linux_dsm_epyc7002/kernel/power/process.c

166 lines
3.4 KiB
C
Raw Normal View History

/*
* 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>
/*
* 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;
while (true) {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
Freezer: avoid freezing kernel threads prematurely Kernel threads should not have TIF_FREEZE set when user space processes are being frozen, since otherwise some of them might be frozen prematurely. To prevent this from happening we can (1) make exit_mm() unset TIF_FREEZE unconditionally just after clearing tsk->mm and (2) make try_to_freeze_tasks() check if p->mm is different from zero and PF_BORROWED_MM is unset in p->flags when user space processes are to be frozen. Namely, when user space processes are being frozen, we only should set TIF_FREEZE for tasks that have p->mm different from NULL and don't have PF_BORROWED_MM set in p->flags. For this reason task_lock() must be used to prevent try_to_freeze_tasks() from racing with use_mm()/unuse_mm(), in which p->mm and p->flags.PF_BORROWED_MM are changed under task_lock(p). Also, we need to prevent the following scenario from happening: * daemonize() is called by a task spawned from a user space code path * freezer checks if the task has p->mm set and the result is positive * task enters exit_mm() and clears its TIF_FREEZE * freezer sets TIF_FREEZE for the task * task calls try_to_freeze() and goes to the refrigerator, which is wrong at that point This requires us to acquire task_lock(p) before p->flags.PF_BORROWED_MM and p->mm are examined and release it after TIF_FREEZE is set for p (or it turns out that TIF_FREEZE should not be set). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Gautham R Shenoy <ego@in.ibm.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:33 +07:00
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);
if (!todo || time_after(jiffies, end_time))
break;
/*
* We need to retry, but first give the freezing tasks some
* time to enter the regrigerator.
*/
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) {
/* 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);
read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
Freezer: avoid freezing kernel threads prematurely Kernel threads should not have TIF_FREEZE set when user space processes are being frozen, since otherwise some of them might be frozen prematurely. To prevent this from happening we can (1) make exit_mm() unset TIF_FREEZE unconditionally just after clearing tsk->mm and (2) make try_to_freeze_tasks() check if p->mm is different from zero and PF_BORROWED_MM is unset in p->flags when user space processes are to be frozen. Namely, when user space processes are being frozen, we only should set TIF_FREEZE for tasks that have p->mm different from NULL and don't have PF_BORROWED_MM set in p->flags. For this reason task_lock() must be used to prevent try_to_freeze_tasks() from racing with use_mm()/unuse_mm(), in which p->mm and p->flags.PF_BORROWED_MM are changed under task_lock(p). Also, we need to prevent the following scenario from happening: * daemonize() is called by a task spawned from a user space code path * freezer checks if the task has p->mm set and the result is positive * task enters exit_mm() and clears its TIF_FREEZE * freezer sets TIF_FREEZE for the task * task calls try_to_freeze() and goes to the refrigerator, which is wrong at that point This requires us to acquire task_lock(p) before p->flags.PF_BORROWED_MM and p->mm are examined and release it after TIF_FREEZE is set for p (or it turns out that TIF_FREEZE should not be set). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Gautham R Shenoy <ego@in.ibm.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@nigel.suspend2.net> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:47:33 +07:00
if (freezing(p) && !freezer_should_skip(p))
sched_show_task(p);
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.");
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>
2009-06-17 05:32:41 +07:00
oom_killer_disable();
Exit:
BUG_ON(in_atomic());
printk("\n");
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>
2009-06-17 05:32:41 +07:00
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;
Freezer: Fix buggy resume test for tasks frozen with cgroup freezer When the cgroup freezer is used to freeze tasks we do not want to thaw those tasks during resume. Currently we test the cgroup freezer state of the resuming tasks to see if the cgroup is FROZEN. If so then we don't thaw the task. However, the FREEZING state also indicates that the task should remain frozen. This also avoids a problem pointed out by Oren Ladaan: the freezer state transition from FREEZING to FROZEN is updated lazily when userspace reads or writes the freezer.state file in the cgroup filesystem. This means that resume will thaw tasks in cgroups which should be in the FROZEN state if there is no read/write of the freezer.state file to trigger this transition before suspend. NOTE: Another "simple" solution would be to always update the cgroup freezer state during resume. However it's a bad choice for several reasons: Updating the cgroup freezer state is somewhat expensive because it requires walking all the tasks in the cgroup and checking if they are each frozen. Worse, this could easily make resume run in N^2 time where N is the number of tasks in the cgroup. Finally, updating the freezer state from this code path requires trickier locking because of the way locks must be ordered. Instead of updating the freezer state we rely on the fact that lazy updates only manage the transition from FREEZING to FROZEN. We know that a cgroup with the FREEZING state may actually be FROZEN so test for that state too. This makes sense in the resume path even for partially-frozen cgroups -- those that really are FREEZING but not FROZEN. Reported-by: Oren Ladaan <orenl@cs.columbia.edu> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Cc: stable@kernel.org Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
2010-03-27 05:51:44 +07:00
if (cgroup_freezing_or_frozen(p))
continue;
thaw_process(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
}
void thaw_processes(void)
{
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>
2009-06-17 05:32:41 +07:00
oom_killer_enable();
printk("Restarting tasks ... ");
thaw_tasks(true);
thaw_tasks(false);
schedule();
printk("done.\n");
}