path: root/fs/notify/fanotify/fanotify.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kernel.h> /* UINT_MAX */
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
#include <linux/sched/signal.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <linux/audit.h>
#include <linux/sched/mm.h>
#include <linux/statfs.h>

#include "fanotify.h"

static bool fanotify_path_equal(struct path *p1, struct path *p2)
{
	return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
}

static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
				       __kernel_fsid_t *fsid2)
{
	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
}

static bool fanotify_fh_equal(struct fanotify_fh *fh1,
			      struct fanotify_fh *fh2)
{
	if (fh1->type != fh2->type || fh1->len != fh2->len)
		return false;

	/* Do not merge events if we failed to encode fh */
	if (fh1->type == FILEID_INVALID)
		return false;

	return !fh1->len ||
		!memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
}

static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
				     struct fanotify_fid_event *ffe2)
{
	/* Do not merge fid events without object fh */
	if (!ffe1->object_fh.len)
		return false;

	return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
		fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
}

static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
				      struct fanotify_name_event *fne2)
{
	/*
	 * Do not merge name events without dir fh.
	 * FAN_DIR_MODIFY does not encode object fh, so it may be empty.
	 */
	if (!fne1->dir_fh.len)
		return false;

	if (fne1->name_len != fne2->name_len ||
	    !fanotify_fh_equal(&fne1->dir_fh, &fne2->dir_fh))
		return false;

	return !memcmp(fne1->name, fne2->name, fne1->name_len);
}

static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
			 struct fsnotify_event *new_fsn)
{
	struct fanotify_event *old, *new;

	pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
	old = FANOTIFY_E(old_fsn);
	new = FANOTIFY_E(new_fsn);

	if (old_fsn->objectid != new_fsn->objectid ||
	    old->type != new->type || old->pid != new->pid)
		return false;

	/*
	 * We want to merge many dirent events in the same dir (i.e.
	 * creates/unlinks/renames), but we do not want to merge dirent
	 * events referring to subdirs with dirent events referring to
	 * non subdirs, otherwise, user won't be able to tell from a
	 * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
	 * unlink pair or rmdir+create pair of events.
	 */
	if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
		return false;

	switch (old->type) {
	case FANOTIFY_EVENT_TYPE_PATH:
		return fanotify_path_equal(fanotify_event_path(old),
					   fanotify_event_path(new));
	case FANOTIFY_EVENT_TYPE_FID:
		return fanotify_fid_event_equal(FANOTIFY_FE(old),
						FANOTIFY_FE(new));
	case FANOTIFY_EVENT_TYPE_FID_NAME:
		return fanotify_name_event_equal(FANOTIFY_NE(old),
						 FANOTIFY_NE(new));
	default:
		WARN_ON_ONCE(1);
	}

	return false;
}

/* and the list better be locked by something too! */
static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
{
	struct fsnotify_event *test_event;
	struct fanotify_event *new;

	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
	new = FANOTIFY_E(event);

	/*
	 * Don't merge a permission event with any other event so that we know
	 * the event structure we have created in fanotify_handle_event() is the
	 * one we should check for permission response.
	 */
	if (fanotify_is_perm_event(new->mask))
		return 0;

	list_for_each_entry_reverse(test_event, list, list) {
		if (fanotify_should_merge(test_event, event)) {
			FANOTIFY_E(test_event)->mask |= new->mask;
			return 1;
		}
	}

	return 0;
}

/*
 * Wait for response to permission event. The function also takes care of
 * freeing the permission event (or offloads that in case the wait is canceled
 * by a signal). The function returns 0 in case access got allowed by userspace,
 * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
 * the wait got interrupted by a signal.
 */
static int fanotify_get_response(struct fsnotify_group *group,
				 struct fanotify_perm_event *event,
				 struct fsnotify_iter_info *iter_info)
{
	int ret;

	pr_debug("%s: group=%p event=%p\n", __func__, group, event);

	ret = wait_event_killable(group->fanotify_data.access_waitq,
				  event->state == FAN_EVENT_ANSWERED);
	/* Signal pending? */
	if (ret < 0) {
		spin_lock(&group->notification_lock);
		/* Event reported to userspace and no answer yet? */
		if (event->state == FAN_EVENT_REPORTED) {
			/* Event will get freed once userspace answers to it */
			event->state = FAN_EVENT_CANCELED;
			spin_unlock(&group->notification_lock);
			return ret;
		}
		/* Event not yet reported? Just remove it. */
		if (event->state == FAN_EVENT_INIT)
			fsnotify_remove_queued_event(group, &event->fae.fse);
		/*
		 * Event may be also answered in case signal delivery raced
		 * with wakeup. In that case we have nothing to do besides
		 * freeing the event and reporting error.
		 */
		spin_unlock(&group->notification_lock);
		goto out;
	}

	/* userspace responded, convert to something usable */
	switch (event->response & ~FAN_AUDIT) {
	case FAN_ALLOW:
		ret = 0;
		break;
	case FAN_DENY:
	default:
		ret = -EPERM;
	}

	/* Check if the response should be audited */
	if (event->response & FAN_AUDIT)
		audit_fanotify(event->response & ~FAN_AUDIT);

	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
		 group, event, ret);
out:
	fsnotify_destroy_event(group, &event->fae.fse);

	return ret;
}

/*
 * This function returns a mask for an event that only contains the flags
 * that have been specifically requested by the user. Flags that may have
 * been included within the event mask, but have not been explicitly
 * requested by the user, will not be present in the returned mask.
 */
static u32 fanotify_group_event_mask(struct fsnotify_group *group,
				     struct fsnotify_iter_info *iter_info,
				     u32 event_mask, const void *data,
				     int data_type)
{
	__u32 marks_mask = 0, marks_ignored_mask = 0;
	__u32 test_mask, user_mask