Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

1 files changed, 51 insertions, 3 deletions

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index cf90b1fa2c60..7b25b53c474a 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -6,6 +6,8 @@
 #include <linux/huge_mm.h>
 #include <linux/swap.h>
 #include <linux/string.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/swapops.h>
 
 /**
  * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
@@ -99,7 +101,8 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
 
 	update_lru_size(lruvec, lru, folio_zonenum(folio),
 			folio_nr_pages(folio));
-	list_add(&folio->lru, &lruvec->lists[lru]);
+	if (lru != LRU_UNEVICTABLE)
+		list_add(&folio->lru, &lruvec->lists[lru]);
 }
 
 static __always_inline void add_page_to_lru_list(struct page *page,
@@ -115,6 +118,7 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
 
 	update_lru_size(lruvec, lru, folio_zonenum(folio),
 			folio_nr_pages(folio));
+	/* This is not expected to be used on LRU_UNEVICTABLE */
 	list_add_tail(&folio->lru, &lruvec->lists[lru]);
 }
 
@@ -127,8 +131,11 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page,
 static __always_inline
 void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
 {
-	list_del(&folio->lru);
-	update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio),
+	enum lru_list lru = folio_lru_list(folio);
+
+	if (lru != LRU_UNEVICTABLE)
+		list_del(&folio->lru);
+	update_lru_size(lruvec, lru, folio_zonenum(folio),
 			-folio_nr_pages(folio));
 }
 
@@ -311,5 +318,46 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
 	return atomic_read(&mm->tlb_flush_pending) > 1;
 }
 
+/*
+ * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
+ * replace a none pte.  NOTE!  This should only be called when *pte is already
+ * cleared so we will never accidentally replace something valuable.  Meanwhile
+ * none pte also means we are not demoting the pte so tlb flushed is not needed.
+ * E.g., when pte cleared the caller should have taken care of the tlb flush.
+ *
+ * Must be called with pgtable lock held so that no thread will see the none
+ * pte, and if they see it, they'll fault and serialize at the pgtable lock.
+ *
+ * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled.
+ */
+static inline void
+pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
+			      pte_t *pte, pte_t pteval)
+{
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	bool arm_uffd_pte = false;
+
+	/* The current status of the pte should be "cleared" before calling */
+	WARN_ON_ONCE(!pte_none(*pte));
+
+	if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
+		return;
+
+	/* A uffd-wp wr-protected normal pte */
+	if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
+		arm_uffd_pte = true;
+
+	/*
+	 * A uffd-wp wr-protected swap pte.  Note: this should even cover an
+	 * existing pte marker with uffd-wp bit set.
+	 */
+	if (unlikely(pte_swp_uffd_wp_any(pteval)))
+		arm_uffd_pte = true;
+
+	if (unlikely(arm_uffd_pte))
+		set_pte_at(vma->vm_mm, addr, pte,
+			   make_pte_marker(PTE_MARKER_UFFD_WP));
+#endif
+}
 
 #endif