remarkable-linux/kernel/res_counter.c
Glauber Costa 0e90b31f4b net: introduce res_counter_charge_nofail() for socket allocations
There is a case in __sk_mem_schedule(), where an allocation
is beyond the maximum, but yet we are allowed to proceed.
It happens under the following condition:

	sk->sk_wmem_queued + size >= sk->sk_sndbuf

The network code won't revert the allocation in this case,
meaning that at some point later it'll try to do it. Since
this is never communicated to the underlying res_counter
code, there is an inbalance in res_counter uncharge operation.

I see two ways of fixing this:

1) storing the information about those allocations somewhere
   in memcg, and then deducting from that first, before
   we start draining the res_counter,
2) providing a slightly different allocation function for
   the res_counter, that matches the original behavior of
   the network code more closely.

I decided to go for #2 here, believing it to be more elegant,
since #1 would require us to do basically that, but in a more
obscure way.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
CC: Tejun Heo <tj@kernel.org>
CC: Li Zefan <lizf@cn.fujitsu.com>
CC: Laurent Chavey <chavey@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-01-22 15:08:46 -05:00

216 lines
4.5 KiB
C

/*
* resource cgroups
*
* Copyright 2007 OpenVZ SWsoft Inc
*
* Author: Pavel Emelianov <xemul@openvz.org>
*
*/
#include <linux/types.h>
#include <linux/parser.h>
#include <linux/fs.h>
#include <linux/res_counter.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
counter->limit = RESOURCE_MAX;
counter->soft_limit = RESOURCE_MAX;
counter->parent = parent;
}
int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
{
if (counter->usage + val > counter->limit) {
counter->failcnt++;
return -ENOMEM;
}
counter->usage += val;
if (counter->usage > counter->max_usage)
counter->max_usage = counter->usage;
return 0;
}
int res_counter_charge(struct res_counter *counter, unsigned long val,
struct res_counter **limit_fail_at)
{
int ret;
unsigned long flags;
struct res_counter *c, *u;
*limit_fail_at = NULL;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
ret = res_counter_charge_locked(c, val);
spin_unlock(&c->lock);
if (ret < 0) {
*limit_fail_at = c;
goto undo;
}
}
ret = 0;
goto done;
undo:
for (u = counter; u != c; u = u->parent) {
spin_lock(&u->lock);
res_counter_uncharge_locked(u, val);
spin_unlock(&u->lock);
}
done:
local_irq_restore(flags);
return ret;
}
int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
struct res_counter **limit_fail_at)
{
int ret, r;
unsigned long flags;
struct res_counter *c;
r = ret = 0;
*limit_fail_at = NULL;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
r = res_counter_charge_locked(c, val);
if (r)
c->usage += val;
spin_unlock(&c->lock);
if (r < 0 && ret == 0) {
*limit_fail_at = c;
ret = r;
}
}
local_irq_restore(flags);
return ret;
}
void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
{
if (WARN_ON(counter->usage < val))
val = counter->usage;
counter->usage -= val;
}
void res_counter_uncharge(struct res_counter *counter, unsigned long val)
{
unsigned long flags;
struct res_counter *c;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
res_counter_uncharge_locked(c, val);
spin_unlock(&c->lock);
}
local_irq_restore(flags);
}
static inline unsigned long long *
res_counter_member(struct res_counter *counter, int member)
{
switch (member) {
case RES_USAGE:
return &counter->usage;
case RES_MAX_USAGE:
return &counter->max_usage;
case RES_LIMIT:
return &counter->limit;
case RES_FAILCNT:
return &counter->failcnt;
case RES_SOFT_LIMIT:
return &counter->soft_limit;
};
BUG();
return NULL;
}
ssize_t res_counter_read(struct res_counter *counter, int member,
const char __user *userbuf, size_t nbytes, loff_t *pos,
int (*read_strategy)(unsigned long long val, char *st_buf))
{
unsigned long long *val;
char buf[64], *s;
s = buf;
val = res_counter_member(counter, member);
if (read_strategy)
s += read_strategy(*val, s);
else
s += sprintf(s, "%llu\n", *val);
return simple_read_from_buffer((void __user *)userbuf, nbytes,
pos, buf, s - buf);
}
#if BITS_PER_LONG == 32
u64 res_counter_read_u64(struct res_counter *counter, int member)
{
unsigned long flags;
u64 ret;
spin_lock_irqsave(&counter->lock, flags);
ret = *res_counter_member(counter, member);
spin_unlock_irqrestore(&counter->lock, flags);
return ret;
}
#else
u64 res_counter_read_u64(struct res_counter *counter, int member)
{
return *res_counter_member(counter, member);
}
#endif
int res_counter_memparse_write_strategy(const char *buf,
unsigned long long *res)
{
char *end;
/* return RESOURCE_MAX(unlimited) if "-1" is specified */
if (*buf == '-') {
*res = simple_strtoull(buf + 1, &end, 10);
if (*res != 1 || *end != '\0')
return -EINVAL;
*res = RESOURCE_MAX;
return 0;
}
*res = memparse(buf, &end);
if (*end != '\0')
return -EINVAL;
*res = PAGE_ALIGN(*res);
return 0;
}
int res_counter_write(struct res_counter *counter, int member,
const char *buf, write_strategy_fn write_strategy)
{
char *end;
unsigned long flags;
unsigned long long tmp, *val;
if (write_strategy) {
if (write_strategy(buf, &tmp))
return -EINVAL;
} else {
tmp = simple_strtoull(buf, &end, 10);
if (*end != '\0')
return -EINVAL;
}
spin_lock_irqsave(&counter->lock, flags);
val = res_counter_member(counter, member);
*val = tmp;
spin_unlock_irqrestore(&counter->lock, flags);
return 0;
}