When __fsnotify_recalc_mask() recomputes the mask on the watched object, the compiler can "optimize" the code to perform partial updates to the mask (including zeroing it at the beginning). Thus places checking the object mask without conn->lock such as fsnotify_object_watched() could see invalid states of the mask. Make sure the mask update is performed by one memory store using WRITE_ONCE(). Reported-by: syzbot+701037856c25b143f1ad@xxxxxxxxxxxxxxxxxxxxxxxxx Reported-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx> Link: https://lore.kernel.org/all/CACT4Y+Zk0ohwwwHSD63U2-PQ=UuamXczr1mKBD6xtj2dyYKBvA@xxxxxxxxxxxxxx Signed-off-by: Jan Kara <jack@xxxxxxx> --- fs/notify/fsnotify.c | 21 ++++++++++++--------- fs/notify/inotify/inotify_user.c | 2 +- fs/notify/mark.c | 8 ++++++-- include/linux/fsnotify_backend.h | 6 ++++-- 4 files changed, 23 insertions(+), 14 deletions(-) Third time is the charm :) I plan to merge this patch through my tree. Review is welcome. Changes since v2: * Use READ_ONCE to access i_fsnotify_mask in fsnotify_inode_watches_children() diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index ff69ae24c4e8..6675c4182dbf 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -172,8 +172,10 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ - marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask); - marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask); + marks_mask |= fsnotify_parent_needed_mask( + READ_ONCE(inode->i_fsnotify_mask)); + marks_mask |= fsnotify_parent_needed_mask( + READ_ONCE(inode->i_sb->s_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask(mnt_mask); /* Did they subscribe for this event with parent/name info? */ @@ -184,8 +186,8 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { - __u32 marks_mask = inode->i_fsnotify_mask | mnt_mask | - inode->i_sb->s_fsnotify_mask; + __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | + READ_ONCE(inode->i_sb->s_fsnotify_mask); return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } @@ -202,7 +204,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); - __u32 mnt_mask = path ? real_mount(path->mnt)->mnt_fsnotify_mask : 0; + __u32 mnt_mask = path ? + READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; @@ -546,13 +549,13 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, (!inode2 || !inode2->i_fsnotify_marks)) return 0; - marks_mask = sb->s_fsnotify_mask; + marks_mask = READ_ONCE(sb->s_fsnotify_mask); if (mnt) - marks_mask |= mnt->mnt_fsnotify_mask; + marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) - marks_mask |= inode->i_fsnotify_mask; + marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) - marks_mask |= inode2->i_fsnotify_mask; + marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); /* diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 4ffc30606e0b..e163a4b79022 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -569,7 +569,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* more bits in old than in new? */ int dropped = (old_mask & ~new_mask); /* more bits in this fsn_mark than the inode's mask? */ - int do_inode = (new_mask & ~inode->i_fsnotify_mask); + int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask)); /* update the inode with this new fsn_mark */ if (dropped || do_inode) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index c3eefa70633c..4aba49a58edd 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -128,7 +128,7 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; - return *fsnotify_conn_mask_p(conn); + return READ_ONCE(*fsnotify_conn_mask_p(conn)); } static void fsnotify_get_sb_watched_objects(struct super_block *sb) @@ -245,7 +245,11 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } - *fsnotify_conn_mask_p(conn) = new_mask; + /* + * We use WRITE_ONCE() to prevent silly compiler optimizations from + * confusing readers not holding conn->lock with partial updates. + */ + WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask); return fsnotify_update_iref(conn, want_iref); } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 4dd6143db271..06b0c4be428c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -594,12 +594,14 @@ static inline __u32 fsnotify_parent_needed_mask(__u32 mask) static inline int fsnotify_inode_watches_children(struct inode *inode) { + __u32 mask = READ_ONCE(inode->i_fsnotify_mask); + /* FS_EVENT_ON_CHILD is set if the inode may care */ - if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) + if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ - return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; + return mask & FS_EVENTS_POSS_ON_CHILD; } /* -- 2.35.3
