UML: add support for KASAN under x86_64

Make KASAN run on User Mode Linux on x86_64.

The UML-specific KASAN initializer uses mmap to map the ~16TB of shadow
memory to the location defined by KASAN_SHADOW_OFFSET.  kasan_init()
utilizes constructors to initialize KASAN before main().

The location of the KASAN shadow memory, starting at
KASAN_SHADOW_OFFSET, can be configured using the KASAN_SHADOW_OFFSET
option. The default location of this offset is 0x100000000000, which
keeps it out-of-the-way even on UML setups with more "physical" memory.

For low-memory setups, 0x7fff8000 can be used instead, which fits in an
immediate and is therefore faster, as suggested by Dmitry Vyukov. There
is usually enough free space at this location; however, it is a config
option so that it can be easily changed if needed.

Note that, unlike KASAN on other architectures, vmalloc allocations
still use the shadow memory allocated upfront, rather than allocating
and free-ing it per-vmalloc allocation.

If another architecture chooses to go down the same path, we should
replace the checks for CONFIG_UML with something more generic, such
as:
- A CONFIG_KASAN_NO_SHADOW_ALLOC option, which architectures could set
- or, a way of having architecture-specific versions of these vmalloc
  and module shadow memory allocation options.

Also note that, while UML supports both KASAN in inline mode
(CONFIG_KASAN_INLINE) and static linking (CONFIG_STATIC_LINK), it does
not support both at the same time.

Signed-off-by: Patricia Alfonso <trishalfonso@google.com>
Co-developed-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Signed-off-by: Richard Weinberger <richard@nod.at>

8 files changed, 103 insertions, 4 deletions

diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 7b0f953e7d6c..78de31ac1da7 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -12,6 +12,8 @@ config UML
 	select ARCH_HAS_STRNLEN_USER
 	select ARCH_NO_PREEMPT
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_KASAN if X86_64
+	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_UID16
@@ -219,6 +221,19 @@ config UML_TIME_TRAVEL_SUPPORT
 
 	  It is safe to say Y, but you probably don't need this.
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0x100000000000
+	help
+	  This is the offset at which the ~16TB of shadow memory is
+	  mapped and used by KASAN for memory debugging. This can be any
+	  address that has at least KASAN_SHADOW_SIZE (total address space divided
+	  by 8) amount of space so that the KASAN shadow memory does not conflict
+	  with anything. The default is 0x100000000000, which works even if mem is
+	  set to a large value. On low-memory systems, try 0x7fff8000, as it fits
+	  into the immediate of most instructions, improving performance.
+
 endmenu
 
 source "arch/um/drivers/Kconfig"
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index eca6c452a41b..fd481ac371de 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -83,6 +83,8 @@
   }
   .init_array : {
 	__init_array_start = .;
+	*(.kasan_init)
+	*(.init_array.*)
 	*(.init_array)
 	__init_array_end = .;
   }
diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h
new file mode 100644
index 000000000000..0d6547f4ec85
--- /dev/null
+++ b/arch/um/include/asm/kasan.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_UM_KASAN_H
+#define __ASM_UM_KASAN_H
+
+#include <linux/init.h>
+#include <linux/const.h>
+
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
+/* used in kasan_mem_to_shadow to divide by 8 */
+#define KASAN_SHADOW_SCALE_SHIFT 3
+
+#ifdef CONFIG_X86_64
+#define KASAN_HOST_USER_SPACE_END_ADDR 0x00007fffffffffffUL
+/* KASAN_SHADOW_SIZE is the size of total address space divided by 8 */
+#define KASAN_SHADOW_SIZE ((KASAN_HOST_USER_SPACE_END_ADDR + 1) >> \
+			KASAN_SHADOW_SCALE_SHIFT)
+#else
+#error "KASAN_SHADOW_SIZE is not defined for this sub-architecture"
+#endif /* CONFIG_X86_64 */
+
+#define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET)
+#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
+
+#ifdef CONFIG_KASAN
+void kasan_init(void);
+void kasan_map_memory(void *start, unsigned long len);
+extern int kasan_um_is_ready;
+
+#ifdef CONFIG_STATIC_LINK
+#define kasan_arch_is_ready() (kasan_um_is_ready)
+#endif
+#else
+static inline void kasan_init(void) { }
+#endif /* CONFIG_KASAN */
+
+#endif /* __ASM_UM_KASAN_H */
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index 2f2a8ce92f1e..2b7fc5b54164 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -109,7 +109,11 @@ SECTIONS
      be empty, which isn't pretty.  */
   . = ALIGN(32 / 8);
   .preinit_array     : { *(.preinit_array) }
-  .init_array     : { *(.init_array) }
+  .init_array     : {
+    *(.kasan_init)
+    *(.init_array.*)
+    *(.init_array)
+  }
   .fini_array     : { *(.fini_array) }
   .data           : {
     INIT_TASK_DATA(KERNEL_STACK_SIZE)
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 15295c3237a0..276a1f0b91f1 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -18,6 +18,25 @@
 #include <kern_util.h>
 #include <mem_user.h>
 #include <os.h>
+#include <linux/sched/task.h>
+
+#ifdef CONFIG_KASAN
+int kasan_um_is_ready;
+void kasan_init(void)
+{
+	/*
+	 * kasan_map_memory will map all of the required address space and
+	 * the host machine will allocate physical memory as necessary.
+	 */
+	kasan_map_memory((void *)KASAN_SHADOW_START, KASAN_SHADOW_SIZE);
+	init_task.kasan_depth = 0;
+	kasan_um_is_ready = true;
+}
+
+static void (*kasan_init_ptr)(void)
+__section(".kasan_init") __used
+= kasan_init;
+#endif
 
 /* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
 unsigned long *empty_zero_page = NULL;
diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c
index 86df52168bd9..fd3b61b3d4d2 100644
--- a/arch/um/kernel/stacktrace.c
+++ b/arch/um/kernel/stacktrace.c
@@ -27,7 +27,7 @@ void dump_trace(struct task_struct *tsk,
 
 	frame = (struct stack_frame *)bp;
 	while (((long) sp & (THREAD_SIZE-1)) != 0) {
-		addr = *sp;
+		addr = READ_ONCE_NOCHECK(*sp);
 		if (__kernel_text_address(addr)) {
 			reliable = 0;
 			if ((unsigned long) sp == bp + sizeof(long)) {
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 3c1b77474d2d..8530b2e08604 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -17,6 +17,28 @@
 #include <init.h>
 #include <os.h>
 
+/*
+ * kasan_map_memory - maps memory from @start with a size of @len.
+ * The allocated memory is filled with zeroes upon success.
+ * @start: the start address of the memory to be mapped
+ * @len: the length of the memory to be mapped
+ *
+ * This function is used to map shadow memory for KASAN in uml
+ */
+void kasan_map_memory(void *start, size_t len)
+{
+	if (mmap(start,
+		 len,
+		 PROT_READ|PROT_WRITE,
+		 MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE|MAP_NORESERVE,
+		 -1,
+		 0) == MAP_FAILED) {
+		os_info("Couldn't allocate shadow memory: %s\n.",
+			strerror(errno));
+		exit(1);
+	}
+}
+
 /* Set by make_tempfile() during early boot. */
 static char *tempdir = NULL;
 
diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c
index 715594fe5719..cb667c9225ab 100644
--- a/arch/um/os-Linux/user_syms.c
+++ b/arch/um/os-Linux/user_syms.c
@@ -27,10 +27,10 @@ EXPORT_SYMBOL(strstr);
 #ifndef __x86_64__
 extern void *memcpy(void *, const void *, size_t);
 EXPORT_SYMBOL(memcpy);
-#endif
-
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memset);
+#endif
+
 EXPORT_SYMBOL(printf);
 
 /* Here, instead, I can provide a fake prototype. Yes, someone cares: genksyms.