[PATCH] iommu/arm-smmu-v3: Fix event queue overflow acknowledgment

[Krcka, Tomas]

> On 28. Mar 2023, at 13:56, Will Deacon <will at kernel.org> wrote:
> 
> 
> On Tue, Mar 28, 2023 at 07:13:52AM +0000, Krcka, Tomas wrote:
>> 
>>> On 27. Mar 2023, at 14:12, Will Deacon <will at kernel.org> wrote:
>>> 
>>> 
>>> On Wed, Mar 08, 2023 at 09:20:47AM +0000, Tomas Krcka wrote:
>>>> When an overflow occurs in the event queue, the SMMU toggles overflow
>>>> flag OVFLG in the PROD register.
>>>> The evtq thread is supposed to acknowledge the overflow flag by toggling
>>>> flag OVACKFLG in the CONS register, otherwise the overflow condition is
>>>> still active (OVFLG != OVACKFLG).
>>>> 
>>>> Currently the acknowledge register is toggled after clearing the event
>>>> queue but is never propagated to the hardware. It would be done next
>>>> time when executing evtq thread.
>>>> 
>>>> The SMMU still adds elements to the queue when the overflow condition is
>>>> active but any subsequent overflow information after clearing the event
>>>> queue will be lost.
>>>> 
>>>> This change keeps the SMMU in sync as it's expected by design.
>>>> 
>>>> Signed-off-by: Tomas Krcka <krckatom at amazon.de>
>>>> Suggested-by: KarimAllah Ahmed <karahmed at amazon.de>
>>>> ---
>>>> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 +
>>>> 1 file changed, 1 insertion(+)
>>>> 
>>>> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>>>> index f2425b0f0cd6..acc1ff5ff69b 100644
>>>> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>>>> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>>>> @@ -1579,6 +1579,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
>>>>     /* Sync our overflow flag, as we believe we're up to speed */
>>>>     llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
>>>>                 Q_IDX(llq, llq->cons);
>>>> +     queue_sync_cons_out(q);
>>>>     return IRQ_HANDLED;
>>>> }
>>> 
>>> I think I probably did mean to have something like this, but can we
>>> only do the actual h/w update if overflow has occurred? Otherwise I think
>>> we're pointlessly writing back the same value most of the time.
>>> 
>>> Will
>> 
>> Yes, we can, but then same applies for the priq as well, there we also write back
>> every time.
> 
> Sure, feel free to update both.
> 

OK, I sent it as new patch: https://lore.kernel.org/lkml/20230329123420.34641-1-tomas.krcka@gmail.com





Amazon Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
Sitz: Berlin
Ust-ID: DE 289 237 879