Commit a4130bbe authored by Lance Yang's avatar Lance Yang Committed by Liu Shixin
Browse files

mm/vmscan: avoid split lazyfree THP during shrink_folio_list() 

mainline inclusion
from mainline-v6.11-rc1
commit 735ecdfaf4e802209caf34b7ac45adf448c54ccc
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/IAIHQO

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=735ecdfaf4e802209caf34b7ac45adf448c54ccc

--------------------------------

When the user no longer requires the pages, they would use
madvise(MADV_FREE) to mark the pages as lazy free.  Subsequently, they
typically would not re-write to that memory again.

During memory reclaim, if we detect that the large folio and its PMD are
both still marked as clean and there are no unexpected references (such as
GUP), so we can just discard the memory lazily, improving the efficiency
of memory reclamation in this case.

On an Intel i5 CPU, reclaiming 1GiB of lazyfree THPs using
mem_cgroup_force_empty() results in the following runtimes in seconds
(shorter is better):

--------------------------------------------
|     Old       |      New       |  Change  |
--------------------------------------------
|   0.683426    |    0.049197    |  -92.80% |
--------------------------------------------

[ioworker0@gmail.com: minor changes per David]
  Link: https://lkml.kernel.org/r/20240622100057.3352-1-ioworker0@gmail.com
Link: https://lkml.kernel.org/r/20240614015138.31461-4-ioworker0@gmail.com


Signed-off-by: default avatarLance Yang <ioworker0@gmail.com>
Suggested-by: default avatarZi Yan <ziy@nvidia.com>
Suggested-by: default avatarDavid Hildenbrand <david@redhat.com>
Cc: Bang Li <libang.li@antgroup.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Fangrui Song <maskray@google.com>
Cc: Jeff Xie <xiehuan09@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLiu Shixin <liushixin2@huawei.com>
parent e9c07c32

include/linux/huge_mm.h

+9 −0
Original line number Diff line number Diff line
@@ -421,6 +421,8 @@ static inline bool thp_migration_supported(void) 


void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,

			   pmd_t *pmd, bool freeze, struct folio *folio);

bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,

			   pmd_t *pmdp, struct folio *folio);



#else /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -484,6 +486,13 @@ static inline void split_huge_pmd_locked(struct vm_area_struct *vma, 
					 unsigned long address, pmd_t *pmd,

					 bool freeze, struct folio *folio) {}



static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,

					 unsigned long addr, pmd_t *pmdp,

					 struct folio *folio)

{

	return false;

}



#define split_huge_pud(__vma, __pmd, __address)	\

	do { } while (0)

mm/huge_memory.c

+66 −0
Original line number Diff line number Diff line
@@ -2857,6 +2857,72 @@ static void unmap_folio(struct folio *folio) 
	try_to_unmap_flush();

}



static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma,

					    unsigned long addr, pmd_t *pmdp,

					    struct folio *folio)

{

	struct mm_struct *mm = vma->vm_mm;

	int ref_count, map_count;

	pmd_t orig_pmd = *pmdp;

	struct page *page;



	if (folio_test_dirty(folio) || pmd_dirty(orig_pmd))

		return false;



	orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp);



	/*

	 * Syncing against concurrent GUP-fast:

	 * - clear PMD; barrier; read refcount

	 * - inc refcount; barrier; read PMD

	 */

	smp_mb();



	ref_count = folio_ref_count(folio);

	map_count = folio_mapcount(folio);



	/*

	 * Order reads for folio refcount and dirty flag

	 * (see comments in __remove_mapping()).

	 */

	smp_rmb();



	/*

	 * If the folio or its PMD is redirtied at this point, or if there

	 * are unexpected references, we will give up to discard this folio

	 * and remap it.

	 *

	 * The only folio refs must be one from isolation plus the rmap(s).

	 */

	if (folio_test_dirty(folio) || pmd_dirty(orig_pmd) ||

	    ref_count != map_count + 1) {

		set_pmd_at(mm, addr, pmdp, orig_pmd);

		return false;

	}



	folio_remove_rmap_pmd(folio, page, vma);

	zap_deposited_table(mm, pmdp);

	add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR);

	if (vma->vm_flags & VM_LOCKED)

		mlock_drain_local();

	folio_put(folio);



	return true;

}



bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,

			   pmd_t *pmdp, struct folio *folio)

{

	VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio);

	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);

	VM_WARN_ON_ONCE(!IS_ALIGNED(addr, HPAGE_PMD_SIZE));



	if (folio_test_anon(folio) && !folio_test_swapbacked(folio))

		return __discard_anon_folio_pmd_locked(vma, addr, pmdp, folio);



	return false;

}



static void remap_page(struct folio *folio, unsigned long nr)

{

	int i = 0;

mm/rmap.c

+16 −10
Original line number Diff line number Diff line
@@ -1653,17 +1653,23 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, 
			goto walk_abort;

		}



		if (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)) {

		if (!pvmw.pte) {

			if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd,

						  folio))

				goto walk_done;



			if (flags & TTU_SPLIT_HUGE_PMD) {

				/*

			 * We temporarily have to drop the PTL and start once

			 * again from that now-PTE-mapped page table.

				 * We temporarily have to drop the PTL and

				 * restart so we can process the PTE-mapped THP.

				 */

			split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd,

					      false, folio);

				split_huge_pmd_locked(vma, pvmw.address,

						      pvmw.pmd, false, folio);

				flags &= ~TTU_SPLIT_HUGE_PMD;

				page_vma_mapped_walk_restart(&pvmw);

				continue;

			}

		}



		/* Unexpected PMD-mapped THP? */

		VM_BUG_ON_FOLIO(!pvmw.pte, folio);