On Tue, 2022-03-01 at 19:30 +0800, xiubli@xxxxxxxxxx wrote:
> From: Xiubo Li <xiubli@xxxxxxxxxx>
>
> ------------[ cut here ]------------
> kernel BUG at fs/ceph/dir.c:537!
> invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
> CPU: 16 PID: 21641 Comm: ls Tainted: G E 5.17.0-rc2+ #92
> Hardware name: Red Hat RHEV Hypervisor, BIOS 1.11.0-2.el7 04/01/2014
>
> The corresponding code in ceph_readdir() is:
>
> BUG_ON(rde->offset < ctx->pos);
>
> Signed-off-by: Xiubo Li <xiubli@xxxxxxxxxx>
> ---
> fs/ceph/dir.c | 13 +++++++------
> fs/ceph/inode.c | 5 +++--
> fs/ceph/mds_client.c | 2 +-
> 3 files changed, 11 insertions(+), 9 deletions(-)
>
> diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
> index a449f4a07c07..6be0c1f793c2 100644
> --- a/fs/ceph/dir.c
> +++ b/fs/ceph/dir.c
> @@ -534,6 +534,13 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
> .ctext_len = rde->altname_len };
> u32 olen = oname.len;
>
> + err = ceph_fname_to_usr(&fname, &tname, &oname, NULL);
> + if (err) {
> + pr_err("%s unable to decode %.*s, got %d\n", __func__,
> + rde->name_len, rde->name, err);
> + goto out;
> + }
> +
> BUG_ON(rde->offset < ctx->pos);
> BUG_ON(!rde->inode.in);
>
> @@ -542,12 +549,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
> i, rinfo->dir_nr, ctx->pos,
> rde->name_len, rde->name, &rde->inode.in);
>
> - err = ceph_fname_to_usr(&fname, &tname, &oname, NULL);
> - if (err) {
> - dout("Unable to decode %.*s. Skipping it.\n", rde->name_len, rde->name);
> - continue;
> - }
> -
> if (!dir_emit(ctx, oname.name, oname.len,
> ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
> le32_to_cpu(rde->inode.in->mode) >> 12)) {
> diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> index 8b0832271fdf..2bc2f02b84e8 100644
> --- a/fs/ceph/inode.c
> +++ b/fs/ceph/inode.c
> @@ -1898,8 +1898,9 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
>
> err = ceph_fname_to_usr(&fname, &tname, &oname, &is_nokey);
> if (err) {
> - dout("Unable to decode %.*s. Skipping it.", rde->name_len, rde->name);
> - continue;
> + pr_err("%s unable to decode %.*s, got %d\n", __func__,
> + rde->name_len, rde->name, err);
> + goto out;
> }
>
Is this really an improvement? Suppose I have one dentry with a corrupt
name. Do I want to fail a readdir request which might allow me to get at
other dentries in that directory that isn't corrupt?
Maybe we should try to emit some placeholder there?
> dname.name = oname.name;
> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> index 914a6e68bb56..94b4c6508044 100644
> --- a/fs/ceph/mds_client.c
> +++ b/fs/ceph/mds_client.c
> @@ -3474,7 +3474,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
> if (err == 0) {
> if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
> req->r_op == CEPH_MDS_OP_LSSNAP))
> - ceph_readdir_prepopulate(req, req->r_session);
> + err = ceph_readdir_prepopulate(req, req->r_session);
> }
> current->journal_info = NULL;
> mutex_unlock(&req->r_fill_mutex);
--
Jeff Layton <jlayton@xxxxxxxxxx>
