kernel_optimize_test/mm/oom_kill.c
Jerome Marchand eca56ff906 mm, shmem: add internal shmem resident memory accounting
Currently looking at /proc/<pid>/status or statm, there is no way to
distinguish shmem pages from pages mapped to a regular file (shmem pages
are mapped to /dev/zero), even though their implication in actual memory
use is quite different.

The internal accounting currently counts shmem pages together with
regular files.  As a preparation to extend the userspace interfaces,
this patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
shmem pages separately from MM_FILEPAGES.  The next patch will expose it
to userspace - this patch doesn't change the exported values yet, by
adding up MM_SHMEMPAGES to MM_FILEPAGES at places where MM_FILEPAGES was
used before.  The only user-visible change after this patch is the OOM
killer message that separates the reported "shmem-rss" from "file-rss".

[vbabka@suse.cz: forward-porting, tweak changelog]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 16:00:49 -08:00

772 lines
21 KiB
C

/*
* 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...
* 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()
* 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/gfp.h>
#include <linux/sched.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/memcontrol.h>
#include <linux/mempolicy.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/freezer.h>
#include <linux/ftrace.h>
#include <linux/ratelimit.h>
#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;
DEFINE_MUTEX(oom_lock);
#ifdef CONFIG_NUMA
/**
* has_intersects_mems_allowed() - check task eligiblity for kill
* @start: task struct of which task to consider
* @mask: nodemask passed to page allocator for mempolicy ooms
*
* Task eligibility is determined by whether or not a candidate task, @tsk,
* shares the same mempolicy nodes as current if it is bound by such a policy
* and whether or not it has the same set of allowed cpuset nodes.
*/
static bool has_intersects_mems_allowed(struct task_struct *start,
const nodemask_t *mask)
{
struct task_struct *tsk;
bool ret = false;
rcu_read_lock();
for_each_thread(start, tsk) {
if (mask) {
/*
* If this is a mempolicy constrained oom, tsk's
* cpuset is irrelevant. Only return true if its
* mempolicy intersects current, otherwise it may be
* needlessly killed.
*/
ret = mempolicy_nodemask_intersects(tsk, mask);
} else {
/*
* This is not a mempolicy constrained oom, so only
* check the mems of tsk's cpuset.
*/
ret = cpuset_mems_allowed_intersects(current, tsk);
}
if (ret)
break;
}
rcu_read_unlock();
return ret;
}
#else
static bool has_intersects_mems_allowed(struct task_struct *tsk,
const nodemask_t *mask)
{
return true;
}
#endif /* CONFIG_NUMA */
/*
* The process p may have detached its own ->mm while exiting or through
* use_mm(), but one or more of its subthreads may still have a valid
* pointer. Return p, or any of its subthreads with a valid ->mm, with
* task_lock() held.
*/
struct task_struct *find_lock_task_mm(struct task_struct *p)
{
struct task_struct *t;
rcu_read_lock();
for_each_thread(p, t) {
task_lock(t);
if (likely(t->mm))
goto found;
task_unlock(t);
}
t = NULL;
found:
rcu_read_unlock();
return t;
}
/*
* order == -1 means the oom kill is required by sysrq, otherwise only
* for display purposes.
*/
static inline bool is_sysrq_oom(struct oom_control *oc)
{
return oc->order == -1;
}
/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
if (is_global_init(p))
return true;
if (p->flags & PF_KTHREAD)
return true;
/* When mem_cgroup_out_of_memory() and p is not member of the group */
if (memcg && !task_in_mem_cgroup(p, memcg))
return true;
/* p may not have freeable memory in nodemask */
if (!has_intersects_mems_allowed(p, nodemask))
return true;
return false;
}
/**
* oom_badness - heuristic function to determine which candidate task to kill
* @p: task struct of which task we should calculate
* @totalpages: total present RAM allowed for page allocation
*
* 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 oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
long points;
long adj;
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
p = find_lock_task_mm(p);
if (!p)
return 0;
adj = (long)p->signal->oom_score_adj;
if (adj == OOM_SCORE_ADJ_MIN) {
task_unlock(p);
return 0;
}
/*
* The baseline for the badness score is the proportion of RAM that each
* task's rss, pagetable and swap space use.
*/
points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm);
task_unlock(p);
/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
points -= (points * 3) / 100;
/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;
points += adj;
/*
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
return points > 0 ? points : 1;
}
/*
* Determine the type of allocation constraint.
*/
#ifdef CONFIG_NUMA
static enum oom_constraint constrained_alloc(struct oom_control *oc,
unsigned long *totalpages)
{
struct zone *zone;
struct zoneref *z;
enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
bool cpuset_limited = false;
int nid;
/* Default to all available memory */
*totalpages = totalram_pages + total_swap_pages;
if (!oc->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.
* Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
*/
if (oc->gfp_mask & __GFP_THISNODE)
return CONSTRAINT_NONE;
/*
* 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 (oc->nodemask &&
!nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
*totalpages = total_swap_pages;
for_each_node_mask(nid, *oc->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, oc->zonelist,
high_zoneidx, oc->nodemask)
if (!cpuset_zone_allowed(zone, oc->gfp_mask))
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 oom_control *oc,
unsigned long *totalpages)
{
*totalpages = totalram_pages + total_swap_pages;
return CONSTRAINT_NONE;
}
#endif
enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
struct task_struct *task, unsigned long totalpages)
{
if (oom_unkillable_task(task, NULL, oc->nodemask))
return OOM_SCAN_CONTINUE;
/*
* This task already has access to memory reserves and is being killed.
* Don't allow any other task to have access to the reserves.
*/
if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
if (!is_sysrq_oom(oc))
return OOM_SCAN_ABORT;
}
if (!task->mm)
return OOM_SCAN_CONTINUE;
/*
* If task is allocating a lot of memory and has been marked to be
* killed first if it triggers an oom, then select it.
*/
if (oom_task_origin(task))
return OOM_SCAN_SELECT;
if (task_will_free_mem(task) && !is_sysrq_oom(oc))
return OOM_SCAN_ABORT;
return OOM_SCAN_OK;
}
/*
* Simple selection loop. We chose the process with the highest
* number of 'points'. Returns -1 on scan abort.
*/
static struct task_struct *select_bad_process(struct oom_control *oc,
unsigned int *ppoints, unsigned long totalpages)
{
struct task_struct *g, *p;
struct task_struct *chosen = NULL;
unsigned long chosen_points = 0;
rcu_read_lock();
for_each_process_thread(g, p) {
unsigned int points;
switch (oom_scan_process_thread(oc, p, totalpages)) {
case OOM_SCAN_SELECT:
chosen = p;
chosen_points = ULONG_MAX;
/* fall through */
case OOM_SCAN_CONTINUE:
continue;
case OOM_SCAN_ABORT:
rcu_read_unlock();
return (struct task_struct *)(-1UL);
case OOM_SCAN_OK:
break;
};
points = oom_badness(p, NULL, oc->nodemask, totalpages);
if (!points || points < chosen_points)
continue;
/* Prefer thread group leaders for display purposes */
if (points == chosen_points && thread_group_leader(chosen))
continue;
chosen = p;
chosen_points = points;
}
if (chosen)
get_task_struct(chosen);
rcu_read_unlock();
*ppoints = chosen_points * 1000 / totalpages;
return chosen;
}
/**
* dump_tasks - dump current memory state of all system tasks
* @memcg: current's memory controller, if constrained
* @nodemask: nodemask passed to page allocator for mempolicy ooms
*
* Dumps the current memory state of all eligible tasks. Tasks not in the same
* memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
* are not shown.
* State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
* swapents, oom_score_adj value, and name.
*/
static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
struct task_struct *p;
struct task_struct *task;
pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n");
rcu_read_lock();
for_each_process(p) {
if (oom_unkillable_task(p, memcg, nodemask))
continue;
task = find_lock_task_mm(p);
if (!task) {
/*
* This is a kthread or all of p's threads have already
* detached their mm's. There's no need to report
* them; they can't be oom killed anyway.
*/
continue;
}
pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n",
task->pid, from_kuid(&init_user_ns, task_uid(task)),
task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
atomic_long_read(&task->mm->nr_ptes),
mm_nr_pmds(task->mm),
get_mm_counter(task->mm, MM_SWAPENTS),
task->signal->oom_score_adj, task->comm);
task_unlock(task);
}
rcu_read_unlock();
}
static void dump_header(struct oom_control *oc, struct task_struct *p,
struct mem_cgroup *memcg)
{
pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
"oom_score_adj=%hd\n",
current->comm, oc->gfp_mask, oc->order,
current->signal->oom_score_adj);
cpuset_print_current_mems_allowed();
dump_stack();
if (memcg)
mem_cgroup_print_oom_info(memcg, p);
else
show_mem(SHOW_MEM_FILTER_NODES);
if (sysctl_oom_dump_tasks)
dump_tasks(memcg, oc->nodemask);
}
/*
* Number of OOM victims in flight
*/
static atomic_t oom_victims = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
bool oom_killer_disabled __read_mostly;
/**
* mark_oom_victim - mark the given task as OOM victim
* @tsk: task to mark
*
* Has to be called with oom_lock held and never after
* oom has been disabled already.
*/
void mark_oom_victim(struct task_struct *tsk)
{
WARN_ON(oom_killer_disabled);
/* OOM killer might race with memcg OOM */
if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
/*
* Make sure that the task is woken up from uninterruptible sleep
* if it is frozen because OOM killer wouldn't be able to free
* any memory and livelock. freezing_slow_path will tell the freezer
* that TIF_MEMDIE tasks should be ignored.
*/
__thaw_task(tsk);
atomic_inc(&oom_victims);
}
/**
* exit_oom_victim - note the exit of an OOM victim
*/
void exit_oom_victim(void)
{
clear_thread_flag(TIF_MEMDIE);
if (!atomic_dec_return(&oom_victims))
wake_up_all(&oom_victims_wait);
}
/**
* oom_killer_disable - disable OOM killer
*
* Forces all page allocations to fail rather than trigger OOM killer.
* Will block and wait until all OOM victims are killed.
*
* The function cannot be called when there are runnable user tasks because
* the userspace would see unexpected allocation failures as a result. Any
* new usage of this function should be consulted with MM people.
*
* Returns true if successful and false if the OOM killer cannot be
* disabled.
*/
bool oom_killer_disable(void)
{
/*
* Make sure to not race with an ongoing OOM killer
* and that the current is not the victim.
*/
mutex_lock(&oom_lock);
if (test_thread_flag(TIF_MEMDIE)) {
mutex_unlock(&oom_lock);
return false;
}
oom_killer_disabled = true;
mutex_unlock(&oom_lock);
wait_event(oom_victims_wait, !atomic_read(&oom_victims));
return true;
}
/**
* oom_killer_enable - enable OOM killer
*/
void oom_killer_enable(void)
{
oom_killer_disabled = false;
}
/*
* task->mm can be NULL if the task is the exited group leader. So to
* determine whether the task is using a particular mm, we examine all the
* task's threads: if one of those is using this mm then this task was also
* using it.
*/
static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
{
struct task_struct *t;
for_each_thread(p, t) {
struct mm_struct *t_mm = READ_ONCE(t->mm);
if (t_mm)
return t_mm == mm;
}
return false;
}
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* Must be called while holding a reference to p, which will be released upon
* returning.
*/
void oom_kill_process(struct oom_control *oc, struct task_struct *p,
unsigned int points, unsigned long totalpages,
struct mem_cgroup *memcg, const char *message)
{
struct task_struct *victim = p;
struct task_struct *child;
struct task_struct *t;
struct mm_struct *mm;
unsigned int victim_points = 0;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
/*
* 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
*/
task_lock(p);
if (p->mm && task_will_free_mem(p)) {
mark_oom_victim(p);
task_unlock(p);
put_task_struct(p);
return;
}
task_unlock(p);
if (__ratelimit(&oom_rs))
dump_header(oc, p, memcg);
pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
message, task_pid_nr(p), p->comm, points);
/*
* If any of p's children has a different mm and is eligible for kill,
* the one with the highest oom_badness() score is sacrificed for its
* parent. This attempts to lose the minimal amount of work done while
* still freeing memory.
*/
read_lock(&tasklist_lock);
for_each_thread(p, t) {
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
if (process_shares_mm(child, p->mm))
continue;
/*
* oom_badness() returns 0 if the thread is unkillable
*/
child_points = oom_badness(child, memcg, oc->nodemask,
totalpages);
if (child_points > victim_points) {
put_task_struct(victim);
victim = child;
victim_points = child_points;
get_task_struct(victim);
}
}
}
read_unlock(&tasklist_lock);
p = find_lock_task_mm(victim);
if (!p) {
put_task_struct(victim);
return;
} else if (victim != p) {
get_task_struct(p);
put_task_struct(victim);
victim = p;
}
/* Get a reference to safely compare mm after task_unlock(victim) */
mm = victim->mm;
atomic_inc(&mm->mm_count);
/*
* We should send SIGKILL before setting TIF_MEMDIE in order to prevent
* the OOM victim from depleting the memory reserves from the user
* space under its control.
*/
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
mark_oom_victim(victim);
pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
K(get_mm_counter(victim->mm, MM_FILEPAGES)),
K(get_mm_counter(victim->mm, MM_SHMEMPAGES)));
task_unlock(victim);
/*
* Kill all user processes sharing victim->mm in other thread groups, if
* any. They don't get access to memory reserves, though, to avoid
* depletion of all memory. This prevents mm->mmap_sem livelock when an
* oom killed thread cannot exit because it requires the semaphore and
* its contended by another thread trying to allocate memory itself.
* That thread will now get access to memory reserves since it has a
* pending fatal signal.
*/
rcu_read_lock();
for_each_process(p) {
if (!process_shares_mm(p, mm))
continue;
if (same_thread_group(p, victim))
continue;
if (unlikely(p->flags & PF_KTHREAD))
continue;
if (is_global_init(p))
continue;
if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
continue;
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
}
rcu_read_unlock();
mmdrop(mm);
put_task_struct(victim);
}
#undef K
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint,
struct mem_cgroup *memcg)
{
if (likely(!sysctl_panic_on_oom))
return;
if (sysctl_panic_on_oom != 2) {
/*
* panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel
* does not panic for cpuset, mempolicy, or memcg allocation
* failures.
*/
if (constraint != CONSTRAINT_NONE)
return;
}
/* Do not panic for oom kills triggered by sysrq */
if (is_sysrq_oom(oc))
return;
dump_header(oc, NULL, memcg);
panic("Out of memory: %s panic_on_oom is enabled\n",
sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}
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);
/**
* out_of_memory - kill the "best" process when we run out of memory
* @oc: pointer to struct oom_control
*
* 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.
*/
bool out_of_memory(struct oom_control *oc)
{
struct task_struct *p;
unsigned long totalpages;
unsigned long freed = 0;
unsigned int uninitialized_var(points);
enum oom_constraint constraint = CONSTRAINT_NONE;
if (oom_killer_disabled)
return false;
blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
if (freed > 0)
/* Got some memory back in the last second. */
return true;
/*
* If current has a pending SIGKILL or is exiting, then automatically
* select it. The goal is to allow it to allocate so that it may
* quickly exit and free its memory.
*
* But don't select if current has already released its mm and cleared
* TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur.
*/
if (current->mm &&
(fatal_signal_pending(current) || task_will_free_mem(current))) {
mark_oom_victim(current);
return true;
}
/*
* Check if there were limitations on the allocation (only relevant for
* NUMA) that may require different handling.
*/
constraint = constrained_alloc(oc, &totalpages);
if (constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
check_panic_on_oom(oc, constraint, NULL);
if (sysctl_oom_kill_allocating_task && current->mm &&
!oom_unkillable_task(current, NULL, oc->nodemask) &&
current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
get_task_struct(current);
oom_kill_process(oc, current, 0, totalpages, NULL,
"Out of memory (oom_kill_allocating_task)");
return true;
}
p = select_bad_process(oc, &points, totalpages);
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p && !is_sysrq_oom(oc)) {
dump_header(oc, NULL, NULL);
panic("Out of memory and no killable processes...\n");
}
if (p && p != (void *)-1UL) {
oom_kill_process(oc, p, points, totalpages, NULL,
"Out of memory");
/*
* Give the killed process a good chance to exit before trying
* to allocate memory again.
*/
schedule_timeout_killable(1);
}
return true;
}
/*
* The pagefault handler calls here because it is out of memory, so kill a
* memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a
* parallel oom killing is already in progress so do nothing.
*/
void pagefault_out_of_memory(void)
{
struct oom_control oc = {
.zonelist = NULL,
.nodemask = NULL,
.gfp_mask = 0,
.order = 0,
};
if (mem_cgroup_oom_synchronize(true))
return;
if (!mutex_trylock(&oom_lock))
return;
if (!out_of_memory(&oc)) {
/*
* There shouldn't be any user tasks runnable while the
* OOM killer is disabled, so the current task has to
* be a racing OOM victim for which oom_killer_disable()
* is waiting for.
*/
WARN_ON(test_thread_flag(TIF_MEMDIE));
}
mutex_unlock(&oom_lock);
}