PCI AER: support Multiple Error Received and no error source id

Based on PCI Express AER specs, a root port might receive multiple
TLP errors while it could only save a correctable error source id
and an uncorrectable error source id at the same time. In addition,
some root port hardware might be unable to provide a correct source
id, i.e., the source id, or the bus id part of the source id provided
by root port might be equal to 0.

The patchset implements the support in kernel by searching the device
tree under the root port.

Patch 1 changes parameter cb of function pci_walk_bus to return a value.
When cb return non-zero, pci_walk_bus stops more searching on the
device tree.

Reviewed-by: Andrew Patterson <[e-mail]>
Signed-off-by: Zhang Yanmin <[e-mail]>
Signed-off-by: Jesse Barnes <[e-mail]>

arch/powerpc/platforms/pseries/eeh_driver.c

···
  * passed back in "userdata".
  */
 
-static void eeh_report_error(struct pci_dev *dev, void *userdata)
+static int eeh_report_error(struct pci_dev *dev, void *userdata)
 {
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver = dev->driver;
···
 	dev->error_state = pci_channel_io_frozen;
 
 	if (!driver)
-		return;
+		return 0;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->error_detected)
-		return;
+		return 0;
 
 	rc = driver->err_handler->error_detected (dev, pci_channel_io_frozen);
 
 	/* A driver that needs a reset trumps all others */
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+	return 0;
 }
 
 /**
···
  * Cumulative response passed back in "userdata".
  */
 
-static void eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
+static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
 {
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver = dev->driver;
···
 	if (!driver ||
 	    !driver->err_handler ||
 	    !driver->err_handler->mmio_enabled)
-		return;
+		return 0;
 
 	rc = driver->err_handler->mmio_enabled (dev);
 
 	/* A driver that needs a reset trumps all others */
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+	return 0;
 }
 
 /**
  * eeh_report_reset - tell device that slot has been reset
  */
 
-static void eeh_report_reset(struct pci_dev *dev, void *userdata)
+static int eeh_report_reset(struct pci_dev *dev, void *userdata)
 {
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver = dev->driver;
 
 	if (!driver)
-		return;
+		return 0;
 
 	dev->error_state = pci_channel_io_normal;
 
···
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->slot_reset)
-		return;
+		return 0;
 
 	rc = driver->err_handler->slot_reset(dev);
 	if ((*res == PCI_ERS_RESULT_NONE) ||
 	    (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
 	if (*res == PCI_ERS_RESULT_DISCONNECT &&
 	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+
+	return 0;
 }
 
 /**
  * eeh_report_resume - tell device to resume normal operations
  */
 
-static void eeh_report_resume(struct pci_dev *dev, void *userdata)
+static int eeh_report_resume(struct pci_dev *dev, void *userdata)
 {
 	struct pci_driver *driver = dev->driver;
 
 	dev->error_state = pci_channel_io_normal;
 
 	if (!driver)
-		return;
+		return 0;
 
 	eeh_enable_irq(dev);
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->resume)
-		return;
+		return 0;
 
 	driver->err_handler->resume(dev);
+
+	return 0;
 }
 
 /**
···
  * dead, and that no further recovery attempts will be made on it.
  */
 
-static void eeh_report_failure(struct pci_dev *dev, void *userdata)
+static int eeh_report_failure(struct pci_dev *dev, void *userdata)
 {
 	struct pci_driver *driver = dev->driver;
 
 	dev->error_state = pci_channel_io_perm_failure;
 
 	if (!driver)
-		return;
+		return 0;
 
 	eeh_disable_irq(dev);
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->error_detected)
-		return;
+		return 0;
 
 	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
+
+	return 0;
 }
 
 /* ------------------------------------------------------- */

drivers/pci/bus.c

···
  *  Walk the given bus, including any bridged devices
  *  on buses under this bus.  Call the provided callback
  *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ *
  */
-void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *),
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
 	struct list_head *next;
+	int retval;
 
 	bus = top;
 	down_read(&pci_bus_sem);
···
 
 		/* Run device routines with the device locked */
 		down(&dev->dev.sem);
-		cb(dev, userdata);
+		retval = cb(dev, userdata);
 		up(&dev->dev.sem);
+		if (retval)
+			break;
 	}
 	up_read(&pci_bus_sem);
 }

drivers/pci/pcie/aer/aerdrv_core.c

···
 #endif  /*  0  */
 
 
-static void set_device_error_reporting(struct pci_dev *dev, void *data)
+static int set_device_error_reporting(struct pci_dev *dev, void *data)
 {
 	bool enable = *((bool *)data);
 
···
 
 	if (enable)
 		pcie_set_ecrc_checking(dev);
+
+	return 0;
 }
 
 /**
···
 	return NULL;
 }
 
-static void report_error_detected(struct pci_dev *dev, void *data)
+static int report_error_detected(struct pci_dev *dev, void *data)
 {
 	pci_ers_result_t vote;
 	struct pci_error_handlers *err_handler;
···
 				   dev->driver ?
 				   "no AER-aware driver" : "no driver");
 		}
-		return;
+		return 0;
 	}
 
 	err_handler = dev->driver->err_handler;
 	vote = err_handler->error_detected(dev, result_data->state);
 	result_data->result = merge_result(result_data->result, vote);
-	return;
+	return 0;
 }
 
-static void report_mmio_enabled(struct pci_dev *dev, void *data)
+static int report_mmio_enabled(struct pci_dev *dev, void *data)
 {
 	pci_ers_result_t vote;
 	struct pci_error_handlers *err_handler;
···
 	if (!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->mmio_enabled)
-		return;
+		return 0;
 
 	err_handler = dev->driver->err_handler;
 	vote = err_handler->mmio_enabled(dev);
 	result_data->result = merge_result(result_data->result, vote);
-	return;
+	return 0;
 }
 
-static void report_slot_reset(struct pci_dev *dev, void *data)
+static int report_slot_reset(struct pci_dev *dev, void *data)
 {
 	pci_ers_result_t vote;
 	struct pci_error_handlers *err_handler;
···
 	if (!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->slot_reset)
-		return;
+		return 0;
 
 	err_handler = dev->driver->err_handler;
 	vote = err_handler->slot_reset(dev);
 	result_data->result = merge_result(result_data->result, vote);
-	return;
+	return 0;
 }
 
-static void report_resume(struct pci_dev *dev, void *data)
+static int report_resume(struct pci_dev *dev, void *data)
 {
 	struct pci_error_handlers *err_handler;
 
···
 	if (!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->resume)
-		return;
+		return 0;
 
 	err_handler = dev->driver->err_handler;
 	err_handler->resume(dev);
-	return;
+	return 0;
 }
 
 /**
···
 static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 	enum pci_channel_state state,
 	char *error_mesg,
-	void (*cb)(struct pci_dev *, void *))
+	int (*cb)(struct pci_dev *, void *))
 {
 	struct aer_broadcast_data result_data;
 

include/linux/pci.h

···
 int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
 		    int pass);
 
-void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *),
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata);
 int pci_cfg_space_size_ext(struct pci_dev *dev);
 int pci_cfg_space_size(struct pci_dev *dev);