summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_trie.c3
-rw-r--r--net/ipv4/inet_connection_sock.c34
-rw-r--r--net/ipv4/inet_diag.c8
-rw-r--r--net/ipv4/ip_vti.c14
-rw-r--r--net/ipv4/netfilter/arp_tables.c6
-rw-r--r--net/ipv4/netfilter/ip_tables.c6
-rw-r--r--net/ipv4/ping.c1
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c31
-rw-r--r--net/ipv4/tcp_cong.c5
-rw-r--r--net/ipv4/tcp_dctcp.c20
-rw-r--r--net/ipv4/tcp_fastopen.c5
-rw-r--r--net/ipv4/tcp_illinois.c21
-rw-r--r--net/ipv4/tcp_input.c55
-rw-r--r--net/ipv4/tcp_ipv4.c3
-rw-r--r--net/ipv4/tcp_minisocks.c14
-rw-r--r--net/ipv4/tcp_output.c64
-rw-r--r--net/ipv4/tcp_vegas.c19
-rw-r--r--net/ipv4/tcp_vegas.h3
-rw-r--r--net/ipv4/tcp_westwood.c15
-rw-r--r--net/ipv4/udp.c24
21 files changed, 261 insertions, 99 deletions
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e13fcc602da2..09b62e17dd8c 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1164,6 +1164,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
state = fa->fa_state;
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
+ new_fa->tb_id = tb->tb_id;
err = netdev_switch_fib_ipv4_add(key, plen, fi,
new_fa->fa_tos,
@@ -1764,7 +1765,7 @@ void fib_table_flush_external(struct fib_table *tb)
/* record local slen */
slen = fa->fa_slen;
- if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL))
+ if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD))
continue;
netdev_switch_fib_ipv4_del(n->key,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5c3dd6267ed3..8976ca423a07 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,6 +564,40 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
}
EXPORT_SYMBOL(inet_rtx_syn_ack);
+/* return true if req was found in the syn_table[] */
+static bool reqsk_queue_unlink(struct request_sock_queue *queue,
+ struct request_sock *req)
+{
+ struct listen_sock *lopt = queue->listen_opt;
+ struct request_sock **prev;
+ bool found = false;
+
+ spin_lock(&queue->syn_wait_lock);
+
+ for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
+ prev = &(*prev)->dl_next) {
+ if (*prev == req) {
+ *prev = req->dl_next;
+ found = true;
+ break;
+ }
+ }
+
+ spin_unlock(&queue->syn_wait_lock);
+ if (del_timer(&req->rsk_timer))
+ reqsk_put(req);
+ return found;
+}
+
+void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+{
+ if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) {
+ reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+ reqsk_put(req);
+ }
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
+
static void reqsk_timer_handler(unsigned long data)
{
struct request_sock *req = (struct request_sock *)data;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index bb77ebdae3b3..4d32262c7502 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -224,14 +224,16 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT) {
- int err = 0;
+ union tcp_cc_info info;
+ size_t sz = 0;
+ int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
- err = ca_ops->get_info(sk, ext, skb);
+ sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
- if (err < 0)
+ if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9f7269f3c54a..0c152087ca15 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
- skb->mark = be32_to_cpu(tunnel->parms.i_key);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
@@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!tunnel)
return 1;
@@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(tunnel->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
@@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(tunnel->parms.o_key);
-
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
@@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
return vti_xmit(skb, dev, &fl);
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 13bfe84bf3ca..a61200754f4b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1075,6 +1075,9 @@ static int do_replace(struct net *net, const void __user *user,
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
@@ -1499,6 +1502,9 @@ static int compat_do_replace(struct net *net, void __user *user,
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c69db7fa25ee..2d0e265fef6e 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1262,6 +1262,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
@@ -1809,6 +1812,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a93f260cf24c..05ff44b758df 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
if (sk_hashed(sk)) {
write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
+ sk_nulls_node_init(&sk->sk_nulls_node);
sock_put(sk);
isk->inet_num = 0;
isk->inet_sport = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a78540f28276..f45f2a12f37b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -902,6 +902,10 @@ static int ip_error(struct sk_buff *skb)
bool send;
int code;
+ /* IP on this device is disabled. */
+ if (!in_dev)
+ goto out;
+
net = dev_net(rt->dst.dev);
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
@@ -962,10 +966,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (dst_metric_locked(dst, RTAX_MTU))
return;
- if (dst->dev->mtu < mtu)
- return;
-
- if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+ if (ipv4_mtu(dst) < mtu)
return;
if (mtu < ip_rt_min_pmtu)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8c5cd9efebbc..f1377f2a0472 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -252,6 +252,7 @@
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
+#include <linux/inet_diag.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
@@ -401,6 +402,7 @@ void tcp_init_sock(struct sock *sk)
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
+ u64_stats_init(&tp->syncp);
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
@@ -2592,11 +2594,12 @@ EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif
/* Return information about state of tcp endpoint in API format. */
-void tcp_get_info(const struct sock *sk, struct tcp_info *info)
+void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
+ unsigned int start;
u32 rate;
memset(info, 0, sizeof(*info));
@@ -2663,6 +2666,12 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
rate = READ_ONCE(sk->sk_max_pacing_rate);
info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tp->syncp);
+ info->tcpi_bytes_acked = tp->bytes_acked;
+ info->tcpi_bytes_received = tp->bytes_received;
+ } while (u64_stats_fetch_retry_irq(&tp->syncp, start));
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -2734,6 +2743,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
}
+ case TCP_CC_INFO: {
+ const struct tcp_congestion_ops *ca_ops;
+ union tcp_cc_info info;
+ size_t sz = 0;
+ int attr;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ ca_ops = icsk->icsk_ca_ops;
+ if (ca_ops && ca_ops->get_info)
+ sz = ca_ops->get_info(sk, ~0U, &attr, &info);
+
+ len = min_t(unsigned int, len, sz);
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &info, len))
+ return -EFAULT;
+ return 0;
+ }
case TCP_QUICKACK:
val = !icsk->icsk_ack.pingpong;
break;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 7a5ae50c80c8..84be008c945c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
+ icsk->icsk_ca_setsockopt = 1;
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
@@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
rcu_read_lock();
ca = __tcp_ca_find_autoload(name);
/* No change asking for existing value */
- if (ca == icsk->icsk_ca_ops)
+ if (ca == icsk->icsk_ca_ops) {
+ icsk->icsk_ca_setsockopt = 1;
goto out;
+ }
if (!ca)
err = -ENOENT;
else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 4376016f7fa5..4c41c1287197 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -277,7 +277,8 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
}
}
-static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
@@ -286,18 +287,17 @@ static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
*/
if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcp_dctcp_info info;
-
- memset(&info, 0, sizeof(info));
+ memset(info, 0, sizeof(struct tcp_dctcp_info));
if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
- info.dctcp_enabled = 1;
- info.dctcp_ce_state = (u16) ca->ce_state;
- info.dctcp_alpha = ca->dctcp_alpha;
- info.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_enabled = 1;
+ info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
+ info->dctcp.dctcp_alpha = ca->dctcp_alpha;
+ info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
+ info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
}
- return nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
+ *attr = INET_DIAG_DCTCPINFO;
+ return sizeof(*info);
}
return 0;
}
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e3d87aca6be8..46b087a27503 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -206,6 +206,11 @@ static bool tcp_fastopen_create_child(struct sock *sk,
skb_set_owner_r(skb2, child);
__skb_queue_tail(&child->sk_receive_queue, skb2);
tp->syn_data_acked = 1;
+
+ /* u64_stats_update_begin(&tp->syncp) not needed here,
+ * as we certainly are not changing upper 32bit value (0)
+ */
+ tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
} else {
end_seq = TCP_SKB_CB(skb)->seq + 1;
}
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 67476f085e48..f71002e4db0b 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -300,24 +300,25 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
}
/* Extract info for Tcp socket info provided via netlink. */
-static int tcp_illinois_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct illinois *ca = inet_csk_ca(sk);
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = 1,
- .tcpv_rttcnt = ca->cnt_rtt,
- .tcpv_minrtt = ca->base_rtt,
- };
+ info->vegas.tcpv_enabled = 1;
+ info->vegas.tcpv_rttcnt = ca->cnt_rtt;
+ info->vegas.tcpv_minrtt = ca->base_rtt;
+ info->vegas.tcpv_rtt = 0;
- if (info.tcpv_rttcnt > 0) {
+ if (info->vegas.tcpv_rttcnt > 0) {
u64 t = ca->sum_rtt;
- do_div(t, info.tcpv_rttcnt);
- info.tcpv_rtt = t;
+ do_div(t, info->vegas.tcpv_rttcnt);
+ info->vegas.tcpv_rtt = t;
}
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3a4d9b34bed4..c9ab964189a0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1820,14 +1820,12 @@ advance_sp:
for (j = 0; j < used_sacks; j++)
tp->recv_sack_cache[i++] = sp[j];
- tcp_mark_lost_retrans(sk);
-
- tcp_verify_left_out(tp);
-
if ((state.reord < tp->fackets_out) &&
((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
+ tcp_mark_lost_retrans(sk);
+ tcp_verify_left_out(tp);
out:
#if FASTRETRANS_DEBUG > 0
@@ -2700,16 +2698,21 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
+ if ((flag & FLAG_SND_UNA_ADVANCED) &&
+ tcp_try_undo_loss(sk, false))
+ return;
+
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
/* Step 3.b. A timeout is spurious if not all data are
* lost, i.e., never-retransmitted data are (s)acked.
*/
- if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
return;
- if (after(tp->snd_nxt, tp->high_seq) &&
- (flag & FLAG_DATA_SACKED || is_dupack)) {
- tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
+ if (after(tp->snd_nxt, tp->high_seq)) {
+ if (flag & FLAG_DATA_SACKED || is_dupack)
+ tp->frto = 0; /* Step 3.a. loss was real */
} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
tp->high_seq = tp->snd_nxt;
__tcp_push_pending_frames(sk, tcp_current_mss(sk),
@@ -2734,8 +2737,6 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
- if (tcp_try_undo_loss(sk, false))
- return;
tcp_xmit_retransmit_queue(sk);
}
@@ -3280,6 +3281,28 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
}
+/* If we update tp->snd_una, also update tp->bytes_acked */
+static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
+{
+ u32 delta = ack - tp->snd_una;
+
+ u64_stats_update_begin(&tp->syncp);
+ tp->bytes_acked += delta;
+ u64_stats_update_end(&tp->syncp);
+ tp->snd_una = ack;
+}
+
+/* If we update tp->rcv_nxt, also update tp->bytes_received */
+static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
+{
+ u32 delta = seq - tp->rcv_nxt;
+
+ u64_stats_update_begin(&tp->syncp);
+ tp->bytes_received += delta;
+ u64_stats_update_end(&tp->syncp);
+ tp->rcv_nxt = seq;
+}
+
/* Update our send window.
*
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
@@ -3315,7 +3338,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
}
}
- tp->snd_una = ack;
+ tcp_snd_una_update(tp, ack);
return flag;
}
@@ -3497,7 +3520,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
* Note, we use the fact that SND.UNA>=SND.WL2.
*/
tcp_update_wl(tp, ack_seq);
- tp->snd_una = ack;
+ tcp_snd_una_update(tp, ack);
flag |= FLAG_WIN_UPDATE;
tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
@@ -4236,7 +4259,7 @@ static void tcp_ofo_queue(struct sock *sk)
tail = skb_peek_tail(&sk->sk_receive_queue);
eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
if (!eaten)
__skb_queue_tail(&sk->sk_receive_queue, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4404,7 +4427,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
__skb_pull(skb, hdrlen);
eaten = (tail &&
tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
- tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
@@ -4497,7 +4520,7 @@ queue_and_out:
eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
}
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
if (skb->len)
tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -5245,7 +5268,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
tcp_rcv_rtt_measure_ts(sk, skb);
__skb_pull(skb, tcp_header_len);
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
eaten = 1;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3571f2be4470..fc1c658ec6c1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,8 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d6311b5365..17e7339ee5ca 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -300,7 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tw->tw_v6_daddr = sk->sk_v6_daddr;
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
- tw->tw_flowlabel = np->flow_label >> 12;
+ tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
@@ -420,7 +420,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
rcu_read_unlock();
}
- if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+ /* If no valid choice made yet, assign current system default ca. */
+ if (!ca_got_dst &&
+ (!icsk->icsk_ca_setsockopt ||
+ !try_module_get(icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
@@ -755,10 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
- inet_csk_reqsk_queue_unlink(sk, req);
- inet_csk_reqsk_queue_removed(sk, req);
-
+ inet_csk_reqsk_queue_drop(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
+ /* Warning: caller must not call reqsk_put(req);
+ * child stole last reference on it.
+ */
return child;
listen_overflow:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8c8d7e06b72f..a369e8a70b2c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2812,39 +2812,65 @@ begin_fwd:
}
}
-/* Send a fin. The caller locks the socket for us. This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+ int amt, status;
+
+ if (size <= sk->sk_forward_alloc)
+ return;
+ amt = sk_mem_pages(size);
+ sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+ sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
*/
void tcp_send_fin(struct sock *sk)
{
+ struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int mss_now;
- /* Optimization, tack on the FIN if we have a queue of
- * unsent frames. But be careful about outgoing SACKS
- * and IP options.
+ /* Optimization, tack on the FIN if we have one skb in write queue and
+ * this skb was not yet sent, or we are under memory pressure.
+ * Note: in the latter case, FIN packet will be sent after a timeout,
+ * as TCP stack thinks it has already been transmitted.
*/
- mss_now = tcp_current_mss(sk);
-
- if (tcp_send_head(sk)) {
- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
- TCP_SKB_CB(skb)->end_seq++;
+ if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+ TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+ TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
+ if (!tcp_send_head(sk)) {
+ /* This means tskb was already sent.
+ * Pretend we included the FIN on previous transmit.
+ * We need to set tp->snd_nxt to the value it would have
+ * if FIN had been sent. This is because retransmit path
+ * does not change tp->snd_nxt.
+ */
+ tp->snd_nxt++;
+ return;
+ }
} else {
- /* Socket is locked, keep trying until memory is available. */
- for (;;) {
- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
- if (skb)
- break;
- yield();
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+ if (unlikely(!skb)) {
+ if (tskb)
+ goto coalesce;
+ return;
}
+ skb_reserve(skb, MAX_TCP_HEADER);
+ sk_forced_wmem_schedule(sk, skb->truesize);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index c71a1b8f7bde..a6cea1d5e20d 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -286,18 +286,19 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
}
/* Extract info for Tcp socket info provided via netlink. */
-int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct vegas *ca = inet_csk_ca(sk);
+
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = ca->doing_vegas_now,
- .tcpv_rttcnt = ca->cntRTT,
- .tcpv_rtt = ca->baseRTT,
- .tcpv_minrtt = ca->minRTT,
- };
-
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ info->vegas.tcpv_enabled = ca->doing_vegas_now,
+ info->vegas.tcpv_rttcnt = ca->cntRTT,
+ info->vegas.tcpv_rtt = ca->baseRTT,
+ info->vegas.tcpv_minrtt = ca->minRTT,
+
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index e8a6b33cc61d..ef9da5306c68 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -19,6 +19,7 @@ void tcp_vegas_init(struct sock *sk);
void tcp_vegas_state(struct sock *sk, u8 ca_state);
void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
-int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info);
#endif /* __TCP_VEGAS_H */
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index b3c57cceb990..c10732e39837 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -256,18 +256,19 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
}
/* Extract info for Tcp socket info provided via netlink. */
-static int tcp_westwood_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct westwood *ca = inet_csk_ca(sk);
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = 1,
- .tcpv_rtt = jiffies_to_usecs(ca->rtt),
- .tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
- };
+ info->vegas.tcpv_enabled = 1;
+ info->vegas.tcpv_rttcnt = 0;
+ info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt),
+ info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d10b7e0112eb..83aa604f9273 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
+#include <linux/inetdevice.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
@@ -1345,10 +1346,8 @@ csum_copy_err:
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
@@ -1962,6 +1961,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
struct sock *sk;
struct dst_entry *dst;
int dif = skb->dev->ifindex;
+ int ours;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1971,14 +1971,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
uh = udp_hdr(skb);
if (skb->pkt_type == PACKET_BROADCAST ||
- skb->pkt_type == PACKET_MULTICAST)
+ skb->pkt_type == PACKET_MULTICAST) {
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+ if (!in_dev)
+ return;
+
+ ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+ iph->protocol);
+ if (!ours)
+ return;
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else if (skb->pkt_type == PACKET_HOST)
+ } else if (skb->pkt_type == PACKET_HOST) {
sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else
+ } else {
return;
+ }
if (!sk)
return;
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-09 20:00:56 +0000