Re: [PATCH v4 1/1] mm/highmem: Remove deprecated kmap_atomic
On Wed, 10 Feb 2021 16:33:07 -0800 Ira Weiny wrote: > > Signed-off-by: Ira Weiny > > This already has my signed off by so I'm not going to 'review'. With Prathu's > testing information I hope this can land. > > Andrew did you see this patch? I did now ;) Tossed onto the post-rc1 pile, thanks,
Re: [PATCH v4 1/1] mm/highmem: Remove deprecated kmap_atomic
On Thu, Feb 04, 2021 at 01:02:53PM +0530, Prathu Baronia wrote:
> From: Ira Weiny
>
> kmap_atomic() is being deprecated in favor of kmap_local_page().
>
> Replace the uses of kmap_atomic() within the highmem code.
>
> On profiling clear_huge_page() using ftrace an improvement
> of 62% was observed on the below setup.
>
> Setup:-
> Below data has been collected on Qualcomm's SM7250 SoC THP enabled
> (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76)
> switched on and set to max frequency, also DDR set to perf governor.
>
> FTRACE Data:-
>
> Base data:-
> Number of iterations: 48
> Mean of allocation time: 349.5 us
> std deviation: 74.5 us
>
> v4 data:-
> Number of iterations: 48
> Mean of allocation time: 131 us
> std deviation: 32.7 us
>
> The following simple userspace experiment to allocate
> 100MB(BUF_SZ) of pages and writing to it gave us a good insight,
> we observed an improvement of 42% in allocation and writing timings.
> -
> Test code snippet
> -
> clock_start();
> buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */
>
> for(i=0; i < BUF_SZ_PAGES; i++)
> {
> *((int *)(buf + (i*PAGE_SIZE))) = 1;
> }
> clock_end();
> -
>
> Malloc test timings for 100MB anon allocation:-
>
> Base data:-
> Number of iterations: 100
> Mean of allocation time: 31831 us
> std deviation: 4286 us
>
> v4 data:-
> Number of iterations: 100
> Mean of allocation time: 18193 us
> std deviation: 4915 us
>
> Signed-off-by: Ira Weiny
This already has my signed off by so I'm not going to 'review'. With Prathu's
testing information I hope this can land.
Andrew did you see this patch?
Thanks,
Ira
> Signed-off-by: Prathu Baronia
> [Updated commit text with test data]
> ---
> include/linux/highmem.h | 28 ++--
> 1 file changed, 14 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/highmem.h b/include/linux/highmem.h
> index d2c70d3772a3..9a202c7e4e26 100644
> --- a/include/linux/highmem.h
> +++ b/include/linux/highmem.h
> @@ -146,9 +146,9 @@ static inline void invalidate_kernel_vmap_range(void
> *vaddr, int size)
> #ifndef clear_user_highpage
> static inline void clear_user_highpage(struct page *page, unsigned long
> vaddr)
> {
> - void *addr = kmap_atomic(page);
> + void *addr = kmap_local_page(page);
> clear_user_page(addr, vaddr, page);
> - kunmap_atomic(addr);
> + kunmap_local(addr);
> }
> #endif
>
> @@ -199,9 +199,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct
> *vma,
>
> static inline void clear_highpage(struct page *page)
> {
> - void *kaddr = kmap_atomic(page);
> + void *kaddr = kmap_local_page(page);
> clear_page(kaddr);
> - kunmap_atomic(kaddr);
> + kunmap_local(kaddr);
> }
>
> /*
> @@ -216,7 +216,7 @@ static inline void zero_user_segments(struct page *page,
> unsigned start1, unsigned end1,
> unsigned start2, unsigned end2)
> {
> - void *kaddr = kmap_atomic(page);
> + void *kaddr = kmap_local_page(page);
> unsigned int i;
>
> BUG_ON(end1 > page_size(page) || end2 > page_size(page));
> @@ -227,7 +227,7 @@ static inline void zero_user_segments(struct page *page,
> if (end2 > start2)
> memset(kaddr + start2, 0, end2 - start2);
>
> - kunmap_atomic(kaddr);
> + kunmap_local(kaddr);
> for (i = 0; i < compound_nr(page); i++)
> flush_dcache_page(page + i);
> }
> @@ -252,11 +252,11 @@ static inline void copy_user_highpage(struct page *to,
> struct page *from,
> {
> char *vfrom, *vto;
>
> - vfrom = kmap_atomic(from);
> - vto = kmap_atomic(to);
> + vfrom = kmap_local_page(from);
> + vto = kmap_local_page(to);
> copy_user_page(vto, vfrom, vaddr, to);
> - kunmap_atomic(vto);
> - kunmap_atomic(vfrom);
> + kunmap_local(vto);
> + kunmap_local(vfrom);
> }
>
> #endif
> @@ -267,11 +267,11 @@ static inline void copy_highpage(struct page *to,
> struct page *from)
> {
> char *vfrom, *vto;
>
> - vfrom = kmap_atomic(from);
> - vto = kmap_atomic(to);
> + vfrom = kmap_local_page(from);
> + vto = kmap_local_page(to);
> copy_page(vto, vfrom);
> - kunmap_atomic(vto);
> - kunmap_atomic(vfrom);
> + kunmap_local(vto);
> + kunmap_local(vfrom);
> }
>
> #endif
> --
> 2.17.1
>
[PATCH v4 1/1] mm/highmem: Remove deprecated kmap_atomic
From: Ira Weiny
kmap_atomic() is being deprecated in favor of kmap_local_page().
Replace the uses of kmap_atomic() within the highmem code.
On profiling clear_huge_page() using ftrace an improvement
of 62% was observed on the below setup.
Setup:-
Below data has been collected on Qualcomm's SM7250 SoC THP enabled
(kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76)
switched on and set to max frequency, also DDR set to perf governor.
FTRACE Data:-
Base data:-
Number of iterations: 48
Mean of allocation time: 349.5 us
std deviation: 74.5 us
v4 data:-
Number of iterations: 48
Mean of allocation time: 131 us
std deviation: 32.7 us
The following simple userspace experiment to allocate
100MB(BUF_SZ) of pages and writing to it gave us a good insight,
we observed an improvement of 42% in allocation and writing timings.
-
Test code snippet
-
clock_start();
buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */
for(i=0; i < BUF_SZ_PAGES; i++)
{
*((int *)(buf + (i*PAGE_SIZE))) = 1;
}
clock_end();
-
Malloc test timings for 100MB anon allocation:-
Base data:-
Number of iterations: 100
Mean of allocation time: 31831 us
std deviation: 4286 us
v4 data:-
Number of iterations: 100
Mean of allocation time: 18193 us
std deviation: 4915 us
Signed-off-by: Ira Weiny
Signed-off-by: Prathu Baronia
[Updated commit text with test data]
---
include/linux/highmem.h | 28 ++--
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d2c70d3772a3..9a202c7e4e26 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -146,9 +146,9 @@ static inline void invalidate_kernel_vmap_range(void
*vaddr, int size)
#ifndef clear_user_highpage
static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
{
- void *addr = kmap_atomic(page);
+ void *addr = kmap_local_page(page);
clear_user_page(addr, vaddr, page);
- kunmap_atomic(addr);
+ kunmap_local(addr);
}
#endif
@@ -199,9 +199,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct
*vma,
static inline void clear_highpage(struct page *page)
{
- void *kaddr = kmap_atomic(page);
+ void *kaddr = kmap_local_page(page);
clear_page(kaddr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
}
/*
@@ -216,7 +216,7 @@ static inline void zero_user_segments(struct page *page,
unsigned start1, unsigned end1,
unsigned start2, unsigned end2)
{
- void *kaddr = kmap_atomic(page);
+ void *kaddr = kmap_local_page(page);
unsigned int i;
BUG_ON(end1 > page_size(page) || end2 > page_size(page));
@@ -227,7 +227,7 @@ static inline void zero_user_segments(struct page *page,
if (end2 > start2)
memset(kaddr + start2, 0, end2 - start2);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
for (i = 0; i < compound_nr(page); i++)
flush_dcache_page(page + i);
}
@@ -252,11 +252,11 @@ static inline void copy_user_highpage(struct page *to,
struct page *from,
{
char *vfrom, *vto;
- vfrom = kmap_atomic(from);
- vto = kmap_atomic(to);
+ vfrom = kmap_local_page(from);
+ vto = kmap_local_page(to);
copy_user_page(vto, vfrom, vaddr, to);
- kunmap_atomic(vto);
- kunmap_atomic(vfrom);
+ kunmap_local(vto);
+ kunmap_local(vfrom);
}
#endif
@@ -267,11 +267,11 @@ static inline void copy_highpage(struct page *to, struct
page *from)
{
char *vfrom, *vto;
- vfrom = kmap_atomic(from);
- vto = kmap_atomic(to);
+ vfrom = kmap_local_page(from);
+ vto = kmap_local_page(to);
copy_page(vto, vfrom);
- kunmap_atomic(vto);
- kunmap_atomic(vfrom);
+ kunmap_local(vto);
+ kunmap_local(vfrom);
}
#endif
--
2.17.1
