aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c222
-rw-r--r--net/core/dev_ioctl.c13
-rw-r--r--net/core/dst.c16
-rw-r--r--net/core/ethtool.c21
-rw-r--r--net/core/fib_rules.c9
-rw-r--r--net/core/filter.c453
-rw-r--r--net/core/flow_dissector.c100
-rw-r--r--net/core/lwt_bpf.c2
-rw-r--r--net/core/neighbour.c18
-rw-r--r--net/core/net-sysfs.c17
-rw-r--r--net/core/net-traces.c3
-rw-r--r--net/core/rtnetlink.c371
-rw-r--r--net/core/skbuff.c63
-rw-r--r--net/core/sock.c17
-rw-r--r--net/core/sock_reuseport.c12
16 files changed, 1004 insertions, 335 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f7fb7e3f2acf..0b7b4c22719e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -188,7 +188,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
}
if (!skb->len) {
skb = skb_set_peeked(skb);
- if (unlikely(IS_ERR(skb))) {
+ if (IS_ERR(skb)) {
*err = PTR_ERR(skb);
return NULL;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 97abddd9039a..24ac9083bc13 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
#include <linux/crash_dump.h>
#include <linux/sctp.h>
#include <net/udp_tunnel.h>
+#include <linux/net_namespace.h>
#include "net-sysfs.h"
@@ -162,7 +163,6 @@ static struct list_head offload_base __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
- struct net_device *dev,
struct netdev_notifier_info *info);
static struct napi_struct *napi_by_id(unsigned int napi_id);
@@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id);
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+static DEFINE_MUTEX(ifalias_mutex);
+
/* protects napi_hash addition/deletion and napi_gen_id */
static DEFINE_SPINLOCK(napi_hash_lock);
@@ -1147,9 +1149,8 @@ static int dev_alloc_name_ns(struct net *net,
return ret;
}
-static int dev_get_valid_name(struct net *net,
- struct net_device *dev,
- const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+ const char *name)
{
BUG_ON(!net);
@@ -1165,6 +1166,7 @@ static int dev_get_valid_name(struct net *net,
return 0;
}
+EXPORT_SYMBOL(dev_get_valid_name);
/**
* dev_change_name - change name of a device
@@ -1265,29 +1267,53 @@ rollback:
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
- char *new_ifalias;
-
- ASSERT_RTNL();
+ struct dev_ifalias *new_alias = NULL;
if (len >= IFALIASZ)
return -EINVAL;
- if (!len) {
- kfree(dev->ifalias);
- dev->ifalias = NULL;
- return 0;
+ if (len) {
+ new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
+ if (!new_alias)
+ return -ENOMEM;
+
+ memcpy(new_alias->ifalias, alias, len);
+ new_alias->ifalias[len] = 0;
}
- new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
- if (!new_ifalias)
- return -ENOMEM;
- dev->ifalias = new_ifalias;
- memcpy(dev->ifalias, alias, len);
- dev->ifalias[len] = 0;
+ mutex_lock(&ifalias_mutex);
+ rcu_swap_protected(dev->ifalias, new_alias,
+ mutex_is_locked(&ifalias_mutex));
+ mutex_unlock(&ifalias_mutex);
+
+ if (new_alias)
+ kfree_rcu(new_alias, rcuhead);
return len;
}
+/**
+ * dev_get_alias - get ifalias of a device
+ * @dev: device
+ * @name: buffer to store name of ifalias
+ * @len: size of buffer
+ *
+ * get ifalias for a device. Caller must make sure dev cannot go
+ * away, e.g. rcu read lock or own a reference count to device.
+ */
+int dev_get_alias(const struct net_device *dev, char *name, size_t len)
+{
+ const struct dev_ifalias *alias;
+ int ret = 0;
+
+ rcu_read_lock();
+ alias = rcu_dereference(dev->ifalias);
+ if (alias)
+ ret = snprintf(name, len, "%s", alias->ifalias);
+ rcu_read_unlock();
+
+ return ret;
+}
/**
* netdev_features_change - device changes features
@@ -1312,10 +1338,11 @@ EXPORT_SYMBOL(netdev_features_change);
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
- struct netdev_notifier_change_info change_info;
+ struct netdev_notifier_change_info change_info = {
+ .info.dev = dev,
+ };
- change_info.flags_changed = 0;
- call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGE,
&change_info.info);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
}
@@ -1536,9 +1563,10 @@ EXPORT_SYMBOL(dev_disable_lro);
static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
struct net_device *dev)
{
- struct netdev_notifier_info info;
+ struct netdev_notifier_info info = {
+ .dev = dev,
+ };
- netdev_notifier_info_init(&info, dev);
return nb->notifier_call(nb, val, &info);
}
@@ -1663,11 +1691,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
*/
static int call_netdevice_notifiers_info(unsigned long val,
- struct net_device *dev,
struct netdev_notifier_info *info)
{
ASSERT_RTNL();
- netdev_notifier_info_init(info, dev);
return raw_notifier_call_chain(&netdev_chain, val, info);
}
@@ -1682,9 +1708,11 @@ static int call_netdevice_notifiers_info(unsigned long val,
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- struct netdev_notifier_info info;
+ struct netdev_notifier_info info = {
+ .dev = dev,
+ };
- return call_netdevice_notifiers_info(val, dev, &info);
+ return call_netdevice_notifiers_info(val, &info);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
@@ -2012,6 +2040,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
return 0;
}
+EXPORT_SYMBOL(netdev_txq_to_tc);
#ifdef CONFIG_XPS
static DEFINE_MUTEX(xps_map_mutex);
@@ -3864,8 +3893,8 @@ drop:
static u32 netif_receive_generic_xdp(struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
+ u32 metalen, act = XDP_DROP;
struct xdp_buff xdp;
- u32 act = XDP_DROP;
void *orig_data;
int hlen, off;
u32 mac_len;
@@ -3876,8 +3905,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
if (skb_cloned(skb))
return XDP_PASS;
- if (skb_linearize(skb))
- goto do_drop;
+ /* XDP packets must be linear and must have sufficient headroom
+ * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+ * native XDP provides, thus we need to do it here as well.
+ */
+ if (skb_is_nonlinear(skb) ||
+ skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+ int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+ int troom = skb->tail + skb->data_len - skb->end;
+
+ /* In case we have to go down the path and also linearize,
+ * then lets do the pskb_expand_head() work just once here.
+ */
+ if (pskb_expand_head(skb,
+ hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+ troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+ goto do_drop;
+ if (troom > 0 && __skb_linearize(skb))
+ goto do_drop;
+ }
/* The XDP program wants to see the packet starting at the MAC
* header.
@@ -3885,6 +3931,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
mac_len = skb->data - skb_mac_header(skb);
hlen = skb_headlen(skb) + mac_len;
xdp.data = skb->data - mac_len;
+ xdp.data_meta = xdp.data;
xdp.data_end = xdp.data + hlen;
xdp.data_hard_start = skb->data - skb_headroom(skb);
orig_data = xdp.data;
@@ -3902,10 +3949,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
case XDP_REDIRECT:
case XDP_TX:
__skb_push(skb, mac_len);
- /* fall through */
+ break;
case XDP_PASS:
+ metalen = xdp.data - xdp.data_meta;
+ if (metalen)
+ skb_metadata_set(skb, metalen);
break;
-
default:
bpf_warn_invalid_xdp_action(act);
/* fall through */
@@ -4443,6 +4492,33 @@ out:
return ret;
}
+/**
+ * netif_receive_skb_core - special purpose version of netif_receive_skb
+ * @skb: buffer to process
+ *
+ * More direct receive version of netif_receive_skb(). It should
+ * only be used by callers that have a need to skip RPS and Generic XDP.
+ * Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+ int ret;
+
+ rcu_read_lock();
+ ret = __netif_receive_skb_core(skb, false);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
@@ -4695,6 +4771,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
diffs |= skb_metadata_dst_cmp(p, skb);
+ diffs |= skb_metadata_differs(p, skb);
if (maclen == ETH_HLEN)
diffs |= compare_ether_header(skb_mac_header(p),
skb_mac_header(skb));
@@ -6228,9 +6305,19 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
- void *upper_priv, void *upper_info)
-{
- struct netdev_notifier_changeupper_info changeupper_info;
+ void *upper_priv, void *upper_info,
+ struct netlink_ext_ack *extack)
+{
+ struct netdev_notifier_changeupper_info changeupper_info = {
+ .info = {
+ .dev = dev,
+ .extack = extack,
+ },
+ .upper_dev = upper_dev,
+ .master = master,
+ .linking = true,
+ .upper_info = upper_info,
+ };
int ret = 0;
ASSERT_RTNL();
@@ -6248,12 +6335,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (master && netdev_master_upper_dev_get(dev))
return -EBUSY;
- changeupper_info.upper_dev = upper_dev;
- changeupper_info.master = master;
- changeupper_info.linking = true;
- changeupper_info.upper_info = upper_info;
-
- ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
@@ -6264,7 +6346,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
return ret;
- ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
@@ -6289,9 +6371,11 @@ rollback:
* returns zero.
*/
int netdev_upper_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+ struct net_device *upper_dev,
+ struct netlink_ext_ack *extack)
{
- return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
+ return __netdev_upper_dev_link(dev, upper_dev, false,
+ NULL, NULL, extack);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
@@ -6310,10 +6394,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
*/
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
- void *upper_priv, void *upper_info)
+ void *upper_priv, void *upper_info,
+ struct netlink_ext_ack *extack)
{
return __netdev_upper_dev_link(dev, upper_dev, true,
- upper_priv, upper_info);
+ upper_priv, upper_info, extack);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
@@ -6328,20 +6413,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link);
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
- struct netdev_notifier_changeupper_info changeupper_info;
+ struct netdev_notifier_changeupper_info changeupper_info = {
+ .info = {
+ .dev = dev,
+ },
+ .upper_dev = upper_dev,
+ .linking = false,
+ };
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,
+ call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
- call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
@@ -6357,11 +6446,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink);
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info)
{
- struct netdev_notifier_bonding_info info;
+ struct netdev_notifier_bonding_info info = {
+ .info.dev = dev,
+ };
memcpy(&info.bonding_info, bonding_info,
sizeof(struct netdev_bonding_info));
- call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+ call_netdevice_notifiers_info(NETDEV_BONDING_INFO,
&info.info);
}
EXPORT_SYMBOL(netdev_bonding_info_change);
@@ -6487,11 +6578,13 @@ EXPORT_SYMBOL(dev_get_nest_level);
void netdev_lower_state_changed(struct net_device *lower_dev,
void *lower_state_info)
{
- struct netdev_notifier_changelowerstate_info changelowerstate_info;
+ struct netdev_notifier_changelowerstate_info changelowerstate_info = {
+ .info.dev = lower_dev,
+ };
ASSERT_RTNL();
changelowerstate_info.lower_state_info = lower_state_info;
- call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+ call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE,
&changelowerstate_info.info);
}
EXPORT_SYMBOL(netdev_lower_state_changed);
@@ -6782,11 +6875,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
if (dev->flags & IFF_UP &&
(changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
- struct netdev_notifier_change_info change_info;
+ struct netdev_notifier_change_info change_info = {
+ .info = {
+ .dev = dev,
+ },
+ .flags_changed = changes,
+ };
- change_info.flags_changed = changes;
- call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
- &change_info.info);
+ call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info);
}
}
@@ -7157,7 +7253,7 @@ static void rollback_registered_many(struct list_head *head)
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
- GFP_KERNEL);
+ GFP_KERNEL, NULL);
/*
* Flush the unicast and multicast chains
@@ -8244,7 +8340,7 @@ EXPORT_SYMBOL(unregister_netdev);
int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
{
- int err;
+ int err, new_nsid;
ASSERT_RTNL();
@@ -8300,7 +8396,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net)
+ new_nsid = peernet2id_alloc(dev_net(dev), net);
+ else
+ new_nsid = peernet2id(dev_net(dev), net);
+ rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid);
/*
* Flush the unicast and multicast chains
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 709a4e6fb447..f9c7a88cd981 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -303,7 +303,18 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
case SIOCSIFTXQLEN:
if (ifr->ifr_qlen < 0)
return -EINVAL;
- dev->tx_queue_len = ifr->ifr_qlen;
+ if (dev->tx_queue_len ^ ifr->ifr_qlen) {
+ unsigned int orig_len = dev->tx_queue_len;
+
+ dev->tx_queue_len = ifr->ifr_qlen;
+ err = call_netdevice_notifiers(
+ NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+ err = notifier_to_errno(err);
+ if (err) {
+ dev->tx_queue_len = orig_len;
+ return err;
+ }
+ }
return 0;
case SIOCSIFNAME:
diff --git a/net/core/dst.c b/net/core/dst.c
index a6c47da7d0f8..662a2d4a3d19 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
return md_dst;
}
EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu);
+
+void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst)
+{
+#ifdef CONFIG_DST_CACHE
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu);
+
+ if (one_md_dst->type == METADATA_IP_TUNNEL)
+ dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache);
+ }
+#endif
+ free_percpu(md_dst);
+}
+EXPORT_SYMBOL_GPL(metadata_dst_free_percpu);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 3228411ada0f..f8fcf450a36e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
return 0;
}
+/* Given two link masks, AND them together and save the result in dst. */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+ struct ethtool_link_ksettings *src)
+{
+ unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS);
+ unsigned int idx = 0;
+
+ for (; idx < size; idx++) {
+ dst->link_modes.supported[idx] &=
+ src->link_modes.supported[idx];
+ dst->link_modes.advertising[idx] &=
+ src->link_modes.advertising[idx];
+ }
+}
+EXPORT_SYMBOL(ethtool_intersect_link_masks);
+
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32)
{
@@ -436,7 +452,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32);
/* return false if legacy contained non-0 deprecated fields
- * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated
+ * maxtxpkt/maxrxpkt. rest of ksettings always updated
*/
static bool
convert_legacy_settings_to_link_ksettings(
@@ -451,8 +467,7 @@ convert_legacy_settings_to_link_ksettings(
* deprecated legacy fields, and they should not use
* %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS
*/
- if (legacy_settings->transceiver ||
- legacy_settings->maxtxpkt ||
+ if (legacy_settings->maxtxpkt ||
legacy_settings->maxrxpkt)
retval = false;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a6d97c1d810..fafd0a41e3f7 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -314,10 +314,12 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
static int call_fib_rule_notifiers(struct net *net,
enum fib_event_type event_type,
struct fib_rule *rule,
- struct fib_rules_ops *ops)
+ struct fib_rules_ops *ops,
+ struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = ops->family,
+ .info.extack = extack,
.rule = rule,
};
@@ -609,7 +611,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
if (rule->tun_id)
ip_tunnel_need_metadata();
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack);
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
flush_route_cache(ops);
rules_ops_put(ops);
@@ -749,7 +751,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
}
}
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops,
+ NULL);
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).portid);
fib_rule_put(rule);
diff --git a/net/core/filter.c b/net/core/filter.c
index 82edad58d066..a0112168d6f9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -43,6 +43,7 @@
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
+#include <asm/cmpxchg.h>
#include <linux/filter.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
@@ -989,10 +990,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
- bool ret = __sk_filter_charge(sk, fp);
- if (ret)
- refcount_inc(&fp->refcnt);
- return ret;
+ if (!refcount_inc_not_zero(&fp->refcnt))
+ return false;
+
+ if (!__sk_filter_charge(sk, fp)) {
+ sk_filter_release(fp);
+ return false;
+ }
+ return true;
}
static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
@@ -1402,7 +1407,7 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
{
int err = __bpf_try_make_writable(skb, write_len);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return err;
}
@@ -1835,31 +1840,32 @@ static const struct bpf_func_proto bpf_redirect_proto = {
.arg2_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
+ struct bpf_map *, map, u32, key, u64, flags)
{
- struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+ /* If user passes invalid input drop the packet. */
if (unlikely(flags))
- return SK_ABORTED;
+ return SK_DROP;
- ri->ifindex = key;
- ri->flags = flags;
- ri->map = map;
+ tcb->bpf.key = key;
+ tcb->bpf.flags = flags;
+ tcb->bpf.map = map;
- return SK_REDIRECT;
+ return SK_PASS;
}
-struct sock *do_sk_redirect_map(void)
+struct sock *do_sk_redirect_map(struct sk_buff *skb)
{
- struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
struct sock *sk = NULL;
- if (ri->map) {
- sk = __sock_map_lookup_elem(ri->map, ri->ifindex);
+ if (tcb->bpf.map) {
+ sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
- ri->ifindex = 0;
- ri->map = NULL;
- /* we do not clear flags for future lookup */
+ tcb->bpf.key = 0;
+ tcb->bpf.map = NULL;
}
return sk;
@@ -1869,9 +1875,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
.func = bpf_sk_redirect_map,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_ANYTHING,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
};
BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -1962,7 +1969,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
bpf_pull_mac_rcsum(skb);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -1984,7 +1991,7 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
ret = skb_vlan_pop(skb);
bpf_pull_mac_rcsum(skb);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2178,7 +2185,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
* need to be verified first.
*/
ret = bpf_skb_proto_xlat(skb, proto);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2303,7 +2310,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) :
bpf_skb_net_grow(skb, len_diff_abs);
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2394,7 +2401,7 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
skb_gso_reset(skb);
}
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return ret;
}
@@ -2434,7 +2441,7 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
skb_reset_mac_header(skb);
}
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
return 0;
}
@@ -2447,14 +2454,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
.arg3_type = ARG_ANYTHING,
};
+static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
+{
+ return xdp_data_meta_unsupported(xdp) ? 0 :
+ xdp->data - xdp->data_meta;
+}
+
BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
{
+ unsigned long metalen = xdp_get_metalen(xdp);
+ void *data_start = xdp->data_hard_start + metalen;
void *data = xdp->data + offset;
- if (unlikely(data < xdp->data_hard_start ||
+ if (unlikely(data < data_start ||
data > xdp->data_end - ETH_HLEN))
return -EINVAL;
+ if (metalen)
+ memmove(xdp->data_meta + offset,
+ xdp->data_meta, metalen);
+ xdp->data_meta += offset;
xdp->data = data;
return 0;
@@ -2468,6 +2487,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
.arg2_type = ARG_ANYTHING,
};
+BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
+{
+ void *meta = xdp->data_meta + offset;
+ unsigned long metalen = xdp->data - meta;
+
+ if (xdp_data_meta_unsupported(xdp))
+ return -ENOTSUPP;
+ if (unlikely(meta < xdp->data_hard_start ||
+ meta > xdp->data))
+ return -EINVAL;
+ if (unlikely((metalen & (sizeof(__u32) - 1)) ||
+ (metalen > 32)))
+ return -EACCES;
+
+ xdp->data_meta = meta;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
+ .func = bpf_xdp_adjust_meta,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
static int __bpf_tx_xdp(struct net_device *dev,
struct bpf_map *map,
struct xdp_buff *xdp,
@@ -2482,10 +2528,36 @@ static int __bpf_tx_xdp(struct net_device *dev,
err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
if (err)
return err;
- if (map)
+ dev->netdev_ops->ndo_xdp_flush(dev);
+ return 0;
+}
+
+static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
+ struct bpf_map *map,
+ struct xdp_buff *xdp,
+ u32 index)
+{
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ struct net_device *dev = fwd;
+
+ if (!dev->netdev_ops->ndo_xdp_xmit)
+ return -EOPNOTSUPP;
+
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ if (err)
+ return err;
__dev_map_insert_ctx(map, index);
- else
- dev->netdev_ops->ndo_xdp_flush(dev);
+
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ struct bpf_cpu_map_entry *rcpu = fwd;
+
+ err = cpu_map_enqueue(rcpu, xdp, dev_rx);
+ if (err)
+ return err;
+ __cpu_map_insert_ctx(map, index);
+ }
return 0;
}
@@ -2495,11 +2567,33 @@ void xdp_do_flush_map(void)
struct bpf_map *map = ri->map_to_flush;
ri->map_to_flush = NULL;
- if (map)
- __dev_map_flush(map);
+ if (map) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ __dev_map_flush(map);
+ break;
+ case BPF_MAP_TYPE_CPUMAP:
+ __cpu_map_flush(map);
+ break;
+ default:
+ break;
+ }
+ }
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
+{
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ return __dev_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_CPUMAP:
+ return __cpu_map_lookup_elem(map, index);
+ default:
+ return NULL;
+ }
+}
+
static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
unsigned long aux)
{
@@ -2512,8 +2606,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err;
ri->ifindex = 0;
@@ -2526,7 +2620,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
goto err;
}
- fwd = __dev_map_lookup_elem(map, index);
+ fwd = __xdp_map_lookup_elem(map, index);
if (!fwd) {
err = -EINVAL;
goto err;
@@ -2534,7 +2628,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
if (ri->map_to_flush && ri->map_to_flush != map)
xdp_do_flush_map();
- err = __bpf_tx_xdp(fwd, map, xdp, index);
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index);
if (unlikely(err))
goto err;
@@ -2576,54 +2670,88 @@ err:
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (skb->len > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
- unsigned int len;
int err = 0;
ri->ifindex = 0;
ri->map = NULL;
ri->map_owner = 0;
- if (map) {
- if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
- err = -EFAULT;
- map = NULL;
- goto err;
- }
- fwd = __dev_map_lookup_elem(map, index);
- } else {
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
+ err = -EFAULT;
+ map = NULL;
+ goto err;
}
+ fwd = __xdp_map_lookup_elem(map, index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
- if (unlikely(!(fwd->flags & IFF_UP))) {
- err = -ENETDOWN;
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+ skb->dev = fwd;
+ } else {
+ /* TODO: Handle BPF_MAP_TYPE_CPUMAP */
+ err = -EBADRQC;
goto err;
}
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len) {
- err = -EMSGSIZE;
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ return 0;
+err:
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ return err;
+}
+
+int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ u32 index = ri->ifindex;
+ struct net_device *fwd;
+ int err = 0;
+
+ if (ri->map)
+ return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+
+ ri->ifindex = 0;
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
goto err;
}
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+
skb->dev = fwd;
- map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
- : _trace_xdp_redirect(dev, xdp_prog, index);
+ _trace_xdp_redirect(dev, xdp_prog, index);
return 0;
err:
- map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
- : _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+ _trace_xdp_redirect_err(dev, xdp_prog, index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
@@ -2692,7 +2820,8 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_clone_redirect ||
func == bpf_l3_csum_replace ||
func == bpf_l4_csum_replace ||
- func == bpf_xdp_adjust_head)
+ func == bpf_xdp_adjust_head ||
+ func == bpf_xdp_adjust_meta)
return true;
return false;
@@ -2943,14 +3072,15 @@ static const struct bpf_func_proto *
bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
{
if (!md_dst) {
- /* Race is not possible, since it's called from verifier
- * that is holding verifier mutex.
- */
- md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
- METADATA_IP_TUNNEL,
- GFP_KERNEL);
- if (!md_dst)
+ struct metadata_dst __percpu *tmp;
+
+ tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
+ METADATA_IP_TUNNEL,
+ GFP_KERNEL);
+ if (!tmp)
return NULL;
+ if (cmpxchg(&md_dst, NULL, tmp))
+ metadata_dst_free_percpu(tmp);
}
switch (which) {
@@ -3145,7 +3275,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
static const struct bpf_func_proto bpf_setsockopt_proto = {
.func = bpf_setsockopt,
- .gpl_only = true,
+ .gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
@@ -3154,6 +3284,47 @@ static const struct bpf_func_proto bpf_setsockopt_proto = {
.arg5_type = ARG_CONST_SIZE,
};
+BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
+ int, level, int, optname, char *, optval, int, optlen)
+{
+ struct sock *sk = bpf_sock->sk;
+
+ if (!sk_fullsock(sk))
+ goto err_clear;
+
+#ifdef CONFIG_INET
+ if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
+ if (optname == TCP_CONGESTION) {
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (!icsk->icsk_ca_ops || optlen <= 1)
+ goto err_clear;
+ strncpy(optval, icsk->icsk_ca_ops->name, optlen);
+ optval[optlen - 1] = 0;
+ } else {
+ goto err_clear;
+ }
+ } else {
+ goto err_clear;
+ }
+ return 0;
+#endif
+err_clear:
+ memset(optval, 0, optlen);
+ return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_getsockopt_proto = {
+ .func = bpf_getsockopt,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg5_type = ARG_CONST_SIZE,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@@ -3288,6 +3459,8 @@ xdp_func_proto(enum bpf_func_id func_id)
return &bpf_get_smp_processor_id_proto;
case BPF_FUNC_xdp_adjust_head:
return &bpf_xdp_adjust_head_proto;
+ case BPF_FUNC_xdp_adjust_meta:
+ return &bpf_xdp_adjust_meta_proto;
case BPF_FUNC_redirect:
return &bpf_xdp_redirect_proto;
case BPF_FUNC_redirect_map:
@@ -3330,6 +3503,8 @@ static const struct bpf_func_proto *
switch (func_id) {
case BPF_FUNC_setsockopt:
return &bpf_setsockopt_proto;
+ case BPF_FUNC_getsockopt:
+ return &bpf_getsockopt_proto;
case BPF_FUNC_sock_map_update:
return &bpf_sock_map_update_proto;
default:
@@ -3418,6 +3593,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
case bpf_ctx_range(struct __sk_buff, data):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, data_end):
if (size != size_default)
return false;
@@ -3444,6 +3620,7 @@ static bool sk_filter_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, data_end):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
@@ -3468,6 +3645,7 @@ static bool lwt_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
return false;
}
@@ -3586,6 +3764,9 @@ static bool tc_cls_act_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data):
info->reg_type = PTR_TO_PACKET;
break;
+ case bpf_ctx_range(struct __sk_buff, data_meta):
+ info->reg_type = PTR_TO_PACKET_META;
+ break;
case bpf_ctx_range(struct __sk_buff, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
@@ -3596,6 +3777,25 @@ static bool tc_cls_act_is_valid_access(int off, int size,
return bpf_skb_is_valid_access(off, size, type, info);
}
+static bool
+tc_cls_act_is_valid_access_analyzer(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
+{
+ switch (off) {
+ case offsetof(struct sk_buff, len):
+ return true;
+ case offsetof(struct sk_buff, data):
+ info->reg_type = PTR_TO_PACKET;
+ return true;
+ case offsetof(struct sk_buff, cb) +
+ offsetof(struct bpf_skb_data_end, data_end):
+ info->reg_type = PTR_TO_PACKET_END;
+ return true;
+ }
+ return false;
+}
+
static bool __is_valid_xdp_access(int off, int size)
{
if (off < 0 || off >= sizeof(struct xdp_md))
@@ -3619,6 +3819,9 @@ static bool xdp_is_valid_access(int off, int size,
case offsetof(struct xdp_md, data):
info->reg_type = PTR_TO_PACKET;
break;
+ case offsetof(struct xdp_md, data_meta):
+ info->reg_type = PTR_TO_PACKET_META;
+ break;
case offsetof(struct xdp_md, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
@@ -3627,6 +3830,21 @@ static bool xdp_is_valid_access(int off, int size,
return __is_valid_xdp_access(off, size);
}
+static bool xdp_is_valid_access_analyzer(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
+{
+ switch (off) {
+ case offsetof(struct xdp_buff, data):
+ info->reg_type = PTR_TO_PACKET;
+ return true;
+ case offsetof(struct xdp_buff, data_end):
+ info->reg_type = PTR_TO_PACKET_END;
+ return true;
+ }
+ return false;
+}
+
void bpf_warn_invalid_xdp_action(u32 act)
{
const u32 act_max = XDP_REDIRECT;
@@ -3677,9 +3895,14 @@ static bool sk_skb_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
+ switch (off) {
+ case bpf_ctx_range(struct __sk_buff, tc_classid):
+ case bpf_ctx_range(struct __sk_buff, data_meta):
+ return false;
+ }
+
if (type == BPF_WRITE) {
switch (off) {
- case bpf_ctx_range(struct __sk_buff, mark):
case bpf_ctx_range(struct __sk_buff, tc_index):
case bpf_ctx_range(struct __sk_buff, priority):
break;
@@ -3689,7 +3912,7 @@ static bool sk_skb_is_valid_access(int off, int size,
}
switch (off) {
- case bpf_ctx_range(struct __sk_buff, tc_classid):
+ case bpf_ctx_range(struct __sk_buff, mark):
return false;
case bpf_ctx_range(struct __sk_buff, data):
info->reg_type = PTR_TO_PACKET;
@@ -3847,6 +4070,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
offsetof(struct sk_buff, data));
break;
+ case offsetof(struct __sk_buff, data_meta):
+ off = si->off;
+ off -= offsetof(struct __sk_buff, data_meta);
+ off += offsetof(struct sk_buff, cb);
+ off += offsetof(struct bpf_skb_data_end, data_meta);
+ *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+ si->src_reg, off);
+ break;
+
case offsetof(struct __sk_buff, data_end):
off = si->off;
off -= offsetof(struct __sk_buff, data_end);
@@ -4095,6 +4327,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
si->dst_reg, si->src_reg,
offsetof(struct xdp_buff, data));
break;
+ case offsetof(struct xdp_md, data_meta):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta),
+ si->dst_reg, si->src_reg,
+ offsetof(struct xdp_buff, data_meta));
+ break;
case offsetof(struct xdp_md, data_end):
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end),
si->dst_reg, si->src_reg,
@@ -4238,68 +4475,128 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
}
-const struct bpf_verifier_ops sk_filter_prog_ops = {
+static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
+ const struct bpf_insn *si,
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog, u32 *target_size)
+{
+ struct bpf_insn *insn = insn_buf;
+ int off;
+
+ switch (si->off) {
+ case offsetof(struct __sk_buff, data_end):
+ off = si->off;
+ off -= offsetof(struct __sk_buff, data_end);
+ off += offsetof(struct sk_buff, cb);
+ off += offsetof(struct tcp_skb_cb, bpf.data_end);
+ *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
+ si->src_reg, off);
+ break;
+ default:
+ return bpf_convert_ctx_access(type, si, insn_buf, prog,
+ target_size);
+ }
+
+ return insn - insn_buf;
+}
+
+const struct bpf_verifier_ops sk_filter_verifier_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
};
-const struct bpf_verifier_ops tc_cls_act_prog_ops = {
+const struct bpf_prog_ops sk_filter_prog_ops = {
+};
+
+const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
.get_func_proto = tc_cls_act_func_proto,
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+};
+
+const struct bpf_verifier_ops tc_cls_act_analyzer_ops = {
+ .is_valid_access = tc_cls_act_is_valid_access_analyzer,
+};
+
+const struct bpf_prog_ops tc_cls_act_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops xdp_prog_ops = {
+const struct bpf_verifier_ops xdp_verifier_ops = {
.get_func_proto = xdp_func_proto,
.is_valid_access = xdp_is_valid_access,
.convert_ctx_access = xdp_convert_ctx_access,
+};
+
+const struct bpf_verifier_ops xdp_analyzer_ops = {
+ .is_valid_access = xdp_is_valid_access_analyzer,
+};
+
+const struct bpf_prog_ops xdp_prog_ops = {
.test_run = bpf_prog_test_run_xdp,
};
-const struct bpf_verifier_ops cg_skb_prog_ops = {
+const struct bpf_verifier_ops cg_skb_verifier_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_skb_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops lwt_inout_prog_ops = {
+const struct bpf_verifier_ops lwt_inout_verifier_ops = {
.get_func_proto = lwt_inout_func_proto,
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+};
+
+const struct bpf_prog_ops lwt_inout_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops lwt_xmit_prog_ops = {
+const struct bpf_verifier_ops lwt_xmit_verifier_ops = {
.get_func_proto = lwt_xmit_func_proto,
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+};
+
+const struct bpf_prog_ops lwt_xmit_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
-const struct bpf_verifier_ops cg_sock_prog_ops = {
+const struct bpf_verifier_ops cg_sock_verifier_ops = {
.get_func_proto = sock_filter_func_proto,
.is_valid_access = sock_filter_is_valid_access,
.convert_ctx_access = sock_filter_convert_ctx_access,
};
-const struct bpf_verifier_ops sock_ops_prog_ops = {
+const struct bpf_prog_ops cg_sock_prog_ops = {
+};
+
+const struct bpf_verifier_ops sock_ops_verifier_ops = {
.get_func_proto = sock_ops_func_proto,
.is_valid_access = sock_ops_is_valid_access,
.convert_ctx_access = sock_ops_convert_ctx_access,
};
-const struct bpf_verifier_ops sk_skb_prog_ops = {
+const struct bpf_prog_ops sock_ops_prog_ops = {
+};
+
+const struct bpf_verifier_ops sk_skb_verifier_ops = {
.get_func_proto = sk_skb_func_proto,
.is_valid_access = sk_skb_is_valid_access,
- .convert_ctx_access = bpf_convert_ctx_access,
+ .convert_ctx_access = sk_skb_convert_ctx_access,
.gen_prologue = sk_skb_prologue,
};
+const struct bpf_prog_ops sk_skb_prog_ops = {
+};
+
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0a977373d003..1f5caafb4492 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,7 @@
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <net/dsa.h>
+#include <net/dst_metadata.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/gre.h>
@@ -115,6 +116,102 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
}
EXPORT_SYMBOL(__skb_flow_get_ports);
+static void
+skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
+{
+ struct flow_dissector_key_control *ctrl;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL))
+ return;
+
+ ctrl = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ target_container);
+ ctrl->addr_type = type;
+}
+
+static void
+__skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
+{
+ struct ip_tunnel_info *info;
+ struct ip_tunnel_key *key;
+
+ /* A quick check to see if there might be something to do. */
+ if (!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS))
+ return;
+
+ info = skb_tunnel_info(skb);
+ if (!info)
+ return;
+
+ key = &info->key;
+
+ switch (ip_tunnel_info_af(info)) {
+ case AF_INET:
+ skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ flow_dissector,
+ target_container);
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+ struct flow_dissector_key_ipv4_addrs *ipv4;
+
+ ipv4 = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ target_container);
+ ipv4->src = key->u.ipv4.src;
+ ipv4->dst = key->u.ipv4.dst;
+ }
+ break;
+ case AF_INET6:
+ skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ flow_dissector,
+ target_container);
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+ struct flow_dissector_key_ipv6_addrs *ipv6;
+
+ ipv6 = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
+ target_container);
+ ipv6->src = key->u.ipv6.src;
+ ipv6->dst = key->u.ipv6.dst;
+ }
+ break;
+ }
+
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *keyid;
+
+ keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ target_container);
+ keyid->keyid = tunnel_id_to_key32(key->tun_id);
+ }
+
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+ struct flow_dissector_key_ports *tp;
+
+ tp = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ target_container);
+ tp->src = key->tp_src;
+ tp->dst = key->tp_dst;
+ }
+}
+
static enum flow_dissect_ret
__skb_flow_dissect_mpls(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
@@ -478,6 +575,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
+ __skb_flow_dissect_tunnel_info(skb, flow_dissector,
+ target_container);
+
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct ethhdr *eth = eth_hdr(skb);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 1307731ddfe4..e7e626fb87bb 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -51,7 +51,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
*/
preempt_disable();
rcu_read_lock();
- bpf_compute_data_end(skb);
+ bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(lwt->prog, skb);
rcu_read_unlock();
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 16a1a4c4eb57..6ea3a1a7f36a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -457,7 +457,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
const void *pkey)
{
struct neighbour *n;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val;
struct neigh_hash_table *nht;
@@ -488,7 +488,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
struct net_device *dev, bool want_ref)
{
u32 hash_val;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
int error;
struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
struct neigh_hash_table *nht;
@@ -572,7 +572,7 @@ out_neigh_release:
}
EXPORT_SYMBOL(__neigh_create);
-static u32 pneigh_hash(const void *pkey, int key_len)
+static u32 pneigh_hash(const void *pkey, unsigned int key_len)
{
u32 hash_val = *(u32 *)(pkey + key_len - 4);
hash_val ^= (hash_val >> 16);
@@ -585,7 +585,7 @@ static u32 pneigh_hash(const void *pkey, int key_len)
static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
struct net *net,
const void *pkey,
- int key_len,
+ unsigned int key_len,
struct net_device *dev)
{
while (n) {
@@ -601,7 +601,7 @@ static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl,
struct net *net, const void *pkey, struct net_device *dev)
{
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
return __pneigh_lookup_1(tbl->phash_buckets[hash_val],
@@ -614,7 +614,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
struct net_device *dev, int creat)
{
struct pneigh_entry *n;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
read_lock_bh(&tbl->lock);
@@ -659,7 +659,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
struct net_device *dev)
{
struct pneigh_entry *n, **np;
- int key_len = tbl->key_len;
+ unsigned int key_len = tbl->key_len;
u32 hash_val = pneigh_hash(pkey, key_len);
write_lock_bh(&tbl->lock);
@@ -1662,7 +1662,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(dst_attr) < tbl->key_len)
+ if (nla_len(dst_attr) < (int)tbl->key_len)
goto out;
if (ndm->ndm_flags & NTF_PROXY) {
@@ -1730,7 +1730,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tbl == NULL)
return -EAFNOSUPPORT;
- if (nla_len(tb[NDA_DST]) < tbl->key_len)
+ if (nla_len(tb[NDA_DST]) < (int)tbl->key_len)
goto out;
dst = nla_data(tb[NDA_DST]);
lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 927a6dcbad96..51d5836d8fb9 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -391,10 +391,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
if (len > 0 && buf[len - 1] == '\n')
--count;
- if (!rtnl_trylock())
- return restart_syscall();
ret = dev_set_alias(netdev, buf, count);
- rtnl_unlock();
return ret < 0 ? ret : len;
}
@@ -403,13 +400,12 @@ static ssize_t ifalias_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
const struct net_device *netdev = to_net_dev(dev);
+ char tmp[IFALIASZ];
ssize_t ret = 0;
- if (!rtnl_trylock())
- return restart_syscall();
- if (netdev->ifalias)
- ret = sprintf(buf, "%s\n", netdev->ifalias);
- rtnl_unlock();
+ ret = dev_get_alias(netdev, tmp, sizeof(tmp));
+ if (ret > 0)
+ ret = sprintf(buf, "%s\n", tmp);
return ret;
}
static DEVICE_ATTR_RW(ifalias);
@@ -1488,7 +1484,10 @@ static void netdev_release(struct device *d)
BUG_ON(dev->reg_state != NETREG_RELEASED);
- kfree(dev->ifalias);
+ /* no need to wait for rcu grace period:
+ * device is dead and about to be freed.
+ */
+ kfree(rcu_access_pointer(dev->ifalias));
netdev_freemem(dev);
}
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 1132820c8e62..8dcd9b0be04a 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/tcp.h>
#include <trace/events/fib.h>
#include <trace/events/qdisc.h>
#if IS_ENABLED(CONFIG_IPV6)
@@ -48,3 +49,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a78fd61da0ec..de24d394c69e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
{
const struct rtnl_af_ops *ops;
- list_for_each_entry(ops, &rtnl_af_ops, list) {
+ list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
if (ops->family == family)
return ops;
}
@@ -470,32 +470,22 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
void rtnl_af_register(struct rtnl_af_ops *ops)
{
rtnl_lock();
- list_add_tail(&ops->list, &rtnl_af_ops);
+ list_add_tail_rcu(&ops->list, &rtnl_af_ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_af_register);
/**
- * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
- * @ops: struct rtnl_af_ops * to unregister
- *
- * The caller must hold the rtnl_mutex.
- */
-void __rtnl_af_unregister(struct rtnl_af_ops *ops)
-{
- list_del(&ops->list);
-}
-EXPORT_SYMBOL_GPL(__rtnl_af_unregister);
-
-/**
* rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
* @ops: struct rtnl_af_ops * to unregister
*/
void rtnl_af_unregister(struct rtnl_af_ops *ops)
{
rtnl_lock();
- __rtnl_af_unregister(ops);
+ list_del_rcu(&ops->list);
rtnl_unlock();
+
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(rtnl_af_unregister);
@@ -508,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
/* IFLA_AF_SPEC */
size = nla_total_size(sizeof(struct nlattr));
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_link_af_size) {
/* AF_* + nested data */
size += nla_total_size(sizeof(struct nlattr)) +
af_ops->get_link_af_size(dev, ext_filter_mask);
}
}
+ rcu_read_unlock();
return size;
}
@@ -522,11 +514,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev,
static bool rtnl_have_link_slave_info(const struct net_device *dev)
{
struct net_device *master_dev;
+ bool ret = false;
- master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+ rcu_read_lock();
+
+ master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
if (master_dev && master_dev->rtnl_link_ops)
- return true;
- return false;
+ ret = true;
+ rcu_read_unlock();
+ return ret;
}
static int rtnl_link_slave_info_fill(struct sk_buff *skb,
@@ -923,6 +919,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
+ rtnl_xdp_size() /* IFLA_XDP */
+ nla_total_size(4) /* IFLA_EVENT */
+ + nla_total_size(4) /* IFLA_NEW_NETNSID */
+ nla_total_size(1); /* IFLA_PROTO_DOWN */
}
@@ -1211,6 +1208,36 @@ nla_put_vfinfo_failure:
return -EMSGSIZE;
}
+static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
+ struct net_device *dev,
+ u32 ext_filter_mask)
+{
+ struct nlattr *vfinfo;
+ int i, num_vfs;
+
+ if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0))
+ return 0;
+
+ num_vfs = dev_num_vf(dev->dev.parent);
+ if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs))
+ return -EMSGSIZE;
+
+ if (!dev->netdev_ops->ndo_get_vf_config)
+ return 0;
+
+ vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
+ if (!vfinfo)
+ return -EMSGSIZE;
+
+ for (i = 0; i < num_vfs; i++) {
+ if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
+ return -EMSGSIZE;
+ }
+
+ nla_nest_end(skb, vfinfo);
+ return 0;
+}
+
static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
{
struct rtnl_link_ifmap map;
@@ -1307,16 +1334,106 @@ static u32 rtnl_get_event(unsigned long event)
return rtnl_event_type;
}
+static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
+{
+ const struct net_device *upper_dev;
+ int ret = 0;
+
+ rcu_read_lock();
+
+ upper_dev = netdev_master_upper_dev_get_rcu(dev);
+ if (upper_dev)
+ ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex);
+
+ rcu_read_unlock();
+ return ret;
+}
+
+static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
+{
+ int ifindex = dev_get_iflink(dev);
+
+ if (dev->ifindex == ifindex)
+ return 0;
+
+ return nla_put_u32(skb, IFLA_LINK, ifindex);
+}
+
+static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ char buf[IFALIASZ];
+ int ret;
+
+ ret = dev_get_alias(dev, buf, sizeof(buf));
+ return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0;
+}
+
+static int rtnl_fill_link_netnsid(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
+ struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
+
+ if (!net_eq(dev_net(dev), link_net)) {
+ int id = peernet2id_alloc(dev_net(dev), link_net);
+
+ if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+ return -EMSGSIZE;
+ }
+ }
+
+ return 0;
+}
+
+static int rtnl_fill_link_af(struct sk_buff *skb,
+ const struct net_device *dev,
+ u32 ext_filter_mask)
+{
+ const struct rtnl_af_ops *af_ops;
+ struct nlattr *af_spec;
+
+ af_spec = nla_nest_start(skb, IFLA_AF_SPEC);
+ if (!af_spec)
+ return -EMSGSIZE;
+
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
+ struct nlattr *af;
+ int err;
+
+ if (!af_ops->fill_link_af)
+ continue;
+
+ af = nla_nest_start(skb, af_ops->family);
+ if (!af)
+ return -EMSGSIZE;
+
+ err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
+ /*
+ * Caller may return ENODATA to indicate that there
+ * was no data to be dumped. This is not an error, it
+ * means we should trim the attribute header and
+ * continue.
+ */
+ if (err == -ENODATA)
+ nla_nest_cancel(skb, af);
+ else if (err < 0)
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, af);
+ }
+
+ nla_nest_end(skb, af_spec);
+ return 0;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask,
- u32 event)
+ u32 event, int *new_nsid)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
- struct nlattr *af_spec;
- struct rtnl_af_ops *af_ops;
- struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
@@ -1345,15 +1462,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
- (dev->ifindex != dev_get_iflink(dev) &&
- nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
- (upper_dev &&
- nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
+ nla_put_iflink(skb, dev) ||
+ put_master_ifindex(skb, dev) ||
nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
(dev->qdisc &&
nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
- (dev->ifalias &&
- nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+ nla_put_ifalias(skb, dev) ||
nla_put_u32(skb, IFLA_CARRIER_CHANGES,
atomic_read(&dev->carrier_changes)) ||
nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
@@ -1385,27 +1499,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (rtnl_fill_stats(skb, dev))
goto nla_put_failure;
- if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) &&
- nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)))
+ if (rtnl_fill_vf(skb, dev, ext_filter_mask))
goto nla_put_failure;
- if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent &&
- ext_filter_mask & RTEXT_FILTER_VF) {
- int i;
- struct nlattr *vfinfo;
- int num_vfs = dev_num_vf(dev->dev.parent);
-
- vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
- if (!vfinfo)
- goto nla_put_failure;
- for (i = 0; i < num_vfs; i++) {
- if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
- goto nla_put_failure;
- }
-
- nla_nest_end(skb, vfinfo);
- }
-
if (rtnl_port_fill(skb, dev, ext_filter_mask))
goto nla_put_failure;
@@ -1417,51 +1513,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
goto nla_put_failure;
}
- if (dev->rtnl_link_ops &&
- dev->rtnl_link_ops->get_link_net) {
- struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
-
- if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id_alloc(dev_net(dev), link_net);
-
- if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
- goto nla_put_failure;
- }
- }
-
- if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
+ if (rtnl_fill_link_netnsid(skb, dev))
goto nla_put_failure;
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
- if (af_ops->fill_link_af) {
- struct nlattr *af;
- int err;
-
- if (!(af = nla_nest_start(skb, af_ops->family)))
- goto nla_put_failure;
-
- err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
-
- /*
- * Caller may return ENODATA to indicate that there
- * was no data to be dumped. This is not an error, it
- * means we should trim the attribute header and
- * continue.
- */
- if (err == -ENODATA)
- nla_nest_cancel(skb, af);
- else if (err < 0)
- goto nla_put_failure;
-
- nla_nest_end(skb, af);
- }
- }
+ if (new_nsid &&
+ nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0)
+ goto nla_put_failure;
- nla_nest_end(skb, af_spec);
+ rcu_read_lock();
+ if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
+ goto nla_put_failure_rcu;
+ rcu_read_unlock();
nlmsg_end(skb, nlh);
return 0;
+nla_put_failure_rcu:
+ rcu_read_unlock();
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
@@ -1483,7 +1551,10 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_LINKINFO] = { .type = NLA_NESTED },
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_NET_NS_FD] = { .type = NLA_U32 },
- [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
+ /* IFLA_IFALIAS is a string, but policy is set to NLA_BINARY to
+ * allow 0-length string (needed to remove an alias).
+ */
+ [IFLA_IFALIAS] = { .type = NLA_BINARY, .len = IFALIASZ - 1 },
[IFLA_VFINFO_LIST] = {. type = NLA_NESTED },
[IFLA_VF_PORTS] = { .type = NLA_NESTED },
[IFLA_PORT_SELF] = { .type = NLA_NESTED },
@@ -1658,7 +1729,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags,
- ext_filter_mask, 0);
+ ext_filter_mask, 0, NULL);
if (err < 0) {
if (likely(skb->len))
@@ -1723,17 +1794,27 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
- if (!(af_ops = rtnl_af_lookup(nla_type(af))))
+ rcu_read_lock();
+ af_ops = rtnl_af_lookup(nla_type(af));
+ if (!af_ops) {
+ rcu_read_unlock();
return -EAFNOSUPPORT;
+ }
- if (!af_ops->set_link_af)
+ if (!af_ops->set_link_af) {
+ rcu_read_unlock();
return -EOPNOTSUPP;
+ }
if (af_ops->validate_link_af) {
err = af_ops->validate_link_af(dev, af);
- if (err < 0)
+ if (err < 0) {
+ rcu_read_unlock();
return err;
+ }
}
+
+ rcu_read_unlock();
}
}
@@ -1909,7 +1990,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
return err;
}
-static int do_set_master(struct net_device *dev, int ifindex)
+static int do_set_master(struct net_device *dev, int ifindex,
+ struct netlink_ext_ack *extack)
{
struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops;
@@ -1934,7 +2016,7 @@ static int do_set_master(struct net_device *dev, int ifindex)
return -EINVAL;
ops = upper_dev->netdev_ops;
if (ops->ndo_add_slave) {
- err = ops->ndo_add_slave(upper_dev, dev);
+ err = ops->ndo_add_slave(upper_dev, dev, extack);
if (err)
return err;
} else {
@@ -2067,7 +2149,7 @@ static int do_setlink(const struct sk_buff *skb,
}
if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
@@ -2093,7 +2175,7 @@ static int do_setlink(const struct sk_buff *skb,
dev->tx_queue_len = orig_len;
goto errout;
}
- status |= DO_SETLINK_NOTIFY;
+ status |= DO_SETLINK_MODIFIED;
}
}
@@ -2190,13 +2272,17 @@ static int do_setlink(const struct sk_buff *skb,
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
- if (!(af_ops = rtnl_af_lookup(nla_type(af))))
- BUG();
+ rcu_read_lock();
+
+ BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
err = af_ops->set_link_af(dev, af);
- if (err < 0)
+ if (err < 0) {
+ rcu_read_unlock();
goto errout;
+ }
+ rcu_read_unlock();
status |= DO_SETLINK_NOTIFY;
}
}
@@ -2248,7 +2334,7 @@ static int do_setlink(const struct sk_buff *skb,
errout:
if (status & DO_SETLINK_MODIFIED) {
- if (status & DO_SETLINK_NOTIFY)
+ if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
netdev_state_change(dev);
if (err < 0)
@@ -2576,12 +2662,6 @@ replay:
return err;
slave_data = slave_attr;
}
- if (m_ops->slave_validate) {
- err = m_ops->slave_validate(tb, slave_data,
- extack);
- if (err < 0)
- return err;
- }
}
if (dev) {
@@ -2711,7 +2791,8 @@ replay:
goto out_unregister;
}
if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]),
+ extack);
if (err)
goto out_unregister;
}
@@ -2771,7 +2852,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
return -ENOBUFS;
err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
+ nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
@@ -2856,7 +2937,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
unsigned int change,
- u32 event, gfp_t flags)
+ u32 event, gfp_t flags, int *new_nsid)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2867,7 +2948,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
if (skb == NULL)
goto errout;
- err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
+ err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event,
+ new_nsid);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -2890,14 +2972,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
static void rtmsg_ifinfo_event(int type, struct net_device *dev,
unsigned int change, u32 event,
- gfp_t flags)
+ gfp_t flags, int *new_nsid)
{
struct sk_buff *skb;
if (dev->reg_state != NETREG_REGISTERED)
return;
- skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
+ skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid);
if (skb)
rtmsg_ifinfo_send(skb, dev, flags);
}
@@ -2905,9 +2987,15 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev,
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
gfp_t flags)
{
- rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
+ rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL);
+}
+
+void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags, int *new_nsid)
+{
+ rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags,
+ new_nsid);
}
-EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
@@ -3014,21 +3102,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
}
EXPORT_SYMBOL(ndo_dflt_fdb_add);
-static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid,
+ struct netlink_ext_ack *extack)
{
u16 vid = 0;
if (vlan_attr) {
if (nla_len(vlan_attr) != sizeof(u16)) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+ NL_SET_ERR_MSG(extack, "invalid vlan attribute size");
return -EINVAL;
}
vid = nla_get_u16(vlan_attr);
if (!vid || vid >= VLAN_VID_MASK) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
- vid);
+ NL_SET_ERR_MSG(extack, "invalid vlan id");
return -EINVAL;
}
}
@@ -3053,24 +3141,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
+ NL_SET_ERR_MSG(extack, "invalid ifindex");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
- pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
+ NL_SET_ERR_MSG(extack, "invalid address");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
- err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
if (err)
return err;
@@ -3157,24 +3245,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
+ NL_SET_ERR_MSG(extack, "invalid ifindex");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
- pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n");
+ NL_SET_ERR_MSG(extack, "invalid address");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
- err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
if (err)
return err;
@@ -3614,7 +3702,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
- pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
@@ -3689,7 +3777,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
- pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+ NL_SET_ERR_MSG(extack, "unknown ifindex");
return -ENODEV;
}
@@ -3854,6 +3942,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
return -EMSGSIZE;
ifsm = nlmsg_data(nlh);
+ ifsm->family = PF_UNSPEC;
+ ifsm->pad1 = 0;
+ ifsm->pad2 = 0;
ifsm->ifindex = dev->ifindex;
ifsm->filter_mask = filter_mask;
@@ -3937,25 +4028,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
if (!attr)
goto nla_put_failure;
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->fill_stats_af) {
struct nlattr *af;
int err;
af = nla_nest_start(skb, af_ops->family);
- if (!af)
+ if (!af) {
+ rcu_read_unlock();
goto nla_put_failure;
-
+ }
err = af_ops->fill_stats_af(skb, dev);
- if (err == -ENODATA)
+ if (err == -ENODATA) {
nla_nest_cancel(skb, af);
- else if (err < 0)
+ } else if (err < 0) {
+ rcu_read_unlock();
goto nla_put_failure;
+ }
nla_nest_end(skb, af);
}
}
+ rcu_read_unlock();
nla_nest_end(skb, attr);
@@ -4024,7 +4120,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
/* for IFLA_STATS_AF_SPEC */
size += nla_total_size(0);
- list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_stats_af_size) {
size += nla_total_size(
af_ops->get_stats_af_size(dev));
@@ -4033,6 +4130,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
size += nla_total_size(0);
}
}
+ rcu_read_unlock();
}
return size;
@@ -4276,15 +4374,20 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
switch (event) {
case NETDEV_REBOOT:
+ case NETDEV_CHANGEMTU:
case NETDEV_CHANGEADDR:
case NETDEV_CHANGENAME:
case NETDEV_FEAT_CHANGE:
case NETDEV_BONDING_FAILOVER:
+ case NETDEV_POST_TYPE_CHANGE:
case NETDEV_NOTIFY_PEERS:
+ case NETDEV_CHANGEUPPER:
case NETDEV_RESEND_IGMP:
case NETDEV_CHANGEINFODATA:
+ case NETDEV_CHANGELOWERSTATE:
+ case NETDEV_CHANGE_TX_QUEUE_LEN:
rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
- GFP_KERNEL);
+ GFP_KERNEL, NULL);
break;
default:
break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 16982de649b9..97e604d55d55 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1124,9 +1124,13 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len);
if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
+ struct sock *save_sk = skb->sk;
+
/* Streams do not free skb on error. Reset to prev state. */
msg->msg_iter = orig_iter;
+ skb->sk = sk;
___pskb_trim(skb, orig_len);
+ skb->sk = save_sk;
return err;
}
@@ -1350,8 +1354,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
/* Set the tail pointer and length */
skb_put(n, skb->len);
- if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
copy_skb_header(n, skb);
return n;
@@ -1449,8 +1452,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
BUG_ON(nhead < 0);
- if (skb_shared(skb))
- BUG();
+ BUG_ON(skb_shared(skb));
size = SKB_DATA_ALIGN(size);
@@ -1509,6 +1511,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
+ skb_metadata_clear(skb);
+
/* It is not generally safe to change skb->truesize.
* For the moment, we really care of rx path, or
* when skb is orphaned (not attached to a socket).
@@ -1593,9 +1597,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
- if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
- skb->len + head_copy_len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+ skb->len + head_copy_len));
copy_skb_header(n, skb);
@@ -1876,8 +1879,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
return NULL;
}
- if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
- BUG();
+ BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
+ skb_tail_pointer(skb), delta));
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
@@ -1896,7 +1899,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
}
/* If we need update frag list, we are in troubles.
- * Certainly, it possible to add an offset to skb data,
+ * Certainly, it is possible to add an offset to skb data,
* but taking into account that pulling is expected to
* be very rare operation, it is worth to fight against
* further bloating skb head and crucify ourselves here instead.
@@ -2848,12 +2851,15 @@ EXPORT_SYMBOL(skb_queue_purge);
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
@@ -4762,6 +4768,7 @@ EXPORT_SYMBOL(kfree_skb_partial);
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
{
+ struct skb_shared_info *to_shinfo, *from_shinfo;
int i, delta, len = from->len;
*fragstolen = false;
@@ -4776,7 +4783,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
return true;
}
- if (skb_has_frag_list(to) || skb_has_frag_list(from))
+ to_shinfo = skb_shinfo(to);
+ from_shinfo = skb_shinfo(from);
+ if (to_shinfo->frag_list || from_shinfo->frag_list)
return false;
if (skb_zcopy(to) || skb_zcopy(from))
return false;
@@ -4785,8 +4794,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
struct page *page;
unsigned int offset;
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags >= MAX_SKB_FRAGS)
return false;
if (skb_head_is_locked(from))
@@ -4797,12 +4806,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
- skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+ skb_fill_page_desc(to, to_shinfo->nr_frags,
page, offset, skb_headlen(from));
*fragstolen = true;
} else {
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags > MAX_SKB_FRAGS)
return false;
delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
@@ -4810,19 +4819,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
WARN_ON_ONCE(delta < len);
- memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
- skb_shinfo(from)->frags,
- skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
- skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+ memcpy(to_shinfo->frags + to_shinfo->nr_frags,
+ from_shinfo->frags,
+ from_shinfo->nr_frags * sizeof(skb_frag_t));
+ to_shinfo->nr_frags += from_shinfo->nr_frags;
if (!skb_cloned(from))
- skb_shinfo(from)->nr_frags = 0;
+ from_shinfo->nr_frags = 0;
/* if the skb is not cloned this does nothing
* since we set nr_frags to 0.
*/
- for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
- skb_frag_ref(from, i);
+ for (i = 0; i < from_shinfo->nr_frags; i++)
+ __skb_frag_ref(&from_shinfo->frags[i]);
to->truesize += delta;
to->len += len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 9b7b6bbb2a23..759400053110 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1654,6 +1654,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
sock_copy(newsk, sk);
+ newsk->sk_prot_creator = sk->sk_prot;
+
/* SANITY */
if (likely(newsk->sk_net_refcnt))
get_net(sock_net(newsk));
@@ -1675,20 +1677,28 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_dst_pending_confirm = 0;
newsk->sk_wmem_queued = 0;
newsk->sk_forward_alloc = 0;
+
+ /* sk->sk_memcg will be populated at accept() time */
+ newsk->sk_memcg = NULL;
+
atomic_set(&newsk->sk_drops, 0);
newsk->sk_send_head = NULL;
newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
atomic_set(&newsk->sk_zckey, 0);
sock_reset_flag(newsk, SOCK_DONE);
+ cgroup_sk_alloc(&newsk->sk_cgrp_data);
- filter = rcu_dereference_protected(newsk->sk_filter, 1);
+ rcu_read_lock();
+ filter = rcu_dereference(sk->sk_filter);
if (filter != NULL)
/* though it's an empty new sock, the charging may fail
* if sysctl_optmem_max was changed between creation of
* original socket and cloning
*/
is_charged = sk_filter_charge(newsk, filter);
+ RCU_INIT_POINTER(newsk->sk_filter, filter);
+ rcu_read_unlock();
if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
/* We need to make sure that we don't uncharge the new
@@ -1709,9 +1719,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
- mem_cgroup_sk_alloc(newsk);
- cgroup_sk_alloc(&newsk->sk_cgrp_data);
-
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -2678,7 +2685,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk_init_common(sk);
sk->sk_send_head = NULL;
- init_timer(&sk->sk_timer);
+ timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index eed1ebf7f29d..b1e0dbea1e8c 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk)
* soft irq of receive path or setsockopt from process context
*/
spin_lock_bh(&reuseport_lock);
- WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
- lockdep_is_held(&reuseport_lock)),
- "multiple allocations for the same socket");
+
+ /* Allocation attempts can occur concurrently via the setsockopt path
+ * and the bind/hash path. Nothing to do when we lose the race.
+ */
+ if (rcu_dereference_protected(sk->sk_reuseport_cb,
+ lockdep_is_held(&reuseport_lock)))
+ goto out;
+
reuse = __reuseport_alloc(INIT_SOCKS);
if (!reuse) {
spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk)
reuse->num_socks = 1;
rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+out:
spin_unlock_bh(&reuseport_lock);
return 0;
Powered by cgit, Gruvboxed by Blaster4385.