[PATCH v3 3/9] mm/huge_memory: honor MM_CP_TRY_CHANGE_WRITABLE in change_huge_pud()

["Carlos López" <clopez@suse.de>]

change_protection() applies vma->vm_page_prot, which lacks the write bit
for CoW and write-notified mappings. MM_CP_TRY_CHANGE_WRITABLE makes
entries writable again if a write fault would only set the write bit.

However, change_huge_pud() ignores the flag. For example, device DAX
mappings are write-notified once soft-dirty tracking is armed through
/proc/pid/clear_refs, and a protection change then leaves dirty PUDs
read-only, so the next write to each of them faults.

Fix this by adding can_change_pud_writable(), based on
can_change_pmd_writable(). It omits the NUMA and uffd-wp checks, as
change_huge_pud() bails out on those changes.

Signed-off-by: Carlos López <clopez@suse.de>
---
 include/linux/pgtable.h |  5 +++++
 mm/huge_memory.c        | 28 +++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 780fe849ff8b..943d7e95f426 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1866,6 +1866,11 @@ static inline int pmd_soft_dirty(pmd_t pmd)
 	return 0;
 }
 
+static inline int pud_soft_dirty(pud_t pud)
+{
+	return 0;
+}
+
 static inline pte_t pte_mksoft_dirty(pte_t pte)
 {
 	return pte;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index eb913acb03b7..080b718eb7de 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2833,6 +2833,29 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline bool can_change_pud_writable(struct vm_area_struct *vma,
+					   unsigned long addr, pud_t pud)
+{
+	struct page *page;
+
+	if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
+		return false;
+
+	/* Do we need write faults for softdirty tracking? */
+	if (vma_soft_dirty_enabled(vma) && !pud_soft_dirty(pud))
+		return false;
+
+	if (!(vma->vm_flags & VM_SHARED)) {
+		/* See can_change_pte_writable(). */
+		page = vm_normal_page_pud(vma, addr, pud);
+		return page && PageAnon(page) && PageAnonExclusive(page);
+	}
+
+	/* See can_change_pte_writable(). */
+	return pud_dirty(pud);
+}
+
 /*
  * Returns:
  *
@@ -2840,7 +2863,6 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
  * - 1: if pud can be skipped
  * - HPAGE_PUD_NR: if pud was successfully processed
  */
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pud_t *pudp, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags)
@@ -2872,6 +2894,10 @@ int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 */
 	oldpud = pudp_invalidate(vma, addr, pudp);
 	entry = pud_modify(oldpud, newprot);
+	/* See change_pte_range(). */
+	if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pud_write(entry) &&
+	    can_change_pud_writable(vma, addr, entry))
+		entry = pud_mkwrite(entry);
 	set_pud_at(mm, addr, pudp, entry);
 	tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE);
 
-- 
2.51.0