[PATCH mm-new v4 5/6] mm: khugepaged: skip lazy-free folios at scanning

[Vernon Yang <vernon2gm@gmail.com>]

For example, create three task: hot1 -> cold -> hot2. After all three
task are created, each allocate memory 128MB. the hot1/hot2 task
continuously access 128 MB memory, while the cold task only accesses
its memory briefly andthen call madvise(MADV_FREE). However, khugepaged
still prioritizes scanning the cold task and only scans the hot2 task
after completing the scan of the cold task.

So if the user has explicitly informed us via MADV_FREE that this memory
will be freed, it is appropriate for khugepaged to skip it only, thereby
avoiding unnecessary scan and collapse operations to reducing CPU
wastage.

Here are the performance test results:
(Throughput bigger is better, other smaller is better)

Testing on x86_64 machine:

| task hot2           | without patch | with patch    |  delta  |
|---------------------|---------------|---------------|---------|
| total accesses time |  3.14 sec     |  2.93 sec     | -6.69%  |
| cycles per access   |  4.96         |  2.21         | -55.44% |
| Throughput          |  104.38 M/sec |  111.89 M/sec | +7.19%  |
| dTLB-load-misses    |  284814532    |  69597236     | -75.56% |

Testing on qemu-system-x86_64 -enable-kvm:

| task hot2           | without patch | with patch    |  delta  |
|---------------------|---------------|---------------|---------|
| total accesses time |  3.35 sec     |  2.96 sec     | -11.64% |
| cycles per access   |  7.29         |  2.07         | -71.60% |
| Throughput          |  97.67 M/sec  |  110.77 M/sec | +13.41% |
| dTLB-load-misses    |  241600871    |  3216108      | -98.67% |

Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
---
 include/trace/events/huge_memory.h |  1 +
 mm/khugepaged.c                    | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 3d1069c3f0c5..e3856f8ab9eb 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -25,6 +25,7 @@
 	EM( SCAN_PAGE_LRU,		"page_not_in_lru")		\
 	EM( SCAN_PAGE_LOCK,		"page_locked")			\
 	EM( SCAN_PAGE_ANON,		"page_not_anon")		\
+	EM( SCAN_PAGE_LAZYFREE,		"page_lazyfree")		\
 	EM( SCAN_PAGE_COMPOUND,		"page_compound")		\
 	EM( SCAN_ANY_PROCESS,		"no_process_for_page")		\
 	EM( SCAN_VMA_NULL,		"vma_null")			\
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6df2857d94c6..8a7008760566 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -46,6 +46,7 @@ enum scan_result {
 	SCAN_PAGE_LRU,
 	SCAN_PAGE_LOCK,
 	SCAN_PAGE_ANON,
+	SCAN_PAGE_LAZYFREE,
 	SCAN_PAGE_COMPOUND,
 	SCAN_ANY_PROCESS,
 	SCAN_VMA_NULL,
@@ -1258,6 +1259,7 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 	pmd_t *pmd;
 	pte_t *pte, *_pte;
 	int none_or_zero = 0, shared = 0, referenced = 0;
+	int lazyfree = 0;
 	enum scan_result result = SCAN_FAIL;
 	struct page *page = NULL;
 	struct folio *folio = NULL;
@@ -1343,6 +1345,21 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 		}
 		folio = page_folio(page);
 
+		if (cc->is_khugepaged && !pte_dirty(pteval) &&
+		    folio_is_lazyfree(folio)) {
+			++lazyfree;
+
+			/*
+			 * The lazyfree folios are reclaimed and become pte_none.
+			 * Ensure they do not continue to be collapsed when
+			 * skipped ahead.
+			 */
+			if ((lazyfree + none_or_zero) > khugepaged_max_ptes_none) {
+				result = SCAN_PAGE_LAZYFREE;
+				goto out_unmap;
+			}
+		}
+
 		if (!folio_test_anon(folio)) {
 			result = SCAN_PAGE_ANON;
 			goto out_unmap;
-- 
2.51.0