netfilter: x_tables: pack percpu counter allocations

instead of allocating each xt_counter individually, allocate 4k chunks
and then use these for counter allocation requests.

This should speed up rule evaluation by increasing data locality,
also speeds up ruleset loading because we reduce calls to the percpu
allocator.

As Eric points out we can't use PAGE_SIZE, page_allocator would fail on
arches with 64k page size.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This commit is contained in:
Florian Westphal
2016-11-22 14:44:19 +01:00
committed by Pablo Neira Ayuso
parent f28e15bace
commit ae0ac0ed6f
5 changed files with 48 additions and 19 deletions

View File

@@ -411,13 +411,14 @@ static inline int check_target(struct arpt_entry *e, const char *name)
}
static inline int
find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
struct xt_percpu_counter_alloc_state *alloc_state)
{
struct xt_entry_target *t;
struct xt_target *target;
int ret;
if (!xt_percpu_counter_alloc(&e->counters))
if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
return -ENOMEM;
t = arpt_get_target(e);
@@ -525,6 +526,7 @@ static inline void cleanup_entry(struct arpt_entry *e)
static int translate_table(struct xt_table_info *newinfo, void *entry0,
const struct arpt_replace *repl)
{
struct xt_percpu_counter_alloc_state alloc_state = { 0 };
struct arpt_entry *iter;
unsigned int *offsets;
unsigned int i;
@@ -587,7 +589,8 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
/* Finally, each sanity check must pass */
i = 0;
xt_entry_foreach(iter, entry0, newinfo->size) {
ret = find_check_entry(iter, repl->name, repl->size);
ret = find_check_entry(iter, repl->name, repl->size,
&alloc_state);
if (ret != 0)
break;
++i;

View File

@@ -531,7 +531,8 @@ static int check_target(struct ipt_entry *e, struct net *net, const char *name)
static int
find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
unsigned int size)
unsigned int size,
struct xt_percpu_counter_alloc_state *alloc_state)
{
struct xt_entry_target *t;
struct xt_target *target;
@@ -540,7 +541,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
if (!xt_percpu_counter_alloc(&e->counters))
if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
return -ENOMEM;
j = 0;
@@ -676,6 +677,7 @@ static int
translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ipt_replace *repl)
{
struct xt_percpu_counter_alloc_state alloc_state = { 0 };
struct ipt_entry *iter;
unsigned int *offsets;
unsigned int i;
@@ -735,7 +737,8 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
/* Finally, each sanity check must pass */
i = 0;
xt_entry_foreach(iter, entry0, newinfo->size) {
ret = find_check_entry(iter, net, repl->name, repl->size);
ret = find_check_entry(iter, net, repl->name, repl->size,
&alloc_state);
if (ret != 0)
break;
++i;