[PATCH v2 43/47] mm/huge_memory: split huge PUDs when adjusting VMA boundaries

["David Hildenbrand (Arm)" <david@kernel.org>]

PFN mappings such as VFIO PCI BAR mappings can use PUD leaves while
allowing VMA splits at page granularity. However, vma_adjust_trans_huge()
only handles PMDs.

After faulting a writable PUD-sized VFIO BAR mapping, changing its first
page to read-only with mprotect() makes the PMD walk treat the PUD leaf
as a PMD table. Applying MADV_DONTFORK to the first PMD-sized chunk leaves
the PUD spanning two VMAs: the PMD-aligned boundary skips splitting.

Walk the page tables once at each adjusted boundary and split a huge
PUD or PMD leaf as needed. Handle PUD leaves even when the boundary is
PMD-aligned.

Fixes: f9e54c3a2f5b7 ("vfio/pci: implement huge_fault support")
Cc: stable@vger.kernel.org
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
---
 mm/huge_memory.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 60 insertions(+), 10 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f1b3f744c630..6ff3faa200f9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3504,16 +3504,66 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 	__split_huge_pmd(vma, pmd, address, freeze);
 }
 
-static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address)
+static bool pud_split_required(const struct vm_area_struct *vma,
+		unsigned long address)
 {
+	if (!IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+		return false;
+	if (IS_ALIGNED(address, HPAGE_PUD_SIZE))
+		return false;
 	/*
-	 * If the new address isn't hpage aligned and it could previously
-	 * contain an hugepage: check if we need to split an huge pmd.
+	 * Only selected VMAs support mapping PUDs for now. Lift the
+	 * restriction once this changes.
 	 */
-	if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) &&
-	    range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE),
-			 ALIGN(address, HPAGE_PMD_SIZE)))
-		split_huge_pmd_address(vma, address, false);
+	if (!vma_is_dax(vma) && !vma_test_any(vma, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT))
+		return false;
+	return range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PUD_SIZE),
+			    ALIGN(address, HPAGE_PUD_SIZE));
+}
+
+static bool pmd_split_required(const struct vm_area_struct *vma,
+		unsigned long address)
+{
+	if (IS_ALIGNED(address, HPAGE_PMD_SIZE))
+		return false;
+
+	return range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE),
+			    ALIGN(address, HPAGE_PMD_SIZE));
+}
+
+static void split_huge_leaf(struct vm_area_struct *vma,
+		unsigned long address)
+{
+	const bool split_pud = pud_split_required(vma, address);
+	const bool split_pmd = pmd_split_required(vma, address);
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	/*
+	 * mmap, VMA and rmap write locks protect the walk; the split helpers
+	 * take the page table locks.
+	 */
+	if (!split_pud && !split_pmd)
+		return;
+
+	pgd = pgd_offset(vma->vm_mm, address);
+	if (!pgd_present(*pgd))
+		return;
+
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		return;
+
+	pud = pud_offset(p4d, address);
+	if (pud_leaf(*pud))
+		__split_huge_pud(vma, pud, address);
+	if (!split_pmd || !pud_present(*pud))
+		return;
+
+	pmd = pmd_offset(pud, address);
+	__split_huge_pmd(vma, pmd, address, false);
 }
 
 void vma_adjust_trans_huge(struct vm_area_struct *vma,
@@ -3522,14 +3572,14 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 			   struct vm_area_struct *next)
 {
 	/* Check if we need to split start first. */
-	split_huge_pmd_if_needed(vma, start);
+	split_huge_leaf(vma, start);
 
 	/* Check if we need to split end next. */
-	split_huge_pmd_if_needed(vma, end);
+	split_huge_leaf(vma, end);
 
 	/* If we're incrementing next->vm_start, we might need to split it. */
 	if (next)
-		split_huge_pmd_if_needed(next, end);
+		split_huge_leaf(next, end);
 }
 
 /*

-- 
2.43.0