From: Robin Murphy <robin.murphy@arm.com>
To: "guojinhui.liam" <guojinhui.liam@bytedance.com>,
will@kernel.org, mark.rutland@arm.com
Cc: lizefan.x@bytedance.com, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] perf/arm-cmn: Fix CMN_DTM_UNIT_INFO offset in CMN700
Date: Tue, 12 Sep 2023 09:08:00 +0100 [thread overview]
Message-ID: <d7c4f92f-a68c-26cf-896b-122158097622@arm.com> (raw)
In-Reply-To: <20230912040309.1789-1-guojinhui.liam@bytedance.com>
On 2023-09-12 05:03, guojinhui.liam wrote:
> The por_dtm_unit_info's offest is 0x0960 in CMN700 according to
> the CMN700 spec.
>
> CMN700 spec link:
> https://developer.arm.com/documentation/102308/0302/?lang=en
> por_dtm_unit_info can be found in section [4.3.13.10 por_dtm_unit_info].
>
> Signed-off-by: guojinhui.liam <guojinhui.liam@bytedance.com>
> ---
> drivers/perf/arm-cmn.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
> index 913dc04b3a40..6f3fafee0ac9 100644
> --- a/drivers/perf/arm-cmn.c
> +++ b/drivers/perf/arm-cmn.c
> @@ -113,6 +113,7 @@
> #define CMN_DTM_PMEVCNTSR 0x240
>
> #define CMN_DTM_UNIT_INFO 0x0910
> +#define CMN700_DTM_UNIT_INFO 0x0960
>
> #define CMN_DTM_NUM_COUNTERS 4
> /* Want more local counters? Why not replicate the whole DTM! Ugh... */
> @@ -2247,6 +2248,8 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
>
> if (cmn->part == PART_CMN600)
> xp->dtc = 0xf;
> + else if (cmn->part == PART_CMN700)
> + xp->dtc = 1 << readl_relaxed(xp_region + CMN700_DTM_UNIT_INFO);
I'd prefer to fix this more thoroughly, since there are still potential
issues with this code as-is. I already have that patch written[1],
however it ended up spawning a couple more patches to revisit actually
making meaningful use of the DTC domain information[2], which I've still
been debugging, but I hope to post the whole series soon.
Thanks,
Robin.
[1]
https://gitlab.arm.com/linux-arm/linux-rm/-/commit/e4216d99eed2cd951fc515f06ccf31672fb3f58d
[2]
https://gitlab.arm.com/linux-arm/linux-rm/-/commits/cmn-dev?ref_type=heads
> else
> xp->dtc = 1 << readl_relaxed(xp_region + CMN_DTM_UNIT_INFO);
>
prev parent reply other threads:[~2023-09-12 8:08 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-12 4:03 guojinhui.liam
2023-09-12 8:08 ` Robin Murphy [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d7c4f92f-a68c-26cf-896b-122158097622@arm.com \
--to=robin.murphy@arm.com \
--cc=guojinhui.liam@bytedance.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan.x@bytedance.com \
--cc=mark.rutland@arm.com \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®