From: Manfred Spraul <manfred@colorfullife.com>

Below is a patch that redefines the kmem_cache_alloc `align' argument:

- align not zero: use the specified alignment.  I think values smaller than
  sizeof(void*) will work, even on archs with strict alignment requirement (or
  at least: slab shouldn't crash.  Obviously the user must handle the
  alignment properly).

- align zero:
* debug on: align to sizeof(void*)
* debug off, SLAB_HWCACHE_ALIGN clear: align to sizeof(void*)
* debug off, SLAB_HWCACHE_ALIGN set: align to the smaller of
   - cache_line_size()
   - the object size, rounded up to the next power of two.
  Slab never honored cache align for tiny objects: otherwise the 32-byte
  kmalloc objects would use 128 byte objects.

There is one additional point: right now slab uses ints for the bufctls. 
Using short would save two bytes for each object.  Initially I had used short,
but davem objected.  IIRC because some archs do not handle short efficiently. 
Should I allow arch overrides for the bufctls?  On i386, saving two bytes
might allow a few additional anon_vma objects in each page.


---

 25-akpm/mm/slab.c |   25 ++++++++++++-------------
 1 files changed, 12 insertions(+), 13 deletions(-)

diff -puN mm/slab.c~slab-alignment-fixes mm/slab.c
--- 25/mm/slab.c~slab-alignment-fixes	Wed Apr 21 14:44:16 2004
+++ 25-akpm/mm/slab.c	Wed Apr 21 14:44:16 2004
@@ -1150,14 +1150,22 @@ kmem_cache_create (const char *name, siz
 		BUG();
 
 	if (align) {
-		/* minimum supported alignment: */
-		if (align < BYTES_PER_WORD)
-			align = BYTES_PER_WORD;
-
 		/* combinations of forced alignment and advanced debugging is
 		 * not yet implemented.
 		 */
 		flags &= ~(SLAB_RED_ZONE|SLAB_STORE_USER);
+	} else {
+		if (flags & SLAB_HWCACHE_ALIGN) {
+			/* Default alignment: as specified by the arch code.
+			 * Except if an object is really small, then squeeze multiple
+			 * into one cacheline.
+			 */
+			align = cache_line_size();
+			while (size <= align/2)
+				align /= 2;
+		} else {
+			align = BYTES_PER_WORD;
+		}
 	}
 
 	/* Get cache's description obj. */
@@ -1210,15 +1218,6 @@ kmem_cache_create (const char *name, siz
 		 */
 		flags |= CFLGS_OFF_SLAB;
 
-	if (!align) {
-		/* Default alignment: compile time specified l1 cache size.
-		 * Except if an object is really small, then squeeze multiple
-		 * into one cacheline.
-		 */
-		align = cache_line_size();
-		while (size <= align/2)
-			align /= 2;
-	}
 	size = ALIGN(size, align);
 
 	/* Cal size (in pages) of slabs, and the num of objs per slab.

_