Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Hyeonggon Yoo <42.hyeyoo@gmail.com>
To:     linux-mm@kvack.org
Cc:     Christoph Lameter <cl@linux.com>,
        Pekka Enberg <penberg@kernel.org>,
        David Rientjes <rientjes@google.com>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Marco Elver <elver@google.com>,
        Matthew WilCox <willy@infradead.org>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        linux-kernel@vger.kernel.org, 42.hyeyoo@gmail.com
Subject: [PATCH v3 2/2] mm/slub: refactor deactivate_slab()
Date:   Mon,  7 Mar 2022 07:40:56 +0000
Message-Id: <20220307074057.902222-3-42.hyeyoo@gmail.com>
In-Reply-To: <20220307074057.902222-1-42.hyeyoo@gmail.com>
References: <20220307074057.902222-1-42.hyeyoo@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Simplify deactivate_slab() by unlocking n->list_lock and retrying
cmpxchg_double() when cmpxchg_double() fails, and perform
add_{partial,full} only when it succeed.

Releasing and taking n->list_lock again here is not harmful as SLUB
avoids deactivating slabs as much as possible.

[ vbabka@suse.cz: perform add_{partial,full} when cmpxchg_double()
  succeed.

  count deactivating full slabs even if debugging flag is not set. ]

Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
---
 mm/slub.c | 91 +++++++++++++++++++++++--------------------------------
 1 file changed, 38 insertions(+), 53 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 1ce09b0347ad..f0cb9d0443ac 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2348,10 +2348,10 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
 static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 			    void *freelist)
 {
-	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
+	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE, M_FULL_NOLIST };
 	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
-	int lock = 0, free_delta = 0;
-	enum slab_modes l = M_NONE, m = M_NONE;
+	int free_delta = 0;
+	enum slab_modes mode = M_NONE;
 	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
 	unsigned long flags = 0;
@@ -2393,14 +2393,10 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 	 * Ensure that the slab is unfrozen while the list presence
 	 * reflects the actual number of objects during unfreeze.
 	 *
-	 * We setup the list membership and then perform a cmpxchg
-	 * with the count. If there is a mismatch then the slab
-	 * is not unfrozen but the slab is on the wrong list.
-	 *
-	 * Then we restart the process which may have to remove
-	 * the slab from the list that we just put it on again
-	 * because the number of objects in the slab may have
-	 * changed.
+	 * We first perform cmpxchg holding lock and insert to list
+	 * when it succeed. If there is mismatch then the slab is not
+	 * unfrozen and number of objects in the slab may have changed.
+	 * Then release lock and retry cmpxchg again.
 	 */
 redo:
 
@@ -2420,61 +2416,50 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
 	new.frozen = 0;
 
 	if (!new.inuse && n->nr_partial >= s->min_partial)
-		m = M_FREE;
+		mode = M_FREE;
 	else if (new.freelist) {
-		m = M_PARTIAL;
-		if (!lock) {
-			lock = 1;
-			/*
-			 * Taking the spinlock removes the possibility that
-			 * acquire_slab() will see a slab that is frozen
-			 */
-			spin_lock_irqsave(&n->list_lock, flags);
-		}
-	} else {
-		m = M_FULL;
-		if (kmem_cache_debug_flags(s, SLAB_STORE_USER) && !lock) {
-			lock = 1;
-			/*
-			 * This also ensures that the scanning of full
-			 * slabs from diagnostic functions will not see
-			 * any frozen slabs.
-			 */
-			spin_lock_irqsave(&n->list_lock, flags);
-		}
-	}
-
-	if (l != m) {
-		if (l == M_PARTIAL)
-			remove_partial(n, slab);
-		else if (l == M_FULL)
-			remove_full(s, n, slab);
+		mode = M_PARTIAL;
+		/*
+		 * Taking the spinlock removes the possibility that
+		 * acquire_slab() will see a slab that is frozen
+		 */
+		spin_lock_irqsave(&n->list_lock, flags);
+	} else if (kmem_cache_debug_flags(s, SLAB_STORE_USER)) {
+		mode = M_FULL;
+		/*
+		 * This also ensures that the scanning of full
+		 * slabs from diagnostic functions will not see
+		 * any frozen slabs.
+		 */
+		spin_lock_irqsave(&n->list_lock, flags);
+	} else
+		mode = M_FULL_NOLIST;
 
-		if (m == M_PARTIAL)
-			add_partial(n, slab, tail);
-		else if (m == M_FULL)
-			add_full(s, n, slab);
-	}
 
-	l = m;
 	if (!cmpxchg_double_slab(s, slab,
 				old.freelist, old.counters,
 				new.freelist, new.counters,
-				"unfreezing slab"))
+				"unfreezing slab")) {
+		if (mode == M_PARTIAL || mode == M_FULL)
+			spin_unlock_irqrestore(&n->list_lock, flags);
 		goto redo;
+	}
 
-	if (lock)
-		spin_unlock_irqrestore(&n->list_lock, flags);
 
-	if (m == M_PARTIAL)
+	if (mode == M_PARTIAL) {
+		add_partial(n, slab, tail);
+		spin_unlock_irqrestore(&n->list_lock, flags);
 		stat(s, tail);
-	else if (m == M_FULL)
-		stat(s, DEACTIVATE_FULL);
-	else if (m == M_FREE) {
+	} else if (mode == M_FREE) {
 		stat(s, DEACTIVATE_EMPTY);
 		discard_slab(s, slab);
 		stat(s, FREE_SLAB);
-	}
+	} else if (mode == M_FULL) {
+		add_full(s, n, slab);
+		spin_unlock_irqrestore(&n->list_lock, flags);
+		stat(s, DEACTIVATE_FULL);
+	} else if (mode == M_FULL_NOLIST)
+		stat(s, DEACTIVATE_FULL);
 }
 
 #ifdef CONFIG_SLUB_CPU_PARTIAL
-- 
2.33.1