netfilter: x_tables: align per cpu xt_counter

Let's force a 16 bytes alignment on xt_counter percpu allocations,
so that bytes and packets sit in same cache line.

xt_counter being exported to user space, we cannot add __align(16) on
the structure itself.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 95693c4cebdda473a2f3e427dcc2511e83bf7405..1c97a2204379e14676ee33f0b15c5174b7afe680 100644 (file)
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -356,7 +356,8 @@ static inline unsigned long ifname_compare_aligned(const char *_a,
  * so nothing needs to be done there.
  *
  * xt_percpu_counter_alloc returns the address of the percpu
- * counter, or 0 on !SMP.
+ * counter, or 0 on !SMP. We force an alignment of 16 bytes
+ * so that bytes/packets share a common cache line.
  *
  * Hence caller must use IS_ERR_VALUE to check for error, this
  * allows us to return 0 for single core systems without forcing
@@ -365,7 +366,8 @@ static inline unsigned long ifname_compare_aligned(const char *_a,
 static inline u64 xt_percpu_counter_alloc(void)
 {
        if (nr_cpu_ids > 1) {
-               void __percpu *res = alloc_percpu(struct xt_counters);
+               void __percpu *res = __alloc_percpu(sizeof(struct xt_counters),
+                                                   sizeof(struct xt_counters));
 
                if (res == NULL)
                        return (u64) -ENOMEM;