net: tcp: add RTAX_CC_ALGO fib handling
This patch adds the minimum necessary for the RTAX_CC_ALGO congestion
control metric to be set up and dumped back to user space.
While the internal representation of RTAX_CC_ALGO is handled as a u32
key, we avoided to expose this implementation detail to user space, thus
instead, we chose the netlink attribute that is being exchanged between
user space to be the actual congestion control algorithm name, similarly
as in the setsockopt(2) API in order to allow for maximum flexibility,
even for 3rd party modules.
It is a bit unfortunate that RTAX_QUICKACK used up a whole RTAX slot as
it should have been stored in RTAX_FEATURES instead, we first thought
about reusing it for the congestion control key, but it brings more
complications and/or confusion than worth it.
Joint work with Florian Westphal.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index da983d4..6a6cdad 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -50,6 +50,7 @@
#include <net/arp.h>
#include <net/route.h>
#include <net/udp.h>
+#include <net/tcp.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
@@ -669,9 +670,19 @@
for (i = 0; i < RTAX_MAX; i++) {
if (metrics[i]) {
+ if (i == RTAX_CC_ALGO - 1) {
+ char tmp[TCP_CA_NAME_MAX], *name;
+
+ name = tcp_ca_get_name_by_key(metrics[i], tmp);
+ if (!name)
+ continue;
+ if (nla_put_string(skb, i + 1, name))
+ goto nla_put_failure;
+ } else {
+ if (nla_put_u32(skb, i + 1, metrics[i]))
+ goto nla_put_failure;
+ }
valid++;
- if (nla_put_u32(skb, i+1, metrics[i]))
- goto nla_put_failure;
}
}
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index d332aef..df48034 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -298,7 +298,8 @@
int type = nla_type(attr);
if (type) {
- if (type > RTAX_MAX || nla_len(attr) < 4)
+ if (type > RTAX_MAX || type == RTAX_CC_ALGO ||
+ nla_len(attr) < 4)
goto err_inval;
fi->fib_metrics[type-1] = nla_get_u32(attr);
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 86e3807..3f19fcb 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -29,6 +29,7 @@
#include <linux/route.h> /* RTF_xxx */
#include <net/neighbour.h>
#include <net/netlink.h>
+#include <net/tcp.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/fib_rules.h>
@@ -273,7 +274,8 @@
size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(4) /* RTA_TABLE */
+ nla_total_size(2) /* RTA_DST */
- + nla_total_size(4); /* RTA_PRIORITY */
+ + nla_total_size(4) /* RTA_PRIORITY */
+ + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
/* space for nested metrics */
payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f99f41b..d2b7b55 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -360,7 +360,8 @@
+ nla_total_size(4) /* RTA_TABLE */
+ nla_total_size(4) /* RTA_DST */
+ nla_total_size(4) /* RTA_PRIORITY */
- + nla_total_size(4); /* RTA_PREFSRC */
+ + nla_total_size(4) /* RTA_PREFSRC */
+ + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
/* space for nested metrics */
payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
@@ -859,7 +860,16 @@
if (type > RTAX_MAX)
goto err_inval;
- val = nla_get_u32(nla);
+ 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)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 454771d..34dcbb5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1488,10 +1488,22 @@
int type = nla_type(nla);
if (type) {
+ u32 val;
+
if (unlikely(type > RTAX_MAX))
goto err;
+ if (type == RTAX_CC_ALGO) {
+ char tmp[TCP_CA_NAME_MAX];
- mp[type - 1] = nla_get_u32(nla);
+ nla_strlcpy(tmp, nla, sizeof(tmp));
+ val = tcp_ca_get_key_by_name(tmp);
+ if (val == TCP_CA_UNSPEC)
+ goto err;
+ } else {
+ val = nla_get_u32(nla);
+ }
+
+ mp[type - 1] = val;
__set_bit(type - 1, mxc->mx_valid);
}
}
@@ -2571,7 +2583,8 @@
+ nla_total_size(4) /* RTA_OIF */
+ nla_total_size(4) /* RTA_PRIORITY */
+ RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
- + nla_total_size(sizeof(struct rta_cacheinfo));
+ + nla_total_size(sizeof(struct rta_cacheinfo))
+ + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
}
static int rt6_fill_node(struct net *net,