fs/proc/task_mmu: account non-present entries as "maybe shared, but no idea how often"

We currently rely on mapcount information for pages referenced by
non-present entries to calculate the USS (shared vs.  private) and the
PSS.

However, relying on mapcounts for non-present entries doesn't make any
sense.  We have to treat such entries as "maybe shared, but no idea how
often", implying that they will *not* get accounted towards the USS, and
will get fully accounted to the PSS (no idea how often shared).

There is one exception: device exclusive entries essentially behave like
present entries (e.g., mapcount incremented).

In smaps_pmd_entry(), use is_pfn_swap_entry() instead of
is_migration_entry(), which should not make a real difference but makes
the code look more similar to the PTE variant.

While at it, adjust the comments in smaps_account().

Link: https://lkml.kernel.org/r/20240607122357.115423-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Oscar Salvador <osalvador@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/proc/task_mmu.c

@@ -442,7 +442,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
 		bool compound, bool young, bool dirty, bool locked,
-		bool migration)
+		bool present)
 {
 	struct folio *folio = page_folio(page);
 	int i, nr = compound ? compound_nr(page) : 1;
@@ -471,22 +471,27 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	 * Then accumulate quantities that may depend on sharing, or that may
 	 * differ page-by-page.
 	 *
-	 * refcount == 1 guarantees the page is mapped exactly once.
+	 * refcount == 1 for present entries guarantees that the folio is mapped
-	 * If any subpage of the compound page mapped with PTE it would elevate
+	 * exactly once. For large folios this implies that exactly one
-	 * the refcount.
+	 * PTE/PMD/... maps (a part of) this folio.
 	 *
-	 * The page_mapcount() is called to get a snapshot of the mapcount.
+	 * Treat all non-present entries (where relying on the mapcount and
-	 * Without holding the page lock this snapshot can be slightly wrong as
+	 * refcount doesn't make sense) as "maybe shared, but not sure how
-	 * we cannot always read the mapcount atomically.  It is not safe to
+	 * often". We treat device private entries as being fake-present.
-	 * call page_mapcount() even with PTL held if the page is not mapped,
+	 *
-	 * especially for migration entries.  Treat regular migration entries
+	 * Note that it would not be safe to read the mapcount especially for
-	 * as mapcount == 1.
+	 * pages referenced by migration entries, even with the PTL held.
 	 */
-	if ((folio_ref_count(folio) == 1) || migration) {
+	if (folio_ref_count(folio) == 1 || !present) {
 		smaps_page_accumulate(mss, folio, size, size << PSS_SHIFT,
-				dirty, locked, true);
+				      dirty, locked, present);
 		return;
 	}
+	/*
+	 * The page_mapcount() is called to get a snapshot of the mapcount.
+	 * Without holding the folio lock this snapshot can be slightly wrong as
+	 * we cannot always read the mapcount atomically.
+	 */
 	for (i = 0; i < nr; i++, page++) {
 		int mapcount = page_mapcount(page);
 		unsigned long pss = PAGE_SIZE << PSS_SHIFT;
@@ -531,13 +536,14 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
-	bool migration = false, young = false, dirty = false;
+	bool present = false, young = false, dirty = false;
 	pte_t ptent = ptep_get(pte);
 
 	if (pte_present(ptent)) {
 		page = vm_normal_page(vma, addr, ptent);
 		young = pte_young(ptent);
 		dirty = pte_dirty(ptent);
+		present = true;
 	} else if (is_swap_pte(ptent)) {
 		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
@@ -555,8 +561,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 				mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
 			}
 		} else if (is_pfn_swap_entry(swpent)) {
-			if (is_migration_entry(swpent))
+			if (is_device_private_entry(swpent))
-				migration = true;
+				present = true;
 			page = pfn_swap_entry_to_page(swpent);
 		}
 	} else {
@@ -567,7 +573,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, young, dirty, locked, migration);
+	smaps_account(mss, page, false, young, dirty, locked, present);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -578,19 +584,18 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
+	bool present = false;
 	struct folio *folio;
-	bool migration = false;
 
 	if (pmd_present(*pmd)) {
 		page = vm_normal_page_pmd(vma, addr, *pmd);
+		present = true;
 	} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
-		if (is_migration_entry(entry)) {
+		if (is_pfn_swap_entry(entry))
-			migration = true;
 			page = pfn_swap_entry_to_page(entry);
 	}
-	}
 	if (IS_ERR_OR_NULL(page))
 		return;
 	folio = page_folio(page);
@@ -604,7 +609,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 		mss->file_thp += HPAGE_PMD_SIZE;
 
 	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd),
-		      locked, migration);
+		      locked, present);
 }
 #else
 static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -735,17 +740,21 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 	struct vm_area_struct *vma = walk->vma;
 	pte_t ptent = huge_ptep_get(pte);
 	struct folio *folio = NULL;
+	bool present = false;
 
 	if (pte_present(ptent)) {
 		folio = page_folio(pte_page(ptent));
+		present = true;
 	} else if (is_swap_pte(ptent)) {
 		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
 		if (is_pfn_swap_entry(swpent))
 			folio = pfn_swap_entry_folio(swpent);
 	}
+
 	if (folio) {
-		if (folio_likely_mapped_shared(folio) ||
+		/* We treat non-present entries as "maybe shared". */
+		if (!present || folio_likely_mapped_shared(folio) ||
 		    hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else