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

__asm__(".align 4\n"
	"kernel_thread_helper:\n\t"
	"movl %edx,%eax\n\t"
	"pushl %edx\n\t"
	"call *%ebx\n\t"
	"pushl %eax\n\t"
	"call do_exit");

/*
 * Create a kernel thread
 */
int arch_kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
{
	struct task_struct *p;
	struct pt_regs regs;

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

	regs.ebx = (unsigned long) fn;
	regs.edx = (unsigned long) arg;

	regs.xds = __KERNEL_DS;
	regs.xes = __KERNEL_DS;
	regs.orig_eax = -1;
	regs.eip = (unsigned long) kernel_thread_helper;
	regs.xcs = __KERNEL_CS;
	regs.eflags = 0x286;

	/* Ok, create the new process.. */
	p = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
	return IS_ERR(p) ? PTR_ERR(p) : p->pid;
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	/* nothing to do ... */
}

void flush_thread(void)
{
	struct task_struct *tsk = current;

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

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		// temporary debugging check
		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();
		}
	}
}

/*
 * Save a segment.
 */
#define savesegment(seg,value) \
	asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))

int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
	unsigned long unused,
	struct task_struct * p, struct pt_regs * regs)
{
	struct pt_regs * childregs;
	struct task_struct *tsk;

	childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
	struct_cpy(childregs, regs);
	childregs->eax = 0;
	childregs->esp = esp;
	p->set_child_tid = p->clear_child_tid = NULL;

	p->thread.esp = (unsigned long) childregs;
	p->thread.esp0 = (unsigned long) (childregs+1);

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

	savesegment(fs,p->thread.fs);
	savesegment(gs,p->thread.gs);

	tsk = current;
	unlazy_fpu(tsk);
	struct_cpy(&p->thread.i387, &tsk->thread.i387);

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

		if (copy_from_user(&info, (void *)childregs->esi, sizeof(info)))
			return -EFAULT;
		if (LDT_empty(&info))
			return -EINVAL;

		idx = info.entry_number;
		if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
			return -EINVAL;

		desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
		desc->a = LDT_entry_a(&info);
		desc->b = LDT_entry_b(&info);
	}
	return 0;
}

/*
 * 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;
	savesegment(fs,dump->regs.fs);
	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);
}

/* 
 * 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;
	
	ptregs = *(struct pt_regs *)((unsigned long)tsk + THREAD_SIZE - sizeof(struct pt_regs));

	ptregs.xcs &= 0xffff;
	ptregs.xds &= 0xffff;
	ptregs.xes &= 0xffff;
	ptregs.xss &= 0xffff;

	elf_core_copy_regs(regs, &ptregs);

	return 1;
}

/*
 * This special macro can be used to load a debugging register
 */
#define loaddebug(thread,register) \
		__asm__("movl %0,%%db" #register  \
			: /* no output */ \
			:"r" (thread->debugreg[register]))

/*
 *	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.
 */
void __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 = init_tss + cpu;

	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */

	unlazy_fpu(prev_p);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	tss->esp0 = next->esp0;

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

	/*
	 * Save away %fs and %gs. No need to save %es and %ds, as
	 * those are always kernel segments while inside the kernel.
	 */
	asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
	asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));

	/*
	 * Restore %fs and %gs if needed.
	 */
	if (unlikely(prev->fs | prev->gs | next->fs | next->gs)) {
		loadsegment(fs, next->fs);
		loadsegment(gs, next->gs);
	}

	/*
	 * 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);
	}

	if (unlikely(prev->ioperm || next->ioperm)) {
		if (next->ioperm) {
			/*
			 * 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,
				 IO_BITMAP_SIZE*sizeof(unsigned long));
			tss->bitmap = 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->bitmap = INVALID_IO_BITMAP_OFFSET;
	}
}

asmlinkage int sys_fork(struct pt_regs regs)
{
	struct task_struct *p;

	p = do_fork(SIGCHLD, regs.esp, &regs, 0, NULL, NULL);
	return IS_ERR(p) ? PTR_ERR(p) : p->pid;
}

asmlinkage int sys_clone(struct pt_regs regs)
{
	struct task_struct *p;
	unsigned long clone_flags;
	unsigned long newsp;
	int *parent_tidptr, *child_tidptr;

	clone_flags = regs.ebx;
	newsp = regs.ecx;
	parent_tidptr = (int *)regs.edx;
	child_tidptr = (int *)regs.edi;
	if (!newsp)
		newsp = regs.esp;
	p = do_fork(clone_flags & ~CLONE_IDLETASK, newsp, &regs, 0, parent_tidptr, child_tidptr);
	return IS_ERR(p) ? PTR_ERR(p) : p->pid;
}

/*
 * 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)
{
	struct task_struct *p;

	p = do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, &regs, 0, NULL, NULL);
	return IS_ERR(p) ? PTR_ERR(p) : p->pid;
}

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

	filename = getname((char *) regs.ebx);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;
	error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, &regs);
	if (error == 0)
		current->ptrace &= ~PT_DTRACE;
	putname(filename);
out:
	return error;
}

/*
 * 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)
{
	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)p;
	esp = p->thread.esp;
	if (!stack_page || esp < stack_page || esp > 8188+stack_page)
		return 0;
	/* include/asm-i386/system.h:switch_to() pushes ebp last. */
	ebp = *(unsigned long *) esp;
	do {
		if (ebp < stack_page || ebp > 8184+stack_page)
			return 0;
		eip = *(unsigned long *) (ebp+4);
		if (eip < first_sched || eip >= last_sched)
			return eip;
		ebp = *(unsigned long *) ebp;
	} while (count++ < 16);
	return 0;
}
#undef last_sched
#undef first_sched

/*
 * 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 *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;

	cpu = smp_processor_id();

	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);


	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 >> 23) & 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 *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;

	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;
}