15 files changed, 46 insertions, 193 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 25f87bccbf8f..c940cb6f0409 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -82,6 +82,7 @@ config X86
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
 	select DCACHE_WORD_ACCESS
+	select GENERIC_SMP_IDLE_THREAD
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -160,9 +161,6 @@ config RWSEM_GENERIC_SPINLOCK
 config RWSEM_XCHGADD_ALGORITHM
 	def_bool X86_XADD
 
-config ARCH_HAS_CPU_IDLE_WAIT
-	def_bool y
-
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 94e91e401da9..277418ff8b52 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -149,7 +149,6 @@ archheaders:
 head-y := arch/x86/kernel/head_$(BITS).o
 head-y += arch/x86/kernel/head$(BITS).o
 head-y += arch/x86/kernel/head.o
-head-y += arch/x86/kernel/init_task.o
 
 libs-y  += arch/x86/lib/
 
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 5e1a2eef3e7c..b13fe63bdc59 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -19,7 +19,7 @@
 #ifdef CONFIG_X86_64
 #define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_ORDER)
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_SIZE_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ade619ff9e2a..ef17af013475 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,8 +15,8 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
-#define THREAD_ORDER	1
-#define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
+#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 #define STACKFAULT_STACK 0
 #define DOUBLEFAULT_STACK 1
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 7639dbf5d223..320f7bb95f76 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,8 +1,8 @@
 #ifndef _ASM_X86_PAGE_64_DEFS_H
 #define _ASM_X86_PAGE_64_DEFS_H
 
-#define THREAD_ORDER	1
-#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
+#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
 #define CURRENT_MASK (~(THREAD_SIZE - 1))
 
 #define EXCEPTION_STACK_ORDER 0
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4fa7dcceb6c0..ccbb1ea99ccb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -974,8 +974,6 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
-void cpu_idle_wait(void);
-
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0434c400287c..f8cbc6f20e31 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -62,6 +62,8 @@ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
 /* Static state in head.S used to set up a CPU */
 extern unsigned long stack_start; /* Initial stack pointer address */
 
+struct task_struct;
+
 struct smp_ops {
 	void (*smp_prepare_boot_cpu)(void);
 	void (*smp_prepare_cpus)(unsigned max_cpus);
@@ -70,7 +72,7 @@ struct smp_ops {
 	void (*stop_other_cpus)(int wait);
 	void (*smp_send_reschedule)(int cpu);
 
-	int (*cpu_up)(unsigned cpu);
+	int (*cpu_up)(unsigned cpu, struct task_struct *tidle);
 	int (*cpu_disable)(void);
 	void (*cpu_die)(unsigned int cpu);
 	void (*play_dead)(void);
@@ -113,9 +115,9 @@ static inline void smp_cpus_done(unsigned int max_cpus)
 	smp_ops.smp_cpus_done(max_cpus);
 }
 
-static inline int __cpu_up(unsigned int cpu)
+static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
-	return smp_ops.cpu_up(cpu);
+	return smp_ops.cpu_up(cpu, tidle);
 }
 
 static inline int __cpu_disable(void)
@@ -152,7 +154,7 @@ void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
-int native_cpu_up(unsigned int cpunum);
+int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
 void native_cpu_die(unsigned int cpu);
 void native_play_dead(void);
@@ -162,6 +164,7 @@ int wbinvd_on_all_cpus(void);
 
 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_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ad6df8ccd715..73cfe0d309c9 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -155,24 +155,6 @@ struct thread_info {
 
 #define PREEMPT_ACTIVE		0x10000000
 
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
-#else
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_NOTRACK)
-#endif
-
-#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-
-#define alloc_thread_info_node(tsk, node)				\
-({									\
-	struct page *page = alloc_pages_node(node, THREAD_FLAGS,	\
-					     THREAD_ORDER);		\
-	struct thread_info *ret = page ? page_address(page) : NULL;	\
-									\
-	ret;								\
-})
-
 #ifdef CONFIG_X86_32
 
 #define STACK_WARN	(THREAD_SIZE/8)
@@ -282,8 +264,7 @@ static inline bool is_ia32_task(void)
 
 #ifndef __ASSEMBLY__
 extern void arch_task_cache_init(void);
-extern void free_thread_info(struct thread_info *ti);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
-#define arch_task_cache_init arch_task_cache_init
+extern void arch_release_task_struct(struct task_struct *tsk);
 #endif
 #endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 532d2e090e6f..56ebd1f98447 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
+extra-y                := head_$(BITS).o head$(BITS).o head.o vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 459e78cbf61e..07b0c0db466c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -2401,7 +2401,7 @@ static void __exit apm_exit(void)
 		 * (pm_idle), Wait for all processors to update cached/local
 		 * copies of pm_idle before proceeding.
 		 */
-		cpu_idle_wait();
+		kick_all_cpus_sync();
 	}
 	if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0)
 	    && (apm_info.connection_version > 0x0100)) {
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
deleted file mode 100644
index 43e9ccf44947..000000000000
--- a/arch/x86/kernel/init_task.c
+++ /dev/null
@@ -1,42 +0,0 @@
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/init_task.h>
-#include <linux/fs.h>
-#include <linux/mqueue.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-
-/*
- * Initial thread structure.
- *
- * We need to make sure that this is THREAD_SIZE aligned due to the
- * way process stacks are handled. This is done by having a special
- * "init_task" linker map entry..
- */
-union thread_union init_thread_union __init_task_data =
-	{ INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-struct task_struct init_task = INIT_TASK(init_task);
-EXPORT_SYMBOL(init_task);
-
-/*
- * per-CPU TSS segments. Threads are completely 'soft' on Linux,
- * no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data..cacheline_aligned
- * section. Since TSS's are completely CPU-local, we want them
- * on exact cacheline boundaries, to eliminate cacheline ping-pong.
- */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
-
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 58b7f27cb3e9..344faf8d0d62 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -127,8 +127,8 @@ void __cpuinit irq_ctx_init(int cpu)
 		return;
 
 	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREAD_FLAGS,
-					       THREAD_ORDER));
+					       THREADINFO_GFP,
+					       THREAD_SIZE_ORDER));
 	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
 	irqctx->tinfo.cpu		= cpu;
 	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
@@ -137,8 +137,8 @@ void __cpuinit irq_ctx_init(int cpu)
 	per_cpu(hardirq_ctx, cpu) = irqctx;
 
 	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREAD_FLAGS,
-					       THREAD_ORDER));
+					       THREADINFO_GFP,
+					       THREAD_SIZE_ORDER));
 	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
 	irqctx->tinfo.cpu		= cpu;
 	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 1d92a5ab6e8b..e8173154800d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -27,6 +27,15 @@
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
 
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU(unsigned char, is_idle);
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -67,10 +76,9 @@ void free_thread_xstate(struct task_struct *tsk)
 	fpu_free(&tsk->thread.fpu);
 }
 
-void free_thread_info(struct thread_info *ti)
+void arch_release_task_struct(struct task_struct *tsk)
 {
-	free_thread_xstate(ti->task);
-	free_pages((unsigned long)ti, THREAD_ORDER);
+	free_thread_xstate(tsk);
 }
 
 void arch_task_cache_init(void)
@@ -516,26 +524,6 @@ void stop_this_cpu(void *dummy)
 	}
 }
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
 /* Default MONITOR/MWAIT with no hints, used for default C1 state */
 static void mwait_idle(void)
 {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6e1e406038c2..3acaf51dfddb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -76,20 +76,8 @@
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
-/* Store all idle threads, this can be reused instead of creating
-* a new thread. Also avoids complicated thread destroy functionality
-* for idle threads.
-*/
 #ifdef CONFIG_HOTPLUG_CPU
 /*
- * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
- * removed after init for !CONFIG_HOTPLUG_CPU.
- */
-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))
-
-/*
  * We need this for trampoline_base protection from concurrent accesses when
  * off- and onlining cores wildly.
  */
@@ -97,20 +85,16 @@ static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
 
 void cpu_hotplug_driver_lock(void)
 {
-        mutex_lock(&x86_cpu_hotplug_driver_mutex);
+	mutex_lock(&x86_cpu_hotplug_driver_mutex);
 }
 
 void cpu_hotplug_driver_unlock(void)
 {
-        mutex_unlock(&x86_cpu_hotplug_driver_mutex);
+	mutex_unlock(&x86_cpu_hotplug_driver_mutex);
 }
 
 ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
 ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
-#else
-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
 
 /* Number of siblings per CPU package */
@@ -618,22 +602,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	return (send_status | accept_status);
 }
 
-struct create_idle {
-	struct work_struct work;
-	struct task_struct *idle;
-	struct completion done;
-	int cpu;
-};
-
-static void __cpuinit do_fork_idle(struct work_struct *work)
-{
-	struct create_idle *c_idle =
-		container_of(work, struct create_idle, work);
-
-	c_idle->idle = fork_idle(c_idle->cpu);
-	complete(&c_idle->done);
-}
-
 /* reduce the number of lines printed when booting a large cpu count system */
 static void __cpuinit announce_cpu(int cpu, int apicid)
 {
@@ -660,58 +628,31 @@ static void __cpuinit announce_cpu(int cpu, int apicid)
  * Returns zero if CPU booted OK, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int __cpuinit do_boot_cpu(int apicid, int cpu)
+static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 {
 	unsigned long boot_error = 0;
 	unsigned long start_ip;
 	int timeout;
-	struct create_idle c_idle = {
-		.cpu	= cpu,
-		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
-	};
-
-	INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
 
 	alternatives_smp_switch(1);
 
-	c_idle.idle = get_idle_for_cpu(cpu);
-
-	/*
-	 * We can't use kernel_thread since we must avoid to
-	 * reschedule the child.
-	 */
-	if (c_idle.idle) {
-		c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *)
-			(THREAD_SIZE +  task_stack_page(c_idle.idle))) - 1);
-		init_idle(c_idle.idle, cpu);
-		goto do_rest;
-	}
+	idle->thread.sp = (unsigned long) (((struct pt_regs *)
+			  (THREAD_SIZE +  task_stack_page(idle))) - 1);
+	per_cpu(current_task, cpu) = idle;
 
-	schedule_work(&c_idle.work);
-	wait_for_completion(&c_idle.done);
-
-	if (IS_ERR(c_idle.idle)) {
-		printk("failed fork for CPU %d\n", cpu);
-		destroy_work_on_stack(&c_idle.work);
-		return PTR_ERR(c_idle.idle);
-	}
-
-	set_idle_for_cpu(cpu, c_idle.idle);
-do_rest:
-	per_cpu(current_task, cpu) = c_idle.idle;
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	irq_ctx_init(cpu);
 #else
-	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
 	per_cpu(kernel_stack, cpu) =
-		(unsigned long)task_stack_page(c_idle.idle) -
+		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
 #endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
-	stack_start  = c_idle.idle->thread.sp;
+	stack_start  = idle->thread.sp;
 
 	/* start_ip had better be page-aligned! */
 	start_ip = trampoline_address();
@@ -813,12 +754,10 @@ do_rest:
 		 */
 		smpboot_restore_warm_reset_vector();
 	}
-
-	destroy_work_on_stack(&c_idle.work);
 	return boot_error;
 }
 
-int __cpuinit native_cpu_up(unsigned int cpu)
+int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int apicid = apic->cpu_present_to_apicid(cpu);
 	unsigned long flags;
@@ -851,7 +790,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
-	err = do_boot_cpu(apicid, cpu);
+	err = do_boot_cpu(apicid, cpu, tidle);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
 		return -EIO;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 0503c0c493a9..3700945ed0d5 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -265,18 +265,8 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 		set_cpu_possible(cpu, false);
 	}
 
-	for_each_possible_cpu (cpu) {
-		struct task_struct *idle;
-
-		if (cpu == 0)
-			continue;
-
-		idle = fork_idle(cpu);
-		if (IS_ERR(idle))
-			panic("failed fork for CPU %d", cpu);
-
+	for_each_possible_cpu(cpu)
 		set_cpu_present(cpu, true);
-	}
 }
 
 static int __cpuinit
@@ -346,9 +336,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
-static int __cpuinit xen_cpu_up(unsigned int cpu)
+static int __cpuinit xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
-	struct task_struct *idle = idle_task(cpu);
 	int rc;
 
 	per_cpu(current_task, cpu) = idle;
@@ -562,10 +551,10 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	xen_init_lock_cpu(0);
 }
 
-static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
+static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc;
-	rc = native_cpu_up(cpu);
+	rc = native_cpu_up(cpu, tidle);
 	WARN_ON (xen_smp_intr_init(cpu));
 	return rc;
 }