sched/numa: implement access PID reset logic

This helps to ensure that only recently accessed PIDs scan the VMAs.

Current implementation: (idea supported by PeterZ)

 1. Accessing PID information is maintained in two windows. 
    access_pids[1] being newest.

 2. Reset old access PID info i.e.  access_pid[0] every (4 *
    sysctl_numa_balancing_scan_delay) interval after initial scan delay
    period expires.

The above interval seemed to be experimentally optimum since it avoids
frequent reset of access info as well as helps clearing the old access
info regularly.  The reset logic is implemented in scan path.

Link: https://lkml.kernel.org/r/f7a675f66d1442d048b4216b2baf94515012c405.1677672277.git.raghavendra.kt@amd.comSigned-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Suggested-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Bharata B Rao <bharata@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -1692,8 +1692,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 	unsigned int pid_bit;
 
 	pid_bit = current->pid % BITS_PER_LONG;
-	if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) {
-		__set_bit(pid_bit, &vma->numab_state->access_pids);
+	if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) {
+		__set_bit(pid_bit, &vma->numab_state->access_pids[1]);
 	}
 }
 #else /* !CONFIG_NUMA_BALANCING */

include/linux/mm_types.h

@@ -477,7 +477,8 @@ struct vma_lock {
 
 struct vma_numab_state {
 	unsigned long next_scan;
-	unsigned long access_pids;
+	unsigned long next_pid_reset;
+	unsigned long access_pids[2];
 };
 
 /*

kernel/sched/fair.c

@@ -2930,6 +2930,7 @@ static void reset_ptenuma_scan(struct task_struct *p)
 
 static bool vma_is_accessed(struct vm_area_struct *vma)
 {
+	unsigned long pids;
 	/*
 	 * Allow unconditional access first two times, so that all the (pages)
 	 * of VMAs get prot_none fault introduced irrespective of accesses.
@@ -2939,10 +2940,12 @@ static bool vma_is_accessed(struct vm_area_struct *vma)
 	if (READ_ONCE(current->mm->numa_scan_seq) < 2)
 		return true;
 
-	return test_bit(current->pid % BITS_PER_LONG,
-				&vma->numab_state->access_pids);
+	pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1];
+	return test_bit(current->pid % BITS_PER_LONG, &pids);
 }
 
+#define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay)
+
 /*
  * The expensive part of numa migration is done from task_work context.
  * Triggered from task_tick_numa().
@@ -3051,6 +3054,10 @@ static void task_numa_work(struct callback_head *work)
 
 			vma->numab_state->next_scan = now +
 				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+
+			/* Reset happens after 4 times scan delay of scan start */
+			vma->numab_state->next_pid_reset =  vma->numab_state->next_scan +
+				msecs_to_jiffies(VMA_PID_RESET_PERIOD);
 		}
 
 		/*
@@ -3065,6 +3072,18 @@ static void task_numa_work(struct callback_head *work)
 		if (!vma_is_accessed(vma))
 			continue;
 
+		/*
+		 * RESET access PIDs regularly for old VMAs. Resetting after checking
+		 * vma for recent access to avoid clearing PID info before access..
+		 */
+		if (mm->numa_scan_seq &&
+				time_after(jiffies, vma->numab_state->next_pid_reset)) {
+			vma->numab_state->next_pid_reset = vma->numab_state->next_pid_reset +
+				msecs_to_jiffies(VMA_PID_RESET_PERIOD);
+			vma->numab_state->access_pids[0] = READ_ONCE(vma->numab_state->access_pids[1]);
+			vma->numab_state->access_pids[1] = 0;
+		}
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);