Some platforms can customize the PTE PMD entry soft-dirty bit making it
unavailable even if the architecture provides the resource.

Add an API which architectures can define their specific implementations
to detect if soft-dirty bit is available on which device the kernel is
running.

This patch is removing "ifdef CONFIG_MEM_SOFT_DIRTY" in favor of
pgtable_supports_soft_dirty() checks that defaults to
IS_ENABLED(CONFIG_MEM_SOFT_DIRTY), if not overridden by
the architecture, no change in behavior is expected.

We make sure to never set VM_SOFTDIRTY if !pgtable_supports_soft_dirty(),
so we will never run into VM_SOFTDIRTY checks.

Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 fs/proc/task_mmu.c      | 15 ++++++---------
 include/linux/mm.h      |  3 +++
 include/linux/pgtable.h | 12 ++++++++++++
 mm/debug_vm_pgtable.c   | 10 +++++-----
 mm/huge_memory.c        | 13 +++++++------
 mm/internal.h           |  2 +-
 mm/mmap.c               |  6 ++++--
 mm/mremap.c             | 13 +++++++------
 mm/userfaultfd.c        | 10 ++++------
 mm/vma.c                |  6 ++++--
 mm/vma_exec.c           |  5 ++++-
 11 files changed, 57 insertions(+), 38 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 41b062ce6ad8..2b4ab5718ab5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1584,8 +1584,6 @@ struct clear_refs_private {
 	enum clear_refs_types type;
 };
 
-#ifdef CONFIG_MEM_SOFT_DIRTY
-
 static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	struct folio *folio;
@@ -1605,6 +1603,8 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr,
 static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte)
 {
+	if (!pgtable_supports_soft_dirty())
+		return;
 	/*
 	 * The soft-dirty tracker uses #PF-s to catch writes
 	 * to pages, so write-protect the pte as well. See the
@@ -1630,19 +1630,16 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		set_pte_at(vma->vm_mm, addr, pte, ptent);
 	}
 }
-#else
-static inline void clear_soft_dirty(struct vm_area_struct *vma,
-		unsigned long addr, pte_t *pte)
-{
-}
-#endif
 
-#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t old, pmd = *pmdp;
 
+	if (!pgtable_supports_soft_dirty())
+		return;
+
 	if (pmd_present(pmd)) {
 		/* See comment in change_huge_pmd() */
 		old = pmdp_invalidate(vma, addr, pmdp);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 43eec43da66a..687c462f2a71 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -861,6 +861,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 static inline void vm_flags_init(struct vm_area_struct *vma,
 				 vm_flags_t flags)
 {
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
 	ACCESS_PRIVATE(vma, __vm_flags) = flags;
 }
 
@@ -879,6 +880,7 @@ static inline void vm_flags_reset(struct vm_area_struct *vma,
 static inline void vm_flags_reset_once(struct vm_area_struct *vma,
 				       vm_flags_t flags)
 {
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
 	vma_assert_write_locked(vma);
 	WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
 }
@@ -886,6 +888,7 @@ static inline void vm_flags_reset_once(struct vm_area_struct *vma,
 static inline void vm_flags_set(struct vm_area_struct *vma,
 				vm_flags_t flags)
 {
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
 	vma_start_write(vma);
 	ACCESS_PRIVATE(vma, __vm_flags) |= flags;
 }
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 32e8457ad535..b13b6f42be3c 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1553,6 +1553,18 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
+/*
+ * Some platforms can customize the PTE soft-dirty bit making it unavailable
+ * even if the architecture provides the resource.
+ * Adding this API allows architectures to add their own checks for the
+ * devices on which the kernel is running.
+ * Note: When overriding it, please make sure the CONFIG_MEM_SOFT_DIRTY
+ * is part of this macro.
+ */
+#ifndef pgtable_supports_soft_dirty
+#define pgtable_supports_soft_dirty()	IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
 static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 1eae87dbef73..ae9b9310d96f 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -704,7 +704,7 @@ static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
 
-	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
+	if (!pgtable_supports_soft_dirty())
 		return;
 
 	pr_debug("Validating PTE soft dirty\n");
@@ -717,7 +717,7 @@ static void __init pte_swap_soft_dirty_tests(struct pgtable_debug_args *args)
 	pte_t pte;
 	softleaf_t entry;
 
-	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
+	if (!pgtable_supports_soft_dirty())
 		return;
 
 	pr_debug("Validating PTE swap soft dirty\n");
@@ -734,7 +734,7 @@ static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
-	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
+	if (!pgtable_supports_soft_dirty())
 		return;
 
 	if (!has_transparent_hugepage())
@@ -750,8 +750,8 @@ static void __init pmd_leaf_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pmd_t pmd;
 
-	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) ||
-		!IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION))
+	if (!pgtable_supports_soft_dirty() ||
+	    !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION))
 		return;
 
 	if (!has_transparent_hugepage())
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0184cd915f44..d04fedbbf799 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2427,12 +2427,13 @@ static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
 
 static pmd_t move_soft_dirty_pmd(pmd_t pmd)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	if (unlikely(pmd_is_migration_entry(pmd)))
-		pmd = pmd_swp_mksoft_dirty(pmd);
-	else if (pmd_present(pmd))
-		pmd = pmd_mksoft_dirty(pmd);
-#endif
+	if (pgtable_supports_soft_dirty()) {
+		if (unlikely(pmd_is_migration_entry(pmd)))
+			pmd = pmd_swp_mksoft_dirty(pmd);
+		else if (pmd_present(pmd))
+			pmd = pmd_mksoft_dirty(pmd);
+	}
+
 	return pmd;
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 929bc4a5dd98..04c307ee33ae 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1554,7 +1554,7 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 	 * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY)
 	 * will be constantly true.
 	 */
-	if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
+	if (!pgtable_supports_soft_dirty())
 		return false;
 
 	/*
diff --git a/mm/mmap.c b/mm/mmap.c
index dc51680824ec..4bdb9ffa9e25 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1448,8 +1448,10 @@ static struct vm_area_struct *__install_special_mapping(
 		return ERR_PTR(-ENOMEM);
 
 	vma_set_range(vma, addr, addr + len, 0);
-	vm_flags_init(vma, (vm_flags | mm->def_flags |
-		      VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK);
+	vm_flags |= mm->def_flags | VM_DONTEXPAND;
+	if (pgtable_supports_soft_dirty())
+		vm_flags |= VM_SOFTDIRTY;
+	vm_flags_init(vma, vm_flags & ~VM_LOCKED_MASK);
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
 	vma->vm_ops = ops;
diff --git a/mm/mremap.c b/mm/mremap.c
index fdb0485ede74..672264807db6 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -165,12 +165,13 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 	 * Set soft dirty bit so we can notice
 	 * in userspace the ptes were moved.
 	 */
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	if (pte_present(pte))
-		pte = pte_mksoft_dirty(pte);
-	else
-		pte = pte_swp_mksoft_dirty(pte);
-#endif
+	if (pgtable_supports_soft_dirty()) {
+		if (pte_present(pte))
+			pte = pte_mksoft_dirty(pte);
+		else
+			pte = pte_swp_mksoft_dirty(pte);
+	}
+
 	return pte;
 }
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index bd1f74a7a5ac..e6dfd5f28acd 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1119,9 +1119,8 @@ static long move_present_ptes(struct mm_struct *mm,
 
 		orig_dst_pte = folio_mk_pte(src_folio, dst_vma->vm_page_prot);
 		/* Set soft dirty bit so userspace can notice the pte was moved */
-#ifdef CONFIG_MEM_SOFT_DIRTY
-		orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
-#endif
+		if (pgtable_supports_soft_dirty())
+			orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
 		if (pte_dirty(orig_src_pte))
 			orig_dst_pte = pte_mkdirty(orig_dst_pte);
 		orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
@@ -1208,9 +1207,8 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
-#endif
+	if (pgtable_supports_soft_dirty())
+		orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);
 
diff --git a/mm/vma.c b/mm/vma.c
index 6cb082bc5e29..ad3d905a81db 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2555,7 +2555,8 @@ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
 	 * then new mapped in-place (which must be aimed as
 	 * a completely new data area).
 	 */
-	vm_flags_set(vma, VM_SOFTDIRTY);
+	if (pgtable_supports_soft_dirty())
+		vm_flags_set(vma, VM_SOFTDIRTY);
 
 	vma_set_page_prot(vma);
 }
@@ -2860,7 +2861,8 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	mm->data_vm += len >> PAGE_SHIFT;
 	if (vm_flags & VM_LOCKED)
 		mm->locked_vm += (len >> PAGE_SHIFT);
-	vm_flags_set(vma, VM_SOFTDIRTY);
+	if (pgtable_supports_soft_dirty())
+		vm_flags_set(vma, VM_SOFTDIRTY);
 	return 0;
 
 mas_store_fail:
diff --git a/mm/vma_exec.c b/mm/vma_exec.c
index 922ee51747a6..8134e1afca68 100644
--- a/mm/vma_exec.c
+++ b/mm/vma_exec.c
@@ -107,6 +107,7 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
 int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
 			  unsigned long *top_mem_p)
 {
+	unsigned long flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
 	int err;
 	struct vm_area_struct *vma = vm_area_alloc(mm);
 
@@ -137,7 +138,9 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
 	BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
 	vma->vm_end = STACK_TOP_MAX;
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
-	vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP);
+	if (pgtable_supports_soft_dirty())
+		flags |= VM_SOFTDIRTY;
+	vm_flags_init(vma, flags);
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
 	err = insert_vm_struct(mm, vma);
-- 
2.34.1


Some platforms can customize the PTE/PMD entry uffd-wp bit making
it unavailable even if the architecture provides the resource.
This patch adds a macro API pgtable_supports_uffd_wp() that allows
architectures to define their specific implementations to check if
the uffd-wp bit is available on which device the kernel is running.

Also this patch is removing "ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP" and
"ifdef CONFIG_PTE_MARKER_UFFD_WP" in favor of pgtable_supports_uffd_wp()
and uffd_supports_wp_marker() checks respectively that default to
IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP) and
"IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP) && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP)"
if not overridden by the architecture, no change in behavior is expected.

Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 fs/userfaultfd.c                   | 22 +++++-----
 include/asm-generic/pgtable_uffd.h | 17 ++++++++
 include/linux/mm_inline.h          |  8 ++--
 include/linux/userfaultfd_k.h      | 69 ++++++++++++++++++------------
 mm/memory.c                        |  6 ++-
 5 files changed, 78 insertions(+), 44 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 4e900091849b..1590de993e55 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1289,9 +1289,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
 		vm_flags |= VM_UFFD_MISSING;
 	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
-#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
-		goto out;
-#endif
+		if (!pgtable_supports_uffd_wp())
+			goto out;
+
 		vm_flags |= VM_UFFD_WP;
 	}
 	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
@@ -1999,14 +1999,14 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	uffdio_api.features &=
 		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
 #endif
-#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
-	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
-#endif
-#ifndef CONFIG_PTE_MARKER_UFFD_WP
-	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
-	uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
-	uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
-#endif
+	if (!pgtable_supports_uffd_wp())
+		uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
+
+	if (!uffd_supports_wp_marker()) {
+		uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+		uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
+		uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
+	}
 
 	ret = -EINVAL;
 	if (features & ~uffdio_api.features)
diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
index 828966d4c281..0d85791efdf7 100644
--- a/include/asm-generic/pgtable_uffd.h
+++ b/include/asm-generic/pgtable_uffd.h
@@ -1,6 +1,23 @@
 #ifndef _ASM_GENERIC_PGTABLE_UFFD_H
 #define _ASM_GENERIC_PGTABLE_UFFD_H
 
+/*
+ * Some platforms can customize the uffd-wp bit, making it unavailable
+ * even if the architecture provides the resource.
+ * Adding this API allows architectures to add their own checks for the
+ * devices on which the kernel is running.
+ * Note: When overriding it, please make sure the
+ * CONFIG_HAVE_ARCH_USERFAULTFD_WP is part of this macro.
+ */
+#ifndef pgtable_supports_uffd_wp
+#define pgtable_supports_uffd_wp()	IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP)
+#endif
+
+static inline bool uffd_supports_wp_marker(void)
+{
+	return pgtable_supports_uffd_wp() && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP);
+}
+
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 static __always_inline int pte_uffd_wp(pte_t pte)
 {
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index ca7a18351797..2ced24fc3beb 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -553,7 +553,6 @@ static inline pte_marker copy_pte_marker(
 
 	return dstm;
 }
-#endif
 
 /*
  * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
@@ -571,9 +570,11 @@ static inline bool
 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;
 
+	if (!uffd_supports_wp_marker())
+		return false;
+
 	/* The current status of the pte should be "cleared" before calling */
 	WARN_ON_ONCE(!pte_none(ptep_get(pte)));
 
@@ -602,7 +603,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 			   make_pte_marker(PTE_MARKER_UFFD_WP));
 		return true;
 	}
-#endif
+
 	return false;
 }
 
@@ -616,6 +617,7 @@ static inline bool vma_has_recency(const struct vm_area_struct *vma)
 
 	return true;
 }
+#endif
 
 /**
  * num_pages_contiguous() - determine the number of contiguous pages
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 96b089dff4ef..fd5f42765497 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -228,15 +228,14 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 	if (wp_async && (vm_flags == VM_UFFD_WP))
 		return true;
 
-#ifndef CONFIG_PTE_MARKER_UFFD_WP
 	/*
 	 * If user requested uffd-wp but not enabled pte markers for
 	 * uffd-wp, then shmem & hugetlbfs are not supported but only
 	 * anonymous.
 	 */
-	if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma))
+	if (!uffd_supports_wp_marker() && (vm_flags & VM_UFFD_WP) &&
+	    !vma_is_anonymous(vma))
 		return false;
-#endif
 
 	/* By default, allow any of anon|shmem|hugetlb */
 	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
@@ -291,6 +290,43 @@ void userfaultfd_release_new(struct userfaultfd_ctx *ctx);
 void userfaultfd_release_all(struct mm_struct *mm,
 			     struct userfaultfd_ctx *ctx);
 
+static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
+{
+	/* Only wr-protect mode uses pte markers */
+	if (!userfaultfd_wp(vma))
+		return false;
+
+	/* File-based uffd-wp always need markers */
+	if (!vma_is_anonymous(vma))
+		return true;
+
+	/*
+	 * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED
+	 * enabled (to apply markers on zero pages).
+	 */
+	return userfaultfd_wp_unpopulated(vma);
+}
+
+/*
+ * Returns true if this is a swap pte and was uffd-wp wr-protected in either
+ * forms (pte marker or a normal swap pte), false otherwise.
+ */
+static inline bool pte_swp_uffd_wp_any(pte_t pte)
+{
+	if (!uffd_supports_wp_marker())
+		return false;
+
+	if (pte_present(pte))
+		return false;
+
+	if (pte_swp_uffd_wp(pte))
+		return true;
+
+	if (pte_is_uffd_wp_marker(pte))
+		return true;
+
+	return false;
+}
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -415,23 +451,9 @@ static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma)
 	return false;
 }
 
-#endif /* CONFIG_USERFAULTFD */
-
 static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
 {
-	/* Only wr-protect mode uses pte markers */
-	if (!userfaultfd_wp(vma))
-		return false;
-
-	/* File-based uffd-wp always need markers */
-	if (!vma_is_anonymous(vma))
-		return true;
-
-	/*
-	 * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED
-	 * enabled (to apply markers on zero pages).
-	 */
-	return userfaultfd_wp_unpopulated(vma);
+	return false;
 }
 
 /*
@@ -440,16 +462,7 @@ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
  */
 static inline bool pte_swp_uffd_wp_any(pte_t pte)
 {
-#ifdef CONFIG_PTE_MARKER_UFFD_WP
-	if (pte_present(pte))
-		return false;
-	if (pte_swp_uffd_wp(pte))
-		return true;
-
-	if (pte_is_uffd_wp_marker(pte))
-		return true;
-#endif
 	return false;
 }
-
+#endif /* CONFIG_USERFAULTFD */
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/mm/memory.c b/mm/memory.c
index 50b93b45b174..6675e87eb7dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1590,7 +1590,9 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 {
 	bool was_installed = false;
 
-#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	if (!uffd_supports_wp_marker())
+		return false;
+
 	/* Zap on anonymous always means dropping everything */
 	if (vma_is_anonymous(vma))
 		return false;
@@ -1607,7 +1609,7 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 		pte++;
 		addr += PAGE_SIZE;
 	}
-#endif
+
 	return was_installed;
 }
 
-- 
2.34.1


The Svrsw60t59b extension allows to free the PTE reserved bits 60
and 59 for software to use.

Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 arch/riscv/Kconfig             | 14 ++++++++++++++
 arch/riscv/include/asm/hwcap.h |  1 +
 arch/riscv/kernel/cpufeature.c |  1 +
 3 files changed, 16 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 22cda9c452d2..829d95d173cf 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -849,6 +849,20 @@ config RISCV_ISA_ZICBOP
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_SVRSW60T59B
+	bool "Svrsw60t59b extension support for using PTE bits 60 and 59"
+	depends on MMU && 64BIT
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Adds support to dynamically detect the presence of the Svrsw60t59b
+	  extension and enable its usage.
+
+	  The Svrsw60t59b extension allows to free the PTE reserved bits 60
+	  and 59 for software to use.
+
+	  If you don't know what to do here, say Y.
+
 config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
 	def_bool y
 	# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index affd63e11b0a..f98fcb5c17d5 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -106,6 +106,7 @@
 #define RISCV_ISA_EXT_ZAAMO		97
 #define RISCV_ISA_EXT_ZALRSC		98
 #define RISCV_ISA_EXT_ZICBOP		99
+#define RISCV_ISA_EXT_SVRSW60T59B	100
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 72ca768f4e91..5441282656a7 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -539,6 +539,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(svrsw60t59b, RISCV_ISA_EXT_SVRSW60T59B),
 	__RISCV_ISA_EXT_DATA(svvptc, RISCV_ISA_EXT_SVVPTC),
 };
 
-- 
2.34.1


The Svrsw60t59b extension allows to free the PTE reserved bits 60 and 59
for software, this patch uses bit 59 for soft-dirty.

To add swap PTE soft-dirty tracking, we borrow bit 3 which is available
for swap PTEs on RISC-V systems.

Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 arch/riscv/Kconfig                    |  1 +
 arch/riscv/include/asm/pgtable-bits.h | 19 +++++++
 arch/riscv/include/asm/pgtable.h      | 75 ++++++++++++++++++++++++++-
 3 files changed, 93 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 829d95d173cf..e5f070485bbe 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -142,6 +142,7 @@ config RISCV
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_SOFT_DIRTY if 64BIT && MMU && RISCV_ISA_SVRSW60T59B
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index 179bd4afece4..f3bac2bbc157 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -19,6 +19,25 @@
 #define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
 
 #define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/* ext_svrsw60t59b: bit 59 for soft-dirty tracking */
+#define _PAGE_SOFT_DIRTY						\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 (1UL << 59) : 0)
+/*
+ * Bit 3 is always zero for swap entry computation, so we
+ * can borrow it for swap page soft-dirty tracking.
+ */
+#define _PAGE_SWP_SOFT_DIRTY						\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 _PAGE_EXEC : 0)
+#else
+#define _PAGE_SOFT_DIRTY	0
+#define _PAGE_SWP_SOFT_DIRTY	0
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 5a08eb5fe99f..049ba0e64f94 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -428,7 +428,7 @@ static inline pte_t pte_mkwrite_novma(pte_t pte)
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_DIRTY);
+	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
@@ -456,6 +456,42 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+#define pgtable_supports_soft_dirty()				\
+	(IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) &&			\
+	 riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B))
+
+static inline bool pte_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_SOFT_DIRTY));
+}
+
+static inline bool pte_swp_soft_dirty(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_SWP_SOFT_DIRTY));
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define pte_leaf_size(pte)	(pte_napot(pte) ?				\
 					napot_cont_size(napot_cont_order(pte)) :\
@@ -805,6 +841,40 @@ static inline pud_t pud_mkspecial(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline bool pmd_soft_dirty(pmd_t pmd)
+{
+	return pte_soft_dirty(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)));
+}
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+static inline bool pmd_swp_soft_dirty(pmd_t pmd)
+{
+	return pte_swp_soft_dirty(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)));
+}
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
@@ -1003,7 +1073,8 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
  *
  * Format of swap PTE:
  *	bit            0:	_PAGE_PRESENT (zero)
- *	bit       1 to 3:       _PAGE_LEAF (zero)
+ *	bit       1 to 2:	(zero)
+ *	bit            3:	_PAGE_SWP_SOFT_DIRTY
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type
-- 
2.34.1


The Svrsw60t59b extension allows to free the PTE reserved bits 60 and 59
for software, this patch uses bit 60 for uffd-wp tracking

Additionally for tracking the uffd-wp state as a PTE swap bit, we borrow
bit 4 which is not involved into swap entry computation.

Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 arch/riscv/Kconfig                    |  1 +
 arch/riscv/include/asm/pgtable-bits.h | 18 +++++++
 arch/riscv/include/asm/pgtable.h      | 68 +++++++++++++++++++++++++++
 3 files changed, 87 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e5f070485bbe..b2eff4789fe2 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -148,6 +148,7 @@ config RISCV
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if 64BIT && MMU
 	select HAVE_ARCH_USERFAULTFD_MINOR if 64BIT && USERFAULTFD
+	select HAVE_ARCH_USERFAULTFD_WP if 64BIT && MMU && USERFAULTFD && RISCV_ISA_SVRSW60T59B
 	select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CONTEXT_TRACKING_USER
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index f3bac2bbc157..b422d9691e60 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -38,6 +38,24 @@
 #define _PAGE_SWP_SOFT_DIRTY	0
 #endif /* CONFIG_MEM_SOFT_DIRTY */
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+
+/* ext_svrsw60t59b: Bit(60) for uffd-wp tracking */
+#define _PAGE_UFFD_WP							\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 (1UL << 60) : 0)
+/*
+ * Bit 4 is not involved into swap entry computation, so we
+ * can borrow it for swap page uffd-wp tracking.
+ */
+#define _PAGE_SWP_UFFD_WP						\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 _PAGE_USER : 0)
+#else
+#define _PAGE_UFFD_WP		0
+#define _PAGE_SWP_UFFD_WP	0
+#endif
+
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 049ba0e64f94..1c311193e7da 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -417,6 +417,41 @@ static inline pte_t pte_wrprotect(pte_t pte)
 	return __pte(pte_val(pte) & ~(_PAGE_WRITE));
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define pgtable_supports_uffd_wp()	\
+	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)
+
+static inline bool pte_uffd_wp(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_UFFD_WP);
+}
+
+static inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte_wrprotect(__pte(pte_val(pte) | _PAGE_UFFD_WP));
+}
+
+static inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_UFFD_WP));
+}
+
+static inline bool pte_swp_uffd_wp(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_SWP_UFFD_WP);
+}
+
+static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_UFFD_WP);
+}
+
+static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_SWP_UFFD_WP));
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 /* static inline pte_t pte_mkread(pte_t pte) */
 
 static inline pte_t pte_mkwrite_novma(pte_t pte)
@@ -841,6 +876,38 @@ static inline pud_t pud_mkspecial(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline bool pmd_uffd_wp(pmd_t pmd)
+{
+	return pte_uffd_wp(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
+{
+	return pte_pmd(pte_mkuffd_wp(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
+{
+	return pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd)));
+}
+
+static inline bool pmd_swp_uffd_wp(pmd_t pmd)
+{
+	return pte_swp_uffd_wp(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd)));
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline bool pmd_soft_dirty(pmd_t pmd)
 {
@@ -1075,6 +1142,7 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
  *	bit            0:	_PAGE_PRESENT (zero)
  *	bit       1 to 2:	(zero)
  *	bit            3:	_PAGE_SWP_SOFT_DIRTY
+ *	bit            4:	_PAGE_SWP_UFFD_WP
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type
-- 
2.34.1


Add description for the Svrsw60t59b extension (PTE Reserved for SW
bits 60:59) extension which was ratified recently in
riscv-non-isa/riscv-iommu.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
---
 Documentation/devicetree/bindings/riscv/extensions.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 543ac94718e8..194ef4754452 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -217,6 +217,12 @@ properties:
             memory types as ratified in the 20191213 version of the privileged
             ISA specification.
 
+        - const: svrsw60t59b
+          description:
+            The Svrsw60t59b extension for providing two more bits[60:59] to
+            PTE/PMD entry as ratified at commit 28bde925e7a7 ("PTE Reserved
+            for SW bits 60:59") of riscv-non-isa/riscv-iommu.
+
         - const: svvptc
           description:
             The standard Svvptc supervisor-level extension for
-- 
2.34.1