Let's use folio_walk instead, so we can avoid taking a folio reference
just to read the nid and get rid of another follow_page()/FOLL_DUMP
user. Use FW_ZEROPAGE so we can return "-EFAULT" for it as documented.
The possible return values for follow_page() were confusing, especially
with FOLL_DUMP set. We'll handle it like documented in the man page:
* -EFAULT: This is a zero page or the memory area is not mapped by the
process.
* -ENOENT: The page is not present.
We'll keep setting -ENOENT for ZONE_DEVICE. Maybe not the right thing to
do, but it likely doesn't really matter (just like for weird devmap,
whereby we fake "not present").
Note that the other errors (-EACCESS, -EBUSY, -EIO, -EINVAL, -ENOMEM)
so far only applied when actually moving pages, not when only
querying stats.
We'll effectively drop the "secretmem" check we had in follow_page(), but
that shouldn't really matter here, we're not accessing folio/page content
after all.
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
mm/migrate.c | 31 +++++++++++++++----------------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index aa482c954cb0..b5365a434ba9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -50,6 +50,7 @@
#include <linux/random.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>
+#include <linux/pagewalk.h>
#include <asm/tlbflush.h>
@@ -2331,28 +2332,26 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
for (i = 0; i < nr_pages; i++) {
unsigned long addr = (unsigned long)(*pages);
struct vm_area_struct *vma;
- struct page *page;
+ struct folio_walk fw;
+ struct folio *folio;
int err = -EFAULT;
vma = vma_lookup(mm, addr);
if (!vma)
goto set_status;
- /* FOLL_DUMP to ignore special (like zero) pages */
- page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
-
- err = PTR_ERR(page);
- if (IS_ERR(page))
- goto set_status;
-
- err = -ENOENT;
- if (!page)
- goto set_status;
-
- if (!is_zone_device_page(page))
- err = page_to_nid(page);
-
- put_page(page);
+ folio = folio_walk_start(&fw, vma, addr, FW_ZEROPAGE);
+ if (folio) {
+ if (is_zero_folio(folio) || is_huge_zero_folio(folio))
+ err = -EFAULT;
+ else if (folio_is_zone_device(folio))
+ err = -ENOENT;
+ else
+ err = folio_nid(folio);
+ folio_walk_end(&fw, vma);
+ } else {
+ err = -ENOENT;
+ }
set_status:
*status = err;
--
2.45.2
