exec.c

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

		if (i >= files->max_fds || i >= files->max_fdset)
			break;
		set = files->close_on_exec->fds_bits[j];
		if (!set)
			continue;
		files->close_on_exec->fds_bits[j] = 0;
		write_unlock(&files->file_lock);
		for ( ; set ; i++,set >>= 1) {
			if (set & 1) {
				sys_close(i);
			}
		}
		write_lock(&files->file_lock);

	}
	write_unlock(&files->file_lock);
}

/*
 * An execve() will automatically "de-thread" the process.
 * Note: we don't have to hold the tasklist_lock to test
 * whether we migth need to do this. If we're not part of
 * a thread group, there is no way we can become one
 * dynamically. And if we are, we only need to protect the
 * unlink - even if we race with the last other thread exit,
 * at worst the list_del_init() might end up being a no-op.
 */
static inline void de_thread(struct task_struct *tsk)
{
	if (!list_empty(&tsk->thread_group)) {
		write_lock_irq(&tasklist_lock);
		list_del_init(&tsk->thread_group);
		write_unlock_irq(&tasklist_lock);
	}

	/* Minor oddity: this might stay the same. */
	tsk->tgid = tsk->pid;
}

int flush_old_exec(struct linux_binprm * bprm)
{
	char * name;
	int i, ch, retval;
	struct signal_struct * oldsig;

	/*
	 * Make sure we have a private signal table
	 */
	oldsig = current->sig;
	retval = make_private_signals();
	if (retval) goto flush_failed;

	/* 
	 * Release all of the old mmap stuff
	 */
	retval = exec_mmap();
	if (retval) goto mmap_failed;

	/* This is the point of no return */
	release_old_signals(oldsig);

	current->sas_ss_sp = current->sas_ss_size = 0;

	if (current->euid == current->uid && current->egid == current->gid)
		current->dumpable = 1;
	name = bprm->filename;
	for (i=0; (ch = *(name++)) != '\0';) {
		if (ch == '/')
			i = 0;
		else
			if (i < 15)
				current->comm[i++] = ch;
	}
	current->comm[i] = '\0';

	flush_thread();

	de_thread(current);

	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || 
	    permission(bprm->file->f_dentry->d_inode,MAY_READ))
		current->dumpable = 0;

	/* An exec changes our domain. We are no longer part of the thread
	   group */
	   
	current->self_exec_id++;
			
	flush_signal_handlers(current);
	flush_old_files(current->files);

	return 0;

mmap_failed:
flush_failed:
	spin_lock_irq(&current->sigmask_lock);
	if (current->sig != oldsig)
		kfree(current->sig);
	current->sig = oldsig;
	spin_unlock_irq(&current->sigmask_lock);
	return retval;
}

/*
 * We mustn't allow tracing of suid binaries, unless
 * the tracer has the capability to trace anything..
 */
static inline int must_not_trace_exec(struct task_struct * p)
{
	return (p->ptrace & PT_PTRACED) && !cap_raised(p->p_pptr->cap_effective, CAP_SYS_PTRACE);
}

/* 
 * Fill the binprm structure from the inode. 
 * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
 */
int prepare_binprm(struct linux_binprm *bprm)
{
	int mode;
	struct inode * inode = bprm->file->f_dentry->d_inode;

	mode = inode->i_mode;
	/* Huh? We had already checked for MAY_EXEC, WTF do we check this? */
	if (!(mode & 0111))	/* with at least _one_ execute bit set */
		return -EACCES;
	if (bprm->file->f_op == NULL)
		return -EACCES;

	bprm->e_uid = current->euid;
	bprm->e_gid = current->egid;

	if(!IS_NOSUID(inode)) {
		/* Set-uid? */
		if (mode & S_ISUID)
			bprm->e_uid = inode->i_uid;

		/* Set-gid? */
		/*
		 * If setgid is set but no group execute bit then this
		 * is a candidate for mandatory locking, not a setgid
		 * executable.
		 */
		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
			bprm->e_gid = inode->i_gid;
	}

	/* We don't have VFS support for capabilities yet */
	cap_clear(bprm->cap_inheritable);
	cap_clear(bprm->cap_permitted);
	cap_clear(bprm->cap_effective);

	/*  To support inheritance of root-permissions and suid-root
         *  executables under compatibility mode, we raise all three
         *  capability sets for the file.
         *
         *  If only the real uid is 0, we only raise the inheritable
         *  and permitted sets of the executable file.
         */

	if (!issecure(SECURE_NOROOT)) {
		if (bprm->e_uid == 0 || current->uid == 0) {
			cap_set_full(bprm->cap_inheritable);
			cap_set_full(bprm->cap_permitted);
		}
		if (bprm->e_uid == 0) 
			cap_set_full(bprm->cap_effective);
	}

	memset(bprm->buf,0,BINPRM_BUF_SIZE);
	return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
}

/*
 * This function is used to produce the new IDs and capabilities
 * from the old ones and the file's capabilities.
 *
 * The formula used for evolving capabilities is:
 *
 *       pI' = pI
 * (***) pP' = (fP & X) | (fI & pI)
 *       pE' = pP' & fE          [NB. fE is 0 or ~0]
 *
 * I=Inheritable, P=Permitted, E=Effective // p=process, f=file
 * ' indicates post-exec(), and X is the global 'cap_bset'.
 *
 */

void compute_creds(struct linux_binprm *bprm) 
{
	kernel_cap_t new_permitted, working;
	int do_unlock = 0;

	new_permitted = cap_intersect(bprm->cap_permitted, cap_bset);
	working = cap_intersect(bprm->cap_inheritable,
				current->cap_inheritable);
	new_permitted = cap_combine(new_permitted, working);

	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
	    !cap_issubset(new_permitted, current->cap_permitted)) {
                current->dumpable = 0;
		
		lock_kernel();
		if (must_not_trace_exec(current)
		    || atomic_read(&current->fs->count) > 1
		    || atomic_read(&current->files->count) > 1
		    || atomic_read(&current->sig->count) > 1) {
			if(!capable(CAP_SETUID)) {
				bprm->e_uid = current->uid;
				bprm->e_gid = current->gid;
			}
			if(!capable(CAP_SETPCAP)) {
				new_permitted = cap_intersect(new_permitted,
							current->cap_permitted);
			}
		}
		do_unlock = 1;
	}


	/* For init, we want to retain the capabilities set
         * in the init_task struct. Thus we skip the usual
         * capability rules */
	if (current->pid != 1) {
		current->cap_permitted = new_permitted;
		current->cap_effective =
			cap_intersect(new_permitted, bprm->cap_effective);
	}
	
        /* AUD: Audit candidate if current->cap_effective is set */

        current->suid = current->euid = current->fsuid = bprm->e_uid;
        current->sgid = current->egid = current->fsgid = bprm->e_gid;

	if(do_unlock)
		unlock_kernel();
	current->keep_capabilities = 0;
}


void remove_arg_zero(struct linux_binprm *bprm)
{
	if (bprm->argc) {
		unsigned long offset;
		char * kaddr;
		struct page *page;

		offset = bprm->p % PAGE_SIZE;
		goto inside;

		while (bprm->p++, *(kaddr+offset++)) {
			if (offset != PAGE_SIZE)
				continue;
			offset = 0;
			kunmap(page);
inside:
			page = bprm->page[bprm->p/PAGE_SIZE];
			kaddr = kmap(page);
		}
		kunmap(page);
		bprm->argc--;
	}
}

/*
 * cycle the list of binary formats handler, until one recognizes the image
 */
int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
{
	int try,retval=0;
	struct linux_binfmt *fmt;
#ifdef __alpha__
	/* handle /sbin/loader.. */
	{
	    struct exec * eh = (struct exec *) bprm->buf;

	    if (!bprm->loader && eh->fh.f_magic == 0x183 &&
		(eh->fh.f_flags & 0x3000) == 0x3000)
	    {
		char * dynloader[] = { "/sbin/loader" };
		struct file * file;
		unsigned long loader;

		allow_write_access(bprm->file);
		fput(bprm->file);
		bprm->file = NULL;

	        loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);

		file = open_exec(dynloader[0]);
		retval = PTR_ERR(file);
		if (IS_ERR(file))
			return retval;
		bprm->file = file;
		bprm->loader = loader;
		retval = prepare_binprm(bprm);
		if (retval<0)
			return retval;
		/* should call search_binary_handler recursively here,
		   but it does not matter */
	    }
	}
#endif
	for (try=0; try<2; try++) {
		read_lock(&binfmt_lock);
		for (fmt = formats ; fmt ; fmt = fmt->next) {
			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
			if (!fn)
				continue;
			if (!try_inc_mod_count(fmt->module))
				continue;
			read_unlock(&binfmt_lock);
			retval = fn(bprm, regs);
			if (retval >= 0) {
				put_binfmt(fmt);
				allow_write_access(bprm->file);
				if (bprm->file)
					fput(bprm->file);
				bprm->file = NULL;
				current->did_exec = 1;
				return retval;
			}
			read_lock(&binfmt_lock);
			put_binfmt(fmt);
			if (retval != -ENOEXEC)
				break;
			if (!bprm->file) {
				read_unlock(&binfmt_lock);
				return retval;
			}
		}
		read_unlock(&binfmt_lock);
		if (retval != -ENOEXEC) {
			break;
#ifdef CONFIG_KMOD
		}else{
#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
			char modname[20];
			if (printable(bprm->buf[0]) &&
			    printable(bprm->buf[1]) &&
			    printable(bprm->buf[2]) &&
			    printable(bprm->buf[3]))
				break; /* -ENOEXEC */
			sprintf(modname, "binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
			request_module(modname);
#endif
		}
	}
	return retval;
}


/*
 * sys_execve() executes a new program.
 */
int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs)
{
	struct linux_binprm bprm;
	struct file *file;
	int retval;
	int i;

	file = open_exec(filename);

	retval = PTR_ERR(file);
	if (IS_ERR(file))
		return retval;

	bprm.p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
	memset(bprm.page, 0, MAX_ARG_PAGES*sizeof(bprm.page[0])); 

	bprm.file = file;
	bprm.filename = filename;
	bprm.sh_bang = 0;
	bprm.loader = 0;
	bprm.exec = 0;
	if ((bprm.argc = count(argv, bprm.p / sizeof(void *))) < 0) {
		allow_write_access(file);
		fput(file);
		return bprm.argc;
	}

	if ((bprm.envc = count(envp, bprm.p / sizeof(void *))) < 0) {
		allow_write_access(file);
		fput(file);
		return bprm.envc;
	}

	retval = prepare_binprm(&bprm);
	if (retval < 0) 
		goto out; 

	retval = copy_strings_kernel(1, &bprm.filename, &bprm);
	if (retval < 0) 
		goto out; 

	bprm.exec = bprm.p;
	retval = copy_strings(bprm.envc, envp, &bprm);
	if (retval < 0) 
		goto out; 

	retval = copy_strings(bprm.argc, argv, &bprm);
	if (retval < 0) 
		goto out; 

	retval = search_binary_handler(&bprm,regs);
	if (retval >= 0)
		/* execve success */
		return retval;

out:
	/* Something went wrong, return the inode and free the argument pages*/
	allow_write_access(bprm.file);
	if (bprm.file)
		fput(bprm.file);

	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
		struct page * page = bprm.page[i];
		if (page)
			__free_page(page);
	}

	return retval;
}

void set_binfmt(struct linux_binfmt *new)
{
	struct linux_binfmt *old = current->binfmt;
	if (new && new->module)
		__MOD_INC_USE_COUNT(new->module);
	current->binfmt = new;
	if (old && old->module)
		__MOD_DEC_USE_COUNT(old->module);
}

int do_coredump(long signr, struct pt_regs * regs)
{
	struct linux_binfmt * binfmt;
	char corename[6+sizeof(current->comm)];
	struct file * file;
	struct inode * inode;

	lock_kernel();
	binfmt = current->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	if (!current->dumpable || atomic_read(&current->mm->mm_users) != 1)
		goto fail;
	current->dumpable = 0;
	if (current->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
		goto fail;

	memcpy(corename,"core.", 5);
#if 0
	memcpy(corename+5,current->comm,sizeof(current->comm));
#else
	corename[4] = '\0';
#endif
	file = filp_open(corename, O_CREAT | 2 | O_TRUNC | O_NOFOLLOW, 0600);
	if (IS_ERR(file))
		goto fail;
	inode = file->f_dentry->d_inode;
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */

	if (!S_ISREG(inode->i_mode))
		goto close_fail;
	if (!file->f_op)
		goto close_fail;
	if (!file->f_op->write)
		goto close_fail;
	if (!binfmt->core_dump(signr, regs, file))
		goto close_fail;
	unlock_kernel();
	filp_close(file, NULL);
	return 1;

close_fail:
	filp_close(file, NULL);
fail:
	unlock_kernel();
	return 0;
}