ARM: 9016/2: Initialize the mapping of KASan shadow memory

This patch initializes KASan shadow region's page table and memory.
There are two stage for KASan initializing:

1. At early boot stage the whole shadow region is mapped to just
   one physical page (kasan_zero_page). It is finished by the function
   kasan_early_init which is called by __mmap_switched(arch/arm/kernel/
   head-common.S)

2. After the calling of paging_init, we use kasan_zero_page as zero
   shadow for some memory that KASan does not need to track, and we
   allocate a new shadow space for the other memory that KASan need to
   track. These issues are finished by the function kasan_init which is
   call by setup_arch.

When using KASan we also need to increase the THREAD_SIZE_ORDER
from 1 to 2 as the extra calls for shadow memory uses quite a bit
of stack.

As we need to make a temporary copy of the PGD when setting up
shadow memory we create a helpful PGD_SIZE definition for both
LPAE and non-LPAE setups.

The KASan core code unconditionally calls pud_populate() so this
needs to be changed from BUG() to do {} while (0) when building
with KASan enabled.

After the initial development by Andre Ryabinin several modifications
have been made to this code:

Abbott Liu <liuwenliang@huawei.com>
- Add support ARM LPAE: If LPAE is enabled, KASan shadow region's
  mapping table need be copied in the pgd_alloc() function.
- Change kasan_pte_populate,kasan_pmd_populate,kasan_pud_populate,
  kasan_pgd_populate from .meminit.text section to .init.text section.
  Reported by Florian Fainelli <f.fainelli@gmail.com>

Linus Walleij <linus.walleij@linaro.org>:
- Drop the custom mainpulation of TTBR0 and just use
  cpu_switch_mm() to switch the pgd table.
- Adopt to handle 4th level page tabel folding.
- Rewrite the entire page directory and page entry initialization
  sequence to be recursive based on ARM64:s kasan_init.c.

Ard Biesheuvel <ardb@kernel.org>:
- Necessary underlying fixes.
- Crucial bug fixes to the memory set-up code.

Co-developed-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Co-developed-by: Abbott Liu <liuwenliang@huawei.com>
Co-developed-by: Ard Biesheuvel <ardb@kernel.org>

Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: kasan-dev@googlegroups.com
Cc: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Ard Biesheuvel <ardb@kernel.org> # QEMU/KVM/mach-virt/LPAE/8G
Tested-by: Florian Fainelli <f.fainelli@gmail.com> # Brahma SoCs
Tested-by: Ahmad Fatoum <a.fatoum@pengutronix.de> # i.MX6Q
Reported-by: Russell King - ARM Linux <rmk+kernel@armlinux.org.uk>
Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: Abbott Liu <liuwenliang@huawei.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

arch/arm/include/asm/kasan.h

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/arm/include/asm/kasan.h
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ */
+
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifdef CONFIG_KASAN
+
+#include <asm/kasan_def.h>
+
+#define KASAN_SHADOW_SCALE_SHIFT 3
+
+/*
+ * The compiler uses a shadow offset assuming that addresses start
+ * from 0. Kernel addresses don't start from 0, so shadow
+ * for kernel really starts from 'compiler's shadow offset' +
+ * ('kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT)
+ */
+
+asmlinkage void kasan_early_init(void);
+extern void kasan_init(void);
+
+#else
+static inline void kasan_init(void) { }
+#endif
+
+#endif

arch/arm/include/asm/pgalloc.h

@@ -21,6 +21,7 @@
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
 #ifdef CONFIG_ARM_LPAE
+#define PGD_SIZE		(PTRS_PER_PGD * sizeof(pgd_t))
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
@@ -28,14 +29,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 }
 
 #else	/* !CONFIG_ARM_LPAE */
+#define PGD_SIZE		(PAGE_SIZE << 2)
 
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
+#ifdef CONFIG_KASAN
+/* The KASan core unconditionally calls pud_populate() on all architectures */
+#define pud_populate(mm,pmd,pte)	do { } while (0)
+#else
 #define pud_populate(mm,pmd,pte)	BUG()
-
+#endif
 #endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);

arch/arm/include/asm/thread_info.h

@@ -13,7 +13,15 @@
 #include <asm/fpstate.h>
 #include <asm/page.h>
 
+#ifdef CONFIG_KASAN
+/*
+ * KASan uses a lot of extra stack space so the thread size order needs to
+ * be increased.
+ */
+#define THREAD_SIZE_ORDER	2
+#else
 #define THREAD_SIZE_ORDER	1
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_START_SP		(THREAD_SIZE - 8)
 

arch/arm/kernel/head-common.S

@@ -111,6 +111,9 @@ __mmap_switched:
 	str	r8, [r2]			@ Save atags pointer
 	cmp	r3, #0
 	strne	r10, [r3]			@ Save control register values
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
 	mov	lr, #0
 	b	start_kernel
 ENDPROC(__mmap_switched)

arch/arm/kernel/setup.c

@@ -59,6 +59,7 @@
 #include <asm/unwind.h>
 #include <asm/memblock.h>
 #include <asm/virt.h>
+#include <asm/kasan.h>
 
 #include "atags.h"
 
@@ -1145,6 +1146,7 @@ void __init setup_arch(char **cmdline_p)
 	early_ioremap_reset();
 
 	paging_init(mdesc);
+	kasan_init();
 	request_standard_resources(mdesc);
 
 	if (mdesc->restart)

arch/arm/mm/Makefile

@@ -113,3 +113,6 @@ obj-$(CONFIG_CACHE_L2X0_PMU)	+= cache-l2x0-pmu.o
 obj-$(CONFIG_CACHE_XSC3L2)	+= cache-xsc3l2.o
 obj-$(CONFIG_CACHE_TAUROS2)	+= cache-tauros2.o
 obj-$(CONFIG_CACHE_UNIPHIER)	+= cache-uniphier.o
+
+KASAN_SANITIZE_kasan_init.o	:= n
+obj-$(CONFIG_KASAN)		+= kasan_init.o

arch/arm/mm/kasan_init.c

@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains kasan initialization code for ARM.
+ *
+ * Copyright (c) 2018 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/sched/task.h>
+#include <linux/start_kernel.h>
+#include <linux/pgtable.h>
+#include <asm/cputype.h>
+#include <asm/highmem.h>
+#include <asm/mach/map.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/procinfo.h>
+#include <asm/proc-fns.h>
+
+#include "mm.h"
+
+static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+
+pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
+
+static __init void *kasan_alloc_block(size_t size)
+{
+	return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_KASAN, NUMA_NO_NODE);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+				      unsigned long end, bool early)
+{
+	unsigned long next;
+	pte_t *ptep = pte_offset_kernel(pmdp, addr);
+
+	do {
+		pte_t entry;
+		void *p;
+
+		next = addr + PAGE_SIZE;
+
+		if (!early) {
+			if (!pte_none(READ_ONCE(*ptep)))
+				continue;
+
+			p = kasan_alloc_block(PAGE_SIZE);
+			if (!p) {
+				panic("%s failed to allocate shadow page for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			memset(p, KASAN_SHADOW_INIT, PAGE_SIZE);
+			entry = pfn_pte(virt_to_pfn(p),
+					__pgprot(pgprot_val(PAGE_KERNEL)));
+		} else if (pte_none(READ_ONCE(*ptep))) {
+			/*
+			 * The early shadow memory is mapping all KASan
+			 * operations to one and the same page in memory,
+			 * "kasan_early_shadow_page" so that the instrumentation
+			 * will work on a scratch area until we can set up the
+			 * proper KASan shadow memory.
+			 */
+			entry = pfn_pte(virt_to_pfn(kasan_early_shadow_page),
+					__pgprot(_L_PTE_DEFAULT | L_PTE_DIRTY | L_PTE_XN));
+		} else {
+			/*
+			 * Early shadow mappings are PMD_SIZE aligned, so if the
+			 * first entry is already set, they must all be set.
+			 */
+			return;
+		}
+
+		set_pte_at(&init_mm, addr, ptep, entry);
+	} while (ptep++, addr = next, addr != end);
+}
+
+/*
+ * The pmd (page middle directory) is only used on LPAE
+ */
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+				      unsigned long end, bool early)
+{
+	unsigned long next;
+	pmd_t *pmdp = pmd_offset(pudp, addr);
+
+	do {
+		if (pmd_none(*pmdp)) {
+			/*
+			 * We attempt to allocate a shadow block for the PMDs
+			 * used by the PTEs for this address if it isn't already
+			 * allocated.
+			 */
+			void *p = early ? kasan_early_shadow_pte :
+				kasan_alloc_block(PAGE_SIZE);
+
+			if (!p) {
+				panic("%s failed to allocate shadow block for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			pmd_populate_kernel(&init_mm, pmdp, p);
+			flush_pmd_entry(pmdp);
+		}
+
+		next = pmd_addr_end(addr, end);
+		kasan_pte_populate(pmdp, addr, next, early);
+	} while (pmdp++, addr = next, addr != end);
+}
+
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+				      bool early)
+{
+	unsigned long next;
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
+
+	pgdp = pgd_offset_k(addr);
+
+	do {
+		/*
+		 * Allocate and populate the shadow block of p4d folded into
+		 * pud folded into pmd if it doesn't already exist
+		 */
+		if (!early && pgd_none(*pgdp)) {
+			void *p = kasan_alloc_block(PAGE_SIZE);
+
+			if (!p) {
+				panic("%s failed to allocate shadow block for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			pgd_populate(&init_mm, pgdp, p);
+		}
+
+		next = pgd_addr_end(addr, end);
+		/*
+		 * We just immediately jump over the p4d and pud page
+		 * directories since we believe ARM32 will never gain four
+		 * nor five level page tables.
+		 */
+		p4dp = p4d_offset(pgdp, addr);
+		pudp = pud_offset(p4dp, addr);
+
+		kasan_pmd_populate(pudp, addr, next, early);
+	} while (pgdp++, addr = next, addr != end);
+}
+
+extern struct proc_info_list *lookup_processor_type(unsigned int);
+
+void __init kasan_early_init(void)
+{
+	struct proc_info_list *list;
+
+	/*
+	 * locate processor in the list of supported processor
+	 * types.  The linker builds this table for us from the
+	 * entries in arch/arm/mm/proc-*.S
+	 */
+	list = lookup_processor_type(read_cpuid_id());
+	if (list) {
+#ifdef MULTI_CPU
+		processor = *list->proc;
+#endif
+	}
+
+	BUILD_BUG_ON((KASAN_SHADOW_END - (1UL << 29)) != KASAN_SHADOW_OFFSET);
+	/*
+	 * We walk the page table and set all of the shadow memory to point
+	 * to the scratch page.
+	 */
+	kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+}
+
+static void __init clear_pgds(unsigned long start,
+			unsigned long end)
+{
+	for (; start && start < end; start += PMD_SIZE)
+		pmd_clear(pmd_off_k(start));
+}
+
+static int __init create_mapping(void *start, void *end)
+{
+	void *shadow_start, *shadow_end;
+
+	shadow_start = kasan_mem_to_shadow(start);
+	shadow_end = kasan_mem_to_shadow(end);
+
+	pr_info("Mapping kernel virtual memory block: %px-%px at shadow: %px-%px\n",
+		start, end, shadow_start, shadow_end);
+
+	kasan_pgd_populate((unsigned long)shadow_start & PAGE_MASK,
+			   PAGE_ALIGN((unsigned long)shadow_end), false);
+	return 0;
+}
+
+void __init kasan_init(void)
+{
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	/*
+	 * We are going to perform proper setup of shadow memory.
+	 *
+	 * At first we should unmap early shadow (clear_pgds() call bellow).
+	 * However, instrumented code can't execute without shadow memory.
+	 *
+	 * To keep the early shadow memory MMU tables around while setting up
+	 * the proper shadow memory, we copy swapper_pg_dir (the initial page
+	 * table) to tmp_pgd_table and use that to keep the early shadow memory
+	 * mapped until the full shadow setup is finished. Then we swap back
+	 * to the proper swapper_pg_dir.
+	 */
+
+	memcpy(tmp_pgd_table, swapper_pg_dir, sizeof(tmp_pgd_table));
+#ifdef CONFIG_ARM_LPAE
+	/* We need to be in the same PGD or this won't work */
+	BUILD_BUG_ON(pgd_index(KASAN_SHADOW_START) !=
+		     pgd_index(KASAN_SHADOW_END));
+	memcpy(tmp_pmd_table,
+	       pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)),
+	       sizeof(tmp_pmd_table));
+	set_pgd(&tmp_pgd_table[pgd_index(KASAN_SHADOW_START)],
+		__pgd(__pa(tmp_pmd_table) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
+#endif
+	cpu_switch_mm(tmp_pgd_table, &init_mm);
+	local_flush_tlb_all();
+
+	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START),
+				    kasan_mem_to_shadow((void *)-1UL) + 1);
+
+	for_each_mem_range(i, &pa_start, &pa_end) {
+		void *start = __va(pa_start);
+		void *end = __va(pa_end);
+
+		/* Do not attempt to shadow highmem */
+		if (pa_start >= arm_lowmem_limit) {
+			pr_info("Skip highmem block at %pa-%pa\n", &pa_start, &pa_end);
+			continue;
+		}
+		if (pa_end > arm_lowmem_limit) {
+			pr_info("Truncating shadow for memory block at %pa-%pa to lowmem region at %pa\n",
+				&pa_start, &pa_end, &arm_lowmem_limit);
+			end = __va(arm_lowmem_limit);
+		}
+		if (start >= end) {
+			pr_info("Skipping invalid memory block %pa-%pa (virtual %p-%p)\n",
+				&pa_start, &pa_end, start, end);
+			continue;
+		}
+
+		create_mapping(start, end);
+	}
+
+	/*
+	 * 1. The module global variables are in MODULES_VADDR ~ MODULES_END,
+	 *    so we need to map this area.
+	 * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR
+	 *    ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't
+	 *    use kasan_populate_zero_shadow.
+	 */
+	create_mapping((void *)MODULES_VADDR, (void *)(PKMAP_BASE + PMD_SIZE));
+
+	/*
+	 * KAsan may reuse the contents of kasan_early_shadow_pte directly, so
+	 * we should make sure that it maps the zero page read-only.
+	 */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte_at(&init_mm, KASAN_SHADOW_START + i*PAGE_SIZE,
+			   &kasan_early_shadow_pte[i],
+			   pfn_pte(virt_to_pfn(kasan_early_shadow_page),
+				__pgprot(pgprot_val(PAGE_KERNEL)
+					 | L_PTE_RDONLY)));
+
+	cpu_switch_mm(swapper_pg_dir, &init_mm);
+	local_flush_tlb_all();
+
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	pr_info("Kernel address sanitizer initialized\n");
+	init_task.kasan_depth = 0;
+}

arch/arm/mm/pgd.c

@@ -66,7 +66,21 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	new_pmd = pmd_alloc(mm, new_pud, 0);
 	if (!new_pmd)
 		goto no_pmd;
-#endif
+#ifdef CONFIG_KASAN
+	/*
+	 * Copy PMD table for KASAN shadow mappings.
+	 */
+	init_pgd = pgd_offset_k(TASK_SIZE);
+	init_p4d = p4d_offset(init_pgd, TASK_SIZE);
+	init_pud = pud_offset(init_p4d, TASK_SIZE);
+	init_pmd = pmd_offset(init_pud, TASK_SIZE);
+	new_pmd = pmd_offset(new_pud, TASK_SIZE);
+	memcpy(new_pmd, init_pmd,
+	       (pmd_index(MODULES_VADDR) - pmd_index(TASK_SIZE))
+	       * sizeof(pmd_t));
+	clean_dcache_area(new_pmd, PTRS_PER_PMD * sizeof(pmd_t));
+#endif /* CONFIG_KASAN */
+#endif /* CONFIG_LPAE */
 
 	if (!vectors_high()) {
 		/*