aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/net/ipv4
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2020-07-25 17:49:04 -0700
committerDavid S. Miller <davem@davemloft.net>2020-07-25 17:49:04 -0700
commita57066b1a01977a646145f4ce8dfb4538b08368a (patch)
tree57c2b4fa2fc48e687a1820b9bf4ef4f4363be0f9 /net/ipv4
parentMerge branch 'net-dsa-mv88e6xxx-port-mtu-support' (diff)
parentMerge tag 'riscv-for-linus-5.8-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux into master (diff)
downloadwireguard-linux-a57066b1a01977a646145f4ce8dfb4538b08368a.tar.xz
wireguard-linux-a57066b1a01977a646145f4ce8dfb4538b08368a.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
The UDP reuseport conflict was a little bit tricky. The net-next code, via bpf-next, extracted the reuseport handling into a helper so that the BPF sk lookup code could invoke it. At the same time, the logic for reuseport handling of unconnected sockets changed via commit efc6b6f6c3113e8b203b9debfb72d81e0f3dcace which changed the logic to carry on the reuseport result into the rest of the lookup loop if we do not return immediately. This requires moving the reuseport_has_conns() logic into the callers. While we are here, get rid of inline directives as they do not belong in foo.c files. The other changes were cases of more straightforward overlapping modifications. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_input.c11
-rw-r--r--net/ipv4/tcp_output.c13
-rw-r--r--net/ipv4/udp.c30
3 files changed, 28 insertions, 26 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 82906deb7874..a018bafd7bdf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3514,10 +3514,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
}
}
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
*/
static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
{
@@ -3526,7 +3524,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
if (before(ack, tp->tlp_high_seq))
return;
- if (flag & FLAG_DSACKING_ACK) {
+ if (!tp->tlp_retrans) {
+ /* TLP of new data has been acknowledged */
+ tp->tlp_high_seq = 0;
+ } else if (flag & FLAG_DSACKING_ACK) {
/* This DSACK means original and TLP probe arrived; no loss */
tp->tlp_high_seq = 0;
} else if (after(ack, tp->tlp_high_seq)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc0117013ba5..d8f16f6a9b02 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2632,6 +2632,11 @@ void tcp_send_loss_probe(struct sock *sk)
int pcount;
int mss = tcp_current_mss(sk);
+ /* At most one outstanding TLP */
+ if (tp->tlp_high_seq)
+ goto rearm_timer;
+
+ tp->tlp_retrans = 0;
skb = tcp_send_head(sk);
if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
pcount = tp->packets_out;
@@ -2649,10 +2654,6 @@ void tcp_send_loss_probe(struct sock *sk)
return;
}
- /* At most one outstanding TLP retransmission. */
- if (tp->tlp_high_seq)
- goto rearm_timer;
-
if (skb_still_in_host_queue(sk, skb))
goto rearm_timer;
@@ -2674,10 +2675,12 @@ void tcp_send_loss_probe(struct sock *sk)
if (__tcp_retransmit_skb(sk, skb, 1))
goto rearm_timer;
+ tp->tlp_retrans = 1;
+
+probe_sent:
/* Record snd_nxt for loss detection. */
tp->tlp_high_seq = tp->snd_nxt;
-probe_sent:
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
/* Reset s.t. tcp_rearm_rto will restart timer from now */
inet_csk(sk)->icsk_pending = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5a6a2f6d86b9..0fb5e4ea133f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -409,10 +409,10 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
udp_ehash_secret + net_hash_mix(net));
}
-static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
- struct sk_buff *skb,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum)
+static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum)
{
struct sock *reuse_sk = NULL;
u32 hash;
@@ -421,9 +421,6 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
- /* Fall back to scoring if group has connections */
- if (reuseport_has_conns(sk, false))
- return NULL;
}
return reuse_sk;
}
@@ -447,21 +444,22 @@ static struct sock *udp4_lib_lookup2(struct net *net,
if (score > badness) {
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
- if (result)
+ /* Fall back to scoring if group has connections */
+ if (result && !reuseport_has_conns(sk, false))
return result;
+ result = result ? : sk;
badness = score;
- result = sk;
}
}
return result;
}
-static inline struct sock *udp4_lookup_run_bpf(struct net *net,
- struct udp_table *udptable,
- struct sk_buff *skb,
- __be32 saddr, __be16 sport,
- __be32 daddr, u16 hnum)
+static struct sock *udp4_lookup_run_bpf(struct net *net,
+ struct udp_table *udptable,
+ struct sk_buff *skb,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
@@ -475,7 +473,7 @@ static inline struct sock *udp4_lookup_run_bpf(struct net *net,
return sk;
reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
- if (reuse_sk)
+ if (reuse_sk && !reuseport_has_conns(sk, false))
sk = reuse_sk;
return sk;
}
@@ -2107,7 +2105,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
/*
* UDP-Lite specific tests, ignored on UDP sockets
*/
- if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
+ if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
/*
* MIB statistics other than incrementing the error count are