Resguardo inicial

linux-7.2.3/kernel/kcsan/.kunitconfig

@@ -0,0 +1,24 @@
+# Note that the KCSAN tests need to run on an SMP setup.
+# Under kunit_tool, this can be done by using the --qemu_args
+# option to configure a machine with several cores. For example:
+# ./tools/testing/kunit/kunit.py run --kunitconfig=kernel/kcsan \
+# 				 --arch=x86_64 --qemu_args="-smp 8"
+
+CONFIG_KUNIT=y
+
+CONFIG_DEBUG_KERNEL=y
+
+# Need some level of concurrency to test a concurrency sanitizer.
+CONFIG_SMP=y
+
+CONFIG_KCSAN=y
+CONFIG_KCSAN_KUNIT_TEST=y
+
+# Set these if you want to run test_barrier_nothreads
+#CONFIG_KCSAN_STRICT=y
+#CONFIG_KCSAN_WEAK_MEMORY=y
+
+# This prevents the test from timing out on many setups. Feel free to remove
+# (or alter) this, in conjunction with setting a different test timeout with,
+# for example, the --timeout kunit_tool option.
+CONFIG_KCSAN_REPORT_ONCE_IN_MS=100

linux-7.2.3/kernel/kcsan/Makefile

@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0
+CONTEXT_ANALYSIS := y
+
+KCSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+UBSAN_SANITIZE := n
+
+CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_debugfs.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE)
+
+CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \
+	$(call cc-option,-mno-outline-atomics) \
+	-fno-stack-protector -DDISABLE_BRANCH_PROFILING
+
+obj-y := core.o debugfs.o report.o
+
+KCSAN_INSTRUMENT_BARRIERS_selftest.o := y
+obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
+
+CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -fno-omit-frame-pointer
+CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN)
+obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o

linux-7.2.3/kernel/kcsan/debugfs.c

@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN debugfs interface.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#define pr_fmt(fmt) "kcsan: " fmt
+
+#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/sched.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"
+
+atomic_long_t kcsan_counters[KCSAN_COUNTER_COUNT];
+static const char *const counter_names[] = {
+	[KCSAN_COUNTER_USED_WATCHPOINTS]		= "used_watchpoints",
+	[KCSAN_COUNTER_SETUP_WATCHPOINTS]		= "setup_watchpoints",
+	[KCSAN_COUNTER_DATA_RACES]			= "data_races",
+	[KCSAN_COUNTER_ASSERT_FAILURES]			= "assert_failures",
+	[KCSAN_COUNTER_NO_CAPACITY]			= "no_capacity",
+	[KCSAN_COUNTER_REPORT_RACES]			= "report_races",
+	[KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN]		= "races_unknown_origin",
+	[KCSAN_COUNTER_UNENCODABLE_ACCESSES]		= "unencodable_accesses",
+	[KCSAN_COUNTER_ENCODING_FALSE_POSITIVES]	= "encoding_false_positives",
+};
+static_assert(ARRAY_SIZE(counter_names) == 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;
+static DEFINE_RAW_SPINLOCK(report_filterlist_lock);
+
+/*
+ * The microbenchmark allows benchmarking KCSAN core runtime only. To run
+ * multiple threads, pipe 'microbench=<iters>' from multiple tasks into the
+ * debugfs file. This will not generate any conflicts, and tests fast-path only.
+ */
+static noinline void microbenchmark(unsigned long iters)
+{
+	const struct kcsan_ctx ctx_save = current->kcsan_ctx;
+	const bool was_enabled = READ_ONCE(kcsan_enabled);
+	u64 cycles;
+
+	/* We may have been called from an atomic region; reset context. */
+	memset(&current->kcsan_ctx, 0, sizeof(current->kcsan_ctx));
+	/*
+	 * Disable to benchmark fast-path for all accesses, and (expected
+	 * negligible) call into slow-path, but never set up watchpoints.
+	 */
+	WRITE_ONCE(kcsan_enabled, false);
+
+	pr_info("%s begin | iters: %lu\n", __func__, iters);
+
+	cycles = get_cycles();
+	while (iters--) {
+		unsigned long addr = iters & ((PAGE_SIZE << 8) - 1);
+		int type = !(iters & 0x7f) ? KCSAN_ACCESS_ATOMIC :
+				(!(iters & 0xf) ? KCSAN_ACCESS_WRITE : 0);
+		__kcsan_check_access((void *)addr, sizeof(long), type);
+	}
+	cycles = get_cycles() - cycles;
+
+	pr_info("%s end   | cycles: %llu\n", __func__, cycles);
+
+	WRITE_ONCE(kcsan_enabled, was_enabled);
+	/* restore context */
+	current->kcsan_ctx = ctx_save;
+}
+
+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 */
+
+	raw_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:
+	raw_spin_unlock_irqrestore(&report_filterlist_lock, flags);
+	return ret;
+}
+
+static void set_report_filterlist_whitelist(bool whitelist)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&report_filterlist_lock, flags);
+	report_filterlist.whitelist = whitelist;
+	raw_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);
+	unsigned long *delay_free = NULL;
+	unsigned long *new_addrs = NULL;
+	size_t new_size = 0;
+	ssize_t ret = 0;
+
+	if (!addr) {
+		pr_err("could not find function: '%s'\n", func);
+		return -ENOENT;
+	}
+
+retry_alloc:
+	/*
+	 * Check if we need an allocation, and re-validate under the lock. Since
+	 * the report_filterlist_lock is a raw, cannot allocate under the lock.
+	 */
+	if (data_race(report_filterlist.used == report_filterlist.size)) {
+		new_size = (report_filterlist.size ?: 4) * 2;
+		delay_free = new_addrs = kmalloc_array(new_size, sizeof(unsigned long), GFP_KERNEL);
+		if (!new_addrs)
+			return -ENOMEM;
+	}
+
+	raw_spin_lock_irqsave(&report_filterlist_lock, flags);
+	if (report_filterlist.used == report_filterlist.size) {
+		/* Check we pre-allocated enough, and retry if not. */
+		if (report_filterlist.used >= new_size) {
+			raw_spin_unlock_irqrestore(&report_filterlist_lock, flags);
+			kfree(new_addrs); /* kfree(NULL) is safe */
+			delay_free = new_addrs = NULL;
+			goto retry_alloc;
+		}
+
+		if (report_filterlist.used)
+			memcpy(new_addrs, report_filterlist.addrs, report_filterlist.used * sizeof(unsigned long));
+		delay_free = report_filterlist.addrs; /* free the old list */
+		report_filterlist.addrs = new_addrs;  /* switch to the new list */
+		report_filterlist.size = new_size;
+	}
+
+	/* Note: deduplicating should be done in userspace. */
+	report_filterlist.addrs[report_filterlist.used++] = addr;
+	report_filterlist.sorted = false;
+
+	raw_spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	kfree(delay_free);
+	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_names[i],
+			   atomic_long_read(&kcsan_counters[i]));
+	}
+
+	/* show filter functions, and filter type */
+	raw_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]);
+	raw_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;
+	const size_t read_len = min(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 (str_has_prefix(arg, "microbench=")) {
+		unsigned long iters;
+
+		if (kstrtoul(&arg[strlen("microbench=")], 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
+};
+
+static int __init kcsan_debugfs_init(void)
+{
+	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
+	return 0;
+}
+
+late_initcall(kcsan_debugfs_init);

linux-7.2.3/kernel/kcsan/encoding.h

@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KCSAN watchpoint encoding.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#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, the report logic will filter out the false positive (see report.c).
+ */
+#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS)
+
+/* Bitmasks for the encoded watchpoint access information. */
+#define WATCHPOINT_WRITE_MASK	BIT(BITS_PER_LONG-1)
+#define WATCHPOINT_SIZE_MASK	GENMASK(BITS_PER_LONG-2, WATCHPOINT_ADDR_BITS)
+#define WATCHPOINT_ADDR_MASK	GENMASK(WATCHPOINT_ADDR_BITS-1, 0)
+static_assert(WATCHPOINT_ADDR_MASK == (1UL << WATCHPOINT_ADDR_BITS) - 1);
+static_assert((WATCHPOINT_WRITE_MASK ^ WATCHPOINT_SIZE_MASK ^ WATCHPOINT_ADDR_MASK) == ~0UL);
+
+static inline bool check_encodable(unsigned long addr, size_t size)
+{
+	/*
+	 * While we can encode addrs<PAGE_SIZE, avoid crashing with a NULL
+	 * pointer deref inside KCSAN.
+	 */
+	return addr >= PAGE_SIZE && 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 __always_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 __always_inline int watchpoint_slot(unsigned long addr)
+{
+	return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS;
+}
+
+static __always_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 */

linux-7.2.3/kernel/kcsan/kcsan.h

@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
+ * see Documentation/dev-tools/kcsan.rst.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#ifndef _KERNEL_KCSAN_KCSAN_H
+#define _KERNEL_KCSAN_KCSAN_H
+
+#include <linux/atomic.h>
+#include <linux/kcsan.h>
+#include <linux/sched.h>
+
+/* The number of adjacent watchpoints to check. */
+#define KCSAN_CHECK_ADJACENT 1
+#define NUM_SLOTS (1 + 2*KCSAN_CHECK_ADJACENT)
+
+extern unsigned int kcsan_udelay_task;
+extern unsigned int kcsan_udelay_interrupt;
+
+/*
+ * Globally enable and disable KCSAN.
+ */
+extern bool kcsan_enabled;
+
+/*
+ * Save/restore IRQ flags state trace dirtied by KCSAN.
+ */
+void kcsan_save_irqtrace(struct task_struct *task);
+void kcsan_restore_irqtrace(struct task_struct *task);
+
+/*
+ * Statistics counters displayed via debugfs; should only be modified in
+ * slow-paths.
+ */
+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,
+
+	/*
+	 * Total number of ASSERT failures due to races. If the observed race is
+	 * due to two conflicting ASSERT type accesses, then both will be
+	 * counted.
+	 */
+	KCSAN_COUNTER_ASSERT_FAILURES,
+
+	/*
+	 * 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 */
+};
+extern atomic_long_t kcsan_counters[KCSAN_COUNTER_COUNT];
+
+/*
+ * Returns true if data races in the function symbol that maps to func_addr
+ * (offsets are ignored) should *not* be reported.
+ */
+extern bool kcsan_skip_report_debugfs(unsigned long func_addr);
+
+/*
+ * Value-change states.
+ */
+enum kcsan_value_change {
+	/*
+	 * Did not observe a value-change, however, it is valid to report the
+	 * race, depending on preferences.
+	 */
+	KCSAN_VALUE_CHANGE_MAYBE,
+
+	/*
+	 * Did not observe a value-change, and it is invalid to report the race.
+	 */
+	KCSAN_VALUE_CHANGE_FALSE,
+
+	/*
+	 * The value was observed to change, and the race should be reported.
+	 */
+	KCSAN_VALUE_CHANGE_TRUE,
+};
+
+/*
+ * The calling thread hit and consumed a watchpoint: set the access information
+ * to be consumed by the reporting thread. No report is printed yet.
+ */
+void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type,
+			   unsigned long ip, int watchpoint_idx);
+
+/*
+ * The calling thread observed that the watchpoint it set up was hit and
+ * consumed: print the full report based on information set by the racing
+ * thread.
+ */
+void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type,
+			       unsigned long ip, enum kcsan_value_change value_change,
+			       int watchpoint_idx, u64 old, u64 new, u64 mask);
+
+/*
+ * No other thread was observed to race with the access, but the data value
+ * before and after the stall differs. Reports a race of "unknown origin".
+ */
+void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type,
+				 unsigned long ip, u64 old, u64 new, u64 mask);
+
+#endif /* _KERNEL_KCSAN_KCSAN_H */

linux-7.2.3/kernel/kcsan/permissive.h

@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Special rules for ignoring entire classes of data-racy memory accesses. None
+ * of the rules here imply that such data races are generally safe!
+ *
+ * All rules in this file can be configured via CONFIG_KCSAN_PERMISSIVE. Keep
+ * them separate from core code to make it easier to audit.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#ifndef _KERNEL_KCSAN_PERMISSIVE_H
+#define _KERNEL_KCSAN_PERMISSIVE_H
+
+#include <linux/bitops.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+
+/*
+ * Access ignore rules based on address.
+ */
+static __always_inline bool kcsan_ignore_address(const volatile void *ptr)
+{
+	if (!IS_ENABLED(CONFIG_KCSAN_PERMISSIVE))
+		return false;
+
+	/*
+	 * Data-racy bitops on current->flags are too common, ignore completely
+	 * for now.
+	 */
+	return ptr == &current->flags;
+}
+
+/*
+ * Data race ignore rules based on access type and value change patterns.
+ */
+static bool
+kcsan_ignore_data_race(size_t size, int type, u64 old, u64 new, u64 diff)
+{
+	if (!IS_ENABLED(CONFIG_KCSAN_PERMISSIVE))
+		return false;
+
+	/*
+	 * Rules here are only for plain read accesses, so that we still report
+	 * data races between plain read-write accesses.
+	 */
+	if (type || size > sizeof(long))
+		return false;
+
+	/*
+	 * A common pattern is checking/setting just 1 bit in a variable; for
+	 * example:
+	 *
+	 *	if (flags & SOME_FLAG) { ... }
+	 *
+	 * and elsewhere flags is updated concurrently:
+	 *
+	 *	flags |= SOME_OTHER_FLAG; // just 1 bit
+	 *
+	 * While it is still recommended that such accesses be marked
+	 * appropriately, in many cases these types of data races are so common
+	 * that marking them all is often unrealistic and left to maintainer
+	 * preference.
+	 *
+	 * The assumption in all cases is that with all known compiler
+	 * optimizations (including those that tear accesses), because no more
+	 * than 1 bit changed, the plain accesses are safe despite the presence
+	 * of data races.
+	 *
+	 * The rules here will ignore the data races if we observe no more than
+	 * 1 bit changed.
+	 *
+	 * Of course many operations can effecively change just 1 bit, but the
+	 * general assuption that data races involving 1-bit changes can be
+	 * tolerated still applies.
+	 *
+	 * And in case a true bug is missed, the bug likely manifests as a
+	 * reportable data race elsewhere.
+	 */
+	if (hweight64(diff) == 1) {
+		/*
+		 * Exception: Report data races where the values look like
+		 * ordinary booleans (one of them was 0 and the 0th bit was
+		 * changed) More often than not, they come with interesting
+		 * memory ordering requirements, so let's report them.
+		 */
+		if (!((!old || !new) && diff == 1))
+			return true;
+	}
+
+	return false;
+}
+
+#endif /* _KERNEL_KCSAN_PERMISSIVE_H */

linux-7.2.3/kernel/kcsan/report.c

@@ -0,0 +1,720 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN reporting.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/jiffies.h>
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.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
+
+/* Common access info. */
+struct access_info {
+	const volatile void	*ptr;
+	size_t			size;
+	int			access_type;
+	int			task_pid;
+	int			cpu_id;
+	unsigned long		ip;
+};
+
+/*
+ * Other thread info: communicated from other racing thread to thread that set
+ * up the watchpoint, which then prints the complete report atomically.
+ */
+struct other_info {
+	struct access_info	ai;
+	unsigned long		stack_entries[NUM_STACK_ENTRIES];
+	int			num_stack_entries;
+
+	/*
+	 * Optionally pass @current. Typically we do not need to pass @current
+	 * via @other_info since just @task_pid is sufficient. Passing @current
+	 * has additional overhead.
+	 *
+	 * To safely pass @current, we must either use get_task_struct/
+	 * put_task_struct, or stall the thread that populated @other_info.
+	 *
+	 * We cannot rely on get_task_struct/put_task_struct in case
+	 * release_report() races with a task being released, and would have to
+	 * free it in release_report(). This may result in deadlock if we want
+	 * to use KCSAN on the allocators.
+	 *
+	 * Since we also want to reliably print held locks for
+	 * CONFIG_KCSAN_VERBOSE, the current implementation stalls the thread
+	 * that populated @other_info until it has been consumed.
+	 */
+	struct task_struct	*task;
+};
+
+/*
+ * To never block any producers of struct other_info, we need as many elements
+ * as we have watchpoints (upper bound on concurrent races to report).
+ */
+static struct other_info other_infos[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
+
+/*
+ * Information about reported races; used to rate limit reporting.
+ */
+struct report_time {
+	/*
+	 * The last time the race was reported.
+	 */
+	unsigned long time;
+
+	/*
+	 * The frames of the 2 threads; if only 1 thread is known, one frame
+	 * will be 0.
+	 */
+	unsigned long frame1;
+	unsigned long frame2;
+};
+
+/*
+ * Since we also want to be able to debug allocators with KCSAN, to avoid
+ * deadlock, report_times cannot be dynamically resized with krealloc in
+ * rate_limit_report.
+ *
+ * Therefore, we use a fixed-size array, which at most will occupy a page. This
+ * still adequately rate limits reports, assuming that a) number of unique data
+ * races is not excessive, and b) occurrence of unique races within the
+ * same time window is limited.
+ */
+#define REPORT_TIMES_MAX (PAGE_SIZE / sizeof(struct report_time))
+#define REPORT_TIMES_SIZE                                                      \
+	(CONFIG_KCSAN_REPORT_ONCE_IN_MS > REPORT_TIMES_MAX ?                   \
+		 REPORT_TIMES_MAX :                                            \
+		 CONFIG_KCSAN_REPORT_ONCE_IN_MS)
+static struct report_time report_times[REPORT_TIMES_SIZE];
+
+/*
+ * Spinlock serializing report generation, and access to @other_infos. Although
+ * it could make sense to have a finer-grained locking story for @other_infos,
+ * report generation needs to be serialized either way, so not much is gained.
+ */
+static DEFINE_RAW_SPINLOCK(report_lock);
+
+/*
+ * Checks if the race identified by thread frames frame1 and frame2 has
+ * been reported since (now - KCSAN_REPORT_ONCE_IN_MS).
+ */
+static bool rate_limit_report(unsigned long frame1, unsigned long frame2)
+	__must_hold(&report_lock)
+{
+	struct report_time *use_entry = &report_times[0];
+	unsigned long invalid_before;
+	int i;
+
+	BUILD_BUG_ON(CONFIG_KCSAN_REPORT_ONCE_IN_MS != 0 && REPORT_TIMES_SIZE == 0);
+
+	if (CONFIG_KCSAN_REPORT_ONCE_IN_MS == 0)
+		return false;
+
+	invalid_before = jiffies - msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS);
+
+	/* Check if a matching race report exists. */
+	for (i = 0; i < REPORT_TIMES_SIZE; ++i) {
+		struct report_time *rt = &report_times[i];
+
+		/*
+		 * Must always select an entry for use to store info as we
+		 * cannot resize report_times; at the end of the scan, use_entry
+		 * will be the oldest entry, which ideally also happened before
+		 * KCSAN_REPORT_ONCE_IN_MS ago.
+		 */
+		if (time_before(rt->time, use_entry->time))
+			use_entry = rt;
+
+		/*
+		 * Initially, no need to check any further as this entry as well
+		 * as following entries have never been used.
+		 */
+		if (rt->time == 0)
+			break;
+
+		/* Check if entry expired. */
+		if (time_before(rt->time, invalid_before))
+			continue; /* before KCSAN_REPORT_ONCE_IN_MS ago */
+
+		/* Reported recently, check if race matches. */
+		if ((rt->frame1 == frame1 && rt->frame2 == frame2) ||
+		    (rt->frame1 == frame2 && rt->frame2 == frame1))
+			return true;
+	}
+
+	use_entry->time = jiffies;
+	use_entry->frame1 = frame1;
+	use_entry->frame2 = frame2;
+	return false;
+}
+
+/*
+ * Special rules to skip reporting.
+ */
+static bool
+skip_report(enum kcsan_value_change value_change, unsigned long top_frame)
+{
+	/* Should never get here if value_change==FALSE. */
+	WARN_ON_ONCE(value_change == KCSAN_VALUE_CHANGE_FALSE);
+
+	/*
+	 * The first call to skip_report always has value_change==TRUE, since we
+	 * cannot know the value written of an instrumented access. For the 2nd
+	 * call there are 6 cases with CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY:
+	 *
+	 * 1. read watchpoint, conflicting write (value_change==TRUE): report;
+	 * 2. read watchpoint, conflicting write (value_change==MAYBE): skip;
+	 * 3. write watchpoint, conflicting write (value_change==TRUE): report;
+	 * 4. write watchpoint, conflicting write (value_change==MAYBE): skip;
+	 * 5. write watchpoint, conflicting read (value_change==MAYBE): skip;
+	 * 6. write watchpoint, conflicting read (value_change==TRUE): report;
+	 *
+	 * Cases 1-4 are intuitive and expected; case 5 ensures we do not report
+	 * data races where the write may have rewritten the same value; case 6
+	 * is possible either if the size is larger than what we check value
+	 * changes for or the access type is KCSAN_ACCESS_ASSERT.
+	 */
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) &&
+	    value_change == KCSAN_VALUE_CHANGE_MAYBE) {
+		/*
+		 * 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];
+		int len = scnprintf(buf, sizeof(buf), "%ps", (void *)top_frame);
+
+		if (!strnstr(buf, "rcu_", len) &&
+		    !strnstr(buf, "_rcu", len) &&
+		    !strnstr(buf, "_srcu", len))
+			return true;
+	}
+
+	return kcsan_skip_report_debugfs(top_frame);
+}
+
+static const char *get_access_type(int type)
+{
+	if (type & KCSAN_ACCESS_ASSERT) {
+		if (type & KCSAN_ACCESS_SCOPED) {
+			if (type & KCSAN_ACCESS_WRITE)
+				return "assert no accesses (reordered)";
+			else
+				return "assert no writes (reordered)";
+		} else {
+			if (type & KCSAN_ACCESS_WRITE)
+				return "assert no accesses";
+			else
+				return "assert no writes";
+		}
+	}
+
+	switch (type) {
+	case 0:
+		return "read";
+	case KCSAN_ACCESS_ATOMIC:
+		return "read (marked)";
+	case KCSAN_ACCESS_WRITE:
+		return "write";
+	case KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "write (marked)";
+	case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE:
+		return "read-write";
+	case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "read-write (marked)";
+	case KCSAN_ACCESS_SCOPED:
+		return "read (reordered)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC:
+		return "read (marked, reordered)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE:
+		return "write (reordered)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "write (marked, reordered)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE:
+		return "read-write (reordered)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "read-write (marked, reordered)";
+	default:
+		BUG();
+	}
+}
+
+static const char *get_bug_type(int type)
+{
+	return (type & KCSAN_ACCESS_ASSERT) != 0 ? "assert: race" : "data-race";
+}
+
+/* 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(const unsigned long stack_entries[], int num_entries)
+{
+	char buf[64];
+	char *cur;
+	int len, skip;
+
+	for (skip = 0; skip < num_entries; ++skip) {
+		len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skip]);
+
+		/* Never show tsan_* or {read,write}_once_size. */
+		if (strnstr(buf, "tsan_", len) ||
+		    strnstr(buf, "_once_size", len))
+			continue;
+
+		cur = strnstr(buf, "kcsan_", len);
+		if (cur) {
+			cur += strlen("kcsan_");
+			if (!str_has_prefix(cur, "test"))
+				continue; /* KCSAN runtime function. */
+			/* KCSAN related test. */
+		}
+
+		/*
+		 * No match for runtime functions -- @skip entries to skip to
+		 * get to first frame of interest.
+		 */
+		break;
+	}
+
+	return skip;
+}
+
+/*
+ * Skips to the first entry that matches the function of @ip, and then replaces
+ * that entry with @ip, returning the entries to skip with @replaced containing
+ * the replaced entry.
+ */
+static int
+replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip,
+		    unsigned long *replaced)
+{
+	unsigned long symbolsize, offset;
+	unsigned long target_func;
+	int skip;
+
+	if (kallsyms_lookup_size_offset(ip, &symbolsize, &offset))
+		target_func = ip - offset;
+	else
+		goto fallback;
+
+	for (skip = 0; skip < num_entries; ++skip) {
+		unsigned long func = stack_entries[skip];
+
+		if (!kallsyms_lookup_size_offset(func, &symbolsize, &offset))
+			goto fallback;
+		func -= offset;
+
+		if (func == target_func) {
+			*replaced = stack_entries[skip];
+			stack_entries[skip] = ip;
+			return skip;
+		}
+	}
+
+fallback:
+	/* Should not happen; the resulting stack trace is likely misleading. */
+	WARN_ONCE(1, "Cannot find frame for %pS in stack trace", (void *)ip);
+	return get_stack_skipnr(stack_entries, num_entries);
+}
+
+static int
+sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip,
+		       unsigned long *replaced)
+{
+	return ip ? replace_stack_entry(stack_entries, num_entries, ip, replaced) :
+			  get_stack_skipnr(stack_entries, num_entries);
+}
+
+/* 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));
+}
+
+static void
+print_stack_trace(unsigned long stack_entries[], int num_entries, unsigned long reordered_to)
+	__must_hold(&report_lock)
+{
+	stack_trace_print(stack_entries, num_entries, 0);
+	if (reordered_to)
+		pr_err("  |\n  +-> reordered to: %pS\n", (void *)reordered_to);
+}
+
+static void print_verbose_info(struct task_struct *task)
+	__must_hold(&report_lock)
+{
+	if (!task)
+		return;
+
+	/* Restore IRQ state trace for printing. */
+	kcsan_restore_irqtrace(task);
+
+	pr_err("\n");
+	debug_show_held_locks(task);
+	print_irqtrace_events(task);
+}
+
+static void print_report(enum kcsan_value_change value_change,
+			 const struct access_info *ai,
+			 struct other_info *other_info,
+			 u64 old, u64 new, u64 mask)
+	__must_hold(&report_lock)
+{
+	unsigned long reordered_to = 0;
+	unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
+	int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
+	int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip, &reordered_to);
+	unsigned long this_frame = stack_entries[skipnr];
+	unsigned long other_reordered_to = 0;
+	unsigned long other_frame = 0;
+	int other_skipnr = 0; /* silence uninit warnings */
+
+	/*
+	 * Must check report filter rules before starting to print.
+	 */
+	if (skip_report(KCSAN_VALUE_CHANGE_TRUE, stack_entries[skipnr]))
+		return;
+
+	if (other_info) {
+		other_skipnr = sanitize_stack_entries(other_info->stack_entries,
+						      other_info->num_stack_entries,
+						      other_info->ai.ip, &other_reordered_to);
+		other_frame = other_info->stack_entries[other_skipnr];
+
+		/* @value_change is only known for the other thread */
+		if (skip_report(value_change, other_frame))
+			return;
+	}
+
+	if (rate_limit_report(this_frame, other_frame))
+		return;
+
+	/* Print report header. */
+	pr_err("==================================================================\n");
+	if (other_info) {
+		int cmp;
+
+		/*
+		 * Order functions lexographically for consistent bug titles.
+		 * Do not print offset of functions to keep title short.
+		 */
+		cmp = sym_strcmp((void *)other_frame, (void *)this_frame);
+		pr_err("BUG: KCSAN: %s in %ps / %ps\n",
+		       get_bug_type(ai->access_type | other_info->ai.access_type),
+		       (void *)(cmp < 0 ? other_frame : this_frame),
+		       (void *)(cmp < 0 ? this_frame : other_frame));
+	} else {
+		pr_err("BUG: KCSAN: %s in %pS\n", get_bug_type(ai->access_type),
+		       (void *)this_frame);
+	}
+
+	pr_err("\n");
+
+	/* Print information about the racing accesses. */
+	if (other_info) {
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(other_info->ai.access_type), other_info->ai.ptr,
+		       other_info->ai.size, get_thread_desc(other_info->ai.task_pid),
+		       other_info->ai.cpu_id);
+
+		/* Print the other thread's stack trace. */
+		print_stack_trace(other_info->stack_entries + other_skipnr,
+				  other_info->num_stack_entries - other_skipnr,
+				  other_reordered_to);
+		if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+			print_verbose_info(other_info->task);
+
+		pr_err("\n");
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(ai->access_type), ai->ptr, ai->size,
+		       get_thread_desc(ai->task_pid), ai->cpu_id);
+	} else {
+		pr_err("race at unknown origin, with %s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(ai->access_type), ai->ptr, ai->size,
+		       get_thread_desc(ai->task_pid), ai->cpu_id);
+	}
+	/* Print stack trace of this thread. */
+	print_stack_trace(stack_entries + skipnr, num_stack_entries - skipnr, reordered_to);
+	if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+		print_verbose_info(current);
+
+	/* Print observed value change. */
+	if (ai->size <= 8) {
+		int hex_len = ai->size * 2;
+		u64 diff = old ^ new;
+
+		if (mask)
+			diff &= mask;
+		if (diff) {
+			pr_err("\n");
+			pr_err("value changed: 0x%0*llx -> 0x%0*llx\n",
+			       hex_len, old, hex_len, new);
+			if (mask) {
+				pr_err(" bits changed: 0x%0*llx with mask 0x%0*llx\n",
+				       hex_len, diff, hex_len, mask);
+			}
+		}
+	}
+
+	/* Print report footer. */
+	pr_err("\n");
+	pr_err("Reported by Kernel Concurrency Sanitizer on:\n");
+	dump_stack_print_info(KERN_DEFAULT);
+	pr_err("==================================================================\n");
+
+	check_panic_on_warn("KCSAN");
+}
+
+static void release_report(unsigned long *flags, struct other_info *other_info)
+	__releases(&report_lock)
+{
+	/*
+	 * Use size to denote valid/invalid, since KCSAN entirely ignores
+	 * 0-sized accesses.
+	 */
+	other_info->ai.size = 0;
+	raw_spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/*
+ * Sets @other_info->task and awaits consumption of @other_info.
+ */
+static void set_other_info_task_blocking(unsigned long *flags,
+					 const struct access_info *ai,
+					 struct other_info *other_info)
+	__must_hold(&report_lock)
+{
+	/*
+	 * We may be instrumenting a code-path where current->state is already
+	 * something other than TASK_RUNNING.
+	 */
+	const bool is_running = task_is_running(current);
+	/*
+	 * To avoid deadlock in case we are in an interrupt here and this is a
+	 * race with a task on the same CPU (KCSAN_INTERRUPT_WATCHER), provide a
+	 * timeout to ensure this works in all contexts.
+	 *
+	 * Await approximately the worst case delay of the reporting thread (if
+	 * we are not interrupted).
+	 */
+	int timeout = max(kcsan_udelay_task, kcsan_udelay_interrupt);
+
+	other_info->task = current;
+	do {
+		if (is_running) {
+			/*
+			 * Let lockdep know the real task is sleeping, to print
+			 * the held locks (recall we turned lockdep off, so
+			 * locking/unlocking @report_lock won't be recorded).
+			 */
+			set_current_state(TASK_UNINTERRUPTIBLE);
+		}
+		raw_spin_unlock_irqrestore(&report_lock, *flags);
+		/*
+		 * We cannot call schedule() since we also cannot reliably
+		 * determine if sleeping here is permitted -- see in_atomic().
+		 */
+
+		udelay(1);
+		raw_spin_lock_irqsave(&report_lock, *flags);
+		if (timeout-- < 0) {
+			/*
+			 * Abort. Reset @other_info->task to NULL, since it
+			 * appears the other thread is still going to consume
+			 * it. It will result in no verbose info printed for
+			 * this task.
+			 */
+			other_info->task = NULL;
+			break;
+		}
+		/*
+		 * If invalid, or @ptr nor @current matches, then @other_info
+		 * has been consumed and we may continue. If not, retry.
+		 */
+	} while (other_info->ai.size && other_info->ai.ptr == ai->ptr &&
+		 other_info->task == current);
+	if (is_running)
+		set_current_state(TASK_RUNNING);
+}
+
+/* Populate @other_info; requires that the provided @other_info not in use. */
+static void prepare_report_producer(unsigned long *flags,
+				    const struct access_info *ai,
+				    struct other_info *other_info)
+	__must_not_hold(&report_lock)
+{
+	raw_spin_lock_irqsave(&report_lock, *flags);
+
+	/*
+	 * The same @other_infos entry cannot be used concurrently, because
+	 * there is a one-to-one mapping to watchpoint slots (@watchpoints in
+	 * core.c), and a watchpoint is only released for reuse after reporting
+	 * is done by the consumer of @other_info. Therefore, it is impossible
+	 * for another concurrent prepare_report_producer() to set the same
+	 * @other_info, and are guaranteed exclusivity for the @other_infos
+	 * entry pointed to by @other_info.
+	 *
+	 * To check this property holds, size should never be non-zero here,
+	 * because every consumer of struct other_info resets size to 0 in
+	 * release_report().
+	 */
+	WARN_ON(other_info->ai.size);
+
+	other_info->ai = *ai;
+	other_info->num_stack_entries = stack_trace_save(other_info->stack_entries, NUM_STACK_ENTRIES, 2);
+
+	if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+		set_other_info_task_blocking(flags, ai, other_info);
+
+	raw_spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/* Awaits producer to fill @other_info and then returns. */
+static bool prepare_report_consumer(unsigned long *flags,
+				    const struct access_info *ai,
+				    struct other_info *other_info)
+	__cond_acquires(true, &report_lock)
+{
+
+	raw_spin_lock_irqsave(&report_lock, *flags);
+	while (!other_info->ai.size) { /* Await valid @other_info. */
+		raw_spin_unlock_irqrestore(&report_lock, *flags);
+		cpu_relax();
+		raw_spin_lock_irqsave(&report_lock, *flags);
+	}
+
+	/* Should always have a matching access based on watchpoint encoding. */
+	if (WARN_ON(!matching_access((unsigned long)other_info->ai.ptr & WATCHPOINT_ADDR_MASK, other_info->ai.size,
+				     (unsigned long)ai->ptr & WATCHPOINT_ADDR_MASK, ai->size)))
+		goto discard;
+
+	if (!matching_access((unsigned long)other_info->ai.ptr, other_info->ai.size,
+			     (unsigned long)ai->ptr, ai->size)) {
+		/*
+		 * If the actual accesses to not match, this was a false
+		 * positive due to watchpoint encoding.
+		 */
+		atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ENCODING_FALSE_POSITIVES]);
+		goto discard;
+	}
+
+	return true;
+
+discard:
+	release_report(flags, other_info);
+	return false;
+}
+
+static struct access_info prepare_access_info(const volatile void *ptr, size_t size,
+					      int access_type, unsigned long ip)
+{
+	return (struct access_info) {
+		.ptr		= ptr,
+		.size		= size,
+		.access_type	= access_type,
+		.task_pid	= in_task() ? task_pid_nr(current) : -1,
+		.cpu_id		= raw_smp_processor_id(),
+		/* Only replace stack entry with @ip if scoped access. */
+		.ip		= (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0,
+	};
+}
+
+void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type,
+			   unsigned long ip, int watchpoint_idx)
+{
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
+	unsigned long flags;
+
+	kcsan_disable_current();
+	lockdep_off(); /* See kcsan_report_known_origin(). */
+
+	prepare_report_producer(&flags, &ai, &other_infos[watchpoint_idx]);
+
+	lockdep_on();
+	kcsan_enable_current();
+}
+
+void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type,
+			       unsigned long ip, enum kcsan_value_change value_change,
+			       int watchpoint_idx, u64 old, u64 new, u64 mask)
+{
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
+	struct other_info *other_info = &other_infos[watchpoint_idx];
+	unsigned long flags = 0;
+
+	kcsan_disable_current();
+	/*
+	 * Because we may generate reports when we're in scheduler code, the use
+	 * of printk() could deadlock. Until such time that all printing code
+	 * called in print_report() is scheduler-safe, accept the risk, and just
+	 * get our message out. As such, also disable lockdep to hide the
+	 * warning, and avoid disabling lockdep for the rest of the kernel.
+	 */
+	lockdep_off();
+
+	if (!prepare_report_consumer(&flags, &ai, other_info))
+		goto out;
+	/*
+	 * Never report if value_change is FALSE, only when it is
+	 * either TRUE or MAYBE. In case of MAYBE, further filtering may
+	 * be done once we know the full stack trace in print_report().
+	 */
+	if (value_change != KCSAN_VALUE_CHANGE_FALSE)
+		print_report(value_change, &ai, other_info, old, new, mask);
+
+	release_report(&flags, other_info);
+out:
+	lockdep_on();
+	kcsan_enable_current();
+}
+
+void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type,
+				 unsigned long ip, u64 old, u64 new, u64 mask)
+{
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
+	unsigned long flags;
+
+	kcsan_disable_current();
+	lockdep_off(); /* See kcsan_report_known_origin(). */
+
+	raw_spin_lock_irqsave(&report_lock, flags);
+	print_report(KCSAN_VALUE_CHANGE_TRUE, &ai, NULL, old, new, mask);
+	raw_spin_unlock_irqrestore(&report_lock, flags);
+
+	lockdep_on();
+	kcsan_enable_current();
+}

linux-7.2.3/kernel/kcsan/selftest.c

@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN short boot-time selftests.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
+
+#define pr_fmt(fmt) "kcsan: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/kcsan-checks.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "encoding.h"
+
+#define ITERS_PER_TEST 2000
+
+/*
+ * Test watchpoint encode and decode: check that encoding some access's info,
+ * and then subsequent decode preserves the access's info.
+ */
+static bool __init test_encode_decode(void)
+{
+	int i;
+
+	for (i = 0; i < ITERS_PER_TEST; ++i) {
+		size_t size = get_random_u32_inclusive(1, MAX_ENCODABLE_SIZE);
+		bool is_write = !!get_random_u32_below(2);
+		unsigned long verif_masked_addr;
+		long encoded_watchpoint;
+		bool verif_is_write;
+		unsigned long addr;
+		size_t verif_size;
+
+		get_random_bytes(&addr, sizeof(addr));
+		if (addr < PAGE_SIZE)
+			addr = PAGE_SIZE;
+
+		if (WARN_ON(!check_encodable(addr, size)))
+			return false;
+
+		encoded_watchpoint = encode_watchpoint(addr, size, 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 __init 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;
+
+	/*
+	 * An access of size 0 could match another access, as demonstrated here.
+	 * Rather than add more comparisons to 'matching_access()', which would
+	 * end up in the fast-path for *all* checks, check_access() simply
+	 * returns for all accesses of size 0.
+	 */
+	if (WARN_ON(!matching_access(8, 8, 12, 0)))
+		return false;
+
+	return true;
+}
+
+/*
+ * Correct memory barrier instrumentation is critical to avoiding false
+ * positives: simple test to check at boot certain barriers are always properly
+ * instrumented. See kcsan_test for a more complete test.
+ */
+static DEFINE_SPINLOCK(test_spinlock);
+static bool __init test_barrier(void)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+	struct kcsan_scoped_access *reorder_access = &current->kcsan_ctx.reorder_access;
+#else
+	struct kcsan_scoped_access *reorder_access = NULL;
+#endif
+	bool ret = true;
+	arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED;
+	atomic_t dummy;
+	long test_var;
+
+	if (!reorder_access || !IS_ENABLED(CONFIG_SMP))
+		return true;
+
+#define __KCSAN_CHECK_BARRIER(access_type, barrier, name)					\
+	do {											\
+		reorder_access->type = (access_type) | KCSAN_ACCESS_SCOPED;			\
+		reorder_access->size = 1;							\
+		barrier;									\
+		if (reorder_access->size != 0) {						\
+			pr_err("improperly instrumented type=(" #access_type "): " name "\n");	\
+			ret = false;								\
+		}										\
+	} while (0)
+#define KCSAN_CHECK_READ_BARRIER(b)  __KCSAN_CHECK_BARRIER(0, b, #b)
+#define KCSAN_CHECK_WRITE_BARRIER(b) __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE, b, #b)
+#define KCSAN_CHECK_RW_BARRIER(b)    __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND, b, #b)
+
+	kcsan_nestable_atomic_begin(); /* No watchpoints in called functions. */
+
+	KCSAN_CHECK_READ_BARRIER(mb());
+	KCSAN_CHECK_READ_BARRIER(rmb());
+	KCSAN_CHECK_READ_BARRIER(smp_mb());
+	KCSAN_CHECK_READ_BARRIER(smp_rmb());
+	KCSAN_CHECK_READ_BARRIER(dma_rmb());
+	KCSAN_CHECK_READ_BARRIER(smp_mb__before_atomic());
+	KCSAN_CHECK_READ_BARRIER(smp_mb__after_atomic());
+	KCSAN_CHECK_READ_BARRIER(smp_mb__after_spinlock());
+	KCSAN_CHECK_READ_BARRIER(smp_store_mb(test_var, 0));
+	KCSAN_CHECK_READ_BARRIER(smp_store_release(&test_var, 0));
+	KCSAN_CHECK_READ_BARRIER(xchg(&test_var, 0));
+	KCSAN_CHECK_READ_BARRIER(xchg_release(&test_var, 0));
+	KCSAN_CHECK_READ_BARRIER(cmpxchg(&test_var, 0,  0));
+	KCSAN_CHECK_READ_BARRIER(cmpxchg_release(&test_var, 0,  0));
+	KCSAN_CHECK_READ_BARRIER(atomic_set_release(&dummy, 0));
+	KCSAN_CHECK_READ_BARRIER(atomic_add_return(1, &dummy));
+	KCSAN_CHECK_READ_BARRIER(atomic_add_return_release(1, &dummy));
+	KCSAN_CHECK_READ_BARRIER(atomic_fetch_add(1, &dummy));
+	KCSAN_CHECK_READ_BARRIER(atomic_fetch_add_release(1, &dummy));
+	KCSAN_CHECK_READ_BARRIER(test_and_set_bit(0, &test_var));
+	KCSAN_CHECK_READ_BARRIER(test_and_clear_bit(0, &test_var));
+	KCSAN_CHECK_READ_BARRIER(test_and_change_bit(0, &test_var));
+	KCSAN_CHECK_READ_BARRIER(clear_bit_unlock(0, &test_var));
+	KCSAN_CHECK_READ_BARRIER(__clear_bit_unlock(0, &test_var));
+	arch_spin_lock(&arch_spinlock);
+	KCSAN_CHECK_READ_BARRIER(arch_spin_unlock(&arch_spinlock));
+	spin_lock(&test_spinlock);
+	KCSAN_CHECK_READ_BARRIER(spin_unlock(&test_spinlock));
+
+	KCSAN_CHECK_WRITE_BARRIER(mb());
+	KCSAN_CHECK_WRITE_BARRIER(wmb());
+	KCSAN_CHECK_WRITE_BARRIER(smp_mb());
+	KCSAN_CHECK_WRITE_BARRIER(smp_wmb());
+	KCSAN_CHECK_WRITE_BARRIER(dma_wmb());
+	KCSAN_CHECK_WRITE_BARRIER(smp_mb__before_atomic());
+	KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_atomic());
+	KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_spinlock());
+	KCSAN_CHECK_WRITE_BARRIER(smp_store_mb(test_var, 0));
+	KCSAN_CHECK_WRITE_BARRIER(smp_store_release(&test_var, 0));
+	KCSAN_CHECK_WRITE_BARRIER(xchg(&test_var, 0));
+	KCSAN_CHECK_WRITE_BARRIER(xchg_release(&test_var, 0));
+	KCSAN_CHECK_WRITE_BARRIER(cmpxchg(&test_var, 0,  0));
+	KCSAN_CHECK_WRITE_BARRIER(cmpxchg_release(&test_var, 0,  0));
+	KCSAN_CHECK_WRITE_BARRIER(atomic_set_release(&dummy, 0));
+	KCSAN_CHECK_WRITE_BARRIER(atomic_add_return(1, &dummy));
+	KCSAN_CHECK_WRITE_BARRIER(atomic_add_return_release(1, &dummy));
+	KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add(1, &dummy));
+	KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add_release(1, &dummy));
+	KCSAN_CHECK_WRITE_BARRIER(test_and_set_bit(0, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(test_and_clear_bit(0, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(test_and_change_bit(0, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock(0, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(__clear_bit_unlock(0, &test_var));
+	arch_spin_lock(&arch_spinlock);
+	KCSAN_CHECK_WRITE_BARRIER(arch_spin_unlock(&arch_spinlock));
+	spin_lock(&test_spinlock);
+	KCSAN_CHECK_WRITE_BARRIER(spin_unlock(&test_spinlock));
+
+	KCSAN_CHECK_RW_BARRIER(mb());
+	KCSAN_CHECK_RW_BARRIER(wmb());
+	KCSAN_CHECK_RW_BARRIER(rmb());
+	KCSAN_CHECK_RW_BARRIER(smp_mb());
+	KCSAN_CHECK_RW_BARRIER(smp_wmb());
+	KCSAN_CHECK_RW_BARRIER(smp_rmb());
+	KCSAN_CHECK_RW_BARRIER(dma_wmb());
+	KCSAN_CHECK_RW_BARRIER(dma_rmb());
+	KCSAN_CHECK_RW_BARRIER(smp_mb__before_atomic());
+	KCSAN_CHECK_RW_BARRIER(smp_mb__after_atomic());
+	KCSAN_CHECK_RW_BARRIER(smp_mb__after_spinlock());
+	KCSAN_CHECK_RW_BARRIER(smp_store_mb(test_var, 0));
+	KCSAN_CHECK_RW_BARRIER(smp_store_release(&test_var, 0));
+	KCSAN_CHECK_RW_BARRIER(xchg(&test_var, 0));
+	KCSAN_CHECK_RW_BARRIER(xchg_release(&test_var, 0));
+	KCSAN_CHECK_RW_BARRIER(cmpxchg(&test_var, 0,  0));
+	KCSAN_CHECK_RW_BARRIER(cmpxchg_release(&test_var, 0,  0));
+	KCSAN_CHECK_RW_BARRIER(atomic_set_release(&dummy, 0));
+	KCSAN_CHECK_RW_BARRIER(atomic_add_return(1, &dummy));
+	KCSAN_CHECK_RW_BARRIER(atomic_add_return_release(1, &dummy));
+	KCSAN_CHECK_RW_BARRIER(atomic_fetch_add(1, &dummy));
+	KCSAN_CHECK_RW_BARRIER(atomic_fetch_add_release(1, &dummy));
+	KCSAN_CHECK_RW_BARRIER(test_and_set_bit(0, &test_var));
+	KCSAN_CHECK_RW_BARRIER(test_and_clear_bit(0, &test_var));
+	KCSAN_CHECK_RW_BARRIER(test_and_change_bit(0, &test_var));
+	KCSAN_CHECK_RW_BARRIER(clear_bit_unlock(0, &test_var));
+	KCSAN_CHECK_RW_BARRIER(__clear_bit_unlock(0, &test_var));
+	arch_spin_lock(&arch_spinlock);
+	KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock));
+	spin_lock(&test_spinlock);
+	KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock));
+	KCSAN_CHECK_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+	KCSAN_CHECK_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+	kcsan_nestable_atomic_end();
+
+	return ret;
+}
+
+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("selftest: " #do_test " failed");               \
+	} while (0)
+
+	RUN_TEST(test_encode_decode);
+	RUN_TEST(test_matching_access);
+	RUN_TEST(test_barrier);
+
+	pr_info("selftest: %d/%d tests passed\n", passed, total);
+	if (passed != total)
+		panic("selftests failed");
+	return 0;
+}
+postcore_initcall(kcsan_selftest);