1 files changed, 186 insertions, 105 deletions

diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index ac5f8345bae9..e95ce7d7a76e 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -1,8 +1,14 @@
 // 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>
@@ -26,6 +32,7 @@ struct access_info {
 	int			access_type;
 	int			task_pid;
 	int			cpu_id;
+	unsigned long		ip;
 };
 
 /*
@@ -208,9 +215,9 @@ 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 (scoped)";
+				return "assert no accesses (reordered)";
 			else
-				return "assert no writes (scoped)";
+				return "assert no writes (reordered)";
 		} else {
 			if (type & KCSAN_ACCESS_WRITE)
 				return "assert no accesses";
@@ -228,14 +235,22 @@ static const char *get_access_type(int type)
 		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 (scoped)";
+		return "read (reordered)";
 	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC:
-		return "read (marked, scoped)";
+		return "read (marked, reordered)";
 	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE:
-		return "write (scoped)";
+		return "write (reordered)";
 	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
-		return "write (marked, scoped)";
+		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();
 	}
@@ -275,8 +290,8 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 
 		cur = strnstr(buf, "kcsan_", len);
 		if (cur) {
-			cur += sizeof("kcsan_") - 1;
-			if (strncmp(cur, "test", sizeof("test") - 1))
+			cur += strlen("kcsan_");
+			if (!str_has_prefix(cur, "test"))
 				continue; /* KCSAN runtime function. */
 			/* KCSAN related test. */
 		}
@@ -291,6 +306,52 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 	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)
 {
@@ -303,28 +364,38 @@ static int sym_strcmp(void *addr1, void *addr2)
 	return strncmp(buf1, buf2, sizeof(buf1));
 }
 
+static void
+print_stack_trace(unsigned long stack_entries[], int num_entries, unsigned long reordered_to)
+{
+	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)
 {
 	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);
 }
 
-/*
- * Returns true if a report was generated, false otherwise.
- */
-static bool print_report(enum kcsan_value_change value_change,
-			 enum kcsan_report_type type,
+static void print_report(enum kcsan_value_change value_change,
 			 const struct access_info *ai,
-			 const struct other_info *other_info)
+			 struct other_info *other_info,
+			 u64 old, u64 new, u64 mask)
 {
+	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 = get_stack_skipnr(stack_entries, num_stack_entries);
+	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 */
 
@@ -332,25 +403,25 @@ static bool print_report(enum kcsan_value_change value_change,
 	 * Must check report filter rules before starting to print.
 	 */
 	if (skip_report(KCSAN_VALUE_CHANGE_TRUE, stack_entries[skipnr]))
-		return false;
+		return;
 
-	if (type == KCSAN_REPORT_RACE_SIGNAL) {
-		other_skipnr = get_stack_skipnr(other_info->stack_entries,
-						other_info->num_stack_entries);
+	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 false;
+			return;
 	}
 
 	if (rate_limit_report(this_frame, other_frame))
-		return false;
+		return;
 
 	/* Print report header. */
 	pr_err("==================================================================\n");
-	switch (type) {
-	case KCSAN_REPORT_RACE_SIGNAL: {
+	if (other_info) {
 		int cmp;
 
 		/*
@@ -362,32 +433,24 @@ static bool print_report(enum kcsan_value_change value_change,
 		       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));
-	} break;
-
-	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+	} else {
 		pr_err("BUG: KCSAN: %s in %pS\n", get_bug_type(ai->access_type),
 		       (void *)this_frame);
-		break;
-
-	default:
-		BUG();
 	}
 
 	pr_err("\n");
 
 	/* Print information about the racing accesses. */
-	switch (type) {
-	case KCSAN_REPORT_RACE_SIGNAL:
+	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. */
-		stack_trace_print(other_info->stack_entries + other_skipnr,
+		print_stack_trace(other_info->stack_entries + other_skipnr,
 				  other_info->num_stack_entries - other_skipnr,
-				  0);
-
+				  other_reordered_to);
 		if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
 			print_verbose_info(other_info->task);
 
@@ -395,42 +458,50 @@ static bool print_report(enum kcsan_value_change value_change,
 		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);
-		break;
-
-	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+	} 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);
-		break;
-
-	default:
-		BUG();
 	}
 	/* Print stack trace of this thread. */
-	stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr,
-			  0);
-
+	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");
 
-	return true;
+	check_panic_on_warn("KCSAN");
 }
 
 static void release_report(unsigned long *flags, struct other_info *other_info)
 {
-	if (other_info)
-		/*
-		 * Use size to denote valid/invalid, since KCSAN entirely
-		 * ignores 0-sized accesses.
-		 */
-		other_info->ai.size = 0;
-
+	/*
+	 * 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);
 }
 
@@ -448,7 +519,7 @@ static void set_other_info_task_blocking(unsigned long *flags,
 	 * We may be instrumenting a code-path where current->state is already
 	 * something other than TASK_RUNNING.
 	 */
-	const bool is_running = current->state == 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
@@ -552,7 +623,7 @@ static bool prepare_report_consumer(unsigned long *flags,
 		 * If the actual accesses to not match, this was a false
 		 * positive due to watchpoint encoding.
 		 */
-		kcsan_counter_inc(KCSAN_COUNTER_ENCODING_FALSE_POSITIVES);
+		atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ENCODING_FALSE_POSITIVES]);
 		goto discard;
 	}
 
@@ -563,72 +634,82 @@ discard:
 	return false;
 }
 
-/*
- * Depending on the report type either sets @other_info and returns false, or
- * awaits @other_info and returns true. If @other_info is not required for the
- * report type, simply acquires @report_lock and returns true.
- */
-static noinline bool prepare_report(unsigned long *flags,
-				    enum kcsan_report_type type,
-				    const struct access_info *ai,
-				    struct other_info *other_info)
-{
-	switch (type) {
-	case KCSAN_REPORT_CONSUMED_WATCHPOINT:
-		prepare_report_producer(flags, ai, other_info);
-		return false;
-	case KCSAN_REPORT_RACE_SIGNAL:
-		return prepare_report_consumer(flags, ai, other_info);
-	default:
-		/* @other_info not required; just acquire @report_lock. */
-		raw_spin_lock_irqsave(&report_lock, *flags);
-		return true;
-	}
-}
-
-void kcsan_report(const volatile void *ptr, size_t size, int access_type,
-		  enum kcsan_value_change value_change,
-		  enum kcsan_report_type type, int watchpoint_idx)
+static struct access_info prepare_access_info(const volatile void *ptr, size_t size,
+					      int access_type, unsigned long ip)
 {
-	unsigned long flags = 0;
-	const struct access_info ai = {
+	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()
+		.cpu_id		= raw_smp_processor_id(),
+		/* Only replace stack entry with @ip if scoped access. */
+		.ip		= (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0,
 	};
-	struct other_info *other_info = type == KCSAN_REPORT_RACE_UNKNOWN_ORIGIN
-					? NULL : &other_infos[watchpoint_idx];
+}
+
+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();
-	if (WARN_ON(watchpoint_idx < 0 || watchpoint_idx >= ARRAY_SIZE(other_infos)))
-		goto out;
+	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();
 	/*
-	 * With TRACE_IRQFLAGS, lockdep's IRQ trace state becomes corrupted if
-	 * we do not turn off lockdep here; this could happen due to recursion
-	 * into lockdep via KCSAN if we detect a race in utilities used by
-	 * lockdep.
+	 * 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(&flags, type, &ai, other_info)) {
-		/*
-		 * Never report if value_change is FALSE, only if we 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().
-		 */
-		bool reported = value_change != KCSAN_VALUE_CHANGE_FALSE &&
-				print_report(value_change, type, &ai, other_info);
+	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);
 
-		if (reported && panic_on_warn)
-			panic("panic_on_warn set ...\n");
+	release_report(&flags, other_info);
+out:
+	lockdep_on();
+	kcsan_enable_current();
+}
 
-		release_report(&flags, other_info);
-	}
+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();
-out:
 	kcsan_enable_current();
 }