summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c30
-rw-r--r--net/core/dev_api.c16
-rw-r--r--net/core/fib_rules.c48
-rw-r--r--net/core/filter.c80
-rw-r--r--net/core/link_watch.c28
-rw-r--r--net/core/lock_debug.c2
-rw-r--r--net/core/lwtunnel.c26
-rw-r--r--net/core/netdev-genl.c9
-rw-r--r--net/core/rtnetlink.c12
-rw-r--r--net/core/selftests.c18
-rw-r--r--net/core/sock.c5
11 files changed, 190 insertions, 84 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 0608605cfc24..1be7cb73a602 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1518,16 +1518,10 @@ void netdev_features_change(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_features_change);
-/**
- * netdev_state_change - device changes state
- * @dev: device to cause notification
- *
- * Called to indicate a device has changed state. This function calls
- * the notifier chains for netdev_chain and sends a NEWLINK message
- * to the routing socket.
- */
-void netdev_state_change(struct net_device *dev)
+void netif_state_change(struct net_device *dev)
{
+ netdev_ops_assert_locked_or_invisible(dev);
+
if (dev->flags & IFF_UP) {
struct netdev_notifier_change_info change_info = {
.info.dev = dev,
@@ -1538,7 +1532,6 @@ void netdev_state_change(struct net_device *dev)
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
}
}
-EXPORT_SYMBOL(netdev_state_change);
/**
* __netdev_notify_peers - notify network peers about existence of @dev,
@@ -11941,15 +11934,24 @@ void unregister_netdevice_many_notify(struct list_head *head,
BUG_ON(dev->reg_state != NETREG_REGISTERED);
}
- /* If device is running, close it first. */
+ /* If device is running, close it first. Start with ops locked... */
list_for_each_entry(dev, head, unreg_list) {
- list_add_tail(&dev->close_list, &close_head);
- netdev_lock_ops(dev);
+ if (netdev_need_ops_lock(dev)) {
+ list_add_tail(&dev->close_list, &close_head);
+ netdev_lock(dev);
+ }
+ }
+ dev_close_many(&close_head, true);
+ /* ... now unlock them and go over the rest. */
+ list_for_each_entry(dev, head, unreg_list) {
+ if (netdev_need_ops_lock(dev))
+ netdev_unlock(dev);
+ else
+ list_add_tail(&dev->close_list, &close_head);
}
dev_close_many(&close_head, true);
list_for_each_entry(dev, head, unreg_list) {
- netdev_unlock_ops(dev);
/* And unlink it from device chain. */
unlist_netdevice(dev);
netdev_lock(dev);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90bafb0b1b8c..90898cd540ce 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -327,3 +327,19 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
return ret;
}
EXPORT_SYMBOL_GPL(dev_xdp_propagate);
+
+/**
+ * netdev_state_change() - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+ netdev_lock_ops(dev);
+ netif_state_change(dev);
+ netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(netdev_state_change);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 4bc64d912a1c..7af302080a66 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -257,6 +257,24 @@ static int nla_put_port_range(struct sk_buff *skb, int attrtype,
return nla_put(skb, attrtype, sizeof(*range), range);
}
+static bool fib_rule_iif_match(const struct fib_rule *rule, int iifindex,
+ const struct flowi *fl)
+{
+ u8 iif_is_l3_master = READ_ONCE(rule->iif_is_l3_master);
+
+ return iif_is_l3_master ? l3mdev_fib_rule_iif_match(fl, iifindex) :
+ fl->flowi_iif == iifindex;
+}
+
+static bool fib_rule_oif_match(const struct fib_rule *rule, int oifindex,
+ const struct flowi *fl)
+{
+ u8 oif_is_l3_master = READ_ONCE(rule->oif_is_l3_master);
+
+ return oif_is_l3_master ? l3mdev_fib_rule_oif_match(fl, oifindex) :
+ fl->flowi_oif == oifindex;
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -264,11 +282,11 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
int iifindex, oifindex, ret = 0;
iifindex = READ_ONCE(rule->iifindex);
- if (iifindex && (iifindex != fl->flowi_iif))
+ if (iifindex && !fib_rule_iif_match(rule, iifindex, fl))
goto out;
oifindex = READ_ONCE(rule->oifindex);
- if (oifindex && (oifindex != fl->flowi_oif))
+ if (oifindex && !fib_rule_oif_match(rule, oifindex, fl))
goto out;
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
@@ -736,16 +754,20 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule,
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname);
- if (dev)
+ if (dev) {
nlrule->iifindex = dev->ifindex;
+ nlrule->iif_is_l3_master = netif_is_l3_master(dev);
+ }
}
if (tb[FRA_OIFNAME]) {
struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname);
- if (dev)
+ if (dev) {
nlrule->oifindex = dev->ifindex;
+ nlrule->oif_is_l3_master = netif_is_l3_master(dev);
+ }
}
return 0;
@@ -1336,11 +1358,17 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
list_for_each_entry(rule, rules, list) {
if (rule->iifindex == -1 &&
- strcmp(dev->name, rule->iifname) == 0)
+ strcmp(dev->name, rule->iifname) == 0) {
WRITE_ONCE(rule->iifindex, dev->ifindex);
+ WRITE_ONCE(rule->iif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
if (rule->oifindex == -1 &&
- strcmp(dev->name, rule->oifname) == 0)
+ strcmp(dev->name, rule->oifname) == 0) {
WRITE_ONCE(rule->oifindex, dev->ifindex);
+ WRITE_ONCE(rule->oif_is_l3_master,
+ netif_is_l3_master(dev));
+ }
}
}
@@ -1349,10 +1377,14 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
- if (rule->iifindex == dev->ifindex)
+ if (rule->iifindex == dev->ifindex) {
WRITE_ONCE(rule->iifindex, -1);
- if (rule->oifindex == dev->ifindex)
+ WRITE_ONCE(rule->iif_is_l3_master, false);
+ }
+ if (rule->oifindex == dev->ifindex) {
WRITE_ONCE(rule->oifindex, -1);
+ WRITE_ONCE(rule->oif_is_l3_master, false);
+ }
}
}
diff --git a/net/core/filter.c b/net/core/filter.c
index bc6828761a47..79cab4d78dc3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -218,24 +218,36 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
return 0;
}
+static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset)
+{
+ if (likely(offset >= 0))
+ return offset;
+
+ if (offset >= SKF_NET_OFF)
+ return offset - SKF_NET_OFF + skb_network_offset(skb);
+
+ if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb))
+ return offset - SKF_LL_OFF + skb_mac_offset(skb);
+
+ return INT_MIN;
+}
+
BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- u8 tmp, *ptr;
+ u8 tmp;
const int len = sizeof(tmp);
- if (offset >= 0) {
- if (headlen - offset >= len)
- return *(u8 *)(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return tmp;
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return *(u8 *)ptr;
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return *(u8 *)(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return tmp;
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
@@ -248,21 +260,19 @@ BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- __be16 tmp, *ptr;
+ __be16 tmp;
const int len = sizeof(tmp);
- if (offset >= 0) {
- if (headlen - offset >= len)
- return get_unaligned_be16(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return be16_to_cpu(tmp);
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return get_unaligned_be16(ptr);
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return get_unaligned_be16(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be16_to_cpu(tmp);
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
@@ -275,21 +285,19 @@ BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
- __be32 tmp, *ptr;
+ __be32 tmp;
const int len = sizeof(tmp);
- if (likely(offset >= 0)) {
- if (headlen - offset >= len)
- return get_unaligned_be32(data + offset);
- if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
- return be32_to_cpu(tmp);
- } else {
- ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
- if (likely(ptr))
- return get_unaligned_be32(ptr);
- }
+ offset = bpf_skb_load_helper_convert_offset(skb, offset);
+ if (offset == INT_MIN)
+ return -EFAULT;
- return -EFAULT;
+ if (headlen - offset >= len)
+ return get_unaligned_be32(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be32_to_cpu(tmp);
+ else
+ return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index cb04ef2b9807..864f3bbc3a4c 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -183,7 +183,7 @@ static void linkwatch_do_dev(struct net_device *dev)
else
dev_deactivate(dev);
- netdev_state_change(dev);
+ netif_state_change(dev);
}
/* Note: our callers are responsible for calling netdev_tracker_free().
* This is the reason we use __dev_put() instead of dev_put().
@@ -240,7 +240,9 @@ static void __linkwatch_run_queue(int urgent_only)
*/
netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
spin_unlock_irq(&lweventlist_lock);
+ netdev_lock_ops(dev);
linkwatch_do_dev(dev);
+ netdev_unlock_ops(dev);
do_dev--;
spin_lock_irq(&lweventlist_lock);
}
@@ -253,25 +255,41 @@ static void __linkwatch_run_queue(int urgent_only)
spin_unlock_irq(&lweventlist_lock);
}
-void linkwatch_sync_dev(struct net_device *dev)
+static bool linkwatch_clean_dev(struct net_device *dev)
{
unsigned long flags;
- int clean = 0;
+ bool clean = false;
spin_lock_irqsave(&lweventlist_lock, flags);
if (!list_empty(&dev->link_watch_list)) {
list_del_init(&dev->link_watch_list);
- clean = 1;
+ clean = true;
/* We must release netdev tracker under
* the spinlock protection.
*/
netdev_tracker_free(dev, &dev->linkwatch_dev_tracker);
}
spin_unlock_irqrestore(&lweventlist_lock, flags);
- if (clean)
+
+ return clean;
+}
+
+void __linkwatch_sync_dev(struct net_device *dev)
+{
+ netdev_ops_assert_locked(dev);
+
+ if (linkwatch_clean_dev(dev))
linkwatch_do_dev(dev);
}
+void linkwatch_sync_dev(struct net_device *dev)
+{
+ if (linkwatch_clean_dev(dev)) {
+ netdev_lock_ops(dev);
+ linkwatch_do_dev(dev);
+ netdev_unlock_ops(dev);
+ }
+}
/* Must be called with the rtnl semaphore held */
void linkwatch_run_queue(void)
diff --git a/net/core/lock_debug.c b/net/core/lock_debug.c
index b7f22dc92a6f..941e26c1343d 100644
--- a/net/core/lock_debug.c
+++ b/net/core/lock_debug.c
@@ -20,11 +20,11 @@ int netdev_debug_event(struct notifier_block *nb, unsigned long event,
switch (cmd) {
case NETDEV_REGISTER:
case NETDEV_UP:
+ case NETDEV_CHANGE:
netdev_ops_assert_locked(dev);
fallthrough;
case NETDEV_DOWN:
case NETDEV_REBOOT:
- case NETDEV_CHANGE:
case NETDEV_UNREGISTER:
case NETDEV_CHANGEMTU:
case NETDEV_CHANGEADDR:
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e39a459540ec..60f27cb4e54f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -333,6 +333,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -348,8 +350,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -364,11 +368,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +386,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -396,8 +404,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -412,11 +422,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +440,8 @@ int lwtunnel_input(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5d7af50fe702..230743bdbb14 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -861,14 +861,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&priv->lock);
+ err = 0;
netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
- if (!netdev || !netif_device_present(netdev)) {
+ if (!netdev) {
err = -ENODEV;
goto err_unlock_sock;
}
-
- if (!netdev_need_ops_lock(netdev)) {
+ if (!netif_device_present(netdev))
+ err = -ENODEV;
+ else if (!netdev_need_ops_lock(netdev))
err = -EOPNOTSUPP;
+ if (err) {
NL_SET_BAD_ATTR(info->extack,
info->attrs[NETDEV_A_DEV_IFINDEX]);
goto err_unlock;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c23852835050..c5a7f41982a5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1043,7 +1043,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
-void netdev_set_operstate(struct net_device *dev, int newstate)
+void netif_set_operstate(struct net_device *dev, int newstate)
{
unsigned int old = READ_ONCE(dev->operstate);
@@ -1052,9 +1052,9 @@ void netdev_set_operstate(struct net_device *dev, int newstate)
return;
} while (!try_cmpxchg(&dev->operstate, &old, newstate));
- netdev_state_change(dev);
+ netif_state_change(dev);
}
-EXPORT_SYMBOL(netdev_set_operstate);
+EXPORT_SYMBOL(netif_set_operstate);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
@@ -1080,7 +1080,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
break;
}
- netdev_set_operstate(dev, operstate);
+ netif_set_operstate(dev, operstate);
}
static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -3027,7 +3027,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
err = validate_linkmsg(dev, tb, extack);
if (err < 0)
- goto errout;
+ return err;
if (tb[IFLA_IFNAME])
nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -3396,7 +3396,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
errout:
if (status & DO_SETLINK_MODIFIED) {
if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
- netdev_state_change(dev);
+ netif_state_change(dev);
if (err < 0)
net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
diff --git a/net/core/selftests.c b/net/core/selftests.c
index e99ae983fca9..35f807ea9952 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
ehdr->h_proto = htons(ETH_P_IP);
if (attr->tcp) {
+ memset(thdr, 0, sizeof(*thdr));
thdr->source = htons(attr->sport);
thdr->dest = htons(attr->dport);
thdr->doff = sizeof(struct tcphdr) / 4;
- thdr->check = 0;
} else {
uhdr->source = htons(attr->sport);
uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
attr->id = net_test_next_id;
shdr->id = net_test_next_id++;
- if (attr->size)
- skb_put(skb, attr->size);
- if (attr->max_size && attr->max_size > skb->len)
- skb_put(skb, attr->max_size - skb->len);
+ if (attr->size) {
+ void *payload = skb_put(skb, attr->size);
+
+ memset(payload, 0, attr->size);
+ }
+
+ if (attr->max_size && attr->max_size > skb->len) {
+ size_t pad_len = attr->max_size - skb->len;
+ void *pad = skb_put(skb, pad_len);
+
+ memset(pad, 0, pad_len);
+ }
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/net/core/sock.c b/net/core/sock.c
index f67a3c5b0988..e54449c9ab0b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2130,6 +2130,8 @@ lenout:
*/
static inline void sock_lock_init(struct sock *sk)
{
+ sk_owner_clear(sk);
+
if (sk->sk_kern_sock)
sock_lock_init_class_and_name(
sk,
@@ -2226,6 +2228,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
cgroup_sk_free(&sk->sk_cgrp_data);
mem_cgroup_sk_free(sk);
security_sk_free(sk);
+
+ sk_owner_put(sk);
+
if (slab != NULL)
kmem_cache_free(slab, sk);
else
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-27 21:28:19 +0000