[v6,1/3] mm/mmap: separate writenotify and dirty tracking logic
Commit Message
vma_wants_writenotify() is specifically intended for setting PTE page table
flags, accounting for existing PTE flag state and whether that might
already be read-only while mixing this check with a check whether the
filesystem performs dirty tracking.
Separate out the notions of dirty tracking and a PTE write notify checking
in order that we can invoke the dirty tracking check from elsewhere.
Note that this change introduces a very small duplicate check of the
separated out vm_ops_needs_writenotify(). This is necessary to avoid making
vma_needs_dirty_tracking() needlessly complicated (e.g. passing a
check_writenotify flag or having it assume this check was already
performed). This is such a small check that it doesn't seem too egregious
to do this.
Signed-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>
---
include/linux/mm.h | 1 +
mm/mmap.c | 36 +++++++++++++++++++++++++++---------
2 files changed, 28 insertions(+), 9 deletions(-)
@@ -2422,6 +2422,7 @@ 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)
{
@@ -1475,6 +1475,31 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
}
#endif /* __ARCH_WANT_SYS_OLD_MMAP */
+/* Do VMA operations imply write notify is required? */
+static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops)
+{
+ return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite);
+}
+
+/*
+ * Does this VMA require the underlying folios to have their dirty state
+ * tracked?
+ */
+bool vma_needs_dirty_tracking(struct vm_area_struct *vma)
+{
+ /* Does the filesystem need to be notified? */
+ if (vm_ops_needs_writenotify(vma->vm_ops))
+ return true;
+
+ /* Specialty mapping? */
+ if (vma->vm_flags & VM_PFNMAP)
+ return false;
+
+ /* Can the mapping track the dirty pages? */
+ return vma->vm_file && vma->vm_file->f_mapping &&
+ mapping_can_writeback(vma->vm_file->f_mapping);
+}
+
/*
* Some shared mappings will want the pages marked read-only
* to track write events. If so, we'll downgrade vm_page_prot
@@ -1484,14 +1509,13 @@ 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)))
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
@@ -1511,13 +1535,7 @@ 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_needs_dirty_tracking(vma);
}
/*