[PATCH] ibmvnic: Clear pending interrupt after device reset

[PATCH] ibmvnic: Clear pending interrupt after device reset

[Thomas Falcon]

Due to a firmware bug, the hypervisor can send an interrupt to a
transmit or receive queue just prior to a partition migration, not
allowing the device enough time to handle it and send an EOI. When
the partition migrates, the interrupt is lost but an "EOI-pending"
flag for the interrupt line is still set in firmware. No further
interrupts will be sent until that flag is cleared, effectively
freezing that queue. To workaround this, the driver will disable the
hardware interrupt and send an H_EOI signal prior to re-enabling it.
This will flush the pending EOI and allow the driver to continue
operation.

Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index f84a920..ef7995fc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1034,16 +1034,14 @@ static int __ibmvnic_open(struct net_device *netdev)
 		netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i);
 		if (prev_state == VNIC_CLOSED)
 			enable_irq(adapter->rx_scrq[i]->irq);
-		else
-			enable_scrq_irq(adapter, adapter->rx_scrq[i]);
+		enable_scrq_irq(adapter, adapter->rx_scrq[i]);
 	}
 
 	for (i = 0; i < adapter->req_tx_queues; i++) {
 		netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i);
 		if (prev_state == VNIC_CLOSED)
 			enable_irq(adapter->tx_scrq[i]->irq);
-		else
-			enable_scrq_irq(adapter, adapter->tx_scrq[i]);
+		enable_scrq_irq(adapter, adapter->tx_scrq[i]);
 	}
 
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
@@ -1184,6 +1182,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
 			if (adapter->tx_scrq[i]->irq) {
 				netdev_dbg(netdev,
 					   "Disabling tx_scrq[%d] irq\n", i);
+				disable_scrq_irq(adapter, adapter->tx_scrq[i]);
 				disable_irq(adapter->tx_scrq[i]->irq);
 			}
 	}
@@ -1193,6 +1192,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
 			if (adapter->rx_scrq[i]->irq) {
 				netdev_dbg(netdev,
 					   "Disabling rx_scrq[%d] irq\n", i);
+				disable_scrq_irq(adapter, adapter->rx_scrq[i]);
 				disable_irq(adapter->rx_scrq[i]->irq);
 			}
 		}
@@ -2601,12 +2601,19 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 {
 	struct device *dev = &adapter->vdev->dev;
 	unsigned long rc;
+	u64 val;
 
 	if (scrq->hw_irq > 0x100000000ULL) {
 		dev_err(dev, "bad hw_irq = %lx\n", scrq->hw_irq);
 		return 1;
 	}
 
+	val = (0xff000000) | scrq->hw_irq;
+	rc = plpar_hcall_norets(H_EOI, val);
+	if (rc)
+		dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
+			val, rc);
+
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
 				H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
 	if (rc)
-- 
1.8.3.1

Re: [PATCH] ibmvnic: Clear pending interrupt after device reset

[David Miller]

From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Sun, 15 Apr 2018 18:53:36 -0500

> Due to a firmware bug, the hypervisor can send an interrupt to a
> transmit or receive queue just prior to a partition migration, not
> allowing the device enough time to handle it and send an EOI. When
> the partition migrates, the interrupt is lost but an "EOI-pending"
> flag for the interrupt line is still set in firmware. No further
> interrupts will be sent until that flag is cleared, effectively
> freezing that queue. To workaround this, the driver will disable the
> hardware interrupt and send an H_EOI signal prior to re-enabling it.
> This will flush the pending EOI and allow the driver to continue
> operation.
> 
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>

Hey Thomas, I see two copies of this patch posted.  Any special
reason for that?

Thanks.

Re: [PATCH] ibmvnic: Clear pending interrupt after device reset

[Thomas Falcon]

On 04/15/2018 07:55 PM, David Miller wrote:
> From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
> Date: Sun, 15 Apr 2018 18:53:36 -0500
>
>> Due to a firmware bug, the hypervisor can send an interrupt to a
>> transmit or receive queue just prior to a partition migration, not
>> allowing the device enough time to handle it and send an EOI. When
>> the partition migrates, the interrupt is lost but an "EOI-pending"
>> flag for the interrupt line is still set in firmware. No further
>> interrupts will be sent until that flag is cleared, effectively
>> freezing that queue. To workaround this, the driver will disable the
>> hardware interrupt and send an H_EOI signal prior to re-enabling it.
>> This will flush the pending EOI and allow the driver to continue
>> operation.
>>
>> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
> Hey Thomas, I see two copies of this patch posted.  Any special
> reason for that?
>
> Thanks.
>
Sorry, I misspelled one of the email addresses and mistakenly resent it.  Please ignore this one.

Re: [PATCH] ibmvnic: Clear pending interrupt after device reset

[David Miller]

From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Sun, 15 Apr 2018 18:53:36 -0500

> Due to a firmware bug, the hypervisor can send an interrupt to a
> transmit or receive queue just prior to a partition migration, not
> allowing the device enough time to handle it and send an EOI. When
> the partition migrates, the interrupt is lost but an "EOI-pending"
> flag for the interrupt line is still set in firmware. No further
> interrupts will be sent until that flag is cleared, effectively
> freezing that queue. To workaround this, the driver will disable the
> hardware interrupt and send an H_EOI signal prior to re-enabling it.
> This will flush the pending EOI and allow the driver to continue
> operation.
> 
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>

Applied, thanks Thomas.

Re: [PATCH] ibmvnic: Clear pending interrupt after device reset

[Thomas Falcon]

On 04/15/2018 06:27 PM, Thomas Falcon wrote:
> Due to a firmware bug, the hypervisor can send an interrupt to a
> transmit or receive queue just prior to a partition migration, not
> allowing the device enough time to handle it and send an EOI. When
> the partition migrates, the interrupt is lost but an "EOI-pending"
> flag for the interrupt line is still set in firmware. No further
> interrupts will be sent until that flag is cleared, effectively
> freezing that queue. To workaround this, the driver will disable the
> hardware interrupt and send an H_EOI signal prior to re-enabling it.
> This will flush the pending EOI and allow the driver to continue
> operation.

Excuse me, I misspelled the linuxppc-dev email address.

Tom

> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
> ---
>  drivers/net/ethernet/ibm/ibmvnic.c | 15 +++++++++++----
>  1 file changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
> index f84a920..ef7995fc 100644
> --- a/drivers/net/ethernet/ibm/ibmvnic.c
> +++ b/drivers/net/ethernet/ibm/ibmvnic.c
> @@ -1034,16 +1034,14 @@ static int __ibmvnic_open(struct net_device *netdev)
>  		netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i);
>  		if (prev_state == VNIC_CLOSED)
>  			enable_irq(adapter->rx_scrq[i]->irq);
> -		else
> -			enable_scrq_irq(adapter, adapter->rx_scrq[i]);
> +		enable_scrq_irq(adapter, adapter->rx_scrq[i]);
>  	}
>
>  	for (i = 0; i < adapter->req_tx_queues; i++) {
>  		netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i);
>  		if (prev_state == VNIC_CLOSED)
>  			enable_irq(adapter->tx_scrq[i]->irq);
> -		else
> -			enable_scrq_irq(adapter, adapter->tx_scrq[i]);
> +		enable_scrq_irq(adapter, adapter->tx_scrq[i]);
>  	}
>
>  	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
> @@ -1184,6 +1182,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
>  			if (adapter->tx_scrq[i]->irq) {
>  				netdev_dbg(netdev,
>  					   "Disabling tx_scrq[%d] irq\n", i);
> +				disable_scrq_irq(adapter, adapter->tx_scrq[i]);
>  				disable_irq(adapter->tx_scrq[i]->irq);
>  			}
>  	}
> @@ -1193,6 +1192,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
>  			if (adapter->rx_scrq[i]->irq) {
>  				netdev_dbg(netdev,
>  					   "Disabling rx_scrq[%d] irq\n", i);
> +				disable_scrq_irq(adapter, adapter->rx_scrq[i]);
>  				disable_irq(adapter->rx_scrq[i]->irq);
>  			}
>  		}
> @@ -2601,12 +2601,19 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
>  {
>  	struct device *dev = &adapter->vdev->dev;
>  	unsigned long rc;
> +	u64 val;
>
>  	if (scrq->hw_irq > 0x100000000ULL) {
>  		dev_err(dev, "bad hw_irq = %lx\n", scrq->hw_irq);
>  		return 1;
>  	}
>
> +	val = (0xff000000) | scrq->hw_irq;
> +	rc = plpar_hcall_norets(H_EOI, val);
> +	if (rc)
> +		dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
> +			val, rc);
> +
>  	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
>  				H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
>  	if (rc)