[PATCH v2 2/3] mm: provide mapping_wrprotect_range() function

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

in the fb_defio video driver, page dirty state is used to determine when
frame buffer pages have been changed, allowing for batched, deferred I/O to
be performed for efficiency.

This implementation had only one means of doing so effectively - the use of
the folio_mkclean() function.

However, this use of the function is inappropriate, as the fb_defio
implementation allocates kernel memory to back the framebuffer, and then is
forced to specified page->index, mapping fields in order to permit the
folio_mkclean() rmap traversal to proceed correctly.

It is not correct to specify these fields on kernel-allocated memory, and
moreover since these are not folios, page->index, mapping are deprecated
fields, soon to be removed.

We therefore need to provide a means by which we can correctly traverse the
reverse mapping and write-protect mappings for a page backing an
address_space page cache object at a given offset.

This patch provides this - mapping_wrprotect_range() - which allows for
this operation to be performed for a specified address_space, offset, PFN
and size, without requiring a folio nor, of course, an inappropriate use of
page->index, mapping.

With this provided, we can subsequently adjust the fb_defio implementation
to make use of this function and avoid incorrect invocation of
folio_mkclean() and more importantly, incorrect manipulation of
page->index and mapping fields.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
 include/linux/rmap.h |  3 ++
 mm/rmap.c            | 74 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 4509a43fe59f..e28622ee4648 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -754,6 +754,9 @@ unsigned long page_address_in_vma(const struct folio *folio,
  */
 int folio_mkclean(struct folio *);
 
+int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff,
+		unsigned long pfn, unsigned long nr_pages);
+
 int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
 		      struct vm_area_struct *vma);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 52f98f6ccb56..66cc318925bc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1129,6 +1129,80 @@ int folio_mkclean(struct folio *folio)
 }
 EXPORT_SYMBOL_GPL(folio_mkclean);
 
+struct wrprotect_file_state {
+	int cleaned;
+	pgoff_t pgoff;
+	unsigned long pfn;
+	unsigned long nr_pages;
+};
+
+static bool mapping_wrprotect_range_one(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long address, void *arg)
+{
+	struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg;
+	struct page_vma_mapped_walk pvmw = {
+		.pfn		= state->pfn,
+		.nr_pages	= state->nr_pages,
+		.pgoff		= state->pgoff,
+		.vma		= vma,
+		.address	= address,
+		.flags		= PVMW_SYNC,
+	};
+
+	state->cleaned += page_vma_mkclean_one(&pvmw);
+
+	return true;
+}
+
+static void __rmap_walk_file(struct folio *folio, struct address_space *mapping,
+			     pgoff_t pgoff_start, unsigned long nr_pages,
+			     struct rmap_walk_control *rwc, bool locked);
+
+/**
+ * mapping_wrprotect_range() - Write-protect all mappings in a specified range.
+ *
+ * @mapping:	The mapping whose reverse mapping should be traversed.
+ * @pgoff:	The page offset at which @pfn is mapped within @mapping.
+ * @pfn:	The PFN of the page mapped in @mapping at @pgoff.
+ * @nr_pages:	The number of physically contiguous base pages spanned.
+ *
+ * Traverses the reverse mapping, finding all VMAs which contain a shared
+ * mapping of the pages in the specified range in @mapping, and write-protects
+ * them (that is, updates the page tables to mark the mappings read-only such
+ * that a write protection fault arises when the mappings are written to).
+ *
+ * The @pfn value need not refer to a folio, but rather can reference a kernel
+ * allocation which is mapped into userland. We therefore do not require that
+ * the page maps to a folio with a valid mapping or index field, rather the
+ * caller specifies these in @mapping and @pgoff.
+ *
+ * Return: the number of write-protected PTEs, or an error.
+ */
+int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff,
+		unsigned long pfn, unsigned long nr_pages)
+{
+	struct wrprotect_file_state state = {
+		.cleaned = 0,
+		.pgoff = pgoff,
+		.pfn = pfn,
+		.nr_pages = nr_pages,
+	};
+	struct rmap_walk_control rwc = {
+		.arg = (void *)&state,
+		.rmap_one = mapping_wrprotect_range_one,
+		.invalid_vma = invalid_mkclean_vma,
+	};
+
+	if (!mapping)
+		return 0;
+
+	__rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc,
+			 /* locked = */false);
+
+	return state.cleaned;
+}
+EXPORT_SYMBOL_GPL(mapping_wrprotect_range);
+
 /**
  * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
  *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
-- 
2.48.1