summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c9
-rw-r--r--net/core/fib_rules.c6
-rw-r--r--net/core/filter.c28
-rw-r--r--net/core/flow_dissector.c12
-rw-r--r--net/core/lwt_bpf.c12
-rw-r--r--net/core/lwtunnel.c6
-rw-r--r--net/core/netdev-genl.c4
-rw-r--r--net/core/netdev_rx_queue.c8
8 files changed, 68 insertions, 17 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 0c6c270d9f7d..f81ce83fb325 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5381,8 +5381,6 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
u32 tail;
reason = SKB_DROP_REASON_DEV_READY;
- if (unlikely(!netif_running(skb->dev)))
- goto bad_dev;
sd = &per_cpu(softnet_data, cpu);
@@ -5394,6 +5392,10 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
backlog_lock_irq_save(sd, &flags);
qlen = skb_queue_len(&sd->input_pkt_queue);
if (likely(qlen <= max_backlog)) {
+ if (unlikely(!netif_running(skb->dev))) {
+ backlog_unlock_irq_restore(sd, flags);
+ goto bad_dev;
+ }
if (!qlen) {
/* Schedule NAPI for backlog device. We can use
* non atomic operation as we own the queue lock.
@@ -11217,7 +11219,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
spin_lock_init(&dev->tx_global_lock);
-
+ spin_lock_init(&dev->watchdog_lock);
+ dev->watchdog_ref_held = false;
return 0;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 8ca634964e36..cf374c208732 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -349,7 +349,7 @@ jumped:
if (err != -EAGAIN) {
if ((arg->flags & FIB_LOOKUP_NOREF) ||
- likely(refcount_inc_not_zero(&rule->refcnt))) {
+ likely(fib_rule_get_safe(rule))) {
arg->rule = rule;
goto out;
}
@@ -410,8 +410,12 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
if (!ops)
return -EAFNOSUPPORT;
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+ if (!fib_rule_get_safe(rule))
+ continue;
+
err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD,
rule, family, extack);
+ fib_rule_put(rule);
if (err)
break;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 40037413dd4e..f21aeff99cc9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2834,6 +2834,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
if (!space || (space == 1 && start != offset))
copy = msg->sg.data[i].length;
+ if (unlikely(copy + len < copy))
+ return -EINVAL;
+
page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
get_order(copy + len));
if (unlikely(!page))
@@ -2997,8 +3000,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
u32, len, u64, flags)
{
u32 i = 0, l = 0, space, offset = 0;
- u64 last = start + len;
- int pop;
+ u64 last = (u64)start + len;
+ u32 pop;
if (unlikely(flags))
return -EINVAL;
@@ -4430,7 +4433,7 @@ u32 xdp_master_redirect(struct xdp_buff *xdp)
struct net_device *master, *slave;
master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev);
- if (unlikely(!(master->flags & IFF_UP)))
+ if (unlikely(!master || !(master->flags & IFF_UP)))
return XDP_ABORTED;
slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp);
if (slave && slave != xdp->rxq->dev) {
@@ -5571,11 +5574,24 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
KERNEL_SOCKPTR(optval), *optlen);
}
+static bool sk_allows_sol_ip_sockopt(struct sock *sk)
+{
+ switch (sk->sk_family) {
+ case AF_INET:
+ return true;
+ case AF_INET6:
+ /* Allow getting/setting sockopt for possible ipv4-mapped ipv6 socket. */
+ return sk->sk_type != SOCK_RAW && !ipv6_only_sock(sk);
+ default:
+ return false;
+ }
+}
+
static int sol_ip_sockopt(struct sock *sk, int optname,
char *optval, int *optlen,
bool getopt)
{
- if (sk->sk_family != AF_INET)
+ if (!sk_allows_sol_ip_sockopt(sk))
return -EINVAL;
switch (optname) {
@@ -6166,7 +6182,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
struct in_device *in_dev;
struct net_device *dev;
struct fib_result res;
- struct flowi4 fl4;
+ struct flowi4 fl4 = {};
u32 mtu = 0;
int err;
@@ -6306,7 +6322,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
struct neighbour *neigh;
struct net_device *dev;
struct inet6_dev *idev;
- struct flowi6 fl6;
+ struct flowi6 fl6 = {};
int strict = 0;
int oif, err;
u32 mtu = 0;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2a98f5fa74eb..8aa4f9b4df81 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1173,13 +1173,21 @@ bool __skb_flow_dissect(const struct net *net,
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
- struct ethhdr *eth = eth_hdr(skb);
struct flow_dissector_key_eth_addrs *key_eth_addrs;
key_eth_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS,
target_container);
- memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
+ /* TC filter blocks can be shared across devices with
+ * different link types, so we cannot validate this
+ * when the filter is installed -- check at dissect time.
+ */
+ if (skb && skb->dev &&
+ skb->dev->type == ARPHRD_ETHER &&
+ skb_mac_header_was_set(skb))
+ memcpy(key_eth_addrs, eth_hdr(skb), sizeof(*key_eth_addrs));
+ else
+ memset(key_eth_addrs, 0, sizeof(*key_eth_addrs));
}
if (dissector_uses_key(flow_dissector,
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index f71ef82a5f3d..bf588f508b79 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -599,6 +599,7 @@ static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len)
int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
{
+ bool is_udp_tunnel;
struct iphdr *iph;
bool ipv4;
int err;
@@ -612,10 +613,16 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
ipv4 = true;
if (unlikely(len < iph->ihl * 4))
return -EINVAL;
+ is_udp_tunnel = iph->protocol == IPPROTO_UDP;
+ if (unlikely(is_udp_tunnel && len < iph->ihl * 4 + sizeof(struct udphdr)))
+ return -EINVAL;
} else if (iph->version == 6) {
ipv4 = false;
if (unlikely(len < sizeof(struct ipv6hdr)))
return -EINVAL;
+ is_udp_tunnel = ((struct ipv6hdr *)iph)->nexthdr == NEXTHDR_UDP;
+ if (unlikely(is_udp_tunnel && len < sizeof(struct ipv6hdr) + sizeof(struct udphdr)))
+ return -EINVAL;
} else {
return -EINVAL;
}
@@ -637,6 +644,11 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
if (ingress)
skb_postpush_rcsum(skb, iph, len);
skb_reset_network_header(skb);
+ if (is_udp_tunnel) {
+ size_t iph_sz = ipv4 ? iph->ihl * 4 : sizeof(struct ipv6hdr);
+
+ skb_set_transport_header(skb, skb_network_offset(skb) + iph_sz);
+ }
memcpy(skb_network_header(skb), hdr, len);
bpf_compute_data_pointers(skb);
skb_clear_hash(skb);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index f9d76d85d04f..b01a395d9a96 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -350,6 +350,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
if (likely(ops && ops->output)) {
+ /* Encap pushes outer headers over the metadata; drop it. */
+ skb_metadata_clear(skb);
dev_xmit_recursion_inc();
ret = ops->output(net, sk, skb);
dev_xmit_recursion_dec();
@@ -404,6 +406,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
if (likely(ops && ops->xmit)) {
+ /* Encap pushes outer headers over the metadata; drop it. */
+ skb_metadata_clear(skb);
dev_xmit_recursion_inc();
ret = ops->xmit(skb);
dev_xmit_recursion_dec();
@@ -455,6 +459,8 @@ int lwtunnel_input(struct sk_buff *skb)
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
if (likely(ops && ops->input)) {
+ /* Encap pushes outer headers over the metadata; drop it. */
+ skb_metadata_clear(skb);
dev_xmit_recursion_inc();
ret = ops->input(skb);
dev_xmit_recursion_dec();
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 119eaa6501d5..ed76544b2d45 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -2,6 +2,7 @@
#include <linux/netdevice.h>
#include <linux/notifier.h>
+#include <linux/pid_namespace.h>
#include <linux/rtnetlink.h>
#include <net/busy_poll.h>
#include <net/net_namespace.h>
@@ -189,7 +190,8 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
goto nla_put_failure;
if (napi->thread) {
- pid = task_pid_nr(napi->thread);
+ pid = task_pid_nr_ns(napi->thread,
+ task_active_pid_ns(current));
if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
goto nla_put_failure;
}
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index de4dac4c88b3..00a7011eb4d5 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -338,12 +338,12 @@ void __netif_mp_uninstall_rxq(struct netdev_rx_queue *rxq,
void netif_rxq_cleanup_unlease(struct netdev_rx_queue *phys_rxq,
struct netdev_rx_queue *virt_rxq)
{
- struct pp_memory_provider_params *p = &phys_rxq->mp_params;
unsigned int rxq_idx = get_netdev_rx_queue_index(phys_rxq);
+ struct pp_memory_provider_params p = phys_rxq->mp_params;
- if (!p->mp_ops)
+ if (!p.mp_ops)
return;
- __netif_mp_uninstall_rxq(virt_rxq, p);
- __netif_mp_close_rxq(phys_rxq->dev, rxq_idx, p);
+ __netif_mp_close_rxq(phys_rxq->dev, rxq_idx, &p);
+ __netif_mp_uninstall_rxq(virt_rxq, &p);
}
generated by cgit v1.2.3 (git 2.25.1) at 2026-07-24 20:09:08 +0000