[PATCH net-next v5] ipv6: add IFLA_INET6_RA_MTU to expose mtu value

[PATCH net-next v5] ipv6: add IFLA_INET6_RA_MTU to expose mtu value

[Rocco Yue]

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 addition, you can also get a link notification
when ra_mtu is updated so it doesn't have to poll.

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 can obtain the correct ipv6 ra_mtu value
and compare 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@mediatek.com>
---
 include/net/if_inet6.h             |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 net/ipv6/addrconf.c                |  9 +++++++++
 net/ipv6/ndisc.c                   | 17 +++++++++++------
 tools/include/uapi/linux/if_link.h |  1 +
 5 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 42235c178b06..653e7d0f65cb 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -210,6 +210,8 @@ 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 8aad65b69054..eebd3894fe89 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 8381288a0d6e..2ceeb93b6008 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -394,6 +394,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 		ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
 
 	ndev->cnf.mtu6 = dev->mtu;
+	ndev->ra_mtu = U32_MIN;
 	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
 	if (!ndev->nd_parms) {
 		kfree(ndev);
@@ -3849,6 +3850,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
 	}
 
 	idev->tstamp = jiffies;
+	idev->ra_mtu = U32_MIN;
 
 	/* Last: Shot the device (if unregistered) */
 	if (unregister) {
@@ -5543,6 +5545,7 @@ 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;
 }
 
@@ -5651,6 +5654,9 @@ 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:
@@ -5767,6 +5773,9 @@ 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_REJECT,
+					    .reject_message =
+						"IFLA_INET6_RA_MTU can not be set" },
 };
 
 static int check_addr_gen_mode(int mode)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c467c6419893..4b098521a44c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1391,12 +1391,6 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 		}
 	}
 
-	/*
-	 *	Send a notify if RA changed managed/otherconf flags or timer settings
-	 */
-	if (send_ifinfo_notify)
-		inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
-
 skip_linkparms:
 
 	/*
@@ -1496,6 +1490,11 @@ 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;
+			send_ifinfo_notify = true;
+		}
+
 		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) {
@@ -1519,6 +1518,12 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 		ND_PRINTK(2, warn, "RA: invalid RA options\n");
 	}
 out:
+	/* Send a notify if RA changed managed/otherconf flags or
+	 * timer settings or ra_mtu value
+	 */
+	if (send_ifinfo_notify)
+		inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
+
 	fib6_info_release(rt);
 	if (neigh)
 		neigh_release(neigh);
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index eb15f319aa57..b3610fdd1fee 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

Re: [PATCH net-next v5] ipv6: add IFLA_INET6_RA_MTU to expose mtu value

[David Ahern]

On 8/25/21 11:46 PM, Rocco Yue wrote:
> @@ -5651,6 +5654,9 @@ 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))

I should have seen this earlier. The intent here is to only notify
userspace if the RA contains an MTU in which case this should be

	if (idev->ra_mtu &&
	    nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu))

and in which case idev->ra_mtu should be initialized to 0 explicitly,
not U32_MIN.

Re: [PATCH net-next v5] ipv6: add IFLA_INET6_RA_MTU to expose mtu value

[Rocco Yue]

On Fri, 2021-08-27 at 13:28 +0800, David Ahern wrote:
> On 8/25/21 11:46 PM, Rocco Yue wrote:
>> @@ -5651,6 +5654,9 @@ 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))
> 
> I should have seen this earlier. The intent here is to only notify
> userspace if the RA contains an MTU in which case this should be
> 
> 	if (idev->ra_mtu &&
> 	    nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu))
> 

Hi David,

Thanks for your pretty suggestion.

When ra_mtu = 0, notify userspace is really unnecessary. At first
I did this because when userspace get ra_mtu = 0 through getlink,
then the corresponding operation can be performed.

After adding the restriction of "idev->ra_mtu", I think userspace can
judge whether the mtu option is carried in the RA by judging whether it
can be parsed to IFLA_INET6_RA_MTU after getlink, and perform the
corresponding operation.

I will push the next version.

> and in which case idev->ra_mtu should be initialized to 0 explicitly,
> not U32_MIN.

will do.

Thanks