mm: Make pte_mkwrite() take a VMA

The x86 Shadow stack feature includes a new type of memory called shadow stack. This shadow stack memory has some unusual properties, which requires some core mm changes to function properly. One of these unusual properties is that shadow stack memory is writable, but only in limited ways. These limits are applied via a specific PTE bit combination. Nevertheless, the memory is writable, and core mm code will need to apply the writable permissions in the typical paths that call pte_mkwrite(). Future patches will make pte_mkwrite() take a VMA, so that the x86 implementation of it can know whether to create regular writable or shadow stack mappings. But there are a couple of challenges to this. Modifying the signatures of each arch pte_mkwrite() implementation would be error prone because some are generated with macros and would need to be re-implemented. Also, some pte_mkwrite() callers operate on kernel memory without a VMA. So this can be done in a three step process. First pte_mkwrite() can be renamed to pte_mkwrite_novma() in each arch, with a generic pte_mkwrite() added that just calls pte_mkwrite_novma(). Next callers without a VMA can be moved to pte_mkwrite_novma(). And lastly, pte_mkwrite() and all callers can be changed to take/pass a VMA. Previous work pte_mkwrite() renamed pte_mkwrite_novma() and converted callers that don't have a VMA were to use pte_mkwrite_novma(). So now change pte_mkwrite() to take a VMA and change the remaining callers to pass a VMA. Apply the same changes for pmd_mkwrite(). No functional change. Suggested-by: David Hildenbrand <[email protected]> Signed-off-by: Rick Edgecombe <[email protected]> Signed-off-by: Dave Hansen <[email protected]> Reviewed-by: Mike Rapoport (IBM) <[email protected]> Acked-by: David Hildenbrand <[email protected]> Link: https://lore.kernel.org/all/20230613001108.3040476-4-rick.p.edgecombe%40intel.com
kawasaki · Jul 11, 2023 · 161e393 · 161e393
1 parent 6ecc21b
commit 161e393
Show file tree

Hide file tree

Showing 10 changed files with 24 additions and 22 deletions.
diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst
@@ -46,7 +46,8 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_mkclean               | Creates a clean PTE                              |
 +---------------------------+--------------------------------------------------+
-| pte_mkwrite               | Creates a writable PTE                           |
+| pte_mkwrite               | Creates a writable PTE of the type specified by  |
+|                           | the VMA.                                         |
 +---------------------------+--------------------------------------------------+
 | pte_mkwrite_novma         | Creates a writable PTE, of the conventional type |
 |                           | of writable.                                     |
@@ -121,7 +122,8 @@ PMD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pmd_mkclean               | Creates a clean PMD                              |
 +---------------------------+--------------------------------------------------+
-| pmd_mkwrite               | Creates a writable PMD                           |
+| pmd_mkwrite               | Creates a writable PMD of the type specified by  |
+|                           | the VMA.                                         |
 +---------------------------+--------------------------------------------------+
 | pmd_mkwrite_novma         | Creates a writable PMD, of the conventional type |
 |                           | of writable.                                     |

diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -1277,7 +1277,7 @@ void free_compound_page(struct page *page);
 static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
-		pte = pte_mkwrite(pte);
+		pte = pte_mkwrite(pte, vma);
 	return pte;
 }
 

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
@@ -516,14 +516,14 @@ extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
 #endif
 
 #ifndef pte_mkwrite
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
 {
 	return pte_mkwrite_novma(pte);
 }
 #endif
 
 #if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite)
-static inline pmd_t pmd_mkwrite(pmd_t pmd)
+static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 {
 	return pmd_mkwrite_novma(pmd);
 }

diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
@@ -109,10 +109,10 @@ static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx)
 	WARN_ON(!pte_same(pte, pte));
 	WARN_ON(!pte_young(pte_mkyoung(pte_mkold(pte))));
 	WARN_ON(!pte_dirty(pte_mkdirty(pte_mkclean(pte))));
-	WARN_ON(!pte_write(pte_mkwrite(pte_wrprotect(pte))));
+	WARN_ON(!pte_write(pte_mkwrite(pte_wrprotect(pte), args->vma)));
 	WARN_ON(pte_young(pte_mkold(pte_mkyoung(pte))));
 	WARN_ON(pte_dirty(pte_mkclean(pte_mkdirty(pte))));
-	WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte))));
+	WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte, args->vma))));
 	WARN_ON(pte_dirty(pte_wrprotect(pte_mkclean(pte))));
 	WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte))));
 }
@@ -156,7 +156,7 @@ static void __init pte_advanced_tests(struct pgtable_debug_args *args)
 	pte = pte_mkclean(pte);
 	set_pte_at(args->mm, args->vaddr, args->ptep, pte);
 	flush_dcache_page(page);
-	pte = pte_mkwrite(pte);
+	pte = pte_mkwrite(pte, args->vma);
 	pte = pte_mkdirty(pte);
 	ptep_set_access_flags(args->vma, args->vaddr, args->ptep, pte, 1);
 	pte = ptep_get(args->ptep);
@@ -202,10 +202,10 @@ static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx)
 	WARN_ON(!pmd_same(pmd, pmd));
 	WARN_ON(!pmd_young(pmd_mkyoung(pmd_mkold(pmd))));
 	WARN_ON(!pmd_dirty(pmd_mkdirty(pmd_mkclean(pmd))));
-	WARN_ON(!pmd_write(pmd_mkwrite(pmd_wrprotect(pmd))));
+	WARN_ON(!pmd_write(pmd_mkwrite(pmd_wrprotect(pmd), args->vma)));
 	WARN_ON(pmd_young(pmd_mkold(pmd_mkyoung(pmd))));
 	WARN_ON(pmd_dirty(pmd_mkclean(pmd_mkdirty(pmd))));
-	WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd))));
+	WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd, args->vma))));
 	WARN_ON(pmd_dirty(pmd_wrprotect(pmd_mkclean(pmd))));
 	WARN_ON(!pmd_dirty(pmd_wrprotect(pmd_mkdirty(pmd))));
 	/*
@@ -256,7 +256,7 @@ static void __init pmd_advanced_tests(struct pgtable_debug_args *args)
 	pmd = pmd_mkclean(pmd);
 	set_pmd_at(args->mm, vaddr, args->pmdp, pmd);
 	flush_dcache_page(page);
-	pmd = pmd_mkwrite(pmd);
+	pmd = pmd_mkwrite(pmd, args->vma);
 	pmd = pmd_mkdirty(pmd);
 	pmdp_set_access_flags(args->vma, vaddr, args->pmdp, pmd, 1);
 	pmd = READ_ONCE(*args->pmdp);

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
@@ -551,7 +551,7 @@ __setup("transparent_hugepage=", setup_transparent_hugepage);
 pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
-		pmd = pmd_mkwrite(pmd);
+		pmd = pmd_mkwrite(pmd, vma);
 	return pmd;
 }
 
@@ -1572,7 +1572,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
 	pmd = pmd_mkyoung(pmd);
 	if (writable)
-		pmd = pmd_mkwrite(pmd);
+		pmd = pmd_mkwrite(pmd, vma);
 	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
 	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 	spin_unlock(vmf->ptl);
@@ -1925,7 +1925,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	/* See change_pte_range(). */
 	if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) &&
 	    can_change_pmd_writable(vma, addr, entry))
-		entry = pmd_mkwrite(entry);
+		entry = pmd_mkwrite(entry, vma);
 
 	ret = HPAGE_PMD_NR;
 	set_pmd_at(mm, addr, pmd, entry);
@@ -2243,7 +2243,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			if (write)
-				entry = pte_mkwrite(entry);
+				entry = pte_mkwrite(entry, vma);
 			if (anon_exclusive)
 				SetPageAnonExclusive(page + i);
 			if (!young)
@@ -3287,7 +3287,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
 	if (is_writable_migration_entry(entry))
-		pmde = pmd_mkwrite(pmde);
+		pmde = pmd_mkwrite(pmde, vma);
 	if (pmd_swp_uffd_wp(*pvmw->pmd))
 		pmde = pmd_mkuffd_wp(pmde);
 	if (!is_migration_entry_young(entry))

diff --git a/mm/memory.c b/mm/memory.c
@@ -4119,7 +4119,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	entry = mk_pte(&folio->page, vma->vm_page_prot);
 	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
-		entry = pte_mkwrite(pte_mkdirty(entry));
+		entry = pte_mkwrite(pte_mkdirty(entry), vma);
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
@@ -4808,7 +4808,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	pte = pte_modify(old_pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (writable)
-		pte = pte_mkwrite(pte);
+		pte = pte_mkwrite(pte, vma);
 	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);

diff --git a/mm/migrate.c b/mm/migrate.c
@@ -220,7 +220,7 @@ static bool remove_migration_pte(struct folio *folio,
 		if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
 			pte = pte_mkdirty(pte);
 		if (is_writable_migration_entry(entry))
-			pte = pte_mkwrite(pte);
+			pte = pte_mkwrite(pte, vma);
 		else if (pte_swp_uffd_wp(old_pte))
 			pte = pte_mkuffd_wp(pte);
 

diff --git a/mm/migrate_device.c b/mm/migrate_device.c
@@ -623,7 +623,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		}
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (vma->vm_flags & VM_WRITE)
-			entry = pte_mkwrite(pte_mkdirty(entry));
+			entry = pte_mkwrite(pte_mkdirty(entry), vma);
 	}
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);

diff --git a/mm/mprotect.c b/mm/mprotect.c
@@ -185,7 +185,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
 			    !pte_write(ptent) &&
 			    can_change_pte_writable(vma, addr, ptent))
-				ptent = pte_mkwrite(ptent);
+				ptent = pte_mkwrite(ptent, vma);
 
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
 			if (pte_needs_flush(oldpte, ptent))

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
@@ -72,7 +72,7 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd,
 	if (page_in_cache && !vm_shared)
 		writable = false;
 	if (writable)
-		_dst_pte = pte_mkwrite(_dst_pte);
+		_dst_pte = pte_mkwrite(_dst_pte, dst_vma);
 	if (flags & MFILL_ATOMIC_WP)
 		_dst_pte = pte_mkuffd_wp(_dst_pte);