summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/igmp.c4
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_output.c13
-rw-r--r--net/ipv4/ip_tunnel.c22
-rw-r--r--net/ipv4/ip_tunnel_core.c2
-rw-r--r--net/ipv4/ip_vti.c14
-rw-r--r--net/ipv4/netfilter/arp_tables.c5
-rw-r--r--net/ipv4/netfilter/ip_tables.c5
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c10
-rw-r--r--net/ipv4/netfilter/ipt_ULOG.c7
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/tcp_input.c43
-rw-r--r--net/ipv4/tcp_offload.c13
-rw-r--r--net/ipv4/tcp_output.c31
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv4/xfrm4_policy.c7
18 files changed, 122 insertions, 68 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7a1874b7b8fd..cfeb85cff4f0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,10 +263,8 @@ void build_ehash_secret(void)
get_random_bytes(&rnd, sizeof(rnd));
} while (rnd == 0);
- if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) {
+ if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
- net_secret_init();
- }
}
EXPORT_SYMBOL(build_ehash_secret);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index dace87f06e5f..7defdc9ba167 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -736,7 +736,7 @@ static void igmp_gq_timer_expire(unsigned long data)
in_dev->mr_gq_running = 0;
igmpv3_send_report(in_dev, NULL);
- __in_dev_put(in_dev);
+ in_dev_put(in_dev);
}
static void igmp_ifc_timer_expire(unsigned long data)
@@ -749,7 +749,7 @@ static void igmp_ifc_timer_expire(unsigned long data)
igmp_ifc_start_timer(in_dev,
unsolicited_report_interval(in_dev));
}
- __in_dev_put(in_dev);
+ in_dev_put(in_dev);
}
static void igmp_ifc_event(struct in_device *in_dev)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7bd8983dbfcf..96da9c77deca 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -287,7 +287,7 @@ begintw:
if (unlikely(!INET_TW_MATCH(sk, net, acookie,
saddr, daddr, ports,
dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872c54f9..3982eabf61e1 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk,
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
- skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
- /* specify the length of each IP datagram fragment */
- skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
__skb_queue_tail(queue, skb);
+ } else if (skb_is_gso(skb)) {
+ goto append;
}
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ /* specify the length of each IP datagram fragment */
+ skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
+append:
return skb_append_datato_frags(sk, skb, getfrag, from,
(length - transhdrlen));
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ac9fabe0300f..63a6d6d6b875 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -623,6 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
tunnel->err_count = 0;
}
+ tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
@@ -641,18 +642,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len;
- if (max_headroom > dev->needed_headroom) {
+ if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
- if (skb_cow_head(skb, dev->needed_headroom)) {
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return;
- }
+
+ if (skb_cow_head(skb, dev->needed_headroom)) {
+ dev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return;
}
err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol,
- ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df,
- !net_eq(tunnel->net, dev_net(dev)));
+ tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)));
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return;
@@ -853,8 +853,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
- if (!IS_ERR(itn->fb_tunnel_dev))
+ if (!IS_ERR(itn->fb_tunnel_dev)) {
itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+ ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
+ }
rtnl_unlock();
return PTR_RET(itn->fb_tunnel_dev);
@@ -884,8 +886,6 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev, head);
}
- if (itn->fb_tunnel_dev)
- unregister_netdevice_queue(itn->fb_tunnel_dev, head);
}
void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index d6c856b17fd4..c31e3ad98ef2 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -61,7 +61,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
- __skb_push(skb, sizeof(struct iphdr));
+ skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e805e7b3030e..6e87f853d033 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -125,8 +125,17 @@ static int vti_rcv(struct sk_buff *skb)
iph->saddr, iph->daddr, 0);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ u32 oldmark = skb->mark;
+ int ret;
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+ /* temporarily mark the skb with the tunnel o_key, to
+ * only match policies with this mark.
+ */
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+ ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+ skb->mark = oldmark;
+ if (!ret)
return -1;
tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -135,7 +144,6 @@ static int vti_rcv(struct sk_buff *skb)
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- skb->mark = 0;
secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
@@ -167,7 +175,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 85a4f21aac1a..59da7cde0724 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -271,6 +271,11 @@ unsigned int arpt_do_table(struct sk_buff *skb,
local_bh_disable();
addend = xt_write_recseq_begin();
private = table->private;
+ /*
+ * Ensure we load private-> members after we've fetched the base
+ * pointer.
+ */
+ smp_read_barrier_depends();
table_base = private->entries[smp_processor_id()];
e = get_entry(table_base, private->hook_entry[hook]);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d23118d95ff9..718dfbd30cbe 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -327,6 +327,11 @@ ipt_do_table(struct sk_buff *skb,
addend = xt_write_recseq_begin();
private = table->private;
cpu = smp_processor_id();
+ /*
+ * Ensure we load private-> members after we've fetched the base
+ * pointer.
+ */
+ smp_read_barrier_depends();
table_base = private->entries[cpu];
jumpstack = (struct ipt_entry **)private->jumpstack[cpu];
stackptr = per_cpu_ptr(private->stackptr, cpu);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 67e17dcda65e..b6346bf2fde3 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
if (th == NULL)
return NF_DROP;
- synproxy_parse_options(skb, par->thoff, th, &opts);
+ if (!synproxy_parse_options(skb, par->thoff, th, &opts))
+ return NF_DROP;
if (th->syn && !(th->ack || th->fin || th->rst)) {
/* Initial SYN from client */
@@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
/* fall through */
case TCP_CONNTRACK_SYN_SENT:
- synproxy_parse_options(skb, thoff, th, &opts);
+ if (!synproxy_parse_options(skb, thoff, th, &opts))
+ return NF_DROP;
if (!th->syn && th->ack &&
CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
@@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
if (!th->syn || !th->ack)
break;
- synproxy_parse_options(skb, thoff, th, &opts);
+ if (!synproxy_parse_options(skb, thoff, th, &opts))
+ return NF_DROP;
+
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy->tsoff = opts.tsval - synproxy->its;
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index cbc22158af49..9cb993cd224b 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net,
ub->qlen++;
pm = nlmsg_data(nlh);
+ memset(pm, 0, sizeof(*pm));
/* We might not have a timestamp, get one */
if (skb->tstamp.tv64 == 0)
@@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net,
}
else if (loginfo->prefix[0] != '\0')
strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix));
- else
- *(pm->prefix) = '\0';
if (in && in->hard_header_len > 0 &&
skb->mac_header != skb->network_header &&
@@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net,
if (in)
strncpy(pm->indev_name, in->name, sizeof(pm->indev_name));
- else
- pm->indev_name[0] = '\0';
if (out)
strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
- else
- pm->outdev_name[0] = '\0';
/* copy_len <= skb->len, so can't fail. */
if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bfec521c717f..193db03540ad 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -218,8 +218,10 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
ipv4_sk_update_pmtu(skb, sk, info);
- else if (type == ICMP_REDIRECT)
+ else if (type == ICMP_REDIRECT) {
ipv4_sk_redirect(skb, sk);
+ return;
+ }
/* Report error on raw socket, if:
1. User requested ip_recverr.
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 727f4365bcdf..6011615e810d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2072,7 +2072,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
RT_SCOPE_LINK);
goto make_route;
}
- if (fl4->saddr) {
+ if (!fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 25a89eaa669d..068c8fb0d158 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1284,7 +1284,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+ TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ TCP_SKB_CB(prev)->end_seq++;
+
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
@@ -2853,7 +2856,8 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
* left edge of the send window.
* See draft-ietf-tcplw-high-performance-00, section 3.3.
*/
- if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
+ if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+ flag & FLAG_ACKED)
seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
if (seq_rtt < 0)
@@ -2868,14 +2872,19 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
}
/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
-static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
+static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
{
struct tcp_sock *tp = tcp_sk(sk);
s32 seq_rtt = -1;
- if (tp->lsndtime && !tp->total_retrans)
- seq_rtt = tcp_time_stamp - tp->lsndtime;
- tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
+ if (synack_stamp && !tp->total_retrans)
+ seq_rtt = tcp_time_stamp - synack_stamp;
+
+ /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
+ * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
+ */
+ if (!tp->srtt)
+ tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
}
static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
@@ -2978,6 +2987,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
s32 seq_rtt = -1;
s32 ca_seq_rtt = -1;
ktime_t last_ackt = net_invalid_timestamp();
+ bool rtt_update;
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
@@ -3054,14 +3064,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
flag |= FLAG_SACK_RENEGING;
- if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) ||
- (flag & FLAG_ACKED))
- tcp_rearm_rto(sk);
+ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt);
if (flag & FLAG_ACKED) {
const struct tcp_congestion_ops *ca_ops
= inet_csk(sk)->icsk_ca_ops;
+ tcp_rearm_rto(sk);
if (unlikely(icsk->icsk_mtup.probe_size &&
!after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
tcp_mtup_probe_success(sk);
@@ -3100,6 +3109,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
}
+ } else if (skb && rtt_update && sack_rtt >= 0 &&
+ sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) {
+ /* Do not re-arm RTO if the sack RTT is measured from data sent
+ * after when the head was last (re)transmitted. Otherwise the
+ * timeout may continue to extend in loss recovery.
+ */
+ tcp_rearm_rto(sk);
}
#if FASTRETRANS_DEBUG > 0
@@ -3288,7 +3304,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
@@ -5584,6 +5600,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct request_sock *req;
int queued = 0;
bool acceptable;
+ u32 synack_stamp;
tp->rx_opt.saw_tstamp = 0;
@@ -5666,9 +5683,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
* so release it.
*/
if (req) {
+ synack_stamp = tcp_rsk(req)->snt_synack;
tp->total_retrans = req->num_retrans;
reqsk_fastopen_remove(sk, req, false);
} else {
+ synack_stamp = tp->lsndtime;
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_congestion_control(sk);
@@ -5691,7 +5710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
- tcp_synack_rtt_meas(sk, req);
+ tcp_synack_rtt_meas(sk, synack_stamp);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
@@ -5709,6 +5728,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on first data packet */
tp->lsndtime = tcp_time_stamp;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3a7525e6c086..533c58a5cfb7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -18,6 +18,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int sum_truesize = 0;
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
@@ -102,13 +103,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be gso_skb->truesize
- * So we account mss bytes of 'true size' for each segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
+ sum_truesize += skb->truesize;
}
skb = skb->next;
th = tcp_hdr(skb);
@@ -125,7 +120,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
+ sum_truesize += skb->truesize;
+ atomic_add(sum_truesize - gso_skb->truesize,
+ &skb->sk->sk_wmem_alloc);
}
delta = htonl(oldlen + (skb_tail_pointer(skb) -
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c83cb8bf137..d46f2143305c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -637,6 +637,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
unsigned int size = 0;
unsigned int eff_sacks;
+ opts->options = 0;
+
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
if (unlikely(*md5)) {
@@ -895,8 +897,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_orphan(skb);
skb->sk = sk;
- skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
- tcp_wfree : sock_wfree;
+ skb->destructor = tcp_wfree;
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
/* Build TCP header and checksum it. */
@@ -985,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
- if (skb->len <= mss_now || !sk_can_gso(sk) ||
- skb->ip_summed == CHECKSUM_NONE) {
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
+ if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
@@ -1066,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -1840,7 +1841,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
-
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
@@ -1869,13 +1869,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
break;
}
- /* TSQ : sk_wmem_alloc accounts skb truesize,
- * including skb overhead. But thats OK.
+ /* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * This allows for :
+ * - better RTT estimation and ACK scheduling
+ * - faster recovery
+ * - high rates
*/
- if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+ limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
break;
}
+
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2337,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 74d2c95db57f..0ca44df51ee9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -658,7 +658,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
break;
case ICMP_REDIRECT:
ipv4_sk_redirect(skb, sk);
- break;
+ goto out;
}
/*
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 9a459be24af7..e1a63930a967 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -104,9 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
const struct iphdr *iph = ip_hdr(skb);
u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
struct flowi4 *fl4 = &fl->u.ip4;
+ int oif = 0;
+
+ if (skb_dst(skb))
+ oif = skb_dst(skb)->dev->ifindex;
memset(fl4, 0, sizeof(struct flowi4));
fl4->flowi4_mark = skb->mark;
+ fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
@@ -235,7 +240,7 @@ static struct dst_ops xfrm4_dst_ops = {
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
- .gc_thresh = 1024,
+ .gc_thresh = 32768,
};
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
generated by cgit (git 2.34.1) at 2025-04-21 22:55:53 +0000