6.18-stable review patch. If anyone has any objections, please let me know. ------------------ From: Aldo Ariel Panzardo [ Upstream commit 2cb947450e0e5a88bb6bb5fca6dbfda1910e74b0 ] nilfs_find_or_create_root() links a new checkpoint root into the checkpoint tree and drops ns_cptree_lock before creating the root's sysfs group. If nilfs_sysfs_create_snapshot_group() then fails, the root is freed while it is still reachable from ns_cptree, so a concurrent nilfs_lookup_root() can dereference freed memory. nilfs_sysfs_create_snapshot_group() allocates memory and creates sysfs nodes and may sleep, so it cannot run under the ns_cptree_lock spinlock. Reorder the creation path so that the sysfs group is set up before the root is published: initialize the root, create its sysfs group outside the lock, and only then take ns_cptree_lock to link it into the tree. On sysfs failure the root was never visible and is freed directly; in the unlikely case a root with the same checkpoint number is already present, the sysfs group of the new root is removed before it is freed. Concurrent insertions are already serialized by ns_snapshot_mount_mutex, so only the race against nilfs_lookup_root() needs to be closed. Because kobject_put() does not guarantee that the embedded kobject's release callback has run by the time it returns (CONFIG_DEBUG_KOBJECT_RELEASE defers it), the container must not be freed until the release completes. Keep that wait_for_completion() of snapshot_kobj_unregister inside the sysfs helpers, so both the creation error path and nilfs_sysfs_delete_snapshot_group() wait for the release before their callers free the root. Fixes: dd70edbde262 ("nilfs2: integrate sysfs support into driver") Cc: stable@vger.kernel.org Signed-off-by: Aldo Ariel Panzardo Acked-by: Ryusuke Konishi Signed-off-by: Viacheslav Dubeyko Signed-off-by: Sasha Levin --- fs/nilfs2/sysfs.c | 5 ++++- fs/nilfs2/the_nilfs.c | 34 +++++++++++++++++++++------------- 2 files changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index bc52afbfc5c73..5bb74a45ad1ed 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -195,8 +195,10 @@ int nilfs_sysfs_create_snapshot_group(struct nilfs_root *root) "%llu", root->cno); } - if (err) + if (err) { kobject_put(&root->snapshot_kobj); + wait_for_completion(&root->snapshot_kobj_unregister); + } return err; } @@ -204,6 +206,7 @@ int nilfs_sysfs_create_snapshot_group(struct nilfs_root *root) void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *root) { kobject_put(&root->snapshot_kobj); + wait_for_completion(&root->snapshot_kobj_unregister); } /************************************************************************ diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 9911a484398a0..b453229db3af9 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -887,6 +887,26 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno) if (!new) return NULL; + new->cno = cno; + new->ifile = NULL; + new->nilfs = nilfs; + refcount_set(&new->count, 1); + atomic64_set(&new->inodes_count, 0); + atomic64_set(&new->blocks_count, 0); + + /* + * Register the sysfs group before publishing the root in the + * checkpoint tree. nilfs_sysfs_create_snapshot_group() can sleep, + * so it must run outside ns_cptree_lock; creating it first also + * ensures a concurrent nilfs_lookup_root() can never observe a root + * whose sysfs registration later fails and gets freed. + */ + err = nilfs_sysfs_create_snapshot_group(new); + if (err) { + kfree(new); + return NULL; + } + spin_lock(&nilfs->ns_cptree_lock); p = &nilfs->ns_cptree.rb_node; @@ -903,29 +923,17 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno) } else { refcount_inc(&root->count); spin_unlock(&nilfs->ns_cptree_lock); + nilfs_sysfs_delete_snapshot_group(new); kfree(new); return root; } } - new->cno = cno; - new->ifile = NULL; - new->nilfs = nilfs; - refcount_set(&new->count, 1); - atomic64_set(&new->inodes_count, 0); - atomic64_set(&new->blocks_count, 0); - rb_link_node(&new->rb_node, parent, p); rb_insert_color(&new->rb_node, &nilfs->ns_cptree); spin_unlock(&nilfs->ns_cptree_lock); - err = nilfs_sysfs_create_snapshot_group(new); - if (err) { - kfree(new); - new = NULL; - } - return new; } -- 2.53.0