mm, oom: remove task_lock protecting comm printing
The oom killer takes task_lock() in a couple of places solely to protect
printing the task's comm.
A process's comm, including current's comm, may change due to
/proc/pid/comm or PR_SET_NAME.
The comm will always be NULL-terminated, so the worst race scenario would
only be during update. We can tolerate a comm being printed that is in
the middle of an update to avoid taking the lock.
Other locations in the kernel have already dropped task_lock() when
printing comm, so this is consistent.
Signed-off-by: David Rientjes <rientjes@google.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 1b35799..5a13119 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -93,7 +93,7 @@
extern void rebuild_sched_domains(void);
-extern void cpuset_print_task_mems_allowed(struct task_struct *p);
+extern void cpuset_print_current_mems_allowed(void);
/*
* read_mems_allowed_begin is required when making decisions involving
@@ -219,7 +219,7 @@
partition_sched_domains(1, NULL, NULL);
}
-static inline void cpuset_print_task_mems_allowed(struct task_struct *p)
+static inline void cpuset_print_current_mems_allowed(void)
{
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f0acff0..9ef59a3 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2598,22 +2598,22 @@
}
/**
- * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
- * @tsk: pointer to task_struct of some task.
+ * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed
*
- * Description: Prints @task's name, cpuset name, and cached copy of its
+ * Description: Prints current's name, cpuset name, and cached copy of its
* mems_allowed to the kernel log.
*/
-void cpuset_print_task_mems_allowed(struct task_struct *tsk)
+void cpuset_print_current_mems_allowed(void)
{
struct cgroup *cgrp;
rcu_read_lock();
- cgrp = task_cs(tsk)->css.cgroup;
- pr_info("%s cpuset=", tsk->comm);
+ cgrp = task_cs(current)->css.cgroup;
+ pr_info("%s cpuset=", current->comm);
pr_cont_cgroup_name(cgrp);
- pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed));
+ pr_cont(" mems_allowed=%*pbl\n",
+ nodemask_pr_args(¤t->mems_allowed));
rcu_read_unlock();
}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c170d9f..58f3d27 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -377,13 +377,11 @@
static void dump_header(struct oom_control *oc, struct task_struct *p,
struct mem_cgroup *memcg)
{
- task_lock(current);
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_task_mems_allowed(current);
- task_unlock(current);
+ cpuset_print_current_mems_allowed();
dump_stack();
if (memcg)
mem_cgroup_print_oom_info(memcg, p);
@@ -509,10 +507,8 @@
if (__ratelimit(&oom_rs))
dump_header(oc, p, memcg);
- task_lock(p);
pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
message, task_pid_nr(p), p->comm, points);
- task_unlock(p);
/*
* If any of p's children has a different mm and is eligible for kill,
@@ -586,10 +582,8 @@
if (fatal_signal_pending(p))
continue;
- task_lock(p); /* Protect ->comm from prctl() */
pr_info("Kill process %d (%s) sharing same memory\n",
task_pid_nr(p), p->comm);
- task_unlock(p);
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
}
rcu_read_unlock();
