summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/devinet.c66
-rw-r--r--net/ipv4/esp4.c6
-rw-r--r--net/ipv4/inet_fragment.c20
-rw-r--r--net/ipv4/ip_fragment.c25
-rw-r--r--net/ipv4/ip_gre.c5
-rw-r--r--net/ipv4/ip_options.c5
-rw-r--r--net/ipv4/ipconfig.c3
-rw-r--r--net/ipv4/netfilter/Kconfig13
-rw-r--r--net/ipv4/syncookies.c4
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c7
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/tcp_output.c17
-rw-r--r--net/ipv4/udp.c7
15 files changed, 120 insertions, 77 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 68f6a94f766..c929d9c1c4b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1333,8 +1333,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
iph->frag_off |= htons(IP_MF);
offset += (skb->len - skb->mac_len - iph->ihl * 4);
} else {
- if (!(iph->frag_off & htons(IP_DF)))
- iph->id = htons(id++);
+ iph->id = htons(id++);
}
iph->tot_len = htons(skb->len - skb->mac_len);
iph->check = 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f678507bc82..c6287cd978c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -587,13 +587,16 @@ static void check_lifetime(struct work_struct *work)
{
unsigned long now, next, next_sec, next_sched;
struct in_ifaddr *ifa;
+ struct hlist_node *n;
int i;
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
- rcu_read_lock();
for (i = 0; i < IN4_ADDR_HSIZE; i++) {
+ bool change_needed = false;
+
+ rcu_read_lock();
hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) {
unsigned long age;
@@ -606,16 +609,7 @@ static void check_lifetime(struct work_struct *work)
if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
age >= ifa->ifa_valid_lft) {
- struct in_ifaddr **ifap ;
-
- rtnl_lock();
- for (ifap = &ifa->ifa_dev->ifa_list;
- *ifap != NULL; ifap = &ifa->ifa_next) {
- if (*ifap == ifa)
- inet_del_ifa(ifa->ifa_dev,
- ifap, 1);
- }
- rtnl_unlock();
+ change_needed = true;
} else if (ifa->ifa_preferred_lft ==
INFINITY_LIFE_TIME) {
continue;
@@ -625,10 +619,8 @@ static void check_lifetime(struct work_struct *work)
next = ifa->ifa_tstamp +
ifa->ifa_valid_lft * HZ;
- if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) {
- ifa->ifa_flags |= IFA_F_DEPRECATED;
- rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
- }
+ if (!(ifa->ifa_flags & IFA_F_DEPRECATED))
+ change_needed = true;
} else if (time_before(ifa->ifa_tstamp +
ifa->ifa_preferred_lft * HZ,
next)) {
@@ -636,8 +628,42 @@ static void check_lifetime(struct work_struct *work)
ifa->ifa_preferred_lft * HZ;
}
}
+ rcu_read_unlock();
+ if (!change_needed)
+ continue;
+ rtnl_lock();
+ hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) {
+ unsigned long age;
+
+ if (ifa->ifa_flags & IFA_F_PERMANENT)
+ continue;
+
+ /* We try to batch several events at once. */
+ age = (now - ifa->ifa_tstamp +
+ ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+
+ if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_valid_lft) {
+ struct in_ifaddr **ifap;
+
+ for (ifap = &ifa->ifa_dev->ifa_list;
+ *ifap != NULL; ifap = &(*ifap)->ifa_next) {
+ if (*ifap == ifa) {
+ inet_del_ifa(ifa->ifa_dev,
+ ifap, 1);
+ break;
+ }
+ }
+ } else if (ifa->ifa_preferred_lft !=
+ INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_preferred_lft &&
+ !(ifa->ifa_flags & IFA_F_DEPRECATED)) {
+ ifa->ifa_flags |= IFA_F_DEPRECATED;
+ rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
+ }
+ }
+ rtnl_unlock();
}
- rcu_read_unlock();
next_sec = round_jiffies_up(next);
next_sched = next;
@@ -802,8 +828,12 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg
if (nlh->nlmsg_flags & NLM_F_EXCL ||
!(nlh->nlmsg_flags & NLM_F_REPLACE))
return -EEXIST;
-
- set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft);
+ ifa = ifa_existing;
+ set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+ cancel_delayed_work(&check_lifetime_work);
+ schedule_delayed_work(&check_lifetime_work, 0);
+ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
+ blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
}
return 0;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 3b4f0cd2e63..4cfe34d4cc9 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
/* skb is pure payload to encrypt */
- err = -ENOMEM;
-
esp = x->data;
aead = esp->aead;
alen = crypto_aead_authsize(aead);
@@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
}
tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
- if (!tmp)
+ if (!tmp) {
+ err = -ENOMEM;
goto error;
+ }
seqhi = esp_tmp_seqhi(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 245ae078a07..f4fd23de9b1 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -21,6 +21,7 @@
#include <linux/rtnetlink.h>
#include <linux/slab.h>
+#include <net/sock.h>
#include <net/inet_frag.h>
static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -277,6 +278,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
__releases(&f->lock)
{
struct inet_frag_queue *q;
+ int depth = 0;
hlist_for_each_entry(q, &f->hash[hash], list) {
if (q->net == nf && f->match(q, key)) {
@@ -284,9 +286,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
read_unlock(&f->lock);
return q;
}
+ depth++;
}
read_unlock(&f->lock);
- return inet_frag_create(nf, f, key);
+ if (depth <= INETFRAGS_MAXDEPTH)
+ return inet_frag_create(nf, f, key);
+ else
+ return ERR_PTR(-ENOBUFS);
}
EXPORT_SYMBOL(inet_frag_find);
+
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+ const char *prefix)
+{
+ static const char msg[] = "inet_frag_find: Fragment hash bucket"
+ " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
+ ". Dropping fragment.\n";
+
+ if (PTR_ERR(q) == -ENOBUFS)
+ LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+}
+EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b6d30acb600..52c273ea05c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -248,8 +248,7 @@ static void ip_expire(unsigned long arg)
if (!head->dev)
goto out_rcu_unlock;
- /* skb dst is stale, drop it, and perform route lookup again */
- skb_dst_drop(head);
+ /* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
@@ -292,14 +291,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
- if (q == NULL)
- goto out_nomem;
-
+ if (IS_ERR_OR_NULL(q)) {
+ inet_frag_maybe_warn_overflow(q, pr_fmt());
+ return NULL;
+ }
return container_of(q, struct ipq, q);
-
-out_nomem:
- LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
- return NULL;
}
/* Is the fragment too far ahead to be part of ipq? */
@@ -526,9 +522,16 @@ found:
qp->q.max_size = skb->len + ihl;
if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- qp->q.meat == qp->q.len)
- return ip_frag_reasm(qp, prev, dev);
+ qp->q.meat == qp->q.len) {
+ unsigned long orefdst = skb->_skb_refdst;
+
+ skb->_skb_refdst = 0UL;
+ err = ip_frag_reasm(qp, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return err;
+ }
+ skb_dst_drop(skb);
inet_frag_lru_move(&qp->q);
return -EINPROGRESS;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d0ef0e674ec..91d66dbde9c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -798,10 +798,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
- if (skb->protocol == htons(ETH_P_IP))
- tiph = (const struct iphdr *)skb->data;
- else
- tiph = &tunnel->parms.iph;
+ tiph = (const struct iphdr *)skb->data;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 310a3647c83..ec7264514a8 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -370,7 +370,6 @@ int ip_options_compile(struct net *net,
}
switch (optptr[3]&0xF) {
case IPOPT_TS_TSONLY:
- opt->ts = optptr - iph;
if (skb)
timeptr = &optptr[optptr[2]-1];
opt->ts_needtime = 1;
@@ -381,7 +380,6 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 2;
goto error;
}
- opt->ts = optptr - iph;
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
@@ -396,7 +394,6 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 2;
goto error;
}
- opt->ts = optptr - iph;
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
@@ -429,12 +426,12 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 3;
goto error;
}
- opt->ts = optptr - iph;
if (skb) {
optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
opt->is_changed = 1;
}
}
+ opt->ts = optptr - iph;
break;
case IPOPT_RA:
if (optlen < 4) {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 98cbc687701..bf6c5cf31ae 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1522,7 +1522,8 @@ static int __init ip_auto_config(void)
}
for (i++; i < CONF_NAMESERVERS_MAX; i++)
if (ic_nameservers[i] != NONE)
- pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]);
+ pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]);
+ pr_cont("\n");
#endif /* !SILENT */
return 0;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index ce2d43e1f09..0d755c50994 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -36,19 +36,6 @@ config NF_CONNTRACK_PROC_COMPAT
If unsure, say Y.
-config IP_NF_QUEUE
- tristate "IP Userspace queueing via NETLINK (OBSOLETE)"
- depends on NETFILTER_ADVANCED
- help
- Netfilter has the ability to queue packets to user space: the
- netlink device can be used to access them using this driver.
-
- This option enables the old IPv4-only "ip_queue" implementation
- which has been obsoleted by the new "nfnetlink_queue" code (see
- CONFIG_NETFILTER_NETLINK_QUEUE).
-
- To compile it as a module, choose M here. If unsure, say N.
-
config IP_NF_IPTABLES
tristate "IP tables support (required for filtering/masq/NAT)"
default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index ef54377fb11..397e0f69435 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -349,8 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
- RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+ flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
(opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
ireq->loc_addr, th->source, th->dest);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 47e854fcae2..e2202079070 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -775,7 +775,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
* Make sure that we have exactly size bytes
* available to the caller, no more, no less.
*/
- skb->avail_size = size;
+ skb->reserved_tailroom = skb->end - skb->tail - size;
return skb;
}
__kfree_skb(skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0d9bdacce99..3bd55bad230 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2059,11 +2059,8 @@ void tcp_enter_loss(struct sock *sk, int how)
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- if (!how) {
- /* Push undo marker, if it was plain RTO and nothing
- * was retransmitted. */
- tp->undo_marker = tp->snd_una;
- } else {
+ tp->undo_marker = tp->snd_una;
+ if (how) {
tp->sacked_out = 0;
tp->fackets_out = 0;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4a8ec457310..d09203c6326 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -274,13 +274,6 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
struct inet_sock *inet = inet_sk(sk);
u32 mtu = tcp_sk(sk)->mtu_info;
- /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
- * send out by Linux are always <576bytes so they should go through
- * unfragmented).
- */
- if (sk->sk_state == TCP_LISTEN)
- return;
-
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -408,6 +401,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
+ /* We are not interested in TCP_LISTEN and open_requests
+ * (SYN-ACKs send out by Linux are always <576bytes so
+ * they should go through unfragmented).
+ */
+ if (sk->sk_state == TCP_LISTEN)
+ goto out;
+
tp->mtu_info = info;
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e2b4461074d..509912a5ff9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1298,7 +1298,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
eat = min_t(int, len, skb_headlen(skb));
if (eat) {
__skb_pull(skb, eat);
- skb->avail_size -= eat;
len -= eat;
if (!len)
return;
@@ -1810,8 +1809,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
goto send_now;
}
- /* Ok, it looks like it is advisable to defer. */
- tp->tso_deferred = 1 | (jiffies << 1);
+ /* Ok, it looks like it is advisable to defer.
+ * Do not rearm the timer if already set to not break TCP ACK clocking.
+ */
+ if (!tp->tso_deferred)
+ tp->tso_deferred = 1 | (jiffies << 1);
return true;
@@ -2386,8 +2388,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- /* make sure skb->data is aligned on arches that require it */
- if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+ /* make sure skb->data is aligned on arches that require it
+ * and check if ack-trimming & collapsing extended the headroom
+ * beyond what csum_start can cover.
+ */
+ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
+ skb_headroom(skb) >= 0xFFFF)) {
struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
GFP_ATOMIC);
return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
@@ -2707,6 +2713,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
skb_reserve(skb, MAX_TCP_HEADER);
skb_dst_set(skb, dst);
+ security_skb_owned_by(skb, sk);
mss = dst_metric_advmss(dst);
if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 265c42cf963..0a073a26372 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb)
void udp_destroy_sock(struct sock *sk)
{
+ struct udp_sock *up = udp_sk(sk);
bool slow = lock_sock_fast(sk);
udp_flush_pending_frames(sk);
unlock_sock_fast(sk, slow);
+ if (static_key_false(&udp_encap_needed) && up->encap_type) {
+ void (*encap_destroy)(struct sock *sk);
+ encap_destroy = ACCESS_ONCE(up->encap_destroy);
+ if (encap_destroy)
+ encap_destroy(sk);
+ }
}
/*
generated by cgit v1.2.3-70-g09d2 (git 2.51.2) at 2025-11-02 08:23:45 +0000