[PATCH for-next 1/4] RDMA/bnxt_re: Add support for optimized modify QP

[Selvin Xavier <selvin.xavier@broadcom.com>]

From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>

Modify QP improvements are for state transitions
from INIT -> RTR and RTR -> RTS.
In order to support the Modify QP Optimization feature,
the driver is expected to check for the feature support
in the CMDQ_QUERY_FUNC and register its support for this
feature with the FW in CMDQ_INITIALIZE_FIRMWARE.

Additionally, the driver is required to specify the new
fields and attribute masks for the transitions as follows:
1. INIT -> RTR:
   - New fields: srq_used, type.
   - enable srq_used when RC QP is configured to use SRQ.
   - set the type based on the QP type.
   - Mandatory masks:
     - RC: CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS,
           CMDQ_MODIFY_QP_MODIFY_MASK_PKEY
     - UD QP and QP1: CMDQ_MODIFY_QP_MODIFY_MASK_PKEY,
                      CMDQ_MODIFY_QP_MODIFY_MASK_QKEY
2. RTR -> RTS:
   - New fields: type
   - set the type based on the QP type.
   - Mandatory masks:
     - RC: CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS
     - UD QP and QP1: CMDQ_MODIFY_QP_MODIFY_MASK_QKEY

Reviewed-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Reviewed-by: Tushar Rane <tushar.rane@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/infiniband/hw/bnxt_re/qplib_fp.c   | 40 ++++++++++++++++++++++++++++++
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c |  6 ++++-
 drivers/infiniband/hw/bnxt_re/qplib_res.h  |  5 ++++
 drivers/infiniband/hw/bnxt_re/roce_hsi.h   |  3 +++
 4 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 42e98e5..775604f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -1277,6 +1277,40 @@ static void __filter_modify_flags(struct bnxt_qplib_qp *qp)
 	}
 }
 
+static void bnxt_set_mandatory_attributes(struct bnxt_qplib_qp *qp,
+					  struct cmdq_modify_qp *req)
+{
+	u32 mandatory_flags = 0;
+
+	if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_RC)
+		mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS;
+
+	if (qp->cur_qp_state == CMDQ_MODIFY_QP_NEW_STATE_INIT &&
+	    qp->state == CMDQ_MODIFY_QP_NEW_STATE_RTR) {
+		if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_RC && qp->srq)
+			req->flags = CMDQ_MODIFY_QP_FLAGS_SRQ_USED;
+		mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY;
+	}
+
+	if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_UD ||
+	    qp->type == CMDQ_MODIFY_QP_QP_TYPE_GSI)
+		mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_QKEY;
+
+	qp->modify_flags |= mandatory_flags;
+	req->qp_type = qp->type;
+}
+
+static bool is_optimized_state_transition(struct bnxt_qplib_qp *qp)
+{
+	if ((qp->cur_qp_state == CMDQ_MODIFY_QP_NEW_STATE_INIT &&
+	     qp->state == CMDQ_MODIFY_QP_NEW_STATE_RTR) ||
+	    (qp->cur_qp_state == CMDQ_MODIFY_QP_NEW_STATE_RTR &&
+	     qp->state == CMDQ_MODIFY_QP_NEW_STATE_RTS))
+		return true;
+
+	return false;
+}
+
 int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 {
 	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
@@ -1293,6 +1327,12 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 
 	/* Filter out the qp_attr_mask based on the state->new transition */
 	__filter_modify_flags(qp);
+	if (qp->modify_flags & CMDQ_MODIFY_QP_MODIFY_MASK_STATE) {
+		/* Set mandatory attributes for INIT -> RTR and RTR -> RTS transition */
+		if (_is_optimize_modify_qp_supported(res->dattr->dev_cap_flags2) &&
+		    is_optimized_state_transition(qp))
+			bnxt_set_mandatory_attributes(qp, &req);
+	}
 	bmask = qp->modify_flags;
 	req.modify_mask = cpu_to_le32(qp->modify_flags);
 	req.qp_cid = cpu_to_le32(qp->id);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 3ffaef0c..f66c5e4 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -832,6 +832,7 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 	struct creq_initialize_fw_resp resp = {};
 	struct cmdq_initialize_fw req = {};
 	struct bnxt_qplib_cmdqmsg msg = {};
+	u16 flags = 0;
 	u8 pgsz, lvl;
 	int rc;
 
@@ -906,7 +907,10 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 
 skip_ctx_setup:
 	if (BNXT_RE_HW_RETX(rcfw->res->dattr->dev_cap_flags))
-		req.flags |= cpu_to_le16(CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED);
+		flags |= cpu_to_le16(CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED);
+	if (_is_optimize_modify_qp_supported(rcfw->res->dattr->dev_cap_flags2))
+		flags |= CMDQ_INITIALIZE_FW_FLAGS_OPTIMIZE_MODIFY_QP_SUPPORTED;
+	req.flags |= cpu_to_le16(flags);
 	req.stat_ctx_id = cpu_to_le32(ctx->stats.fw_id);
 	bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0);
 	rc = bnxt_qplib_rcfw_send_message(rcfw, &msg);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index c2f7103..ef198a6 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -576,4 +576,9 @@ static inline bool _is_relaxed_ordering_supported(u16 dev_cap_ext_flags2)
 	return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_MEMORY_REGION_RO_SUPPORTED;
 }
 
+static inline bool _is_optimize_modify_qp_supported(u16 dev_cap_ext_flags2)
+{
+	return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_OPTIMIZE_MODIFY_QP_SUPPORTED;
+}
+
 #endif /* __BNXT_QPLIB_RES_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index 3ec8952..69d50d7 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -216,6 +216,8 @@ struct cmdq_initialize_fw {
 	__le16	flags;
 	#define CMDQ_INITIALIZE_FW_FLAGS_MRAV_RESERVATION_SPLIT          0x1UL
 	#define CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED     0x2UL
+	#define CMDQ_INITIALIZE_FW_FLAGS_DRV_VERSION                     0x4UL
+	#define CMDQ_INITIALIZE_FW_FLAGS_OPTIMIZE_MODIFY_QP_SUPPORTED    0x8UL
 	__le16	cookie;
 	u8	resp_size;
 	u8	reserved8;
@@ -559,6 +561,7 @@ struct cmdq_modify_qp {
 	#define CMDQ_MODIFY_QP_OPCODE_LAST     CMDQ_MODIFY_QP_OPCODE_MODIFY_QP
 	u8	cmd_size;
 	__le16	flags;
+	 #define CMDQ_MODIFY_QP_FLAGS_SRQ_USED       0x1UL
 	__le16	cookie;
 	u8	resp_size;
 	u8	qp_type;
-- 
2.5.5