mm: numa: Revert temporarily disabling of NUMA migration

With the scan rate code working (at least for multi-instance specjbb),
the large hammer that is "sched: Do not migrate memory immediately after
switching node" can be replaced with something smarter. Revert temporarily
migration disabling and all traces of numa_migrate_seq.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-61-git-send-email-mgorman@suse.deSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -1340,7 +1340,6 @@ struct task_struct {
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	int numa_scan_seq;
-	int numa_migrate_seq;
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
 	unsigned long numa_migrate_retry;

kernel/sched/core.c

@@ -1731,7 +1731,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_migrate_seq = 1;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
@@ -4488,7 +4487,6 @@ void sched_setnuma(struct task_struct *p, int nid)
 		p->sched_class->put_prev_task(rq, p);
 
 	p->numa_preferred_nid = nid;
-	p->numa_migrate_seq = 1;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);

kernel/sched/fair.c

@@ -1261,16 +1261,8 @@ static void numa_migrate_preferred(struct task_struct *p)
 {
 	/* Success if task is already running on preferred CPU */
 	p->numa_migrate_retry = 0;
-	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid) {
-		/*
-		 * If migration is temporarily disabled due to a task migration
-		 * then re-enable it now as the task is running on its
-		 * preferred node and memory should migrate locally
-		 */
-		if (!p->numa_migrate_seq)
-			p->numa_migrate_seq++;
+	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
 		return;
-	}
 
 	/* This task has no NUMA fault statistics yet */
 	if (unlikely(p->numa_preferred_nid == -1))
@@ -1367,7 +1359,6 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
-	p->numa_migrate_seq++;
 	p->numa_scan_period_max = task_scan_max(p);
 
 	/* If the task is part of a group prevent parallel updates to group stats */
@@ -4730,20 +4721,6 @@ static void move_task(struct task_struct *p, struct lb_env *env)
 	set_task_cpu(p, env->dst_cpu);
 	activate_task(env->dst_rq, p, 0);
 	check_preempt_curr(env->dst_rq, p, 0);
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->numa_preferred_nid != -1) {
-		int src_nid = cpu_to_node(env->src_cpu);
-		int dst_nid = cpu_to_node(env->dst_cpu);
-
-		/*
-		 * If the load balancer has moved the task then limit
-		 * migrations from taking place in the short term in
-		 * case this is a short-lived migration.
-		 */
-		if (src_nid != dst_nid && dst_nid != p->numa_preferred_nid)
-			p->numa_migrate_seq = 0;
-	}
-#endif
 }
 
 /*

mm/mempolicy.c

@@ -2404,18 +2404,6 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
 		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid)
 			goto out;
-
-#ifdef CONFIG_NUMA_BALANCING
-		/*
-		 * If the scheduler has just moved us away from our
-		 * preferred node, do not bother migrating pages yet.
-		 * This way a short and temporary process migration will
-		 * not cause excessive memory migration.
-		 */
-		if (thisnid != current->numa_preferred_nid &&
-				!current->numa_migrate_seq)
-			goto out;
-#endif
 	}
 
 	if (curnid != polnid)