2 files changed, 129 insertions, 148 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 31abd1c2c0c5..de54ea0094a1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,6 +1127,24 @@ static int mem_cgroup_count_children(struct mem_cgroup *mem)
 }
 
 /*
+ * Return the memory (and swap, if configured) limit for a memcg.
+ */
+u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+{
+        u64 limit;
+        u64 memsw;
+
+        limit = res_counter_read_u64(&memcg->res, RES_LIMIT) +
+                        total_swap_pages;
+        memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+        /*
+         * If memsw is finite and limits the amount of swap space available
+         * to this memcg, return that limit.
+         */
+        return min(limit, memsw);
+}
+
+/*
  * Visit the first child (need not be the first child as per the ordering
  * of the cgroup list, since we track last_scanned_child) of @mem and use
  * that to reclaim free pages from.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0a4ca8a0234b..d3def05a33d9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -4,6 +4,8 @@
  *  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...
+ *  Copyright (C)  2010  Google, Inc.
+ *      Rewritten by David Rientjes
  *
  *  The routines in this file are used to kill a process when
  *  we're seriously out of memory. This gets called from __alloc_pages()
@@ -34,7 +36,6 @@ int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
-/* #define DEBUG */
 
 #ifdef CONFIG_NUMA
 /**
@@ -140,137 +141,76 @@ static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem,
 }
 
 /**
- * badness - calculate a numeric value for how bad this task has been
+ * oom_badness - heuristic function to determine which candidate task to kill
  * @p: task struct of which task we should calculate
- * @uptime: current uptime in seconds
+ * @totalpages: total present RAM allowed for page allocation
  *
- * 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)
+ * The heuristic for determining which task to kill is made to be as simple and
+ * predictable as possible.  The goal is to return the highest value for the
+ * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned long badness(struct task_struct *p, struct mem_cgroup *mem,
-                      const nodemask_t *nodemask, unsigned long uptime)
+unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
+                      const nodemask_t *nodemask, unsigned long totalpages)
 {
-        unsigned long points, cpu_time, run_time;
-        struct task_struct *child;
-        struct task_struct *c, *t;
-        int oom_adj = p->signal->oom_adj;
-        struct task_cputime task_time;
-        unsigned long utime;
-        unsigned long stime;
+        int points;
 
         if (oom_unkillable_task(p, mem, nodemask))
                 return 0;
-        if (oom_adj == OOM_DISABLE)
-                return 0;
 
         p = find_lock_task_mm(p);
         if (!p)
                 return 0;
 
         /*
-         * The memory size of the process is the basis for the badness.
-         */
-        points = p->mm->total_vm;
-        task_unlock(p);
-
-        /*
-         * swapoff can easily use up all memory, so kill those first.
-         */
-        if (p->flags & PF_OOM_ORIGIN)
-                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.
+         * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't
+         * need to be executed for something that cannot be killed.
          */
-        t = p;
-        do {
-                list_for_each_entry(c, &t->children, sibling) {
-                        child = find_lock_task_mm(c);
-                        if (child) {
-                                if (child->mm != p->mm)
-                                        points += child->mm->total_vm/2 + 1;
-                                task_unlock(child);
-                        }
-                }
-        } while_each_thread(p, t);
+        if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+                task_unlock(p);
+                return 0;
+        }
 
         /*
-         * 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.
+         * When the PF_OOM_ORIGIN bit is set, it indicates the task should have
+         * priority for oom killing.
          */
-        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;
-        else
-                run_time = 0;
-
-        if (cpu_time)
-                points /= int_sqrt(cpu_time);
-        if (run_time)
-                points /= int_sqrt(int_sqrt(run_time));
+        if (p->flags & PF_OOM_ORIGIN) {
+                task_unlock(p);
+                return 1000;
+        }
 
         /*
-         * Niced processes are most likely less important, so double
-         * their badness points.
+         * The memory controller may have a limit of 0 bytes, so avoid a divide
+         * by zero, if necessary.
          */
-        if (task_nice(p) > 0)
-                points *= 2;
+        if (!totalpages)
+                totalpages = 1;
 
         /*
-         * Superuser processes are usually more important, so we make it
-         * less likely that we kill those.
+         * The baseline for the badness score is the proportion of RAM that each
+         * task's rss and swap space use.
          */
-        if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
-            has_capability_noaudit(p, CAP_SYS_RESOURCE))
-                points /= 4;
+        points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 /
+                        totalpages;
+        task_unlock(p);
 
         /*
-         * 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.
+         * Root processes get 3% bonus, just like the __vm_enough_memory()
+         * implementation used by LSMs.
          */
-        if (has_capability_noaudit(p, CAP_SYS_RAWIO))
-                points /= 4;
+        if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+                points -= 30;
 
         /*
-         * Adjust the score by oom_adj.
+         * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
+         * either completely disable oom killing or always prefer a certain
+         * task.
          */
-        if (oom_adj) {
-                if (oom_adj > 0) {
-                        if (!points)
-                                points = 1;
-                        points <<= oom_adj;
-                } else
-                        points >>= -(oom_adj);
-        }
+        points += p->signal->oom_score_adj;
 
-#ifdef DEBUG
-        printk(KERN_DEBUG "OOMkill: task %d (%s) got %lu points\n",
-        p->pid, p->comm, points);
-#endif
-        return points;
+        if (points < 0)
+                return 0;
+        return (points < 1000) ? points : 1000;
 }
 
 /*
@@ -278,12 +218,20 @@ unsigned long badness(struct task_struct *p, struct mem_cgroup *mem,
  */
 #ifdef CONFIG_NUMA
 static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
-                                    gfp_t gfp_mask, nodemask_t *nodemask)
+                                gfp_t gfp_mask, nodemask_t *nodemask,
+                                unsigned long *totalpages)
 {
         struct zone *zone;
         struct zoneref *z;
         enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+        bool cpuset_limited = false;
+        int nid;
 
+        /* Default to all available memory */
+        *totalpages = totalram_pages + total_swap_pages;
+
+        if (!zonelist)
+                return CONSTRAINT_NONE;
         /*
          * Reach here only when __GFP_NOFAIL is used. So, we should avoid
          * to kill current.We have to random task kill in this case.
@@ -293,26 +241,37 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
                 return CONSTRAINT_NONE;
 
         /*
-         * The nodemask here is a nodemask passed to alloc_pages(). Now,
-         * cpuset doesn't use this nodemask for its hardwall/softwall/hierarchy
-         * feature. mempolicy is an only user of nodemask here.
-         * check mempolicy's nodemask contains all N_HIGH_MEMORY
+         * This is not a __GFP_THISNODE allocation, so a truncated nodemask in
+         * the page allocator means a mempolicy is in effect.  Cpuset policy
+         * is enforced in get_page_from_freelist().
          */
-        if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask))
+        if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask)) {
+                *totalpages = total_swap_pages;
+                for_each_node_mask(nid, *nodemask)
+                        *totalpages += node_spanned_pages(nid);
                 return CONSTRAINT_MEMORY_POLICY;
+        }
 
         /* Check this allocation failure is caused by cpuset's wall function */
         for_each_zone_zonelist_nodemask(zone, z, zonelist,
                         high_zoneidx, nodemask)
                 if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
-                        return CONSTRAINT_CPUSET;
+                        cpuset_limited = true;
 
+        if (cpuset_limited) {
+                *totalpages = total_swap_pages;
+                for_each_node_mask(nid, cpuset_current_mems_allowed)
+                        *totalpages += node_spanned_pages(nid);
+                return CONSTRAINT_CPUSET;
+        }
         return CONSTRAINT_NONE;
 }
 #else
 static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
-                                gfp_t gfp_mask, nodemask_t *nodemask)
+                                gfp_t gfp_mask, nodemask_t *nodemask,
+                                unsigned long *totalpages)
 {
+        *totalpages = totalram_pages + total_swap_pages;
         return CONSTRAINT_NONE;
 }
 #endif
@@ -323,17 +282,16 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
  *
  * (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, const nodemask_t *nodemask)
+static struct task_struct *select_bad_process(unsigned int *ppoints,
+                unsigned long totalpages, struct mem_cgroup *mem,
+                const nodemask_t *nodemask)
 {
         struct task_struct *p;
         struct task_struct *chosen = NULL;
-        struct timespec uptime;
         *ppoints = 0;
 
-        do_posix_clock_monotonic_gettime(&uptime);
         for_each_process(p) {
-                unsigned long points;
+                unsigned int points;
 
                 if (oom_unkillable_task(p, mem, nodemask))
                         continue;
@@ -365,11 +323,11 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
                                 return ERR_PTR(-1UL);
 
                         chosen = p;
-                        *ppoints = ULONG_MAX;
+                        *ppoints = 1000;
                 }
 
-                points = badness(p, mem, nodemask, uptime.tv_sec);
-                if (points > *ppoints || !chosen) {
+                points = oom_badness(p, mem, nodemask, totalpages);
+                if (points > *ppoints) {
                         chosen = p;
                         *ppoints = points;
                 }
@@ -384,7 +342,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
  *
  * 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.
+ * value, oom_score_adj value, and name.
  *
  * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
  * shown.
@@ -396,8 +354,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
         struct task_struct *p;
         struct task_struct *task;
 
-        printk(KERN_INFO "[ pid ]   uid  tgid total_vm      rss cpu oom_adj "
-               "name\n");
+        pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
         for_each_process(p) {
                 if (p->flags & PF_KTHREAD)
                         continue;
@@ -414,10 +371,11 @@ static void dump_tasks(const struct mem_cgroup *mem)
                         continue;
                 }
 
-                printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3u     %3d %s\n",
-                       task->pid, __task_cred(task)->uid, task->tgid,
-                       task->mm->total_vm, get_mm_rss(task->mm),
-                       task_cpu(task), task->signal->oom_adj, task->comm);
+                pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
+                        task->pid, __task_cred(task)->uid, task->tgid,
+                        task->mm->total_vm, get_mm_rss(task->mm),
+                        task_cpu(task), task->signal->oom_adj,
+                        task->signal->oom_score_adj, task->comm);
                 task_unlock(task);
         }
 }
@@ -427,8 +385,9 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 {
         task_lock(current);
         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);
+                "oom_adj=%d, oom_score_adj=%d\n",
+                current->comm, gfp_mask, order, current->signal->oom_adj,
+                current->signal->oom_score_adj);
         cpuset_print_task_mems_allowed(current);
         task_unlock(current);
         dump_stack();
@@ -468,14 +427,14 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
 #undef K
 
 static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-                            unsigned long points, struct mem_cgroup *mem,
-                            nodemask_t *nodemask, const char *message)
+                            unsigned int points, unsigned long totalpages,
+                            struct mem_cgroup *mem, nodemask_t *nodemask,
+                            const char *message)
 {
         struct task_struct *victim = p;
         struct task_struct *child;
         struct task_struct *t = p;
-        unsigned long victim_points = 0;
-        struct timespec uptime;
+        unsigned int victim_points = 0;
 
         if (printk_ratelimit())
                 dump_header(p, gfp_mask, order, mem);
@@ -491,7 +450,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
         }
 
         task_lock(p);
-        pr_err("%s: Kill process %d (%s) score %lu or sacrifice child\n",
+        pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n",
                 message, task_pid_nr(p), p->comm, points);
         task_unlock(p);
 
@@ -501,14 +460,15 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
          * parent.  This attempts to lose the minimal amount of work done while
          * still freeing memory.
          */
-        do_posix_clock_monotonic_gettime(&uptime);
         do {
                 list_for_each_entry(child, &t->children, sibling) {
-                        unsigned long child_points;
+                        unsigned int child_points;
 
-                        /* badness() returns 0 if the thread is unkillable */
-                        child_points = badness(child, mem, nodemask,
-                                               uptime.tv_sec);
+                        /*
+                         * oom_badness() returns 0 if the thread is unkillable
+                         */
+                        child_points = oom_badness(child, mem, nodemask,
+                                                                totalpages);
                         if (child_points > victim_points) {
                                 victim = child;
                                 victim_points = child_points;
@@ -546,17 +506,19 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
 {
-        unsigned long points = 0;
+        unsigned long limit;
+        unsigned int points = 0;
         struct task_struct *p;
 
         check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0);
+        limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
         read_lock(&tasklist_lock);
 retry:
-        p = select_bad_process(&points, mem, NULL);
+        p = select_bad_process(&points, limit, mem, NULL);
         if (!p || PTR_ERR(p) == -1UL)
                 goto out;
 
-        if (oom_kill_process(p, gfp_mask, 0, points, mem, NULL,
+        if (oom_kill_process(p, gfp_mask, 0, points, limit, mem, NULL,
                                 "Memory cgroup out of memory"))
                 goto retry;
 out:
@@ -681,8 +643,9 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
                 int order, nodemask_t *nodemask)
 {
         struct task_struct *p;
+        unsigned long totalpages;
         unsigned long freed = 0;
-        unsigned long points;
+        unsigned int points;
         enum oom_constraint constraint = CONSTRAINT_NONE;
 
         blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
@@ -705,8 +668,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
          * Check if there were limitations on the allocation (only relevant for
          * NUMA) that may require different handling.
          */
-        if (zonelist)
-                constraint = constrained_alloc(zonelist, gfp_mask, nodemask);
+        constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
+                                                &totalpages);
         check_panic_on_oom(constraint, gfp_mask, order);
 
         read_lock(&tasklist_lock);
@@ -718,14 +681,14 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
                  * non-zero, current could not be killed so we must fallback to
                  * the tasklist scan.
                  */
-                if (!oom_kill_process(current, gfp_mask, order, 0, NULL,
-                                nodemask,
+                if (!oom_kill_process(current, gfp_mask, order, 0, totalpages,
+                                NULL, nodemask,
                                 "Out of memory (oom_kill_allocating_task)"))
                         return;
         }
 
 retry:
-        p = select_bad_process(&points, NULL,
+        p = select_bad_process(&points, totalpages, NULL,
                         constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
                                                                  NULL);
         if (PTR_ERR(p) == -1UL)
@@ -738,8 +701,8 @@ retry:
                 panic("Out of memory and no killable processes...\n");
         }
 
-        if (oom_kill_process(p, gfp_mask, order, points, NULL, nodemask,
-                             "Out of memory"))
+        if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
+                                nodemask, "Out of memory"))
                 goto retry;
         read_unlock(&tasklist_lock);