[PATCH RFC 1/3] IB/iser: Post header-only PDUs inline

[Andrei-Alexandru Bleortu]

iser_post_send() posts every PDU by reference, and the QP asks for no
inline data. Before the HCA can send a SCSI command it therefore has
to DMA-read the 76 bytes of iSER and iSCSI headers from host memory,
and that read is on the latency path of every command.

Ask for ISER_HEADERS_LEN bytes of inline data when creating the QP,
and create the QP without inline data if the device refuses. Post a
PDU without a data segment with IB_SEND_INLINE when it fits in the
inline size the device granted. PDUs with a data segment are posted
by reference as before.

Providers copy inline data from sg_list[].addr as a kernel virtual
address. The inline path therefore points tx_sg[0] at the headers'
virtual address, and the by-reference path now sets it to the DMA
address on every post. The mapping is still synced and unmapped through
tx_desc->dma_addr.

Assisted-by: LLM
Signed-off-by: Andrei-Alexandru Bleortu <me@xxxxxxxxxxxx>
---
 drivers/infiniband/ulp/iser/iscsi_iser.h |  2 ++
 drivers/infiniband/ulp/iser/iser_verbs.c | 29 ++++++++++++++++++++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 1d7ac24c4c00..ebd994d425a3 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -362,6 +362,7 @@ struct iser_fr_pool {
  * @device:              reference to iser device
  * @fr_pool:             connection fast registration pool
  * @pi_support:          Indicate device T10-PI support
+ * @max_inline_data:     inline data size granted to the QP
  * @reg_cqe:             completion handler
  */
 struct ib_conn {
@@ -372,6 +373,7 @@ struct ib_conn {
 	struct iser_device          *device;
 	struct iser_fr_pool          fr_pool;
 	bool			     pi_support;
+	u32			     max_inline_data;
 	struct ib_cqe		     reg_cqe;
 };
 
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ab2a27d23478..6319d7fd17cf 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -230,7 +230,7 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn)
 	struct iser_conn *iser_conn = to_iser_conn(ib_conn);
 	struct iser_device	*device;
 	struct ib_device	*ib_dev;
-	struct ib_qp_init_attr	init_attr;
+	struct ib_qp_init_attr	init_attr, attr;
 	int			ret = -ENOMEM;
 	unsigned int max_send_wr, cq_size;
 
@@ -271,11 +271,23 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn)
 		init_attr.create_flags |= IB_QP_CREATE_INTEGRITY_EN;
 	iser_conn->max_cmds = ISER_GET_MAX_XMIT_CMDS(max_send_wr - 1);
 
-	ret = rdma_create_qp(ib_conn->cma_id, device->pd, &init_attr);
+	/*
+	 * Ask for enough inline data to post the iSER and iSCSI headers
+	 * inline (see iser_post_send()).  If the device cannot provide it,
+	 * create the QP without inline data.
+	 */
+	attr = init_attr;
+	attr.cap.max_inline_data = ISER_HEADERS_LEN;
+	ret = rdma_create_qp(ib_conn->cma_id, device->pd, &attr);
+	if (ret) {
+		attr = init_attr;
+		ret = rdma_create_qp(ib_conn->cma_id, device->pd, &attr);
+	}
 	if (ret)
 		goto out_err;
 
 	ib_conn->qp = ib_conn->cma_id->qp;
+	ib_conn->max_inline_data = attr.cap.max_inline_data;
 	iser_info("setting conn %p cma_id %p qp %p max_send_wr %d\n", ib_conn,
 		  ib_conn->cma_id, ib_conn->cma_id->qp, max_send_wr);
 	return ret;
@@ -870,6 +882,19 @@ int iser_post_send(struct ib_conn *ib_conn, struct iser_tx_desc *tx_desc)
 	wr->opcode = IB_WR_SEND;
 	wr->send_flags = IB_SEND_SIGNALED;
 
+	/*
+	 * Post a header-only PDU inline if it fits in the granted inline
+	 * size, so the HCA does not have to DMA-read it from host memory.
+	 * The CPU copies inline data from a kernel virtual address, so point
+	 * the SGE at the headers.
+	 */
+	tx_desc->tx_sg[0].addr = tx_desc->dma_addr;
+	if (tx_desc->num_sge == 1 &&
+	    tx_desc->tx_sg[0].length <= ib_conn->max_inline_data) {
+		tx_desc->tx_sg[0].addr = (uintptr_t)&tx_desc->iser_header;
+		wr->send_flags |= IB_SEND_INLINE;
+	}
+
 	if (tx_desc->inv_wr.next)
 		first_wr = &tx_desc->inv_wr;
 	else if (tx_desc->reg_wr.wr.next)
-- 
2.56.0