[3/3] dmaengine: idxd: Do not call DMX TX callbacks during workqueue disable

  On driver unload any pending descriptors are flushed and pending
DMA descriptors are explicitly completed:
idxd_dmaengine_drv_remove() ->
	drv_disable_wq() ->
		idxd_wq_free_irq() ->
			idxd_flush_pending_descs() ->
				idxd_dma_complete_txd()

With this done during driver unload any remaining descriptor is
likely stuck and can be dropped. Even so, the descriptor may still
have a callback set that could no longer be accessible. An
example of such a problem is when the dmatest fails and the dmatest
module is unloaded. The failure of dmatest leaves descriptors with
dma_async_tx_descriptor::callback pointing to code that no longer
exist. This causes a page fault as below at the time the IDXD driver
is unloaded when it attempts to run the callback:
 BUG: unable to handle page fault for address: ffffffffc0665190
 #PF: supervisor instruction fetch in kernel mode
 #PF: error_code(0x0010) - not-present page

Fix this by clearing the callback pointers on the transmit
descriptors only when workqueue is disabled.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
---

History of refactoring made the Fixes: hard to identify by me.

 drivers/dma/idxd/device.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
  

On 12/2/2022 11:25 AM, Reinette Chatre wrote:
> On driver unload any pending descriptors are flushed and pending
> DMA descriptors are explicitly completed:
> idxd_dmaengine_drv_remove() ->
> 	drv_disable_wq() ->
> 		idxd_wq_free_irq() ->
> 			idxd_flush_pending_descs() ->
> 				idxd_dma_complete_txd()
> 
> With this done during driver unload any remaining descriptor is
> likely stuck and can be dropped. Even so, the descriptor may still
> have a callback set that could no longer be accessible. An
> example of such a problem is when the dmatest fails and the dmatest
> module is unloaded. The failure of dmatest leaves descriptors with
> dma_async_tx_descriptor::callback pointing to code that no longer
> exist. This causes a page fault as below at the time the IDXD driver
> is unloaded when it attempts to run the callback:
>   BUG: unable to handle page fault for address: ffffffffc0665190
>   #PF: supervisor instruction fetch in kernel mode
>   #PF: error_code(0x0010) - not-present page
> 
> Fix this by clearing the callback pointers on the transmit
> descriptors only when workqueue is disabled.
> 
> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>

> ---
> 
> History of refactoring made the Fixes: hard to identify by me.
> 
>   drivers/dma/idxd/device.c | 10 ++++++++++
>   1 file changed, 10 insertions(+)
> 
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
> index b4d7bb923a40..2ac71a34fa34 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -1156,6 +1156,7 @@ int idxd_device_load_config(struct idxd_device *idxd)
>   
>   static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
>   {
> +	struct dma_async_tx_descriptor *tx;
>   	struct idxd_desc *desc, *itr;
>   	struct llist_node *head;
>   	LIST_HEAD(flist);
> @@ -1175,6 +1176,15 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
>   	list_for_each_entry_safe(desc, itr, &flist, list) {
>   		list_del(&desc->list);
>   		ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
> +		/*
> +		 * wq is being disabled. Any remaining descriptors are
> +		 * likely to be stuck and can be dropped. callback could
> +		 * point to code that is no longer accessible, for example
> +		 * if dmatest module has been unloaded.
> +		 */
> +		tx = &desc->txd;
> +		tx->callback = NULL;
> +		tx->callback_result = NULL;
>   		idxd_dma_complete_txd(desc, ctype, true);
>   	}
>   }
  

Hi, Reinette,

> On driver unload any pending descriptors are flushed and pending DMA
> descriptors are explicitly completed:
> idxd_dmaengine_drv_remove() ->
> 	drv_disable_wq() ->
> 		idxd_wq_free_irq() ->
> 			idxd_flush_pending_descs() ->
> 				idxd_dma_complete_txd()
> 
> With this done during driver unload any remaining descriptor is likely stuck and
> can be dropped. Even so, the descriptor may still have a callback set that could
> no longer be accessible. An example of such a problem is when the dmatest fails
> and the dmatest module is unloaded. The failure of dmatest leaves descriptors
> with dma_async_tx_descriptor::callback pointing to code that no longer exist.
> This causes a page fault as below at the time the IDXD driver is unloaded when it
> attempts to run the callback:
>  BUG: unable to handle page fault for address: ffffffffc0665190
>  #PF: supervisor instruction fetch in kernel mode
>  #PF: error_code(0x0010) - not-present page
> 
> Fix this by clearing the callback pointers on the transmit descriptors only when
> workqueue is disabled.
> 
> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
> ---
> 
> History of refactoring made the Fixes: hard to identify by me.
> 
>  drivers/dma/idxd/device.c | 10 ++++++++++
>  1 file changed, 10 insertions(+)
> 
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index
> b4d7bb923a40..2ac71a34fa34 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -1156,6 +1156,7 @@ int idxd_device_load_config(struct idxd_device *idxd)
> 
>  static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)  {
> +	struct dma_async_tx_descriptor *tx;

Nitpicking. It's better to move this line to below:

>  	struct idxd_desc *desc, *itr;
>  	struct llist_node *head;
>  	LIST_HEAD(flist);
> @@ -1175,6 +1176,15 @@ static void idxd_flush_pending_descs(struct
> idxd_irq_entry *ie)
>  	list_for_each_entry_safe(desc, itr, &flist, list) {

here?
+	struct dma_async_tx_descriptor *tx;

>  		list_del(&desc->list);
>  		ctype = desc->completion->status ?
> IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
> +		/*
> +		 * wq is being disabled. Any remaining descriptors are
> +		 * likely to be stuck and can be dropped. callback could
> +		 * point to code that is no longer accessible, for example
> +		 * if dmatest module has been unloaded.
> +		 */
> +		tx = &desc->txd;
> +		tx->callback = NULL;
> +		tx->callback_result = NULL;
>  		idxd_dma_complete_txd(desc, ctype, true);
>  	}
>  }
> --
> 2.34.1

Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>

Thanks.

-Fenghua
  

Hi Fenghua,

On 12/2/2022 1:12 PM, Yu, Fenghua wrote:

...

>> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index
>> b4d7bb923a40..2ac71a34fa34 100644
>> --- a/drivers/dma/idxd/device.c
>> +++ b/drivers/dma/idxd/device.c
>> @@ -1156,6 +1156,7 @@ int idxd_device_load_config(struct idxd_device *idxd)
>>
>>  static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)  {
>> +	struct dma_async_tx_descriptor *tx;
> 
> Nitpicking. It's better to move this line to below:
> 
>>  	struct idxd_desc *desc, *itr;
>>  	struct llist_node *head;
>>  	LIST_HEAD(flist);
>> @@ -1175,6 +1176,15 @@ static void idxd_flush_pending_descs(struct
>> idxd_irq_entry *ie)
>>  	list_for_each_entry_safe(desc, itr, &flist, list) {
> 
> here?
> +	struct dma_async_tx_descriptor *tx;
> 

Will do.

>>  		list_del(&desc->list);
>>  		ctype = desc->completion->status ?
>> IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
>> +		/*
>> +		 * wq is being disabled. Any remaining descriptors are
>> +		 * likely to be stuck and can be dropped. callback could
>> +		 * point to code that is no longer accessible, for example
>> +		 * if dmatest module has been unloaded.
>> +		 */
>> +		tx = &desc->txd;
>> +		tx->callback = NULL;
>> +		tx->callback_result = NULL;
>>  		idxd_dma_complete_txd(desc, ctype, true);
>>  	}
>>  }
>> --
>> 2.34.1
> 
> Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>

Thank you very much.

Reinette