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

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: Lance Yang <ioworker0@gmail.com>
Suggested-by: Zi Yan <ziy@nvidia.com>
Suggested-by: David 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: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 82 insertions, 10 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b247490a0931..18bcd7672a89 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2689,6 +2689,72 @@ 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;
diff --git a/mm/rmap.c b/mm/rmap.c
index 42ffdcdfcd27..69cbd7ac2a5c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1678,16 +1678,22 @@ 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)) {
-			/*
-			 * We temporarily have to drop the PTL and start once
-			 * again from that now-PTE-mapped page table.
-			 */
-			split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd,
-					      false, folio);
-			flags &= ~TTU_SPLIT_HUGE_PMD;
-			page_vma_mapped_walk_restart(&pvmw);
-			continue;
+		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
+				 * restart so we can process the PTE-mapped THP.
+				 */
+				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? */