linux_dsm_epyc7002/kernel/power/process.c
Rafael J. Wysocki 7f33d49a2e mm, PM/Freezer: Disable OOM killer when tasks are frozen
Currently, the following scenario appears to be possible in theory:

* Tasks are frozen for hibernation or suspend.
* Free pages are almost exhausted.
* Certain piece of code in the suspend code path attempts to allocate
  some memory using GFP_KERNEL and allocation order less than or
  equal to PAGE_ALLOC_COSTLY_ORDER.
* __alloc_pages_internal() cannot find a free page so it invokes the
  OOM killer.
* The OOM killer attempts to kill a task, but the task is frozen, so
  it doesn't die immediately.
* __alloc_pages_internal() jumps to 'restart', unsuccessfully tries
  to find a free page and invokes the OOM killer.
* No progress can be made.

Although it is now hard to trigger during hibernation due to the memory
shrinking carried out by the hibernation code, it is theoretically
possible to trigger during suspend after the memory shrinking has been
removed from that code path.  Moreover, since memory allocations are
going to be used for the hibernation memory shrinking, it will be even
more likely to happen during hibernation.

To prevent it from happening, introduce the oom_killer_disabled switch
that will cause __alloc_pages_internal() to fail in the situations in
which the OOM killer would have been called and make the freezer set
this switch after tasks have been successfully frozen.

[akpm@linux-foundation.org: be nicer to the namespace]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Fengguang Wu <fengguang.wu@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 19:47:40 -07:00

160 lines
3.3 KiB
C

/*
* drivers/power/process.c - Functions for starting/stopping processes on
* suspend transitions.
*
* Originally from swsusp.
*/
#undef DEBUG
#include <linux/interrupt.h>
#include <linux/suspend.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/freezer.h>
/*
* Timeout for stopping processes
*/
#define TIMEOUT (20 * HZ)
static inline int freezeable(struct task_struct * p)
{
if ((p == current) ||
(p->flags & PF_NOFREEZE) ||
(p->exit_state != 0))
return 0;
return 1;
}
static int try_to_freeze_tasks(bool sig_only)
{
struct task_struct *g, *p;
unsigned long end_time;
unsigned int todo;
struct timeval start, end;
u64 elapsed_csecs64;
unsigned int elapsed_csecs;
do_gettimeofday(&start);
end_time = jiffies + TIMEOUT;
do {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (frozen(p) || !freezeable(p))
continue;
if (!freeze_task(p, sig_only))
continue;
/*
* Now that we've done set_freeze_flag, don't
* perturb a task in TASK_STOPPED or TASK_TRACED.
* It is "frozen enough". If the task does wake
* up, it will immediately call try_to_freeze.
*/
if (!task_is_stopped_or_traced(p) &&
!freezer_should_skip(p))
todo++;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
yield(); /* Yield is okay here */
if (time_after(jiffies, end_time))
break;
} while (todo);
do_gettimeofday(&end);
elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
do_div(elapsed_csecs64, NSEC_PER_SEC / 100);
elapsed_csecs = elapsed_csecs64;
if (todo) {
/* This does not unfreeze processes that are already frozen
* (we have slightly ugly calling convention in that respect,
* and caller must call thaw_processes() if something fails),
* but it cleans up leftover PF_FREEZE requests.
*/
printk("\n");
printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
"(%d tasks refusing to freeze):\n",
elapsed_csecs / 100, elapsed_csecs % 100, todo);
show_state();
read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
if (freezing(p) && !freezer_should_skip(p))
printk(KERN_ERR " %s\n", p->comm);
cancel_freezing(p);
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
} else {
printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100,
elapsed_csecs % 100);
}
return todo ? -EBUSY : 0;
}
/**
* freeze_processes - tell processes to enter the refrigerator
*/
int freeze_processes(void)
{
int error;
printk("Freezing user space processes ... ");
error = try_to_freeze_tasks(true);
if (error)
goto Exit;
printk("done.\n");
printk("Freezing remaining freezable tasks ... ");
error = try_to_freeze_tasks(false);
if (error)
goto Exit;
printk("done.");
oom_killer_disable();
Exit:
BUG_ON(in_atomic());
printk("\n");
return error;
}
static void thaw_tasks(bool nosig_only)
{
struct task_struct *g, *p;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (!freezeable(p))
continue;
if (nosig_only && should_send_signal(p))
continue;
if (cgroup_frozen(p))
continue;
thaw_process(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
}
void thaw_processes(void)
{
oom_killer_enable();
printk("Restarting tasks ... ");
thaw_tasks(true);
thaw_tasks(false);
schedule();
printk("done.\n");
}