[PATCH] coresight-tmc: Add configurable timeout for flush and tmcready

Yuanfang Zhang quic_yuanfang at quicinc.com
Mon Jun 30 03:40:53 PDT 2025



On 6/27/2025 10:17 PM, Leo Yan wrote:
> On Fri, Jun 27, 2025 at 12:23:29PM +0100, James Clark wrote:
>>
>>
>> On 27/06/2025 12:10 pm, Yuanfang Zhang wrote:
>>> The current implementation uses a fixed timeout via
>>> coresight_timeout(), which may be insufficient when multiple
>>> sources are enabled or under heavy load, leading to TMC
>>> readiness or flush completion timeout.
>>>
>>> This patch introduces a configurable timeout mechanism for
>>> flush and tmcready.
>>>
>>
>> What kind of values are you using? Is there a reason to not increase the
>> global one?
> 
> IIUC, this patch is related to patch [1].
> 
> It seems to me that both patches aim to address the long latency when
> flushing the TMC, but take different approaches. In the earlier patch,
> both Mike and I questioned how the timeout occurred in hardware, but
> no information provided about the cause.
> 
> I would suggest that we first make clear if this is a hardware quirk or
> a common issue in Arm CoreSight.
> 
> Thanks,
> Leo
> 
sure, now this issue has been found that not only CPU ETM, but also subsystem ETM.
> [1] https://lore.kernel.org/linux-arm-kernel/CAJ9a7Vgre_3mkXB_xeVx5N9BqPTa2Ai4_8E+daDZ-yAUv44A9g@mail.gmail.com/




More information about the linux-arm-kernel mailing list