[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211214122507.GC14247@willie-the-truck>
Date: Tue, 14 Dec 2021 12:25:08 +0000
From: Will Deacon <will@...nel.org>
To: Bharat Bhushan <bbhushan2@...vell.com>
Cc: mark.rutland@....com, robh+dt@...nel.org, bbudiredla@...vell.com,
sgoutham@...vell.com, linux-arm-kernel@...ts.infradead.org,
devicetree@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v6 4/4] perf/marvell: cn10k DDR perf event core ownership
On Fri, Oct 29, 2021 at 05:26:43PM +0530, Bharat Bhushan wrote:
> As DDR perf event counters are not per core, so they should be accessed
> only by one core at a time. Select new core when previously owning core
> is going offline.
>
> Signed-off-by: Bharat Bhushan <bbhushan2@...vell.com>
> ---
> v1->v6
> - No Change
>
> drivers/perf/marvell_cn10k_ddr_pmu.c | 50 ++++++++++++++++++++++++++--
> include/linux/cpuhotplug.h | 1 +
> 2 files changed, 49 insertions(+), 2 deletions(-)
I don't think the driver is much use without this patch, so please can you
move the Kconfig stuff to a patch at the end so that the driver can't be
enabled in a broken state half way through the series?
Will
Powered by blists - more mailing lists