mm, slub: splice cpu and page freelists in deactivate_slab()

In deactivate_slab() we currently move all but one objects on the cpu
freelist to the page freelist one by one using the costly cmpxchg_double()
operation.  Then we unfreeze the page while moving the last object on page
freelist, with a final cmpxchg_double().

This can be optimized to avoid the cmpxchg_double() per object.  Just
count the objects on cpu freelist (to adjust page->inuse properly) and
also remember the last object in the chain.  Then splice page->freelist to
the last object and effectively add the whole cpu freelist to
page->freelist while unfreezing the page, with a single cmpxchg_double().

Link: https://lkml.kernel.org/r/20210115183543.15097-1-vbabka@suse.czSigned-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Jann Horn <jannh@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/slub.c

@@ -2167,9 +2167,9 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 {
 	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-	int lock = 0;
+	int lock = 0, free_delta = 0;
 	enum slab_modes l = M_NONE, m = M_NONE;
-	void *nextfree;
+	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
 	struct page new;
 	struct page old;
@@ -2180,45 +2180,34 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 	}
 
 	/*
-	 * Stage one: Free all available per cpu objects back
-	 * to the page freelist while it is still frozen. Leave the
-	 * last one.
-	 *
-	 * There is no need to take the list->lock because the page
-	 * is still frozen.
+	 * Stage one: Count the objects on cpu's freelist as free_delta and
+	 * remember the last object in freelist_tail for later splicing.
 	 */
-	while (freelist && (nextfree = get_freepointer(s, freelist))) {
-		void *prior;
-		unsigned long counters;
+	freelist_tail = NULL;
+	freelist_iter = freelist;
+	while (freelist_iter) {
+		nextfree = get_freepointer(s, freelist_iter);
 
 		/*
 		 * If 'nextfree' is invalid, it is possible that the object at
-		 * 'freelist' is already corrupted.  So isolate all objects
-		 * starting at 'freelist'.
+		 * 'freelist_iter' is already corrupted.  So isolate all objects
+		 * starting at 'freelist_iter' by skipping them.
 		 */
-		if (freelist_corrupted(s, page, &freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist_iter, nextfree))
 			break;
 
-		do {
-			prior = page->freelist;
-			counters = page->counters;
-			set_freepointer(s, freelist, prior);
-			new.counters = counters;
-			new.inuse--;
-			VM_BUG_ON(!new.frozen);
-
-		} while (!__cmpxchg_double_slab(s, page,
-			prior, counters,
-			freelist, new.counters,
-			"drain percpu freelist"));
+		freelist_tail = freelist_iter;
+		free_delta++;
 
-		freelist = nextfree;
+		freelist_iter = nextfree;
 	}
 
 	/*
-	 * Stage two: Ensure that the page is unfrozen while the
-	 * list presence reflects the actual number of objects
-	 * during unfreeze.
+	 * Stage two: Unfreeze the page while splicing the per-cpu
+	 * freelist to the head of page's freelist.
+	 *
+	 * Ensure that the page 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 page
@@ -2231,15 +2220,15 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 	 */
 redo:
 
-	old.freelist = page->freelist;
-	old.counters = page->counters;
+	old.freelist = READ_ONCE(page->freelist);
+	old.counters = READ_ONCE(page->counters);
 	VM_BUG_ON(!old.frozen);
 
 	/* Determine target state of the slab */
 	new.counters = old.counters;
-	if (freelist) {
-		new.inuse--;
-		set_freepointer(s, freelist, old.freelist);
+	if (freelist_tail) {
+		new.inuse -= free_delta;
+		set_freepointer(s, freelist_tail, old.freelist);
 		new.freelist = freelist;
 	} else
 		new.freelist = old.freelist;