mm: memcontrol: fix potential oom_lock recursion deadlock

syzbot is reporting GFP_KERNEL allocation with oom_lock held when
reporting memcg OOM [1].  If this allocation triggers the global OOM
situation then the system can livelock because the GFP_KERNEL
allocation with oom_lock held cannot trigger the global OOM killer
because __alloc_pages_may_oom() fails to hold oom_lock.

Fix this problem by removing the allocation from memory_stat_format()
completely, and pass static buffer when calling from memcg OOM path.

Note that the caller holding filesystem lock was the trigger for syzbot
to report this locking dependency.  Doing GFP_KERNEL allocation with
filesystem lock held can deadlock the system even without involving OOM
situation.

Link: https://syzkaller.appspot.com/bug?extid=2d2aeadc6ce1e1f11d45
Link: https://lkml.kernel.org/r/86afb39f-8c65-bec2-6cfc-c5e3cd600c0b@I-love.SAKURA.ne.jp
Fixes: c8713d0b23123759 ("mm: memcontrol: dump memory.stat during cgroup OOM")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: syzbot <syzbot+2d2aeadc6ce1e1f11d45@syzkaller.appspotmail.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c65751ab4516bd64317fbfeb56de76a33864968f..b69979c9ced5c26d0bd238e0e090ce3851daa321 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1490,14 +1490,12 @@ static const unsigned int memcg_vm_event_stat[] = {
 #endif
 };
 
-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
@@ -1539,8 +1537,6 @@ 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))
@@ -1576,7 +1572,10 @@ 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)),
@@ -1597,11 +1596,8 @@ 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);
 }
 
 /*
@@ -6405,11 +6401,11 @@ 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;