Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "Initial roundup of 4.5 merge window patches

   - Remove usage of ib_query_device and instead store attributes in
     ib_device struct

   - Move iopoll out of block and into lib, rename to irqpoll, and use
     in several places in the rdma stack as our new completion queue
     polling library mechanism.  Update the other block drivers that
     already used iopoll to use the new mechanism too.

   - Replace the per-entry GID table locks with a single GID table lock

   - IPoIB multicast cleanup

   - Cleanups to the IB MR facility

   - Add support for 64bit extended IB counters

   - Fix for netlink oops while parsing RDMA nl messages

   - RoCEv2 support for the core IB code

   - mlx4 RoCEv2 support

   - mlx5 RoCEv2 support

   - Cross Channel support for mlx5

   - Timestamp support for mlx5

   - Atomic support for mlx5

   - Raw QP support for mlx5

   - MAINTAINERS update for mlx4/mlx5

   - Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates

   - Add support for remote invalidate to the iSER driver (pushed
     through the RDMA tree due to dependencies, acknowledged by nab)

   - Update to NFSoRDMA (pushed through the RDMA tree due to
     dependencies, acknowledged by Bruce)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits)
  IB/mlx5: Unify CQ create flags check
  IB/mlx5: Expose Raw Packet QP to user space consumers
  {IB, net}/mlx5: Move the modify QP operation table to mlx5_ib
  IB/mlx5: Support setting Ethernet priority for Raw Packet QPs
  IB/mlx5: Add Raw Packet QP query functionality
  IB/mlx5: Add create and destroy functionality for Raw Packet QP
  IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types
  IB/mlx5: Allocate a Transport Domain for each ucontext
  net/mlx5_core: Warn on unsupported events of QP/RQ/SQ
  net/mlx5_core: Add RQ and SQ event handling
  net/mlx5_core: Export transport objects
  IB/mlx5: Expose CQE version to user-space
  IB/mlx5: Add CQE version 1 support to user QPs and SRQs
  IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext
  IB/sa: Fix netlink local service GFP crash
  IB/srpt: Remove redundant wc array
  IB/qib: Improve ipoib UD performance
  IB/mlx4: Advertise RoCE v2 support
  IB/mlx4: Create and use another QP1 for RoCEv2
  IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers
  ...

1 files changed, 68 insertions, 50 deletions

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 468c5e132563..f121e6129339 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -29,7 +29,6 @@
 #include <target/iscsi/iscsi_transport.h>
 #include <linux/semaphore.h>
 
-#include "isert_proto.h"
 #include "ib_isert.h"
 
 #define	ISERT_MAX_CONN		8
@@ -95,22 +94,6 @@ isert_qp_event_callback(struct ib_event *e, void *context)
 	}
 }
 
-static int
-isert_query_device(struct ib_device *ib_dev, struct ib_device_attr *devattr)
-{
-	int ret;
-
-	ret = ib_query_device(ib_dev, devattr);
-	if (ret) {
-		isert_err("ib_query_device() failed: %d\n", ret);
-		return ret;
-	}
-	isert_dbg("devattr->max_sge: %d\n", devattr->max_sge);
-	isert_dbg("devattr->max_sge_rd: %d\n", devattr->max_sge_rd);
-
-	return 0;
-}
-
 static struct isert_comp *
 isert_comp_get(struct isert_conn *isert_conn)
 {
@@ -157,9 +140,9 @@ isert_create_qp(struct isert_conn *isert_conn,
 	attr.recv_cq = comp->cq;
 	attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS;
 	attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1;
-	attr.cap.max_send_sge = device->dev_attr.max_sge;
-	isert_conn->max_sge = min(device->dev_attr.max_sge,
-				  device->dev_attr.max_sge_rd);
+	attr.cap.max_send_sge = device->ib_device->attrs.max_sge;
+	isert_conn->max_sge = min(device->ib_device->attrs.max_sge,
+				  device->ib_device->attrs.max_sge_rd);
 	attr.cap.max_recv_sge = 1;
 	attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	attr.qp_type = IB_QPT_RC;
@@ -287,8 +270,7 @@ isert_free_comps(struct isert_device *device)
 }
 
 static int
-isert_alloc_comps(struct isert_device *device,
-		  struct ib_device_attr *attr)
+isert_alloc_comps(struct isert_device *device)
 {
 	int i, max_cqe, ret = 0;
 
@@ -308,7 +290,7 @@ isert_alloc_comps(struct isert_device *device,
 		return -ENOMEM;
 	}
 
-	max_cqe = min(ISER_MAX_CQ_LEN, attr->max_cqe);
+	max_cqe = min(ISER_MAX_CQ_LEN, device->ib_device->attrs.max_cqe);
 
 	for (i = 0; i < device->comps_used; i++) {
 		struct ib_cq_init_attr cq_attr = {};
@@ -344,17 +326,15 @@ out_cq:
 static int
 isert_create_device_ib_res(struct isert_device *device)
 {
-	struct ib_device_attr *dev_attr;
+	struct ib_device *ib_dev = device->ib_device;
 	int ret;
 
-	dev_attr = &device->dev_attr;
-	ret = isert_query_device(device->ib_device, dev_attr);
-	if (ret)
-		goto out;
+	isert_dbg("devattr->max_sge: %d\n", ib_dev->attrs.max_sge);
+	isert_dbg("devattr->max_sge_rd: %d\n", ib_dev->attrs.max_sge_rd);
 
 	/* asign function handlers */
-	if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS &&
-	    dev_attr->device_cap_flags & IB_DEVICE_SIGNATURE_HANDOVER) {
+	if (ib_dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS &&
+	    ib_dev->attrs.device_cap_flags & IB_DEVICE_SIGNATURE_HANDOVER) {
 		device->use_fastreg = 1;
 		device->reg_rdma_mem = isert_reg_rdma;
 		device->unreg_rdma_mem = isert_unreg_rdma;
@@ -364,11 +344,11 @@ isert_create_device_ib_res(struct isert_device *device)
 		device->unreg_rdma_mem = isert_unmap_cmd;
 	}
 
-	ret = isert_alloc_comps(device, dev_attr);
+	ret = isert_alloc_comps(device);
 	if (ret)
 		goto out;
 
-	device->pd = ib_alloc_pd(device->ib_device);
+	device->pd = ib_alloc_pd(ib_dev);
 	if (IS_ERR(device->pd)) {
 		ret = PTR_ERR(device->pd);
 		isert_err("failed to allocate pd, device %p, ret=%d\n",
@@ -377,7 +357,7 @@ isert_create_device_ib_res(struct isert_device *device)
 	}
 
 	/* Check signature cap */
-	device->pi_capable = dev_attr->device_cap_flags &
+	device->pi_capable = ib_dev->attrs.device_cap_flags &
 			     IB_DEVICE_SIGNATURE_HANDOVER ? true : false;
 
 	return 0;
@@ -676,6 +656,32 @@ out_login_buf:
 	return ret;
 }
 
+static void
+isert_set_nego_params(struct isert_conn *isert_conn,
+		      struct rdma_conn_param *param)
+{
+	struct ib_device_attr *attr = &isert_conn->device->ib_device->attrs;
+
+	/* Set max inflight RDMA READ requests */
+	isert_conn->initiator_depth = min_t(u8, param->initiator_depth,
+				attr->max_qp_init_rd_atom);
+	isert_dbg("Using initiator_depth: %u\n", isert_conn->initiator_depth);
+
+	if (param->private_data) {
+		u8 flags = *(u8 *)param->private_data;
+
+		/*
+		 * use remote invalidation if the both initiator
+		 * and the HCA support it
+		 */
+		isert_conn->snd_w_inv = !(flags & ISER_SEND_W_INV_NOT_SUP) &&
+					  (attr->device_cap_flags &
+					   IB_DEVICE_MEM_MGT_EXTENSIONS);
+		if (isert_conn->snd_w_inv)
+			isert_info("Using remote invalidation\n");
+	}
+}
+
 static int
 isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
@@ -714,11 +720,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	}
 	isert_conn->device = device;
 
-	/* Set max inflight RDMA READ requests */
-	isert_conn->initiator_depth = min_t(u8,
-				event->param.conn.initiator_depth,
-				device->dev_attr.max_qp_init_rd_atom);
-	isert_dbg("Using initiator_depth: %u\n", isert_conn->initiator_depth);
+	isert_set_nego_params(isert_conn, &event->param.conn);
 
 	ret = isert_conn_setup_qp(isert_conn, cma_id);
 	if (ret)
@@ -1050,8 +1052,8 @@ isert_create_send_desc(struct isert_conn *isert_conn,
 	ib_dma_sync_single_for_cpu(ib_dev, tx_desc->dma_addr,
 				   ISER_HEADERS_LEN, DMA_TO_DEVICE);
 
-	memset(&tx_desc->iser_header, 0, sizeof(struct iser_hdr));
-	tx_desc->iser_header.flags = ISER_VER;
+	memset(&tx_desc->iser_header, 0, sizeof(struct iser_ctrl));
+	tx_desc->iser_header.flags = ISCSI_CTRL;
 
 	tx_desc->num_sge = 1;
 	tx_desc->isert_cmd = isert_cmd;
@@ -1097,7 +1099,14 @@ isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 
 	isert_cmd->rdma_wr.iser_ib_op = ISER_IB_SEND;
 	send_wr->wr_id = (uintptr_t)&isert_cmd->tx_desc;
-	send_wr->opcode = IB_WR_SEND;
+
+	if (isert_conn->snd_w_inv && isert_cmd->inv_rkey) {
+		send_wr->opcode  = IB_WR_SEND_WITH_INV;
+		send_wr->ex.invalidate_rkey = isert_cmd->inv_rkey;
+	} else {
+		send_wr->opcode = IB_WR_SEND;
+	}
+
 	send_wr->sg_list = &tx_desc->tx_sg[0];
 	send_wr->num_sge = isert_cmd->tx_desc.num_sge;
 	send_wr->send_flags = IB_SEND_SIGNALED;
@@ -1486,6 +1495,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 		isert_cmd->read_va = read_va;
 		isert_cmd->write_stag = write_stag;
 		isert_cmd->write_va = write_va;
+		isert_cmd->inv_rkey = read_stag ? read_stag : write_stag;
 
 		ret = isert_handle_scsi_cmd(isert_conn, isert_cmd, cmd,
 					rx_desc, (unsigned char *)hdr);
@@ -1543,21 +1553,21 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 static void
 isert_rx_do_work(struct iser_rx_desc *rx_desc, struct isert_conn *isert_conn)
 {
-	struct iser_hdr *iser_hdr = &rx_desc->iser_header;
+	struct iser_ctrl *iser_ctrl = &rx_desc->iser_header;
 	uint64_t read_va = 0, write_va = 0;
 	uint32_t read_stag = 0, write_stag = 0;
 
-	switch (iser_hdr->flags & 0xF0) {
+	switch (iser_ctrl->flags & 0xF0) {
 	case ISCSI_CTRL:
-		if (iser_hdr->flags & ISER_RSV) {
-			read_stag = be32_to_cpu(iser_hdr->read_stag);
-			read_va = be64_to_cpu(iser_hdr->read_va);
+		if (iser_ctrl->flags & ISER_RSV) {
+			read_stag = be32_to_cpu(iser_ctrl->read_stag);
+			read_va = be64_to_cpu(iser_ctrl->read_va);
 			isert_dbg("ISER_RSV: read_stag: 0x%x read_va: 0x%llx\n",
 				  read_stag, (unsigned long long)read_va);
 		}
-		if (iser_hdr->flags & ISER_WSV) {
-			write_stag = be32_to_cpu(iser_hdr->write_stag);
-			write_va = be64_to_cpu(iser_hdr->write_va);
+		if (iser_ctrl->flags & ISER_WSV) {
+			write_stag = be32_to_cpu(iser_ctrl->write_stag);
+			write_va = be64_to_cpu(iser_ctrl->write_va);
 			isert_dbg("ISER_WSV: write_stag: 0x%x write_va: 0x%llx\n",
 				  write_stag, (unsigned long long)write_va);
 		}
@@ -1568,7 +1578,7 @@ isert_rx_do_work(struct iser_rx_desc *rx_desc, struct isert_conn *isert_conn)
 		isert_err("iSER Hello message\n");
 		break;
 	default:
-		isert_warn("Unknown iSER hdr flags: 0x%02x\n", iser_hdr->flags);
+		isert_warn("Unknown iSER hdr flags: 0x%02x\n", iser_ctrl->flags);
 		break;
 	}
 
@@ -3095,12 +3105,20 @@ isert_rdma_accept(struct isert_conn *isert_conn)
 	struct rdma_cm_id *cm_id = isert_conn->cm_id;
 	struct rdma_conn_param cp;
 	int ret;
+	struct iser_cm_hdr rsp_hdr;
 
 	memset(&cp, 0, sizeof(struct rdma_conn_param));
 	cp.initiator_depth = isert_conn->initiator_depth;
 	cp.retry_count = 7;
 	cp.rnr_retry_count = 7;
 
+	memset(&rsp_hdr, 0, sizeof(rsp_hdr));
+	rsp_hdr.flags = ISERT_ZBVA_NOT_USED;
+	if (!isert_conn->snd_w_inv)
+		rsp_hdr.flags = rsp_hdr.flags | ISERT_SEND_W_INV_NOT_USED;
+	cp.private_data = (void *)&rsp_hdr;
+	cp.private_data_len = sizeof(rsp_hdr);
+
 	ret = rdma_accept(cm_id, &cp);
 	if (ret) {
 		isert_err("rdma_accept() failed with: %d\n", ret);