From: Shakeel Butt <shakeelb@google.com> mainline inclusion from mainline-v5.3-rc1 commit 6ba749ee78ef42ffdf4b95c042fc574a37d229d9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6E9D3 CVE: NA -------------------------------- oom_unkillable_task() can be called from three different contexts i.e. global OOM, memcg OOM and oom_score procfs interface. At the moment oom_unkillable_task() does a task_in_mem_cgroup() check on the given process. Since there is no reason to perform task_in_mem_cgroup() check for global OOM and oom_score procfs interface, those contexts provide NULL memcg and skips the task_in_mem_cgroup() check. However for memcg OOM context, the oom_unkillable_task() is always called from mem_cgroup_scan_tasks() and thus task_in_mem_cgroup() check becomes redundant and effectively dead code. So, just remove the task_in_mem_cgroup() check altogether. Link: http://lkml.kernel.org/r/20190624212631.87212-2-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Roman Gushchin <guro@fb.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Jackson <pj@sgi.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Conflicts: mm/page_alloc.c Signed-off-by: Ma Wupeng <mawupeng1@huawei.com> Reviewed-by: Nanyong Sun <sunnanyong@huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- fs/proc/base.c | 2 +- include/linux/memcontrol.h | 7 ------- include/linux/oom.h | 2 +- mm/memcontrol.c | 26 -------------------------- mm/oom_kill.c | 23 +++++++++-------------- 5 files changed, 11 insertions(+), 49 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index d7e94f7b5ad3..45ac75d16d71 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -552,7 +552,7 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; - points = oom_badness(task, NULL, NULL, totalpages) * + points = oom_badness(task, NULL, totalpages) * 1000 / totalpages; seq_printf(m, "%lu\n", points); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 594925ea3076..23db8eec0755 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -436,7 +436,6 @@ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); -bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); @@ -907,12 +906,6 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return true; } -static inline bool task_in_mem_cgroup(struct task_struct *task, - const struct mem_cgroup *memcg) -{ - return true; -} - static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; diff --git a/include/linux/oom.h b/include/linux/oom.h index 123538b89dc8..76a2086af472 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -109,7 +109,7 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) bool __oom_reap_task_mm(struct mm_struct *mm); extern unsigned long oom_badness(struct task_struct *p, - struct mem_cgroup *memcg, const nodemask_t *nodemask, + const nodemask_t *nodemask, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 886d6b0a4fce..fe854542fb77 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1332,32 +1332,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, *lru_size += nr_pages; } -bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) -{ - struct mem_cgroup *task_memcg; - struct task_struct *p; - bool ret; - - p = find_lock_task_mm(task); - if (p) { - task_memcg = get_mem_cgroup_from_mm(p->mm); - task_unlock(p); - } else { - /* - * All threads may have already detached their mm's, but the oom - * killer still needs to detect if they have already been oom - * killed to prevent needlessly killing additional tasks. - */ - rcu_read_lock(); - task_memcg = mem_cgroup_from_task(task); - css_get(&task_memcg->css); - rcu_read_unlock(); - } - ret = mem_cgroup_is_descendant(task_memcg, memcg); - css_put(&task_memcg->css); - return ret; -} - /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 41fcb8e45319..d2639ce2cec4 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -158,17 +158,13 @@ static inline bool is_memcg_oom(struct oom_control *oc) /* 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) + 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; @@ -199,20 +195,19 @@ static bool is_dump_unreclaim_slabs(void) * 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, +unsigned long oom_badness(struct task_struct *p, const nodemask_t *nodemask, unsigned long totalpages) { long points; long adj; - if (oom_unkillable_task(p, memcg, nodemask)) + if (oom_unkillable_task(p, nodemask)) return 0; p = find_lock_task_mm(p); @@ -369,7 +364,7 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) struct oom_control *oc = arg; unsigned long points; - if (oom_unkillable_task(task, NULL, oc->nodemask)) + if (oom_unkillable_task(task, oc->nodemask)) goto next; /* @@ -393,7 +388,7 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) goto select; } - points = oom_badness(task, NULL, oc->nodemask, oc->totalpages); + points = oom_badness(task, oc->nodemask, oc->totalpages); if (oom_next_task(task, oc, points)) goto next; @@ -446,7 +441,7 @@ static int dump_task(struct task_struct *p, void *arg) struct task_struct *task; struct sp_proc_stat *stat; - if (oom_unkillable_task(p, NULL, oc->nodemask)) + if (oom_unkillable_task(p, oc->nodemask)) return 0; task = find_lock_task_mm(p); @@ -1086,8 +1081,8 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* * oom_badness() returns 0 if the thread is unkillable */ - child_points = oom_badness(child, - oc->memcg, oc->nodemask, oc->totalpages); + child_points = oom_badness(child, oc->nodemask, + oc->totalpages); if (child_points > victim_points) { put_task_struct(victim); victim = child; @@ -1276,7 +1271,7 @@ bool out_of_memory(struct oom_control *oc) 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, oc->nodemask) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); oc->chosen = current; -- 2.25.1