From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/oom_kill.c | 502 +++++++++++++++++++++++++++++++++++--------------------
1 files changed, 317 insertions(+), 185 deletions(-)
diff --git a/kernel/mm/oom_kill.c b/kernel/mm/oom_kill.c
index 3f5a60a..e722c68 100644
--- a/kernel/mm/oom_kill.c
+++ b/kernel/mm/oom_kill.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/oom_kill.c
*
@@ -25,7 +26,9 @@
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
+#include <linux/sched/debug.h>
#include <linux/swap.h>
+#include <linux/syscalls.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
@@ -49,6 +52,9 @@
#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>
+#undef CREATE_TRACE_POINTS
+#include <trace/hooks/mm.h>
+
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;
@@ -65,21 +71,33 @@
/* Serializes oom_score_adj and oom_score_adj_min updates */
DEFINE_MUTEX(oom_adj_mutex);
+static inline bool is_memcg_oom(struct oom_control *oc)
+{
+ return oc->memcg != NULL;
+}
+
#ifdef CONFIG_NUMA
/**
- * has_intersects_mems_allowed() - check task eligiblity for kill
+ * oom_cpuset_eligible() - check task eligiblity for kill
* @start: task struct of which task to consider
- * @mask: nodemask passed to page allocator for mempolicy ooms
+ * @oc: pointer to struct oom_control
*
* 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.
+ *
+ * This function is assuming oom-killer context and 'current' has triggered
+ * the oom-killer.
*/
-static bool has_intersects_mems_allowed(struct task_struct *start,
- const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *start,
+ struct oom_control *oc)
{
struct task_struct *tsk;
bool ret = false;
+ const nodemask_t *mask = oc->nodemask;
+
+ if (is_memcg_oom(oc))
+ return true;
rcu_read_lock();
for_each_thread(start, tsk) {
@@ -106,8 +124,7 @@
return ret;
}
#else
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
- const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc)
{
return true;
}
@@ -115,7 +132,7 @@
/*
* 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
+ * kthread_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.
*/
@@ -147,28 +164,13 @@
return oc->order == -1;
}
-static inline bool is_memcg_oom(struct oom_control *oc)
-{
- return oc->memcg != NULL;
-}
-
/* 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)
+static bool oom_unkillable_task(struct task_struct *p)
{
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;
}
@@ -188,32 +190,29 @@
global_node_page_state(NR_ISOLATED_FILE) +
global_node_page_state(NR_UNEVICTABLE);
- return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
+ return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
}
/**
* 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
- * @memcg: task's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
*
* 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 oom_badness(struct task_struct *p, unsigned long totalpages)
{
long points;
long adj;
- if (oom_unkillable_task(p, memcg, nodemask))
- return 0;
+ if (oom_unkillable_task(p))
+ return LONG_MIN;
p = find_lock_task_mm(p);
if (!p)
- return 0;
+ return LONG_MIN;
/*
* Do not even consider tasks which are explicitly marked oom
@@ -225,7 +224,7 @@
test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
in_vfork(p)) {
task_unlock(p);
- return 0;
+ return LONG_MIN;
}
/*
@@ -240,18 +239,14 @@
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;
+ return points;
}
-enum oom_constraint {
- CONSTRAINT_NONE,
- CONSTRAINT_CPUSET,
- CONSTRAINT_MEMORY_POLICY,
- CONSTRAINT_MEMCG,
+static const char * const oom_constraint_text[] = {
+ [CONSTRAINT_NONE] = "CONSTRAINT_NONE",
+ [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET",
+ [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY",
+ [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG",
};
/*
@@ -261,7 +256,7 @@
{
struct zone *zone;
struct zoneref *z;
- enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
+ enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask);
bool cpuset_limited = false;
int nid;
@@ -271,7 +266,7 @@
}
/* Default to all available memory */
- oc->totalpages = totalram_pages + total_swap_pages;
+ oc->totalpages = totalram_pages() + total_swap_pages;
if (!IS_ENABLED(CONFIG_NUMA))
return CONSTRAINT_NONE;
@@ -295,20 +290,20 @@
!nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
oc->totalpages = total_swap_pages;
for_each_node_mask(nid, *oc->nodemask)
- oc->totalpages += node_spanned_pages(nid);
+ oc->totalpages += node_present_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)
+ highest_zoneidx, oc->nodemask)
if (!cpuset_zone_allowed(zone, oc->gfp_mask))
cpuset_limited = true;
if (cpuset_limited) {
oc->totalpages = total_swap_pages;
for_each_node_mask(nid, cpuset_current_mems_allowed)
- oc->totalpages += node_spanned_pages(nid);
+ oc->totalpages += node_present_pages(nid);
return CONSTRAINT_CPUSET;
}
return CONSTRAINT_NONE;
@@ -317,9 +312,13 @@
static int oom_evaluate_task(struct task_struct *task, void *arg)
{
struct oom_control *oc = arg;
- unsigned long points;
+ long points;
- if (oom_unkillable_task(task, NULL, oc->nodemask))
+ if (oom_unkillable_task(task))
+ goto next;
+
+ /* p may not have freeable memory in nodemask */
+ if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc))
goto next;
/*
@@ -339,17 +338,31 @@
* killed first if it triggers an oom, then select it.
*/
if (oom_task_origin(task)) {
- points = ULONG_MAX;
+ points = LONG_MAX;
goto select;
}
- points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
- if (!points || points < oc->chosen_points)
+ points = oom_badness(task, oc->totalpages);
+
+ if (points == LONG_MIN)
goto next;
- /* Prefer thread group leaders for display purposes */
- if (points == oc->chosen_points && thread_group_leader(oc->chosen))
+ /*
+ * Check to see if this is the worst task with a non-negative
+ * ADJ score seen so far
+ */
+ if (task->signal->oom_score_adj >= 0 &&
+ points > oc->chosen_non_negative_adj_points) {
+ if (oc->chosen_non_negative_adj)
+ put_task_struct(oc->chosen_non_negative_adj);
+ get_task_struct(task);
+ oc->chosen_non_negative_adj = task;
+ oc->chosen_non_negative_adj_points = points;
+ }
+
+ if (points < oc->chosen_points)
goto next;
+
select:
if (oc->chosen)
put_task_struct(oc->chosen);
@@ -359,8 +372,11 @@
next:
return 0;
abort:
+ if (oc->chosen_non_negative_adj)
+ put_task_struct(oc->chosen_non_negative_adj);
if (oc->chosen)
put_task_struct(oc->chosen);
+ oc->chosen_non_negative_adj = NULL;
oc->chosen = (void *)-1UL;
return 1;
}
@@ -371,6 +387,10 @@
*/
static void select_bad_process(struct oom_control *oc)
{
+ oc->chosen_points = LONG_MIN;
+ oc->chosen_non_negative_adj_points = LONG_MIN;
+ oc->chosen_non_negative_adj = NULL;
+
if (is_memcg_oom(oc))
mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
else {
@@ -383,13 +403,57 @@
rcu_read_unlock();
}
- oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
+ if (oc->chosen_non_negative_adj) {
+ /*
+ * If oc->chosen has a negative ADJ, and we found a task with
+ * a postive ADJ to kill, kill the task with the positive ADJ
+ * instead.
+ */
+ if (oc->chosen && oc->chosen->signal->oom_score_adj < 0) {
+ put_task_struct(oc->chosen);
+ oc->chosen = oc->chosen_non_negative_adj;
+ oc->chosen_points = oc->chosen_non_negative_adj_points;
+ } else
+ put_task_struct(oc->chosen_non_negative_adj);
+ }
+}
+
+static int dump_task(struct task_struct *p, void *arg)
+{
+ struct oom_control *oc = arg;
+ struct task_struct *task;
+
+ if (oom_unkillable_task(p))
+ return 0;
+
+ /* p may not have freeable memory in nodemask */
+ if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc))
+ return 0;
+
+ 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.
+ */
+ return 0;
+ }
+
+ pr_info("[%7d] %5d %5d %8lu %8lu %8ld %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),
+ mm_pgtables_bytes(task->mm),
+ get_mm_counter(task->mm, MM_SWAPENTS),
+ task->signal->oom_score_adj, task->comm);
+ task_unlock(task);
+
+ return 0;
}
/**
* 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
+ * @oc: pointer to struct oom_control
*
* 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
@@ -397,59 +461,55 @@
* State information includes task's pid, uid, tgid, vm size, rss,
* pgtables_bytes, swapents, oom_score_adj value, and name.
*/
-static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct oom_control *oc)
{
- struct task_struct *p;
- struct task_struct *task;
-
pr_info("Tasks state (memory values in pages):\n");
pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes 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;
- }
+ if (is_memcg_oom(oc))
+ mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+ else {
+ struct task_struct *p;
- pr_info("[%7d] %5d %5d %8lu %8lu %8ld %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),
- mm_pgtables_bytes(task->mm),
- get_mm_counter(task->mm, MM_SWAPENTS),
- task->signal->oom_score_adj, task->comm);
- task_unlock(task);
+ rcu_read_lock();
+ for_each_process(p)
+ dump_task(p, oc);
+ rcu_read_unlock();
}
- rcu_read_unlock();
+}
+
+static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
+{
+ /* one line summary of the oom killer context. */
+ pr_info("oom-kill:constraint=%s,nodemask=%*pbl",
+ oom_constraint_text[oc->constraint],
+ nodemask_pr_args(oc->nodemask));
+ cpuset_print_current_mems_allowed();
+ mem_cgroup_print_oom_context(oc->memcg, victim);
+ pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid,
+ from_kuid(&init_user_ns, task_uid(victim)));
}
static void dump_header(struct oom_control *oc, struct task_struct *p)
{
- pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n",
- current->comm, oc->gfp_mask, &oc->gfp_mask,
- nodemask_pr_args(oc->nodemask), oc->order,
+ pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n",
+ current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
current->signal->oom_score_adj);
if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
pr_warn("COMPACTION is disabled!!!\n");
- cpuset_print_current_mems_allowed();
dump_stack();
if (is_memcg_oom(oc))
- mem_cgroup_print_oom_info(oc->memcg, p);
+ mem_cgroup_print_oom_meminfo(oc->memcg);
else {
show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
if (is_dump_unreclaim_slabs())
dump_unreclaimable_slab();
}
if (sysctl_oom_dump_tasks)
- dump_tasks(oc->memcg, oc->nodemask);
+ dump_tasks(oc);
+ if (p)
+ dump_oom_summary(oc, p);
}
/*
@@ -504,7 +564,7 @@
set_bit(MMF_UNSTABLE, &mm->flags);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
- if (!can_madv_dontneed_vma(vma))
+ if (!can_madv_lru_vma(vma))
continue;
/*
@@ -518,19 +578,21 @@
* count elevated without a good reason.
*/
if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
- const unsigned long start = vma->vm_start;
- const unsigned long end = vma->vm_end;
+ struct mmu_notifier_range range;
struct mmu_gather tlb;
- tlb_gather_mmu(&tlb, mm, start, end);
- if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) {
- tlb_finish_mmu(&tlb, start, end);
+ mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
+ vma, mm, vma->vm_start,
+ vma->vm_end);
+ tlb_gather_mmu(&tlb, mm, range.start, range.end);
+ if (mmu_notifier_invalidate_range_start_nonblock(&range)) {
+ tlb_finish_mmu(&tlb, range.start, range.end);
ret = false;
continue;
}
- unmap_page_range(&tlb, vma, start, end, NULL);
- mmu_notifier_invalidate_range_end(mm, start, end);
- tlb_finish_mmu(&tlb, start, end);
+ unmap_page_range(&tlb, vma, range.start, range.end, NULL);
+ mmu_notifier_invalidate_range_end(&range);
+ tlb_finish_mmu(&tlb, range.start, range.end);
}
}
@@ -547,7 +609,7 @@
{
bool ret = true;
- if (!down_read_trylock(&mm->mmap_sem)) {
+ if (!mmap_read_trylock(mm)) {
trace_skip_task_reaping(tsk->pid);
return false;
}
@@ -555,8 +617,8 @@
/*
* MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
* work on the mm anymore. The check for MMF_OOM_SKIP must run
- * under mmap_sem for reading because it serializes against the
- * down_write();up_write() cycle in exit_mmap().
+ * under mmap_lock for reading because it serializes against the
+ * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap().
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
trace_skip_task_reaping(tsk->pid);
@@ -578,7 +640,7 @@
out_finish:
trace_finish_task_reaping(tsk->pid);
out_unlock:
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
return ret;
}
@@ -589,7 +651,7 @@
int attempts = 0;
struct mm_struct *mm = tsk->signal->oom_mm;
- /* Retry the down_read_trylock(mmap_sem) a few times */
+ /* Retry the mmap_read_trylock(mm) a few times */
while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
@@ -599,6 +661,7 @@
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
+ sched_show_task(tsk);
debug_show_all_locks();
done:
@@ -606,7 +669,7 @@
/*
* Hide this mm from OOM killer because it has been either reaped or
- * somebody can't call up_write(mmap_sem).
+ * somebody can't call mmap_write_unlock(mm).
*/
set_bit(MMF_OOM_SKIP, &mm->flags);
@@ -663,6 +726,20 @@
#endif /* CONFIG_MMU */
/**
+ * tsk->mm has to be non NULL and caller has to guarantee it is stable (either
+ * under task_lock or operate on the current).
+ */
+static void __mark_oom_victim(struct task_struct *tsk)
+{
+ struct mm_struct *mm = tsk->mm;
+
+ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
+ mmgrab(tsk->signal->oom_mm);
+ set_bit(MMF_OOM_VICTIM, &mm->flags);
+ }
+}
+
+/**
* mark_oom_victim - mark the given task as OOM victim
* @tsk: task to mark
*
@@ -674,18 +751,13 @@
*/
static void mark_oom_victim(struct task_struct *tsk)
{
- struct mm_struct *mm = tsk->mm;
-
WARN_ON(oom_killer_disabled);
/* OOM killer might race with memcg OOM */
if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
return;
/* oom_mm is bound to the signal struct life time. */
- if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
- mmgrab(tsk->signal->oom_mm);
- set_bit(MMF_OOM_VICTIM, &mm->flags);
- }
+ __mark_oom_victim(tsk);
/*
* Make sure that the task is woken up from uninterruptible sleep
@@ -832,7 +904,7 @@
return ret;
}
-static void __oom_kill_process(struct task_struct *victim)
+static void __oom_kill_process(struct task_struct *victim, const char *message)
{
struct task_struct *p;
struct mm_struct *mm;
@@ -840,6 +912,8 @@
p = find_lock_task_mm(victim);
if (!p) {
+ pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n",
+ message, task_pid_nr(victim), victim->comm);
put_task_struct(victim);
return;
} else if (victim != p) {
@@ -861,19 +935,21 @@
* 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, PIDTYPE_TGID);
+ do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID);
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)));
+ pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB, UID:%u pgtables:%lukB oom_score_adj:%hd\n",
+ message, task_pid_nr(victim), victim->comm, K(mm->total_vm),
+ K(get_mm_counter(mm, MM_ANONPAGES)),
+ K(get_mm_counter(mm, MM_FILEPAGES)),
+ K(get_mm_counter(mm, MM_SHMEMPAGES)),
+ from_kuid(&init_user_ns, task_uid(victim)),
+ mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj);
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
+ * depletion of all memory. This prevents mm->mmap_lock 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
@@ -894,12 +970,12 @@
continue;
}
/*
- * No use_mm() user needs to read from the userspace so we are
- * ok to reap it.
+ * No kthead_use_mm() user needs to read from the userspace so
+ * we are ok to reap it.
*/
if (unlikely(p->flags & PF_KTHREAD))
continue;
- do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, PIDTYPE_TGID);
+ do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID);
}
rcu_read_unlock();
@@ -915,25 +991,20 @@
* Kill provided task unless it's secured by setting
* oom_score_adj to OOM_SCORE_ADJ_MIN.
*/
-static int oom_kill_memcg_member(struct task_struct *task, void *unused)
+static int oom_kill_memcg_member(struct task_struct *task, void *message)
{
if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN &&
!is_global_init(task)) {
get_task_struct(task);
- __oom_kill_process(task);
+ __oom_kill_process(task, message);
}
return 0;
}
static void oom_kill_process(struct oom_control *oc, const char *message)
{
- struct task_struct *p = oc->chosen;
- unsigned int points = oc->chosen_points;
- struct task_struct *victim = p;
- struct task_struct *child;
- struct task_struct *t;
+ struct task_struct *victim = oc->chosen;
struct mem_cgroup *oom_group;
- unsigned int victim_points = 0;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
@@ -942,57 +1013,18 @@
* its children or threads, just give it access to memory reserves
* so it can die quickly
*/
- task_lock(p);
- if (task_will_free_mem(p)) {
- mark_oom_victim(p);
- wake_oom_reaper(p);
- task_unlock(p);
- put_task_struct(p);
+ task_lock(victim);
+ if (task_will_free_mem(victim)) {
+ mark_oom_victim(victim);
+ wake_oom_reaper(victim);
+ task_unlock(victim);
+ put_task_struct(victim);
return;
}
- task_unlock(p);
+ task_unlock(victim);
if (__ratelimit(&oom_rs))
- dump_header(oc, p);
-
- 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);
-
- /*
- * The task 'p' might have already exited before reaching here. The
- * put_task_struct() will free task_struct 'p' while the loop still try
- * to access the field of 'p', so, get an extra reference.
- */
- get_task_struct(p);
- 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,
- oc->memcg, oc->nodemask, oc->totalpages);
- if (child_points > victim_points) {
- put_task_struct(victim);
- victim = child;
- victim_points = child_points;
- get_task_struct(victim);
- }
- }
- }
- put_task_struct(p);
- read_unlock(&tasklist_lock);
+ dump_header(oc, victim);
/*
* Do we need to kill the entire memory cgroup?
@@ -1001,14 +1033,15 @@
*/
oom_group = mem_cgroup_get_oom_group(victim, oc->memcg);
- __oom_kill_process(victim);
+ __oom_kill_process(victim, message);
/*
* If necessary, kill all tasks in the selected memory cgroup.
*/
if (oom_group) {
mem_cgroup_print_oom_group(oom_group);
- mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, NULL);
+ mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member,
+ (void*)message);
mem_cgroup_put(oom_group);
}
}
@@ -1016,8 +1049,7 @@
/*
* Determines whether the kernel must panic because of the panic_on_oom sysctl.
*/
-static void check_panic_on_oom(struct oom_control *oc,
- enum oom_constraint constraint)
+static void check_panic_on_oom(struct oom_control *oc)
{
if (likely(!sysctl_panic_on_oom))
return;
@@ -1027,7 +1059,7 @@
* does not panic for cpuset, mempolicy, or memcg allocation
* failures.
*/
- if (constraint != CONSTRAINT_NONE)
+ if (oc->constraint != CONSTRAINT_NONE)
return;
}
/* Do not panic for oom kills triggered by sysrq */
@@ -1064,7 +1096,6 @@
bool out_of_memory(struct oom_control *oc)
{
unsigned long freed = 0;
- enum oom_constraint constraint = CONSTRAINT_NONE;
if (oom_killer_disabled)
return false;
@@ -1101,13 +1132,14 @@
* Check if there were limitations on the allocation (only relevant for
* NUMA and memcg) that may require different handling.
*/
- constraint = constrained_alloc(oc);
- if (constraint != CONSTRAINT_MEMORY_POLICY)
+ oc->constraint = constrained_alloc(oc);
+ if (oc->constraint != CONSTRAINT_MEMORY_POLICY)
oc->nodemask = NULL;
- check_panic_on_oom(oc, constraint);
+ check_panic_on_oom(oc);
if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
- current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
+ current->mm && !oom_unkillable_task(current) &&
+ oom_cpuset_eligible(current, oc) &&
current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
get_task_struct(current);
oc->chosen = current;
@@ -1118,6 +1150,12 @@
select_bad_process(oc);
/* Found nothing?!?! */
if (!oc->chosen) {
+ int ret = false;
+
+ trace_android_vh_oom_check_panic(oc, &ret);
+ if (ret)
+ return true;
+
dump_header(oc, NULL);
pr_warn("Out of memory and no killable processes...\n");
/*
@@ -1154,3 +1192,97 @@
if (__ratelimit(&pfoom_rs))
pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n");
}
+
+SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
+{
+#ifdef CONFIG_MMU
+ struct mm_struct *mm = NULL;
+ struct task_struct *task;
+ struct task_struct *p;
+ unsigned int f_flags;
+ bool reap = false;
+ struct pid *pid;
+ long ret = 0;
+
+ if (flags)
+ return -EINVAL;
+
+ pid = pidfd_get_pid(pidfd, &f_flags);
+ if (IS_ERR(pid))
+ return PTR_ERR(pid);
+
+ task = get_pid_task(pid, PIDTYPE_TGID);
+ if (!task) {
+ ret = -ESRCH;
+ goto put_pid;
+ }
+
+ /*
+ * Make sure to choose a thread which still has a reference to mm
+ * during the group exit
+ */
+ p = find_lock_task_mm(task);
+ if (!p) {
+ ret = -ESRCH;
+ goto put_task;
+ }
+
+ mm = p->mm;
+ mmgrab(mm);
+
+ /*
+ * If we are too late and exit_mmap already checked mm_is_oom_victim
+ * then will block on mmap_read_lock until exit_mmap releases mmap_lock
+ */
+ set_bit(MMF_OOM_VICTIM, &mm->flags);
+
+ if (task_will_free_mem(p))
+ reap = true;
+ else {
+ /* Error only if the work has not been done already */
+ if (!test_bit(MMF_OOM_SKIP, &mm->flags))
+ ret = -EINVAL;
+ }
+ task_unlock(p);
+
+ if (!reap)
+ goto drop_mm;
+
+ if (mmap_read_lock_killable(mm)) {
+ ret = -EINTR;
+ goto drop_mm;
+ }
+ /*
+ * Check MMF_OOM_SKIP again under mmap_read_lock protection to ensure
+ * possible change in exit_mmap is seen
+ */
+ if (!test_bit(MMF_OOM_SKIP, &mm->flags) && !__oom_reap_task_mm(mm))
+ ret = -EAGAIN;
+ mmap_read_unlock(mm);
+
+drop_mm:
+ mmdrop(mm);
+put_task:
+ put_task_struct(task);
+put_pid:
+ put_pid(pid);
+ return ret;
+#else
+ return -ENOSYS;
+#endif /* CONFIG_MMU */
+}
+
+void add_to_oom_reaper(struct task_struct *p)
+{
+ p = find_lock_task_mm(p);
+ if (!p)
+ return;
+
+ get_task_struct(p);
+ if (task_will_free_mem(p)) {
+ __mark_oom_victim(p);
+ wake_oom_reaper(p);
+ }
+ task_unlock(p);
+ put_task_struct(p);
+}
--
Gitblit v1.6.2