Re: [PATCH v6 08/11] drivers: perf: hisi: use poll method to avoid L3C counter overflow

From	Mark Rutland <mark.rutland@arm.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH v6 08/11] drivers: perf: hisi: use poll method to avoid L3C counter overflow
Date	2017-03-28 13:20 +0200
Message-ID	<tpXkl-6JL-3@gated-at.bofh.it> (permalink)
References	<tjmdQ-87B-19@gated-at.bofh.it> <tnvBU-6kG-17@gated-at.bofh.it> <torcR-5YR-5@gated-at.bofh.it> <tow2S-10z-7@gated-at.bofh.it> <tpwtQ-3Lz-13@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Mon, Mar 27, 2017 at 12:03:24PM +0530, Anurup M wrote:
> On Friday 24 March 2017 05:13 PM, Mark Rutland wrote:
> >>>How do we ensure that we don't take the interrupt in the middle of a
> >>>> >sequence of accesses to the HW?
> >>>
> >>>The L3 cache and MN PMU does not use the overflow IRQ and it does
> >>>not occur here
> >>>as the interrupt Mask register is by default masked in hardware.
> >I was referring to the timer interrupt which backs the hrtimer.
> >
> >i.e. how do we guarantee that hisi_hrtimer_callback() is not called
> >while we are in the middle of a RMW sequence? Are interrupts disabled
> >for all of those seqeunces?
> 
> The HW access via djtag read and write are protected by spin_lock_irqsave.

Thanks for the explanation.

I mistakenly thought that there were sequences that would need to make
several hisi_djtag_{read,writel}() calls that might conflict with the
overflow handler, but that is not the case, so the spin_lock_irqsave()
does appear to be sufficient.

Thanks,
Mark.

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

Re: [PATCH v6 08/11] drivers: perf: hisi: use poll method to avoid  L3C counter overflow Mark Rutland <mark.rutland@arm.com> - 2017-03-28 13:20 +0200

csiph-web