linux_dsm_epyc7002/kernel/power/process.c
Oleg Nesterov 5d8f72b55c freezer: change ptrace_stop/do_signal_stop to use freezable_schedule()
try_to_freeze_tasks() and cgroup_freezer rely on scheduler locks
to ensure that a task doing STOPPED/TRACED -> RUNNING transition
can't escape freezing. This mostly works, but ptrace_stop() does
not necessarily call schedule(), it can change task->state back to
RUNNING and check freezing() without any lock/barrier in between.

We could add the necessary barrier, but this patch changes
ptrace_stop() and do_signal_stop() to use freezable_schedule().
This fixes the race, freezer_count() and freezer_should_skip()
carefully avoid the race.

And this simplifies the code, try_to_freeze_tasks/update_if_frozen
no longer need to use task_is_stopped_or_traced() checks with the
non trivial assumptions. We can rely on the mechanism which was
specially designed to mark the sleeping task as "frozen enough".

v2: As Tejun pointed out, we can also change get_signal_to_deliver()
and move try_to_freeze() up before 'relock' label.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2012-10-26 14:27:49 -07:00

210 lines
4.3 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/oom.h>
#include <linux/suspend.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/freezer.h>
#include <linux/delay.h>
#include <linux/workqueue.h>
#include <linux/kmod.h>
/*
* Timeout for stopping processes
*/
#define TIMEOUT (20 * HZ)
static int try_to_freeze_tasks(bool user_only)
{
struct task_struct *g, *p;
unsigned long end_time;
unsigned int todo;
bool wq_busy = false;
struct timeval start, end;
u64 elapsed_csecs64;
unsigned int elapsed_csecs;
bool wakeup = false;
do_gettimeofday(&start);
end_time = jiffies + TIMEOUT;
if (!user_only)
freeze_workqueues_begin();
while (true) {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (p == current || !freeze_task(p))
continue;
if (!freezer_should_skip(p))
todo++;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
if (!user_only) {
wq_busy = freeze_workqueues_busy();
todo += wq_busy;
}
if (!todo || time_after(jiffies, end_time))
break;
if (pm_wakeup_pending()) {
wakeup = true;
break;
}
/*
* We need to retry, but first give the freezing tasks some
* time to enter the refrigerator.
*/
msleep(10);
}
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) {
printk("\n");
printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds "
"(%d tasks refusing to freeze, wq_busy=%d):\n",
wakeup ? "aborted" : "failed",
elapsed_csecs / 100, elapsed_csecs % 100,
todo - wq_busy, wq_busy);
if (!wakeup) {
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (p != current && !freezer_should_skip(p)
&& freezing(p) && !frozen(p))
sched_show_task(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 - Signal user space processes to enter the refrigerator.
*
* On success, returns 0. On failure, -errno and system is fully thawed.
*/
int freeze_processes(void)
{
int error;
error = __usermodehelper_disable(UMH_FREEZING);
if (error)
return error;
if (!pm_freezing)
atomic_inc(&system_freezing_cnt);
printk("Freezing user space processes ... ");
pm_freezing = true;
error = try_to_freeze_tasks(true);
if (!error) {
printk("done.");
__usermodehelper_set_disable_depth(UMH_DISABLED);
oom_killer_disable();
}
printk("\n");
BUG_ON(in_atomic());
if (error)
thaw_processes();
return error;
}
/**
* freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
*
* On success, returns 0. On failure, -errno and only the kernel threads are
* thawed, so as to give a chance to the caller to do additional cleanups
* (if any) before thawing the userspace tasks. So, it is the responsibility
* of the caller to thaw the userspace tasks, when the time is right.
*/
int freeze_kernel_threads(void)
{
int error;
printk("Freezing remaining freezable tasks ... ");
pm_nosig_freezing = true;
error = try_to_freeze_tasks(false);
if (!error)
printk("done.");
printk("\n");
BUG_ON(in_atomic());
if (error)
thaw_kernel_threads();
return error;
}
void thaw_processes(void)
{
struct task_struct *g, *p;
if (pm_freezing)
atomic_dec(&system_freezing_cnt);
pm_freezing = false;
pm_nosig_freezing = false;
oom_killer_enable();
printk("Restarting tasks ... ");
thaw_workqueues();
read_lock(&tasklist_lock);
do_each_thread(g, p) {
__thaw_task(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
usermodehelper_enable();
schedule();
printk("done.\n");
}
void thaw_kernel_threads(void)
{
struct task_struct *g, *p;
pm_nosig_freezing = false;
printk("Restarting kernel threads ... ");
thaw_workqueues();
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (p->flags & (PF_KTHREAD | PF_WQ_WORKER))
__thaw_task(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
schedule();
printk("done.\n");
}