summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c7
-rw-r--r--net/ipv4/gre_demux.c8
-rw-r--r--net/ipv4/inet_fragment.c5
-rw-r--r--net/ipv4/ip_forward.c71
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/ip_tunnel.c56
-rw-r--r--net/ipv4/ip_tunnel_core.c46
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipmr.c13
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c4
-rw-r--r--net/ipv4/route.c13
-rw-r--r--net/ipv4/tcp.c8
-rw-r--r--net/ipv4/tcp_cong.c3
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_output.c33
16 files changed, 191 insertions, 86 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ecd2c3f245c..19ab78aca54 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
segs = ERR_PTR(-EPROTONOSUPPORT);
- /* Note : following gso_segment() might change skb->encapsulation */
- udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
ops = rcu_dereference(inet_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 1863422fb7d..250be7421ab 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -182,6 +182,14 @@ static int gre_cisco_rcv(struct sk_buff *skb)
int i;
bool csum_err = false;
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ }
+#endif
+
if (parse_gre_header(skb, &tpi, &csum_err) < 0)
goto drop;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bb075fc9a14..3b01959bf4b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
}
work = frag_mem_limit(nf) - nf->low_thresh;
- while (work > 0) {
+ while (work > 0 || force) {
spin_lock(&nf->lru_lock);
if (list_empty(&nf->lru_list)) {
@@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &hb->chain);
+ inet_frag_lru_add(nf, qp);
spin_unlock(&hb->chain_lock);
read_unlock(&f->lock);
- inet_frag_lru_add(nf, qp);
+
return qp;
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217a8af..f3869c186d9 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb)
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
@@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb)
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8971780aec7..73c6b63bba7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
to->ipvs_property = from->ipvs_property;
#endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 50228be5c17..a82a22d8f77 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t)
tunnel_dst_set(t, NULL);
}
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
{
int i;
for_each_possible_cpu(i)
__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
}
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
{
@@ -119,52 +120,6 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
return (struct rtable *)dst;
}
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_sw_netstats *tstats =
- per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
-
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- tot->collisions = dev->stats.collisions;
-
- return tot;
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
{
@@ -461,9 +416,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
@@ -759,7 +711,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
if (set_mtu)
dev->mtu = mtu;
}
- tunnel_dst_reset_all(t);
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(dev);
}
@@ -1088,7 +1040,7 @@ void ip_tunnel_uninit(struct net_device *dev)
if (itn->fb_tunnel_dev != dev)
ip_tunnel_del(netdev_priv(dev));
- tunnel_dst_reset_all(tunnel);
+ ip_tunnel_dst_reset_all(tunnel);
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6156f4ef5e9..8d69626f220 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -148,3 +148,49 @@ error:
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_sw_netstats *tstats =
+ per_cpu_ptr(dev->tstats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ }
+
+ tot->multicast = dev->stats.multicast;
+
+ tot->rx_crc_errors = dev->stats.rx_crc_errors;
+ tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+ tot->rx_length_errors = dev->stats.rx_length_errors;
+ tot->rx_frame_errors = dev->stats.rx_frame_errors;
+ tot->rx_errors = dev->stats.rx_errors;
+
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+ tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+ tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+ tot->tx_errors = dev->stats.tx_errors;
+
+ tot->collisions = dev->stats.collisions;
+
+ return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138fa52..b3e86ea7b71 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@ static int __init ic_open_devs(void)
msleep(1);
- if time_before(jiffies, next_msg)
+ if (time_before(jiffies, next_msg))
continue;
elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b9b3472975b..28863570dd6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2255,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
}
static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+ u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+ int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2329,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
if (skb == NULL)
goto errout;
- err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2368,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0)
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
@@ -2382,7 +2384,8 @@ next_entry:
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0) {
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d551e31b416..7c676671329 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct,
map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
} else {
/* DNAT replies */
- map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
- map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+ map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+ map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
}
if (map.from == map.to)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25071b48921..4c011ec69ed 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1597,6 +1597,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1695,10 +1696,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0)
+ if (err != 0) {
+ if (!IN_DEV_FORWARD(in_dev))
+ err = -EHOSTUNREACH;
goto no_route;
-
- RT_CACHE_STAT_INC(in_slow_tot);
+ }
if (res.type == RTN_BROADCAST)
goto brd_input;
@@ -1712,8 +1714,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto local_input;
}
- if (!IN_DEV_FORWARD(in_dev))
+ if (!IN_DEV_FORWARD(in_dev)) {
+ err = -EHOSTUNREACH;
goto no_route;
+ }
if (res.type != RTN_UNICAST)
goto martian_destination;
@@ -1768,6 +1772,7 @@ local_input:
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9f3a2db9109..97c8f5620c4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
}
}
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+ int *copied, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
int err, flags;
@@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
if (unlikely(tp->fastopen_req == NULL))
return -ENOBUFS;
tp->fastopen_req->data = msg;
+ tp->fastopen_req->size = size;
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
msg->msg_namelen, flags);
- *size = tp->fastopen_req->copied;
+ *copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
return err;
}
@@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
flags = msg->msg_flags;
if (flags & MSG_FASTOPEN) {
- err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+ err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
else if (err)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf18ae4..2388275adb9 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
left = tp->snd_cwnd - in_flight;
if (sk_can_gso(sk) &&
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
- left * tp->mss_cache < sk->sk_gso_max_size &&
- left < sk->sk_gso_max_segs)
+ left < tp->xmit_size_goal_segs)
return true;
return left <= tcp_max_tso_deferred_mss(tp);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba79fa6..eeaac399420 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1945,8 +1945,9 @@ void tcp_enter_loss(struct sock *sk, int how)
if (skb == tcp_send_head(sk))
break;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->undo_marker = 0;
+
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf97651049..1e4eac779f5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,7 +2628,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
{
__be32 dest, src;
__u16 destp, srcp;
- long delta = tw->tw_ttd - jiffies;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
dest = tw->tw_daddr;
src = tw->tw_rcv_saddr;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3be16727f05..17a11e65e57 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -767,6 +767,17 @@ void tcp_release_cb(struct sock *sk)
if (flags & (1UL << TCP_TSQ_DEFERRED))
tcp_tsq_handler(sk);
+ /* Here begins the tricky part :
+ * We are called from release_sock() with :
+ * 1) BH disabled
+ * 2) sk_lock.slock spinlock held
+ * 3) socket owned by us (sk->sk_lock.owned == 1)
+ *
+ * But following code is meant to be called from BH handlers,
+ * so we should keep BH disabled, but early release socket ownership
+ */
+ sock_release_ownership(sk);
+
if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
tcp_write_timer_handler(sk);
__sock_put(sk);
@@ -864,8 +875,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
fclone->fclone == SKB_FCLONE_CLONE))
- NET_INC_STATS_BH(sock_net(sk),
- LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
if (unlikely(skb_cloned(skb)))
skb = pskb_copy(skb, gfp_mask);
@@ -2337,6 +2348,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned int cur_mss;
+ int err;
/* Inconslusive MTU probe */
if (icsk->icsk_mtup.probe_size) {
@@ -2400,11 +2412,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
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) :
- -ENOBUFS;
+ err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+ -ENOBUFS;
} else {
- return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
+
+ if (likely(!err))
+ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+ return err;
}
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2908,7 +2924,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
- syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+ space = min_t(size_t, space, fo->size);
+
+ /* limit to order-0 allocations */
+ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+ syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
sk->sk_allocation);
if (syn_data == NULL)
goto fallback;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-12 05:31:38 +0000