diff options
author | Ira Weiny <ira.weiny@intel.com> | 2021-11-05 21:45:06 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-06 21:30:43 +0100 |
commit | d2c20e51e3966bc668ef1ef21fbe90704286c8d0 (patch) | |
tree | 2b21e360ffc772b8b8c7b40ab1665cf67ea49a8c | |
parent | mm/zsmalloc.c: close race window between zs_pool_dec_isolated() and zs_unregi... (diff) | |
download | linux-d2c20e51e3966bc668ef1ef21fbe90704286c8d0.tar.xz linux-d2c20e51e3966bc668ef1ef21fbe90704286c8d0.zip |
mm/highmem: remove deprecated kmap_atomic
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
[willy@infradead.org: fix zero_user_segments()]
Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org
Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Prathu Baronia <prathu.baronia@oneplus.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r-- | include/linux/highmem.h | 28 | ||||
-rw-r--r-- | mm/highmem.c | 6 |
2 files changed, 17 insertions, 17 deletions
diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..31ebee36f26c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -143,9 +143,9 @@ 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 @@ -177,9 +177,9 @@ 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); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -202,7 +202,7 @@ 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)); @@ -213,7 +213,7 @@ 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); } @@ -238,11 +238,11 @@ 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 @@ -253,11 +253,11 @@ 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 diff --git a/mm/highmem.c b/mm/highmem.c index 4212ad0e4a19..eb3b8c288de4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -383,7 +383,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); if (end1 > start1) { - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start1, 0, this_end - start1); } end1 -= this_end; @@ -398,7 +398,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, if (end2 > start2) { if (!kaddr) - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start2, 0, this_end - start2); } end2 -= this_end; @@ -406,7 +406,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, } if (kaddr) { - kunmap_atomic(kaddr); + kunmap_local(kaddr); flush_dcache_page(page + i); } |