Re: [PATCH net-next 02/13] ipv6: annotate data-races around cnf.disable_ipv6

[Jiri Pirko <jiri@resnulli.us>]

Mon, Feb 26, 2024 at 04:50:44PM CET, edumazet@google.com wrote:
>disable_ipv6 is read locklessly, add appropriate READ_ONCE()
>and WRITE_ONCE() annotations.
>
>Signed-off-by: Eric Dumazet <edumazet@google.com>
>---
> net/ipv6/addrconf.c   | 12 ++++++------
> net/ipv6/ip6_input.c  |  4 ++--
> net/ipv6/ip6_output.c |  2 +-
> 3 files changed, 9 insertions(+), 9 deletions(-)
>
>diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
>index a280614b37652deee0d1f3c70ba1b41b01cc7d91..0d7746b113cc65303b5c2ec223b3331c3598ded6 100644
>--- a/net/ipv6/addrconf.c
>+++ b/net/ipv6/addrconf.c
>@@ -4214,7 +4214,7 @@ static void addrconf_dad_work(struct work_struct *w)
> 			if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
> 			    ipv6_addr_equal(&ifp->addr, &addr)) {
> 				/* DAD failed for link-local based on MAC */
>-				idev->cnf.disable_ipv6 = 1;
>+				WRITE_ONCE(idev->cnf.disable_ipv6, 1);
> 
> 				pr_info("%s: IPv6 being disabled!\n",
> 					ifp->idev->dev->name);
>@@ -6388,7 +6388,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
> 		idev = __in6_dev_get(dev);
> 		if (idev) {
> 			int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
>-			idev->cnf.disable_ipv6 = newf;
>+
>+			WRITE_ONCE(idev->cnf.disable_ipv6, newf);
> 			if (changed)
> 				dev_disable_change(idev);
> 		}
>@@ -6397,15 +6398,14 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
> 
> static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
> {
>-	struct net *net;
>+	struct net *net = (struct net *)table->extra2;

How is this related to the rest of the patch and why is it okay to
access table->extra2 without holding rtnl mutex?


> 	int old;
> 
> 	if (!rtnl_trylock())
> 		return restart_syscall();
> 
>-	net = (struct net *)table->extra2;
> 	old = *p;
>-	*p = newf;
>+	WRITE_ONCE(*p, newf);
> 
> 	if (p == &net->ipv6.devconf_dflt->disable_ipv6) {
> 		rtnl_unlock();
>@@ -6413,7 +6413,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
> 	}
> 
> 	if (p == &net->ipv6.devconf_all->disable_ipv6) {
>-		net->ipv6.devconf_dflt->disable_ipv6 = newf;
>+		WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf);
> 		addrconf_disable_change(net, newf);
> 	} else if ((!newf) ^ (!old))
> 		dev_disable_change((struct inet6_dev *)table->extra1);
>diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
>index b8378814532cead0275e8b7a656f78450993f619..1ba97933c74fbd12e21f273f0aeda2313bd608b7 100644
>--- a/net/ipv6/ip6_input.c
>+++ b/net/ipv6/ip6_input.c
>@@ -168,9 +168,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
> 
> 	SKB_DR_SET(reason, NOT_SPECIFIED);
> 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
>-	    !idev || unlikely(idev->cnf.disable_ipv6)) {
>+	    !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
> 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
>-		if (idev && unlikely(idev->cnf.disable_ipv6))
>+		if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6)))
> 			SKB_DR_SET(reason, IPV6DISABLED);
> 		goto drop;
> 	}
>diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
>index 31b86fe661aa6cd94fb5d8848900406c2db110e3..0559bd0005858631f88c706f98c625ad0bfff278 100644
>--- a/net/ipv6/ip6_output.c
>+++ b/net/ipv6/ip6_output.c
>@@ -234,7 +234,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
> 	skb->protocol = htons(ETH_P_IPV6);
> 	skb->dev = dev;
> 
>-	if (unlikely(idev->cnf.disable_ipv6)) {
>+	if (unlikely(READ_ONCE(idev->cnf.disable_ipv6))) {
> 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
> 		kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED);
> 		return 0;
>-- 
>2.44.0.rc1.240.g4c46232300-goog
>
>