@@ -342,6 +342,9 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
void pci_enable_acs(struct pci_dev *dev);
+/* PCI error reporting and recovery */
+void pci_do_recovery(struct pci_dev *dev, int severity);
+
#ifdef CONFIG_PCIE_PTM
void pci_ptm_init(struct pci_dev *dev);
#else
@@ -6,7 +6,7 @@
# Build PCI Express ASPM if needed
obj-$(CONFIG_PCIEASPM) += aspm.o
-pcieportdrv-y := portdrv_core.o portdrv_pci.o portdrv_bus.o
+pcieportdrv-y := portdrv_core.o portdrv_pci.o portdrv_bus.o pcie-err.o
pcieportdrv-$(CONFIG_ACPI) += portdrv_acpi.o
obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o
@@ -76,36 +76,6 @@ struct aer_rpc {
*/
};
-struct aer_broadcast_data {
- enum pci_channel_state state;
- enum pci_ers_result result;
-};
-
-static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
- enum pci_ers_result new)
-{
- if (new == PCI_ERS_RESULT_NO_AER_DRIVER)
- return PCI_ERS_RESULT_NO_AER_DRIVER;
-
- if (new == PCI_ERS_RESULT_NONE)
- return orig;
-
- switch (orig) {
- case PCI_ERS_RESULT_CAN_RECOVER:
- case PCI_ERS_RESULT_RECOVERED:
- orig = new;
- break;
- case PCI_ERS_RESULT_DISCONNECT:
- if (new == PCI_ERS_RESULT_NEED_RESET)
- orig = PCI_ERS_RESULT_NEED_RESET;
- break;
- default:
- break;
- }
-
- return orig;
-}
-
extern struct bus_type pcie_port_bus_type;
void aer_isr(struct work_struct *work);
void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/kfifo.h>
#include "aerdrv.h"
+#include "../../pci.h"
#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
@@ -234,189 +235,6 @@ static bool find_source_device(struct pci_dev *parent,
return true;
}
-static int report_error_detected(struct pci_dev *dev, void *data)
-{
- pci_ers_result_t vote;
- const struct pci_error_handlers *err_handler;
- struct aer_broadcast_data *result_data;
- result_data = (struct aer_broadcast_data *) data;
-
- device_lock(&dev->dev);
- dev->error_state = result_data->state;
-
- if (!dev->driver ||
- !dev->driver->err_handler ||
- !dev->driver->err_handler->error_detected) {
- if (result_data->state == pci_channel_io_frozen &&
- dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
- /*
- * In case of fatal recovery, if one of down-
- * stream device has no driver. We might be
- * unable to recover because a later insmod
- * of a driver for this device is unaware of
- * its hw state.
- */
- dev_printk(KERN_DEBUG, &dev->dev, "device has %s\n",
- dev->driver ?
- "no AER-aware driver" : "no driver");
- }
-
- /*
- * If there's any device in the subtree that does not
- * have an error_detected callback, returning
- * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
- * the subsequent mmio_enabled/slot_reset/resume
- * callbacks of "any" device in the subtree. All the
- * devices in the subtree are left in the error state
- * without recovery.
- */
-
- if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
- vote = PCI_ERS_RESULT_NO_AER_DRIVER;
- else
- vote = PCI_ERS_RESULT_NONE;
- } else {
- err_handler = dev->driver->err_handler;
- vote = err_handler->error_detected(dev, result_data->state);
- }
-
- result_data->result = merge_result(result_data->result, vote);
- device_unlock(&dev->dev);
- return 0;
-}
-
-static int report_mmio_enabled(struct pci_dev *dev, void *data)
-{
- pci_ers_result_t vote;
- const struct pci_error_handlers *err_handler;
- struct aer_broadcast_data *result_data;
- result_data = (struct aer_broadcast_data *) data;
-
- device_lock(&dev->dev);
- if (!dev->driver ||
- !dev->driver->err_handler ||
- !dev->driver->err_handler->mmio_enabled)
- goto out;
-
- err_handler = dev->driver->err_handler;
- vote = err_handler->mmio_enabled(dev);
- result_data->result = merge_result(result_data->result, vote);
-out:
- device_unlock(&dev->dev);
- return 0;
-}
-
-static int report_slot_reset(struct pci_dev *dev, void *data)
-{
- pci_ers_result_t vote;
- const struct pci_error_handlers *err_handler;
- struct aer_broadcast_data *result_data;
- result_data = (struct aer_broadcast_data *) data;
-
- device_lock(&dev->dev);
- if (!dev->driver ||
- !dev->driver->err_handler ||
- !dev->driver->err_handler->slot_reset)
- goto out;
-
- err_handler = dev->driver->err_handler;
- vote = err_handler->slot_reset(dev);
- result_data->result = merge_result(result_data->result, vote);
-out:
- device_unlock(&dev->dev);
- return 0;
-}
-
-static int report_resume(struct pci_dev *dev, void *data)
-{
- const struct pci_error_handlers *err_handler;
-
- device_lock(&dev->dev);
- dev->error_state = pci_channel_io_normal;
-
- if (!dev->driver ||
- !dev->driver->err_handler ||
- !dev->driver->err_handler->resume)
- goto out;
-
- err_handler = dev->driver->err_handler;
- err_handler->resume(dev);
-out:
- device_unlock(&dev->dev);
- return 0;
-}
-
-/**
- * broadcast_error_message - handle message broadcast to downstream drivers
- * @dev: pointer to from where in a hierarchy message is broadcasted down
- * @state: error state
- * @error_mesg: message to print
- * @cb: callback to be broadcasted
- *
- * Invoked during error recovery process. Once being invoked, the content
- * of error severity will be broadcasted to all downstream drivers in a
- * hierarchy in question.
- */
-static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
- enum pci_channel_state state,
- char *error_mesg,
- int (*cb)(struct pci_dev *, void *))
-{
- struct aer_broadcast_data result_data;
-
- dev_printk(KERN_DEBUG, &dev->dev, "broadcast %s message\n", error_mesg);
- result_data.state = state;
- if (cb == report_error_detected)
- result_data.result = PCI_ERS_RESULT_CAN_RECOVER;
- else
- result_data.result = PCI_ERS_RESULT_RECOVERED;
-
- if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- /*
- * If the error is reported by a bridge, we think this error
- * is related to the downstream link of the bridge, so we
- * do error recovery on all subordinates of the bridge instead
- * of the bridge and clear the error status of the bridge.
- */
- if (cb == report_error_detected)
- dev->error_state = state;
- pci_walk_bus(dev->subordinate, cb, &result_data);
- if (cb == report_resume) {
- pci_cleanup_aer_uncorrect_error_status(dev);
- dev->error_state = pci_channel_io_normal;
- }
- } else {
- /*
- * If the error is reported by an end point, we think this
- * error is related to the upstream link of the end point.
- */
- if (state == pci_channel_io_normal)
- /*
- * the error is non fatal so the bus is ok, just invoke
- * the callback for the function that logged the error.
- */
- cb(dev, &result_data);
- else
- pci_walk_bus(dev->bus, cb, &result_data);
- }
-
- return result_data.result;
-}
-
-/**
- * default_reset_link - default reset function
- * @dev: pointer to pci_dev data structure
- *
- * Invoked when performing link reset on a Downstream Port or a
- * Root Port with no aer driver.
- */
-static pci_ers_result_t default_reset_link(struct pci_dev *dev)
-{
- pci_reset_bridge_secondary_bus(dev);
- dev_printk(KERN_DEBUG, &dev->dev, "downstream link has been reset\n");
- return PCI_ERS_RESULT_RECOVERED;
-}
-
static int find_aer_service_iter(struct device *device, void *data)
{
struct pcie_port_service_driver *service_driver, **drv;
@@ -434,7 +252,7 @@ static int find_aer_service_iter(struct device *device, void *data)
return 0;
}
-static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev)
+struct pcie_port_service_driver *pci_find_aer_service(struct pci_dev *dev)
{
struct pcie_port_service_driver *drv = NULL;
@@ -442,108 +260,7 @@ static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev)
return drv;
}
-
-static pci_ers_result_t reset_link(struct pci_dev *dev)
-{
- struct pci_dev *udev;
- pci_ers_result_t status;
- struct pcie_port_service_driver *driver;
-
- if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
- /* Reset this port for all subordinates */
- udev = dev;
- } else {
- /* Reset the upstream component (likely downstream port) */
- udev = dev->bus->self;
- }
-
- /* Use the aer driver of the component firstly */
- driver = find_aer_service(udev);
-
- if (driver && driver->reset_link) {
- status = driver->reset_link(udev);
- } else if (udev->has_secondary_link) {
- status = default_reset_link(udev);
- } else {
- dev_printk(KERN_DEBUG, &dev->dev,
- "no link-reset support at upstream device %s\n",
- pci_name(udev));
- return PCI_ERS_RESULT_DISCONNECT;
- }
-
- if (status != PCI_ERS_RESULT_RECOVERED) {
- dev_printk(KERN_DEBUG, &dev->dev,
- "link reset at upstream device %s failed\n",
- pci_name(udev));
- return PCI_ERS_RESULT_DISCONNECT;
- }
-
- return status;
-}
-
-/**
- * pci_do_recovery - handle nonfatal/fatal error recovery process
- * @dev: pointer to a pci_dev data structure of agent detecting an error
- * @severity: error severity type
- *
- * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
- * error detected message to all downstream drivers within a hierarchy in
- * question and return the returned code.
- */
-static void pci_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)
- state = pci_channel_io_frozen;
- else
- state = pci_channel_io_normal;
-
- status = broadcast_error_message(dev,
- state,
- "error_detected",
- report_error_detected);
-
- if (severity == AER_FATAL) {
- result = reset_link(dev);
- if (result != PCI_ERS_RESULT_RECOVERED)
- goto failed;
- }
-
- if (status == PCI_ERS_RESULT_CAN_RECOVER)
- status = broadcast_error_message(dev,
- state,
- "mmio_enabled",
- report_mmio_enabled);
-
- if (status == PCI_ERS_RESULT_NEED_RESET) {
- /*
- * TODO: Should call platform-specific
- * functions to reset slot before calling
- * drivers' slot_reset callbacks?
- */
- status = broadcast_error_message(dev,
- state,
- "slot_reset",
- report_slot_reset);
- }
-
- if (status != PCI_ERS_RESULT_RECOVERED)
- goto failed;
-
- broadcast_error_message(dev,
- state,
- "resume",
- report_resume);
-
- dev_info(&dev->dev, "AER: Device recovery successful\n");
- return;
-
-failed:
- /* TODO: Should kernel panic here? */
- dev_info(&dev->dev, "AER: Device recovery failed\n");
-}
+EXPORT_SYMBOL(pci_find_aer_service);
/**
* handle_error_source - handle logging error into an event log
new file mode 100644
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file implements the error recovery as a core part of PCIe error reporting.
+ * When a PCIe error is delivered, an error message will be collected and printed
+ * to console, then, an error recovery procedure will be executed by following
+ * the PCI error recovery rules.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ * Tom Long Nguyen (tom.l.nguyen@intel.com)
+ * Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/aer.h>
+#include <linux/pcieport_if.h>
+#include "portdrv.h"
+
+struct aer_broadcast_data {
+ enum pci_channel_state state;
+ enum pci_ers_result result;
+};
+
+static pci_ers_result_t merge_result(enum pci_ers_result orig,
+ enum pci_ers_result new)
+{
+ if (new == PCI_ERS_RESULT_NO_AER_DRIVER)
+ return PCI_ERS_RESULT_NO_AER_DRIVER;
+
+ if (new == PCI_ERS_RESULT_NONE)
+ return orig;
+
+ switch (orig) {
+ case PCI_ERS_RESULT_CAN_RECOVER:
+ case PCI_ERS_RESULT_RECOVERED:
+ orig = new;
+ break;
+ case PCI_ERS_RESULT_DISCONNECT:
+ if (new == PCI_ERS_RESULT_NEED_RESET)
+ orig = PCI_ERS_RESULT_NEED_RESET;
+ break;
+ default:
+ break;
+ }
+
+ return orig;
+}
+
+static int report_mmio_enabled(struct pci_dev *dev, void *data)
+{
+ pci_ers_result_t vote;
+ const struct pci_error_handlers *err_handler;
+ struct aer_broadcast_data *result_data;
+
+ result_data = (struct aer_broadcast_data *) data;
+
+ device_lock(&dev->dev);
+ if (!dev->driver ||
+ !dev->driver->err_handler ||
+ !dev->driver->err_handler->mmio_enabled)
+ goto out;
+
+ err_handler = dev->driver->err_handler;
+ vote = err_handler->mmio_enabled(dev);
+ result_data->result = merge_result(result_data->result, vote);
+out:
+ device_unlock(&dev->dev);
+ return 0;
+}
+
+static int report_slot_reset(struct pci_dev *dev, void *data)
+{
+ pci_ers_result_t vote;
+ const struct pci_error_handlers *err_handler;
+ struct aer_broadcast_data *result_data;
+
+ result_data = (struct aer_broadcast_data *) data;
+
+ device_lock(&dev->dev);
+ if (!dev->driver ||
+ !dev->driver->err_handler ||
+ !dev->driver->err_handler->slot_reset)
+ goto out;
+
+ err_handler = dev->driver->err_handler;
+ vote = err_handler->slot_reset(dev);
+ result_data->result = merge_result(result_data->result, vote);
+out:
+ device_unlock(&dev->dev);
+ return 0;
+}
+
+static int report_resume(struct pci_dev *dev, void *data)
+{
+ const struct pci_error_handlers *err_handler;
+
+ device_lock(&dev->dev);
+ dev->error_state = pci_channel_io_normal;
+
+ if (!dev->driver ||
+ !dev->driver->err_handler ||
+ !dev->driver->err_handler->resume)
+ goto out;
+
+ err_handler = dev->driver->err_handler;
+ err_handler->resume(dev);
+out:
+ device_unlock(&dev->dev);
+ return 0;
+}
+
+static int report_error_detected(struct pci_dev *dev, void *data)
+{
+ pci_ers_result_t vote;
+ const struct pci_error_handlers *err_handler;
+ struct aer_broadcast_data *result_data;
+
+ result_data = (struct aer_broadcast_data *) data;
+
+ device_lock(&dev->dev);
+ dev->error_state = result_data->state;
+
+ if (!dev->driver ||
+ !dev->driver->err_handler ||
+ !dev->driver->err_handler->error_detected) {
+ if (result_data->state == pci_channel_io_frozen &&
+ dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+ /*
+ * In case of fatal recovery, if one of down-
+ * stream device has no driver. We might be
+ * unable to recover because a later insmod
+ * of a driver for this device is unaware of
+ * its hw state.
+ */
+ dev_printk(KERN_DEBUG, &dev->dev, "device has %s\n",
+ dev->driver ?
+ "no error-aware driver" : "no driver");
+ }
+
+ /*
+ * If there's any device in the subtree that does not
+ * have an error_detected callback, returning
+ * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
+ * the subsequent mmio_enabled/slot_reset/resume
+ * callbacks of "any" device in the subtree. All the
+ * devices in the subtree are left in the error state
+ * without recovery.
+ */
+
+ if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
+ vote = PCI_ERS_RESULT_NO_AER_DRIVER;
+ else
+ vote = PCI_ERS_RESULT_NONE;
+ } else {
+ err_handler = dev->driver->err_handler;
+ vote = err_handler->error_detected(dev, result_data->state);
+ }
+
+ result_data->result = merge_result(result_data->result, vote);
+ device_unlock(&dev->dev);
+ return 0;
+}
+
+/**
+ * default_reset_link - default reset function
+ * @dev: pointer to pci_dev data structure
+ *
+ * Invoked when performing link reset on a Downstream Port or a
+ * Root Port with no aer driver.
+ */
+static pci_ers_result_t default_reset_link(struct pci_dev *dev)
+{
+ pci_reset_bridge_secondary_bus(dev);
+ dev_printk(KERN_DEBUG, &dev->dev, "downstream link has been reset\n");
+ return PCI_ERS_RESULT_RECOVERED;
+}
+
+static pci_ers_result_t reset_link(struct pci_dev *dev)
+{
+ struct pci_dev *udev;
+ pci_ers_result_t status;
+ struct pcie_port_service_driver *driver = NULL;
+
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ /* Reset this port for all subordinates */
+ udev = dev;
+ } else {
+ /* Reset the upstream component (likely downstream port) */
+ udev = dev->bus->self;
+ }
+
+#if IS_ENABLED(CONFIG_PCIEAER)
+ /* Use the aer driver of the component firstly */
+ driver = pci_find_aer_service(udev);
+#endif
+
+ if (driver && driver->reset_link) {
+ status = driver->reset_link(udev);
+ } else if (udev->has_secondary_link) {
+ status = default_reset_link(udev);
+ } else {
+ dev_printk(KERN_DEBUG, &dev->dev,
+ "no link-reset support at upstream device %s\n",
+ pci_name(udev));
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ if (status != PCI_ERS_RESULT_RECOVERED) {
+ dev_printk(KERN_DEBUG, &dev->dev,
+ "link reset at upstream device %s failed\n",
+ pci_name(udev));
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ return status;
+}
+
+/**
+ * broadcast_error_message - handle message broadcast to downstream drivers
+ * @dev: pointer to from where in a hierarchy message is broadcasted down
+ * @state: error state
+ * @error_mesg: message to print
+ * @cb: callback to be broadcasted
+ *
+ * Invoked during error recovery process. Once being invoked, the content
+ * of error severity will be broadcasted to all downstream drivers in a
+ * hierarchy in question.
+ */
+static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
+ enum pci_channel_state state,
+ char *error_mesg,
+ int (*cb)(struct pci_dev *, void *))
+{
+ struct aer_broadcast_data result_data;
+
+ dev_printk(KERN_DEBUG, &dev->dev, "broadcast %s message\n", error_mesg);
+ result_data.state = state;
+ if (cb == report_error_detected)
+ result_data.result = PCI_ERS_RESULT_CAN_RECOVER;
+ else
+ result_data.result = PCI_ERS_RESULT_RECOVERED;
+
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ /*
+ * If the error is reported by a bridge, we think this error
+ * is related to the downstream link of the bridge, so we
+ * do error recovery on all subordinates of the bridge instead
+ * of the bridge and clear the error status of the bridge.
+ */
+ if (cb == report_error_detected)
+ dev->error_state = state;
+ pci_walk_bus(dev->subordinate, cb, &result_data);
+ if (cb == report_resume) {
+ pci_cleanup_aer_uncorrect_error_status(dev);
+ dev->error_state = pci_channel_io_normal;
+ }
+ } else {
+ /*
+ * If the error is reported by an end point, we think this
+ * error is related to the upstream link of the end point.
+ */
+ pci_walk_bus(dev->bus, cb, &result_data);
+ }
+
+ return result_data.result;
+}
+
+/**
+ * pci_do_recovery - handle nonfatal/fatal error recovery process
+ * @dev: pointer to a pci_dev data structure of agent detecting an error
+ * @severity: error severity type
+ *
+ * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
+ * error detected message to all downstream drivers within a hierarchy in
+ * question and return the returned code.
+ */
+void pci_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)
+ state = pci_channel_io_frozen;
+ else
+ state = pci_channel_io_normal;
+
+ status = broadcast_error_message(dev,
+ state,
+ "error_detected",
+ report_error_detected);
+
+ if (severity == AER_FATAL) {
+ result = reset_link(dev);
+ if (result != PCI_ERS_RESULT_RECOVERED)
+ goto failed;
+ }
+
+ if (status == PCI_ERS_RESULT_CAN_RECOVER)
+ status = broadcast_error_message(dev,
+ state,
+ "mmio_enabled",
+ report_mmio_enabled);
+
+ if (status == PCI_ERS_RESULT_NEED_RESET) {
+ /*
+ * TODO: Should call platform-specific
+ * functions to reset slot before calling
+ * drivers' slot_reset callbacks?
+ */
+ status = broadcast_error_message(dev,
+ state,
+ "slot_reset",
+ report_slot_reset);
+ }
+
+ if (status != PCI_ERS_RESULT_RECOVERED)
+ goto failed;
+
+ broadcast_error_message(dev,
+ state,
+ "resume",
+ report_resume);
+
+ dev_info(&dev->dev, "Device recovery successful\n");
+ return;
+
+failed:
+ /* TODO: Should kernel panic here? */
+ dev_info(&dev->dev, "Device recovery failed\n");
+}
@@ -79,4 +79,5 @@ static inline void pcie_port_platform_notify(struct pci_dev *port, int *mask)
static inline void pcie_port_platform_notify(struct pci_dev *port, int *mask){}
#endif /* !CONFIG_ACPI */
+struct pcie_port_service_driver *pci_find_aer_service(struct pci_dev *dev);
#endif /* _PORTDRV_H_ */
This patch factors out error reporting callbacks, which are currently tightly coupled with AER. DPC should be able to register callbacks and attmept recovery when DPC trigger event occurs. Signed-off-by: Oza Pawandeep <poza@codeaurora.org>