lockdep: Fix usage_traceoverflow

Basically print_lock_class_header()'s for loop is out of sync with the
the size of of ->usage_traces[].

Also clean things up a bit while at it, to avoid such mishaps in the future.

Fixes: 23870f12 ("locking/lockdep: Fix "USED" <- "IN-NMI" inversions")
Reported-by: Qian Cai <cai@redhat.com>
Debugged-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Qian Cai <cai@redhat.com>
Link: https://lkml.kernel.org/r/20200930094937.GE2651@hirez.programming.kicks-ass.net

include/linux/lockdep_types.h

@@ -35,8 +35,12 @@ enum lockdep_wait_type {
 /*
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
+ *
+ * XXX_LOCK_USAGE_STATES is the number of lines in lockdep_states.h, for each
+ * of those we generates 4 states, Additionally we report on USED and USED_READ.
  */
-#define XXX_LOCK_USAGE_STATES		(1+2*4)
+#define XXX_LOCK_USAGE_STATES		2
+#define LOCK_TRACE_STATES		(XXX_LOCK_USAGE_STATES*4 + 2)
 
 /*
  * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
@@ -106,7 +110,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	const struct lock_trace		*usage_traces[XXX_LOCK_USAGE_STATES];
+	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
 	/*
 	 * Generation counter, when doing certain classes of graph walking,

kernel/locking/lockdep.c

@@ -585,6 +585,8 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
+	[LOCK_USED_READ] = "INITIAL READ USE",
+	/* abused as string storage for verify_lock_unused() */
 	[LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
@@ -1939,7 +1941,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 #endif
 	printk(KERN_CONT " {\n");
 
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+	for (bit = 0; bit < LOCK_TRACE_STATES; bit++) {
 		if (class->usage_mask & (1 << bit)) {
 			int len = depth;
 
@@ -3969,7 +3971,7 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int old_mask, new_mask, ret = 1;
+	unsigned int new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
@@ -3996,30 +3998,26 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	if (unlikely(hlock_class(this)->usage_mask & new_mask))
 		goto unlock;
 
-	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
-	/*
-	 * Save one usage_traces[] entry and map both LOCK_USED and
-	 * LOCK_USED_READ onto the same entry.
-	 */
-	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
-		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
-			goto unlock;
-		new_bit = LOCK_USED;
+	if (new_bit < LOCK_TRACE_STATES) {
+		if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
+			return 0;
 	}
 
-	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
-		return 0;
-
 	switch (new_bit) {
+	case 0 ... LOCK_USED-1:
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
+			return 0;
+		break;
+
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
+
 	default:
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
+		break;
 	}
 
 unlock:

kernel/locking/lockdep_internals.h

@@ -20,9 +20,12 @@ enum lock_usage_bit {
 #undef LOCKDEP_STATE
 	LOCK_USED,
 	LOCK_USED_READ,
-	LOCK_USAGE_STATES
+	LOCK_USAGE_STATES,
 };
 
+/* states after LOCK_USED_READ are not traced and printed */
+static_assert(LOCK_TRACE_STATES == LOCK_USAGE_STATES);
+
 #define LOCK_USAGE_READ_MASK 1
 #define LOCK_USAGE_DIR_MASK  2
 #define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
@@ -121,7 +124,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
-#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
+#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
 
 extern void get_usage_chars(struct lock_class *class,
 			    char usage[LOCK_USAGE_CHARS]);