diff mbox series

[v6,05/10] PCI/AER: Apply function level reset to RCiEP on fatal error

Message ID 20200922213859.108826-6-seanvk.dev@oregontracks.org
State Superseded
Delegated to: Bjorn Helgaas
Headers show
Series Add RCEC handling to PCI/AER | expand

Commit Message

Sean V Kelley Sept. 22, 2020, 9:38 p.m. UTC
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>

Attempt to do function level reset for an RCiEP associated with an
RCEC device on fatal error.

Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
---
 drivers/pci/pcie/err.c | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

Comments

Bjorn Helgaas Sept. 25, 2020, 9:58 p.m. UTC | #1
On Tue, Sep 22, 2020 at 02:38:54PM -0700, Sean V Kelley wrote:
> From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
> 
> Attempt to do function level reset for an RCiEP associated with an
> RCEC device on fatal error.
> 
> Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
> ---
>  drivers/pci/pcie/err.c | 31 ++++++++++++++++++++++---------
>  1 file changed, 22 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
> index e575fa6cee63..5380ecc41506 100644
> --- a/drivers/pci/pcie/err.c
> +++ b/drivers/pci/pcie/err.c
> @@ -169,6 +169,17 @@ static void pci_bridge_walk(struct pci_dev *bridge, int (*cb)(struct pci_dev *,
>  		cb(bridge, userdata);
>  }
>  
> +static pci_ers_result_t flr_on_rciep(struct pci_dev *dev)
> +{
> +	if (!pcie_has_flr(dev))
> +		return PCI_ERS_RESULT_NONE;
> +
> +	if (pcie_flr(dev))
> +		return PCI_ERS_RESULT_DISCONNECT;
> +
> +	return PCI_ERS_RESULT_RECOVERED;
> +}

Either we reset the device or we didn't; there is no third option.

If I read it correctly, nothing in pcie_do_recovery() cares about the
difference between PCI_ERS_RESULT_NONE and PCI_ERS_RESULT_DISCONNECT.
The status does get returned, but only edr_handle_event() looks at it,
and it doesn't care about the difference either.

So I think this should just return PCI_ERS_RESULT_RECOVERED or
PCI_ERS_RESULT_DISCONNECT.

>  pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
>  			pci_channel_state_t state,
>  			pci_ers_result_t (*reset_subordinate_devices)(struct pci_dev *pdev))
> @@ -195,15 +206,17 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
>  	if (state == pci_channel_io_frozen) {
>  		pci_bridge_walk(bridge, report_frozen_detected, &status);
>  		if (type == PCI_EXP_TYPE_RC_END) {
> -			pci_warn(dev, "link reset not possible for RCiEP\n");
> -			status = PCI_ERS_RESULT_NONE;
> -			goto failed;
> -		}
> -
> -		status = reset_subordinate_devices(bridge);
> -		if (status != PCI_ERS_RESULT_RECOVERED) {
> -			pci_warn(dev, "subordinate device reset failed\n");
> -			goto failed;
> +			status = flr_on_rciep(dev);
> +			if (status != PCI_ERS_RESULT_RECOVERED) {
> +				pci_warn(dev, "function level reset failed\n");
> +				goto failed;
> +			}
> +		} else {
> +			status = reset_subordinate_devices(bridge);
> +			if (status != PCI_ERS_RESULT_RECOVERED) {
> +				pci_warn(dev, "subordinate device reset failed\n");
> +				goto failed;
> +			}
>  		}
>  	} else {
>  		pci_bridge_walk(bridge, report_normal_detected, &status);
> -- 
> 2.28.0
>
Sean V Kelley Sept. 25, 2020, 10:54 p.m. UTC | #2
On 25 Sep 2020, at 14:58, Bjorn Helgaas wrote:

> On Tue, Sep 22, 2020 at 02:38:54PM -0700, Sean V Kelley wrote:
>> From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
>>
>> Attempt to do function level reset for an RCiEP associated with an
>> RCEC device on fatal error.
>>
>> Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
>> ---
>>  drivers/pci/pcie/err.c | 31 ++++++++++++++++++++++---------
>>  1 file changed, 22 insertions(+), 9 deletions(-)
>>
>> diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
>> index e575fa6cee63..5380ecc41506 100644
>> --- a/drivers/pci/pcie/err.c
>> +++ b/drivers/pci/pcie/err.c
>> @@ -169,6 +169,17 @@ static void pci_bridge_walk(struct pci_dev 
>> *bridge, int (*cb)(struct pci_dev *,
>>  		cb(bridge, userdata);
>>  }
>>
>> +static pci_ers_result_t flr_on_rciep(struct pci_dev *dev)
>> +{
>> +	if (!pcie_has_flr(dev))
>> +		return PCI_ERS_RESULT_NONE;
>> +
>> +	if (pcie_flr(dev))
>> +		return PCI_ERS_RESULT_DISCONNECT;
>> +
>> +	return PCI_ERS_RESULT_RECOVERED;
>> +}
>
> Either we reset the device or we didn't; there is no third option.
>
> If I read it correctly, nothing in pcie_do_recovery() cares about the
> difference between PCI_ERS_RESULT_NONE and PCI_ERS_RESULT_DISCONNECT.
> The status does get returned, but only edr_handle_event() looks at it,
> and it doesn't care about the difference either.
>
> So I think this should just return PCI_ERS_RESULT_RECOVERED or
> PCI_ERS_RESULT_DISCONNECT.

You raise a good point. As currently implemented, the usage requires 
either a reset or not result. Will change.

Thanks,

Sean

>
>>  pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
>>  			pci_channel_state_t state,
>>  			pci_ers_result_t (*reset_subordinate_devices)(struct pci_dev 
>> *pdev))
>> @@ -195,15 +206,17 @@ pci_ers_result_t pcie_do_recovery(struct 
>> pci_dev *dev,
>>  	if (state == pci_channel_io_frozen) {
>>  		pci_bridge_walk(bridge, report_frozen_detected, &status);
>>  		if (type == PCI_EXP_TYPE_RC_END) {
>> -			pci_warn(dev, "link reset not possible for RCiEP\n");
>> -			status = PCI_ERS_RESULT_NONE;
>> -			goto failed;
>> -		}
>> -
>> -		status = reset_subordinate_devices(bridge);
>> -		if (status != PCI_ERS_RESULT_RECOVERED) {
>> -			pci_warn(dev, "subordinate device reset failed\n");
>> -			goto failed;
>> +			status = flr_on_rciep(dev);
>> +			if (status != PCI_ERS_RESULT_RECOVERED) {
>> +				pci_warn(dev, "function level reset failed\n");
>> +				goto failed;
>> +			}
>> +		} else {
>> +			status = reset_subordinate_devices(bridge);
>> +			if (status != PCI_ERS_RESULT_RECOVERED) {
>> +				pci_warn(dev, "subordinate device reset failed\n");
>> +				goto failed;
>> +			}
>>  		}
>>  	} else {
>>  		pci_bridge_walk(bridge, report_normal_detected, &status);
>> -- 
>> 2.28.0
>>
diff mbox series

Patch

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index e575fa6cee63..5380ecc41506 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -169,6 +169,17 @@  static void pci_bridge_walk(struct pci_dev *bridge, int (*cb)(struct pci_dev *,
 		cb(bridge, userdata);
 }
 
+static pci_ers_result_t flr_on_rciep(struct pci_dev *dev)
+{
+	if (!pcie_has_flr(dev))
+		return PCI_ERS_RESULT_NONE;
+
+	if (pcie_flr(dev))
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
 pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 			pci_channel_state_t state,
 			pci_ers_result_t (*reset_subordinate_devices)(struct pci_dev *pdev))
@@ -195,15 +206,17 @@  pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	if (state == pci_channel_io_frozen) {
 		pci_bridge_walk(bridge, report_frozen_detected, &status);
 		if (type == PCI_EXP_TYPE_RC_END) {
-			pci_warn(dev, "link reset not possible for RCiEP\n");
-			status = PCI_ERS_RESULT_NONE;
-			goto failed;
-		}
-
-		status = reset_subordinate_devices(bridge);
-		if (status != PCI_ERS_RESULT_RECOVERED) {
-			pci_warn(dev, "subordinate device reset failed\n");
-			goto failed;
+			status = flr_on_rciep(dev);
+			if (status != PCI_ERS_RESULT_RECOVERED) {
+				pci_warn(dev, "function level reset failed\n");
+				goto failed;
+			}
+		} else {
+			status = reset_subordinate_devices(bridge);
+			if (status != PCI_ERS_RESULT_RECOVERED) {
+				pci_warn(dev, "subordinate device reset failed\n");
+				goto failed;
+			}
 		}
 	} else {
 		pci_bridge_walk(bridge, report_normal_detected, &status);