mm: mlock: update mlock_pte_range to handle large folio

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 as if folio is not fully
    mapped to a VM_LOCKED VMA, if system is in memory pressure,
    page reclaim is allowed to pick up this folio, split it
    and reclaim the pages which are not in VM_LOCKED 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.

Link: https://lkml.kernel.org/r/20230918073318.1181104-4-fengwei.yin@intel.com
Signed-off-by: Yin Fengwei <fengwei.yin@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/mlock.c

@@ -305,6 +305,58 @@ 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);
+
+	for (i = 0; i < count; i++, pte++) {
+		pte_t entry = ptep_get(pte);
+
+		if (!pte_present(entry))
+			break;
+		if (pte_pfn(entry) - pfn >= nr)
+			break;
+	}
+
+	return i;
+}
+
+static inline bool allow_mlock_munlock(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long start,
+		unsigned long end, unsigned int step)
+{
+	/*
+	 * 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.
+	 */
+	if (!(vma->vm_flags & VM_LOCKED))
+		return true;
+
+	/* folio not in range [start, end), skip mlock */
+	if (!folio_within_range(folio, vma, start, end))
+		return false;
+
+	/* folio is not fully mapped, skip mlock */
+	if (step != folio_nr_pages(folio))
+		return false;
+
+	return true;
+}
+
 static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
 			   unsigned long end, struct mm_walk *walk)
 
@@ -314,6 +366,8 @@ 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;
+	unsigned long start = addr;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
@@ -334,6 +388,7 @@ 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 +396,19 @@ 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 (!allow_mlock_munlock(folio, vma, start, end, step))
+			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: