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

[Yin Fengwei <fengwei.yin@intel.com>]

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
    and fully mapped to page table.

    fully mapped folio is required to handle the case that
    mremap happens in the middle of large folio and split
    pages of large folio to two different VMA.

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

    This is required to handle the case that the large folio is
    mlocked, later the VMA is split in the middle of large folio.

Signed-off-by: Yin Fengwei <fengwei.yin@intel.com>
---
 mm/mlock.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index 0a0c996c5c21..8056f9176b70 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -305,6 +305,50 @@ void munlock_folio(struct folio *folio)
 	local_unlock(&mlock_fbatch.lock);
 }
 
+static inline unsigned int folio_mlock_step(struct folio *folio,
+		pte_t *pte, unsigned long addr, unsigned long end)
+{
+	unsigned int count, i, nr = folio_nr_pages(folio);
+	unsigned long pfn = folio_pfn(folio);
+	pte_t ptent = ptep_get(pte);
+
+	if (!folio_test_large(folio))
+		return 1;
+
+	count = pfn + nr - pte_pfn(ptent);
+	count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT);
+
+	if (!pte)
+		return count;
+
+	for (i = 0; i < count; i++, pte++) {
+		pte_t entry = ptep_get(pte);
+
+		if (pte_none(entry) || !pte_present(entry))
+			break;
+		if (pte_pfn(entry) - pfn >= nr)
+			break;
+	}
+
+	return i;
+}
+
+static inline bool should_mlock_folio(struct folio *folio,
+				struct vm_area_struct *vma, pte_t *pte)
+{
+	/*
+	 * 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 !(vma->vm_flags & VM_LOCKED) ||
+			folio_within_vma(folio, vma, pte);
+}
+
 static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 			   unsigned long end, struct mm_walk *walk)
 
@@ -314,6 +358,7 @@ 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) {
@@ -334,6 +379,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 		walk->action = ACTION_AGAIN;
 		return 0;
 	}
+
 	for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = ptep_get(pte);
 		if (!pte_present(ptent))
@@ -341,12 +387,19 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 		folio = vm_normal_folio(vma, addr, ptent);
 		if (!folio || folio_is_zone_device(folio))
 			continue;
-		if (folio_test_large(folio))
-			continue;
+
+		step = folio_mlock_step(folio, pte, addr, end);
+		if (!should_mlock_folio(folio, vma, pte))
+			goto next_entry;
+
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_folio(folio);
 		else
 			munlock_folio(folio);
+
+next_entry:
+		pte += step - 1;
+		addr += (step - 1) << PAGE_SHIFT;
 	}
 	pte_unmap(start_pte);
 out:
-- 
2.39.2