[PATCH v1 2/4] mm: smaller folio_pte_batch() improvements

[David Hildenbrand <david@redhat.com>]

Let's clean up a bit:

(1) No need for start_ptep vs. ptep anymore, we can simply use ptep

(2) Let's switch to "unsigned int" for everything

(3) We can simplify the code by leaving the pte unchanged after the
    pte_same() check.

(4) Clarify that we should never exceed a single VMA; it indicates a
    problem in the caller.

No functional change intended.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 mm/internal.h | 37 +++++++++++++++----------------------
 1 file changed, 15 insertions(+), 22 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 9690c75063881..ca6590c6d9eab 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -221,7 +221,7 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
  * folio_pte_batch - detect a PTE batch for a large folio
  * @folio: The large folio to detect a PTE batch for.
  * @addr: The user virtual address the first page is mapped at.
- * @start_ptep: Page table pointer for the first entry.
+ * @ptep: Page table pointer for the first entry.
  * @pte: Page table entry for the first page.
  * @max_nr: The maximum number of table entries to consider.
  * @flags: Flags to modify the PTE batch semantics.
@@ -233,24 +233,24 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
  *		  first one is dirty.
  *
  * Detect a PTE batch: consecutive (present) PTEs that map consecutive
- * pages of the same large folio.
+ * pages of the same large folio in a single VMA and a single page table.
  *
  * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
  * the accessed bit, writable bit, dirty bit (unless FPB_HONOR_DIRTY is set) and
  * soft-dirty bit (unless FPB_HONOR_SOFT_DIRTY is set).
  *
- * start_ptep must map any page of the folio. max_nr must be at least one and
- * must be limited by the caller so scanning cannot exceed a single page table.
+ * @ptep must map any page of the folio. max_nr must be at least one and
+ * must be limited by the caller so scanning cannot exceed a single VMA and
+ * a single page table.
  *
  * Return: the number of table entries in the batch.
  */
-static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
-		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
+static inline unsigned int folio_pte_batch(struct folio *folio, unsigned long addr,
+		pte_t *ptep, pte_t pte, unsigned int max_nr, fpb_t flags,
 		bool *any_writable, bool *any_young, bool *any_dirty)
 {
-	pte_t expected_pte, *ptep;
-	bool writable, young, dirty;
-	int nr, cur_nr;
+	unsigned int nr, cur_nr;
+	pte_t expected_pte;
 
 	if (any_writable)
 		*any_writable = false;
@@ -267,29 +267,22 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 	max_nr = min_t(unsigned long, max_nr,
 		       folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
 
-	nr = pte_batch_hint(start_ptep, pte);
+	nr = pte_batch_hint(ptep, pte);
 	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
-	ptep = start_ptep + nr;
+	ptep = ptep + nr;
 
 	while (nr < max_nr) {
 		pte = ptep_get(ptep);
-		if (any_writable)
-			writable = !!pte_write(pte);
-		if (any_young)
-			young = !!pte_young(pte);
-		if (any_dirty)
-			dirty = !!pte_dirty(pte);
-		pte = __pte_batch_clear_ignored(pte, flags);
 
-		if (!pte_same(pte, expected_pte))
+		if (!pte_same(__pte_batch_clear_ignored(pte, flags), expected_pte))
 			break;
 
 		if (any_writable)
-			*any_writable |= writable;
+			*any_writable |= pte_write(pte);
 		if (any_young)
-			*any_young |= young;
+			*any_young |= pte_young(pte);
 		if (any_dirty)
-			*any_dirty |= dirty;
+			*any_dirty |= pte_dirty(pte);
 
 		cur_nr = pte_batch_hint(ptep, pte);
 		expected_pte = pte_advance_pfn(expected_pte, cur_nr);
-- 
2.49.0