Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve the scalability of the CFS bandwidth unthrottling logic with
   large number of CPUs.

 - Fix & rework various cpuidle routines, simplify interaction with the
   generic scheduler code. Add __cpuidle methods as noinstr to objtool's
   noinstr detection and fix boatloads of cpuidle bugs & quirks.

 - Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
   previously issued registrations.

 - Limit scheduler slice duration to the sysctl_sched_latency period, to
   improve scheduling granularity with a large number of SCHED_IDLE
   tasks.

 - Debuggability enhancement on sys_exit(): warn about disabled IRQs,
   but also enable them to prevent a cascade of followup problems and
   repeat warnings.

 - Fix the rescheduling logic in prio_changed_dl().

 - Micro-optimize cpufreq and sched-util methods.

 - Micro-optimize ttwu_runnable()

 - Micro-optimize the idle-scanning in update_numa_stats(),
   select_idle_capacity() and steal_cookie_task().

 - Update the RSEQ code & self-tests

 - Constify various scheduler methods

 - Remove unused methods

 - Refine __init tags

 - Documentation updates

 - Misc other cleanups, fixes

* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
  sched/rt: pick_next_rt_entity(): check list_entry
  sched/deadline: Add more reschedule cases to prio_changed_dl()
  sched/fair: sanitize vruntime of entity being placed
  sched/fair: Remove capacity inversion detection
  sched/fair: unlink misfit task from cpu overutilized
  objtool: mem*() are not uaccess safe
  cpuidle: Fix poll_idle() noinstr annotation
  sched/clock: Make local_clock() noinstr
  sched/clock/x86: Mark sched_clock() noinstr
  x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
  x86/atomics: Always inline arch_atomic64*()
  cpuidle: tracing, preempt: Squash _rcuidle tracing
  cpuidle: tracing: Warn about !rcu_is_watching()
  cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
  cpuidle: drivers: firmware: psci: Dont instrument suspend code
  KVM: selftests: Fix build of rseq test
  exit: Detect and fix irq disabled state in oops
  cpuidle, arm64: Fix the ARM64 cpuidle logic
  cpuidle: mvebu: Fix duplicate flags assignment
  sched/fair: Limit sched slice duration
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -619,6 +619,8 @@ process migrations.
 and is an example of this type.
 
 
+.. _cgroupv2-limits-distributor:
+
 Limits
 ------
 
@@ -635,6 +637,7 @@ process migrations.
 "io.max" limits the maximum BPS and/or IOPS that a cgroup can consume
 on an IO device and is an example of this type.
 
+.. _cgroupv2-protections-distributor:
 
 Protections
 -----------

Documentation/scheduler/index.rst

@@ -15,6 +15,7 @@ Linux Scheduler
     sched-capacity
     sched-energy
     schedutil
+    sched-util-clamp
     sched-nice-design
     sched-rt-group
     sched-stats

arch/alpha/kernel/process.c

@@ -57,7 +57,6 @@ EXPORT_SYMBOL(pm_power_off);
 void arch_cpu_idle(void)
 {
 	wtint(0);
-	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_dead(void)

arch/alpha/kernel/vmlinux.lds.S

@@ -27,7 +27,6 @@ SECTIONS
 		HEAD_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		*(.fixup)
 		*(.gnu.warning)

arch/arc/kernel/process.c

@@ -114,6 +114,8 @@ void arch_cpu_idle(void)
 		"sleep %0	\n"
 		:
 		:"I"(arg)); /* can't be "r" has to be embedded const */
+
+	raw_local_irq_disable();
 }
 
 #else	/* ARC700 */
@@ -122,6 +124,7 @@ void arch_cpu_idle(void)
 {
 	/* sleep, but enable both set E1/E2 (levels of interrupts) before committing */
 	__asm__ __volatile__("sleep 0x3	\n");
+	raw_local_irq_disable();
 }
 
 #endif

arch/arc/kernel/vmlinux.lds.S

@@ -85,7 +85,6 @@ SECTIONS
 		_stext = .;
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/arm/include/asm/vmlinux.lds.h

@@ -96,7 +96,6 @@
 		SOFTIRQENTRY_TEXT					\
 		TEXT_TEXT						\
 		SCHED_TEXT						\
-		CPUIDLE_TEXT						\
 		LOCK_TEXT						\
 		KPROBES_TEXT						\
 		ARM_STUBS_TEXT						\

arch/arm/kernel/cpuidle.c

@@ -26,8 +26,8 @@ static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init;
  *
  * Returns the index passed as parameter
  */
-int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
-		struct cpuidle_driver *drv, int index)
+__cpuidle int arm_cpuidle_simple_enter(struct cpuidle_device *dev, struct
+				       cpuidle_driver *drv, int index)
 {
 	cpu_do_idle();
 

arch/arm/kernel/process.c

@@ -78,7 +78,6 @@ void arch_cpu_idle(void)
 		arm_pm_idle();
 	else
 		cpu_do_idle();
-	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_prepare(void)

arch/arm/kernel/smp.c

@@ -638,7 +638,7 @@ static void do_handle_IPI(int ipinr)
 	unsigned int cpu = smp_processor_id();
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
+		trace_ipi_entry(ipi_types[ipinr]);
 
 	switch (ipinr) {
 	case IPI_WAKEUP:
@@ -685,7 +685,7 @@ static void do_handle_IPI(int ipinr)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+		trace_ipi_exit(ipi_types[ipinr]);
 }
 
 /* Legacy version, should go away once all irqchips have been converted */
@@ -708,7 +708,7 @@ static irqreturn_t ipi_handler(int irq, void *data)
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
+	trace_ipi_raise(target, ipi_types[ipinr]);
 	__ipi_send_mask(ipi_desc[ipinr], target);
 }
 

arch/arm/mach-davinci/cpuidle.c

@@ -44,7 +44,7 @@ static void davinci_save_ddr_power(int enter, bool pdown)
 }
 
 /* Actual code that puts the SoC in different idle states */
-static int davinci_enter_idle(struct cpuidle_device *dev,
+static __cpuidle int davinci_enter_idle(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv, int index)
 {
 	davinci_save_ddr_power(1, ddr2_pdown);

arch/arm/mach-gemini/board-dt.c

@@ -42,8 +42,9 @@ static void gemini_idle(void)
 	 */
 
 	/* FIXME: Enabling interrupts here is racy! */
-	local_irq_enable();
+	raw_local_irq_enable();
 	cpu_do_idle();
+	raw_local_irq_disable();
 }
 
 static void __init gemini_init_machine(void)

arch/arm/mach-imx/cpuidle-imx5.c

@@ -8,7 +8,7 @@
 #include <asm/system_misc.h>
 #include "cpuidle.h"
 
-static int imx5_cpuidle_enter(struct cpuidle_device *dev,
+static __cpuidle int imx5_cpuidle_enter(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv, int index)
 {
 	arm_pm_idle();

arch/arm/mach-imx/cpuidle-imx6q.c

@@ -17,7 +17,7 @@
 static int num_idle_cpus = 0;
 static DEFINE_RAW_SPINLOCK(cpuidle_lock);
 
-static int imx6q_enter_wait(struct cpuidle_device *dev,
+static __cpuidle int imx6q_enter_wait(struct cpuidle_device *dev,
 				      struct cpuidle_driver *drv, int index)
 {
 	raw_spin_lock(&cpuidle_lock);
@@ -25,9 +25,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev,
 		imx6_set_lpm(WAIT_UNCLOCKED);
 	raw_spin_unlock(&cpuidle_lock);
 
-	ct_idle_enter();
+	ct_cpuidle_enter();
 	cpu_do_idle();
-	ct_idle_exit();
+	ct_cpuidle_exit();
 
 	raw_spin_lock(&cpuidle_lock);
 	if (num_idle_cpus-- == num_online_cpus())

arch/arm/mach-imx/cpuidle-imx6sl.c

@@ -11,7 +11,7 @@
 #include "common.h"
 #include "cpuidle.h"
 
-static int imx6sl_enter_wait(struct cpuidle_device *dev,
+static __cpuidle int imx6sl_enter_wait(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
 	imx6_set_lpm(WAIT_UNCLOCKED);

arch/arm/mach-imx/cpuidle-imx6sx.c

@@ -30,7 +30,7 @@ static int imx6sx_idle_finish(unsigned long val)
 	return 0;
 }
 
-static int imx6sx_enter_wait(struct cpuidle_device *dev,
+static __cpuidle int imx6sx_enter_wait(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
 	imx6_set_lpm(WAIT_UNCLOCKED);
@@ -47,7 +47,9 @@ static int imx6sx_enter_wait(struct cpuidle_device *dev,
 		cpu_pm_enter();
 		cpu_cluster_pm_enter();
 
+		ct_cpuidle_enter();
 		cpu_suspend(0, imx6sx_idle_finish);
+		ct_cpuidle_exit();
 
 		cpu_cluster_pm_exit();
 		cpu_pm_exit();
@@ -87,7 +89,8 @@ static struct cpuidle_driver imx6sx_cpuidle_driver = {
 			 */
 			.exit_latency = 300,
 			.target_residency = 500,
-			.flags = CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP |
+				 CPUIDLE_FLAG_RCU_IDLE,
 			.enter = imx6sx_enter_wait,
 			.name = "LOW-POWER-IDLE",
 			.desc = "ARM power off",

arch/arm/mach-imx/cpuidle-imx7ulp.c

@@ -12,7 +12,7 @@
 #include "common.h"
 #include "cpuidle.h"
 
-static int imx7ulp_enter_wait(struct cpuidle_device *dev,
+static __cpuidle int imx7ulp_enter_wait(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv, int index)
 {
 	if (index == 1)

arch/arm/mach-omap2/common.h

@@ -256,11 +256,13 @@ extern u32 omap4_get_cpu1_ns_pa_addr(void);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PM)
 extern int omap4_mpuss_init(void);
-extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
+extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state,
+				bool rcuidle);
 extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state);
 #else
 static inline int omap4_enter_lowpower(unsigned int cpu,
-					unsigned int power_state)
+					unsigned int power_state,
+					bool rcuidle)
 {
 	cpu_do_idle();
 	return 0;

arch/arm/mach-omap2/cpuidle34xx.c

@@ -133,7 +133,7 @@ static int omap3_enter_idle(struct cpuidle_device *dev,
 	}
 
 	/* Execute ARM wfi */
-	omap_sram_idle();
+	omap_sram_idle(true);
 
 	/*
 	 * Call idle CPU PM enter notifier chain to restore
@@ -265,6 +265,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 	.owner            = THIS_MODULE,
 	.states = {
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 2 + 2,
 			.target_residency = 5,
@@ -272,6 +273,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU ON + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 10 + 10,
 			.target_residency = 30,
@@ -279,6 +281,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU ON + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 50 + 50,
 			.target_residency = 300,
@@ -286,6 +289,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU RET + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 1500 + 1800,
 			.target_residency = 4000,
@@ -293,6 +297,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU OFF + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 2500 + 7500,
 			.target_residency = 12000,
@@ -300,6 +305,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU RET + CORE RET",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 3000 + 8500,
 			.target_residency = 15000,
@@ -307,6 +313,7 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.desc		  = "MPU OFF + CORE RET",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 10000 + 30000,
 			.target_residency = 30000,
@@ -328,6 +335,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 	.owner            = THIS_MODULE,
 	.states = {
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 110 + 162,
 			.target_residency = 5,
@@ -335,6 +343,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU ON + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 106 + 180,
 			.target_residency = 309,
@@ -342,6 +351,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU ON + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 107 + 410,
 			.target_residency = 46057,
@@ -349,6 +359,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU RET + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 121 + 3374,
 			.target_residency = 46057,
@@ -356,6 +367,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU OFF + CORE ON",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 855 + 1146,
 			.target_residency = 46057,
@@ -363,6 +375,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU RET + CORE RET",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 7580 + 4134,
 			.target_residency = 484329,
@@ -370,6 +383,7 @@ static struct cpuidle_driver omap3430_idle_driver = {
 			.desc		  = "MPU OFF + CORE RET",
 		},
 		{
+			.flags		  = CPUIDLE_FLAG_RCU_IDLE,
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 7505 + 15274,
 			.target_residency = 484329,

arch/arm/mach-omap2/cpuidle44xx.c

@@ -105,7 +105,7 @@ static int omap_enter_idle_smp(struct cpuidle_device *dev,
 	}
 	raw_spin_unlock_irqrestore(&mpu_lock, flag);
 
-	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
+	omap4_enter_lowpower(dev->cpu, cx->cpu_state, true);
 
 	raw_spin_lock_irqsave(&mpu_lock, flag);
 	if (cx->mpu_state_vote == num_online_cpus())
@@ -151,10 +151,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 				 (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 +166,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 
 	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
@@ -178,13 +178,13 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 				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;
 			}
 		}
 	}
 
-	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
+	omap4_enter_lowpower(dev->cpu, cx->cpu_state, true);
 	cpu_done[dev->cpu] = true;
 
 	/* Wakeup CPU1 only if it is not offlined */
@@ -194,9 +194,9 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 		    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 +222,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	cpu_pm_exit();
 
 cpu_pm_out:
-	RCU_NONIDLE(tick_broadcast_exit());
+	tick_broadcast_exit();
 
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
@@ -247,7 +247,8 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* 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 +257,8 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* 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 +284,8 @@ static struct cpuidle_driver omap5_idle_driver = {
 			/* 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",

arch/arm/mach-omap2/omap-mpuss-lowpower.c

@@ -33,6 +33,7 @@
  * and first to wake-up when MPUSS low power states are excercised
  */
 
+#include <linux/cpuidle.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/errno.h>
@@ -214,6 +215,7 @@ static void __init save_l2x0_context(void)
  * of OMAP4 MPUSS subsystem
  * @cpu : CPU ID
  * @power_state: Low power state.
+ * @rcuidle: RCU needs to be idled
  *
  * MPUSS states for the context save:
  * save_state =
@@ -222,7 +224,8 @@ static void __init save_l2x0_context(void)
  *	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)
+__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;
@@ -268,6 +271,10 @@ int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
 	cpu_clear_prev_logic_pwrst(cpu);
 	pwrdm_set_next_pwrst(pm_info->pwrdm, power_state);
 	pwrdm_set_logic_retst(pm_info->pwrdm, cpu_logic_state);
+
+	if (rcuidle)
+		ct_cpuidle_enter();
+
 	set_cpu_wakeup_addr(cpu, __pa_symbol(omap_pm_ops.resume));
 	omap_pm_ops.scu_prepare(cpu, power_state);
 	l2x0_pwrst_prepare(cpu, save_state);
@@ -283,6 +290,9 @@ int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
 	if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) && cpu)
 		gic_dist_enable();
 
+	if (rcuidle)
+		ct_cpuidle_exit();
+
 	/*
 	 * Restore the CPUx power state to ON otherwise CPUx
 	 * power domain can transitions to programmed low power

arch/arm/mach-omap2/pm.h

@@ -29,7 +29,7 @@ static inline int omap4_idle_init(void)
 
 extern void *omap3_secure_ram_storage;
 extern void omap3_pm_off_mode_enable(int);
-extern void omap_sram_idle(void);
+extern void omap_sram_idle(bool rcuidle);
 extern int omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused);
 
 extern int omap3_pm_get_suspend_state(struct powerdomain *pwrdm);

arch/arm/mach-omap2/pm34xx.c

@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/cpuidle.h>
 
 #include <trace/events/power.h>
 
@@ -174,7 +175,7 @@ static int omap34xx_do_sram_idle(unsigned long save_state)
 	return 0;
 }
 
-void omap_sram_idle(void)
+__cpuidle void omap_sram_idle(bool rcuidle)
 {
 	/* Variable to tell what needs to be saved and restored
 	 * in omap_sram_idle*/
@@ -254,11 +255,18 @@ void omap_sram_idle(void)
 	 */
 	if (save_state)
 		omap34xx_save_context(omap3_arm_context);
+
+	if (rcuidle)
+		ct_cpuidle_enter();
+
 	if (save_state == 1 || save_state == 3)
 		cpu_suspend(save_state, omap34xx_do_sram_idle);
 	else
 		omap34xx_do_sram_idle(save_state);
 
+	if (rcuidle)
+		ct_cpuidle_exit();
+
 	/* Restore normal SDRC POWER settings */
 	if (cpu_is_omap3430() && omap_rev() >= OMAP3430_REV_ES3_0 &&
 	    (omap_type() == OMAP2_DEVICE_TYPE_EMU ||
@@ -294,7 +302,7 @@ static void omap3_pm_idle(void)
 	if (omap_irq_pending())
 		return;
 
-	omap_sram_idle();
+	omap3_do_wfi();
 }
 
 #ifdef CONFIG_SUSPEND
@@ -316,7 +324,7 @@ static int omap3_pm_suspend(void)
 
 	omap3_intc_suspend();
 
-	omap_sram_idle();
+	omap_sram_idle(false);
 
 restore:
 	/* Restore next_pwrsts */

arch/arm/mach-omap2/pm44xx.c

@@ -76,7 +76,7 @@ static int omap4_pm_suspend(void)
 	 * domain CSWR is not supported by hardware.
 	 * More details can be found in OMAP4430 TRM section 4.3.4.2.
 	 */
-	omap4_enter_lowpower(cpu_id, cpu_suspend_state);
+	omap4_enter_lowpower(cpu_id, cpu_suspend_state, false);
 
 	/* Restore next powerdomain state */
 	list_for_each_entry(pwrst, &pwrst_list, node) {

arch/arm/mach-omap2/powerdomain.c

@@ -187,7 +187,7 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
 			trace_state = (PWRDM_TRACE_STATES_FLAG |
 				       ((next & OMAP_POWERSTATE_MASK) << 8) |
 				       ((prev & OMAP_POWERSTATE_MASK) << 0));
-			trace_power_domain_target_rcuidle(pwrdm->name,
+			trace_power_domain_target(pwrdm->name,
 						  trace_state,
 						  raw_smp_processor_id());
 		}
@@ -541,7 +541,7 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
 
 	if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
 		/* Trace the pwrdm desired target state */
-		trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
+		trace_power_domain_target(pwrdm->name, pwrst,
 					  raw_smp_processor_id());
 		/* Program the pwrdm desired target state */
 		ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);

arch/arm/mach-s3c/cpuidle-s3c64xx.c

@@ -19,9 +19,8 @@
 #include "regs-sys-s3c64xx.h"
 #include "regs-syscon-power-s3c64xx.h"
 
-static int s3c64xx_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv,
-			      int index)
+static __cpuidle int s3c64xx_enter_idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
 {
 	unsigned long tmp;
 

arch/arm64/kernel/cpuidle.c

@@ -62,15 +62,15 @@ int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 	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;
 
 	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
-		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter,
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM_RCU(psci_cpu_suspend_enter,
 						lpi->index, state);
 	else
-		return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+		return CPU_PM_CPU_IDLE_ENTER_PARAM_RCU(psci_cpu_suspend_enter,
 					     lpi->index, state);
 }
 #endif

arch/arm64/kernel/idle.c

@@ -42,5 +42,4 @@ void noinstr arch_cpu_idle(void)
 	 * tricks
 	 */
 	cpu_do_idle();
-	raw_local_irq_enable();
 }

arch/arm64/kernel/smp.c

@@ -865,7 +865,7 @@ static void do_handle_IPI(int ipinr)
 	unsigned int cpu = smp_processor_id();
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
+		trace_ipi_entry(ipi_types[ipinr]);
 
 	switch (ipinr) {
 	case IPI_RESCHEDULE:
@@ -914,7 +914,7 @@ static void do_handle_IPI(int ipinr)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+		trace_ipi_exit(ipi_types[ipinr]);
 }
 
 static irqreturn_t ipi_handler(int irq, void *data)

arch/arm64/kernel/suspend.c

@@ -4,6 +4,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/pgtable.h>
+#include <linux/cpuidle.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
@@ -104,6 +105,10 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * From this point debug exceptions are disabled to prevent
 	 * updates to mdscr register (saved and restored along with
 	 * general purpose registers) from kernel debuggers.
+	 *
+	 * Strictly speaking the trace_hardirqs_off() here is superfluous,
+	 * hardirqs should be firmly off by now. This really ought to use
+	 * something like raw_local_daif_save().
 	 */
 	flags = local_daif_save();
 
@@ -120,6 +125,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 */
 	arm_cpuidle_save_irq_context(&context);
 
+	ct_cpuidle_enter();
+
 	if (__cpu_suspend_enter(&state)) {
 		/* Call the suspend finisher */
 		ret = fn(arg);
@@ -133,8 +140,11 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		 */
 		if (!ret)
 			ret = -EOPNOTSUPP;
+
+		ct_cpuidle_exit();
 	} else {
-		RCU_NONIDLE(__cpu_suspend_exit());
+		ct_cpuidle_exit();
+		__cpu_suspend_exit();
 	}
 
 	arm_cpuidle_restore_irq_context(&context);

arch/arm64/kernel/vmlinux.lds.S

@@ -175,7 +175,6 @@ SECTIONS
 			ENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
-			CPUIDLE_TEXT
 			LOCK_TEXT
 			KPROBES_TEXT
 			HYPERVISOR_TEXT

arch/csky/kernel/process.c

@@ -100,6 +100,5 @@ void arch_cpu_idle(void)
 #ifdef CONFIG_CPU_PM_STOP
 	asm volatile("stop\n");
 #endif
-	raw_local_irq_enable();
 }
 #endif

arch/csky/kernel/smp.c

@@ -309,7 +309,7 @@ void arch_cpu_idle_dead(void)
 	while (!secondary_stack)
 		arch_cpu_idle();
 
-	local_irq_disable();
+	raw_local_irq_disable();
 
 	asm volatile(
 		"mov	sp, %0\n"

arch/csky/kernel/vmlinux.lds.S

@@ -34,7 +34,6 @@ SECTIONS
 		SOFTIRQENTRY_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		*(.fixup)

arch/hexagon/kernel/process.c

@@ -44,7 +44,6 @@ void arch_cpu_idle(void)
 {
 	__vmwait();
 	/*  interrupts wake us up, but irqs are still disabled */
-	raw_local_irq_enable();
 }
 
 /*

arch/hexagon/kernel/vmlinux.lds.S

@@ -41,7 +41,6 @@ SECTIONS
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		*(.fixup)

arch/ia64/kernel/process.c

@@ -242,6 +242,7 @@ void arch_cpu_idle(void)
 		(*mark_idle)(1);
 
 	raw_safe_halt();
+	raw_local_irq_disable();
 
 	if (mark_idle)
 		(*mark_idle)(0);

arch/ia64/kernel/time.c

@@ -25,6 +25,7 @@
 #include <linux/platform_device.h>
 #include <linux/sched/cputime.h>
 
+#include <asm/cputime.h>
 #include <asm/delay.h>
 #include <asm/efi.h>
 #include <asm/hw_irq.h>

arch/ia64/kernel/vmlinux.lds.S

@@ -51,7 +51,6 @@ SECTIONS {
 		__end_ivt_text = .;
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/loongarch/kernel/idle.c

@@ -13,4 +13,5 @@ void __cpuidle arch_cpu_idle(void)
 {
 	raw_local_irq_enable();
 	__arch_cpu_idle(); /* idle instruction needs irq enabled */
+	raw_local_irq_disable();
 }

arch/loongarch/kernel/vmlinux.lds.S

@@ -43,7 +43,6 @@ SECTIONS
 	.text : {
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/m68k/kernel/vmlinux-nommu.lds

@@ -48,7 +48,6 @@ SECTIONS {
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		*(.fixup)
 		. = ALIGN(16);

arch/m68k/kernel/vmlinux-std.lds

@@ -19,7 +19,6 @@ SECTIONS
 	IRQENTRY_TEXT
 	SOFTIRQENTRY_TEXT
 	SCHED_TEXT
-	CPUIDLE_TEXT
 	LOCK_TEXT
 	*(.fixup)
 	*(.gnu.warning)

arch/m68k/kernel/vmlinux-sun3.lds

@@ -19,7 +19,6 @@ SECTIONS
 	IRQENTRY_TEXT
 	SOFTIRQENTRY_TEXT
 	SCHED_TEXT
-	CPUIDLE_TEXT
 	LOCK_TEXT
 	*(.fixup)
 	*(.gnu.warning)

arch/microblaze/kernel/process.c

@@ -140,5 +140,4 @@ int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu)
 
 void arch_cpu_idle(void)
 {
-       raw_local_irq_enable();
 }

arch/microblaze/kernel/vmlinux.lds.S

@@ -36,7 +36,6 @@ SECTIONS {
 		EXIT_TEXT
 		EXIT_CALL
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/mips/kernel/idle.c

@@ -33,13 +33,13 @@ static void __cpuidle r3081_wait(void)
 {
 	unsigned long cfg = read_c0_conf();
 	write_c0_conf(cfg | R30XX_CONF_HALT);
-	raw_local_irq_enable();
 }
 
 void __cpuidle r4k_wait(void)
 {
 	raw_local_irq_enable();
 	__r4k_wait();
+	raw_local_irq_disable();
 }
 
 /*
@@ -57,7 +57,6 @@ void __cpuidle r4k_wait_irqoff(void)
 		"	.set	arch=r4000	\n"
 		"	wait			\n"
 		"	.set	pop		\n");
-	raw_local_irq_enable();
 }
 
 /*
@@ -77,7 +76,6 @@ static void __cpuidle rm7k_wait_irqoff(void)
 		"	wait						\n"
 		"	mtc0	$1, $12		# stalls until W stage	\n"
 		"	.set	pop					\n");
-	raw_local_irq_enable();
 }
 
 /*
@@ -103,6 +101,8 @@ static void __cpuidle au1k_wait(void)
 	"	nop				\n"
 	"	.set	pop			\n"
 	: : "r" (au1k_wait), "r" (c0status));
+
+	raw_local_irq_disable();
 }
 
 static int __initdata nowait;
@@ -241,17 +241,15 @@ void __init check_wait(void)
 	}
 }
 
-void arch_cpu_idle(void)
+__cpuidle void arch_cpu_idle(void)
 {
 	if (cpu_wait)
 		cpu_wait();
-	else
-		raw_local_irq_enable();
 }
 
 #ifdef CONFIG_CPU_IDLE
 
-int mips_cpuidle_wait_enter(struct cpuidle_device *dev,
+__cpuidle int mips_cpuidle_wait_enter(struct cpuidle_device *dev,
 				      struct cpuidle_driver *drv, int index)
 {
 	arch_cpu_idle();

arch/mips/kernel/vmlinux.lds.S

@@ -61,7 +61,6 @@ SECTIONS
 	.text : {
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/nios2/kernel/process.c

@@ -33,7 +33,6 @@ EXPORT_SYMBOL(pm_power_off);
 
 void arch_cpu_idle(void)
 {
-	raw_local_irq_enable();
 }
 
 /*

arch/nios2/kernel/vmlinux.lds.S

@@ -24,7 +24,6 @@ SECTIONS
 	.text : {
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT

arch/openrisc/kernel/process.c

@@ -102,6 +102,7 @@ void arch_cpu_idle(void)
 	raw_local_irq_enable();
 	if (mfspr(SPR_UPR) & SPR_UPR_PMP)
 		mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
+	raw_local_irq_disable();
 }
 
 void (*pm_power_off)(void) = NULL;

arch/openrisc/kernel/vmlinux.lds.S

@@ -52,7 +52,6 @@ SECTIONS
           _stext = .;
 	  TEXT_TEXT
 	  SCHED_TEXT
-	  CPUIDLE_TEXT
 	  LOCK_TEXT
 	  KPROBES_TEXT
 	  IRQENTRY_TEXT

arch/parisc/kernel/process.c

@@ -183,8 +183,6 @@ void arch_cpu_idle_dead(void)
 
 void __cpuidle arch_cpu_idle(void)
 {
-	raw_local_irq_enable();
-
 	/* nop on real hardware, qemu will idle sleep. */
 	asm volatile("or %%r10,%%r10,%%r10\n":::);
 }

arch/parisc/kernel/vmlinux.lds.S

@@ -86,7 +86,6 @@ SECTIONS
 		TEXT_TEXT
 		LOCK_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT

arch/powerpc/kernel/idle.c

@@ -51,10 +51,9 @@ void arch_cpu_idle(void)
 		 * Some power_save functions return with
 		 * interrupts enabled, some don't.
 		 */
-		if (irqs_disabled())
-			raw_local_irq_enable();
+		if (!irqs_disabled())
+			raw_local_irq_disable();
 	} else {
-		raw_local_irq_enable();
 		/*
 		 * Go into low thread priority and possibly
 		 * low power mode.

arch/powerpc/kernel/vmlinux.lds.S

@@ -112,7 +112,6 @@ SECTIONS
 #endif
 		NOINSTR_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/riscv/kernel/process.c

@@ -39,7 +39,6 @@ extern asmlinkage void ret_from_kernel_thread(void);
 void arch_cpu_idle(void)
 {
 	cpu_do_idle();
-	raw_local_irq_enable();
 }
 
 void __show_regs(struct pt_regs *regs)

arch/riscv/kernel/vmlinux-xip.lds.S

@@ -39,7 +39,6 @@ SECTIONS
 		_stext = .;
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		ENTRY_TEXT

arch/riscv/kernel/vmlinux.lds.S

@@ -42,7 +42,6 @@ SECTIONS
 		_stext = .;
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		ENTRY_TEXT

arch/s390/kernel/idle.c

@@ -12,9 +12,9 @@
 #include <linux/notifier.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/sched/cputime.h>
 #include <trace/events/power.h>
 #include <asm/cpu_mf.h>
+#include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
@@ -66,7 +66,6 @@ void arch_cpu_idle(void)
 	idle->idle_count++;
 	account_idle_time(cputime_to_nsecs(idle_time));
 	raw_write_seqcount_end(&idle->seqcount);
-	raw_local_irq_enable();
 }
 
 static ssize_t show_idle_count(struct device *dev,

arch/s390/kernel/vmlinux.lds.S

@@ -44,7 +44,6 @@ SECTIONS
 		HEAD_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/s390/kernel/vtime.c

@@ -7,13 +7,13 @@
  */
 
 #include <linux/kernel_stat.h>
-#include <linux/sched/cputime.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
 #include <asm/alternative.h>
+#include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
 #include <asm/cpu_mf.h>

arch/sh/kernel/idle.c

@@ -25,6 +25,7 @@ void default_idle(void)
 	raw_local_irq_enable();
 	/* Isn't this racy ? */
 	cpu_sleep();
+	raw_local_irq_disable();
 	clear_bl_bit();
 }
 

arch/sh/kernel/vmlinux.lds.S

@@ -30,7 +30,6 @@ SECTIONS
 		HEAD_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/sparc/kernel/leon_pmc.c

@@ -57,6 +57,8 @@ static void pmc_leon_idle_fixup(void)
 		"lda	[%0] %1, %%g0\n"
 		:
 		: "r"(address), "i"(ASI_LEON_BYPASS));
+
+	raw_local_irq_disable();
 }
 
 /*
@@ -70,6 +72,8 @@ static void pmc_leon_idle(void)
 
 	/* For systems without power-down, this will be no-op */
 	__asm__ __volatile__ ("wr	%g0, %asr19\n\t");
+
+	raw_local_irq_disable();
 }
 
 /* Install LEON Power Down function */

arch/sparc/kernel/process_32.c

@@ -71,7 +71,6 @@ void arch_cpu_idle(void)
 {
 	if (sparc_idle)
 		(*sparc_idle)();
-	raw_local_irq_enable();
 }
 
 /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */

arch/sparc/kernel/process_64.c

@@ -59,7 +59,6 @@ void arch_cpu_idle(void)
 {
 	if (tlb_type != hypervisor) {
 		touch_nmi_watchdog();
-		raw_local_irq_enable();
 	} else {
 		unsigned long pstate;
 
@@ -90,6 +89,8 @@ void arch_cpu_idle(void)
 			"wrpr %0, %%g0, %%pstate"
 			: "=&r" (pstate)
 			: "i" (PSTATE_IE));
+
+		raw_local_irq_disable();
 	}
 }
 

arch/sparc/kernel/vmlinux.lds.S

@@ -50,7 +50,6 @@ SECTIONS
 		HEAD_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT

arch/um/kernel/dyn.lds.S

@@ -74,7 +74,6 @@ SECTIONS
     _stext = .;
     TEXT_TEXT
     SCHED_TEXT
-    CPUIDLE_TEXT
     LOCK_TEXT
     IRQENTRY_TEXT
     SOFTIRQENTRY_TEXT

arch/um/kernel/process.c

@@ -218,7 +218,6 @@ void arch_cpu_idle(void)
 {
 	cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
 	um_idle_sleep();
-	raw_local_irq_enable();
 }
 
 int __cant_sleep(void) {

arch/um/kernel/uml.lds.S

@@ -35,7 +35,6 @@ SECTIONS
     _stext = .;
     TEXT_TEXT
     SCHED_TEXT
-    CPUIDLE_TEXT
     LOCK_TEXT
     IRQENTRY_TEXT
     SOFTIRQENTRY_TEXT

arch/x86/boot/compressed/vmlinux.lds.S

@@ -34,6 +34,7 @@ SECTIONS
 		_text = .; 	/* Text */
 		*(.text)
 		*(.text.*)
+		*(.noinstr.text)
 		_etext = . ;
 	}
 	.rodata : {

arch/x86/coco/tdx/tdcall.S

@@ -31,6 +31,8 @@
 					  TDX_R12 | TDX_R13 | \
 					  TDX_R14 | TDX_R15 )
 
+.section .noinstr.text, "ax"
+
 /*
  * __tdx_module_call()  - Used by TDX guests to request services from
  * the TDX module (does not include VMM services) using TDCALL instruction.
@@ -139,19 +141,6 @@ SYM_FUNC_START(__tdx_hypercall)
 
 	movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx
 
-	/*
-	 * For the idle loop STI needs to be called directly before the TDCALL
-	 * that enters idle (EXIT_REASON_HLT case). STI instruction enables
-	 * interrupts only one instruction later. If there is a window between
-	 * STI and the instruction that emulates the HALT state, there is a
-	 * chance for interrupts to happen in this window, which can delay the
-	 * HLT operation indefinitely. Since this is the not the desired
-	 * result, conditionally call STI before TDCALL.
-	 */
-	testq $TDX_HCALL_ISSUE_STI, %rsi
-	jz .Lskip_sti
-	sti
-.Lskip_sti:
 	tdcall
 
 	/*

arch/x86/coco/tdx/tdx.c

@@ -64,8 +64,9 @@ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
 }
 
 /* Called from __tdx_hypercall() for unrecoverable failure */
-void __tdx_hypercall_failed(void)
+noinstr void __tdx_hypercall_failed(void)
 {
+	instrumentation_begin();
 	panic("TDVMCALL failed. TDX module bug?");
 }
 
@@ -75,7 +76,7 @@ void __tdx_hypercall_failed(void)
  * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and
  * guest sides of these calls.
  */
-static u64 hcall_func(u64 exit_reason)
+static __always_inline u64 hcall_func(u64 exit_reason)
 {
 	return exit_reason;
 }
@@ -220,7 +221,7 @@ static int ve_instr_len(struct ve_info *ve)
 	}
 }
 
-static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
+static u64 __cpuidle __halt(const bool irq_disabled)
 {
 	struct tdx_hypercall_args args = {
 		.r10 = TDX_HYPERCALL_STANDARD,
@@ -240,20 +241,14 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
 	 * can keep the vCPU in virtual HLT, even if an IRQ is
 	 * pending, without hanging/breaking the guest.
 	 */
-	return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
+	return __tdx_hypercall(&args, 0);
 }
 
 static int handle_halt(struct ve_info *ve)
 {
-	/*
-	 * Since non safe halt is mainly used in CPU offlining
-	 * and the guest will always stay in the halt state, don't
-	 * call the STI instruction (set do_sti as false).
-	 */
 	const bool irq_disabled = irqs_disabled();
-	const bool do_sti = false;
 
-	if (__halt(irq_disabled, do_sti))
+	if (__halt(irq_disabled))
 		return -EIO;
 
 	return ve_instr_len(ve);
@@ -261,18 +256,12 @@ static int handle_halt(struct ve_info *ve)
 
 void __cpuidle tdx_safe_halt(void)
 {
-	 /*
-	  * For do_sti=true case, __tdx_hypercall() function enables
-	  * interrupts using the STI instruction before the TDCALL. So
-	  * set irq_disabled as false.
-	  */
 	const bool irq_disabled = false;
-	const bool do_sti = true;
 
 	/*
 	 * Use WARN_ONCE() to report the failure.
 	 */
-	if (__halt(irq_disabled, do_sti))
+	if (__halt(irq_disabled))
 		WARN_ONCE(1, "HLT instruction emulation failed\n");
 }
 

arch/x86/events/amd/brs.c

@@ -41,18 +41,15 @@ static inline unsigned int brs_to(int idx)
 	return MSR_AMD_SAMP_BR_FROM + 2 * idx + 1;
 }
 
-static inline void set_debug_extn_cfg(u64 val)
+static __always_inline void set_debug_extn_cfg(u64 val)
 {
 	/* bits[4:3] must always be set to 11b */
-	wrmsrl(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3);
+	__wrmsr(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3, val >> 32);
 }
 
-static inline u64 get_debug_extn_cfg(void)
+static __always_inline u64 get_debug_extn_cfg(void)
 {
-	u64 val;
-
-	rdmsrl(MSR_AMD_DBG_EXTN_CFG, val);
-	return val;
+	return __rdmsr(MSR_AMD_DBG_EXTN_CFG);
 }
 
 static bool __init amd_brs_detect(void)
@@ -405,7 +402,7 @@ void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_i
  * called from ACPI processor_idle.c or acpi_pad.c
  * with interrupts disabled
  */
-void perf_amd_brs_lopwr_cb(bool lopwr_in)
+void noinstr perf_amd_brs_lopwr_cb(bool lopwr_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	union amd_debug_extn_cfg cfg;

arch/x86/include/asm/atomic64_32.h

@@ -71,7 +71,7 @@ ATOMIC64_DECL(add_unless);
  * the old value.
  */
 
-static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	return arch_cmpxchg64(&v->counter, o, n);
 }
@@ -85,7 +85,7 @@ static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
  * Atomically xchgs the value of @v to @n and returns
  * the old value.
  */
-static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
+static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 {
 	s64 o;
 	unsigned high = (unsigned)(n >> 32);
@@ -104,7 +104,7 @@ static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
  *
  * Atomically sets the value of @v to @n.
  */
-static inline void arch_atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
@@ -119,7 +119,7 @@ static inline void arch_atomic64_set(atomic64_t *v, s64 i)
  *
  * Atomically reads the value of @v and returns it.
  */
-static inline s64 arch_atomic64_read(const atomic64_t *v)
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
 	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
@@ -133,7 +133,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + *@v
  */
-static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -145,7 +145,7 @@ static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 /*
  * Other variants with different arithmetic operators:
  */
-static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -154,7 +154,7 @@ static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
 
-static inline s64 arch_atomic64_inc_return(atomic64_t *v)
+static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
 	s64 a;
 	alternative_atomic64(inc_return, "=&A" (a),
@@ -163,7 +163,7 @@ static inline s64 arch_atomic64_inc_return(atomic64_t *v)
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
 
-static inline s64 arch_atomic64_dec_return(atomic64_t *v)
+static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
 	s64 a;
 	alternative_atomic64(dec_return, "=&A" (a),
@@ -179,7 +179,7 @@ static inline s64 arch_atomic64_dec_return(atomic64_t *v)
  *
  * Atomically adds @i to @v.
  */
-static inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -194,7 +194,7 @@ static inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -208,7 +208,7 @@ static inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void arch_atomic64_inc(atomic64_t *v)
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
@@ -221,7 +221,7 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void arch_atomic64_dec(atomic64_t *v)
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
@@ -237,7 +237,7 @@ static inline void arch_atomic64_dec(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns non-zero if the add was done, zero otherwise.
  */
-static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
@@ -248,7 +248,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 }
 #define arch_atomic64_add_unless arch_atomic64_add_unless
 
-static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
+static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
 	alternative_atomic64(inc_not_zero, "=&a" (r),
@@ -257,7 +257,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 
-static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	s64 r;
 	alternative_atomic64(dec_if_positive, "=&A" (r),
@@ -269,7 +269,7 @@ static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-static inline void arch_atomic64_and(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -277,7 +277,7 @@ static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 		c = old;
 }
 
-static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -288,7 +288,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
-static inline void arch_atomic64_or(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -296,7 +296,7 @@ static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 		c = old;
 }
 
-static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -307,7 +307,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
-static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -315,7 +315,7 @@ static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 		c = old;
 }
 
-static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 
@@ -326,7 +326,7 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
 
-static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
 	s64 old, c = 0;
 

arch/x86/include/asm/atomic64_64.h

@@ -17,7 +17,7 @@
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-static inline s64 arch_atomic64_read(const atomic64_t *v)
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	return __READ_ONCE((v)->counter);
 }
@@ -29,7 +29,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void arch_atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	__WRITE_ONCE(v->counter, i);
 }
@@ -55,7 +55,7 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void arch_atomic64_sub(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
@@ -71,7 +71,7 @@ static inline void arch_atomic64_sub(s64 i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
+static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i);
 }
@@ -113,7 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
+static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e);
 }
@@ -127,7 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
+static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e);
 }
@@ -142,7 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v)
+static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i);
 }
@@ -161,25 +161,25 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
 
-static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	return arch_atomic64_add_return(-i, v);
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
 
-static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
 #define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
-static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
 
-static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
 }
@@ -191,13 +191,13 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s
 }
 #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 
-static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
+static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	return arch_xchg(&v->counter, new);
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
 
-static inline void arch_atomic64_and(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
 			: "+m" (v->counter)
@@ -205,7 +205,7 @@ static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 			: "memory");
 }
 
-static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 
@@ -215,7 +215,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
-static inline void arch_atomic64_or(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "orq %1,%0"
 			: "+m" (v->counter)
@@ -223,7 +223,7 @@ static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 			: "memory");
 }
 
-static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 
@@ -233,7 +233,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
-static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorq %1,%0"
 			: "+m" (v->counter)
@@ -241,7 +241,7 @@ static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 			: "memory");
 }
 
-static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 

arch/x86/include/asm/fpu/xcr.h

@@ -5,7 +5,7 @@
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
 #define XCR_XFEATURE_IN_USE_MASK	0x00000001
 
-static inline u64 xgetbv(u32 index)
+static __always_inline u64 xgetbv(u32 index)
 {
 	u32 eax, edx;
 
@@ -27,7 +27,7 @@ static inline void xsetbv(u32 index, u64 value)
  *
  * Callers should check X86_FEATURE_XGETBV1.
  */
-static inline u64 xfeatures_in_use(void)
+static __always_inline u64 xfeatures_in_use(void)
 {
 	return xgetbv(XCR_XFEATURE_IN_USE_MASK);
 }

arch/x86/include/asm/irqflags.h

@@ -8,9 +8,6 @@
 
 #include <asm/nospec-branch.h>
 
-/* Provide __cpuidle; we can't safely include <linux/cpu.h> */
-#define __cpuidle __section(".cpuidle.text")
-
 /*
  * Interrupt control:
  */
@@ -45,13 +42,13 @@ static __always_inline void native_irq_enable(void)
 	asm volatile("sti": : :"memory");
 }
 
-static inline __cpuidle void native_safe_halt(void)
+static __always_inline void native_safe_halt(void)
 {
 	mds_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
-static inline __cpuidle void native_halt(void)
+static __always_inline void native_halt(void)
 {
 	mds_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
@@ -84,7 +81,7 @@ static __always_inline void arch_local_irq_enable(void)
  * Used in the idle loop; sti takes one instruction cycle
  * to complete:
  */
-static inline __cpuidle void arch_safe_halt(void)
+static __always_inline void arch_safe_halt(void)
 {
 	native_safe_halt();
 }
@@ -93,7 +90,7 @@ static inline __cpuidle void arch_safe_halt(void)
  * Used when interrupts are already enabled or to
  * shutdown the processor:
  */
-static inline __cpuidle void halt(void)
+static __always_inline void halt(void)
 {
 	native_halt();
 }

arch/x86/include/asm/kvmclock.h

@@ -8,7 +8,7 @@ extern struct clocksource kvm_clock;
 
 DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 
-static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
 {
 	return &this_cpu_read(hv_clock_per_cpu)->pvti;
 }

arch/x86/include/asm/mwait.h

@@ -26,7 +26,7 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-static inline void __monitor(const void *eax, unsigned long ecx,
+static __always_inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {
 	/* "monitor %eax, %ecx, %edx;" */
@@ -34,7 +34,7 @@ static inline void __monitor(const void *eax, unsigned long ecx,
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static inline void __monitorx(const void *eax, unsigned long ecx,
+static __always_inline void __monitorx(const void *eax, unsigned long ecx,
 			      unsigned long edx)
 {
 	/* "monitorx %eax, %ecx, %edx;" */
@@ -42,7 +42,7 @@ static inline void __monitorx(const void *eax, unsigned long ecx,
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
 {
 	mds_idle_clear_cpu_buffers();
 
@@ -77,7 +77,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
  * EAX                     (logical) address to monitor
  * ECX                     #GP if not zero
  */
-static inline void __mwaitx(unsigned long eax, unsigned long ebx,
+static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
 				     unsigned long ecx)
 {
 	/* No MDS buffer clear as this is AMD/HYGON only */
@@ -87,7 +87,7 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
-static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
 	mds_idle_clear_cpu_buffers();
 	/* "mwait %eax, %ecx;" */
@@ -105,7 +105,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  * New with Core Duo processors, MWAIT can take some hints based on CPU
  * capability.
  */
-static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {

arch/x86/include/asm/nospec-branch.h

@@ -564,7 +564,7 @@ static __always_inline void mds_user_clear_cpu_buffers(void)
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void mds_idle_clear_cpu_buffers(void)
 {
 	if (static_branch_likely(&mds_idle_clear))
 		mds_clear_cpu_buffers();

arch/x86/include/asm/paravirt.h

@@ -26,7 +26,7 @@ DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
 
 void paravirt_set_sched_clock(u64 (*func)(void));
 
-static inline u64 paravirt_sched_clock(void)
+static __always_inline u64 paravirt_sched_clock(void)
 {
 	return static_call(pv_sched_clock)();
 }
@@ -168,7 +168,7 @@ static inline void __write_cr4(unsigned long x)
 	PVOP_VCALL1(cpu.write_cr4, x);
 }
 
-static inline void arch_safe_halt(void)
+static __always_inline void arch_safe_halt(void)
 {
 	PVOP_VCALL0(irq.safe_halt);
 }
@@ -178,7 +178,9 @@ static inline void halt(void)
 	PVOP_VCALL0(irq.halt);
 }
 
-static inline void wbinvd(void)
+extern noinstr void pv_native_wbinvd(void);
+
+static __always_inline void wbinvd(void)
 {
 	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
 }

arch/x86/include/asm/perf_event.h

@@ -586,7 +586,7 @@ extern void perf_amd_brs_lopwr_cb(bool lopwr_in);
 
 DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb);
 
-static inline void perf_lopwr_cb(bool lopwr_in)
+static __always_inline void perf_lopwr_cb(bool lopwr_in)
 {
 	static_call_mod(perf_lopwr_cb)(lopwr_in);
 }

arch/x86/include/asm/pvclock.h

@@ -7,6 +7,7 @@
 
 /* some helper functions for xen and kvm pv clock sources */
 u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
 void pvclock_set_flags(u8 flags);
 unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
@@ -39,7 +40,7 @@ bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src,
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
  */
-static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
+static __always_inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 {
 	u64 product;
 #ifdef __i386__

arch/x86/include/asm/shared/io.h

@@ -5,13 +5,13 @@
 #include <linux/types.h>
 
 #define BUILDIO(bwl, bw, type)						\
-static inline void __out##bwl(type value, u16 port)			\
+static __always_inline void __out##bwl(type value, u16 port)		\
 {									\
 	asm volatile("out" #bwl " %" #bw "0, %w1"			\
 		     : : "a"(value), "Nd"(port));			\
 }									\
 									\
-static inline type __in##bwl(u16 port)					\
+static __always_inline type __in##bwl(u16 port)				\
 {									\
 	type value;							\
 	asm volatile("in" #bwl " %w1, %" #bw "0"			\

arch/x86/include/asm/shared/tdx.h

@@ -8,7 +8,6 @@
 #define TDX_HYPERCALL_STANDARD  0
 
 #define TDX_HCALL_HAS_OUTPUT	BIT(0)
-#define TDX_HCALL_ISSUE_STI	BIT(1)
 
 #define TDX_CPUID_LEAF_ID	0x21
 #define TDX_IDENT		"IntelTDX    "

arch/x86/include/asm/special_insns.h

@@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru)
 }
 #endif
 
-static inline void native_wbinvd(void)
+static __always_inline void native_wbinvd(void)
 {
 	asm volatile("wbinvd": : :"memory");
 }
@@ -179,7 +179,7 @@ static inline void __write_cr4(unsigned long x)
 	native_write_cr4(x);
 }
 
-static inline void wbinvd(void)
+static __always_inline void wbinvd(void)
 {
 	native_wbinvd();
 }
@@ -196,7 +196,7 @@ static inline void load_gs_index(unsigned int selector)
 
 #endif /* CONFIG_PARAVIRT_XXL */
 
-static inline void clflush(volatile void *__p)
+static __always_inline void clflush(volatile void *__p)
 {
 	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
@@ -295,7 +295,7 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 	return 0;
 }
 
-static inline void tile_release(void)
+static __always_inline void tile_release(void)
 {
 	/*
 	 * Instruction opcode for TILERELEASE; supported in binutils

arch/x86/include/asm/xen/hypercall.h

@@ -382,7 +382,7 @@ MULTI_stack_switch(struct multicall_entry *mcl,
 }
 #endif
 
-static inline int
+static __always_inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
 	return _hypercall2(int, sched_op, cmd, arg);

arch/x86/kernel/cpu/bugs.c

@@ -86,7 +86,7 @@ void update_spec_ctrl_cond(u64 val)
 		wrmsrl(MSR_IA32_SPEC_CTRL, val);
 }
 
-u64 spec_ctrl_current(void)
+noinstr u64 spec_ctrl_current(void)
 {
 	return this_cpu_read(x86_spec_ctrl_current);
 }

arch/x86/kernel/cpu/vmware.c

@@ -143,7 +143,7 @@ static __init int parse_no_stealacc(char *arg)
 }
 early_param("no-steal-acc", parse_no_stealacc);
 
-static unsigned long long notrace vmware_sched_clock(void)
+static noinstr u64 vmware_sched_clock(void)
 {
 	unsigned long long ns;
 

arch/x86/kernel/fpu/core.c

@@ -853,12 +853,12 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
  * Initialize register state that may prevent from entering low-power idle.
  * This function will be invoked from the cpuidle driver only when needed.
  */
-void fpu_idle_fpregs(void)
+noinstr void fpu_idle_fpregs(void)
 {
 	/* Note: AMX_TILE being enabled implies XGETBV1 support */
 	if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
 	    (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
 		tile_release();
-		fpregs_deactivate(&current->thread.fpu);
+		__this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 	}
 }

arch/x86/kernel/kvmclock.c

@@ -71,12 +71,12 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 	return -ENODEV;
 }
 
-static u64 kvm_clock_read(void)
+static noinstr u64 kvm_clock_read(void)
 {
 	u64 ret;
 
 	preempt_disable_notrace();
-	ret = pvclock_clocksource_read(this_cpu_pvti());
+	ret = pvclock_clocksource_read_nowd(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -86,7 +86,7 @@ static u64 kvm_clock_get_cycles(struct clocksource *cs)
 	return kvm_clock_read();
 }
 
-static u64 kvm_sched_clock_read(void)
+static noinstr u64 kvm_sched_clock_read(void)
 {
 	return kvm_clock_read() - kvm_sched_clock_offset;
 }

arch/x86/kernel/paravirt.c

@@ -216,6 +216,11 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
 	native_set_debugreg(regno, val);
 }
 
+noinstr void pv_native_wbinvd(void)
+{
+	native_wbinvd();
+}
+
 static noinstr void pv_native_irq_enable(void)
 {
 	native_irq_enable();
@@ -225,6 +230,11 @@ static noinstr void pv_native_irq_disable(void)
 {
 	native_irq_disable();
 }
+
+static noinstr void pv_native_safe_halt(void)
+{
+	native_safe_halt();
+}
 #endif
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
@@ -256,7 +266,7 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.read_cr0		= native_read_cr0,
 	.cpu.write_cr0		= native_write_cr0,
 	.cpu.write_cr4		= native_write_cr4,
-	.cpu.wbinvd		= native_wbinvd,
+	.cpu.wbinvd		= pv_native_wbinvd,
 	.cpu.read_msr		= native_read_msr,
 	.cpu.write_msr		= native_write_msr,
 	.cpu.read_msr_safe	= native_read_msr_safe,
@@ -290,7 +300,7 @@ struct paravirt_patch_template pv_ops = {
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(native_save_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
-	.irq.safe_halt		= native_safe_halt,
+	.irq.safe_halt		= pv_native_safe_halt,
 	.irq.halt		= native_halt,
 #endif /* CONFIG_PARAVIRT_XXL */
 

arch/x86/kernel/process.c

@@ -24,6 +24,7 @@
 #include <linux/cpuidle.h>
 #include <linux/acpi.h>
 #include <linux/elf-randomize.h>
+#include <linux/static_call.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/cpu.h>
@@ -694,7 +695,24 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(boot_option_idle_override);
 
-static void (*x86_idle)(void);
+/*
+ * We use this if we don't have any better idle routine..
+ */
+void __cpuidle default_idle(void)
+{
+	raw_safe_halt();
+	raw_local_irq_disable();
+}
+#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
+EXPORT_SYMBOL(default_idle);
+#endif
+
+DEFINE_STATIC_CALL_NULL(x86_idle, default_idle);
+
+static bool x86_idle_set(void)
+{
+	return !!static_call_query(x86_idle);
+}
 
 #ifndef CONFIG_SMP
 static inline void play_dead(void)
@@ -717,28 +735,17 @@ void arch_cpu_idle_dead(void)
 /*
  * Called from the generic idle code.
  */
-void arch_cpu_idle(void)
+void __cpuidle arch_cpu_idle(void)
 {
-	x86_idle();
+	static_call(x86_idle)();
 }
 
-/*
- * We use this if we don't have any better idle routine..
- */
-void __cpuidle default_idle(void)
-{
-	raw_safe_halt();
-}
-#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
-EXPORT_SYMBOL(default_idle);
-#endif
-
 #ifdef CONFIG_XEN
 bool xen_set_default_idle(void)
 {
-	bool ret = !!x86_idle;
+	bool ret = x86_idle_set();
 
-	x86_idle = default_idle;
+	static_call_update(x86_idle, default_idle);
 
 	return ret;
 }
@@ -800,13 +807,7 @@ static void amd_e400_idle(void)
 
 	default_idle();
 
-	/*
-	 * The switch back from broadcast mode needs to be called with
-	 * interrupts disabled.
-	 */
-	raw_local_irq_disable();
 	tick_broadcast_exit();
-	raw_local_irq_enable();
 }
 
 /*
@@ -864,12 +865,10 @@ static __cpuidle void mwait_idle(void)
 		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		if (!need_resched())
+		if (!need_resched()) {
 			__sti_mwait(0, 0);
-		else
-			raw_local_irq_enable();
-	} else {
-		raw_local_irq_enable();
+			raw_local_irq_disable();
+		}
 	}
 	__current_clr_polling();
 }
@@ -880,20 +879,20 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 	if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1)
 		pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
 #endif
-	if (x86_idle || boot_option_idle_override == IDLE_POLL)
+	if (x86_idle_set() || boot_option_idle_override == IDLE_POLL)
 		return;
 
 	if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
 		pr_info("using AMD E400 aware idle routine\n");
-		x86_idle = amd_e400_idle;
+		static_call_update(x86_idle, amd_e400_idle);
 	} else if (prefer_mwait_c1_over_halt(c)) {
 		pr_info("using mwait in idle threads\n");
-		x86_idle = mwait_idle;
+		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
-		x86_idle = tdx_safe_halt;
+		static_call_update(x86_idle, tdx_safe_halt);
 	} else
-		x86_idle = default_idle;
+		static_call_update(x86_idle, default_idle);
 }
 
 void amd_e400_c1e_apic_setup(void)
@@ -946,7 +945,7 @@ static int __init idle_setup(char *str)
 		 * To continue to load the CPU idle driver, don't touch
 		 * the boot_option_idle_override.
 		 */
-		x86_idle = default_idle;
+		static_call_update(x86_idle, default_idle);
 		boot_option_idle_override = IDLE_HALT;
 	} else if (!strcmp(str, "nomwait")) {
 		/*

arch/x86/kernel/pvclock.c

@@ -64,7 +64,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 	return flags & valid_flags;
 }
 
-u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+static __always_inline
+u64 __pvclock_clocksource_read(struct pvclock_vcpu_time_info *src, bool dowd)
 {
 	unsigned version;
 	u64 ret;
@@ -77,7 +78,7 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 		flags = src->flags;
 	} while (pvclock_read_retry(src, version));
 
-	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
+	if (dowd && unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
 		src->flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 	}
@@ -100,16 +101,25 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 	 * updating at the same time, and one of them could be slightly behind,
 	 * making the assumption that last_value always go forward fail to hold.
 	 */
-	last = atomic64_read(&last_value);
+	last = arch_atomic64_read(&last_value);
 	do {
-		if (ret < last)
+		if (ret <= last)
 			return last;
-		last = atomic64_cmpxchg(&last_value, last, ret);
-	} while (unlikely(last != ret));
+	} while (!arch_atomic64_try_cmpxchg(&last_value, &last, ret));
 
 	return ret;
 }
 
+u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+	return __pvclock_clocksource_read(src, true);
+}
+
+noinstr u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src)
+{
+	return __pvclock_clocksource_read(src, false);
+}
+
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 			    struct pvclock_vcpu_time_info *vcpu_time,
 			    struct timespec64 *ts)

arch/x86/kernel/tsc.c

@@ -215,7 +215,7 @@ static void __init cyc2ns_init_secondary_cpus(void)
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
-u64 native_sched_clock(void)
+noinstr u64 native_sched_clock(void)
 {
 	if (static_branch_likely(&__use_tsc)) {
 		u64 tsc_now = rdtsc();
@@ -248,7 +248,7 @@ u64 native_sched_clock_from_tsc(u64 tsc)
 /* We need to define a real function for sched_clock, to override the
    weak default version */
 #ifdef CONFIG_PARAVIRT
-unsigned long long sched_clock(void)
+noinstr u64 sched_clock(void)
 {
 	return paravirt_sched_clock();
 }
@@ -258,8 +258,7 @@ bool using_native_sched_clock(void)
 	return static_call_query(pv_sched_clock) == native_sched_clock;
 }
 #else
-unsigned long long
-sched_clock(void) __attribute__((alias("native_sched_clock")));
+u64 sched_clock(void) __attribute__((alias("native_sched_clock")));
 
 bool using_native_sched_clock(void) { return true; }
 #endif

arch/x86/kernel/vmlinux.lds.S

@@ -129,7 +129,6 @@ SECTIONS
 		HEAD_TEXT
 		TEXT_TEXT
 		SCHED_TEXT
-		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
 		SOFTIRQENTRY_TEXT

arch/x86/lib/memcpy_64.S

@@ -8,7 +8,7 @@
 #include <asm/alternative.h>
 #include <asm/export.h>
 
-.pushsection .noinstr.text, "ax"
+.section .noinstr.text, "ax"
 
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
@@ -43,7 +43,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
+SYM_FUNC_ALIAS(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 /*
@@ -184,4 +184,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	RET
 SYM_FUNC_END(memcpy_orig)
 
-.popsection