[PATCH v10 0/6] KASAN for powerpc64 radix

@@ -12,6 +12,9 @@ config HAVE_ARCH_KASAN_HW_TAGS
 config HAVE_ARCH_KASAN_VMALLOC
 	bool
 
+config ARCH_DISABLE_KASAN_INLINE
+	def_bool n
+
 config CC_HAS_KASAN_GENERIC
 	def_bool $(cc-option, -fsanitize=kernel-address)
 

@@ -130,6 +133,7 @@ config KASAN_OUTLINE
 
 config KASAN_INLINE
 	bool "Inline instrumentation"
+	depends on !ARCH_DISABLE_KASAN_INLINE
 	help
 	  Compiler directly inserts code checking shadow memory before
 	  memory accesses. This is faster than outline (in some workloads

@@ -141,6 +145,7 @@ endchoice
 config KASAN_STACK
 	bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
 	depends on KASAN_GENERIC || KASAN_SW_TAGS
+	depends on !ARCH_DISABLE_KASAN_INLINE
 	default y if CC_IS_GCC
 	help
 	  The LLVM stack address sanitizer has a know problem that

@@ -154,6 +159,9 @@ config KASAN_STACK
 	  but clang users can still enable it for builds without
 	  CONFIG_COMPILE_TEST.	On gcc it is assumed to always be safe
 	  to use and enabled by default.
+	  If the architecture disables inline instrumentation, this is
+	  also disabled as it adds inline-style instrumentation that
+	  is run unconditionally.
 
 config KASAN_SW_TAGS_IDENTIFY
 	bool "Enable memory corruption identification"

@@ -23,6 +23,10 @@ struct kunit_kasan_expectation {
 
 #endif
 
+#ifndef kasan_arch_is_ready
+static inline bool kasan_arch_is_ready(void)	{ return true; }
+#endif
+
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 #include <linux/pgtable.h>

@@ -348,6 +348,10 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return false;
 
+	/* We can't read the shadow byte if the arch isn't ready */
+	if (!kasan_arch_is_ready())
+		return false;
+
 	if (!kasan_byte_accessible(tagged_object)) {
 		kasan_report_invalid_free(tagged_object, ip);
 		return true;

@@ -163,6 +163,9 @@ static __always_inline bool check_region_inline(unsigned long addr,
 						size_t size, bool write,
 						unsigned long ret_ip)
 {
+	if (!kasan_arch_is_ready())
+		return true;
+
 	if (unlikely(size == 0))
 		return true;
 

@@ -85,6 +85,10 @@ void kasan_poison(const void *address, size_t size, u8 value)
 	address = kasan_reset_tag(address);
 	size = round_up(size, KASAN_GRANULE_SIZE);
 
+	/* Don't touch the shadow memory if arch isn't ready */
+	if (!kasan_arch_is_ready())
+		return;
+
 	/* Skip KFENCE memory if called explicitly outside of sl*b. */
 	if (is_kfence_address(address))
 		return;

@@ -43,10 +43,22 @@ static inline bool kasan_arch_is_ready(void)	{ return true; }
 #define PTE_HWTABLE_PTRS 0
 #endif
 
+#ifndef MAX_PTRS_PER_PTE
+#define MAX_PTRS_PER_PTE PTRS_PER_PTE
+#endif
+
+#ifndef MAX_PTRS_PER_PMD
+#define MAX_PTRS_PER_PMD PTRS_PER_PMD
+#endif
+
+#ifndef MAX_PTRS_PER_PUD
+#define MAX_PTRS_PER_PUD PTRS_PER_PUD
+#endif
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
-extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
-extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
+extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS];
+extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD];
+extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD];
 extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
 
 int kasan_populate_early_shadow(const void *shadow_start,

@@ -41,7 +41,7 @@ static inline bool kasan_p4d_table(pgd_t pgd)
 }
 #endif
 #if CONFIG_PGTABLE_LEVELS > 3
-pud_t kasan_early_shadow_pud[PTRS_PER_PUD] __page_aligned_bss;
+pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD] __page_aligned_bss;
 static inline bool kasan_pud_table(p4d_t p4d)
 {
 	return p4d_page(p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud));

@@ -53,7 +53,7 @@ static inline bool kasan_pud_table(p4d_t p4d)
 }
 #endif
 #if CONFIG_PGTABLE_LEVELS > 2
-pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD] __page_aligned_bss;
+pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD] __page_aligned_bss;
 static inline bool kasan_pmd_table(pud_t pud)
 {
 	return pud_page(pud) == virt_to_page(lm_alias(kasan_early_shadow_pmd));

@@ -64,7 +64,7 @@ static inline bool kasan_pmd_table(pud_t pud)
 	return false;
 }
 #endif
-pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS]
 	__page_aligned_bss;
 
 static inline bool kasan_pte_table(pmd_t pmd)

@@ -22,7 +22,8 @@ out-of-bounds accesses for global variables is only supported since Clang 11.
 Tag-based KASAN is only supported in Clang.
 
 Currently generic KASAN is supported for the x86_64, arm, arm64, xtensa, s390
-and riscv architectures, and tag-based KASAN modes are supported only for arm64.
+and riscv architectures. It is also supported on 32-bit powerpc kernels.
+Tag-based KASAN modes are supported only for arm64.
 
 Usage
 -----

@@ -332,7 +333,9 @@ CONFIG_KASAN_VMALLOC
 ~~~~~~~~~~~~~~~~~~~~
 
 With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the
-cost of greater memory usage. Currently this is only supported on x86.
+cost of greater memory usage. Currently this supported on x86, s390
+and 32-bit powerpc. It is optional, except on 32-bit powerpc kernels
+with module support, where it is required.
 
 This works by hooking into vmalloc and vmap, and dynamically
 allocating real shadow memory to back the mappings.

@@ -0,0 +1,12 @@
+KASAN is supported on powerpc on 32-bit only.
+
+32 bit support
+==============
+
+KASAN is supported on both hash and nohash MMUs on 32-bit.
+
+The shadow area sits at the top of the kernel virtual memory space above the
+fixmap area and occupies one eighth of the total kernel virtual memory space.
+
+Instrumentation of the vmalloc area is optional, unless built with modules,
+in which case it is required.

@@ -2,6 +2,6 @@
 
 KASAN_SANITIZE := n
 
-obj-$(CONFIG_PPC32)           += kasan_init_32.o
+obj-$(CONFIG_PPC32)           += init_32.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_BOOK3S_32)	+= book3s_32.o

@@ -22,8 +22,9 @@ out-of-bounds accesses for global variables is only supported since Clang 11.
 Tag-based KASAN is only supported in Clang.
 
 Currently generic KASAN is supported for the x86_64, arm, arm64, xtensa, s390
-and riscv architectures. It is also supported on 32-bit powerpc kernels.
-Tag-based KASAN modes are supported only for arm64.
+and riscv architectures. It is also supported on powerpc for 32-bit powerpc
+kernels and for 64-bit kernels running under the Radix MMU. Tag-based KASAN
+modes are supported only for arm64.
 
 Usage
 -----

@@ -334,8 +335,8 @@ CONFIG_KASAN_VMALLOC
 
 With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the
 cost of greater memory usage. Currently this supported on x86, s390
-and 32-bit powerpc. It is optional, except on 32-bit powerpc kernels
-with module support, where it is required.
+and powerpc. It is optional, except on 64-bit powerpc kernels, and on
+32-bit powerpc kernels with module support, where it is required.
 
 This works by hooking into vmalloc and vmap, and dynamically
 allocating real shadow memory to back the mappings.

@@ -1,4 +1,4 @@
-KASAN is supported on powerpc on 32-bit only.
+KASAN is supported on powerpc on 32-bit and Radix 64-bit only.
 
 32 bit support
 ==============

@@ -10,3 +10,49 @@ fixmap area and occupies one eighth of the total kernel virtual memory space.
 
 Instrumentation of the vmalloc area is optional, unless built with modules,
 in which case it is required.
+
+64 bit support
+==============
+
+Currently, only the radix MMU is supported. There have been versions for hash
+and Book3E processors floating around on the mailing list, but nothing has been
+merged.
+
+KASAN support on Book3S is a bit tricky to get right:
+
+ - It would be good to support inline instrumentation so as to be able to catch
+   stack issues that cannot be caught with outline mode.
+
+ - Inline instrumentation requires a fixed offset.
+
+ - Book3S runs code with translations off ("real mode") during boot, including a
+   lot of generic device-tree parsing code which is used to determine MMU
+   features.
+
+ - Some code - most notably a lot of KVM code - also runs with translations off
+   after boot.
+
+ - Therefore any offset has to point to memory that is valid with
+   translations on or off.
+
+One approach is just to give up on inline instrumentation. This way boot-time
+checks can be delayed until after the MMU is set is up, and we can just not
+instrument any code that runs with translations off after booting. This is the
+current approach.
+
+To avoid this limitiation, the KASAN shadow would have to be placed inside the
+linear mapping, using the same high-bits trick we use for the rest of the linear
+mapping. This is tricky:
+
+ - We'd like to place it near the start of physical memory. In theory we can do
+   this at run-time based on how much physical memory we have, but this requires
+   being able to arbitrarily relocate the kernel, which is basically the tricky
+   part of KASLR. Not being game to implement both tricky things at once, this
+   is hopefully something we can revisit once we get KASLR for Book3S.
+
+ - Alternatively, we can place the shadow at the _end_ of memory, but this
+   requires knowing how much contiguous physical memory a system has _at compile
+   time_. This is a big hammer, and has some unfortunate consequences: inablity
+   to handle discontiguous physical memory, total failure to boot on machines
+   with less memory than specified, and that machines with more memory than
+   specified can't use it. This was deemed unacceptable.

@@ -118,6 +118,7 @@ config PPC
 	# Please keep this list sorted alphabetically.
 	#
 	select ARCH_32BIT_OFF_T if PPC32
+	select ARCH_DISABLE_KASAN_INLINE	if PPC_RADIX_MMU
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE

@@ -183,7 +184,8 @@ config PPC
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
-	select HAVE_ARCH_KASAN_VMALLOC		if PPC32 && PPC_PAGE_SHIFT <= 14
+	select HAVE_ARCH_KASAN			if PPC_RADIX_MMU
+	select HAVE_ARCH_KASAN_VMALLOC		if HAVE_ARCH_KASAN
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT

@@ -397,4 +397,5 @@ config PPC_FAST_ENDIAN_SWITCH
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
-	default 0xe0000000
+	default 0xe0000000 if PPC32
+	default 0xa80e000000000000 if PPC64

@@ -18,6 +18,10 @@
 #include <asm/book3s/64/hash-4k.h>
 #endif
 
+#define H_PTRS_PER_PTE		(1 << H_PTE_INDEX_SIZE)
+#define H_PTRS_PER_PMD		(1 << H_PMD_INDEX_SIZE)
+#define H_PTRS_PER_PUD		(1 << H_PUD_INDEX_SIZE)
+
 /* Bits to set in a PMD/PUD/PGD entry valid bit*/
 #define HASH_PMD_VAL_BITS		(0x8000000000000000UL)
 #define HASH_PUD_VAL_BITS		(0x8000000000000000UL)

@@ -230,6 +230,10 @@ extern unsigned long __pmd_frag_size_shift;
 #define PTRS_PER_PUD	(1 << PUD_INDEX_SIZE)
 #define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
 
+#define MAX_PTRS_PER_PTE ((H_PTRS_PER_PTE > R_PTRS_PER_PTE) ? H_PTRS_PER_PTE : R_PTRS_PER_PTE)
+#define MAX_PTRS_PER_PMD ((H_PTRS_PER_PMD > R_PTRS_PER_PMD) ? H_PTRS_PER_PMD : R_PTRS_PER_PMD)
+#define MAX_PTRS_PER_PUD ((H_PTRS_PER_PUD > R_PTRS_PER_PUD) ? H_PTRS_PER_PUD : R_PTRS_PER_PUD)
+
 /* PMD_SHIFT determines what a second-level page table entry can map */
 #define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)

@@ -35,6 +35,11 @@
 #define RADIX_PMD_SHIFT		(PAGE_SHIFT + RADIX_PTE_INDEX_SIZE)
 #define RADIX_PUD_SHIFT		(RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE)
 #define RADIX_PGD_SHIFT		(RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE)
+
+#define R_PTRS_PER_PTE		(1 << RADIX_PTE_INDEX_SIZE)
+#define R_PTRS_PER_PMD		(1 << RADIX_PMD_INDEX_SIZE)
+#define R_PTRS_PER_PUD		(1 << RADIX_PUD_INDEX_SIZE)
+
 /*
  * Size of EA range mapped by our pagetables.
  */

@@ -68,11 +73,11 @@
  *
  *
  * 3rd quadrant expanded:
- * +------------------------------+
+ * +------------------------------+  Highest address (0xc010000000000000)
+ * +------------------------------+  KASAN shadow end (0xc00fc00000000000)
  * |                              |
  * |                              |
- * |                              |
- * +------------------------------+  Kernel vmemmap end (0xc010000000000000)
+ * +------------------------------+  Kernel vmemmap end/shadow start (0xc00e000000000000)
  * |                              |
  * |           512TB		  |
  * |                              |

@@ -126,6 +131,8 @@
 #define RADIX_VMEMMAP_SIZE	RADIX_KERN_MAP_SIZE
 #define RADIX_VMEMMAP_END	(RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
 
+/* For the sizes of the shadow area, see kasan.h */
+
 #ifndef __ASSEMBLY__
 #define RADIX_PTE_TABLE_SIZE	(sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
 #define RADIX_PMD_TABLE_SIZE	(sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE)

@@ -30,7 +30,29 @@
 
 #define KASAN_SHADOW_OFFSET	ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
 
+#ifdef CONFIG_PPC32
 #define KASAN_SHADOW_END	(-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT))
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * The shadow ends before the highest accessible address
+ * because we don't need a shadow for the shadow. Instead:
+ * c00e000000000000 << 3 + a80e000000000000000 = c00fc00000000000
+ */
+#define KASAN_SHADOW_END 0xc00fc00000000000UL
+
+DECLARE_STATIC_KEY_FALSE(powerpc_kasan_enabled_key);
+
+static __always_inline bool kasan_arch_is_ready(void)
+{
+	if (static_branch_likely(&powerpc_kasan_enabled_key))
+		return true;
+	return false;
+}
+
+#define kasan_arch_is_ready kasan_arch_is_ready
+#endif
 
 #ifdef CONFIG_KASAN
 void kasan_early_init(void);

@@ -32,6 +32,17 @@ KASAN_SANITIZE_early_32.o := n
 KASAN_SANITIZE_cputable.o := n
 KASAN_SANITIZE_prom_init.o := n
 KASAN_SANITIZE_btext.o := n
+KASAN_SANITIZE_paca.o := n
+KASAN_SANITIZE_setup_64.o := n
+KASAN_SANITIZE_mce.o := n
+KASAN_SANITIZE_mce_power.o := n
+
+# we have to be particularly careful in ppc64 to exclude code that
+# runs with translations off, as we cannot access the shadow with
+# translations off. However, ppc32 can sanitize this.
+ifdef CONFIG_PPC64
+KASAN_SANITIZE_traps.o := n
+endif
 
 ifdef CONFIG_KASAN
 CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING

@@ -2157,8 +2157,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack,
 			break;
 
 		stack = (unsigned long *) sp;
-		newsp = stack[0];
-		ip = stack[STACK_FRAME_LR_SAVE];
+		newsp = READ_ONCE_NOCHECK(stack[0]);
+		ip = READ_ONCE_NOCHECK(stack[STACK_FRAME_LR_SAVE]);
 		if (!firstframe || ip != lr) {
 			printk("%s["REG"] ["REG"] %pS",
 				loglvl, sp, ip, (void *)ip);

@@ -2176,17 +2176,19 @@ void show_stack(struct task_struct *tsk, unsigned long *stack,
 		 * See if this is an exception frame.
 		 * We look for the "regshere" marker in the current frame.
 		 */
-		if (validate_sp(sp, tsk, STACK_INT_FRAME_SIZE)
-		    && stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+		if (validate_sp(sp, tsk, STACK_INT_FRAME_SIZE) &&
+		    (READ_ONCE_NOCHECK(stack[STACK_FRAME_MARKER]) ==
+		     STACK_FRAME_REGS_MARKER)) {
 			struct pt_regs *regs = (struct pt_regs *)
 				(sp + STACK_FRAME_OVERHEAD);
 
-			lr = regs->link;
+			lr = READ_ONCE_NOCHECK(regs->link);
 			printk("%s--- interrupt: %lx at %pS\n",
-			       loglvl, regs->trap, (void *)regs->nip);
+			       loglvl, READ_ONCE_NOCHECK(regs->trap),
+			       (void *)READ_ONCE_NOCHECK(regs->nip));
 			__show_regs(regs);
 			printk("%s--- interrupt: %lx\n",
-			       loglvl, regs->trap);
+			       loglvl, READ_ONCE_NOCHECK(regs->trap));
 
 			firstframe = 1;
 		}

@@ -136,3 +136,8 @@ obj-$(CONFIG_KVM_BOOK3S_64_PR) += kvm-pr.o
 obj-$(CONFIG_KVM_BOOK3S_64_HV) += kvm-hv.o
 
 obj-y += $(kvm-book3s_64-builtin-objs-y)
+
+# KVM does a lot in real-mode, and 64-bit Book3S KASAN doesn't support that
+ifdef CONFIG_PPC_BOOK3S_64
+KASAN_SANITIZE := n
+endif

@@ -21,3 +21,12 @@ obj-$(CONFIG_PPC_PKEY)	+= pkeys.o
 
 # Instrumenting the SLB fault path can lead to duplicate SLB entries
 KCOV_INSTRUMENT_slb.o := n
+
+# Parts of these can run in real mode and therefore are
+# not safe with the current outline KASAN implementation
+KASAN_SANITIZE_mmu_context.o := n
+KASAN_SANITIZE_pgtable.o := n
+KASAN_SANITIZE_radix_pgtable.o := n
+KASAN_SANITIZE_radix_tlb.o := n
+KASAN_SANITIZE_slb.o := n
+KASAN_SANITIZE_pkeys.o := n

@@ -5,3 +5,4 @@ KASAN_SANITIZE := n
 obj-$(CONFIG_PPC32)           += init_32.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_BOOK3S_32)	+= book3s_32.o
+obj-$(CONFIG_PPC_BOOK3S_64)   += init_book3s_64.o

@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KASAN for 64-bit Book3S powerpc
+ *
+ * Copyright (C) 2019-2020 IBM Corporation
+ * Author: Daniel Axtens <dja@axtens.net>
+ */
+
+#define DISABLE_BRANCH_PROFILING
+
+#include <linux/kasan.h>
+#include <linux/printk.h>
+#include <linux/sched/task.h>
+#include <linux/memblock.h>
+#include <asm/pgalloc.h>
+
+DEFINE_STATIC_KEY_FALSE(powerpc_kasan_enabled_key);
+
+static void __init kasan_init_phys_region(void *start, void *end)
+{
+	unsigned long k_start, k_end, k_cur;
+	void *va;
+
+	if (start >= end)
+		return;
+
+	k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
+	k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
+
+	va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
+		map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
+}
+
+void __init kasan_init(void)
+{
+	/*
+	 * We want to do the following things:
+	 *  1) Map real memory into the shadow for all physical memblocks
+	 *     This takes us from c000... to c008...
+	 *  2) Leave a hole over the shadow of vmalloc space. KASAN_VMALLOC
+	 *     will manage this for us.
+	 *     This takes us from c008... to c00a...
+	 *  3) Map the 'early shadow'/zero page over iomap and vmemmap space.
+	 *     This takes us up to where we start at c00e...
+	 */
+
+	void *k_start = kasan_mem_to_shadow((void *)RADIX_VMALLOC_END);
+	void *k_end = kasan_mem_to_shadow((void *)RADIX_VMEMMAP_END);
+	phys_addr_t start, end;
+	u64 i;
+	pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL);
+
+	if (!early_radix_enabled())
+		panic("KASAN requires radix!");
+
+	for_each_mem_range(i, &start, &end)
+		kasan_init_phys_region((void *)start, (void *)end);
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		__set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page,
+			     &kasan_early_shadow_pte[i], zero_pte, 0);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		pmd_populate_kernel(&init_mm, &kasan_early_shadow_pmd[i],
+				    kasan_early_shadow_pte);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		pud_populate(&init_mm, &kasan_early_shadow_pud[i],
+			     kasan_early_shadow_pmd);
+
+	/* map the early shadow over the iomap and vmemmap space */
+	kasan_populate_early_shadow(k_start, k_end);
+
+	/* mark early shadow region as RO and wipe it */
+	zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO);
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		__set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page,
+			     &kasan_early_shadow_pte[i], zero_pte, 0);
+
+	/*
+	 * clear_page relies on some cache info that hasn't been set up yet.
+	 * It ends up looping ~forever and blows up other data.
+	 * Use memset instead.
+	 */
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+
+	static_branch_inc(&powerpc_kasan_enabled_key);
+
+	/* Enable error messages */
+	init_task.kasan_depth = 0;
+	pr_info("KASAN init done (64-bit Book3S)\n");
+}
+
+void __init kasan_late_init(void) { }

@@ -20,6 +20,7 @@
 #include <linux/seq_file.h>
 #include <asm/fixmap.h>
 #include <linux/const.h>
+#include <linux/kasan.h>
 #include <asm/page.h>
 #include <asm/hugetlb.h>
 

@@ -317,6 +318,23 @@ static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start)
 	unsigned long addr;
 	unsigned int i;
 
+#if defined(CONFIG_KASAN) && defined(CONFIG_PPC_BOOK3S_64)
+	/*
+	 * On radix + KASAN, we want to check for the KASAN "early" shadow
+	 * which covers huge quantities of memory with the same set of
+	 * read-only PTEs. If it is, we want to note the first page (to see
+	 * the status change), and then note the last page. This gives us good
+	 * results without spending ages noting the exact same PTEs over 100s of
+	 * terabytes of memory.
+	 */
+	if (p4d_page(*p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud))) {
+		walk_pmd(st, pud, start);
+		addr = start + (PTRS_PER_PUD - 1) * PUD_SIZE;
+		walk_pmd(st, pud, addr);
+		return;
+	}
+#endif
+
 	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
 		addr = start + i * PUD_SIZE;
 		if (!pud_none(*pud) && !pud_is_leaf(*pud))

@@ -387,11 +405,11 @@ static void populate_markers(void)
 #endif
 	address_markers[i++].start_address = FIXADDR_START;
 	address_markers[i++].start_address = FIXADDR_TOP;
+#endif /* CONFIG_PPC64 */
 #ifdef CONFIG_KASAN
 	address_markers[i++].start_address = KASAN_SHADOW_START;
 	address_markers[i++].start_address = KASAN_SHADOW_END;
 #endif
-#endif /* CONFIG_PPC64 */
 }
 
 static int ptdump_show(struct seq_file *m, void *v)

@@ -101,6 +101,7 @@ config PPC_BOOK3S_64
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select IRQ_WORK
 	select PPC_MM_SLICES
+	select KASAN_VMALLOC if KASAN
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"

@@ -1,4 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
+
+# nothing that deals with real mode is safe to KASAN
+# in particular, idle code runs a bunch of things in real mode
+KASAN_SANITIZE_idle.o := n
+KASAN_SANITIZE_pci-ioda.o := n
+
 obj-y			+= setup.o opal-call.o opal-wrappers.o opal.o opal-async.o
 obj-y			+= idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o

@@ -30,3 +30,6 @@ obj-$(CONFIG_PPC_SVM)		+= svm.o
 obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
 obj-$(CONFIG_SUSPEND)		+= suspend.o
+
+# nothing that operates in real mode is safe for KASAN
+KASAN_SANITIZE_ras.o := n