mm: rename vm_ops->find_special_page() to vm_ops->find_normal_page()

... and hide it behind a kconfig option. There is really no need for any
!xen code to perform this check.

The naming is a bit off: we want to find the "normal" page when a PTE was
marked "special". So it's really not "finding a special" page.

Improve the documentation, and add a comment in the code where XEN ends up
performing the pte_mkspecial() through a hypercall. More details can be
found in commit 923b2919e2c3 ("xen/gntdev: mark userspace PTEs as special
on x86 PV guests").

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: David Hildenbrand <[e-mail]>
Reviewed-by: Oscar Salvador <[e-mail]>
Reviewed-by: Lorenzo Stoakes <[e-mail]>
Reviewed-by: Wei Yang <[e-mail]>
Cc: David Vrabel <[e-mail]>
Cc: Alistair Popple <[e-mail]>
Cc: Al Viro <[e-mail]>
Cc: Baolin Wang <[e-mail]>
Cc: Barry Song <[e-mail]>
Cc: Christian Brauner <[e-mail]>
Cc: Christophe Leroy <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Dev Jain <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Jan Kara <[e-mail]>
Cc: Jann Horn <[e-mail]>
Cc: Juegren Gross <[e-mail]>
Cc: Lance Yang <[e-mail]>
Cc: Liam Howlett <[e-mail]>
Cc: Madhavan Srinivasan <[e-mail]>
Cc: Mariano Pache <[e-mail]>
Cc: Matthew Wilcox (Oracle) <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Mike Rapoport <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Oleksandr Tyshchenko <[e-mail]>
Cc: Ryan Roberts <[e-mail]>
Cc: Stefano Stabellini <[e-mail]>
Cc: Suren Baghdasaryan <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: Zi Yan <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

drivers/xen/Kconfig

···
 	depends on XEN
 	default m
 	select MMU_NOTIFIER
+	select FIND_NORMAL_PAGE
 	help
 	  Allows userspace processes to use grants.
 

drivers/xen/gntdev.c

···
 	BUG_ON(pgnr >= map->count);
 	pte_maddr = arbitrary_virt_to_machine(pte).maddr;
 
+	/* Note: this will perform a pte_mkspecial() through the hypercall. */
 	gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
 			  map->grants[pgnr].ref,
 			  map->grants[pgnr].domid);
···
 	gntdev_put_map(priv, map);
 }
 
-static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
+static struct page *gntdev_vma_find_normal_page(struct vm_area_struct *vma,
 						 unsigned long addr)
 {
 	struct gntdev_grant_map *map = vma->vm_private_data;
···
 static const struct vm_operations_struct gntdev_vmops = {
 	.open = gntdev_vma_open,
 	.close = gntdev_vma_close,
-	.find_special_page = gntdev_vma_find_special_page,
+	.find_normal_page = gntdev_vma_find_normal_page,
 };
 
 /* ------------------------------------------------------------------ */

include/linux/mm.h

···
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr, pgoff_t *ilx);
 #endif
+#ifdef CONFIG_FIND_NORMAL_PAGE
 	/*
-	 * Called by vm_normal_page() for special PTEs to find the
-	 * page for @addr.  This is useful if the default behavior
-	 * (using pte_page()) would not find the correct page.
+	 * Called by vm_normal_page() for special PTEs in @vma at @addr. This
+	 * allows for returning a "normal" page from vm_normal_page() even
+	 * though the PTE indicates that the "struct page" either does not exist
+	 * or should not be touched: "special".
+	 *
+	 * Do not add new users: this really only works when a "normal" page
+	 * was mapped, but then the PTE got changed to something weird (+
+	 * marked special) that would not make pte_pfn() identify the originally
+	 * inserted page.
 	 */
-	struct page *(*find_special_page)(struct vm_area_struct *vma,
-					  unsigned long addr);
+	struct page *(*find_normal_page)(struct vm_area_struct *vma,
+					 unsigned long addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
 };
 
 #ifdef CONFIG_NUMA_BALANCING

mm/Kconfig

···
 
 	  Note: now only empty user PTE page table pages will be reclaimed.
 
+config FIND_NORMAL_PAGE
+	def_bool n
 
 source "mm/damon/Kconfig"
 

mm/memory.c

···
  * trivial. Secondly, an architecture may not have a spare page table
  * entry bit, which requires a more complicated scheme, described below.
  *
+ * With CONFIG_FIND_NORMAL_PAGE, we might have the "special" bit set on
+ * page table entries that actually map "normal" pages: however, that page
+ * cannot be looked up through the PFN stored in the page table entry, but
+ * instead will be looked up through vm_ops->find_normal_page(). So far, this
+ * only applies to PTEs.
+ *
  * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
  * special mapping (even if there are underlying and valid "struct pages").
  * COWed pages of a VM_PFNMAP are always normal.
···
 {
 	if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) {
 		if (unlikely(special)) {
-			if (vma->vm_ops && vma->vm_ops->find_special_page)
-				return vma->vm_ops->find_special_page(vma, addr);
+#ifdef CONFIG_FIND_NORMAL_PAGE
+			if (vma->vm_ops && vma->vm_ops->find_normal_page)
+				return vma->vm_ops->find_normal_page(vma, addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
 			if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 				return NULL;
 			if (is_zero_pfn(pfn) || is_huge_zero_pfn(pfn))

tools/testing/vma/vma_internal.h

···
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr, pgoff_t *ilx);
 #endif
+#ifdef CONFIG_FIND_NORMAL_PAGE
 	/*
-	 * Called by vm_normal_page() for special PTEs to find the
-	 * page for @addr.  This is useful if the default behavior
-	 * (using pte_page()) would not find the correct page.
+	 * Called by vm_normal_page() for special PTEs in @vma at @addr. This
+	 * allows for returning a "normal" page from vm_normal_page() even
+	 * though the PTE indicates that the "struct page" either does not exist
+	 * or should not be touched: "special".
+	 *
+	 * Do not add new users: this really only works when a "normal" page
+	 * was mapped, but then the PTE got changed to something weird (+
+	 * marked special) that would not make pte_pfn() identify the originally
+	 * inserted page.
 	 */
-	struct page *(*find_special_page)(struct vm_area_struct *vma,
-					  unsigned long addr);
+	struct page *(*find_normal_page)(struct vm_area_struct *vma,
+					 unsigned long addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
 };
 
 struct vm_unmapped_area_info {