diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 8fe8895894d83463038b876ff078ba1c44a4c9b0..cf1295c2bb66dc59a08a1a377b87a1889ca7df01 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -33,7 +33,8 @@ Table of Contents
2 Modifying System Parameters
3 Per-Process Parameters
- 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
+ 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
+ score
3.2 /proc/<pid>/oom_score - Display current oom-killer score
3.3 /proc/<pid>/io - Display the IO accounting fields
3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
@@ -1234,42 +1235,61 @@ of the kernel.
CHAPTER 3: PER-PROCESS PARAMETERS
------------------------------------------------------------------------------
-3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
-------------------------------------------------------
-
-This file can be used to adjust the score used to select which processes
-should be killed in an out-of-memory situation. Giving it a high score will
-increase the likelihood of this process being killed by the oom-killer. Valid
-values are in the range -16 to +15, plus the special value -17, which disables
-oom-killing altogether for this process.
-
-The process to be killed in an out-of-memory situation is selected among all others
-based on its badness score. This value equals the original memory size of the process
-and is then updated according to its CPU time (utime + stime) and the
-run time (uptime - start time). The longer it runs the smaller is the score.
-Badness score is divided by the square root of the CPU time and then by
-the double square root of the run time.
-
-Swapped out tasks are killed first. Half of each child's memory size is added to
-the parent's score if they do not share the same memory. Thus forking servers
-are the prime candidates to be killed. Having only one 'hungry' child will make
-parent less preferable than the child.
-
-/proc/<pid>/oom_score shows process' current badness score.
-
-The following heuristics are then applied:
- * if the task was reniced, its score doubles
- * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
- or CAP_SYS_RAWIO) have their score divided by 4
- * if oom condition happened in one cpuset and checked process does not belong
- to it, its score is divided by 8
- * the resulting score is multiplied by two to the power of oom_adj, i.e.
- points <<= oom_adj when it is positive and
- points >>= -(oom_adj) otherwise
-
-The task with the highest badness score is then selected and its children
-are killed, process itself will be killed in an OOM situation when it does
-not have children or some of them disabled oom like described above.
+3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
+--------------------------------------------------------------------------------
+
+These file can be used to adjust the badness heuristic used to select which
+process gets killed in out of memory conditions.
+
+The badness heuristic assigns a value to each candidate task ranging from 0
+(never kill) to 1000 (always kill) to determine which process is targeted. The
+units are roughly a proportion along that range of allowed memory the process
+may allocate from based on an estimation of its current memory and swap use.
+For example, if a task is using all allowed memory, its badness score will be
+1000. If it is using half of its allowed memory, its score will be 500.
+
+There is an additional factor included in the badness score: root
+processes are given 3% extra memory over other tasks.
+
+The amount of "allowed" memory depends on the context in which the oom killer
+was called. If it is due to the memory assigned to the allocating task's cpuset
+being exhausted, the allowed memory represents the set of mems assigned to that
+cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
+memory represents the set of mempolicy nodes. If it is due to a memory
+limit (or swap limit) being reached, the allowed memory is that configured
+limit. Finally, if it is due to the entire system being out of memory, the
+allowed memory represents all allocatable resources.
+
+The value of /proc/<pid>/oom_score_adj is added to the badness score before it
+is used to determine which task to kill. Acceptable values range from -1000
+(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
+polarize the preference for oom killing either by always preferring a certain
+task or completely disabling it. The lowest possible value, -1000, is
+equivalent to disabling oom killing entirely for that task since it will always
+report a badness score of 0.
+
+Consequently, it is very simple for userspace to define the amount of memory to
+consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
+example, is roughly equivalent to allowing the remainder of tasks sharing the
+same system, cpuset, mempolicy, or memory controller resources to use at least
+50% more memory. A value of -500, on the other hand, would be roughly
+equivalent to discounting 50% of the task's allowed memory from being considered
+as scoring against the task.
+
+For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
+be used to tune the badness score. Its acceptable values range from -16
+(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
+(OOM_DISABLE) to disable oom killing entirely for that task. Its value is
+scaled linearly with /proc/<pid>/oom_score_adj.
+
+Writing to /proc/<pid>/oom_score_adj or /proc/<pid>/oom_adj will change the
+other with its scaled value.
+
+Caveat: when a parent task is selected, the oom killer will sacrifice any first
+generation children with seperate address spaces instead, if possible. This
+avoids servers and important system daemons from being killed and loses the
+minimal amount of work.
+
3.2 /proc/<pid>/oom_score - Display current oom-killer score
-------------------------------------------------------------
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5949d0ac30f2d8b6f0b3a3027a0872c4244f49c6..f923b728388ae2ee1e75d54dd127c6288f120683 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -63,6 +63,7 @@
#include <linux/namei.h>
#include <linux/mnt_namespace.h>
#include <linux/mm.h>
+#include <linux/swap.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
#include <linux/stacktrace.h>
@@ -430,12 +431,11 @@ static const struct file_operations proc_lstats_operations = {
static int proc_oom_score(struct task_struct *task, char *buffer)
{
unsigned long points = 0;
- struct timespec uptime;
- do_posix_clock_monotonic_gettime(&uptime);
read_lock(&tasklist_lock);
if (pid_alive(task))
- points = badness(task, NULL, NULL, uptime.tv_sec);
+ points = oom_badness(task, NULL, NULL,
+ totalram_pages + total_swap_pages);
read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
@@ -1038,7 +1038,15 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
}
task->signal->oom_adj = oom_adjust;
-
+ /*
+ * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+ * value is always attainable.
+ */
+ if (task->signal->oom_adj == OOM_ADJUST_MAX)
+ task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX;
+ else
+ task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
+ -OOM_DISABLE;
unlock_task_sighand(task, &flags);
put_task_struct(task);
@@ -1051,6 +1059,82 @@ static const struct file_operations proc_oom_adjust_operations = {
.llseek = generic_file_llseek,
};
+static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ char buffer[PROC_NUMBUF];
+ int oom_score_adj = OOM_SCORE_ADJ_MIN;
+ unsigned long flags;
+ size_t len;
+
+ if (!task)
+ return -ESRCH;
+ if (lock_task_sighand(task, &flags)) {
+ oom_score_adj = task->signal->oom_score_adj;
+ unlock_task_sighand(task, &flags);
+ }
+ put_task_struct(task);
+ len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF];
+ unsigned long flags;
+ long oom_score_adj;
+ int err;
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+
+ err = strict_strtol(strstrip(buffer), 0, &oom_score_adj);
+ if (err)
+ return -EINVAL;
+ if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
+ oom_score_adj > OOM_SCORE_ADJ_MAX)
+ return -EINVAL;
+
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ if (!lock_task_sighand(task, &flags)) {
+ put_task_struct(task);
+ return -ESRCH;
+ }
+ if (oom_score_adj < task->signal->oom_score_adj &&
+ !capable(CAP_SYS_RESOURCE)) {
+ unlock_task_sighand(task, &flags);
+ put_task_struct(task);
+ return -EACCES;
+ }
+
+ task->signal->oom_score_adj = oom_score_adj;
+ /*
+ * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
+ * always attainable.
+ */
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ task->signal->oom_adj = OOM_DISABLE;
+ else
+ task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
+ OOM_SCORE_ADJ_MAX;
+ unlock_task_sighand(task, &flags);
+ put_task_struct(task);
+ return count;
+}
+
+static const struct file_operations proc_oom_score_adj_operations = {
+ .read = oom_score_adj_read,
+ .write = oom_score_adj_write,
+};
+
#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
@@ -2623,6 +2707,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+ REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
@@ -2957,6 +3042,7 @@ static const struct pid_entry tid_base_stuff[] = {
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+ REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUSR, proc_sessionid_operations),
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9f1afd361583f794e28bcdcd1e6ad20a5288e3af..73564cac38c77b31786caf1303f5b44582af0ee6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -125,6 +125,8 @@ void mem_cgroup_update_file_mapped(struct page *page, int val);
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
gfp_t gfp_mask, int nid,
int zid);
+u64 mem_cgroup_get_limit(struct mem_cgroup *mem);
+
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
struct mem_cgroup;
@@ -304,6 +306,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
return 0;
}
+static inline
+u64 mem_cgroup_get_limit(struct mem_cgroup *mem)
+{
+ return 0;
+}
+
#endif /* CONFIG_CGROUP_MEM_CONT */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 40e5e3a6bc2018a2fee2bf43777ad749bce63101..73b8d7b6dd19055183206d25f336876073a7d0e7 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -1,14 +1,24 @@
#ifndef __INCLUDE_LINUX_OOM_H
#define __INCLUDE_LINUX_OOM_H
-/* /proc/<pid>/oom_adj set to -17 protects from the oom-killer */
+/*
+ * /proc/<pid>/oom_adj set to -17 protects from the oom-killer
+ */
#define OOM_DISABLE (-17)
/* inclusive */
#define OOM_ADJUST_MIN (-16)
#define OOM_ADJUST_MAX 15
+/*
+ * /proc/<pid>/oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for
+ * pid.
+ */
+#define OOM_SCORE_ADJ_MIN (-1000)
+#define OOM_SCORE_ADJ_MAX 1000
+
#ifdef __KERNEL__
+#include <linux/sched.h>
#include <linux/types.h>
#include <linux/nodemask.h>
@@ -27,6 +37,8 @@ enum oom_constraint {
CONSTRAINT_MEMCG,
};
+extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
+ const nodemask_t *nodemask, unsigned long totalpages);
extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9591907c4f79262e82089cfa5c1f1cae502d56e0..ce160d68f5e706fb3c157940e68ccac3627dccef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -621,7 +621,8 @@ struct signal_struct {
struct tty_audit_buf *tty_audit_buf;
#endif
- int oom_adj; /* OOM kill score adjustment (bit shift) */
+ int oom_adj; /* OOM kill score adjustment (bit shift) */
+ int oom_score_adj; /* OOM kill score adjustment */
};
/* Context switch must be unlocked if interrupts are to be enabled */
diff --git a/kernel/fork.c b/kernel/fork.c
index a82a65cef741935adc51082640f63c9a5049b5ea..98b450876f93878b437bbbc6efe6abd1c4028b29 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -899,6 +899,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
tty_audit_fork(sig);
sig->oom_adj = current->signal->oom_adj;
+ sig->oom_score_adj = current->signal->oom_score_adj;
return 0;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 31abd1c2c0c5b2f3f9f1b5cb197a948cddb76596..de54ea0094a1be4e512b0ac602e28d2a3ac4a695 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1126,6 +1126,24 @@ static int mem_cgroup_count_children(struct mem_cgroup *mem)
return num;
}
+/*
+ * 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
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 0a4ca8a0234b5da6696235dd79c15ea1ed046a8f..d3def05a33d99f6699e6dd6ea9472e6e7da54443 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 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
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);