Re: [PATCH v2 1/1] NFSD: fix problems with cleanup on errors in nfsd4_copy

[Jeff Layton <jlayton@kernel.org>]

On Sat, 2023-01-28 at 20:44 -0800, Dai Ngo wrote:
> When nfsd4_copy fails to allocate memory for async_copy->cp_src, or
> nfs4_init_copy_state fails, it calls cleanup_async_copy to do the
> cleanup for the async_copy which causes page fault since async_copy
> is not yet initialized.
> 
> This patch rearranges the order of initializing the fields in
> async_copy and adds checks in cleanup_async_copy to skip un-initialized
> fields.
> 
> Fixes: ce0887ac96d3 ("NFSD add nfs4 inter ssc to nfsd4_copy")
> Fixes: 87689df69491 ("NFSD: Shrink size of struct nfsd4_copy")
> Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
> ---
>  fs/nfsd/nfs4proc.c  | 12 ++++++++----
>  fs/nfsd/nfs4state.c |  5 +++--
>  2 files changed, 11 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
> index 57f791899de3..0754b38d3a43 100644
> --- a/fs/nfsd/nfs4proc.c
> +++ b/fs/nfsd/nfs4proc.c
> @@ -1687,9 +1687,12 @@ static void cleanup_async_copy(struct nfsd4_copy *copy)
>  {
>  	nfs4_free_copy_state(copy);
>  	release_copy_files(copy);
> -	spin_lock(&copy->cp_clp->async_lock);
> -	list_del(&copy->copies);
> -	spin_unlock(&copy->cp_clp->async_lock);
> +	if (copy->cp_clp) {
> +		spin_lock(&copy->cp_clp->async_lock);
> +		if (!list_empty(&copy->copies))
> +			list_del(&copy->copies);

Can we make this a list_del_init? If cleanup_async_copy were called on
this twice, then the second time could end up corrupting the
async_copies list. The cost difference is negligible here.

> +		spin_unlock(&copy->cp_clp->async_lock);
> +	}
>  	nfs4_put_copy(copy);
>  }
>  
> @@ -1786,12 +1789,13 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
>  		async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
>  		if (!async_copy)
>  			goto out_err;
> +		INIT_LIST_HEAD(&async_copy->copies);
> +		refcount_set(&async_copy->refcount, 1);
>  		async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL);
>  		if (!async_copy->cp_src)
>  			goto out_err;
>  		if (!nfs4_init_copy_state(nn, copy))
>  			goto out_err;
> -		refcount_set(&async_copy->refcount, 1);
>  		memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.cs_stid,
>  			sizeof(copy->cp_res.cb_stateid));
>  		dup_copy_fields(copy, async_copy);
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index ace02fd0d590..c39e43742dd6 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -975,7 +975,6 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
>  
>  	stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
>  	stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
> -	stid->cs_type = cs_type;
>  
>  	idr_preload(GFP_KERNEL);
>  	spin_lock(&nn->s2s_cp_lock);
> @@ -986,6 +985,7 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
>  	idr_preload_end();
>  	if (new_id < 0)
>  		return 0;
> +	stid->cs_type = cs_type;
>  	return 1;
>  }
>  
> @@ -1019,7 +1019,8 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy)
>  {
>  	struct nfsd_net *nn;
>  
> -	WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID);
> +	if (copy->cp_stateid.cs_type != NFS4_COPY_STID)
> +		return;

It's probably fine to keep the WARN_ON_ONCE here. You're testing the
condition anyway so you can do:

    if (WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID))


>  	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
>  	spin_lock(&nn->s2s_cp_lock);
>  	idr_remove(&nn->s2s_cp_stateids,

-- 
Jeff Layton <jlayton@kernel.org>