Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

1 files changed, 214 insertions, 168 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 687376ab07e8..7b1093397319 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -52,6 +52,7 @@
 #include <asm/desc.h>
 #include <asm/nmi.h>
 #include <asm/irq.h>
+#include <asm/idle.h>
 #include <asm/smp.h>
 #include <asm/trampoline.h>
 #include <asm/cpu.h>
@@ -88,7 +89,7 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
 #else
-struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
 #define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
 #endif
@@ -123,13 +124,12 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 
 static atomic_t init_deasserted;
 
-static int boot_cpu_logical_apicid;
 
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
 /* Set if we find a B stepping CPU */
-int __cpuinitdata smp_b_stepping;
+static int __cpuinitdata smp_b_stepping;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
 
@@ -165,6 +165,8 @@ static void unmap_cpu_to_node(int cpu)
 #endif
 
 #ifdef CONFIG_X86_32
+static int boot_cpu_logical_apicid;
+
 u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
 					{ [0 ... NR_CPUS-1] = BAD_APICID };
 
@@ -210,13 +212,13 @@ static void __cpuinit smp_callin(void)
 	/*
 	 * (This works even if the APIC is not enabled.)
 	 */
-	phys_id = GET_APIC_ID(read_apic_id());
+	phys_id = read_apic_id();
 	cpuid = smp_processor_id();
 	if (cpu_isset(cpuid, cpu_callin_map)) {
 		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
 					phys_id, cpuid);
 	}
-	Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
+	pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
 
 	/*
 	 * STARTUP IPIs are fragile beasts as they might sometimes
@@ -251,12 +253,13 @@ static void __cpuinit smp_callin(void)
 	 * boards)
 	 */
 
-	Dprintk("CALLIN, before setup_local_APIC().\n");
+	pr_debug("CALLIN, before setup_local_APIC().\n");
 	smp_callin_clear_local_apic();
 	setup_local_APIC();
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
+	notify_cpu_starting(cpuid);
 	/*
 	 * Get our bogomips.
 	 *
@@ -266,7 +269,7 @@ static void __cpuinit smp_callin(void)
 	local_irq_enable();
 	calibrate_delay();
 	local_irq_disable();
-	Dprintk("Stack at about %p\n", &cpuid);
+	pr_debug("Stack at about %p\n", &cpuid);
 
 	/*
 	 * Save our processor parameters
@@ -279,6 +282,8 @@ static void __cpuinit smp_callin(void)
 	cpu_set(cpuid, cpu_callin_map);
 }
 
+static int __cpuinitdata unsafe_smp;
+
 /*
  * Activate a secondary processor.
  */
@@ -326,15 +331,22 @@ static void __cpuinit start_secondary(void *unused)
 	 * for which cpus receive the IPI. Holding this
 	 * lock helps us to not include this cpu in a currently in progress
 	 * smp_call_function().
+	 *
+	 * We need to hold vector_lock so there the set of online cpus
+	 * does not change while we are assigning vectors to cpus.  Holding
+	 * this lock ensures we don't half assign or remove an irq from a cpu.
 	 */
-	ipi_call_lock_irq();
-#ifdef CONFIG_X86_IO_APIC
-	setup_vector_irq(smp_processor_id());
-#endif
+	ipi_call_lock();
+	lock_vector_lock();
+	__setup_vector_irq(smp_processor_id());
 	cpu_set(smp_processor_id(), cpu_online_map);
-	ipi_call_unlock_irq();
+	unlock_vector_lock();
+	ipi_call_unlock();
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 
+	/* enable local interrupts */
+	local_irq_enable();
+
 	setup_secondary_clock();
 
 	wmb();
@@ -387,7 +399,7 @@ static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c)
 				goto valid_k7;
 
 		/* If we get here, not a certified SMP capable AMD system. */
-		add_taint(TAINT_UNSAFE_SMP);
+		unsafe_smp = 1;
 	}
 
 valid_k7:
@@ -404,12 +416,10 @@ static void __cpuinit smp_checks(void)
 	 * Don't taint if we are running SMP kernel on a single non-MP
 	 * approved Athlon
 	 */
-	if (tainted & TAINT_UNSAFE_SMP) {
-		if (num_online_cpus())
-			printk(KERN_INFO "WARNING: This combination of AMD"
-				"processors is not suitable for SMP.\n");
-		else
-			tainted &= ~TAINT_UNSAFE_SMP;
+	if (unsafe_smp && num_online_cpus() > 1) {
+		printk(KERN_INFO "WARNING: This combination of AMD"
+			"processors is not suitable for SMP.\n");
+		add_taint(TAINT_UNSAFE_SMP);
 	}
 }
 
@@ -438,7 +448,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	cpu_set(cpu, cpu_sibling_setup_map);
 
 	if (smp_num_siblings > 1) {
-		for_each_cpu_mask(i, cpu_sibling_setup_map) {
+		for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
 			if (c->phys_proc_id == cpu_data(i).phys_proc_id &&
 			    c->cpu_core_id == cpu_data(i).cpu_core_id) {
 				cpu_set(i, per_cpu(cpu_sibling_map, cpu));
@@ -461,7 +471,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		return;
 	}
 
-	for_each_cpu_mask(i, cpu_sibling_setup_map) {
+	for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
 			cpu_set(i, c->llc_shared_map);
@@ -513,7 +523,7 @@ static void impress_friends(void)
 	/*
 	 * Allow the user to impress friends.
 	 */
-	Dprintk("Before bogomips.\n");
+	pr_debug("Before bogomips.\n");
 	for_each_possible_cpu(cpu)
 		if (cpu_isset(cpu, cpu_callout_map))
 			bogosum += cpu_data(cpu).loops_per_jiffy;
@@ -523,7 +533,7 @@ static void impress_friends(void)
 		bogosum/(500000/HZ),
 		(bogosum/(5000/HZ))%100);
 
-	Dprintk("Before bogocount - setting activated=1.\n");
+	pr_debug("Before bogocount - setting activated=1.\n");
 }
 
 static inline void __inquire_remote_apic(int apicid)
@@ -533,10 +543,10 @@ static inline void __inquire_remote_apic(int apicid)
 	int timeout;
 	u32 status;
 
-	printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid);
+	printk(KERN_INFO "Inquiring remote APIC 0x%x...\n", apicid);
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
-		printk(KERN_INFO "... APIC #%d %s: ", apicid, names[i]);
+		printk(KERN_INFO "... APIC 0x%x %s: ", apicid, names[i]);
 
 		/*
 		 * Wait for idle.
@@ -546,8 +556,7 @@ static inline void __inquire_remote_apic(int apicid)
 			printk(KERN_CONT
 			       "a previous APIC delivery may have failed\n");
 
-		apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
-		apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]);
+		apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
 
 		timeout = 0;
 		do {
@@ -579,29 +588,24 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 	int maxlvt;
 
 	/* Target chip */
-	apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
-
 	/* Boot on the stack */
 	/* Kick the second */
-	apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+	apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
 
-	Dprintk("Waiting for send to finish...\n");
+	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
 
 	/*
 	 * Give the other CPU some time to accept the IPI.
 	 */
 	udelay(200);
-	/*
-	 * Due to the Pentium erratum 3AP.
-	 */
-	maxlvt = lapic_get_maxlvt();
-	if (maxlvt > 3) {
-		apic_read_around(APIC_SPIV);
-		apic_write(APIC_ESR, 0);
+	if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+		maxlvt = lapic_get_maxlvt();
+		if (maxlvt > 3)			/* Due to the Pentium erratum 3AP.  */
+			apic_write(APIC_ESR, 0);
+		accept_status = (apic_read(APIC_ESR) & 0xEF);
 	}
-	accept_status = (apic_read(APIC_ESR) & 0xEF);
-	Dprintk("NMI sent.\n");
+	pr_debug("NMI sent.\n");
 
 	if (send_status)
 		printk(KERN_ERR "APIC never delivered???\n");
@@ -625,42 +629,40 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 		return send_status;
 	}
 
+	maxlvt = lapic_get_maxlvt();
+
 	/*
 	 * Be paranoid about clearing APIC errors.
 	 */
 	if (APIC_INTEGRATED(apic_version[phys_apicid])) {
-		apic_read_around(APIC_SPIV);
-		apic_write(APIC_ESR, 0);
+		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
+			apic_write(APIC_ESR, 0);
 		apic_read(APIC_ESR);
 	}
 
-	Dprintk("Asserting INIT.\n");
+	pr_debug("Asserting INIT.\n");
 
 	/*
 	 * Turn INIT on target chip
 	 */
-	apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 	/*
 	 * Send IPI
 	 */
-	apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT
-				| APIC_DM_INIT);
+	apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+		       phys_apicid);
 
-	Dprintk("Waiting for send to finish...\n");
+	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
 
 	mdelay(10);
 
-	Dprintk("Deasserting INIT.\n");
+	pr_debug("Deasserting INIT.\n");
 
 	/* Target chip */
-	apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 	/* Send IPI */
-	apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+	apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
 
-	Dprintk("Waiting for send to finish...\n");
+	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
 
 	mb();
@@ -687,55 +689,46 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 	/*
 	 * Run STARTUP IPI loop.
 	 */
-	Dprintk("#startup loops: %d.\n", num_starts);
-
-	maxlvt = lapic_get_maxlvt();
+	pr_debug("#startup loops: %d.\n", num_starts);
 
 	for (j = 1; j <= num_starts; j++) {
-		Dprintk("Sending STARTUP #%d.\n", j);
-		apic_read_around(APIC_SPIV);
-		apic_write(APIC_ESR, 0);
+		pr_debug("Sending STARTUP #%d.\n", j);
+		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
+			apic_write(APIC_ESR, 0);
 		apic_read(APIC_ESR);
-		Dprintk("After apic_write.\n");
+		pr_debug("After apic_write.\n");
 
 		/*
 		 * STARTUP IPI
 		 */
 
 		/* Target chip */
-		apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
 		/* Boot on the stack */
 		/* Kick the second */
-		apic_write_around(APIC_ICR, APIC_DM_STARTUP
-					| (start_eip >> 12));
+		apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+			       phys_apicid);
 
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
 		udelay(300);
 
-		Dprintk("Startup point 1.\n");
+		pr_debug("Startup point 1.\n");
 
-		Dprintk("Waiting for send to finish...\n");
+		pr_debug("Waiting for send to finish...\n");
 		send_status = safe_apic_wait_icr_idle();
 
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
 		udelay(200);
-		/*
-		 * Due to the Pentium erratum 3AP.
-		 */
-		if (maxlvt > 3) {
-			apic_read_around(APIC_SPIV);
+		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
-		}
 		accept_status = (apic_read(APIC_ESR) & 0xEF);
 		if (send_status || accept_status)
 			break;
 	}
-	Dprintk("After Startup.\n");
+	pr_debug("After Startup.\n");
 
 	if (send_status)
 		printk(KERN_ERR "APIC never delivered???\n");
@@ -763,12 +756,20 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
 }
 
 #ifdef CONFIG_X86_64
+
+/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */
+static void __ref free_bootmem_pda(struct x8664_pda *oldpda)
+{
+	if (!after_bootmem)
+		free_bootmem((unsigned long)oldpda, sizeof(*oldpda));
+}
+
 /*
  * Allocate node local memory for the AP pda.
  *
  * Must be called after the _cpu_pda pointer table is initialized.
  */
-static int __cpuinit get_local_pda(int cpu)
+int __cpuinit get_local_pda(int cpu)
 {
 	struct x8664_pda *oldpda, *newpda;
 	unsigned long size = sizeof(struct x8664_pda);
@@ -791,8 +792,7 @@ static int __cpuinit get_local_pda(int cpu)
 
 	if (oldpda) {
 		memcpy(newpda, oldpda, size);
-		if (!after_bootmem)
-			free_bootmem((unsigned long)oldpda, size);
+		free_bootmem_pda(oldpda);
 	}
 
 	newpda->in_bootmem = 0;
@@ -874,7 +874,7 @@ do_rest:
 	start_ip = setup_trampoline();
 
 	/* So we see what's up   */
-	printk(KERN_INFO "Booting processor %d/%d ip %lx\n",
+	printk(KERN_INFO "Booting processor %d APIC 0x%x ip 0x%lx\n",
 			  cpu, apicid, start_ip);
 
 	/*
@@ -886,16 +886,18 @@ do_rest:
 
 	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
 
-		Dprintk("Setting warm reset code and vector.\n");
+		pr_debug("Setting warm reset code and vector.\n");
 
 		store_NMI_vector(&nmi_high, &nmi_low);
 
 		smpboot_setup_warm_reset_vector(start_ip);
 		/*
 		 * Be paranoid about clearing APIC errors.
-	 	*/
-		apic_write(APIC_ESR, 0);
-		apic_read(APIC_ESR);
+		*/
+		if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+			apic_write(APIC_ESR, 0);
+			apic_read(APIC_ESR);
+		}
 	}
 
 	/*
@@ -907,9 +909,9 @@ do_rest:
 		/*
 		 * allow APs to start initializing.
 		 */
-		Dprintk("Before Callout %d.\n", cpu);
+		pr_debug("Before Callout %d.\n", cpu);
 		cpu_set(cpu, cpu_callout_map);
-		Dprintk("After Callout %d.\n", cpu);
+		pr_debug("After Callout %d.\n", cpu);
 
 		/*
 		 * Wait 5s total for a response
@@ -922,10 +924,10 @@ do_rest:
 
 		if (cpu_isset(cpu, cpu_callin_map)) {
 			/* number CPUs logically, starting from 1 (BSP is 0) */
-			Dprintk("OK.\n");
+			pr_debug("OK.\n");
 			printk(KERN_INFO "CPU%d: ", cpu);
 			print_cpu_info(&cpu_data(cpu));
-			Dprintk("CPU has booted.\n");
+			pr_debug("CPU has booted.\n");
 		} else {
 			boot_error = 1;
 			if (*((volatile unsigned char *)trampoline_base)
@@ -970,7 +972,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 
 	WARN_ON(irqs_disabled());
 
-	Dprintk("++++++++++++++++++++=_---CPU UP  %u\n", cpu);
+	pr_debug("++++++++++++++++++++=_---CPU UP  %u\n", cpu);
 
 	if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid ||
 	    !physid_isset(apicid, phys_cpu_present_map)) {
@@ -982,7 +984,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 	 * Already booted CPU?
 	 */
 	if (cpu_isset(cpu, cpu_callin_map)) {
-		Dprintk("do_boot_cpu %d Already started\n", cpu);
+		pr_debug("do_boot_cpu %d Already started\n", cpu);
 		return -ENOSYS;
 	}
 
@@ -1009,7 +1011,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 	err = do_boot_cpu(apicid, cpu);
 #endif
 	if (err) {
-		Dprintk("do_boot_cpu failed %d\n", err);
+		pr_debug("do_boot_cpu failed %d\n", err);
 		return -EIO;
 	}
 
@@ -1055,6 +1057,34 @@ static __init void disable_smp(void)
 static int __init smp_sanity_check(unsigned max_cpus)
 {
 	preempt_disable();
+
+#if defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
+	if (def_to_bigsmp && nr_cpu_ids > 8) {
+		unsigned int cpu;
+		unsigned nr;
+
+		printk(KERN_WARNING
+		       "More than 8 CPUs detected - skipping them.\n"
+		       "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n");
+
+		nr = 0;
+		for_each_present_cpu(cpu) {
+			if (nr >= 8)
+				cpu_clear(cpu, cpu_present_map);
+			nr++;
+		}
+
+		nr = 0;
+		for_each_possible_cpu(cpu) {
+			if (nr >= 8)
+				cpu_clear(cpu, cpu_possible_map);
+			nr++;
+		}
+
+		nr_cpu_ids = 8;
+	}
+#endif
+
 	if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
 		printk(KERN_WARNING "weird, boot CPU (#%d) not listed"
 				    "by the BIOS.\n", hard_smp_processor_id());
@@ -1147,10 +1177,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	 * Setup boot CPU information
 	 */
 	smp_store_cpu_info(0); /* Final full version of the data */
+#ifdef CONFIG_X86_32
 	boot_cpu_logical_apicid = logical_smp_processor_id();
+#endif
 	current_thread_info()->cpu = 0;  /* needed? */
 	set_cpu_sibling_map(0);
 
+#ifdef CONFIG_X86_64
+	enable_IR_x2apic();
+	setup_apic_routing();
+#endif
+
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
 		disable_smp();
@@ -1158,9 +1195,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 	preempt_disable();
-	if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
-		     GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+		     read_apic_id(), boot_cpu_physical_apicid);
 		/* Or can we switch back to PIC here? */
 	}
 	preempt_enable();
@@ -1193,6 +1230,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	printk(KERN_INFO "CPU%d: ", 0);
 	print_cpu_info(&cpu_data(0));
 	setup_boot_clock();
+
+	if (is_uv_system())
+		uv_system_init();
 out:
 	preempt_enable();
 }
@@ -1213,7 +1253,7 @@ void __init native_smp_prepare_boot_cpu(void)
 
 void __init native_smp_cpus_done(unsigned int max_cpus)
 {
-	Dprintk("Boot done.\n");
+	pr_debug("Boot done.\n");
 
 	impress_friends();
 	smp_checks();
@@ -1223,39 +1263,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	check_nmi_watchdog();
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void remove_siblinginfo(int cpu)
-{
-	int sibling;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-
-	for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
-		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
-		/*/
-		 * last thread sibling in this cpu core going down
-		 */
-		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
-			cpu_data(sibling).booted_cores--;
-	}
-
-	for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
-		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
-	cpus_clear(per_cpu(cpu_sibling_map, cpu));
-	cpus_clear(per_cpu(cpu_core_map, cpu));
-	c->phys_proc_id = 0;
-	c->cpu_core_id = 0;
-	cpu_clear(cpu, cpu_sibling_setup_map);
-}
-
-static int additional_cpus __initdata = -1;
-
-static __init int setup_additional_cpus(char *s)
-{
-	return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL;
-}
-early_param("additional_cpus", setup_additional_cpus);
-
 /*
  * cpu_possible_map should be static, it cannot change as cpu's
  * are onlined, or offlined. The reason is per-cpu data-structures
@@ -1275,24 +1282,13 @@ early_param("additional_cpus", setup_additional_cpus);
  */
 __init void prefill_possible_map(void)
 {
-	int i;
-	int possible;
+	int i, possible;
 
 	/* no processor from mptable or madt */
 	if (!num_processors)
 		num_processors = 1;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	if (additional_cpus == -1) {
-		if (disabled_cpus > 0)
-			additional_cpus = disabled_cpus;
-		else
-			additional_cpus = 0;
-	}
-#else
-	additional_cpus = 0;
-#endif
-	possible = num_processors + additional_cpus;
+	possible = num_processors + disabled_cpus;
 	if (possible > NR_CPUS)
 		possible = NR_CPUS;
 
@@ -1305,17 +1301,64 @@ __init void prefill_possible_map(void)
 	nr_cpu_ids = possible;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void remove_siblinginfo(int cpu)
+{
+	int sibling;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) {
+		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
+		/*/
+		 * last thread sibling in this cpu core going down
+		 */
+		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
+			cpu_data(sibling).booted_cores--;
+	}
+
+	for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu))
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
+	cpus_clear(per_cpu(cpu_sibling_map, cpu));
+	cpus_clear(per_cpu(cpu_core_map, cpu));
+	c->phys_proc_id = 0;
+	c->cpu_core_id = 0;
+	cpu_clear(cpu, cpu_sibling_setup_map);
+}
+
 static void __ref remove_cpu_from_maps(int cpu)
 {
 	cpu_clear(cpu, cpu_online_map);
 	cpu_clear(cpu, cpu_callout_map);
 	cpu_clear(cpu, cpu_callin_map);
 	/* was set by cpu_init() */
-	clear_bit(cpu, (unsigned long *)&cpu_initialized);
+	cpu_clear(cpu, cpu_initialized);
 	numa_remove_cpu(cpu);
 }
 
-int __cpu_disable(void)
+void cpu_disable_common(void)
+{
+	int cpu = smp_processor_id();
+	/*
+	 * HACK:
+	 * Allow any queued timer interrupts to get serviced
+	 * This is only a temporary solution until we cleanup
+	 * fixup_irqs as we do for IA64.
+	 */
+	local_irq_enable();
+	mdelay(1);
+
+	local_irq_disable();
+	remove_siblinginfo(cpu);
+
+	/* It's now safe to remove this processor from the online map */
+	lock_vector_lock();
+	remove_cpu_from_maps(cpu);
+	unlock_vector_lock();
+	fixup_irqs(cpu_online_map);
+}
+
+int native_cpu_disable(void)
 {
 	int cpu = smp_processor_id();
 
@@ -1334,25 +1377,11 @@ int __cpu_disable(void)
 		stop_apic_nmi_watchdog(NULL);
 	clear_local_APIC();
 
-	/*
-	 * HACK:
-	 * Allow any queued timer interrupts to get serviced
-	 * This is only a temporary solution until we cleanup
-	 * fixup_irqs as we do for IA64.
-	 */
-	local_irq_enable();
-	mdelay(1);
-
-	local_irq_disable();
-	remove_siblinginfo(cpu);
-
-	/* It's now safe to remove this processor from the online map */
-	remove_cpu_from_maps(cpu);
-	fixup_irqs(cpu_online_map);
+	cpu_disable_common();
 	return 0;
 }
 
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
 {
 	/* We don't do anything here: idle task is faking death itself. */
 	unsigned int i;
@@ -1369,28 +1398,45 @@ void __cpu_die(unsigned int cpu)
 	}
 	printk(KERN_ERR "CPU %u didn't die...\n", cpu);
 }
+
+void play_dead_common(void)
+{
+	idle_task_exit();
+	reset_lazy_tlbstate();
+	irq_ctx_exit(raw_smp_processor_id());
+	c1e_remove_cpu(raw_smp_processor_id());
+
+	mb();
+	/* Ack it */
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+
+	/*
+	 * With physical CPU hotplug, we should halt the cpu
+	 */
+	local_irq_disable();
+}
+
+void native_play_dead(void)
+{
+	play_dead_common();
+	wbinvd_halt();
+}
+
 #else /* ... !CONFIG_HOTPLUG_CPU */
-int __cpu_disable(void)
+int native_cpu_disable(void)
 {
 	return -ENOSYS;
 }
 
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
 {
 	/* We said "no" in __cpu_disable */
 	BUG();
 }
-#endif
 
-/*
- * If the BIOS enumerates physical processors before logical,
- * maxcpus=N at enumeration-time can be used to disable HT.
- */
-static int __init parse_maxcpus(char *arg)
+void native_play_dead(void)
 {
-	extern unsigned int maxcpus;
-
-	maxcpus = simple_strtoul(arg, NULL, 0);
-	return 0;
+	BUG();
 }
-early_param("maxcpus", parse_maxcpus);
+
+#endif