cxl: Prove CXL locking

When CONFIG_PROVE_LOCKING is enabled the 'struct device' definition gets
an additional mutex that is not clobbered by
lockdep_set_novalidate_class() like the typical device_lock(). This
allows for local annotation of subsystem locks with mutex_lock_nested()
per the subsystem's object/lock hierarchy. For CXL, this primarily needs
the ability to lock ports by depth and child objects of ports by their
parent parent-port lock.

Reviewed-by: Jonathan Cameron <[e-mail]>
Reviewed-by: Ben Widawsky <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Dan Williams <[e-mail]>

drivers/cxl/acpi.c

···
 {
 	struct cxl_dport *dport;
 
-	device_lock(&port->dev);
+	cxl_device_lock(&port->dev);
 	list_for_each_entry(dport, &port->dports, list)
 		if (dport->dport == dev) {
-			device_unlock(&port->dev);
+			cxl_device_unlock(&port->dev);
 			return dport;
 		}
 
-	device_unlock(&port->dev);
+	cxl_device_unlock(&port->dev);
 	return NULL;
 }
 
···
 	if (IS_ERR(cxld))
 		return PTR_ERR(cxld);
 
-	device_lock(&port->dev);
+	cxl_device_lock(&port->dev);
 	dport = list_first_entry(&port->dports, typeof(*dport), list);
-	device_unlock(&port->dev);
+	cxl_device_unlock(&port->dev);
 
 	single_port_map[0] = dport->port_id;
 

drivers/cxl/core/pmem.c

···
 	 * work to flush. Once the state has been changed to 'dead' then no new
 	 * work can be queued by user-triggered bind.
 	 */
-	device_lock(&cxl_nvb->dev);
+	cxl_device_lock(&cxl_nvb->dev);
 	flush = cxl_nvb->state != CXL_NVB_NEW;
 	cxl_nvb->state = CXL_NVB_DEAD;
-	device_unlock(&cxl_nvb->dev);
+	cxl_device_unlock(&cxl_nvb->dev);
 
 	/*
 	 * Even though the device core will trigger device_release_driver()

drivers/cxl/core/port.c

···
 	ssize_t offset = 0;
 	int i, rc = 0;
 
-	device_lock(dev);
+	cxl_device_lock(dev);
 	for (i = 0; i < cxld->interleave_ways; i++) {
 		struct cxl_dport *dport = cxld->target[i];
 		struct cxl_dport *next = NULL;
···
 			break;
 		offset += rc;
 	}
-	device_unlock(dev);
+	cxl_device_unlock(dev);
 
 	if (rc < 0)
 		return rc;
···
 }
 EXPORT_SYMBOL_NS_GPL(is_root_decoder, CXL);
 
+bool is_cxl_decoder(struct device *dev)
+{
+	return dev->type->release == cxl_decoder_release;
+}
+EXPORT_SYMBOL_NS_GPL(is_cxl_decoder, CXL);
+
 struct cxl_decoder *to_cxl_decoder(struct device *dev)
 {
 	if (dev_WARN_ONCE(dev, dev->type->release != cxl_decoder_release,
···
 	struct cxl_port *port = to_cxl_port(dev);
 	struct cxl_dport *dport, *_d;
 
-	device_lock(dev);
+	cxl_device_lock(dev);
 	list_for_each_entry_safe(dport, _d, &port->dports, list)
 		cxl_dport_release(dport);
-	device_unlock(dev);
+	cxl_device_unlock(dev);
 	ida_free(&cxl_port_ida, port->id);
 	kfree(port);
 }
···
 	.groups = cxl_port_attribute_groups,
 };
 
+bool is_cxl_port(struct device *dev)
+{
+	return dev->type == &cxl_port_type;
+}
+EXPORT_SYMBOL_NS_GPL(is_cxl_port, CXL);
+
 struct cxl_port *to_cxl_port(struct device *dev)
 {
 	if (dev_WARN_ONCE(dev, dev->type != &cxl_port_type,
···
 		return NULL;
 	return container_of(dev, struct cxl_port, dev);
 }
+EXPORT_SYMBOL_NS_GPL(to_cxl_port, CXL);
 
 static void unregister_port(void *_port)
 {
 	struct cxl_port *port = _port;
 	struct cxl_dport *dport;
 
-	device_lock(&port->dev);
+	cxl_device_lock(&port->dev);
 	list_for_each_entry(dport, &port->dports, list) {
 		char link_name[CXL_TARGET_STRLEN];
 
···
 			continue;
 		sysfs_remove_link(&port->dev.kobj, link_name);
 	}
-	device_unlock(&port->dev);
+	cxl_device_unlock(&port->dev);
 	device_unregister(&port->dev);
 }
 
···
 {
 	struct cxl_dport *dup;
 
-	device_lock(&port->dev);
+	cxl_device_lock(&port->dev);
 	dup = find_dport(port, new->port_id);
 	if (dup)
 		dev_err(&port->dev,
···
 			dev_name(dup->dport));
 	else
 		list_add_tail(&new->list, &port->dports);
-	device_unlock(&port->dev);
+	cxl_device_unlock(&port->dev);
 
 	return dup ? -EEXIST : 0;
 }
···
 	if (!target_map)
 		return 0;
 
-	device_lock(&port->dev);
+	cxl_device_lock(&port->dev);
 	if (list_empty(&port->dports)) {
 		rc = -EINVAL;
 		goto out_unlock;
···
 	}
 
 out_unlock:
-	device_unlock(&port->dev);
+	cxl_device_unlock(&port->dev);
 
 	return rc;
 }
···
 
 static int cxl_bus_probe(struct device *dev)
 {
-	return to_cxl_drv(dev->driver)->probe(dev);
+	int rc;
+
+	/*
+	 * Take the CXL nested lock since the driver core only holds
+	 * @dev->mutex and not @dev->lockdep_mutex.
+	 */
+	cxl_nested_lock(dev);
+	rc = to_cxl_drv(dev->driver)->probe(dev);
+	cxl_nested_unlock(dev);
+
+	return rc;
 }
 
 static void cxl_bus_remove(struct device *dev)
 {
 	struct cxl_driver *cxl_drv = to_cxl_drv(dev->driver);
 
+	cxl_nested_lock(dev);
 	if (cxl_drv->remove)
 		cxl_drv->remove(dev);
+	cxl_nested_unlock(dev);
 }
 
 struct bus_type cxl_bus_type = {

drivers/cxl/cxl.h

···
 	return port->uport == port->dev.parent;
 }
 
+bool is_cxl_port(struct device *dev);
 struct cxl_port *to_cxl_port(struct device *dev);
 struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport,
 				   resource_size_t component_reg_phys,
···
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 bool is_root_decoder(struct device *dev);
+bool is_cxl_decoder(struct device *dev);
 struct cxl_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 					   unsigned int nr_targets);
 struct cxl_decoder *cxl_switch_decoder_alloc(struct cxl_port *port,
···
  */
 #ifndef __mock
 #define __mock static
+#endif
+
+#ifdef CONFIG_PROVE_CXL_LOCKING
+enum cxl_lock_class {
+	CXL_ANON_LOCK,
+	CXL_NVDIMM_LOCK,
+	CXL_NVDIMM_BRIDGE_LOCK,
+	CXL_PORT_LOCK,
+	/*
+	 * Be careful to add new lock classes here, CXL_PORT_LOCK is
+	 * extended by the port depth, so a maximum CXL port topology
+	 * depth would need to be defined first.
+	 */
+};
+
+static inline void cxl_nested_lock(struct device *dev)
+{
+	if (is_cxl_port(dev)) {
+		struct cxl_port *port = to_cxl_port(dev);
+
+		mutex_lock_nested(&dev->lockdep_mutex,
+				  CXL_PORT_LOCK + port->depth);
+	} else if (is_cxl_decoder(dev)) {
+		struct cxl_port *port = to_cxl_port(dev->parent);
+
+		/*
+		 * A decoder is the immediate child of a port, so set
+		 * its lock class equal to other child device siblings.
+		 */
+		mutex_lock_nested(&dev->lockdep_mutex,
+				  CXL_PORT_LOCK + port->depth + 1);
+	} else if (is_cxl_nvdimm_bridge(dev))
+		mutex_lock_nested(&dev->lockdep_mutex, CXL_NVDIMM_BRIDGE_LOCK);
+	else if (is_cxl_nvdimm(dev))
+		mutex_lock_nested(&dev->lockdep_mutex, CXL_NVDIMM_LOCK);
+	else
+		mutex_lock_nested(&dev->lockdep_mutex, CXL_ANON_LOCK);
+}
+
+static inline void cxl_nested_unlock(struct device *dev)
+{
+	mutex_unlock(&dev->lockdep_mutex);
+}
+
+static inline void cxl_device_lock(struct device *dev)
+{
+	/*
+	 * For double lock errors the lockup will happen before lockdep
+	 * warns at cxl_nested_lock(), so assert explicitly.
+	 */
+	lockdep_assert_not_held(&dev->lockdep_mutex);
+
+	device_lock(dev);
+	cxl_nested_lock(dev);
+}
+
+static inline void cxl_device_unlock(struct device *dev)
+{
+	cxl_nested_unlock(dev);
+	device_unlock(dev);
+}
+#else
+static inline void cxl_nested_lock(struct device *dev)
+{
+}
+
+static inline void cxl_nested_unlock(struct device *dev)
+{
+}
+
+static inline void cxl_device_lock(struct device *dev)
+{
+	device_lock(dev);
+}
+
+static inline void cxl_device_unlock(struct device *dev)
+{
+	device_unlock(dev);
+}
 #endif
 #endif /* __CXL_H__ */

drivers/cxl/pmem.c

···
 	if (!cxl_nvb)
 		return -ENXIO;
 
-	device_lock(&cxl_nvb->dev);
+	cxl_device_lock(&cxl_nvb->dev);
 	if (!cxl_nvb->nvdimm_bus) {
 		rc = -ENXIO;
 		goto out;
···
 	dev_set_drvdata(dev, nvdimm);
 	rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm);
 out:
-	device_unlock(&cxl_nvb->dev);
+	cxl_device_unlock(&cxl_nvb->dev);
 	put_device(&cxl_nvb->dev);
 
 	return rc;
···
 	struct nvdimm_bus *victim_bus = NULL;
 	bool release = false, rescan = false;
 
-	device_lock(&cxl_nvb->dev);
+	cxl_device_lock(&cxl_nvb->dev);
 	switch (cxl_nvb->state) {
 	case CXL_NVB_ONLINE:
 		if (!online_nvdimm_bus(cxl_nvb)) {
···
 	default:
 		break;
 	}
-	device_unlock(&cxl_nvb->dev);
+	cxl_device_unlock(&cxl_nvb->dev);
 
 	if (release)
 		device_release_driver(&cxl_nvb->dev);
···
 		return 0;
 
 	cxl_nvb = to_cxl_nvdimm_bridge(dev);
-	device_lock(dev);
+	cxl_device_lock(dev);
 	cxl_nvb->state = CXL_NVB_NEW;
-	device_unlock(dev);
+	cxl_device_unlock(dev);
 
 	return 0;
 }

drivers/nvdimm/nd-core.h

···
 }
 #endif
 
-#ifdef CONFIG_PROVE_LOCKING
+#ifdef CONFIG_PROVE_NVDIMM_LOCKING
 extern struct class *nd_class;
 
 enum {

lib/Kconfig.debug

···
 	  include the IPI handler function currently executing (if any)
 	  and relevant stack traces.
 
+choice
+	prompt "Lock debugging: prove subsystem device_lock() correctness"
+	depends on PROVE_LOCKING
+	help
+	  For subsystems that have instrumented their usage of the device_lock()
+	  with nested annotations, enable lock dependency checking. The locking
+	  hierarchy 'subclass' identifiers are not compatible across
+	  sub-systems, so only one can be enabled at a time.
+
+config PROVE_NVDIMM_LOCKING
+	bool "NVDIMM"
+	depends on LIBNVDIMM
+	help
+	  Enable lockdep to validate nd_device_lock() usage.
+
+config PROVE_CXL_LOCKING
+	bool "CXL"
+	depends on CXL_BUS
+	help
+	  Enable lockdep to validate cxl_device_lock() usage.
+
+endchoice
+
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS