| Message ID | 20250123194108.1025273-3-mszeredi@redhat.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mount notification | expand |
On Thu, Jan 23, 2025 at 2:41 PM Miklos Szeredi <mszeredi@redhat.com> wrote: > > Add notifications for attaching and detaching mounts. Adding the SELinux list to my reply as things like this really should go to the full list. For those of you seeing this for the first time, the full patchset from Miklos can be found at the lore link below. Policy folks, please read my comments at the bottom, there is a question for you there. https://lore.kernel.org/linux-security-module/20250123194108.1025273-1-mszeredi@redhat.com > The following new event masks are added: > > FAN_MNT_ATTACH - Mount was attached > FAN_MNT_DETACH - Mount was detached > > If a mount is moved, then the event is reported with (FAN_MNT_ATTACH | > FAN_MNT_DETACH). > > These events add an info record of type FAN_EVENT_INFO_TYPE_MNT containing > these fields identifying the affected mounts: > > __u64 mnt_id - the ID of the mount (see statmount(2)) > > FAN_REPORT_MNT must be supplied to fanotify_init() to receive these events > and no other type of event can be received with this report type. > > Marks are added with FAN_MARK_MNTNS, which records the mount namespace from > an nsfs file (e.g. /proc/self/ns/mnt). The policy folks can correct me, but to put some context on this (pardon the pun), I believe most public SELinux policies label the nsfs files based on the associated process, e.g. if sshd is running in the sshd_t domain, the /proc/<sshd>/ns files will be labeled as sshd_t. > Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> > --- > fs/mount.h | 2 + > fs/namespace.c | 14 +++-- > fs/notify/fanotify/fanotify.c | 38 +++++++++++-- > fs/notify/fanotify/fanotify.h | 18 +++++++ > fs/notify/fanotify/fanotify_user.c | 86 +++++++++++++++++++++++++----- > fs/notify/fdinfo.c | 5 ++ > include/linux/fanotify.h | 12 +++-- > include/uapi/linux/fanotify.h | 10 ++++ > security/selinux/hooks.c | 4 ++ > 9 files changed, 166 insertions(+), 23 deletions(-) I'll refrain from trimming the original patch for easier viewing by the SELinux folks. > diff --git a/fs/mount.h b/fs/mount.h > index 33311ad81042..9689e7bf4501 100644 > --- a/fs/mount.h > +++ b/fs/mount.h > @@ -174,3 +174,5 @@ static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) > { > return container_of(ns, struct mnt_namespace, ns); > } > + > +struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry); > diff --git a/fs/namespace.c b/fs/namespace.c > index eac057e56948..4d9072fd1263 100644 > --- a/fs/namespace.c > +++ b/fs/namespace.c > @@ -2101,16 +2101,24 @@ struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool pre > } > } > > +struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry) > +{ > + if (!is_mnt_ns_file(dentry)) > + return NULL; > + > + return to_mnt_ns(get_proc_ns(dentry->d_inode)); > +} > + > static bool mnt_ns_loop(struct dentry *dentry) > { > /* Could bind mounting the mount namespace inode cause a > * mount namespace loop? > */ > - struct mnt_namespace *mnt_ns; > - if (!is_mnt_ns_file(dentry)) > + struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry); > + > + if (!mnt_ns) > return false; > > - mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); > return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; > } > > diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c > index 24c7c5df4998..b1937f92f105 100644 > --- a/fs/notify/fanotify/fanotify.c > +++ b/fs/notify/fanotify/fanotify.c > @@ -166,6 +166,8 @@ static bool fanotify_should_merge(struct fanotify_event *old, > case FANOTIFY_EVENT_TYPE_FS_ERROR: > return fanotify_error_event_equal(FANOTIFY_EE(old), > FANOTIFY_EE(new)); > + case FANOTIFY_EVENT_TYPE_MNT: > + return false; > default: > WARN_ON_ONCE(1); > } > @@ -303,7 +305,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, > pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n", > __func__, iter_info->report_mask, event_mask, data, data_type); > > - if (!fid_mode) { > + if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) { > + if (data_type != FSNOTIFY_EVENT_MNT) > + return 0; > + } else if (!fid_mode) { > /* Do we have path to open a file descriptor? */ > if (!path) > return 0; > @@ -548,6 +553,20 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path, > return &pevent->fae; > } > > +static struct fanotify_event *fanotify_alloc_mnt_event(u64 mnt_id, gfp_t gfp) > +{ > + struct fanotify_mnt_event *pevent; > + > + pevent = kmem_cache_alloc(fanotify_mnt_event_cachep, gfp); > + if (!pevent) > + return NULL; > + > + pevent->fae.type = FANOTIFY_EVENT_TYPE_MNT; > + pevent->mnt_id = mnt_id; > + > + return &pevent->fae; > +} > + > static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, > gfp_t gfp) > { > @@ -715,6 +734,7 @@ static struct fanotify_event *fanotify_alloc_event( > fid_mode); > struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); > const struct path *path = fsnotify_data_path(data, data_type); > + u64 mnt_id = fsnotify_data_mnt_id(data, data_type); > struct mem_cgroup *old_memcg; > struct dentry *moved = NULL; > struct inode *child = NULL; > @@ -810,8 +830,12 @@ static struct fanotify_event *fanotify_alloc_event( > moved, &hash, gfp); > } else if (fid_mode) { > event = fanotify_alloc_fid_event(id, fsid, &hash, gfp); > - } else { > + } else if (path) { > event = fanotify_alloc_path_event(path, &hash, gfp); > + } else if (mnt_id) { > + event = fanotify_alloc_mnt_event(mnt_id, gfp); > + } else { > + WARN_ON_ONCE(1); > } > > if (!event) > @@ -910,7 +934,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, > BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); > BUILD_BUG_ON(FAN_RENAME != FS_RENAME); > > - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); > + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 23); > > mask = fanotify_group_event_mask(group, iter_info, &match_mask, > mask, data, data_type, dir); > @@ -1011,6 +1035,11 @@ static void fanotify_free_error_event(struct fsnotify_group *group, > mempool_free(fee, &group->fanotify_data.error_events_pool); > } > > +static void fanotify_free_mnt_event(struct fanotify_event *event) > +{ > + kmem_cache_free(fanotify_mnt_event_cachep, FANOTIFY_ME(event)); > +} > + > static void fanotify_free_event(struct fsnotify_group *group, > struct fsnotify_event *fsn_event) > { > @@ -1037,6 +1066,9 @@ static void fanotify_free_event(struct fsnotify_group *group, > case FANOTIFY_EVENT_TYPE_FS_ERROR: > fanotify_free_error_event(group, event); > break; > + case FANOTIFY_EVENT_TYPE_MNT: > + fanotify_free_mnt_event(event); > + break; > default: > WARN_ON_ONCE(1); > } > diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h > index e5ab33cae6a7..f1a7cbedc9e3 100644 > --- a/fs/notify/fanotify/fanotify.h > +++ b/fs/notify/fanotify/fanotify.h > @@ -9,6 +9,7 @@ extern struct kmem_cache *fanotify_mark_cache; > extern struct kmem_cache *fanotify_fid_event_cachep; > extern struct kmem_cache *fanotify_path_event_cachep; > extern struct kmem_cache *fanotify_perm_event_cachep; > +extern struct kmem_cache *fanotify_mnt_event_cachep; > > /* Possible states of the permission event */ > enum { > @@ -244,6 +245,7 @@ enum fanotify_event_type { > FANOTIFY_EVENT_TYPE_PATH_PERM, > FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ > FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ > + FANOTIFY_EVENT_TYPE_MNT, > __FANOTIFY_EVENT_TYPE_NUM > }; > > @@ -409,12 +411,23 @@ struct fanotify_path_event { > struct path path; > }; > > +struct fanotify_mnt_event { > + struct fanotify_event fae; > + u64 mnt_id; > +}; > + > static inline struct fanotify_path_event * > FANOTIFY_PE(struct fanotify_event *event) > { > return container_of(event, struct fanotify_path_event, fae); > } > > +static inline struct fanotify_mnt_event * > +FANOTIFY_ME(struct fanotify_event *event) > +{ > + return container_of(event, struct fanotify_mnt_event, fae); > +} > + > /* > * Structure for permission fanotify events. It gets allocated and freed in > * fanotify_handle_event() since we wait there for user response. When the > @@ -456,6 +469,11 @@ static inline bool fanotify_is_error_event(u32 mask) > return mask & FAN_FS_ERROR; > } > > +static inline bool fanotify_is_mnt_event(u32 mask) > +{ > + return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH); > +} > + > static inline const struct path *fanotify_event_path(struct fanotify_event *event) > { > if (event->type == FANOTIFY_EVENT_TYPE_PATH) > diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c > index 2d85c71717d6..da97eb01e2fa 100644 > --- a/fs/notify/fanotify/fanotify_user.c > +++ b/fs/notify/fanotify/fanotify_user.c > @@ -114,6 +114,7 @@ struct kmem_cache *fanotify_mark_cache __ro_after_init; > struct kmem_cache *fanotify_fid_event_cachep __ro_after_init; > struct kmem_cache *fanotify_path_event_cachep __ro_after_init; > struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; > +struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init; > > #define FANOTIFY_EVENT_ALIGN 4 > #define FANOTIFY_FID_INFO_HDR_LEN \ > @@ -122,6 +123,8 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; > sizeof(struct fanotify_event_info_pidfd) > #define FANOTIFY_ERROR_INFO_LEN \ > (sizeof(struct fanotify_event_info_error)) > +#define FANOTIFY_MNT_INFO_LEN \ > + (sizeof(struct fanotify_event_info_mnt)) > > static int fanotify_fid_info_len(int fh_len, int name_len) > { > @@ -183,6 +186,8 @@ static size_t fanotify_event_len(unsigned int info_mode, > fh_len = fanotify_event_object_fh_len(event); > event_len += fanotify_fid_info_len(fh_len, dot_len); > } > + if (fanotify_is_mnt_event(event->mask)) > + event_len += FANOTIFY_MNT_INFO_LEN; > > return event_len; > } > @@ -380,6 +385,25 @@ static int process_access_response(struct fsnotify_group *group, > return -ENOENT; > } > > +static size_t copy_mnt_info_to_user(struct fanotify_event *event, > + char __user *buf, int count) > +{ > + struct fanotify_event_info_mnt info = { }; > + > + info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT; > + info.hdr.len = FANOTIFY_MNT_INFO_LEN; > + > + if (WARN_ON(count < info.hdr.len)) > + return -EFAULT; > + > + info.mnt_id = FANOTIFY_ME(event)->mnt_id; > + > + if (copy_to_user(buf, &info, sizeof(info))) > + return -EFAULT; > + > + return info.hdr.len; > +} > + > static size_t copy_error_info_to_user(struct fanotify_event *event, > char __user *buf, int count) > { > @@ -642,6 +666,14 @@ static int copy_info_records_to_user(struct fanotify_event *event, > total_bytes += ret; > } > > + if (fanotify_is_mnt_event(event->mask)) { > + ret = copy_mnt_info_to_user(event, buf, count); > + if (ret < 0) > + return ret; > + buf += ret; > + count -= ret; > + total_bytes += ret; > + } > return total_bytes; > } > > @@ -1446,6 +1478,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) > if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID)) > return -EINVAL; > > + /* Don't allow mixing mnt events with inode events for now */ > + if (flags & FAN_REPORT_MNT) { > + if (class != FAN_CLASS_NOTIF) > + return -EINVAL; > + if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR)) > + return -EINVAL; > + } > + > if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) > return -EINVAL; > > @@ -1685,7 +1725,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > int dfd, const char __user *pathname) > { > struct inode *inode = NULL; > - struct vfsmount *mnt = NULL; > struct fsnotify_group *group; > struct path path; > struct fan_fsid __fsid, *fsid = NULL; > @@ -1718,6 +1757,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > case FAN_MARK_FILESYSTEM: > obj_type = FSNOTIFY_OBJ_TYPE_SB; > break; > + case FAN_MARK_MNTNS: > + obj_type = FSNOTIFY_OBJ_TYPE_MNTNS; > + break; > default: > return -EINVAL; > } > @@ -1765,6 +1807,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > return -EINVAL; > group = fd_file(f)->private_data; > > + /* Only report mount events on mnt namespace */ > + if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) { > + if (mask & ~FANOTIFY_MOUNT_EVENTS) > + return -EINVAL; > + if (mark_type != FAN_MARK_MNTNS) > + return -EINVAL; > + } else { > + if (mask & FANOTIFY_MOUNT_EVENTS) > + return -EINVAL; > + if (mark_type == FAN_MARK_MNTNS) > + return -EINVAL; > + } > + > /* > * An unprivileged user is not allowed to setup mount nor filesystem > * marks. This also includes setting up such marks by a group that > @@ -1802,7 +1857,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > * point. > */ > fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); > - if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) && > + if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) && > (!fid_mode || mark_type == FAN_MARK_MOUNT)) > return -EINVAL; > > @@ -1848,17 +1903,21 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > } > > /* inode held in place by reference to path; group by fget on fd */ > - if (mark_type == FAN_MARK_INODE) { > + if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) { > inode = path.dentry->d_inode; > obj = inode; > - } else { > - mnt = path.mnt; > - if (mark_type == FAN_MARK_MOUNT) > - obj = mnt; > - else > - obj = mnt->mnt_sb; > + } else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { > + obj = path.mnt; > + } else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) { > + obj = path.mnt->mnt_sb; > + } else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) { > + obj = mnt_ns_from_dentry(path.dentry); > } > > + ret = -EINVAL; > + if (!obj) > + goto path_put_and_out; > + > /* > * If some other task has this inode open for write we should not add > * an ignore mask, unless that ignore mask is supposed to survive > @@ -1866,10 +1925,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > */ > if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) && > !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) { > - ret = mnt ? -EINVAL : -EISDIR; > + ret = !inode ? -EINVAL : -EISDIR; > /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */ > if (ignore == FAN_MARK_IGNORE && > - (mnt || S_ISDIR(inode->i_mode))) > + (!inode || S_ISDIR(inode->i_mode))) > goto path_put_and_out; > > ret = 0; > @@ -1878,7 +1937,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, > } > > /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ > - if (mnt || !S_ISDIR(inode->i_mode)) { > + if (!inode || !S_ISDIR(inode->i_mode)) { > mask &= ~FAN_EVENT_ON_CHILD; > umask = FAN_EVENT_ON_CHILD; > /* > @@ -1952,7 +2011,7 @@ static int __init fanotify_user_setup(void) > FANOTIFY_DEFAULT_MAX_USER_MARKS); > > BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); > - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 13); > + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14); > BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11); > > fanotify_mark_cache = KMEM_CACHE(fanotify_mark, > @@ -1965,6 +2024,7 @@ static int __init fanotify_user_setup(void) > fanotify_perm_event_cachep = > KMEM_CACHE(fanotify_perm_event, SLAB_PANIC); > } > + fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC); > > fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS; > init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] = > diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c > index e933f9c65d90..1161eabf11ee 100644 > --- a/fs/notify/fdinfo.c > +++ b/fs/notify/fdinfo.c > @@ -121,6 +121,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) > > seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n", > sb->s_dev, mflags, mark->mask, mark->ignore_mask); > + } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) { > + struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector); > + > + seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n", > + mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask); > } > } > > diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h > index 89ff45bd6f01..fc142be2542d 100644 > --- a/include/linux/fanotify.h > +++ b/include/linux/fanotify.h > @@ -25,7 +25,7 @@ > > #define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) > > -#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) > +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT) > > /* > * fanotify_init() flags that require CAP_SYS_ADMIN. > @@ -38,7 +38,8 @@ > FAN_REPORT_PIDFD | \ > FAN_REPORT_FD_ERROR | \ > FAN_UNLIMITED_QUEUE | \ > - FAN_UNLIMITED_MARKS) > + FAN_UNLIMITED_MARKS | \ > + FAN_REPORT_MNT) > > /* > * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN. > @@ -58,7 +59,7 @@ > #define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) > > #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ > - FAN_MARK_FILESYSTEM) > + FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS) > > #define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ > FAN_MARK_FLUSH) > @@ -99,10 +100,13 @@ > /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ > #define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) > > +#define FANOTIFY_MOUNT_EVENTS (FAN_MNT_ATTACH | FAN_MNT_DETACH) > + > /* Events that user can request to be notified on */ > #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ > FANOTIFY_INODE_EVENTS | \ > - FANOTIFY_ERROR_EVENTS) > + FANOTIFY_ERROR_EVENTS | \ > + FANOTIFY_MOUNT_EVENTS) > > /* Events that require a permission response from user */ > #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ > diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h > index 34f221d3a1b9..69340e483ae7 100644 > --- a/include/uapi/linux/fanotify.h > +++ b/include/uapi/linux/fanotify.h > @@ -25,6 +25,8 @@ > #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ > #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ > #define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ > +#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */ > +#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */ > > #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ > > @@ -61,6 +63,7 @@ > #define FAN_REPORT_NAME 0x00000800 /* Report events with name */ > #define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ > #define FAN_REPORT_FD_ERROR 0x00002000 /* event->fd can report error */ > +#define FAN_REPORT_MNT 0x00004000 /* Report mount events */ > > /* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ > #define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) > @@ -91,6 +94,7 @@ > #define FAN_MARK_INODE 0x00000000 > #define FAN_MARK_MOUNT 0x00000010 > #define FAN_MARK_FILESYSTEM 0x00000100 > +#define FAN_MARK_MNTNS 0x00000110 > > /* > * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY > @@ -143,6 +147,7 @@ struct fanotify_event_metadata { > #define FAN_EVENT_INFO_TYPE_DFID 3 > #define FAN_EVENT_INFO_TYPE_PIDFD 4 > #define FAN_EVENT_INFO_TYPE_ERROR 5 > +#define FAN_EVENT_INFO_TYPE_MNT 6 > > /* Special info types for FAN_RENAME */ > #define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 > @@ -189,6 +194,11 @@ struct fanotify_event_info_error { > __u32 error_count; > }; > > +struct fanotify_event_info_mnt { > + struct fanotify_event_info_header hdr; > + __u64 mnt_id; > +}; > + > /* > * User space may need to record additional information about its decision. > * The extra information type records what kind of information is included. > diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c > index 171dd7fceac5..d2b3e60e2be9 100644 > --- a/security/selinux/hooks.c > +++ b/security/selinux/hooks.c > @@ -3395,6 +3395,10 @@ static int selinux_path_notify(const struct path *path, u64 mask, > case FSNOTIFY_OBJ_TYPE_INODE: > perm = FILE__WATCH; > break; > + case FSNOTIFY_OBJ_TYPE_MNTNS: > + /* FIXME: Is this correct??? */ > + perm = FILE__WATCH; > + break; If I understand the commit description correctly, security_path_notify(path, mask, FSNOTIFY_OBJ_TYPE_MNTNS) indicates a change in the mount namespace indicated by the @path parameter, with the initial mntns changes being limited to attach/detach and possibly some other attributes (see patch 4/4), although the latter looks like it will probably happen at a later date. My initial thinking is that if we limit ourselves to existing SELinux policy permissions, this is much more of FILE__WATCH_MOUNT operation rather than a FILE__WATCH operation as while the /proc/PID/ns/mnt file specified in @path is simply a file, it represents much more than that. However, it we want to consider adding a new SELinux policy permission (which is easy to do), we may want to consider adding a new mount namespace specific permission, e.g. FILE__WATCH_MOUNTNS, this would make it easier for policy developers to distinguish between watching a traditional mount point and a mount namespace (although given the common approaches to labeling this may not be very significant). I'd personally like to hear from the SELinux policy folks on this (the SELinux reference policy has also been CC'd). If we reuse the file/watch_mount permission the policy rule would look something like below where <subject> is the SELinux domain of the process making the change, and <mntns_label> is the label of the /proc/PID/ns/mnt file: allow <subject> <mntns_label>:file { watch_mount }; If we add a new file/watch_mountns permission the policy rule would look like this: allow <subject> <mntns_label>:file { watch_mountns }; > default: > return -EINVAL; > } > -- > 2.47.1
On Saturday, 25 January 2025 06:38:45 AEDT Paul Moore wrote: > My initial thinking is that if we limit ourselves to existing SELinux > policy permissions, this is much more of FILE__WATCH_MOUNT operation > rather than a FILE__WATCH operation as while the /proc/PID/ns/mnt file > specified in @path is simply a file, it represents much more than > that. However, it we want to consider adding a new SELinux policy > permission (which is easy to do), we may want to consider adding a new > mount namespace specific permission, e.g. FILE__WATCH_MOUNTNS, this > would make it easier for policy developers to distinguish between > watching a traditional mount point and a mount namespace (although > given the common approaches to labeling this may not be very > significant). I'd personally like to hear from the SELinux policy > folks on this (the SELinux reference policy has also been CC'd). > > If we reuse the file/watch_mount permission the policy rule would look > something like below where <subject> is the SELinux domain of the > process making the change, and <mntns_label> is the label of the > /proc/PID/ns/mnt file: > > allow <subject> <mntns_label>:file { watch_mount }; > > If we add a new file/watch_mountns permission the policy rule would > look like this: > > allow <subject> <mntns_label>:file { watch_mountns }; What's the benefit in watching mount being separate from watching a namespace mount? In what situation could a process be permitted one of those but not the other?
On Sat, 25 Jan 2025 at 02:17, Russell Coker <russell@coker.com.au> wrote: > What's the benefit in watching mount being separate from watching a namespace > mount? 1) fanotify_mark(fan_fd, FAN_MARK_ADD | FAN_MARK_MOUNT, FAN_OPEN, AT_FDCWD, "/proc/self/ns/mnt"); This notifies on mount and unmount events in the current mount namespace. 2) fanotify_mark(fan, FAN_MARK_ADD | FAN_MARK_MOUNT, FAN_OPEN, AT_FDCWD, "/proc/self/ns/mnt"); This notifies on open events within the nsfs mount (proc uses a kernel private nsfs mount, so all accesses through proc will trigger this). The latter doesn't really make sense (these files are not openable), but it's doable with current kernels and events on the failed opens do get generated. So overloading FILE__WATCH_MOUNT might work, but it is also very confusing, since watching a mount namespace and watching a mount mean completely different things. Thanks, Miklos
On Tue, 28 Jan 2025 at 13:42, Miklos Szeredi <miklos@szeredi.hu> wrote: > fanotify_mark(fan_fd, FAN_MARK_ADD | FAN_MARK_MOUNT, FAN_OPEN, > AT_FDCWD, "/proc/self/ns/mnt"); Sorry, this should have been: 1) fanotify_mark(fan_fd, FAN_MARK_ADD | FAN_MARK_MNTNS, FAN_MNT_ATTACH | FAN_MNT_DETACH, AT_FDCWD, "/proc/self/ns/mnt"); This notifies on mount and unmount events in the current mount namespace.
> If I understand the commit description correctly, > security_path_notify(path, mask, FSNOTIFY_OBJ_TYPE_MNTNS) indicates a > change in the mount namespace indicated by the @path parameter, with > the initial mntns changes being limited to attach/detach and possibly > some other attributes (see patch 4/4), although the latter looks like > it will probably happen at a later date. > > My initial thinking is that if we limit ourselves to existing SELinux > policy permissions, this is much more of FILE__WATCH_MOUNT operation > rather than a FILE__WATCH operation as while the /proc/PID/ns/mnt file > specified in @path is simply a file, it represents much more than > that. However, it we want to consider adding a new SELinux policy > permission (which is easy to do), we may want to consider adding a new > mount namespace specific permission, e.g. FILE__WATCH_MOUNTNS, this > would make it easier for policy developers to distinguish between > watching a traditional mount point and a mount namespace (although > given the common approaches to labeling this may not be very > significant). I'd personally like to hear from the SELinux policy > folks on this (the SELinux reference policy has also been CC'd). > > If we reuse the file/watch_mount permission the policy rule would look > something like below where <subject> is the SELinux domain of the > process making the change, and <mntns_label> is the label of the > /proc/PID/ns/mnt file: > > allow <subject> <mntns_label>:file { watch_mount }; > > If we add a new file/watch_mountns permission the policy rule would > look like this: > > allow <subject> <mntns_label>:file { watch_mountns }; > I've gone back and forth on this a few times. If I understand it correctly, I think we might really want to have a new permission here, which is sad, because in my humble opinion, the watch_* permissions are already more complicated than I like. "watch" does seem to be the wrong thing because this grants more than just changes to the specific file. However, "watch_mount" is a very highly privileged operation. Allowing watch on all reads and writes in the whole file hierarchy from a mount point is a substantial amount of access, and seems quite a bit more substantial than just watching new mounts being attached and detached (and similar) within a given mount namespace. FWIW I do think the assumption that different labeling between /proc/pid files and mountpoints generally does make this not a problem in practice. But in my opinion overloading watch_mount for this case seems different from the existing watch_mount permission to warrant not doing it. Particularly with watch_mount being such a privileged operation. -Daniel
diff --git a/fs/mount.h b/fs/mount.h index 33311ad81042..9689e7bf4501 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -174,3 +174,5 @@ static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } + +struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry); diff --git a/fs/namespace.c b/fs/namespace.c index eac057e56948..4d9072fd1263 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2101,16 +2101,24 @@ struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool pre } } +struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry) +{ + if (!is_mnt_ns_file(dentry)) + return NULL; + + return to_mnt_ns(get_proc_ns(dentry->d_inode)); +} + static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ - struct mnt_namespace *mnt_ns; - if (!is_mnt_ns_file(dentry)) + struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry); + + if (!mnt_ns) return false; - mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 24c7c5df4998..b1937f92f105 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -166,6 +166,8 @@ static bool fanotify_should_merge(struct fanotify_event *old, case FANOTIFY_EVENT_TYPE_FS_ERROR: return fanotify_error_event_equal(FANOTIFY_EE(old), FANOTIFY_EE(new)); + case FANOTIFY_EVENT_TYPE_MNT: + return false; default: WARN_ON_ONCE(1); } @@ -303,7 +305,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n", __func__, iter_info->report_mask, event_mask, data, data_type); - if (!fid_mode) { + if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) { + if (data_type != FSNOTIFY_EVENT_MNT) + return 0; + } else if (!fid_mode) { /* Do we have path to open a file descriptor? */ if (!path) return 0; @@ -548,6 +553,20 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path, return &pevent->fae; } +static struct fanotify_event *fanotify_alloc_mnt_event(u64 mnt_id, gfp_t gfp) +{ + struct fanotify_mnt_event *pevent; + + pevent = kmem_cache_alloc(fanotify_mnt_event_cachep, gfp); + if (!pevent) + return NULL; + + pevent->fae.type = FANOTIFY_EVENT_TYPE_MNT; + pevent->mnt_id = mnt_id; + + return &pevent->fae; +} + static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, gfp_t gfp) { @@ -715,6 +734,7 @@ static struct fanotify_event *fanotify_alloc_event( fid_mode); struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); const struct path *path = fsnotify_data_path(data, data_type); + u64 mnt_id = fsnotify_data_mnt_id(data, data_type); struct mem_cgroup *old_memcg; struct dentry *moved = NULL; struct inode *child = NULL; @@ -810,8 +830,12 @@ static struct fanotify_event *fanotify_alloc_event( moved, &hash, gfp); } else if (fid_mode) { event = fanotify_alloc_fid_event(id, fsid, &hash, gfp); - } else { + } else if (path) { event = fanotify_alloc_path_event(path, &hash, gfp); + } else if (mnt_id) { + event = fanotify_alloc_mnt_event(mnt_id, gfp); + } else { + WARN_ON_ONCE(1); } if (!event) @@ -910,7 +934,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(FAN_RENAME != FS_RENAME); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 23); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); @@ -1011,6 +1035,11 @@ static void fanotify_free_error_event(struct fsnotify_group *group, mempool_free(fee, &group->fanotify_data.error_events_pool); } +static void fanotify_free_mnt_event(struct fanotify_event *event) +{ + kmem_cache_free(fanotify_mnt_event_cachep, FANOTIFY_ME(event)); +} + static void fanotify_free_event(struct fsnotify_group *group, struct fsnotify_event *fsn_event) { @@ -1037,6 +1066,9 @@ static void fanotify_free_event(struct fsnotify_group *group, case FANOTIFY_EVENT_TYPE_FS_ERROR: fanotify_free_error_event(group, event); break; + case FANOTIFY_EVENT_TYPE_MNT: + fanotify_free_mnt_event(event); + break; default: WARN_ON_ONCE(1); } diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index e5ab33cae6a7..f1a7cbedc9e3 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -9,6 +9,7 @@ extern struct kmem_cache *fanotify_mark_cache; extern struct kmem_cache *fanotify_fid_event_cachep; extern struct kmem_cache *fanotify_path_event_cachep; extern struct kmem_cache *fanotify_perm_event_cachep; +extern struct kmem_cache *fanotify_mnt_event_cachep; /* Possible states of the permission event */ enum { @@ -244,6 +245,7 @@ enum fanotify_event_type { FANOTIFY_EVENT_TYPE_PATH_PERM, FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ + FANOTIFY_EVENT_TYPE_MNT, __FANOTIFY_EVENT_TYPE_NUM }; @@ -409,12 +411,23 @@ struct fanotify_path_event { struct path path; }; +struct fanotify_mnt_event { + struct fanotify_event fae; + u64 mnt_id; +}; + static inline struct fanotify_path_event * FANOTIFY_PE(struct fanotify_event *event) { return container_of(event, struct fanotify_path_event, fae); } +static inline struct fanotify_mnt_event * +FANOTIFY_ME(struct fanotify_event *event) +{ + return container_of(event, struct fanotify_mnt_event, fae); +} + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the @@ -456,6 +469,11 @@ static inline bool fanotify_is_error_event(u32 mask) return mask & FAN_FS_ERROR; } +static inline bool fanotify_is_mnt_event(u32 mask) +{ + return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH); +} + static inline const struct path *fanotify_event_path(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_PATH) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 2d85c71717d6..da97eb01e2fa 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -114,6 +114,7 @@ struct kmem_cache *fanotify_mark_cache __ro_after_init; struct kmem_cache *fanotify_fid_event_cachep __ro_after_init; struct kmem_cache *fanotify_path_event_cachep __ro_after_init; struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; +struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ @@ -122,6 +123,8 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; sizeof(struct fanotify_event_info_pidfd) #define FANOTIFY_ERROR_INFO_LEN \ (sizeof(struct fanotify_event_info_error)) +#define FANOTIFY_MNT_INFO_LEN \ + (sizeof(struct fanotify_event_info_mnt)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -183,6 +186,8 @@ static size_t fanotify_event_len(unsigned int info_mode, fh_len = fanotify_event_object_fh_len(event); event_len += fanotify_fid_info_len(fh_len, dot_len); } + if (fanotify_is_mnt_event(event->mask)) + event_len += FANOTIFY_MNT_INFO_LEN; return event_len; } @@ -380,6 +385,25 @@ static int process_access_response(struct fsnotify_group *group, return -ENOENT; } +static size_t copy_mnt_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_event_info_mnt info = { }; + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT; + info.hdr.len = FANOTIFY_MNT_INFO_LEN; + + if (WARN_ON(count < info.hdr.len)) + return -EFAULT; + + info.mnt_id = FANOTIFY_ME(event)->mnt_id; + + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + return info.hdr.len; +} + static size_t copy_error_info_to_user(struct fanotify_event *event, char __user *buf, int count) { @@ -642,6 +666,14 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_is_mnt_event(event->mask)) { + ret = copy_mnt_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } return total_bytes; } @@ -1446,6 +1478,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID)) return -EINVAL; + /* Don't allow mixing mnt events with inode events for now */ + if (flags & FAN_REPORT_MNT) { + if (class != FAN_CLASS_NOTIF) + return -EINVAL; + if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR)) + return -EINVAL; + } + if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) return -EINVAL; @@ -1685,7 +1725,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, int dfd, const char __user *pathname) { struct inode *inode = NULL; - struct vfsmount *mnt = NULL; struct fsnotify_group *group; struct path path; struct fan_fsid __fsid, *fsid = NULL; @@ -1718,6 +1757,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, case FAN_MARK_FILESYSTEM: obj_type = FSNOTIFY_OBJ_TYPE_SB; break; + case FAN_MARK_MNTNS: + obj_type = FSNOTIFY_OBJ_TYPE_MNTNS; + break; default: return -EINVAL; } @@ -1765,6 +1807,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EINVAL; group = fd_file(f)->private_data; + /* Only report mount events on mnt namespace */ + if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) { + if (mask & ~FANOTIFY_MOUNT_EVENTS) + return -EINVAL; + if (mark_type != FAN_MARK_MNTNS) + return -EINVAL; + } else { + if (mask & FANOTIFY_MOUNT_EVENTS) + return -EINVAL; + if (mark_type == FAN_MARK_MNTNS) + return -EINVAL; + } + /* * An unprivileged user is not allowed to setup mount nor filesystem * marks. This also includes setting up such marks by a group that @@ -1802,7 +1857,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, * point. */ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); - if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) && + if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) && (!fid_mode || mark_type == FAN_MARK_MOUNT)) return -EINVAL; @@ -1848,17 +1903,21 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } /* inode held in place by reference to path; group by fget on fd */ - if (mark_type == FAN_MARK_INODE) { + if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) { inode = path.dentry->d_inode; obj = inode; - } else { - mnt = path.mnt; - if (mark_type == FAN_MARK_MOUNT) - obj = mnt; - else - obj = mnt->mnt_sb; + } else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { + obj = path.mnt; + } else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) { + obj = path.mnt->mnt_sb; + } else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) { + obj = mnt_ns_from_dentry(path.dentry); } + ret = -EINVAL; + if (!obj) + goto path_put_and_out; + /* * If some other task has this inode open for write we should not add * an ignore mask, unless that ignore mask is supposed to survive @@ -1866,10 +1925,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, */ if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) && !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) { - ret = mnt ? -EINVAL : -EISDIR; + ret = !inode ? -EINVAL : -EISDIR; /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */ if (ignore == FAN_MARK_IGNORE && - (mnt || S_ISDIR(inode->i_mode))) + (!inode || S_ISDIR(inode->i_mode))) goto path_put_and_out; ret = 0; @@ -1878,7 +1937,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ - if (mnt || !S_ISDIR(inode->i_mode)) { + if (!inode || !S_ISDIR(inode->i_mode)) { mask &= ~FAN_EVENT_ON_CHILD; umask = FAN_EVENT_ON_CHILD; /* @@ -1952,7 +2011,7 @@ static int __init fanotify_user_setup(void) FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 13); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11); fanotify_mark_cache = KMEM_CACHE(fanotify_mark, @@ -1965,6 +2024,7 @@ static int __init fanotify_user_setup(void) fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event, SLAB_PANIC); } + fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC); fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS; init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] = diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index e933f9c65d90..1161eabf11ee 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -121,6 +121,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n", sb->s_dev, mflags, mark->mask, mark->ignore_mask); + } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) { + struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector); + + seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n", + mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask); } } diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 89ff45bd6f01..fc142be2542d 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ #define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) -#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT) /* * fanotify_init() flags that require CAP_SYS_ADMIN. @@ -38,7 +38,8 @@ FAN_REPORT_PIDFD | \ FAN_REPORT_FD_ERROR | \ FAN_UNLIMITED_QUEUE | \ - FAN_UNLIMITED_MARKS) + FAN_UNLIMITED_MARKS | \ + FAN_REPORT_MNT) /* * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN. @@ -58,7 +59,7 @@ #define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ - FAN_MARK_FILESYSTEM) + FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS) #define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ FAN_MARK_FLUSH) @@ -99,10 +100,13 @@ /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ #define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) +#define FANOTIFY_MOUNT_EVENTS (FAN_MNT_ATTACH | FAN_MNT_DETACH) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ FANOTIFY_INODE_EVENTS | \ - FANOTIFY_ERROR_EVENTS) + FANOTIFY_ERROR_EVENTS | \ + FANOTIFY_MOUNT_EVENTS) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 34f221d3a1b9..69340e483ae7 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -25,6 +25,8 @@ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ #define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ +#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */ +#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ @@ -61,6 +63,7 @@ #define FAN_REPORT_NAME 0x00000800 /* Report events with name */ #define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ #define FAN_REPORT_FD_ERROR 0x00002000 /* event->fd can report error */ +#define FAN_REPORT_MNT 0x00004000 /* Report mount events */ /* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ #define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) @@ -91,6 +94,7 @@ #define FAN_MARK_INODE 0x00000000 #define FAN_MARK_MOUNT 0x00000010 #define FAN_MARK_FILESYSTEM 0x00000100 +#define FAN_MARK_MNTNS 0x00000110 /* * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY @@ -143,6 +147,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 #define FAN_EVENT_INFO_TYPE_ERROR 5 +#define FAN_EVENT_INFO_TYPE_MNT 6 /* Special info types for FAN_RENAME */ #define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 @@ -189,6 +194,11 @@ struct fanotify_event_info_error { __u32 error_count; }; +struct fanotify_event_info_mnt { + struct fanotify_event_info_header hdr; + __u64 mnt_id; +}; + /* * User space may need to record additional information about its decision. * The extra information type records what kind of information is included. diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 171dd7fceac5..d2b3e60e2be9 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3395,6 +3395,10 @@ static int selinux_path_notify(const struct path *path, u64 mask, case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; + case FSNOTIFY_OBJ_TYPE_MNTNS: + /* FIXME: Is this correct??? */ + perm = FILE__WATCH; + break; default: return -EINVAL; }
Add notifications for attaching and detaching mounts. The following new event masks are added: FAN_MNT_ATTACH - Mount was attached FAN_MNT_DETACH - Mount was detached If a mount is moved, then the event is reported with (FAN_MNT_ATTACH | FAN_MNT_DETACH). These events add an info record of type FAN_EVENT_INFO_TYPE_MNT containing these fields identifying the affected mounts: __u64 mnt_id - the ID of the mount (see statmount(2)) FAN_REPORT_MNT must be supplied to fanotify_init() to receive these events and no other type of event can be received with this report type. Marks are added with FAN_MARK_MNTNS, which records the mount namespace from an nsfs file (e.g. /proc/self/ns/mnt). Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> --- fs/mount.h | 2 + fs/namespace.c | 14 +++-- fs/notify/fanotify/fanotify.c | 38 +++++++++++-- fs/notify/fanotify/fanotify.h | 18 +++++++ fs/notify/fanotify/fanotify_user.c | 86 +++++++++++++++++++++++++----- fs/notify/fdinfo.c | 5 ++ include/linux/fanotify.h | 12 +++-- include/uapi/linux/fanotify.h | 10 ++++ security/selinux/hooks.c | 4 ++ 9 files changed, 166 insertions(+), 23 deletions(-)