X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Foom_kill.c;h=e9654b7ad11bf1b77da5ad2c683e20cb0b006c4c;hb=refs%2Fheads%2Fvserver;hp=45d790268c0eaeed503a352a84712bf1c5ba9bf5;hpb=f7f1b0f1e2fbadeab12d24236000e778aa9b1ead;p=linux-2.6.git

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 45d790268..e9654b7ad 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -6,8 +6,8 @@
  *	for goading me into coding this file...
  *
  *  The routines in this file are used to kill a process when
- *  we're seriously out of memory. This gets called from kswapd()
- *  in linux/mm/vmscan.c when we really run out of memory.
+ *  we're seriously out of memory. This gets called from __alloc_pages()
+ *  in mm/page_alloc.c when we really run out of memory.
  *
  *  Since we won't call these routines often (on a well-configured
  *  machine) this file will double as a 'coding guide' and a signpost
@@ -15,18 +15,24 @@
  *  kernel subsystems and hints as to where to find out what things do.
  */
 
+#include <linux/oom.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
+#include <linux/cpuset.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/vs_memory.h>
 
+int sysctl_panic_on_oom;
 /* #define DEBUG */
 
 /**
- * oom_badness - calculate a numeric value for how bad this task has been
+ * badness - calculate a numeric value for how bad this task has been
  * @p: task struct of which task we should calculate
- * @p: current uptime in seconds
+ * @uptime: current uptime in seconds
  *
  * The formula used is relatively simple and documented inline in the
  * function. The main rationale is that we want to select a good task
@@ -45,28 +51,51 @@
 unsigned long badness(struct task_struct *p, unsigned long uptime)
 {
 	unsigned long points, cpu_time, run_time, s;
-	struct list_head *tsk;
+	struct mm_struct *mm;
+	struct task_struct *child;
 
-	if (!p->mm)
+	task_lock(p);
+	mm = p->mm;
+	if (!mm) {
+		task_unlock(p);
 		return 0;
+	}
 
 	/*
 	 * The memory size of the process is the basis for the badness.
 	 */
-	points = p->mm->total_vm;
-	/* FIXME add vserver badness ;) */
+	points = mm->total_vm;
+
+	/*
+	 * add points for context badness
+	 */
+
+	points += vx_badness(p, mm);
+
+	/*
+	 * After this unlock we can no longer dereference local variable `mm'
+	 */
+	task_unlock(p);
+
+	/*
+	 * swapoff can easily use up all memory, so kill those first.
+	 */
+	if (p->flags & PF_SWAPOFF)
+		return ULONG_MAX;
 
 	/*
 	 * Processes which fork a lot of child processes are likely
-	 * a good choice. We add the vmsize of the childs if they
+	 * a good choice. We add half the vmsize of the children if they
 	 * have an own mm. This prevents forking servers to flood the
-	 * machine with an endless amount of childs
+	 * machine with an endless amount of children. In case a single
+	 * child is eating the vast majority of memory, adding only half
+	 * to the parents will make the child our kill candidate of choice.
 	 */
-	list_for_each(tsk, &p->children) {
-		struct task_struct *chld;
-		chld = list_entry(tsk, struct task_struct, sibling);
-		if (chld->mm != p->mm && chld->mm)
-			points += chld->mm->total_vm;
+	list_for_each_entry(child, &p->children, sibling) {
+		task_lock(child);
+		if (child->mm != mm && child->mm)
+			points += child->mm->total_vm/2 + 1;
+		task_unlock(child);
 	}
 
 	/*
@@ -113,6 +142,14 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
 		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.
 	 */
@@ -124,73 +161,140 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	}
 
 #ifdef DEBUG
-	printk(KERN_DEBUG "OOMkill: task %d (%s) got %d points\n",
-	p->pid, p->comm, points);
+	printk(KERN_DEBUG "OOMkill: task %d:#%u (%s) got %d points\n",
+		p->pid, p->xid, p->comm, points);
 #endif
 	return points;
 }
 
+/*
+ * Types of limitations to the nodes from which allocations may occur
+ */
+#define CONSTRAINT_NONE 1
+#define CONSTRAINT_MEMORY_POLICY 2
+#define CONSTRAINT_CPUSET 3
+
+/*
+ * Determine the type of allocation constraint.
+ */
+static inline int constrained_alloc(struct zonelist *zonelist, gfp_t gfp_mask)
+{
+#ifdef CONFIG_NUMA
+	struct zone **z;
+	nodemask_t nodes;
+	int node;
+
+	nodes_clear(nodes);
+	/* node has memory ? */
+	for_each_online_node(node)
+		if (NODE_DATA(node)->node_present_pages)
+			node_set(node, nodes);
+
+	for (z = zonelist->zones; *z; z++)
+		if (cpuset_zone_allowed_softwall(*z, gfp_mask))
+			node_clear(zone_to_nid(*z), nodes);
+		else
+			return CONSTRAINT_CPUSET;
+
+	if (!nodes_empty(nodes))
+		return CONSTRAINT_MEMORY_POLICY;
+#endif
+
+	return CONSTRAINT_NONE;
+}
+
 /*
  * Simple selection loop. We chose the process with the highest
  * number of 'points'. We expect the caller will lock the tasklist.
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
-static struct task_struct * select_bad_process(void)
+static struct task_struct *select_bad_process(unsigned long *ppoints)
 {
-	unsigned long maxpoints = 0;
 	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
 	struct timespec uptime;
+	*ppoints = 0;
 
 	do_posix_clock_monotonic_gettime(&uptime);
-	do_each_thread(g, p)
-		/* skip the init task with pid == 1 */
-		if (p->pid > 1 && p->oomkilladj != OOM_DISABLE) {
-			unsigned long points;
-
-			/*
-			 * This is in the process of releasing memory so wait it
-			 * to finish before killing some other task by mistake.
-			 */
-			if ((unlikely(test_tsk_thread_flag(p, TIF_MEMDIE)) || (p->flags & PF_EXITING)) &&
-			    !(p->flags & PF_DEAD))
+	do_each_thread(g, p) {
+		unsigned long points;
+
+		/*
+		 * skip kernel threads and tasks which have already released
+		 * their mm.
+		 */
+		if (!p->mm)
+			continue;
+		/* skip the init task */
+		if (is_init(p))
+			continue;
+
+		/*
+		 * This task already has access to memory reserves and is
+		 * being killed. Don't allow any other task access to the
+		 * memory reserve.
+		 *
+		 * Note: this may have a chance of deadlock if it gets
+		 * blocked waiting for another task which itself is waiting
+		 * for memory. Is there a better alternative?
+		 */
+		if (test_tsk_thread_flag(p, TIF_MEMDIE))
+			return ERR_PTR(-1UL);
+
+		/*
+		 * 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 easy OOM deadlock.
+		 */
+		if (p->flags & PF_EXITING) {
+			if (p != current)
 				return ERR_PTR(-1UL);
-			if (p->flags & PF_SWAPOFF)
-				return p;
-
-			points = badness(p, uptime.tv_sec);
-			if (points > maxpoints || !chosen) {
-				chosen = p;
-				maxpoints = points;
-			}
+
+			chosen = p;
+			*ppoints = ULONG_MAX;
 		}
-	while_each_thread(g, p);
+
+		if (p->oomkilladj == OOM_DISABLE)
+			continue;
+
+		points = badness(p, uptime.tv_sec);
+		if (points > *ppoints || !chosen) {
+			chosen = p;
+			*ppoints = points;
+		}
+	} while_each_thread(g, p);
+
 	return chosen;
 }
 
 /**
- * We must be careful though to never send SIGKILL a process with
- * CAP_SYS_RAW_IO set, send SIGTERM instead (but it's unlikely that
- * we select a process with CAP_SYS_RAW_IO set).
+ * 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
+ * set.
  */
-static void __oom_kill_task(task_t *p)
+static void __oom_kill_task(struct task_struct *p, int verbose)
 {
-	if (p->pid == 1) {
+	if (is_init(p)) {
 		WARN_ON(1);
 		printk(KERN_WARNING "tried to kill init!\n");
 		return;
 	}
 
-	task_lock(p);
-	if (!p->mm || p->mm == &init_mm) {
+	if (!p->mm) {
 		WARN_ON(1);
 		printk(KERN_WARNING "tried to kill an mm-less task!\n");
-		task_unlock(p);
 		return;
 	}
-	task_unlock(p);
-	printk(KERN_ERR "Out of Memory: Killed process %d (%s).\n", p->pid, p->comm);
+
+	if (verbose)
+		printk(KERN_ERR "Killed process %d:#%u (%s)\n",
+				p->pid, p->xid, p->comm);
 
 	/*
 	 * We give our sacrificial lamb high priority and access to
@@ -203,91 +307,170 @@ static void __oom_kill_task(task_t *p)
 	force_sig(SIGKILL, p);
 }
 
-static struct mm_struct *oom_kill_task(task_t *p)
+static int oom_kill_task(struct task_struct *p)
 {
-	struct mm_struct *mm = get_task_mm(p);
-	task_t * g, * q;
-
-	if (!mm)
-		return NULL;
-	if (mm == &init_mm) {
-		mmput(mm);
-		return NULL;
-	}
+	struct mm_struct *mm;
+	struct task_struct *g, *q;
+
+	mm = p->mm;
+
+	/* 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 (mm == NULL)
+		return 1;
+
+	/*
+	 * Don't kill the process if any threads are set to OOM_DISABLE
+	 */
+	do_each_thread(g, q) {
+		if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
+			return 1;
+	} while_each_thread(g, q);
+
+	__oom_kill_task(p, 1);
 
-	__oom_kill_task(p);
 	/*
 	 * kill all processes that share the ->mm (i.e. all threads),
-	 * but are in a different thread group
+	 * 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)
+	do_each_thread(g, q) {
 		if (q->mm == mm && q->tgid != p->tgid)
-			__oom_kill_task(q);
-	while_each_thread(g, q);
+			force_sig(SIGKILL, q);
+	} while_each_thread(g, q);
 
-	return mm;
+	return 0;
 }
 
-static struct mm_struct *oom_kill_process(struct task_struct *p)
+static int oom_kill_process(struct task_struct *p, unsigned long points,
+		const char *message)
 {
- 	struct mm_struct *mm;
 	struct task_struct *c;
 	struct list_head *tsk;
 
+	/*
+	 * 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, 0);
+		return 0;
+	}
+
+	printk(KERN_ERR "%s: kill process %d:#%u (%s) score %li or a child\n",
+				message, p->pid, p->xid, p->comm, points);
+
 	/* Try to kill a child first */
 	list_for_each(tsk, &p->children) {
 		c = list_entry(tsk, struct task_struct, sibling);
 		if (c->mm == p->mm)
 			continue;
-		mm = oom_kill_task(c);
-		if (mm)
-			return mm;
+		if (!oom_kill_task(c))
+			return 0;
 	}
 	return oom_kill_task(p);
 }
 
+static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
+
+int register_oom_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_oom_notifier);
+
+int unregister_oom_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_oom_notifier);
+
 /**
- * oom_kill - kill the "best" process when we run out of memory
+ * out_of_memory - kill the "best" process when we run out of memory
  *
  * If we run out of memory, we have the choice between either
  * killing a random task (bad), letting the system crash (worse)
  * OR try to be smart about which process to kill. Note that we
  * don't have to be perfect here, we just have to be good.
  */
-void out_of_memory(unsigned int __nocast gfp_mask)
+void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 {
-	struct mm_struct *mm = NULL;
-	task_t * p;
+	struct task_struct *p;
+	unsigned long points = 0;
+	unsigned long freed = 0;
 
+	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
+	if (freed > 0)
+		/* Got some memory back in the last second. */
+		return;
+
+	if (printk_ratelimit()) {
+		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();
+	}
+
+	cpuset_lock();
 	read_lock(&tasklist_lock);
+
+	/*
+	 * Check if there were limitations on the allocation (only relevant for
+	 * NUMA) that may require different handling.
+	 */
+	switch (constrained_alloc(zonelist, gfp_mask)) {
+	case CONSTRAINT_MEMORY_POLICY:
+		oom_kill_process(current, points,
+				"No available memory (MPOL_BIND)");
+		break;
+
+	case CONSTRAINT_CPUSET:
+		oom_kill_process(current, points,
+				"No available memory in cpuset");
+		break;
+
+	case CONSTRAINT_NONE:
+		if (sysctl_panic_on_oom)
+			panic("out of memory. panic_on_oom is selected\n");
 retry:
-	p = select_bad_process();
+		/*
+		 * Rambo mode: Shoot down a process and hope it solves whatever
+		 * issues we may have.
+		 */
+		p = select_bad_process(&points);
+
+		if (PTR_ERR(p) == -1UL)
+			goto out;
+
+		/* Found nothing?!?! Either we hang forever, or we panic. */
+		if (!p) {
+			read_unlock(&tasklist_lock);
+			cpuset_unlock();
+			panic("Out of memory and no killable processes...\n");
+		}
 
-	if (PTR_ERR(p) == -1UL)
-		goto out;
+		if (oom_kill_process(p, points, "Out of memory"))
+			goto retry;
 
-	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!p) {
-		read_unlock(&tasklist_lock);
-		show_free_areas();
-		panic("Out of memory and no killable processes...\n");
+		break;
 	}
 
-	printk("oom-killer: gfp_mask=0x%x\n", gfp_mask);
-	show_free_areas();
-	mm = oom_kill_process(p);
-	if (!mm)
-		goto retry;
-
- out:
+out:
 	read_unlock(&tasklist_lock);
-	if (mm)
-		mmput(mm);
+	cpuset_unlock();
 
 	/*
 	 * Give "p" a good chance of killing itself before we
-	 * retry to allocate memory.
+	 * retry to allocate memory unless "p" is current
 	 */
-	__set_current_state(TASK_INTERRUPTIBLE);
-	schedule_timeout(1);
+	if (!test_thread_flag(TIF_MEMDIE))
+		schedule_timeout_uninterruptible(1);
 }