PCI AER: multiple error support

When a root port receives the same errors more than once before the
kernel process them, the Multiple Error Messages Received flags are set
by hardware. Because the root port could only save one kind of
correctable error source id and another uncorrectable error source id at
the same time, the second message sender id is lost if the 2 messages
are sent from 2 different devices. This patch makes the kernel search
all devices under the root port when multiple messages are received.

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/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index dadf492e9ce9208a2a939f7ea308ed99b662f4e9..bbd7428ca2d0eab8b954d75362a1de54d7906e93 100644 (file)
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -57,8 +57,10 @@ struct header_log_regs {
        unsigned int dw3;
 };
 
+#define AER_MAX_MULTI_ERR_DEVICES      5       /* Not likely to have more */
 struct aer_err_info {
-       struct pci_dev *dev;
+       struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+       int error_dev_num;
        u16 id;
        int severity;                   /* 0:NONFATAL | 1:FATAL | 2:COR */
        int flags;

diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 2750e7b266b4b9a7b7b47e325bd28469bab77326..3d8872704a583d4406b3b4c1b5bf68aacfe4ee22 100644 (file)
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -158,6 +158,17 @@ static inline int compare_device_id(struct pci_dev *dev,
        return 0;
 }
 
+static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
+{
+       if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
+               e_info->dev[e_info->error_dev_num] = dev;
+               e_info->error_dev_num++;
+               return 1;
+       } else
+               return 0;
+}
+
+
 #define        PCI_BUS(x)      (((x) >> 8) & 0xff)
 
 static int find_device_iter(struct pci_dev *dev, void *data)
@@ -176,15 +187,31 @@ static int find_device_iter(struct pci_dev *dev, void *data)
        if (!nosourceid && (PCI_BUS(e_info->id) != 0)) {
                result = compare_device_id(dev, e_info);
                if (result)
-                       e_info->dev = dev;
-               return result;
+                       add_error_device(e_info, dev);
+
+               /*
+                * If there is no multiple error, we stop
+                * or continue based on the id comparing.
+                */
+               if (!(e_info->flags & AER_MULTI_ERROR_VALID_FLAG))
+                       return result;
+
+               /*
+                * If there are multiple errors and id does match,
+                * We need continue to search other devices under
+                * the root port. Return 0 means that.
+                */
+               if (result)
+                       return 0;
        }
 
        /*
-        * Next is to check when bus id is equal to 0 or
-        * nosourceid==y. Some ports might lose the bus
-        * id of error source id. We check AER status
-        * registers to find the initial reporter.
+        * When either
+        *      1) nosourceid==y;
+        *      2) bus id is equal to 0. Some ports might lose the bus
+        *              id of error source id;
+        *      3) There are multiple errors and prior id comparing fails;
+        * We check AER status registers to find the initial reporter.
         */
        if (atomic_read(&dev->enable_cnt) == 0)
                return 0;
@@ -213,8 +240,8 @@ static int find_device_iter(struct pci_dev *dev, void *data)
                                pos + PCI_ERR_COR_MASK,
                                &mask);
                if (status & ERR_CORRECTABLE_ERROR_MASK & ~mask) {
-                       e_info->dev = dev;
-                       return 1;
+                       add_error_device(e_info, dev);
+                       goto added;
                }
        } else {
                pci_read_config_dword(dev,
@@ -224,12 +251,18 @@ static int find_device_iter(struct pci_dev *dev, void *data)
                                pos + PCI_ERR_UNCOR_MASK,
                                &mask);
                if (status & ERR_UNCORRECTABLE_ERROR_MASK & ~mask) {
-                       e_info->dev = dev;
-                       return 1;
+                       add_error_device(e_info, dev);
+                       goto added;
                }
        }
 
        return 0;
+
+added:
+       if (e_info->flags & AER_MULTI_ERROR_VALID_FLAG)
+               return 0;
+       else
+               return 1;
 }
 
 /**
@@ -709,6 +742,28 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
        return AER_SUCCESS;
 }
 
+static inline void aer_process_err_devices(struct pcie_device *p_device,
+                       struct aer_err_info *e_info)
+{
+       int i;
+
+       if (!e_info->dev[0]) {
+               dev_printk(KERN_DEBUG, &p_device->port->dev,
+                               "can't find device of ID%04x\n",
+                               e_info->id);
+       }
+
+       for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
+               if (get_device_error_info(e_info->dev[i], e_info) ==
+                               AER_SUCCESS) {
+                       aer_print_error(e_info->dev[i], e_info);
+                       handle_error_source(p_device,
+                                       e_info->dev[i],
+                                       e_info);
+               }
+       }
+}
+
 /**
  * aer_isr_one_error - consume an error detected by root port
  * @p_device: pointer to error root port service device
@@ -754,18 +809,7 @@ static void aer_isr_one_error(struct pcie_device *p_device,
                        e_info->flags |= AER_MULTI_ERROR_VALID_FLAG;
 
                find_source_device(p_device->port, e_info);
-               if (e_info->dev == NULL) {
-                       printk(KERN_DEBUG "%s->can't find device of ID%04x\n",
-                               __func__, e_info->id);
-                       continue;
-               }
-               if (get_device_error_info(e_info->dev, e_info) ==
-                               AER_SUCCESS) {
-                       aer_print_error(e_info->dev, e_info);
-                       handle_error_source(p_device,
-                               e_info->dev,
-                               e_info);
-               }
+               aer_process_err_devices(p_device, e_info);
        }
 
        kfree(e_info);