Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Qi Zheng <zhengqi.arch@bytedance.com>
To:     akpm@linux-foundation.org, david@fromorbit.com, tkhai@ya.ru,
        vbabka@suse.cz, roman.gushchin@linux.dev, djwong@kernel.org,
        brauner@kernel.org, paulmck@kernel.org, tytso@mit.edu
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
        linux-arm-msm@vger.kernel.org, dm-devel@redhat.com,
        linux-raid@vger.kernel.org, linux-bcache@vger.kernel.org,
        virtualization@lists.linux-foundation.org,
        linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
        linux-nfs@vger.kernel.org, linux-xfs@vger.kernel.org,
        linux-btrfs@vger.kernel.org, Qi Zheng <zhengqi.arch@bytedance.com>
Subject: [PATCH 22/29] drm/ttm: introduce pool_shrink_rwsem
Date:   Thu, 22 Jun 2023 16:53:28 +0800
Message-Id: <20230622085335.77010-23-zhengqi.arch@bytedance.com>
In-Reply-To: <20230622085335.77010-1-zhengqi.arch@bytedance.com>
References: <20230622085335.77010-1-zhengqi.arch@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Currently, the synchronize_shrinkers() is only used by TTM
pool. It only requires that no shrinkers run in parallel.

After we use RCU+refcount method to implement the lockless
slab shrink, we can not use shrinker_rwsem or synchronize_rcu()
to guarantee that all shrinker invocations have seen an update
before freeing memory.

So we introduce a new pool_shrink_rwsem to implement a private
synchronize_shrinkers(), so as to achieve the same purpose.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 drivers/gpu/drm/ttm/ttm_pool.c | 15 +++++++++++++++
 include/linux/shrinker.h       |  1 -
 mm/vmscan.c                    | 15 ---------------
 3 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index cddb9151d20f..713b1c0a70e1 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -74,6 +74,7 @@ static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
 static struct shrinker mm_shrinker;
+static DECLARE_RWSEM(pool_shrink_rwsem);
 
 /* Allocate pages of size 1 << order with the given gfp_flags */
 static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
@@ -317,6 +318,7 @@ static unsigned int ttm_pool_shrink(void)
 	unsigned int num_pages;
 	struct page *p;
 
+	down_read(&pool_shrink_rwsem);
 	spin_lock(&shrinker_lock);
 	pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
 	list_move_tail(&pt->shrinker_list, &shrinker_list);
@@ -329,6 +331,7 @@ static unsigned int ttm_pool_shrink(void)
 	} else {
 		num_pages = 0;
 	}
+	up_read(&pool_shrink_rwsem);
 
 	return num_pages;
 }
@@ -572,6 +575,18 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 }
 EXPORT_SYMBOL(ttm_pool_init);
 
+/**
+ * synchronize_shrinkers - Wait for all running shrinkers to complete.
+ *
+ * This is useful to guarantee that all shrinker invocations have seen an
+ * update, before freeing memory, similar to rcu.
+ */
+static void synchronize_shrinkers(void)
+{
+	down_write(&pool_shrink_rwsem);
+	up_write(&pool_shrink_rwsem);
+}
+
 /**
  * ttm_pool_fini - Cleanup a pool
  *
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 8e9ba6fa3fcc..4094e4c44e80 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -105,7 +105,6 @@ extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker,
 					    const char *fmt, ...);
 extern void unregister_shrinker(struct shrinker *shrinker);
 extern void free_prealloced_shrinker(struct shrinker *shrinker);
-extern void synchronize_shrinkers(void);
 
 typedef unsigned long (*count_objects_cb)(struct shrinker *s,
 					  struct shrink_control *sc);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 64ff598fbad9..3a8d50ad6ff6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -844,21 +844,6 @@ void unregister_and_free_shrinker(struct shrinker *shrinker)
 }
 EXPORT_SYMBOL(unregister_and_free_shrinker);
 
-/**
- * synchronize_shrinkers - Wait for all running shrinkers to complete.
- *
- * This is equivalent to calling unregister_shrink() and register_shrinker(),
- * but atomically and with less overhead. This is useful to guarantee that all
- * shrinker invocations have seen an update, before freeing memory, similar to
- * rcu.
- */
-void synchronize_shrinkers(void)
-{
-	down_write(&shrinker_rwsem);
-	up_write(&shrinker_rwsem);
-}
-EXPORT_SYMBOL(synchronize_shrinkers);
-
 #define SHRINK_BATCH 128
 
 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
-- 
2.30.2