From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
To: Anshuman Khandual <anshuman.khandual@arm.com>,
Will Deacon <will@kernel.org>,
Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, ilkka@os.amperecomputing.com
Subject: [PATCH v2] perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled
Date: Fri, 6 Sep 2024 12:15:39 -0700 [thread overview]
Message-ID: <20240906191539.4847-1-ilkka@os.amperecomputing.com> (raw)
The PMU driver attempts to use PC_WRITE_RETIRED for the HW branch event,
if enabled. However, PC_WRITE_RETIRED counts only taken branches,
whereas BR_RETIRED counts also non-taken ones.
Furthermore, perf uses HW branch event to calculate branch misses ratio,
implying BR_RETIRED is the correct event to count.
We keep PC_WRITE_RETIRED still as an option in case BR_RETIRED isn't
implemented.
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
---
v2: Instead of removing PC_WRITE_RETIRED, keep it as an alternative
---
drivers/perf/arm_pmuv3.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index d246840797b6..f5ee6e2adb30 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1089,14 +1089,14 @@ static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu,
if (event->attr.type == PERF_TYPE_HARDWARE &&
event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) {
- if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
- armpmu->pmceid_bitmap))
- return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED;
-
if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED,
armpmu->pmceid_bitmap))
return ARMV8_PMUV3_PERFCTR_BR_RETIRED;
+ if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
+ armpmu->pmceid_bitmap))
+ return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED;
+
return HW_OP_UNSUPPORTED;
}
--
2.42.0
next reply other threads:[~2024-09-06 19:16 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-06 19:15 Ilkka Koskinen [this message]
2024-09-09 16:15 ` Will Deacon
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=20240906191539.4847-1-ilkka@os.amperecomputing.com \
--to=ilkka@os.amperecomputing.com \
--cc=anshuman.khandual@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--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®