From: Al Viro <viro@zeniv.linux.org.uk> mainline inclusion from mainline-v6.8-rc1 commit da549bdd15c295c24b2ee7ffe7ad0f3877fa8a87 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Saves a pointer per struct dentry and actually makes the things less clumsy. Cleaned the d_walk() and dcache_readdir() a bit by use of hlist_for_... iterators. A couple of new helpers - d_first_child() and d_next_sibling(), to make the expressions less awful. Reviewed-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Conflicts: Documentation/filesystems/porting.rst fs/coda/cache.c fs/dcache.c fs/tracefs/inode.c fs/notify/fsnotify.c fs/nfsd/nfsctl.c [Context Changed for Documentation/filesystems/porting.rst] [b31559f8e471 not applied for fs/coda/cache.c] [Context Changed for fs/dcache.c] [8186fff7ab64 not applied for fs/tracefs/inode.c] [172e422ffea2 not applied for fs/notify/fsnotify.c] [b7a14708aafe not applied for fs/nfsd/nfsctl.c] Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- Documentation/filesystems/porting.rst | 9 +++ arch/powerpc/platforms/cell/spufs/inode.c | 5 +- fs/afs/dynroot.c | 5 +- fs/autofs/expire.c | 7 +-- fs/ceph/dir.c | 2 +- fs/ceph/mds_client.c | 2 +- fs/coda/cache.c | 2 +- fs/dcache.c | 76 +++++++++++------------ fs/libfs.c | 45 +++++++------- fs/nfsd/nfsctl.c | 5 +- fs/notify/fsnotify.c | 2 +- include/linux/dcache.h | 20 ++++-- 12 files changed, 97 insertions(+), 83 deletions(-) diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 41d964b48e65..55e6dd4e037c 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1063,3 +1063,12 @@ On same-directory ->rename() the (tautological) update of .. is not protected by any locks; just don't do it if the old parent is the same as the new one. We really can't lock two subdirectories in same-directory rename - not without deadlocks. + +--- + +**mandatory** + +The list of children anchored in parent dentry got turned into hlist now. +Field names got changed (->d_children/->d_sib instead of ->d_subdirs/->d_child +for anchor/entries resp.), so any affected places will be immediately caught +by compiler. diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 38c5be34c895..71019bfa0eb7 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -145,10 +145,11 @@ spufs_evict_inode(struct inode *inode) static void spufs_prune_dir(struct dentry *dir) { - struct dentry *dentry, *tmp; + struct dentry *dentry; + struct hlist_node *n; inode_lock(d_inode(dir)); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { + hlist_for_each_entry_safe(dentry, n, &dir->d_children, d_sib) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { dget_dlock(dentry); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 10905a53d5b2..8cb0f28b38e0 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -373,7 +373,7 @@ int afs_dynroot_populate(struct super_block *sb) void afs_dynroot_depopulate(struct super_block *sb) { struct afs_net *net = afs_sb2net(sb); - struct dentry *root = sb->s_root, *subdir, *tmp; + struct dentry *root = sb->s_root, *subdir; /* Prevent more subdirs from being created */ mutex_lock(&net->proc_cells_lock); @@ -382,10 +382,11 @@ void afs_dynroot_depopulate(struct super_block *sb) mutex_unlock(&net->proc_cells_lock); if (root) { + struct hlist_node *n; inode_lock(root->d_inode); /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) { if (subdir->d_fsdata) { subdir->d_fsdata = NULL; dput(subdir); diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 038b3d2d9f57..39d8c84c16f4 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -73,12 +73,9 @@ static int autofs_mount_busy(struct vfsmount *mnt, /* p->d_lock held */ static struct dentry *positive_after(struct dentry *p, struct dentry *child) { - if (child) - child = list_next_entry(child, d_child); - else - child = list_first_entry(&p->d_subdirs, struct dentry, d_child); + child = child ? d_next_sibling(child) : d_first_child(p); - list_for_each_entry_from(child, &p->d_subdirs, d_child) { + hlist_for_each_entry_from(child, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { dget_dlock(child); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 1395b71df5cc..2b23577be7d2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -171,7 +171,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx, /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_child when we initially get results back from the MDS, and + * d_children when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 11289ce8a8cc..d4d9266ff6d7 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2100,7 +2100,7 @@ static bool drop_negative_children(struct dentry *dentry) goto out; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_child) { + hlist_for_each_entry(child, &dentry->d_children, d_sib) { if (d_really_is_positive(child)) { all_negative = false; break; diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 3b8c4513118f..c2e9fb052d7b 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -93,7 +93,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_child) { + hlist_for_each_entry(de, &parent->d_children, d_sib) { /* don't know what to do with negative dentries */ if (d_inode(de) ) coda_flag_inode(d_inode(de), flag); diff --git a/fs/dcache.c b/fs/dcache.c index 3e0b9abbf4d8..95dd0c659fdc 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -51,8 +51,8 @@ * - d_lru * - d_count * - d_unhashed() - * - d_parent and d_subdirs - * - childrens' d_child and d_parent + * - d_parent and d_chilren + * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: @@ -550,7 +550,7 @@ void d_drop(struct dentry *dentry) } EXPORT_SYMBOL(d_drop); -static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) +static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* @@ -558,12 +558,12 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; - if (unlikely(list_empty(&dentry->d_child))) + if (unlikely(hlist_unhashed(&dentry->d_sib))) return; - __list_del_entry(&dentry->d_child); + __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been - * a normal list member, it didn't matter - ->d_child.next would've + * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - @@ -571,20 +571,20 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found - * using the value left in its ->d_child.next. And if _that_ + * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * - * Solution: make sure that the pointer left behind in ->d_child.next + * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ - while (dentry->d_child.next != &parent->d_subdirs) { - next = list_entry(dentry->d_child.next, struct dentry, d_child); + while (dentry->d_sib.next) { + next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; - dentry->d_child.next = next->d_child.next; + dentry->d_sib.next = next->d_sib.next; } } @@ -613,7 +613,7 @@ static void __dentry_kill(struct dentry *dentry) } /* if it was on the hash then remove it */ __d_drop(dentry); - dentry_unlist(dentry, parent); + dentry_unlist(dentry); if (parent) { if (dentry->d_flags & DCACHE_NEGATIVE_ACCOUNT) { atomic_dec(&parent->d_neg_dnum); @@ -1421,8 +1421,7 @@ enum d_walk_ret { static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { - struct dentry *this_parent; - struct list_head *next; + struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; @@ -1444,13 +1443,9 @@ static void d_walk(struct dentry *parent, void *data, break; } repeat: - next = this_parent->d_subdirs.next; + dentry = d_first_child(this_parent); resume: - while (next != &this_parent->d_subdirs) { - struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_child); - next = tmp->next; - + hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; @@ -1471,7 +1466,7 @@ static void d_walk(struct dentry *parent, void *data, continue; } - if (!list_empty(&dentry->d_subdirs)) { + if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; @@ -1486,24 +1481,23 @@ static void d_walk(struct dentry *parent, void *data, rcu_read_lock(); ascend: if (this_parent != parent) { - struct dentry *child = this_parent; - this_parent = child->d_parent; + dentry = this_parent; + this_parent = dentry->d_parent; - spin_unlock(&child->d_lock); + spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ - do { - next = child->d_child.next; - if (next == &this_parent->d_subdirs) - goto ascend; - child = list_entry(next, struct dentry, d_child); - } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); - rcu_read_unlock(); - goto resume; + hlist_for_each_entry_continue(dentry, d_sib) { + if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { + rcu_read_unlock(); + goto resume; + } + } + goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; @@ -1603,7 +1597,7 @@ int d_set_mounted(struct dentry *dentry) * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level - * whenever the d_subdirs list is non-empty and continue + * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, @@ -1730,7 +1724,7 @@ EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ - if (!list_empty(&dentry->d_subdirs)) + if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ @@ -1888,9 +1882,9 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); - INIT_LIST_HEAD(&dentry->d_subdirs); + INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); - INIT_LIST_HEAD(&dentry->d_child); + INIT_HLIST_NODE(&dentry->d_sib); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { @@ -1947,7 +1941,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) */ __dget_dlock(parent); dentry->d_parent = parent; - list_add(&dentry->d_child, &parent->d_subdirs); + hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); out: return dentry; @@ -3093,11 +3087,15 @@ static void __d_move(struct dentry *dentry, struct dentry *target, } else { target->d_parent = old_parent; swap_names(dentry, target); - list_move(&target->d_child, &target->d_parent->d_subdirs); + if (!hlist_unhashed(&target->d_sib)) + __hlist_del(&target->d_sib); + hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } - list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); + if (!hlist_unhashed(&dentry->d_sib)) + __hlist_del(&dentry->d_sib); + hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); diff --git a/fs/libfs.c b/fs/libfs.c index fd5d30c798de..cdb9d5683aec 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -101,15 +101,16 @@ EXPORT_SYMBOL(dcache_dir_close); * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, - struct list_head *p, + struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); - while ((p = p->next) != &dentry->d_subdirs) { - struct dentry *d = list_entry(p, struct dentry, d_child); + while (*p) { + struct dentry *d = hlist_entry(*p, struct dentry, d_sib); + p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; @@ -123,8 +124,10 @@ static struct dentry *scan_positives(struct dentry *cursor, count = 1; } if (need_resched()) { - list_move(&cursor->d_child, p); - p = &cursor->d_child; + if (!hlist_unhashed(&cursor->d_sib)) + __hlist_del(&cursor->d_sib); + hlist_add_behind(&cursor->d_sib, &d->d_sib); + p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); @@ -156,13 +159,12 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) inode_lock_shared(dentry->d_inode); if (offset > 2) - to = scan_positives(cursor, &dentry->d_subdirs, + to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); + hlist_del_init(&cursor->d_sib); if (to) - list_move(&cursor->d_child, &to->d_child); - else - list_del_init(&cursor->d_child); + hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); @@ -184,19 +186,16 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *anchor = &dentry->d_subdirs; struct dentry *next = NULL; - struct list_head *p; + struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) - p = anchor; - else if (!list_empty(&cursor->d_child)) - p = &cursor->d_child; + p = &dentry->d_children.first; else - return 0; + p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, @@ -204,13 +203,12 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; - p = &next->d_child; + p = &next->d_sib.next; } spin_lock(&dentry->d_lock); + hlist_del_init(&cursor->d_sib); if (next) - list_move_tail(&cursor->d_child, &next->d_child); - else - list_del_init(&cursor->d_child); + hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); @@ -544,12 +542,11 @@ const struct file_operations simple_offset_dir_operations = { static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { - struct dentry *child = NULL; - struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs; + struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); - while ((p = p->next) != &parent->d_subdirs) { - struct dentry *d = container_of(p, struct dentry, d_child); + d = prev ? d_next_sibling(prev) : d_first_child(parent); + hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) @@ -710,7 +707,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_child) { + hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 887035b74467..83e0d7555374 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1285,9 +1285,10 @@ static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) static void nfsdfs_remove_files(struct dentry *root) { - struct dentry *dentry, *tmp; + struct dentry *dentry; + struct hlist_node *n; - list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) { + hlist_for_each_entry_safe(dentry, n, &root->d_children, d_sib) { if (!simple_positive(dentry)) { WARN_ON_ONCE(1); /* I think this can't happen? */ continue; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 9cc4ebb53504..d334cafd6020 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -120,7 +120,7 @@ void fsnotify_set_children_dentry_flags(struct inode *inode) * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_child) { + hlist_for_each_entry(child, &alias->d_children, d_sib) { if (!child->d_inode) continue; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3c29580178cd..c94aaeb401f9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -69,12 +69,12 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 32 /* 192 bytes */ +# define DNAME_INLINE_LEN 40 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 36 /* 128 bytes */ -# else # define DNAME_INLINE_LEN 40 /* 128 bytes */ +# else +# define DNAME_INLINE_LEN 44 /* 128 bytes */ # endif #endif @@ -103,8 +103,8 @@ struct dentry { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; - struct list_head d_child; /* child of parent list */ - struct list_head d_subdirs; /* our children */ + struct hlist_node d_sib; /* child of parent list */ + struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ @@ -611,4 +611,14 @@ struct name_snapshot { void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); +static inline struct dentry *d_first_child(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); +} + +static inline struct dentry *d_next_sibling(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); +} + #endif /* __LINUX_DCACHE_H */ -- 2.39.2

From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v6.12-rc3 commit 903dc9c43a155e0893280c7472d4a9a3a83d75a6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Testing shows that the EBUSY error return from mtree_alloc_cyclic() leaks into user space. The ERRORS section of "man creat(2)" says:

EBUSY O_EXCL was specified in flags and pathname refers to a block device that is in use by the system (e.g., it is mounted).

ENOSPC is closer to what applications expect in this situation. Note that the normal range of simple directory offset values is 2..2^63, so hitting this error is going to be rare to impossible. Fixes: 6faddda69f62 ("libfs: Add directory operations for stable offsets") Cc: stable@vger.kernel.org # v6.9+ Reviewed-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-2-cel@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index cdb9d5683aec..bf2ea681bbb8 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -284,8 +284,8 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, LONG_MAX, &octx->next_offset, GFP_KERNEL); - if (ret < 0) - return ret; + if (unlikely(ret < 0)) + return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; -- 2.39.2

From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v6.12-rc3 commit b662d858131da9a8a14e68661656989b14dbf113 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The current directory offset allocator (based on mtree_alloc_cyclic) stores the next offset value to return in octx->next_offset. This mechanism typically returns values that increase monotonically over time. Eventually, though, the newly allocated offset value wraps back to a low number (say, 2) which is smaller than other already- allocated offset values. Yu Kuai <yukuai3@huawei.com> reports that, after commit 64a7ce76fb90 ("libfs: fix infinite directory reads for offset dir"), if a directory's offset allocator wraps, existing entries are no longer visible via readdir/getdents because offset_readdir() stops listing entries once an entry's offset is larger than octx->next_offset. These entries vanish persistently -- they can be looked up, but will never again appear in readdir(3) output. The reason for this is that the commit treats directory offsets as monotonically increasing integer values rather than opaque cookies, and introduces this comparison: if (dentry2offset(dentry) >= last_index) { On 64-bit platforms, the directory offset value upper bound is 2^63 - 1. Directory offsets will monotonically increase for millions of years without wrapping. On 32-bit platforms, however, LONG_MAX is 2^31 - 1. The allocator can wrap after only a few weeks (at worst). Revert commit 64a7ce76fb90 ("libfs: fix infinite directory reads for offset dir") to prepare for a fix that can work properly on 32-bit systems and might apply to recent LTS kernels where shmem employs the simple_offset mechanism. Reported-by: Yu Kuai <yukuai3@huawei.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-4-cel@kernel.org Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 35 +++++++++++------------------------ 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 86c96964e181..aa1ee33b6899 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -371,14 +371,6 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } -static int offset_dir_open(struct inode *inode, struct file *file) -{ - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - - file->private_data = (void *)ctx->next_offset; - return 0; -} - /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -392,9 +384,6 @@ static int offset_dir_open(struct inode *inode, struct file *file) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { - struct inode *inode = file->f_inode; - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -408,8 +397,7 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) } /* In this case, ->private_data is protected by f_pos_lock */ - if (!offset) - file->private_data = (void *)ctx->next_offset; + file->private_data = NULL; return vfs_setpos(file, offset, LONG_MAX); } @@ -440,7 +428,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) +static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -448,21 +436,17 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return; - - if (dentry2offset(dentry) >= last_index) { - dput(dentry); - return; - } + return ERR_PTR(-ENOENT); if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - return; + break; } ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } + return NULL; } /** @@ -489,19 +473,22 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; - long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - offset_iterate_dir(d_inode(dir), ctx, last_index); + /* In this case, ->private_data is protected by f_pos_lock */ + if (ctx->pos == DIR_OFFSET_MIN) + file->private_data = NULL; + else if (file->private_data == ERR_PTR(-ENOENT)) + return 0; + file->private_data = offset_iterate_dir(d_inode(dir), ctx); return 0; } const struct file_operations simple_offset_dir_operations = { - .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, -- 2.39.2

From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v6.12-rc3 commit b9b588f22a0c049a14885399e27625635ae6ef91 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWT7 CVE: CVE-2024-57952 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The mtree mechanism has been effective at creating directory offsets that are stable over multiple opendir instances. However, it has not been able to handle the subtleties of renames that are concurrent with readdir. Instead of using the mtree to emit entries in the order of their offset values, use it only to map incoming ctx->pos to a starting entry. Then use the directory's d_children list, which is already maintained properly by the dcache, to find the next child to emit. One of the sneaky things about this is that when the mtree-allocated offset value wraps (which is very rare), looking up ctx->pos++ is not going to find the next entry; it will return NULL. Instead, by following the d_children list, the offset values can appear in any order but all of the entries in the directory will be visited eventually. Note also that the readdir() is guaranteed to reach the tail of this list. Entries are added only at the head of d_children, and readdir walks from its current position in that list towards its tail. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20241228175522.1854234-6-cel@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1@huawei.com> --- fs/libfs.c | 84 +++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 58 insertions(+), 26 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 6369390f40d4..6ded891f79d6 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -239,12 +239,13 @@ EXPORT_SYMBOL(simple_dir_inode_operations); /* simple_offset_add() never assigns these to a dentry */ enum { + DIR_OFFSET_FIRST = 2, /* Find first real entry */ DIR_OFFSET_EOD = S32_MAX, }; /* simple_offset_add() allocation range */ enum { - DIR_OFFSET_MIN = 2, + DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; @@ -406,51 +407,82 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) +static struct dentry *find_positive_dentry(struct dentry *parent, + struct dentry *dentry, + bool next) { - MA_STATE(mas, &octx->mt, offset, offset); + struct dentry *found = NULL; + + spin_lock(&parent->d_lock); + if (next) + dentry = d_next_sibling(dentry); + else if (!dentry) + dentry = d_first_child(parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (!simple_positive(dentry)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(dentry)) + found = dget_dlock(dentry); + spin_unlock(&dentry->d_lock); + if (likely(found)) + break; + } + spin_unlock(&parent->d_lock); + return found; +} + +static noinline_for_stack struct dentry * +offset_dir_lookup(struct dentry *parent, loff_t offset) +{ + struct inode *inode = d_inode(parent); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; - rcu_read_lock(); - child = mas_find(&mas, DIR_OFFSET_MAX); - if (!child) - goto out; - spin_lock(&child->d_lock); - if (simple_positive(child)) - found = dget_dlock(child); - spin_unlock(&child->d_lock); -out: - rcu_read_unlock(); + MA_STATE(mas, &octx->mt, offset, offset); + + if (offset == DIR_OFFSET_FIRST) + found = find_positive_dentry(parent, NULL, false); + else { + rcu_read_lock(); + child = mas_find(&mas, DIR_OFFSET_MAX); + found = find_positive_dentry(parent, child, false); + rcu_read_unlock(); + } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - long offset = dentry2offset(dentry); - return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, - inode->i_ino, fs_umode_to_dtype(inode->i_mode)); + return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, + inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { - struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); + struct dentry *dir = file->f_path.dentry; struct dentry *dentry; + dentry = offset_dir_lookup(dir, ctx->pos); + if (!dentry) + goto out_eod; while (true) { - dentry = offset_find_next(octx, ctx->pos); - if (!dentry) - goto out_eod; + struct dentry *next; - if (!offset_dir_emit(ctx, dentry)) { - dput(dentry); + ctx->pos = dentry2offset(dentry); + if (!offset_dir_emit(ctx, dentry)) break; - } - ctx->pos = dentry2offset(dentry) + 1; + next = find_positive_dentry(dir, dentry, true); dput(dentry); + + if (!next) + goto out_eod; + dentry = next; } + dput(dentry); return; out_eod: @@ -489,7 +521,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos != DIR_OFFSET_EOD) - offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(file, ctx); return 0; } -- 2.39.2