Commit 9dc30648 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'per-route-dctcp-receive-side' 



Daniel Borkmann says:

====================
tcp: receive-side per route dctcp handling

Original cover letter:

  Currently, the following case doesn't use DCTCP, even if it should:

    - responder has f.e. cubic as system wide default
    - 'ip route congctl dctcp $src' was set

  Then, DCTCP is NOT used if a DCTCP sender attempts to connect from a
  host in the $src range: ECT(0) is set, but listen_sk is not dctcp, so
  we fail the INET_ECN_is_not_ect sanity check.

  We also have to examine the dst used for the SYN/ACK reply to make
  this case work.

  In order to minimize additional cost, store the 'ecn is must have'
  information is the dst_features field.

  The set targets -next instead of -net since this doesn't seem to be a
  serious bug and to give the change more soak time until it hits linus
  tree.

v1 -> v2:
 - Addressed Dave's feedback, not exposing any bits to user space
 - Added patch 3 to reject incorrect configurations
 - Rest as is, rebased and retested
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 87583ebb c3a8d947

include/net/dst.h

+6 −0
Original line number Diff line number Diff line
@@ -207,6 +207,12 @@ static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) 
		p[metric-1] = val;

}



/* Kernel-internal feature bits that are unallocated in user space. */

#define DST_FEATURE_ECN_CA	(1 << 31)



#define DST_FEATURE_MASK	(DST_FEATURE_ECN_CA)

#define DST_FEATURE_ECN_MASK	(DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN)



static inline u32

dst_feature(const struct dst_entry *dst, u32 feature)

{

include/net/tcp.h

+1 −1
Original line number Diff line number Diff line
@@ -888,7 +888,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); 
extern struct tcp_congestion_ops tcp_reno;



struct tcp_congestion_ops *tcp_ca_find_key(u32 key);

u32 tcp_ca_get_key_by_name(const char *name);

u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);

#ifdef CONFIG_INET

char *tcp_ca_get_name_by_key(u32 key, char *buffer);

#else

include/uapi/linux/rtnetlink.h

+7 −4
Original line number Diff line number Diff line
@@ -418,10 +418,13 @@ enum { 


#define RTAX_MAX (__RTAX_MAX - 1)



#define RTAX_FEATURE_ECN	0x00000001

#define RTAX_FEATURE_SACK	0x00000002

#define RTAX_FEATURE_TIMESTAMP	0x00000004

#define RTAX_FEATURE_ALLFRAG	0x00000008

#define RTAX_FEATURE_ECN	(1 << 0)

#define RTAX_FEATURE_SACK	(1 << 1)

#define RTAX_FEATURE_TIMESTAMP	(1 << 2)

#define RTAX_FEATURE_ALLFRAG	(1 << 3)



#define RTAX_FEATURE_MASK	(RTAX_FEATURE_ECN | RTAX_FEATURE_SACK | \

				 RTAX_FEATURE_TIMESTAMP | RTAX_FEATURE_ALLFRAG)



struct rta_session {

	__u8	proto;

net/core/rtnetlink.c

+6 −0
Original line number Diff line number Diff line
@@ -678,6 +678,12 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) 
					continue;

				if (nla_put_string(skb, i + 1, name))

					goto nla_put_failure;

			} else if (i == RTAX_FEATURES - 1) {

				u32 user_features = metrics[i] & RTAX_FEATURE_MASK;



				BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK);

				if (nla_put_u32(skb, i + 1, user_features))

					goto nla_put_failure;

			} else {

				if (nla_put_u32(skb, i + 1, metrics[i]))

					goto nla_put_failure;

net/ipv4/fib_semantics.c

+47 −30
Original line number Diff line number Diff line
@@ -876,6 +876,50 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) 
	return true;

}



static int

fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)

{

	bool ecn_ca = false;

	struct nlattr *nla;

	int remaining;



	if (!cfg->fc_mx)

		return 0;



	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {

		int type = nla_type(nla);

		u32 val;



		if (!type)

			continue;

		if (type > RTAX_MAX)

			return -EINVAL;



		if (type == RTAX_CC_ALGO) {

			char tmp[TCP_CA_NAME_MAX];



			nla_strlcpy(tmp, nla, sizeof(tmp));

			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);

			if (val == TCP_CA_UNSPEC)

				return -EINVAL;

		} else {

			val = nla_get_u32(nla);

		}

		if (type == RTAX_ADVMSS && val > 65535 - 40)

			val = 65535 - 40;

		if (type == RTAX_MTU && val > 65535 - 15)

			val = 65535 - 15;

		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))

			return -EINVAL;

		fi->fib_metrics[type - 1] = val;

	}



	if (ecn_ca)

		fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;



	return 0;

}



struct fib_info *fib_create_info(struct fib_config *cfg)

{

	int err;
@@ -948,36 +992,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) 
			goto failure;

	} endfor_nexthops(fi)



	if (cfg->fc_mx) {

		struct nlattr *nla;

		int remaining;



		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {

			int type = nla_type(nla);



			if (type) {

				u32 val;



				if (type > RTAX_MAX)

					goto err_inval;

				if (type == RTAX_CC_ALGO) {

					char tmp[TCP_CA_NAME_MAX];



					nla_strlcpy(tmp, nla, sizeof(tmp));

					val = tcp_ca_get_key_by_name(tmp);

					if (val == TCP_CA_UNSPEC)

						goto err_inval;

				} else {

					val = nla_get_u32(nla);

				}

				if (type == RTAX_ADVMSS && val > 65535 - 40)

					val = 65535 - 40;

				if (type == RTAX_MTU && val > 65535 - 15)

					val = 65535 - 15;

				fi->fib_metrics[type - 1] = val;

			}

		}

	}

	err = fib_convert_metrics(fi, cfg);

	if (err)

		goto failure;



	if (cfg->fc_mp) {

#ifdef CONFIG_IP_ROUTE_MULTIPATH

CRA Git | Maintained and supported by SUSTech CRA and CCSE