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

11 files changed, 146 insertions, 47 deletions

diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h
index 268f99b4602b..18f48a6f2ff6 100644
--- a/arch/alpha/include/asm/page.h
+++ b/arch/alpha/include/asm/page.h
@@ -17,9 +17,9 @@
 extern void clear_page(void *page);
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vmaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 extern void copy_page(void * _to, void * _from);
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index ddd4d17cf9a0..d952352bd008 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -48,43 +48,84 @@ static inline u8 mte_get_random_tag(void)
 	return mte_get_ptr_tag(addr);
 }
 
+static inline u64 __stg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline u64 __stzg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stzg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline void __dc_gva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gva, %0" : : "r"(p) : "memory");
+}
+
+static inline void __dc_gzva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gzva, %0" : : "r"(p) : "memory");
+}
+
 /*
  * Assign allocation tags for a region of memory based on the pointer tag.
  * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and
- * size must be non-zero and MTE_GRANULE_SIZE aligned.
+ * size must be MTE_GRANULE_SIZE aligned.
  */
-static inline void mte_set_mem_tag_range(void *addr, size_t size,
-						u8 tag, bool init)
+static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
+					 bool init)
 {
-	u64 curr, end;
+	u64 curr, mask, dczid_bs, end1, end2, end3;
 
-	if (!size)
-		return;
+	/* Read DC G(Z)VA block size from the system register. */
+	dczid_bs = 4ul << (read_cpuid(DCZID_EL0) & 0xf);
 
 	curr = (u64)__tag_set(addr, tag);
-	end = curr + size;
+	mask = dczid_bs - 1;
+	/* STG/STZG up to the end of the first block. */
+	end1 = curr | mask;
+	end3 = curr + size;
+	/* DC GVA / GZVA in [end1, end2) */
+	end2 = end3 & ~mask;
 
 	/*
-	 * 'asm volatile' is required to prevent the compiler to move
-	 * the statement outside of the loop.
+	 * The following code uses STG on the first DC GVA block even if the
+	 * start address is aligned - it appears to be faster than an alignment
+	 * check + conditional branch. Also, if the range size is at least 2 DC
+	 * GVA blocks, the first two loops can use post-condition to save one
+	 * branch each.
 	 */
-	if (init) {
-		do {
-			asm volatile(__MTE_PREAMBLE "stzg %0, [%0]"
-				     :
-				     : "r" (curr)
-				     : "memory");
-			curr += MTE_GRANULE_SIZE;
-		} while (curr != end);
-	} else {
-		do {
-			asm volatile(__MTE_PREAMBLE "stg %0, [%0]"
-				     :
-				     : "r" (curr)
-				     : "memory");
-			curr += MTE_GRANULE_SIZE;
-		} while (curr != end);
-	}
+#define SET_MEMTAG_RANGE(stg_post, dc_gva)		\
+	do {						\
+		if (size >= 2 * dczid_bs) {		\
+			do {				\
+				curr = stg_post(curr);	\
+			} while (curr < end1);		\
+							\
+			do {				\
+				dc_gva(curr);		\
+				curr += dczid_bs;	\
+			} while (curr < end2);		\
+		}					\
+							\
+		while (curr < end3)			\
+			curr = stg_post(curr);		\
+	} while (0)
+
+	if (init)
+		SET_MEMTAG_RANGE(__stzg_post, __dc_gzva);
+	else
+		SET_MEMTAG_RANGE(__stg_post, __dc_gva);
+#undef SET_MEMTAG_RANGE
 }
 
 void mte_enable_kernel_sync(void);
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index bc88a1ced0d7..67bf259ae768 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -37,6 +37,7 @@ void mte_free_tag_storage(char *storage);
 /* track which pages have valid allocation tags */
 #define PG_mte_tagged	PG_arch_2
 
+void mte_zero_clear_page_tags(void *addr);
 void mte_sync_tags(pte_t *ptep, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
@@ -53,6 +54,9 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
 /* unused if !CONFIG_ARM64_MTE, silence the compiler */
 #define PG_mte_tagged	0
 
+static inline void mte_zero_clear_page_tags(void *addr)
+{
+}
 static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
 {
 }
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 012cffc574e8..ed1b9dcf12b2 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -13,6 +13,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
+#include <linux/types.h> /* for gfp_t */
 #include <asm/pgtable-types.h>
 
 struct page;
@@ -28,9 +29,12 @@ void copy_user_highpage(struct page *to, struct page *from,
 void copy_highpage(struct page *to, struct page *from);
 #define __HAVE_ARCH_COPY_HIGHPAGE
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr);
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
+
+void tag_clear_highpage(struct page *to);
+#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
 
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
index 351537c12f36..e83643b3995f 100644
--- a/arch/arm64/lib/mte.S
+++ b/arch/arm64/lib/mte.S
@@ -37,6 +37,26 @@ SYM_FUNC_START(mte_clear_page_tags)
 SYM_FUNC_END(mte_clear_page_tags)
 
 /*
+ * Zero the page and tags at the same time
+ *
+ * Parameters:
+ *	x0 - address to the beginning of the page
+ */
+SYM_FUNC_START(mte_zero_clear_page_tags)
+	mrs	x1, dczid_el0
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+	and	x0, x0, #(1 << MTE_TAG_SHIFT) - 1	// clear the tag
+
+1:	dc	gzva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_zero_clear_page_tags)
+
+/*
  * Copy the tags from the source page to the destination one
  *   x0 - address of the destination page
  *   x1 - address of the source page
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index d0f972a45099..349c488765ca 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -919,3 +919,29 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 	debug_exception_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug_exception);
+
+/*
+ * Used during anonymous page fault handling.
+ */
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr)
+{
+	gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO;
+
+	/*
+	 * If the page is mapped with PROT_MTE, initialise the tags at the
+	 * point of allocation and page zeroing as this is usually faster than
+	 * separate DC ZVA and STGM.
+	 */
+	if (vma->vm_flags & VM_MTE)
+		flags |= __GFP_ZEROTAGS;
+
+	return alloc_page_vma(flags, vma, vaddr);
+}
+
+void tag_clear_highpage(struct page *page)
+{
+	mte_zero_clear_page_tags(page_address(page));
+	page_kasan_tag_reset(page);
+	set_bit(PG_mte_tagged, &page->flags);
+}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 9b0ad5ba77d2..35936c5ae1ce 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,9 +46,13 @@
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
+#define TCR_MTE_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
 #else
-#define TCR_KASAN_HW_FLAGS 0
+/*
+ * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on
+ * TBI being enabled at EL1.
+ */
+#define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1
 #endif
 
 /*
@@ -454,7 +458,7 @@ SYM_FUNC_START(__cpu_setup)
 	msr_s	SYS_TFSRE0_EL1, xzr
 
 	/* set the TCR_EL1 bits */
-	mov_q	x10, TCR_KASAN_HW_FLAGS
+	mov_q	x10, TCR_MTE_FLAGS
 	orr	tcr, tcr, x10
 1:
 #endif
diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h
index f4dc81fa7146..1b990466d540 100644
--- a/arch/ia64/include/asm/page.h
+++ b/arch/ia64/include/asm/page.h
@@ -82,16 +82,16 @@ do {						\
 } while (0)
 
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr)		\
+#define alloc_zeroed_user_highpage_movable(vma, vaddr)			\
 ({									\
 	struct page *page = alloc_page_vma(				\
-		GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr);	\
+		GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr);		\
 	if (page)							\
  		flush_dcache_page(page);				\
 	page;								\
 })
 
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 8d0f862ee9d7..c9d0d84158a4 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -13,9 +13,9 @@ extern unsigned long memory_end;
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
 #define __va(paddr)		((void *)((unsigned long)(paddr)))
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index cc98f9b78fd4..479dc76e0eca 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -68,9 +68,9 @@ static inline void copy_page(void *to, void *from)
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 /*
  * These are used to make use of C type-checking..
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 7555b48803a8..4d5810c8fab7 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -34,9 +34,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	copy_page(to, from);
 }
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))