oom: various fixes and improvements for 2.6.18-rc2

Index: linux-2.6/mm/vmscan.c
===================================================================
@@ -62,6 +62,8 @@ struct scan_control {
 	int swap_cluster_max;
 
 	int swappiness;
+
+	int all_unreclaimable;
 };
 
 /*

@@ -925,6 +927,7 @@ static unsigned long shrink_zones(int pr
 	unsigned long nr_reclaimed = 0;
 	int i;
 
+	sc->all_unreclaimable = 1;
 	for (i = 0; zones[i] != NULL; i++) {
 		struct zone *zone = zones[i];
 

@@ -941,6 +944,8 @@ static unsigned long shrink_zones(int pr
 		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 			continue;	/* Let kswapd poll it */
 
+		sc->all_unreclaimable = 0;
+
 		nr_reclaimed += shrink_zone(priority, zone, sc);
 	}
 	return nr_reclaimed;

@@ -1021,6 +1026,9 @@ unsigned long try_to_free_pages(struct z
 		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
 			blk_congestion_wait(WRITE, HZ/10);
 	}
+	/* top priority shrink_caches still had more to do? don't OOM, then */
+	if (!sc.all_unreclaimable)
+		ret = 1;
 out:
 	for (i = 0; zones[i] != 0; i++) {
 		struct zone *zone = zones[i];

Index: linux-2.6/mm/vmscan.c
===================================================================
@@ -697,6 +697,11 @@ done:
 	return nr_reclaimed;
 }
 
+static inline int zone_is_near_oom(struct zone *zone)
+{
+	return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
+}
+
 /*
  * This moves pages from the active list to the inactive list.
  *

@@ -732,6 +737,9 @@ static void shrink_active_list(unsigned 
 		long distress;
 		long swap_tendency;
 
+		if (zone_is_near_oom(zone))
+			goto force_reclaim_mapped;
+
 		/*
 		 * `distress' is a measure of how much trouble we're having
 		 * reclaiming pages.  0 -> no problems.  100 -> great trouble.

@@ -767,6 +775,7 @@ static void shrink_active_list(unsigned 
 		 * memory onto the inactive list.
 		 */
 		if (swap_tendency >= 100)
+force_reclaim_mapped:
 			reclaim_mapped = 1;
 	}
 

@@ -1161,7 +1170,7 @@ scan:
 			if (zone->all_unreclaimable)
 				continue;
 			if (nr_slab == 0 && zone->pages_scanned >=
-				    (zone->nr_active + zone->nr_inactive) * 4)
+				    (zone->nr_active + zone->nr_inactive) * 6)
 				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and

Index: linux-2.6/kernel/cpuset.c
===================================================================
@@ -2369,7 +2369,7 @@ EXPORT_SYMBOL_GPL(cpuset_mem_spread_node
 int cpuset_excl_nodes_overlap(const struct task_struct *p)
 {
 	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
-	int overlap = 0;		/* do cpusets overlap? */
+	int overlap = 1;		/* do cpusets overlap? */
 
 	task_lock(current);
 	if (current->flags & PF_EXITING) {

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -127,6 +127,14 @@ unsigned long badness(struct task_struct
 		points /= 4;
 
 	/*
+	 * If p's nodes don't overlap ours, it may still help to kill p
+	 * because p may have allocated or otherwise mapped memory on
+	 * this node before. However it will be less likely.
+	 */
+	if (!cpuset_excl_nodes_overlap(p))
+		points /= 8;
+
+	/*
 	 * Adjust the score by oomkilladj.
 	 */
 	if (p->oomkilladj) {

@@ -196,9 +204,6 @@ static struct task_struct *select_bad_pr
 			continue;
 		if (p->oomkilladj == OOM_DISABLE)
 			continue;
-		/* If p's nodes don't overlap ours, it won't help to kill p. */
-		if (!cpuset_excl_nodes_overlap(p))
-			continue;
 
 		/*
 		 * This is in the process of releasing memory so wait for it

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -208,11 +208,26 @@ static struct task_struct *select_bad_pr
 		/*
 		 * This is in the process of releasing memory so wait for it
 		 * to finish before killing some other task by mistake.
+		 *
+		 * However, if p is the current task, we allow the 'kill' to
+		 * go ahead if it is exiting: this will simply set TIF_MEMDIE,
+		 * which will allow it to gain access to memory reserves in
+		 * the process of exiting and releasing its resources.
+		 * Otherwise we could get an OOM deadlock.
 		 */
 		releasing = test_tsk_thread_flag(p, TIF_MEMDIE) ||
 						p->flags & PF_EXITING;
-		if (releasing && !(p->flags & PF_DEAD))
+		if (releasing) {
+			/* PF_DEAD tasks have already released their mm */
+			if (p->flags & PF_DEAD)
+				continue;
+			if (p->flags & PF_EXITING && p == current) {
+				chosen = p;
+				*ppoints = ULONG_MAX;
+				break;
+			}
 			return ERR_PTR(-1UL);
+		}
 		if (p->flags & PF_SWAPOFF)
 			return p;
 

@@ -246,8 +261,11 @@ static void __oom_kill_task(struct task_
 		return;
 	}
 	task_unlock(p);
-	printk(KERN_ERR "%s: Killed process %d (%s).\n",
+
+	if (message) {
+		printk(KERN_ERR "%s: Killed process %d (%s).\n",
 				message, p->pid, p->comm);
+	}
 
 	/*
 	 * We give our sacrificial lamb high priority and access to

@@ -298,8 +316,17 @@ static int oom_kill_process(struct task_
 	struct task_struct *c;
 	struct list_head *tsk;
 
-	printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li and "
-		"children.\n", p->pid, p->comm, points);
+	/*
+	 * If the task is already exiting, don't alarm the sysadmin or kill
+	 * its children or threads, just set TIF_MEMDIE so it can die quickly
+	 */
+	if (p->flags & PF_EXITING) {
+		__oom_kill_task(p, NULL);
+		return 0;
+	}
+
+	printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li"
+			" and children.\n", p->pid, p->comm, points);
 	/* Try to kill a child first */
 	list_for_each(tsk, &p->children) {
 		c = list_entry(tsk, struct task_struct, sibling);

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -202,8 +202,6 @@ static struct task_struct *select_bad_pr
 		/* skip the init task with pid == 1 */
 		if (p->pid == 1)
 			continue;
-		if (p->oomkilladj == OOM_DISABLE)
-			continue;
 
 		/*
 		 * This is in the process of releasing memory so wait for it

@@ -228,6 +226,8 @@ static struct task_struct *select_bad_pr
 			}
 			return ERR_PTR(-1UL);
 		}
+		if (p->oomkilladj == OOM_DISABLE)
+			continue;
 		if (p->flags & PF_SWAPOFF)
 			return p;
 

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -58,6 +58,12 @@ unsigned long badness(struct task_struct
 	}
 
 	/*
+	 * swapoff can easily use up all memory, so kill those first.
+	 */
+	if (p->flags & PF_SWAPOFF)
+		return ULONG_MAX;
+
+	/*
 	 * The memory size of the process is the basis for the badness.
 	 */
 	points = mm->total_vm;

@@ -228,8 +234,6 @@ static struct task_struct *select_bad_pr
 		}
 		if (p->oomkilladj == OOM_DISABLE)
 			continue;
-		if (p->flags & PF_SWAPOFF)
-			return p;
 
 		points = badness(p, uptime.tv_sec);
 		if (points > *ppoints || !chosen) {

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -205,6 +205,9 @@ static struct task_struct *select_bad_pr
 		unsigned long points;
 		int releasing;
 
+		/* skip kernel threads */
+		if (!p->mm)
+			continue;
 		/* skip the init task with pid == 1 */
 		if (p->pid == 1)
 			continue;

Index: linux-2.6/mm/oom_kill.c
===================================================================
@@ -359,8 +359,9 @@ void out_of_memory(struct zonelist *zone
 	unsigned long points = 0;
 
 	if (printk_ratelimit()) {
-		printk("oom-killer: gfp_mask=0x%x, order=%d\n",
-			gfp_mask, order);
+		printk(KERN_WARNING "%s invoked oom-killer: "
+			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+			current->comm, gfp_mask, order, current->oomkilladj);
 		dump_stack();
 		show_mem();
 	}