process.c

优龙2410linux2.6.8内核源代码

	set_ti_thread_flag(p->thread_info, TIF_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));

	if (unlikely(me->thread.io_bitmap_ptr != NULL)) { 
		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) 
			return -ENOMEM;
		memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES);
	} 

	/*
	 * Set a new TLS for the child thread?
	 */
	if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
		if (test_thread_flag(TIF_IA32))
			err = ia32_child_tls(p, childregs); 
		else 			
#endif	 
			err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); 
		if (err) 
			goto out;
	}
	err = 0;
out:
	if (err && p->thread.io_bitmap_ptr)
		kfree(p->thread.io_bitmap_ptr);
	return err;
}

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

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

	unlazy_fpu(prev_p);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	tss->rsp0 = next->rsp0;

	/* 
	 * Switch DS and ES.
	 * This won't pick up thread selector changes, but I guess that is ok.
	 */
	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);

	load_TLS(next, cpu);

	/* 
	 * 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 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;
	}
	{ 
		unsigned gsindex;
		asm volatile("movl %%gs,%0" : "=g" (gsindex)); 
		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;
	}

	/* 
	 * 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_info + THREAD_SIZE - PDA_STACKOFFSET);

	/*
	 * Now maybe reload the debug registers
	 */
	if (unlikely(next->debugreg7)) {
		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) {
			/*
			 * 2 cachelines copy ... not good, but not that
			 * bad either. Anyone got something better?
			 * This only affects processes which use ioperm().
			 */
			memcpy(tss->io_bitmap, next->io_bitmap_ptr, IO_BITMAP_BYTES);
			tss->io_bitmap_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_bitmap_base = INVALID_IO_BITMAP_OFFSET;
		}
	}

	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); 
	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 */
	clear_thread_flag(TIF_IA32); 
}

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

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.rsp;
	return do_fork(clone_flags & ~CLONE_IDLETASK, newsp, &regs, 0, 
		    parent_tid, child_tid);
}

/*
 * 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, NULL);
}

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

	if (!p || p == current || p->state==TASK_RUNNING)
		return 0; 
	stack = (unsigned long)p->thread_info; 
	if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE)
		return 0;
	fp = *(u64 *)(p->thread.rsp);
	do { 
		if (fp < (unsigned long)stack || fp > (unsigned long)stack+THREAD_SIZE)
			return 0; 
		rip = *(u64 *)(fp+8); 
		if (!in_sched_functions(rip))
			return rip; 
		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) 
			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)
			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); 
				asm volatile("movl %0,%%fs" :: "r" (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 */
		asm volatile("movl %0,%%fs" :: "r" (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;
		if (task->thread.gsindex == GS_TLS_SEL)
			base = read_32bit_tls(task, GS_TLS);
		else if (doit) {
			rdmsrl(MSR_KERNEL_GS_BASE, base);
		} 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);
} 

/* 
 * 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 *pp, ptregs;

	pp = (struct pt_regs *)(tsk->thread.rsp0);
	--pp; 

	ptregs = *pp; 
	ptregs.cs &= 0xffff;
	ptregs.ss &= 0xffff;

	elf_core_copy_regs(regs, &ptregs);
 
	return 1;
}