UBSAN: run-time undefined behavior sanity checker

UBSAN uses compile-time instrumentation to catch undefined behavior
(UB).  Compiler inserts code that perform certain kinds of checks before
operations that could cause UB.  If check fails (i.e.  UB detected)
__ubsan_handle_* function called to print error message.

So the most of the work is done by compiler.  This patch just implements
ubsan handlers printing errors.

GCC has this capability since 4.9.x [1] (see -fsanitize=undefined
option and its suboptions).
However GCC 5.x has more checkers implemented [2].
Article [3] has a bit more details about UBSAN in the GCC.

[1] - https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/Debugging-Options.html
[2] - https://gcc.gnu.org/onlinedocs/gcc/Debugging-Options.html
[3] - http://developerblog.redhat.com/2014/10/16/gcc-undefined-behavior-sanitizer-ubsan/

Issues which UBSAN has found thus far are:

Found bugs:

 * out-of-bounds access - 97840cb67ff5 ("netfilter: nfnetlink: fix
   insufficient validation in nfnetlink_bind")

undefined shifts:

 * d48458d4a768 ("jbd2: use a better hash function for the revoke
   table")

 * 10632008b9e1 ("clockevents: Prevent shift out of bounds")

 * 'x << -1' shift in ext4 -
   http://lkml.kernel.org/r/<5444EF21.8020501@samsung.com>

 * undefined rol32(0) -
   http://lkml.kernel.org/r/<1449198241-20654-1-git-send-email-sasha.levin@oracle.com>

 * undefined dirty_ratelimit calculation -
   http://lkml.kernel.org/r/<566594E2.3050306@odin.com>

 * undefined roundown_pow_of_two(0) -
   http://lkml.kernel.org/r/<1449156616-11474-1-git-send-email-sasha.levin@oracle.com>

 * [WONTFIX] undefined shift in __bpf_prog_run -
   http://lkml.kernel.org/r/<CACT4Y+ZxoR3UjLgcNdUm4fECLMx2VdtfrENMtRRCdgHB2n0bJA@mail.gmail.com>

   WONTFIX here because it should be fixed in bpf program, not in kernel.

signed overflows:

 * 32a8df4e0b33f ("sched: Fix odd values in effective_load()
   calculations")

 * mul overflow in ntp -
   http://lkml.kernel.org/r/<1449175608-1146-1-git-send-email-sasha.levin@oracle.com>

 * incorrect conversion into rtc_time in rtc_time64_to_tm() -
   http://lkml.kernel.org/r/<1449187944-11730-1-git-send-email-sasha.levin@oracle.com>

 * unvalidated timespec in io_getevents() -
   http://lkml.kernel.org/r/<CACT4Y+bBxVYLQ6LtOKrKtnLthqLHcw-BMp3aqP3mjdAvr9FULQ@mail.gmail.com>

 * [NOTABUG] signed overflow in ktime_add_safe() -
   http://lkml.kernel.org/r/<CACT4Y+aJ4muRnWxsUe1CMnA6P8nooO33kwG-c8YZg=0Xc8rJqw@mail.gmail.com>

[akpm@linux-foundation.org: fix unused local warning]
[akpm@linux-foundation.org: fix __int128 build woes]
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yury Gribov <y.gribov@samsung.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 574 insertions, 0 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f75a33f..157220b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1893,6 +1893,8 @@ source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
 
+source "lib/Kconfig.ubsan"
+
 config ARCH_HAS_DEVMEM_IS_ALLOWED
 	bool
 
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
new file mode 100644
index 0000000..49518fb
--- /dev/null
+++ b/lib/Kconfig.ubsan
@@ -0,0 +1,29 @@
+config ARCH_HAS_UBSAN_SANITIZE_ALL
+	bool
+
+config UBSAN
+	bool "Undefined behaviour sanity checker"
+	help
+	  This option enables undefined behaviour sanity checker
+	  Compile-time instrumentation is used to detect various undefined
+	  behaviours in runtime. Various types of checks may be enabled
+	  via boot parameter ubsan_handle (see: Documentation/ubsan.txt).
+
+config UBSAN_SANITIZE_ALL
+	bool "Enable instrumentation for the entire kernel"
+	depends on UBSAN
+	depends on ARCH_HAS_UBSAN_SANITIZE_ALL
+	default y
+	help
+	  This option activates instrumentation for the entire kernel.
+	  If you don't enable this option, you have to explicitly specify
+	  UBSAN_SANITIZE := y for the files/directories you want to check for UB.
+
+config UBSAN_ALIGNMENT
+	bool "Enable checking of pointers alignment"
+	depends on UBSAN
+	default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  This option enables detection of unaligned memory accesses.
+	  Enabling this option on architectures that support unalligned
+	  accesses may produce a lot of false positives.
diff --git a/lib/Makefile b/lib/Makefile
index b2a82e6..2d4bc33 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -209,3 +209,6 @@ quiet_cmd_build_OID_registry = GEN     $@
 clean-files	+= oid_registry_data.c
 
 obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
+obj-$(CONFIG_UBSAN) += ubsan.o
+
+UBSAN_SANITIZE_ubsan.o := n
diff --git a/lib/ubsan.c b/lib/ubsan.c
new file mode 100644
index 0000000..8799ae5
--- /dev/null
+++ b/lib/ubsan.c
@@ -0,0 +1,456 @@
+/*
+ * UBSAN error reporting functions
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+
+#include "ubsan.h"
+
+const char *type_check_kinds[] = {
+	"load of",
+	"store to",
+	"reference binding to",
+	"member access within",
+	"member call on",
+	"constructor call on",
+	"downcast of",
+	"downcast of"
+};
+
+#define REPORTED_BIT 31
+
+#if (BITS_PER_LONG == 64) && defined(__BIG_ENDIAN)
+#define COLUMN_MASK (~(1U << REPORTED_BIT))
+#define LINE_MASK   (~0U)
+#else
+#define COLUMN_MASK   (~0U)
+#define LINE_MASK (~(1U << REPORTED_BIT))
+#endif
+
+#define VALUE_LENGTH 40
+
+static bool was_reported(struct source_location *location)
+{
+	return test_and_set_bit(REPORTED_BIT, &location->reported);
+}
+
+static void print_source_location(const char *prefix,
+				struct source_location *loc)
+{
+	pr_err("%s %s:%d:%d\n", prefix, loc->file_name,
+		loc->line & LINE_MASK, loc->column & COLUMN_MASK);
+}
+
+static bool suppress_report(struct source_location *loc)
+{
+	return current->in_ubsan || was_reported(loc);
+}
+
+static bool type_is_int(struct type_descriptor *type)
+{
+	return type->type_kind == type_kind_int;
+}
+
+static bool type_is_signed(struct type_descriptor *type)
+{
+	WARN_ON(!type_is_int(type));
+	return  type->type_info & 1;
+}
+
+static unsigned type_bit_width(struct type_descriptor *type)
+{
+	return 1 << (type->type_info >> 1);
+}
+
+static bool is_inline_int(struct type_descriptor *type)
+{
+	unsigned inline_bits = sizeof(unsigned long)*8;
+	unsigned bits = type_bit_width(type);
+
+	WARN_ON(!type_is_int(type));
+
+	return bits <= inline_bits;
+}
+
+static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
+{
+	if (is_inline_int(type)) {
+		unsigned extra_bits = sizeof(s_max)*8 - type_bit_width(type);
+		return ((s_max)val) << extra_bits >> extra_bits;
+	}
+
+	if (type_bit_width(type) == 64)
+		return *(s64 *)val;
+
+	return *(s_max *)val;
+}
+
+static bool val_is_negative(struct type_descriptor *type, unsigned long val)
+{
+	return type_is_signed(type) && get_signed_val(type, val) < 0;
+}
+
+static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
+{
+	if (is_inline_int(type))
+		return val;
+
+	if (type_bit_width(type) == 64)
+		return *(u64 *)val;
+
+	return *(u_max *)val;
+}
+
+static void val_to_string(char *str, size_t size, struct type_descriptor *type,
+	unsigned long value)
+{
+	if (type_is_int(type)) {
+		if (type_bit_width(type) == 128) {
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+			u_max val = get_unsigned_val(type, value);
+
+			scnprintf(str, size, "0x%08x%08x%08x%08x",
+				(u32)(val >> 96),
+				(u32)(val >> 64),
+				(u32)(val >> 32),
+				(u32)(val));
+#else
+			WARN_ON(1);
+#endif
+		} else if (type_is_signed(type)) {
+			scnprintf(str, size, "%lld",
+				(s64)get_signed_val(type, value));
+		} else {
+			scnprintf(str, size, "%llu",
+				(u64)get_unsigned_val(type, value));
+		}
+	}
+}
+
+static bool location_is_valid(struct source_location *loc)
+{
+	return loc->file_name != NULL;
+}
+
+static DEFINE_SPINLOCK(report_lock);
+
+static void ubsan_prologue(struct source_location *location,
+			unsigned long *flags)
+{
+	current->in_ubsan++;
+	spin_lock_irqsave(&report_lock, *flags);
+
+	pr_err("========================================"
+		"========================================\n");
+	print_source_location("UBSAN: Undefined behaviour in", location);
+}
+
+static void ubsan_epilogue(unsigned long *flags)
+{
+	dump_stack();
+	pr_err("========================================"
+		"========================================\n");
+	spin_unlock_irqrestore(&report_lock, *flags);
+	current->in_ubsan--;
+}
+
+static void handle_overflow(struct overflow_data *data, unsigned long lhs,
+			unsigned long rhs, char op)
+{
+
+	struct type_descriptor *type = data->type;
+	unsigned long flags;
+	char lhs_val_str[VALUE_LENGTH];
+	char rhs_val_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs);
+	val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs);
+	pr_err("%s integer overflow:\n",
+		type_is_signed(type) ? "signed" : "unsigned");
+	pr_err("%s %c %s cannot be represented in type %s\n",
+		lhs_val_str,
+		op,
+		rhs_val_str,
+		type->type_name);
+
+	ubsan_epilogue(&flags);
+}
+
+void __ubsan_handle_add_overflow(struct overflow_data *data,
+				unsigned long lhs,
+				unsigned long rhs)
+{
+
+	handle_overflow(data, lhs, rhs, '+');
+}
+EXPORT_SYMBOL(__ubsan_handle_add_overflow);
+
+void __ubsan_handle_sub_overflow(struct overflow_data *data,
+				unsigned long lhs,
+				unsigned long rhs)
+{
+	handle_overflow(data, lhs, rhs, '-');
+}
+EXPORT_SYMBOL(__ubsan_handle_sub_overflow);
+
+void __ubsan_handle_mul_overflow(struct overflow_data *data,
+				unsigned long lhs,
+				unsigned long rhs)
+{
+	handle_overflow(data, lhs, rhs, '*');
+}
+EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
+
+void __ubsan_handle_negate_overflow(struct overflow_data *data,
+				unsigned long old_val)
+{
+	unsigned long flags;
+	char old_val_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val);
+
+	pr_err("negation of %s cannot be represented in type %s:\n",
+		old_val_str, data->type->type_name);
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
+
+
+void __ubsan_handle_divrem_overflow(struct overflow_data *data,
+				unsigned long lhs,
+				unsigned long rhs)
+{
+	unsigned long flags;
+	char rhs_val_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs);
+
+	if (type_is_signed(data->type) && get_signed_val(data->type, rhs) == -1)
+		pr_err("division of %s by -1 cannot be represented in type %s\n",
+			rhs_val_str, data->type->type_name);
+	else
+		pr_err("division by zero\n");
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_divrem_overflow);
+
+static void handle_null_ptr_deref(struct type_mismatch_data *data)
+{
+	unsigned long flags;
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	pr_err("%s null pointer of type %s\n",
+		type_check_kinds[data->type_check_kind],
+		data->type->type_name);
+
+	ubsan_epilogue(&flags);
+}
+
+static void handle_missaligned_access(struct type_mismatch_data *data,
+				unsigned long ptr)
+{
+	unsigned long flags;
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	pr_err("%s misaligned address %p for type %s\n",
+		type_check_kinds[data->type_check_kind],
+		(void *)ptr, data->type->type_name);
+	pr_err("which requires %ld byte alignment\n", data->alignment);
+
+	ubsan_epilogue(&flags);
+}
+
+static void handle_object_size_mismatch(struct type_mismatch_data *data,
+					unsigned long ptr)
+{
+	unsigned long flags;
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+	pr_err("%s address %pk with insufficient space\n",
+		type_check_kinds[data->type_check_kind],
+		(void *) ptr);
+	pr_err("for an object of type %s\n", data->type->type_name);
+	ubsan_epilogue(&flags);
+}
+
+void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
+				unsigned long ptr)
+{
+
+	if (!ptr)
+		handle_null_ptr_deref(data);
+	else if (data->alignment && !IS_ALIGNED(ptr, data->alignment))
+		handle_missaligned_access(data, ptr);
+	else
+		handle_object_size_mismatch(data, ptr);
+}
+EXPORT_SYMBOL(__ubsan_handle_type_mismatch);
+
+void __ubsan_handle_nonnull_return(struct nonnull_return_data *data)
+{
+	unsigned long flags;
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	pr_err("null pointer returned from function declared to never return null\n");
+
+	if (location_is_valid(&data->attr_location))
+		print_source_location("returns_nonnull attribute specified in",
+				&data->attr_location);
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_nonnull_return);
+
+void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data,
+					unsigned long bound)
+{
+	unsigned long flags;
+	char bound_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(bound_str, sizeof(bound_str), data->type, bound);
+	pr_err("variable length array bound value %s <= 0\n", bound_str);
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive);
+
+void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
+				unsigned long index)
+{
+	unsigned long flags;
+	char index_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(index_str, sizeof(index_str), data->index_type, index);
+	pr_err("index %s is out of range for type %s\n", index_str,
+		data->array_type->type_name);
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
+
+void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
+					unsigned long lhs, unsigned long rhs)
+{
+	unsigned long flags;
+	struct type_descriptor *rhs_type = data->rhs_type;
+	struct type_descriptor *lhs_type = data->lhs_type;
+	char rhs_str[VALUE_LENGTH];
+	char lhs_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs);
+	val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs);
+
+	if (val_is_negative(rhs_type, rhs))
+		pr_err("shift exponent %s is negative\n", rhs_str);
+
+	else if (get_unsigned_val(rhs_type, rhs) >=
+		type_bit_width(lhs_type))
+		pr_err("shift exponent %s is too large for %u-bit type %s\n",
+			rhs_str,
+			type_bit_width(lhs_type),
+			lhs_type->type_name);
+	else if (val_is_negative(lhs_type, lhs))
+		pr_err("left shift of negative value %s\n",
+			lhs_str);
+	else
+		pr_err("left shift of %s by %s places cannot be"
+			" represented in type %s\n",
+			lhs_str, rhs_str,
+			lhs_type->type_name);
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds);
+
+
+void __noreturn
+__ubsan_handle_builtin_unreachable(struct unreachable_data *data)
+{
+	unsigned long flags;
+
+	ubsan_prologue(&data->location, &flags);
+	pr_err("calling __builtin_unreachable()\n");
+	ubsan_epilogue(&flags);
+	panic("can't return from __builtin_unreachable()");
+}
+EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
+
+void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
+				unsigned long val)
+{
+	unsigned long flags;
+	char val_str[VALUE_LENGTH];
+
+	if (suppress_report(&data->location))
+		return;
+
+	ubsan_prologue(&data->location, &flags);
+
+	val_to_string(val_str, sizeof(val_str), data->type, val);
+
+	pr_err("load of value %s is not a valid value for type %s\n",
+		val_str, data->type->type_name);
+
+	ubsan_epilogue(&flags);
+}
+EXPORT_SYMBOL(__ubsan_handle_load_invalid_value);
diff --git a/lib/ubsan.h b/lib/ubsan.h
new file mode 100644
index 0000000..b2d18d4
--- /dev/null
+++ b/lib/ubsan.h
@@ -0,0 +1,84 @@
+#ifndef _LIB_UBSAN_H
+#define _LIB_UBSAN_H
+
+enum {
+	type_kind_int = 0,
+	type_kind_float = 1,
+	type_unknown = 0xffff
+};
+
+struct type_descriptor {
+	u16 type_kind;
+	u16 type_info;
+	char type_name[1];
+};
+
+struct source_location {
+	const char *file_name;
+	union {
+		unsigned long reported;
+		struct {
+			u32 line;
+			u32 column;
+		};
+	};
+};
+
+struct overflow_data {
+	struct source_location location;
+	struct type_descriptor *type;
+};
+
+struct type_mismatch_data {
+	struct source_location location;
+	struct type_descriptor *type;
+	unsigned long alignment;
+	unsigned char type_check_kind;
+};
+
+struct nonnull_arg_data {
+	struct source_location location;
+	struct source_location attr_location;
+	int arg_index;
+};
+
+struct nonnull_return_data {
+	struct source_location location;
+	struct source_location attr_location;
+};
+
+struct vla_bound_data {
+	struct source_location location;
+	struct type_descriptor *type;
+};
+
+struct out_of_bounds_data {
+	struct source_location location;
+	struct type_descriptor *array_type;
+	struct type_descriptor *index_type;
+};
+
+struct shift_out_of_bounds_data {
+	struct source_location location;
+	struct type_descriptor *lhs_type;
+	struct type_descriptor *rhs_type;
+};
+
+struct unreachable_data {
+	struct source_location location;
+};
+
+struct invalid_value_data {
+	struct source_location location;
+	struct type_descriptor *type;
+};
+
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+typedef __int128 s_max;
+typedef unsigned __int128 u_max;
+#else
+typedef s64 s_max;
+typedef u64 u_max;
+#endif
+
+#endif