lkml.org 
[lkml]   [2009]   [Jun]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Subject[PATCH V3: 1/3] pci: Provide Multiple Error Received and no error source id support on AER
From
Date

Changelog since V2:
1) Probe devices under the root port when the bus id of
the source id is equal to 0; V2 does so when device id is
equal to 0;
2) Add more comments on critical path of finding devices.

Changelog since V1:
Version 2 adds nosourceid, a boot parameter. When
aerdriver.nosourceid=y, aerdriver doesn't use the source
id saved by root port. Instead, it searches the device
tree under the root port to find the reporter. So if hardware
has errata and root port saves a bad source id, aerdriver
still could find the reporter.
There are 2 scenarios under which aerdriver searches the
device tree under root port:
1) nosourceid=n and error source id is equal to 0;
2) nosourceid=y.

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.

Signed-off-by: Zhang Yanmin <yanmin.zhang@linux.intel.com>

---

--- linux-2.6.30-rc3/arch/powerpc/platforms/pseries/eeh_driver.c 2009-04-27 15:48:28.000000000 +0800
+++ linux-2.6.30-rc3_pciwalk/arch/powerpc/platforms/pseries/eeh_driver.c 2009-04-29 10:39:41.000000000 +0800
@@ -122,7 +122,7 @@ static void eeh_enable_irq(struct pci_de
* 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;
@@ -130,19 +130,21 @@ static void eeh_report_error(struct pci_
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;
}

/**
@@ -153,7 +155,7 @@ static void eeh_report_error(struct pci_
* 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;
@@ -161,26 +163,28 @@ static void eeh_report_mmio_enabled(stru
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;

@@ -188,35 +192,39 @@ static void eeh_report_reset(struct pci_

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;
}

/**
@@ -226,22 +234,24 @@ static void eeh_report_resume(struct pci
* 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;
}

/* ------------------------------------------------------- */
--- linux-2.6.30-rc3/drivers/pci/bus.c 2009-04-27 15:48:31.000000000 +0800
+++ linux-2.6.30-rc3_pciwalk/drivers/pci/bus.c 2009-05-05 14:10:36.000000000 +0800
@@ -201,13 +201,18 @@ void pci_enable_bridges(struct pci_bus *
* 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);
@@ -231,8 +236,10 @@ void pci_walk_bus(struct pci_bus *top, v

/* 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);
}
--- linux-2.6.30-rc3/drivers/pci/pcie/aer/aerdrv_core.c 2009-04-27 15:48:31.000000000 +0800
+++ linux-2.6.30-rc3_pciwalk/drivers/pci/pcie/aer/aerdrv_core.c 2009-04-29 10:37:16.000000000 +0800
@@ -109,19 +109,21 @@ int pci_cleanup_aer_correct_error_status
#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 (dev->pcie_type != PCIE_RC_PORT &&
dev->pcie_type != PCIE_SW_UPSTREAM_PORT &&
dev->pcie_type != PCIE_SW_DOWNSTREAM_PORT)
- return;
+ return 0;

if (enable)
pci_enable_pcie_error_reporting(dev);
else
pci_disable_pcie_error_reporting(dev);
+
+ return 0;
}

/**
@@ -205,7 +207,7 @@ static struct device* find_source_device
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;
@@ -230,16 +232,16 @@ static void report_error_detected(struct
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;
@@ -249,15 +251,15 @@ static void report_mmio_enabled(struct p
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;
@@ -267,15 +269,15 @@ static void report_slot_reset(struct pci
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;

@@ -284,11 +286,11 @@ static void report_resume(struct pci_dev
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;
}

/**
@@ -305,7 +307,7 @@ static void report_resume(struct pci_dev
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;

--- linux-2.6.30-rc3/include/linux/pci.h 2009-04-27 15:48:33.000000000 +0800
+++ linux-2.6.30-rc3_pciwalk/include/linux/pci.h 2009-04-29 10:31:58.000000000 +0800
@@ -790,7 +790,7 @@ const struct pci_device_id *pci_match_id
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);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2009-06-09 09:25    [W:0.036 / U:5.052 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site