IB/mad: Add support for additional MAD info to/from drivers

In order to support alternate sized MADs (and variable sized MADs on OPA
devices) add in/out MAD size parameters to the process_mad core call.

In addition, add an out_mad_pkey_index to communicate the pkey index the driver
wishes the MAD stack to use when sending OPA MAD responses.

The out MAD size and the out MAD PKey index are required by the MAD
stack to generate responses on OPA devices.

Furthermore, the in and out MAD parameters are made generic by specifying them
as ib_mad_hdr rather than ib_mad.

Drivers are modified as needed and are protected by BUG_ON flags if the MAD
sizes passed to them is incorrect.

Signed-off-by: Ira Weiny <[e-mail]>
Signed-off-by: Doug Ledford <[e-mail]>

drivers/infiniband/core/mad.c

···
 	struct ib_wc mad_wc;
 	struct ib_send_wr *send_wr = &mad_send_wr->send_wr;
 	size_t mad_size = port_mad_size(mad_agent_priv->qp_info->port_priv);
+	u16 out_mad_pkey_index = 0;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
···
 
 	/* No GRH for DR SMP */
 	ret = device->process_mad(device, 0, port_num, &mad_wc, NULL,
-				  (const struct ib_mad *)smp,
-				  (struct ib_mad *)mad_priv->mad);
+				  (const struct ib_mad_hdr *)smp, mad_size,
+				  (struct ib_mad_hdr *)mad_priv->mad,
+				  &mad_size, &out_mad_pkey_index);
 	switch (ret)
 	{
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY:
···
 	struct ib_mad_agent_private *mad_agent;
 	int port_num;
 	int ret = IB_MAD_RESULT_SUCCESS;
+	size_t mad_size;
+	u16 resp_mad_pkey_index = 0;
 
 	mad_list = (struct ib_mad_list_head *)(unsigned long)wc->wr_id;
 	qp_info = mad_list->mad_queue->qp_info;
···
 	if (!validate_mad((const struct ib_mad_hdr *)recv->mad, qp_info->qp->qp_num))
 		goto out;
 
-	response = alloc_mad_private(recv->mad_size, GFP_ATOMIC);
+	mad_size = recv->mad_size;
+	response = alloc_mad_private(mad_size, GFP_KERNEL);
 	if (!response) {
 		dev_err(&port_priv->device->dev,
 			"ib_mad_recv_done_handler no memory for response buffer\n");
···
 		ret = port_priv->device->process_mad(port_priv->device, 0,
 						     port_priv->port_num,
 						     wc, &recv->grh,
-						     (const struct ib_mad *)recv->mad,
-						     (struct ib_mad *)response->mad);
+						     (const struct ib_mad_hdr *)recv->mad,
+						     recv->mad_size,
+						     (struct ib_mad_hdr *)response->mad,
+						     &mad_size, &resp_mad_pkey_index);
 		if (ret & IB_MAD_RESULT_SUCCESS) {
 			if (ret & IB_MAD_RESULT_CONSUMED)
 				goto out;

drivers/infiniband/core/sysfs.c

···
 	int width  = (tab_attr->index >> 16) & 0xff;
 	struct ib_mad *in_mad  = NULL;
 	struct ib_mad *out_mad = NULL;
+	size_t mad_size = sizeof(*out_mad);
+	u16 out_mad_pkey_index = 0;
 	ssize_t ret;
 
 	if (!p->ibdev->process_mad)
···
 	in_mad->data[41] = p->port_num;	/* PortSelect field */
 
 	if ((p->ibdev->process_mad(p->ibdev, IB_MAD_IGNORE_MKEY,
-		 p->port_num, NULL, NULL, in_mad, out_mad) &
+		 p->port_num, NULL, NULL,
+		 (const struct ib_mad_hdr *)in_mad, mad_size,
+		 (struct ib_mad_hdr *)out_mad, &mad_size,
+		 &out_mad_pkey_index) &
 	     (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
 	    (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
 		ret = -EINVAL;

drivers/infiniband/hw/amso1100/c2_provider.c

···
 			  u8 port_num,
 			  const struct ib_wc *in_wc,
 			  const struct ib_grh *in_grh,
-			  const struct ib_mad *in_mad, struct ib_mad *out_mad)
+			  const struct ib_mad_hdr *in_mad,
+			  size_t in_mad_size,
+			  struct ib_mad_hdr *out_mad,
+			  size_t *out_mad_size,
+			  u16 *out_mad_pkey_index)
 {
 	pr_debug("%s:%u\n", __func__, __LINE__);
 	return -ENOSYS;

drivers/infiniband/hw/cxgb3/iwch_provider.c

···
 			    u8 port_num,
 			    const struct ib_wc *in_wc,
 			    const struct ib_grh *in_grh,
-			    const struct ib_mad *in_mad, struct ib_mad *out_mad)
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }

drivers/infiniband/hw/cxgb4/provider.c

···
 static int c4iw_process_mad(struct ib_device *ibdev, int mad_flags,
 			    u8 port_num, const struct ib_wc *in_wc,
 			    const struct ib_grh *in_grh,
-			    const struct ib_mad *in_mad,
-			    struct ib_mad *out_mad)
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }

drivers/infiniband/hw/ehca/ehca_iverbs.h

···
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		     const struct ib_mad *in_mad,
-		     struct ib_mad *out_mad);
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index);
 
 void ehca_poll_eqs(unsigned long data);
 

drivers/infiniband/hw/ehca/ehca_sqp.c

···
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		     const struct ib_mad *in_mad, struct ib_mad *out_mad)
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc)
 		return IB_MAD_RESULT_FAILURE;

drivers/infiniband/hw/ipath/ipath_mad.c

···
  */
 int ipath_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		      const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		      const struct ib_mad *in_mad, struct ib_mad *out_mad)
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/hw/ipath/ipath_verbs.h

···
 		      u8 port_num,
 		      const struct ib_wc *in_wc,
 		      const struct ib_grh *in_grh,
-		      const struct ib_mad *in_mad, struct ib_mad *out_mad);
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 
 /*
  * Compare the lower 24 bits of the two values.

drivers/infiniband/hw/mlx4/mad.c

···
 
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
+
 	switch (rdma_port_get_link_layer(ibdev, port_num)) {
 	case IB_LINK_LAYER_INFINIBAND:
 		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,

drivers/infiniband/hw/mlx4/mlx4_ib.h

···
 		 const void *in_mad, void *response_mad);
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags,	u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 int mlx4_ib_mad_init(struct mlx4_ib_dev *dev);
 void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev);
 

drivers/infiniband/hw/mlx5/mad.c

···
 
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
 	u16 slid;
 	int err;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

···
 int mlx5_ib_fmr_dealloc(struct ib_fmr *ibfmr);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_ucontext *context,
 					  struct ib_udata *udata);

drivers/infiniband/hw/mthca/mthca_dev.h

···
 		      u8 port_num,
 		      const struct ib_wc *in_wc,
 		      const struct ib_grh *in_grh,
-		      const struct ib_mad *in_mad,
-		      struct ib_mad *out_mad);
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 int mthca_create_agents(struct mthca_dev *dev);
 void mthca_free_agents(struct mthca_dev *dev);
 

drivers/infiniband/hw/mthca/mthca_mad.c

···
 		      u8 port_num,
 		      const struct ib_wc *in_wc,
 		      const struct ib_grh *in_grh,
-		      const struct ib_mad *in_mad,
-		      struct ib_mad *out_mad)
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int err;
 	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	/* Forward locally generated traps to the SM */
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&

drivers/infiniband/hw/nes/nes_verbs.c

···
  */
 static int nes_process_mad(struct ib_device *ibdev, int mad_flags,
 		u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		const struct ib_mad *in_mad, struct ib_mad *out_mad)
+		const struct ib_mad_hdr *in, size_t in_mad_size,
+		struct ib_mad_hdr *out, size_t *out_mad_size,
+		u16 *out_mad_pkey_index)
 {
 	nes_debug(NES_DBG_INIT, "\n");
 	return -ENOSYS;

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

···
 		       u8 port_num,
 		       const struct ib_wc *in_wc,
 		       const struct ib_grh *in_grh,
-		       const struct ib_mad *in_mad, struct ib_mad *out_mad)
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index)
 {
 	int status;
 	struct ocrdma_dev *dev;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_PERF_MGMT:

drivers/infiniband/hw/ocrdma/ocrdma_ah.h

···
 		       u8 port_num,
 		       const struct ib_wc *in_wc,
 		       const struct ib_grh *in_grh,
-		       const struct ib_mad *in_mad, struct ib_mad *out_mad);
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index);
 #endif				/* __OCRDMA_AH_H__ */

drivers/infiniband/hw/qib/qib_mad.c

···
  */
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		    const struct ib_mad *in_mad, struct ib_mad *out_mad)
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index)
 {
 	int ret;
 	struct qib_ibport *ibp = to_iport(ibdev, port);
 	struct qib_pportdata *ppd = ppd_from_ibp(ibp);
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/hw/qib/qib_verbs.h

···
 void qib_node_desc_chg(struct qib_ibport *ibp);
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		    const struct ib_mad *in_mad, struct ib_mad *out_mad);
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index);
 int qib_create_agents(struct qib_ibdev *dev);
 void qib_free_agents(struct qib_ibdev *dev);
 

include/rdma/ib_verbs.h

···
 	struct ib_uobject	*uobject;
 };
 
-struct ib_mad;
+struct ib_mad_hdr;
 struct ib_grh;
 
 enum ib_process_mad_flags {
···
 						  u8 port_num,
 						  const struct ib_wc *in_wc,
 						  const struct ib_grh *in_grh,
-						  const struct ib_mad *in_mad,
-						  struct ib_mad *out_mad);
+						  const struct ib_mad_hdr *in_mad,
+						  size_t in_mad_size,
+						  struct ib_mad_hdr *out_mad,
+						  size_t *out_mad_size,
+						  u16 *out_mad_pkey_index);
 	struct ib_xrcd *	   (*alloc_xrcd)(struct ib_device *device,
 						 struct ib_ucontext *ucontext,
 						 struct ib_udata *udata);