sched/fair: Care divide error in update_task_scan_period()

While offling node by hot removing memory, the following divide error occurs:

   divide error: 0000 [#1] SMP
   [...]
   Call Trace:
    [...] handle_mm_fault
    [...] ? try_to_wake_up
    [...] ? wake_up_state
    [...] __do_page_fault
    [...] ? do_futex
    [...] ? put_prev_entity
    [...] ? __switch_to
    [...] do_page_fault
    [...] page_fault
   [...]
   RIP  [<ffffffff810a7081>] task_numa_fault
    RSP <ffff88084eb2bcb0>

The issue occurs as follows:
1. When page fault occurs and page is allocated from node 1, task_struct->numa_faults_buffer_memory[] of node 1 is incremented and p->numa_faults_locality[] is also incremented as follows:

o numa_faults_buffer_memory[] o numa_faults_locality[]
NR_NUMA_HINT_FAULT_TYPES
| 0 | 1 |
---------------------------------- ----------------------
node 0 | 0 | 0 | remote | 0 |
node 1 | 0 | 1 | locale | 1 |
---------------------------------- ----------------------

2. node 1 is offlined by hot removing memory.

3. When page fault occurs, fault_types[] is calculated by using

      p->numa_faults_buffer_memory[] of all online nodes in
      task_numa_placement(). But node 1 was offline by step 2. So
      the fault_types[] is calculated by using only
      p->numa_faults_buffer_memory[] of node 0. So both of fault_types[]
      are set to 0.

4. The values(0) of fault_types[] pass to update_task_scan_period().

   5. numa_faults_locality[1] is set to 1. So the following division is
      calculated.

         static void update_task_scan_period(struct task_struct *p,
                                 unsigned long shared, unsigned long private){
         ...
                 ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
         }

   6. But both of private and shared are set to 0. So divide error
      occurs here.

The divide error is rare case because the trigger is node offline. By this patch, when both of private and shared are set to 0, denominator is set to 1 for avoiding divide error.

Signed-off-by Yasuaki Ishimatsu <[email protected]>

CC Wanpeng Li <[email protected]>

CC Rik van Riel <[email protected]>

CC Peter Zijlstra <[email protected]>

---
  kernel/sched/fair.c | 11 ++++++++++-
  1 file changed, 10 insertions(+), 1 deletion(-)

kernel/sched/fair.c +10 -1

index bfa3c86..580fc74 100644
@@ -1466,6 +1466,7 @@ static void update_task_scan_period(struct task_struct *p,
 
  	unsigned long remote = p->numa_faults_locality[0];
  	unsigned long local = p->numa_faults_locality[1];
+	unsigned long total_faults = shared + private;
 
  	/*
  	 * If there were no record hinting faults then either the task is

@@ -1496,6 +1497,14 @@ static void update_task_scan_period(struct task_struct *p,
  			slot = 1;
  		diff = slot * period_slot;
  	} else {
+		/*
+		 * This is a rare case. total_faults might become 0 after
+		 * offlining node. In this case, total_faults is set to 1
+		 * for avoiding divide error.
+		 */
+		if (unlikely(total_faults == 0))
+			total_faults = 1;
+
  		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
 
  		/*

@@ -1506,7 +1515,7 @@ static void update_task_scan_period(struct task_struct *p,
  		 * scanning faster if shared accesses dominate as it may
  		 * simply bounce migrations uselessly
  		 */
-		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (total_faults));
  		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
  	}
 

+++ b/kernel/sched/fair.c

kernel/sched/fair.c +9 -0

@@ -1466,6 +1466,7 @@ static void update_task_scan_period(struct task_struct *p,
 
 	unsigned long remote = p->numa_faults_locality[0];
 	unsigned long local = p->numa_faults_locality[1];
+	unsigned long total_faults = shared + private;
 
 	/*
 	 * If there were no record hinting faults then either the task is

@@ -1496,6 +1497,14 @@ static void update_task_scan_period(struct task_struct *p,
 			slot = 1;
 		diff = slot * period_slot;
 	} else {
+		/*
+		 * This is a rare case. total_faults might become 0 after
+		 * offlining node. In this case, total_faults is set to 1
+		 * for avoiding divide error.
+		 */
+		if (unlikely(total_faults == 0))
+			total_faults = 1;
+
 		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
 
 		/*

Quoted 23 lines · Yasuaki Ishimatsu

+++ b/kernel/sched/fair.c

kernel/sched/fair.c +9 -0

@@ -1466,6 +1466,7 @@ static void update_task_scan_period(struct task_struct *p,
 
  	unsigned long remote = p->numa_faults_locality[0];
  	unsigned long local = p->numa_faults_locality[1];
+	unsigned long total_faults = shared + private;
 
  	/*
  	 * If there were no record hinting faults then either the task is

@@ -1496,6 +1497,14 @@ static void update_task_scan_period(struct task_struct *p,
  			slot = 1;
  		diff = slot * period_slot;
  	} else {
+		/*
+		 * This is a rare case. total_faults might become 0 after
+		 * offlining node. In this case, total_faults is set to 1
+		 * for avoiding divide error.
+		 */
+		if (unlikely(total_faults == 0))
+			total_faults = 1;
+
  		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
 

kernel/sched/fair.c static void update_task_scan_period(struct task_struct *p, · line 1519

Quoted 8 lines

kernel/sched/fair.c +1 -1

  		/*

@@ -1506,7 +1515,7 @@ static void update_task_scan_period(struct task_struct *p,
  		 * scanning faster if shared accesses dominate as it may
  		 * simply bounce migrations uselessly
  		 */
-		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (total_faults));
  		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;

So what was wrong with the 'normal' unconditional +1 approach? Also you've got superfluous parenthese.