From: Will McVicker <willmcvicker@google.com>
To: "Catalin Marinas" <catalin.marinas@arm.com>,
"Will Deacon" <will@kernel.org>,
"Peter Griffin" <peter.griffin@linaro.org>,
"André Draszik" <andre.draszik@linaro.org>,
"Tudor Ambarus" <tudor.ambarus@linaro.org>,
"Rob Herring" <robh@kernel.org>,
"Krzysztof Kozlowski" <krzk+dt@kernel.org>,
"Conor Dooley" <conor+dt@kernel.org>,
"Alim Akhtar" <alim.akhtar@samsung.com>,
"Daniel Lezcano" <daniel.lezcano@linaro.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Saravana Kannan" <saravanak@google.com>,
"Krzysztof Kozlowski" <krzk@kernel.org>
Cc: Will McVicker <willmcvicker@google.com>,
Donghoon Yu <hoony.yu@samsung.com>,
Hosung Kim <hosung0.kim@samsung.com>,
kernel-team@android.com, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org,
Youngmin Nam <youngmin.nam@samsung.com>,
linux-samsung-soc@vger.kernel.org, devicetree@vger.kernel.org
Subject: [PATCH v2 2/7] clocksource/drivers/exynos_mct: Don't register as a sched_clock on arm64
Date: Wed, 2 Apr 2025 16:33:53 -0700 [thread overview]
Message-ID: <20250402233407.2452429-3-willmcvicker@google.com> (raw)
In-Reply-To: <20250402233407.2452429-1-willmcvicker@google.com>
To use the MCT as a sched_clock, the timer value has to be accessed vi
an MCT register which is extremely slow. To improve performance on Arm64
SoCs, use the Arm architected timer as the default clocksource. Note, we
can't completely disable the MCT on Arm64 since it needs to be used as
the wakeup source for the arch_timer to exit the "c2" idle state.
Since ARM SoCs don't have an architectured timer, the MCT will continue
to be the default clocksource. Detailed discussion on this topic can be
found at [1].
[1] https://lore.kernel.org/linux-samsung-soc/1400188079-21832-1-git-send-email-chirantan@chromium.org/
Signed-off-by: Donghoon Yu <hoony.yu@samsung.com>
Signed-off-by: Youngmin Nam <youngmin.nam@samsung.com>
[Original commit from https://android.googlesource.com/kernel/gs/+/630817f7080e92c5e0216095ff52f6eb8dd00727
Signed-off-by: Will McVicker <willmcvicker@google.com>
Reviewed-by: Youngmin Nam <youngmin.nam@samsung.com>
---
drivers/clocksource/exynos_mct.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index da09f467a6bb..96361d5dc57d 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -219,12 +219,18 @@ static struct clocksource mct_frc = {
.resume = exynos4_frc_resume,
};
+/*
+ * Since ARM devices do not have an architected timer, they need to continue
+ * using the MCT as the main clocksource for timekeeping, sched_clock, and the
+ * delay timer. For AARCH64 SoCs, the architected timer is the preferred
+ * clocksource due to it's superior performance.
+ */
+#if defined(CONFIG_ARM)
static u64 notrace exynos4_read_sched_clock(void)
{
return exynos4_read_count_32();
}
-#if defined(CONFIG_ARM)
static struct delay_timer exynos4_delay_timer;
static cycles_t exynos4_read_current_timer(void)
@@ -250,12 +256,13 @@ static int __init exynos4_clocksource_init(bool frc_shared)
exynos4_delay_timer.read_current_timer = &exynos4_read_current_timer;
exynos4_delay_timer.freq = clk_rate;
register_current_timer_delay(&exynos4_delay_timer);
+
+ sched_clock_register(exynos4_read_sched_clock, 32, clk_rate);
#endif
if (clocksource_register_hz(&mct_frc, clk_rate))
panic("%s: can't register clocksource\n", mct_frc.name);
- sched_clock_register(exynos4_read_sched_clock, 32, clk_rate);
return 0;
}
--
2.49.0.472.ge94155a9ec-goog
next prev parent reply other threads:[~2025-04-02 23:34 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20250402233425epcas2p479285add99d27dc18aabd2295bfcbdc8@epcas2p4.samsung.com>
2025-04-02 23:33 ` [PATCH v2 0/7] Add module support for Arm64 Exynos MCT driver Will McVicker
2025-04-02 23:33 ` [PATCH v2 1/7] of/irq: Export of_irq_count for modules Will McVicker
2025-04-02 23:33 ` Will McVicker [this message]
2025-04-02 23:51 ` [PATCH v2 2/7] clocksource/drivers/exynos_mct: Don't register as a sched_clock on arm64 John Stultz
2025-04-08 19:57 ` William McVicker
2025-04-02 23:33 ` [PATCH v2 3/7] clocksource/drivers/exynos_mct: Set local timer interrupts as percpu Will McVicker
2025-05-08 10:12 ` Peter Griffin
2025-04-02 23:33 ` [PATCH v2 4/7] arm64: dts: exynos: gs101: Add 'local-timer-stop' to cpuidle nodes Will McVicker
2025-05-08 10:11 ` Peter Griffin
2025-04-02 23:33 ` [PATCH v2 5/7] clocksource/drivers/exynos_mct: Fix uninitialized irq name warning Will McVicker
2025-05-08 10:19 ` Peter Griffin
2025-04-02 23:33 ` [PATCH v2 6/7] clocksource/drivers/exynos_mct: Add module support Will McVicker
2025-04-15 16:50 ` Daniel Lezcano
2025-04-15 21:25 ` William McVicker
2025-04-16 11:15 ` Daniel Lezcano
2025-05-08 11:44 ` Peter Griffin
2025-04-16 0:48 ` John Stultz
2025-04-16 13:46 ` Daniel Lezcano
2025-04-16 19:48 ` John Stultz
2025-04-16 21:00 ` John Stultz
2025-05-13 14:52 ` Daniel Lezcano
2025-05-14 23:16 ` William McVicker
2025-05-23 15:03 ` Daniel Lezcano
2025-05-23 17:06 ` William McVicker
2025-05-23 18:06 ` Saravana Kannan
2025-05-23 20:39 ` Daniel Lezcano
2025-04-02 23:33 ` [PATCH v2 7/7] arm64: exynos: Drop select CLKSRC_EXYNOS_MCT Will McVicker
2025-04-04 1:11 ` [PATCH v2 0/7] Add module support for Arm64 Exynos MCT driver Youngmin Nam
2025-04-04 6:02 ` Krzysztof Kozlowski
2025-04-04 6:17 ` Youngmin Nam
2025-04-08 19:57 ` William McVicker
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=20250402233407.2452429-3-willmcvicker@google.com \
--to=willmcvicker@google.com \
--cc=alim.akhtar@samsung.com \
--cc=andre.draszik@linaro.org \
--cc=catalin.marinas@arm.com \
--cc=conor+dt@kernel.org \
--cc=daniel.lezcano@linaro.org \
--cc=devicetree@vger.kernel.org \
--cc=hoony.yu@samsung.com \
--cc=hosung0.kim@samsung.com \
--cc=kernel-team@android.com \
--cc=krzk+dt@kernel.org \
--cc=krzk@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-samsung-soc@vger.kernel.org \
--cc=peter.griffin@linaro.org \
--cc=robh@kernel.org \
--cc=saravanak@google.com \
--cc=tglx@linutronix.de \
--cc=tudor.ambarus@linaro.org \
--cc=will@kernel.org \
--cc=youngmin.nam@samsung.com \
/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;
as well as URLs for NNTP newsgroup(s).