process_32.c

linux 内核源代码

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
		struct desc_struct *desc;
		struct user_desc info;
		int idx;

		err = -EFAULT;
		if (copy_from_user(&info, (void __user *)childregs->esi, sizeof(info)))
			goto out;
		err = -EINVAL;
		if (LDT_empty(&info))
			goto out;

		idx = info.entry_number;
		if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
			goto out;

		desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
		desc->a = LDT_entry_a(&info);
		desc->b = LDT_entry_b(&info);
	}

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

/*
 * fill in the user structure for a core dump..
 */
void dump_thread(struct pt_regs * regs, struct user * dump)
{
	int i;

/* changed the size calculations - should hopefully work better. lbt */
	dump->magic = CMAGIC;
	dump->start_code = 0;
	dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
	dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
	dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
	dump->u_dsize -= dump->u_tsize;
	dump->u_ssize = 0;
	for (i = 0; i < 8; i++)
		dump->u_debugreg[i] = current->thread.debugreg[i];  

	if (dump->start_stack < TASK_SIZE)
		dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;

	dump->regs.ebx = regs->ebx;
	dump->regs.ecx = regs->ecx;
	dump->regs.edx = regs->edx;
	dump->regs.esi = regs->esi;
	dump->regs.edi = regs->edi;
	dump->regs.ebp = regs->ebp;
	dump->regs.eax = regs->eax;
	dump->regs.ds = regs->xds;
	dump->regs.es = regs->xes;
	dump->regs.fs = regs->xfs;
	savesegment(gs,dump->regs.gs);
	dump->regs.orig_eax = regs->orig_eax;
	dump->regs.eip = regs->eip;
	dump->regs.cs = regs->xcs;
	dump->regs.eflags = regs->eflags;
	dump->regs.esp = regs->esp;
	dump->regs.ss = regs->xss;

	dump->u_fpvalid = dump_fpu (regs, &dump->i387);
}
EXPORT_SYMBOL(dump_thread);

/* 
 * Capture the user space registers if the task is not running (in user space)
 */
int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
{
	struct pt_regs ptregs = *task_pt_regs(tsk);
	ptregs.xcs &= 0xffff;
	ptregs.xds &= 0xffff;
	ptregs.xes &= 0xffff;
	ptregs.xss &= 0xffff;

	elf_core_copy_regs(regs, &ptregs);

	return 1;
}

#ifdef CONFIG_SECCOMP
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();
}
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)
{
	struct thread_struct *next;

	next = &next_p->thread;

	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
		set_debugreg(next->debugreg[0], 0);
		set_debugreg(next->debugreg[1], 1);
		set_debugreg(next->debugreg[2], 2);
		set_debugreg(next->debugreg[3], 3);
		/* no 4 and 5 */
		set_debugreg(next->debugreg[6], 6);
		set_debugreg(next->debugreg[7], 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

	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;
	}
	/*
	 * 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.
	 */
	tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
}

/*
 *	switch_to(x,yn) 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
 * the wrong process. Lazy FP saving no longer makes any sense
 * with modern CPU's, and this simplifies a lot of things (SMP
 * and UP become the same).
 *
 * NOTE! We used to use the x86 hardware context switching. The
 * reason for not using it any more becomes apparent when you
 * try to recover gracefully from saved state that is no longer
 * valid (stale segment register values in particular). With the
 * hardware task-switch, there is no way to fix up bad state in
 * a reasonable manner.
 *
 * The fact that Intel documents the hardware task-switching to
 * be slow is a fairly red herring - this code is not noticeably
 * faster. However, there _is_ some room for improvement here,
 * so the performance issues may eventually be a valid point.
 * More important, however, is the fact that this allows us much
 * more flexibility.
 *
 * The return value (in %eax) will be the "prev" task after
 * the task-switch, and shows up in ret_from_fork in entry.S,
 * for example.
 */
struct task_struct fastcall * __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);

	/* 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);

	/*
	 * Reload esp0.
	 */
	load_esp0(tss, next);

	/*
	 * Save away %gs. No need to save %fs, as it was saved on the
	 * stack on entry.  No need to save %es and %ds, as those are
	 * always kernel segments while inside the kernel.  Doing this
	 * before setting the new TLS descriptors avoids the situation
	 * where we temporarily have non-reloadable segments in %fs
	 * and %gs.  This could be an issue if the NMI handler ever
	 * used %fs or %gs (it does not today), or if the kernel is
	 * running inside of a hypervisor layer.
	 */
	savesegment(gs, prev->gs);

	/*
	 * Load the per-thread Thread-Local Storage descriptor.
	 */
	load_TLS(next, cpu);

	/*
	 * Restore IOPL if needed.  In normal use, the flags restore
	 * in the switch assembly will handle this.  But if the kernel
	 * is running virtualized at a non-zero CPL, the popf will
	 * not restore flags, so it must be done in a separate step.
	 */
	if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
		set_iopl_mask(next->iopl);

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

	/*
	 * 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_leave_lazy_cpu_mode();

	/* 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();

	/*
	 * Restore %gs if needed (which is common)
	 */
	if (prev->gs | next->gs)
		loadsegment(gs, next->gs);

	x86_write_percpu(current_task, next_p);

	return prev_p;
}

asmlinkage int sys_fork(struct pt_regs regs)
{
	return do_fork(SIGCHLD, regs.esp, &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.ebx;
	newsp = regs.ecx;
	parent_tidptr = (int __user *)regs.edx;
	child_tidptr = (int __user *)regs.edi;
	if (!newsp)
		newsp = regs.esp;
	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.esp, &regs, 0, NULL, NULL);
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage int sys_execve(struct pt_regs regs)
{
	int error;
	char * filename;

	filename = getname((char __user *) regs.ebx);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;
	error = do_execve(filename,
			(char __user * __user *) regs.ecx,
			(char __user * __user *) regs.edx,
			&regs);
	if (error == 0) {
		task_lock(current);
		current->ptrace &= ~PT_DTRACE;
		task_unlock(current);
		/* Make sure we don't return using sysenter.. */
		set_thread_flag(TIF_IRET);
	}
	putname(filename);
out:
	return error;
}

#define top_esp                (THREAD_SIZE - sizeof(unsigned long))
#define top_ebp                (THREAD_SIZE - 2*sizeof(unsigned long))

unsigned long get_wchan(struct task_struct *p)
{
	unsigned long ebp, esp, eip;
	unsigned long stack_page;
	int count = 0;
	if (!p || p == current || p->state == TASK_RUNNING)
		return 0;
	stack_page = (unsigned long)task_stack_page(p);
	esp = p->thread.esp;
	if (!stack_page || esp < stack_page || esp > top_esp+stack_page)
		return 0;
	/* include/asm-i386/system.h:switch_to() pushes ebp last. */
	ebp = *(unsigned long *) esp;
	do {
		if (ebp < stack_page || ebp > top_ebp+stack_page)
			return 0;
		eip = *(unsigned long *) (ebp+4);
		if (!in_sched_functions(eip))
			return eip;
		ebp = *(unsigned long *) ebp;
	} while (count++ < 16);
	return 0;
}

/*
 * sys_alloc_thread_area: get a yet unused TLS descriptor index.
 */
static int get_free_idx(void)
{
	struct thread_struct *t = &current->thread;
	int idx;

	for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
		if (desc_empty(t->tls_array + idx))
			return idx + GDT_ENTRY_TLS_MIN;
	return -ESRCH;
}

/*
 * Set a given TLS descriptor:
 */
asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
{
	struct thread_struct *t = &current->thread;
	struct user_desc info;
	struct desc_struct *desc;
	int cpu, idx;

	if (copy_from_user(&info, u_info, sizeof(info)))
		return -EFAULT;
	idx = info.entry_number;

	/*
	 * index -1 means the kernel should try to find and
	 * allocate an empty descriptor:
	 */
	if (idx == -1) {
		idx = get_free_idx();
		if (idx < 0)
			return idx;
		if (put_user(idx, &u_info->entry_number))
			return -EFAULT;
	}

	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
		return -EINVAL;

	desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN;

	/*
	 * We must not get preempted while modifying the TLS.
	 */
	cpu = get_cpu();

	if (LDT_empty(&info)) {
		desc->a = 0;
		desc->b = 0;
	} else {
		desc->a = LDT_entry_a(&info);
		desc->b = LDT_entry_b(&info);
	}
	load_TLS(t, cpu);

	put_cpu();

	return 0;
}

/*
 * Get the current Thread-Local Storage area:
 */

#define GET_BASE(desc) ( \
	(((desc)->a >> 16) & 0x0000ffff) | \
	(((desc)->b << 16) & 0x00ff0000) | \
	( (desc)->b        & 0xff000000)   )

#define GET_LIMIT(desc) ( \
	((desc)->a & 0x0ffff) | \
	 ((desc)->b & 0xf0000) )
	
#define GET_32BIT(desc)		(((desc)->b >> 22) & 1)
#define GET_CONTENTS(desc)	(((desc)->b >> 10) & 3)
#define GET_WRITABLE(desc)	(((desc)->b >>  9) & 1)
#define GET_LIMIT_PAGES(desc)	(((desc)->b >> 23) & 1)
#define GET_PRESENT(desc)	(((desc)->b >> 15) & 1)
#define GET_USEABLE(desc)	(((desc)->b >> 20) & 1)

asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
{
	struct user_desc info;
	struct desc_struct *desc;
	int idx;

	if (get_user(idx, &u_info->entry_number))
		return -EFAULT;
	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
		return -EINVAL;

	memset(&info, 0, sizeof(info));

	desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;

	info.entry_number = idx;
	info.base_addr = GET_BASE(desc);
	info.limit = GET_LIMIT(desc);
	info.seg_32bit = GET_32BIT(desc);
	info.contents = GET_CONTENTS(desc);
	info.read_exec_only = !GET_WRITABLE(desc);
	info.limit_in_pages = GET_LIMIT_PAGES(desc);
	info.seg_not_present = !GET_PRESENT(desc);
	info.useable = GET_USEABLE(desc);

	if (copy_to_user(u_info, &info, sizeof(info)))
		return -EFAULT;
	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;
}