[RFC PATCH v2 3/3] mm: mlock: update mlock_pte_range to handle large folio

[Yin Fengwei]

Current kernel only lock base size folio during mlock syscall.
Add large folio support with following rules:
  - Only mlock large folio when it's in VM_LOCKED VMA range

  - If there is cow folio, mlock the cow folio as cow folio
    is also in VM_LOCKED VMA range.

  - munlock will apply to the large folio which is in VMA range
    or cross the VMA boundary.

The last rule is used to handle the case that the large folio is
mlocked, later the VMA is split in the middle of large folio
and this large folio become cross VMA boundary.

Signed-off-by: Yin Fengwei <fengwei.yin@xxxxxxxxx>
---
 mm/mlock.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 99 insertions(+), 5 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index 0a0c996c5c214..f49e079066870 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -305,6 +305,95 @@ void munlock_folio(struct folio *folio)
 	local_unlock(&mlock_fbatch.lock);
 }
 
+static inline bool should_mlock_folio(struct folio *folio,
+					struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_LOCKED)
+		return (!folio_test_large(folio) ||
+				folio_within_vma(folio, vma));
+
+	/*
+	 * For unlock, allow munlock large folio which is partially
+	 * mapped to VMA. As it's possible that large folio is
+	 * mlocked and VMA is split later.
+	 *
+	 * During memory pressure, such kind of large folio can
+	 * be split. And the pages are not in VM_LOCKed VMA
+	 * can be reclaimed.
+	 */
+
+	return true;
+}
+
+static inline unsigned int get_folio_mlock_step(struct folio *folio,
+			pte_t pte, unsigned long addr, unsigned long end)
+{
+	unsigned int nr;
+
+	nr = folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte);
+	return min_t(unsigned int, nr, (end - addr) >> PAGE_SHIFT);
+}
+
+void mlock_folio_range(struct folio *folio, struct vm_area_struct *vma,
+		pte_t *pte, unsigned long addr, unsigned int nr)
+{
+	struct folio *cow_folio;
+	unsigned int step = 1;
+
+	mlock_folio(folio);
+	if (nr == 1)
+		return;
+
+	for (; nr > 0; pte += step, addr += (step << PAGE_SHIFT), nr -= step) {
+		pte_t ptent;
+
+		step = 1;
+		ptent = ptep_get(pte);
+
+		if (!pte_present(ptent))
+			continue;
+
+		cow_folio = vm_normal_folio(vma, addr, ptent);
+		if (!cow_folio || cow_folio == folio) {
+			continue;
+		}
+
+		mlock_folio(cow_folio);
+		step = get_folio_mlock_step(folio, ptent,
+				addr, addr + (nr << PAGE_SHIFT));
+	}
+}
+
+void munlock_folio_range(struct folio *folio, struct vm_area_struct *vma,
+		pte_t *pte, unsigned long addr, unsigned int nr)
+{
+	struct folio *cow_folio;
+	unsigned int step = 1;
+
+	munlock_folio(folio);
+	if (nr == 1)
+		return;
+
+	for (; nr > 0; pte += step, addr += (step << PAGE_SHIFT), nr -= step) {
+		pte_t ptent;
+
+		step = 1;
+		ptent = ptep_get(pte);
+
+		if (!pte_present(ptent))
+			continue;
+
+		cow_folio = vm_normal_folio(vma, addr, ptent);
+		if (!cow_folio || cow_folio == folio) {
+			continue;
+		}
+
+		munlock_folio(cow_folio);
+		step = get_folio_mlock_step(folio, ptent,
+				addr, addr + (nr << PAGE_SHIFT));
+	}
+}
+
 static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 			   unsigned long end, struct mm_walk *walk)
 
@@ -314,6 +403,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 	pte_t *start_pte, *pte;
 	pte_t ptent;
 	struct folio *folio;
+	unsigned int step = 1;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
@@ -329,24 +419,28 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 		goto out;
 	}
 
-	start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	pte = start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!start_pte) {
 		walk->action = ACTION_AGAIN;
 		return 0;
 	}
-	for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
+
+	for (; addr != end; pte += step, addr += (step << PAGE_SHIFT)) {
+		step = 1;
 		ptent = ptep_get(pte);
 		if (!pte_present(ptent))
 			continue;
 		folio = vm_normal_folio(vma, addr, ptent);
 		if (!folio || folio_is_zone_device(folio))
 			continue;
-		if (folio_test_large(folio))
+		if (!should_mlock_folio(folio, vma))
 			continue;
+
+		step = get_folio_mlock_step(folio, ptent, addr, end);
 		if (vma->vm_flags & VM_LOCKED)
-			mlock_folio(folio);
+			mlock_folio_range(folio, vma, pte, addr, step);
 		else
-			munlock_folio(folio);
+			munlock_folio_range(folio, vma, pte, addr, step);
 	}
 	pte_unmap(start_pte);
 out:
-- 
2.39.2