linux-kernel - [PATCH v12 2/2] Add the missing information for the oom report

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1530796829-4539-2-git-send-email-ufo19890607@gmail.com>
Date:   Thu,  5 Jul 2018 21:20:29 +0800
From:   ufo19890607@...il.com
To:     akpm@...ux-foundation.org, mhocko@...e.com, rientjes@...gle.com,
        kirill.shutemov@...ux.intel.com, aarcange@...hat.com,
        penguin-kernel@...ove.sakura.ne.jp, guro@...com,
        yang.s@...baba-inc.com
Cc:     linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        yuzhoujian@...ichuxing.com
Subject: [PATCH v12 2/2] Add the missing information for the oom report

From: yuzhoujian <yuzhoujian@...ichuxing.com>

The current oom report doesn't display victim's memcg context during the
global OOM situation. While this information is not strictly needed, it
can be really helpful for containerized environments to locate which
container has lost a process. Now that we have a single line for the oom
context, we can trivially add both the oom memcg (this can be either
global_oom or a specific memcg which hits its hard limits) and task_memcg
which is the victim's memcg.

Signed-off-by: yuzhoujian <yuzhoujian@...ichuxing.com>
---
 include/linux/memcontrol.h | 14 +++++++++++---
 mm/memcontrol.c            | 36 ++++++++++++++++++++++--------------
 mm/oom_kill.c              | 10 ++++++----
 3 files changed, 39 insertions(+), 21 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c6fb116e925..96a73f989101 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -491,8 +491,10 @@ void mem_cgroup_handle_over_high(void);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
-				struct task_struct *p);
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
+		struct task_struct *p);
+
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -903,7 +905,13 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 }
 
 static inline void
-mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
+				struct task_struct *p)
+{
+}
+
+static inline void
+mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6f0d5ef320a..18deea974cfd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1119,32 +1119,40 @@ static const char *const memcg1_stat_names[] = {
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /**
- * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
- * @memcg: The memory cgroup that went over limit
+ * mem_cgroup_print_oom_context: Print OOM context information relevant to
+ * memory controller.
+ * @memcg: The origin memory cgroup that went over limit
  * @p: Task that is going to be killed
  *
  * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
  * enabled
  */
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct mem_cgroup *iter;
-	unsigned int i;
+	struct cgroup *origin_cgrp, *kill_cgrp;
 
 	rcu_read_lock();
-
+	if (memcg) {
+		pr_cont(",oom_memcg=");
+		pr_cont_cgroup_path(memcg->css.cgroup);
+	} else
+		pr_cont(",global_oom");
 	if (p) {
-		pr_info("Task in ");
+		pr_cont(",task_memcg=");
 		pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-		pr_cont(" killed as a result of limit of ");
-	} else {
-		pr_info("Memory limit reached of cgroup ");
 	}
-
-	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_cont("\n");
-
 	rcu_read_unlock();
+}
+
+/**
+ * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
+ * memory controller.
+ * @memcg: The memory cgroup that went over limit
+ */
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *iter;
+	unsigned int i;
 
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memory)),
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c38f224b0d9e..9e80f6c2eb2e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -430,13 +430,15 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 	dump_stack();
 
 	/* one line summary of the oom killer context. */
-	pr_info("oom-kill:constraint=%s,nodemask=%*pbl,task=%s,pid=%5d,uid=%5d",
+	pr_info("oom-kill:constraint=%s,nodemask=%*pbl",
 			oom_constraint_text[oc->constraint],
-			nodemask_pr_args(oc->nodemask),
-			p->comm, p->pid, from_kuid(&init_user_ns, task_uid(p)));
+			nodemask_pr_args(oc->nodemask));
+	mem_cgroup_print_oom_context(oc->memcg, p);
 	cpuset_print_current_mems_allowed();
+	pr_cont(",task=%s,pid=%5d,uid=%5d\n", p->comm, p->pid,
+		from_kuid(&init_user_ns, task_uid(p)));
 	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())
-- 
2.14.1