From 9baf93d68bcc3d0a6042283b82603c076e25e4f5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:16 -0300 Subject: [PATCH 01/34] fsnotify: pass data_type to fsnotify_name() Align the arguments of fsnotify_name() to those of fsnotify(). Link: https://lore.kernel.org/r/20211025192746.66445-2-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 12d3a7d308ab..d1144d7c3536 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,20 +26,21 @@ * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ -static inline void fsnotify_name(struct inode *dir, __u32 mask, - struct inode *child, - const struct qstr *name, u32 cookie) +static inline int fsnotify_name(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) - return; + return 0; - fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); + return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); + fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -154,8 +155,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); - fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, + old_dir, old_name, fs_cookie); + fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, + new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); @@ -209,7 +212,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); + fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, + dir, &new_dentry->d_name, 0); } /* From fd5a3ff49a19aa69e2bc1e26e98037c2d778e61a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:17 -0300 Subject: [PATCH 02/34] fsnotify: pass dentry instead of inode data Define a new data type to pass for event - FSNOTIFY_EVENT_DENTRY. Use it to pass the dentry instead of it's ->d_inode where available. This is needed in preparation to the refactor to retrieve the super block from the data field. In some cases (i.e. mkdir in kernfs), the data inode comes from a negative dentry, such that no super block information would be available. By receiving the dentry itself, instead of the inode, fsnotify can derive the super block even on these cases. Link: https://lore.kernel.org/r/20211025192746.66445-3-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein [Expand explanation in commit message] Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 5 ++--- include/linux/fsnotify_backend.h | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 3 deletions(-) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index d1144d7c3536..df0fa4687a18 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -39,8 +39,7 @@ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, - dir, &dentry->d_name, 0); + fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -87,7 +86,7 @@ notify_child: */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { - fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); + fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1ce66748a2d2..a2db821e8a8f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -248,6 +248,7 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, + FSNOTIFY_EVENT_DENTRY, }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -255,6 +256,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; + case FSNOTIFY_EVENT_DENTRY: + return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: @@ -262,6 +265,19 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) } } +static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_DENTRY: + /* Non const is needed for dget() */ + return (struct dentry *)data; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry; + default: + return NULL; + } +} + static inline const struct path *fsnotify_data_path(const void *data, int data_type) { From dabe729dddca550446e9cc118c96d1f91703345b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:18 -0300 Subject: [PATCH 03/34] fsnotify: clarify contract for create event hooks Clarify argument names and contract for fsnotify_create() and fsnotify_mkdir() to reflect the anomaly of kernfs, which leaves dentries negavite after mkdir/create. Remove the WARN_ON(!inode) in audit code that were added by the Fixes commit under the wrong assumption that dentries cannot be negative after mkdir/create. Fixes: aa93bdc5500c ("fsnotify: use helpers to access data by data_type") Link: https://lore.kernel.org/linux-fsdevel/87mtp5yz0q.fsf@collabora.com/ Link: https://lore.kernel.org/r/20211025192746.66445-4-krisman@collabora.com Reviewed-by: Jan Kara Reported-by: Gabriel Krisman Bertazi Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 ++++++++++++++++------ kernel/audit_fsnotify.c | 3 +-- kernel/audit_watch.c | 3 +-- 3 files changed, 18 insertions(+), 10 deletions(-) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index df0fa4687a18..1e5f7435a4b5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -192,16 +192,22 @@ static inline void fsnotify_inoderemove(struct inode *inode) /* * fsnotify_create - 'name' was linked in + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE); + fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory + * + * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ @@ -230,12 +236,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) /* * fsnotify_mkdir - directory 'name' was created + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); + fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 60739d5e3373..02348b48447c 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -160,8 +160,7 @@ static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask, audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) { diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2acf7ca49154..223eed7b39cd 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -472,8 +472,7 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask, parent = container_of(inode_mark, struct audit_parent, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_watch_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO) && inode) From cc53b55f697fe5aa98bdbfdfe67c6401da242155 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:19 -0300 Subject: [PATCH 04/34] fsnotify: Don't insert unmergeable events in hashtable Some events, like the overflow event, are not mergeable, so they are not hashed. But, when failing inside fsnotify_add_event for lack of space, fsnotify_add_event() still calls the insert hook, which adds the overflow event to the merge list. Add a check to prevent any kind of unmergeable event to be inserted in the hashtable. Fixes: 94e00d28a680 ("fsnotify: use hash table for faster events merge") Link: https://lore.kernel.org/r/20211025192746.66445-5-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 057abd2cf887..310246f8d3f1 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -702,6 +702,9 @@ static void fanotify_insert_event(struct fsnotify_group *group, assert_spin_locked(&group->notification_lock); + if (!fanotify_is_hashed_event(event->mask)) + return; + pr_debug("%s: group=%p event=%p bucket=%u\n", __func__, group, event, bucket); @@ -779,8 +782,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, fsn_event = &event->fse; ret = fsnotify_add_event(group, fsn_event, fanotify_merge, - fanotify_is_hashed_event(mask) ? - fanotify_insert_event : NULL); + fanotify_insert_event); if (ret) { /* Permission events shouldn't be merged */ BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS); From b9928e80dda84b349ba8de01780b9bef2fc36ffa Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:20 -0300 Subject: [PATCH 05/34] fanotify: Fold event size calculation to its own function Every time this function is invoked, it is immediately added to FAN_EVENT_METADATA_LEN, since there is no need to just calculate the length of info records. This minor clean up folds the rest of the calculation into the function, which now operates in terms of events, returning the size of the entire event, including metadata. Link: https://lore.kernel.org/r/20211025192746.66445-6-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 35 +++++++++++++++++------------- 1 file changed, 20 insertions(+), 15 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 6facdf476255..6895ec310b5d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -126,17 +126,24 @@ static int fanotify_fid_info_len(int fh_len, int name_len) FANOTIFY_EVENT_ALIGN); } -static int fanotify_event_info_len(unsigned int info_mode, - struct fanotify_event *event) +static size_t fanotify_event_len(unsigned int info_mode, + struct fanotify_event *event) { - struct fanotify_info *info = fanotify_event_info(event); - int dir_fh_len = fanotify_event_dir_fh_len(event); - int fh_len = fanotify_event_object_fh_len(event); - int info_len = 0; + size_t event_len = FAN_EVENT_METADATA_LEN; + struct fanotify_info *info; + int dir_fh_len; + int fh_len; int dot_len = 0; + if (!info_mode) + return event_len; + + info = fanotify_event_info(event); + dir_fh_len = fanotify_event_dir_fh_len(event); + fh_len = fanotify_event_object_fh_len(event); + if (dir_fh_len) { - info_len += fanotify_fid_info_len(dir_fh_len, info->name_len); + event_len += fanotify_fid_info_len(dir_fh_len, info->name_len); } else if ((info_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { /* @@ -147,12 +154,12 @@ static int fanotify_event_info_len(unsigned int info_mode, } if (info_mode & FAN_REPORT_PIDFD) - info_len += FANOTIFY_PIDFD_INFO_HDR_LEN; + event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; if (fh_len) - info_len += fanotify_fid_info_len(fh_len, dot_len); + event_len += fanotify_fid_info_len(fh_len, dot_len); - return info_len; + return event_len; } /* @@ -181,7 +188,7 @@ static void fanotify_unhash_event(struct fsnotify_group *group, static struct fanotify_event *get_one_event(struct fsnotify_group *group, size_t count) { - size_t event_size = FAN_EVENT_METADATA_LEN; + size_t event_size; struct fanotify_event *event = NULL; struct fsnotify_event *fsn_event; unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); @@ -194,8 +201,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group, goto out; event = FANOTIFY_E(fsn_event); - if (info_mode) - event_size += fanotify_event_info_len(info_mode, event); + event_size = fanotify_event_len(info_mode, event); if (event_size > count) { event = ERR_PTR(-EINVAL); @@ -537,8 +543,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - metadata.event_len = FAN_EVENT_METADATA_LEN + - fanotify_event_info_len(info_mode, event); + metadata.event_len = fanotify_event_len(info_mode, event); metadata.metadata_len = FAN_EVENT_METADATA_LEN; metadata.vers = FANOTIFY_METADATA_VERSION; metadata.reserved = 0; From 8299212cbdb01a5867e230e961f82e5c02a6de34 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:21 -0300 Subject: [PATCH 06/34] fanotify: Split fsid check from other fid mode checks FAN_FS_ERROR will require fsid, but not necessarily require the filesystem to expose a file handle. Split those checks into different functions, so they can be used separately when setting up an event. While there, update a comment about tmpfs having 0 fsid, which is no longer true. Link: https://lore.kernel.org/r/20211025192746.66445-7-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 6895ec310b5d..adeae6d65e35 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1300,16 +1300,15 @@ out_destroy_group: return fd; } -/* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) +static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) { __kernel_fsid_t root_fsid; int err; /* - * Make sure path is not in filesystem with zero fsid (e.g. tmpfs). + * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse). */ - err = vfs_get_fsid(path->dentry, fsid); + err = vfs_get_fsid(dentry, fsid); if (err) return err; @@ -1317,10 +1316,10 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) return -ENODEV; /* - * Make sure path is not inside a filesystem subvolume (e.g. btrfs) + * Make sure dentry is not of a filesystem subvolume (e.g. btrfs) * which uses a different fsid than sb root. */ - err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid); + err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid); if (err) return err; @@ -1328,6 +1327,12 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) root_fsid.val[1] != fsid->val[1]) return -EXDEV; + return 0; +} + +/* Check if filesystem can encode a unique fid */ +static int fanotify_test_fid(struct dentry *dentry) +{ /* * We need to make sure that the file system supports at least * encoding a file handle so user can use name_to_handle_at() to @@ -1335,8 +1340,8 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) * objects. However, name_to_handle_at() requires that the * filesystem also supports decoding file handles. */ - if (!path->dentry->d_sb->s_export_op || - !path->dentry->d_sb->s_export_op->fh_to_dentry) + if (!dentry->d_sb->s_export_op || + !dentry->d_sb->s_export_op->fh_to_dentry) return -EOPNOTSUPP; return 0; @@ -1487,7 +1492,11 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } if (fid_mode) { - ret = fanotify_test_fid(&path, &__fsid); + ret = fanotify_test_fsid(path.dentry, &__fsid); + if (ret) + goto path_put_and_out; + + ret = fanotify_test_fid(path.dentry); if (ret) goto path_put_and_out; From e0462f91d24756916fded4313d508e0fc52f39c9 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:22 -0300 Subject: [PATCH 07/34] inotify: Don't force FS_IN_IGNORED According to Amir: "FS_IN_IGNORED is completely internal to inotify and there is no need to set it in i_fsnotify_mask at all, so if we remove the bit from the output of inotify_arg_to_mask() no functionality will change and we will be able to overload the event bit for FS_ERROR." This is done in preparation to overload FS_ERROR with the notification mechanism in fanotify. Link: https://lore.kernel.org/r/20211025192746.66445-8-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/inotify/inotify_user.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 62051247f6d2..29fca3284bb5 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -94,10 +94,10 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg) __u32 mask; /* - * Everything should accept their own ignored and should receive events - * when the inode is unmounted. All directories care about children. + * Everything should receive events when the inode is unmounted. + * All directories care about children. */ - mask = (FS_IN_IGNORED | FS_UNMOUNT); + mask = (FS_UNMOUNT); if (S_ISDIR(inode->i_mode)) mask |= FS_EVENT_ON_CHILD; From 808967a0a4d2f4ce6a2005c5692fffbecaf018c1 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:23 -0300 Subject: [PATCH 08/34] fsnotify: Add helper to detect overflow_event Similarly to fanotify_is_perm_event and friends, provide a helper predicate to say whether a mask is of an overflow event. Link: https://lore.kernel.org/r/20211025192746.66445-9-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.h | 3 ++- include/linux/fsnotify_backend.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 4a5e555dc3d2..c42cf8fd7d79 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -315,7 +315,8 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event) */ static inline bool fanotify_is_hashed_event(u32 mask) { - return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW); + return !(fanotify_is_perm_event(mask) || + fsnotify_is_overflow_event(mask)); } static inline unsigned int fanotify_event_hash_bucket( diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a2db821e8a8f..749bc85e1d1c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -510,6 +510,11 @@ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) fsnotify_add_event(group, group->overflow_event, NULL, NULL); } +static inline bool fsnotify_is_overflow_event(u32 mask) +{ + return mask & FS_Q_OVERFLOW; +} + static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); From 1ad03c3a326a86e259389592117252c851873395 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:24 -0300 Subject: [PATCH 09/34] fsnotify: Add wrapper around fsnotify_add_event fsnotify_add_event is growing in number of parameters, which in most case are just passed a NULL pointer. So, split out a new fsnotify_insert_event function to clean things up for users who don't need an insert hook. Link: https://lore.kernel.org/r/20211025192746.66445-10-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 4 ++-- fs/notify/inotify/inotify_fsnotify.c | 2 +- fs/notify/notification.c | 12 ++++++------ include/linux/fsnotify_backend.h | 23 ++++++++++++++++------- 4 files changed, 25 insertions(+), 16 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 310246f8d3f1..f82e20228999 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -781,8 +781,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, } fsn_event = &event->fse; - ret = fsnotify_add_event(group, fsn_event, fanotify_merge, - fanotify_insert_event); + ret = fsnotify_insert_event(group, fsn_event, fanotify_merge, + fanotify_insert_event); if (ret) { /* Permission events shouldn't be merged */ BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d1a64daa0171..a96582cbfad1 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -116,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, if (len) strcpy(event->name, name->name); - ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL); + ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 32f45543b9c6..44bb10f50715 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -78,12 +78,12 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ -int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)) +int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 749bc85e1d1c..b323d0c4b967 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -498,16 +498,25 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)); +extern int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)); + +static inline int fsnotify_add_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *)) +{ + return fsnotify_insert_event(group, event, merge, NULL); +} + /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { - fsnotify_add_event(group, group->overflow_event, NULL, NULL); + fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) From 29335033c574a15334015d8c4e36862cff3d3384 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:25 -0300 Subject: [PATCH 10/34] fsnotify: Retrieve super block from the data field Some file system events (i.e. FS_ERROR) might not be associated with an inode or directory. For these, we can retrieve the super block from the data field. But, since the super_block is available in the data field on every event type, simplify the code to always retrieve it from there, through a new helper. Link: https://lore.kernel.org/r/20211025192746.66445-11-krisman@collabora.com Suggested-by: Jan Kara Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 7 +++---- include/linux/fsnotify_backend.h | 15 +++++++++++++++ 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 963e6ce75b96..fde3a1115a17 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -455,16 +455,16 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - - * either @dir or @inode must be non-NULL. - * if both are non-NULL event may be reported to both. + * If @dir and @inode are both non-NULL, event may be + * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); + struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; - struct super_block *sb; struct mount *mnt = NULL; struct inode *parent = NULL; int ret = 0; @@ -483,7 +483,6 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, */ parent = dir; } - sb = inode->i_sb; /* * Optimization: srcu_read_lock() has a memory barrier which can diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b323d0c4b967..035438fe4a43 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -289,6 +289,21 @@ static inline const struct path *fsnotify_data_path(const void *data, } } +static inline struct super_block *fsnotify_data_sb(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_INODE: + return ((struct inode *)data)->i_sb; + case FSNOTIFY_EVENT_DENTRY: + return ((struct dentry *)data)->d_sb; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry->d_sb; + default: + return NULL; + } +} + enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, From 24dca90590509a7a6cbe0650100c90c5b8a3468a Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:26 -0300 Subject: [PATCH 11/34] fsnotify: Protect fsnotify_handle_inode_event from no-inode events FAN_FS_ERROR allows events without inodes - i.e. for file system-wide errors. Even though fsnotify_handle_inode_event is not currently used by fanotify, this patch protects other backends from cases where neither inode or dir are provided. Also document the constraints of the interface (inode and dir cannot be both NULL). Link: https://lore.kernel.org/r/20211025192746.66445-12-krisman@collabora.com Suggested-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Jan Kara --- fs/nfsd/filecache.c | 3 +++ fs/notify/fsnotify.c | 3 +++ include/linux/fsnotify_backend.h | 1 + 3 files changed, 7 insertions(+) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index be3c1aad50ea..fdf89fcf1a0c 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -602,6 +602,9 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { + if (WARN_ON_ONCE(!inode)) + return 0; + trace_nfsd_file_fsnotify_handle_event(inode, mask); /* Should be no marks on non-regular files */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index fde3a1115a17..4034ca566f95 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -252,6 +252,9 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group, if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; + if (WARN_ON_ONCE(!inode && !dir)) + return 0; + if ((inode_mark->mask & FS_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 035438fe4a43..b71dc788018e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -136,6 +136,7 @@ struct mem_cgroup; * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. + * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * From 330ae77d2a5b0af32c0f29e139bf28ec8591de59 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:27 -0300 Subject: [PATCH 12/34] fsnotify: Pass group argument to free_event For group-wide mempool backed events, like FS_ERROR, the free_event callback will need to reference the group's mempool to free the memory. Wire that argument into the current callers. Link: https://lore.kernel.org/r/20211025192746.66445-13-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 3 ++- fs/notify/group.c | 2 +- fs/notify/inotify/inotify_fsnotify.c | 3 ++- fs/notify/notification.c | 2 +- include/linux/fsnotify_backend.h | 2 +- 5 files changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index f82e20228999..c620b4f6fe12 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -835,7 +835,8 @@ static void fanotify_free_name_event(struct fanotify_event *event) kfree(FANOTIFY_NE(event)); } -static void fanotify_free_event(struct fsnotify_event *fsn_event) +static void fanotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { struct fanotify_event *event; diff --git a/fs/notify/group.c b/fs/notify/group.c index fb89c351295d..6a297efc4788 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -88,7 +88,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group) * that deliberately ignores overflow events. */ if (group->overflow_event) - group->ops->free_event(group->overflow_event); + group->ops->free_event(group, group->overflow_event); fsnotify_put_group(group); } diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index a96582cbfad1..d92d7b0adc9a 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -177,7 +177,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group) dec_inotify_instances(group->inotify_data.ucounts); } -static void inotify_free_event(struct fsnotify_event *fsn_event) +static void inotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { kfree(INOTIFY_E(fsn_event)); } diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 44bb10f50715..9022ae650cf8 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -64,7 +64,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group, WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } - group->ops->free_event(event); + group->ops->free_event(group, event); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b71dc788018e..3a7c31436182 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -156,7 +156,7 @@ struct fsnotify_ops { const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); - void (*free_event)(struct fsnotify_event *event); + void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; From 12f47bf0f0990933d95d021d13d31bda010648fd Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:28 -0300 Subject: [PATCH 13/34] fanotify: Support null inode event in fanotify_dfid_inode FAN_FS_ERROR doesn't support DFID, but this function is still called for every event. The problem is that it is not capable of handling null inodes, which now can happen in case of superblock error events. For this case, just returning dir will be enough. Link: https://lore.kernel.org/r/20211025192746.66445-14-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index c620b4f6fe12..397ee623ff1e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -452,7 +452,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data, if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) return dir; - if (S_ISDIR(inode->i_mode)) + if (inode && S_ISDIR(inode->i_mode)) return inode; return dir; From 74fe4734897a2da2ae2a665a5e622cd490d36eaf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:29 -0300 Subject: [PATCH 14/34] fanotify: Allow file handle encoding for unhashed events Allow passing a NULL hash to fanotify_encode_fh and avoid calculating the hash if not needed. Link: https://lore.kernel.org/r/20211025192746.66445-15-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 397ee623ff1e..ec84fee7ad01 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -403,8 +403,12 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, fh->type = type; fh->len = fh_len; - /* Mix fh into event merge key */ - *hash ^= fanotify_hash_fh(fh); + /* + * Mix fh into event merge key. Hash might be NULL in case of + * unhashed FID events (i.e. FAN_FS_ERROR). + */ + if (hash) + *hash ^= fanotify_hash_fh(fh); return FANOTIFY_FH_HDR_LEN + fh_len; From 272531ac619b374ab474e989eb387162fded553f Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:30 -0300 Subject: [PATCH 15/34] fanotify: Encode empty file handle when no inode is provided Instead of failing, encode an invalid file handle in fanotify_encode_fh if no inode is provided. This bogus file handle will be reported by FAN_FS_ERROR for non-inode errors. Link: https://lore.kernel.org/r/20211025192746.66445-16-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index ec84fee7ad01..c64d61b673ca 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -370,8 +370,14 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, fh->type = FILEID_ROOT; fh->len = 0; fh->flags = 0; + + /* + * Invalid FHs are used by FAN_FS_ERROR for errors not + * linked to any inode. The f_handle won't be reported + * back to userspace. + */ if (!inode) - return 0; + goto out; /* * !gpf means preallocated variable size fh, but fh_len could @@ -403,6 +409,7 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, fh->type = type; fh->len = fh_len; +out: /* * Mix fh into event merge key. Hash might be NULL in case of * unhashed FID events (i.e. FAN_FS_ERROR). From 4fe595cf1c80e7a5af4d00c4da29def64aff57a2 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:31 -0300 Subject: [PATCH 16/34] fanotify: Require fid_mode for any non-fd event Like inode events, FAN_FS_ERROR will require fid mode. Therefore, convert the verification during fanotify_mark(2) to require fid for any non-fd event. This means fid_mode will not only be required for inode events, but for any event that doesn't provide a descriptor. Link: https://lore.kernel.org/r/20211025192746.66445-17-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 12 ++++++------ include/linux/fanotify.h | 3 +++ 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index adeae6d65e35..66ee3c2805c7 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1458,14 +1458,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, goto fput_and_out; /* - * Events with data type inode do not carry enough information to report - * event->fd, so we do not allow setting a mask for inode events unless - * group supports reporting fid. - * inode events are not supported on a mount mark, because they do not - * carry enough information (i.e. path) to be filtered by mount point. + * Events that do not carry enough information to report + * event->fd require a group that supports reporting fid. Those + * events are not supported on a mount mark, because they do not + * carry enough information (i.e. path) to be filtered by mount + * point. */ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); - if (mask & FANOTIFY_INODE_EVENTS && + if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) && (!fid_mode || mark_type == FAN_MARK_MOUNT)) goto fput_and_out; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index eec3b7c40811..52d464802d99 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -84,6 +84,9 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ */ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +/* Events that can be reported with event->fd */ +#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) + /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) From 9daa811073fa19c08e8aad3b90f9235fed161acf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:32 -0300 Subject: [PATCH 17/34] fsnotify: Support FS_ERROR event type Expose a new type of fsnotify event for filesystems to report errors for userspace monitoring tools. fanotify will send this type of notification for FAN_FS_ERROR events. This also introduce a helper for generating the new event. Link: https://lore.kernel.org/r/20211025192746.66445-18-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 13 +++++++++++++ include/linux/fsnotify_backend.h | 32 +++++++++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1e5f7435a4b5..787545e87eeb 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -339,4 +339,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } +static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, + int error) +{ + struct fs_error_report report = { + .error = error, + .inode = inode, + .sb = sb, + }; + + return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, + NULL, NULL, NULL, 0); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3a7c31436182..00dbaafbcf95 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -42,6 +42,12 @@ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ + +/* + * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify + * which does not support FS_ERROR. + */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ @@ -95,7 +101,8 @@ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ - FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ + FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ @@ -250,6 +257,13 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_ERROR, +}; + +struct fs_error_report { + int error; + struct inode *inode; + struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -261,6 +275,8 @@ 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_ERROR: + return ((struct fs_error_report *)data)->inode; default: return NULL; } @@ -300,6 +316,20 @@ 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_ERROR: + return ((struct fs_error_report *) data)->sb; + default: + return NULL; + } +} + +static inline struct fs_error_report *fsnotify_data_error_report( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_ERROR: + return (struct fs_error_report *) data; default: return NULL; } From 8d11a4f43ef4679be0908026907a7613b33d7127 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:33 -0300 Subject: [PATCH 18/34] fanotify: Reserve UAPI bits for FAN_FS_ERROR FAN_FS_ERROR allows reporting of event type FS_ERROR to userspace, which is a mechanism to report file system wide problems via fanotify. This commit preallocate userspace visible bits to match the FS_ERROR event. Link: https://lore.kernel.org/r/20211025192746.66445-19-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + include/uapi/linux/fanotify.h | 1 + 2 files changed, 2 insertions(+) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index c64d61b673ca..8f152445d75c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -752,6 +752,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); + BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 64553df9d735..2990731ddc8b 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -20,6 +20,7 @@ #define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ From 734a1a5eccc5f7473002b0669f788e135f1f64aa Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:34 -0300 Subject: [PATCH 19/34] fanotify: Pre-allocate pool of error events Pre-allocate slots for file system errors to have greater chances of succeeding, since error events can happen in GFP_NOFS context. This patch introduces a group-wide mempool of error events, shared by all FAN_FS_ERROR marks in this group. Link: https://lore.kernel.org/r/20211025192746.66445-20-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 3 +++ fs/notify/fanotify/fanotify.h | 11 +++++++++++ fs/notify/fanotify/fanotify_user.c | 26 +++++++++++++++++++++++++- include/linux/fsnotify_backend.h | 2 ++ 4 files changed, 41 insertions(+), 1 deletion(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 8f152445d75c..01d68dfc74aa 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -819,6 +819,9 @@ static void fanotify_free_group_priv(struct fsnotify_group *group) if (group->fanotify_data.ucounts) dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_GROUPS); + + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + mempool_exit(&group->fanotify_data.error_events_pool); } static void fanotify_free_path_event(struct fanotify_event *event) diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index c42cf8fd7d79..a577e87fac2b 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -141,6 +141,7 @@ enum fanotify_event_type { FANOTIFY_EVENT_TYPE_PATH, FANOTIFY_EVENT_TYPE_PATH_PERM, FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ + FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ __FANOTIFY_EVENT_TYPE_NUM }; @@ -196,6 +197,16 @@ FANOTIFY_NE(struct fanotify_event *event) return container_of(event, struct fanotify_name_event, fae); } +struct fanotify_error_event { + struct fanotify_event fae; +}; + +static inline struct fanotify_error_event * +FANOTIFY_EE(struct fanotify_event *event) +{ + return container_of(event, struct fanotify_error_event, fae); +} + static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 66ee3c2805c7..2f4182b754b2 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -30,6 +30,7 @@ #define FANOTIFY_DEFAULT_MAX_EVENTS 16384 #define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192 #define FANOTIFY_DEFAULT_MAX_GROUPS 128 +#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32 /* * Legacy fanotify marks limits (8192) is per group and we introduced a tunable @@ -1054,6 +1055,15 @@ out_dec_ucounts: return ERR_PTR(ret); } +static int fanotify_group_init_error_pool(struct fsnotify_group *group) +{ + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + return 0; + + return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool, + FANOTIFY_DEFAULT_FEE_POOL_SIZE, + sizeof(struct fanotify_error_event)); +} static int fanotify_add_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, unsigned int type, @@ -1062,6 +1072,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, { struct fsnotify_mark *fsn_mark; __u32 added; + int ret = 0; mutex_lock(&group->mark_mutex); fsn_mark = fsnotify_find_mark(connp, group); @@ -1072,13 +1083,26 @@ static int fanotify_add_mark(struct fsnotify_group *group, return PTR_ERR(fsn_mark); } } + + /* + * Error events are pre-allocated per group, only if strictly + * needed (i.e. FAN_FS_ERROR was requested). + */ + if (!(flags & FAN_MARK_IGNORED_MASK) && (mask & FAN_FS_ERROR)) { + ret = fanotify_group_init_error_pool(group); + if (ret) + goto out; + } + added = fanotify_mark_add_to_mask(fsn_mark, mask, flags); if (added & ~fsnotify_conn_mask(fsn_mark->connector)) fsnotify_recalc_mask(fsn_mark->connector); + +out: mutex_unlock(&group->mark_mutex); fsnotify_put_mark(fsn_mark); - return 0; + return ret; } static int fanotify_add_vfsmount_mark(struct fsnotify_group *group, diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 00dbaafbcf95..51ef2b079bfa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -19,6 +19,7 @@ #include #include #include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -246,6 +247,7 @@ struct fsnotify_group { int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; + mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; From 83e9acbe13dc1b767f91b5c1350f7a65689b26f6 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:35 -0300 Subject: [PATCH 20/34] fanotify: Support enqueueing of error events Once an error event is triggered, enqueue it in the notification group, similarly to what is done for other events. FAN_FS_ERROR is not handled specially, since the memory is now handled by a preallocated mempool. For now, make the event unhashed. A future patch implements merging of this kind of event. Link: https://lore.kernel.org/r/20211025192746.66445-21-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 35 +++++++++++++++++++++++++++++++++++ fs/notify/fanotify/fanotify.h | 6 ++++++ 2 files changed, 41 insertions(+) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 01d68dfc74aa..1f195c95dfcd 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -574,6 +574,27 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id, return &fne->fae; } +static struct fanotify_event *fanotify_alloc_error_event( + struct fsnotify_group *group, + __kernel_fsid_t *fsid, + const void *data, int data_type) +{ + struct fs_error_report *report = + fsnotify_data_error_report(data, data_type); + struct fanotify_error_event *fee; + + if (WARN_ON_ONCE(!report)) + return NULL; + + fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS); + if (!fee) + return NULL; + + fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + + return &fee->fae; +} + static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, @@ -641,6 +662,9 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if (fanotify_is_perm_event(mask)) { event = fanotify_alloc_perm_event(path, gfp); + } else if (fanotify_is_error_event(mask)) { + event = fanotify_alloc_error_event(group, fsid, data, + data_type); } else if (name_event && (file_name || child)) { event = fanotify_alloc_name_event(id, fsid, file_name, child, &hash, gfp); @@ -850,6 +874,14 @@ static void fanotify_free_name_event(struct fanotify_event *event) kfree(FANOTIFY_NE(event)); } +static void fanotify_free_error_event(struct fsnotify_group *group, + struct fanotify_event *event) +{ + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + mempool_free(fee, &group->fanotify_data.error_events_pool); +} + static void fanotify_free_event(struct fsnotify_group *group, struct fsnotify_event *fsn_event) { @@ -873,6 +905,9 @@ static void fanotify_free_event(struct fsnotify_group *group, case FANOTIFY_EVENT_TYPE_OVERFLOW: kfree(event); break; + case FANOTIFY_EVENT_TYPE_FS_ERROR: + fanotify_free_error_event(group, event); + break; default: WARN_ON_ONCE(1); } diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index a577e87fac2b..ebef952481fa 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -298,6 +298,11 @@ static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) return container_of(fse, struct fanotify_event, fse); } +static inline bool fanotify_is_error_event(u32 mask) +{ + return mask & FAN_FS_ERROR; +} + static inline bool fanotify_event_has_path(struct fanotify_event *event) { return event->type == FANOTIFY_EVENT_TYPE_PATH || @@ -327,6 +332,7 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event) static inline bool fanotify_is_hashed_event(u32 mask) { return !(fanotify_is_perm_event(mask) || + fanotify_is_error_event(mask) || fsnotify_is_overflow_event(mask)); } From 8a6ae64132fd27a944faed7bc38484827609eb76 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:36 -0300 Subject: [PATCH 21/34] fanotify: Support merging of error events Error events (FAN_FS_ERROR) against the same file system can be merged by simply iterating the error count. The hash is taken from the fsid, without considering the FH. This means that only the first error object is reported. Link: https://lore.kernel.org/r/20211025192746.66445-22-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 26 ++++++++++++++++++++++++-- fs/notify/fanotify/fanotify.h | 4 +++- 2 files changed, 27 insertions(+), 3 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 1f195c95dfcd..cedcb1546804 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -111,6 +111,16 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1, return fanotify_info_equal(info1, info2); } +static bool fanotify_error_event_equal(struct fanotify_error_event *fee1, + struct fanotify_error_event *fee2) +{ + /* Error events against the same file system are always merged. */ + if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid)) + return false; + + return true; +} + static bool fanotify_should_merge(struct fanotify_event *old, struct fanotify_event *new) { @@ -141,6 +151,9 @@ static bool fanotify_should_merge(struct fanotify_event *old, case FANOTIFY_EVENT_TYPE_FID_NAME: return fanotify_name_event_equal(FANOTIFY_NE(old), FANOTIFY_NE(new)); + case FANOTIFY_EVENT_TYPE_FS_ERROR: + return fanotify_error_event_equal(FANOTIFY_EE(old), + FANOTIFY_EE(new)); default: WARN_ON_ONCE(1); } @@ -176,6 +189,10 @@ static int fanotify_merge(struct fsnotify_group *group, break; if (fanotify_should_merge(old, new)) { old->mask |= new->mask; + + if (fanotify_is_error_event(old->mask)) + FANOTIFY_EE(old)->err_count++; + return 1; } } @@ -577,7 +594,8 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id, static struct fanotify_event *fanotify_alloc_error_event( struct fsnotify_group *group, __kernel_fsid_t *fsid, - const void *data, int data_type) + const void *data, int data_type, + unsigned int *hash) { struct fs_error_report *report = fsnotify_data_error_report(data, data_type); @@ -591,6 +609,10 @@ static struct fanotify_event *fanotify_alloc_error_event( return NULL; fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + fee->err_count = 1; + fee->fsid = *fsid; + + *hash ^= fanotify_hash_fsid(fsid); return &fee->fae; } @@ -664,7 +686,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, event = fanotify_alloc_perm_event(path, gfp); } else if (fanotify_is_error_event(mask)) { event = fanotify_alloc_error_event(group, fsid, data, - data_type); + data_type, &hash); } else if (name_event && (file_name || child)) { event = fanotify_alloc_name_event(id, fsid, file_name, child, &hash, gfp); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index ebef952481fa..2b032b79d5b0 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -199,6 +199,9 @@ FANOTIFY_NE(struct fanotify_event *event) struct fanotify_error_event { struct fanotify_event fae; + u32 err_count; /* Suppressed errors count */ + + __kernel_fsid_t fsid; /* FSID this error refers to. */ }; static inline struct fanotify_error_event * @@ -332,7 +335,6 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event) static inline bool fanotify_is_hashed_event(u32 mask) { return !(fanotify_is_perm_event(mask) || - fanotify_is_error_event(mask) || fsnotify_is_overflow_event(mask)); } From 2c5069433a3adc01ff9c5673567961bb7f138074 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:37 -0300 Subject: [PATCH 22/34] fanotify: Wrap object_fh inline space in a creator macro fanotify_error_event would duplicate this sequence of declarations that already exist elsewhere with a slight different size. Create a helper macro to avoid code duplication. Link: https://lore.kernel.org/r/20211025192746.66445-23-krisman@collabora.com Suggested-by: Jan Kara Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 2b032b79d5b0..3510d06654ed 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -171,12 +171,18 @@ static inline void fanotify_init_event(struct fanotify_event *event, event->pid = NULL; } +#define FANOTIFY_INLINE_FH(name, size) \ +struct { \ + struct fanotify_fh (name); \ + /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \ + unsigned char _inline_fh_buf[(size)]; \ +} + struct fanotify_fid_event { struct fanotify_event fae; __kernel_fsid_t fsid; - struct fanotify_fh object_fh; - /* Reserve space in object_fh.buf[] - access with fanotify_fh_buf() */ - unsigned char _inline_fh_buf[FANOTIFY_INLINE_FH_LEN]; + + FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN); }; static inline struct fanotify_fid_event * From 4bd5a5c8e6e5cd964e9738e6ef87f6c2cb453edf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:38 -0300 Subject: [PATCH 23/34] fanotify: Add helpers to decide whether to report FID/DFID Now that there is an event that reports FID records even for a zeroed file handle, wrap the logic that deides whether to issue the records into helper functions. This shouldn't have any impact on the code, but simplifies further patches. Link: https://lore.kernel.org/r/20211025192746.66445-24-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.h | 10 ++++++++++ fs/notify/fanotify/fanotify_user.c | 13 +++++++------ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 3510d06654ed..80af269eebb8 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -264,6 +264,16 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event) return info ? fanotify_info_dir_fh_len(info) : 0; } +static inline bool fanotify_event_has_object_fh(struct fanotify_event *event) +{ + return fanotify_event_object_fh_len(event) > 0; +} + +static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event) +{ + return fanotify_event_dir_fh_len(event) > 0; +} + struct fanotify_path_event { struct fanotify_event fae; struct path path; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 2f4182b754b2..a9b5c36ee49e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -140,10 +140,9 @@ static size_t fanotify_event_len(unsigned int info_mode, return event_len; info = fanotify_event_info(event); - dir_fh_len = fanotify_event_dir_fh_len(event); - fh_len = fanotify_event_object_fh_len(event); - if (dir_fh_len) { + if (fanotify_event_has_dir_fh(event)) { + dir_fh_len = fanotify_event_dir_fh_len(event); event_len += fanotify_fid_info_len(dir_fh_len, info->name_len); } else if ((info_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { @@ -157,8 +156,10 @@ static size_t fanotify_event_len(unsigned int info_mode, if (info_mode & FAN_REPORT_PIDFD) event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; - if (fh_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); + } return event_len; } @@ -451,7 +452,7 @@ static int copy_info_records_to_user(struct fanotify_event *event, /* * Event info records order is as follows: dir fid + name, child fid. */ - if (fanotify_event_dir_fh_len(event)) { + if (fanotify_event_has_dir_fh(event)) { info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : FAN_EVENT_INFO_TYPE_DFID; ret = copy_fid_info_to_user(fanotify_event_fsid(event), @@ -467,7 +468,7 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } - if (fanotify_event_object_fh_len(event)) { + if (fanotify_event_has_object_fh(event)) { const char *dot = NULL; int dot_len = 0; From 572c28f27a269f88e2d8d7b6b1507f114d637337 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:40 -0300 Subject: [PATCH 24/34] fanotify: WARN_ON against too large file handles struct fanotify_error_event, at least, is preallocated and isn't able to to handle arbitrarily large file handles. Future-proof the code by complaining loudly if a handle larger than MAX_HANDLE_SZ is ever found. Link: https://lore.kernel.org/r/20211025192746.66445-26-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index cedcb1546804..45df610debbe 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -360,13 +360,23 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, static int fanotify_encode_fh_len(struct inode *inode) { int dwords = 0; + int fh_len; if (!inode) return 0; exportfs_encode_inode_fh(inode, NULL, &dwords, NULL); + fh_len = dwords << 2; - return dwords << 2; + /* + * struct fanotify_error_event might be preallocated and is + * limited to MAX_HANDLE_SZ. This should never happen, but + * safeguard by forcing an invalid file handle. + */ + if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ)) + return 0; + + return fh_len; } /* From 936d6a38be39177495af38497bf8da1c6128fa1b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:41 -0300 Subject: [PATCH 25/34] fanotify: Report fid info for file related file system errors Plumb the pieces to add a FID report to error records. Since all error event memory must be pre-allocated, we pre-allocate the maximum file handle size possible, such that it should always fit. For errors that don't expose a file handle, report it with an invalid FID. Internally we use zero-length FILEID_ROOT file handle for passing the information (which we report as zero-length FILEID_INVALID file handle to userspace) so we update the handle reporting code to deal with this case correctly. Link: https://lore.kernel.org/r/20211025192746.66445-27-krisman@collabora.com Link: https://lore.kernel.org/r/20211025192746.66445-25-krisman@collabora.com Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara [Folded two patches into 2 to make series bisectable] Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 11 +++++++++++ fs/notify/fanotify/fanotify.h | 9 +++++++++ fs/notify/fanotify/fanotify_user.c | 8 +++++--- 3 files changed, 25 insertions(+), 3 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 45df610debbe..465f07e70e6d 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -609,7 +609,9 @@ static struct fanotify_event *fanotify_alloc_error_event( { struct fs_error_report *report = fsnotify_data_error_report(data, data_type); + struct inode *inode; struct fanotify_error_event *fee; + int fh_len; if (WARN_ON_ONCE(!report)) return NULL; @@ -622,6 +624,15 @@ static struct fanotify_event *fanotify_alloc_error_event( fee->err_count = 1; fee->fsid = *fsid; + inode = report->inode; + fh_len = fanotify_encode_fh_len(inode); + + /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */ + if (!fh_len && inode) + inode = NULL; + + fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0); + *hash ^= fanotify_hash_fsid(fsid); return &fee->fae; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 80af269eebb8..edd7587adcc5 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -208,6 +208,8 @@ struct fanotify_error_event { u32 err_count; /* Suppressed errors count */ __kernel_fsid_t fsid; /* FSID this error refers to. */ + + FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ); }; static inline struct fanotify_error_event * @@ -222,6 +224,8 @@ static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event) return &FANOTIFY_FE(event)->fsid; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return &FANOTIFY_NE(event)->fsid; + else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return &FANOTIFY_EE(event)->fsid; else return NULL; } @@ -233,6 +237,8 @@ static inline struct fanotify_fh *fanotify_event_object_fh( return &FANOTIFY_FE(event)->object_fh; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return fanotify_info_file_fh(&FANOTIFY_NE(event)->info); + else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return &FANOTIFY_EE(event)->object_fh; else return NULL; } @@ -266,6 +272,9 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event) static inline bool fanotify_event_has_object_fh(struct fanotify_event *event) { + /* For error events, even zeroed fh are reported. */ + if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return true; return fanotify_event_object_fh_len(event) > 0; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index a9b5c36ee49e..ff4a7373f7a5 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -339,9 +339,6 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n", __func__, fh_len, name_len, info_len, count); - if (!fh_len) - return 0; - if (WARN_ON_ONCE(len < sizeof(info) || len > count)) return -EFAULT; @@ -376,6 +373,11 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, handle.handle_type = fh->type; handle.handle_bytes = fh_len; + + /* Mangle handle_type for bad file_handle */ + if (!fh_len) + handle.handle_type = FILEID_INVALID; + if (copy_to_user(buf, &handle, sizeof(handle))) return -EFAULT; From 130a3c742107acff985541c28360c8b40203559c Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:42 -0300 Subject: [PATCH 26/34] fanotify: Emit generic error info for error event The error info is a record sent to users on FAN_FS_ERROR events documenting the type of error. It also carries an error count, documenting how many errors were observed since the last reporting. Link: https://lore.kernel.org/r/20211025192746.66445-28-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + fs/notify/fanotify/fanotify.h | 1 + fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++++++++ include/uapi/linux/fanotify.h | 7 ++++++ 4 files changed, 45 insertions(+) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 465f07e70e6d..af61425e6e3b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -621,6 +621,7 @@ static struct fanotify_event *fanotify_alloc_error_event( return NULL; fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + fee->error = report->error; fee->err_count = 1; fee->fsid = *fsid; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index edd7587adcc5..d25f500bf7e7 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -205,6 +205,7 @@ FANOTIFY_NE(struct fanotify_event *event) struct fanotify_error_event { struct fanotify_event fae; + s32 error; /* Error reported by the Filesystem. */ u32 err_count; /* Suppressed errors count */ __kernel_fsid_t fsid; /* FSID this error refers to. */ diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ff4a7373f7a5..fb817028d0b6 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -115,6 +115,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) #define FANOTIFY_PIDFD_INFO_HDR_LEN \ sizeof(struct fanotify_event_info_pidfd) +#define FANOTIFY_ERROR_INFO_LEN \ + (sizeof(struct fanotify_event_info_error)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -139,6 +141,9 @@ static size_t fanotify_event_len(unsigned int info_mode, if (!info_mode) return event_len; + if (fanotify_is_error_event(event->mask)) + event_len += FANOTIFY_ERROR_INFO_LEN; + info = fanotify_event_info(event); if (fanotify_event_has_dir_fh(event)) { @@ -324,6 +329,28 @@ static int process_access_response(struct fsnotify_group *group, return -ENOENT; } +static size_t copy_error_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_event_info_error info; + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR; + info.hdr.pad = 0; + info.hdr.len = FANOTIFY_ERROR_INFO_LEN; + + if (WARN_ON(count < info.hdr.len)) + return -EFAULT; + + info.error = fee->error; + info.error_count = fee->err_count; + + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + return info.hdr.len; +} + static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, int info_type, const char *name, size_t name_len, @@ -530,6 +557,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_is_error_event(event->mask)) { + ret = copy_error_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 2990731ddc8b..bd1932c2074d 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -126,6 +126,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -160,6 +161,12 @@ struct fanotify_event_info_pidfd { __s32 pidfd; }; +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + struct fanotify_response { __s32 fd; __u32 response; From 9709bd548f11a092d124698118013f66e1740f9b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:43 -0300 Subject: [PATCH 27/34] fanotify: Allow users to request FAN_FS_ERROR events Wire up the FAN_FS_ERROR event in the fanotify_mark syscall, allowing user space to request the monitoring of FAN_FS_ERROR events. These events are limited to filesystem marks, so check it is the case in the syscall handler. Link: https://lore.kernel.org/r/20211025192746.66445-29-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 2 +- fs/notify/fanotify/fanotify_user.c | 4 ++++ include/linux/fanotify.h | 6 +++++- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index af61425e6e3b..b6091775aa6e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -822,7 +822,7 @@ 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(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20); mask = fanotify_group_event_mask(group, iter_info, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index fb817028d0b6..559bc1e9926d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1520,6 +1520,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group->priority == FS_PRIO_0) goto fput_and_out; + if (mask & FAN_FS_ERROR && + mark_type != FAN_MARK_FILESYSTEM) + goto fput_and_out; + /* * Events that do not carry enough information to report * event->fd require a group that supports reporting fid. Those diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 52d464802d99..616af2ea20f3 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -91,9 +91,13 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) +/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ +#define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ - FANOTIFY_INODE_EVENTS) + FANOTIFY_INODE_EVENTS | \ + FANOTIFY_ERROR_EVENTS) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ From 9a089b21f79b47eed240d4da7ea0d049de7c9b4d Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:44 -0300 Subject: [PATCH 28/34] ext4: Send notifications on error Send a FS_ERROR message via fsnotify to a userspace monitoring tool whenever a ext4 error condition is triggered. This follows the existing error conditions in ext4, so it is hooked to the ext4_error* functions. Link: https://lore.kernel.org/r/20211025192746.66445-30-krisman@collabora.com Signed-off-by: Gabriel Krisman Bertazi Acked-by: Theodore Ts'o Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Jan Kara --- fs/ext4/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88d5d274a868..1a766c68a55e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ @@ -759,6 +760,8 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } + fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } @@ -789,6 +792,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } + fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } @@ -827,6 +832,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } + fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } @@ -894,6 +901,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } + fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } From 5451093081db6ca1a708d149e11cfd219800bc4c Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:45 -0300 Subject: [PATCH 29/34] samples: Add fs error monitoring example Introduce an example of a FAN_FS_ERROR fanotify user to track filesystem errors. Link: https://lore.kernel.org/r/20211025192746.66445-31-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- samples/Kconfig | 9 +++ samples/Makefile | 1 + samples/fanotify/Makefile | 5 ++ samples/fanotify/fs-monitor.c | 142 ++++++++++++++++++++++++++++++++++ 4 files changed, 157 insertions(+) create mode 100644 samples/fanotify/Makefile create mode 100644 samples/fanotify/fs-monitor.c diff --git a/samples/Kconfig b/samples/Kconfig index b0503ef058d3..88353b8eac0b 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -120,6 +120,15 @@ config SAMPLE_CONNECTOR with it. See also Documentation/driver-api/connector.rst +config SAMPLE_FANOTIFY_ERROR + bool "Build fanotify error monitoring sample" + depends on FANOTIFY + help + When enabled, this builds an example code that uses the + FAN_FS_ERROR fanotify mechanism to monitor filesystem + errors. + See also Documentation/admin-guide/filesystem-monitoring.rst. + config SAMPLE_HIDRAW bool "hidraw sample" depends on CC_CAN_LINK && HEADERS_INSTALL diff --git a/samples/Makefile b/samples/Makefile index 087e0988ccc5..931a81847c48 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -5,6 +5,7 @@ subdir-$(CONFIG_SAMPLE_AUXDISPLAY) += auxdisplay subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs obj-$(CONFIG_SAMPLE_CONFIGFS) += configfs/ obj-$(CONFIG_SAMPLE_CONNECTOR) += connector/ +obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR) += fanotify/ subdir-$(CONFIG_SAMPLE_HIDRAW) += hidraw obj-$(CONFIG_SAMPLE_HW_BREAKPOINT) += hw_breakpoint/ obj-$(CONFIG_SAMPLE_KDB) += kdb/ diff --git a/samples/fanotify/Makefile b/samples/fanotify/Makefile new file mode 100644 index 000000000000..e20db1bdde3b --- /dev/null +++ b/samples/fanotify/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +userprogs-always-y += fs-monitor + +userccflags += -I usr/include -Wall + diff --git a/samples/fanotify/fs-monitor.c b/samples/fanotify/fs-monitor.c new file mode 100644 index 000000000000..a0e44cd31e6f --- /dev/null +++ b/samples/fanotify/fs-monitor.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2021, Collabora Ltd. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef FAN_FS_ERROR +#define FAN_FS_ERROR 0x00008000 +#define FAN_EVENT_INFO_TYPE_ERROR 5 + +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; +#endif + +#ifndef FILEID_INO32_GEN +#define FILEID_INO32_GEN 1 +#endif + +#ifndef FILEID_INVALID +#define FILEID_INVALID 0xff +#endif + +static void print_fh(struct file_handle *fh) +{ + int i; + uint32_t *h = (uint32_t *) fh->f_handle; + + printf("\tfh: "); + for (i = 0; i < fh->handle_bytes; i++) + printf("%hhx", fh->f_handle[i]); + printf("\n"); + + printf("\tdecoded fh: "); + if (fh->handle_type == FILEID_INO32_GEN) + printf("inode=%u gen=%u\n", h[0], h[1]); + else if (fh->handle_type == FILEID_INVALID && !fh->handle_bytes) + printf("Type %d (Superblock error)\n", fh->handle_type); + else + printf("Type %d (Unknown)\n", fh->handle_type); + +} + +static void handle_notifications(char *buffer, int len) +{ + struct fanotify_event_metadata *event = + (struct fanotify_event_metadata *) buffer; + struct fanotify_event_info_header *info; + struct fanotify_event_info_error *err; + struct fanotify_event_info_fid *fid; + int off; + + for (; FAN_EVENT_OK(event, len); event = FAN_EVENT_NEXT(event, len)) { + + if (event->mask != FAN_FS_ERROR) { + printf("unexpected FAN MARK: %llx\n", event->mask); + goto next_event; + } + + if (event->fd != FAN_NOFD) { + printf("Unexpected fd (!= FAN_NOFD)\n"); + goto next_event; + } + + printf("FAN_FS_ERROR (len=%d)\n", event->event_len); + + for (off = sizeof(*event) ; off < event->event_len; + off += info->len) { + info = (struct fanotify_event_info_header *) + ((char *) event + off); + + switch (info->info_type) { + case FAN_EVENT_INFO_TYPE_ERROR: + err = (struct fanotify_event_info_error *) info; + + printf("\tGeneric Error Record: len=%d\n", + err->hdr.len); + printf("\terror: %d\n", err->error); + printf("\terror_count: %d\n", err->error_count); + break; + + case FAN_EVENT_INFO_TYPE_FID: + fid = (struct fanotify_event_info_fid *) info; + + printf("\tfsid: %x%x\n", + fid->fsid.val[0], fid->fsid.val[1]); + print_fh((struct file_handle *) &fid->handle); + break; + + default: + printf("\tUnknown info type=%d len=%d:\n", + info->info_type, info->len); + } + } +next_event: + printf("---\n\n"); + } +} + +int main(int argc, char **argv) +{ + int fd; + + char buffer[BUFSIZ]; + + if (argc < 2) { + printf("Missing path argument\n"); + return 1; + } + + fd = fanotify_init(FAN_CLASS_NOTIF|FAN_REPORT_FID, O_RDONLY); + if (fd < 0) + errx(1, "fanotify_init"); + + if (fanotify_mark(fd, FAN_MARK_ADD|FAN_MARK_FILESYSTEM, + FAN_FS_ERROR, AT_FDCWD, argv[1])) { + errx(1, "fanotify_mark"); + } + + while (1) { + int n = read(fd, buffer, BUFSIZ); + + if (n < 0) + errx(1, "read"); + + handle_notifications(buffer, n); + } + + return 0; +} From c0baf9ac0b05d53dfe0436661dbdc5e43c01c5e0 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:46 -0300 Subject: [PATCH 30/34] docs: Document the FAN_FS_ERROR event Document the FAN_FS_ERROR event for user administrators and user space developers. Link: https://lore.kernel.org/r/20211025192746.66445-32-krisman@collabora.com Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Jan Kara Signed-off-by: Jan Kara --- .../admin-guide/filesystem-monitoring.rst | 74 +++++++++++++++++++ Documentation/admin-guide/index.rst | 1 + 2 files changed, 75 insertions(+) create mode 100644 Documentation/admin-guide/filesystem-monitoring.rst diff --git a/Documentation/admin-guide/filesystem-monitoring.rst b/Documentation/admin-guide/filesystem-monitoring.rst new file mode 100644 index 000000000000..5a3c84e60095 --- /dev/null +++ b/Documentation/admin-guide/filesystem-monitoring.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================== +File system Monitoring with fanotify +==================================== + +File system Error Reporting +=========================== + +Fanotify supports the FAN_FS_ERROR event type for file system-wide error +reporting. It is meant to be used by file system health monitoring +daemons, which listen for these events and take actions (notify +sysadmin, start recovery) when a file system problem is detected. + +By design, a FAN_FS_ERROR notification exposes sufficient information +for a monitoring tool to know a problem in the file system has happened. +It doesn't necessarily provide a user space application with semantics +to verify an IO operation was successfully executed. That is out of +scope for this feature. Instead, it is only meant as a framework for +early file system problem detection and reporting recovery tools. + +When a file system operation fails, it is common for dozens of kernel +errors to cascade after the initial failure, hiding the original failure +log, which is usually the most useful debug data to troubleshoot the +problem. For this reason, FAN_FS_ERROR tries to report only the first +error that occurred for a file system since the last notification, and +it simply counts additional errors. This ensures that the most +important pieces of information are never lost. + +FAN_FS_ERROR requires the fanotify group to be setup with the +FAN_REPORT_FID flag. + +At the time of this writing, the only file system that emits FAN_FS_ERROR +notifications is Ext4. + +A FAN_FS_ERROR Notification has the following format:: + + [ Notification Metadata (Mandatory) ] + [ Generic Error Record (Mandatory) ] + [ FID record (Mandatory) ] + +The order of records is not guaranteed, and new records might be added +in the future. Therefore, applications must not rely on the order and +must be prepared to skip over unknown records. Please refer to +``samples/fanotify/fs-monitor.c`` for an example parser. + +Generic error record +-------------------- + +The generic error record provides enough information for a file system +agnostic tool to learn about a problem in the file system, without +providing any additional details about the problem. This record is +identified by ``struct fanotify_event_info_header.info_type`` being set +to FAN_EVENT_INFO_TYPE_ERROR. + + struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; + }; + +The `error` field identifies the type of error using errno values. +`error_count` tracks the number of errors that occurred and were +suppressed to preserve the original error information, since the last +notification. + +FID record +---------- + +The FID record can be used to uniquely identify the inode that triggered +the error through the combination of fsid and file handle. A file system +specific application can use that information to attempt a recovery +procedure. Errors that are not related to an inode are reported with an +empty file handle of type FILEID_INVALID. diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index dc00afcabb95..1bedab498104 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -82,6 +82,7 @@ configure specific aspects of kernel behavior to your liking. edid efi-stub ext4 + filesystem-monitoring nfs/index gpio/index highuid From 8fc70b3a142f97f7859bf052151df896933d2586 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 28 Oct 2021 15:56:28 -0300 Subject: [PATCH 31/34] samples: Make fs-monitor depend on libc and headers Prevent build errors when headers or libc are not available, such as on kernel build bots, like the below: samples/fanotify/fs-monitor.c:7:10: fatal error: errno.h: No such file or directory 7 | #include | ^~~~~~~~~ Link: https://lore.kernel.org/r/87fsslasgz.fsf@collabora.com Suggested-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- samples/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/Kconfig b/samples/Kconfig index 88353b8eac0b..56539b21f2c7 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -122,7 +122,7 @@ config SAMPLE_CONNECTOR config SAMPLE_FANOTIFY_ERROR bool "Build fanotify error monitoring sample" - depends on FANOTIFY + depends on FANOTIFY && CC_CAN_LINK && HEADERS_INSTALL help When enabled, this builds an example code that uses the FAN_FS_ERROR fanotify mechanism to monitor filesystem From 9abeae5d4458326e16df7ea237104b58c27dfd77 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 28 Oct 2021 18:05:49 -0300 Subject: [PATCH 32/34] docs: Fix formatting of literal sections in fanotify docs Stephen Rothwell reported the following warning was introduced by commit c0baf9ac0b05 ("docs: Document the FAN_FS_ERROR event"). Documentation/admin-guide/filesystem-monitoring.rst:60: WARNING: Definition list ends without a blank line; unexpected unindent. Link: https://lore.kernel.org/r/87y26camhe.fsf@collabora.com Reported-by: Stephen Rothwell Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- .../admin-guide/filesystem-monitoring.rst | 20 +++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/Documentation/admin-guide/filesystem-monitoring.rst b/Documentation/admin-guide/filesystem-monitoring.rst index 5a3c84e60095..ab8dba76283c 100644 --- a/Documentation/admin-guide/filesystem-monitoring.rst +++ b/Documentation/admin-guide/filesystem-monitoring.rst @@ -35,9 +35,11 @@ notifications is Ext4. A FAN_FS_ERROR Notification has the following format:: - [ Notification Metadata (Mandatory) ] - [ Generic Error Record (Mandatory) ] - [ FID record (Mandatory) ] + :: + + [ Notification Metadata (Mandatory) ] + [ Generic Error Record (Mandatory) ] + [ FID record (Mandatory) ] The order of records is not guaranteed, and new records might be added in the future. Therefore, applications must not rely on the order and @@ -53,11 +55,13 @@ providing any additional details about the problem. This record is identified by ``struct fanotify_event_info_header.info_type`` being set to FAN_EVENT_INFO_TYPE_ERROR. - struct fanotify_event_info_error { - struct fanotify_event_info_header hdr; - __s32 error; - __u32 error_count; - }; + :: + + struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; + }; The `error` field identifies the type of error using errno values. `error_count` tracks the number of errors that occurred and were From b7eccf75c28e5469bb4685a03310dbb66ee323f9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 1 Nov 2021 12:47:32 +0100 Subject: [PATCH 33/34] samples: Fix warning in fsnotify sample The fsnotify sample code generates the following warning on powerpc: samples/fanotify/fs-monitor.c: In function 'handle_notifications': samples/fanotify/fs-monitor.c:68:36: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 2 has type '__u64' {aka 'long unsigned int'} [-Wformat=] 68 | printf("unexpected FAN MARK: %llx\n", event->mask); | ~~~^ ~~~~~~~~~~~ | | | | | __u64 {aka long unsigned int} | long long unsigned int | %lx Fix the problem by explicitely typing the argument to proper type. Reported-by: Stephen Rothwell Signed-off-by: Jan Kara --- samples/fanotify/fs-monitor.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/samples/fanotify/fs-monitor.c b/samples/fanotify/fs-monitor.c index a0e44cd31e6f..2e08a1807db7 100644 --- a/samples/fanotify/fs-monitor.c +++ b/samples/fanotify/fs-monitor.c @@ -65,7 +65,8 @@ static void handle_notifications(char *buffer, int len) for (; FAN_EVENT_OK(event, len); event = FAN_EVENT_NEXT(event, len)) { if (event->mask != FAN_FS_ERROR) { - printf("unexpected FAN MARK: %llx\n", event->mask); + printf("unexpected FAN MARK: %llx\n", + (unsigned long long)event->mask); goto next_event; } From 15c72660fe9a3fddb301ac90175860b14c63ff03 Mon Sep 17 00:00:00 2001 From: Zhang Mingyu Date: Mon, 1 Nov 2021 07:51:52 +0000 Subject: [PATCH 34/34] samples: remove duplicate include in fs-monitor.c 'sys/types.h' included in 'samples/fanotify/fs-monitor.c' is duplicated.It is also included on 15 line. Link: https://lore.kernel.org/r/20211101075152.35780-1-zhang.mingyu@zte.com.cn Reported-by: Zeal Robot Signed-off-by: Zhang Mingyu Signed-off-by: Jan Kara --- samples/fanotify/fs-monitor.c | 1 - 1 file changed, 1 deletion(-) diff --git a/samples/fanotify/fs-monitor.c b/samples/fanotify/fs-monitor.c index 2e08a1807db7..608db24c471e 100644 --- a/samples/fanotify/fs-monitor.c +++ b/samples/fanotify/fs-monitor.c @@ -12,7 +12,6 @@ #include #include #include -#include #ifndef FAN_FS_ERROR #define FAN_FS_ERROR 0x00008000