diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ccb91a255c6de81f321540f59aff94ce2f568ea0..79fb1248f0ceb7f882a623389c958190c85e29d8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -838,6 +838,12 @@
 			on every CPU online, such as boot, and resume from suspend.
 			Default: 10000
 
+	cpuhp.parallel=
+			[SMP] Enable/disable parallel bringup of secondary CPUs
+			Format: <bool>
+			Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise
+			the parameter has no effect.
+
 	crash_kexec_post_notifiers
 			Run kdump after running panic-notifiers and dumping
 			kmsg. This only for the users who doubt kdump always
diff --git a/arch/Kconfig b/arch/Kconfig
index d3015a61c14865b11e8b69856e902aae8a23d872..64d771855ecda980ca89b0d10e2816f2976920dd 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -53,6 +53,10 @@ config HOTPLUG_SPLIT_STARTUP
 	bool
 	select HOTPLUG_CORE_SYNC_FULL
 
+config HOTPLUG_PARALLEL
+	bool
+	select HOTPLUG_SPLIT_STARTUP
+
 config GENERIC_ENTRY
 	bool
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index bc2d0a1d7608898746c2c1088a7b491bcd6a63f5..a5e414cd82be08b80136b828eb20aa89bb71d1d8 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -524,6 +524,7 @@ void cpuhp_ap_sync_alive(void);
 void arch_cpuhp_sync_state_poll(void);
 void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu);
 int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle);
+bool arch_cpuhp_init_parallel_bringup(void);
 
 #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD
 void cpuhp_ap_report_dead(void);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d2487aa4e7c8b64dc557bc6b505a14077d62dcd1..005f863a3d2bf1a25ed5aa3a65769b37f9640b2f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -649,8 +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
@@ -1747,18 +1762,96 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu)
 	return 0;
 }
 
-void __init 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 (!--ncpus)
 			break;
-		if (!cpu_online(cpu))
-			cpu_up(cpu, CPUHP_ONLINE);
+
+		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));
+		}
 	}
 }
 
+#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;