kcsan: Add Kernel Concurrency Sanitizer infrastructure

Kernel Concurrency Sanitizer (KCSAN) is a dynamic data-race detector for
kernel space. KCSAN is a sampling watchpoint-based data-race detector.
See the included Documentation/dev-tools/kcsan.rst for more details.

This patch adds basic infrastructure, but does not yet enable KCSAN for
any architecture.

Signed-off-by: Marco Elver <elver@google.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

MAINTAINERS

@@ -8848,6 +8848,17 @@ F:	Documentation/kbuild/kconfig*
 F:	scripts/kconfig/
 F:	scripts/Kconfig.include
 
+KCSAN
+M:	Marco Elver <elver@google.com>
+R:	Dmitry Vyukov <dvyukov@google.com>
+L:	kasan-dev@googlegroups.com
+S:	Maintained
+F:	Documentation/dev-tools/kcsan.rst
+F:	include/linux/kcsan*.h
+F:	kernel/kcsan/
+F:	lib/Kconfig.kcsan
+F:	scripts/Makefile.kcsan
+
 KDUMP
 M:	Dave Young <dyoung@redhat.com>
 M:	Baoquan He <bhe@redhat.com>

Makefile

@@ -478,7 +478,7 @@ export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
 export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE
-export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN
+export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN CFLAGS_KCSAN
 export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE
 export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
 export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
@@ -900,6 +900,7 @@ endif
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 include scripts/Makefile.ubsan
+include scripts/Makefile.kcsan
 
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 KBUILD_CPPFLAGS += $(KCPPFLAGS)

include/linux/compiler-clang.h

@@ -24,6 +24,15 @@
 #define __no_sanitize_address
 #endif
 
+#if __has_feature(thread_sanitizer)
+/* emulate gcc's __SANITIZE_THREAD__ flag */
+#define __SANITIZE_THREAD__
+#define __no_sanitize_thread \
+		__attribute__((no_sanitize("thread")))
+#else
+#define __no_sanitize_thread
+#endif
+
 /*
  * Not all versions of clang implement the the type-generic versions
  * of the builtin overflow checkers. Fortunately, clang implements

include/linux/compiler-gcc.h

@@ -145,6 +145,13 @@
 #define __no_sanitize_address
 #endif
 
+#if defined(__SANITIZE_THREAD__) && __has_attribute(__no_sanitize_thread__)
+#define __no_sanitize_thread                                                   \
+	__attribute__((__noinline__)) __attribute__((no_sanitize_thread))
+#else
+#define __no_sanitize_thread
+#endif
+
 #if GCC_VERSION >= 50100
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif

include/linux/compiler.h

@@ -178,6 +178,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #endif
 
 #include <uapi/linux/types.h>
+#include <linux/kcsan-checks.h>
 
 #define __READ_ONCE_SIZE						\
 ({									\
@@ -193,12 +194,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	}								\
 })
 
-static __always_inline
-void __read_once_size(const volatile void *p, void *res, int size)
-{
-	__READ_ONCE_SIZE;
-}
-
 #ifdef CONFIG_KASAN
 /*
  * We can't declare function 'inline' because __no_sanitize_address confilcts
@@ -207,18 +202,44 @@ void __read_once_size(const volatile void *p, void *res, int size)
  * '__maybe_unused' allows us to avoid defined-but-not-used warnings.
  */
 # define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused
+# define __no_sanitize_or_inline __no_kasan_or_inline
 #else
 # define __no_kasan_or_inline __always_inline
 #endif
 
-static __no_kasan_or_inline
+#ifdef __SANITIZE_THREAD__
+/*
+ * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in
+ * compilation units where instrumentation is disabled.
+ */
+# define __no_kcsan_or_inline __no_sanitize_thread notrace __maybe_unused
+# define __no_sanitize_or_inline __no_kcsan_or_inline
+#else
+# define __no_kcsan_or_inline __always_inline
+#endif
+
+#ifndef __no_sanitize_or_inline
+#define __no_sanitize_or_inline __always_inline
+#endif
+
+static __no_kcsan_or_inline
+void __read_once_size(const volatile void *p, void *res, int size)
+{
+	kcsan_check_atomic_read(p, size);
+	__READ_ONCE_SIZE;
+}
+
+static __no_sanitize_or_inline
 void __read_once_size_nocheck(const volatile void *p, void *res, int size)
 {
 	__READ_ONCE_SIZE;
 }
 
-static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+static __no_kcsan_or_inline
+void __write_once_size(volatile void *p, void *res, int size)
 {
+	kcsan_check_atomic_write(p, size);
+
 	switch (size) {
 	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
 	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;

include/linux/kcsan-checks.h

@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_KCSAN_CHECKS_H
+#define _LINUX_KCSAN_CHECKS_H
+
+#include <linux/types.h>
+
+/*
+ * Access type modifiers.
+ */
+#define KCSAN_ACCESS_WRITE 0x1
+#define KCSAN_ACCESS_ATOMIC 0x2
+
+/*
+ * __kcsan_*: Always calls into runtime when KCSAN is enabled. This may be used
+ * even in compilation units that selectively disable KCSAN, but must use KCSAN
+ * to validate access to an address.   Never use these in header files!
+ */
+#ifdef CONFIG_KCSAN
+/**
+ * __kcsan_check_access - check generic access for data race
+ *
+ * @ptr address of access
+ * @size size of access
+ * @type access type modifier
+ */
+void __kcsan_check_access(const volatile void *ptr, size_t size, int type);
+
+#else
+static inline void __kcsan_check_access(const volatile void *ptr, size_t size,
+					int type) { }
+#endif
+
+/*
+ * kcsan_*: Only calls into runtime when the particular compilation unit has
+ * KCSAN instrumentation enabled. May be used in header files.
+ */
+#ifdef __SANITIZE_THREAD__
+#define kcsan_check_access __kcsan_check_access
+#else
+static inline void kcsan_check_access(const volatile void *ptr, size_t size,
+				      int type) { }
+#endif
+
+/**
+ * __kcsan_check_read - check regular read access for data races
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+#define __kcsan_check_read(ptr, size) __kcsan_check_access(ptr, size, 0)
+
+/**
+ * __kcsan_check_write - check regular write access for data races
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+#define __kcsan_check_write(ptr, size)                                         \
+	__kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
+
+/**
+ * kcsan_check_read - check regular read access for data races
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+#define kcsan_check_read(ptr, size) kcsan_check_access(ptr, size, 0)
+
+/**
+ * kcsan_check_write - check regular write access for data races
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+#define kcsan_check_write(ptr, size)                                           \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
+
+/*
+ * Check for atomic accesses: if atomic access are not ignored, this simply
+ * aliases to kcsan_check_access, otherwise becomes a no-op.
+ */
+#ifdef CONFIG_KCSAN_IGNORE_ATOMICS
+#define kcsan_check_atomic_read(...)                                           \
+	do {                                                                   \
+	} while (0)
+#define kcsan_check_atomic_write(...)                                          \
+	do {                                                                   \
+	} while (0)
+#else
+#define kcsan_check_atomic_read(ptr, size)                                     \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC)
+#define kcsan_check_atomic_write(ptr, size)                                    \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE)
+#endif
+
+#endif /* _LINUX_KCSAN_CHECKS_H */

include/linux/kcsan.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_KCSAN_H
+#define _LINUX_KCSAN_H
+
+#include <linux/kcsan-checks.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KCSAN
+
+/*
+ * Context for each thread of execution: for tasks, this is stored in
+ * task_struct, and interrupts access internal per-CPU storage.
+ */
+struct kcsan_ctx {
+	int disable_count; /* disable counter */
+	int atomic_next; /* number of following atomic ops */
+
+	/*
+	 * We distinguish between: (a) nestable atomic regions that may contain
+	 * other nestable regions; and (b) flat atomic regions that do not keep
+	 * track of nesting. Both (a) and (b) are entirely independent of each
+	 * other, and a flat region may be started in a nestable region or
+	 * vice-versa.
+	 *
+	 * This is required because, for example, in the annotations for
+	 * seqlocks, we declare seqlock writer critical sections as (a) nestable
+	 * atomic regions, but reader critical sections as (b) flat atomic
+	 * regions, but have encountered cases where seqlock reader critical
+	 * sections are contained within writer critical sections (the opposite
+	 * may be possible, too).
+	 *
+	 * To support these cases, we independently track the depth of nesting
+	 * for (a), and whether the leaf level is flat for (b).
+	 */
+	int atomic_nest_count;
+	bool in_flat_atomic;
+};
+
+/**
+ * kcsan_init - initialize KCSAN runtime
+ */
+void kcsan_init(void);
+
+/**
+ * kcsan_disable_current - disable KCSAN for the current context
+ *
+ * Supports nesting.
+ */
+void kcsan_disable_current(void);
+
+/**
+ * kcsan_enable_current - re-enable KCSAN for the current context
+ *
+ * Supports nesting.
+ */
+void kcsan_enable_current(void);
+
+/**
+ * kcsan_nestable_atomic_begin - begin nestable atomic region
+ *
+ * Accesses within the atomic region may appear to race with other accesses but
+ * should be considered atomic.
+ */
+void kcsan_nestable_atomic_begin(void);
+
+/**
+ * kcsan_nestable_atomic_end - end nestable atomic region
+ */
+void kcsan_nestable_atomic_end(void);
+
+/**
+ * kcsan_flat_atomic_begin - begin flat atomic region
+ *
+ * Accesses within the atomic region may appear to race with other accesses but
+ * should be considered atomic.
+ */
+void kcsan_flat_atomic_begin(void);
+
+/**
+ * kcsan_flat_atomic_end - end flat atomic region
+ */
+void kcsan_flat_atomic_end(void);
+
+/**
+ * kcsan_atomic_next - consider following accesses as atomic
+ *
+ * Force treating the next n memory accesses for the current context as atomic
+ * operations.
+ *
+ * @n number of following memory accesses to treat as atomic.
+ */
+void kcsan_atomic_next(int n);
+
+#else /* CONFIG_KCSAN */
+
+static inline void kcsan_init(void) { }
+
+static inline void kcsan_disable_current(void) { }
+
+static inline void kcsan_enable_current(void) { }
+
+static inline void kcsan_nestable_atomic_begin(void) { }
+
+static inline void kcsan_nestable_atomic_end(void) { }
+
+static inline void kcsan_flat_atomic_begin(void) { }
+
+static inline void kcsan_flat_atomic_end(void) { }
+
+static inline void kcsan_atomic_next(int n) { }
+
+#endif /* CONFIG_KCSAN */
+
+#endif /* _LINUX_KCSAN_H */

include/linux/sched.h

@@ -31,6 +31,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
 #include <linux/rseq.h>
+#include <linux/kcsan.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -1172,6 +1173,9 @@ struct task_struct {
 #ifdef CONFIG_KASAN
 	unsigned int			kasan_depth;
 #endif
+#ifdef CONFIG_KCSAN
+	struct kcsan_ctx		kcsan_ctx;
+#endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack: */

init/init_task.c

@@ -161,6 +161,14 @@ struct task_struct init_task
 #ifdef CONFIG_KASAN
 	.kasan_depth	= 1,
 #endif
+#ifdef CONFIG_KCSAN
+	.kcsan_ctx = {
+		.disable_count		= 0,
+		.atomic_next		= 0,
+		.atomic_nest_count	= 0,
+		.in_flat_atomic		= false,
+	},
+#endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	.softirqs_enabled = 1,
 #endif

init/main.c

@@ -93,6 +93,7 @@
 #include <linux/rodata_test.h>
 #include <linux/jump_label.h>
 #include <linux/mem_encrypt.h>
+#include <linux/kcsan.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -779,6 +780,7 @@ asmlinkage __visible void __init start_kernel(void)
 	acpi_subsystem_init();
 	arch_post_acpi_subsys_init();
 	sfi_init_late();
+	kcsan_init();
 
 	/* Do the rest non-__init'ed, we're now alive */
 	arch_call_rest_init();

kernel/Makefile

@@ -102,6 +102,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
+obj-$(CONFIG_KCSAN) += kcsan/
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 

kernel/kcsan/Makefile

@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+KCSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
+
+CFLAGS_core.o := $(call cc-option,-fno-conserve-stack,) \
+	$(call cc-option,-fno-stack-protector,)
+
+obj-y := core.o debugfs.o report.o
+obj-$(CONFIG_KCSAN_SELFTEST) += test.o

kernel/kcsan/atomic.h

@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ATOMIC_H
+#define _KERNEL_KCSAN_ATOMIC_H
+
+#include <linux/jiffies.h>
+
+/*
+ * Helper that returns true if access to ptr should be considered as an atomic
+ * access, even though it is not explicitly atomic.
+ *
+ * List all volatile globals that have been observed in races, to suppress
+ * data race reports between accesses to these variables.
+ *
+ * For now, we assume that volatile accesses of globals are as strong as atomic
+ * accesses (READ_ONCE, WRITE_ONCE cast to volatile). The situation is still not
+ * entirely clear, as on some architectures (Alpha) READ_ONCE/WRITE_ONCE do more
+ * than cast to volatile. Eventually, we hope to be able to remove this
+ * function.
+ */
+static inline bool kcsan_is_atomic(const volatile void *ptr)
+{
+	/* only jiffies for now */
+	return ptr == &jiffies;
+}
+
+#endif /* _KERNEL_KCSAN_ATOMIC_H */

kernel/kcsan/debugfs.c

@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/atomic.h>
+#include <linux/bsearch.h>
+#include <linux/bug.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+#include "kcsan.h"
+
+/*
+ * Statistics counters.
+ */
+static atomic_long_t counters[KCSAN_COUNTER_COUNT];
+
+/*
+ * Addresses for filtering functions from reporting. This list can be used as a
+ * whitelist or blacklist.
+ */
+static struct {
+	unsigned long *addrs; /* array of addresses */
+	size_t size; /* current size */
+	int used; /* number of elements used */
+	bool sorted; /* if elements are sorted */
+	bool whitelist; /* if list is a blacklist or whitelist */
+} report_filterlist = {
+	.addrs = NULL,
+	.size = 8, /* small initial size */
+	.used = 0,
+	.sorted = false,
+	.whitelist = false, /* default is blacklist */
+};
+static DEFINE_SPINLOCK(report_filterlist_lock);
+
+static const char *counter_to_name(enum kcsan_counter_id id)
+{
+	switch (id) {
+	case KCSAN_COUNTER_USED_WATCHPOINTS:
+		return "used_watchpoints";
+	case KCSAN_COUNTER_SETUP_WATCHPOINTS:
+		return "setup_watchpoints";
+	case KCSAN_COUNTER_DATA_RACES:
+		return "data_races";
+	case KCSAN_COUNTER_NO_CAPACITY:
+		return "no_capacity";
+	case KCSAN_COUNTER_REPORT_RACES:
+		return "report_races";
+	case KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN:
+		return "races_unknown_origin";
+	case KCSAN_COUNTER_UNENCODABLE_ACCESSES:
+		return "unencodable_accesses";
+	case KCSAN_COUNTER_ENCODING_FALSE_POSITIVES:
+		return "encoding_false_positives";
+	case KCSAN_COUNTER_COUNT:
+		BUG();
+	}
+	return NULL;
+}
+
+void kcsan_counter_inc(enum kcsan_counter_id id)
+{
+	atomic_long_inc(&counters[id]);
+}
+
+void kcsan_counter_dec(enum kcsan_counter_id id)
+{
+	atomic_long_dec(&counters[id]);
+}
+
+/*
+ * The microbenchmark allows benchmarking KCSAN core runtime only. To run
+ * multiple threads, pipe 'microbench=<iters>' from multiple tasks into the
+ * debugfs file.
+ */
+static void microbenchmark(unsigned long iters)
+{
+	cycles_t cycles;
+
+	pr_info("KCSAN: %s begin | iters: %lu\n", __func__, iters);
+
+	cycles = get_cycles();
+	while (iters--) {
+		/*
+		 * We can run this benchmark from multiple tasks; this address
+		 * calculation increases likelyhood of some accesses overlapping
+		 * (they still won't conflict because all are reads).
+		 */
+		unsigned long addr =
+			iters % (CONFIG_KCSAN_NUM_WATCHPOINTS * PAGE_SIZE);
+		__kcsan_check_read((void *)addr, sizeof(long));
+	}
+	cycles = get_cycles() - cycles;
+
+	pr_info("KCSAN: %s end   | cycles: %llu\n", __func__, cycles);
+}
+
+static int cmp_filterlist_addrs(const void *rhs, const void *lhs)
+{
+	const unsigned long a = *(const unsigned long *)rhs;
+	const unsigned long b = *(const unsigned long *)lhs;
+
+	return a < b ? -1 : a == b ? 0 : 1;
+}
+
+bool kcsan_skip_report_debugfs(unsigned long func_addr)
+{
+	unsigned long symbolsize, offset;
+	unsigned long flags;
+	bool ret = false;
+
+	if (!kallsyms_lookup_size_offset(func_addr, &symbolsize, &offset))
+		return false;
+	func_addr -= offset; /* get function start */
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	if (report_filterlist.used == 0)
+		goto out;
+
+	/* Sort array if it is unsorted, and then do a binary search. */
+	if (!report_filterlist.sorted) {
+		sort(report_filterlist.addrs, report_filterlist.used,
+		     sizeof(unsigned long), cmp_filterlist_addrs, NULL);
+		report_filterlist.sorted = true;
+	}
+	ret = !!bsearch(&func_addr, report_filterlist.addrs,
+			report_filterlist.used, sizeof(unsigned long),
+			cmp_filterlist_addrs);
+	if (report_filterlist.whitelist)
+		ret = !ret;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+	return ret;
+}
+
+static void set_report_filterlist_whitelist(bool whitelist)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	report_filterlist.whitelist = whitelist;
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+}
+
+/* Returns 0 on success, error-code otherwise. */
+static ssize_t insert_report_filterlist(const char *func)
+{
+	unsigned long flags;
+	unsigned long addr = kallsyms_lookup_name(func);
+	ssize_t ret = 0;
+
+	if (!addr) {
+		pr_err("KCSAN: could not find function: '%s'\n", func);
+		return -ENOENT;
+	}
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+
+	if (report_filterlist.addrs == NULL) {
+		/* initial allocation */
+		report_filterlist.addrs =
+			kmalloc_array(report_filterlist.size,
+				      sizeof(unsigned long), GFP_KERNEL);
+		if (report_filterlist.addrs == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	} else if (report_filterlist.used == report_filterlist.size) {
+		/* resize filterlist */
+		size_t new_size = report_filterlist.size * 2;
+		unsigned long *new_addrs =
+			krealloc(report_filterlist.addrs,
+				 new_size * sizeof(unsigned long), GFP_KERNEL);
+
+		if (new_addrs == NULL) {
+			/* leave filterlist itself untouched */
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		report_filterlist.size = new_size;
+		report_filterlist.addrs = new_addrs;
+	}
+
+	/* Note: deduplicating should be done in userspace. */
+	report_filterlist.addrs[report_filterlist.used++] =
+		kallsyms_lookup_name(func);
+	report_filterlist.sorted = false;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+	return ret;
+}
+
+static int show_info(struct seq_file *file, void *v)
+{
+	int i;
+	unsigned long flags;
+
+	/* show stats */
+	seq_printf(file, "enabled: %i\n", READ_ONCE(kcsan_enabled));
+	for (i = 0; i < KCSAN_COUNTER_COUNT; ++i)
+		seq_printf(file, "%s: %ld\n", counter_to_name(i),
+			   atomic_long_read(&counters[i]));
+
+	/* show filter functions, and filter type */
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	seq_printf(file, "\n%s functions: %s\n",
+		   report_filterlist.whitelist ? "whitelisted" : "blacklisted",
+		   report_filterlist.used == 0 ? "none" : "");
+	for (i = 0; i < report_filterlist.used; ++i)
+		seq_printf(file, " %ps\n", (void *)report_filterlist.addrs[i]);
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	return 0;
+}
+
+static int debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_info, NULL);
+}
+
+static ssize_t debugfs_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *off)
+{
+	char kbuf[KSYM_NAME_LEN];
+	char *arg;
+	int read_len = count < (sizeof(kbuf) - 1) ? count : (sizeof(kbuf) - 1);
+
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EFAULT;
+	kbuf[read_len] = '\0';
+	arg = strstrip(kbuf);
+
+	if (!strcmp(arg, "on")) {
+		WRITE_ONCE(kcsan_enabled, true);
+	} else if (!strcmp(arg, "off")) {
+		WRITE_ONCE(kcsan_enabled, false);
+	} else if (!strncmp(arg, "microbench=", sizeof("microbench=") - 1)) {
+		unsigned long iters;
+
+		if (kstrtoul(&arg[sizeof("microbench=") - 1], 0, &iters))
+			return -EINVAL;
+		microbenchmark(iters);
+	} else if (!strcmp(arg, "whitelist")) {
+		set_report_filterlist_whitelist(true);
+	} else if (!strcmp(arg, "blacklist")) {
+		set_report_filterlist_whitelist(false);
+	} else if (arg[0] == '!') {
+		ssize_t ret = insert_report_filterlist(&arg[1]);
+
+		if (ret < 0)
+			return ret;
+	} else {
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static const struct file_operations debugfs_ops = { .read = seq_read,
+						    .open = debugfs_open,
+						    .write = debugfs_write,
+						    .release = single_release };
+
+void __init kcsan_debugfs_init(void)
+{
+	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
+}

kernel/kcsan/encoding.h

@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ENCODING_H
+#define _KERNEL_KCSAN_ENCODING_H
+
+#include <linux/bits.h>
+#include <linux/log2.h>
+#include <linux/mm.h>
+
+#include "kcsan.h"
+
+#define SLOT_RANGE PAGE_SIZE
+#define INVALID_WATCHPOINT 0
+#define CONSUMED_WATCHPOINT 1
+
+/*
+ * The maximum useful size of accesses for which we set up watchpoints is the
+ * max range of slots we check on an access.
+ */
+#define MAX_ENCODABLE_SIZE (SLOT_RANGE * (1 + KCSAN_CHECK_ADJACENT))
+
+/*
+ * Number of bits we use to store size info.
+ */
+#define WATCHPOINT_SIZE_BITS bits_per(MAX_ENCODABLE_SIZE)
+/*
+ * This encoding for addresses discards the upper (1 for is-write + SIZE_BITS);
+ * however, most 64-bit architectures do not use the full 64-bit address space.
+ * Also, in order for a false positive to be observable 2 things need to happen:
+ *
+ *	1. different addresses but with the same encoded address race;
+ *	2. and both map onto the same watchpoint slots;
+ *
+ * Both these are assumed to be very unlikely. However, in case it still happens
+ * happens, the report logic will filter out the false positive (see report.c).
+ */
+#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG - 1 - WATCHPOINT_SIZE_BITS)
+
+/*
+ * Masks to set/retrieve the encoded data.
+ */
+#define WATCHPOINT_WRITE_MASK BIT(BITS_PER_LONG - 1)
+#define WATCHPOINT_SIZE_MASK                                                   \
+	GENMASK(BITS_PER_LONG - 2, BITS_PER_LONG - 2 - WATCHPOINT_SIZE_BITS)
+#define WATCHPOINT_ADDR_MASK                                                   \
+	GENMASK(BITS_PER_LONG - 3 - WATCHPOINT_SIZE_BITS, 0)
+
+static inline bool check_encodable(unsigned long addr, size_t size)
+{
+	return size <= MAX_ENCODABLE_SIZE;
+}
+
+static inline long encode_watchpoint(unsigned long addr, size_t size,
+				     bool is_write)
+{
+	return (long)((is_write ? WATCHPOINT_WRITE_MASK : 0) |
+		      (size << WATCHPOINT_ADDR_BITS) |
+		      (addr & WATCHPOINT_ADDR_MASK));
+}
+
+static inline bool decode_watchpoint(long watchpoint,
+				     unsigned long *addr_masked, size_t *size,
+				     bool *is_write)
+{
+	if (watchpoint == INVALID_WATCHPOINT ||
+	    watchpoint == CONSUMED_WATCHPOINT)
+		return false;
+
+	*addr_masked = (unsigned long)watchpoint & WATCHPOINT_ADDR_MASK;
+	*size = ((unsigned long)watchpoint & WATCHPOINT_SIZE_MASK) >>
+		WATCHPOINT_ADDR_BITS;
+	*is_write = !!((unsigned long)watchpoint & WATCHPOINT_WRITE_MASK);
+
+	return true;
+}
+
+/*
+ * Return watchpoint slot for an address.
+ */
+static inline int watchpoint_slot(unsigned long addr)
+{
+	return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS;
+}
+
+static inline bool matching_access(unsigned long addr1, size_t size1,
+				   unsigned long addr2, size_t size2)
+{
+	unsigned long end_range1 = addr1 + size1 - 1;
+	unsigned long end_range2 = addr2 + size2 - 1;
+
+	return addr1 <= end_range2 && addr2 <= end_range1;
+}
+
+#endif /* _KERNEL_KCSAN_ENCODING_H */

kernel/kcsan/kcsan.h

@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
+ * see Documentation/dev-tools/kcsan.rst.
+ */
+
+#ifndef _KERNEL_KCSAN_KCSAN_H
+#define _KERNEL_KCSAN_KCSAN_H
+
+#include <linux/kcsan.h>
+
+/* The number of adjacent watchpoints to check. */
+#define KCSAN_CHECK_ADJACENT 1
+
+/*
+ * Globally enable and disable KCSAN.
+ */
+extern bool kcsan_enabled;
+
+/*
+ * Initialize debugfs file.
+ */
+void kcsan_debugfs_init(void);
+
+enum kcsan_counter_id {
+	/*
+	 * Number of watchpoints currently in use.
+	 */
+	KCSAN_COUNTER_USED_WATCHPOINTS,
+
+	/*
+	 * Total number of watchpoints set up.
+	 */
+	KCSAN_COUNTER_SETUP_WATCHPOINTS,
+
+	/*
+	 * Total number of data races.
+	 */
+	KCSAN_COUNTER_DATA_RACES,
+
+	/*
+	 * Number of times no watchpoints were available.
+	 */
+	KCSAN_COUNTER_NO_CAPACITY,
+
+	/*
+	 * A thread checking a watchpoint raced with another checking thread;
+	 * only one will be reported.
+	 */
+	KCSAN_COUNTER_REPORT_RACES,
+
+	/*
+	 * Observed data value change, but writer thread unknown.
+	 */
+	KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN,
+
+	/*
+	 * The access cannot be encoded to a valid watchpoint.
+	 */
+	KCSAN_COUNTER_UNENCODABLE_ACCESSES,
+
+	/*
+	 * Watchpoint encoding caused a watchpoint to fire on mismatching
+	 * accesses.
+	 */
+	KCSAN_COUNTER_ENCODING_FALSE_POSITIVES,
+
+	KCSAN_COUNTER_COUNT, /* number of counters */
+};
+
+/*
+ * Increment/decrement counter with given id; avoid calling these in fast-path.
+ */
+void kcsan_counter_inc(enum kcsan_counter_id id);
+void kcsan_counter_dec(enum kcsan_counter_id id);
+
+/*
+ * Returns true if data races in the function symbol that maps to func_addr
+ * (offsets are ignored) should *not* be reported.
+ */
+bool kcsan_skip_report_debugfs(unsigned long func_addr);
+
+enum kcsan_report_type {
+	/*
+	 * The thread that set up the watchpoint and briefly stalled was
+	 * signalled that another thread triggered the watchpoint.
+	 */
+	KCSAN_REPORT_RACE_SIGNAL,
+
+	/*
+	 * A thread found and consumed a matching watchpoint.
+	 */
+	KCSAN_REPORT_CONSUMED_WATCHPOINT,
+
+	/*
+	 * No other thread was observed to race with the access, but the data
+	 * value before and after the stall differs.
+	 */
+	KCSAN_REPORT_RACE_UNKNOWN_ORIGIN,
+};
+/*
+ * Print a race report from thread that encountered the race.
+ */
+void kcsan_report(const volatile void *ptr, size_t size, bool is_write,
+		  bool value_change, int cpu_id, enum kcsan_report_type type);
+
+#endif /* _KERNEL_KCSAN_KCSAN_H */

kernel/kcsan/report.c

@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/preempt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/stacktrace.h>
+
+#include "kcsan.h"
+#include "encoding.h"
+
+/*
+ * Max. number of stack entries to show in the report.
+ */
+#define NUM_STACK_ENTRIES 64
+
+/*
+ * Other thread info: communicated from other racing thread to thread that set
+ * up the watchpoint, which then prints the complete report atomically. Only
+ * need one struct, as all threads should to be serialized regardless to print
+ * the reports, with reporting being in the slow-path.
+ */
+static struct {
+	const volatile void *ptr;
+	size_t size;
+	bool is_write;
+	int task_pid;
+	int cpu_id;
+	unsigned long stack_entries[NUM_STACK_ENTRIES];
+	int num_stack_entries;
+} other_info = { .ptr = NULL };
+
+/*
+ * This spinlock protects reporting and other_info, since other_info is usually
+ * required when reporting.
+ */
+static DEFINE_SPINLOCK(report_lock);
+
+/*
+ * Special rules to skip reporting.
+ */
+static bool skip_report(bool is_write, bool value_change,
+			unsigned long top_frame)
+{
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) && is_write &&
+	    !value_change) {
+		/*
+		 * The access is a write, but the data value did not change.
+		 *
+		 * We opt-out of this filter for certain functions at request of
+		 * maintainers.
+		 */
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%ps", (void *)top_frame);
+		if (!strnstr(buf, "rcu_", sizeof(buf)) &&
+		    !strnstr(buf, "_rcu", sizeof(buf)) &&
+		    !strnstr(buf, "_srcu", sizeof(buf)))
+			return true;
+	}
+
+	return kcsan_skip_report_debugfs(top_frame);
+}
+
+static inline const char *get_access_type(bool is_write)
+{
+	return is_write ? "write" : "read";
+}
+
+/* Return thread description: in task or interrupt. */
+static const char *get_thread_desc(int task_id)
+{
+	if (task_id != -1) {
+		static char buf[32]; /* safe: protected by report_lock */
+
+		snprintf(buf, sizeof(buf), "task %i", task_id);
+		return buf;
+	}
+	return "interrupt";
+}
+
+/* Helper to skip KCSAN-related functions in stack-trace. */
+static int get_stack_skipnr(unsigned long stack_entries[], int num_entries)
+{
+	char buf[64];
+	int skip = 0;
+
+	for (; skip < num_entries; ++skip) {
+		snprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skip]);
+		if (!strnstr(buf, "csan_", sizeof(buf)) &&
+		    !strnstr(buf, "tsan_", sizeof(buf)) &&
+		    !strnstr(buf, "_once_size", sizeof(buf))) {
+			break;
+		}
+	}
+	return skip;
+}
+
+/* Compares symbolized strings of addr1 and addr2. */
+static int sym_strcmp(void *addr1, void *addr2)
+{
+	char buf1[64];
+	char buf2[64];
+
+	snprintf(buf1, sizeof(buf1), "%pS", addr1);
+	snprintf(buf2, sizeof(buf2), "%pS", addr2);
+	return strncmp(buf1, buf2, sizeof(buf1));
+}
+
+/*
+ * Returns true if a report was generated, false otherwise.
+ */
+static bool print_report(const volatile void *ptr, size_t size, bool is_write,
+			 bool value_change, int cpu_id,
+			 enum kcsan_report_type type)
+{
+	unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
+	int num_stack_entries =
+		stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
+	int skipnr = get_stack_skipnr(stack_entries, num_stack_entries);
+	int other_skipnr;
+
+	/*
+	 * Must check report filter rules before starting to print.
+	 */
+	if (skip_report(is_write, true, stack_entries[skipnr]))
+		return false;
+
+	if (type == KCSAN_REPORT_RACE_SIGNAL) {
+		other_skipnr = get_stack_skipnr(other_info.stack_entries,
+						other_info.num_stack_entries);
+
+		/* value_change is only known for the other thread */
+		if (skip_report(other_info.is_write, value_change,
+				other_info.stack_entries[other_skipnr]))
+			return false;
+	}
+
+	/* Print report header. */
+	pr_err("==================================================================\n");
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL: {
+		void *this_fn = (void *)stack_entries[skipnr];
+		void *other_fn = (void *)other_info.stack_entries[other_skipnr];
+		int cmp;
+
+		/*
+		 * Order functions lexographically for consistent bug titles.
+		 * Do not print offset of functions to keep title short.
+		 */
+		cmp = sym_strcmp(other_fn, this_fn);
+		pr_err("BUG: KCSAN: data-race in %ps / %ps\n",
+		       cmp < 0 ? other_fn : this_fn,
+		       cmp < 0 ? this_fn : other_fn);
+	} break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("BUG: KCSAN: data-race in %pS\n",
+		       (void *)stack_entries[skipnr]);
+		break;
+
+	default:
+		BUG();
+	}
+
+	pr_err("\n");
+
+	/* Print information about the racing accesses. */
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL:
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(other_info.is_write), other_info.ptr,
+		       other_info.size, get_thread_desc(other_info.task_pid),
+		       other_info.cpu_id);
+
+		/* Print the other thread's stack trace. */
+		stack_trace_print(other_info.stack_entries + other_skipnr,
+				  other_info.num_stack_entries - other_skipnr,
+				  0);
+
+		pr_err("\n");
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(is_write), ptr, size,
+		       get_thread_desc(in_task() ? task_pid_nr(current) : -1),
+		       cpu_id);
+		break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("race at unknown origin, with %s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(is_write), ptr, size,
+		       get_thread_desc(in_task() ? task_pid_nr(current) : -1),
+		       cpu_id);
+		break;
+
+	default:
+		BUG();
+	}
+	/* Print stack trace of this thread. */
+	stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr,
+			  0);
+
+	/* Print report footer. */
+	pr_err("\n");
+	pr_err("Reported by Kernel Concurrency Sanitizer on:\n");
+	dump_stack_print_info(KERN_DEFAULT);
+	pr_err("==================================================================\n");
+
+	return true;
+}
+
+static void release_report(unsigned long *flags, enum kcsan_report_type type)
+{
+	if (type == KCSAN_REPORT_RACE_SIGNAL)
+		other_info.ptr = NULL; /* mark for reuse */
+
+	spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/*
+ * Depending on the report type either sets other_info and returns false, or
+ * acquires the matching other_info and returns true. If other_info is not
+ * required for the report type, simply acquires report_lock and returns true.
+ */
+static bool prepare_report(unsigned long *flags, const volatile void *ptr,
+			   size_t size, bool is_write, int cpu_id,
+			   enum kcsan_report_type type)
+{
+	if (type != KCSAN_REPORT_CONSUMED_WATCHPOINT &&
+	    type != KCSAN_REPORT_RACE_SIGNAL) {
+		/* other_info not required; just acquire report_lock */
+		spin_lock_irqsave(&report_lock, *flags);
+		return true;
+	}
+
+retry:
+	spin_lock_irqsave(&report_lock, *flags);
+
+	switch (type) {
+	case KCSAN_REPORT_CONSUMED_WATCHPOINT:
+		if (other_info.ptr != NULL)
+			break; /* still in use, retry */
+
+		other_info.ptr = ptr;
+		other_info.size = size;
+		other_info.is_write = is_write;
+		other_info.task_pid = in_task() ? task_pid_nr(current) : -1;
+		other_info.cpu_id = cpu_id;
+		other_info.num_stack_entries = stack_trace_save(
+			other_info.stack_entries, NUM_STACK_ENTRIES, 1);
+
+		spin_unlock_irqrestore(&report_lock, *flags);
+
+		/*
+		 * The other thread will print the summary; other_info may now
+		 * be consumed.
+		 */
+		return false;
+
+	case KCSAN_REPORT_RACE_SIGNAL:
+		if (other_info.ptr == NULL)
+			break; /* no data available yet, retry */
+
+		/*
+		 * First check if this is the other_info we are expecting, i.e.
+		 * matches based on how watchpoint was encoded.
+		 */
+		if (!matching_access((unsigned long)other_info.ptr &
+					     WATCHPOINT_ADDR_MASK,
+				     other_info.size,
+				     (unsigned long)ptr & WATCHPOINT_ADDR_MASK,
+				     size))
+			break; /* mismatching watchpoint, retry */
+
+		if (!matching_access((unsigned long)other_info.ptr,
+				     other_info.size, (unsigned long)ptr,
+				     size)) {
+			/*
+			 * If the actual accesses to not match, this was a false
+			 * positive due to watchpoint encoding.
+			 */
+			kcsan_counter_inc(
+				KCSAN_COUNTER_ENCODING_FALSE_POSITIVES);
+
+			/* discard this other_info */
+			release_report(flags, KCSAN_REPORT_RACE_SIGNAL);
+			return false;
+		}
+
+		/*
+		 * Matching & usable access in other_info: keep other_info_lock
+		 * locked, as this thread consumes it to print the full report;
+		 * unlocked in release_report.
+		 */
+		return true;
+
+	default:
+		BUG();
+	}
+
+	spin_unlock_irqrestore(&report_lock, *flags);
+	goto retry;
+}
+
+void kcsan_report(const volatile void *ptr, size_t size, bool is_write,
+		  bool value_change, int cpu_id, enum kcsan_report_type type)
+{
+	unsigned long flags = 0;
+
+	kcsan_disable_current();
+	if (prepare_report(&flags, ptr, size, is_write, cpu_id, type)) {
+		if (print_report(ptr, size, is_write, value_change, cpu_id,
+				 type) &&
+		    panic_on_warn)
+			panic("panic_on_warn set ...\n");
+
+		release_report(&flags, type);
+	}
+	kcsan_enable_current();
+}

kernel/kcsan/test.c

@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/types.h>
+
+#include "encoding.h"
+
+#define ITERS_PER_TEST 2000
+
+/* Test requirements. */
+static bool test_requires(void)
+{
+	/* random should be initialized for the below tests */
+	return prandom_u32() + prandom_u32() != 0;
+}
+
+/*
+ * Test watchpoint encode and decode: check that encoding some access's info,
+ * and then subsequent decode preserves the access's info.
+ */
+static bool test_encode_decode(void)
+{
+	int i;
+
+	for (i = 0; i < ITERS_PER_TEST; ++i) {
+		size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1;
+		bool is_write = !!prandom_u32_max(2);
+		unsigned long addr;
+
+		prandom_bytes(&addr, sizeof(addr));
+		if (WARN_ON(!check_encodable(addr, size)))
+			return false;
+
+		/* encode and decode */
+		{
+			const long encoded_watchpoint =
+				encode_watchpoint(addr, size, is_write);
+			unsigned long verif_masked_addr;
+			size_t verif_size;
+			bool verif_is_write;
+
+			/* check special watchpoints */
+			if (WARN_ON(decode_watchpoint(
+				    INVALID_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(decode_watchpoint(
+				    CONSUMED_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+
+			/* check decoding watchpoint returns same data */
+			if (WARN_ON(!decode_watchpoint(
+				    encoded_watchpoint, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(verif_masked_addr !=
+				    (addr & WATCHPOINT_ADDR_MASK)))
+				goto fail;
+			if (WARN_ON(verif_size != size))
+				goto fail;
+			if (WARN_ON(is_write != verif_is_write))
+				goto fail;
+
+			continue;
+fail:
+			pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n",
+			       __func__, is_write ? "write" : "read", size,
+			       addr, encoded_watchpoint,
+			       verif_is_write ? "write" : "read", verif_size,
+			       verif_masked_addr);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/* Test access matching function. */
+static bool test_matching_access(void)
+{
+	if (WARN_ON(!matching_access(10, 1, 10, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 2, 11, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 1, 9, 2)))
+		return false;
+	if (WARN_ON(matching_access(10, 1, 11, 1)))
+		return false;
+	if (WARN_ON(matching_access(9, 1, 10, 1)))
+		return false;
+	return true;
+}
+
+static int __init kcsan_selftest(void)
+{
+	int passed = 0;
+	int total = 0;
+
+#define RUN_TEST(do_test)                                                      \
+	do {                                                                   \
+		++total;                                                       \
+		if (do_test())                                                 \
+			++passed;                                              \
+		else                                                           \
+			pr_err("KCSAN selftest: " #do_test " failed");         \
+	} while (0)
+
+	RUN_TEST(test_requires);
+	RUN_TEST(test_encode_decode);
+	RUN_TEST(test_matching_access);
+
+	pr_info("KCSAN selftest: %d/%d tests passed\n", passed, total);
+	if (passed != total)
+		panic("KCSAN selftests failed");
+	return 0;
+}
+postcore_initcall(kcsan_selftest);

lib/Kconfig.debug

@@ -2086,6 +2086,8 @@ source "lib/Kconfig.kgdb"
 
 source "lib/Kconfig.ubsan"
 
+source "lib/Kconfig.kcsan"
+
 config ARCH_HAS_DEVMEM_IS_ALLOWED
 	bool