summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c5
-rw-r--r--net/ipv4/esp4.c7
-rw-r--r--net/ipv4/esp4_offload.c6
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/fib_lookup.h7
-rw-r--r--net/ipv4/fib_semantics.c6
-rw-r--r--net/ipv4/fib_trie.c22
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/ping.c10
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c43
-rw-r--r--net/ipv4/udp_tunnel_nic.c2
13 files changed, 75 insertions, 44 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9c465bac1eb0..72fde2888ad2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1376,8 +1376,11 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
}
ops = rcu_dereference(inet_offloads[proto]);
- if (likely(ops && ops->callbacks.gso_segment))
+ if (likely(ops && ops->callbacks.gso_segment)) {
segs = ops->callbacks.gso_segment(skb, features);
+ if (!segs)
+ skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
+ }
if (IS_ERR_OR_NULL(segs))
goto out;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 851f542928a3..70e6c87fbe3d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -446,6 +446,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
+ unsigned int allocsz;
/* this is non-NULL only with TCP/UDP Encapsulation */
if (x->encap) {
@@ -455,6 +456,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
return err;
}
+ allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
+ if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ goto cow;
+
if (!skb_cloned(skb)) {
if (tailen <= skb_tailroom(skb)) {
nfrags = 1;
@@ -671,7 +676,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
u32 padto;
- padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
+ padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
if (skb->len < padto)
esp.tfclen = padto - skb->len;
}
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index d87f02a6e934..935026f4c807 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -110,8 +110,7 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
struct sk_buff *skb,
netdev_features_t features)
{
- __skb_push(skb, skb->mac_len);
- return skb_mac_gso_segment(skb, features);
+ return skb_eth_gso_segment(skb, features, htons(ETH_P_IP));
}
static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
@@ -160,6 +159,9 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
}
+ if (proto == IPPROTO_IPV6)
+ skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
+
__skb_pull(skb, skb_transport_offset(skb));
ops = rcu_dereference(inet_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4d61ddd8a0ec..85117b45216d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -436,6 +436,9 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
if (net->ipv4.fib_has_custom_local_routes ||
fib4_has_custom_rules(net))
goto full_check;
+ /* Within the same container, it is regarded as a martian source,
+ * and the same host but different containers are not.
+ */
if (inet_lookup_ifaddr_rcu(net, src))
return -EINVAL;
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index e184bcb19943..78e40ea42e58 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -16,10 +16,9 @@ struct fib_alias {
u8 fa_slen;
u32 tb_id;
s16 fa_default;
- u8 offload:1,
- trap:1,
- offload_failed:1,
- unused:5;
+ u8 offload;
+ u8 trap;
+ u8 offload_failed;
struct rcu_head rcu;
};
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b4589861b84c..2dd375f7407b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -525,9 +525,9 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
fri.dst_len = dst_len;
fri.tos = fa->fa_tos;
fri.type = fa->fa_type;
- fri.offload = fa->offload;
- fri.trap = fa->trap;
- fri.offload_failed = fa->offload_failed;
+ fri.offload = READ_ONCE(fa->offload);
+ fri.trap = READ_ONCE(fa->trap);
+ fri.offload_failed = READ_ONCE(fa->offload_failed);
err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 8060524f4256..f7f74d5c14da 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1047,19 +1047,23 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
if (!fa_match)
goto out;
- if (fa_match->offload == fri->offload && fa_match->trap == fri->trap &&
- fa_match->offload_failed == fri->offload_failed)
+ /* These are paired with the WRITE_ONCE() happening in this function.
+ * The reason is that we are only protected by RCU at this point.
+ */
+ if (READ_ONCE(fa_match->offload) == fri->offload &&
+ READ_ONCE(fa_match->trap) == fri->trap &&
+ READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
goto out;
- fa_match->offload = fri->offload;
- fa_match->trap = fri->trap;
+ WRITE_ONCE(fa_match->offload, fri->offload);
+ WRITE_ONCE(fa_match->trap, fri->trap);
/* 2 means send notifications only if offload_failed was changed. */
if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
- fa_match->offload_failed == fri->offload_failed)
+ READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
goto out;
- fa_match->offload_failed = fri->offload_failed;
+ WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
if (!net->ipv4.sysctl_fib_notify_on_flag_change)
goto out;
@@ -2297,9 +2301,9 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
fri.dst_len = KEYLENGTH - fa->fa_slen;
fri.tos = fa->fa_tos;
fri.type = fa->fa_type;
- fri.offload = fa->offload;
- fri.trap = fa->trap;
- fri.offload_failed = fa->offload_failed;
+ fri.offload = READ_ONCE(fa->offload);
+ fri.trap = READ_ONCE(fa->trap);
+ fri.offload_failed = READ_ONCE(fa->offload_failed);
err = fib_dump_info(skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 139cec29ed06..7911916a480b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -991,7 +991,7 @@ static int __ip_append_data(struct sock *sk,
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
- tskey = sk->sk_tskey++;
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 07274619b9ea..29bbe2b08ae9 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -256,7 +256,9 @@ static int __net_init ipmr_rules_init(struct net *net)
return 0;
err2:
+ rtnl_lock();
ipmr_free_table(mrt);
+ rtnl_unlock();
err1:
fib_rules_unregister(ops);
return err;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index bcf7bc71cb56..3ee947557b88 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -172,16 +172,22 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
struct sock *sk = NULL;
struct inet_sock *isk;
struct hlist_nulls_node *hnode;
- int dif = skb->dev->ifindex;
+ int dif, sdif;
if (skb->protocol == htons(ETH_P_IP)) {
+ dif = inet_iif(skb);
+ sdif = inet_sdif(skb);
pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
(int)ident, &ip_hdr(skb)->daddr, dif);
#if IS_ENABLED(CONFIG_IPV6)
} else if (skb->protocol == htons(ETH_P_IPV6)) {
+ dif = inet6_iif(skb);
+ sdif = inet6_sdif(skb);
pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
(int)ident, &ipv6_hdr(skb)->daddr, dif);
#endif
+ } else {
+ return NULL;
}
read_lock_bh(&ping_table.lock);
@@ -221,7 +227,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
}
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != inet_sdif(skb))
+ sk->sk_bound_dev_if != sdif)
continue;
sock_hold(sk);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff6f91cdb6c4..f33ad1f383b6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3395,8 +3395,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
fa->fa_tos == fri.tos &&
fa->fa_info == res.fi &&
fa->fa_type == fri.type) {
- fri.offload = fa->offload;
- fri.trap = fa->trap;
+ fri.offload = READ_ONCE(fa->offload);
+ fri.trap = READ_ONCE(fa->trap);
break;
}
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bdf108f544a4..28ff2a820f7c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -937,6 +937,22 @@ void tcp_remove_empty_skb(struct sock *sk)
}
}
+/* skb changing from pure zc to mixed, must charge zc */
+static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
+{
+ if (unlikely(skb_zcopy_pure(skb))) {
+ u32 extra = skb->truesize -
+ SKB_TRUESIZE(skb_end_offset(skb));
+
+ if (!sk_wmem_schedule(sk, extra))
+ return -ENOMEM;
+
+ sk_mem_charge(sk, extra);
+ skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
+ }
+ return 0;
+}
+
static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
struct page *page, int offset, size_t *size)
{
@@ -972,7 +988,7 @@ new_segment:
tcp_mark_push(tp, skb);
goto new_segment;
}
- if (!sk_wmem_schedule(sk, copy))
+ if (tcp_downgrade_zcopy_pure(sk, skb) || !sk_wmem_schedule(sk, copy))
return NULL;
if (can_coalesce) {
@@ -1320,19 +1336,8 @@ new_segment:
copy = min_t(int, copy, pfrag->size - pfrag->offset);
- /* skb changing from pure zc to mixed, must charge zc */
- if (unlikely(skb_zcopy_pure(skb))) {
- u32 extra = skb->truesize -
- SKB_TRUESIZE(skb_end_offset(skb));
-
- if (!sk_wmem_schedule(sk, extra))
- goto wait_for_space;
-
- sk_mem_charge(sk, extra);
- skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
- }
-
- if (!sk_wmem_schedule(sk, copy))
+ if (tcp_downgrade_zcopy_pure(sk, skb) ||
+ !sk_wmem_schedule(sk, copy))
goto wait_for_space;
err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
@@ -1679,11 +1684,13 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
if (!copied)
copied = used;
break;
- } else if (used <= len) {
- seq += used;
- copied += used;
- offset += used;
}
+ if (WARN_ON_ONCE(used > len))
+ used = len;
+ seq += used;
+ copied += used;
+ offset += used;
+
/* If recv_actor drops the lock (e.g. TCP splice
* receive) the skb pointer might be invalid when
* getting here: tcp_collapse might have deleted it
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index b91003538d87..bc3a043a5d5c 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -846,7 +846,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
list_for_each_entry(node, &info->shared->devices, list)
if (node->dev == dev)
break;
- if (node->dev != dev)
+ if (list_entry_is_head(node, &info->shared->devices, list))
return;
list_del(&node->list);
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-29 10:57:47 +0000