Re: [PATCH] mm/mincore: allow for making sys_mincore() privileged

[Linus Torvalds]

On Sat, Jan 5, 2019 at 3:05 PM Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>
> That would be nicer than my patch, simply because removing code is
> always nice. And arguably it's a better semantic anyway.

Yeah, I wonder why we did that thing where mincore() walks the page
tables, but if they are empty it looks in the page cache.

[... goes and looks in history ..]

It goes back to forever, it looks like. I can't find a reason.

Anyway, a removal patch would look something like the attached, I
think. That makes mincore() actually say how many pages are in _this_
mapping, not how many pages could be paged in without doing IO.

Hmm. Maybe we should try this first. Simplicity is always good.

Again, obviously untested.

                   Linus
 mm/mincore.c | 74 +++++-------------------------------------------------------
 1 file changed, 6 insertions(+), 68 deletions(-)

diff --git a/mm/mincore.c b/mm/mincore.c
index 218099b5ed31..317eb64ea4ef 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -42,64 +42,12 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 	return 0;
 }
 
-/*
- * Later we can get more picky about what "in core" means precisely.
- * For now, simply check to see if the page is in the page cache,
- * and is up to date; i.e. that no page-in operation would be required
- * at this time if an application were to map and access this page.
- */
-static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
-{
-	unsigned char present = 0;
-	struct page *page;
-
-	/*
-	 * When tmpfs swaps out a page from a file, any process mapping that
-	 * file will not get a swp_entry_t in its pte, but rather it is like
-	 * any other file mapping (ie. marked !present and faulted in with
-	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
-	 */
-#ifdef CONFIG_SWAP
-	if (shmem_mapping(mapping)) {
-		page = find_get_entry(mapping, pgoff);
-		/*
-		 * shmem/tmpfs may return swap: account for swapcache
-		 * page too.
-		 */
-		if (xa_is_value(page)) {
-			swp_entry_t swp = radix_to_swp_entry(page);
-			page = find_get_page(swap_address_space(swp),
-					     swp_offset(swp));
-		}
-	} else
-		page = find_get_page(mapping, pgoff);
-#else
-	page = find_get_page(mapping, pgoff);
-#endif
-	if (page) {
-		present = PageUptodate(page);
-		put_page(page);
-	}
-
-	return present;
-}
-
 static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
 				struct vm_area_struct *vma, unsigned char *vec)
 {
 	unsigned long nr = (end - addr) >> PAGE_SHIFT;
-	int i;
 
-	if (vma->vm_file) {
-		pgoff_t pgoff;
-
-		pgoff = linear_page_index(vma, addr);
-		for (i = 0; i < nr; i++, pgoff++)
-			vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
-	} else {
-		for (i = 0; i < nr; i++)
-			vec[i] = 0;
-	}
+	memset(vec, 0, nr);
 	return nr;
 }
 
@@ -144,21 +92,11 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		else { /* pte is a swap entry */
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (non_swap_entry(entry)) {
-				/*
-				 * migration or hwpoison entries are always
-				 * uptodate
-				 */
-				*vec = 1;
-			} else {
-#ifdef CONFIG_SWAP
-				*vec = mincore_page(swap_address_space(entry),
-						    swp_offset(entry));
-#else
-				WARN_ON(1);
-				*vec = 1;
-#endif
-			}
+			/*
+			 * migration or hwpoison entries are always
+			 * uptodate
+			 */
+			*vec = !!non_swap_entry(entry);
 		}
 		vec++;
 	}