1 files changed, 100 insertions, 591 deletions

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index be3c7a299f0..7bc86bbe748 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,8 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -24,28 +22,26 @@
 #include <linux/vmalloc.h>
 #include <linux/user.h>
 #include <linux/interrupt.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
-#include <linux/init.h>
 #include <linux/mc146818rtc.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/personality.h>
-#include <linux/tick.h>
 #include <linux/percpu.h>
+#include <linux/prctl.h>
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/kdebug.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
-#include <asm/io.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/desc.h>
-#include <asm/vm86.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
 #endif
@@ -54,20 +50,13 @@
 
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
-#include <asm/kdebug.h>
+#include <asm/idle.h>
+#include <asm/syscalls.h>
+#include <asm/debugreg.h>
+#include <asm/switch_to.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-
-static int hlt_counter;
-
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
-DEFINE_PER_CPU(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
+asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 /*
  * Return saved PC of a blocked thread.
@@ -77,262 +66,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return ((unsigned long *)tsk->thread.sp)[3];
 }
 
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
-
-void disable_hlt(void)
-{
-	hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-	hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
-	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we
-		 * test NEED_RESCHED:
-		 */
-		smp_mb();
-
-		local_irq_disable();
-		if (!need_resched()) {
-			ktime_t t0, t1;
-			u64 t0n, t1n;
-
-			t0 = ktime_get();
-			t0n = ktime_to_ns(t0);
-			safe_halt();	/* enables interrupts racelessly */
-			local_irq_disable();
-			t1 = ktime_get();
-			t1n = ktime_to_ns(t1);
-			sched_clock_idle_wakeup_event(t1n - t0n);
-		}
-		local_irq_enable();
-		current_thread_info()->status |= TS_POLLING;
-	} else {
-		/* loop is done by the caller */
-		cpu_relax();
-	}
-}
-#ifdef CONFIG_APM_MODULE
-EXPORT_SYMBOL(default_idle);
-#endif
-
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-	cpu_relax();
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <asm/nmi.h>
-/* We don't actually take CPU down, just spin without interrupts. */
-static inline void play_dead(void)
-{
-	/* This must be done before dead CPU ack */
-	cpu_exit_clear();
-	wbinvd();
-	mb();
-	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
-
-	/*
-	 * With physical CPU hotplug, we should halt the cpu
-	 */
-	local_irq_disable();
-	while (1)
-		halt();
-}
-#else
-static inline void play_dead(void)
-{
-	BUG();
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
-	int cpu = smp_processor_id();
-
-	current_thread_info()->status |= TS_POLLING;
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		tick_nohz_stop_sched_tick();
-		while (!need_resched()) {
-			void (*idle)(void);
-
-			if (__get_cpu_var(cpu_idle_state))
-				__get_cpu_var(cpu_idle_state) = 0;
-
-			check_pgt_cache();
-			rmb();
-			idle = pm_idle;
-
-			if (rcu_pending(cpu))
-				rcu_check_callbacks(cpu, 0);
-
-			if (!idle)
-				idle = default_idle;
-
-			if (cpu_is_offline(cpu))
-				play_dead();
-
-			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
-			idle();
-		}
-		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
-	}
-}
-
-static void do_nothing(void *unused)
-{
-}
-
-void cpu_idle_wait(void)
-{
-	unsigned int cpu, this_cpu = get_cpu();
-	cpumask_t map, tmp = current->cpus_allowed;
-
-	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
-	put_cpu();
-
-	cpus_clear(map);
-	for_each_online_cpu(cpu) {
-		per_cpu(cpu_idle_state, cpu) = 1;
-		cpu_set(cpu, map);
-	}
-
-	__get_cpu_var(cpu_idle_state) = 0;
-
-	wmb();
-	do {
-		ssleep(1);
-		for_each_online_cpu(cpu) {
-			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
-				cpu_clear(cpu, map);
-		}
-		cpus_and(map, map, cpu_online_map);
-		/*
-		 * We waited 1 sec, if a CPU still did not call idle
-		 * it may be because it is in idle and not waking up
-		 * because it has nothing to do.
-		 * Give all the remaining CPUS a kick.
-		 */
-		smp_call_function_mask(map, do_nothing, NULL, 0);
-	} while (!cpus_empty(map));
-
-	set_cpus_allowed(current, tmp);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(ax, cx);
-	}
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
-	local_irq_enable();
-	mwait_idle_with_hints(0, 0);
-}
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
-	static int selected;
-
-	if (selected)
-		return;
-#ifdef CONFIG_X86_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
-		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
-			" performance may degrade.\n");
-	}
-#endif
-	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
-		/*
-		 * Skip, if setup has overridden idle.
-		 * One CPU supports mwait => All CPUs supports mwait
-		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
-	if (!strcmp(str, "poll")) {
-		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
-	} else if (!strcmp(str, "mwait"))
-		force_mwait = 1;
-	else
-		return -1;
-
-	boot_option_idle_override = 1;
-	return 0;
-}
-early_param("idle", idle_setup);
-
-void __show_registers(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
 	unsigned long d0, d1, d2, d3, d6, d7;
@@ -342,32 +76,24 @@ void __show_registers(struct pt_regs *regs, int all)
 	if (user_mode_vm(regs)) {
 		sp = regs->sp;
 		ss = regs->ss & 0xffff;
-		savesegment(gs, gs);
+		gs = get_user_gs(regs);
 	} else {
-		sp = (unsigned long) (&regs->sp);
+		sp = kernel_stack_pointer(regs);
 		savesegment(ss, ss);
 		savesegment(gs, gs);
 	}
 
-	printk("\n");
-	printk("Pid: %d, comm: %s %s (%s %.*s)\n",
-			task_pid_nr(current), current->comm,
-			print_tainted(), init_utsname()->release,
-			(int)strcspn(init_utsname()->version, " "),
-			init_utsname()->version);
-
-	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
-			0xffff & regs->cs, regs->ip, regs->flags,
+	printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
+			(u16)regs->cs, regs->ip, regs->flags,
 			smp_processor_id());
 	print_symbol("EIP is at %s\n", regs->ip);
 
-	printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);
-	printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
+	printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
 		regs->si, regs->di, regs->bp, sp);
-	printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
-	       regs->ds & 0xffff, regs->es & 0xffff,
-	       regs->fs & 0xffff, gs, ss);
+	printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
+	       (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
 
 	if (!all)
 		return;
@@ -376,104 +102,25 @@ void __show_registers(struct pt_regs *regs, int all)
 	cr2 = read_cr2();
 	cr3 = read_cr3();
 	cr4 = read_cr4_safe();
-	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
+	printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
 			cr0, cr2, cr3, cr4);
 
 	get_debugreg(d0, 0);
 	get_debugreg(d1, 1);
 	get_debugreg(d2, 2);
 	get_debugreg(d3, 3);
-	printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
-			d0, d1, d2, d3);
-
 	get_debugreg(d6, 6);
 	get_debugreg(d7, 7);
-	printk("DR6: %08lx DR7: %08lx\n",
-			d6, d7);
-}
-
-void show_regs(struct pt_regs *regs)
-{
-	__show_registers(regs, 1);
-	show_trace(NULL, regs, &regs->sp, regs->bp);
-}
-
-/*
- * This gets run with %bx containing the
- * function to call, and %dx containing
- * the "args".
- */
-extern void kernel_thread_helper(void);
-
-/*
- * Create a kernel thread
- */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-	struct pt_regs regs;
 
-	memset(&regs, 0, sizeof(regs));
-
-	regs.bx = (unsigned long) fn;
-	regs.dx = (unsigned long) arg;
-
-	regs.ds = __USER_DS;
-	regs.es = __USER_DS;
-	regs.fs = __KERNEL_PERCPU;
-	regs.orig_ax = -1;
-	regs.ip = (unsigned long) kernel_thread_helper;
-	regs.cs = __KERNEL_CS | get_kernel_rpl();
-	regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
-
-	/* Ok, create the new process.. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
-/*
- * Free current thread data structures etc..
- */
-void exit_thread(void)
-{
-	/* The process may have allocated an io port bitmap... nuke it. */
-	if (unlikely(test_thread_flag(TIF_IO_BITMAP))) {
-		struct task_struct *tsk = current;
-		struct thread_struct *t = &tsk->thread;
-		int cpu = get_cpu();
-		struct tss_struct *tss = &per_cpu(init_tss, cpu);
-
-		kfree(t->io_bitmap_ptr);
-		t->io_bitmap_ptr = NULL;
-		clear_thread_flag(TIF_IO_BITMAP);
-		/*
-		 * Careful, clear this in the TSS too:
-		 */
-		memset(tss->io_bitmap, 0xff, tss->io_bitmap_max);
-		t->io_bitmap_max = 0;
-		tss->io_bitmap_owner = NULL;
-		tss->io_bitmap_max = 0;
-		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
-		put_cpu();
-	}
-}
+	/* Only print out debug registers if they are in their non-default state. */
+	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
+	    (d6 == DR6_RESERVED) && (d7 == 0x400))
+		return;
 
-void flush_thread(void)
-{
-	struct task_struct *tsk = current;
-
-	tsk->thread.debugreg0 = 0;
-	tsk->thread.debugreg1 = 0;
-	tsk->thread.debugreg2 = 0;
-	tsk->thread.debugreg3 = 0;
-	tsk->thread.debugreg6 = 0;
-	tsk->thread.debugreg7 = 0;
-	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));	
-	clear_tsk_thread_flag(tsk, TIF_DEBUG);
-	/*
-	 * Forget coprocessor state..
-	 */
-	clear_fpu(tsk);
-	clear_used_math();
+	printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
+			d0, d1, d2, d3);
+	printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n",
+			d6, d7);
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -482,36 +129,49 @@ void release_thread(struct task_struct *dead_task)
 	release_vm86_irqs(dead_task);
 }
 
-/*
- * This gets called before we allocate a new thread and copy
- * the current task into it.
- */
-void prepare_to_copy(struct task_struct *tsk)
-{
-	unlazy_fpu(tsk);
-}
-
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
-	unsigned long unused,
-	struct task_struct * p, struct pt_regs * regs)
+int copy_thread(unsigned long clone_flags, unsigned long sp,
+	unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs * childregs;
+	struct pt_regs *childregs = task_pt_regs(p);
 	struct task_struct *tsk;
 	int err;
 
-	childregs = task_pt_regs(p);
-	*childregs = *regs;
-	childregs->ax = 0;
-	childregs->sp = sp;
-
 	p->thread.sp = (unsigned long) childregs;
 	p->thread.sp0 = (unsigned long) (childregs+1);
 
-	p->thread.ip = (unsigned long) ret_from_fork;
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		p->thread.ip = (unsigned long) ret_from_kernel_thread;
+		task_user_gs(p) = __KERNEL_STACK_CANARY;
+		childregs->ds = __USER_DS;
+		childregs->es = __USER_DS;
+		childregs->fs = __KERNEL_PERCPU;
+		childregs->bx = sp;	/* function */
+		childregs->bp = arg;
+		childregs->orig_ax = -1;
+		childregs->cs = __KERNEL_CS | get_kernel_rpl();
+		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
+		p->thread.fpu_counter = 0;
+		p->thread.io_bitmap_ptr = NULL;
+		memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+		return 0;
+	}
+	*childregs = *current_pt_regs();
+	childregs->ax = 0;
+	if (sp)
+		childregs->sp = sp;
 
-	savesegment(gs, p->thread.gs);
+	p->thread.ip = (unsigned long) ret_from_fork;
+	task_user_gs(p) = get_user_gs(current_pt_regs());
 
+	p->thread.fpu_counter = 0;
+	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
+	err = -ENOMEM;
+
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
 	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
 						IO_BITMAP_BYTES, GFP_KERNEL);
@@ -538,112 +198,29 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
 	return err;
 }
 
-#ifdef CONFIG_SECCOMP
-static void hard_disable_TSC(void)
-{
-	write_cr4(read_cr4() | X86_CR4_TSD);
-}
-void disable_TSC(void)
-{
-	preempt_disable();
-	if (!test_and_set_thread_flag(TIF_NOTSC))
-		/*
-		 * Must flip the CPU state synchronously with
-		 * TIF_NOTSC in the current running context.
-		 */
-		hard_disable_TSC();
-	preempt_enable();
-}
-static void hard_enable_TSC(void)
-{
-	write_cr4(read_cr4() & ~X86_CR4_TSD);
-}
-#endif /* CONFIG_SECCOMP */
-
-static noinline void
-__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
-		 struct tss_struct *tss)
+void
+start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 {
-	struct thread_struct *prev, *next;
-	unsigned long debugctl;
-
-	prev = &prev_p->thread;
-	next = &next_p->thread;
-
-	debugctl = prev->debugctlmsr;
-	if (next->ds_area_msr != prev->ds_area_msr) {
-		/* we clear debugctl to make sure DS
-		 * is not in use when we change it */
-		debugctl = 0;
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, 0);
-		wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0);
-	}
-
-	if (next->debugctlmsr != debugctl)
-		wrmsr(MSR_IA32_DEBUGCTLMSR, next->debugctlmsr, 0);
-
-	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
-		set_debugreg(next->debugreg0, 0);
-		set_debugreg(next->debugreg1, 1);
-		set_debugreg(next->debugreg2, 2);
-		set_debugreg(next->debugreg3, 3);
-		/* no 4 and 5 */
-		set_debugreg(next->debugreg6, 6);
-		set_debugreg(next->debugreg7, 7);
-	}
-
-#ifdef CONFIG_SECCOMP
-	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
-	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
-		/* prev and next are different */
-		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
-			hard_disable_TSC();
-		else
-			hard_enable_TSC();
-	}
-#endif
-
-#ifdef X86_BTS
-	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
-		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
-
-	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
-		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
-
-
-	if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
-		/*
-		 * Disable the bitmap via an invalid offset. We still cache
-		 * the previous bitmap owner and the IO bitmap contents:
-		 */
-		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
-		return;
-	}
-
-	if (likely(next == tss->io_bitmap_owner)) {
-		/*
-		 * Previous owner of the bitmap (hence the bitmap content)
-		 * matches the next task, we dont have to do anything but
-		 * to set a valid offset in the TSS:
-		 */
-		tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
-		return;
-	}
+	set_user_gs(regs, 0);
+	regs->fs		= 0;
+	regs->ds		= __USER_DS;
+	regs->es		= __USER_DS;
+	regs->ss		= __USER_DS;
+	regs->cs		= __USER_CS;
+	regs->ip		= new_ip;
+	regs->sp		= new_sp;
+	regs->flags		= X86_EFLAGS_IF;
 	/*
-	 * Lazy TSS's I/O bitmap copy. We set an invalid offset here
-	 * and we let the task to get a GPF in case an I/O instruction
-	 * is performed.  The handler of the GPF will verify that the
-	 * faulting task has a valid I/O bitmap and, it true, does the
-	 * real copy and restart the instruction.  This will save us
-	 * redundant copies when the currently switched task does not
-	 * perform any I/O during its timeslice.
+	 * force it to the iret return path by making it look as if there was
+	 * some work pending.
 	 */
-	tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
+	set_thread_flag(TIF_NOTIFY_RESUME);
 }
+EXPORT_SYMBOL_GPL(start_thread);
+
 
 /*
- *	switch_to(x,yn) should switch tasks from x to y.
+ *	switch_to(x,y) should switch tasks from x to y.
  *
  * We fsave/fwait so that an exception goes off at the right time
  * (as a call from the fsave or fwait in effect) rather than to
@@ -669,21 +246,18 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
  * the task-switch, and shows up in ret_from_fork in entry.S,
  * for example.
  */
-struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+__visible __notrace_funcgraph struct task_struct *
+__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
 				 *next = &next_p->thread;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+	fpu_switch_t fpu;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	__unlazy_fpu(prev_p);
-
-
-	/* we're going to use this soon, after a few expensive things */
-	if (next_p->fpu_counter > 5)
-		prefetch(&next->i387.fxsave);
+	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
 	/*
 	 * Reload esp0.
@@ -700,7 +274,7 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct
 	 * used %fs or %gs (it does not today), or if the kernel is
 	 * running inside of a hypervisor layer.
 	 */
-	savesegment(gs, prev->gs);
+	lazy_save_gs(prev->gs);
 
 	/*
 	 * Load the per-thread Thread-Local Storage descriptor.
@@ -717,6 +291,14 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct
 		set_iopl_mask(next->iopl);
 
 	/*
+	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
+	 * preempt_count of all tasks was equal here and this would not be
+	 * needed.
+	 */
+	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
+	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
 	 */
 	if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
@@ -730,84 +312,23 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
-	/* If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	if (next_p->fpu_counter > 5)
-		math_state_restore();
+	this_cpu_write(kernel_stack,
+		  (unsigned long)task_stack_page(next_p) +
+		  THREAD_SIZE - KERNEL_STACK_OFFSET);
 
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
 	if (prev->gs | next->gs)
-		loadsegment(gs, next->gs);
+		lazy_load_gs(next->gs);
 
-	x86_write_percpu(current_task, next_p);
+	switch_fpu_finish(next_p, fpu);
 
-	return prev_p;
-}
-
-asmlinkage int sys_fork(struct pt_regs regs)
-{
-	return do_fork(SIGCHLD, regs.sp, &regs, 0, NULL, NULL);
-}
-
-asmlinkage int sys_clone(struct pt_regs regs)
-{
-	unsigned long clone_flags;
-	unsigned long newsp;
-	int __user *parent_tidptr, *child_tidptr;
-
-	clone_flags = regs.bx;
-	newsp = regs.cx;
-	parent_tidptr = (int __user *)regs.dx;
-	child_tidptr = (int __user *)regs.di;
-	if (!newsp)
-		newsp = regs.sp;
-	return do_fork(clone_flags, newsp, &regs, 0, parent_tidptr, child_tidptr);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(struct pt_regs regs)
-{
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.sp, &regs, 0, NULL, NULL);
-}
+	this_cpu_write(current_task, next_p);
 
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(struct pt_regs regs)
-{
-	int error;
-	char * filename;
-
-	filename = getname((char __user *) regs.bx);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename,
-			(char __user * __user *) regs.cx,
-			(char __user * __user *) regs.dx,
-			&regs);
-	if (error == 0) {
-		/* Make sure we don't return using sysenter.. */
-		set_thread_flag(TIF_IRET);
-	}
-	putname(filename);
-out:
-	return error;
+	return prev_p;
 }
 
 #define top_esp                (THREAD_SIZE - sizeof(unsigned long))
@@ -837,15 +358,3 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}