summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c5
-rw-r--r--net/core/drop_monitor.c11
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/filter.c38
-rw-r--r--net/core/flow_dissector.c1
-rw-r--r--net/core/lwt_bpf.c7
-rw-r--r--net/core/lwtunnel.c4
-rw-r--r--net/core/neighbour.c3
-rw-r--r--net/core/net-procfs.c38
-rw-r--r--net/core/net-sysfs.c5
-rw-r--r--net/core/net_namespace.c4
-rw-r--r--net/core/rtnetlink.c6
-rw-r--r--net/core/skbuff.c6
-rw-r--r--net/core/skmsg.c17
-rw-r--r--net/core/sock.c2
-rw-r--r--net/core/sock_map.c2
16 files changed, 115 insertions, 36 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index ff336417c9b9..a03036456221 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3766,7 +3766,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
- if (txq->xmit_lock_owner != cpu) {
+ /* Other cpus might concurrently change txq->xmit_lock_owner
+ * to -1 or to their cpu id, but not to our id.
+ */
+ if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
if (dev_xmit_recursion())
goto recursion_alert;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index af0130039f37..e8e8389ddc96 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -277,13 +277,17 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi,
rcu_read_lock();
list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
+ struct net_device *dev;
+
/*
* only add a note to our monitor buffer if:
* 1) this is the dev we received on
* 2) its after the last_rx delta
* 3) our rx_dropped count has gone up
*/
- if ((new_stat->dev == napi->dev) &&
+ /* Paired with WRITE_ONCE() in dropmon_net_event() */
+ dev = READ_ONCE(new_stat->dev);
+ if ((dev == napi->dev) &&
(time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
(napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
trace_drop_common(NULL, NULL);
@@ -1497,7 +1501,10 @@ static int dropmon_net_event(struct notifier_block *ev_block,
mutex_lock(&net_dm_mutex);
list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
if (new_stat->dev == dev) {
- new_stat->dev = NULL;
+
+ /* Paired with READ_ONCE() in trace_napi_poll_hit() */
+ WRITE_ONCE(new_stat->dev, NULL);
+
if (trace_state == TRACE_OFF) {
list_del_rcu(&new_stat->list);
kfree_rcu(new_stat, rcu);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 675f27ef6872..83299a85480a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -300,7 +300,7 @@ jumped:
else
err = ops->action(rule, fl, flags, arg);
- if (!err && ops->suppress && ops->suppress(rule, arg))
+ if (!err && ops->suppress && ops->suppress(rule, flags, arg))
continue;
if (err != -EAGAIN) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 5ebc973ed4c5..e16b2b5cda98 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2516,6 +2516,9 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
if (unlikely(flags))
return -EINVAL;
+ if (unlikely(len == 0))
+ return 0;
+
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
@@ -4248,12 +4251,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
switch (optname) {
case SO_RCVBUF:
val = min_t(u32, val, sysctl_rmem_max);
+ val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
WRITE_ONCE(sk->sk_rcvbuf,
max_t(int, val * 2, SOCK_MIN_RCVBUF));
break;
case SO_SNDBUF:
val = min_t(u32, val, sysctl_wmem_max);
+ val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
WRITE_ONCE(sk->sk_sndbuf,
max_t(int, val * 2, SOCK_MIN_SNDBUF));
@@ -5819,24 +5824,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
if (!th->ack || th->rst || th->syn)
return -ENOENT;
+ if (unlikely(iph_len < sizeof(struct iphdr)))
+ return -EINVAL;
+
if (tcp_synq_no_recent_overflow(sk))
return -ENOENT;
cookie = ntohl(th->ack_seq) - 1;
- switch (sk->sk_family) {
- case AF_INET:
- if (unlikely(iph_len < sizeof(struct iphdr)))
+ /* Both struct iphdr and struct ipv6hdr have the version field at the
+ * same offset so we can cast to the shorter header (struct iphdr).
+ */
+ switch (((struct iphdr *)iph)->version) {
+ case 4:
+ if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
return -EINVAL;
ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
break;
#if IS_BUILTIN(CONFIG_IPV6)
- case AF_INET6:
+ case 6:
if (unlikely(iph_len < sizeof(struct ipv6hdr)))
return -EINVAL;
+ if (sk->sk_family != AF_INET6)
+ return -EINVAL;
+
ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
break;
#endif /* CONFIG_IPV6 */
@@ -6703,6 +6717,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
+ int field_size;
if (off < 0 || off >= sizeof(struct bpf_sock))
return false;
@@ -6714,7 +6729,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
case offsetof(struct bpf_sock, family):
case offsetof(struct bpf_sock, type):
case offsetof(struct bpf_sock, protocol):
- case offsetof(struct bpf_sock, dst_port):
case offsetof(struct bpf_sock, src_port):
case bpf_ctx_range(struct bpf_sock, src_ip4):
case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
@@ -6722,6 +6736,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
+ case bpf_ctx_range(struct bpf_sock, dst_port):
+ field_size = size == size_default ?
+ size_default : sizeof_field(struct bpf_sock, dst_port);
+ bpf_ctx_record_field_size(info, field_size);
+ return bpf_ctx_narrow_access_ok(off, size, field_size);
+ case offsetofend(struct bpf_sock, dst_port) ...
+ offsetof(struct bpf_sock, dst_ip4) - 1:
+ return false;
}
return size == size_default;
@@ -6910,9 +6932,9 @@ void bpf_warn_invalid_xdp_action(u32 act)
{
const u32 act_max = XDP_REDIRECT;
- WARN_ONCE(1, "%s XDP return value %u, expect packet loss!\n",
- act > act_max ? "Illegal" : "Driver unsupported",
- act);
+ pr_warn_once("%s XDP return value %u, expect packet loss!\n",
+ act > act_max ? "Illegal" : "Driver unsupported",
+ act);
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b740a74f06f2..4dac27c98623 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1149,6 +1149,7 @@ proto_again:
VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
}
key_vlan->vlan_tpid = saved_vlan_tpid;
+ key_vlan->vlan_eth_type = proto;
}
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index a5502c5aa44e..bf270b6a99b4 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -158,10 +158,8 @@ static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
return dst->lwtstate->orig_output(net, sk, skb);
}
-static int xmit_check_hhlen(struct sk_buff *skb)
+static int xmit_check_hhlen(struct sk_buff *skb, int hh_len)
{
- int hh_len = skb_dst(skb)->dev->hard_header_len;
-
if (skb_headroom(skb) < hh_len) {
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
@@ -273,6 +271,7 @@ static int bpf_xmit(struct sk_buff *skb)
bpf = bpf_lwt_lwtunnel(dst->lwtstate);
if (bpf->xmit.prog) {
+ int hh_len = dst->dev->hard_header_len;
__be16 proto = skb->protocol;
int ret;
@@ -290,7 +289,7 @@ static int bpf_xmit(struct sk_buff *skb)
/* If the header was expanded, headroom might be too
* small for L2 header to come, expand as needed.
*/
- ret = xmit_check_hhlen(skb);
+ ret = xmit_check_hhlen(skb, hh_len);
if (unlikely(ret))
return ret;
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 2f9c0de533c7..0b64f015b3b0 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -190,6 +190,10 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
if (nla_entype) {
+ if (nla_len(nla_entype) < sizeof(u16)) {
+ NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE");
+ return -EINVAL;
+ }
encap_type = nla_get_u16(nla_entype);
if (lwtunnel_valid_encap_type(encap_type,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 02e55041a881..8b6140e67e7f 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -734,11 +734,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
ASSERT_RTNL();
- n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
+ n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL);
if (!n)
goto out;
- n->protocol = 0;
write_pnet(&n->net, net);
memcpy(n->key, pkey, key_len);
n->dev = dev;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 36347933ec3a..61f5570645e3 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -182,12 +182,23 @@ static const struct seq_operations softnet_seq_ops = {
.show = softnet_seq_show,
};
-static void *ptype_get_idx(loff_t pos)
+static void *ptype_get_idx(struct seq_file *seq, loff_t pos)
{
+ struct list_head *ptype_list = NULL;
struct packet_type *pt = NULL;
+ struct net_device *dev;
loff_t i = 0;
int t;
+ for_each_netdev_rcu(seq_file_net(seq), dev) {
+ ptype_list = &dev->ptype_all;
+ list_for_each_entry_rcu(pt, ptype_list, list) {
+ if (i == pos)
+ return pt;
+ ++i;
+ }
+ }
+
list_for_each_entry_rcu(pt, &ptype_all, list) {
if (i == pos)
return pt;
@@ -208,22 +219,40 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
rcu_read_lock();
- return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
+ return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
+ struct net_device *dev;
struct packet_type *pt;
struct list_head *nxt;
int hash;
++*pos;
if (v == SEQ_START_TOKEN)
- return ptype_get_idx(0);
+ return ptype_get_idx(seq, 0);
pt = v;
nxt = pt->list.next;
+ if (pt->dev) {
+ if (nxt != &pt->dev->ptype_all)
+ goto found;
+
+ dev = pt->dev;
+ for_each_netdev_continue_rcu(seq_file_net(seq), dev) {
+ if (!list_empty(&dev->ptype_all)) {
+ nxt = dev->ptype_all.next;
+ goto found;
+ }
+ }
+
+ nxt = ptype_all.next;
+ goto ptype_all;
+ }
+
if (pt->type == htons(ETH_P_ALL)) {
+ptype_all:
if (nxt != &ptype_all)
goto found;
hash = 0;
@@ -252,7 +281,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v)
if (v == SEQ_START_TOKEN)
seq_puts(seq, "Type Device Function\n");
- else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
+ else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) &&
+ (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) {
if (pt->type == htons(ETH_P_ALL))
seq_puts(seq, "ALL ");
else
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 05b0c60bfba2..ad45f13a0370 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -212,7 +212,7 @@ static ssize_t speed_show(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
- if (netif_running(netdev)) {
+ if (netif_running(netdev) && netif_device_present(netdev)) {
struct ethtool_link_ksettings cmd;
if (!__ethtool_get_link_ksettings(netdev, &cmd))
@@ -1661,6 +1661,9 @@ static void remove_queue_kobjects(struct net_device *dev)
net_rx_queue_update_kobjects(dev, real_rx, 0);
netdev_queue_update_kobjects(dev, real_tx, 0);
+
+ dev->real_num_rx_queues = 0;
+ dev->real_num_tx_queues = 0;
#ifdef CONFIG_SYSFS
kset_unregister(dev->queues_kset);
#endif
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cd1d40195e46..62a972f04cef 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -168,8 +168,10 @@ static void ops_exit_list(const struct pernet_operations *ops,
{
struct net *net;
if (ops->exit) {
- list_for_each_entry(net, net_exit_list, exit_list)
+ list_for_each_entry(net, net_exit_list, exit_list) {
ops->exit(net);
+ cond_resched();
+ }
}
if (ops->exit_batch)
ops->exit_batch(net_exit_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 55c0f32b9375..dbc9b2f53649 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3022,8 +3022,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
unsigned char name_assign_type = NET_NAME_USER;
struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
- const struct rtnl_link_ops *m_ops = NULL;
- struct net_device *master_dev = NULL;
+ const struct rtnl_link_ops *m_ops;
+ struct net_device *master_dev;
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
struct nlattr *tb[IFLA_MAX + 1];
@@ -3063,6 +3063,8 @@ replay:
dev = NULL;
}
+ master_dev = NULL;
+ m_ops = NULL;
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
if (master_dev)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a172d2fe4ff1..9d5be649ec8f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -768,7 +768,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
if (dev)
- printk("%sdev name=%s feat=0x%pNF\n",
+ printk("%sdev name=%s feat=%pNF\n",
level, dev->name, &dev->features);
if (sk)
printk("%ssk family=%hu type=%u proto=%u\n",
@@ -2165,7 +2165,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
/* Free pulled out fragments. */
while ((list = skb_shinfo(skb)->frag_list) != insp) {
skb_shinfo(skb)->frag_list = list->next;
- kfree_skb(list);
+ consume_skb(list);
}
/* And insert new clone at head. */
if (clone) {
@@ -5872,7 +5872,7 @@ static int pskb_carve_frag_list(struct sk_buff *skb,
/* Free pulled out fragments. */
while ((list = shinfo->frag_list) != insp) {
shinfo->frag_list = list->next;
- kfree_skb(list);
+ consume_skb(list);
}
/* And insert new clone at head. */
if (clone) {
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 17cc1edd149c..a606ad8e8be2 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -27,6 +27,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
int elem_first_coalesce)
{
struct page_frag *pfrag = sk_page_frag(sk);
+ u32 osize = msg->sg.size;
int ret = 0;
len -= msg->sg.size;
@@ -35,13 +36,17 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
u32 orig_offset;
int use, i;
- if (!sk_page_frag_refill(sk, pfrag))
- return -ENOMEM;
+ if (!sk_page_frag_refill(sk, pfrag)) {
+ ret = -ENOMEM;
+ goto msg_trim;
+ }
orig_offset = pfrag->offset;
use = min_t(int, len, pfrag->size - orig_offset);
- if (!sk_wmem_schedule(sk, use))
- return -ENOMEM;
+ if (!sk_wmem_schedule(sk, use)) {
+ ret = -ENOMEM;
+ goto msg_trim;
+ }
i = msg->sg.end;
sk_msg_iter_var_prev(i);
@@ -71,6 +76,10 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
}
return ret;
+
+msg_trim:
+ sk_msg_trim(sk, msg, osize);
+ return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_alloc);
diff --git a/net/core/sock.c b/net/core/sock.c
index 57b7a10703c3..c84f68bff7f5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2355,8 +2355,6 @@ static void sk_leave_memory_pressure(struct sock *sk)
}
}
-/* On 32bit arches, an skb frag is limited to 2^15 */
-#define SKB_FRAG_PAGE_ORDER get_order(32768)
DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
/**
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index df52061f99f7..2646e8f98f67 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
if (err)
goto free_stab;
- stab->sks = bpf_map_area_alloc(stab->map.max_entries *
+ stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries *
sizeof(struct sock *),
stab->map.numa_node);
if (stab->sks)
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-09 21:38:26 +0000