X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Foom_kill.c;h=492c98624fc19bfd4b6fbb012b9c5661fc7fdb91;hb=4b42af81f0d7f95dff320f47d99c201925f406f5;hp=175a67a78a99e7b0368dfba11edf9888bc049674;hpb=81236810226f71bd9ff77321c8e8276dae7efc61;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 175a67a..492c986 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -34,6 +34,23 @@ int sysctl_oom_dump_tasks;
 static DEFINE_SPINLOCK(zone_scan_lock);
 /* #define DEBUG */
 
+/*
+ * Is all threads of the target process nodes overlap ours?
+ */
+static int has_intersects_mems_allowed(struct task_struct *tsk)
+{
+	struct task_struct *t;
+
+	t = tsk;
+	do {
+		if (cpuset_mems_allowed_intersects(current, t))
+			return 1;
+		t = next_thread(t);
+	} while (t != tsk);
+
+	return 0;
+}
+
 /**
  * badness - calculate a numeric value for how bad this task has been
  * @p: task struct of which task we should calculate
@@ -58,7 +75,13 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	unsigned long points, cpu_time, run_time;
 	struct mm_struct *mm;
 	struct task_struct *child;
-	int oom_adj;
+	int oom_adj = p->signal->oom_adj;
+	struct task_cputime task_time;
+	unsigned long utime;
+	unsigned long stime;
+
+	if (oom_adj == OOM_DISABLE)
+		return 0;
 
 	task_lock(p);
 	mm = p->mm;
@@ -66,11 +89,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 		task_unlock(p);
 		return 0;
 	}
-	oom_adj = mm->oom_adj;
-	if (oom_adj == OOM_DISABLE) {
-		task_unlock(p);
-		return 0;
-	}
 
 	/*
 	 * The memory size of the process is the basis for the badness.
@@ -85,7 +103,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	/*
 	 * swapoff can easily use up all memory, so kill those first.
 	 */
-	if (p->flags & PF_SWAPOFF)
+	if (p->flags & PF_OOM_ORIGIN)
 		return ULONG_MAX;
 
 	/*
@@ -108,8 +126,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
          * of seconds. There is no particular reason for this other than
          * that it turned out to work very well in practice.
 	 */
-	cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime))
-		>> (SHIFT_HZ + 3);
+	thread_group_cputime(p, &task_time);
+	utime = cputime_to_jiffies(task_time.utime);
+	stime = cputime_to_jiffies(task_time.stime);
+	cpu_time = (utime + stime) >> (SHIFT_HZ + 3);
+
 
 	if (uptime >= p->start_time.tv_sec)
 		run_time = (uptime - p->start_time.tv_sec) >> 10;
@@ -150,7 +171,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * because p may have allocated or otherwise mapped memory on
 	 * this node before. However it will be less likely.
 	 */
-	if (!cpuset_mems_allowed_intersects(current, p))
+	if (!has_intersects_mems_allowed(p))
 		points /= 8;
 
 	/*
@@ -206,13 +227,13 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 static struct task_struct *select_bad_process(unsigned long *ppoints,
 						struct mem_cgroup *mem)
 {
-	struct task_struct *g, *p;
+	struct task_struct *p;
 	struct task_struct *chosen = NULL;
 	struct timespec uptime;
 	*ppoints = 0;
 
 	do_posix_clock_monotonic_gettime(&uptime);
-	do_each_thread(g, p) {
+	for_each_process(p) {
 		unsigned long points;
 
 		/*
@@ -257,12 +278,15 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 			*ppoints = ULONG_MAX;
 		}
 
+		if (p->signal->oom_adj == OOM_DISABLE)
+			continue;
+
 		points = badness(p, uptime.tv_sec);
-		if (points > *ppoints) {
+		if (points > *ppoints || !chosen) {
 			chosen = p;
 			*ppoints = points;
 		}
-	} while_each_thread(g, p);
+	}
 
 	return chosen;
 }
@@ -307,11 +331,27 @@ static void dump_tasks(const struct mem_cgroup *mem)
 		}
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
 		       p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
-		       get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm);
+		       get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj,
+		       p->comm);
 		task_unlock(p);
 	} while_each_thread(g, p);
 }
 
+static void dump_header(gfp_t gfp_mask, int order, struct mem_cgroup *mem)
+{
+	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
+		"oom_adj=%d\n",
+		current->comm, gfp_mask, order, current->signal->oom_adj);
+	task_lock(current);
+	cpuset_print_task_mems_allowed(current);
+	task_unlock(current);
+	dump_stack();
+	mem_cgroup_print_oom_info(mem, current);
+	show_mem();
+	if (sysctl_oom_dump_tasks)
+		dump_tasks(mem);
+}
+
 /*
  * Send SIGKILL to the selected  process irrespective of  CAP_SYS_RAW_IO
  * flag though it's unlikely that  we select a process with CAP_SYS_RAW_IO
@@ -325,8 +365,11 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
 		return;
 	}
 
-	if (!p->mm)
+	if (!p->mm) {
+		WARN_ON(1);
+		printk(KERN_WARNING "tried to kill an mm-less task!\n");
 		return;
+	}
 
 	if (verbose)
 		printk(KERN_ERR "Killed process %d (%s)\n",
@@ -345,27 +388,18 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
 
 static int oom_kill_task(struct task_struct *p)
 {
-	struct mm_struct *mm;
-	struct task_struct *g, *q;
-
-	task_lock(p);
-	mm = p->mm;
-	if (!mm || mm->oom_adj == OOM_DISABLE) {
-		task_unlock(p);
+	/* WARNING: mm may not be dereferenced since we did not obtain its
+	 * value from get_task_mm(p).  This is OK since all we need to do is
+	 * compare mm to q->mm below.
+	 *
+	 * Furthermore, even if mm contains a non-NULL value, p->mm may
+	 * change to NULL at any time since we do not hold task_lock(p).
+	 * However, this is of no concern to us.
+	 */
+	if (!p->mm || p->signal->oom_adj == OOM_DISABLE)
 		return 1;
-	}
-	task_unlock(p);
-	__oom_kill_task(p, 1);
 
-	/*
-	 * kill all processes that share the ->mm (i.e. all threads),
-	 * but are in a different thread group. Don't let them have access
-	 * to memory reserves though, otherwise we might deplete all memory.
-	 */
-	do_each_thread(g, q) {
-		if (q->mm == mm && !same_thread_group(q, p))
-			force_sig(SIGKILL, q);
-	} while_each_thread(g, q);
+	__oom_kill_task(p, 1);
 
 	return 0;
 }
@@ -376,27 +410,14 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	struct task_struct *c;
 
-	if (printk_ratelimit()) {
-		task_lock(current);
-		printk(KERN_WARNING "%s invoked oom-killer: "
-			"gfp_mask=0x%x, order=%d, oom_adj=%d\n",
-			current->comm, gfp_mask, order,
-			current->mm ? current->mm->oom_adj : OOM_DISABLE);
-		cpuset_print_task_mems_allowed(current);
-		task_unlock(current);
-		dump_stack();
-		mem_cgroup_print_oom_info(mem, current);
-		show_mem();
-		if (sysctl_oom_dump_tasks)
-			dump_tasks(mem);
-	}
+	if (printk_ratelimit())
+		dump_header(gfp_mask, order, mem);
 
 	/*
 	 * 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 its mm is still attached.
 	 */
-	if (p->mm && (p->flags & PF_EXITING)) {
+	if (p->flags & PF_EXITING) {
 		__oom_kill_task(p, 0);
 		return 0;
 	}
@@ -526,6 +547,7 @@ retry:
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		read_unlock(&tasklist_lock);
+		dump_header(gfp_mask, order, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
 
@@ -591,8 +613,10 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 		/* Got some memory back in the last second. */
 		return;
 
-	if (sysctl_panic_on_oom == 2)
+	if (sysctl_panic_on_oom == 2) {
+		dump_header(gfp_mask, order, NULL);
 		panic("out of memory. Compulsory panic_on_oom is selected.\n");
+	}
 
 	/*
 	 * Check if there were limitations on the allocation (only relevant for
@@ -608,8 +632,10 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 		break;
 
 	case CONSTRAINT_NONE:
-		if (sysctl_panic_on_oom)
+		if (sysctl_panic_on_oom) {
+			dump_header(gfp_mask, order, NULL);
 			panic("out of memory. panic_on_oom is selected\n");
+		}
 		/* Fall-through */
 	case CONSTRAINT_CPUSET:
 		__out_of_memory(gfp_mask, order);