[PATCH 0/6] variuos patches lined up for .28

[PATCH 0/6] variuos patches lined up for .28

[Peter Zijlstra]

Dumping my current queue...

[PATCH 1/6] lockstat: fixup signed division

[Peter Zijlstra]

[-- Attachment #1: lockstat-fix-div.patch --]
[-- Type: text/plain, Size: 977 bytes --]

Some recent modification to this code made me notice the little todo mark.
Now that we have more elaborate 64-bit division functions this isn't hard.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/lockdep_proc.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

Index: linux-2.6/kernel/lockdep_proc.c
===================================================================
--- linux-2.6.orig/kernel/lockdep_proc.c
+++ linux-2.6/kernel/lockdep_proc.c
@@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m,
 
 static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
-	unsigned long rem;
+	s64 div;
+	s32 rem;
 
 	nr += 5; /* for display rounding */
-	rem = do_div(nr, 1000); /* XXX: do_div_signed */
-	snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
+	div = div_s64_rem(nr, 1000, &rem);
+	snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)

-- 

[PATCH 2/6] sched: fixlet for group load balance

[Peter Zijlstra]

[-- Attachment #1: sched-group-balance-fix.patch --]
[-- Type: text/plain, Size: 1820 bytes --]

We should not only correct the increment for the initial group, but should
be consistent and do so for all the groups we encounter.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched_fair.c |   27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -1086,7 +1086,6 @@ static long effective_load(struct task_g
 		long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
-	long more_w;
 
 	if (!tg->parent)
 		return wl;
@@ -1098,18 +1097,17 @@ static long effective_load(struct task_g
 	if (!wl && sched_feat(ASYM_EFF_LOAD))
 		return wl;
 
-	/*
-	 * Instead of using this increment, also add the difference
-	 * between when the shares were last updated and now.
-	 */
-	more_w = se->my_q->load.weight - se->my_q->rq_weight;
-	wl += more_w;
-	wg += more_w;
-
 	for_each_sched_entity(se) {
-#define D(n) (likely(n) ? (n) : 1)
-
 		long S, rw, s, a, b;
+		long more_w;
+
+		/*
+		 * Instead of using this increment, also add the difference
+		 * between when the shares were last updated and now.
+		 */
+		more_w = se->my_q->load.weight - se->my_q->rq_weight;
+		wl += more_w;
+		wg += more_w;
 
 		S = se->my_q->tg->shares;
 		s = se->my_q->shares;
@@ -1118,7 +1116,11 @@ static long effective_load(struct task_g
 		a = S*(rw + wl);
 		b = S*rw + s*wg;
 
-		wl = s*(a-b)/D(b);
+		wl = s*(a-b);
+
+		if (likely(b))
+			wl /= b;
+
 		/*
 		 * Assume the group is already running and will
 		 * thus already be accounted for in the weight.
@@ -1127,7 +1129,6 @@ static long effective_load(struct task_g
 		 * alter the group weight.
 		 */
 		wg = 0;
-#undef D
 	}
 
 	return wl;

-- 

[PATCH 3/6] sched: add some comments to the bandwidth code

[Peter Zijlstra]

[-- Attachment #1: sched-rt-bw-comment.patch --]
[-- Type: text/plain, Size: 3300 bytes --]

Hopefully clarify some of this code a little.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched_rt.c |   42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

Index: linux-2.6/kernel/sched_rt.c
===================================================================
--- linux-2.6.orig/kernel/sched_rt.c
+++ linux-2.6/kernel/sched_rt.c
@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_SMP
+/*
+ * We ran out of runtime, see if we can borrow some from our neighbours.
+ */
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_
 			continue;
 
 		spin_lock(&iter->rt_runtime_lock);
+		/*
+		 * Either all rqs have inf runtime and there's nothing to steal
+		 * or __disable_runtime() below sets a specific rq to inf to
+		 * indicate its been disabled and disalow stealing.
+		 */
 		if (iter->rt_runtime == RUNTIME_INF)
 			goto next;
 
+		/*
+		 * From runqueues with spare time, take 1/n part of their
+		 * spare time, but no more than our period.
+		 */
 		diff = iter->rt_runtime - iter->rt_time;
 		if (diff > 0) {
 			diff = div_u64((u64)diff, weight);
@@ -274,6 +286,9 @@ next:
 	return more;
 }
 
+/*
+ * Ensure this RQ takes back all the runtime it lend to its neighbours.
+ */
 static void __disable_runtime(struct rq *rq)
 {
 	struct root_domain *rd = rq->rd;
@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq 
 
 		spin_lock(&rt_b->rt_runtime_lock);
 		spin_lock(&rt_rq->rt_runtime_lock);
+		/*
+		 * Either we're all inf and nobody needs to borrow, or we're
+		 * already disabled and thus have nothing to do, or we have
+		 * exactly the right amount of runtime to take out.
+		 */
 		if (rt_rq->rt_runtime == RUNTIME_INF ||
 				rt_rq->rt_runtime == rt_b->rt_runtime)
 			goto balanced;
 		spin_unlock(&rt_rq->rt_runtime_lock);
 
+		/*
+		 * Calculate the difference between what we started out with
+		 * and what we current have, that's the amount of runtime
+		 * we lend and now have to reclaim.
+		 */
 		want = rt_b->rt_runtime - rt_rq->rt_runtime;
 
+		/*
+		 * Greedy reclaim, take back as much as we can.
+		 */
 		for_each_cpu_mask(i, rd->span) {
 			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
 			s64 diff;
 
+			/*
+			 * Can't reclaim from ourselves or disabled runqueues.
+			 */
 			if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
 				continue;
 
@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq 
 		}
 
 		spin_lock(&rt_rq->rt_runtime_lock);
+		/*
+		 * We cannot be left wanting - that would mean some runtime
+		 * leaked out of the system.
+		 */
 		BUG_ON(want);
 balanced:
+		/*
+		 * Disable all the borrow logic by pretending we have inf
+		 * runtime - in which case borrowing doesn't make sense.
+		 */
 		rt_rq->rt_runtime = RUNTIME_INF;
 		spin_unlock(&rt_rq->rt_runtime_lock);
 		spin_unlock(&rt_b->rt_runtime_lock);
@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *
 	if (unlikely(!scheduler_running))
 		return;
 
+	/*
+	 * Reset each runqueue's bandwidth settings
+	 */
 	for_each_leaf_rt_rq(rt_rq, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 

-- 

[PATCH 4/6] sched: more sanity checks on the bandwidth settings

[Peter Zijlstra]

[-- Attachment #1: sched-rt-bw-schedulable-fix.patch --]
[-- Type: text/plain, Size: 2056 bytes --]

While playing around with it, I noticed we missed some sanity checks.
Also add some comments while we're there.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched.c |   33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -8892,11 +8892,29 @@ static int tg_schedulable(struct task_gr
 		runtime = d->rt_runtime;
 	}
 
+	/*
+	 * Cannot have more runtime than the period.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	/*
+	 * Ensure we don't starve existing RT tasks.
+	 */
 	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
 	total = to_ratio(period, runtime);
 
+	/*
+	 * Nobody can have more than the global setting allows.
+	 */
+	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+		return -EINVAL;
+
+	/*
+	 * The sum of our children's runtime should not exceed our own.
+	 */
 	list_for_each_entry_rcu(child, &tg->children, siblings) {
 		period = ktime_to_ns(child->rt_bandwidth.rt_period);
 		runtime = child->rt_bandwidth.rt_runtime;
@@ -9004,19 +9022,24 @@ long sched_group_rt_period(struct task_g
 
 static int sched_rt_global_constraints(void)
 {
-	struct task_group *tg = &root_task_group;
-	u64 rt_runtime, rt_period;
+	u64 runtime, period;
 	int ret = 0;
 
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
-	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	rt_runtime = tg->rt_bandwidth.rt_runtime;
+	runtime = global_rt_runtime();
+	period = global_rt_period();
+
+	/*
+	 * Sanity check on the sysctl variables.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
 
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
-	ret = __rt_schedulable(tg, rt_period, rt_runtime);
+	ret = __rt_schedulable(NULL, 0, 0);
 	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 

-- 

[PATCH 5/6] sched: fixup buddy selection

[Peter Zijlstra]

[-- Attachment #1: sched-fix-buddy.patch --]
[-- Type: text/plain, Size: 867 bytes --]

We should set the buddy even though we might already have the TIF_RESCHED flag
set.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched_fair.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -1350,6 +1350,8 @@ static void check_preempt_wakeup(struct 
 	if (unlikely(se == pse))
 		return;
 
+	cfs_rq_of(pse)->next = pse;
+
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
 	 * wake up path.
@@ -1357,8 +1359,6 @@ static void check_preempt_wakeup(struct 
 	if (test_tsk_need_resched(curr))
 		return;
 
-	cfs_rq_of(pse)->next = pse;
-
 	/*
 	 * Batch tasks do not preempt (their preemption is driven by
 	 * the tick):

-- 

[PATCH 6/6] sched: rework wakeup preemption

[Peter Zijlstra]

[-- Attachment #1: sched-wakeup-preempt.patch --]
[-- Type: text/plain, Size: 4249 bytes --]

Rework the wakeup preemption to work on real runtime instead of
the virtual runtime. This greatly simplifies the code.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched_fair.c |  133 +---------------------------------------------------
 1 file changed, 4 insertions(+), 129 deletions(-)

Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -409,64 +409,6 @@ static u64 sched_vslice_add(struct cfs_r
 }
 
 /*
- * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
- * that it favours >=0 over <0.
- *
- *   -20         |
- *               |
- *     0 --------+-------
- *             .'
- *    19     .'
- *
- */
-static unsigned long
-calc_delta_asym(unsigned long delta, struct sched_entity *se)
-{
-	struct load_weight lw = {
-		.weight = NICE_0_LOAD,
-		.inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
-	};
-
-	for_each_sched_entity(se) {
-		struct load_weight *se_lw = &se->load;
-		unsigned long rw = cfs_rq_of(se)->load.weight;
-
-#ifdef CONFIG_FAIR_SCHED_GROUP
-		struct cfs_rq *cfs_rq = se->my_q;
-		struct task_group *tg = NULL
-
-		if (cfs_rq)
-			tg = cfs_rq->tg;
-
-		if (tg && tg->shares < NICE_0_LOAD) {
-			/*
-			 * scale shares to what it would have been had
-			 * tg->weight been NICE_0_LOAD:
-			 *
-			 *   weight = 1024 * shares / tg->weight
-			 */
-			lw.weight *= se->load.weight;
-			lw.weight /= tg->shares;
-
-			lw.inv_weight = 0;
-
-			se_lw = &lw;
-			rw += lw.weight - se->load.weight;
-		} else
-#endif
-
-		if (se->load.weight < NICE_0_LOAD) {
-			se_lw = &lw;
-			rw += NICE_0_LOAD - se->load.weight;
-		}
-
-		delta = calc_delta_mine(delta, rw, se_lw);
-	}
-
-	return delta;
-}
-
-/*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
  */
@@ -1283,54 +1225,12 @@ static unsigned long wakeup_gran(struct 
 	 * + nice tasks.
 	 */
 	if (sched_feat(ASYM_GRAN))
-		gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
-	else
-		gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+		gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
 
 	return gran;
 }
 
 /*
- * Should 'se' preempt 'curr'.
- *
- *             |s1
- *        |s2
- *   |s3
- *         g
- *      |<--->|c
- *
- *  w(c, s1) = -1
- *  w(c, s2) =  0
- *  w(c, s3) =  1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
-	s64 gran, vdiff = curr->vruntime - se->vruntime;
-
-	if (vdiff < 0)
-		return -1;
-
-	gran = wakeup_gran(curr);
-	if (vdiff > gran)
-		return 1;
-
-	return 0;
-}
-
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-	int depth = 0;
-
-	for_each_sched_entity(se)
-		depth++;
-
-	return depth;
-}
-
-/*
  * Preempt the current task with a newly woken task if needed:
  */
 static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
@@ -1338,7 +1238,7 @@ static void check_preempt_wakeup(struct 
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se, *pse = &p->se;
-	int se_depth, pse_depth;
+	s64 delta_exec;
 
 	if (unlikely(rt_prio(p->prio))) {
 		update_rq_clock(rq);
@@ -1376,33 +1276,8 @@ static void check_preempt_wakeup(struct 
 		return;
 	}
 
-	/*
-	 * preemption test can be made between sibling entities who are in the
-	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
-	 * both tasks until we find their ancestors who are siblings of common
-	 * parent.
-	 */
-
-	/* First walk up until both entities are at same depth */
-	se_depth = depth_se(se);
-	pse_depth = depth_se(pse);
-
-	while (se_depth > pse_depth) {
-		se_depth--;
-		se = parent_entity(se);
-	}
-
-	while (pse_depth > se_depth) {
-		pse_depth--;
-		pse = parent_entity(pse);
-	}
-
-	while (!is_same_group(se, pse)) {
-		se = parent_entity(se);
-		pse = parent_entity(pse);
-	}
-
-	if (wakeup_preempt_entity(se, pse) == 1)
+	delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+	if (delta_exec > wakeup_gran(pse))
 		resched_task(curr);
 }
 

-- 

Re: [PATCH 1/6] lockstat: fixup signed division

[Ingo Molnar]

* Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:

> Some recent modification to this code made me notice the little todo mark.
> Now that we have more elaborate 64-bit division functions this isn't hard.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

applied to tip/core/locking, thanks Peter!

	Ingo

Re: [PATCH 6/6] sched: rework wakeup preemption

[Ingo Molnar]

* Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:

> Rework the wakeup preemption to work on real runtime instead of
> the virtual runtime. This greatly simplifies the code.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

applied the five scheduler patches to tip/sched/devel, thanks Peter!

	Ingo