[v2] dmaengine: idxd: Memory leak and FLR fixes

[PATCH RESEND v2 04/10] dmaengine: idxd: Flush kernel workqueues on Function Level Reset

Posted by Vinicius Costa Gomes 3 weeks, 3 days ago

When a Function Level Reset (FLR) happens, terminate the pending
descriptors that were issued by in-kernel users and disable the
interrupts associated with those. They will be re-enabled after FLR
finishes.

idxd_wq_flush_desc() is declared on idxd.h because it's going to be
used in by the DMA backend in a future patch.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
 drivers/dma/idxd/device.c | 20 ++++++++++++++++++++
 drivers/dma/idxd/idxd.h   |  1 +
 drivers/dma/idxd/irq.c    | 16 ++++++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5265925f3076..b8422dc7d2ca 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1339,6 +1339,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
 
 	free_irq(ie->vector, ie);
 	idxd_flush_pending_descs(ie);
+
+	/* The interrupt might have been already released by FLR */
+	if (ie->int_handle == INVALID_INT_HANDLE)
+		return;
+
 	if (idxd->request_int_handles)
 		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
 	idxd_device_clear_perm_entry(idxd, ie);
@@ -1347,6 +1352,21 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
 	ie->pasid = IOMMU_PASID_INVALID;
 }
 
+void idxd_wq_flush_descs(struct idxd_wq *wq)
+{
+	struct idxd_irq_entry *ie = &wq->ie;
+	struct idxd_device *idxd = wq->idxd;
+
+	if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL)
+		return;
+
+	idxd_flush_pending_descs(ie);
+	if (idxd->request_int_handles)
+		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->int_handle = INVALID_INT_HANDLE;
+}
+
 int idxd_wq_request_irq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index ea8c4daed38d..ce78b9a7c641 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -803,6 +803,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq);
 int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
 void idxd_wq_free_irq(struct idxd_wq *wq);
 int idxd_wq_request_irq(struct idxd_wq *wq);
+void idxd_wq_flush_descs(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 1107db3ce0a3..8d0eaf5029fa 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -397,6 +397,17 @@ static void idxd_device_flr(struct work_struct *work)
 		dev_err(&idxd->pdev->dev, "FLR failed\n");
 }
 
+static void idxd_wqs_flush_descs(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		idxd_wq_flush_descs(wq);
+	}
+}
+
 static irqreturn_t idxd_halt(struct idxd_device *idxd)
 {
 	union gensts_reg gensts;
@@ -415,6 +426,11 @@ static irqreturn_t idxd_halt(struct idxd_device *idxd)
 		} else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
 			idxd->state = IDXD_DEV_HALTED;
 			idxd_mask_error_interrupts(idxd);
+			/* Flush all pending descriptors, and disable
+			 * interrupts, they will be re-enabled when FLR
+			 * concludes.
+			 */
+			idxd_wqs_flush_descs(idxd);
 			dev_dbg(&idxd->pdev->dev,
 				"idxd halted, doing FLR. After FLR, configs are restored\n");
 			INIT_WORK(&idxd->work, idxd_device_flr);

-- 
2.52.0

Re: [PATCH RESEND v2 04/10] dmaengine: idxd: Flush kernel workqueues on Function Level Reset

Posted by Dave Jiang 3 weeks, 2 days ago


On 1/15/26 3:47 PM, Vinicius Costa Gomes wrote:
> When a Function Level Reset (FLR) happens, terminate the pending
> descriptors that were issued by in-kernel users and disable the
> interrupts associated with those. They will be re-enabled after FLR
> finishes.
> 
> idxd_wq_flush_desc() is declared on idxd.h because it's going to be
> used in by the DMA backend in a future patch.
> 
> Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
> ---
>  drivers/dma/idxd/device.c | 20 ++++++++++++++++++++
>  drivers/dma/idxd/idxd.h   |  1 +
>  drivers/dma/idxd/irq.c    | 16 ++++++++++++++++
>  3 files changed, 37 insertions(+)
> 
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
> index 5265925f3076..b8422dc7d2ca 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -1339,6 +1339,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
>  
>  	free_irq(ie->vector, ie);
>  	idxd_flush_pending_descs(ie);
> +
> +	/* The interrupt might have been already released by FLR */
> +	if (ie->int_handle == INVALID_INT_HANDLE)
> +		return;
> +
>  	if (idxd->request_int_handles)
>  		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
>  	idxd_device_clear_perm_entry(idxd, ie);
> @@ -1347,6 +1352,21 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
>  	ie->pasid = IOMMU_PASID_INVALID;
>  }
>  
> +void idxd_wq_flush_descs(struct idxd_wq *wq)
> +{
> +	struct idxd_irq_entry *ie = &wq->ie;
> +	struct idxd_device *idxd = wq->idxd;
> +
Should it take a wq lock for this function?

DJ

> +	if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL)
> +		return;
> +
> +	idxd_flush_pending_descs(ie);
> +	if (idxd->request_int_handles)
> +		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
> +	idxd_device_clear_perm_entry(idxd, ie);
> +	ie->int_handle = INVALID_INT_HANDLE;
> +}
> +
>  int idxd_wq_request_irq(struct idxd_wq *wq)
>  {
>  	struct idxd_device *idxd = wq->idxd;
> diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
> index ea8c4daed38d..ce78b9a7c641 100644
> --- a/drivers/dma/idxd/idxd.h
> +++ b/drivers/dma/idxd/idxd.h
> @@ -803,6 +803,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq);
>  int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
>  void idxd_wq_free_irq(struct idxd_wq *wq);
>  int idxd_wq_request_irq(struct idxd_wq *wq);
> +void idxd_wq_flush_descs(struct idxd_wq *wq);
>  
>  /* submission */
>  int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
> diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
> index 1107db3ce0a3..8d0eaf5029fa 100644
> --- a/drivers/dma/idxd/irq.c
> +++ b/drivers/dma/idxd/irq.c
> @@ -397,6 +397,17 @@ static void idxd_device_flr(struct work_struct *work)
>  		dev_err(&idxd->pdev->dev, "FLR failed\n");
>  }
>  
> +static void idxd_wqs_flush_descs(struct idxd_device *idxd)
> +{
> +	int i;
> +
> +	for (i = 0; i < idxd->max_wqs; i++) {
> +		struct idxd_wq *wq = idxd->wqs[i];
> +
> +		idxd_wq_flush_descs(wq);
> +	}
> +}
> +
>  static irqreturn_t idxd_halt(struct idxd_device *idxd)
>  {
>  	union gensts_reg gensts;
> @@ -415,6 +426,11 @@ static irqreturn_t idxd_halt(struct idxd_device *idxd)
>  		} else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
>  			idxd->state = IDXD_DEV_HALTED;
>  			idxd_mask_error_interrupts(idxd);
> +			/* Flush all pending descriptors, and disable
> +			 * interrupts, they will be re-enabled when FLR
> +			 * concludes.
> +			 */
> +			idxd_wqs_flush_descs(idxd);
>  			dev_dbg(&idxd->pdev->dev,
>  				"idxd halted, doing FLR. After FLR, configs are restored\n");
>  			INIT_WORK(&idxd->work, idxd_device_flr);
>

Re: [PATCH RESEND v2 04/10] dmaengine: idxd: Flush kernel workqueues on Function Level Reset

Posted by Vinicius Costa Gomes 3 weeks, 2 days ago

Dave Jiang <dave.jiang@intel.com> writes:

> On 1/15/26 3:47 PM, Vinicius Costa Gomes wrote:
>> When a Function Level Reset (FLR) happens, terminate the pending
>> descriptors that were issued by in-kernel users and disable the
>> interrupts associated with those. They will be re-enabled after FLR
>> finishes.
>> 
>> idxd_wq_flush_desc() is declared on idxd.h because it's going to be
>> used in by the DMA backend in a future patch.
>> 
>> Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
>> ---
>>  drivers/dma/idxd/device.c | 20 ++++++++++++++++++++
>>  drivers/dma/idxd/idxd.h   |  1 +
>>  drivers/dma/idxd/irq.c    | 16 ++++++++++++++++
>>  3 files changed, 37 insertions(+)
>> 
>> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
>> index 5265925f3076..b8422dc7d2ca 100644
>> --- a/drivers/dma/idxd/device.c
>> +++ b/drivers/dma/idxd/device.c
>> @@ -1339,6 +1339,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
>>  
>>  	free_irq(ie->vector, ie);
>>  	idxd_flush_pending_descs(ie);
>> +
>> +	/* The interrupt might have been already released by FLR */
>> +	if (ie->int_handle == INVALID_INT_HANDLE)
>> +		return;
>> +
>>  	if (idxd->request_int_handles)
>>  		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
>>  	idxd_device_clear_perm_entry(idxd, ie);
>> @@ -1347,6 +1352,21 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
>>  	ie->pasid = IOMMU_PASID_INVALID;
>>  }
>>  
>> +void idxd_wq_flush_descs(struct idxd_wq *wq)
>> +{
>> +	struct idxd_irq_entry *ie = &wq->ie;
>> +	struct idxd_device *idxd = wq->idxd;
>> +
> Should it take a wq lock for this function?
>

Good catch. Will take a another look and see if I am missing any locks
elsewhere.


Cheers,
-- 
Vinicius