Merge tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP updates from Thomas Gleixner:
 "A large update for SMP management:

   - Parallel CPU bringup

     The reason why people are interested in parallel bringup is to
     shorten the (kexec) reboot time of cloud servers to reduce the
     downtime of the VM tenants.

     The current fully serialized bringup does the following per AP:

       1) Prepare callbacks (allocate, intialize, create threads)
       2) Kick the AP alive (e.g. INIT/SIPI on x86)
       3) Wait for the AP to report alive state
       4) Let the AP continue through the atomic bringup
       5) Let the AP run the threaded bringup to full online state

     There are two significant delays:

       #3 The time for an AP to report alive state in start_secondary()
          on x86 has been measured in the range between 350us and 3.5ms
          depending on vendor and CPU type, BIOS microcode size etc.

       #4 The atomic bringup does the microcode update. This has been
          measured to take up to ~8ms on the primary threads depending
          on the microcode patch size to apply.

     On a two socket SKL server with 56 cores (112 threads) the boot CPU
     spends on current mainline about 800ms busy waiting for the APs to
     come up and apply microcode. That's more than 80% of the actual
     onlining procedure.

     This can be reduced significantly by splitting the bringup
     mechanism into two parts:

       1) Run the prepare callbacks and kick the AP alive for each AP
          which needs to be brought up.

          The APs wake up, do their firmware initialization and run the
          low level kernel startup code including microcode loading in
          parallel up to the first synchronization point. (#1 and #2
          above)

       2) Run the rest of the bringup code strictly serialized per CPU
          (#3 - #5 above) as it's done today.

          Parallelizing that stage of the CPU bringup might be possible
          in theory, but it's questionable whether required surgery
          would be justified for a pretty small gain.

     If the system is large enough the first AP is already waiting at
     the first synchronization point when the boot CPU finished the
     wake-up of the last AP. That reduces the AP bringup time on that
     SKL from ~800ms to ~80ms, i.e. by a factor ~10x.

     The actual gain varies wildly depending on the system, CPU,
     microcode patch size and other factors. There are some
     opportunities to reduce the overhead further, but that needs some
     deep surgery in the x86 CPU bringup code.

     For now this is only enabled on x86, but the core functionality
     obviously works for all SMP capable architectures.

   - Enhancements for SMP function call tracing so it is possible to
     locate the scheduling and the actual execution points. That allows
     to measure IPI delivery time precisely"

* tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  trace,smp: Add tracepoints for scheduling remotelly called functions
  trace,smp: Add tracepoints around remotelly called functions
  MAINTAINERS: Add CPU HOTPLUG entry
  x86/smpboot: Fix the parallel bringup decision
  x86/realmode: Make stack lock work in trampoline_compat()
  x86/smp: Initialize cpu_primary_thread_mask late
  cpu/hotplug: Fix off by one in cpuhp_bringup_mask()
  x86/apic: Fix use of X{,2}APIC_ENABLE in asm with older binutils
  x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it
  x86/smpboot: Support parallel startup of secondary CPUs
  x86/smpboot: Implement a bit spinlock to protect the realmode stack
  x86/apic: Save the APIC virtual base address
  cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE
  x86/apic: Provide cpu_primary_thread mask
  x86/smpboot: Enable split CPU startup
  cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism
  cpu/hotplug: Reset task stack state in _cpu_up()
  cpu/hotplug: Remove unused state functions
  riscv: Switch to hotplug core state synchronization
  parisc: Switch to hotplug core state synchronization
  ...

3 files changed, 408 insertions, 200 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index f4a2c5845bcb..88a7ede322bd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/rcupdate.h>
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <linux/kthread.h>
@@ -59,6 +60,7 @@
  * @last:	For multi-instance rollback, remember how far we got
  * @cb_state:	The state for a single callback (install/uninstall)
  * @result:	Result of the operation
+ * @ap_sync_state:	State for AP synchronization
  * @done_up:	Signal completion to the issuer of the task for cpu-up
  * @done_down:	Signal completion to the issuer of the task for cpu-down
  */
@@ -76,6 +78,7 @@ struct cpuhp_cpu_state {
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
 	int			result;
+	atomic_t		ap_sync_state;
 	struct completion	done_up;
 	struct completion	done_down;
 #endif
@@ -276,6 +279,182 @@ static bool cpuhp_is_atomic_state(enum cpuhp_state state)
 	return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
 }
 
+/* Synchronization state management */
+enum cpuhp_sync_state {
+	SYNC_STATE_DEAD,
+	SYNC_STATE_KICKED,
+	SYNC_STATE_SHOULD_DIE,
+	SYNC_STATE_ALIVE,
+	SYNC_STATE_SHOULD_ONLINE,
+	SYNC_STATE_ONLINE,
+};
+
+#ifdef CONFIG_HOTPLUG_CORE_SYNC
+/**
+ * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown
+ * @state:	The synchronization state to set
+ *
+ * No synchronization point. Just update of the synchronization state, but implies
+ * a full barrier so that the AP changes are visible before the control CPU proceeds.
+ */
+static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state)
+{
+	atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state);
+
+	(void)atomic_xchg(st, state);
+}
+
+void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); }
+
+static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state,
+				      enum cpuhp_sync_state next_state)
+{
+	atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
+	ktime_t now, end, start = ktime_get();
+	int sync;
+
+	end = start + 10ULL * NSEC_PER_SEC;
+
+	sync = atomic_read(st);
+	while (1) {
+		if (sync == state) {
+			if (!atomic_try_cmpxchg(st, &sync, next_state))
+				continue;
+			return true;
+		}
+
+		now = ktime_get();
+		if (now > end) {
+			/* Timeout. Leave the state unchanged */
+			return false;
+		} else if (now - start < NSEC_PER_MSEC) {
+			/* Poll for one millisecond */
+			arch_cpuhp_sync_state_poll();
+		} else {
+			usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE);
+		}
+		sync = atomic_read(st);
+	}
+	return true;
+}
+#else  /* CONFIG_HOTPLUG_CORE_SYNC */
+static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { }
+#endif /* !CONFIG_HOTPLUG_CORE_SYNC */
+
+#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD
+/**
+ * cpuhp_ap_report_dead - Update synchronization state to DEAD
+ *
+ * No synchronization point. Just update of the synchronization state.
+ */
+void cpuhp_ap_report_dead(void)
+{
+	cpuhp_ap_update_sync_state(SYNC_STATE_DEAD);
+}
+
+void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { }
+
+/*
+ * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down
+ * because the AP cannot issue complete() at this stage.
+ */
+static void cpuhp_bp_sync_dead(unsigned int cpu)
+{
+	atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
+	int sync = atomic_read(st);
+
+	do {
+		/* CPU can have reported dead already. Don't overwrite that! */
+		if (sync == SYNC_STATE_DEAD)
+			break;
+	} while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE));
+
+	if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) {
+		/* CPU reached dead state. Invoke the cleanup function */
+		arch_cpuhp_cleanup_dead_cpu(cpu);
+		return;
+	}
+
+	/* No further action possible. Emit message and give up. */
+	pr_err("CPU%u failed to report dead state\n", cpu);
+}
+#else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */
+static inline void cpuhp_bp_sync_dead(unsigned int cpu) { }
+#endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */
+
+#ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL
+/**
+ * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive
+ *
+ * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits
+ * for the BP to release it.
+ */
+void cpuhp_ap_sync_alive(void)
+{
+	atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state);
+
+	cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE);
+
+	/* Wait for the control CPU to release it. */
+	while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE)
+		cpu_relax();
+}
+
+static bool cpuhp_can_boot_ap(unsigned int cpu)
+{
+	atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
+	int sync = atomic_read(st);
+
+again:
+	switch (sync) {
+	case SYNC_STATE_DEAD:
+		/* CPU is properly dead */
+		break;
+	case SYNC_STATE_KICKED:
+		/* CPU did not come up in previous attempt */
+		break;
+	case SYNC_STATE_ALIVE:
+		/* CPU is stuck cpuhp_ap_sync_alive(). */
+		break;
+	default:
+		/* CPU failed to report online or dead and is in limbo state. */
+		return false;
+	}
+
+	/* Prepare for booting */
+	if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED))
+		goto again;
+
+	return true;
+}
+
+void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { }
+
+/*
+ * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up
+ * because the AP cannot issue complete() so early in the bringup.
+ */
+static int cpuhp_bp_sync_alive(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL))
+		return 0;
+
+	if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) {
+		pr_err("CPU%u failed to report alive state\n", cpu);
+		ret = -EIO;
+	}
+
+	/* Let the architecture cleanup the kick alive mechanics. */
+	arch_cpuhp_cleanup_kick_cpu(cpu);
+	return ret;
+}
+#else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */
+static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; }
+static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; }
+#endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */
+
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 bool cpuhp_tasks_frozen;
@@ -470,8 +649,23 @@ bool cpu_smt_possible(void)
 		cpu_smt_control != CPU_SMT_NOT_SUPPORTED;
 }
 EXPORT_SYMBOL_GPL(cpu_smt_possible);
+
+static inline bool cpuhp_smt_aware(void)
+{
+	return topology_smt_supported();
+}
+
+static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
+{
+	return cpu_primary_thread_mask;
+}
 #else
 static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+static inline bool cpuhp_smt_aware(void) { return false; }
+static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
+{
+	return cpu_present_mask;
+}
 #endif
 
 static inline enum cpuhp_state
@@ -558,7 +752,7 @@ static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st,
 	return ret;
 }
 
-static int bringup_wait_for_ap(unsigned int cpu)
+static int bringup_wait_for_ap_online(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 
@@ -579,38 +773,94 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	 */
 	if (!cpu_smt_allowed(cpu))
 		return -ECANCELED;
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP
+static int cpuhp_kick_ap_alive(unsigned int cpu)
+{
+	if (!cpuhp_can_boot_ap(cpu))
+		return -EAGAIN;
+
+	return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu));
+}
+
+static int cpuhp_bringup_ap(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	int ret;
+
+	/*
+	 * Some architectures have to walk the irq descriptors to
+	 * setup the vector space for the cpu which comes online.
+	 * Prevent irq alloc/free across the bringup.
+	 */
+	irq_lock_sparse();
+
+	ret = cpuhp_bp_sync_alive(cpu);
+	if (ret)
+		goto out_unlock;
+
+	ret = bringup_wait_for_ap_online(cpu);
+	if (ret)
+		goto out_unlock;
+
+	irq_unlock_sparse();
 
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 
 	return cpuhp_kick_ap(cpu, st, st->target);
-}
 
+out_unlock:
+	irq_unlock_sparse();
+	return ret;
+}
+#else
 static int bringup_cpu(unsigned int cpu)
 {
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	struct task_struct *idle = idle_thread_get(cpu);
 	int ret;
 
-	/*
-	 * Reset stale stack state from the last time this CPU was online.
-	 */
-	scs_task_reset(idle);
-	kasan_unpoison_task_stack(idle);
+	if (!cpuhp_can_boot_ap(cpu))
+		return -EAGAIN;
 
 	/*
 	 * Some architectures have to walk the irq descriptors to
 	 * setup the vector space for the cpu which comes online.
-	 * Prevent irq alloc/free across the bringup.
+	 *
+	 * Prevent irq alloc/free across the bringup by acquiring the
+	 * sparse irq lock. Hold it until the upcoming CPU completes the
+	 * startup in cpuhp_online_idle() which allows to avoid
+	 * intermediate synchronization points in the architecture code.
 	 */
 	irq_lock_sparse();
 
-	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
-	irq_unlock_sparse();
 	if (ret)
-		return ret;
-	return bringup_wait_for_ap(cpu);
+		goto out_unlock;
+
+	ret = cpuhp_bp_sync_alive(cpu);
+	if (ret)
+		goto out_unlock;
+
+	ret = bringup_wait_for_ap_online(cpu);
+	if (ret)
+		goto out_unlock;
+
+	irq_unlock_sparse();
+
+	if (st->target <= CPUHP_AP_ONLINE_IDLE)
+		return 0;
+
+	return cpuhp_kick_ap(cpu, st, st->target);
+
+out_unlock:
+	irq_unlock_sparse();
+	return ret;
 }
+#endif
 
 static int finish_cpu(unsigned int cpu)
 {
@@ -1099,6 +1349,8 @@ static int takedown_cpu(unsigned int cpu)
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
+	cpuhp_bp_sync_dead(cpu);
+
 	tick_cleanup_dead_cpu(cpu);
 	rcutree_migrate_callbacks(cpu);
 	return 0;
@@ -1345,8 +1597,10 @@ void cpuhp_online_idle(enum cpuhp_state state)
 	if (state != CPUHP_AP_ONLINE_IDLE)
 		return;
 
+	cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE);
+
 	/*
-	 * Unpart the stopper thread before we start the idle loop (and start
+	 * Unpark the stopper thread before we start the idle loop (and start
 	 * scheduling); this ensures the stopper task is always available.
 	 */
 	stop_machine_unpark(smp_processor_id());
@@ -1383,6 +1637,12 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 			ret = PTR_ERR(idle);
 			goto out;
 		}
+
+		/*
+		 * Reset stale stack state from the last time this CPU was online.
+		 */
+		scs_task_reset(idle);
+		kasan_unpoison_task_stack(idle);
 	}
 
 	cpuhp_tasks_frozen = tasks_frozen;
@@ -1502,18 +1762,96 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu)
 	return 0;
 }
 
-void bringup_nonboot_cpus(unsigned int setup_max_cpus)
+static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus,
+				      enum cpuhp_state target)
 {
 	unsigned int cpu;
 
-	for_each_present_cpu(cpu) {
-		if (num_online_cpus() >= setup_max_cpus)
+	for_each_cpu(cpu, mask) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+		if (cpu_up(cpu, target) && can_rollback_cpu(st)) {
+			/*
+			 * If this failed then cpu_up() might have only
+			 * rolled back to CPUHP_BP_KICK_AP for the final
+			 * online. Clean it up. NOOP if already rolled back.
+			 */
+			WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE));
+		}
+
+		if (!--ncpus)
 			break;
-		if (!cpu_online(cpu))
-			cpu_up(cpu, CPUHP_ONLINE);
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_PARALLEL
+static bool __cpuhp_parallel_bringup __ro_after_init = true;
+
+static int __init parallel_bringup_parse_param(char *arg)
+{
+	return kstrtobool(arg, &__cpuhp_parallel_bringup);
+}
+early_param("cpuhp.parallel", parallel_bringup_parse_param);
+
+/*
+ * On architectures which have enabled parallel bringup this invokes all BP
+ * prepare states for each of the to be onlined APs first. The last state
+ * sends the startup IPI to the APs. The APs proceed through the low level
+ * bringup code in parallel and then wait for the control CPU to release
+ * them one by one for the final onlining procedure.
+ *
+ * This avoids waiting for each AP to respond to the startup IPI in
+ * CPUHP_BRINGUP_CPU.
+ */
+static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus)
+{
+	const struct cpumask *mask = cpu_present_mask;
+
+	if (__cpuhp_parallel_bringup)
+		__cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup();
+	if (!__cpuhp_parallel_bringup)
+		return false;
+
+	if (cpuhp_smt_aware()) {
+		const struct cpumask *pmask = cpuhp_get_primary_thread_mask();
+		static struct cpumask tmp_mask __initdata;
+
+		/*
+		 * X86 requires to prevent that SMT siblings stopped while
+		 * the primary thread does a microcode update for various
+		 * reasons. Bring the primary threads up first.
+		 */
+		cpumask_and(&tmp_mask, mask, pmask);
+		cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP);
+		cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE);
+		/* Account for the online CPUs */
+		ncpus -= num_online_cpus();
+		if (!ncpus)
+			return true;
+		/* Create the mask for secondary CPUs */
+		cpumask_andnot(&tmp_mask, mask, pmask);
+		mask = &tmp_mask;
+	}
+
+	/* Bring the not-yet started CPUs up */
+	cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP);
+	cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE);
+	return true;
+}
+#else
+static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; }
+#endif /* CONFIG_HOTPLUG_PARALLEL */
+
+void __init bringup_nonboot_cpus(unsigned int setup_max_cpus)
+{
+	/* Try parallel bringup optimization if enabled */
+	if (cpuhp_bringup_cpus_parallel(setup_max_cpus))
+		return;
+
+	/* Full per CPU serialized bringup */
+	cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE);
+}
+
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
 
@@ -1740,13 +2078,38 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
-	/* Kicks the plugged cpu into life */
+
+#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP
+	/*
+	 * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until
+	 * the next step will release it.
+	 */
+	[CPUHP_BP_KICK_AP] = {
+		.name			= "cpu:kick_ap",
+		.startup.single		= cpuhp_kick_ap_alive,
+	},
+
+	/*
+	 * Waits for the AP to reach cpuhp_ap_sync_alive() and then
+	 * releases it for the complete bringup.
+	 */
+	[CPUHP_BRINGUP_CPU] = {
+		.name			= "cpu:bringup",
+		.startup.single		= cpuhp_bringup_ap,
+		.teardown.single	= finish_cpu,
+		.cant_stop		= true,
+	},
+#else
+	/*
+	 * All-in-one CPU bringup state which includes the kick alive.
+	 */
 	[CPUHP_BRINGUP_CPU] = {
 		.name			= "cpu:bringup",
 		.startup.single		= bringup_cpu,
 		.teardown.single	= finish_cpu,
 		.cant_stop		= true,
 	},
+#endif
 	/* Final state before CPU kills itself */
 	[CPUHP_AP_IDLE_DEAD] = {
 		.name			= "idle:dead",
@@ -2723,6 +3086,7 @@ void __init boot_cpu_hotplug_init(void)
 {
 #ifdef CONFIG_SMP
 	cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask);
+	atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE);
 #endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 	this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
diff --git a/kernel/smp.c b/kernel/smp.c
index ab3e5dad6cfe..385179dae360 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -27,6 +27,9 @@
 #include <linux/jump_label.h>
 
 #include <trace/events/ipi.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/csd.h>
+#undef CREATE_TRACE_POINTS
 
 #include "smpboot.h"
 #include "sched/smp.h"
@@ -121,6 +124,14 @@ send_call_function_ipi_mask(struct cpumask *mask)
 	arch_send_call_function_ipi_mask(mask);
 }
 
+static __always_inline void
+csd_do_func(smp_call_func_t func, void *info, struct __call_single_data *csd)
+{
+	trace_csd_function_entry(func, csd);
+	func(info);
+	trace_csd_function_exit(func, csd);
+}
+
 #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
 
 static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled);
@@ -329,7 +340,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
 	 * even if we haven't sent the smp_call IPI yet (e.g. the stopper
 	 * executes migration_cpu_stop() on the remote CPU).
 	 */
-	if (trace_ipi_send_cpu_enabled()) {
+	if (trace_csd_queue_cpu_enabled()) {
 		call_single_data_t *csd;
 		smp_call_func_t func;
 
@@ -337,7 +348,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
 		func = CSD_TYPE(csd) == CSD_TYPE_TTWU ?
 			sched_ttwu_pending : csd->func;
 
-		trace_ipi_send_cpu(cpu, _RET_IP_, func);
+		trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
 	}
 
 	/*
@@ -375,7 +386,7 @@ static int generic_exec_single(int cpu, struct __call_single_data *csd)
 		csd_lock_record(csd);
 		csd_unlock(csd);
 		local_irq_save(flags);
-		func(info);
+		csd_do_func(func, info, NULL);
 		csd_lock_record(NULL);
 		local_irq_restore(flags);
 		return 0;
@@ -477,7 +488,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
 			}
 
 			csd_lock_record(csd);
-			func(info);
+			csd_do_func(func, info, csd);
 			csd_unlock(csd);
 			csd_lock_record(NULL);
 		} else {
@@ -508,7 +519,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
 
 				csd_lock_record(csd);
 				csd_unlock(csd);
-				func(info);
+				csd_do_func(func, info, csd);
 				csd_lock_record(NULL);
 			} else if (type == CSD_TYPE_IRQ_WORK) {
 				irq_work_single(csd);
@@ -522,8 +533,10 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
 	/*
 	 * Third; only CSD_TYPE_TTWU is left, issue those.
 	 */
-	if (entry)
-		sched_ttwu_pending(entry);
+	if (entry) {
+		csd = llist_entry(entry, typeof(*csd), node.llist);
+		csd_do_func(sched_ttwu_pending, entry, csd);
+	}
 }
 
 
@@ -728,7 +741,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	int cpu, last_cpu, this_cpu = smp_processor_id();
 	struct call_function_data *cfd;
 	bool wait = scf_flags & SCF_WAIT;
-	int nr_cpus = 0, nr_queued = 0;
+	int nr_cpus = 0;
 	bool run_remote = false;
 	bool run_local = false;
 
@@ -786,22 +799,16 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 			csd->node.src = smp_processor_id();
 			csd->node.dst = cpu;
 #endif
+			trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
+
 			if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
 				__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 				nr_cpus++;
 				last_cpu = cpu;
 			}
-			nr_queued++;
 		}
 
 		/*
-		 * Trace each smp_function_call_*() as an IPI, actual IPIs
-		 * will be traced with func==generic_smp_call_function_single_ipi().
-		 */
-		if (nr_queued)
-			trace_ipi_send_cpumask(cfd->cpumask, _RET_IP_, func);
-
-		/*
 		 * Choose the most efficient way to send an IPI. Note that the
 		 * number of CPUs might be zero due to concurrent changes to the
 		 * provided mask.
@@ -816,7 +823,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 		unsigned long flags;
 
 		local_irq_save(flags);
-		func(info);
+		csd_do_func(func, info, NULL);
 		local_irq_restore(flags);
 	}
 
@@ -892,7 +899,7 @@ EXPORT_SYMBOL(setup_max_cpus);
  * SMP mode to <NUM>.
  */
 
-void __weak arch_disable_smp_support(void) { }
+void __weak __init arch_disable_smp_support(void) { }
 
 static int __init nosmp(char *str)
 {
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 2c7396da470c..f47d8f375946 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -325,166 +325,3 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
-
-static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
-
-/*
- * Called to poll specified CPU's state, for example, when waiting for
- * a CPU to come online.
- */
-int cpu_report_state(int cpu)
-{
-	return atomic_read(&per_cpu(cpu_hotplug_state, cpu));
-}
-
-/*
- * If CPU has died properly, set its state to CPU_UP_PREPARE and
- * return success.  Otherwise, return -EBUSY if the CPU died after
- * cpu_wait_death() timed out.  And yet otherwise again, return -EAGAIN
- * if cpu_wait_death() timed out and the CPU still hasn't gotten around
- * to dying.  In the latter two cases, the CPU might not be set up
- * properly, but it is up to the arch-specific code to decide.
- * Finally, -EIO indicates an unanticipated problem.
- *
- * Note that it is permissible to omit this call entirely, as is
- * done in architectures that do no CPU-hotplug error checking.
- */
-int cpu_check_up_prepare(int cpu)
-{
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
-		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
-		return 0;
-	}
-
-	switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) {
-
-	case CPU_POST_DEAD:
-
-		/* The CPU died properly, so just start it up again. */
-		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
-		return 0;
-
-	case CPU_DEAD_FROZEN:
-
-		/*
-		 * Timeout during CPU death, so let caller know.
-		 * The outgoing CPU completed its processing, but after
-		 * cpu_wait_death() timed out and reported the error. The
-		 * caller is free to proceed, in which case the state
-		 * will be reset properly by cpu_set_state_online().
-		 * Proceeding despite this -EBUSY return makes sense
-		 * for systems where the outgoing CPUs take themselves
-		 * offline, with no post-death manipulation required from
-		 * a surviving CPU.
-		 */
-		return -EBUSY;
-
-	case CPU_BROKEN:
-
-		/*
-		 * The most likely reason we got here is that there was
-		 * a timeout during CPU death, and the outgoing CPU never
-		 * did complete its processing.  This could happen on
-		 * a virtualized system if the outgoing VCPU gets preempted
-		 * for more than five seconds, and the user attempts to
-		 * immediately online that same CPU.  Trying again later
-		 * might return -EBUSY above, hence -EAGAIN.
-		 */
-		return -EAGAIN;
-
-	case CPU_UP_PREPARE:
-		/*
-		 * Timeout while waiting for the CPU to show up. Allow to try
-		 * again later.
-		 */
-		return 0;
-
-	default:
-
-		/* Should not happen.  Famous last words. */
-		return -EIO;
-	}
-}
-
-/*
- * Mark the specified CPU online.
- *
- * Note that it is permissible to omit this call entirely, as is
- * done in architectures that do no CPU-hotplug error checking.
- */
-void cpu_set_state_online(int cpu)
-{
-	(void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Wait for the specified CPU to exit the idle loop and die.
- */
-bool cpu_wait_death(unsigned int cpu, int seconds)
-{
-	int jf_left = seconds * HZ;
-	int oldstate;
-	bool ret = true;
-	int sleep_jf = 1;
-
-	might_sleep();
-
-	/* The outgoing CPU will normally get done quite quickly. */
-	if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD)
-		goto update_state_early;
-	udelay(5);
-
-	/* But if the outgoing CPU dawdles, wait increasingly long times. */
-	while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) {
-		schedule_timeout_uninterruptible(sleep_jf);
-		jf_left -= sleep_jf;
-		if (jf_left <= 0)
-			break;
-		sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10);
-	}
-update_state_early:
-	oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
-update_state:
-	if (oldstate == CPU_DEAD) {
-		/* Outgoing CPU died normally, update state. */
-		smp_mb(); /* atomic_read() before update. */
-		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD);
-	} else {
-		/* Outgoing CPU still hasn't died, set state accordingly. */
-		if (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
-					&oldstate, CPU_BROKEN))
-			goto update_state;
-		ret = false;
-	}
-	return ret;
-}
-
-/*
- * Called by the outgoing CPU to report its successful death.  Return
- * false if this report follows the surviving CPU's timing out.
- *
- * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU
- * timed out.  This approach allows architectures to omit calls to
- * cpu_check_up_prepare() and cpu_set_state_online() without defeating
- * the next cpu_wait_death()'s polling loop.
- */
-bool cpu_report_death(void)
-{
-	int oldstate;
-	int newstate;
-	int cpu = smp_processor_id();
-
-	oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
-	do {
-		if (oldstate != CPU_BROKEN)
-			newstate = CPU_DEAD;
-		else
-			newstate = CPU_DEAD_FROZEN;
-	} while (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
-				     &oldstate, newstate));
-	return newstate == CPU_DEAD;
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */