diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 106f0e8af177..8054f44d39cf 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1257,7 +1257,7 @@ out_free_interp: } reloc_func_desc = interp_load_addr; - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); kfree(interp_elf_ex); @@ -1354,7 +1354,7 @@ out_free_dentry: kfree(interp_elf_ex); kfree(interp_elf_phdata); out_free_file: - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); if (interpreter) fput(interpreter); out_free_ph: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index f1a7c4875c4a..c13ee8180b17 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -394,7 +394,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) goto error; } - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); interpreter = NULL; } @@ -467,7 +467,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) error: if (interpreter) { - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); } kfree(interpreter_name); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7872de140489..583107ce4fa6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2544,6 +2544,15 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } + /* + * Don't allow defrag on pre-content watched files, as it could + * populate the page cache with 0's via readahead. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + ret = -EINVAL; + goto out; + } + if (argp) { if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index df69d9f63d6b..379b534952eb 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -961,7 +961,7 @@ static int btrfs_fill_super(struct super_block *sb, #endif sb->s_xattr = btrfs_xattr_handlers; sb->s_time_gran = 1; - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; err = super_setup_bdi(sb); if (err) { diff --git a/fs/exec.c b/fs/exec.c index 98cb7ba9983c..c41cfd35c74c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -912,7 +912,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) path_noexec(&file->f_path)) return ERR_PTR(-EACCES); - err = deny_write_access(file); + err = exe_file_deny_write_access(file); if (err) return ERR_PTR(err); @@ -927,7 +927,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers - * must call allow_write_access() before fput() on release. Also see + * must call exe_file_allow_write_access() before fput() on release. Also see * do_close_execat(). */ struct file *open_exec(const char *name) @@ -1471,7 +1471,7 @@ static void do_close_execat(struct file *file) { if (!file) return; - allow_write_access(file); + exe_file_allow_write_access(file); fput(file); } @@ -1797,7 +1797,7 @@ static int exec_binprm(struct linux_binprm *bprm) bprm->file = bprm->interpreter; bprm->interpreter = NULL; - allow_write_access(exec); + exe_file_allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3bd96c3d4cd0..a5205149adba 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -756,6 +756,9 @@ retry: return VM_FAULT_SIGBUS; } } else { + result = filemap_fsnotify_fault(vmf); + if (unlikely(result)) + return result; filemap_invalidate_lock_shared(mapping); } result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 785809f33ff4..029fc5fc4ffe 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5312,6 +5312,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; + /* HSM events are allowed by default. */ + sb->s_iflags |= SB_I_ALLOW_HSM; + err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; diff --git a/fs/fcntl.c b/fs/fcntl.c index 49884fa3c81d..5598e4d57422 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -1158,10 +1158,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | - __FMODE_EXEC | __FMODE_NONOTIFY)); + __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index 34d5baa5d88a..5f3b6da0e022 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -301,7 +301,6 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, */ static int zisofs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; int err; @@ -311,16 +310,15 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) PAGE_SHIFT <= zisofs_block_shift ? (1 << (zisofs_block_shift - PAGE_SHIFT)) : 0; struct page **pages; - pgoff_t index = page->index, end_index; + pgoff_t index = folio->index, end_index; end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; /* - * If this page is wholly outside i_size we just return zero; + * If this folio is wholly outside i_size we just return zero; * do_generic_file_read() will handle this for us */ if (index >= end_index) { - SetPageUptodate(page); - unlock_page(page); + folio_end_read(folio, true); return 0; } @@ -338,10 +336,10 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) pages = kcalloc(max_t(unsigned int, zisofs_pages_per_cblock, 1), sizeof(*pages), GFP_KERNEL); if (!pages) { - unlock_page(page); + folio_unlock(folio); return -ENOMEM; } - pages[full_page] = page; + pages[full_page] = &folio->page; for (i = 0; i < pcount; i++, index++) { if (i != full_page) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 24c7c5df4998..95646f7c46ca 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -223,7 +223,7 @@ static int fanotify_get_response(struct fsnotify_group *group, struct fanotify_perm_event *event, struct fsnotify_iter_info *iter_info) { - int ret; + int ret, errno; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -262,14 +262,23 @@ static int fanotify_get_response(struct fsnotify_group *group, ret = 0; break; case FAN_DENY: + /* Check custom errno from pre-content events */ + errno = fanotify_get_response_errno(event->response); + if (errno) { + ret = -errno; + break; + } + fallthrough; default: ret = -EPERM; } /* Check if the response should be audited */ - if (event->response & FAN_AUDIT) - audit_fanotify(event->response & ~FAN_AUDIT, - &event->audit_rule); + if (event->response & FAN_AUDIT) { + u32 response = event->response & + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS); + audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule); + } pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, group, event, ret); @@ -548,9 +557,13 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path, return &pevent->fae; } -static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, +static struct fanotify_event *fanotify_alloc_perm_event(const void *data, + int data_type, gfp_t gfp) { + const struct path *path = fsnotify_data_path(data, data_type); + const struct file_range *range = + fsnotify_data_file_range(data, data_type); struct fanotify_perm_event *pevent; pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); @@ -564,6 +577,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; + /* NULL ppos means no range info */ + pevent->ppos = range ? &range->pos : NULL; + pevent->count = range ? range->count : 0; path_get(path); return &pevent->fae; @@ -801,7 +817,7 @@ static struct fanotify_event *fanotify_alloc_event( old_memcg = set_active_memcg(group->memcg); if (fanotify_is_perm_event(mask)) { - event = fanotify_alloc_perm_event(path, gfp); + event = fanotify_alloc_perm_event(data, data_type, gfp); } else if (fanotify_is_error_event(mask)) { event = fanotify_alloc_error_event(group, fsid, data, data_type, &hash); @@ -909,8 +925,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(FAN_RENAME != FS_RENAME); + BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index e5ab33cae6a7..c12cbc270539 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -425,6 +425,8 @@ FANOTIFY_PE(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; + const loff_t *ppos; /* optional file range info */ + size_t count; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ @@ -446,6 +448,14 @@ static inline bool fanotify_is_perm_event(u32 mask) mask & FANOTIFY_PERM_EVENTS; } +static inline bool fanotify_event_has_access_range(struct fanotify_event *event) +{ + if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS)) + return false; + + return FANOTIFY_PERM(event)->ppos; +} + static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct fanotify_event, fse); @@ -518,3 +528,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark) return mflags; } + +static inline u32 fanotify_get_response_errno(int res) +{ + return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK; +} diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 2d85c71717d6..19435cd2c41f 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -100,8 +100,7 @@ static void __init fanotify_sysctls_init(void) * * Internal and external open flags are stored together in field f_flags of * struct file. Only external open flags shall be allowed in event_f_flags. - * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be - * excluded. + * Internal flags like FMODE_EXEC shall be excluded. */ #define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \ O_ACCMODE | O_APPEND | O_NONBLOCK | \ @@ -118,10 +117,12 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) -#define FANOTIFY_PIDFD_INFO_HDR_LEN \ +#define FANOTIFY_PIDFD_INFO_LEN \ sizeof(struct fanotify_event_info_pidfd) #define FANOTIFY_ERROR_INFO_LEN \ (sizeof(struct fanotify_event_info_error)) +#define FANOTIFY_RANGE_INFO_LEN \ + (sizeof(struct fanotify_event_info_range)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -159,9 +160,6 @@ static size_t fanotify_event_len(unsigned int info_mode, int fh_len; int dot_len = 0; - if (!info_mode) - return event_len; - if (fanotify_is_error_event(event->mask)) event_len += FANOTIFY_ERROR_INFO_LEN; @@ -176,14 +174,17 @@ static size_t fanotify_event_len(unsigned int info_mode, dot_len = 1; } - if (info_mode & FAN_REPORT_PIDFD) - event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; - if (fanotify_event_has_object_fh(event)) { fh_len = fanotify_event_object_fh_len(event); event_len += fanotify_fid_info_len(fh_len, dot_len); } + if (info_mode & FAN_REPORT_PIDFD) + event_len += FANOTIFY_PIDFD_INFO_LEN; + + if (fanotify_event_has_access_range(event)) + event_len += FANOTIFY_RANGE_INFO_LEN; + return event_len; } @@ -258,12 +259,11 @@ static int create_fd(struct fsnotify_group *group, const struct path *path, return client_fd; /* - * we need a new file handle for the userspace program so it can read even if it was - * originally opened O_WRONLY. + * We provide an fd for the userspace program, so it could access the + * file without generating fanotify events itself. */ - new_file = dentry_open(path, - group->fanotify_data.f_flags | __FMODE_NONOTIFY, - current_cred()); + new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags, + current_cred()); if (IS_ERR(new_file)) { put_unused_fd(client_fd); client_fd = PTR_ERR(new_file); @@ -327,11 +327,12 @@ static int process_access_response(struct fsnotify_group *group, struct fanotify_perm_event *event; int fd = response_struct->fd; u32 response = response_struct->response; + int errno = fanotify_get_response_errno(response); int ret = info_len; struct fanotify_response_info_audit_rule friar; - pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__, - group, fd, response, info, info_len); + pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n", + __func__, group, fd, response, errno, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the @@ -342,7 +343,31 @@ static int process_access_response(struct fsnotify_group *group, switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: + if (errno) + return -EINVAL; + break; case FAN_DENY: + /* Custom errno is supported only for pre-content groups */ + if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT) + return -EINVAL; + + /* + * Limit errno to values expected on open(2)/read(2)/write(2) + * of regular files. + */ + switch (errno) { + case 0: + case EIO: + case EPERM: + case EBUSY: + case ETXTBSY: + case EAGAIN: + case ENOSPC: + case EDQUOT: + break; + default: + return -EINVAL; + } break; default: return -EINVAL; @@ -506,7 +531,7 @@ static int copy_pidfd_info_to_user(int pidfd, size_t count) { struct fanotify_event_info_pidfd info = { }; - size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN; + size_t info_len = FANOTIFY_PIDFD_INFO_LEN; if (WARN_ON_ONCE(info_len > count)) return -EFAULT; @@ -521,6 +546,30 @@ static int copy_pidfd_info_to_user(int pidfd, return info_len; } +static size_t copy_range_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_perm_event *pevent = FANOTIFY_PERM(event); + struct fanotify_event_info_range info = { }; + size_t info_len = FANOTIFY_RANGE_INFO_LEN; + + if (WARN_ON_ONCE(info_len > count)) + return -EFAULT; + + if (WARN_ON_ONCE(!pevent->ppos)) + return -EINVAL; + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; + info.hdr.len = info_len; + info.offset = *(pevent->ppos); + info.count = pevent->count; + + if (copy_to_user(buf, &info, info_len)) + return -EFAULT; + + return info_len; +} + static int copy_info_records_to_user(struct fanotify_event *event, struct fanotify_info *info, unsigned int info_mode, int pidfd, @@ -642,6 +691,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_event_has_access_range(event)) { + ret = copy_range_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } @@ -756,12 +814,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, buf += FAN_EVENT_METADATA_LEN; count -= FAN_EVENT_METADATA_LEN; - if (info_mode) { - ret = copy_info_records_to_user(event, info, info_mode, pidfd, - buf, count); - if (ret < 0) - goto out_close_fd; - } + ret = copy_info_records_to_user(event, info, info_mode, pidfd, + buf, count); + if (ret < 0) + goto out_close_fd; if (f) fd_install(fd, f); @@ -1294,7 +1350,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group) } static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, - unsigned int fan_flags) + __u32 mask, unsigned int fan_flags) { /* * Non evictable mark cannot be downgraded to evictable mark. @@ -1321,6 +1377,11 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) return -EEXIST; + /* For now pre-content events are not generated for directories */ + mask |= fsn_mark->mask; + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EEXIST; + return 0; } @@ -1347,7 +1408,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, /* * Check if requested mark flags conflict with an existing mark flags. */ - ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags); + ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags); if (ret) goto out; @@ -1409,6 +1470,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; unsigned int internal_flags = 0; + struct file *file; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1477,7 +1539,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) return -EINVAL; - f_flags = O_RDWR | __FMODE_NONOTIFY; + f_flags = O_RDWR; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; if (flags & FAN_NONBLOCK) @@ -1555,10 +1617,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } - fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); + fd = get_unused_fd_flags(f_flags); if (fd < 0) goto out_destroy_group; + file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group, + f_flags, FMODE_NONOTIFY); + if (IS_ERR(file)) { + fd = PTR_ERR(file); + put_unused_fd(fd); + goto out_destroy_group; + } + fd_install(fd, file); return fd; out_destroy_group: @@ -1638,11 +1708,23 @@ static int fanotify_events_supported(struct fsnotify_group *group, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + bool is_dir = d_is_dir(path->dentry); /* Strict validation of events in non-dir inode mask with v5.17+ APIs */ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) || (mask & FAN_RENAME) || (flags & FAN_MARK_IGNORE); + /* + * Filesystems need to opt-into pre-content evnets (a.k.a HSM) + * and they are only supported on regular files and directories. + */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS) { + if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM)) + return -EOPNOTSUPP; + if (!is_dir && !d_is_reg(path->dentry)) + return -EINVAL; + } + /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of @@ -1675,7 +1757,7 @@ static int fanotify_events_supported(struct fsnotify_group *group, * but because we always allowed it, error only when using new APIs. */ if (strict_dir_events && mark_type == FAN_MARK_INODE && - !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) + !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) return -ENOTDIR; return 0; @@ -1776,10 +1858,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EPERM; /* - * Permission events require minimum priority FAN_CLASS_CONTENT. + * Permission events are not allowed for FAN_CLASS_NOTIF. + * Pre-content permission events are not allowed for FAN_CLASS_CONTENT. */ if (mask & FANOTIFY_PERM_EVENTS && - group->priority < FSNOTIFY_PRIO_CONTENT) + group->priority == FSNOTIFY_PRIO_NORMAL) + return -EINVAL; + else if (mask & FANOTIFY_PRE_CONTENT_EVENTS && + group->priority == FSNOTIFY_PRIO_CONTENT) return -EINVAL; if (mask & FAN_FS_ERROR && @@ -1814,6 +1900,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) return -EINVAL; + /* Pre-content events are not currently generated for directories. */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EINVAL; + if (mark_cmd == FAN_MARK_FLUSH) { if (mark_type == FAN_MARK_MOUNT) fsnotify_clear_vfsmount_marks_by_group(group); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f976949d2634..8ee495a58d0a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -193,7 +193,7 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, return mask & marks_mask; } -/* Are there any inode/mount/sb objects that are interested in this event? */ +/* 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) { @@ -203,6 +203,24 @@ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } +/* Report pre-content event with optional range info */ +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count) +{ + struct file_range range; + + /* Report page aligned range only when pos is known */ + if (!ppos) + return fsnotify_path(path, FS_PRE_ACCESS); + + range.path = path; + range.pos = PAGE_ALIGN_DOWN(*ppos); + range.count = PAGE_ALIGN(*ppos + count) - range.pos; + + return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, + FSNOTIFY_EVENT_FILE_RANGE); +} + /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with @@ -623,11 +641,72 @@ out: } 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. + * 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) +{ + struct dentry *dentry = file->f_path.dentry, *parent; + struct super_block *sb = dentry->d_sb; + __u32 mnt_mask, p_mask; + + /* Is it a file opened by fanotify? */ + if (FMODE_FSNOTIFY_NONE(file->f_mode)) + return; + + /* + * Permission events is a super set of pre-content events, so if there + * are no permission event watchers, there are also no pre-content event + * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. + */ + if (likely(!fsnotify_sb_has_priority_watchers(sb, + FSNOTIFY_PRIO_CONTENT))) { + file->f_mode |= FMODE_NONOTIFY_PERM; + return; + } + + /* + * If there are permission event watchers but no pre-content event + * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. + */ + 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; + } + + /* + * OK, there are some pre-content watchers. Check if anybody is + * watching for pre-content events on *this* file. + */ + 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; + + /* 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; + } + /* Nobody watching for pre-content events from this file */ + file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; +} +#endif + static __init int fsnotify_init(void) { int ret; - BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); + BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 993375f0db67..cd7d11b0eb08 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -121,7 +121,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, event->sync_cookie = cookie; event->name_len = len; if (len) - strcpy(event->name, name->name); + strscpy(event->name, name->name, event->name_len + 1); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { diff --git a/fs/open.c b/fs/open.c index e6911101fe71..d11d373dca80 100644 --- a/fs/open.c +++ b/fs/open.c @@ -81,14 +81,18 @@ long vfs_truncate(const struct path *path, loff_t length) if (!S_ISREG(inode->i_mode)) return -EINVAL; - error = mnt_want_write(path->mnt); - if (error) - goto out; - idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) - goto mnt_drop_write_and_out; + return error; + + error = fsnotify_truncate_perm(path, length); + if (error) + return error; + + error = mnt_want_write(path->mnt); + if (error) + return error; error = -EPERM; if (IS_APPEND(inode)) @@ -114,7 +118,7 @@ put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); -out: + return error; } EXPORT_SYMBOL_GPL(vfs_truncate); @@ -175,11 +179,18 @@ long do_ftruncate(struct file *file, loff_t length, int small) /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; - sb_start_write(inode->i_sb); + error = security_file_truncate(file); - if (!error) - error = do_truncate(file_mnt_idmap(file), dentry, length, - ATTR_MTIME | ATTR_CTIME, file); + if (error) + return error; + + error = fsnotify_truncate_perm(&file->f_path, length); + if (error) + return error; + + sb_start_write(inode->i_sb); + error = do_truncate(file_mnt_idmap(file), dentry, length, + ATTR_MTIME | ATTR_CTIME, file); sb_end_write(inode->i_sb); return error; @@ -901,7 +912,7 @@ static int do_dentry_open(struct file *f, f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { - f->f_mode = FMODE_PATH | FMODE_OPENED; + f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY; f->f_op = &empty_fops; return 0; } @@ -929,6 +940,12 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; + /* + * Set FMODE_NONOTIFY_* bits according to existing permission watches. + * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't + * change anything. + */ + file_set_fsnotify_mode(f); error = fsnotify_open_perm(f); if (error) goto cleanup_all; @@ -1105,6 +1122,23 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred) +{ + struct file *f = alloc_empty_file(flags, cred); + if (!IS_ERR(f)) { + int error; + + f->f_mode |= FMODE_NONOTIFY; + error = vfs_open(path, f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + } + return f; +} + /** * dentry_create - Create and open a file * @path: path to create @@ -1202,7 +1236,7 @@ inline struct open_how build_open_how(int flags, umode_t mode) inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; - u64 strip = __FMODE_NONOTIFY | O_CLOEXEC; + u64 strip = O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); @@ -1210,9 +1244,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) "struct open_flags doesn't yet handle flags > 32 bits"); /* - * Strip flags that either shouldn't be set by userspace like - * FMODE_NONOTIFY or that aren't relevant in determining struct - * open_flags like O_CLOEXEC. + * Strip flags that aren't relevant in determining struct open_flags. */ flags &= ~strip; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 9a435b1ff264..f7a7d89c345e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1451,6 +1451,9 @@ xfs_dax_read_fault( trace_xfs_read_fault(ip, order); + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; xfs_ilock(ip, XFS_MMAPLOCK_SHARED); ret = xfs_dax_fault_locked(vmf, order, false); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); @@ -1479,6 +1482,16 @@ xfs_write_fault( vm_fault_t ret; trace_xfs_write_fault(ip, order); + /* + * Usually we get here from ->page_mkwrite callback but in case of DAX + * we will get here also for ordinary write fault. Handle HSM + * notifications for that case. + */ + if (IS_DAX(inode)) { + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; + } sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 394fdf3bb535..8524b9d42873 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1730,7 +1730,7 @@ xfs_fs_fill_super( sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 89ff45bd6f01..78f660ebc318 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -89,6 +89,16 @@ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ FAN_RENAME) +/* Content events can be used to inspect file content */ +#define FANOTIFY_CONTENT_PERM_EVENTS (FAN_OPEN_PERM | FAN_OPEN_EXEC_PERM | \ + FAN_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FANOTIFY_PRE_CONTENT_EVENTS (FAN_PRE_ACCESS) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FANOTIFY_CONTENT_PERM_EVENTS | \ + FANOTIFY_PRE_CONTENT_EVENTS) + /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) @@ -104,10 +114,6 @@ FANOTIFY_INODE_EVENTS | \ FANOTIFY_ERROR_EVENTS) -/* Events that require a permission response from user */ -#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ - FAN_OPEN_EXEC_PERM) - /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) @@ -126,7 +132,9 @@ /* These masks check for invalid bits in permission responses. */ #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) -#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) +#define FANOTIFY_RESPONSE_VALID_MASK \ + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \ + (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT)) /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS diff --git a/include/linux/fs.h b/include/linux/fs.h index 7e29433c5ecc..a1230c40fef1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -173,13 +173,20 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* FMODE_* bit 24 */ - /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)(1 << 25)) +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) +/* + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) + +/* + * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) @@ -190,6 +197,32 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) +/* + * The two FMODE_NONOTIFY* define which fsnotify events should not be generated + * for a file. These are the possible values of (f->f_mode & + * FMODE_FSNOTIFY_MASK) and their meaning: + * + * FMODE_NONOTIFY - suppress all (incl. non-permission) events. + * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. + */ +#define FMODE_FSNOTIFY_MASK \ + (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) + +#define FMODE_FSNOTIFY_NONE(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#define FMODE_FSNOTIFY_PERM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ + (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) +#define FMODE_FSNOTIFY_HSM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0) +#else +#define FMODE_FSNOTIFY_PERM(mode) 0 +#define FMODE_FSNOTIFY_HSM(mode) 0 +#endif + + /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -1232,6 +1265,7 @@ extern int send_sigurg(struct file *file); #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ +#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { @@ -2751,6 +2785,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); @@ -3059,6 +3095,28 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } + +/* + * Do not prevent write to executable file when watched by pre-content events. + * + * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at + * the time of file open and remains constant for entire lifetime of the file, + * so if pre-content watches are added post execution or removed before the end + * of the execution, it will not cause i_writecount reference leak. + */ +static inline int exe_file_deny_write_access(struct file *exe_file) +{ + if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return 0; + return deny_write_access(exe_file); +} +static inline void exe_file_allow_write_access(struct file *exe_file) +{ + if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return; + allow_write_access(exe_file); +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3707,11 +3765,9 @@ struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) -#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & __FMODE_NONOTIFY))) +#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 278620e063ab..1a9ef8f6784d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -108,38 +108,35 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } +static inline int fsnotify_path(const struct path *path, __u32 mask) +{ + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); +} + static inline int fsnotify_file(struct file *file, __u32 mask) { - const struct path *path; - /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ - if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) + if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; - path = &file->f_path; - /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ - if (mask & ALL_FSNOTIFY_PERM_EVENTS && - !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, - FSNOTIFY_PRIO_CONTENT)) - return 0; - - return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); + return fsnotify_path(&file->f_path, mask); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + +void file_set_fsnotify_mode(struct file *file); + /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { - __u32 fsnotify_mask = FS_ACCESS_PERM; - /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection @@ -147,14 +144,49 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, */ lockdep_assert_once(file_write_not_started(file)); + if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS))) + return 0; + + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + + /* + * read()/write() and other types of access generate pre-content events. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + int ret = fsnotify_pre_content(&file->f_path, ppos, count); + + if (ret) + return ret; + } + if (!(perm_mask & MAY_READ)) return 0; - return fsnotify_file(file, fsnotify_mask); + /* + * read() also generates the legacy FS_ACCESS_PERM event, so content + * scanners can inspect the content filled by pre-content event. + */ + return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } /* - * fsnotify_file_perm - permission hook before file access + * fsnotify_truncate_perm - permission hook before file truncate + */ +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + struct inode *inode = d_inode(path->dentry); + + if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) || + !fsnotify_sb_has_priority_watchers(inode->i_sb, + FSNOTIFY_PRIO_PRE_CONTENT)) + return 0; + + return fsnotify_pre_content(path, &length, 0); +} + +/* + * fsnotify_file_perm - permission hook before file access (unknown range) */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { @@ -168,22 +200,34 @@ static inline int fsnotify_open_perm(struct file *file) { int ret; + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + if (file->f_flags & __FMODE_EXEC) { - ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); + ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); if (ret) return ret; } - return fsnotify_file(file, FS_OPEN_PERM); + return fsnotify_path(&file->f_path, FS_OPEN_PERM); } #else +static inline void file_set_fsnotify_mode(struct file *file) +{ +} + static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + return 0; +} + static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3ecf7768e577..0d24a21a8e60 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -55,6 +55,9 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ +/* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ /* * Set on inode mark that cares about things that happen to its children. @@ -77,8 +80,14 @@ */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) -#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ - FS_OPEN_EXEC_PERM) +/* Content events can be used to inspect file content */ +#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ + FS_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS) + +#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \ + FSNOTIFY_PRE_CONTENT_EVENTS) /* * This is a list of all events that may get sent to a parent that is watching @@ -285,6 +294,7 @@ static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, + FSNOTIFY_EVENT_FILE_RANGE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, @@ -297,6 +307,17 @@ struct fs_error_report { struct super_block *sb; }; +struct file_range { + const struct path *path; + loff_t pos; + size_t count; +}; + +static inline const struct path *file_range_path(const struct file_range *range) +{ + return range->path; +} + static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { @@ -306,6 +327,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_FILE_RANGE: + return d_inode(file_range_path(data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: @@ -321,6 +344,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry; default: return NULL; } @@ -332,6 +357,8 @@ static inline const struct path *fsnotify_data_path(const void *data, switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data); default: return NULL; } @@ -347,6 +374,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data, return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: @@ -366,6 +395,18 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +static inline const struct file_range *fsnotify_data_file_range( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_FILE_RANGE: + return (struct file_range *)data; + default: + return NULL; + } +} + /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not @@ -854,9 +895,17 @@ static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count); #else +static inline int fsnotify_pre_content(const struct path *path, + const loff_t *ppos, size_t count) +{ + return 0; +} + static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) diff --git a/include/linux/mm.h b/include/linux/mm.h index c39c4945946c..e6c3c9cbcfe5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3420,6 +3420,7 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 80f37a0d40d7..613475285643 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -6,7 +6,6 @@ /* * FMODE_EXEC is 0x20 - * FMODE_NONOTIFY is 0x4000000 * These cannot be used by userspace O_* until internal and external open * flags are split. * -Eric Paris diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 34f221d3a1b9..bd8167979707 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -25,6 +25,9 @@ #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_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FAN_PRE_ACCESS 0x00100000 /* Pre-content access hook */ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ @@ -143,6 +146,7 @@ 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_RANGE 6 /* Special info types for FAN_RENAME */ #define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 @@ -189,6 +193,13 @@ struct fanotify_event_info_error { __u32 error_count; }; +struct fanotify_event_info_range { + struct fanotify_event_info_header hdr; + __u32 pad; + __u64 offset; + __u64 count; +}; + /* * User space may need to record additional information about its decision. * The extra information type records what kind of information is included. @@ -224,6 +235,13 @@ struct fanotify_response_info_audit_rule { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +/* errno other than EPERM can specified in upper byte of deny response */ +#define FAN_ERRNO_BITS 8 +#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS) +#define FAN_ERRNO_MASK ((1 << FAN_ERRNO_BITS) - 1) +#define FAN_DENY_ERRNO(err) \ + (FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT)) + #define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ #define FAN_INFO 0x20 /* Bitmask to indicate additional information */ diff --git a/kernel/fork.c b/kernel/fork.c index 1450b461d196..015c397f47ca 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -625,8 +625,8 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) * We depend on the oldmm having properly denied write access to the * exe_file already. */ - if (exe_file && deny_write_access(exe_file)) - pr_warn_once("deny_write_access() failed in %s\n", __func__); + if (exe_file && exe_file_deny_write_access(exe_file)) + pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU @@ -1424,13 +1424,13 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ - if (unlikely(deny_write_access(new_exe_file))) + if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { - allow_write_access(old_exe_file); + exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; @@ -1471,7 +1471,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) return ret; } - ret = deny_write_access(new_exe_file); + ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); @@ -1483,7 +1483,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) mmap_write_unlock(mm); if (old_exe_file) { - allow_write_access(old_exe_file); + exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; diff --git a/mm/filemap.c b/mm/filemap.c index f61cf51c2238..a800f9eee774 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -3150,6 +3151,14 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; + /* + * If we have pre-content watches we need to disable readahead to make + * sure that we don't populate our mapping with 0 filled pages that we + * never emitted an event for. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { @@ -3218,6 +3227,10 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file *fpin = NULL; unsigned int mmap_miss; + /* See comment in do_sync_mmap_readahead. */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) + return fpin; + /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; @@ -3276,6 +3289,48 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) return ret; } +/** + * filemap_fsnotify_fault - maybe emit a pre-content event. + * @vmf: struct vm_fault containing details of the fault. + * + * If we have a pre-content watch on this file we will emit an event for this + * range. If we return anything the fault caller should return immediately, we + * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the + * fault again and then the fault handler will run the second time through. + * + * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened. + */ +vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) +{ + struct file *fpin = NULL; + int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS; + loff_t pos = vmf->pgoff >> PAGE_SHIFT; + size_t count = PAGE_SIZE; + int err; + + /* + * We already did this and now we're retrying with everything locked, + * don't emit the event and continue. + */ + if (vmf->flags & FAULT_FLAG_TRIED) + return 0; + + /* No watches, we're done. */ + if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode))) + return 0; + + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + return VM_FAULT_SIGBUS; + + err = fsnotify_file_area_perm(fpin, mask, &pos, count); + fput(fpin); + if (err) + return VM_FAULT_SIGBUS; + return VM_FAULT_RETRY; +} +EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); + /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault @@ -3379,6 +3434,37 @@ retry_find: * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { + /* + * If this is a precontent file we have can now emit an event to + * try and populate the folio. + */ + if (!(vmf->flags & FAULT_FLAG_TRIED) && + unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + loff_t pos = folio_pos(folio); + size_t count = folio_size(folio); + + /* We're NOWAIT, we have to retry. */ + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) { + folio_unlock(folio); + goto out_retry; + } + + if (mapping_locked) + filemap_invalidate_unlock_shared(mapping); + mapping_locked = false; + + folio_unlock(folio); + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + if (!fpin) + goto out_retry; + + error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos, + count); + if (error) + ret = VM_FAULT_SIGBUS; + goto out_retry; + } + /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we diff --git a/mm/memory.c b/mm/memory.c index 75c2dfd04f72..32e20f41ed20 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -76,6 +76,7 @@ #include #include #include +#include #include @@ -5662,8 +5663,17 @@ out_map: static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; + if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); + /* + * Currently we just emit PAGE_SIZE for our fault events, so don't allow + * a huge fault if we have a pre content watch on this file. This would + * be trivial to support, but there would need to be tests to ensure + * this works properly and those don't exist currently. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; @@ -5687,6 +5697,9 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) @@ -5709,6 +5722,9 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -5726,6 +5742,9 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + /* See comment in create_huge_pmd. */ + if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) + goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) diff --git a/mm/nommu.c b/mm/nommu.c index 9cb6e99215e2..baa79abdaf03 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1613,6 +1613,13 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); +vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) +{ + BUG(); + return 0; +} +EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); + vm_fault_t filemap_fault(struct vm_fault *vmf) { BUG(); diff --git a/mm/readahead.c b/mm/readahead.c index ea650b8b02fb..703b3d19c41b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -128,6 +128,7 @@ #include #include #include +#include #include "internal.h" @@ -548,6 +549,15 @@ void page_cache_sync_ra(struct readahead_control *ractl, unsigned long max_pages, contig_count; pgoff_t prev_index, miss; + /* + * If we have pre-content watches we need to disable readahead to make + * sure that we don't find 0 filled pages in cache that we never emitted + * events for. Filesystems supporting HSM must make sure to not call + * this function with ractl->file unset for files handled by HSM. + */ + if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) + return; + /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced @@ -626,6 +636,10 @@ void page_cache_async_ra(struct readahead_control *ractl, if (!ra->ra_pages) return; + /* See the comment in page_cache_sync_ra. */ + if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) + return; + /* * Same bit is used for PG_readahead and PG_reclaim. */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 366c87a40bd1..f57b7b189df4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3404,7 +3404,8 @@ static int selinux_path_notify(const struct path *path, u64 mask, perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ - if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) + if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_PRE_ACCESS | + FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm);