mm/ksm: convert break_ksm() from walk_page_range_vma() to folio_walk

Let's simplify by reusing folio_walk.  Keep the existing behavior by
handling migration entries and zeropages.

Link: https://lkml.kernel.org/r/20240802155524.517137-12-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/ksm.c b/mm/ksm.c
index 0f5b2bba4ef0775fa7d61742589482e7312fa9f0..8e53666bc7b0c1d353772c795fa694919c3ec24f 100644 (file)
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -608,47 +608,6 @@ static inline bool ksm_test_exit(struct mm_struct *mm)
        return atomic_read(&mm->mm_users) == 0;
 }
 
-static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next,
-                       struct mm_walk *walk)
-{
-       struct page *page = NULL;
-       spinlock_t *ptl;
-       pte_t *pte;
-       pte_t ptent;
-       int ret;
-
-       pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-       if (!pte)
-               return 0;
-       ptent = ptep_get(pte);
-       if (pte_present(ptent)) {
-               page = vm_normal_page(walk->vma, addr, ptent);
-       } else if (!pte_none(ptent)) {
-               swp_entry_t entry = pte_to_swp_entry(ptent);
-
-               /*
-                * As KSM pages remain KSM pages until freed, no need to wait
-                * here for migration to end.
-                */
-               if (is_migration_entry(entry))
-                       page = pfn_swap_entry_to_page(entry);
-       }
-       /* return 1 if the page is an normal ksm page or KSM-placed zero page */
-       ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent);
-       pte_unmap_unlock(pte, ptl);
-       return ret;
-}
-
-static const struct mm_walk_ops break_ksm_ops = {
-       .pmd_entry = break_ksm_pmd_entry,
-       .walk_lock = PGWALK_RDLOCK,
-};
-
-static const struct mm_walk_ops break_ksm_lock_vma_ops = {
-       .pmd_entry = break_ksm_pmd_entry,
-       .walk_lock = PGWALK_WRLOCK,
-};
-
 /*
  * We use break_ksm to break COW on a ksm page by triggering unsharing,
  * such that the ksm page will get replaced by an exclusive anonymous page.
@@ -665,16 +624,26 @@ static const struct mm_walk_ops break_ksm_lock_vma_ops = {
 static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma)
 {
        vm_fault_t ret = 0;
-       const struct mm_walk_ops *ops = lock_vma ?
-                               &break_ksm_lock_vma_ops : &break_ksm_ops;
+
+       if (lock_vma)
+               vma_start_write(vma);
 
        do {
-               int ksm_page;
+               bool ksm_page = false;
+               struct folio_walk fw;
+               struct folio *folio;
 
                cond_resched();
-               ksm_page = walk_page_range_vma(vma, addr, addr + 1, ops, NULL);
-               if (WARN_ON_ONCE(ksm_page < 0))
-                       return ksm_page;
+               folio = folio_walk_start(&fw, vma, addr,
+                                        FW_MIGRATION | FW_ZEROPAGE);
+               if (folio) {
+                       /* Small folio implies FW_LEVEL_PTE. */
+                       if (!folio_test_large(folio) &&
+                           (folio_test_ksm(folio) || is_ksm_zero_pte(fw.pte)))
+                               ksm_page = true;
+                       folio_walk_end(&fw, vma);
+               }
+
                if (!ksm_page)
                        return 0;
                ret = handle_mm_fault(vma, addr,