[GIT PULL] scheduler fixes

[GIT PULL] scheduler fixes

[Ingo Molnar]

Linus,

Please pull the latest sched-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus

 Thanks,

	Ingo

------------------>
Mike Galbraith (1):
      sched: Use LAST_BUDDY only to minimize negative wakeup preemption effects

Peter Zijlstra (2):
      sched: Disable SD_PREFER_LOCAL for MC/CPU domains
      sched: Do less agressive buddy clearing


 arch/x86/include/asm/topology.h |    1 +
 include/linux/topology.h        |    4 +-
 kernel/sched.c                  |    2 +-
 kernel/sched_fair.c             |   46 ++++++++++++++++++--------------------
 4 files changed, 26 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 25a9284..d823c24 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ extern unsigned long node_remap_size[];
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
+				| 1*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_POWERSAVINGS_BALANCE		\
 				| 0*SD_SHARE_PKG_RESOURCES		\
diff --git a/include/linux/topology.h b/include/linux/topology.h
index fc0bf3e..57e6357 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -129,7 +129,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
-				| 1*SD_PREFER_LOCAL			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 1*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
@@ -162,7 +162,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
-				| 1*SD_PREFER_LOCAL			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
diff --git a/kernel/sched.c b/kernel/sched.c
index 789001d..cae6700 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2008,7 +2008,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) &&
+	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
 			(&p->se == cfs_rq_of(&p->se)->next ||
 			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4e777b4..dfcf0c9 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -863,10 +863,15 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	struct sched_entity *se = __pick_next_entity(cfs_rq);
 
 	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
-		return cfs_rq->next;
+		se = cfs_rq->next;
 
+	/*
+	 * Prefer last buddy, try to return the CPU to a preempted task.
+	 */
 	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
-		return cfs_rq->last;
+		se = cfs_rq->last;
+
+	clear_buddies(cfs_rq, se);
 
 	return se;
 }
@@ -1582,17 +1587,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(se == pse))
 		return;
 
-	/*
-	 * Only set the backward buddy when the current task is still on the
-	 * rq. This can happen when a wakeup gets interleaved with schedule on
-	 * the ->pre_schedule() or idle_balance() point, either of which can
-	 * drop the rq lock.
-	 *
-	 * Also, during early boot the idle thread is in the fair class, for
-	 * obvious reasons its a bad idea to schedule back to the idle thread.
-	 */
-	if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-		set_last_buddy(se);
 	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
 		set_next_buddy(pse);
 
@@ -1639,8 +1633,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
 	BUG_ON(!pse);
 
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
 		resched_task(curr);
+		/*
+		 * Only set the backward buddy when the current task is still
+		 * on the rq. This can happen when a wakeup gets interleaved
+		 * with schedule on the ->pre_schedule() or idle_balance()
+		 * point, either of which can * drop the rq lock.
+		 *
+		 * Also, during early boot the idle thread is in the fair class,
+		 * for obvious reasons its a bad idea to schedule back to it.
+		 */
+		if (unlikely(!se->on_rq || curr == rq->idle))
+			return;
+		if (sched_feat(LAST_BUDDY))
+			set_last_buddy(se);
+	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1654,16 +1662,6 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
-		/*
-		 * If se was a buddy, clear it so that it will have to earn
-		 * the favour again.
-		 *
-		 * If se was not a buddy, clear the buddies because neither
-		 * was elegible to run, let them earn it again.
-		 *
-		 * IOW. unconditionally clear buddies.
-		 */
-		__clear_buddies(cfs_rq, NULL);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);

[GIT PULL, v2] scheduler fixes

[Ingo Molnar]

* Ingo Molnar <mingo@elte.hu> wrote:

> Linus,
> 
> Please pull the latest sched-fixes-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus

Sorry - the tail commit was bad and i forgot to exclude it. Updated pull 
request (with different URI):

Please pull the latest sched-fixes-for-linus-2 git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus-2

 Thanks,

	Ingo

------------------>
Peter Zijlstra (2):
      sched: Disable SD_PREFER_LOCAL for MC/CPU domains
      sched: Do less agressive buddy clearing


 arch/x86/include/asm/topology.h |    1 +
 include/linux/topology.h        |    4 ++--
 kernel/sched_fair.c             |   27 +++++++++++++--------------
 3 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 25a9284..d823c24 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ extern unsigned long node_remap_size[];
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
+				| 1*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_POWERSAVINGS_BALANCE		\
 				| 0*SD_SHARE_PKG_RESOURCES		\
diff --git a/include/linux/topology.h b/include/linux/topology.h
index fc0bf3e..57e6357 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -129,7 +129,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
-				| 1*SD_PREFER_LOCAL			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 1*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
@@ -162,7 +162,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
-				| 1*SD_PREFER_LOCAL			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4e777b4..c32c3e6 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -861,12 +861,21 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *buddy;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
-		return cfs_rq->next;
+	if (cfs_rq->next) {
+		buddy = cfs_rq->next;
+		cfs_rq->next = NULL;
+		if (wakeup_preempt_entity(buddy, se) < 1)
+			return buddy;
+	}
 
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
-		return cfs_rq->last;
+	if (cfs_rq->last) {
+		buddy = cfs_rq->last;
+		cfs_rq->last = NULL;
+		if (wakeup_preempt_entity(buddy, se) < 1)
+			return buddy;
+	}
 
 	return se;
 }
@@ -1654,16 +1663,6 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
-		/*
-		 * If se was a buddy, clear it so that it will have to earn
-		 * the favour again.
-		 *
-		 * If se was not a buddy, clear the buddies because neither
-		 * was elegible to run, let them earn it again.
-		 *
-		 * IOW. unconditionally clear buddies.
-		 */
-		__clear_buddies(cfs_rq, NULL);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);

Re: [GIT PULL v2] scheduler fixes

[pr-tracker-bot]

The pull request you sent on Sun, 17 Nov 2019 11:41:12 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/cbb104f91dfec8ae5bc67ff6dc67b824330a0919

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL v2] scheduler fixes

[Ingo Molnar]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Sat, Nov 16, 2019 at 2:44 PM Valentin Schneider
> <valentin.schneider@arm.com> wrote:
> >
> > > Valentin Schneider (2):
> > >       sched/uclamp: Fix overzealous type replacement
> >
> > This one got a v2 (was missing one location), acked by Vincent:
> >
> >   20191115103908.27610-1-valentin.schneider@arm.com
> >
> > >       sched/topology, cpuset: Account for housekeeping CPUs to avoid empty cpumasks
> >
> > And this one is no longer needed, as Michal & I understood (IOW the fix in
> > rc6 is sufficient), see:
> >
> >   c425c5cb-ba8a-e5f6-d91c-5479779cfb7a@arm.com
> 
> Ingo, what do you want me to do? Pull it anyway and send updates
> later? Or skip this pull request?
> 
> I'll leave it pending for now,

We ended up zapping the final two commits from sched/urgent.

Please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

   # HEAD: 6e1ff0773f49c7d38e8b4a9df598def6afb9f415 sched/uclamp: Fix incorrect condition

Misc fixes:

 - Fix potential deadlock under CONFIG_DEBUG_OBJECTS=y
 - PELT metrics update ordering fix
 - uclamp logic fix

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      sched/core: Avoid spurious lock dependencies

Qais Yousef (1):
      sched/uclamp: Fix incorrect condition

Vincent Guittot (1):
      sched/pelt: Fix update of blocked PELT ordering


 kernel/sched/core.c |  5 +++--
 kernel/sched/fair.c | 29 ++++++++++++++++++++---------
 2 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0f2eb3629070..44123b4d14e8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1065,7 +1065,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
-	if (!p->uclamp[clamp_id].active) {
+	if (p->uclamp[clamp_id].active) {
 		uclamp_rq_dec_id(rq, p, clamp_id);
 		uclamp_rq_inc_id(rq, p, clamp_id);
 	}
@@ -6019,10 +6019,11 @@ void init_idle(struct task_struct *idle, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
+	__sched_fork(0, idle);
+
 	raw_spin_lock_irqsave(&idle->pi_lock, flags);
 	raw_spin_lock(&rq->lock);
 
-	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 	idle->flags |= PF_IDLE;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 22a2fed29054..69a81a5709ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7547,6 +7547,19 @@ static void update_blocked_averages(int cpu)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
+	/*
+	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+	 * that RT, DL and IRQ signals have been updated before updating CFS.
+	 */
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
+	update_irq_load_avg(rq, 0);
+
+	/* Don't need periodic decay once load/util_avg are null */
+	if (others_have_blocked(rq))
+		done = false;
+
 	/*
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
@@ -7574,14 +7587,6 @@ static void update_blocked_averages(int cpu)
 			done = false;
 	}
 
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
-	/* Don't need periodic decay once load/util_avg are null */
-	if (others_have_blocked(rq))
-		done = false;
-
 	update_blocked_load_status(rq, !done);
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -7642,12 +7647,18 @@ static inline void update_blocked_averages(int cpu)
 
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
-	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
 
+	/*
+	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+	 * that RT, DL and IRQ signals have been updated before updating CFS.
+	 */
 	curr_class = rq->curr->sched_class;
 	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
 	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
+
+	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+
 	update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
 	rq_unlock_irqrestore(rq, &rf);
 }

[GIT PULL, v2] scheduler fixes

[Ingo Molnar]

Linus,

Please pull the latest sched-urgent-for-linus git tree from:

   git://tesla.tglx.de/git/linux-2.6-tip.git sched-urgent-for-linus

[ Note, the diffstat is different from the v1 version, a new fix was 
  added.]

 Thanks,

	Ingo

------------------>
Peter Zijlstra (1):
      posix-cpu-timers: Cure SMP wobbles

Shawn Bohrer (1):
      sched/rt: Migrate equal priority tasks to available CPUs

Simon Kirby (1):
      sched: Fix up wchan borkage


 include/linux/sched.h     |    1 -
 kernel/posix-cpu-timers.c |    5 +++--
 kernel/sched.c            |   26 +-------------------------
 kernel/sched_rt.c         |    4 ++--
 4 files changed, 6 insertions(+), 30 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4ac2c05..41d0237 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1956,7 +1956,6 @@ static inline void disable_sched_clock_irqtime(void) {}
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
-extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 58f405b..c8008dd 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -250,7 +250,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	do {
 		times->utime = cputime_add(times->utime, t->utime);
 		times->stime = cputime_add(times->stime, t->stime);
-		times->sum_exec_runtime += t->se.sum_exec_runtime;
+		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
@@ -312,7 +312,8 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		thread_group_cputime(p, &cputime);
+		cpu->sched = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index ec5f472..b50b0f0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3725,30 +3725,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 }
 
 /*
- * Return sum_exec_runtime for the thread group.
- * In case the task is currently running, return the sum plus current's
- * pending runtime that have not been accounted yet.
- *
- * Note that the thread group might have other running tasks as well,
- * so the return value not includes other pending runtime that other
- * running tasks might have.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	struct task_cputime totals;
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
-/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
@@ -4372,7 +4348,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 97540f0..af11778 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1050,7 +1050,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
 	    (curr->rt.nr_cpus_allowed < 2 ||
-	     curr->prio < p->prio) &&
+	     curr->prio <= p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
@@ -1581,7 +1581,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    p->rt.nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
 	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio))
+	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
 

[GIT PULL, v2] scheduler fixes

[Ingo Molnar]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Sun, Dec 19, 2010 at 7:27 AM, Ingo Molnar <mingo@elte.hu> wrote:
> > @@ -3943,6 +4128,7 @@ need_resched_nonpreemptible:
> >                rq->nr_switches++;
> >                rq->curr = next;
> >                ++*switch_count;
> > +               WARN_ON_ONCE(test_tsk_need_resched(next));
> >
> >                context_switch(rq, prev, next); /* unlocks the rq */
> >                /*
> > diff --git a/kernel/timer.c b/kern
> 
> Please don't add like this in an -rc. It looks like it's some
> debugging aid, I don't think it should have gone in now.

Yeah - sorry about that. The warning is bogus - please pull the updated tree below. 
(Can also be pulled on top of the previous one.)

Thanks,

	Ingo

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus

------------------>
Heiko Carstens (1):
      nohz: Fix get_next_timer_interrupt() vs cpu hotplug

Ingo Molnar (1):
      sched: Remove debugging check

Mike Galbraith (1):
      Sched: fix skip_clock_update optimization

Peter Zijlstra (3):
      sched: Cure more NO_HZ load average woes
      sched: Fix the irqtime code to deal with u64 wraps
      sched: Fix the irqtime code for 32bit


 include/linux/sched.h |    2 +-
 kernel/fork.c         |    1 +
 kernel/sched.c        |  287 ++++++++++++++++++++++++++++++++++++++++---------
 kernel/timer.c        |    8 ++-
 4 files changed, 245 insertions(+), 53 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c79e92..2238745 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern unsigned long this_cpu_load(void);
 
 
-extern void calc_global_load(void);
+extern void calc_global_load(unsigned long ticks);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b159c5..5447dc7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -273,6 +273,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
+	clear_tsk_need_resched(tsk);
 	stackend = end_of_stack(tsk);
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
diff --git a/kernel/sched.c b/kernel/sched.c
index dc91a4d..297d1a0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -636,22 +636,18 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
 
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
 {
-	if (!rq->skip_clock_update) {
-		int cpu = cpu_of(rq);
-		u64 irq_time;
+	s64 delta;
 
-		rq->clock = sched_clock_cpu(cpu);
-		irq_time = irq_time_cpu(cpu);
-		if (rq->clock - irq_time > rq->clock_task)
-			rq->clock_task = rq->clock - irq_time;
+	if (rq->skip_clock_update)
+		return;
 
-		sched_irq_time_avg_update(rq, irq_time);
-	}
+	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
 }
 
 /*
@@ -1924,10 +1920,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
  * They are read and saved off onto struct rq in update_rq_clock().
  * This may result in other CPU reading this CPU's irq time and can
  * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
  */
 static DEFINE_PER_CPU(u64, cpu_hardirq_time);
 static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1945,19 +1940,58 @@ void disable_sched_clock_irqtime(void)
 	sched_clock_irqtime = 0;
 }
 
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
 {
-	if (!sched_clock_irqtime)
-		return 0;
+	__this_cpu_inc(irq_time_seq.sequence);
+	smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+	smp_wmb();
+	__this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	u64 irq_time;
+	unsigned seq;
 
+	do {
+		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+		irq_time = per_cpu(cpu_softirq_time, cpu) +
+			   per_cpu(cpu_hardirq_time, cpu);
+	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+	return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
 	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
 }
+#endif /* CONFIG_64BIT */
 
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
 void account_system_vtime(struct task_struct *curr)
 {
 	unsigned long flags;
+	s64 delta;
 	int cpu;
-	u64 now, delta;
 
 	if (!sched_clock_irqtime)
 		return;
@@ -1965,9 +1999,10 @@ void account_system_vtime(struct task_struct *curr)
 	local_irq_save(flags);
 
 	cpu = smp_processor_id();
-	now = sched_clock_cpu(cpu);
-	delta = now - per_cpu(irq_start_time, cpu);
-	per_cpu(irq_start_time, cpu) = now;
+	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+	__this_cpu_add(irq_start_time, delta);
+
+	irq_time_write_begin();
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
 	 * We want to continue accounting softirq time to ksoftirqd thread
@@ -1975,33 +2010,55 @@ void account_system_vtime(struct task_struct *curr)
 	 * that do not consume any time, but still wants to run.
 	 */
 	if (hardirq_count())
-		per_cpu(cpu_hardirq_time, cpu) += delta;
+		__this_cpu_add(cpu_hardirq_time, delta);
 	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
-		per_cpu(cpu_softirq_time, cpu) += delta;
+		__this_cpu_add(cpu_softirq_time, delta);
 
+	irq_time_write_end();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
-		u64 delta_irq = curr_irq_time - rq->prev_irq_time;
-		rq->prev_irq_time = curr_irq_time;
-		sched_rt_avg_update(rq, delta_irq);
-	}
+	s64 irq_delta;
+
+	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+	rq->clock_task += delta;
+
+	if (irq_delta && sched_feat(NONIRQ_POWER))
+		sched_rt_avg_update(rq, irq_delta);
 }
 
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	return 0;
+	rq->clock_task += delta;
 }
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -2129,7 +2186,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (test_tsk_need_resched(rq->curr))
+	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -3119,6 +3176,15 @@ static long calc_load_fold_active(struct rq *this_rq)
 	return delta;
 }
 
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	load += 1UL << (FSHIFT - 1);
+	return load >> FSHIFT;
+}
+
 #ifdef CONFIG_NO_HZ
 /*
  * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3148,6 +3214,128 @@ static long calc_load_fold_idle(void)
 
 	return delta;
 }
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x:         base of the power
+ * @frac_bits: fractional bits of @x
+ * @n:         power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+	unsigned long result = 1UL << frac_bits;
+
+	if (n) for (;;) {
+		if (n & 1) {
+			result *= x;
+			result += 1UL << (frac_bits - 1);
+			result >>= frac_bits;
+		}
+		n >>= 1;
+		if (!n)
+			break;
+		x *= x;
+		x += 1UL << (frac_bits - 1);
+		x >>= frac_bits;
+	}
+
+	return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ *    = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ *  ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ *    = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ *              n         1 - x^(n+1)
+ *     S_n := \Sum x^i = -------------
+ *             i=0          1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+	    unsigned long active, unsigned int n)
+{
+
+	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+	long delta, active, n;
+
+	if (time_before(jiffies, calc_load_update))
+		return;
+
+	/*
+	 * If we crossed a calc_load_update boundary, make sure to fold
+	 * any pending idle changes, the respective CPUs might have
+	 * missed the tick driven calc_load_account_active() update
+	 * due to NO_HZ.
+	 */
+	delta = calc_load_fold_idle();
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
+	/*
+	 * If we were idle for multiple load cycles, apply them.
+	 */
+	if (ticks >= LOAD_FREQ) {
+		n = ticks / LOAD_FREQ;
+
+		active = atomic_long_read(&calc_load_tasks);
+		active = active > 0 ? active * FIXED_1 : 0;
+
+		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+		calc_load_update += n * LOAD_FREQ;
+	}
+
+	/*
+	 * Its possible the remainder of the above division also crosses
+	 * a LOAD_FREQ period, the regular check in calc_global_load()
+	 * which comes after this will take care of that.
+	 *
+	 * Consider us being 11 ticks before a cycle completion, and us
+	 * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+	 * age us 4 cycles, and the test in calc_global_load() will
+	 * pick up the final one.
+	 */
+}
 #else
 static void calc_load_account_idle(struct rq *this_rq)
 {
@@ -3157,6 +3345,10 @@ static inline long calc_load_fold_idle(void)
 {
 	return 0;
 }
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
 #endif
 
 /**
@@ -3174,24 +3366,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 	loads[2] = (avenrun[2] + offset) << shift;
 }
 
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	return load >> FSHIFT;
-}
-
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
  * CPUs have updated calc_load_tasks.
  */
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
 {
-	unsigned long upd = calc_load_update + 10;
 	long active;
 
-	if (time_before(jiffies, upd))
+	calc_global_nohz(ticks);
+
+	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
 	active = atomic_long_read(&calc_load_tasks);
@@ -3845,7 +4030,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	if (prev->se.on_rq)
 		update_rq_clock(rq);
-	rq->skip_clock_update = 0;
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3903,7 +4087,6 @@ need_resched_nonpreemptible:
 		hrtick_clear(rq);
 
 	raw_spin_lock_irq(&rq->lock);
-	clear_tsk_need_resched(prev);
 
 	switch_count = &prev->nivcsw;
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3935,6 +4118,8 @@ need_resched_nonpreemptible:
 
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
+	clear_tsk_need_resched(prev);
+	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
diff --git a/kernel/timer.c b/kernel/timer.c
index 68a9ae7..353b922 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1252,6 +1252,12 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 	unsigned long expires;
 
+	/*
+	 * Pretend that there is no timer pending if the cpu is offline.
+	 * Possible pending timers will be migrated later to an active cpu.
+	 */
+	if (cpu_is_offline(smp_processor_id()))
+		return now + NEXT_TIMER_MAX_DELTA;
 	spin_lock(&base->lock);
 	if (time_before_eq(base->next_timer, base->timer_jiffies))
 		base->next_timer = __next_timer_interrupt(base);
@@ -1319,7 +1325,7 @@ void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
 	update_wall_time();
-	calc_global_load();
+	calc_global_load(ticks);
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM

[GIT PULL, v2] scheduler fixes

[Ingo Molnar]

Linus,

Please pull the latest sched-fixes-for-linus-2 git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus-2

This excludes the "sched: avoid flexible array member inside struct 
(gcc extension)" commit you objected to. Did a test-build and a 
test-boot of this, just in case...

 Thanks,

	Ingo

------------------>
Ron (1):
      sched: Fix fallback sched_clock()'s offset when using jiffies


 kernel/sched_clock.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 819f17a..e1d16c9 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -38,7 +38,8 @@
  */
 unsigned long long __attribute__((weak)) sched_clock(void)
 {
-	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
+					* (NSEC_PER_SEC / HZ);
 }
 
 static __read_mostly int sched_clock_running;