[PATCH v3 3/9] mm/hugetlb: make pud_huge() and follow_huge_pud() aware of non-present pud entry

[Naoya Horiguchi]

From: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>

follow_pud_mask() does not support non-present pud entry now.  As long as
I tested on x86_64 server, follow_pud_mask() still simply returns
no_page_table() for non-present_pud_entry() due to pud_bad(), so no severe
user-visible effect should happen.  But generally we should call
follow_huge_pud() for non-present pud entry for 1GB hugetlb page.

Update pud_huge() and follow_huge_pud() to handle non-present pud entries.
The changes are similar to previous works for pud entries commit e66f17ff7177
("mm/hugetlb: take page table lock in follow_huge_pmd()") and commit
cbef8478bee5 ("mm/hugetlb: pmd_huge() returns true for non-present hugepage").

Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
---
v2 -> v3:
- fixed typos in subject and description,
- added comment on pud_huge(),
- added comment about fallback for hwpoisoned entry,
- updated initial check about FOLL_{PIN,GET} flags.
---
 arch/x86/mm/hugetlbpage.c |  8 +++++++-
 mm/hugetlb.c              | 32 ++++++++++++++++++++++++++++++--
 2 files changed, 37 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index a0d023cb4292..9c8193df0187 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -68,9 +68,15 @@ int pmd_huge(pmd_t pmd)
 		(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
 }
 
+/*
+ * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal
+ * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
+ * Otherwise, returns 0.
+ */
 int pud_huge(pud_t pud)
 {
-	return !!(pud_val(pud) & _PAGE_PSE);
+	return !pud_none(pud) &&
+		(pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
 }
 #endif
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 03fdf342f5f2..4c30f3fcfe50 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6963,10 +6963,38 @@ struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
 		pud_t *pud, int flags)
 {
-	if (flags & (FOLL_GET | FOLL_PIN))
+	struct page *page = NULL;
+	spinlock_t *ptl;
+	pte_t pte;
+
+	if (WARN_ON_ONCE(flags & FOLL_PIN))
 		return NULL;
 
-	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+retry:
+	ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud);
+	if (!pud_huge(*pud))
+		goto out;
+	pte = huge_ptep_get((pte_t *)pud);
+	if (pte_present(pte)) {
+		page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+			page = NULL;
+			goto out;
+		}
+	} else {
+		if (is_hugetlb_entry_migration(pte)) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, (pte_t *)pud, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
+	return page;
 }
 
 struct page * __weak
-- 
2.25.1