linux_dsm_epyc7002/kernel/power/process.c

225 lines
5.0 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>
#include <linux/workqueue.h>
#include <linux/kmod.h>
/*
* Timeout for stopping processes
*/
unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC;
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_msecs64;
unsigned int elapsed_msecs;
bool wakeup = false;
int sleep_usecs = USEC_PER_MSEC;
do_gettimeofday(&start);
end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs);
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. Start with an initial
* 1 ms sleep followed by exponential backoff until 8 ms.
*/
usleep_range(sleep_usecs / 2, sleep_usecs);
if (sleep_usecs < 8 * USEC_PER_MSEC)
sleep_usecs *= 2;
}
do_gettimeofday(&end);
elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
do_div(elapsed_msecs64, NSEC_PER_MSEC);
elapsed_msecs = elapsed_msecs64;
if (todo) {
printk("\n");
printk(KERN_ERR "Freezing of tasks %s after %d.%03d seconds "
"(%d tasks refusing to freeze, wq_busy=%d):\n",
wakeup ? "aborted" : "failed",
elapsed_msecs / 1000, elapsed_msecs % 1000,
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.%03d seconds) ", elapsed_msecs / 1000,
elapsed_msecs % 1000);
}
return todo ? -EBUSY : 0;
}
/**
* freeze_processes - Signal user space processes to enter the refrigerator.
* The current thread will not be frozen. The same process that calls
* freeze_processes must later call thaw_processes.
*
* On success, returns 0. On failure, -errno and system is fully thawed.
*/
int freeze_processes(void)
{
int error;
PM / Sleep: Mitigate race between the freezer and request_firmware() There is a race condition between the freezer and request_firmware() such that if request_firmware() is run on one CPU and freeze_processes() is run on another CPU and usermodehelper_disable() called by it succeeds to grab umhelper_sem for writing before usermodehelper_read_trylock() called from request_firmware() acquires it for reading, the request_firmware() will fail and trigger a WARN_ON() complaining that it was called at a wrong time. However, in fact, it wasn't called at a wrong time and freeze_processes() simply happened to be executed simultaneously. To avoid this race, at least in some cases, modify usermodehelper_read_trylock() so that it doesn't fail if the freezing of tasks has just started and hasn't been completed yet. Instead, during the freezing of tasks, it will try to freeze the task that has called it so that it can wait until user space is thawed without triggering the scary warning. For this purpose, change usermodehelper_disabled so that it can take three different values, UMH_ENABLED (0), UMH_FREEZING and UMH_DISABLED. The first one means that usermode helpers are enabled, the last one means "hard disable" (i.e. the system is not ready for usermode helpers to be used) and the second one is reserved for the freezer. Namely, when freeze_processes() is started, it sets usermodehelper_disabled to UMH_FREEZING which tells usermodehelper_read_trylock() that it shouldn't fail just yet and should call try_to_freeze() if woken up and cannot return immediately. This way all freezable tasks that happen to call request_firmware() right before freeze_processes() is started and lose the race for umhelper_sem with it will be frozen and will sleep until thaw_processes() unsets usermodehelper_disabled. [For the non-freezable callers of request_firmware() the race for umhelper_sem against freeze_processes() is unfortunately unavoidable.] Reported-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@vger.kernel.org
2012-03-29 04:30:28 +07:00
error = __usermodehelper_disable(UMH_FREEZING);
if (error)
return error;
/* Make sure this task doesn't get frozen */
current->flags |= PF_SUSPEND_TASK;
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
if (!pm_freezing)
atomic_inc(&system_freezing_cnt);
printk("Freezing user space processes ... ");
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
pm_freezing = true;
error = try_to_freeze_tasks(true);
if (!error) {
printk("done.");
PM / Sleep: Mitigate race between the freezer and request_firmware() There is a race condition between the freezer and request_firmware() such that if request_firmware() is run on one CPU and freeze_processes() is run on another CPU and usermodehelper_disable() called by it succeeds to grab umhelper_sem for writing before usermodehelper_read_trylock() called from request_firmware() acquires it for reading, the request_firmware() will fail and trigger a WARN_ON() complaining that it was called at a wrong time. However, in fact, it wasn't called at a wrong time and freeze_processes() simply happened to be executed simultaneously. To avoid this race, at least in some cases, modify usermodehelper_read_trylock() so that it doesn't fail if the freezing of tasks has just started and hasn't been completed yet. Instead, during the freezing of tasks, it will try to freeze the task that has called it so that it can wait until user space is thawed without triggering the scary warning. For this purpose, change usermodehelper_disabled so that it can take three different values, UMH_ENABLED (0), UMH_FREEZING and UMH_DISABLED. The first one means that usermode helpers are enabled, the last one means "hard disable" (i.e. the system is not ready for usermode helpers to be used) and the second one is reserved for the freezer. Namely, when freeze_processes() is started, it sets usermodehelper_disabled to UMH_FREEZING which tells usermodehelper_read_trylock() that it shouldn't fail just yet and should call try_to_freeze() if woken up and cannot return immediately. This way all freezable tasks that happen to call request_firmware() right before freeze_processes() is started and lose the race for umhelper_sem with it will be frozen and will sleep until thaw_processes() unsets usermodehelper_disabled. [For the non-freezable callers of request_firmware() the race for umhelper_sem against freeze_processes() is unfortunately unavoidable.] Reported-by: Stephen Boyd <sboyd@codeaurora.org> Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@vger.kernel.org
2012-03-29 04:30:28 +07:00
__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 ... ");
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
pm_nosig_freezing = true;
error = try_to_freeze_tasks(false);
if (!error)
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
printk("\n");
BUG_ON(in_atomic());
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
if (error)
thaw_kernel_threads();
return error;
}
void thaw_processes(void)
{
struct task_struct *g, *p;
struct task_struct *curr = current;
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
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) {
/* No other threads should have PF_SUSPEND_TASK set */
WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK));
__thaw_task(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
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
WARN_ON(!(curr->flags & PF_SUSPEND_TASK));
curr->flags &= ~PF_SUSPEND_TASK;
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");
}