Merge branch 'for-next/mte' into for-next/core

KASAN optimisations for the hardware tagging (MTE) implementation.

* for-next/mte:
  kasan: disable freed user page poisoning with HW tags
  arm64: mte: handle tags zeroing at page allocation time
  kasan: use separate (un)poison implementation for integrated init
  mm: arch: remove indirection level in alloc_zeroed_user_highpage_movable()
  kasan: speed up mte_set_mem_tag_range

4 files changed, 78 insertions, 56 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 11da8af06704..e6102dfa4faa 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -53,8 +53,10 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x100000u
 #define ___GFP_THISNODE		0x200000u
 #define ___GFP_ACCOUNT		0x400000u
+#define ___GFP_ZEROTAGS		0x800000u
+#define ___GFP_SKIP_KASAN_POISON	0x1000000u
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x800000u
+#define ___GFP_NOLOCKDEP	0x2000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
@@ -229,16 +231,25 @@ struct vm_area_struct;
  * %__GFP_COMP address compound page metadata.
  *
  * %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if
+ * __GFP_ZERO is set.
+ *
+ * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned
+ * on deallocation. Typically used for userspace pages. Currently only has an
+ * effect in HW tags mode.
  */
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
+#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
+#define __GFP_SKIP_KASAN_POISON	((__force gfp_t)___GFP_SKIP_KASAN_POISON)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP))
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /**
@@ -319,7 +330,8 @@ struct vm_area_struct;
 #define GFP_DMA		__GFP_DMA
 #define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
+#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
+			 __GFP_SKIP_KASAN_POISON)
 #define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
 			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
 #define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 832b49b50c7b..8c6e8e996c87 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -152,28 +152,24 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
 }
 #endif
 
-#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 /**
- * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags
- * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
- * This function will allocate a page for a VMA but the caller is expected
- * to specify via movableflags whether the page will be movable in the
- * future or not
+ * This function will allocate a page for a VMA that the caller knows will
+ * be able to migrate in the future using move_pages() or reclaimed
  *
  * An architecture may override this function by defining
- * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own
+ * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own
  * implementation.
  */
 static inline struct page *
-__alloc_zeroed_user_highpage(gfp_t movableflags,
-			struct vm_area_struct *vma,
-			unsigned long vaddr)
+alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+				   unsigned long vaddr)
 {
-	struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags,
-			vma, vaddr);
+	struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 
 	if (page)
 		clear_user_highpage(page, vaddr);
@@ -182,21 +178,6 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
 }
 #endif
 
-/**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
- * @vma: The VMA the page is to be allocated for
- * @vaddr: The virtual address the page will be inserted into
- *
- * This function will allocate a page for a VMA that the caller knows will
- * be able to migrate in the future using move_pages() or reclaimed
- */
-static inline struct page *
-alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-					unsigned long vaddr)
-{
-	return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
-}
-
 static inline void clear_highpage(struct page *page)
 {
 	void *kaddr = kmap_atomic(page);
@@ -204,6 +185,14 @@ static inline void clear_highpage(struct page *page)
 	kunmap_atomic(kaddr);
 }
 
+#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+
+static inline void tag_clear_highpage(struct page *page)
+{
+}
+
+#endif
+
 /*
  * If we pass in a base or tail page, we can zero up to PAGE_SIZE.
  * If we pass in a head page, we can zero up to the size of the compound page.
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b1678a61e6a7..a1c7ce5f3e4f 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/bug.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
 
@@ -79,14 +80,6 @@ static inline void kasan_disable_current(void) {}
 
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-#ifdef CONFIG_KASAN
-
-struct kasan_cache {
-	int alloc_meta_offset;
-	int free_meta_offset;
-	bool is_kmalloc;
-};
-
 #ifdef CONFIG_KASAN_HW_TAGS
 
 DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
@@ -101,11 +94,14 @@ static inline bool kasan_has_integrated_init(void)
 	return kasan_enabled();
 }
 
+void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags);
+void kasan_free_pages(struct page *page, unsigned int order);
+
 #else /* CONFIG_KASAN_HW_TAGS */
 
 static inline bool kasan_enabled(void)
 {
-	return true;
+	return IS_ENABLED(CONFIG_KASAN);
 }
 
 static inline bool kasan_has_integrated_init(void)
@@ -113,8 +109,30 @@ static inline bool kasan_has_integrated_init(void)
 	return false;
 }
 
+static __always_inline void kasan_alloc_pages(struct page *page,
+					      unsigned int order, gfp_t flags)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
+static __always_inline void kasan_free_pages(struct page *page,
+					     unsigned int order)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
 #endif /* CONFIG_KASAN_HW_TAGS */
 
+#ifdef CONFIG_KASAN
+
+struct kasan_cache {
+	int alloc_meta_offset;
+	int free_meta_offset;
+	bool is_kmalloc;
+};
+
 slab_flags_t __kasan_never_merge(void);
 static __always_inline slab_flags_t kasan_never_merge(void)
 {
@@ -130,20 +148,20 @@ static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
 		__kasan_unpoison_range(addr, size);
 }
 
-void __kasan_alloc_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_alloc_pages(struct page *page,
+void __kasan_poison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_poison_pages(struct page *page,
 						unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_alloc_pages(page, order, init);
+		__kasan_poison_pages(page, order, init);
 }
 
-void __kasan_free_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_free_pages(struct page *page,
-						unsigned int order, bool init)
+void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_unpoison_pages(struct page *page,
+						 unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_free_pages(page, order, init);
+		__kasan_unpoison_pages(page, order, init);
 }
 
 void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
@@ -285,21 +303,15 @@ void kasan_restore_multi_shot(bool enabled);
 
 #else /* CONFIG_KASAN */
 
-static inline bool kasan_enabled(void)
-{
-	return false;
-}
-static inline bool kasan_has_integrated_init(void)
-{
-	return false;
-}
 static inline slab_flags_t kasan_never_merge(void)
 {
 	return 0;
 }
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
-static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {}
-static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {}
+static inline void kasan_poison_pages(struct page *page, unsigned int order,
+				      bool init) {}
+static inline void kasan_unpoison_pages(struct page *page, unsigned int order,
+					bool init) {}
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
 				      slab_flags_t *flags) {}
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 04a34c08e0a6..40e2c5000585 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -138,6 +138,9 @@ enum pageflags {
 #ifdef CONFIG_64BIT
 	PG_arch_2,
 #endif
+#ifdef CONFIG_KASAN_HW_TAGS
+	PG_skip_kasan_poison,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */
@@ -443,6 +446,12 @@ TESTCLEARFLAG(Young, young, PF_ANY)
 PAGEFLAG(Idle, idle, PF_ANY)
 #endif
 
+#ifdef CONFIG_KASAN_HW_TAGS
+PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
+#else
+PAGEFLAG_FALSE(SkipKASanPoison)
+#endif
+
 /*
  * PageReported() is used to track reported free pages within the Buddy
  * allocator. We can use the non-atomic version of the test and set