[RFC V1 02/16] mm: Add read-write accessors for vm_page_prot

[Anshuman Khandual]

Currently vma->vm_page_prot is safely read from and written to, without any
locks with READ_ONCE() and WRITE_ONCE(). But with introduction of D128 page
tables on arm64 platform, vm_page_prot grows to 128 bits which can't safely
be handled with READ_ONCE() and WRITE_ONCE().

Add read and write accessors for vm_page_prot like pgprot_read/write_once()
which any platform can override when required, although still defaulting as
READ_ONCE() and WRITE_ONCE(), thus preserving the functionality for others.

Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: David Hildenbrand <david at kernel.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes at oracle.com>
Cc: Mike Rapoport <rppt at kernel.org>
Cc: linux-mm at kvack.org
Cc: linux-kernel at vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual at arm.com>
---
 include/linux/pgtable.h | 14 ++++++++++++++
 mm/huge_memory.c        |  4 ++--
 mm/memory.c             |  2 +-
 mm/migrate.c            |  2 +-
 mm/mmap.c               |  2 +-
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index da17139a1279..8858b8b03a02 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -495,6 +495,20 @@ static inline pgd_t pgdp_get(pgd_t *pgdp)
 }
 #endif
 
+#ifndef pgprot_read_once
+static inline pgprot_t pgprot_read_once(pgprot_t *prot)
+{
+	return READ_ONCE(*prot);
+}
+#endif
+
+#ifndef pgprot_write_once
+static inline void pgprot_write_once(pgprot_t *prot, pgprot_t val)
+{
+	WRITE_ONCE(*prot, val);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d4ca8cfd7f9d..0d9d6569367e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3233,7 +3233,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	} else {
 		pte_t entry;
 
-		entry = mk_pte(page, READ_ONCE(vma->vm_page_prot));
+		entry = mk_pte(page, pgprot_read_once(&vma->vm_page_prot));
 		if (write)
 			entry = pte_mkwrite(entry, vma);
 		if (!young)
@@ -4918,7 +4918,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 
 	entry = softleaf_from_pmd(*pvmw->pmd);
 	folio_get(folio);
-	pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot));
+	pmde = folio_mk_pmd(folio, pgprot_read_once(&vma->vm_page_prot));
 
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
diff --git a/mm/memory.c b/mm/memory.c
index cfc3077fc52f..2d99c9212883 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -895,7 +895,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 
 	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
 
-	pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
+	pte = pte_mkold(mk_pte(page, pgprot_read_once(&vma->vm_page_prot)));
 	if (pte_swp_soft_dirty(orig_pte))
 		pte = pte_mksoft_dirty(pte);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 1bf2cf8c44dd..9db1e6ed9042 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -377,7 +377,7 @@ static bool remove_migration_pte(struct folio *folio,
 			continue;
 
 		folio_get(folio);
-		pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
+		pte = mk_pte(new, pgprot_read_once(&vma->vm_page_prot));
 
 		entry = softleaf_from_pte(old_pte);
 		if (!softleaf_is_migration_young(entry))
diff --git a/mm/mmap.c b/mm/mmap.c
index 843160946aa5..af6870115a9d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -89,7 +89,7 @@ void vma_set_page_prot(struct vm_area_struct *vma)
 		vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
 	}
 	/* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
-	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
+	pgprot_write_once(&vma->vm_page_prot, vm_page_prot);
 }
 
 /*
-- 
2.43.0