s390/kasan: move shadow mapping to decompressor

Since regular paging structs are initialized in decompressor already
move KASAN shadow mapping to decompressor as well. This helps to avoid
allocating KASAN required memory in 1 large chunk, de-duplicate paging
structs creation code and start the uncompressed kernel with KASAN
instrumentation right away. This also allows to avoid all pitfalls
accidentally calling KASAN instrumented code during KASAN initialization.

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

3 files changed, 230 insertions, 15 deletions

diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 2b4048106418..872963c8a0ab 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -32,6 +32,13 @@ struct vmlinux_info {
 	unsigned long init_mm_off;
 	unsigned long swapper_pg_dir_off;
 	unsigned long invalid_pg_dir_off;
+#ifdef CONFIG_KASAN
+	unsigned long kasan_early_shadow_page_off;
+	unsigned long kasan_early_shadow_pte_off;
+	unsigned long kasan_early_shadow_pmd_off;
+	unsigned long kasan_early_shadow_pud_off;
+	unsigned long kasan_early_shadow_p4d_off;
+#endif
 };
 
 void startup_kernel(void);
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index bc07e24329b9..bdf305a93987 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -266,6 +266,13 @@ static void offset_vmlinux_info(unsigned long offset)
 	vmlinux.init_mm_off += offset;
 	vmlinux.swapper_pg_dir_off += offset;
 	vmlinux.invalid_pg_dir_off += offset;
+#ifdef CONFIG_KASAN
+	vmlinux.kasan_early_shadow_page_off += offset;
+	vmlinux.kasan_early_shadow_pte_off += offset;
+	vmlinux.kasan_early_shadow_pmd_off += offset;
+	vmlinux.kasan_early_shadow_pud_off += offset;
+	vmlinux.kasan_early_shadow_p4d_off += offset;
+#endif
 }
 
 void startup_kernel(void)
@@ -307,10 +314,6 @@ void startup_kernel(void)
 	detect_physmem_online_ranges(max_physmem_end);
 	save_ipl_cert_comp_list();
 	rescue_initrd(safe_addr, ident_map_size);
-#ifdef CONFIG_KASAN
-	physmem_alloc_top_down(RR_KASAN, kasan_estimate_memory_needs(get_physmem_usable_total()),
-			       _SEGMENT_SIZE);
-#endif
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
 		random_lma = get_random_base();
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 8f16e6f9fb20..b01ea2abda03 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/sched/task.h>
 #include <linux/pgtable.h>
+#include <linux/kasan.h>
 #include <asm/pgalloc.h>
 #include <asm/facility.h>
 #include <asm/sections.h>
@@ -16,6 +17,182 @@ unsigned long __bootdata_preserved(s390_invalid_asce);
 #define swapper_pg_dir		vmlinux.swapper_pg_dir_off
 #define invalid_pg_dir		vmlinux.invalid_pg_dir_off
 
+enum populate_mode {
+	POPULATE_NONE,
+	POPULATE_ONE2ONE,
+	POPULATE_ABS_LOWCORE,
+#ifdef CONFIG_KASAN
+	POPULATE_KASAN_MAP_SHADOW,
+	POPULATE_KASAN_ZERO_SHADOW,
+	POPULATE_KASAN_SHALLOW
+#endif
+};
+
+static void pgtable_populate(unsigned long addr, unsigned long end, enum populate_mode mode);
+
+#ifdef CONFIG_KASAN
+
+#define kasan_early_shadow_page	vmlinux.kasan_early_shadow_page_off
+#define kasan_early_shadow_pte	((pte_t *)vmlinux.kasan_early_shadow_pte_off)
+#define kasan_early_shadow_pmd	((pmd_t *)vmlinux.kasan_early_shadow_pmd_off)
+#define kasan_early_shadow_pud	((pud_t *)vmlinux.kasan_early_shadow_pud_off)
+#define kasan_early_shadow_p4d	((p4d_t *)vmlinux.kasan_early_shadow_p4d_off)
+#define __sha(x)		((unsigned long)kasan_mem_to_shadow((void *)x))
+
+static pte_t pte_z;
+
+static void kasan_populate_shadow(void)
+{
+	pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY);
+	pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY);
+	p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY);
+	unsigned long untracked_end;
+	unsigned long start, end;
+	int i;
+
+	pte_z = __pte(__pa(kasan_early_shadow_page) | pgprot_val(PAGE_KERNEL_RO));
+	if (!machine.has_nx)
+		pte_z = clear_pte_bit(pte_z, __pgprot(_PAGE_NOEXEC));
+	crst_table_init((unsigned long *)kasan_early_shadow_p4d, p4d_val(p4d_z));
+	crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z));
+	crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z));
+	memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE);
+
+	/*
+	 * Current memory layout:
+	 * +- 0 -------------+	       +- shadow start -+
+	 * |1:1 ident mapping|	      /|1/8 of ident map|
+	 * |		     |	     / |		|
+	 * +-end of ident map+	    /  +----------------+
+	 * | ... gap ...     |	   /   |    kasan	|
+	 * |		     |	  /    |  zero page	|
+	 * +- vmalloc area  -+	 /     |   mapping	|
+	 * | vmalloc_size    |	/      | (untracked)	|
+	 * +- modules vaddr -+ /       +----------------+
+	 * | 2Gb	     |/        |    unmapped	| allocated per module
+	 * +- shadow start  -+	       +----------------+
+	 * | 1/8 addr space  |	       | zero pg mapping| (untracked)
+	 * +- shadow end ----+---------+- shadow end ---+
+	 *
+	 * Current memory layout (KASAN_VMALLOC):
+	 * +- 0 -------------+	       +- shadow start -+
+	 * |1:1 ident mapping|	      /|1/8 of ident map|
+	 * |		     |	     / |		|
+	 * +-end of ident map+	    /  +----------------+
+	 * | ... gap ...     |	   /   | kasan zero page| (untracked)
+	 * |		     |	  /    | mapping	|
+	 * +- vmalloc area  -+	 /     +----------------+
+	 * | vmalloc_size    |	/      |shallow populate|
+	 * +- modules vaddr -+ /       +----------------+
+	 * | 2Gb	     |/        |shallow populate|
+	 * +- shadow start  -+	       +----------------+
+	 * | 1/8 addr space  |	       | zero pg mapping| (untracked)
+	 * +- shadow end ----+---------+- shadow end ---+
+	 */
+
+	for_each_physmem_usable_range(i, &start, &end)
+		pgtable_populate(__sha(start), __sha(end), POPULATE_KASAN_MAP_SHADOW);
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+		untracked_end = VMALLOC_START;
+		/* shallowly populate kasan shadow for vmalloc and modules */
+		pgtable_populate(__sha(VMALLOC_START), __sha(MODULES_END), POPULATE_KASAN_SHALLOW);
+	} else {
+		untracked_end = MODULES_VADDR;
+	}
+	/* populate kasan shadow for untracked memory */
+	pgtable_populate(__sha(ident_map_size), __sha(untracked_end), POPULATE_KASAN_ZERO_SHADOW);
+	pgtable_populate(__sha(MODULES_END), __sha(_REGION1_SIZE), POPULATE_KASAN_ZERO_SHADOW);
+}
+
+static bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr,
+					   unsigned long end, enum populate_mode mode)
+{
+	if (mode == POPULATE_KASAN_ZERO_SHADOW &&
+	    IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+		pgd_populate(&init_mm, pgd, kasan_early_shadow_p4d);
+		return true;
+	}
+	return false;
+}
+
+static bool kasan_p4d_populate_zero_shadow(p4d_t *p4d, unsigned long addr,
+					   unsigned long end, enum populate_mode mode)
+{
+	if (mode == POPULATE_KASAN_ZERO_SHADOW &&
+	    IS_ALIGNED(addr, P4D_SIZE) && end - addr >= P4D_SIZE) {
+		p4d_populate(&init_mm, p4d, kasan_early_shadow_pud);
+		return true;
+	}
+	return false;
+}
+
+static bool kasan_pud_populate_zero_shadow(pud_t *pud, unsigned long addr,
+					   unsigned long end, enum populate_mode mode)
+{
+	if (mode == POPULATE_KASAN_ZERO_SHADOW &&
+	    IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) {
+		pud_populate(&init_mm, pud, kasan_early_shadow_pmd);
+		return true;
+	}
+	return false;
+}
+
+static bool kasan_pmd_populate_zero_shadow(pmd_t *pmd, unsigned long addr,
+					   unsigned long end, enum populate_mode mode)
+{
+	if (mode == POPULATE_KASAN_ZERO_SHADOW &&
+	    IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) {
+		pmd_populate(&init_mm, pmd, kasan_early_shadow_pte);
+		return true;
+	}
+	return false;
+}
+
+static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode)
+{
+	pte_t entry;
+
+	if (mode == POPULATE_KASAN_ZERO_SHADOW) {
+		set_pte(pte, pte_z);
+		return true;
+	}
+	return false;
+}
+#else
+
+static inline void kasan_populate_shadow(void) {}
+
+static inline bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr,
+						  unsigned long end, enum populate_mode mode)
+{
+	return false;
+}
+
+static inline bool kasan_p4d_populate_zero_shadow(p4d_t *p4d, unsigned long addr,
+						  unsigned long end, enum populate_mode mode)
+{
+	return false;
+}
+
+static inline bool kasan_pud_populate_zero_shadow(pud_t *pud, unsigned long addr,
+						  unsigned long end, enum populate_mode mode)
+{
+	return false;
+}
+
+static inline bool kasan_pmd_populate_zero_shadow(pmd_t *pmd, unsigned long addr,
+						  unsigned long end, enum populate_mode mode)
+{
+	return false;
+}
+
+static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode)
+{
+	return false;
+}
+
+#endif
+
 /*
  * Mimic virt_to_kpte() in lack of init_mm symbol. Skip pmd NULL check though.
  */
@@ -24,12 +201,6 @@ static inline pte_t *__virt_to_kpte(unsigned long va)
 	return pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va), va);
 }
 
-enum populate_mode {
-	POPULATE_NONE,
-	POPULATE_ONE2ONE,
-	POPULATE_ABS_LOWCORE,
-};
-
 static void *boot_crst_alloc(unsigned long val)
 {
 	unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER;
@@ -42,14 +213,26 @@ static void *boot_crst_alloc(unsigned long val)
 
 static pte_t *boot_pte_alloc(void)
 {
+	static void *pte_leftover;
 	pte_t *pte;
 
-	pte = (pte_t *)physmem_alloc_top_down(RR_VMEM, _PAGE_TABLE_SIZE, _PAGE_TABLE_SIZE);
+	/*
+	 * handling pte_leftovers this way helps to avoid memory fragmentation
+	 * during POPULATE_KASAN_MAP_SHADOW when EDAT is off
+	 */
+	if (!pte_leftover) {
+		pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE);
+		pte = pte_leftover + _PAGE_TABLE_SIZE;
+	} else {
+		pte = pte_leftover;
+		pte_leftover = NULL;
+	}
+
 	memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE);
 	return pte;
 }
 
-static unsigned long _pa(unsigned long addr, enum populate_mode mode)
+static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_mode mode)
 {
 	switch (mode) {
 	case POPULATE_NONE:
@@ -58,6 +241,12 @@ static unsigned long _pa(unsigned long addr, enum populate_mode mode)
 		return addr;
 	case POPULATE_ABS_LOWCORE:
 		return __abs_lowcore_pa(addr);
+#ifdef CONFIG_KASAN
+	case POPULATE_KASAN_MAP_SHADOW:
+		addr = physmem_alloc_top_down(RR_VMEM, size, size);
+		memset((void *)addr, 0, size);
+		return addr;
+#endif
 	default:
 		return -1;
 	}
@@ -83,7 +272,9 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
 	pte = pte_offset_kernel(pmd, addr);
 	for (; addr < end; addr += PAGE_SIZE, pte++) {
 		if (pte_none(*pte)) {
-			entry = __pte(_pa(addr, mode));
+			if (kasan_pte_populate_zero_shadow(pte, mode))
+				continue;
+			entry = __pte(_pa(addr, PAGE_SIZE, mode));
 			entry = set_pte_bit(entry, PAGE_KERNEL_EXEC);
 			set_pte(pte, entry);
 		}
@@ -101,8 +292,10 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
 	for (; addr < end; addr = next, pmd++) {
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(*pmd)) {
+			if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode))
+				continue;
 			if (can_large_pmd(pmd, addr, next)) {
-				entry = __pmd(_pa(addr, mode));
+				entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode));
 				entry = set_pmd_bit(entry, SEGMENT_KERNEL_EXEC);
 				set_pmd(pmd, entry);
 				continue;
@@ -127,8 +320,10 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
 	for (; addr < end; addr = next, pud++) {
 		next = pud_addr_end(addr, end);
 		if (pud_none(*pud)) {
+			if (kasan_pud_populate_zero_shadow(pud, addr, next, mode))
+				continue;
 			if (can_large_pud(pud, addr, next)) {
-				entry = __pud(_pa(addr, mode));
+				entry = __pud(_pa(addr, _REGION3_SIZE, mode));
 				entry = set_pud_bit(entry, REGION3_KERNEL_EXEC);
 				set_pud(pud, entry);
 				continue;
@@ -153,6 +348,8 @@ static void pgtable_p4d_populate(pgd_t *pgd, unsigned long addr, unsigned long e
 	for (; addr < end; addr = next, p4d++) {
 		next = p4d_addr_end(addr, end);
 		if (p4d_none(*p4d)) {
+			if (kasan_p4d_populate_zero_shadow(p4d, addr, next, mode))
+				continue;
 			pud = boot_crst_alloc(_REGION3_ENTRY_EMPTY);
 			p4d_populate(&init_mm, p4d, pud);
 		}
@@ -170,9 +367,15 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat
 	for (; addr < end; addr = next, pgd++) {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(*pgd)) {
+			if (kasan_pgd_populate_zero_shadow(pgd, addr, next, mode))
+				continue;
 			p4d = boot_crst_alloc(_REGION2_ENTRY_EMPTY);
 			pgd_populate(&init_mm, pgd, p4d);
 		}
+#ifdef CONFIG_KASAN
+		if (mode == POPULATE_KASAN_SHALLOW)
+			continue;
+#endif
 		pgtable_p4d_populate(pgd, addr, next, mode);
 	}
 }
@@ -210,6 +413,8 @@ void setup_vmem(unsigned long asce_limit)
 			 POPULATE_NONE);
 	memcpy_real_ptep = __virt_to_kpte(__memcpy_real_area);
 
+	kasan_populate_shadow();
+
 	S390_lowcore.kernel_asce = swapper_pg_dir | asce_bits;
 	S390_lowcore.user_asce = s390_invalid_asce;