Merge branch 'x86-bsp-hotplug-for-linus' of git://git.kernel.org/pub/…

…scm/linux/kernel/git/tip/tip

Pull x86 BSP hotplug changes from Ingo Molnar:
 "This tree enables CPU#0 (the boot processor) to be onlined/offlined on
  x86, just like any other CPU.  Enabled on Intel CPUs for now.

  Allowing this required the identification and fixing of latent CPU#0
  assumptions (such as CPU#0 initializations, etc.) in the x86
  architecture code, plus the identification of barriers to
  BSP-offlining, such as active PIC interrupts which can only be
  serviced on the BSP.

  It's behind a default-off option, and there's a debug option that
  allows the automatic testing of this feature.

  The motivation of this feature is to allow and prepare for true
  CPU-hotplug hardware support: recent changes to MCE support enable us
  to detect a deteriorating but not yet hard-failing L1/L2 cache on a
  CPU that could be soft-unplugged - or a failing L3 cache on a
  multi-socket system.

  Note that true hardware hot-plug is not yet fully enabled by this,
  because that requires a special platform wakeup sequence to be sent to
  the freshly powered up CPU#0.  Future patches for this are planned,
  once such a platform exists.  Chicken and egg"

* 'x86-bsp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, topology: Debug CPU0 hotplug
  x86/i387.c: Initialize thread xstate only on CPU0 only once
  x86, hotplug: Handle retrigger irq by the first available CPU
  x86, hotplug: The first online processor saves the MTRR state
  x86, hotplug: During CPU0 online, enable x2apic, set_numa_node.
  x86, hotplug: Wake up CPU0 via NMI instead of INIT, SIPI, SIPI
  x86-32, hotplug: Add start_cpu0() entry point to head_32.S
  x86-64, hotplug: Add start_cpu0() entry point to head_64.S
  kernel/cpu.c: Add comment for priority in cpu_hotplug_pm_callback
  x86, hotplug, suspend: Online CPU0 for suspend or hibernate
  x86, hotplug: Support functions for CPU0 online/offline
  x86, topology: Don't offline CPU0 if any PIC irq can not be migrated out of it
  x86, Kconfig: Add config switch for CPU0 hotplug
  doc: Add x86 CPU0 online/offline feature

Documentation/cpu-hotplug.txt

@@ -207,6 +207,30 @@ by making it not-removable.
 
 In such cases you will also notice that the online file is missing under cpu0.
 
+Q: Is CPU0 removable on X86?
+A: Yes. If kernel is compiled with CONFIG_BOOTPARAM_HOTPLUG_CPU0=y, CPU0 is
+removable by default. Otherwise, CPU0 is also removable by kernel option
+cpu0_hotplug.
+
+But some features depend on CPU0. Two known dependencies are:
+
+1. Resume from hibernate/suspend depends on CPU0. Hibernate/suspend will fail if
+CPU0 is offline and you need to online CPU0 before hibernate/suspend can
+continue.
+2. PIC interrupts also depend on CPU0. CPU0 can't be removed if a PIC interrupt
+is detected.
+
+It's said poweroff/reboot may depend on CPU0 on some machines although I haven't
+seen any poweroff/reboot failure so far after CPU0 is offline on a few tested
+machines.
+
+Please let me know if you know or see any other dependencies of CPU0.
+
+If the dependencies are under your control, you can turn on CPU0 hotplug feature
+either by CONFIG_BOOTPARAM_HOTPLUG_CPU0 or by kernel parameter cpu0_hotplug.
+
+--Fenghua Yu <[email protected]>
+
 Q: How do i find out if a particular CPU is not removable?
 A: Depending on the implementation, some architectures may show this by the
 absence of the "online" file. This is done if it can be determined ahead of

Documentation/kernel-parameters.txt

@@ -1984,6 +1984,20 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
 
+	cpu0_hotplug	[X86] Turn on CPU0 hotplug feature when
+			CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
+			Some features depend on CPU0. Known dependencies are:
+			1. Resume from suspend/hibernate depends on CPU0.
+			Suspend/hibernate will fail if CPU0 is offline and you
+			need to online CPU0 before suspend/hibernate.
+			2. PIC interrupts also depend on CPU0. CPU0 can't be
+			removed if a PIC interrupt is detected.
+			It's said poweroff/reboot may depend on CPU0 on some
+			machines although I haven't seen such issues so far
+			after CPU0 is offline on a few tested machines.
+			If the dependencies are under your control, you can
+			turn on cpu0_hotplug.
+
 	nptcg=		[IA-64] Override max number of concurrent global TLB
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.

arch/x86/Kconfig

@@ -1698,6 +1698,50 @@ config HOTPLUG_CPU
 	    automatically on SMP systems. )
 	  Say N if you want to disable CPU hotplug.
 
+config BOOTPARAM_HOTPLUG_CPU0
+	bool "Set default setting of cpu0_hotpluggable"
+	default n
+	depends on HOTPLUG_CPU && EXPERIMENTAL
+	---help---
+	  Set whether default state of cpu0_hotpluggable is on or off.
+
+	  Say Y here to enable CPU0 hotplug by default. If this switch
+	  is turned on, there is no need to give cpu0_hotplug kernel
+	  parameter and the CPU0 hotplug feature is enabled by default.
+
+	  Please note: there are two known CPU0 dependencies if you want
+	  to enable the CPU0 hotplug feature either by this switch or by
+	  cpu0_hotplug kernel parameter.
+
+	  First, resume from hibernate or suspend always starts from CPU0.
+	  So hibernate and suspend are prevented if CPU0 is offline.
+
+	  Second dependency is PIC interrupts always go to CPU0. CPU0 can not
+	  offline if any interrupt can not migrate out of CPU0. There may
+	  be other CPU0 dependencies.
+
+	  Please make sure the dependencies are under your control before
+	  you enable this feature.
+
+	  Say N if you don't want to enable CPU0 hotplug feature by default.
+	  You still can enable the CPU0 hotplug feature at boot by kernel
+	  parameter cpu0_hotplug.
+
+config DEBUG_HOTPLUG_CPU0
+	def_bool n
+	prompt "Debug CPU0 hotplug"
+	depends on HOTPLUG_CPU && EXPERIMENTAL
+	---help---
+	  Enabling this option offlines CPU0 (if CPU0 can be offlined) as
+	  soon as possible and boots up userspace with CPU0 offlined. User
+	  can online CPU0 back after boot time.
+
+	  To debug CPU0 hotplug, you need to enable CPU0 offline/online
+	  feature by either turning on CONFIG_BOOTPARAM_HOTPLUG_CPU0 during
+	  compilation or giving cpu0_hotplug kernel parameter at boot.
+
+	  If unsure, say N.
+
 config COMPAT_VDSO
 	def_bool y
 	prompt "Compat VDSO support"

arch/x86/include/asm/cpu.h

@@ -28,6 +28,10 @@ struct x86_cpu {
 #ifdef CONFIG_HOTPLUG_CPU
 extern int arch_register_cpu(int num);
 extern void arch_unregister_cpu(int);
+extern void __cpuinit start_cpu0(void);
+#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
+extern int _debug_hotplug_cpu(int cpu, int action);
+#endif
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);

arch/x86/include/asm/smp.h

@@ -166,6 +166,7 @@ void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle);
 
+void smp_store_boot_cpu_info(void);
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 

arch/x86/kernel/apic/io_apic.c

@@ -2199,9 +2199,11 @@ static int ioapic_retrigger_irq(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	unsigned long flags;
+	int cpu;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
+	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
+	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;

arch/x86/kernel/cpu/common.c

@@ -1237,7 +1237,7 @@ void __cpuinit cpu_init(void)
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
-	if (cpu != 0 && this_cpu_read(numa_node) == 0 &&
+	if (this_cpu_read(numa_node) == 0 &&
 	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
 		set_numa_node(early_cpu_to_node(cpu));
 #endif
@@ -1269,8 +1269,7 @@ void __cpuinit cpu_init(void)
 	barrier();
 
 	x86_configure_nx();
-	if (cpu != 0)
-		enable_x2apic();
+	enable_x2apic();
 
 	/*
 	 * set up and load the per-CPU TSS

arch/x86/kernel/cpu/mtrr/main.c

@@ -695,11 +695,16 @@ void mtrr_ap_init(void)
 }
 
 /**
- * Save current fixed-range MTRR state of the BSP
+ * Save current fixed-range MTRR state of the first cpu in cpu_online_mask.
  */
 void mtrr_save_state(void)
 {
-	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
+	int first_cpu;
+
+	get_online_cpus();
+	first_cpu = cpumask_first(cpu_online_mask);
+	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
+	put_online_cpus();
 }
 
 void set_mtrr_aps_delayed_init(void)

arch/x86/kernel/head_32.S

@@ -266,6 +266,19 @@ num_subarch_entries = (. - subarch_entries) / 4
 	jmp default_entry
 #endif /* CONFIG_PARAVIRT */
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
+ * up already except stack. We just set up stack here. Then call
+ * start_secondary().
+ */
+ENTRY(start_cpu0)
+	movl stack_start, %ecx
+	movl %ecx, %esp
+	jmp  *(initial_code)
+ENDPROC(start_cpu0)
+#endif
+
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but

arch/x86/kernel/head_64.S

@@ -252,6 +252,22 @@ ENTRY(secondary_startup_64)
 	pushq	%rax		# target address in negative space
 	lretq
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
+ * up already except stack. We just set up stack here. Then call
+ * start_secondary().
+ */
+ENTRY(start_cpu0)
+	movq stack_start(%rip),%rsp
+	movq	initial_code(%rip),%rax
+	pushq	$0		# fake return address to stop unwinder
+	pushq	$__KERNEL_CS	# set correct cs
+	pushq	%rax		# target address in negative space
+	lretq
+ENDPROC(start_cpu0)
+#endif
+
 	/* SMP bootup changes these two */
 	__REFDATA
 	.align	8

arch/x86/kernel/i387.c

@@ -175,7 +175,11 @@ void __cpuinit fpu_init(void)
 		cr0 |= X86_CR0_EM;
 	write_cr0(cr0);
 
-	if (!smp_processor_id())
+	/*
+	 * init_thread_xstate is only called once to avoid overriding
+	 * xstate_size during boot time or during CPU hotplug.
+	 */
+	if (xstate_size == 0)
 		init_thread_xstate();
 
 	mxcsr_feature_mask_init();