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 <andrew.patterson@hp.com>
Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index 9a2a6e32f00f6d0a4a89d536d8da22b676b82a4d..0e8db6771252a2f3dcb4c28891e0f6d2958389a0 100644 (file)
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -122,7 +122,7 @@ static void eeh_enable_irq(struct pci_dev *dev)
  * 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 *dev, void *userdata)
        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_dev *dev, void *userdata)
  * 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(struct pci_dev *dev, void *userdata)
        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_dev *dev, void *userdata)
 
        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_dev *dev, void *userdata)
  * 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;
 }
 
 /* ------------------------------------------------------- */

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 40af27f3104384aa1873b12d1d8153bda17f79b8..cef28a79103f06e9178b9c86419c641cad3b74af 100644 (file)
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -206,13 +206,18 @@ void pci_enable_bridges(struct pci_bus *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);
@@ -236,8 +241,10 @@ void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *),
 
                /* 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);
 }

diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index dd3829e68e3f0670d7ee3bead9138a899d54c12c..a7a3919904bbcb4996e24b01dec9889faa33dcd2 100644 (file)
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -109,7 +109,7 @@ int pci_cleanup_aer_correct_error_status(struct pci_dev *dev)
 #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);
 
@@ -124,6 +124,8 @@ static void set_device_error_reporting(struct pci_dev *dev, void *data)
 
        if (enable)
                pcie_set_ecrc_checking(dev);
+
+       return 0;
 }
 
 /**
@@ -207,7 +209,7 @@ static struct device* find_source_device(struct pci_dev *parent, u16 id)
        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;
@@ -232,16 +234,16 @@ static void report_error_detected(struct pci_dev *dev, void *data)
                                   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;
@@ -251,15 +253,15 @@ static void report_mmio_enabled(struct pci_dev *dev, void *data)
        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;
@@ -269,15 +271,15 @@ static void report_slot_reset(struct pci_dev *dev, void *data)
        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;
 
@@ -286,11 +288,11 @@ static void report_resume(struct pci_dev *dev, void *data)
        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;
 }
 
 /**
@@ -307,7 +309,7 @@ static void report_resume(struct pci_dev *dev, void *data)
 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;
 

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6a1800ecd95d5a29b4ef870810e51c6c6732fbdc..61d9b790d21c5c8daf3f6f801f02155ca438ac1c 100644 (file)
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -789,7 +789,7 @@ const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
 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);