Re: [PATCH v2] mm: memcontrol: fix potential oom_lock recursion deadlock

[Michal Hocko <mhocko@suse.com>]

On Fri 22-07-22 09:46:27, Tetsuo Handa wrote:
> syzbot is reporting GFP_KERNEL allocation with oom_lock held [1]. We
> must make sure that such allocation won't hit __alloc_pages_may_oom()
> path which will retry forever if oom_lock is already held. Use static
> buffer when oom_lock is already held.

The changelog is rather cryptic. Your previous one was more readable.
I would go with:
"
syzbot is reporting GFP_KERNEL allocation with oom_lock held [1]
when reporting memcg oom. This is problematic because this creates a
dependency between GFP_NOFS and GFP_KERNEL over oom_lock which could
dead lock the system.

Fix the problem by removing the allocation from memory_stat_format
completely. Use a statically preallocated buffer instead for this path.
OOM dumping is synchronized by the oom_lock so there is no exclusion
required here. memory_stat_show can use GFP_KERNEL allocation.
"
 
> Link: https://syzkaller.appspot.com/bug?extid=2d2aeadc6ce1e1f11d45 [1]
> Reported-by: syzbot <syzbot+2d2aeadc6ce1e1f11d45@syzkaller.appspotmail.com>
> Suggested-by: Michal Hocko <mhocko@suse.com>
> Fixes: c8713d0b23123759 ("mm: memcontrol: dump memory.stat during cgroup OOM")
> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>

Acked-by: Michal Hocko <mhocko@suse.com>

Thanks!

> ---
> Changes in v2:
>   Use static buffer for OOM reporting, suggested by Michal Hocko <mhocko@suse.com>.
> 
>  mm/memcontrol.c | 22 +++++++++-------------
>  1 file changed, 9 insertions(+), 13 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 618c366a2f07..8092be2fbb7c 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1460,14 +1460,12 @@ static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
>  	return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
>  }
>  
> -static char *memory_stat_format(struct mem_cgroup *memcg)
> +static void memory_stat_format(struct mem_cgroup *memcg, char *buf, int bufsize)
>  {
>  	struct seq_buf s;
>  	int i;
>  
> -	seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE);
> -	if (!s.buffer)
> -		return NULL;
> +	seq_buf_init(&s, buf, bufsize);
>  
>  	/*
>  	 * Provide statistics on the state of the memory subsystem as
> @@ -1533,8 +1531,6 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
>  
>  	/* The above should easily fit into one page */
>  	WARN_ON_ONCE(seq_buf_has_overflowed(&s));
> -
> -	return s.buffer;
>  }
>  
>  #define K(x) ((x) << (PAGE_SHIFT-10))
> @@ -1570,7 +1566,10 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *
>   */
>  void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
>  {
> -	char *buf;
> +	/* Use static buffer, for the caller is holding oom_lock. */
> +	static char buf[PAGE_SIZE];
> +
> +	lockdep_assert_held(&oom_lock);
>  
>  	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
>  		K((u64)page_counter_read(&memcg->memory)),
> @@ -1591,11 +1590,8 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
>  	pr_info("Memory cgroup stats for ");
>  	pr_cont_cgroup_path(memcg->css.cgroup);
>  	pr_cont(":");
> -	buf = memory_stat_format(memcg);
> -	if (!buf)
> -		return;
> +	memory_stat_format(memcg, buf, sizeof(buf));
>  	pr_info("%s", buf);
> -	kfree(buf);
>  }
>  
>  /*
> @@ -6335,11 +6331,11 @@ static int memory_events_local_show(struct seq_file *m, void *v)
>  static int memory_stat_show(struct seq_file *m, void *v)
>  {
>  	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
> -	char *buf;
> +	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
>  
> -	buf = memory_stat_format(memcg);
>  	if (!buf)
>  		return -ENOMEM;
> +	memory_stat_format(memcg, buf, PAGE_SIZE);
>  	seq_puts(m, buf);
>  	kfree(buf);
>  	return 0;
> -- 
> 2.18.4
> 

-- 
Michal Hocko
SUSE Labs