_IPV6))
+ break;
+
+ fh = __skb_header_pointer(skb, nhoff, sizeof(_fh),
+ data, hlen, &_fh);
+
+ if (!fh)
+ goto out_bad;
+
+ key_control->flags |= FLOW_DIS_IS_FRAGMENT;
+
+ nhoff += sizeof(_fh);
+
+ if (!(fh->frag_off & htons(IP6_OFFSET))) {
+ key_control->flags |= FLOW_DIS_FIRST_FRAG;
+ if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) {
+ ip_proto = fh->nexthdr;
+ goto ip_proto_again;
+ }
+ }
+ goto out_good;
+ }
case IPPROTO_IPIP:
proto = htons(ETH_P_IP);
+
+ key_control->flags |= FLOW_DIS_ENCAPSULATION;
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ goto out_good;
+
goto ip;
case IPPROTO_IPV6:
proto = htons(ETH_P_IPV6);
+
+ key_control->flags |= FLOW_DIS_ENCAPSULATION;
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ goto out_good;
+
goto ipv6;
case IPPROTO_MPLS:
proto = htons(ETH_P_MPLS_UC);
@@ -415,12 +470,8 @@ ip_proto_again:
break;
}
- key_basic->n_proto = proto;
- key_basic->ip_proto = ip_proto;
- key_control->thoff = (u16)nhoff;
-
- if (skb_flow_dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_PORTS)) {
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_PORTS)) {
key_ports = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_PORTS,
target_container);
@@ -428,7 +479,15 @@ ip_proto_again:
data, hlen);
}
- return true;
+out_good:
+ ret = true;
+
+out_bad:
+ key_basic->n_proto = proto;
+ key_basic->ip_proto = ip_proto;
+ key_control->thoff = (u16)nhoff;
+
+ return ret;
}
EXPORT_SYMBOL(__skb_flow_dissect);
@@ -438,18 +497,21 @@ static __always_inline void __flow_hash_secret_init(void)
net_get_random_once(&hashrnd, sizeof(hashrnd));
}
-static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval)
+static __always_inline u32 __flow_hash_words(const u32 *words, u32 length,
+ u32 keyval)
{
return jhash2(words, length, keyval);
}
-static inline void *flow_keys_hash_start(struct flow_keys *flow)
+static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow)
{
+ const void *p = flow;
+
BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
- return (void *)flow + FLOW_KEYS_HASH_OFFSET;
+ return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET);
}
-static inline size_t flow_keys_hash_length(struct flow_keys *flow)
+static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
{
size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
@@ -539,7 +601,7 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
__flow_hash_consistentify(keys);
- hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys),
+ hash = __flow_hash_words(flow_keys_hash_start(keys),
flow_keys_hash_length(keys), keyval);
if (!hash)
hash = 1;
@@ -557,8 +619,8 @@ EXPORT_SYMBOL(flow_hash_from_keys);
static inline u32 ___skb_get_hash(const struct sk_buff *skb,
struct flow_keys *keys, u32 keyval)
{
- if (!skb_flow_dissect_flow_keys(skb, keys))
- return 0;
+ skb_flow_dissect_flow_keys(skb, keys,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
return __flow_hash_from_keys(keys, keyval);
}
@@ -602,17 +664,11 @@ EXPORT_SYMBOL(make_flow_keys_digest);
void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
- u32 hash;
__flow_hash_secret_init();
- hash = ___skb_get_hash(skb, &keys, hashrnd);
- if (!hash)
- return;
- if (keys.ports.ports)
- skb->l4_hash = 1;
- skb->sw_hash = 1;
- skb->hash = hash;
+ __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd),
+ flow_keys_have_l4(&keys));
}
EXPORT_SYMBOL(__skb_get_hash);
@@ -624,6 +680,51 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
}
EXPORT_SYMBOL(skb_get_hash_perturb);
+__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6)
+{
+ struct flow_keys keys;
+
+ memset(&keys, 0, sizeof(keys));
+
+ memcpy(&keys.addrs.v6addrs.src, &fl6->saddr,
+ sizeof(keys.addrs.v6addrs.src));
+ memcpy(&keys.addrs.v6addrs.dst, &fl6->daddr,
+ sizeof(keys.addrs.v6addrs.dst));
+ keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+ keys.ports.src = fl6->fl6_sport;
+ keys.ports.dst = fl6->fl6_dport;
+ keys.keyid.keyid = fl6->fl6_gre_key;
+ keys.tags.flow_label = (__force u32)fl6->flowlabel;
+ keys.basic.ip_proto = fl6->flowi6_proto;
+
+ __skb_set_sw_hash(skb, flow_hash_from_keys(&keys),
+ flow_keys_have_l4(&keys));
+
+ return skb->hash;
+}
+EXPORT_SYMBOL(__skb_get_hash_flowi6);
+
+__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4)
+{
+ struct flow_keys keys;
+
+ memset(&keys, 0, sizeof(keys));
+
+ keys.addrs.v4addrs.src = fl4->saddr;
+ keys.addrs.v4addrs.dst = fl4->daddr;
+ keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+ keys.ports.src = fl4->fl4_sport;
+ keys.ports.dst = fl4->fl4_dport;
+ keys.keyid.keyid = fl4->fl4_gre_key;
+ keys.basic.ip_proto = fl4->flowi4_proto;
+
+ __skb_set_sw_hash(skb, flow_hash_from_keys(&keys),
+ flow_keys_have_l4(&keys));
+
+ return skb->hash;
+}
+EXPORT_SYMBOL(__skb_get_hash_flowi4);
+
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
const struct flow_keys *keys, int hlen)
{
@@ -683,12 +784,47 @@ u32 skb_get_poff(const struct sk_buff *skb)
{
struct flow_keys keys;
- if (!skb_flow_dissect_flow_keys(skb, &keys))
+ if (!skb_flow_dissect_flow_keys(skb, &keys, 0))
return 0;
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
}
+__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
+{
+ memset(keys, 0, sizeof(*keys));
+
+ memcpy(&keys->addrs.v6addrs.src, &fl6->saddr,
+ sizeof(keys->addrs.v6addrs.src));
+ memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr,
+ sizeof(keys->addrs.v6addrs.dst));
+ keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+ keys->ports.src = fl6->fl6_sport;
+ keys->ports.dst = fl6->fl6_dport;
+ keys->keyid.keyid = fl6->fl6_gre_key;
+ keys->tags.flow_label = (__force u32)fl6->flowlabel;
+ keys->basic.ip_proto = fl6->flowi6_proto;
+
+ return flow_hash_from_keys(keys);
+}
+EXPORT_SYMBOL(__get_hash_from_flowi6);
+
+__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys)
+{
+ memset(keys, 0, sizeof(*keys));
+
+ keys->addrs.v4addrs.src = fl4->saddr;
+ keys->addrs.v4addrs.dst = fl4->daddr;
+ keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+ keys->ports.src = fl4->fl4_sport;
+ keys->ports.dst = fl4->fl4_dport;
+ keys->keyid.keyid = fl4->fl4_gre_key;
+ keys->basic.ip_proto = fl4->flowi4_proto;
+
+ return flow_hash_from_keys(keys);
+}
+EXPORT_SYMBOL(__get_hash_from_flowi4);
+
static const struct flow_dissector_key flow_keys_dissector_keys[] = {
{
.key_id = FLOW_DISSECTOR_KEY_CONTROL,
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
new file mode 100644
index 000000000000..299cfc24d888
--- /dev/null
+++ b/net/core/lwtunnel.c
@@ -0,0 +1,249 @@
+/*
+ * lwtunnel Infrastructure for light weight tunnels like mpls
+ *
+ * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/lwtunnel.h>
+#include <linux/in.h>
+#include <linux/init.h>
+#include <linux/err.h>
+
+#include <net/lwtunnel.h>
+#include <net/rtnetlink.h>
+#include <net/ip6_fib.h>
+
+struct lwtunnel_state *lwtunnel_state_alloc(int encap_len)
+{
+ struct lwtunnel_state *lws;
+
+ lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC);
+
+ return lws;
+}
+EXPORT_SYMBOL(lwtunnel_state_alloc);
+
+static const struct lwtunnel_encap_ops __rcu *
+ lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly;
+
+int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops,
+ unsigned int num)
+{
+ if (num > LWTUNNEL_ENCAP_MAX)
+ return -ERANGE;
+
+ return !cmpxchg((const struct lwtunnel_encap_ops **)
+ &lwtun_encaps[num],
+ NULL, ops) ? 0 : -1;
+}
+EXPORT_SYMBOL(lwtunnel_encap_add_ops);
+
+int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops,
+ unsigned int encap_type)
+{
+ int ret;
+
+ if (encap_type == LWTUNNEL_ENCAP_NONE ||
+ encap_type > LWTUNNEL_ENCAP_MAX)
+ return -ERANGE;
+
+ ret = (cmpxchg((const struct lwtunnel_encap_ops **)
+ &lwtun_encaps[encap_type],
+ ops, NULL) == ops) ? 0 : -1;
+
+ synchronize_net();
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_encap_del_ops);
+
+int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
+ struct nlattr *encap, unsigned int family,
+ const void *cfg, struct lwtunnel_state **lws)
+{
+ const struct lwtunnel_encap_ops *ops;
+ int ret = -EINVAL;
+
+ if (encap_type == LWTUNNEL_ENCAP_NONE ||
+ encap_type > LWTUNNEL_ENCAP_MAX)
+ return ret;
+
+ ret = -EOPNOTSUPP;
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[encap_type]);
+ if (likely(ops && ops->build_state))
+ ret = ops->build_state(dev, encap, family, cfg, lws);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_build_state);
+
+int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
+{
+ const struct lwtunnel_encap_ops *ops;
+ struct nlattr *nest;
+ int ret = -EINVAL;
+
+ if (!lwtstate)
+ return 0;
+
+ if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
+ lwtstate->type > LWTUNNEL_ENCAP_MAX)
+ return 0;
+
+ ret = -EOPNOTSUPP;
+ nest = nla_nest_start(skb, RTA_ENCAP);
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
+ if (likely(ops && ops->fill_encap))
+ ret = ops->fill_encap(skb, lwtstate);
+ rcu_read_unlock();
+
+ if (ret)
+ goto nla_put_failure;
+ nla_nest_end(skb, nest);
+ ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type);
+ if (ret)
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+
+ return (ret == -EOPNOTSUPP ? 0 : ret);
+}
+EXPORT_SYMBOL(lwtunnel_fill_encap);
+
+int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate)
+{
+ const struct lwtunnel_encap_ops *ops;
+ int ret = 0;
+
+ if (!lwtstate)
+ return 0;
+
+ if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
+ lwtstate->type > LWTUNNEL_ENCAP_MAX)
+ return 0;
+
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
+ if (likely(ops && ops->get_encap_size))
+ ret = nla_total_size(ops->get_encap_size(lwtstate));
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_get_encap_size);
+
+int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+ const struct lwtunnel_encap_ops *ops;
+ int ret = 0;
+
+ if (!a && !b)
+ return 0;
+
+ if (!a || !b)
+ return 1;
+
+ if (a->type != b->type)
+ return 1;
+
+ if (a->type == LWTUNNEL_ENCAP_NONE ||
+ a->type > LWTUNNEL_ENCAP_MAX)
+ return 0;
+
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[a->type]);
+ if (likely(ops && ops->cmp_encap))
+ ret = ops->cmp_encap(a, b);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_cmp_encap);
+
+int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct lwtunnel_encap_ops *ops;
+ struct lwtunnel_state *lwtstate;
+ int ret = -EINVAL;
+
+ if (!dst)
+ goto drop;
+ lwtstate = dst->lwtstate;
+
+ if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
+ lwtstate->type > LWTUNNEL_ENCAP_MAX)
+ return 0;
+
+ ret = -EOPNOTSUPP;
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
+ if (likely(ops && ops->output))
+ ret = ops->output(net, sk, skb);
+ rcu_read_unlock();
+
+ if (ret == -EOPNOTSUPP)
+ goto drop;
+
+ return ret;
+
+drop:
+ kfree_skb(skb);
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_output);
+
+int lwtunnel_input(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct lwtunnel_encap_ops *ops;
+ struct lwtunnel_state *lwtstate;
+ int ret = -EINVAL;
+
+ if (!dst)
+ goto drop;
+ lwtstate = dst->lwtstate;
+
+ if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
+ lwtstate->type > LWTUNNEL_ENCAP_MAX)
+ return 0;
+
+ ret = -EOPNOTSUPP;
+ rcu_read_lock();
+ ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
+ if (likely(ops && ops->input))
+ ret = ops->input(skb);
+ rcu_read_unlock();
+
+ if (ret == -EOPNOTSUPP)
+ goto drop;
+
+ return ret;
+
+drop:
+ kfree_skb(skb);
+
+ return ret;
+}
+EXPORT_SYMBOL(lwtunnel_input);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 84195dacb8b6..1aa8437ed6c4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -274,8 +274,12 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
(entries >= tbl->gc_thresh2 &&
time_after(now, tbl->last_flush + 5 * HZ))) {
if (!neigh_forced_gc(tbl) &&
- entries >= tbl->gc_thresh3)
+ entries >= tbl->gc_thresh3) {
+ net_info_ratelimited("%s: neighbor table overflow!\n",
+ tbl->id);
+ NEIGH_CACHE_STAT_INC(tbl, table_fulls);
goto out_entries;
+ }
}
n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC);
@@ -1849,6 +1853,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast;
ndst.ndts_periodic_gc_runs += st->periodic_gc_runs;
ndst.ndts_forced_gc_runs += st->forced_gc_runs;
+ ndst.ndts_table_fulls += st->table_fulls;
}
if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst))
@@ -2230,14 +2235,53 @@ static void neigh_update_notify(struct neighbour *neigh)
__neigh_notify(neigh, RTM_NEWNEIGH, 0);
}
+static bool neigh_master_filtered(struct net_device *dev, int master_idx)
+{
+ struct net_device *master;
+
+ if (!master_idx)
+ return false;
+
+ master = netdev_master_upper_dev_get(dev);
+ if (!master || master->ifindex != master_idx)
+ return true;
+
+ return false;
+}
+
+static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx)
+{
+ if (filter_idx && dev->ifindex != filter_idx)
+ return true;
+
+ return false;
+}
+
static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
+ const struct nlmsghdr *nlh = cb->nlh;
+ struct nlattr *tb[NDA_MAX + 1];
struct neighbour *n;
int rc, h, s_h = cb->args[1];
int idx, s_idx = idx = cb->args[2];
struct neigh_hash_table *nht;
+ int filter_master_idx = 0, filter_idx = 0;
+ unsigned int flags = NLM_F_MULTI;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
+ if (!err) {
+ if (tb[NDA_IFINDEX])
+ filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
+
+ if (tb[NDA_MASTER])
+ filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
+
+ if (filter_idx || filter_master_idx)
+ flags |= NLM_F_DUMP_FILTERED;
+ }
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
@@ -2250,12 +2294,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
n = rcu_dereference_bh(n->next)) {
if (!net_eq(dev_net(n->dev), net))
continue;
+ if (neigh_ifindex_filtered(n->dev, filter_idx))
+ continue;
+ if (neigh_master_filtered(n->dev, filter_master_idx))
+ continue;
if (idx < s_idx)
goto next;
if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
- NLM_F_MULTI) < 0) {
+ flags) < 0) {
rc = -1;
goto out;
}
@@ -2717,12 +2765,12 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v)
struct neigh_statistics *st = v;
if (v == SEQ_START_TOKEN) {
- seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards\n");
+ seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n");
return 0;
}
seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx "
- "%08lx %08lx %08lx %08lx %08lx\n",
+ "%08lx %08lx %08lx %08lx %08lx %08lx\n",
atomic_read(&tbl->entries),
st->allocs,
@@ -2739,7 +2787,8 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v)
st->periodic_gc_runs,
st->forced_gc_runs,
- st->unres_discards
+ st->unres_discards,
+ st->table_fulls
);
return 0;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 18b34d771ed4..f88a62ab019d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -31,7 +31,6 @@
static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
-static const char fmt_udec[] = "%u\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
@@ -202,7 +201,7 @@ static ssize_t speed_show(struct device *dev,
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!__ethtool_get_settings(netdev, &cmd))
- ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
+ ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
return ret;
@@ -404,6 +403,19 @@ static ssize_t group_store(struct device *dev, struct device_attribute *attr,
NETDEVICE_SHOW(group, fmt_dec);
static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store);
+static int change_proto_down(struct net_device *dev, unsigned long proto_down)
+{
+ return dev_change_proto_down(dev, (bool) proto_down);
+}
+
+static ssize_t proto_down_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ return netdev_store(dev, attr, buf, len, change_proto_down);
+}
+NETDEVICE_SHOW_RW(proto_down, fmt_dec);
+
static ssize_t phys_port_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -459,7 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev,
if (dev_isalive(netdev)) {
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
@@ -501,6 +513,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_phys_port_id.attr,
&dev_attr_phys_port_name.attr,
&dev_attr_phys_switch_id.attr,
+ &dev_attr_proto_down.attr,
NULL,
};
ATTRIBUTE_GROUPS(net_class);
@@ -675,7 +688,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
struct rps_map *old_map, *map;
cpumask_var_t mask;
int err, cpu, i;
- static DEFINE_SPINLOCK(rps_map_lock);
+ static DEFINE_MUTEX(rps_map_mutex);
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -708,18 +721,21 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
map = NULL;
}
- spin_lock(&rps_map_lock);
+ mutex_lock(&rps_map_mutex);
old_map = rcu_dereference_protected(queue->rps_map,
- lockdep_is_held(&rps_map_lock));
+ mutex_is_locked(&rps_map_mutex));
rcu_assign_pointer(queue->rps_map, map);
- spin_unlock(&rps_map_lock);
if (map)
static_key_slow_inc(&rps_needed);
- if (old_map) {
- kfree_rcu(old_map, rcu);
+ if (old_map)
static_key_slow_dec(&rps_needed);
- }
+
+ mutex_unlock(&rps_map_mutex);
+
+ if (old_map)
+ kfree_rcu(old_map, rcu);
+
free_cpumask_var(mask);
return len;
}
@@ -987,15 +1003,12 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
}
#ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
- int i;
-
- for (i = 0; i < dev->num_tx_queues; i++)
- if (queue == &dev->_tx[i])
- break;
+ unsigned int i;
+ i = queue - dev->_tx;
BUG_ON(i >= dev->num_tx_queues);
return i;
@@ -1464,6 +1477,15 @@ static int of_dev_node_match(struct device *dev, const void *data)
return ret == 0 ? dev->of_node == data : ret;
}
+/*
+ * of_find_net_device_by_node - lookup the net device for the device node
+ * @np: OF device node
+ *
+ * Looks up the net_device structure corresponding with the device node.
+ * If successful, returns a pointer to the net_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped when done with the net_device.
+ */
struct net_device *of_find_net_device_by_node(struct device_node *np)
{
struct device *dev;
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index ba3c0120786c..adef015b2f41 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -31,6 +31,7 @@
#include <trace/events/napi.h>
#include <trace/events/sock.h>
#include <trace/events/udp.h>
+#include <trace/events/fib.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index c126a878c47c..94acfc89ad97 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -140,36 +140,42 @@ static void queue_process(struct work_struct *work)
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
*/
-static int poll_one_napi(struct napi_struct *napi, int budget)
+static void poll_one_napi(struct napi_struct *napi)
{
- int work;
+ int work = 0;
/* net_rx_action's ->poll() invocations and our's are
* synchronized by this test which is only made while
* holding the napi->poll_lock.
*/
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
- return budget;
+ return;
- set_bit(NAPI_STATE_NPSVC, &napi->state);
+ /* If we set this bit but see that it has already been set,
+ * that indicates that napi has been disabled and we need
+ * to abort this operation
+ */
+ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state))
+ return;
- work = napi->poll(napi, budget);
- WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
+ /* We explicilty pass the polling call a budget of 0 to
+ * indicate that we are clearing the Tx path only.
+ */
+ work = napi->poll(napi, 0);
+ WARN_ONCE(work, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
-
- return budget - work;
}
-static void poll_napi(struct net_device *dev, int budget)
+static void poll_napi(struct net_device *dev)
{
struct napi_struct *napi;
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(napi, budget);
+ poll_one_napi(napi);
spin_unlock(&napi->poll_lock);
}
}
@@ -179,7 +185,6 @@ static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
- int budget = 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
@@ -202,7 +207,7 @@ static void netpoll_poll_dev(struct net_device *dev)
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
- poll_napi(dev, budget);
+ poll_napi(dev);
up(&ni->dev_lock);
@@ -380,6 +385,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
static atomic_t ip_ident;
struct ipv6hdr *ip6h;
+ WARN_ON_ONCE(!irqs_disabled());
+
udp_len = len + sizeof(*udph);
if (np->ipv6)
ip_len = udp_len + sizeof(*ip6h);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 1cbd209192ea..de8d5cc5eb24 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -273,7 +273,6 @@ struct pktgen_dev {
/* runtime counters relating to clone_skb */
- __u64 allocated_skbs;
__u32 clone_count;
int last_ok; /* Was last skb sent?
* Or a failed transmit of some sort?
@@ -2279,7 +2278,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
{
- pkt_dev->pkt_overhead = 0;
+ pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev);
pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32);
pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev);
pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
@@ -2788,6 +2787,7 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
} else {
skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
}
+ skb_reserve(skb, LL_RESERVED_SPACE(dev));
return skb;
}
@@ -3397,7 +3397,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
return;
}
pkt_dev->last_pkt_size = pkt_dev->skb->len;
- pkt_dev->allocated_skbs++;
pkt_dev->clone_count = 0; /* reset counter */
}
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index 4eab4a94a59d..703cf76aa7c2 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -58,7 +58,7 @@
* jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these
* ldh [18] ; reload payload
* and #0xf ; mask PTP_CLASS_VMASK
- * or #0x70 ; PTP_CLASS_VLAN|PTP_CLASS_L2
+ * or #0xc0 ; PTP_CLASS_VLAN|PTP_CLASS_L2
* ret a ; return PTP class
*
* ; PTP over UDP over IPv4 over 802.1Q over Ethernet
@@ -73,7 +73,7 @@
* jneq #319, drop_8021q_ipv4 ; is port PTP_EV_PORT ?
* ldh [x + 26] ; load payload
* and #0xf ; mask PTP_CLASS_VMASK
- * or #0x50 ; PTP_CLASS_VLAN|PTP_CLASS_IPV4
+ * or #0x90 ; PTP_CLASS_VLAN|PTP_CLASS_IPV4
* ret a ; return PTP class
* drop_8021q_ipv4: ret #0x0 ; PTP_CLASS_NONE
*
@@ -86,7 +86,7 @@
* jneq #319, drop_8021q_ipv6 ; is port PTP_EV_PORT ?
* ldh [66] ; load payload
* and #0xf ; mask PTP_CLASS_VMASK
- * or #0x60 ; PTP_CLASS_VLAN|PTP_CLASS_IPV6
+ * or #0xa0 ; PTP_CLASS_VLAN|PTP_CLASS_IPV6
* ret a ; return PTP class
* drop_8021q_ipv6: ret #0x0 ; PTP_CLASS_NONE
*
@@ -98,7 +98,7 @@
* jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these
* ldh [14] ; reload payload
* and #0xf ; mask PTP_CLASS_VMASK
- * or #0x30 ; PTP_CLASS_L2
+ * or #0x40 ; PTP_CLASS_L2
* ret a ; return PTP class
* drop_ieee1588: ret #0x0 ; PTP_CLASS_NONE
*/
@@ -150,7 +150,7 @@ void __init ptp_classifier_init(void)
{ 0x15, 0, 35, 0x00000000 },
{ 0x28, 0, 0, 0x00000012 },
{ 0x54, 0, 0, 0x0000000f },
- { 0x44, 0, 0, 0x00000070 },
+ { 0x44, 0, 0, 0x000000c0 },
{ 0x16, 0, 0, 0x00000000 },
{ 0x15, 0, 12, 0x00000800 },
{ 0x30, 0, 0, 0x0000001b },
@@ -162,7 +162,7 @@ void __init ptp_classifier_init(void)
{ 0x15, 0, 4, 0x0000013f },
{ 0x48, 0, 0, 0x0000001a },
{ 0x54, 0, 0, 0x0000000f },
- { 0x44, 0, 0, 0x00000050 },
+ { 0x44, 0, 0, 0x00000090 },
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
{ 0x15, 0, 8, 0x000086dd },
@@ -172,7 +172,7 @@ void __init ptp_classifier_init(void)
{ 0x15, 0, 4, 0x0000013f },
{ 0x28, 0, 0, 0x00000042 },
{ 0x54, 0, 0, 0x0000000f },
- { 0x44, 0, 0, 0x00000060 },
+ { 0x44, 0, 0, 0x000000a0 },
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
{ 0x15, 0, 7, 0x000088f7 },
@@ -181,7 +181,7 @@ void __init ptp_classifier_init(void)
{ 0x15, 0, 4, 0x00000000 },
{ 0x28, 0, 0, 0x0000000e },
{ 0x54, 0, 0, 0x0000000f },
- { 0x44, 0, 0, 0x00000030 },
+ { 0x44, 0, 0, 0x00000040 },
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
};
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index b42f0e26f89e..5d26056b6d8f 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -37,90 +37,16 @@
int sysctl_max_syn_backlog = 256;
EXPORT_SYMBOL(sysctl_max_syn_backlog);
-int reqsk_queue_alloc(struct request_sock_queue *queue,
- unsigned int nr_table_entries)
+void reqsk_queue_alloc(struct request_sock_queue *queue)
{
- size_t lopt_size = sizeof(struct listen_sock);
- struct listen_sock *lopt = NULL;
+ spin_lock_init(&queue->rskq_lock);
- nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog);
- nr_table_entries = max_t(u32, nr_table_entries, 8);
- nr_table_entries = roundup_pow_of_two(nr_table_entries + 1);
- lopt_size += nr_table_entries * sizeof(struct request_sock *);
+ spin_lock_init(&queue->fastopenq.lock);
+ queue->fastopenq.rskq_rst_head = NULL;
+ queue->fastopenq.rskq_rst_tail = NULL;
+ queue->fastopenq.qlen = 0;
- if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
- lopt = kzalloc(lopt_size, GFP_KERNEL |
- __GFP_NOWARN |
- __GFP_NORETRY);
- if (!lopt)
- lopt = vzalloc(lopt_size);
- if (!lopt)
- return -ENOMEM;
-
- get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
- spin_lock_init(&queue->syn_wait_lock);
queue->rskq_accept_head = NULL;
- lopt->nr_table_entries = nr_table_entries;
- lopt->max_qlen_log = ilog2(nr_table_entries);
-
- spin_lock_bh(&queue->syn_wait_lock);
- queue->listen_opt = lopt;
- spin_unlock_bh(&queue->syn_wait_lock);
-
- return 0;
-}
-
-void __reqsk_queue_destroy(struct request_sock_queue *queue)
-{
- /* This is an error recovery path only, no locking needed */
- kvfree(queue->listen_opt);
-}
-
-static inline struct listen_sock *reqsk_queue_yank_listen_sk(
- struct request_sock_queue *queue)
-{
- struct listen_sock *lopt;
-
- spin_lock_bh(&queue->syn_wait_lock);
- lopt = queue->listen_opt;
- queue->listen_opt = NULL;
- spin_unlock_bh(&queue->syn_wait_lock);
-
- return lopt;
-}
-
-void reqsk_queue_destroy(struct request_sock_queue *queue)
-{
- /* make all the listen_opt local to us */
- struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
-
- if (listen_sock_qlen(lopt) != 0) {
- unsigned int i;
-
- for (i = 0; i < lopt->nr_table_entries; i++) {
- struct request_sock *req;
-
- spin_lock_bh(&queue->syn_wait_lock);
- while ((req = lopt->syn_table[i]) != NULL) {
- lopt->syn_table[i] = req->dl_next;
- /* Because of following del_timer_sync(),
- * we must release the spinlock here
- * or risk a dead lock.
- */
- spin_unlock_bh(&queue->syn_wait_lock);
- atomic_inc(&lopt->qlen_dec);
- if (del_timer_sync(&req->rsk_timer))
- reqsk_put(req);
- reqsk_put(req);
- spin_lock_bh(&queue->syn_wait_lock);
- }
- spin_unlock_bh(&queue->syn_wait_lock);
- }
- }
-
- if (WARN_ON(listen_sock_qlen(lopt) != 0))
- pr_err("qlen %u\n", listen_sock_qlen(lopt));
- kvfree(lopt);
}
/*
@@ -174,7 +100,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
struct sock *lsk = req->rsk_listener;
struct fastopen_queue *fastopenq;
- fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq;
+ fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
tcp_sk(sk)->fastopen_rsk = NULL;
spin_lock_bh(&fastopenq->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dc004b1e1f85..504bd17b7456 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -96,7 +96,7 @@ int rtnl_is_locked(void)
EXPORT_SYMBOL(rtnl_is_locked);
#ifdef CONFIG_PROVE_LOCKING
-int lockdep_rtnl_is_held(void)
+bool lockdep_rtnl_is_held(void)
{
return lockdep_is_held(&rtnl_mutex);
}
@@ -497,7 +497,8 @@ void rtnl_af_unregister(struct rtnl_af_ops *ops)
}
EXPORT_SYMBOL_GPL(rtnl_af_unregister);
-static size_t rtnl_link_get_af_size(const struct net_device *dev)
+static size_t rtnl_link_get_af_size(const struct net_device *dev,
+ u32 ext_filter_mask)
{
struct rtnl_af_ops *af_ops;
size_t size;
@@ -509,7 +510,7 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev)
if (af_ops->get_link_af_size) {
/* AF_* + nested data */
size += nla_total_size(sizeof(struct nlattr)) +
- af_ops->get_link_af_size(dev);
+ af_ops->get_link_af_size(dev, ext_filter_mask);
}
}
@@ -678,6 +679,12 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
continue;
if (nla_put_string(skb, i + 1, name))
goto nla_put_failure;
+ } else if (i == RTAX_FEATURES - 1) {
+ u32 user_features = metrics[i] & RTAX_FEATURE_MASK;
+
+ BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK);
+ if (nla_put_u32(skb, i + 1, user_features))
+ goto nla_put_failure;
} else {
if (nla_put_u32(skb, i + 1, metrics[i]))
goto nla_put_failure;
@@ -831,7 +838,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
/* IFLA_VF_STATS_BROADCAST */
nla_total_size(sizeof(__u64)) +
/* IFLA_VF_STATS_MULTICAST */
- nla_total_size(sizeof(__u64)));
+ nla_total_size(sizeof(__u64)) +
+ nla_total_size(sizeof(struct ifla_vf_trust)));
return size;
} else
return 0;
@@ -894,9 +902,11 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
+ rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
- + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
+ + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
+ nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
- + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+ + nla_total_size(1); /* IFLA_PROTO_DOWN */
+
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1017,7 +1027,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
@@ -1082,7 +1092,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
(dev->ifalias &&
nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
nla_put_u32(skb, IFLA_CARRIER_CHANGES,
- atomic_read(&dev->carrier_changes)))
+ atomic_read(&dev->carrier_changes)) ||
+ nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
goto nla_put_failure;
if (1) {
@@ -1151,6 +1162,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_link_state vf_linkstate;
struct ifla_vf_rss_query_en vf_rss_query_en;
struct ifla_vf_stats vf_stats;
+ struct ifla_vf_trust vf_trust;
/*
* Not all SR-IOV capable drivers support the
@@ -1160,6 +1172,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
*/
ivi.spoofchk = -1;
ivi.rss_query_en = -1;
+ ivi.trusted = -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
@@ -1173,7 +1186,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
vf_tx_rate.vf =
vf_spoofchk.vf =
vf_linkstate.vf =
- vf_rss_query_en.vf = ivi.vf;
+ vf_rss_query_en.vf =
+ vf_trust.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
@@ -1184,6 +1198,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
vf_spoofchk.setting = ivi.spoofchk;
vf_linkstate.link_state = ivi.linkstate;
vf_rss_query_en.setting = ivi.rss_query_en;
+ vf_trust.setting = ivi.trusted;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
@@ -1201,7 +1216,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
&vf_linkstate) ||
nla_put(skb, IFLA_VF_RSS_QUERY_EN,
sizeof(vf_rss_query_en),
- &vf_rss_query_en))
+ &vf_rss_query_en) ||
+ nla_put(skb, IFLA_VF_TRUST,
+ sizeof(vf_trust), &vf_trust))
goto nla_put_failure;
memset(&vf_stats, 0, sizeof(vf_stats));
if (dev->netdev_ops->ndo_get_vf_stats)
@@ -1263,7 +1280,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (!(af = nla_nest_start(skb, af_ops->family)))
goto nla_put_failure;
- err = af_ops->fill_link_af(skb, dev);
+ err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
/*
* Caller may return ENODATA to indicate that there
@@ -1319,6 +1336,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
[IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_LINK_NETNSID] = { .type = NLA_S32 },
+ [IFLA_PROTO_DOWN] = { .type = NLA_U8 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1337,6 +1355,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
[IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) },
[IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) },
[IFLA_VF_STATS] = { .type = NLA_NESTED },
+ [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) },
};
static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = {
@@ -1576,6 +1595,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
return err;
}
+ if (tb[IFLA_VF_TRUST]) {
+ struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_trust)
+ err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
+ if (err < 0)
+ return err;
+ }
+
return err;
}
@@ -1861,6 +1890,14 @@ static int do_setlink(const struct sk_buff *skb,
}
err = 0;
+ if (tb[IFLA_PROTO_DOWN]) {
+ err = dev_change_proto_down(dev,
+ nla_get_u8(tb[IFLA_PROTO_DOWN]));
+ if (err)
+ goto errout;
+ status |= DO_SETLINK_NOTIFY;
+ }
+
errout:
if (status & DO_SETLINK_MODIFIED) {
if (status & DO_SETLINK_NOTIFY)
@@ -1951,16 +1988,30 @@ static int rtnl_group_dellink(const struct net *net, int group)
return 0;
}
+int rtnl_delete_link(struct net_device *dev)
+{
+ const struct rtnl_link_ops *ops;
+ LIST_HEAD(list_kill);
+
+ ops = dev->rtnl_link_ops;
+ if (!ops || !ops->dellink)
+ return -EOPNOTSUPP;
+
+ ops->dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rtnl_delete_link);
+
static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
- const struct rtnl_link_ops *ops;
struct net_device *dev;
struct ifinfomsg *ifm;
char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
int err;
- LIST_HEAD(list_kill);
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
if (err < 0)
@@ -1982,13 +2033,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
if (!dev)
return -ENODEV;
- ops = dev->rtnl_link_ops;
- if (!ops || !ops->dellink)
- return -EOPNOTSUPP;
-
- ops->dellink(dev, &list_kill);
- unregister_netdevice_many(&list_kill);
- return 0;
+ return rtnl_delete_link(dev);
}
int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
@@ -3021,6 +3066,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
u32 portid = NETLINK_CB(cb->skb).portid;
u32 seq = cb->nlh->nlmsg_seq;
u32 filter_mask = 0;
+ int err;
if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
struct nlattr *extfilt;
@@ -3041,20 +3087,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
- if (idx >= cb->args[0] &&
- br_dev->netdev_ops->ndo_bridge_getlink(
- skb, portid, seq, dev, filter_mask,
- NLM_F_MULTI) < 0)
- break;
+ if (idx >= cb->args[0]) {
+ err = br_dev->netdev_ops->ndo_bridge_getlink(
+ skb, portid, seq, dev,
+ filter_mask, NLM_F_MULTI);
+ if (err < 0 && err != -EOPNOTSUPP)
+ break;
+ }
idx++;
}
if (ops->ndo_bridge_getlink) {
- if (idx >= cb->args[0] &&
- ops->ndo_bridge_getlink(skb, portid, seq, dev,
- filter_mask,
- NLM_F_MULTI) < 0)
- break;
+ if (idx >= cb->args[0]) {
+ err = ops->ndo_bridge_getlink(skb, portid,
+ seq, dev,
+ filter_mask,
+ NLM_F_MULTI);
+ if (err < 0 && err != -EOPNOTSUPP)
+ break;
+ }
idx++;
}
}
@@ -3411,4 +3462,3 @@ void __init rtnetlink_init(void)
rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL);
rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL);
}
-
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b84330e5d30..fab4599ba8b2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -392,7 +392,7 @@ EXPORT_SYMBOL(napi_alloc_frag);
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
- * @length: length to allocate
+ * @len: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
*
* Allocate a new &sk_buff and assign it a usage count of one. The
@@ -461,7 +461,7 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
/**
* __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
* @napi: napi instance this buffer was allocated for
- * @length: length to allocate
+ * @len: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
*
* Allocate a new sk_buff for use in NAPI receive. This buffer will
@@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags);
*/
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
+ unsigned char *data = skb->data;
+
BUG_ON(len > skb->len);
- skb->len -= len;
- BUG_ON(skb->len < skb->data_len);
- skb_postpull_rcsum(skb, skb->data, len);
- return skb->data += len;
+ __skb_pull(skb, len);
+ skb_postpull_rcsum(skb, data, len);
+ return skb->data;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
diff --git a/net/core/sock.c b/net/core/sock.c
index 193901d09757..7529eb9463be 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -422,13 +422,25 @@ static void sock_warn_obsolete_bsdism(const char *name)
}
}
+static bool sock_needs_netstamp(const struct sock *sk)
+{
+ switch (sk->sk_family) {
+ case AF_UNSPEC:
+ case AF_UNIX:
+ return false;
+ default:
+ return true;
+ }
+}
+
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
sk->sk_flags &= ~flags;
- if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
+ if (sock_needs_netstamp(sk) &&
+ !(sk->sk_flags & SK_FLAGS_TIMESTAMP))
net_disable_timestamp();
}
}
@@ -988,6 +1000,10 @@ set_rcvbuf:
sk->sk_max_pacing_rate);
break;
+ case SO_INCOMING_CPU:
+ sk->sk_incoming_cpu = val;
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1578,7 +1594,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
if (newsk->sk_prot->sockets_allocated)
sk_sockets_allocated_inc(newsk);
- if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+ if (sock_needs_netstamp(sk) &&
+ newsk->sk_flags & SK_FLAGS_TIMESTAMP)
net_enable_timestamp();
}
out:
@@ -1639,6 +1656,28 @@ void sock_wfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_wfree);
+void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
+{
+ skb_orphan(skb);
+ skb->sk = sk;
+#ifdef CONFIG_INET
+ if (unlikely(!sk_fullsock(sk))) {
+ skb->destructor = sock_edemux;
+ sock_hold(sk);
+ return;
+ }
+#endif
+ skb->destructor = sock_wfree;
+ skb_set_hash_from_sk(skb, sk);
+ /*
+ * We used to take a refcount on sk, but following operation
+ * is enough to guarantee sk_free() wont free this sock until
+ * all in-flight packets are completed
+ */
+ atomic_add(skb->truesize, &sk->sk_wmem_alloc);
+}
+EXPORT_SYMBOL(skb_set_owner_w);
+
void skb_orphan_partial(struct sk_buff *skb)
{
/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
@@ -1852,6 +1891,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
}
EXPORT_SYMBOL(sock_alloc_send_skb);
+int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
+ struct sockcm_cookie *sockc)
+{
+ struct cmsghdr *cmsg;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+ if (cmsg->cmsg_level != SOL_SOCKET)
+ continue;
+ switch (cmsg->cmsg_type) {
+ case SO_MARK:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ sockc->mark = *(u32 *)CMSG_DATA(cmsg);
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL(sock_cmsg_send);
+
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
@@ -2078,7 +2143,7 @@ suppress_allocation:
EXPORT_SYMBOL(__sk_mem_schedule);
/**
- * __sk_reclaim - reclaim memory_allocated
+ * __sk_mem_reclaim - reclaim memory_allocated
* @sk: socket
* @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
*/
@@ -2353,6 +2418,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
+ sk->sk_incoming_cpu = -1;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -2479,7 +2545,8 @@ void sock_enable_timestamp(struct sock *sk, int flag)
* time stamping, but time stamping might have been on
* already because of the other one
*/
- if (!(previous_flags & SK_FLAGS_TIMESTAMP))
+ if (sock_needs_netstamp(sk) &&
+ !(previous_flags & SK_FLAGS_TIMESTAMP))
net_enable_timestamp();
}
}
@@ -2740,10 +2807,8 @@ static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
return;
kfree(rsk_prot->slab_name);
rsk_prot->slab_name = NULL;
- if (rsk_prot->slab) {
- kmem_cache_destroy(rsk_prot->slab);
- rsk_prot->slab = NULL;
- }
+ kmem_cache_destroy(rsk_prot->slab);
+ rsk_prot->slab = NULL;
}
static int req_prot_init(const struct proto *prot)
@@ -2760,7 +2825,7 @@ static int req_prot_init(const struct proto *prot)
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- 0, NULL);
+ prot->slab_flags, NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -2828,10 +2893,8 @@ void proto_unregister(struct proto *prot)
list_del(&prot->node);
mutex_unlock(&proto_list_mutex);
- if (prot->slab != NULL) {
- kmem_cache_destroy(prot->slab);
- prot->slab = NULL;
- }
+ kmem_cache_destroy(prot->slab);
+ prot->slab = NULL;
req_prot_cleanup(prot->rsk_prot);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index d79866c5f8bc..0c1d58d43f67 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -1,3 +1,5 @@
+/* License: GPL */
+
#include <linux/mutex.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
@@ -90,6 +92,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
goto out;
fprog = filter->prog->orig_prog;
+ if (!fprog)
+ goto out;
+
flen = bpf_classic_proglen(fprog);
attr = nla_reserve(skb, attrtype, flen);
@@ -320,14 +325,4 @@ static int __init sock_diag_init(void)
BUG_ON(!broadcast_wq);
return register_pernet_subsys(&diag_net_ops);
}
-
-static void __exit sock_diag_exit(void)
-{
- unregister_pernet_subsys(&diag_net_ops);
- destroy_workqueue(broadcast_wq);
-}
-
-module_init(sock_diag_init);
-module_exit(sock_diag_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);
+device_initcall(sock_diag_init);
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 43d3dd62fcc8..42689d5c468c 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -60,11 +60,15 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
struct phy_device *phydev;
unsigned int type;
+ if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv)
+ return false;
+
if (skb_headroom(skb) < ETH_HLEN)
return false;
+
__skb_push(skb, ETH_HLEN);
- type = classify(skb);
+ type = ptp_classify_raw(skb);
__skb_pull(skb, ETH_HLEN);
diff --git a/net/core/tso.c b/net/core/tso.c
index 630b30b4fb53..5dca7ce8ee9f 100644
--- a/net/core/tso.c
+++ b/net/core/tso.c
@@ -1,4 +1,5 @@
#include <linux/export.h>
+#include <linux/if_vlan.h>
#include <net/ip.h>
#include <net/tso.h>
#include <asm/unaligned.h>
@@ -14,18 +15,24 @@ EXPORT_SYMBOL(tso_count_descs);
void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
int size, bool is_last)
{
- struct iphdr *iph;
struct tcphdr *tcph;
int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
int mac_hdr_len = skb_network_offset(skb);
memcpy(hdr, skb->data, hdr_len);
- iph = (struct iphdr *)(hdr + mac_hdr_len);
- iph->id = htons(tso->ip_id);
- iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+ if (!tso->ipv6) {
+ struct iphdr *iph = (void *)(hdr + mac_hdr_len);
+
+ iph->id = htons(tso->ip_id);
+ iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+ tso->ip_id++;
+ } else {
+ struct ipv6hdr *iph = (void *)(hdr + mac_hdr_len);
+
+ iph->payload_len = htons(size + tcp_hdrlen(skb));
+ }
tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
put_unaligned_be32(tso->tcp_seq, &tcph->seq);
- tso->ip_id++;
if (!is_last) {
/* Clear all special flags for not last packet */
@@ -61,6 +68,7 @@ void tso_start(struct sk_buff *skb, struct tso_t *tso)
tso->ip_id = ntohs(ip_hdr(skb)->id);
tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
tso->next_frag_idx = 0;
+ tso->ipv6 = vlan_get_protocol(skb) == htons(ETH_P_IPV6);
/* Build first data */
tso->size = skb_headlen(skb) - hdr_len;
diff --git a/net/core/utils.c b/net/core/utils.c
index a7732a068043..3d17ca8b4744 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -301,7 +301,7 @@ out:
EXPORT_SYMBOL(in6_pton);
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
- __be32 from, __be32 to, int pseudohdr)
+ __be32 from, __be32 to, bool pseudohdr)
{
if (skb->ip_summed != CHECKSUM_PARTIAL) {
csum_replace4(sum, from, to);
@@ -318,7 +318,7 @@ EXPORT_SYMBOL(inet_proto_csum_replace4);
void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
const __be32 *from, const __be32 *to,
- int pseudohdr)
+ bool pseudohdr)
{
__be32 diff[] = {
~from[0], ~from[1], ~from[2], ~from[3],
@@ -336,51 +336,15 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
}
EXPORT_SYMBOL(inet_proto_csum_replace16);
-struct __net_random_once_work {
- struct work_struct work;
- struct static_key *key;
-};
-
-static void __net_random_once_deferred(struct work_struct *w)
-{
- struct __net_random_once_work *work =
- container_of(w, struct __net_random_once_work, work);
- BUG_ON(!static_key_enabled(work->key));
- static_key_slow_dec(work->key);
- kfree(work);
-}
-
-static void __net_random_once_disable_jump(struct static_key *key)
+void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
+ __wsum diff, bool pseudohdr)
{
- struct __net_random_once_work *w;
-
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (!w)
- return;
-
- INIT_WORK(&w->work, __net_random_once_deferred);
- w->key = key;
- schedule_work(&w->work);
-}
-
-bool __net_get_random_once(void *buf, int nbytes, bool *done,
- struct static_key *once_key)
-{
- static DEFINE_SPINLOCK(lock);
- unsigned long flags;
-
- spin_lock_irqsave(&lock, flags);
- if (*done) {
- spin_unlock_irqrestore(&lock, flags);
- return false;
+ if (skb->ip_summed != CHECKSUM_PARTIAL) {
+ *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum)));
+ if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
+ skb->csum = ~csum_add(diff, ~skb->csum);
+ } else if (pseudohdr) {
+ *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum)));
}
-
- get_random_bytes(buf, nbytes);
- *done = true;
- spin_unlock_irqrestore(&lock, flags);
-
- __net_random_once_disable_jump(once_key);
-
- return true;
}
-EXPORT_SYMBOL(__net_get_random_once);
+EXPORT_SYMBOL(inet_proto_csum_replace_by_diff);
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-31 10:49:27 +0000