aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/arp.c6
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/inet_hashtables.c68
-rw-r--r--net/ipv4/ip_tunnel_core.c4
-rw-r--r--net/ipv4/netfilter/arp_tables.c14
-rw-r--r--net/ipv4/netfilter/ip_tables.c14
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/syncookies.c9
-rw-r--r--net/ipv4/tcp_bbr.c2
-rw-r--r--net/ipv4/tcp_bpf.c18
-rw-r--r--net/ipv4/tcp_cong.c5
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c33
-rw-r--r--net/ipv4/tcp_output.c9
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv4/udp_offload.c19
18 files changed, 167 insertions, 56 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 687971d83b4e..922dd73e5740 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh);
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
static void parp_redo(struct sk_buff *skb);
+static int arp_is_multicast(const void *pkey);
static const struct neigh_ops arp_generic_ops = {
.family = AF_INET,
@@ -156,6 +157,7 @@ struct neigh_table arp_tbl = {
.key_eq = arp_key_eq,
.constructor = arp_constructor,
.proxy_redo = parp_redo,
+ .is_multicast = arp_is_multicast,
.id = "arp_cache",
.parms = {
.tbl = &arp_tbl,
@@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb)
arp_process(dev_net(skb->dev), NULL, skb);
}
+static int arp_is_multicast(const void *pkey)
+{
+ return ipv4_is_multicast(*((__be32 *)pkey));
+}
/*
* Receive an arp request from the device layer.
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 86a23e4a6a50..cdf6ec5aa45d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
break;
case AF_INET6:
-#ifdef CONFIG_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
if (alen != sizeof(struct in6_addr)) {
NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
return -EINVAL;
@@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
if (has_gw && has_via) {
NL_SET_ERR_MSG(extack,
"Nexthop configuration can not contain both GATEWAY and VIA");
- goto errout;
+ return -EINVAL;
}
return 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4148f5f78f31..f60869acbef0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
- inet_ehash_insert(req_to_sk(req), NULL);
+ inet_ehash_insert(req_to_sk(req), NULL, NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 366a4507b5a3..93474b1bea4e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -479,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
- inet_rsk(reqsk)->ir_mark))
+ inet_rsk(reqsk)->ir_mark)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 8cbe74313f38..45fb450b4522 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -20,6 +20,9 @@
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/inet6_hashtables.h>
+#endif
#include <net/secure_seq.h>
#include <net/ip.h>
#include <net/tcp.h>
@@ -508,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk)
inet->inet_dport);
}
-/* insert a socket into ehash, and eventually remove another one
- * (The another one can be a SYN_RECV or TIMEWAIT
+/* Searches for an exsiting socket in the ehash bucket list.
+ * Returns true if found, false otherwise.
*/
-bool inet_ehash_insert(struct sock *sk, struct sock *osk)
+static bool inet_ehash_lookup_by_sk(struct sock *sk,
+ struct hlist_nulls_head *list)
+{
+ const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
+ const int sdif = sk->sk_bound_dev_if;
+ const int dif = sk->sk_bound_dev_if;
+ const struct hlist_nulls_node *node;
+ struct net *net = sock_net(sk);
+ struct sock *esk;
+
+ INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
+
+ sk_nulls_for_each_rcu(esk, node, list) {
+ if (esk->sk_hash != sk->sk_hash)
+ continue;
+ if (sk->sk_family == AF_INET) {
+ if (unlikely(INET_MATCH(esk, net, acookie,
+ sk->sk_daddr,
+ sk->sk_rcv_saddr,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (sk->sk_family == AF_INET6) {
+ if (unlikely(INET6_MATCH(esk, net,
+ &sk->sk_v6_daddr,
+ &sk->sk_v6_rcv_saddr,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#endif
+ }
+ return false;
+}
+
+/* Insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT)
+ * If an existing socket already exists, socket sk is not inserted,
+ * and sets found_dup_sk parameter to true.
+ */
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
@@ -530,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk)
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
ret = sk_nulls_del_node_init_rcu(osk);
+ } else if (found_dup_sk) {
+ *found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
+ if (*found_dup_sk)
+ ret = false;
}
+
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+
spin_unlock(lock);
+
return ret;
}
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
- bool ok = inet_ehash_insert(sk, osk);
+ bool ok = inet_ehash_insert(sk, osk, found_dup_sk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -583,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk)
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
- inet_ehash_nolisten(sk, osk);
+ inet_ehash_nolisten(sk, osk, NULL);
return 0;
}
WARN_ON(!sk_unhashed(sk));
@@ -679,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- inet_ehash_nolisten(sk, NULL);
+ inet_ehash_nolisten(sk, NULL, NULL);
spin_unlock_bh(&head->lock);
return 0;
}
@@ -758,7 +810,7 @@ ok:
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- inet_ehash_nolisten(sk, (struct sock *)tw);
+ inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 25f1caf5abf9..e25be2d01a7a 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -263,7 +263,7 @@ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu)
const struct icmphdr *icmph = icmp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
- if (mtu <= 576 || iph->frag_off != htons(IP_DF))
+ if (mtu < 576 || iph->frag_off != htons(IP_DF))
return 0;
if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) ||
@@ -359,7 +359,7 @@ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu)
__be16 frag_off;
int offset;
- if (mtu <= IPV6_MIN_MTU)
+ if (mtu < IPV6_MIN_MTU)
return 0;
if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d1e04d2b5170..563b62b76a5f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
local_bh_disable();
addend = xt_write_recseq_begin();
- private = READ_ONCE(table->private); /* Address dependency. */
+ private = rcu_access_pointer(table->private);
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct arpt_entry **)private->jumpstack[cpu];
@@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
@@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size,
unsigned int off, num;
const struct arpt_entry *e;
struct xt_counters *counters;
- struct xt_table_info *private = table->private;
+ struct xt_table_info *private = xt_table_get_private_protected(table);
int ret = 0;
void *loc_cpu_entry;
@@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
if (!IS_ERR(t)) {
struct arpt_getinfo info;
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
@@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
@@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
}
local_bh_disable();
- private = t->private;
+ private = xt_table_get_private_protected(t);
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
@@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
void __user *pos;
unsigned int size;
int ret = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f15bc21d7301..6e2851f8d3a3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb,
WARN_ON(!(table->valid_hooks & (1 << hook)));
local_bh_disable();
addend = xt_write_recseq_begin();
- private = READ_ONCE(table->private); /* Address dependency. */
+ private = rcu_access_pointer(table->private);
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct ipt_entry **)private->jumpstack[cpu];
@@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size,
unsigned int off, num;
const struct ipt_entry *e;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
int ret = 0;
const void *loc_cpu_entry;
@@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
t = xt_request_find_table_lock(net, AF_INET, name);
if (!IS_ERR(t)) {
struct ipt_getinfo info;
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
@@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
t = xt_find_table_lock(net, AF_INET, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
t, uptr->entrytable);
@@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
}
local_bh_disable();
- private = t->private;
+ private = xt_table_get_private_protected(t);
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
@@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
void __user *pos;
unsigned int size;
int ret = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index dc2a399cd9f4..9f43abeac3a8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3222,7 +3222,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
fl4.daddr = dst;
fl4.saddr = src;
- fl4.flowi4_tos = rtm->rtm_tos;
+ fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
fl4.flowi4_uid = uid;
@@ -3246,8 +3246,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
fl4.flowi4_iif = iif; /* for rt_fill_info */
skb->dev = dev;
skb->mark = mark;
- err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
- dev, &res);
+ err = ip_route_input_rcu(skb, dst, src,
+ rtm->rtm_tos & IPTOS_RT_MASK, dev,
+ &res);
rt = skb_rtable(skb);
if (err == 0 && rt->dst.error)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6ac473b47f30..00dc3f943c80 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
@@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6c4d79baff26..6ea3dc2e4219 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
filter_expired = after(tcp_jiffies32,
bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
if (rs->rtt_us >= 0 &&
- (rs->rtt_us <= bbr->min_rtt_us ||
+ (rs->rtt_us < bbr->min_rtt_us ||
(filter_expired && !rs->is_ack_delayed))) {
bbr->min_rtt_us = rs->rtt_us;
bbr->min_rtt_stamp = tcp_jiffies32;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 37f4cb2bba5c..bc7d2a586e18 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
{
struct iov_iter *iter = &msg->msg_iter;
int peek = flags & MSG_PEEK;
- int i, ret, copied = 0;
struct sk_msg *msg_rx;
+ int i, copied = 0;
msg_rx = list_first_entry_or_null(&psock->ingress_msg,
struct sk_msg, list);
@@ -37,17 +37,16 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
page = sg_page(sge);
if (copied + copy > len)
copy = len - copied;
- ret = copy_page_to_iter(page, sge->offset, copy, iter);
- if (ret != copy) {
- msg_rx->sg.start = i;
- return -EFAULT;
- }
+ copy = copy_page_to_iter(page, sge->offset, copy, iter);
+ if (!copy)
+ return copied ? copied : -EFAULT;
copied += copy;
if (likely(!peek)) {
sge->offset += copy;
sge->length -= copy;
- sk_mem_uncharge(sk, copy);
+ if (!msg_rx->skb)
+ sk_mem_uncharge(sk, copy);
msg_rx->sg.size -= copy;
if (!sge->length) {
@@ -56,6 +55,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
put_page(page);
}
} else {
+ /* Lets not optimize peek case if copy_page_to_iter
+ * didn't copy the entire length lets just break.
+ */
+ if (copy != sge->length)
+ return copied;
sk_msg_iter_var_next(i);
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index db47ac24d057..563d016e7478 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -198,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk,
icsk->icsk_ca_setsockopt = 1;
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ if (ca->flags & TCP_CONG_NEEDS_ECN)
+ INET_ECN_xmit(sk);
+ else
+ INET_ECN_dontxmit(sk);
+
if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
tcp_init_congestion_control(sk);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 389d1b340248..ef4bdb038a4b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -510,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk)
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
tcp_sndbuf_expand(sk);
- tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss);
tcp_mstamp_refresh(tp);
tp->rcvq_space.time = tp->tcp_mstamp;
tp->rcvq_space.seq = tp->copied_seq;
@@ -534,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
tp->snd_cwnd_stamp = tcp_jiffies32;
+ tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd,
+ (u32)TCP_INIT_CWND * tp->advmss);
}
/* 4. Recalculate window clamp after socket hit its memory bounds. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7352c097ae48..595dcc3afac5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -980,17 +980,23 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
- tcp_rsk(req)->syn_tos : inet_sk(sk)->tos;
-
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
+ tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+ (inet_sk(sk)->tos & INET_ECN_MASK) :
+ inet_sk(sk)->tos;
+
+ if (!INET_ECN_is_capable(tos) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tos |= INET_ECN_ECT_0;
+
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt),
- tos & ~INET_ECN_MASK);
+ tos);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -1498,6 +1504,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
bool *own_req)
{
struct inet_request_sock *ireq;
+ bool found_dup_sk = false;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
@@ -1535,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
newinet->inet_id = prandom_u32();
- /* Set ToS of the new socket based upon the value of incoming SYN. */
+ /* Set ToS of the new socket based upon the value of incoming SYN.
+ * ECT bits are set later in tcp_init_transfer().
+ */
if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
@@ -1575,12 +1584,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (likely(*own_req)) {
tcp_move_syn(newtp, req);
ireq->ireq_opt = NULL;
} else {
- newinet->inet_opt = NULL;
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ } else {
+ newinet->inet_opt = NULL;
+ }
}
return newsk;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bf48cd73e967..99011768c264 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1880,7 +1880,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
* window, and remember whether we were cwnd-limited then.
*/
if (!before(tp->snd_una, tp->max_packets_seq) ||
- tp->packets_out > tp->max_packets_out) {
+ tp->packets_out > tp->max_packets_out ||
+ is_cwnd_limited) {
tp->max_packets_out = tp->packets_out;
tp->max_packets_seq = tp->snd_nxt;
tp->is_cwnd_limited = is_cwnd_limited;
@@ -2702,6 +2703,10 @@ repair:
else
tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED);
+ is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
+ if (likely(sent_pkts || is_cwnd_limited))
+ tcp_cwnd_validate(sk, is_cwnd_limited);
+
if (likely(sent_pkts)) {
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += sent_pkts;
@@ -2709,8 +2714,6 @@ repair:
/* Send one loss probe per tail loss episode. */
if (push_one != 2)
tcp_schedule_loss_probe(sk, false);
- is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
- tcp_cwnd_validate(sk, is_cwnd_limited);
return false;
}
return !tp->packets_out && !tcp_write_queue_empty(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 09f0a23d1a01..9eeebd4a0054 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2173,7 +2173,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
__skb_pull(skb, skb_transport_offset(skb));
ret = udp_queue_rcv_one_skb(sk, skb);
if (ret > 0)
- ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret);
+ ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret);
}
return 0;
}
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66fbf27b..c62805cd3131 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -366,7 +366,7 @@ out:
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh = udp_gro_udphdr(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
@@ -500,12 +500,22 @@ out:
}
EXPORT_SYMBOL(udp_gro_receive);
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct iphdr *iph = skb_gro_network_header(skb);
+
+ return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ inet_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
rcu_read_lock();
- sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udp_encap_needed_key))
+ sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-19 23:39:04 +0000