[PATCH mm-new v7 4/5] mm: khugepaged: skip lazy-free folios

[Vernon Yang <vernon2gm@gmail.com>]

From: Vernon Yang <yanglincheng@kylinos.cn>

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 and then 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.

And if we collapse with a lazyfree page, that content will never be none
and the deferred shrinker cannot reclaim them.

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>
Acked-by: David Hildenbrand (arm) <david@kernel.org>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
---
 include/trace/events/huge_memory.h |  1 +
 mm/khugepaged.c                    | 13 +++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 384e29f6bef0..bcdc57eea270 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 8b68ae3bc2c5..0d160e612e16 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,
@@ -583,6 +584,12 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		folio = page_folio(page);
 		VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
 
+		if (cc->is_khugepaged && !pte_dirty(pteval) &&
+		    folio_test_lazyfree(folio)) {
+			result = SCAN_PAGE_LAZYFREE;
+			goto out;
+		}
+
 		/* See hpage_collapse_scan_pmd(). */
 		if (folio_maybe_mapped_shared(folio)) {
 			++shared;
@@ -1335,6 +1342,12 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 		}
 		folio = page_folio(page);
 
+		if (cc->is_khugepaged && !pte_dirty(pteval) &&
+		    folio_test_lazyfree(folio)) {
+			result = SCAN_PAGE_LAZYFREE;
+			goto out_unmap;
+		}
+
 		if (!folio_test_anon(folio)) {
 			result = SCAN_PAGE_ANON;
 			goto out_unmap;
-- 
2.51.0