mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-12-27 13:30:45 -05:00
After a Fatal Error has been reported by a device and has been recovered
through a Secondary Bus Reset, AER updates the device's error_state to
pci_channel_io_normal before invoking its driver's ->resume() callback.
By contrast, EEH updates the error_state earlier, namely after resetting
the device and before invoking its driver's ->slot_reset() callback.
Commit c58dc575f3 ("powerpc/pseries: Set error_state to
pci_channel_io_normal in eeh_report_reset()") explains in great detail
that the earlier invocation is necessitated by various drivers checking
accessibility of the device with pci_channel_offline() and avoiding
accesses if it returns true. It returns true for any other error_state
than pci_channel_io_normal.
The device should be accessible already after reset, hence the reasoning
is that it's safe to update the error_state immediately afterwards.
This deviation between AER and EEH seems problematic because drivers
behave differently depending on which error recovery mechanism the
platform uses. Three drivers have gone so far as to update the
error_state themselves, presumably to work around AER's behavior.
For consistency, amend AER to update the error_state at the same recovery
steps as EEH. Drop the now unnecessary workaround from the three drivers.
Keep updating the error_state before ->resume() in case ->error_detected()
or ->mmio_enabled() return PCI_ERS_RESULT_RECOVERED, which causes
->slot_reset() to be skipped. There are drivers doing this even for Fatal
Errors, e.g. mhi_pci_error_detected().
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/4517af6359ffb9d66152b827a5d2833459144e3f.1755008151.git.lukas@wunner.de
300 lines
8.2 KiB
C
300 lines
8.2 KiB
C
// 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)
|
|
*/
|
|
|
|
#define dev_fmt(fmt) "AER: " fmt
|
|
|
|
#include <linux/pci.h>
|
|
#include <linux/pm_runtime.h>
|
|
#include <linux/module.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/aer.h>
|
|
#include "portdrv.h"
|
|
#include "../pci.h"
|
|
|
|
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_error_detected(struct pci_dev *dev,
|
|
pci_channel_state_t state,
|
|
enum pci_ers_result *result)
|
|
{
|
|
struct pci_driver *pdrv;
|
|
pci_ers_result_t vote;
|
|
const struct pci_error_handlers *err_handler;
|
|
|
|
device_lock(&dev->dev);
|
|
pdrv = dev->driver;
|
|
if (pci_dev_is_disconnected(dev)) {
|
|
vote = PCI_ERS_RESULT_DISCONNECT;
|
|
} else if (!pci_dev_set_io_state(dev, state)) {
|
|
pci_info(dev, "can't recover (state transition %u -> %u invalid)\n",
|
|
dev->error_state, state);
|
|
vote = PCI_ERS_RESULT_NONE;
|
|
} else if (!pdrv || !pdrv->err_handler ||
|
|
!pdrv->err_handler->error_detected) {
|
|
/*
|
|
* If any device in the subtree does not have an error_detected
|
|
* callback, PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent
|
|
* error callbacks of "any" device in the subtree, and will
|
|
* exit in the disconnected error state.
|
|
*/
|
|
if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
|
|
vote = PCI_ERS_RESULT_NO_AER_DRIVER;
|
|
pci_info(dev, "can't recover (no error_detected callback)\n");
|
|
} else {
|
|
vote = PCI_ERS_RESULT_NONE;
|
|
}
|
|
} else {
|
|
err_handler = pdrv->err_handler;
|
|
vote = err_handler->error_detected(dev, state);
|
|
}
|
|
pci_uevent_ers(dev, vote);
|
|
*result = merge_result(*result, vote);
|
|
device_unlock(&dev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data)
|
|
{
|
|
pm_runtime_get_sync(&pdev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int pci_pm_runtime_put(struct pci_dev *pdev, void *data)
|
|
{
|
|
pm_runtime_put(&pdev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int report_frozen_detected(struct pci_dev *dev, void *data)
|
|
{
|
|
return report_error_detected(dev, pci_channel_io_frozen, data);
|
|
}
|
|
|
|
static int report_normal_detected(struct pci_dev *dev, void *data)
|
|
{
|
|
return report_error_detected(dev, pci_channel_io_normal, data);
|
|
}
|
|
|
|
static int report_perm_failure_detected(struct pci_dev *dev, void *data)
|
|
{
|
|
struct pci_driver *pdrv;
|
|
const struct pci_error_handlers *err_handler;
|
|
|
|
device_lock(&dev->dev);
|
|
pdrv = dev->driver;
|
|
if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->error_detected)
|
|
goto out;
|
|
|
|
err_handler = pdrv->err_handler;
|
|
err_handler->error_detected(dev, pci_channel_io_perm_failure);
|
|
out:
|
|
pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
|
|
device_unlock(&dev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int report_mmio_enabled(struct pci_dev *dev, void *data)
|
|
{
|
|
struct pci_driver *pdrv;
|
|
pci_ers_result_t vote, *result = data;
|
|
const struct pci_error_handlers *err_handler;
|
|
|
|
device_lock(&dev->dev);
|
|
pdrv = dev->driver;
|
|
if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->mmio_enabled)
|
|
goto out;
|
|
|
|
err_handler = pdrv->err_handler;
|
|
vote = err_handler->mmio_enabled(dev);
|
|
*result = merge_result(*result, vote);
|
|
out:
|
|
device_unlock(&dev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int report_slot_reset(struct pci_dev *dev, void *data)
|
|
{
|
|
struct pci_driver *pdrv;
|
|
pci_ers_result_t vote, *result = data;
|
|
const struct pci_error_handlers *err_handler;
|
|
|
|
device_lock(&dev->dev);
|
|
pdrv = dev->driver;
|
|
if (!pci_dev_set_io_state(dev, pci_channel_io_normal) ||
|
|
!pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset)
|
|
goto out;
|
|
|
|
err_handler = pdrv->err_handler;
|
|
vote = err_handler->slot_reset(dev);
|
|
*result = merge_result(*result, vote);
|
|
out:
|
|
device_unlock(&dev->dev);
|
|
return 0;
|
|
}
|
|
|
|
static int report_resume(struct pci_dev *dev, void *data)
|
|
{
|
|
struct pci_driver *pdrv;
|
|
const struct pci_error_handlers *err_handler;
|
|
|
|
device_lock(&dev->dev);
|
|
pdrv = dev->driver;
|
|
if (!pci_dev_set_io_state(dev, pci_channel_io_normal) ||
|
|
!pdrv || !pdrv->err_handler || !pdrv->err_handler->resume)
|
|
goto out;
|
|
|
|
err_handler = pdrv->err_handler;
|
|
err_handler->resume(dev);
|
|
out:
|
|
pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
|
|
device_unlock(&dev->dev);
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* pci_walk_bridge - walk bridges potentially AER affected
|
|
* @bridge: bridge which may be a Port, an RCEC, or an RCiEP
|
|
* @cb: callback to be called for each device found
|
|
* @userdata: arbitrary pointer to be passed to callback
|
|
*
|
|
* If the device provided is a bridge, walk the subordinate bus, including
|
|
* any bridged devices on buses under this bus. Call the provided callback
|
|
* on each device found.
|
|
*
|
|
* If the device provided has no subordinate bus, e.g., an RCEC or RCiEP,
|
|
* call the callback on the device itself.
|
|
*/
|
|
static void pci_walk_bridge(struct pci_dev *bridge,
|
|
int (*cb)(struct pci_dev *, void *),
|
|
void *userdata)
|
|
{
|
|
if (bridge->subordinate)
|
|
pci_walk_bus(bridge->subordinate, cb, userdata);
|
|
else
|
|
cb(bridge, userdata);
|
|
}
|
|
|
|
pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
|
|
pci_channel_state_t state,
|
|
pci_ers_result_t (*reset_subordinates)(struct pci_dev *pdev))
|
|
{
|
|
int type = pci_pcie_type(dev);
|
|
struct pci_dev *bridge;
|
|
pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
|
|
struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
|
|
|
|
/*
|
|
* If the error was detected by a Root Port, Downstream Port, RCEC,
|
|
* or RCiEP, recovery runs on the device itself. For Ports, that
|
|
* also includes any subordinate devices.
|
|
*
|
|
* If it was detected by another device (Endpoint, etc), recovery
|
|
* runs on the device and anything else under the same Port, i.e.,
|
|
* everything under "bridge".
|
|
*/
|
|
if (type == PCI_EXP_TYPE_ROOT_PORT ||
|
|
type == PCI_EXP_TYPE_DOWNSTREAM ||
|
|
type == PCI_EXP_TYPE_RC_EC ||
|
|
type == PCI_EXP_TYPE_RC_END)
|
|
bridge = dev;
|
|
else
|
|
bridge = pci_upstream_bridge(dev);
|
|
|
|
pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL);
|
|
|
|
pci_dbg(bridge, "broadcast error_detected message\n");
|
|
if (state == pci_channel_io_frozen)
|
|
pci_walk_bridge(bridge, report_frozen_detected, &status);
|
|
else
|
|
pci_walk_bridge(bridge, report_normal_detected, &status);
|
|
|
|
if (status == PCI_ERS_RESULT_CAN_RECOVER) {
|
|
status = PCI_ERS_RESULT_RECOVERED;
|
|
pci_dbg(bridge, "broadcast mmio_enabled message\n");
|
|
pci_walk_bridge(bridge, report_mmio_enabled, &status);
|
|
}
|
|
|
|
if (status == PCI_ERS_RESULT_NEED_RESET ||
|
|
state == pci_channel_io_frozen) {
|
|
if (reset_subordinates(bridge) != PCI_ERS_RESULT_RECOVERED) {
|
|
pci_warn(bridge, "subordinate device reset failed\n");
|
|
goto failed;
|
|
}
|
|
}
|
|
|
|
if (status == PCI_ERS_RESULT_NEED_RESET) {
|
|
/*
|
|
* TODO: Should call platform-specific
|
|
* functions to reset slot before calling
|
|
* drivers' slot_reset callbacks?
|
|
*/
|
|
status = PCI_ERS_RESULT_RECOVERED;
|
|
pci_dbg(bridge, "broadcast slot_reset message\n");
|
|
pci_walk_bridge(bridge, report_slot_reset, &status);
|
|
}
|
|
|
|
if (status != PCI_ERS_RESULT_RECOVERED)
|
|
goto failed;
|
|
|
|
pci_dbg(bridge, "broadcast resume message\n");
|
|
pci_walk_bridge(bridge, report_resume, &status);
|
|
|
|
/*
|
|
* If we have native control of AER, clear error status in the device
|
|
* that detected the error. If the platform retained control of AER,
|
|
* it is responsible for clearing this status. In that case, the
|
|
* signaling device may not even be visible to the OS.
|
|
*/
|
|
if (host->native_aer || pcie_ports_native) {
|
|
pcie_clear_device_status(dev);
|
|
pci_aer_clear_nonfatal_status(dev);
|
|
}
|
|
|
|
pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
|
|
|
|
pci_info(bridge, "device recovery successful\n");
|
|
return status;
|
|
|
|
failed:
|
|
pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
|
|
|
|
pci_walk_bridge(bridge, report_perm_failure_detected, NULL);
|
|
|
|
pci_info(bridge, "device recovery failed\n");
|
|
|
|
return status;
|
|
}
|