arch/x86/kernel/process_64.c

/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 *
 *  X86-64 port
 *	Andi Kleen.
 *
 *	CPU hotplug support - ashok.raj@intel.com
 */

/*
 * This file handles the architecture-dependent parts of process handling..
 */

#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/tick.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
#include <linux/dmi.h>

#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/ds.h>
#include <asm/debugreg.h>
#include <asm/hw_breakpoint.h>

asmlinkage extern void ret_from_fork(void);

DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);

DEFINE_PER_CPU(unsigned long, old_rsp);
static DEFINE_PER_CPU(unsigned char, is_idle);

unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;

static ATOMIC_NOTIFIER_HEAD(idle_notifier);

void idle_notifier_register(struct notifier_block *n)
{
	atomic_notifier_chain_register(&idle_notifier, n);
}
EXPORT_SYMBOL_GPL(idle_notifier_register);

void idle_notifier_unregister(struct notifier_block *n)
{
	atomic_notifier_chain_unregister(&idle_notifier, n);
}
EXPORT_SYMBOL_GPL(idle_notifier_unregister);

void enter_idle(void)
{
	percpu_write(is_idle, 1);
	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}

static void __exit_idle(void)
{
	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
		return;
	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}

/* Called from interrupts to signify idle end */
void exit_idle(void)
{
	/* idle loop has pid 0 */
	if (current->pid)
		return;
	__exit_idle();
}

#ifndef CONFIG_SMP
static inline void play_dead(void)
{
	BUG();
}
#endif

/*
 * 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)
{
	current_thread_info()->status |= TS_POLLING;

	/*
	 * If we're the non-boot CPU, nothing set the stack canary up
	 * for us.  CPU0 already has it initialized but no harm in
	 * doing it again.  This is a good place for updating it, as
	 * we wont ever return from this function (so the invalid
	 * canaries already on the stack wont ever trigger).
	 */
	boot_init_stack_canary();

	/* endless idle loop with no priority at all */
	while (1) {
		tick_nohz_stop_sched_tick(1);
		while (!need_resched()) {

			rmb();

			if (cpu_is_offline(smp_processor_id()))
				play_dead();
			/*
			 * Idle routines should keep interrupts disabled
			 * from here on, until they go to idle.
			 * Otherwise, idle callbacks can misfire.
			 */
			local_irq_disable();
			enter_idle();
			/* Don't trace irqs off for idle */
			stop_critical_timings();
			pm_idle();
			start_critical_timings();
			/* In many cases the interrupt that ended idle
			   has already called exit_idle. But some idle
			   loops can be woken up without interrupt. */
			__exit_idle();
		}

		tick_nohz_restart_sched_tick();
		preempt_enable_no_resched();
		schedule();
		preempt_disable();
	}
}

/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
	unsigned long d0, d1, d2, d3, d6, d7;
	unsigned int fsindex, gsindex;
	unsigned int ds, cs, es;
	const char *board;

	printk("\n");
	print_modules();
	board = dmi_get_system_info(DMI_PRODUCT_NAME);
	if (!board)
		board = "";
	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n",
		current->pid, current->comm, print_tainted(),
		init_utsname()->release,
		(int)strcspn(init_utsname()->version, " "),
		init_utsname()->version, board);
	printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
	printk_address(regs->ip, 1);
	printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
			regs->sp, regs->flags);
	printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->ax, regs->bx, regs->cx);
	printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->dx, regs->si, regs->di);
	printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->bp, regs->r8, regs->r9);
	printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
	       regs->r10, regs->r11, regs->r12);
	printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
	       regs->r13, regs->r14, regs->r15);

	asm("movl %%ds,%0" : "=r" (ds));
	asm("movl %%cs,%0" : "=r" (cs));
	asm("movl %%es,%0" : "=r" (es));
	asm("movl %%fs,%0" : "=r" (fsindex));
	asm("movl %%gs,%0" : "=r" (gsindex));

	rdmsrl(MSR_FS_BASE, fs);
	rdmsrl(MSR_GS_BASE, gs);
	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);

	if (!all)
		return;

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = read_cr4();

	printk(KERN_INFO "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
	       fs, fsindex, gs, gsindex, shadowgs);
	printk(KERN_INFO "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
			es, cr0);
	printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
			cr4);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);
	printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}

void show_regs(struct pt_regs *regs)
{
	printk(KERN_INFO "CPU %d:", smp_processor_id());
	__show_regs(regs, 1);
	show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
}

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		if (dead_task->mm->context.size) {
			printk("WARNING: dead process %8s still has LDT? <%p/%d>\n",
					dead_task->comm,
					dead_task->mm->context.ldt,
					dead_task->mm->context.size);
			BUG();
		}
	}
	if (unlikely(dead_task->thread.debugreg7))
		flush_thread_hw_breakpoint(dead_task);
}

static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
{
	struct user_desc ud = {
		.base_addr = addr,
		.limit = 0xfffff,
		.seg_32bit = 1,
		.limit_in_pages = 1,
		.useable = 1,
	};
	struct desc_struct *desc = t->thread.tls_array;
	desc += tls;
	fill_ldt(desc, &ud);
}

static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
	return get_desc_base(&t->thread.tls_array[tls]);
}

/*
 * 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(unsigned long clone_flags, unsigned long sp,
		unsigned long unused,
	struct task_struct *p, struct pt_regs *regs)
{
	int err;
	struct pt_regs *childregs;
	struct task_struct *me = current;

	childregs = ((struct pt_regs *)
			(THREAD_SIZE + task_stack_page(p))) - 1;
	*childregs = *regs;

	childregs->ax = 0;
	childregs->sp = sp;
	if (sp == ~0UL)
		childregs->sp = (unsigned long)childregs;

	p->thread.sp = (unsigned long) childregs;
	p->thread.sp0 = (unsigned long) (childregs+1);
	p->thread.usersp = me->thread.usersp;

	set_tsk_thread_flag(p, TIF_FORK);

	p->thread.fs = me->thread.fs;
	p->thread.gs = me->thread.gs;
	p->thread.io_bitmap_ptr = NULL;

	savesegment(gs, p->thread.gsindex);
	savesegment(fs, p->thread.fsindex);
	savesegment(es, p->thread.es);
	savesegment(ds, p->thread.ds);

	err = -ENOMEM;
	if (unlikely(test_tsk_thread_flag(me, TIF_DEBUG)))
		if (copy_thread_hw_breakpoint(me, p, clone_flags))
			goto out;

	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) {
			p->thread.io_bitmap_max = 0;
			return -ENOMEM;
		}
		memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
				IO_BITMAP_BYTES);
		set_tsk_thread_flag(p, TIF_IO_BITMAP);
	}

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
		if (test_thread_flag(TIF_IA32))
			err = do_set_thread_area(p, -1,
				(struct user_desc __user *)childregs->si, 0);
		else
#endif
			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
		if (err)
			goto out;
	}

	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
	p->thread.ds_ctx = NULL;

	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
	p->thread.debugctlmsr = 0;

	err = 0;
out:
	if (err && p->thread.io_bitmap_ptr) {
		kfree(p->thread.io_bitmap_ptr);
		p->thread.io_bitmap_max = 0;
	}
	if (err)
		flush_thread_hw_breakpoint(p);

	return err;
}

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
	loadsegment(fs, 0);
	loadsegment(es, 0);
	loadsegment(ds, 0);
	load_gs_index(0);
	regs->ip		= new_ip;
	regs->sp		= new_sp;
	percpu_write(old_rsp, new_sp);
	regs->cs		= __USER_CS;
	regs->ss		= __USER_DS;
	regs->flags		= 0x200;
	set_fs(USER_DS);
	/*
	 * Free the old FP and other extended state
	 */
	free_thread_xstate(current);
}
EXPORT_SYMBOL_GPL(start_thread);

/*
 *	switch_to(x,y) should switch tasks from x to y.
 *
 * This could still be optimized:
 * - fold all the options into a flag word and test it with a single test.
 * - could test fs/gs bitsliced
 *
 * Kprobes not supported here. Set the probe on schedule instead.
 * Function graph tracer not supported too.
 */
__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread;
	struct thread_struct *next = &next_p->thread;
	int cpu = smp_processor_id();
	struct tss_struct *tss = &per_cpu(init_tss, cpu);
	unsigned fsindex, gsindex;

	/* we're going to use this soon, after a few expensive things */
	if (next_p->fpu_counter > 5)
		prefetch(next->xstate);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	load_sp0(tss, next);

	/*
	 * Switch DS and ES.
	 * This won't pick up thread selector changes, but I guess that is ok.
	 */
	savesegment(es, prev->es);
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es);

	savesegment(ds, prev->ds);
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);


	/* We must save %fs and %gs before load_TLS() because
	 * %fs and %gs may be cleared by load_TLS().
	 *
	 * (e.g. xen_load_tls())
	 */
	savesegment(fs, fsindex);
	savesegment(gs, gsindex);

	load_TLS(next, cpu);

	/*
	 * Leave lazy mode, flushing any hypercalls made here.
	 * This must be done before restoring TLS segments so
	 * the GDT and LDT are properly updated, and must be
	 * done before math_state_restore, so the TS bit is up
	 * to date.
	 */
	arch_end_context_switch(next_p);

	/*
	 * Switch FS and GS.
	 *
	 * Segment register != 0 always requires a reload.  Also
	 * reload when it has changed.  When prev process used 64bit
	 * base always reload to avoid an information leak.
	 */
	if (unlikely(fsindex | next->fsindex | prev->fs)) {
		loadsegment(fs, next->fsindex);
		/*
		 * Check if the user used a selector != 0; if yes
		 *  clear 64bit base, since overloaded base is always
		 *  mapped to the Null selector
		 */
		if (fsindex)
			prev->fs = 0;
	}
	/* when next process has a 64bit base use it */
	if (next->fs)
		wrmsrl(MSR_FS_BASE, next->fs);
	prev->fsindex = fsindex;

	if (unlikely(gsindex | next->gsindex | prev->gs)) {
		load_gs_index(next->gsindex);
		if (gsindex)
			prev->gs = 0;
	}
	if (next->gs)
		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
	prev->gsindex = gsindex;

	/* Must be after DS reload */
	unlazy_fpu(prev_p);

	/*
	 * Switch the PDA and FPU contexts.
	 */
	prev->usersp = percpu_read(old_rsp);
	percpu_write(old_rsp, next->usersp);
	percpu_write(current_task, next_p);

	percpu_write(kernel_stack,
		  (unsigned long)task_stack_page(next_p) +
		  THREAD_SIZE - KERNEL_STACK_OFFSET);

	/*
	 * Now maybe reload the debug registers and handle I/O bitmaps
	 */
	if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT ||
		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
		__switch_to_xtra(prev_p, next_p, tss);

	/* 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
	 *
	 * tsk_used_math() checks prevent calling math_state_restore(),
	 * which can sleep in the case of !tsk_used_math()
	 */
	if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
		math_state_restore();
	/*
	 * There's a problem with moving the arch_install_thread_hw_breakpoint()
	 * call before current is updated.  Suppose a kernel breakpoint is
	 * triggered in between the two, the hw-breakpoint handler will see that
	 * the 'current' task does not have TIF_DEBUG flag set and will think it
	 * is leftover from an old task (lazy switching) and will erase it. Then
	 * until the next context switch, no user-breakpoints will be installed.
	 *
	 * The real problem is that it's impossible to update both current and
	 * physical debug registers at the same instant, so there will always be
	 * a window in which they disagree and a breakpoint might get triggered.
	 * Since we use lazy switching, we are forced to assume that a
	 * disagreement means that current is correct and the exception is due
	 * to lazy debug register switching.
	 */
	if (unlikely(test_tsk_thread_flag(next_p, TIF_DEBUG)))
		arch_install_thread_hw_breakpoint(next_p);

	return prev_p;
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage
long sys_execve(char __user *name, char __user * __user *argv,
		char __user * __user *envp, struct pt_regs *regs)
{
	long error;
	char *filename;

	filename = getname(name);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		return error;
	error = do_execve(filename, argv, envp, regs);
	putname(filename);
	return error;
}

void set_personality_64bit(void)
{
	/* inherit personality from parent */

	/* Make sure to be in 64bit mode */
	clear_thread_flag(TIF_IA32);

	/* TBD: overwrites user setup. Should have two bits.
	   But 64bit processes have always behaved this way,
	   so it's not too bad. The main problem is just that
	   32bit childs are affected again. */
	current->personality &= ~READ_IMPLIES_EXEC;
}

asmlinkage long
sys_clone(unsigned long clone_flags, unsigned long newsp,
	  void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
{
	if (!newsp)
		newsp = regs->sp;
	return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}

unsigned long get_wchan(struct task_struct *p)
{
	unsigned long stack;
	u64 fp, ip;
	int count = 0;

	if (!p || p == current || p->state == TASK_RUNNING)
		return 0;
	stack = (unsigned long)task_stack_page(p);
	if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
		return 0;
	fp = *(u64 *)(p->thread.sp);
	do {
		if (fp < (unsigned long)stack ||
		    fp >= (unsigned long)stack+THREAD_SIZE)
			return 0;
		ip = *(u64 *)(fp+8);
		if (!in_sched_functions(ip))
			return ip;
		fp = *(u64 *)fp;
	} while (count++ < 16);
	return 0;
}

long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{
	int ret = 0;
	int doit = task == current;
	int cpu;

	switch (code) {
	case ARCH_SET_GS:
		if (addr >= TASK_SIZE_OF(task))
			return -EPERM;
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to
		   switch. */
		if (addr <= 0xffffffff) {
			set_32bit_tls(task, GS_TLS, addr);
			if (doit) {
				load_TLS(&task->thread, cpu);
				load_gs_index(GS_TLS_SEL);
			}
			task->thread.gsindex = GS_TLS_SEL;
			task->thread.gs = 0;
		} else {
			task->thread.gsindex = 0;
			task->thread.gs = addr;
			if (doit) {
				load_gs_index(0);
				ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
			}
		}
		put_cpu();
		break;
	case ARCH_SET_FS:
		/* Not strictly needed for fs, but do it for symmetry
		   with gs */
		if (addr >= TASK_SIZE_OF(task))
			return -EPERM;
		cpu = get_cpu();
		/* handle small bases via the GDT because that's faster to
		   switch. */
		if (addr <= 0xffffffff) {
			set_32bit_tls(task, FS_TLS, addr);
			if (doit) {
				load_TLS(&task->thread, cpu);
				loadsegment(fs, FS_TLS_SEL);
			}
			task->thread.fsindex = FS_TLS_SEL;
			task->thread.fs = 0;
		} else {
			task->thread.fsindex = 0;
			task->thread.fs = addr;
			if (doit) {
				/* set the selector to 0 to not confuse
				   __switch_to */
				loadsegment(fs, 0);
				ret = checking_wrmsrl(MSR_FS_BASE, addr);
			}
		}
		put_cpu();
		break;
	case ARCH_GET_FS: {
		unsigned long base;
		if (task->thread.fsindex == FS_TLS_SEL)
			base = read_32bit_tls(task, FS_TLS);
		else if (doit)
			rdmsrl(MSR_FS_BASE, base);
		else
			base = task->thread.fs;
		ret = put_user(base, (unsigned long __user *)addr);
		break;
	}
	case ARCH_GET_GS: {
		unsigned long base;
		unsigned gsindex;
		if (task->thread.gsindex == GS_TLS_SEL)
			base = read_32bit_tls(task, GS_TLS);
		else if (doit) {
			savesegment(gs, gsindex);
			if (gsindex)
				rdmsrl(MSR_KERNEL_GS_BASE, base);
			else
				base = task->thread.gs;
		} else
			base = task->thread.gs;
		ret = put_user(base, (unsigned long __user *)addr);
		break;
	}

	default:
		ret = -EINVAL;
		break;
	}

	return ret;
}

long sys_arch_prctl(int code, unsigned long addr)
{
	return do_arch_prctl(current, code, addr);
}