[ewg] [PATCH v2] IB/mlx4: Add send with invalidate support

[Eli Cohen]

>From 2fa86ee977039784f50de982e2f6bf197f00fbeb Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli at mellanox.co.il>
Date: Sun, 11 May 2008 15:02:04 +0300
Subject: [PATCH] IB/mlx4: Add send with invalidate support

Add send with invalidate support to mlx4.

Signed-off-by: Eli Cohen <eli at mellanox.co.il>
---
 drivers/infiniband/hw/mlx4/cq.c   |    8 ++++++++
 drivers/infiniband/hw/mlx4/main.c |    4 ++++
 drivers/infiniband/hw/mlx4/qp.c   |   22 +++++++++++++++++-----
 drivers/net/mlx4/mr.c             |    6 ++++--
 4 files changed, 33 insertions(+), 7 deletions(-)

Changes since last post:
set IB_DEVICE_SEND_W_INV only if FW supports it.

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 4521319..291e856 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -637,6 +637,7 @@ repoll:
 		case MLX4_OPCODE_SEND_IMM:
 			wc->wc_flags |= IB_WC_WITH_IMM;
 		case MLX4_OPCODE_SEND:
+		case MLX4_OPCODE_SEND_INVAL:
 			wc->opcode    = IB_WC_SEND;
 			break;
 		case MLX4_OPCODE_RDMA_READ:
@@ -676,6 +677,13 @@ repoll:
 			wc->wc_flags = IB_WC_WITH_IMM;
 			wc->imm_data = cqe->immed_rss_invalid;
 			break;
+		case MLX4_RECV_OPCODE_SEND_INVAL:
+			wc->opcode = IB_WC_RECV;
+			wc->wc_flags = IB_WC_WITH_INVALIDATE;
+			/*
+			 * TBD: maybe we should just call this ieth_val
+			 */
+			wc->imm_data = be32_to_cpu(cqe->immed_rss_invalid);
 		}
 
 		wc->slid	   = be16_to_cpu(cqe->rlid);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 4d61e32..b1e9505 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -56,6 +56,8 @@ static const char mlx4_ib_version[] =
 	DRV_NAME ": Mellanox ConnectX InfiniBand driver v"
 	DRV_VERSION " (" DRV_RELDATE ")\n";
 
+#define MLX4_FW_VER_LOCAL_SEND_INVL mlx4_fw_ver(2, 5, 0)
+
 static void init_query_mad(struct ib_smp *mad)
 {
 	mad->base_version  = 1;
@@ -103,6 +105,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;
 	if (dev->dev->caps.max_gso_sz)
 		props->device_cap_flags |= IB_DEVICE_UD_TSO;
+	if (dev->dev->caps.fw_ver >=  MLX4_FW_VER_LOCAL_SEND_INVL)
+		props->device_cap_flags |= IB_DEVICE_SEND_W_INV;
 
 	props->vendor_id	   = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
 		0xffffff;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8e02ecf..d0d5f77 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -78,6 +78,7 @@ static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_RDMA_READ]		= __constant_cpu_to_be32(MLX4_OPCODE_RDMA_READ),
 	[IB_WR_ATOMIC_CMP_AND_SWP]	= __constant_cpu_to_be32(MLX4_OPCODE_ATOMIC_CS),
 	[IB_WR_ATOMIC_FETCH_AND_ADD]	= __constant_cpu_to_be32(MLX4_OPCODE_ATOMIC_FA),
+	[IB_WR_SEND_WITH_INV]		= __constant_cpu_to_be32(MLX4_OPCODE_SEND_INVAL),
 };
 
 static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
@@ -1444,6 +1445,21 @@ static int build_lso_seg(struct mlx4_lso_seg *wqe, struct ib_send_wr *wr,
 	return 0;
 }
 
+static __be32 get_ieth(struct ib_send_wr *wr)
+{
+	switch (wr->opcode) {
+	case IB_WR_SEND_WITH_IMM:
+	case IB_WR_RDMA_WRITE_WITH_IMM:
+		return wr->ex.imm_data;
+
+	case IB_WR_SEND_WITH_INV:
+		return cpu_to_be32(wr->ex.invalidate_rkey);
+
+	default:
+		return 0;
+	}
+}
+
 int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		      struct ib_send_wr **bad_wr)
 {
@@ -1490,11 +1506,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				     MLX4_WQE_CTRL_TCP_UDP_CSUM) : 0) |
 			qp->sq_signal_bits;
 
-		if (wr->opcode == IB_WR_SEND_WITH_IMM ||
-		    wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM)
-			ctrl->imm = wr->ex.imm_data;
-		else
-			ctrl->imm = 0;
+		ctrl->imm = get_ieth(wr);
 
 		wqe += sizeof *ctrl;
 		size = sizeof *ctrl / 16;
diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c
index 03a9abc..e78f53d 100644
--- a/drivers/net/mlx4/mr.c
+++ b/drivers/net/mlx4/mr.c
@@ -47,7 +47,7 @@ struct mlx4_mpt_entry {
 	__be32 flags;
 	__be32 qpn;
 	__be32 key;
-	__be32 pd;
+	__be32 pd_flags;
 	__be64 start;
 	__be64 length;
 	__be32 lkey;
@@ -71,6 +71,8 @@ struct mlx4_mpt_entry {
 #define MLX4_MPT_STATUS_SW		0xF0
 #define MLX4_MPT_STATUS_HW		0x00
 
+#define MLX4_MPT_FLAG_EN_INV		0x3000000
+
 static u32 mlx4_buddy_alloc(struct mlx4_buddy *buddy, int order)
 {
 	int o;
@@ -320,7 +322,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 				       mr->access);
 
 	mpt_entry->key	       = cpu_to_be32(key_to_hw_index(mr->key));
-	mpt_entry->pd	       = cpu_to_be32(mr->pd);
+	mpt_entry->pd_flags    = cpu_to_be32(mr->pd | MLX4_MPT_FLAG_EN_INV);
 	mpt_entry->start       = cpu_to_be64(mr->iova);
 	mpt_entry->length      = cpu_to_be64(mr->size);
 	mpt_entry->entity_size = cpu_to_be32(mr->mtt.page_shift);
-- 
1.5.5.1