Re: [PATCH v2 00/44] cpuidle,rcu: Clean up the mess

From: Peter Zijlstra <peterz@infradead.org>
To: 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: Re: [PATCH v2 00/44] cpuidle,rcu: Clean up the mess
Date: Tue, 20 Sep 2022 16:04:47 +0200	[thread overview]
Message-ID: <YynIf5WiWbNdiWsq__46788.7815598928$1663682748$gmane$org@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20220919095939.761690562@infradead.org>


Because Nadav asked about tracing/kprobing idle, I had another go around
and noticed not all functions calling ct_cpuidle_enter are __cpuidle.

Basically all cpuidle_driver::enter functions should be __cpuidle; i'll
do that audit shortly.

For now this is ct_cpuidle_enter / CPU_IDLE_ENTER users.

---

--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -17,8 +17,8 @@
 static int num_idle_cpus = 0;
 static DEFINE_RAW_SPINLOCK(cpuidle_lock);
 
-static int imx6q_enter_wait(struct cpuidle_device *dev,
-			    struct cpuidle_driver *drv, int index)
+static __cpuidle int imx6q_enter_wait(struct cpuidle_device *dev,
+				      struct cpuidle_driver *drv, int index)
 {
 	raw_spin_lock(&cpuidle_lock);
 	if (++num_idle_cpus == num_online_cpus())
--- a/arch/arm/mach-imx/cpuidle-imx6sx.c
+++ b/arch/arm/mach-imx/cpuidle-imx6sx.c
@@ -30,8 +30,8 @@ static int imx6sx_idle_finish(unsigned l
 	return 0;
 }
 
-static int imx6sx_enter_wait(struct cpuidle_device *dev,
-			    struct cpuidle_driver *drv, int index)
+static __cpuidle int imx6sx_enter_wait(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int index)
 {
 	imx6_set_lpm(WAIT_UNCLOCKED);
 
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -224,8 +224,8 @@ static void __init save_l2x0_context(voi
  *	2 - CPUx L1 and logic lost + GIC lost: MPUSS OSWR
  *	3 - CPUx L1 and logic lost + GIC + L2 lost: DEVICE OFF
  */
-int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state,
-			 bool rcuidle)
+__cpuidle int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state,
+				   bool rcuidle)
 {
 	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu);
 	unsigned int save_state = 0, cpu_logic_state = PWRDM_POWER_RET;
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -175,7 +175,7 @@ static int omap34xx_do_sram_idle(unsigne
 	return 0;
 }
 
-void omap_sram_idle(bool rcuidle)
+__cpuidle void omap_sram_idle(bool rcuidle)
 {
 	/* Variable to tell what needs to be saved and restored
 	 * in omap_sram_idle*/
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -62,7 +62,7 @@ int acpi_processor_ffh_lpi_probe(unsigne
 	return psci_acpi_cpu_init_idle(cpu);
 }
 
-int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+__cpuidle int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
 	u32 state = lpi->address;
 
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -31,8 +31,8 @@
  * Called from the CPUidle framework to program the device to the
  * specified target state selected by the governor.
  */
-static int arm_enter_idle_state(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv, int idx)
+static __cpuidle int arm_enter_idle_state(struct cpuidle_device *dev,
+					  struct cpuidle_driver *drv, int idx)
 {
 	/*
 	 * Pass idle state index to arm_cpuidle_suspend which in turn
--- a/drivers/cpuidle/cpuidle-big_little.c
+++ b/drivers/cpuidle/cpuidle-big_little.c
@@ -122,8 +122,8 @@ static int notrace bl_powerdown_finisher
  * Called from the CPUidle framework to program the device to the
  * specified target state selected by the governor.
  */
-static int bl_enter_powerdown(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv, int idx)
+static __cpuidle int bl_enter_powerdown(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int idx)
 {
 	cpu_pm_enter();
 	ct_cpuidle_enter();
--- a/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ b/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -25,9 +25,9 @@
 
 static int (*mvebu_v7_cpu_suspend)(int);
 
-static int mvebu_v7_enter_idle(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv,
-				int index)
+static __cpuidle int mvebu_v7_enter_idle(struct cpuidle_device *dev,
+					 struct cpuidle_driver *drv,
+					 int index)
 {
 	int ret;
 	bool deepidle = false;
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -49,14 +49,9 @@ static inline u32 psci_get_domain_state(
 	return __this_cpu_read(domain_state);
 }
 
-static inline int psci_enter_state(int idx, u32 state)
-{
-	return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, idx, state);
-}
-
-static int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
-					  struct cpuidle_driver *drv, int idx,
-					  bool s2idle)
+static __cpuidle int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
+						    struct cpuidle_driver *drv, int idx,
+						    bool s2idle)
 {
 	struct psci_cpuidle_data *data = this_cpu_ptr(&psci_cpuidle_data);
 	u32 *states = data->psci_states;
@@ -192,12 +187,12 @@ static void psci_idle_init_cpuhp(void)
 		pr_warn("Failed %d while setup cpuhp state\n", err);
 }
 
-static int psci_enter_idle_state(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv, int idx)
+static __cpuidle int psci_enter_idle_state(struct cpuidle_device *dev,
+					   struct cpuidle_driver *drv, int idx)
 {
 	u32 *state = __this_cpu_read(psci_cpuidle_data.psci_states);
 
-	return psci_enter_state(idx, state[idx]);
+	return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, idx, state[idx]);
 }
 
 static const struct of_device_id psci_idle_state_match[] = {
--- a/drivers/cpuidle/cpuidle-qcom-spm.c
+++ b/drivers/cpuidle/cpuidle-qcom-spm.c
@@ -58,8 +58,8 @@ static int qcom_cpu_spc(struct spm_drive
 	return ret;
 }
 
-static int spm_enter_idle_state(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv, int idx)
+static __cpuidle int spm_enter_idle_state(struct cpuidle_device *dev,
+					  struct cpuidle_driver *drv, int idx)
 {
 	struct cpuidle_qcom_spm_data *data = container_of(drv, struct cpuidle_qcom_spm_data,
 							  cpuidle_driver);
--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -93,17 +93,17 @@ static int sbi_suspend(u32 state)
 		return sbi_suspend_finisher(state, 0, 0);
 }
 
-static int sbi_cpuidle_enter_state(struct cpuidle_device *dev,
-				   struct cpuidle_driver *drv, int idx)
+static __cpuidle int sbi_cpuidle_enter_state(struct cpuidle_device *dev,
+					     struct cpuidle_driver *drv, int idx)
 {
 	u32 *states = __this_cpu_read(sbi_cpuidle_data.states);
 
 	return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, states[idx]);
 }
 
-static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
-					  struct cpuidle_driver *drv, int idx,
-					  bool s2idle)
+static __cpuidle int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
+						   struct cpuidle_driver *drv, int idx,
+						   bool s2idle)
 {
 	struct sbi_cpuidle_data *data = this_cpu_ptr(&sbi_cpuidle_data);
 	u32 *states = data->states;
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -160,8 +160,8 @@ static int tegra_cpuidle_coupled_barrier
 	return 0;
 }
 
-static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
-				     int index, unsigned int cpu)
+static __cpuidle int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
+					       int index, unsigned int cpu)
 {
 	int err;
 
@@ -226,9 +226,9 @@ static int tegra_cpuidle_adjust_state_in
 	return index;
 }
 
-static int tegra_cpuidle_enter(struct cpuidle_device *dev,
-			       struct cpuidle_driver *drv,
-			       int index)
+static __cpuidle int tegra_cpuidle_enter(struct cpuidle_device *dev,
+					 struct cpuidle_driver *drv,
+					 int index)
 {
 	bool do_rcu = drv->states[index].flags & CPUIDLE_FLAG_RCU_IDLE;
 	unsigned int cpu = cpu_logical_map(dev->cpu);
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -137,11 +137,13 @@ int cpuidle_find_deepest_state(struct cp
 }
 
 #ifdef CONFIG_SUSPEND
-static void enter_s2idle_proper(struct cpuidle_driver *drv,
-				struct cpuidle_device *dev, int index)
+static __cpuidle void enter_s2idle_proper(struct cpuidle_driver *drv,
+					  struct cpuidle_device *dev, int index)
 {
-	ktime_t time_start, time_end;
 	struct cpuidle_state *target_state = &drv->states[index];
+	ktime_t time_start, time_end;
+
+	instrumentation_begin();
 
 	time_start = ns_to_ktime(local_clock());
 
@@ -152,13 +154,18 @@ static void enter_s2idle_proper(struct c
 	 * suspended is generally unsafe.
 	 */
 	stop_critical_timings();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
 		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
 	target_state->enter_s2idle(dev, drv, index);
 	if (WARN_ON_ONCE(!irqs_disabled()))
 		raw_local_irq_disable();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
 		ct_cpuidle_exit();
+	}
 	tick_unfreeze();
 	start_critical_timings();
 
@@ -166,6 +173,7 @@ static void enter_s2idle_proper(struct c
 
 	dev->states_usage[index].s2idle_time += ktime_us_delta(time_end, time_start);
 	dev->states_usage[index].s2idle_usage++;
+	instrumentation_end();
 }
 
 /**
@@ -200,8 +208,9 @@ int cpuidle_enter_s2idle(struct cpuidle_
  * @drv: cpuidle driver for this cpu
  * @index: index into the states table in @drv of the state to enter
  */
-int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
-			int index)
+__cpuidle int cpuidle_enter_state(struct cpuidle_device *dev,
+				  struct cpuidle_driver *drv,
+				  int index)
 {
 	int entered_state;
 
@@ -209,6 +218,8 @@ int cpuidle_enter_state(struct cpuidle_d
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
 	ktime_t time_start, time_end;
 
+	instrumentation_begin();
+
 	/*
 	 * Tell the time framework to switch to a broadcast timer because our
 	 * local timer will be shut down.  If a local timer is used from another
@@ -235,15 +246,21 @@ int cpuidle_enter_state(struct cpuidle_d
 	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
 		ct_cpuidle_enter();
+		/* Annotate away the indirect call */
+		instrumentation_begin();
+	}
 
 	entered_state = target_state->enter(dev, drv, index);
+
 	if (WARN_ONCE(!irqs_disabled(), "%ps leaked IRQ state", target_state->enter))
 		raw_local_irq_disable();
 
-	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) {
+		instrumentation_end();
 		ct_cpuidle_exit();
+	}
 	start_critical_timings();
 
 	sched_clock_idle_wakeup_event();
@@ -306,6 +323,8 @@ int cpuidle_enter_state(struct cpuidle_d
 		dev->states_usage[index].rejected++;
 	}
 
+	instrumentation_end();
+
 	return entered_state;
 }
 

