sched: fix nr_uninterruptible accounting of frozen tasks really

commit e3c8ca8336 (sched: do not count frozen tasks toward load) broke
the nr_uninterruptible accounting on freeze/thaw. On freeze the task
is excluded from accounting with a check for (task->flags &
PF_FROZEN), but that flag is cleared before the task is thawed. So
while we prevent that the task with state TASK_UNINTERRUPTIBLE
is accounted to nr_uninterruptible on freeze we decrement
nr_uninterruptible on thaw.

Use a separate flag which is handled by the freezing task itself. Set
it before calling the scheduler with TASK_UNINTERRUPTIBLE state and
clear it after we return from frozen state.

Cc: <stable@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 16a982e389fb289560d13039bfb608fd82bbdae2..3ab08e4bb6b87c608d8e58b3f37e4260c18c1f4e 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -209,7 +209,7 @@ extern unsigned long long time_sync_thresh;
                        ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task) \
                                ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-                                (task->flags & PF_FROZEN) == 0)
+                                (task->flags & PF_FREEZING) == 0)
 
 #define __set_task_state(tsk, state_value)             \
        do { (tsk)->state = (state_value); } while (0)
@@ -1680,6 +1680,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_MEMALLOC    0x00000800      /* Allocating memory */
 #define PF_FLUSHER     0x00001000      /* responsible for disk writeback */
 #define PF_USED_MATH   0x00002000      /* if unset the fpu must be initialized before use */
+#define PF_FREEZING    0x00004000      /* freeze in progress. do not account to load */
 #define PF_NOFREEZE    0x00008000      /* this thread should not be frozen */
 #define PF_FROZEN      0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS     0x00020000      /* inside a filesystem transaction */

diff --git a/kernel/freezer.c b/kernel/freezer.c
index 2f4936cf708367c90f3d16fe5a4d9b49ec66e90e..bd1d42b17cb2f52f5156506ba25d75376102af7f 100644 (file)
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -44,12 +44,19 @@ void refrigerator(void)
        recalc_sigpending(); /* We sent fake signal, clean it up */
        spin_unlock_irq(&current->sighand->siglock);
 
+       /* prevent accounting of that task to load */
+       current->flags |= PF_FREEZING;
+
        for (;;) {
                set_current_state(TASK_UNINTERRUPTIBLE);
                if (!frozen(current))
                        break;
                schedule();
        }
+
+       /* Remove the accounting blocker */
+       current->flags &= ~PF_FREEZING;
+
        pr_debug("%s left refrigerator\n", current->comm);
        __set_current_state(save);
 }