2020-08-19 18:50:10

by Matthew Wilcox

Subject: [PATCH 3/8] mm: Optimise madvise WILLNEED

Instead of calling find_get_entry() for every page index, use an XArray
iterator to skip over NULL entries, and avoid calling get_page(),
because we only want the swap entries.

Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
---
mm/madvise.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index dd1d43cf026d..96189acd6969 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -224,25 +224,28 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct address_space *mapping)
{
- pgoff_t index;
+ XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
+ pgoff_t end_index = end / PAGE_SIZE;
struct page *page;
- swp_entry_t swap;

- for (; start < end; start += PAGE_SIZE) {
- index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+ rcu_read_lock();
+ xas_for_each(&xas, page, end_index) {
+ swp_entry_t swap;

- page = find_get_entry(mapping, index);
- if (!xa_is_value(page)) {
- if (page)
- put_page(page);
+ if (!xa_is_value(page))
continue;
- }
+ rcu_read_unlock();
+
swap = radix_to_swp_entry(page);
page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
NULL, 0, false);
if (page)
put_page(page);
+
+ rcu_read_lock();
+ xas_reset(&xas);
}
+ rcu_read_unlock();

lru_add_drain(); /* Push any new pages onto the LRU now */
}
--
2.28.0

2020-08-26 14:36:58

by Johannes Weiner

Subject: Re: [PATCH 3/8] mm: Optimise madvise WILLNEED

On Wed, Aug 19, 2020 at 07:48:45PM +0100, Matthew Wilcox (Oracle) wrote:
> Instead of calling find_get_entry() for every page index, use an XArray
> iterator to skip over NULL entries, and avoid calling get_page(),
> because we only want the swap entries.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>

Acked-by: Johannes Weiner <[email protected]>