[v13,4/6] PCI/DPC: Unify and plumb error handling into DPC

Message ID 1523284914-2037-5-git-send-email-poza@codeaurora.org
State Superseded
Delegated to: Bjorn Helgaas
Headers show
Series
  • Address error and recovery for AER and DPC
Related show

Commit Message

Oza Pawandeep April 9, 2018, 2:41 p.m.
Current DPC driver does not do recovery, e.g. calling end-point's driver's
callbacks, which sanitize the sw.

DPC driver implements link_reset callback, and calls pci_do_recovery().

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>

Comments

Keith Busch April 9, 2018, 11:29 p.m. | #1
On Mon, Apr 09, 2018 at 10:41:52AM -0400, Oza Pawandeep wrote:
> +static int find_dpc_dev_iter(struct device *device, void *data)
> +{
> +	struct pcie_port_service_driver *service_driver;
> +	struct device **dev;
> +
> +	dev = (struct device **) data;
> +
> +	if (device->bus == &pcie_port_bus_type && device->driver) {
> +		service_driver = to_service_driver(device->driver);
> +		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
> +			*dev = device;
> +			return 1;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
> +static struct device *pci_find_dpc_dev(struct pci_dev *pdev)
> +{
> +	struct device *dev = NULL;
> +
> +	device_for_each_child(&pdev->dev, &dev, find_dpc_dev_iter);
> +
> +	return dev;
> +}

The only caller of this doesn't seem to care to use struct device. This
should probably just extract struct dpc_dev directly from in here.
Sinan Kaya April 9, 2018, 11:51 p.m. | #2
On 4/9/2018 7:29 PM, Keith Busch wrote:
> On Mon, Apr 09, 2018 at 10:41:52AM -0400, Oza Pawandeep wrote:
>> +static int find_dpc_dev_iter(struct device *device, void *data)
>> +{
>> +	struct pcie_port_service_driver *service_driver;
>> +	struct device **dev;
>> +
>> +	dev = (struct device **) data;
>> +
>> +	if (device->bus == &pcie_port_bus_type && device->driver) {
>> +		service_driver = to_service_driver(device->driver);
>> +		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
>> +			*dev = device;
>> +			return 1;
>> +		}
>> +	}
>> +
>> +	return 0;
>> +}
>> +
>> +static struct device *pci_find_dpc_dev(struct pci_dev *pdev)
>> +{
>> +	struct device *dev = NULL;
>> +
>> +	device_for_each_child(&pdev->dev, &dev, find_dpc_dev_iter);
>> +
>> +	return dev;
>> +}
> 
> The only caller of this doesn't seem to care to use struct device. This
> should probably just extract struct dpc_dev directly from in here.
> 

Bjorn wants to kill the port service driver infrastructure but that is a much
bigger task. 

How do we obtain the DPC object from the parent object directly? Each port
service driver object is a children.
Sinan Kaya April 10, 2018, 12:05 a.m. | #3
On 4/9/2018 7:51 PM, Sinan Kaya wrote:
> On 4/9/2018 7:29 PM, Keith Busch wrote:
>> On Mon, Apr 09, 2018 at 10:41:52AM -0400, Oza Pawandeep wrote:
>>> +static int find_dpc_dev_iter(struct device *device, void *data)
>>> +{
>>> +	struct pcie_port_service_driver *service_driver;
>>> +	struct device **dev;
>>> +
>>> +	dev = (struct device **) data;
>>> +
>>> +	if (device->bus == &pcie_port_bus_type && device->driver) {
>>> +		service_driver = to_service_driver(device->driver);
>>> +		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
>>> +			*dev = device;
>>> +			return 1;
>>> +		}
>>> +	}
>>> +
>>> +	return 0;
>>> +}
>>> +
>>> +static struct device *pci_find_dpc_dev(struct pci_dev *pdev)
>>> +{
>>> +	struct device *dev = NULL;
>>> +
>>> +	device_for_each_child(&pdev->dev, &dev, find_dpc_dev_iter);
>>> +
>>> +	return dev;
>>> +}
>>
>> The only caller of this doesn't seem to care to use struct device. This
>> should probably just extract struct dpc_dev directly from in here.
>>
> 
> Bjorn wants to kill the port service driver infrastructure but that is a much
> bigger task. 
> 
> How do we obtain the DPC object from the parent object directly? Each port
> service driver object is a children.
> 

How about implementing pcie_port_find_service_dev() as a follow up patch
to "PCI/PORTDRV: Implement generic find service" similar to what was done for
pcie_port_find_service()?

Patch

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 98aeec4..d02e029 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -19,6 +19,7 @@ 
 #include <linux/aer.h>
 #include <linux/pcieport_if.h>
 #include "portdrv.h"
+#include "./../pci.h"
 
 struct aer_broadcast_data {
 	enum pci_channel_state state;
@@ -179,11 +180,12 @@  static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static pci_ers_result_t reset_link(struct pci_dev *dev)
+static pci_ers_result_t reset_link(struct pci_dev *dev, int severity)
 {
 	struct pci_dev *udev;
 	pci_ers_result_t status;
 	struct pcie_port_service_driver *driver = NULL;
+	u32 service;
 
 	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
 		/* Reset this port for all subordinates */
@@ -193,8 +195,12 @@  static pci_ers_result_t reset_link(struct pci_dev *dev)
 		udev = dev->bus->self;
 	}
 
-	/* Use the aer driver of the component firstly */
-	driver = pcie_port_find_service(udev, PCIE_PORT_SERVICE_AER);
+	if (severity == DPC_FATAL)
+		service = PCIE_PORT_SERVICE_DPC;
+	else
+		service = PCIE_PORT_SERVICE_AER;
+
+	driver = pcie_port_find_service(udev, service);
 
 	if (driver && driver->reset_link) {
 		status = driver->reset_link(udev);
@@ -281,7 +287,8 @@  void pcie_do_recovery(struct pci_dev *dev, int severity)
 	pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
 	enum pci_channel_state state;
 
-	if (severity == AER_FATAL)
+	if ((severity == AER_FATAL) ||
+	    (severity == DPC_FATAL))
 		state = pci_channel_io_frozen;
 	else
 		state = pci_channel_io_normal;
@@ -291,8 +298,9 @@  void pcie_do_recovery(struct pci_dev *dev, int severity)
 			"error_detected",
 			report_error_detected);
 
-	if (severity == AER_FATAL) {
-		result = reset_link(dev);
+	if ((severity == AER_FATAL) ||
+	    (severity == DPC_FATAL)) {
+		result = reset_link(dev, severity);
 		if (result != PCI_ERS_RESULT_RECOVERED)
 			goto failed;
 	}
diff --git a/drivers/pci/pcie/pcie-dpc.c b/drivers/pci/pcie/pcie-dpc.c
index 38e40c6..517c8b4 100644
--- a/drivers/pci/pcie/pcie-dpc.c
+++ b/drivers/pci/pcie/pcie-dpc.c
@@ -13,6 +13,7 @@ 
 #include <linux/pcieport_if.h>
 #include "../pci.h"
 #include "aer/aerdrv.h"
+#include "portdrv.h"
 
 struct dpc_dev {
 	struct pcie_device	*dev;
@@ -45,6 +46,33 @@  static const char * const rp_pio_error_string[] = {
 	"Memory Request Completion Timeout",		 /* Bit Position 18 */
 };
 
+static int find_dpc_dev_iter(struct device *device, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+	struct device **dev;
+
+	dev = (struct device **) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		service_driver = to_service_driver(device->driver);
+		if (service_driver->service == PCIE_PORT_SERVICE_DPC) {
+			*dev = device;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static struct device *pci_find_dpc_dev(struct pci_dev *pdev)
+{
+	struct device *dev = NULL;
+
+	device_for_each_child(&pdev->dev, &dev, find_dpc_dev_iter);
+
+	return dev;
+}
+
 static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 {
 	unsigned long timeout = jiffies + HZ;
@@ -82,12 +110,25 @@  static void dpc_wait_link_inactive(struct dpc_dev *dpc)
 		dev_warn(dev, "Link state not disabled for DPC event\n");
 }
 
-static void dpc_work(struct work_struct *work)
+/**
+ * dpc_reset_link - reset link DPC routine
+ * @pdev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver when performing link reset at Root Port.
+ */
+static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
-	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
-	struct pci_dev *dev, *temp, *pdev = dpc->dev->port;
 	struct pci_bus *parent = pdev->subordinate;
-	u16 cap = dpc->cap_pos, ctl;
+	struct pci_dev *dev, *temp;
+	struct dpc_dev *dpc;
+	struct pcie_device *pciedev;
+	struct device *devdpc;
+	u16 cap, ctl;
+
+	devdpc = pci_find_dpc_dev(pdev);
+	pciedev = to_pcie_device(devdpc);
+	dpc = get_service_data(pciedev);
+	cap = dpc->cap_pos;
 
 	pci_lock_rescan_remove();
 	list_for_each_entry_safe_reverse(dev, temp, &parent->devices,
@@ -104,21 +145,31 @@  static void dpc_work(struct work_struct *work)
 
 	dpc_wait_link_inactive(dpc);
 	if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc))
-		return;
+		return PCI_ERS_RESULT_DISCONNECT;
 	if (dpc->rp_extensions && dpc->rp_pio_status) {
 		pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS,
 				       dpc->rp_pio_status);
 		dpc->rp_pio_status = 0;
 	}
 
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
+	pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_STATUS,
 		PCI_EXP_DPC_STATUS_TRIGGER | PCI_EXP_DPC_STATUS_INTERRUPT);
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl);
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL,
 			      ctl | PCI_EXP_DPC_CTL_INT_EN);
+
+	return PCI_ERS_RESULT_RECOVERED;
 }
 
+static void dpc_work(struct work_struct *work)
+{
+	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
+	struct pci_dev *pdev = dpc->dev->port;
+
+	/* From DPC point of view error is always FATAL. */
+	pcie_do_recovery(pdev, DPC_FATAL);
+}
 static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 {
 	struct device *dev = &dpc->dev->device;
@@ -297,6 +348,7 @@  static struct pcie_port_service_driver dpcdriver = {
 	.service	= PCIE_PORT_SERVICE_DPC,
 	.probe		= dpc_probe,
 	.remove		= dpc_remove,
+	.reset_link     = dpc_reset_link,
 };
 
 static int __init dpc_service_init(void)
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 8f87bbe..9cfd0b8 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -15,6 +15,8 @@ 
 #define AER_FATAL			1
 #define AER_CORRECTABLE			2
 
+#define DPC_FATAL			4
+
 struct pci_dev;
 
 struct aer_header_log_regs {