slab: Common Kmalloc cache determination

Extract the optimized lookup functions from slub and put them into
slab_common.c. Then make slab use these functions as well.

Joonsoo notes that this fixes some issues with constant folding which
also reduces the code size for slub.

https://lkml.org/lkml/2012/10/20/82

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2b0ebb6..6d73f0b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -328,6 +328,68 @@
 #endif
 
 /*
+ * Conversion table for small slabs sizes / 8 to the index in the
+ * kmalloc array. This is necessary for slabs < 192 since we have non power
+ * of two cache sizes there. The size of larger slabs can be determined using
+ * fls.
+ */
+static s8 size_index[24] = {
+	3,	/* 8 */
+	4,	/* 16 */
+	5,	/* 24 */
+	5,	/* 32 */
+	6,	/* 40 */
+	6,	/* 48 */
+	6,	/* 56 */
+	6,	/* 64 */
+	1,	/* 72 */
+	1,	/* 80 */
+	1,	/* 88 */
+	1,	/* 96 */
+	7,	/* 104 */
+	7,	/* 112 */
+	7,	/* 120 */
+	7,	/* 128 */
+	2,	/* 136 */
+	2,	/* 144 */
+	2,	/* 152 */
+	2,	/* 160 */
+	2,	/* 168 */
+	2,	/* 176 */
+	2,	/* 184 */
+	2	/* 192 */
+};
+
+static inline int size_index_elem(size_t bytes)
+{
+	return (bytes - 1) / 8;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ */
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+{
+	int index;
+
+	if (size <= 192) {
+		if (!size)
+			return ZERO_SIZE_PTR;
+
+		index = size_index[size_index_elem(size)];
+	} else
+		index = fls(size - 1);
+
+#ifdef CONFIG_ZONE_DMA
+	if (unlikely((flags & SLAB_CACHE_DMA)))
+		return kmalloc_dma_caches[index];
+
+#endif
+	return kmalloc_caches[index];
+}
+
+/*
  * Create the kmalloc array. Some of the regular kmalloc arrays
  * may already have been created because they were needed to
  * enable allocations for slab creation.
@@ -336,6 +398,47 @@
 {
 	int i;
 
+	/*
+	 * Patch up the size_index table if we have strange large alignment
+	 * requirements for the kmalloc array. This is only the case for
+	 * MIPS it seems. The standard arches will not generate any code here.
+	 *
+	 * Largest permitted alignment is 256 bytes due to the way we
+	 * handle the index determination for the smaller caches.
+	 *
+	 * Make sure that nothing crazy happens if someone starts tinkering
+	 * around with ARCH_KMALLOC_MINALIGN
+	 */
+	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
+		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
+
+	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
+		int elem = size_index_elem(i);
+
+		if (elem >= ARRAY_SIZE(size_index))
+			break;
+		size_index[elem] = KMALLOC_SHIFT_LOW;
+	}
+
+	if (KMALLOC_MIN_SIZE >= 64) {
+		/*
+		 * The 96 byte size cache is not used if the alignment
+		 * is 64 byte.
+		 */
+		for (i = 64 + 8; i <= 96; i += 8)
+			size_index[size_index_elem(i)] = 7;
+
+	}
+
+	if (KMALLOC_MIN_SIZE >= 128) {
+		/*
+		 * The 192 byte sized cache is not used if the alignment
+		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
+		 * instead.
+		 */
+		for (i = 128 + 8; i <= 192; i += 8)
+			size_index[size_index_elem(i)] = 8;
+	}
 	/* Caches that are not of the two-to-the-power-of size */
 	if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1])
 		kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
@@ -379,8 +482,6 @@
 	}
 #endif
 }
-
-
 #endif /* !CONFIG_SLOB */