oom_kill.c

最新最稳定的Linux内存管理模块源代码

/*
 *  linux/mm/oom_kill.c
 * 
 *  Copyright (C)  1998,2000  Rik van Riel
 *	Thanks go out to Claus Fischer for some serious inspiration and
 *	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 __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
 *  for newbie kernel hackers. It features several pointers to major
 *  kernel subsystems and hints as to where to find out what things do.
 */

#include <linux/oom.h>
#include <linux/mm.h>
#include <linux/err.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/memcontrol.h>
#include <linux/security.h>

int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks;
static DEFINE_SPINLOCK(zone_scan_lock);
/* #define DEBUG */

/**
 * badness - calculate a numeric value for how bad this task has been
 * @p: task struct of which task we should calculate
 * @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
 * to kill when we run out of memory.
 *
 * Good in this context means that:
 * 1) we lose the minimum amount of work done
 * 2) we recover a large amount of memory
 * 3) we don't kill anything innocent of eating tons of memory
 * 4) we want to kill the minimum amount of processes (one)
 * 5) we try to kill the process the user expects us to kill, this
 *    algorithm has been meticulously tuned to meet the principle
 *    of least surprise ... (be careful when you change it)
 */

unsigned long badness(struct task_struct *p, unsigned long uptime)
{
	unsigned long points, cpu_time, run_time, s;
	struct mm_struct *mm;
	struct task_struct *child;

	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 = mm->total_vm;

	/*
	 * 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 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 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_entry(child, &p->children, sibling) {
		task_lock(child);
		if (child->mm != mm && child->mm)
			points += child->mm->total_vm/2 + 1;
		task_unlock(child);
	}

	/*
	 * CPU time is in tens of seconds and run time is in thousands
         * 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);

	if (uptime >= p->start_time.tv_sec)
		run_time = (uptime - p->start_time.tv_sec) >> 10;
	else
		run_time = 0;

	s = int_sqrt(cpu_time);
	if (s)
		points /= s;
	s = int_sqrt(int_sqrt(run_time));
	if (s)
		points /= s;

	/*
	 * Niced processes are most likely less important, so double
	 * their badness points.
	 */
	if (task_nice(p) > 0)
		points *= 2;

	/*
	 * Superuser processes are usually more important, so we make it
	 * less likely that we kill those.
	 */
	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
	    has_capability_noaudit(p, CAP_SYS_RESOURCE))
		points /= 4;

	/*
	 * We don't want to kill a process with direct hardware access.
	 * Not only could that mess up the hardware, but usually users
	 * tend to only have this flag set on applications they think
	 * of as important.
	 */
	if (has_capability_noaudit(p, 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_mems_allowed_intersects(current, p))
		points /= 8;

	/*
	 * Adjust the score by oomkilladj.
	 */
	if (p->oomkilladj) {
		if (p->oomkilladj > 0) {
			if (!points)
				points = 1;
			points <<= p->oomkilladj;
		} else
			points >>= -(p->oomkilladj);
	}

#ifdef DEBUG
	printk(KERN_DEBUG "OOMkill: task %d (%s) got %lu points\n",
	p->pid, p->comm, points);
#endif
	return points;
}

/*
 * Determine the type of allocation constraint.
 */
static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
						    gfp_t gfp_mask)
{
#ifdef CONFIG_NUMA
	struct zone *zone;
	struct zoneref *z;
	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
	nodemask_t nodes = node_states[N_HIGH_MEMORY];

	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
		if (cpuset_zone_allowed_softwall(zone, gfp_mask))
			node_clear(zone_to_nid(zone), 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(unsigned long *ppoints,
						struct mem_cgroup *mem)
{
	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) {
		unsigned long points;

		/*
		 * skip kernel threads and tasks which have already released
		 * their mm.
		 */
		if (!p->mm)
			continue;
		/* skip the init task */
		if (is_global_init(p))
			continue;
		if (mem && !task_in_mem_cgroup(p, mem))
			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);

			chosen = p;
			*ppoints = ULONG_MAX;
		}

		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;
}

/**
 * dump_tasks - dump current memory state of all system tasks
 * @mem: target memory controller
 *
 * Dumps the current memory state of all system tasks, excluding kernel threads.
 * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
 * score, and name.
 *
 * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
 * shown.
 *
 * Call with tasklist_lock read-locked.
 */
static void dump_tasks(const struct mem_cgroup *mem)
{
	struct task_struct *g, *p;

	printk(KERN_INFO "[ pid ]   uid  tgid total_vm      rss cpu oom_adj "
	       "name\n");
	do_each_thread(g, p) {
		/*
		 * total_vm and rss sizes do not exist for tasks with a
		 * detached mm so there's no need to report them.
		 */
		if (!p->mm)
			continue;
		if (mem && !task_in_mem_cgroup(p, mem))
			continue;
		if (!thread_group_leader(p))
			continue;

		task_lock(p);
		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
		       p->pid, __task_cred(p)->uid, p->tgid,
		       p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p),
		       p->oomkilladj, p->comm);
		task_unlock(p);
	} while_each_thread(g, p);
}

/*
 * 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(struct task_struct *p, int verbose)
{
	if (is_global_init(p)) {
		WARN_ON(1);
		printk(KERN_WARNING "tried to kill init!\n");
		return;
	}