diff --git a/src/soc/intel/broadwell/cpu.c b/src/soc/intel/broadwell/cpu.c
index 15c003e732..2afdfadc3e 100644
--- a/src/soc/intel/broadwell/cpu.c
+++ b/src/soc/intel/broadwell/cpu.c
@@ -570,17 +570,6 @@ static void configure_mca(void)
 		wrmsr(IA32_MC0_STATUS + (i * 4), msr);
 }
 
-static void bsp_init_before_ap_bringup(struct bus *cpu_bus)
-{
-	/* Setup MTRRs based on physical address size. */
-	x86_setup_mtrrs_with_detect();
-	x86_mtrr_check();
-
-	initialize_vr_config();
-	calibrate_24mhz_bclk();
-	configure_pch_power_sharing();
-}
-
 /* All CPUs including BSP will run the following function. */
 static void cpu_core_init(device_t cpu)
 {
@@ -612,14 +601,52 @@ static void cpu_core_init(device_t cpu)
 
 /* MP initialization support. */
 static const void *microcode_patch;
-int ht_disabled;
+static int ht_disabled;
 
-static int adjust_apic_id_ht_disabled(int index, int apic_id)
+static void pre_mp_init(void)
 {
-	return 2 * index;
+	/* Setup MTRRs based on physical address size. */
+	x86_setup_mtrrs_with_detect();
+	x86_mtrr_check();
+
+	initialize_vr_config();
+	calibrate_24mhz_bclk();
+	configure_pch_power_sharing();
 }
 
-static void relocate_and_load_microcode(void)
+static int get_cpu_count(void)
+{
+	msr_t msr;
+	int num_threads;
+	int num_cores;
+
+	msr = rdmsr(CORE_THREAD_COUNT_MSR);
+	num_threads = (msr.lo >> 0) & 0xffff;
+	num_cores = (msr.lo >> 16) & 0xffff;
+	printk(BIOS_DEBUG, "CPU has %u cores, %u threads enabled.\n",
+	       num_cores, num_threads);
+
+	ht_disabled = num_threads == num_cores;
+
+	return num_threads;
+}
+
+static void get_microcode_info(const void **microcode, int *parallel)
+{
+	microcode_patch = intel_microcode_find();
+	*microcode = microcode_patch;
+	*parallel = 1;
+}
+
+static int adjust_apic_id(int index, int apic_id)
+{
+	if (ht_disabled)
+		return 2 * index;
+	else
+		return index;
+}
+
+static void per_cpu_smm_trigger(void)
 {
 	/* Relocate the SMM handler. */
 	smm_relocate();
@@ -628,8 +655,11 @@ static void relocate_and_load_microcode(void)
 	intel_microcode_load_unlocked(microcode_patch);
 }
 
-static void enable_smis(void)
+static void post_mp_init(void)
 {
+	/* Set Max Ratio */
+	set_max_ratio();
+
 	/* Now that all APs have been relocated as well as the BSP let SMIs
 	 * start flowing. */
 	southbridge_smm_enable_smi();
@@ -638,14 +668,27 @@ static void enable_smis(void)
 	smm_lock();
 }
 
-static struct mp_flight_record mp_steps[] = {
-	MP_FR_NOBLOCK_APS(relocate_and_load_microcode,
-	                  relocate_and_load_microcode),
-	MP_FR_BLOCK_APS(mp_initialize_cpu, mp_initialize_cpu),
-	/* Wait for APs to finish initialization before proceeding. */
-	MP_FR_BLOCK_APS(NULL, enable_smis),
+static const struct mp_ops mp_ops = {
+	.pre_mp_init = pre_mp_init,
+	.get_cpu_count = get_cpu_count,
+	.get_smm_info = smm_info,
+	.get_microcode_info = get_microcode_info,
+	.adjust_cpu_apic_entry = adjust_apic_id,
+	.pre_mp_smm_init = smm_initialize,
+	.per_cpu_smm_trigger = per_cpu_smm_trigger,
+	.relocation_handler = smm_relocation_handler,
+	.post_mp_init = post_mp_init,
 };
 
+void broadwell_init_cpus(device_t dev)
+{
+	struct bus *cpu_bus = dev->link_list;
+
+	if (mp_init_with_smm(cpu_bus, &mp_ops)) {
+		printk(BIOS_ERR, "MP initialization failure.\n");
+	}
+}
+
 static struct device_operations cpu_dev_ops = {
 	.init = cpu_core_init,
 };
@@ -662,55 +705,3 @@ static const struct cpu_driver driver __cpu_driver = {
 	.ops      = &cpu_dev_ops,
 	.id_table = cpu_table,
 };
-
-void broadwell_init_cpus(device_t dev)
-{
-	struct bus *cpu_bus = dev->link_list;
-	int num_threads;
-	int num_cores;
-	msr_t msr;
-	struct mp_params mp_params;
-	void *smm_save_area;
-
-	msr = rdmsr(CORE_THREAD_COUNT_MSR);
-	num_threads = (msr.lo >> 0) & 0xffff;
-	num_cores = (msr.lo >> 16) & 0xffff;
-	printk(BIOS_DEBUG, "CPU has %u cores, %u threads enabled.\n",
-	       num_cores, num_threads);
-
-	ht_disabled = num_threads == num_cores;
-
-	/* Perform any necessary BSP initialization before APs are brought up.
-	 * This call also allows the BSP to prepare for any secondary effects
-	 * from calling cpu_initialize() such as smm_init(). */
-	bsp_init_before_ap_bringup(cpu_bus);
-
-	microcode_patch = intel_microcode_find();
-
-	/* Save default SMM area before relocation occurs. */
-	smm_save_area = backup_default_smm_area();
-
-	mp_params.num_cpus = num_threads;
-	mp_params.parallel_microcode_load = 1;
-	if (ht_disabled)
-		mp_params.adjust_apic_id = adjust_apic_id_ht_disabled;
-	else
-		mp_params.adjust_apic_id = NULL;
-	mp_params.flight_plan = &mp_steps[0];
-	mp_params.num_records = ARRAY_SIZE(mp_steps);
-	mp_params.microcode_pointer = microcode_patch;
-
-	/* Load relocation and permanent handlers. Then initiate relocation. */
-	if (smm_initialize())
-		printk(BIOS_CRIT, "SMM initialization failed...\n");
-
-	if (mp_init(cpu_bus, &mp_params)) {
-		printk(BIOS_ERR, "MP initialization failure.\n");
-	}
-
-	/* Set Max Ratio */
-	set_max_ratio();
-
-	/* Restore the default SMM region. */
-	restore_default_smm_area(smm_save_area);
-}
diff --git a/src/soc/intel/broadwell/include/soc/cpu.h b/src/soc/intel/broadwell/include/soc/cpu.h
index 3610e64cfb..9a9e0f4437 100644
--- a/src/soc/intel/broadwell/include/soc/cpu.h
+++ b/src/soc/intel/broadwell/include/soc/cpu.h
@@ -55,12 +55,6 @@
 void set_power_limits(u8 power_limit_1_time);
 int cpu_config_tdp_levels(void);
 
-/*
- * Determine if HyperThreading is disabled.
- * The variable is not valid until setup_ap_init() has been called.
- */
-extern int ht_disabled;
-
 /* CPU identification */
 u32 cpu_family_model(void);
 u32 cpu_stepping(void);
diff --git a/src/soc/intel/broadwell/include/soc/smm.h b/src/soc/intel/broadwell/include/soc/smm.h
index 7f5d6b734c..a5247c48ba 100644
--- a/src/soc/intel/broadwell/include/soc/smm.h
+++ b/src/soc/intel/broadwell/include/soc/smm.h
@@ -53,7 +53,11 @@ static inline int smm_region_size(void)
         return CONFIG_SMM_TSEG_SIZE;
 }
 
-int smm_initialize(void);
+void smm_relocation_handler(int cpu, uintptr_t curr_smbase,
+				uintptr_t staggered_smbase);
+void smm_info(uintptr_t *perm_smbase, size_t *perm_smsize,
+		size_t *smm_save_state_size);
+void smm_initialize(void);
 void smm_relocate(void);
 
 /* These helpers are for performing SMM relocation. */
diff --git a/src/soc/intel/broadwell/smmrelocate.c b/src/soc/intel/broadwell/smmrelocate.c
index 18119f845d..0cc6399780 100644
--- a/src/soc/intel/broadwell/smmrelocate.c
+++ b/src/soc/intel/broadwell/smmrelocate.c
@@ -60,9 +60,9 @@ static inline void write_uncore_emrr(struct smm_relocation_params *relo_params)
 	wrmsr(UNCORE_EMRRphysMask_MSR, relo_params->uncore_emrr_mask);
 }
 
-static void update_save_state(int cpu,
-                              struct smm_relocation_params *relo_params,
-                              const struct smm_runtime *runtime)
+static void update_save_state(int cpu, uintptr_t curr_smbase,
+				uintptr_t staggered_smbase,
+				struct smm_relocation_params *relo_params)
 {
 	u32 smbase;
 	u32 iedbase;
@@ -70,7 +70,7 @@ static void update_save_state(int cpu,
 	/* The relocated handler runs with all CPUs concurrently. Therefore
 	 * stagger the entry points adjusting SMBASE downwards by save state
 	 * size * CPU num. */
-	smbase = relo_params->smram_base - cpu * runtime->save_state_size;
+	smbase = staggered_smbase;
 	iedbase = relo_params->ied_base;
 
 	printk(BIOS_DEBUG, "New SMBASE=0x%08x IEDBASE=0x%08x\n",
@@ -101,8 +101,8 @@ static void update_save_state(int cpu,
 	} else {
 		em64t101_smm_state_save_area_t *save_state;
 
-		save_state = (void *)(runtime->smbase + SMM_DEFAULT_SIZE -
-				      runtime->save_state_size);
+		save_state = (void *)(curr_smbase + SMM_DEFAULT_SIZE -
+				      sizeof(*save_state));
 
 		save_state->smbase = smbase;
 		save_state->iedbase = iedbase;
@@ -130,24 +130,11 @@ static int bsp_setup_msr_save_state(struct smm_relocation_params *relo_params)
 /* The relocation work is actually performed in SMM context, but the code
  * resides in the ramstage module. This occurs by trampolining from the default
  * SMRAM entry point to here. */
-static void asmlinkage cpu_smm_do_relocation(void *arg)
+void smm_relocation_handler(int cpu, uintptr_t curr_smbase,
+				uintptr_t staggered_smbase)
 {
 	msr_t mtrr_cap;
-	struct smm_relocation_params *relo_params;
-	const struct smm_module_params *p;
-	const struct smm_runtime *runtime;
-	int cpu;
-
-	p = arg;
-	runtime = p->runtime;
-	relo_params = p->arg;
-	cpu = p->cpu;
-
-	if (cpu >= CONFIG_MAX_CPUS) {
-		printk(BIOS_CRIT,
-		       "Invalid CPU number assigned in SMM stub: %d\n", cpu);
-		return;
-	}
+	struct smm_relocation_params *relo_params = &smm_reloc_params;
 
 	printk(BIOS_DEBUG, "In relocation handler: cpu %d\n", cpu);
 
@@ -176,7 +163,7 @@ static void asmlinkage cpu_smm_do_relocation(void *arg)
 	}
 
 	/* Make appropriate changes to the save state map. */
-	update_save_state(cpu, relo_params, runtime);
+	update_save_state(cpu, curr_smbase, staggered_smbase, relo_params);
 
 	/* Write EMRR and SMRR MSRs based on indicated support. */
 	mtrr_cap = rdmsr(MTRR_CAP_MSR);
@@ -259,49 +246,6 @@ static void fill_in_relocation_params(device_t dev,
 	params->uncore_emrr_mask.hi = (1 << (39 - 32)) - 1;
 }
 
-static void adjust_apic_id_map(struct smm_loader_params *smm_params)
-{
-	struct smm_runtime *runtime;
-	int i;
-
-	/* Adjust the APIC id map if HT is disabled. */
-	if (!ht_disabled)
-		return;
-
-	runtime = smm_params->runtime;
-
-	/* The APIC ids increment by 2 when HT is disabled. */
-	for (i = 0; i < CONFIG_MAX_CPUS; i++)
-		runtime->apic_id_to_cpu[i] = runtime->apic_id_to_cpu[i] * 2;
-}
-
-static int install_relocation_handler(int num_cpus,
-                                      struct smm_relocation_params *relo_params)
-{
-	/* The default SMM entry can happen in parallel or serially. If the
-	 * default SMM entry is done in parallel the BSP has already setup
-	 * the saving state to each CPU's MSRs. At least one save state size
-	 * is required for the initial SMM entry for the BSP to determine if
-	 * parallel SMM relocation is even feasible.  Set the stack size to
-	 * the save state size, and call into the do_relocation handler. */
-	int save_state_size = sizeof(em64t101_smm_state_save_area_t);
-	struct smm_loader_params smm_params = {
-		.per_cpu_stack_size = save_state_size,
-		.num_concurrent_stacks = num_cpus,
-		.per_cpu_save_state_size = save_state_size,
-		.num_concurrent_save_states = 1,
-		.handler = (smm_handler_t)&cpu_smm_do_relocation,
-		.handler_arg = (void *)relo_params,
-	};
-
-	if (smm_setup_relocation_handler(&smm_params))
-		return -1;
-
-	adjust_apic_id_map(&smm_params);
-
-	return 0;
-}
-
 static void setup_ied_area(struct smm_relocation_params *params)
 {
 	char *ied_base;
@@ -321,35 +265,10 @@ static void setup_ied_area(struct smm_relocation_params *params)
 	memset(ied_base + (1 << 20), 0, (32 << 10));
 }
 
-static int install_permanent_handler(int num_cpus,
-                                     struct smm_relocation_params *relo_params)
-{
-	/* There are num_cpus concurrent stacks and num_cpus concurrent save
-	 * state areas. Lastly, set the stack size to the save state size. */
-	int save_state_size = sizeof(em64t101_smm_state_save_area_t);
-	struct smm_loader_params smm_params = {
-		.per_cpu_stack_size = save_state_size,
-		.num_concurrent_stacks = num_cpus,
-		.per_cpu_save_state_size = save_state_size,
-		.num_concurrent_save_states = num_cpus,
-	};
-
-	printk(BIOS_DEBUG, "Installing SMM handler to 0x%08x\n",
-	       relo_params->smram_base);
-	if (smm_load_module((void *)relo_params->smram_base,
-	                     relo_params->smram_size, &smm_params))
-		return -1;
-
-	adjust_apic_id_map(&smm_params);
-
-	return 0;
-}
-
-static int cpu_smm_setup(void)
+void smm_info(uintptr_t *perm_smbase, size_t *perm_smsize,
+				size_t *smm_save_state_size)
 {
 	device_t dev = SA_DEV_ROOT;
-	int num_cpus;
-	msr_t msr;
 
 	printk(BIOS_DEBUG, "Setting up SMI for CPU\n");
 
@@ -357,50 +276,32 @@ static int cpu_smm_setup(void)
 
 	setup_ied_area(&smm_reloc_params);
 
-	msr = rdmsr(CORE_THREAD_COUNT_MSR);
-	num_cpus = msr.lo & 0xffff;
-	if (num_cpus > CONFIG_MAX_CPUS) {
-		printk(BIOS_CRIT,
-		       "Error: Hardware CPUs (%d) > MAX_CPUS (%d)\n",
-		       num_cpus, CONFIG_MAX_CPUS);
-	}
-
-	if (install_relocation_handler(num_cpus, &smm_reloc_params)) {
-		printk(BIOS_CRIT, "SMM Relocation handler install failed.\n");
-		return -1;
-	}
-
-	if (install_permanent_handler(num_cpus, &smm_reloc_params)) {
-		printk(BIOS_CRIT, "SMM Permanent handler install failed.\n");
-		return -1;
-	}
-
-	/* Ensure the SMM handlers hit DRAM before performing first SMI. */
-	/* TODO(adurbin): Is this really needed? */
-	wbinvd();
-
-	return 0;
+	*perm_smbase = smm_reloc_params.smram_base;
+	*perm_smsize = smm_reloc_params.smram_size;
+	*smm_save_state_size = sizeof(em64t101_smm_state_save_area_t);
 }
 
-int smm_initialize(void)
+void smm_initialize(void)
 {
-	/* Return early if CPU SMM setup failed. */
-	if (cpu_smm_setup())
-		return -1;
-
 	/* Clear the SMM state in the southbridge. */
 	southbridge_smm_clear_state();
 
-	/* Run the relocation handler. */
+	/*
+	 * Run the relocation handler for on the BSP to check and set up
+	 * parallel SMM relocation.
+	 */
 	smm_initiate_relocation();
 
 	if (smm_reloc_params.smm_save_state_in_msrs) {
 		printk(BIOS_DEBUG, "Doing parallel SMM relocation.\n");
 	}
-
-	return 0;
 }
 
+/* The default SMM entry can happen in parallel or serially. If the
+ * default SMM entry is done in parallel the BSP has already setup
+ * the saving state to each CPU's MSRs. At least one save state size
+ * is required for the initial SMM entry for the BSP to determine if
+ * parallel SMM relocation is even feasible. */
 void smm_relocate(void)
 {
 	/*