aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c1
-rw-r--r--net/ipv4/fib_frontend.c5
-rw-r--r--net/ipv4/icmp.c12
-rw-r--r--net/ipv4/inet_connection_sock.c44
-rw-r--r--net/ipv4/inet_fragment.c70
-rw-r--r--net/ipv4/ip_fragment.c2
-rw-r--r--net/ipv4/ip_gre.c5
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/netfilter/Kconfig1
-rw-r--r--net/ipv4/netfilter/arp_tables.c8
-rw-r--r--net/ipv4/netfilter/ip_tables.c8
-rw-r--r--net/ipv4/nexthop.c4
-rw-r--r--net/ipv4/raw.c3
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_ao.c3
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/tcp_output.c4
-rw-r--r--net/ipv4/udp.c15
-rw-r--r--net/ipv4/udp_offload.c38
-rw-r--r--net/ipv4/xfrm4_input.c6
22 files changed, 202 insertions, 52 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55bd72997b3106..fafb123f798be3 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
/* The above will be needed by the transport layer if there is one
* immediately following this IP hdr.
*/
+ NAPI_GRO_CB(skb)->inner_network_offset = off;
/* Note : No need to call skb_gro_postpull_rcsum() here,
* as we already checked checksum over ipv4 header was 0
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 48741352a88a72..c484b1c0fc00a7 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1050,6 +1050,11 @@ next:
e++;
}
}
+
+ /* Don't let NLM_DONE coalesce into a message, even if it could.
+ * Some user space expects NLM_DONE in a separate recv().
+ */
+ err = skb->len;
out:
cb->args[1] = e;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e63a3bf9961762..437e782b9663bb 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -92,6 +92,7 @@
#include <net/inet_common.h>
#include <net/ip_fib.h>
#include <net/l3mdev.h>
+#include <net/addrconf.h>
/*
* Build xmit assembly blocks
@@ -1032,6 +1033,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
struct icmp_ext_hdr *ext_hdr, _ext_hdr;
struct icmp_ext_echo_iio *iio, _iio;
struct net *net = dev_net(skb->dev);
+ struct inet6_dev *in6_dev;
+ struct in_device *in_dev;
struct net_device *dev;
char buff[IFNAMSIZ];
u16 ident_len;
@@ -1115,10 +1118,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
/* Fill bits in reply message */
if (dev->flags & IFF_UP)
status |= ICMP_EXT_ECHOREPLY_ACTIVE;
- if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list)
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev && rcu_access_pointer(in_dev->ifa_list))
status |= ICMP_EXT_ECHOREPLY_IPV4;
- if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
+
+ in6_dev = __in6_dev_get(dev);
+ if (in6_dev && !list_empty(&in6_dev->addr_list))
status |= ICMP_EXT_ECHOREPLY_IPV6;
+
dev_put(dev);
icmphdr->un.echo.sequence |= htons(status);
return true;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7d8090f109ef4e..3b38610958ee4b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
kuid_t sk_uid, bool relax,
bool reuseport_cb_ok, bool reuseport_ok)
{
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- return false;
+ if (ipv6_only_sock(sk2)) {
+ if (sk->sk_family == AF_INET)
+ return false;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ return false;
+#endif
+ }
return inet_bind_conflict(sk, sk2, sk_uid, relax,
reuseport_cb_ok, reuseport_ok);
@@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
struct sock_reuseport *reuseport_cb;
struct inet_bind_hashbucket *head2;
struct inet_bind2_bucket *tb2;
+ bool conflict = false;
bool reuseport_cb_ok;
rcu_read_lock();
@@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l
spin_lock(&head2->lock);
- inet_bind_bucket_for_each(tb2, &head2->chain)
- if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
- break;
+ inet_bind_bucket_for_each(tb2, &head2->chain) {
+ if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk))
+ continue;
- if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok,
- reuseport_ok)) {
- spin_unlock(&head2->lock);
- return true;
+ if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok))
+ continue;
+
+ conflict = true;
+ break;
}
spin_unlock(&head2->lock);
- return false;
+
+ return conflict;
}
/*
@@ -771,6 +781,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
}
EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
+void inet_csk_clear_xmit_timers_sync(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* ongoing timer handlers need to acquire socket lock. */
+ sock_not_owned_by_me(sk);
+
+ icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+
+ sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
+ sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
+ sk_stop_timer_sync(sk, &sk->sk_timer);
+}
+
void inet_csk_delete_keepalive_timer(struct sock *sk)
{
sk_stop_timer(sk, &sk->sk_timer);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7072fc0783ef56..c88c9034d63004 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,8 @@
#include <net/ip.h>
#include <net/ipv6.h>
+#include "../core/sock_destructor.h"
+
/* Use skb->cb to track consecutive/adjacent fragments coming at
* the end of the queue. Nodes in the rb-tree queue will
* contain "runs" of one or more adjacent fragments.
@@ -39,6 +41,7 @@ struct ipfrag_skb_cb {
};
struct sk_buff *next_frag;
int frag_run_len;
+ int ip_defrag_offset;
};
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
@@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
*/
if (!last)
fragrun_create(q, skb); /* First fragment. */
- else if (last->ip_defrag_offset + last->len < end) {
+ else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) {
/* This is the common case: skb goes to the end. */
/* Detect and discard overlaps. */
- if (offset < last->ip_defrag_offset + last->len)
+ if (offset < FRAG_CB(last)->ip_defrag_offset + last->len)
return IPFRAG_OVERLAP;
- if (offset == last->ip_defrag_offset + last->len)
+ if (offset == FRAG_CB(last)->ip_defrag_offset + last->len)
fragrun_append_to_last(q, skb);
else
fragrun_create(q, skb);
@@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
parent = *rbn;
curr = rb_to_skb(parent);
- curr_run_end = curr->ip_defrag_offset +
+ curr_run_end = FRAG_CB(curr)->ip_defrag_offset +
FRAG_CB(curr)->frag_run_len;
- if (end <= curr->ip_defrag_offset)
+ if (end <= FRAG_CB(curr)->ip_defrag_offset)
rbn = &parent->rb_left;
else if (offset >= curr_run_end)
rbn = &parent->rb_right;
- else if (offset >= curr->ip_defrag_offset &&
+ else if (offset >= FRAG_CB(curr)->ip_defrag_offset &&
end <= curr_run_end)
return IPFRAG_DUP;
else
@@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
rb_insert_color(&skb->rbnode, &q->rb_fragments);
}
- skb->ip_defrag_offset = offset;
+ FRAG_CB(skb)->ip_defrag_offset = offset;
return IPFRAG_OK;
}
@@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
struct sk_buff *parent)
{
struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
- struct sk_buff **nextp;
+ void (*destructor)(struct sk_buff *);
+ unsigned int orig_truesize = 0;
+ struct sk_buff **nextp = NULL;
+ struct sock *sk = skb->sk;
int delta;
+ if (sk && is_skb_wmem(skb)) {
+ /* TX: skb->sk might have been passed as argument to
+ * dst->output and must remain valid until tx completes.
+ *
+ * Move sk to reassembled skb and fix up wmem accounting.
+ */
+ orig_truesize = skb->truesize;
+ destructor = skb->destructor;
+ }
+
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
- if (!fp)
- return NULL;
+ if (!fp) {
+ head = skb;
+ goto out_restore_sk;
+ }
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
if (RB_EMPTY_NODE(&skb->rbnode))
FRAG_CB(parent)->next_frag = fp;
@@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
&q->rb_fragments);
if (q->fragments_tail == skb)
q->fragments_tail = fp;
+
+ if (orig_truesize) {
+ /* prevent skb_morph from releasing sk */
+ skb->sk = NULL;
+ skb->destructor = NULL;
+ }
skb_morph(skb, head);
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
rb_replace_node(&head->rbnode, &skb->rbnode,
@@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
consume_skb(head);
head = skb;
}
- WARN_ON(head->ip_defrag_offset != 0);
+ WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0);
delta = -head->truesize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
- return NULL;
+ goto out_restore_sk;
delta += head->truesize;
if (delta)
@@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
- return NULL;
+ goto out_restore_sk;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
@@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
nextp = &skb_shinfo(head)->frag_list;
}
+out_restore_sk:
+ if (orig_truesize) {
+ int ts_delta = head->truesize - orig_truesize;
+
+ /* if this reassembled skb is fragmented later,
+ * fraglist skbs will get skb->sk assigned from head->sk,
+ * and each frag skb will be released via sock_wfree.
+ *
+ * Update sk_wmem_alloc.
+ */
+ head->sk = sk;
+ head->destructor = destructor;
+ refcount_add(ts_delta, &sk->sk_wmem_alloc);
+ }
+
return nextp;
}
EXPORT_SYMBOL(inet_frag_reasm_prepare);
@@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
void *reasm_data, bool try_coalesce)
{
+ struct sock *sk = is_skb_wmem(head) ? head->sk : NULL;
+ const unsigned int head_truesize = head->truesize;
struct sk_buff **nextp = reasm_data;
struct rb_node *rbn;
struct sk_buff *fp;
@@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
head->prev = NULL;
head->tstamp = q->stamp;
head->mono_delivery_time = q->mono_delivery_time;
+
+ if (sk)
+ refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(inet_frag_reasm_finish);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a4941f53b52372..fb947d1613fe2b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
}
skb_dst_drop(skb);
+ skb_orphan(skb);
return -EINPROGRESS;
insert_error:
@@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
struct ipq *qp;
__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
- skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7b16c211b90447..57ddcd8c62f67e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
tpi->flags | TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
} else {
+ if (unlikely(!pskb_may_pull(skb,
+ gre_hdr_len + sizeof(*ershdr))))
+ return PACKET_REJECT;
+
ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
ver = ershdr->ver;
+ iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
tpi->flags | TUNNEL_KEY,
iph->saddr, iph->daddr, tpi->key);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1fe794967211e2..39229fd0601a11 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
* by icmp_hdr(skb)->type.
*/
if (sk->sk_type == SOCK_RAW &&
- !inet_test_bit(HDRINCL, sk))
+ !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH))
icmp_type = fl4->fl4_icmp_type;
else
icmp_type = icmp_hdr(skb)->type;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 8f6e950163a792..1b991b889506a9 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -329,6 +329,7 @@ config NFT_COMPAT_ARP
config IP_NF_ARPFILTER
tristate "arptables-legacy packet filtering support"
select IP_NF_ARPTABLES
+ select NETFILTER_FAMILY_ARP
depends on NETFILTER_XTABLES
help
ARP packet filtering defines a table `filter', which has a series of
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 2407066b0fec11..14365b20f1c5c0 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct arpt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -964,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1254,6 +1258,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct arpt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1262,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 7da1df4997d057..fe89a056eb06c4 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1108,6 +1108,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ipt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1116,6 +1118,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1492,6 +1496,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
void *loc_cpu_entry;
struct ipt_entry *iter;
+ if (len < sizeof(tmp))
+ return -EINVAL;
if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1500,6 +1506,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 74928a9d1aa48b..535856b0f0edce 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -768,8 +768,10 @@ static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used)
struct net *net = nh->net;
int err;
- if (nexthop_notifiers_is_empty(net))
+ if (nexthop_notifiers_is_empty(net)) {
+ *hw_stats_used = false;
return 0;
+ }
err = nh_notifier_grp_hw_stats_init(&info, nh);
if (err)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dcb11f22cbf2b4..4cb43401e0e06c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -612,6 +612,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
+ fl4.fl4_icmp_type = 0;
+ fl4.fl4_icmp_code = 0;
+
if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c8f76f56dc1653..b814fdab19f710 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -926,13 +926,11 @@ void ip_rt_send_redirect(struct sk_buff *skb)
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
-#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (log_martians &&
+ if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
-#endif
}
out_put_peer:
inet_putpeer(peer);
@@ -2168,6 +2166,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
int err = -EINVAL;
u32 tag = 0;
+ if (!in_dev)
+ return -EINVAL;
+
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d20b62d521712a..66d77faca64f6d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2710,7 +2710,7 @@ void tcp_shutdown(struct sock *sk, int how)
/* If we've already sent a FIN, or it's a closed state, skip this. */
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_SYN_SENT |
- TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
+ TCPF_CLOSE_WAIT)) {
/* Clear out any half completed packets. FIN if needed. */
if (tcp_close_state(sk))
tcp_send_fin(sk);
@@ -2819,7 +2819,7 @@ void __tcp_close(struct sock *sk, long timeout)
* machine. State transitions:
*
* TCP_ESTABLISHED -> TCP_FIN_WAIT1
- * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible)
+ * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult)
* TCP_CLOSE_WAIT -> TCP_LAST_ACK
*
* are legal only when FIN has been sent (i.e. in window),
@@ -2931,6 +2931,8 @@ void tcp_close(struct sock *sk, long timeout)
lock_sock(sk);
__tcp_close(sk, timeout);
release_sock(sk);
+ if (!sk->sk_net_refcnt)
+ inet_csk_clear_xmit_timers_sync(sk);
sock_put(sk);
}
EXPORT_SYMBOL(tcp_close);
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 3afeeb68e8a7e2..781b67a525719a 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1068,6 +1068,7 @@ void tcp_ao_connect_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_ao_info *ao_info;
+ struct hlist_node *next;
union tcp_ao_addr *addr;
struct tcp_ao_key *key;
int family, l3index;
@@ -1090,7 +1091,7 @@ void tcp_ao_connect_init(struct sock *sk)
l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
sk->sk_bound_dev_if);
- hlist_for_each_entry_rcu(key, &ao_info->head, node) {
+ hlist_for_each_entry_safe(key, next, &ao_info->head, node) {
if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1))
continue;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5d874817a78db3..a140d9f7a0a36e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6761,6 +6761,8 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tcp_initialize_rcv_mss(sk);
tcp_fast_path_on(tp);
+ if (sk->sk_shutdown & SEND_SHUTDOWN)
+ tcp_shutdown(sk, SEND_SHUTDOWN);
break;
case TCP_FIN_WAIT1: {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a22ee58387518a..e0cef75f85fb92 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -154,6 +154,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
if (tcptw->tw_ts_recent_stamp &&
(!twp || (reuse && time_after32(ktime_get_seconds(),
tcptw->tw_ts_recent_stamp)))) {
+ /* inet_twsk_hashdance() sets sk_refcnt after putting twsk
+ * and releasing the bucket lock.
+ */
+ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
+ return 0;
+
/* In case of repair and re-using TIME-WAIT sockets we still
* want to be sure that it is safe as above but honor the
* sequence numbers and time stamps set as part of the repair
@@ -174,7 +180,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
}
- sock_hold(sktw);
+
return 1;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e3167ad965676f..02caeb7bcf6342 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3563,7 +3563,9 @@ void tcp_send_fin(struct sock *sk)
return;
}
} else {
- skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+ skb = alloc_skb_fclone(MAX_TCP_HEADER,
+ sk_gfp_mask(sk, GFP_ATOMIC |
+ __GFP_NOWARN));
if (unlikely(!skb))
return;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 661d0e0d273f61..b32cf2eeeb41d1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
struct net *net = dev_net(skb->dev);
int iif, sdif;
@@ -582,6 +583,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk,
}
DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+EXPORT_SYMBOL(udp_encap_needed_key);
+
+#if IS_ENABLED(CONFIG_IPV6)
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+EXPORT_SYMBOL(udpv6_encap_needed_key);
+#endif
+
void udp_encap_enable(void)
{
static_branch_inc(&udp_encap_needed_key);
@@ -1116,16 +1124,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
- if (err > 0)
+ if (err > 0) {
err = ip_cmsg_send(sk, msg, &ipc,
sk->sk_family == AF_INET6);
+ connected = 0;
+ }
if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
if (ipc.opt)
free = 1;
- connected = 0;
}
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b9880743765c6c..8721fe5beca2be 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -449,8 +449,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
NAPI_GRO_CB(p)->count++;
p->data_len += skb->len;
- /* sk owenrship - if any - completely transferred to the aggregated packet */
+ /* sk ownership - if any - completely transferred to the aggregated packet */
skb->destructor = NULL;
+ skb->sk = NULL;
p->truesize += skb->truesize;
p->len += skb->len;
@@ -470,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *p;
unsigned int ulen;
int ret = 0;
+ int flush;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
@@ -503,13 +505,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
return p;
}
+ flush = NAPI_GRO_CB(p)->flush;
+
+ if (NAPI_GRO_CB(p)->flush_id != 1 ||
+ NAPI_GRO_CB(p)->count != 1 ||
+ !NAPI_GRO_CB(p)->is_atomic)
+ flush |= NAPI_GRO_CB(p)->flush_id;
+ else
+ NAPI_GRO_CB(p)->is_atomic = false;
+
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
* leading to excessive truesize values.
* On len mismatch merge the first packet shorter than gso_size,
* otherwise complete the GRO packet.
*/
- if (ulen > ntohs(uh2->len)) {
+ if (ulen > ntohs(uh2->len) || flush) {
pp = p;
} else {
if (NAPI_GRO_CB(skb)->is_flist) {
@@ -551,11 +562,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
unsigned int off = skb_gro_offset(skb);
int flush = 1;
- /* we can do L4 aggregation only if the packet can't land in a tunnel
- * otherwise we could corrupt the inner stream
+ /* We can do L4 aggregation only if the packet can't land in a tunnel
+ * otherwise we could corrupt the inner stream. Detecting such packets
+ * cannot be foolproof and the aggregation might still happen in some
+ * cases. Such packets should be caught in udp_unexpected_gso later.
*/
NAPI_GRO_CB(skb)->is_flist = 0;
if (!sk || !udp_sk(sk)->gro_receive) {
+ /* If the packet was locally encapsulated in a UDP tunnel that
+ * wasn't detected above, do not GRO.
+ */
+ if (skb->encapsulation)
+ goto out;
+
if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1;
@@ -709,7 +728,8 @@ EXPORT_SYMBOL(udp_gro_complete);
INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
/* do fraglist only if there is no outer UDP encap (or we already processed it) */
@@ -719,13 +739,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
- if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
- if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
- skb->csum_level++;
- } else {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->csum_level = 0;
- }
+ __skb_incr_checksum_unnecessary(skb);
return 0;
}
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index dae35101d18959..86382e08140ee0 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -63,7 +63,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
ip_send_check(iph);
if (xo && (xo->flags & XFRM_GRO)) {
- skb_mac_header_rebuild(skb);
+ /* The full l2 header needs to be preserved so that re-injecting the packet at l2
+ * works correctly in the presence of vlan tags.
+ */
+ skb_mac_header_rebuild_full(skb, xo->orig_mac_len);
+ skb_reset_network_header(skb);
skb_reset_transport_header(skb);
return 0;
}
generated by cgit 1.2.3-korg (git 2.43.0) at 2025-12-24 00:51:01 +0000