netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH net V3] Exempt multicast addresses from five-second neighbor lifetime
@ 2020-11-10 17:23 Jeff Dike
  2020-11-12 17:32 ` Jakub Kicinski
  0 siblings, 1 reply; 3+ messages in thread
From: Jeff Dike @ 2020-11-10 17:23 UTC (permalink / raw)
  To: netdev; +Cc: David Ahern, Jakub Kicinski, Jeff Dike

Commit 58956317c8de ("neighbor: Improve garbage collection")
guarantees neighbour table entries a five-second lifetime.  Processes
which make heavy use of multicast can fill the neighour table with
multicast addresses in five seconds.  At that point, neighbour entries
can't be GC-ed because they aren't five seconds old yet, the kernel
log starts to fill up with "neighbor table overflow!" messages, and
sends start to fail.

This patch allows multicast addresses to be thrown out before they've
lived out their five seconds.  This makes room for non-multicast
addresses and makes messages to all addresses more reliable in these
circumstances.

Signed-off-by: Jeff Dike <jdike@akamai.com>
---
 include/net/neighbour.h | 1 +
 net/core/neighbour.c    | 2 ++
 net/ipv4/arp.c          | 6 ++++++
 net/ipv6/ndisc.c        | 7 +++++++
 4 files changed, 16 insertions(+)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 81ee17594c32..22ced1381ede 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -204,6 +204,7 @@ struct neigh_table {
 	int			(*pconstructor)(struct pneigh_entry *);
 	void			(*pdestructor)(struct pneigh_entry *);
 	void			(*proxy_redo)(struct sk_buff *skb);
+	int			(*is_multicast)(const void *pkey);
 	bool			(*allow_add)(const struct net_device *dev,
 					     struct netlink_ext_ack *extack);
 	char			*id;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e39e28b0a8d..9500d28a43b0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 
 			write_lock(&n->lock);
 			if ((n->nud_state == NUD_FAILED) ||
+			    (tbl->is_multicast &&
+			     tbl->is_multicast(n->primary_key)) ||
 			    time_after(tref, n->updated))
 				remove = true;
 			write_unlock(&n->lock);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 687971d83b4e..097aa8bf07ee 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh);
 static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
 static void parp_redo(struct sk_buff *skb);
+static int arp_is_multicast(const void *pkey);
 
 static const struct neigh_ops arp_generic_ops = {
 	.family =		AF_INET,
@@ -156,6 +157,7 @@ struct neigh_table arp_tbl = {
 	.key_eq		= arp_key_eq,
 	.constructor	= arp_constructor,
 	.proxy_redo	= parp_redo,
+	.is_multicast   = arp_is_multicast,
 	.id		= "arp_cache",
 	.parms		= {
 		.tbl			= &arp_tbl,
@@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb)
 	arp_process(dev_net(skb->dev), NULL, skb);
 }
 
+static int arp_is_multicast(const void *pkey)
+{
+	return ipv4_is_multicast(*((__be32 *)pkey));
+}
 
 /*
  *	Receive an arp request from the device layer.
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 27f29b957ee7..67457cfadcd2 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
 static int pndisc_constructor(struct pneigh_entry *n);
 static void pndisc_destructor(struct pneigh_entry *n);
 static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
 
 static const struct neigh_ops ndisc_generic_ops = {
 	.family =		AF_INET6,
@@ -115,6 +116,7 @@ struct neigh_table nd_tbl = {
 	.pconstructor =	pndisc_constructor,
 	.pdestructor =	pndisc_destructor,
 	.proxy_redo =	pndisc_redo,
+	.is_multicast = ndisc_is_multicast,
 	.allow_add  =   ndisc_allow_add,
 	.id =		"ndisc_cache",
 	.parms = {
@@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
+static int ndisc_is_multicast(const void *pkey)
+{
+	return ipv6_addr_is_multicast((struct in6_addr *)pkey);
+}
+
 static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
-- 
2.17.1


^ permalink raw reply related	[flat|nested] 3+ messages in thread
* Re: [PATCH net V3] Exempt multicast addresses from five-second neighbor lifetime
  2020-11-10 17:23 [PATCH net V3] Exempt multicast addresses from five-second neighbor lifetime Jeff Dike
@ 2020-11-12 17:32 ` Jakub Kicinski
  2020-11-13  1:59   ` Jeff Dike
  0 siblings, 1 reply; 3+ messages in thread
From: Jakub Kicinski @ 2020-11-12 17:32 UTC (permalink / raw)
  To: Jeff Dike; +Cc: netdev, David Ahern

On Tue, 10 Nov 2020 12:23:05 -0500 Jeff Dike wrote:
> Commit 58956317c8de ("neighbor: Improve garbage collection")
> guarantees neighbour table entries a five-second lifetime.  Processes
> which make heavy use of multicast can fill the neighour table with
> multicast addresses in five seconds.  At that point, neighbour entries
> can't be GC-ed because they aren't five seconds old yet, the kernel
> log starts to fill up with "neighbor table overflow!" messages, and
> sends start to fail.
> 
> This patch allows multicast addresses to be thrown out before they've
> lived out their five seconds.  This makes room for non-multicast
> addresses and makes messages to all addresses more reliable in these
> circumstances.

We should add 

Fixes: 58956317c8de ("neighbor: Improve garbage collection")

right?

> Signed-off-by: Jeff Dike <jdike@akamai.com>

> diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
> index 687971d83b4e..097aa8bf07ee 100644
> --- a/net/ipv4/arp.c
> +++ b/net/ipv4/arp.c
> @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh);
>  static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
>  static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
>  static void parp_redo(struct sk_buff *skb);
> +static int arp_is_multicast(const void *pkey);
>  
>  static const struct neigh_ops arp_generic_ops = {
>  	.family =		AF_INET,
> @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = {
>  	.key_eq		= arp_key_eq,
>  	.constructor	= arp_constructor,
>  	.proxy_redo	= parp_redo,
> +	.is_multicast   = arp_is_multicast,

extreme nit pick - please align the = sign using tabs like the
surrounding code does.

>  	.id		= "arp_cache",
>  	.parms		= {
>  		.tbl			= &arp_tbl,
> @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb)
>  	arp_process(dev_net(skb->dev), NULL, skb);
>  }
>  
> +static int arp_is_multicast(const void *pkey)
> +{
> +	return ipv4_is_multicast(*((__be32 *)pkey));
> +}
>  
>  /*
>   *	Receive an arp request from the device layer.
> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
> index 27f29b957ee7..67457cfadcd2 100644
> --- a/net/ipv6/ndisc.c
> +++ b/net/ipv6/ndisc.c
> @@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
>  static int pndisc_constructor(struct pneigh_entry *n);
>  static void pndisc_destructor(struct pneigh_entry *n);
>  static void pndisc_redo(struct sk_buff *skb);
> +static int ndisc_is_multicast(const void *pkey);
>  
>  static const struct neigh_ops ndisc_generic_ops = {
>  	.family =		AF_INET6,
> @@ -115,6 +116,7 @@ struct neigh_table nd_tbl = {
>  	.pconstructor =	pndisc_constructor,
>  	.pdestructor =	pndisc_destructor,
>  	.proxy_redo =	pndisc_redo,
> +	.is_multicast = ndisc_is_multicast,

looks like the character after = is expected to be a tab, for better or
worse

>  	.allow_add  =   ndisc_allow_add,
>  	.id =		"ndisc_cache",
>  	.parms = {
> @@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb)
>  	kfree_skb(skb);
>  }
>  
> +static int ndisc_is_multicast(const void *pkey)
> +{
> +	return ipv6_addr_is_multicast((struct in6_addr *)pkey);
> +}
> +
>  static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
>  {
>  	struct inet6_dev *idev = __in6_dev_get(skb->dev);


^ permalink raw reply	[flat|nested] 3+ messages in thread
* Re: [PATCH net V3] Exempt multicast addresses from five-second neighbor lifetime
  2020-11-12 17:32 ` Jakub Kicinski
@ 2020-11-13  1:59   ` Jeff Dike
  0 siblings, 0 replies; 3+ messages in thread
From: Jeff Dike @ 2020-11-13  1:59 UTC (permalink / raw)
  To: Jakub Kicinski; +Cc: netdev, David Ahern

Hi Jakub,

Yes to all your suggestions.

Thanks for the review.

Jeff

On 11/12/20 12:32 PM, Jakub Kicinski wrote:
> On Tue, 10 Nov 2020 12:23:05 -0500 Jeff Dike wrote:
>> Commit 58956317c8de ("neighbor: Improve garbage collection")
>> guarantees neighbour table entries a five-second lifetime.  Processes
>> which make heavy use of multicast can fill the neighour table with
>> multicast addresses in five seconds.  At that point, neighbour entries
>> can't be GC-ed because they aren't five seconds old yet, the kernel
>> log starts to fill up with "neighbor table overflow!" messages, and
>> sends start to fail.
>>
>> This patch allows multicast addresses to be thrown out before they've
>> lived out their five seconds.  This makes room for non-multicast
>> addresses and makes messages to all addresses more reliable in these
>> circumstances.
> 
> We should add 
> 
> Fixes: 58956317c8de ("neighbor: Improve garbage collection")
> 
> right?
> 
>> Signed-off-by: Jeff Dike <jdike@akamai.com>
> 
>> diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
>> index 687971d83b4e..097aa8bf07ee 100644
>> --- a/net/ipv4/arp.c
>> +++ b/net/ipv4/arp.c
>> @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh);
>>  static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
>>  static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
>>  static void parp_redo(struct sk_buff *skb);
>> +static int arp_is_multicast(const void *pkey);
>>  
>>  static const struct neigh_ops arp_generic_ops = {
>>  	.family =		AF_INET,
>> @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = {
>>  	.key_eq		= arp_key_eq,
>>  	.constructor	= arp_constructor,
>>  	.proxy_redo	= parp_redo,
>> +	.is_multicast   = arp_is_multicast,
> 
> extreme nit pick - please align the = sign using tabs like the
> surrounding code does.
> 
>>  	.id		= "arp_cache",
>>  	.parms		= {
>>  		.tbl			= &arp_tbl,
>> @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb)
>>  	arp_process(dev_net(skb->dev), NULL, skb);
>>  }
>>  
>> +static int arp_is_multicast(const void *pkey)
>> +{
>> +	return ipv4_is_multicast(*((__be32 *)pkey));
>> +}
>>  
>>  /*
>>   *	Receive an arp request from the device layer.
>> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
>> index 27f29b957ee7..67457cfadcd2 100644
>> --- a/net/ipv6/ndisc.c
>> +++ b/net/ipv6/ndisc.c
>> @@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
>>  static int pndisc_constructor(struct pneigh_entry *n);
>>  static void pndisc_destructor(struct pneigh_entry *n);
>>  static void pndisc_redo(struct sk_buff *skb);
>> +static int ndisc_is_multicast(const void *pkey);
>>  
>>  static const struct neigh_ops ndisc_generic_ops = {
>>  	.family =		AF_INET6,
>> @@ -115,6 +116,7 @@ struct neigh_table nd_tbl = {
>>  	.pconstructor =	pndisc_constructor,
>>  	.pdestructor =	pndisc_destructor,
>>  	.proxy_redo =	pndisc_redo,
>> +	.is_multicast = ndisc_is_multicast,
> 
> looks like the character after = is expected to be a tab, for better or
> worse
> 
>>  	.allow_add  =   ndisc_allow_add,
>>  	.id =		"ndisc_cache",
>>  	.parms = {
>> @@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb)
>>  	kfree_skb(skb);
>>  }
>>  
>> +static int ndisc_is_multicast(const void *pkey)
>> +{
>> +	return ipv6_addr_is_multicast((struct in6_addr *)pkey);
>> +}
>> +
>>  static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
>>  {
>>  	struct inet6_dev *idev = __in6_dev_get(skb->dev);
> 

^ permalink raw reply	[flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-11-13  2:00 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-11-10 17:23 [PATCH net V3] Exempt multicast addresses from five-second neighbor lifetime Jeff Dike
2020-11-12 17:32 ` Jakub Kicinski
2020-11-13  1:59   ` Jeff Dike

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).