slub: add support for kmem_cache_debug in bulk calls

Per request of Joonsoo Kim adding kmem debug support.

I've tested that when debugging is disabled, then there is almost no
performance impact as this code basically gets removed by the compiler.

Need some guidance in enabling and testing this.

bulk- PREVIOUS                  - THIS-PATCH
  1 -  43 cycles(tsc) 10.811 ns -  44 cycles(tsc) 11.236 ns  improved  -2.3%
  2 -  27 cycles(tsc)  6.867 ns -  28 cycles(tsc)  7.019 ns  improved  -3.7%
  3 -  21 cycles(tsc)  5.496 ns -  22 cycles(tsc)  5.526 ns  improved  -4.8%
  4 -  24 cycles(tsc)  6.038 ns -  19 cycles(tsc)  4.786 ns  improved  20.8%
  8 -  17 cycles(tsc)  4.280 ns -  18 cycles(tsc)  4.572 ns  improved  -5.9%
 16 -  17 cycles(tsc)  4.483 ns -  18 cycles(tsc)  4.658 ns  improved  -5.9%
 30 -  18 cycles(tsc)  4.531 ns -  18 cycles(tsc)  4.568 ns  improved   0.0%
 32 -  58 cycles(tsc) 14.586 ns -  65 cycles(tsc) 16.454 ns  improved -12.1%
 34 -  53 cycles(tsc) 13.391 ns -  63 cycles(tsc) 15.932 ns  improved -18.9%
 48 -  65 cycles(tsc) 16.268 ns -  50 cycles(tsc) 12.506 ns  improved  23.1%
 64 -  53 cycles(tsc) 13.440 ns -  63 cycles(tsc) 15.929 ns  improved -18.9%
128 -  79 cycles(tsc) 19.899 ns -  86 cycles(tsc) 21.583 ns  improved  -8.9%
158 -  90 cycles(tsc) 22.732 ns -  90 cycles(tsc) 22.552 ns  improved   0.0%
250 -  95 cycles(tsc) 23.916 ns -  98 cycles(tsc) 24.589 ns  improved  -3.2%

Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Pekka Enberg <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/slub.c

@@ -2757,19 +2757,20 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 	struct page *page;
 	int i;
 
-	/* Debugging fallback to generic bulk */
-	if (kmem_cache_debug(s))
-		return __kmem_cache_free_bulk(s, size, p);
-
 	local_irq_disable();
 	c = this_cpu_ptr(s->cpu_slab);
 
 	for (i = 0; i < size; i++) {
 		void *object = p[i];
 
 		BUG_ON(!object);
+		/* kmem cache debug support */
+		s = cache_from_obj(s, object);
+		if (unlikely(!s))
+			goto exit;
+		slab_free_hook(s, object);
+
 		page = virt_to_head_page(object);
-		BUG_ON(s != page->slab_cache); /* Check if valid slab page */
 
 		if (c->page == page) {
 			/* Fastpath: local CPU free */
@@ -2784,6 +2785,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 			c = this_cpu_ptr(s->cpu_slab);
 		}
 	}
+exit:
 	c->tid = next_tid(c->tid);
 	local_irq_enable();
 }
@@ -2796,10 +2798,6 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	struct kmem_cache_cpu *c;
 	int i;
 
-	/* Debugging fallback to generic bulk */
-	if (kmem_cache_debug(s))
-		return __kmem_cache_alloc_bulk(s, flags, size, p);
-
 	/*
 	 * Drain objects in the per cpu slab, while disabling local
 	 * IRQs, which protects against PREEMPT and interrupts
@@ -2828,8 +2826,20 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			continue; /* goto for-loop */
 		}
 
+		/* kmem_cache debug support */
+		s = slab_pre_alloc_hook(s, flags);
+		if (unlikely(!s)) {
+			__kmem_cache_free_bulk(s, i, p);
+			c->tid = next_tid(c->tid);
+			local_irq_enable();
+			return false;
+		}
+
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
+
+		/* kmem_cache debug support */
+		slab_post_alloc_hook(s, flags, object);
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();