Re: [PATCH v3] net: neighbor: fix a crash caused by mod zero

[Eric Dumazet <eric.dumazet@gmail.com>]

On 12/22/20 1:38 PM, weichenchen wrote:
> pneigh_enqueue() tries to obtain a random delay by mod
> NEIGH_VAR(p, PROXY_DELAY). However, NEIGH_VAR(p, PROXY_DELAY)
> migth be zero at that point because someone could write zero
> to /proc/sys/net/ipv4/neigh/[device]/proxy_delay after the
> callers check it.
> 
> This patch makes pneigh_enqueue() get a delay time passed in
> by the callers and the callers guarantee it is not zero.
> 
> Signed-off-by: weichenchen <weichen.chen@linux.alibaba.com>
> ---
> V3:
>     - Callers need to pass the delay time to pneigh_enqueue()
>       now and they should guarantee it is not zero.
>     - Use READ_ONCE() to read NEIGH_VAR(p, PROXY_DELAY) in both
>       of the existing callers of pneigh_enqueue() and then pass
>       it to pneigh_enqueue().
> V2:
>     - Use READ_ONCE() to prevent the complier from re-reading
>       NEIGH_VAR(p, PROXY_DELAY).
>     - Give a hint to the complier that delay <= 0 is unlikely
>       to happen.
> ---
>  include/net/neighbour.h | 2 +-
>  net/core/neighbour.c    | 5 ++---
>  net/ipv4/arp.c          | 8 +++++---
>  net/ipv6/ndisc.c        | 6 +++---
>  4 files changed, 11 insertions(+), 10 deletions(-)
> 
> diff --git a/include/net/neighbour.h b/include/net/neighbour.h
> index 22ced1381ede..f7564dc5304d 100644
> --- a/include/net/neighbour.h
> +++ b/include/net/neighbour.h
> @@ -352,7 +352,7 @@ struct net *neigh_parms_net(const struct neigh_parms *parms)
>  unsigned long neigh_rand_reach_time(unsigned long base);
>  
>  void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
> -		    struct sk_buff *skb);
> +		    struct sk_buff *skb, int delay);
>  struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net,
>  				   const void *key, struct net_device *dev,
>  				   int creat);
> diff --git a/net/core/neighbour.c b/net/core/neighbour.c
> index 9500d28a43b0..b440f966d109 100644
> --- a/net/core/neighbour.c
> +++ b/net/core/neighbour.c
> @@ -1567,12 +1567,11 @@ static void neigh_proxy_process(struct timer_list *t)
>  }
>  
>  void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
> -		    struct sk_buff *skb)
> +		    struct sk_buff *skb, int delay)
>  {
>  	unsigned long now = jiffies;
>  
> -	unsigned long sched_next = now + (prandom_u32() %
> -					  NEIGH_VAR(p, PROXY_DELAY));
> +	unsigned long sched_next = now + (prandom_u32() % delay);
>  
>  	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
>  		kfree_skb(skb);

This seems rather complex, what about not using a divide in the first place ? :

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9500d28a43b0e1a390382912b6fb59db935e727b..745bc89acc87c2a4802fb6f301c11edd2f0096da 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1569,10 +1569,7 @@ static void neigh_proxy_process(struct timer_list *t)
 void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
                    struct sk_buff *skb)
 {
-       unsigned long now = jiffies;
-
-       unsigned long sched_next = now + (prandom_u32() %
-                                         NEIGH_VAR(p, PROXY_DELAY));
+       unsigned long sched_next = jiffies + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
        if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
                kfree_skb(skb);