1 files changed, 116 insertions, 352 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3f57ce68a3f1..fc78c2325fd2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -60,9 +60,11 @@
 #include <linux/stackprotector.h>
 #include <linux/cpuhotplug.h>
 #include <linux/mc146818rtc.h>
+#include <linux/acpi.h>
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>
+#include <asm/cpuid/api.h>
 #include <asm/desc.h>
 #include <asm/nmi.h>
 #include <asm/irq.h>
@@ -101,10 +103,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
 EXPORT_PER_CPU_SYMBOL(cpu_die_map);
 
-/* Per CPU bogomips and other parameters */
-DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
-EXPORT_PER_CPU_SYMBOL(cpu_info);
-
 /* CPUs which are the primary SMT threads */
 struct cpumask __cpu_primary_thread_mask __read_mostly;
 
@@ -125,25 +123,6 @@ struct mwait_cpu_dead {
  */
 static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead);
 
-/* Logical package management. */
-struct logical_maps {
-	u32	phys_pkg_id;
-	u32	phys_die_id;
-	u32	logical_pkg_id;
-	u32	logical_die_id;
-};
-
-/* Temporary workaround until the full topology mechanics is in place */
-static DEFINE_PER_CPU_READ_MOSTLY(struct logical_maps, logical_maps) = {
-	.phys_pkg_id	= U32_MAX,
-	.phys_die_id	= U32_MAX,
-};
-
-unsigned int __max_logical_packages __read_mostly;
-EXPORT_SYMBOL(__max_logical_packages);
-static unsigned int logical_packages __read_mostly;
-static unsigned int logical_die __read_mostly;
-
 /* Maximum number of SMT threads on any online core */
 int __read_mostly __max_smt_threads = 1;
 
@@ -211,7 +190,7 @@ static void ap_starting(void)
 	apic_ap_setup();
 
 	/* Save the processor parameters. */
-	smp_store_cpu_info(cpuid);
+	identify_secondary_cpu(cpuid);
 
 	/*
 	 * The topology information must be up to date before
@@ -236,7 +215,7 @@ static void ap_calibrate_delay(void)
 {
 	/*
 	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
-	 * smp_store_cpu_info() stored a value that is close but not as
+	 * identify_secondary_cpu() stored a value that is close but not as
 	 * accurate as the value just calculated.
 	 *
 	 * As this is invoked after the TSC synchronization check,
@@ -250,7 +229,7 @@ static void ap_calibrate_delay(void)
 /*
  * Activate a secondary processor.
  */
-static void notrace start_secondary(void *unused)
+static void notrace __noendbr start_secondary(void *unused)
 {
 	/*
 	 * Don't put *anything* except direct CPU state initialization
@@ -269,7 +248,7 @@ static void notrace start_secondary(void *unused)
 		__flush_tlb_all();
 	}
 
-	cpu_init_exception_handling();
+	cpu_init_exception_handling(false);
 
 	/*
 	 * Load the microcode before reaching the AP alive synchronization
@@ -335,126 +314,7 @@ static void notrace start_secondary(void *unused)
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
-
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- * @phys_pkg:	The physical package id to map
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg)
-			return per_cpu(logical_maps.logical_pkg_id, cpu);
-	}
-	return -1;
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
-/**
- * topology_phys_to_logical_die - Map a physical die id to logical
- * @die_id:	The physical die id to map
- * @cur_cpu:	The CPU for which the mapping is done
- *
- * Returns logical die id or -1 if not found
- */
-static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
-{
-	int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id;
-
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(logical_maps.phys_pkg_id, cpu) == proc_id &&
-		    per_cpu(logical_maps.phys_die_id, cpu) == die_id)
-			return per_cpu(logical_maps.logical_die_id, cpu);
-	}
-	return -1;
-}
-
-/**
- * topology_update_package_map - Update the physical to logical package map
- * @pkg:	The physical package id as retrieved via CPUID
- * @cpu:	The cpu for which this is updated
- */
-int topology_update_package_map(unsigned int pkg, unsigned int cpu)
-{
-	int new;
-
-	/* Already available somewhere? */
-	new = topology_phys_to_logical_pkg(pkg);
-	if (new >= 0)
-		goto found;
-
-	new = logical_packages++;
-	if (new != pkg) {
-		pr_info("CPU %u Converting physical %u to logical package %u\n",
-			cpu, pkg, new);
-	}
-found:
-	per_cpu(logical_maps.phys_pkg_id, cpu) = pkg;
-	per_cpu(logical_maps.logical_pkg_id, cpu) = new;
-	cpu_data(cpu).topo.logical_pkg_id = new;
-	return 0;
-}
-/**
- * topology_update_die_map - Update the physical to logical die map
- * @die:	The die id as retrieved via CPUID
- * @cpu:	The cpu for which this is updated
- */
-int topology_update_die_map(unsigned int die, unsigned int cpu)
-{
-	int new;
-
-	/* Already available somewhere? */
-	new = topology_phys_to_logical_die(die, cpu);
-	if (new >= 0)
-		goto found;
-
-	new = logical_die++;
-	if (new != die) {
-		pr_info("CPU %u Converting physical %u to logical die %u\n",
-			cpu, die, new);
-	}
-found:
-	per_cpu(logical_maps.phys_die_id, cpu) = die;
-	per_cpu(logical_maps.logical_die_id, cpu) = new;
-	cpu_data(cpu).topo.logical_die_id = new;
-	return 0;
-}
-
-static void __init smp_store_boot_cpu_info(void)
-{
-	int id = 0; /* CPU 0 */
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	*c = boot_cpu_data;
-	c->cpu_index = id;
-	topology_update_package_map(c->topo.pkg_id, id);
-	topology_update_die_map(c->topo.die_id, id);
-	c->initialized = true;
-}
-
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	/* Copy boot_cpu_data only on the first bringup */
-	if (!c->initialized)
-		*c = boot_cpu_data;
-	c->cpu_index = id;
-	/*
-	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up an AP.
-	 */
-	identify_secondary_cpu(c);
-	c->initialized = true;
-}
+ANNOTATE_NOENDBR_SYM(start_secondary);
 
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -488,6 +348,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 		if (c->topo.pkg_id == o->topo.pkg_id &&
 		    c->topo.die_id == o->topo.die_id &&
+		    c->topo.amd_node_id == o->topo.amd_node_id &&
 		    per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) {
 			if (c->topo.core_id == o->topo.core_id)
 				return topology_sane(c, o, "smt");
@@ -509,10 +370,13 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (c->topo.pkg_id == o->topo.pkg_id &&
-	    c->topo.die_id == o->topo.die_id)
-		return true;
-	return false;
+	if (c->topo.pkg_id != o->topo.pkg_id || c->topo.die_id != o->topo.die_id)
+		return false;
+
+	if (cpu_feature_enabled(X86_FEATURE_TOPOEXT) && topology_amd_nodes_per_pkg() > 1)
+		return c->topo.amd_node_id == o->topo.amd_node_id;
+
+	return true;
 }
 
 static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -557,9 +421,9 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  */
 
 static const struct x86_cpu_id intel_cod_cpu[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0),	/* COD */
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0),	/* COD */
-	X86_MATCH_INTEL_FAM6_MODEL(ANY, 1),		/* SNC */
+	X86_MATCH_VFM(INTEL_HASWELL_X,	 0),	/* COD */
+	X86_MATCH_VFM(INTEL_BROADWELL_X, 0),	/* COD */
+	X86_MATCH_VFM(INTEL_ANY,	 1),	/* SNC */
 	{}
 };
 
@@ -600,12 +464,6 @@ static int x86_core_flags(void)
 	return cpu_core_flags() | x86_sched_itmt_flags();
 }
 #endif
-#ifdef CONFIG_SCHED_SMT
-static int x86_smt_flags(void)
-{
-	return cpu_smt_flags();
-}
-#endif
 #ifdef CONFIG_SCHED_CLUSTER
 static int x86_cluster_flags(void)
 {
@@ -613,14 +471,6 @@ static int x86_cluster_flags(void)
 }
 #endif
 
-static int x86_die_flags(void)
-{
-	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-	       return x86_sched_itmt_flags();
-
-	return 0;
-}
-
 /*
  * Set if a package/die has multiple NUMA nodes inside.
  * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
@@ -636,7 +486,7 @@ static void __init build_sched_topology(void)
 
 #ifdef CONFIG_SCHED_SMT
 	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT)
+		cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT)
 	};
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
@@ -656,7 +506,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG)
+			cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG)
 		};
 	}
 
@@ -670,8 +520,8 @@ static void __init build_sched_topology(void)
 
 void set_cpu_sibling_map(int cpu)
 {
-	bool has_smt = smp_num_siblings > 1;
-	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
+	bool has_smt = __max_threads_per_core > 1;
+	bool has_mp = has_smt || topology_num_cores_per_package() > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
 	int i, threads;
@@ -785,10 +635,9 @@ static void impress_friends(void)
  * But that slows boot and resume on modern processors, which include
  * many cores and don't require that delay.
  *
- * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
- * Modern processor families are quirked to remove the delay entirely.
+ * Cmdline "cpu_init_udelay=" is available to override this delay.
  */
-#define UDELAY_10MS_DEFAULT 10000
+#define UDELAY_10MS_LEGACY 10000
 
 static unsigned int init_udelay = UINT_MAX;
 
@@ -800,21 +649,21 @@ static int __init cpu_init_udelay(char *str)
 }
 early_param("cpu_init_udelay", cpu_init_udelay);
 
-static void __init smp_quirk_init_udelay(void)
+static void __init smp_set_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
 	if (init_udelay != UINT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
-	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON && boot_cpu_data.x86 >= 0x18) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD   && boot_cpu_data.x86 >= 0xF)) {
 		init_udelay = 0;
 		return;
 	}
 	/* else, use legacy delay */
-	init_udelay = UDELAY_10MS_DEFAULT;
+	init_udelay = UDELAY_10MS_LEGACY;
 }
 
 /*
@@ -846,7 +695,7 @@ static void send_init_sequence(u32 phys_apicid)
 /*
  * Wake up AP by INIT, INIT, STARTUP sequence.
  */
-static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu)
 {
 	unsigned long send_status = 0, accept_status = 0;
 	int num_starts, j, maxlvt;
@@ -972,7 +821,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(pcpu_hot.current_task, cpu) = idle;
+	per_cpu(current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
@@ -982,7 +831,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
+	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #endif
 	return 0;
 }
@@ -993,7 +842,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
  * Returns zero if startup was successfully sent, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle)
 {
 	unsigned long start_ip = real_mode_header->trampoline_start;
 	int ret;
@@ -1047,11 +896,11 @@ static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
 	 * - Use an INIT boot APIC message
 	 */
 	if (apic->wakeup_secondary_cpu_64)
-		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu);
 	else if (apic->wakeup_secondary_cpu)
-		ret = apic->wakeup_secondary_cpu(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu);
 	else
-		ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
+		ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu);
 
 	/* If the wakeup mechanism failed, cleanup the warm reset vector */
 	if (ret)
@@ -1068,9 +917,13 @@ int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 
 	pr_debug("++++++++++++++++++++=_---CPU UP  %u\n", cpu);
 
-	if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) ||
-	    !apic_id_valid(apicid)) {
-		pr_err("%s: bad cpu %d\n", __func__, cpu);
+	if (apicid == BAD_APICID || !apic_id_valid(apicid)) {
+		pr_err("CPU %u has invalid APIC ID %x. Aborting bringup\n", cpu, apicid);
+		return -EINVAL;
+	}
+
+	if (!test_bit(apicid, phys_cpu_present_map)) {
+		pr_err("CPU %u APIC ID %x is not present. Aborting bringup\n", cpu, apicid);
 		return -EINVAL;
 	}
 
@@ -1139,54 +992,41 @@ static __init void disable_smp(void)
 	pr_info("SMP disabled\n");
 
 	disable_ioapic_support();
+	topology_reset_possible_cpus_up();
 
-	init_cpu_present(cpumask_of(0));
-	init_cpu_possible(cpumask_of(0));
-
-	if (smp_found_config)
-		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
-	else
-		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
 	cpumask_set_cpu(0, topology_die_cpumask(0));
 }
 
-static void __init smp_cpu_index_default(void)
-{
-	int i;
-	struct cpuinfo_x86 *c;
-
-	for_each_possible_cpu(i) {
-		c = &cpu_data(i);
-		/* mark all to hotplug */
-		c->cpu_index = nr_cpu_ids;
-	}
-}
-
 void __init smp_prepare_cpus_common(void)
 {
-	unsigned int i;
+	unsigned int cpu, node;
 
-	smp_cpu_index_default();
+	/* Mark all except the boot CPU as hotpluggable */
+	for_each_possible_cpu(cpu) {
+		if (cpu)
+			per_cpu(cpu_info.cpu_index, cpu) = nr_cpu_ids;
+	}
 
-	/*
-	 * Setup boot CPU information
-	 */
-	smp_store_boot_cpu_info(); /* Final full version of the data */
-	mb();
+	for_each_possible_cpu(cpu) {
+		node = cpu_to_node(cpu);
 
-	for_each_possible_cpu(i) {
-		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
+		zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map,    cpu), GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&per_cpu(cpu_core_map,       cpu), GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&per_cpu(cpu_die_map,        cpu), GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&per_cpu(cpu_llc_shared_map, cpu), GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&per_cpu(cpu_l2c_shared_map, cpu), GFP_KERNEL, node);
 	}
 
 	set_cpu_sibling_map(0);
 }
 
+void __init smp_prepare_boot_cpu(void)
+{
+	smp_ops.smp_prepare_boot_cpu();
+}
+
 #ifdef CONFIG_X86_64
 /* Establish whether parallel bringup can be supported. */
 bool __init arch_cpuhp_init_parallel_bringup(void)
@@ -1234,7 +1074,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	uv_system_init();
 
-	smp_quirk_init_udelay();
+	smp_set_init_udelay();
 
 	speculative_store_bypass_ht_init();
 
@@ -1265,102 +1105,16 @@ void __init native_smp_prepare_boot_cpu(void)
 	native_pv_lock_init();
 }
 
-void __init calculate_max_logical_packages(void)
-{
-	int ncpus;
-
-	/*
-	 * Today neither Intel nor AMD support heterogeneous systems so
-	 * extrapolate the boot cpu's data to all packages.
-	 */
-	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
-	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-	pr_info("Max logical packages: %u\n", __max_logical_packages);
-}
-
 void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done\n");
 
-	calculate_max_logical_packages();
 	build_sched_topology();
 	nmi_selftest();
 	impress_friends();
 	cache_aps_init();
 }
 
-static int __initdata setup_possible_cpus = -1;
-static int __init _setup_possible_cpus(char *str)
-{
-	get_option(&str, &setup_possible_cpus);
-	return 0;
-}
-early_param("possible_cpus", _setup_possible_cpus);
-
-
-/*
- * cpu_possible_mask should be static, it cannot change as cpu's
- * are onlined, or offlined. The reason is per-cpu data-structures
- * are allocated by some modules at init time, and don't expect to
- * do this dynamically on cpu arrival/departure.
- * cpu_present_mask on the other hand can change dynamically.
- * In case when cpu_hotplug is not compiled, then we resort to current
- * behaviour, which is cpu_possible == cpu_present.
- * - Ashok Raj
- *
- * Three ways to find out the number of additional hotplug CPUs:
- * - If the BIOS specified disabled CPUs in ACPI/mptables use that.
- * - The user can overwrite it with possible_cpus=NUM
- * - Otherwise don't reserve additional CPUs.
- * We do this because additional CPUs waste a lot of memory.
- * -AK
- */
-__init void prefill_possible_map(void)
-{
-	int i, possible;
-
-	i = setup_max_cpus ?: 1;
-	if (setup_possible_cpus == -1) {
-		possible = num_processors;
-#ifdef CONFIG_HOTPLUG_CPU
-		if (setup_max_cpus)
-			possible += disabled_cpus;
-#else
-		if (possible > i)
-			possible = i;
-#endif
-	} else
-		possible = setup_possible_cpus;
-
-	total_cpus = max_t(int, possible, num_processors + disabled_cpus);
-
-	/* nr_cpu_ids could be reduced via nr_cpus= */
-	if (possible > nr_cpu_ids) {
-		pr_warn("%d Processors exceeds NR_CPUS limit of %u\n",
-			possible, nr_cpu_ids);
-		possible = nr_cpu_ids;
-	}
-
-#ifdef CONFIG_HOTPLUG_CPU
-	if (!setup_max_cpus)
-#endif
-	if (possible > i) {
-		pr_warn("%d Processors exceeds max_cpus limit of %u\n",
-			possible, setup_max_cpus);
-		possible = i;
-	}
-
-	set_nr_cpu_ids(possible);
-
-	pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
-		possible, max_t(int, possible - num_processors, 0));
-
-	reset_cpu_possible_mask();
-
-	for (i = 0; i < possible; i++)
-		set_cpu_possible(i, true);
-}
-
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
@@ -1434,6 +1188,12 @@ void cpu_disable_common(void)
 
 	remove_siblinginfo(cpu);
 
+	/*
+	 * Stop allowing kernel-mode FPU. This is needed so that if the CPU is
+	 * brought online again, the initial state is not allowed:
+	 */
+	this_cpu_write(kernel_fpu_allowed, false);
+
 	/* It's now safe to remove this processor from the online map */
 	lock_vector_lock();
 	remove_cpu_from_maps(cpu);
@@ -1484,49 +1244,9 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
-		return;
-
-	eax = CPUID_MWAIT_LEAF;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1547,7 +1267,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1570,6 +1290,50 @@ static inline void mwait_play_dead(void)
 }
 
 /*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead_cpuid_hint(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int highest_cstate = 0;
+	unsigned int highest_subcstate = 0;
+	int i;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		return;
+	if (!this_cpu_has(X86_FEATURE_MWAIT))
+		return;
+	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
+		return;
+
+	eax = CPUID_LEAF_MWAIT;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	/*
+	 * eax will be 0 if EDX enumeration is not valid.
+	 * Initialized below to cstate, sub_cstate value when EDX is valid.
+	 */
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+		eax = 0;
+	} else {
+		edx >>= MWAIT_SUBSTATE_SIZE;
+		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+			if (edx & MWAIT_SUBSTATE_MASK) {
+				highest_cstate = i;
+				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+			}
+		}
+		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+			(highest_subcstate - 1);
+	}
+
+	mwait_play_dead(eax);
+}
+
+/*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
  */
@@ -1619,7 +1383,7 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
+	mwait_play_dead_cpuid_hint();
 	if (cpuidle_play_dead())
 		hlt_play_dead();
 }