* [PATCH v1] ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean
@ 2013-05-15 4:09 Ming Lei
2013-06-19 9:04 ` Marek Szyprowski
0 siblings, 1 reply; 3+ messages in thread
From: Ming Lei @ 2013-05-15 4:09 UTC (permalink / raw)
To: linux-arm-kernel
It is common for one sg to include many pages, so mark all these
pages as clean to avoid unnecessary flushing on them in
set_pte_at() or update_mmu_cache().
The patch might improve loading performance of applciation code a bit.
On the below test code to read file(~1GByte size) from usb mass storage
disk to buffer created with mmap(PROT_READ | PROT_EXEC) on
Pandaboard, average ~1% improvement can be observed with the patch on
10 times test.
unsigned int sum = 0;
static unsigned long tv_diff(struct timeval *tv1, struct timeval *tv2)
{
return (tv2->tv_sec - tv1->tv_sec) * 1000000 +
(tv2->tv_usec - tv1->tv_usec);
}
int main(int argc, char *argv[])
{
char *mbuffer;
int fd;
int i;
unsigned long page_size, size;
struct stat stat;
struct timeval t1, t2;
page_size = getpagesize();
fd = open(argv[1], O_RDONLY);
assert(fd >= 0);
fstat(fd, &stat);
size = stat.st_size;
printf("%s: file %s, file size %lu, page size %lu\n", argv[0],
read_filename, size, page_size);
gettimeofday(&t1, NULL);
mbuffer = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_SHARED, fd, 0);
for (i = 0 ; i < size ; i += page_size)
sum += mbuffer[i];
munmap(mbuffer, page_size);
gettimeofday(&t2, NULL);
printf("\tread mmaped time: %luus\n", tv_diff(&t1, &t2));
close(fd);
}
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
v1:
- fix one mistake on computing pfn, pointed out by Nicolas
arch/arm/mm/dma-mapping.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3..c038ec0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
/*
- * Mark the D-cache clean for this page to avoid extra flushing.
+ * Mark the D-cache clean for these pages to avoid extra flushing.
*/
- if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
- set_bit(PG_dcache_clean, &page->flags);
+ if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+ unsigned long pfn;
+ size_t left = size;
+
+ pfn = page_to_pfn(page) + off / PAGE_SIZE;
+ off %= PAGE_SIZE;
+ if (off) {
+ pfn++;
+ left -= PAGE_SIZE - off;
+ }
+ while (left >= PAGE_SIZE) {
+ page = pfn_to_page(pfn++);
+ set_bit(PG_dcache_clean, &page->flags);
+ left -= PAGE_SIZE;
+ }
+ }
}
/**
--
1.7.9.5
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH v1] ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean
2013-05-15 4:09 [PATCH v1] ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean Ming Lei
@ 2013-06-19 9:04 ` Marek Szyprowski
2013-06-19 11:47 ` Ming Lei
0 siblings, 1 reply; 3+ messages in thread
From: Marek Szyprowski @ 2013-06-19 9:04 UTC (permalink / raw)
To: linux-arm-kernel
Hello,
On 5/15/2013 6:09 AM, Ming Lei wrote:
> It is common for one sg to include many pages, so mark all these
> pages as clean to avoid unnecessary flushing on them in
> set_pte_at() or update_mmu_cache().
>
> The patch might improve loading performance of applciation code a bit.
>
> On the below test code to read file(~1GByte size) from usb mass storage
> disk to buffer created with mmap(PROT_READ | PROT_EXEC) on
> Pandaboard, average ~1% improvement can be observed with the patch on
> 10 times test.
>
> unsigned int sum = 0;
>
> static unsigned long tv_diff(struct timeval *tv1, struct timeval *tv2)
> {
> return (tv2->tv_sec - tv1->tv_sec) * 1000000 +
> (tv2->tv_usec - tv1->tv_usec);
> }
>
> int main(int argc, char *argv[])
> {
> char *mbuffer;
> int fd;
> int i;
> unsigned long page_size, size;
> struct stat stat;
> struct timeval t1, t2;
>
> page_size = getpagesize();
> fd = open(argv[1], O_RDONLY);
> assert(fd >= 0);
>
> fstat(fd, &stat);
> size = stat.st_size;
> printf("%s: file %s, file size %lu, page size %lu\n", argv[0],
> read_filename, size, page_size);
>
> gettimeofday(&t1, NULL);
> mbuffer = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_SHARED, fd, 0);
> for (i = 0 ; i < size ; i += page_size)
> sum += mbuffer[i];
> munmap(mbuffer, page_size);
> gettimeofday(&t2, NULL);
> printf("\tread mmaped time: %luus\n", tv_diff(&t1, &t2));
>
> close(fd);
> }
>
> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> Cc: Russell King <linux@arm.linux.org.uk>
> Signed-off-by: Ming Lei <ming.lei@canonical.com>
Thanks for proving this patch. I'm really sorry for a late reply. I've
applied it to my dma-mapping tree.
> ---
> v1:
> - fix one mistake on computing pfn, pointed out by Nicolas
>
> arch/arm/mm/dma-mapping.c | 20 +++++++++++++++++---
> 1 file changed, 17 insertions(+), 3 deletions(-)
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index ef3e0f3..c038ec0 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
> dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
>
> /*
> - * Mark the D-cache clean for this page to avoid extra flushing.
> + * Mark the D-cache clean for these pages to avoid extra flushing.
> */
> - if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
> - set_bit(PG_dcache_clean, &page->flags);
> + if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
> + unsigned long pfn;
> + size_t left = size;
> +
> + pfn = page_to_pfn(page) + off / PAGE_SIZE;
> + off %= PAGE_SIZE;
> + if (off) {
> + pfn++;
> + left -= PAGE_SIZE - off;
> + }
> + while (left >= PAGE_SIZE) {
> + page = pfn_to_page(pfn++);
> + set_bit(PG_dcache_clean, &page->flags);
> + left -= PAGE_SIZE;
> + }
> + }
> }
>
> /**
Best regards
--
Marek Szyprowski
Samsung R&D Institute Poland
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH v1] ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean
2013-06-19 9:04 ` Marek Szyprowski
@ 2013-06-19 11:47 ` Ming Lei
0 siblings, 0 replies; 3+ messages in thread
From: Ming Lei @ 2013-06-19 11:47 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jun 19, 2013 at 5:04 PM, Marek Szyprowski
<m.szyprowski@samsung.com> wrote:
>
> Thanks for proving this patch. I'm really sorry for a late reply. I've
> applied it to my dma-mapping tree.
That is fine, and the patch has been applied in rmk's patch system.
Thanks,
--
Ming Lei
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2013-06-19 11:47 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-05-15 4:09 [PATCH v1] ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean Ming Lei
2013-06-19 9:04 ` Marek Szyprowski
2013-06-19 11:47 ` Ming Lei
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.