3 files changed, 68 insertions, 38 deletions

diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h
index e7285f01bd04..c2383adcd527 100644
--- a/drivers/net/qlge/qlge.h
+++ b/drivers/net/qlge/qlge.h
@@ -95,6 +95,7 @@ enum {
 
         /* Misc. stuff */
         MAILBOX_COUNT = 16,
+        MAILBOX_TIMEOUT = 5,
 
         PROC_ADDR_RDY = (1 << 31),
         PROC_ADDR_R = (1 << 30),
diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c
index 48b45df85ec9..a2fc70a0d0cc 100644
--- a/drivers/net/qlge/qlge_main.c
+++ b/drivers/net/qlge/qlge_main.c
@@ -3916,6 +3916,9 @@ static int __devinit ql_init_device(struct pci_dev *pdev,
                 goto err_out;
         }
 
+        /* Set PCIe reset type for EEH to fundamental. */
+        pdev->needs_freset = 1;
+        pci_save_state(pdev);
         qdev->reg_base =
             ioremap_nocache(pci_resource_start(pdev, 1),
                             pci_resource_len(pdev, 1));
@@ -4070,6 +4073,33 @@ static void __devexit qlge_remove(struct pci_dev *pdev)
         free_netdev(ndev);
 }
 
+/* Clean up resources without touching hardware. */
+static void ql_eeh_close(struct net_device *ndev)
+{
+        int i;
+        struct ql_adapter *qdev = netdev_priv(ndev);
+
+        if (netif_carrier_ok(ndev)) {
+                netif_carrier_off(ndev);
+                netif_stop_queue(ndev);
+        }
+
+        if (test_bit(QL_ADAPTER_UP, &qdev->flags))
+                cancel_delayed_work_sync(&qdev->asic_reset_work);
+        cancel_delayed_work_sync(&qdev->mpi_reset_work);
+        cancel_delayed_work_sync(&qdev->mpi_work);
+        cancel_delayed_work_sync(&qdev->mpi_idc_work);
+        cancel_delayed_work_sync(&qdev->mpi_port_cfg_work);
+
+        for (i = 0; i < qdev->rss_ring_count; i++)
+                netif_napi_del(&qdev->rx_ring[i].napi);
+
+        clear_bit(QL_ADAPTER_UP, &qdev->flags);
+        ql_tx_ring_clean(qdev);
+        ql_free_rx_buffers(qdev);
+        ql_release_adapter_resources(qdev);
+}
+
 /*
  * This callback is called by the PCI subsystem whenever
  * a PCI bus error is detected.
@@ -4078,17 +4108,21 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev,
                                                enum pci_channel_state state)
 {
         struct net_device *ndev = pci_get_drvdata(pdev);
-        struct ql_adapter *qdev = netdev_priv(ndev);
-
-        netif_device_detach(ndev);
 
-        if (state == pci_channel_io_perm_failure)
+        switch (state) {
+        case pci_channel_io_normal:
+                return PCI_ERS_RESULT_CAN_RECOVER;
+        case pci_channel_io_frozen:
+                netif_device_detach(ndev);
+                if (netif_running(ndev))
+                        ql_eeh_close(ndev);
+                pci_disable_device(pdev);
+                return PCI_ERS_RESULT_NEED_RESET;
+        case pci_channel_io_perm_failure:
+                dev_err(&pdev->dev,
+                        "%s: pci_channel_io_perm_failure.\n", __func__);
                 return PCI_ERS_RESULT_DISCONNECT;
-
-        if (netif_running(ndev))
-                ql_adapter_down(qdev);
-
-        pci_disable_device(pdev);
+        }
 
         /* Request a slot reset. */
         return PCI_ERS_RESULT_NEED_RESET;
@@ -4105,25 +4139,15 @@ static pci_ers_result_t qlge_io_slot_reset(struct pci_dev *pdev)
         struct net_device *ndev = pci_get_drvdata(pdev);
         struct ql_adapter *qdev = netdev_priv(ndev);
 
+        pdev->error_state = pci_channel_io_normal;
+
+        pci_restore_state(pdev);
         if (pci_enable_device(pdev)) {
                 QPRINTK(qdev, IFUP, ERR,
                         "Cannot re-enable PCI device after reset.\n");
                 return PCI_ERS_RESULT_DISCONNECT;
         }
-
         pci_set_master(pdev);
-
-        netif_carrier_off(ndev);
-        ql_adapter_reset(qdev);
-
-        /* Make sure the EEPROM is good */
-        memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len);
-
-        if (!is_valid_ether_addr(ndev->perm_addr)) {
-                QPRINTK(qdev, IFUP, ERR, "After reset, invalid MAC address.\n");
-                return PCI_ERS_RESULT_DISCONNECT;
-        }
-
         return PCI_ERS_RESULT_RECOVERED;
 }
 
@@ -4131,17 +4155,21 @@ static void qlge_io_resume(struct pci_dev *pdev)
 {
         struct net_device *ndev = pci_get_drvdata(pdev);
         struct ql_adapter *qdev = netdev_priv(ndev);
+        int err = 0;
 
-        pci_set_master(pdev);
-
+        if (ql_adapter_reset(qdev))
+                QPRINTK(qdev, DRV, ERR, "reset FAILED!\n");
         if (netif_running(ndev)) {
-                if (ql_adapter_up(qdev)) {
+                err = qlge_open(ndev);
+                if (err) {
                         QPRINTK(qdev, IFUP, ERR,
                                 "Device initialization failed after reset.\n");
                         return;
                 }
+        } else {
+                QPRINTK(qdev, IFUP, ERR,
+                        "Device was not running prior to EEH.\n");
         }
-
         netif_device_attach(ndev);
 }
 
diff --git a/drivers/net/qlge/qlge_mpi.c b/drivers/net/qlge/qlge_mpi.c
index 99e58e3f8e22..aec05f266107 100644
--- a/drivers/net/qlge/qlge_mpi.c
+++ b/drivers/net/qlge/qlge_mpi.c
@@ -470,7 +470,8 @@ end:
  */
 static int ql_mailbox_command(struct ql_adapter *qdev, struct mbox_params *mbcp)
 {
-        int status, count;
+        int status;
+        unsigned long count;
 
 
         /* Begin polled mode for MPI */
@@ -491,14 +492,14 @@ static int ql_mailbox_command(struct ql_adapter *qdev, struct mbox_params *mbcp)
         /* Wait for the command to complete. We loop
          * here because some AEN might arrive while
          * we're waiting for the mailbox command to
-         * complete. If more than 5 arrive then we can
+         * complete. If more than 5 seconds expire we can
          * assume something is wrong. */
-        count = 5;
+        count = jiffies + HZ * MAILBOX_TIMEOUT;
         do {
                 /* Wait for the interrupt to come in. */
                 status = ql_wait_mbx_cmd_cmplt(qdev);
                 if (status)
-                        goto end;
+                        continue;
 
                 /* Process the event.  If it's an AEN, it
                  * will be handled in-line or a worker
@@ -517,15 +518,15 @@ static int ql_mailbox_command(struct ql_adapter *qdev, struct mbox_params *mbcp)
                                         MB_CMD_STS_GOOD) ||
                         ((mbcp->mbox_out[0] & 0x0000f000) ==
                                         MB_CMD_STS_INTRMDT))
-                        break;
-        } while (--count);
+                        goto done;
+        } while (time_before(jiffies, count));
 
-        if (!count) {
-                QPRINTK(qdev, DRV, ERR,
-                        "Timed out waiting for mailbox complete.\n");
-                status = -ETIMEDOUT;
-                goto end;
-        }
+        QPRINTK(qdev, DRV, ERR,
+                "Timed out waiting for mailbox complete.\n");
+        status = -ETIMEDOUT;
+        goto end;
+
+done:
 
         /* Now we can clear the interrupt condition
          * and look at our status.