mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-24 12:44:11 +08:00
mm/gup: accelerate thp gup even for "pages != NULL"
The acceleration of THP was done with ctx.page_mask, however it'll be
ignored if **pages is non-NULL.
The old optimization was introduced in 2013 in 240aadeedc
("mm:
accelerate mm_populate() treatment of THP pages"). It didn't explain why
we can't optimize the **pages non-NULL case. It's possible that at that
time the major goal was for mm_populate() which should be enough back
then.
Optimize thp for all cases, by properly looping over each subpage, doing
cache flushes, and boost refcounts / pincounts where needed in one go.
This can be verified using gup_test below:
# chrt -f 1 ./gup_test -m 512 -t -L -n 1024 -r 10
Before: 13992.50 ( +-8.75%)
After: 378.50 (+-69.62%)
Link: https://lkml.kernel.org/r/20230628215310.73782-6-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A . Shutemov <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
parent
ffe1e78612
commit
57edfcfd34
51
mm/gup.c
51
mm/gup.c
@ -1282,16 +1282,53 @@ retry:
|
||||
goto out;
|
||||
}
|
||||
next_page:
|
||||
if (pages) {
|
||||
pages[i] = page;
|
||||
flush_anon_page(vma, page, start);
|
||||
flush_dcache_page(page);
|
||||
ctx.page_mask = 0;
|
||||
}
|
||||
|
||||
page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
|
||||
if (page_increm > nr_pages)
|
||||
page_increm = nr_pages;
|
||||
|
||||
if (pages) {
|
||||
struct page *subpage;
|
||||
unsigned int j;
|
||||
|
||||
/*
|
||||
* This must be a large folio (and doesn't need to
|
||||
* be the whole folio; it can be part of it), do
|
||||
* the refcount work for all the subpages too.
|
||||
*
|
||||
* NOTE: here the page may not be the head page
|
||||
* e.g. when start addr is not thp-size aligned.
|
||||
* try_grab_folio() should have taken care of tail
|
||||
* pages.
|
||||
*/
|
||||
if (page_increm > 1) {
|
||||
struct folio *folio;
|
||||
|
||||
/*
|
||||
* Since we already hold refcount on the
|
||||
* large folio, this should never fail.
|
||||
*/
|
||||
folio = try_grab_folio(page, page_increm - 1,
|
||||
foll_flags);
|
||||
if (WARN_ON_ONCE(!folio)) {
|
||||
/*
|
||||
* Release the 1st page ref if the
|
||||
* folio is problematic, fail hard.
|
||||
*/
|
||||
gup_put_folio(page_folio(page), 1,
|
||||
foll_flags);
|
||||
ret = -EFAULT;
|
||||
goto out;
|
||||
}
|
||||
}
|
||||
|
||||
for (j = 0; j < page_increm; j++) {
|
||||
subpage = nth_page(page, j);
|
||||
pages[i + j] = subpage;
|
||||
flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
|
||||
flush_dcache_page(subpage);
|
||||
}
|
||||
}
|
||||
|
||||
i += page_increm;
|
||||
start += page_increm * PAGE_SIZE;
|
||||
nr_pages -= page_increm;
|
||||
|
Loading…
Reference in New Issue
Block a user