summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/datagram.c2
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ip_vti.c1
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c1
-rw-r--r--net/ipv4/ping.c56
-rw-r--r--net/ipv4/protocol.c8
-rw-r--r--net/ipv4/raw.c6
-rw-r--r--net/ipv4/route.c8
-rw-r--r--net/ipv4/tcp.c10
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_memcontrol.c2
-rw-r--r--net/ipv4/tcp_metrics.c10
-rw-r--r--net/ipv4/tcp_offload.c31
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/udp.c14
16 files changed, 78 insertions, 87 deletions
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index b28e863fe0a7..19e36376d2a0 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3f858266fa7e..ddf32a6bc415 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -386,7 +386,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
/*
* Handle MSG_ERRQUEUE
*/
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb, *skb2;
@@ -423,6 +423,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index caf01176a5e4..90ff9570d7d4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -454,6 +454,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
+ skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
+
if (tunnel->dev->type == ARPHRD_ETHER) {
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
@@ -461,8 +463,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
skb->dev = tunnel->dev;
}
- skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
-
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5d9c845d288a..52b802a0cd8c 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -126,6 +126,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (!rt->dst.xfrm ||
rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
dev->stats.tx_carrier_errors++;
+ ip_rt_put(rt);
goto tx_error_icmp;
}
tdev = rt->dst.dev;
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 01cffeaa0085..f13bd91d9a56 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -244,6 +244,7 @@ synproxy_recv_client_ack(const struct synproxy_net *snet,
this_cpu_inc(snet->stats->cookie_valid);
opts->mss = mss;
+ opts->options |= XT_SYNPROXY_OPT_MSS;
if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_check_timestamp_cookie(opts);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index cbc85f660d54..242e7f4ed6f4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -772,7 +772,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -830,8 +830,6 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
{
struct inet_sock *isk = inet_sk(sk);
int family = sk->sk_family;
- struct sockaddr_in *sin;
- struct sockaddr_in6 *sin6;
struct sk_buff *skb;
int copied, err;
@@ -841,19 +839,13 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_OOB)
goto out;
- if (addr_len) {
- if (family == AF_INET)
- *addr_len = sizeof(*sin);
- else if (family == AF_INET6 && addr_len)
- *addr_len = sizeof(*sin6);
- }
-
if (flags & MSG_ERRQUEUE) {
if (family == AF_INET) {
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
#if IS_ENABLED(CONFIG_IPV6)
} else if (family == AF_INET6) {
- return pingv6_ops.ipv6_recv_error(sk, msg, len);
+ return pingv6_ops.ipv6_recv_error(sk, msg, len,
+ addr_len);
#endif
}
}
@@ -877,11 +869,15 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/* Copy the address and add cmsg data. */
if (family == AF_INET) {
- sin = (struct sockaddr_in *) msg->msg_name;
- sin->sin_family = AF_INET;
- sin->sin_port = 0 /* skb->h.uh->source */;
- sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
- memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+
+ if (sin) {
+ sin->sin_family = AF_INET;
+ sin->sin_port = 0 /* skb->h.uh->source */;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
+ memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
+ }
if (isk->cmsg_flags)
ip_cmsg_recv(msg, skb);
@@ -890,17 +886,21 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
} else if (family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *ip6 = ipv6_hdr(skb);
- sin6 = (struct sockaddr_in6 *) msg->msg_name;
- sin6->sin6_family = AF_INET6;
- sin6->sin6_port = 0;
- sin6->sin6_addr = ip6->saddr;
-
- sin6->sin6_flowinfo = 0;
- if (np->sndflow)
- sin6->sin6_flowinfo = ip6_flowinfo(ip6);
-
- sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
- IP6CB(skb)->iif);
+ struct sockaddr_in6 *sin6 =
+ (struct sockaddr_in6 *)msg->msg_name;
+
+ if (sin6) {
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = 0;
+ sin6->sin6_addr = ip6->saddr;
+ sin6->sin6_flowinfo = 0;
+ if (np->sndflow)
+ sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+ sin6->sin6_scope_id =
+ ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
+ *addr_len = sizeof(*sin6);
+ }
if (inet6_sk(sk)->rxopt.all)
pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index ce848461acbb..46d6a1c923a8 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -31,10 +31,6 @@
const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
-/*
- * Add a protocol handler to the hash tables
- */
-
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
if (!prot->netns_ok) {
@@ -55,10 +51,6 @@ int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
}
EXPORT_SYMBOL(inet_add_offload);
-/*
- * Remove a protocol from the hash tables.
- */
-
int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
{
int ret;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 41e1d2845c8f..23c3e5b5bb53 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -696,11 +696,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE) {
- err = ip_recv_error(sk, msg, len);
+ err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
@@ -726,6 +723,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f428935c50db..f8da28278014 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1776,8 +1776,12 @@ local_input:
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- if (do_cache)
- rt_cache_route(&FIB_RES_NH(res), rth);
+ if (do_cache) {
+ if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+ rth->dst.flags |= DST_NOCACHE;
+ rt_add_uncached_list(rth);
+ }
+ }
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8e8529d3c8c9..c4638e6f0238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -808,12 +808,6 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
xmit_size_goal = min_t(u32, gso_size,
sk->sk_gso_max_size - 1 - hlen);
- /* TSQ : try to have at least two segments in flight
- * (one in NIC TX ring, another in Qdisc)
- */
- xmit_size_goal = min_t(u32, xmit_size_goal,
- sysctl_tcp_limit_output_bytes >> 1);
-
xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
/* We try hard to avoid divides here */
@@ -1431,7 +1425,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
do {
if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
last_issued, &done,
- &used) == DMA_SUCCESS) {
+ &used) == DMA_COMPLETE) {
/* Safe to free early-copied skbs now */
__skb_queue_purge(&sk->sk_async_wait_queue);
break;
@@ -1439,7 +1433,7 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
(dma_async_is_complete(skb->dma_cookie, done,
- used) == DMA_SUCCESS)) {
+ used) == DMA_COMPLETE)) {
__skb_dequeue(&sk->sk_async_wait_queue);
kfree_skb(skb);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 59a6f8b90cd9..067213924751 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 03e9154f7e68..269a89ecd2f4 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -60,7 +60,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup);
static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
{
struct cg_proto *cg_proto;
- u64 old_lim;
int i;
int ret;
@@ -71,7 +70,6 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
if (val > RES_COUNTER_MAX)
val = RES_COUNTER_MAX;
- old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT);
ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
if (ret)
return ret;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 2ab09cbae74d..06493736fbc8 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -663,10 +663,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
struct tcp_fastopen_cookie *cookie, bool syn_lost)
{
+ struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_metrics_block *tm;
+ if (!dst)
+ return;
rcu_read_lock();
- tm = tcp_get_metrics(sk, __sk_dst_get(sk), true);
+ tm = tcp_get_metrics(sk, dst, true);
if (tm) {
struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
@@ -988,7 +991,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
return 0;
}
-static struct genl_ops tcp_metrics_nl_ops[] = {
+static const struct genl_ops tcp_metrics_nl_ops[] = {
{
.cmd = TCP_METRICS_CMD_GET,
.doit = tcp_metrics_nl_cmd_get,
@@ -1079,8 +1082,7 @@ void __init tcp_metrics_init(void)
if (ret < 0)
goto cleanup;
ret = genl_register_family_with_ops(&tcp_metrics_nl_family,
- tcp_metrics_nl_ops,
- ARRAY_SIZE(tcp_metrics_nl_ops));
+ tcp_metrics_nl_ops);
if (ret < 0)
goto cleanup_subsys;
return;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index a2b68a108eae..05606353c7e7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -274,33 +274,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *
{
const struct iphdr *iph = skb_gro_network_header(skb);
__wsum wsum;
- __sum16 sum;
+
+ /* Don't bother verifying checksum if we're going to flush anyway. */
+ if (NAPI_GRO_CB(skb)->flush)
+ goto skip_csum;
+
+ wsum = skb->csum;
switch (skb->ip_summed) {
+ case CHECKSUM_NONE:
+ wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
+ 0);
+
+ /* fall through */
+
case CHECKSUM_COMPLETE:
if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
- skb->csum)) {
+ wsum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
-flush:
+
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
-
- case CHECKSUM_NONE:
- wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
- skb_gro_len(skb), IPPROTO_TCP, 0);
- sum = csum_fold(skb_checksum(skb,
- skb_gro_offset(skb),
- skb_gro_len(skb),
- wsum));
- if (sum)
- goto flush;
-
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
}
+skip_csum:
return tcp_gro_receive(head, skb);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 672854664ff5..7820f3a7dd70 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1875,8 +1875,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
* - better RTT estimation and ACK scheduling
* - faster recovery
* - high rates
+ * Alas, some drivers / subsystems require a fair amount
+ * of queued bytes to ensure line rate.
+ * One example is wifi aggregation (802.11 AMPDU)
*/
- limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+ limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+ sk->sk_pacing_rate >> 10);
if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
@@ -3093,7 +3097,6 @@ void tcp_send_window_probe(struct sock *sk)
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
- tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
tcp_xmit_probe_skb(sk, 0);
}
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index de86e5bc4462..44f6a20fa29d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -999,7 +999,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -1098,6 +1098,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
struct udp_sock *up = udp_sk(sk);
int ret;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
if (!up->pending) {
struct msghdr msg = { .msg_flags = flags|MSG_MORE };
@@ -1235,14 +1238,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
int is_udplite = IS_UDPLITE(sk);
bool slow;
- /*
- * Check any passed addresses
- */
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1302,6 +1299,7 @@ try_again:
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-17 21:37:35 +0000