Re: [PATCH v4 29/35] mm: slub: Move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context

[Vlastimil Babka <vbabka@suse.cz>]

On 8/9/21 3:41 PM, Qian Cai wrote:
>>  
>> +static DEFINE_MUTEX(flush_lock);
>> +static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
>> +
>>  static void flush_all(struct kmem_cache *s)
>>  {
>> -	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
>> +	struct slub_flush_work *sfw;
>> +	unsigned int cpu;
>> +
>> +	mutex_lock(&flush_lock);
> 
> Vlastimil, taking the lock here could trigger a warning during memory offline/online due to the locking order:
> 
> slab_mutex -> flush_lock
> 
> [   91.374541] WARNING: possible circular locking dependency detected
> [   91.381411] 5.14.0-rc5-next-20210809+ #84 Not tainted
> [   91.387149] ------------------------------------------------------
> [   91.394016] lsbug/1523 is trying to acquire lock:
> [   91.399406] ffff800018e76530 (flush_lock){+.+.}-{3:3}, at: flush_all+0x50/0x1c8
> [   91.407425] 
>                but task is already holding lock:
> [   91.414638] ffff800018e48468 (slab_mutex){+.+.}-{3:3}, at: slab_memory_callback+0x44/0x280
> [   91.423603] 
>                which lock already depends on the new lock.
> 

OK, managed to reproduce in qemu and this fixes it for me on top of
next-20210809. Could you test as well, as your testing might be more
comprehensive? I will format is as a fixup for the proper patch in the series then.

----8<----
From 7ce71c7f9455e8b96dc1b728ea566b6ef5e424e4 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 10 Aug 2021 10:58:07 +0200
Subject: [PATCH] mm, slub: fix memory offline lockdep splat

Reverse order of flush_lock and cpus_read_lock() to prevent lockdep splat.
In slab_mem_going_offline_callback() we already have cpus_read_lock()
held so make sure it's not taken again.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 88a6c3ed2751..073cdd4b020f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2640,13 +2640,13 @@ static bool has_cpu_slab(int cpu, struct kmem_cache *s)
 static DEFINE_MUTEX(flush_lock);
 static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
 
-static void flush_all(struct kmem_cache *s)
+static void flush_all_cpus_locked(struct kmem_cache *s)
 {
 	struct slub_flush_work *sfw;
 	unsigned int cpu;
 
+	lockdep_assert_cpus_held();
 	mutex_lock(&flush_lock);
-	cpus_read_lock();
 
 	for_each_online_cpu(cpu) {
 		sfw = &per_cpu(slub_flush, cpu);
@@ -2667,10 +2667,16 @@ static void flush_all(struct kmem_cache *s)
 		flush_work(&sfw->work);
 	}
 
-	cpus_read_unlock();
 	mutex_unlock(&flush_lock);
 }
 
+static void flush_all(struct kmem_cache *s)
+{
+	cpus_read_lock();
+	flush_all_cpus_locked(s);
+	cpus_read_unlock();
+}
+
 /*
  * Use the cpu notifier to insure that the cpu slabs are flushed when
  * necessary.
@@ -4516,7 +4522,7 @@ EXPORT_SYMBOL(kfree);
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+int __kmem_cache_do_shrink(struct kmem_cache *s)
 {
 	int node;
 	int i;
@@ -4528,7 +4534,6 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	unsigned long flags;
 	int ret = 0;
 
-	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
 		INIT_LIST_HEAD(&discard);
 		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
@@ -4578,13 +4583,21 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	return ret;
 }
 
+int __kmem_cache_shrink(struct kmem_cache *s)
+{
+	flush_all(s);
+	return __kmem_cache_do_shrink(s);
+}
+
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+	list_for_each_entry(s, &slab_caches, list) {
+		flush_all_cpus_locked(s);
+		__kmem_cache_do_shrink(s);
+	}
 	mutex_unlock(&slab_mutex);
 
 	return 0;
-- 
2.32.0