debugobjects: Various backports

@@ -339,6 +339,16 @@ extern void lock_unpin_lock(struct lockd
 #define lockdep_repin_lock(l,c)	lock_repin_lock(&(l)->dep_map, (c))
 #define lockdep_unpin_lock(l,c)	lock_unpin_lock(&(l)->dep_map, (c))
 
+/*
+ * Must use lock_map_aquire_try() with override maps to avoid
+ * lockdep thinking they participate in the block chain.
+ */
+#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type)	\
+	struct lockdep_map _name = {			\
+		.name = #_name "-wait-type-override",	\
+		.wait_type_inner = _wait_type,		\
+		.lock_type = LD_LOCK_WAIT_OVERRIDE, }
+
 #else /* !CONFIG_LOCKDEP */
 
 static inline void lockdep_init_task(struct task_struct *task)

@@ -427,6 +437,9 @@ extern int lockdep_is_held(const void *)
 #define lockdep_repin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 #define lockdep_unpin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 
+#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type)	\
+	struct lockdep_map __maybe_unused _name = {}
+
 #endif /* !LOCKDEP */
 
 enum xhlock_context_t {

@@ -552,6 +565,7 @@ do {									\
 #define rwsem_release(l, i)			lock_release(l, i)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
+#define lock_map_acquire_try(l)			lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_tryread(l)		lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_)
 #define lock_map_release(l)			lock_release(l, _THIS_IP_)

@@ -33,6 +33,7 @@ enum lockdep_wait_type {
 enum lockdep_lock_type {
 	LD_LOCK_NORMAL = 0,	/* normal, catch all */
 	LD_LOCK_PERCPU,		/* percpu */
+	LD_LOCK_WAIT_OVERRIDE,	/* annotation */
 	LD_LOCK_MAX,
 };
 

@@ -2245,6 +2245,9 @@ static inline bool usage_match(struct lo
 
 static inline bool usage_skip(struct lock_list *entry, void *mask)
 {
+	if (entry->class->lock_type == LD_LOCK_NORMAL)
+		return false;
+
 	/*
 	 * Skip local_lock() for irq inversion detection.
 	 *

@@ -2271,14 +2274,16 @@ static inline bool usage_skip(struct loc
 	 * As a result, we will skip local_lock(), when we search for irq
 	 * inversion bugs.
 	 */
-	if (entry->class->lock_type == LD_LOCK_PERCPU) {
-		if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
-			return false;
+	if (entry->class->lock_type == LD_LOCK_PERCPU &&
+	    DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+		return false;
 
-		return true;
-	}
+	/*
+	 * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually
+	 * a lock and only used to override the wait_type.
+	 */
 
-	return false;
+	return true;
 }
 
 /*

@@ -4745,7 +4750,8 @@ static int check_wait_context(struct tas
 
 	for (; depth < curr->lockdep_depth; depth++) {
 		struct held_lock *prev = curr->held_locks + depth;
-		u8 prev_inner = hlock_class(prev)->wait_type_inner;
+		struct lock_class *class = hlock_class(prev);
+		u8 prev_inner = class->wait_type_inner;
 
 		if (prev_inner) {
 			/*

@@ -4755,6 +4761,14 @@ static int check_wait_context(struct tas
 			 * Also due to trylocks.
 			 */
 			curr_inner = min(curr_inner, prev_inner);
+
+			/*
+			 * Allow override for annotations -- this is typically
+			 * only valid/needed for code that only exists when
+			 * CONFIG_PREEMPT_RT=n.
+			 */
+			if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE))
+				curr_inner = prev_inner;
 		}
 	}
 

@@ -601,10 +601,21 @@ static void debug_objects_fill_pool(void
 {
 	/*
 	 * On RT enabled kernels the pool refill must happen in preemptible
-	 * context:
+	 * context -- for !RT kernels we rely on the fact that spinlock_t and
+	 * raw_spinlock_t are basically the same type and this lock-type
+	 * inversion works just fine.
 	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible())
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+		/*
+		 * Annotate away the spinlock_t inside raw_spinlock_t warning
+		 * by temporarily raising the wait-type to WAIT_SLEEP, matching
+		 * the preemptible() condition above.
+		 */
+		static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP);
+		lock_map_acquire_try(&fill_pool_map);
 		fill_pool();
+		lock_map_release(&fill_pool_map);
+	}
 }
 
 static void

@@ -605,7 +605,7 @@ static void debug_objects_fill_pool(void
 	 * raw_spinlock_t are basically the same type and this lock-type
 	 * inversion works just fine.
 	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible() || system_state < SYSTEM_SCHEDULING) {
 		/*
 		 * Annotate away the spinlock_t inside raw_spinlock_t warning
 		 * by temporarily raising the wait-type to WAIT_SLEEP, matching

@@ -608,10 +608,10 @@ static void debug_objects_fill_pool(void
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible() || system_state < SYSTEM_SCHEDULING) {
 		/*
 		 * Annotate away the spinlock_t inside raw_spinlock_t warning
-		 * by temporarily raising the wait-type to WAIT_SLEEP, matching
+		 * by temporarily raising the wait-type to LD_WAIT_CONFIG, matching
 		 * the preemptible() condition above.
 		 */
-		static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP);
+		static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_CONFIG);
 		lock_map_acquire_try(&fill_pool_map);
 		fill_pool();
 		lock_map_release(&fill_pool_map);

@@ -596,15 +596,25 @@ static struct debug_obj *lookup_object_o
 	return NULL;
 }
 
+static inline bool debug_objects_is_pi_blocked_on(void)
+{
+#ifdef CONFIG_RT_MUTEXES
+	return current->pi_blocked_on != NULL;
+#else
+	return false;
+#endif
+}
+
 static void debug_objects_fill_pool(void)
 {
 	/*
 	 * On RT enabled kernels the pool refill must happen in preemptible
-	 * context -- for !RT kernels we rely on the fact that spinlock_t and
-	 * raw_spinlock_t are basically the same type and this lock-type
-	 * inversion works just fine.
+	 * context and not enqueued on an rt_mutex -- for !RT kernels we rely
+	 * on the fact that spinlock_t and raw_spinlock_t are basically the
+	 * same type and this lock-type inversion works just fine.
 	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible() || system_state < SYSTEM_SCHEDULING) {
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || system_state < SYSTEM_SCHEDULING ||
+	    (preemptible() && !debug_objects_is_pi_blocked_on())) {
 		/*
 		 * Annotate away the spinlock_t inside raw_spinlock_t warning
 		 * by temporarily raising the wait-type to LD_WAIT_CONFIG, matching

@@ -606,20 +606,48 @@ static inline bool debug_objects_is_pi_b
 #endif
 }
 
-static void debug_objects_fill_pool(void)
+static inline bool can_fill_pool(void)
 {
 	/*
-	 * On RT enabled kernels the pool refill must happen in preemptible
-	 * context and not enqueued on an rt_mutex -- for !RT kernels we rely
-	 * on the fact that spinlock_t and raw_spinlock_t are basically the
-	 * same type and this lock-type inversion works just fine.
+	 * On !RT enabled kernels there are no restrictions and spinlock_t and
+	 * raw_spinlock_t are the same types.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		return true;
+
+	/*
+	 * On RT enabled kernels, the task must not be blocked on a lock as
+	 * that could corrupt the PI state when blocking on a lock in the
+	 * allocation path.
+	 */
+	if (debug_objects_is_pi_blocked_on())
+		return false;
+
+	/*
+	 * On RT enabled kernels the pool refill should happen in preemptible
+	 * context.
 	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || system_state < SYSTEM_SCHEDULING ||
-	    (preemptible() && !debug_objects_is_pi_blocked_on())) {
+	if (preemptible())
+		return true;
+
+	/*
+	 * Though during system boot before scheduling is set up, preemption is
+	 * disabled and the pool can get exhausted. Before scheduling is active
+	 * a task cannot be blocked on a sleeping lock, but it might hold a lock
+	 * and if interrupted then hard interrupt context might run into a lock
+	 * inversion. So exclude hard interrupt context from allocations before
+	 * scheduling is active.
+	 */
+	return system_state < SYSTEM_SCHEDULING && !in_hardirq();
+}
+
+static void debug_objects_fill_pool(void)
+{
+	if (can_fill_pool()) {
 		/*
 		 * Annotate away the spinlock_t inside raw_spinlock_t warning
 		 * by temporarily raising the wait-type to LD_WAIT_CONFIG, matching
-		 * the preemptible() condition above.
+		 * the preemptible() condition in can_fill_pool().
 		 */
 		static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_CONFIG);
 		lock_map_acquire_try(&fill_pool_map);