tcp: use dctcp if enabled on the route to the initiator

Currently, the following case doesn't use DCTCP, even if it should:
A responder has f.e. Cubic as system wide default, but for a specific
route to the initiating host, DCTCP is being set in RTAX_CC_ALGO. The
initiating host then uses DCTCP as congestion control, but since the
initiator sets ECT(0), tcp_ecn_create_request() doesn't set ecn_ok,
and we have to fall back to Reno after 3WHS completes.

We were thinking on how to solve this in a minimal, non-intrusive
way without bloating tcp_ecn_create_request() needlessly: lets cache
the CA ecn option flag in RTAX_FEATURES. In other words, when ECT(0)
is set on the SYN packet, set ecn_ok=1 iff route RTAX_FEATURES
contains the unexposed (internal-only) DST_FEATURE_ECN_CA. This allows
to only do a single metric feature lookup inside tcp_ecn_create_request().

Joint work with Florian Westphal.

Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Florian Westphal <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
This commit is contained in:
Daniel Borkmann 2015-08-31 15:58:47 +02:00 • committed by David S. Miller
commit c3a8d94746
7 changed files with 36 additions and 9 deletions

View file

@ -879,6 +879,7 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
static int
fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
{
bool ecn_ca = false;
struct nlattr *nla;
int remaining;
@ -898,7 +899,7 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(tmp);
val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC)
return -EINVAL;
} else {
@ -913,6 +914,9 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
fi->fib_metrics[type - 1] = val;
}
if (ecn_ca)
fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
return 0;
}

View file

@ -114,16 +114,19 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
}
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
u32 tcp_ca_get_key_by_name(const char *name)
u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
{
const struct tcp_congestion_ops *ca;
u32 key;
u32 key = TCP_CA_UNSPEC;
might_sleep();
rcu_read_lock();
ca = __tcp_ca_find_autoload(name);
key = ca ? ca->key : TCP_CA_UNSPEC;
if (ca) {
key = ca->key;
*ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN;
}
rcu_read_unlock();
return key;

View file

@ -6003,14 +6003,17 @@ static void tcp_ecn_create_request(struct request_sock *req,
const struct net *net = sock_net(listen_sk);
bool th_ecn = th->ece && th->cwr;
bool ect, ecn_ok;
u32 ecn_ok_dst;
if (!th_ecn)
return;
ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN);
ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk))
if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
(ecn_ok_dst & DST_FEATURE_ECN_CA))
inet_rsk(req)->ecn_ok = 1;
}