[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200703123346.GB18953@willie-the-truck>
Date: Fri, 3 Jul 2020 13:33:47 +0100
From: Will Deacon <will@...nel.org>
To: Jisheng Zhang <Jisheng.Zhang@...aptics.com>
Cc: Robin Murphy <robin.murphy@....com>,
Mark Rutland <mark.rutland@....com>,
Catalin Marinas <catalin.marinas@....com>,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 0/3] arm64: perf: add support for Cortex-A55/A75/A76
On Fri, Jun 19, 2020 at 06:44:37PM +0800, Jisheng Zhang wrote:
> The Cortex-A55/A75/A76 use some implementation defined perf events.
> Add the support.
>
> Jisheng Zhang (3):
> arm64: perf: add support for Cortex-A55
> arm64: perf: add support for Cortex-A75
> arm64: perf: add support for Cortex-A76
>
> arch/arm64/kernel/perf_event.c | 49 +++++++++++++++++++++++++++++++---
> 1 file changed, 45 insertions(+), 4 deletions(-)
Do we really need this? I'd prefer for this stuff to live in userspace
now that the perf tool has supported JSON event descriptions for a while,
and the in-kernel driver advertises the architected events advertised
by PMCEID*.
Will
Powered by blists - more mailing lists