From: Matthew Wilcox <[email protected]>
zram was the motivation for creating memset_l(). Minchan Kim sees a 7%
performance improvement on x86 with 100MB of non-zero deduplicatable
data:
perf stat -r 10 dd if=/dev/zram0 of=/dev/null
vanilla: 0.232050465 seconds time elapsed ( +- 0.51% )
memset_l: 0.217219387 seconds time elapsed ( +- 0.07% )
Signed-off-by: Matthew Wilcox <[email protected]>
Tested-by: Minchan Kim <[email protected]>
---
drivers/block/zram/zram_drv.c | 15 +++------------
1 file changed, 3 insertions(+), 12 deletions(-)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e27d89a36c34..25dcad309695 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -157,20 +157,11 @@ static inline void update_used_max(struct zram *zram,
} while (old_max != cur_max);
}
-static inline void zram_fill_page(char *ptr, unsigned long len,
+static inline void zram_fill_page(void *ptr, unsigned long len,
unsigned long value)
{
- int i;
- unsigned long *page = (unsigned long *)ptr;
-
WARN_ON_ONCE(!IS_ALIGNED(len, sizeof(unsigned long)));
-
- if (likely(value == 0)) {
- memset(ptr, 0, len);
- } else {
- for (i = 0; i < len / sizeof(*page); i++)
- page[i] = value;
- }
+ memset_l(ptr, value, len / sizeof(unsigned long));
}
static bool page_same_filled(void *ptr, unsigned long *element)
@@ -193,7 +184,7 @@ static bool page_same_filled(void *ptr, unsigned long
*element)
static void handle_same_page(struct bio_vec *bvec, unsigned long element)
{
struct page *page = bvec->bv_page;
- void *user_mem;
+ char *user_mem;
user_mem = kmap_atomic(page);
zram_fill_page(user_mem + bvec->bv_offset, bvec->bv_len, element);
--
2.11.0
