mm: split underused THPs

This is an attempt to mitigate the issue of running out of memory when THP
is always enabled.  During runtime whenever a THP is being faulted in
(__do_huge_pmd_anonymous_page) or collapsed by khugepaged
(collapse_huge_page), the THP is added to _deferred_list.  Whenever memory
reclaim happens in linux, the kernel runs the deferred_split shrinker
which goes through the _deferred_list.

If the folio was partially mapped, the shrinker attempts to split it.  If
the folio is not partially mapped, the shrinker checks if the THP was
underused, i.e.  how many of the base 4K pages of the entire THP were
zero-filled.  If this number goes above a certain threshold (decided by
/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none), the
shrinker will attempt to split that THP.  Then at remap time, the pages
that were zero-filled are mapped to the shared zeropage, hence saving
memory.

Link: https://lkml.kernel.org/r/20240830100438.3623486-6-usamaarif642@gmail.com
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
Suggested-by: Rik van Riel <riel@surriel.com>
Co-authored-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Alexander Zhu <alexlzhu@fb.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Shuang Zhai <zhais@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Shuang Zhai <szhai2@cs.rochester.edu>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 58 insertions, 2 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9bc435bef2e6..cec5bce046a0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1187,6 +1187,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(vma->vm_mm);
+		deferred_split_folio(folio, false);
 		spin_unlock(vmf->ptl);
 		count_vm_event(THP_FAULT_ALLOC);
 		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
@@ -3608,6 +3609,39 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
 	return READ_ONCE(ds_queue->split_queue_len);
 }
 
+static bool thp_underused(struct folio *folio)
+{
+	int num_zero_pages = 0, num_filled_pages = 0;
+	void *kaddr;
+	int i;
+
+	if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1)
+		return false;
+
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		kaddr = kmap_local_folio(folio, i * PAGE_SIZE);
+		if (!memchr_inv(kaddr, 0, PAGE_SIZE)) {
+			num_zero_pages++;
+			if (num_zero_pages > khugepaged_max_ptes_none) {
+				kunmap_local(kaddr);
+				return true;
+			}
+		} else {
+			/*
+			 * Another path for early exit once the number
+			 * of non-zero filled pages exceeds threshold.
+			 */
+			num_filled_pages++;
+			if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) {
+				kunmap_local(kaddr);
+				return false;
+			}
+		}
+		kunmap_local(kaddr);
+	}
+	return false;
+}
+
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
@@ -3645,13 +3679,35 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 
 	list_for_each_entry_safe(folio, next, &list, _deferred_list) {
+		bool did_split = false;
+		bool underused = false;
+
+		if (!folio_test_partially_mapped(folio)) {
+			underused = thp_underused(folio);
+			if (!underused)
+				goto next;
+		}
 		if (!folio_trylock(folio))
 			goto next;
-		/* split_huge_page() removes page from list on success */
-		if (!split_folio(folio))
+		if (!split_folio(folio)) {
+			did_split = true;
+			if (underused)
+				count_vm_event(THP_UNDERUSED_SPLIT_PAGE);
 			split++;
+		}
 		folio_unlock(folio);
 next:
+		/*
+		 * split_folio() removes folio from list on success.
+		 * Only add back to the queue if folio is partially mapped.
+		 * If thp_underused returns false, or if split_folio fails
+		 * in the case it was underused, then consider it used and
+		 * don't add it back to split_queue.
+		 */
+		if (!did_split && !folio_test_partially_mapped(folio)) {
+			list_del_init(&folio->_deferred_list);
+			ds_queue->split_queue_len--;
+		}
 		folio_put(folio);
 	}