Re: [PATCH IB/core 2/2] IB/cm: Send authentic pkey in REQ msg and check eligibility of the pkeys

[Hal Rosenstock]

On 5/9/2018 5:30 AM, HÃkon Bugge wrote:
> There is no point in using RDMA CM to establish a connection between
> two QPs that cannot possible communicate. Particularly, if both the
> active and passive side use limited pkeys, they are not able to
> communicate.
> 
> In order to detect this situation, the authentic pkey is used in the
> CM REQ message. The authentic pkey is the one that the HCA inserts
> into the BTH in the IB packets.
> 
> When the passive side receives the REQ, commit ("ib_core: A full pkey
> is required to match a limited one") ensures that
> ib_find_matched_cached_pkey() fails unless at least one of the pkeys
> compared has the full-member bit.
> 
> In the limited-to-limited case, this will prohibit the connection to
> be formed, and thus, Pkey Violation Traps will not be sent to the SM.
> 
> Signed-off-by: HÃkon Bugge <haakon.bugge@xxxxxxxxxx>
> ---
>  drivers/infiniband/core/cm.c | 39 ++++++++++++++++++++++++++++++++-------
>  include/rdma/ib_cm.h         |  4 +++-
>  2 files changed, 35 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
> index a92e1a5c202b..52ed51d5bd2a 100644
> --- a/drivers/infiniband/core/cm.c
> +++ b/drivers/infiniband/core/cm.c
> @@ -3,6 +3,7 @@
>   * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
>   * Copyright (c) 2004, 2005 Voltaire Corporation.  All rights reserved.
>   * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
> + * Copyright (c) 2018 Oracle and/or its affiliates. All rights reserved.
>   *
>   * This software is available to you under a choice of one of two
>   * licenses.  You may choose to be licensed under the terms of the GNU
> @@ -91,6 +92,7 @@ static const char * const ibcm_rej_reason_strs[] = {
>  	[IB_CM_REJ_INVALID_CLASS_VERSION]	= "invalid class version",
>  	[IB_CM_REJ_INVALID_FLOW_LABEL]		= "invalid flow label",
>  	[IB_CM_REJ_INVALID_ALT_FLOW_LABEL]	= "invalid alt flow label",
> +	[IB_CM_REJ_INVALID_PKEY]		= "invalid PKey",

If this patch goes ahead, IBA spec for CM should be updated to include this.

>  };
>  
>  const char *__attribute_const__ ibcm_reject_msg(int reason)
> @@ -518,8 +520,8 @@ static int cm_init_av_by_path(struct sa_path_rec *path, struct cm_av *av,
>  		return -EINVAL;
>  	cm_dev = port->cm_dev;
>  
> -	ret = ib_find_cached_pkey(cm_dev->ib_device, port->port_num,
> -				  be16_to_cpu(path->pkey), &av->pkey_index);
> +	ret = ib_find_matched_cached_pkey(cm_dev->ib_device, port->port_num,
> +					  be16_to_cpu(path->pkey), &av->pkey_index);
>  	if (ret)
>  		return ret;
>  
> @@ -1241,7 +1243,7 @@ static void cm_format_req(struct cm_req_msg *req_msg,
>  	cm_req_set_starting_psn(req_msg, cpu_to_be32(param->starting_psn));
>  	cm_req_set_local_resp_timeout(req_msg,
>  				      param->local_cm_response_timeout);
> -	req_msg->pkey = param->primary_path->pkey;
> +	req_msg->pkey = cpu_to_be16(cm_id_priv->pkey);
>  	cm_req_set_path_mtu(req_msg, param->primary_path->mtu);
>  	cm_req_set_max_cm_retries(req_msg, param->max_cm_retries);
>  
> @@ -1396,7 +1398,23 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
>  	cm_id_priv->responder_resources = param->responder_resources;
>  	cm_id_priv->retry_count = param->retry_count;
>  	cm_id_priv->path_mtu = param->primary_path->mtu;
> -	cm_id_priv->pkey = param->primary_path->pkey;
> +
> +	/*
> +	 * We want to send the pkey used in the BTH in packets
> +	 * sent. This, in order for the passive side to determine if
> +	 * communication is permitted by the respective pkeys.
> +	 *
> +	 * The pkey in the paths are derived from the MGID, which has
> +	 * the full membership bit set. Hence, we retrieve the pkey by
> +	 * using the address vector's pkey_index.

The paths usually come from the SM and I don't expect SM to provide path
between ports of only limited members of partition. Default ACM provider
forms path from multicast group parameters including pkey. Is that the
scenario of concern ? If so, I still don't fully understand the scenario
because limited members are not supposed to be part of a multicast
group. There was some work started to extend this for client/server
model but it was never completed. However, there may be hole(s) in
various components of implementation which open(s) this door.

-- Hal

> +	 */
> +	ret = ib_get_cached_pkey(cm_id_priv->id.device,
> +				 cm_id_priv->av.port->port_num,
> +				 cm_id_priv->av.pkey_index,
> +				 &cm_id_priv->pkey);
> +	if (ret)
> +		goto error1;
> +
>  	cm_id_priv->qp_type = param->qp_type;
>  
>  	ret = cm_alloc_msg(cm_id_priv, &cm_id_priv->msg);
> @@ -1956,16 +1974,19 @@ static int cm_req_handler(struct cm_work *work)
>  				 cm_id_priv);
>  	if (ret) {
>  		int err;
> +		int rej_reason = (ret == -ENOENT ?
> +				  IB_CM_REJ_INVALID_PKEY :
> +				  IB_CM_REJ_INVALID_GID);
>  
>  		err = ib_get_cached_gid(work->port->cm_dev->ib_device,
>  					work->port->port_num, 0,
>  					&work->path[0].sgid,
>  					NULL);
>  		if (err)
> -			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
> +			ib_send_cm_rej(cm_id, rej_reason,
>  				       NULL, 0, NULL, 0);
>  		else
> -			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
> +			ib_send_cm_rej(cm_id, rej_reason,
>  				       &work->path[0].sgid,
>  				       sizeof(work->path[0].sgid),
>  				       NULL, 0);
> @@ -1975,7 +1996,11 @@ static int cm_req_handler(struct cm_work *work)
>  		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
>  					 cm_id_priv);
>  		if (ret) {
> -			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
> +			int rej_reason = (ret == -ENOENT ?
> +					  IB_CM_REJ_INVALID_PKEY :
> +					  IB_CM_REJ_INVALID_ALT_GID);
> +
> +			ib_send_cm_rej(cm_id, rej_reason,
>  				       &work->path[0].sgid,
>  				       sizeof(work->path[0].sgid), NULL, 0);
>  			goto rejected;
> diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
> index 7979cb04f529..56b62303946a 100644
> --- a/include/rdma/ib_cm.h
> +++ b/include/rdma/ib_cm.h
> @@ -3,6 +3,7 @@
>   * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
>   * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
>   * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
> + * Copyright (c) 2018 Oracle and/or its affiliates. All rights reserved.
>   *
>   * This software is available to you under a choice of one of two
>   * licenses.  You may choose to be licensed under the terms of the GNU
> @@ -183,7 +184,8 @@ enum ib_cm_rej_reason {
>  	IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID	= 30,
>  	IB_CM_REJ_INVALID_CLASS_VERSION		= 31,
>  	IB_CM_REJ_INVALID_FLOW_LABEL		= 32,
> -	IB_CM_REJ_INVALID_ALT_FLOW_LABEL	= 33
> +	IB_CM_REJ_INVALID_ALT_FLOW_LABEL	= 33,
> +	IB_CM_REJ_INVALID_PKEY			= 34,
>  };
>  
>  struct ib_cm_rej_event_param {
>