mm/mmap: separate writenotify and dirty tracking logic

Patch series "mm/gup: disallow GUP writing to file-backed mappings by
default", v9.

Writing to file-backed mappings which require folio dirty tracking using
GUP is a fundamentally broken operation, as kernel write access to GUP
mappings do not adhere to the semantics expected by a file system.

A GUP caller uses the direct mapping to access the folio, which does not
cause write notify to trigger, nor does it enforce that the caller marks
the folio dirty.

The problem arises when, after an initial write to the folio, writeback
results in the folio being cleaned and then the caller, via the GUP
interface, writes to the folio again.

As a result of the use of this secondary, direct, mapping to the folio no
write notify will occur, and if the caller does mark the folio dirty, this
will be done so unexpectedly.

For example, consider the following scenario:-

1. A folio is written to via GUP which write-faults the memory, notifying
   the file system and dirtying the folio.
2. Later, writeback is triggered, resulting in the folio being cleaned and
   the PTE being marked read-only.
3. The GUP caller writes to the folio, as it is mapped read/write via the
   direct mapping.
4. The GUP caller, now done with the page, unpins it and sets it dirty
   (though it does not have to).

This change updates both the PUP FOLL_LONGTERM slow and fast APIs.  As
pin_user_pages_fast_only() does not exist, we can rely on a slightly
imperfect whitelisting in the PUP-fast case and fall back to the slow case
should this fail.


This patch (of 3):

vma_wants_writenotify() is specifically intended for setting PTE page
table flags, accounting for existing page table flag state and whether the
underlying filesystem performs dirty tracking for a file-backed mapping.

Everything is predicated firstly on whether the mapping is shared
writable, as this is the only instance where dirty tracking is pertinent -
MAP_PRIVATE mappings will always be CoW'd and unshared, and read-only
file-backed shared mappings cannot be written to, even with FOLL_FORCE.

All other checks are in line with existing logic, though now separated
into checks eplicitily for dirty tracking and those for determining how to
set page table flags.

We make this change so we can perform checks in the GUP logic to determine
which mappings might be problematic when written to.

Link: https://lkml.kernel.org/r/cover.1683235180.git.lstoakes@gmail.com
Link: https://lkml.kernel.org/r/0f218370bd49b4e6bbfbb499f7c7b92c26ba1ceb.1683235180.git.lstoakes@gmail.comSigned-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Mika Penttilä <mpenttil@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Kirill A . Shutemov <kirill@shutemov.name>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -2461,6 +2461,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
+bool vma_needs_dirty_tracking(struct vm_area_struct *vma);
 int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
 static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
 {

mm/mmap.c

@@ -1454,6 +1454,48 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
+static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops)
+{
+	return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite);
+}
+
+static bool vma_is_shared_writable(struct vm_area_struct *vma)
+{
+	return (vma->vm_flags & (VM_WRITE | VM_SHARED)) ==
+		(VM_WRITE | VM_SHARED);
+}
+
+static bool vma_fs_can_writeback(struct vm_area_struct *vma)
+{
+	/* No managed pages to writeback. */
+	if (vma->vm_flags & VM_PFNMAP)
+		return false;
+
+	return vma->vm_file && vma->vm_file->f_mapping &&
+		mapping_can_writeback(vma->vm_file->f_mapping);
+}
+
+/*
+ * Does this VMA require the underlying folios to have their dirty state
+ * tracked?
+ */
+bool vma_needs_dirty_tracking(struct vm_area_struct *vma)
+{
+	/* Only shared, writable VMAs require dirty tracking. */
+	if (!vma_is_shared_writable(vma))
+		return false;
+
+	/* Does the filesystem need to be notified? */
+	if (vm_ops_needs_writenotify(vma->vm_ops))
+		return true;
+
+	/*
+	 * Even if the filesystem doesn't indicate a need for writenotify, if it
+	 * can writeback, dirty tracking is still required.
+	 */
+	return vma_fs_can_writeback(vma);
+}
+
 /*
  * Some shared mappings will want the pages marked read-only
  * to track write events. If so, we'll downgrade vm_page_prot
@@ -1462,21 +1504,18 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
  */
 int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 {
-	vm_flags_t vm_flags = vma->vm_flags;
-	const struct vm_operations_struct *vm_ops = vma->vm_ops;
-
 	/* If it was private or non-writable, the write bit is already clear */
-	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
+	if (!vma_is_shared_writable(vma))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
+	if (vm_ops_needs_writenotify(vma->vm_ops))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify
 	 * won't preserve? */
 	if (pgprot_val(vm_page_prot) !=
-	    pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags)))
+	    pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags)))
 		return 0;
 
 	/*
@@ -1490,13 +1529,8 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	if (userfaultfd_wp(vma))
 		return 1;
 
-	/* Specialty mapping? */
-	if (vm_flags & VM_PFNMAP)
-		return 0;
-
 	/* Can the mapping track the dirty pages? */
-	return vma->vm_file && vma->vm_file->f_mapping &&
-		mapping_can_writeback(vma->vm_file->f_mapping);
+	return vma_fs_can_writeback(vma);
 }
 
 /*