Rasmus Villemoes suggestes to move the aliment check into a separate
function in order to improve the readability.
Furthermore, let's avoid the switch statement since gcc might mess it
up. My gcc 4.9.2 produces the same code for the x86_64
configuration. That is
switch (size) {
case 4:
if (alignment_ok(base, 4))
swap_func = u32_swap;
break;
case 8:
if (alignment_ok(base, 8))
swap_func = u64_swap;
break;
}
if (!swap_func)
swap_func = generic_swap;
}
resulted into the same object code.
Link: https://lkml.org/lkml/2015/5/15/89
Signed-off-by: Daniel Wagner <[email protected]>
Suggested-by: Rasmus Villemoes <[email protected]>
Cc: Andrew Morton <[email protected]>
--
Hi,
I did this patch on top of current mmotm tree [1]. Hopefully I got
this right, if you want it merged into v2 of this patch or any
different version just let me know. Eventually I will get this right
:)
cheers,
daniel
[1] http://ozlabs.org/~akpm/mmotm/
---
lib/sort.c | 30 +++++++++---------------------
1 file changed, 9 insertions(+), 21 deletions(-)
diff --git a/lib/sort.c b/lib/sort.c
index 9c6b229..fc20df4 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -8,6 +8,12 @@
#include <linux/export.h>
#include <linux/sort.h>
+static int alignment_ok(const void *base, int align)
+{
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+ ((unsigned long)base & (align - 1)) == 0;
+}
+
static void u32_swap(void *a, void *b, int size)
{
u32 t = *(u32 *)a;
@@ -58,29 +64,11 @@ void sort(void *base, size_t num, size_t size,
int i = (num/2 - 1) * size, n = num * size, c, r;
if (!swap_func) {
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
- switch (size) {
- case 4:
+ if (size == 4 && alignment_ok(base, 4))
swap_func = u32_swap;
- break;
- case 8:
+ else if (size == 8 && alignment_ok(base, 8))
swap_func = u64_swap;
- break;
- }
-#else
- switch (size) {
- case 4:
- if (((unsigned long)base & 3) == 0)
- swap_func = u32_swap;
- break;
- case 8:
- if (((unsigned long)base & 7) == 0)
- swap_func = u64_swap;
- break;
- }
-#endif /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
-
- if (!swap_func)
+ else
swap_func = generic_swap;
}
--
2.1.0