alistair23-linux/drivers/staging/android/lowmemorykiller.c
Paul E. McKenney 1eda5166c7 staging: android/lowmemorykiller: Don't unregister notifier from atomic context
The lowmemorykiller registers an atomic notifier for notfication of when
the task is freed.  From this atomic notifier callback, it removes the
atomic notifier via task_free_unregister().  This is incorrect because
atomic_notifier_chain_unregister() calls syncronize_rcu(), which can
sleep, which shouldn't be done from an atomic notifier.

Fix this by registering the notifier during init, and only unregister it
if the lowmemorykiller is unloaded.

Rebased to -next by Paul E. McKenney.
Rebased to -next again by Anton Vorontsov.

Signed-off-by: Rabin Vincent <rabin.vincent@stericsson.com>
Signed-off-by: Christian Bejram <christian.bejram@stericsson.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-03-07 13:18:51 -08:00

224 lines
6.3 KiB
C

/* drivers/misc/lowmemorykiller.c
*
* The lowmemorykiller driver lets user-space specify a set of memory thresholds
* where processes with a range of oom_score_adj values will get killed. Specify
* the minimum oom_score_adj values in
* /sys/module/lowmemorykiller/parameters/adj and the number of free pages in
* /sys/module/lowmemorykiller/parameters/minfree. Both files take a comma
* separated list of numbers in ascending order.
*
* For example, write "0,8" to /sys/module/lowmemorykiller/parameters/adj and
* "1024,4096" to /sys/module/lowmemorykiller/parameters/minfree to kill
* processes with a oom_score_adj value of 8 or higher when the free memory
* drops below 4096 pages and kill processes with a oom_score_adj value of 0 or
* higher when the free memory drops below 1024 pages.
*
* The driver considers memory used for caches to be free, but if a large
* percentage of the cached memory is locked this can be very inaccurate
* and processes may not get killed until the normal oom killer is triggered.
*
* Copyright (C) 2007-2008 Google, Inc.
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/oom.h>
#include <linux/sched.h>
#include <linux/rcupdate.h>
#include <linux/profile.h>
#include <linux/notifier.h>
static uint32_t lowmem_debug_level = 2;
static int lowmem_adj[6] = {
0,
1,
6,
12,
};
static int lowmem_adj_size = 4;
static size_t lowmem_minfree[6] = {
3 * 512, /* 6MB */
2 * 1024, /* 8MB */
4 * 1024, /* 16MB */
16 * 1024, /* 64MB */
};
static int lowmem_minfree_size = 4;
static struct task_struct *lowmem_deathpending;
static unsigned long lowmem_deathpending_timeout;
#define lowmem_print(level, x...) \
do { \
if (lowmem_debug_level >= (level)) \
printk(x); \
} while (0)
static int
task_notify_func(struct notifier_block *self, unsigned long val, void *data);
static struct notifier_block task_nb = {
.notifier_call = task_notify_func,
};
static int
task_notify_func(struct notifier_block *self, unsigned long val, void *data)
{
struct task_struct *task = data;
if (task == lowmem_deathpending)
lowmem_deathpending = NULL;
return NOTIFY_OK;
}
static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
{
struct task_struct *tsk;
struct task_struct *selected = NULL;
int rem = 0;
int tasksize;
int i;
int min_score_adj = OOM_SCORE_ADJ_MAX + 1;
int selected_tasksize = 0;
int selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free = global_page_state(NR_FREE_PAGES);
int other_file = global_page_state(NR_FILE_PAGES) -
global_page_state(NR_SHMEM);
/*
* If we already have a death outstanding, then
* bail out right away; indicating to vmscan
* that we have nothing further to offer on
* this pass.
*
* Note: Currently you need CONFIG_PROFILING
* for this to work correctly.
*/
if (lowmem_deathpending &&
time_before_eq(jiffies, lowmem_deathpending_timeout))
return 0;
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
if (other_free < lowmem_minfree[i] &&
other_file < lowmem_minfree[i]) {
min_score_adj = lowmem_adj[i];
break;
}
}
if (sc->nr_to_scan > 0)
lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %d\n",
sc->nr_to_scan, sc->gfp_mask, other_free,
other_file, min_score_adj);
rem = global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_ANON) +
global_page_state(NR_INACTIVE_FILE);
if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
return rem;
}
selected_oom_score_adj = min_score_adj;
rcu_read_lock();
for_each_process(tsk) {
struct task_struct *p;
int oom_score_adj;
if (tsk->flags & PF_KTHREAD)
continue;
p = find_lock_task_mm(tsk);
if (!p)
continue;
oom_score_adj = p->signal->oom_score_adj;
if (oom_score_adj < min_score_adj) {
task_unlock(p);
continue;
}
tasksize = get_mm_rss(p->mm);
task_unlock(p);
if (tasksize <= 0)
continue;
if (selected) {
if (oom_score_adj < selected_oom_score_adj)
continue;
if (oom_score_adj == selected_oom_score_adj &&
tasksize <= selected_tasksize)
continue;
}
selected = p;
selected_tasksize = tasksize;
selected_oom_score_adj = oom_score_adj;
lowmem_print(2, "select %d (%s), adj %d, size %d, to kill\n",
p->pid, p->comm, oom_score_adj, tasksize);
}
if (selected) {
lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
selected->pid, selected->comm,
selected_oom_score_adj, selected_tasksize);
/*
* If CONFIG_PROFILING is off, then we don't want to stall
* the killer by setting lowmem_deathpending.
*/
#ifdef CONFIG_PROFILING
lowmem_deathpending = selected;
lowmem_deathpending_timeout = jiffies + HZ;
#endif
send_sig(SIGKILL, selected, 0);
rem -= selected_tasksize;
}
lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
return rem;
}
static struct shrinker lowmem_shrinker = {
.shrink = lowmem_shrink,
.seeks = DEFAULT_SEEKS * 16
};
static int __init lowmem_init(void)
{
task_handoff_register(&task_nb);
register_shrinker(&lowmem_shrinker);
return 0;
}
static void __exit lowmem_exit(void)
{
unregister_shrinker(&lowmem_shrinker);
task_handoff_unregister(&task_nb);
}
module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
module_param_array_named(adj, lowmem_adj, int, &lowmem_adj_size,
S_IRUGO | S_IWUSR);
module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
S_IRUGO | S_IWUSR);
module_param_named(debug_level, lowmem_debug_level, uint, S_IRUGO | S_IWUSR);
module_init(lowmem_init);
module_exit(lowmem_exit);
MODULE_LICENSE("GPL");