process.c

这个linux源代码是很全面的~基本完整了~使用c编译的~由于时间问题我没有亲自测试~但就算用来做参考资料也是非常好的

{
	struct task_struct *tsk = current;

	memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
	/*
	 * Forget coprocessor state..
	 */
	clear_fpu(tsk);
	tsk->used_math = 0;
}

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		void * ldt = dead_task->mm->context.segments;

		// temporary debugging check
		if (ldt) {
			printk("WARNING: dead process %8s still has LDT? <%p>\n",
					dead_task->comm, ldt);
			BUG();
		}
	}
}

/*
 * we do not have to muck with descriptors here, that is
 * done in switch_mm() as needed.
 */
void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
{
	struct mm_struct * old_mm;
	void *old_ldt, *ldt;
 
	ldt = NULL;
	old_mm = current->mm;
	if (old_mm && (old_ldt = old_mm->context.segments) != NULL) {
		/*
		 * Completely new LDT, we initialize it from the parent:
		 */
		ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE);
		if (!ldt)
			printk(KERN_WARNING "ldt allocation failed\n");
		else
			memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE);
	}
	new_mm->context.segments = ldt;
	new_mm->context.cpuvalid = 0UL;
	return;
}

int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, 
		unsigned long unused,
	struct task_struct * p, struct pt_regs * regs)
{
	struct pt_regs * childregs;
	struct task_struct *me = current;

	childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;

	*childregs = *regs;

	childregs->rax = 0;
	childregs->rsp = rsp;
	if (rsp == ~0) {
		childregs->rsp = (unsigned long)childregs;
	}

	p->thread.rsp = (unsigned long) childregs;
	p->thread.rsp0 = (unsigned long) (childregs+1);
	p->thread.userrsp = current->thread.userrsp; 

	p->thread.rip = (unsigned long) ret_from_fork;

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

	asm("movl %%gs,%0" : "=m" (p->thread.gsindex));
	asm("movl %%fs,%0" : "=m" (p->thread.fsindex));
	asm("movl %%es,%0" : "=m" (p->thread.es));
	asm("movl %%ds,%0" : "=m" (p->thread.ds));

	unlazy_fpu(current);	
	p->thread.i387 = current->thread.i387;

	if (unlikely(me->thread.io_bitmap_ptr != NULL)) { 
		p->thread.io_bitmap_ptr = kmalloc((IO_BITMAP_SIZE+1)*4, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) 
			return -ENOMEM;
		memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, 
		       (IO_BITMAP_SIZE+1)*4);
	} 

	return 0;
}

/*
 * This special macro can be used to load a debugging register
 */
#define loaddebug(thread,register) \
		set_debug(thread->debugreg[register], register)

/*
 *	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
 */
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;
	struct tss_struct *tss = init_tss + smp_processor_id();

	unlazy_fpu(prev_p);

	/*
	 * Reload rsp0, LDT and the page table pointer:
	 */
	tss->rsp0 = next->rsp0;

	/* 
	 * Switch DS and ES.	 
	 */
	asm volatile("movl %%es,%0" : "=m" (prev->es)); 
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es); 
	
	asm volatile ("movl %%ds,%0" : "=m" (prev->ds)); 
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);

	/* 
	 * Switch FS and GS.
	 */
	{ 
		unsigned fsindex;
		asm volatile("movl %%fs,%0" : "=g" (fsindex)); 
		/* 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 changed the selector
		   if yes clear 64bit base. */
		if (unlikely(fsindex != prev->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;
	}
	{
		unsigned gsindex;
		asm volatile("movl %%gs,%0" : "=g" (gsindex)); 
		if (unlikely((gsindex | next->gsindex) || prev->gs))
			load_gs_index(next->gsindex);
		if (unlikely(gsindex != prev->gsindex)) 
			prev->gs = 0;				
		if (next->gs)
			wrmsrl(MSR_KERNEL_GS_BASE, next->gs); 
		prev->gsindex = gsindex;
	}

	/* 
	 * Switch the PDA context.
	 */
	prev->userrsp = read_pda(oldrsp); 
	write_pda(oldrsp, next->userrsp); 
	write_pda(pcurrent, next_p); 
	write_pda(kernelstack, (unsigned long)next_p + THREAD_SIZE - PDA_STACKOFFSET);

	/*
	 * Now maybe reload the debug registers
	 */
	if (unlikely(next->debugreg[7])) {
		loaddebug(next, 0);
		loaddebug(next, 1);
		loaddebug(next, 2);
		loaddebug(next, 3);
		/* no 4 and 5 */
		loaddebug(next, 6);
		loaddebug(next, 7);
	}


	/* 
	 * Handle the IO bitmap 
	 */ 
	if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
		if (next->io_bitmap_ptr) {
			/*
			 * 4 cachelines copy ... not good, but not that
			 * bad either. Anyone got something better?
			 * This only affects processes which use ioperm().
			 * [Putting the TSSs into 4k-tlb mapped regions
			 * and playing VM tricks to switch the IO bitmap
			 * is not really acceptable.]
			 */
			memcpy(tss->io_bitmap, next->io_bitmap_ptr,
				 IO_BITMAP_SIZE*sizeof(u32));
			tss->io_map_base = IO_BITMAP_OFFSET;
		} else {
			/*
			 * a bitmap offset pointing outside of the TSS limit
			 * causes a nicely controllable SIGSEGV if a process
			 * tries to use a port IO instruction. The first
			 * sys_ioperm() call sets up the bitmap properly.
			 */
			tss->io_map_base = INVALID_IO_BITMAP_OFFSET;
		}
	}


	return prev_p;
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage 
long sys_execve(char *name, char **argv,char **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); 
	if (error == 0)
		current->ptrace &= ~PT_DTRACE;
	putname(filename);
	return error;
}

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

	/* Make sure to be in 64bit mode */
	current->thread.flags = 0;
}

asmlinkage long sys_fork(struct pt_regs regs)
{
	return do_fork(SIGCHLD, regs.rsp, &regs, 0, NULL);
}

asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, struct pt_regs regs)
{
	if (!newsp)
		newsp = regs.rsp;
	return do_fork(clone_flags, newsp, &regs, 0, NULL);
}

/*
 * 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 long sys_vfork(struct pt_regs regs)
{
	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.rsp, &regs, 0, NULL);
}

/*
 * These bracket the sleeping functions..
 */
extern void scheduling_functions_start_here(void);
extern void scheduling_functions_end_here(void);
#define first_sched	((unsigned long) scheduling_functions_start_here)
#define last_sched	((unsigned long) scheduling_functions_end_here)

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

	if (!p || p == current || p->state==TASK_RUNNING)
		return 0; 
	if (p->thread.rsp < (u64)p || p->thread.rsp > (u64)p + THREAD_SIZE)
		return 0;
	fp = *(u64 *)(p->thread.rsp);
	do { 
		if (fp < (unsigned long)p || fp > (unsigned long)p+THREAD_SIZE)
			return 0; 
		rip = *(u64 *)(fp+8); 
		if (rip < first_sched || rip >= last_sched)
			return rip; 
		fp = *(u64 *)fp; 
	} while (count++ < 16); 
	return 0;
}
#undef last_sched
#undef first_sched

asmlinkage long sys_arch_prctl(int code, unsigned long addr)
{ 
	int ret = 0; 
	unsigned long tmp; 

	switch (code) { 
	case ARCH_SET_GS:
#ifndef GS_SWITCH_WORKING
		/* Disabled for now because we still have one unexplained bug
		   in the context switch for this. */ 
		return -EINVAL; 
#else
		if (addr >= TASK_SIZE) 
			return -EPERM; 
		asm volatile("movw %%gs,%0" : "=g" (current->thread.gsindex)); 
		asm volatile("movl %0,%%gs" :: "r" (0)); 
		current->thread.gs = addr;
		ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); 
		break;
#endif
	case ARCH_SET_FS:
		/* Not strictly needed for fs, but do it for symmetry
		   with gs. */
		if (addr >= TASK_SIZE)
			return -EPERM; 
		asm volatile("movw %%fs,%0" : "=g" (current->thread.fsindex)); 
		asm volatile("movl %0,%%fs" :: "r" (0)); 
		current->thread.fs = addr;
		ret = checking_wrmsrl(MSR_FS_BASE, addr); 
		break;

		/* Returned value may not be correct when the user changed fs/gs */ 
	case ARCH_GET_FS:
		rdmsrl(MSR_FS_BASE, tmp);
		ret = put_user(tmp, (unsigned long *)addr); 
		break; 

	case ARCH_GET_GS: 
		rdmsrl(MSR_KERNEL_GS_BASE, tmp); 
		ret = put_user(tmp, (unsigned long *)addr); 
		break;

	default:
		ret = -EINVAL;
		break;
	} 
	return ret;	
}