From: Peter Zijlstra <peterz@infradead.org>
To: peterz@infradead.org
Cc: richard.henderson@linaro.org, ink@jurassic.park.msu.ru,
mattst88@gmail.com, vgupta@kernel.org, linux@armlinux.org.uk,
ulli.kroll@googlemail.com, linus.walleij@linaro.org,
shawnguo@kernel.org, Sascha Hauer <s.hauer@pengutronix.de>,
kernel@pengutronix.de, festevam@gmail.com, linux-imx@nxp.com,
tony@atomide.com, khilman@kernel.org, catalin.marinas@arm.com,
will@kernel.org, guoren@kernel.org, bcain@quicinc.com,
chenhuacai@kernel.org, kernel@xen0n.name, geert@linux-m68k.org,
sammy@sammy.net, monstr@monstr.eu, tsbogend@alpha.franken.de,
dinguyen@kernel.org, jonas@southpole.se,
stefan.kristiansson@saunalahti.fi, shorne@gmail.com,
James.Bottomley@HansenPartnership.com, deller@gmx.de,
mpe@ellerman.id.au, npiggin@gmail.com,
christophe.leroy@csgroup.eu, paul.walmsley@sifive.com,
palmer@dabbel
Subject: [PATCH v2 11/44] cpuidle,omap4: Push RCU-idle into driver
Date: Mon, 19 Sep 2022 11:59:50 +0200 [thread overview]
Message-ID: <20220919101521.072508494@infradead.org> (raw)
In-Reply-To: 20220919095939.761690562@infradead.org
Doing RCU-idle outside the driver, only to then temporarily enable it
again, some *four* times, before going idle is daft.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Tested-by: Tony Lindgren <tony@atomide.com>
---
arch/arm/mach-omap2/cpuidle44xx.c | 29 ++++++++++++++++++-----------
1 file changed, 18 insertions(+), 11 deletions(-)
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -105,7 +105,9 @@ static int omap_enter_idle_smp(struct cp
}
raw_spin_unlock_irqrestore(&mpu_lock, flag);
+ ct_idle_enter();
omap4_enter_lowpower(dev->cpu, cx->cpu_state);
+ ct_idle_exit();
raw_spin_lock_irqsave(&mpu_lock, flag);
if (cx->mpu_state_vote == num_online_cpus())
@@ -151,10 +153,10 @@ static int omap_enter_idle_coupled(struc
(cx->mpu_logic_state == PWRDM_POWER_OFF);
/* Enter broadcast mode for periodic timers */
- RCU_NONIDLE(tick_broadcast_enable());
+ tick_broadcast_enable();
/* Enter broadcast mode for one-shot timers */
- RCU_NONIDLE(tick_broadcast_enter());
+ tick_broadcast_enter();
/*
* Call idle CPU PM enter notifier chain so that
@@ -166,7 +168,7 @@ static int omap_enter_idle_coupled(struc
if (dev->cpu == 0) {
pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
- RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state));
+ omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
/*
* Call idle CPU cluster PM enter notifier chain
@@ -178,14 +180,16 @@ static int omap_enter_idle_coupled(struc
index = 0;
cx = state_ptr + index;
pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
- RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state));
+ omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
mpuss_can_lose_context = 0;
}
}
}
+ ct_idle_enter();
omap4_enter_lowpower(dev->cpu, cx->cpu_state);
cpu_done[dev->cpu] = true;
+ ct_idle_exit();
/* Wakeup CPU1 only if it is not offlined */
if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
@@ -194,9 +198,9 @@ static int omap_enter_idle_coupled(struc
mpuss_can_lose_context)
gic_dist_disable();
- RCU_NONIDLE(clkdm_deny_idle(cpu_clkdm[1]));
- RCU_NONIDLE(omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON));
- RCU_NONIDLE(clkdm_allow_idle(cpu_clkdm[1]));
+ clkdm_deny_idle(cpu_clkdm[1]);
+ omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON);
+ clkdm_allow_idle(cpu_clkdm[1]);
if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) &&
mpuss_can_lose_context) {
@@ -222,7 +226,7 @@ static int omap_enter_idle_coupled(struc
cpu_pm_exit();
cpu_pm_out:
- RCU_NONIDLE(tick_broadcast_exit());
+ tick_broadcast_exit();
fail:
cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
@@ -247,7 +251,8 @@ static struct cpuidle_driver omap4_idle_
/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
.exit_latency = 328 + 440,
.target_residency = 960,
- .flags = CPUIDLE_FLAG_COUPLED,
+ .flags = CPUIDLE_FLAG_COUPLED |
+ CPUIDLE_FLAG_RCU_IDLE,
.enter = omap_enter_idle_coupled,
.name = "C2",
.desc = "CPUx OFF, MPUSS CSWR",
@@ -256,7 +261,8 @@ static struct cpuidle_driver omap4_idle_
/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
.exit_latency = 460 + 518,
.target_residency = 1100,
- .flags = CPUIDLE_FLAG_COUPLED,
+ .flags = CPUIDLE_FLAG_COUPLED |
+ CPUIDLE_FLAG_RCU_IDLE,
.enter = omap_enter_idle_coupled,
.name = "C3",
.desc = "CPUx OFF, MPUSS OSWR",
@@ -282,7 +288,8 @@ static struct cpuidle_driver omap5_idle_
/* C2 - CPU0 RET + CPU1 RET + MPU CSWR */
.exit_latency = 48 + 60,
.target_residency = 100,
- .flags = CPUIDLE_FLAG_TIMER_STOP,
+ .flags = CPUIDLE_FLAG_TIMER_STOP |
+ CPUIDLE_FLAG_RCU_IDLE,
.enter = omap_enter_idle_smp,
.name = "C2",
.desc = "CPUx CSWR, MPUSS CSWR",
next prev parent reply other threads:[~2022-09-19 9:59 UTC|newest]
Thread overview: 88+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-19 9:59 [PATCH v2 00/44] cpuidle,rcu: Clean up the mess Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 01/44] x86/perf/amd: Remove tracing from perf_lopwr_cb() Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 02/44] x86/idle: Replace x86_idle with a static_call Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 03/44] cpuidle/poll: Ensure IRQ state is invariant Peter Zijlstra
2022-09-19 13:19 ` Frederic Weisbecker
2022-09-20 8:57 ` Peter Zijlstra
2022-09-20 10:43 ` Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 04/44] cpuidle: Move IRQ state validation Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 05/44] cpuidle,riscv: Push RCU-idle into driver Peter Zijlstra
2022-09-19 11:54 ` Anup Patel
2022-09-19 13:46 ` Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 06/44] cpuidle,tegra: " Peter Zijlstra
2022-09-19 14:05 ` Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 07/44] cpuidle,psci: " Peter Zijlstra
[not found] ` <20220919101520.802976773-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2022-09-19 14:11 ` Frederic Weisbecker
2022-09-21 21:51 ` Kajetan Puchalski
2022-09-22 0:45 ` Guo Ren
2022-09-19 9:59 ` [PATCH v2 08/44] cpuidle,imx6: " Peter Zijlstra
2022-09-19 14:21 ` Frederic Weisbecker
2022-09-19 15:00 ` Peter Zijlstra
2022-09-20 8:58 ` Peter Zijlstra
2022-09-20 9:01 ` Frederic Weisbecker
2022-09-19 14:49 ` Frederic Weisbecker
2022-09-19 15:01 ` Peter Zijlstra
2022-09-19 15:03 ` Peter Zijlstra
2022-09-19 15:17 ` Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 09/44] cpuidle,omap3: " Peter Zijlstra
2022-09-19 14:31 ` Frederic Weisbecker
2022-09-19 15:19 ` Peter Zijlstra
2022-09-20 8:39 ` Frederic Weisbecker
2022-09-19 14:43 ` Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 10/44] cpuidle,armada: " Peter Zijlstra
2022-09-19 14:39 ` Frederic Weisbecker
2022-09-19 9:59 ` Peter Zijlstra [this message]
2022-09-20 10:53 ` [PATCH v2 11/44] cpuidle,omap4: " Frederic Weisbecker
2022-09-19 9:59 ` [PATCH v2 12/44] cpuidle,dt: " Peter Zijlstra
2022-10-04 11:03 ` Ulf Hansson
2022-10-04 11:43 ` Ulf Hansson
2022-11-16 15:29 ` Peter Zijlstra
[not found] ` <Y3UBwYNY15ETUKy9-Nxj+rRp3nVydTX5a5knrm8zTDFooKrT+cvkQGrU6aU0@public.gmane.org>
2022-11-22 16:04 ` Ulf Hansson
2022-09-19 9:59 ` [PATCH v2 13/44] cpuidle: Fix ct_idle_*() usage Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 14/44] cpuidle,cpu_pm: Remove RCU fiddling from cpu_pm_{enter,exit}() Peter Zijlstra
2022-10-04 11:04 ` [PATCH v2 14/44] cpuidle, cpu_pm: Remove RCU fiddling from cpu_pm_{enter, exit}() Ulf Hansson
2022-09-19 9:59 ` [PATCH v2 15/44] acpi_idle: Remove tracing Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 16/44] cpuidle: Annotate poll_idle() Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 17/44] objtool/idle: Validate __cpuidle code as noinstr Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 18/44] cpuidle, intel_idle: Fix CPUIDLE_FLAG_IRQ_ENABLE *again* Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 19/44] cpuidle,intel_idle: Fix CPUIDLE_FLAG_INIT_XSTATE Peter Zijlstra
2022-09-19 9:59 ` [PATCH v2 20/44] cpuidle,intel_idle: Fix CPUIDLE_FLAG_IBRS Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 21/44] arch/idle: Change arch_cpu_idle() IRQ behaviour Peter Zijlstra
2022-09-20 5:08 ` Guo Ren
2022-09-19 10:00 ` [PATCH v2 22/44] x86/tdx: Remove TDX_HCALL_ISSUE_STI Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 23/44] arm,smp: Remove trace_.*_rcuidle() usage Peter Zijlstra
2022-10-04 11:08 ` Ulf Hansson
2022-09-19 10:00 ` [PATCH v2 24/44] arm64,smp: " Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 25/44] printk: " Peter Zijlstra
2022-09-20 2:49 ` Sergey Senozhatsky
2022-09-19 10:00 ` [PATCH v2 26/44] time/tick-broadcast: Remove RCU_NONIDLE usage Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 27/44] cpuidle, sched: Remove annotations from TIF_{POLLING_NRFLAG, NEED_RESCHED} Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 28/44] cpuidle,mwait: Make noinstr clean Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 29/44] cpuidle,tdx: Make tdx " Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 30/44] cpuidle,xenpv: Make more PARAVIRT_XXL " Peter Zijlstra
2022-09-19 10:45 ` Juergen Gross via Virtualization
2022-09-19 10:00 ` [PATCH v2 31/44] cpuidle,nospec: Make " Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 32/44] cpuidle,acpi: " Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 33/44] ftrace: WARN on rcuidle Peter Zijlstra
2022-09-26 18:41 ` Steven Rostedt
2022-10-04 17:19 ` Mark Rutland
2022-09-19 10:00 ` [PATCH v2 34/44] cpuidle,omap3: Use WFI for omap3_pm_idle() Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 35/44] cpuidle,omap3: Push RCU-idle into omap_sram_idle() Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 36/44] cpuidle, omap4: Push RCU-idle into omap4_enter_lowpower() Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 37/44] arm,omap2: Use WFI for omap2_pm_idle() Peter Zijlstra
2022-09-27 6:21 ` Tony Lindgren
2022-09-19 10:00 ` [PATCH v2 38/44] cpuidle,powerdomain: Remove trace_.*_rcuidle() Peter Zijlstra
2022-10-04 11:12 ` Ulf Hansson
2022-09-19 10:00 ` [PATCH v2 39/44] cpuidle,clk: " Peter Zijlstra
2022-09-28 18:01 ` Stephen Boyd
2022-10-04 11:09 ` Ulf Hansson
2022-09-19 10:00 ` [PATCH v2 40/44] ubsan: Fix objtool UACCESS warns Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 41/44] intel_idle: Add force_irq_on module param Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 42/44] entry, kasan, x86: Disallow overriding mem*() functions Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 43/44] sched: Always inline __this_cpu_preempt_check() Peter Zijlstra
2022-09-19 10:00 ` [PATCH v2 44/44] arm64,riscv,perf: Remove RCU_NONIDLE() usage Peter Zijlstra
2022-09-19 15:21 ` [PATCH v2 00/44] cpuidle,rcu: Clean up the mess Rafael J. Wysocki
2022-09-20 12:31 ` Frederic Weisbecker
2022-09-20 14:04 ` Peter Zijlstra
2022-09-27 6:31 ` Tony Lindgren
[not found] ` <20220919095939.761690562-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2022-10-04 15:15 ` Ulf Hansson
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=20220919101521.072508494@infradead.org \
--to=peterz@infradead.org \
--cc=James.Bottomley@HansenPartnership.com \
--cc=bcain@quicinc.com \
--cc=catalin.marinas@arm.com \
--cc=chenhuacai@kernel.org \
--cc=christophe.leroy@csgroup.eu \
--cc=deller@gmx.de \
--cc=dinguyen@kernel.org \
--cc=festevam@gmail.com \
--cc=geert@linux-m68k.org \
--cc=guoren@kernel.org \
--cc=ink@jurassic.park.msu.ru \
--cc=jonas@southpole.se \
--cc=kernel@pengutronix.de \
--cc=kernel@xen0n.name \
--cc=khilman@kernel.org \
--cc=linus.walleij@linaro.org \
--cc=linux-imx@nxp.com \
--cc=linux@armlinux.org.uk \
--cc=mattst88@gmail.com \
--cc=monstr@monstr.eu \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=palmer@dabbel \
--cc=paul.walmsley@sifive.com \
--cc=richard.henderson@linaro.org \
--cc=s.hauer@pengutronix.de \
--cc=sammy@sammy.net \
--cc=shawnguo@kernel.org \
--cc=shorne@gmail.com \
--cc=stefan.kristiansson@saunalahti.fi \
--cc=tony@atomide.com \
--cc=tsbogend@alpha.franken.de \
--cc=ulli.kroll@googlemail.com \
--cc=vgupta@kernel.org \
--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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).