[PATCH net-next v2] ipv6: add IFLA_INET6_RA_MTU to expose mtu value in the RA message

From: Rocco Yue
Date: Fri Jul 30 2021 - 22:09:34 EST


The kernel provides a "/proc/sys/net/ipv6/conf/<iface>/mtu"
file, which can temporarily record the mtu value of the last
received RA message when the RA mtu value is lower than the
interface mtu, but this proc has following limitations:

(1) when the interface mtu (/sys/class/net/<iface>/mtu) is
updeated, mtu6 (/proc/sys/net/ipv6/conf/<iface>/mtu) will
be updated to the value of interface mtu;
(2) mtu6 (/proc/sys/net/ipv6/conf/<iface>/mtu) only affect
ipv6 connection, and not affect ipv4.

Therefore, when the mtu option is carried in the RA message,
there will be a problem that the user sometimes cannot obtain
RA mtu value correctly by reading mtu6.

After this patch set, if a RA message carries the mtu option,
you can send a netlink msg which nlmsg_type is RTM_GETLINK,
and then by parsing the attribute of IFLA_INET6_RA_MTU to
get the mtu value carried in the RA message received on the
inet6 device.

In this way, if the MTU values that the device receives from
the network in the PCO IPv4 and the RA IPv6 procedures are
different, the user space process can read ra_mtu to get
the mtu value carried in the RA message without worrying
about the issue of ipv4 being stuck due to the late arrival
of RA message. After comparing the value of ra_mtu and ipv4
mtu, then the device can use the lower MTU value for both
IPv4 and IPv6.

Signed-off-by: Rocco Yue <rocco.yue@xxxxxxxxxxxx>
---
include/net/if_inet6.h | 2 ++
include/uapi/linux/if_link.h | 1 +
net/ipv6/addrconf.c | 5 +++++
net/ipv6/ndisc.c | 5 +++++
tools/include/uapi/linux/if_link.h | 1 +
5 files changed, 14 insertions(+)

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 71bb4cc4d05d..5cc260dead33 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -213,6 +213,8 @@ struct inet6_dev {

unsigned long tstamp; /* ipv6InterfaceTable update timestamp */
struct rcu_head rcu;
+
+ unsigned int ra_mtu;
};

static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 4882e81514b6..fcd1ae29f154 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -417,6 +417,7 @@ enum {
IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
IFLA_INET6_TOKEN, /* device token */
IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+ IFLA_INET6_RA_MTU, /* mtu carried in the RA message */
__IFLA_INET6_MAX
};

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3bf685fe64b9..98eeaba9f86c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5537,6 +5537,7 @@ static inline size_t inet6_ifla6_size(void)
+ nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */
+ nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */
+ nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */
+ + nla_total_size(4) /* IFLA_INET6_RA_MTU */
+ 0;
}

@@ -5645,6 +5646,9 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode))
goto nla_put_failure;

+ if (nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu))
+ goto nla_put_failure;
+
return 0;

nla_put_failure:
@@ -5761,6 +5765,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token,
static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = {
[IFLA_INET6_ADDR_GEN_MODE] = { .type = NLA_U8 },
[IFLA_INET6_TOKEN] = { .len = sizeof(struct in6_addr) },
+ [IFLA_INET6_RA_MTU] = { .type = NLA_U32 },
};

static int check_addr_gen_mode(int mode)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c467c6419893..9c6417a8e2b7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1496,6 +1496,11 @@ static void ndisc_router_discovery(struct sk_buff *skb)
memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
mtu = ntohl(n);

+ if (in6_dev->ra_mtu != mtu) {
+ in6_dev->ra_mtu = mtu;
+ ND_PRINTK(2, info, "update ra_mtu to %d\n", in6_dev->ra_mtu);
+ }
+
if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
} else if (in6_dev->cnf.mtu6 != mtu) {
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index d208b2af697f..303085cdc271 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -230,6 +230,7 @@ enum {
IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
IFLA_INET6_TOKEN, /* device token */
IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+ IFLA_INET6_RA_MTU, /* mtu carried in the RA message */
__IFLA_INET6_MAX
};

--
2.18.0