Skip to content
Snippets Groups Projects
exec.c 45.2 KiB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
	/* This is the point of no return */
	current->sas_ss_sp = current->sas_ss_size = 0;

	if (current_euid() == current_uid() && current_egid() == current_gid())
Alan Cox's avatar
Alan Cox committed
	else
		set_dumpable(current->mm, suid_dumpable);
Linus Torvalds's avatar
Linus Torvalds committed
	name = bprm->filename;

	/* Copies the binary name from after last slash */
Linus Torvalds's avatar
Linus Torvalds committed
	for (i=0; (ch = *(name++)) != '\0';) {
		if (ch == '/')
			i = 0; /* overwrite what we wrote */
Linus Torvalds's avatar
Linus Torvalds committed
		else
			if (i < (sizeof(tcomm) - 1))
				tcomm[i++] = ch;
	}
	tcomm[i] = '\0';
	set_task_comm(current, tcomm);

	/* Set the new mm task size. We have to do that late because it may
	 * depend on TIF_32BIT which is only updated in flush_thread() on
	 * some architectures like powerpc
	 */
	current->mm->task_size = TASK_SIZE;

	/* install the new credentials */
	if (bprm->cred->uid != current_euid() ||
	    bprm->cred->gid != current_egid()) {
		current->pdeath_signal = 0;
	} else if (file_permission(bprm->file, MAY_READ) ||
		   bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) {
		set_dumpable(current->mm, suid_dumpable);
	/*
	 * Flush performance counters when crossing a
	 * security domain:
	 */
	if (!get_dumpable(current->mm))
Linus Torvalds's avatar
Linus Torvalds committed
	/* An exec changes our domain. We are no longer part of the thread
	   group */

	current->self_exec_id++;
			
	flush_signal_handlers(current, 0);
	flush_old_files(current->files);
}
EXPORT_SYMBOL(setup_new_exec);
Linus Torvalds's avatar
Linus Torvalds committed

/*
 * Prepare credentials and lock ->cred_guard_mutex.
 * install_exec_creds() commits the new creds and drops the lock.
 * Or, if exec fails before, free_bprm() should release ->cred and
 * and unlock.
 */
int prepare_bprm_creds(struct linux_binprm *bprm)
{
	if (mutex_lock_interruptible(&current->cred_guard_mutex))
		return -ERESTARTNOINTR;

	bprm->cred = prepare_exec_creds();
	if (likely(bprm->cred))
		return 0;

	mutex_unlock(&current->cred_guard_mutex);
	return -ENOMEM;
}

void free_bprm(struct linux_binprm *bprm)
{
	free_arg_pages(bprm);
	if (bprm->cred) {
		mutex_unlock(&current->cred_guard_mutex);
		abort_creds(bprm->cred);
	}
	kfree(bprm);
}

/*
 * install the new credentials for this executable
 */
void install_exec_creds(struct linux_binprm *bprm)
{
	security_bprm_committing_creds(bprm);

	commit_creds(bprm->cred);
	bprm->cred = NULL;
	/*
	 * cred_guard_mutex must be held at least to this point to prevent
	 * ptrace_attach() from altering our determination of the task's
	 * credentials; any time after this it may be unlocked.
	 */
	security_bprm_committed_creds(bprm);
	mutex_unlock(&current->cred_guard_mutex);
}
EXPORT_SYMBOL(install_exec_creds);

/*
 * determine how safe it is to execute the proposed program
 * - the caller must hold current->cred_guard_mutex to protect against
int check_unsafe_exec(struct linux_binprm *bprm)
	struct task_struct *p = current, *t;
	int res = 0;

	bprm->unsafe = tracehook_unsafe_exec(p);

	n_fs = 1;
	write_lock(&p->fs->lock);
	for (t = next_thread(p); t != p; t = next_thread(t)) {
		if (t->fs == p->fs)
			n_fs++;
	}
	if (p->fs->users > n_fs) {
		bprm->unsafe |= LSM_UNSAFE_SHARE;
	} else {
		res = -EAGAIN;
		if (!p->fs->in_exec) {
			p->fs->in_exec = 1;
			res = 1;
		}
	}
	write_unlock(&p->fs->lock);

	return res;
Linus Torvalds's avatar
Linus Torvalds committed
/* 
 * Fill the binprm structure from the inode. 
 * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
 *
 * This may be called multiple times for binary chains (scripts for example).
Linus Torvalds's avatar
Linus Torvalds committed
 */
int prepare_binprm(struct linux_binprm *bprm)
{
	struct inode * inode = bprm->file->f_path.dentry->d_inode;
Linus Torvalds's avatar
Linus Torvalds committed
	int retval;

	mode = inode->i_mode;
	if (bprm->file->f_op == NULL)
		return -EACCES;

	/* clear any previous set[ug]id data from a previous binary */
	bprm->cred->euid = current_euid();
	bprm->cred->egid = current_egid();
Linus Torvalds's avatar
Linus Torvalds committed

	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
Linus Torvalds's avatar
Linus Torvalds committed
		/* Set-uid? */
		if (mode & S_ISUID) {
			bprm->per_clear |= PER_CLEAR_ON_SETID;
			bprm->cred->euid = inode->i_uid;
Linus Torvalds's avatar
Linus Torvalds committed
		}

		/* 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->per_clear |= PER_CLEAR_ON_SETID;
			bprm->cred->egid = inode->i_gid;
Linus Torvalds's avatar
Linus Torvalds committed
		}
	}

	/* fill in binprm security blob */
	retval = security_bprm_set_creds(bprm);
Linus Torvalds's avatar
Linus Torvalds committed
	if (retval)
		return retval;
Linus Torvalds's avatar
Linus Torvalds committed

	memset(bprm->buf, 0, BINPRM_BUF_SIZE);
	return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
Linus Torvalds's avatar
Linus Torvalds committed
}

EXPORT_SYMBOL(prepare_binprm);

/*
 * Arguments are '\0' separated strings found at the location bprm->p
 * points to; chop off the first by relocating brpm->p to right after
 * the first '\0' encountered.
 */
int remove_arg_zero(struct linux_binprm *bprm)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int ret = 0;
	unsigned long offset;
	char *kaddr;
	struct page *page;
	if (!bprm->argc)
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	do {
		offset = bprm->p & ~PAGE_MASK;
		page = get_arg_page(bprm, bprm->p, 0);
		if (!page) {
			ret = -EFAULT;
			goto out;
		}
		kaddr = kmap_atomic(page, KM_USER0);
		for (; offset < PAGE_SIZE && kaddr[offset];
				offset++, bprm->p++)
			;
		kunmap_atomic(kaddr, KM_USER0);
		put_arg_page(page);
		if (offset == PAGE_SIZE)
			free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
	} while (offset == PAGE_SIZE);
	bprm->p++;
	bprm->argc--;
	ret = 0;
out:
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(remove_arg_zero);

/*
 * cycle the list of binary formats handler, until one recognizes the image
 */
int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
{
	unsigned int depth = bprm->recursion_depth;
Linus Torvalds's avatar
Linus Torvalds committed
	int try,retval;
	struct linux_binfmt *fmt;

	retval = security_bprm_check(bprm);
	if (retval)
		return retval;

	/* kernel module loader fixup */
	/* so we don't try to load run modprobe in kernel space. */
	set_fs(USER_DS);
Al Viro's avatar
Al Viro committed

	retval = audit_bprm(bprm);
	if (retval)
		return retval;

Linus Torvalds's avatar
Linus Torvalds committed
	retval = -ENOENT;
	for (try=0; try<2; try++) {
		read_lock(&binfmt_lock);
		list_for_each_entry(fmt, &formats, lh) {
Linus Torvalds's avatar
Linus Torvalds committed
			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
			if (!fn)
				continue;
			if (!try_module_get(fmt->module))
				continue;
			read_unlock(&binfmt_lock);
			retval = fn(bprm, regs);
			/*
			 * Restore the depth counter to its starting value
			 * in this call, so we don't have to rely on every
			 * load_binary function to restore it on return.
			 */
			bprm->recursion_depth = depth;
Linus Torvalds's avatar
Linus Torvalds committed
			if (retval >= 0) {
				if (depth == 0)
					tracehook_report_exec(fmt, bprm, regs);
Linus Torvalds's avatar
Linus Torvalds committed
				put_binfmt(fmt);
				allow_write_access(bprm->file);
				if (bprm->file)
					fput(bprm->file);
				bprm->file = NULL;
				current->did_exec = 1;
				proc_exec_connector(current);
Linus Torvalds's avatar
Linus Torvalds committed
				return retval;
			}
			read_lock(&binfmt_lock);
			put_binfmt(fmt);
			if (retval != -ENOEXEC || bprm->mm == NULL)
				break;
			if (!bprm->file) {
				read_unlock(&binfmt_lock);
				return retval;
			}
		}
		read_unlock(&binfmt_lock);
		if (retval != -ENOEXEC || bprm->mm == NULL) {
			break;
#ifdef CONFIG_MODULES
		} else {
Linus Torvalds's avatar
Linus Torvalds committed
#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
			if (printable(bprm->buf[0]) &&
			    printable(bprm->buf[1]) &&
			    printable(bprm->buf[2]) &&
			    printable(bprm->buf[3]))
				break; /* -ENOEXEC */
			request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
#endif
		}
	}
	return retval;
}

EXPORT_SYMBOL(search_binary_handler);

/*
 * sys_execve() executes a new program.
 */
int do_execve(char * filename,
	char __user *__user *argv,
	char __user *__user *envp,
	struct pt_regs * regs)
{
	struct linux_binprm *bprm;
	struct file *file;
	struct files_struct *displaced;
Linus Torvalds's avatar
Linus Torvalds committed
	int retval;

	retval = unshare_files(&displaced);
Linus Torvalds's avatar
Linus Torvalds committed
	retval = -ENOMEM;
	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!bprm)
Linus Torvalds's avatar
Linus Torvalds committed

	retval = prepare_bprm_creds(bprm);
	if (retval)

	retval = check_unsafe_exec(bprm);
Linus Torvalds's avatar
Linus Torvalds committed
	file = open_exec(filename);
	retval = PTR_ERR(file);
	if (IS_ERR(file))
		goto out_unmark;
Linus Torvalds's avatar
Linus Torvalds committed

	sched_exec();

	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;

	retval = bprm_mm_init(bprm);
	if (retval)
		goto out_file;
Linus Torvalds's avatar
Linus Torvalds committed

	bprm->argc = count(argv, MAX_ARG_STRINGS);
Linus Torvalds's avatar
Linus Torvalds committed
	if ((retval = bprm->argc) < 0)
Linus Torvalds's avatar
Linus Torvalds committed

	bprm->envc = count(envp, MAX_ARG_STRINGS);
Linus Torvalds's avatar
Linus Torvalds committed
	if ((retval = bprm->envc) < 0)
		goto out;

	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;

Oleg Nesterov's avatar
Oleg Nesterov committed
	current->flags &= ~PF_KTHREAD;
Linus Torvalds's avatar
Linus Torvalds committed
	retval = search_binary_handler(bprm,regs);
Linus Torvalds's avatar
Linus Torvalds committed

	current->stack_start = current->mm->start_stack;

	current->fs->in_exec = 0;
	current->in_execve = 0;
	acct_update_integrals(current);
	free_bprm(bprm);
	if (displaced)
		put_files_struct(displaced);
	return retval;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	if (bprm->mm)
		mmput (bprm->mm);
Linus Torvalds's avatar
Linus Torvalds committed

out_file:
	if (bprm->file) {
		allow_write_access(bprm->file);
		fput(bprm->file);
	}
out_unmark:
	if (clear_in_exec)
		current->fs->in_exec = 0;
	current->in_execve = 0;
	free_bprm(bprm);
Linus Torvalds's avatar
Linus Torvalds committed

	if (displaced)
		reset_files_struct(displaced);
Linus Torvalds's avatar
Linus Torvalds committed
out_ret:
	return retval;
}

void set_binfmt(struct linux_binfmt *new)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct mm_struct *mm = current->mm;

	if (mm->binfmt)
		module_put(mm->binfmt->module);
Linus Torvalds's avatar
Linus Torvalds committed

	if (new)
		__module_get(new->module);
Linus Torvalds's avatar
Linus Torvalds committed
}

EXPORT_SYMBOL(set_binfmt);

/* format_corename will inspect the pattern parameter, and output a
 * name into corename, which must have space for at least
 * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
 */
static int format_corename(char *corename, long signr)
Linus Torvalds's avatar
Linus Torvalds committed
{
	const struct cred *cred = current_cred();
	const char *pat_ptr = core_pattern;
	int ispipe = (*pat_ptr == '|');
Linus Torvalds's avatar
Linus Torvalds committed
	char *out_ptr = corename;
	char *const out_end = corename + CORENAME_MAX_SIZE;
	int rc;
	int pid_in_pattern = 0;

	/* Repeat as long as we have more pattern to process and more output
	   space */
	while (*pat_ptr) {
		if (*pat_ptr != '%') {
			if (out_ptr == out_end)
				goto out;
			*out_ptr++ = *pat_ptr++;
		} else {
			switch (*++pat_ptr) {
			case 0:
				goto out;
			/* Double percent, output one percent */
			case '%':
				if (out_ptr == out_end)
					goto out;
				*out_ptr++ = '%';
				break;
			/* pid */
			case 'p':
				pid_in_pattern = 1;
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", task_tgid_vnr(current));
Linus Torvalds's avatar
Linus Torvalds committed
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* uid */
			case 'u':
				rc = snprintf(out_ptr, out_end - out_ptr,
Linus Torvalds's avatar
Linus Torvalds committed
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* gid */
			case 'g':
				rc = snprintf(out_ptr, out_end - out_ptr,
Linus Torvalds's avatar
Linus Torvalds committed
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* signal that caused the coredump */
			case 's':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%ld", signr);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* UNIX time of coredump */
			case 't': {
				struct timeval tv;
				do_gettimeofday(&tv);
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", tv.tv_sec);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			}
			/* hostname */
			case 'h':
				down_read(&uts_sem);
				rc = snprintf(out_ptr, out_end - out_ptr,
Linus Torvalds's avatar
Linus Torvalds committed
				up_read(&uts_sem);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* executable */
			case 'e':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%s", current->comm);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* core limit size */
			case 'c':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
Linus Torvalds's avatar
Linus Torvalds committed
			default:
				break;
			}
			++pat_ptr;
		}
	}
	/* Backward compatibility with core_uses_pid:
	 *
	 * If core_pattern does not include a %p (as is the default)
	 * and core_uses_pid is set, then .%pid will be appended to
	 * the filename. Do not do this for piped commands. */
	if (!ispipe && !pid_in_pattern && core_uses_pid) {
Linus Torvalds's avatar
Linus Torvalds committed
		rc = snprintf(out_ptr, out_end - out_ptr,
			      ".%d", task_tgid_vnr(current));
Linus Torvalds's avatar
Linus Torvalds committed
		if (rc > out_end - out_ptr)
			goto out;
		out_ptr += rc;
	}
Linus Torvalds's avatar
Linus Torvalds committed
	*out_ptr = 0;
static int zap_process(struct task_struct *start)
{
	struct task_struct *t;
	start->signal->flags = SIGNAL_GROUP_EXIT;
	start->signal->group_stop_count = 0;

	t = start;
	do {
		if (t != current && t->mm) {
			sigaddset(&t->pending.signal, SIGKILL);
			signal_wake_up(t, 1);
	} while_each_thread(start, t);
static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
				struct core_state *core_state, int exit_code)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct task_struct *g, *p;
	unsigned long flags;

	spin_lock_irq(&tsk->sighand->siglock);
	if (!signal_group_exit(tsk->signal)) {
		mm->core_state = core_state;
		tsk->signal->group_exit_code = exit_code;
Linus Torvalds's avatar
Linus Torvalds committed
	}
	spin_unlock_irq(&tsk->sighand->siglock);
	if (unlikely(nr < 0))
		return nr;
Linus Torvalds's avatar
Linus Torvalds committed

	if (atomic_read(&mm->mm_users) == nr + 1)
	/*
	 * We should find and kill all tasks which use this mm, and we should
	 * count them correctly into ->nr_threads. We don't take tasklist
	 * lock, but this is safe wrt:
	 *
	 * fork:
	 *	None of sub-threads can fork after zap_process(leader). All
	 *	processes which were created before this point should be
	 *	visible to zap_threads() because copy_process() adds the new
	 *	process to the tail of init_task.tasks list, and lock/unlock
	 *	of ->siglock provides a memory barrier.
	 *
	 * do_exit:
	 *	The caller holds mm->mmap_sem. This means that the task which
	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
	 *	its ->mm.
	 *
	 * de_thread:
	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
	 *	we must see either old or new leader, this does not matter.
	 *	However, it can change p->sighand, so lock_task_sighand(p)
	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
	 *	it can't fail.
	 *
	 *	Note also that "g" can be the old leader with ->mm == NULL
	 *	and already unhashed and thus removed from ->thread_group.
	 *	This is OK, __unhash_process()->list_del_rcu() does not
	 *	clear the ->next pointer, we will find the new leader via
	 *	next_thread().
	 */
	rcu_read_lock();
	for_each_process(g) {
		if (g == tsk->group_leader)
			continue;
		if (g->flags & PF_KTHREAD)
			continue;
				if (unlikely(p->mm == mm)) {
					lock_task_sighand(p, &flags);
					unlock_task_sighand(p, &flags);
				}
		} while_each_thread(g, p);
	rcu_read_unlock();
	atomic_set(&core_state->nr_threads, nr);
static int coredump_wait(int exit_code, struct core_state *core_state)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;
	struct completion *vfork_done;
	int core_waiters;
Linus Torvalds's avatar
Linus Torvalds committed

	init_completion(&core_state->startup);
	core_state->dumper.task = tsk;
	core_state->dumper.next = NULL;
	core_waiters = zap_threads(tsk, mm, core_state, exit_code);
	up_write(&mm->mmap_sem);

	if (unlikely(core_waiters < 0))
		goto fail;

	/*
	 * Make sure nobody is waiting for us to release the VM,
	 * otherwise we can deadlock when we wait on each other
	 */
	vfork_done = tsk->vfork_done;
	if (vfork_done) {
		tsk->vfork_done = NULL;
		complete(vfork_done);
	}

	if (core_waiters)
		wait_for_completion(&core_state->startup);
fail:
	return core_waiters;
static void coredump_finish(struct mm_struct *mm)
{
	struct core_thread *curr, *next;
	struct task_struct *task;

	next = mm->core_state->dumper.next;
	while ((curr = next) != NULL) {
		next = curr->next;
		task = curr->task;
		/*
		 * see exit_mm(), curr->task must not see
		 * ->task == NULL before we read ->next.
		 */
		smp_mb();
		curr->task = NULL;
		wake_up_process(task);
	}

	mm->core_state = NULL;
}

/*
 * set_dumpable converts traditional three-value dumpable to two flags and
 * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
 * these bits are not changed atomically.  So get_dumpable can observe the
 * intermediate state.  To avoid doing unexpected behavior, get get_dumpable
 * return either old dumpable or new one by paying attention to the order of
 * modifying the bits.
 *
 * dumpable |   mm->flags (binary)
 * old  new | initial interim  final
 * ---------+-----------------------
 *  0    1  |   00      01      01
 *  0    2  |   00      10(*)   11
 *  1    0  |   01      00      00
 *  1    2  |   01      11      11
 *  2    0  |   11      10(*)   00
 *  2    1  |   11      11      01
 *
 * (*) get_dumpable regards interim value of 10 as 11.
 */
void set_dumpable(struct mm_struct *mm, int value)
{
	switch (value) {
	case 0:
		clear_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 1:
		set_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 2:
		set_bit(MMF_DUMP_SECURELY, &mm->flags);
		smp_wmb();
		set_bit(MMF_DUMPABLE, &mm->flags);
		break;
	}
}

int get_dumpable(struct mm_struct *mm)
{
	int ret;

	ret = mm->flags & 0x3;
	return (ret >= 2) ? 2 : ret;
}

static void wait_for_dump_helpers(struct file *file)
{
	struct pipe_inode_info *pipe;

	pipe = file->f_path.dentry->d_inode->i_pipe;

	pipe_lock(pipe);
	pipe->readers++;
	pipe->writers--;

	while ((pipe->readers > 1) && (!signal_pending(current))) {
		wake_up_interruptible_sync(&pipe->wait);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
		pipe_wait(pipe);
	}

	pipe->readers--;
	pipe->writers++;
	pipe_unlock(pipe);

}


void do_coredump(long signr, int exit_code, struct pt_regs *regs)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct core_state core_state;
Linus Torvalds's avatar
Linus Torvalds committed
	char corename[CORENAME_MAX_SIZE + 1];
	struct mm_struct *mm = current->mm;
	struct linux_binfmt * binfmt;
	struct inode * inode;
	const struct cred *old_cred;
	struct cred *cred;
Linus Torvalds's avatar
Linus Torvalds committed
	int retval = 0;
Alan Cox's avatar
Alan Cox committed
	int flag = 0;
	int dump_count = 0;
	static atomic_t core_dump_count = ATOMIC_INIT(0);
	struct coredump_params cprm = {
		.signr = signr,
		.regs = regs,
		.limit = current->signal->rlim[RLIMIT_CORE].rlim_cur,
	};
Linus Torvalds's avatar
Linus Torvalds committed

	audit_core_dumps(signr);

Linus Torvalds's avatar
Linus Torvalds committed
	if (!binfmt || !binfmt->core_dump)
		goto fail;

	cred = prepare_creds();
	if (!cred) {
		retval = -ENOMEM;
		goto fail;
	}

Linus Torvalds's avatar
Linus Torvalds committed
	down_write(&mm->mmap_sem);
	/*
	 * If another thread got here first, or we are not dumpable, bail out.
	 */
	if (mm->core_state || !get_dumpable(mm)) {
Linus Torvalds's avatar
Linus Torvalds committed
		up_write(&mm->mmap_sem);
		put_cred(cred);
Linus Torvalds's avatar
Linus Torvalds committed
		goto fail;
	}
Alan Cox's avatar
Alan Cox committed

	/*
	 *	We cannot trust fsuid as being the "true" uid of the
	 *	process nor do we know its entire history. We only know it
	 *	was tainted so we dump it as root in mode 2.
	 */
	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
Alan Cox's avatar
Alan Cox committed
		flag = O_EXCL;		/* Stop rewrite attacks */
		cred->fsuid = 0;	/* Dump root private */
Alan Cox's avatar
Alan Cox committed
	}
	retval = coredump_wait(exit_code, &core_state);
	if (retval < 0) {
		put_cred(cred);
	}

	old_cred = override_creds(cred);
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 * Clear any false indication of pending signals that might
	 * be seen by the filesystem code called to write the core file.
	 */
	clear_thread_flag(TIF_SIGPENDING);

	/*
	 * lock_kernel() because format_corename() is controlled by sysctl, which
	 * uses lock_kernel()
	 */
 	lock_kernel();
	ispipe = format_corename(corename, signr);
Linus Torvalds's avatar
Linus Torvalds committed
	unlock_kernel();
	if ((!ispipe) && (cprm.limit < binfmt->min_coredump))
		if (cprm.limit == 0) {
			/*
			 * Normally core limits are irrelevant to pipes, since
			 * we're not writing to the file system, but we use
			 * cprm.limit of 0 here as a speacial value. Any
			 * non-zero limit gets set to RLIM_INFINITY below, but
			 * a limit of 0 skips the dump.  This is a consistent
			 * way to catch recursive crashes.  We can still crash
			 * if the core_pattern binary sets RLIM_CORE =  !0
			 * but it runs as root, and can do lots of stupid things
			 * Note that we use task_tgid_vnr here to grab the pid
			 * of the process group leader.  That way we get the
			 * right pid if a thread in a multi-threaded
			 * core_pattern process dies.
			 */
			printk(KERN_WARNING
				"Process %d(%s) has RLIMIT_CORE set to 0\n",
				task_tgid_vnr(current), current->comm);
			printk(KERN_WARNING "Aborting core\n");
			goto fail_unlock;
		}

		dump_count = atomic_inc_return(&core_dump_count);
		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
			printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
			       task_tgid_vnr(current), current->comm);
			printk(KERN_WARNING "Skipping core dump\n");
			goto fail_dropcount;
		}

		helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
		if (!helper_argv) {
			printk(KERN_WARNING "%s failed to allocate memory\n",
			       __func__);
		cprm.limit = RLIM_INFINITY;
		/* SIGPIPE can happen, but it's just never processed */
		if (call_usermodehelper_pipe(helper_argv[0], helper_argv, NULL,
 			printk(KERN_INFO "Core dump to %s pipe failed\n",
			       corename);
		cprm.file = filp_open(corename,
				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
				 0600);
	if (IS_ERR(cprm.file))
	inode = cprm.file->f_path.dentry->d_inode;
Linus Torvalds's avatar
Linus Torvalds committed
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */
	if (!ispipe && d_unhashed(cprm.file->f_path.dentry))
Linus Torvalds's avatar
Linus Torvalds committed
		goto close_fail;

	/* AK: actually i see no reason to not allow this for named pipes etc.,
	   but keep the previous behaviour for now. */
	if (!ispipe && !S_ISREG(inode->i_mode))
Linus Torvalds's avatar
Linus Torvalds committed
		goto close_fail;
Ingo Molnar's avatar
Ingo Molnar committed
	/*
	 * Dont allow local users get cute and trick others to coredump
	 * into their pre-created files:
	 */
	if (inode->i_uid != current_fsuid())
Ingo Molnar's avatar
Ingo Molnar committed
		goto close_fail;
	if (!cprm.file->f_op)
Linus Torvalds's avatar
Linus Torvalds committed
		goto close_fail;
	if (!cprm.file->f_op->write)
Linus Torvalds's avatar
Linus Torvalds committed
		goto close_fail;
	if (!ispipe &&
	    do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file) != 0)
Linus Torvalds's avatar
Linus Torvalds committed
		goto close_fail;

	retval = binfmt->core_dump(&cprm);
Linus Torvalds's avatar
Linus Torvalds committed

	if (retval)
		current->signal->group_exit_code |= 0x80;
close_fail:
		wait_for_dump_helpers(cprm.file);
	filp_close(cprm.file, NULL);
fail_dropcount:
	if (dump_count)
		atomic_dec(&core_dump_count);
Linus Torvalds's avatar
Linus Torvalds committed
fail_unlock:
	revert_creds(old_cred);
	put_cred(cred);
	coredump_finish(mm);
Linus Torvalds's avatar
Linus Torvalds committed
fail:
	return;
Linus Torvalds's avatar
Linus Torvalds committed
}