diff mbox series

[v2,5/8] capp/phb4: Force CAPP to PCIe mode during kernel shutdown

Message ID 20181209141744.4787-6-vaibhav@linux.ibm.com
State Superseded
Headers show
Series Enable fast-reboot support for CAPI-2 | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch success master/apply_patch Successfully applied
snowpatch_ozlabs/snowpatch_job_snowpatch-skiboot success Test snowpatch/job/snowpatch-skiboot on branch master

Commit Message

Vaibhav Jain Dec. 9, 2018, 2:17 p.m. UTC
This patch introduces a new opal syncer for PHB4 named
phb4_host_sync_reset(). We register this opal syncer when CAPP is
activated successfully in phb4_set_capi_mode() so that it will be
called at kernel shutdown during fast-reset.

During kernel shutdown the function will then repeatedly call
phb->ops->set_capi_mode() to switch switch CAPP to PCIe mode. In case
set_capi_mode() indicates its OPAL_BUSY, which indicates that CAPP is
still transitioning to new state; it calls slot->ops.run_sm() to
ensure that Opal slot reset state machine makes forward progress.

Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
---
 hw/phb4.c | 39 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 37 insertions(+), 2 deletions(-)

Comments

Andrew Donnellan Dec. 10, 2018, 5:18 a.m. UTC | #1
On 10/12/18 1:17 am, Vaibhav Jain wrote:
> This patch introduces a new opal syncer for PHB4 named
> phb4_host_sync_reset(). We register this opal syncer when CAPP is
> activated successfully in phb4_set_capi_mode() so that it will be
> called at kernel shutdown during fast-reset.
> 
> During kernel shutdown the function will then repeatedly call
> phb->ops->set_capi_mode() to switch switch CAPP to PCIe mode. In case
> set_capi_mode() indicates its OPAL_BUSY, which indicates that CAPP is
> still transitioning to new state; it calls slot->ops.run_sm() to
> ensure that Opal slot reset state machine makes forward progress.
> 
> Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
> ---
>   hw/phb4.c | 39 +++++++++++++++++++++++++++++++++++++--
>   1 file changed, 37 insertions(+), 2 deletions(-)
> 
> diff --git a/hw/phb4.c b/hw/phb4.c
> index df483e27..97c77a89 100644
> --- a/hw/phb4.c
> +++ b/hw/phb4.c
> @@ -2768,6 +2768,37 @@ static void phb4_training_trace(struct phb4 *p)
>   	}
>   }
>   
> +/*
> + * This helper is called repeatedly by the host sync notifier mechanism, which
> + * relies on the kernel to regularly poll the OPAL_SYNC_HOST_REBOOT call as it
> + * shuts down.
> + */
> +static bool phb4_host_sync_reset(void *data)
> +{
> +	struct phb4 *p = (struct phb4 *)data;
> +	struct phb *phb = &p->phb;
> +	int64_t rc = 0;
> +
> +	/* Make sure no-one modifies the phb flags while we are active */
> +	phb_lock(phb);
> +
> +	/* Make sure CAPP is attached to the PHB */
> +	if (phb->capp)
> +		/* Call phb ops to disable capi */
> +		rc = phb->ops->set_capi_mode(phb, OPAL_PHB_CAPI_MODE_PCIE,
> +				       phb->capp->attached_pe);
> +	else
> +		rc = OPAL_SUCCESS;

This code is fine, but I'm assuming that set_capi_mode() will still 
return OPAL_SUCCESS if the CAPP isn't attached, right?

...

>   static int64_t phb4_poll_link(struct pci_slot *slot)
>   {
>   	struct phb4 *p = phb_to_phb4(slot->phb);
> @@ -4419,7 +4450,7 @@ static int64_t phb4_init_capp(struct phb4 *p)
>   		capp->capp_xscom_offset = CAPP1_REG_OFFSET;
>   	}
>   
> -	capp->attached_pe = phb4_get_reserved_pe_number(phb);
> +	capp->attached_pe = phb4_get_reserved_pe_number(&p->phb);
>   
>   	/* Load capp microcode into the capp unit */
>   	load_capp_ucode(p);
> @@ -4462,7 +4493,8 @@ static int64_t phb4_set_capi_mode(struct phb *phb, uint64_t mode,
>   			break;
>   		}
>   
> -		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL + offset, &reg);
> +		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL +
> +			   capp->capp_xscom_offset, &reg);

These two hunks need to be moved to previous patches - snowpatch is 
reporting this breaks bisection.

With that fixed:

Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>

>   		if ((reg & PPC_BIT(5))) {
>   			PHBERR(p, "CAPP: recovery failed (%016llx)\n", reg);
>   			ret = OPAL_HARDWARE;
> @@ -4492,6 +4524,9 @@ static int64_t phb4_set_capi_mode(struct phb *phb, uint64_t mode,
>   					       CAPP_MAX_STQ_ENGINES |
>   					       CAPP_MIN_DMA_READ_ENGINES);
>   		if (ret == OPAL_SUCCESS) {
> +			/* register notification on system shutdown */
> +			opal_add_host_sync_notifier(&phb4_host_sync_reset, p);
> +
>   			/* Disable fast reboot for CAPP */
>   			disable_fast_reboot("CAPP being enabled");
>   		} else {
>
Vaibhav Jain Dec. 10, 2018, 7:04 a.m. UTC | #2
Andrew Donnellan <andrew.donnellan@au1.ibm.com> writes:

>> +static bool phb4_host_sync_reset(void *data)
>> +{
>> +	struct phb4 *p = (struct phb4 *)data;
>> +	struct phb *phb = &p->phb;
>> +	int64_t rc = 0;
>> +
>> +	/* Make sure no-one modifies the phb flags while we are active */
>> +	phb_lock(phb);
>> +
>> +	/* Make sure CAPP is attached to the PHB */
>> +	if (phb->capp)
>> +		/* Call phb ops to disable capi */
>> +		rc = phb->ops->set_capi_mode(phb, OPAL_PHB_CAPI_MODE_PCIE,
>> +				       phb->capp->attached_pe);
>> +	else
>> +		rc = OPAL_SUCCESS;
>
> This code is fine, but I'm assuming that set_capi_mode() will still 
> return OPAL_SUCCESS if the CAPP isn't attached, right?

No, with phb->capp un-initialized phb4_set_capi_mode() will return
OPAL_UNSUPPORTED and opal_sync_host_reboot() will return OPAL_BUSY_EVENT
back to kernel which will then continue to call opal_sync_host_reboot()

> ...
>
>>   static int64_t phb4_poll_link(struct pci_slot *slot)
>>   {
>>   	struct phb4 *p = phb_to_phb4(slot->phb);
>> @@ -4419,7 +4450,7 @@ static int64_t phb4_init_capp(struct phb4 *p)
>>   		capp->capp_xscom_offset = CAPP1_REG_OFFSET;
>>   	}
>>   
>> -	capp->attached_pe = phb4_get_reserved_pe_number(phb);
>> +	capp->attached_pe = phb4_get_reserved_pe_number(&p->phb);
>>   
>>   	/* Load capp microcode into the capp unit */
>>   	load_capp_ucode(p);
>> @@ -4462,7 +4493,8 @@ static int64_t phb4_set_capi_mode(struct phb *phb, uint64_t mode,
>>   			break;
>>   		}
>>   
>> -		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL + offset, &reg);
>> +		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL +
>> +			   capp->capp_xscom_offset, &reg);
>
> These two hunks need to be moved to previous patches - snowpatch is 
> reporting this breaks bisection.
Thanks for pointing this out. I will get it fixed

>
> With that fixed:
>
> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Thanks,
diff mbox series

Patch

diff --git a/hw/phb4.c b/hw/phb4.c
index df483e27..97c77a89 100644
--- a/hw/phb4.c
+++ b/hw/phb4.c
@@ -2768,6 +2768,37 @@  static void phb4_training_trace(struct phb4 *p)
 	}
 }
 
+/*
+ * This helper is called repeatedly by the host sync notifier mechanism, which
+ * relies on the kernel to regularly poll the OPAL_SYNC_HOST_REBOOT call as it
+ * shuts down.
+ */
+static bool phb4_host_sync_reset(void *data)
+{
+	struct phb4 *p = (struct phb4 *)data;
+	struct phb *phb = &p->phb;
+	int64_t rc = 0;
+
+	/* Make sure no-one modifies the phb flags while we are active */
+	phb_lock(phb);
+
+	/* Make sure CAPP is attached to the PHB */
+	if (phb->capp)
+		/* Call phb ops to disable capi */
+		rc = phb->ops->set_capi_mode(phb, OPAL_PHB_CAPI_MODE_PCIE,
+				       phb->capp->attached_pe);
+	else
+		rc = OPAL_SUCCESS;
+
+	/* Continue kicking state-machine if in middle of a mode transition */
+	if (rc == OPAL_BUSY)
+		rc = phb->slot->ops.run_sm(phb->slot);
+
+	phb_unlock(phb);
+
+	return rc <= OPAL_SUCCESS;
+}
+
 static int64_t phb4_poll_link(struct pci_slot *slot)
 {
 	struct phb4 *p = phb_to_phb4(slot->phb);
@@ -4419,7 +4450,7 @@  static int64_t phb4_init_capp(struct phb4 *p)
 		capp->capp_xscom_offset = CAPP1_REG_OFFSET;
 	}
 
-	capp->attached_pe = phb4_get_reserved_pe_number(phb);
+	capp->attached_pe = phb4_get_reserved_pe_number(&p->phb);
 
 	/* Load capp microcode into the capp unit */
 	load_capp_ucode(p);
@@ -4462,7 +4493,8 @@  static int64_t phb4_set_capi_mode(struct phb *phb, uint64_t mode,
 			break;
 		}
 
-		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL + offset, &reg);
+		xscom_read(p->chip_id, CAPP_ERR_STATUS_CTRL +
+			   capp->capp_xscom_offset, &reg);
 		if ((reg & PPC_BIT(5))) {
 			PHBERR(p, "CAPP: recovery failed (%016llx)\n", reg);
 			ret = OPAL_HARDWARE;
@@ -4492,6 +4524,9 @@  static int64_t phb4_set_capi_mode(struct phb *phb, uint64_t mode,
 					       CAPP_MAX_STQ_ENGINES |
 					       CAPP_MIN_DMA_READ_ENGINES);
 		if (ret == OPAL_SUCCESS) {
+			/* register notification on system shutdown */
+			opal_add_host_sync_notifier(&phb4_host_sync_reset, p);
+
 			/* Disable fast reboot for CAPP */
 			disable_fast_reboot("CAPP being enabled");
 		} else {