Re: [PATCH] netfilter: use per-cpu spinlock rather than RCU

[Eric Dumazet <dada1@cosmosbay.com>]

Stephen Hemminger a écrit :
> This is an alternative version of ip/ip6/arp tables locking using
> per-cpu locks.  This avoids the overhead of synchronize_net() during
> update but still removes the expensive rwlock in earlier versions.
> 
> The idea for this came from an earlier version done by Eric Duzamet.
> Locking is done per-cpu, the fast path locks on the current cpu
> and updates counters.  The slow case involves acquiring the locks on
> all cpu's.
> 
> The mutex that was added for 2.6.30 in xt_table is unnecessary since
> there already is a mutex for xt[af].mutex that is held.
> 
> Tested basic functionality (add/remove/list), but don't have test cases
> for stress, ip6tables or arptables.
> 
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

Patch seems good to me, but apparently xt_replace_table()
misses the "acquiring the locks on all cpus" you mentioned in ChangeLog ?

I am still off-computers until tomorrow so cannot provide a patch for this, sorry.

Some form of

local_bh_disable();
for_each_possible_cpu(cpu)
	spin_lock(&per_cpu(ip_tables_lock, cpu));

oldinfo = private;
/* do the substitution */
table->private = newinfo;
newinfo->initial_entries = oldinfo->initial_entries;

for_each_possible_cpu(cpu)
	spin_unlock(&per_cpu(ip_tables_lock, cpu));
local_bh_enable();


But I wonder if this could hit a limit of max spinlocks held by this cpu, say on a 4096 cpu machine ?



--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html