Re: [PATCH RFC v2 3/4] pNFS/flexfiles: Treat ENETUNREACH errors as fatal in containers

[Jeff Layton <jlayton@kernel.org>]

On Thu, 2025-03-20 at 16:40 -0400, trondmy@kernel.org wrote:
> From: Trond Myklebust <trond.myklebust@hammerspace.com>
> 
> Propagate the NFS_MOUNT_NETUNREACH_FATAL flag to work with the pNFS
> flexfiles client. In these circumstances, the client needs to treat the
> ENETDOWN and ENETUNREACH errors as fatal, and should abandon the
> attempted I/O.
> 
> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> ---
>  fs/nfs/flexfilelayout/flexfilelayout.c | 23 +++++++++++++++++++++--
>  fs/nfs/nfs3client.c                    |  2 ++
>  fs/nfs/nfs4client.c                    |  5 +++++
>  include/linux/nfs4.h                   |  1 +
>  4 files changed, 29 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
> index 98b45b636be3..f89fdba7289d 100644
> --- a/fs/nfs/flexfilelayout/flexfilelayout.c
> +++ b/fs/nfs/flexfilelayout/flexfilelayout.c
> @@ -1154,10 +1154,14 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
>  		rpc_wake_up(&tbl->slot_tbl_waitq);
>  		goto reset;
>  	/* RPC connection errors */
> +	case -ENETDOWN:
> +	case -ENETUNREACH:
> +		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
> +			return -NFS4ERR_FATAL_IOERROR;
> +		fallthrough;
>  	case -ECONNREFUSED:
>  	case -EHOSTDOWN:
>  	case -EHOSTUNREACH:
> -	case -ENETUNREACH:
>  	case -EIO:
>  	case -ETIMEDOUT:
>  	case -EPIPE:
> @@ -1183,6 +1187,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
>  
>  /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
>  static int ff_layout_async_handle_error_v3(struct rpc_task *task,
> +					   struct nfs_client *clp,
>  					   struct pnfs_layout_segment *lseg,
>  					   u32 idx)
>  {
> @@ -1200,6 +1205,11 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
>  	case -EJUKEBOX:
>  		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
>  		goto out_retry;
> +	case -ENETDOWN:
> +	case -ENETUNREACH:
> +		if (test_bit(NFS_CS_NETUNREACH_FATAL, &clp->cl_flags))
> +			return -NFS4ERR_FATAL_IOERROR;
> +		fallthrough;
>  	default:
>  		dprintk("%s DS connection error %d\n", __func__,
>  			task->tk_status);
> @@ -1234,7 +1244,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
>  
>  	switch (vers) {
>  	case 3:
> -		return ff_layout_async_handle_error_v3(task, lseg, idx);
> +		return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
>  	case 4:
>  		return ff_layout_async_handle_error_v4(task, state, clp,
>  						       lseg, idx);
> @@ -1337,6 +1347,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
>  		return task->tk_status;
>  	case -EAGAIN:
>  		goto out_eagain;
> +	case -NFS4ERR_FATAL_IOERROR:
> +		task->tk_status = -EIO;
> +		return 0;
>  	}
>  
>  	return 0;
> @@ -1507,6 +1520,9 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
>  		return task->tk_status;
>  	case -EAGAIN:
>  		return -EAGAIN;
> +	case -NFS4ERR_FATAL_IOERROR:
> +		task->tk_status = -EIO;
> +		return 0;
>  	}
>  
>  	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
> @@ -1551,6 +1567,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
>  	case -EAGAIN:
>  		rpc_restart_call_prepare(task);
>  		return -EAGAIN;
> +	case -NFS4ERR_FATAL_IOERROR:
> +		task->tk_status = -EIO;
> +		return 0;
>  	}
>  
>  	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
> diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
> index b0c8a39c2bbd..0d7310c1ee0c 100644
> --- a/fs/nfs/nfs3client.c
> +++ b/fs/nfs/nfs3client.c
> @@ -120,6 +120,8 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
>  
>  	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
>  		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
> +	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
> +		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
>  
>  	__set_bit(NFS_CS_DS, &cl_init.init_flags);
>  
> diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
> index 8f7d40844cdc..9bfb88d791ab 100644
> --- a/fs/nfs/nfs4client.c
> +++ b/fs/nfs/nfs4client.c
> @@ -939,6 +939,9 @@ static int nfs4_set_client(struct nfs_server *server,
>  		__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
>  	server->port = rpc_get_port((struct sockaddr *)addr);
>  
> +	if (server->options & NFS_MOUNT_NETUNREACH_FATAL)

^^^

That should be checking server->flags.

With that fix in place, this patchset seems to do the right thing. It
takes roughly a minute or two for the RPCs to expire, but they do
eventually expire now.

Nice work!


> +		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
> +
>  	/* Allocate or find a client reference we can use */
>  	clp = nfs_get_client(&cl_init);
>  	if (IS_ERR(clp))
> @@ -1013,6 +1016,8 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
>  
>  	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
>  		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
> +	if (test_bit(NFS_CS_NETUNREACH_FATAL, &mds_clp->cl_flags))
> +		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
>  
>  	__set_bit(NFS_CS_PNFS, &cl_init.init_flags);
>  	cl_init.max_connect = NFS_MAX_TRANSPORTS;
> diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
> index 5fa60fe441b5..d8cad844870a 100644
> --- a/include/linux/nfs4.h
> +++ b/include/linux/nfs4.h
> @@ -300,6 +300,7 @@ enum nfsstat4 {
>  /* error codes for internal client use */
>  #define NFS4ERR_RESET_TO_MDS   12001
>  #define NFS4ERR_RESET_TO_PNFS  12002
> +#define NFS4ERR_FATAL_IOERROR  12003
>  
>  static inline bool seqid_mutating_err(u32 err)
>  {

-- 
Jeff Layton <jlayton@kernel.org>