With rmap batching from [1] -- rebased+changed on top of that -- we could turn
that into an effective (untested):
if (page && folio_test_anon(folio)) {
+ nr = folio_nr_pages_cont_mapped(folio, page, src_pte, addr, end,
+ pte, enforce_uffd_wp, &nr_dirty,
+ &nr_writable);
/*
* If this page may have been pinned by the parent process,
* copy the page immediately for the child so that we'll always
* guarantee the pinned page won't be randomly replaced in the
* future.
*/
- folio_get(folio);
- if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) {
+ folio_ref_add(folio, nr);
+ if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, nr, src_vma))) {
/* Page may be pinned, we have to copy. */
- folio_put(folio);
- return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
- addr, rss, prealloc, page);
+ folio_ref_sub(folio, nr);
+ ret = copy_present_page(dst_vma, src_vma, dst_pte,
+ src_pte, addr, rss, prealloc,
+ page);
+ return ret == 0 ? 1 : ret;
}
- rss[MM_ANONPAGES]++;
+ rss[MM_ANONPAGES] += nr;
} else if (page) {
- folio_get(folio);
- folio_dup_file_rmap_pte(folio, page);
- rss[mm_counter_file(page)]++;
+ nr = folio_nr_pages_cont_mapped(folio, page, src_pte, addr, end,
+ pte, enforce_uffd_wp, &nr_dirty,
+ &nr_writable);
+ folio_ref_add(folio, nr);
+ folio_dup_file_rmap_ptes(folio, page, nr);
+ rss[mm_counter_file(page)] += nr;
}
We'll have to test performance, but it could be that we want to specialize
more on !folio_test_large(). That code is very performance-sensitive.
[1] https://lkml.kernel.org/r/20231204142146.91437-1-david@xxxxxxxxxx
So, on top of [1] without rmap batching but with a slightly modified
version of yours (that keeps the existing code structure as pointed out
and e.g., updates counter updates), running my fork() microbenchmark
with a 1 GiB of memory:
Compared to [1], with all order-0 pages it gets 13--14% _slower_ and
with all PTE-mapped THP (order-9) it gets ~29--30% _faster_.
So looks like we really want to have a completely seprate code path for
"!folio_test_large()" to keep that case as fast as possible. And
"Likely" we want to use "likely(!folio_test_large()". ;)
Performing rmap batching on top of that code only slightly (another 1%
or so) improves performance in the PTE-mapped THP (order-9) case right
now, in contrast to other rmap batching. Reason is as all rmap code gets
inlined here and we're only doing subpage mapcount updates + PAE handling.
--
Cheers,
David / dhildenb
