diff options
Diffstat (limited to 'fs/notify')
| -rw-r--r-- | fs/notify/dnotify/dnotify.c | 8 | ||||
| -rw-r--r-- | fs/notify/fanotify/fanotify.c | 49 | ||||
| -rw-r--r-- | fs/notify/fanotify/fanotify.h | 27 | ||||
| -rw-r--r-- | fs/notify/fanotify/fanotify_user.c | 144 | ||||
| -rw-r--r-- | fs/notify/fdinfo.c | 5 | ||||
| -rw-r--r-- | fs/notify/fsnotify.c | 132 | ||||
| -rw-r--r-- | fs/notify/fsnotify.h | 11 | ||||
| -rw-r--r-- | fs/notify/mark.c | 14 |
8 files changed, 296 insertions, 94 deletions
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index c4cdaf5fa7ed..9fb73bafd41d 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -308,6 +308,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } + error = file_f_owner_allocate(filp); + if (error) + goto out_err; + /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { @@ -315,10 +319,6 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } - error = file_f_owner_allocate(filp); - if (error) - goto out_err; - /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 95646f7c46ca..bfe884d624e7 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); } @@ -312,7 +314,10 @@ 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; @@ -410,7 +415,7 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, { int dwords, type = 0; char *ext_buf = NULL; - void *buf = fh->buf; + void *buf = fh + 1; int err; fh->type = FILEID_ROOT; @@ -449,7 +454,13 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, dwords = fh_len >> 2; type = exportfs_encode_fid(inode, buf, &dwords); err = -EINVAL; - if (type <= 0 || type == FILEID_INVALID || fh_len != dwords << 2) + /* + * Unlike file_handle, type and len of struct fanotify_fh are u8. + * Traditionally, filesystem return handle_type < 0xff, but there + * is no enforecement for that in vfs. + */ + BUILD_BUG_ON(MAX_HANDLE_SZ > 0xff || FILEID_INVALID > 0xff); + if (type <= 0 || type >= FILEID_INVALID || fh_len != dwords << 2) goto out_err; fh->type = type; @@ -557,6 +568,20 @@ 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 void *data, int data_type, gfp_t gfp) @@ -731,6 +756,7 @@ 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; @@ -826,8 +852,12 @@ 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) @@ -927,7 +957,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_RENAME != FS_RENAME); BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 24); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); @@ -985,6 +1015,7 @@ finish: static void fanotify_free_group_priv(struct fsnotify_group *group) { + put_user_ns(group->user_ns); kfree(group->fanotify_data.merge_hash); if (group->fanotify_data.ucounts) dec_ucount(group->fanotify_data.ucounts, @@ -1028,6 +1059,11 @@ 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) { @@ -1054,6 +1090,9 @@ 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 c12cbc270539..b78308975082 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 { @@ -24,7 +25,7 @@ enum { * stored in either the first or last 2 dwords. */ #define FANOTIFY_INLINE_FH_LEN (3 << 2) -#define FANOTIFY_FH_HDR_LEN offsetof(struct fanotify_fh, buf) +#define FANOTIFY_FH_HDR_LEN sizeof(struct fanotify_fh) /* Fixed size struct for file handle */ struct fanotify_fh { @@ -33,7 +34,6 @@ struct fanotify_fh { #define FANOTIFY_FH_FLAG_EXT_BUF 1 u8 flags; u8 pad; - unsigned char buf[]; } __aligned(4); /* Variable size struct for dir file handle + child file handle + name */ @@ -91,7 +91,7 @@ static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh) BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4); BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) > FANOTIFY_INLINE_FH_LEN); - return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *)); + return (char **)ALIGN((unsigned long)(fh + 1), __alignof__(char *)); } static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh) @@ -101,7 +101,7 @@ static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh) static inline void *fanotify_fh_buf(struct fanotify_fh *fh) { - return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf; + return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh + 1; } static inline int fanotify_info_dir_fh_len(struct fanotify_info *info) @@ -244,6 +244,7 @@ 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 }; @@ -276,7 +277,7 @@ static inline void fanotify_init_event(struct fanotify_event *event, #define FANOTIFY_INLINE_FH(name, size) \ struct { \ struct fanotify_fh name; \ - /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \ + /* Space for filehandle - access with fanotify_fh_buf() */ \ unsigned char _inline_fh_buf[size]; \ } @@ -409,12 +410,23 @@ 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 @@ -466,6 +478,11 @@ 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 ba3e2d09eb44..b192ee068a7a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -113,6 +113,7 @@ 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 \ @@ -123,6 +124,8 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; (sizeof(struct fanotify_event_info_error)) #define FANOTIFY_RANGE_INFO_LEN \ (sizeof(struct fanotify_event_info_range)) +#define FANOTIFY_MNT_INFO_LEN \ + (sizeof(struct fanotify_event_info_mnt)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -178,6 +181,8 @@ 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; if (info_mode & FAN_REPORT_PIDFD) event_len += FANOTIFY_PIDFD_INFO_LEN; @@ -405,6 +410,25 @@ 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) { @@ -700,6 +724,15 @@ 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; } @@ -1301,6 +1334,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, * A group with FAN_UNLIMITED_MARKS does not contribute to mark count * in the limited groups account. */ + BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_MARKS)); if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) && !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS)) return ERR_PTR(-ENOSPC); @@ -1465,6 +1499,7 @@ static struct hlist_head *fanotify_alloc_merge_hash(void) /* fanotify syscalls */ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) { + struct user_namespace *user_ns = current_user_ns(); struct fsnotify_group *group; int f_flags, fd; unsigned int fid_mode = flags & FANOTIFY_FID_BITS; @@ -1479,10 +1514,11 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) /* * An unprivileged user can setup an fanotify group with * limited functionality - an unprivileged group is limited to - * notification events with file handles and it cannot use - * unlimited queue/marks. + * notification events with file handles or mount ids and it + * cannot use unlimited queue/marks. */ - if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode) + if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || + !(flags & (FANOTIFY_FID_BITS | FAN_REPORT_MNT))) return -EPERM; /* @@ -1508,6 +1544,14 @@ 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; @@ -1553,8 +1597,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) } /* Enforce groups limits per user in all containing user ns */ - group->fanotify_data.ucounts = inc_ucount(current_user_ns(), - current_euid(), + group->fanotify_data.ucounts = inc_ucount(user_ns, current_euid(), UCOUNT_FANOTIFY_GROUPS); if (!group->fanotify_data.ucounts) { fd = -EMFILE; @@ -1563,6 +1606,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.flags = flags | internal_flags; group->memcg = get_mem_cgroup_from_mm(current->mm); + group->user_ns = get_user_ns(user_ns); group->fanotify_data.merge_hash = fanotify_alloc_merge_hash(); if (!group->fanotify_data.merge_hash) { @@ -1596,21 +1640,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } + BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_QUEUE)); if (flags & FAN_UNLIMITED_QUEUE) { - fd = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto out_destroy_group; group->max_events = UINT_MAX; } else { group->max_events = fanotify_max_queued_events; } - if (flags & FAN_UNLIMITED_MARKS) { - fd = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto out_destroy_group; - } - if (flags & FAN_ENABLE_AUDIT) { fd = -EPERM; if (!capable(CAP_AUDIT_WRITE)) @@ -1767,16 +1803,17 @@ 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; + struct user_namespace *user_ns = NULL; + struct mnt_namespace *mntns; u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS; unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS; unsigned int obj_type, fid_mode; - void *obj; + void *obj = NULL; u32 umask = 0; int ret; @@ -1800,6 +1837,9 @@ 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; } @@ -1847,13 +1887,24 @@ 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 - * was initialized by an unprivileged user. + * A user is allowed to setup sb/mount/mntns marks only if it is + * capable in the user ns where the group was created. */ - if ((!capable(CAP_SYS_ADMIN) || - FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) && + if (!ns_capable(group->user_ns, CAP_SYS_ADMIN) && mark_type != FAN_MARK_INODE) return -EPERM; @@ -1888,7 +1939,7 @@ 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; @@ -1905,12 +1956,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EINVAL; if (mark_cmd == FAN_MARK_FLUSH) { - if (mark_type == FAN_MARK_MOUNT) - fsnotify_clear_vfsmount_marks_by_group(group); - else if (mark_type == FAN_MARK_FILESYSTEM) - fsnotify_clear_sb_marks_by_group(group); - else - fsnotify_clear_inode_marks_by_group(group); + fsnotify_clear_marks_by_group(group, obj_type); return 0; } @@ -1937,18 +1983,35 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, fsid = &__fsid; } - /* inode held in place by reference to path; group by fget on fd */ - if (mark_type == FAN_MARK_INODE) { + /* + * In addition to being capable in the user ns where group was created, + * the user also needs to be capable in the user ns associated with + * the filesystem or in the user ns associated with the mntns + * (when marking mntns). + */ + 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) { + user_ns = path.mnt->mnt_sb->s_user_ns; + obj = path.mnt; + } else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) { + user_ns = path.mnt->mnt_sb->s_user_ns; + obj = path.mnt->mnt_sb; + } else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) { + mntns = mnt_ns_from_dentry(path.dentry); + user_ns = mntns->user_ns; + obj = mntns; } + ret = -EPERM; + if (user_ns && !ns_capable(user_ns, CAP_SYS_ADMIN)) + goto path_put_and_out; + + 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 @@ -1956,10 +2019,10 @@ 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; @@ -1968,7 +2031,7 @@ 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; /* @@ -2042,7 +2105,7 @@ 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, @@ -2055,6 +2118,7 @@ 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/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 8ee495a58d0a..079b868552c2 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -28,6 +28,11 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) fsnotify_clear_marks_by_mount(mnt); } +void __fsnotify_mntns_delete(struct mnt_namespace *mntns) +{ + fsnotify_clear_marks_by_mntns(mntns); +} + /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. @@ -194,8 +199,8 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, } /* Are there any inode/mount/sb objects that watch for these events? */ -static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, - __u32 mask) +static inline __u32 fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, + __u32 mask) { __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | READ_ONCE(inode->i_sb->s_fsnotify_mask); @@ -420,7 +425,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type, file_name, cookie, iter_info); } -static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp) +static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; @@ -538,14 +543,15 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); - struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); + const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); + struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL; struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; - __u32 test_mask, marks_mask; + __u32 test_mask, marks_mask = 0; if (path) mnt = real_mount(path->mnt); @@ -578,17 +584,20 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, if ((!sbinfo || !sbinfo->sb_marks) && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && - (!inode2 || !inode2->i_fsnotify_marks)) + (!inode2 || !inode2->i_fsnotify_marks) && + (!mnt_data || !mnt_data->ns->n_fsnotify_marks)) return 0; - marks_mask = READ_ONCE(sb->s_fsnotify_mask); + if (sb) + marks_mask |= READ_ONCE(sb->s_fsnotify_mask); if (mnt) marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); - + if (mnt_data) + marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask); /* * If this is a modify event we may need to clear some ignore masks. @@ -618,6 +627,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } + if (mnt_data) { + iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] = + fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks); + } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark @@ -643,20 +656,20 @@ EXPORT_SYMBOL_GPL(fsnotify); #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* - * At open time we check fsnotify_sb_has_priority_watchers() and set the - * FMODE_NONOTIFY_ mode bits accordignly. + * At open time we check fsnotify_sb_has_priority_watchers(), call the open perm + * hook and set the FMODE_NONOTIFY_ mode bits accordignly. * Later, fsnotify permission hooks do not check if there are permission event * watches, but that there were permission event watches at open time. */ -void file_set_fsnotify_mode(struct file *file) +int fsnotify_open_perm_and_set_mode(struct file *file) { struct dentry *dentry = file->f_path.dentry, *parent; struct super_block *sb = dentry->d_sb; - __u32 mnt_mask, p_mask; + __u32 mnt_mask, p_mask = 0; /* Is it a file opened by fanotify? */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) - return; + return 0; /* * Permission events is a super set of pre-content events, so if there @@ -665,48 +678,93 @@ void file_set_fsnotify_mode(struct file *file) */ if (likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT))) { - file->f_mode |= FMODE_NONOTIFY_PERM; - return; + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); + return 0; + } + + /* + * OK, there are some permission event watchers. Check if anybody is + * watching for permission events on *this* file. + */ + mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); + p_mask = fsnotify_object_watched(d_inode(dentry), mnt_mask, + ALL_FSNOTIFY_PERM_EVENTS); + if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { + parent = dget_parent(dentry); + p_mask |= fsnotify_inode_watches_children(d_inode(parent)); + dput(parent); + } + + /* + * Legacy FAN_ACCESS_PERM events have very high performance overhead, + * so unlikely to be used in the wild. If they are used there will be + * no optimizations at all. + */ + if (unlikely(p_mask & FS_ACCESS_PERM)) { + /* Enable all permission and pre-content events */ + file_set_fsnotify_mode(file, 0); + goto open_perm; } /* - * If there are permission event watchers but no pre-content event + * Pre-content events are only supported on regular files. + * If there are pre-content event watchers and no permission access * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. + * That is the common case with HSM service. */ - if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || - likely(!fsnotify_sb_has_priority_watchers(sb, - FSNOTIFY_PRIO_PRE_CONTENT))) { - file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; - return; + if (d_is_reg(dentry) && (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)) { + file_set_fsnotify_mode(file, FMODE_NONOTIFY | + FMODE_NONOTIFY_PERM); + goto open_perm; } + /* Nobody watching permission and pre-content events on this file */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); + +open_perm: /* - * OK, there are some pre-content watchers. Check if anybody is - * watching for pre-content events on *this* file. + * Send open perm events depending on object masks and regardless of + * FMODE_NONOTIFY_PERM. */ - mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); - if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask, - FSNOTIFY_PRE_CONTENT_EVENTS))) - return; + if (file->f_flags & __FMODE_EXEC && p_mask & FS_OPEN_EXEC_PERM) { + int ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); - /* Is parent watching for pre-content events on this file? */ - if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { - parent = dget_parent(dentry); - p_mask = fsnotify_inode_watches_children(d_inode(parent)); - dput(parent); - if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) - return; + if (ret) + return ret; } - /* Nobody watching for pre-content events from this file */ - file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; + + if (p_mask & FS_OPEN_PERM) + return fsnotify_path(&file->f_path, FS_OPEN_PERM); + + return 0; } #endif +void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) +{ + struct fsnotify_mnt data = { + .ns = ns, + .mnt_id = real_mount(mnt)->mnt_id_unique, + }; + + if (WARN_ON_ONCE(!ns)) + return; + + /* + * This is an optimization as well as making sure fsnotify_init() has + * been called. + */ + if (!ns->n_fsnotify_marks) + return; + + fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0); +} + static __init int fsnotify_init(void) { int ret; - BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24); + BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index 663759ed6fbc..5950c7a67f41 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -33,6 +33,12 @@ static inline struct super_block *fsnotify_conn_sb( return conn->obj; } +static inline struct mnt_namespace *fsnotify_conn_mntns( + struct fsnotify_mark_connector *conn) +{ + return conn->obj; +} + static inline struct super_block *fsnotify_object_sb(void *obj, enum fsnotify_obj_type obj_type) { @@ -89,6 +95,11 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) fsnotify_destroy_marks(fsnotify_sb_marks(sb)); } +static inline void fsnotify_clear_marks_by_mntns(struct mnt_namespace *mntns) +{ + fsnotify_destroy_marks(&mntns->n_fsnotify_marks); +} + /* * update the dentry->d_flags of all of inode's children to indicate if inode cares * about events that happen to its children. diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 4981439e6209..798340db69d7 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -107,6 +107,8 @@ static fsnotify_connp_t *fsnotify_object_connp(void *obj, return &real_mount(obj)->mnt_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_sb_marks(obj); + case FSNOTIFY_OBJ_TYPE_MNTNS: + return &((struct mnt_namespace *)obj)->n_fsnotify_marks; default: return NULL; } @@ -120,6 +122,8 @@ static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; + else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) + return &fsnotify_conn_mntns(conn)->n_fsnotify_mask; return NULL; } @@ -346,12 +350,15 @@ static void *fsnotify_detach_connector_from_object( fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; + } else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) { + fsnotify_conn_mntns(conn)->n_fsnotify_mask = 0; } rcu_assign_pointer(*connp, NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; - fsnotify_update_sb_watchers(sb, conn); + if (sb) + fsnotify_update_sb_watchers(sb, conn); return inode; } @@ -724,7 +731,7 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj, * Attach the sb info before attaching a connector to any object on sb. * The sb info will remain attached as long as sb lives. */ - if (!fsnotify_sb_info(sb)) { + if (sb && !fsnotify_sb_info(sb)) { err = fsnotify_attach_info_to_sb(sb); if (err) return err; @@ -770,7 +777,8 @@ restart: /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: - fsnotify_update_sb_watchers(sb, conn); + if (sb) + fsnotify_update_sb_watchers(sb, conn); /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone |