Thread (7 messages) 7 messages, 2 authors, 2021-12-14

RE: [EXT] Re: [PATCH v6 4/4] perf/marvell: cn10k DDR perf event core ownership

From: Bharat Bhushan <bbhushan2@marvell.com>
Date: 2021-12-14 12:27:32
Also in: linux-arm-kernel, lkml

-----Original Message-----
From: Will Deacon <will@kernel.org>
Sent: Tuesday, December 14, 2021 5:55 PM
To: Bharat Bhushan <bbhushan2@marvell.com>
Cc: mark.rutland@arm.com; robh+dt@kernel.org; Bhaskara Budiredla
[off-list ref]; Sunil Kovvuri Goutham [off-list ref];
linux-arm-kernel@lists.infradead.org; devicetree@vger.kernel.org; linux-
kernel@vger.kernel.org
Subject: [EXT] Re: [PATCH v6 4/4] perf/marvell: cn10k DDR perf event core
ownership

External Email

----------------------------------------------------------------------
On Fri, Oct 29, 2021 at 05:26:43PM +0530, Bharat Bhushan wrote:
quoted
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@marvell.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?
Okay, will change.

Thanks
-Bharat
Will
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help