[net-2.6 PATCH 0/2] qlge: Fixes for qlge.

[net-2.6 PATCH 0/2] qlge: Fixes for qlge.

[Ron Mercer]

Fix EEH and firmware mailbox command processor.

[net-2.6 PATCH 1/2] qlge: Fix EEH handling.

[Ron Mercer]

Clean up driver resources without touch the hardware. Add pci
save/restore state.

Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
---
 drivers/net/qlge/qlge_main.c |   78 ++++++++++++++++++++++++++++--------------
 1 files changed, 52 insertions(+), 26 deletions(-)

diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c
index 48b45df..cea7531 100644
--- a/drivers/net/qlge/qlge_main.c
+++ b/drivers/net/qlge/qlge_main.c
@@ -3916,6 +3916,7 @@ static int __devinit ql_init_device(struct pci_dev *pdev,
 		goto err_out;
 	}
 
+	pci_save_state(pdev);
 	qdev->reg_base =
 	    ioremap_nocache(pci_resource_start(pdev, 1),
 			    pci_resource_len(pdev, 1));
@@ -4070,6 +4071,33 @@ 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 +4106,21 @@ 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 +4137,15 @@ 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 +4153,21 @@ 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);
 }
 
-- 
1.6.0.2

[net-2.6 PATCH 2/2] qlge: Fix firmware mailbox command timeout.

[Ron Mercer]

The mailbox command process would only process a maximum of 5 unrelated
firmware events while waiting for it's command completion status.
It should process an unlimited number of events while waiting for a maximum of 5 seconds.

Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
---
 drivers/net/qlge/qlge.h     |    1 +
 drivers/net/qlge/qlge_mpi.c |   23 ++++++++++++-----------
 2 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h
index e7285f0..c2383ad 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_mpi.c b/drivers/net/qlge/qlge_mpi.c
index 99e58e3..bcf13c9 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 */
@@ -491,9 +492,9 @@ 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);
@@ -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.
-- 
1.6.0.2

Re: [net-2.6 PATCH 0/2] qlge: Fixes for qlge.

[David Miller]

From: Ron Mercer <ron.mercer@qlogic.com>
Date: Wed, 28 Oct 2009 11:39:19 -0700

> Fix EEH and firmware mailbox command processor.

Both applied to net-2.6, thanks Ron.