2020-08-18 08:35:14

by Tianxianting

[permalink] [raw]
Subject: [PATCH] mm/memory-failure: do pgoff calculation before for_each_process()

There is no need to calcaulate pgoff in each loop of for_each_process(),
so move it to the place before for_each_process(), which can save some
CPU cycles.

Signed-off-by: Xianting Tian <[email protected]>
---
mm/memory-failure.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 47b8ccb1f..7dc2c9d3b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -484,11 +484,12 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
struct vm_area_struct *vma;
struct task_struct *tsk;
struct address_space *mapping = page->mapping;
+ pgoff_t pgoff;

i_mmap_lock_read(mapping);
read_lock(&tasklist_lock);
+ pgoff = page_to_pgoff(page);
for_each_process(tsk) {
- pgoff_t pgoff = page_to_pgoff(page);
struct task_struct *t = task_early_kill(tsk, force_early);

if (!t)
--
2.17.1


Subject: Re: [PATCH] mm/memory-failure: do pgoff calculation before for_each_process()

On Tue, Aug 18, 2020 at 04:26:47PM +0800, Xianting Tian wrote:
> There is no need to calcaulate pgoff in each loop of for_each_process(),
> so move it to the place before for_each_process(), which can save some
> CPU cycles.
>
> Signed-off-by: Xianting Tian <[email protected]>

Looks good to me. Thank you.

Acked-by: Naoya Horiguchi <[email protected]>