[for-next V2 1/5] RDMA/bnxt_re: Enable RoCE on virtual functions

[Devesh Sharma <devesh.sharma-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>]

From: Selvin Xavier <selvin.xavier-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>

RoCE can be used by virtual functions (VFs) as well. Adding
code changes to allow resource reservation, initialization
and avail the resources to the RDMA applications running on
those VFs.

Currently, fifty percent of the total available resources
are reserved for PF and remaining are equally divided among
active VFs.

Signed-off-by: Selvin Xavier <selvin.xavier-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
Signed-off-by: Devesh Sharma <devesh.sharma-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h  |  15 ++++
 drivers/infiniband/hw/bnxt_re/ib_verbs.c |  17 ++--
 drivers/infiniband/hw/bnxt_re/main.c     | 135 ++++++++++++++++++++++++-------
 drivers/infiniband/hw/bnxt_re/qplib_sp.c |  37 ++++++++-
 drivers/infiniband/hw/bnxt_re/qplib_sp.h |   5 +-
 drivers/infiniband/hw/bnxt_re/roce_hsi.h |  10 +++
 6 files changed, 182 insertions(+), 37 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index ecbac91..b604277 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -57,6 +57,19 @@
 #define BNXT_RE_MAX_MRW_COUNT		(64 * 1024)
 #define BNXT_RE_MAX_SRQC_COUNT		(64 * 1024)
 #define BNXT_RE_MAX_CQ_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_64K	(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_256K	(256 * 1024)
+
+/* Number of MRs to reserve for PF, leaving remainder for VFs */
+#define BNXT_RE_RESVD_MR_FOR_PF         (32 * 1024)
+#define BNXT_RE_MAX_GID_PER_VF          128
+
+/*
+ * Percentage of resources of each type reserved for PF.
+ * Remaining resources are divided equally among VFs.
+ * [0, 100]
+ */
+#define BNXT_RE_PCT_RSVD_FOR_PF         50
 
 #define BNXT_RE_UD_QP_HW_STALL		0x400000
 
@@ -145,6 +158,8 @@ struct bnxt_re_dev {
 	struct bnxt_re_ah		*sqp_ah;
 	struct bnxt_re_sqp_entries sqp_tbl[1024];
 	atomic_t nq_alloc_cnt;
+	u32 is_virtfn;
+	u32 num_vfs;
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2032db7..6dd2fe1 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -2295,10 +2295,14 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, struct ib_recv_wr *wr,
 /* Completion Queues */
 int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
 {
-	struct bnxt_re_cq *cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
-	struct bnxt_re_dev *rdev = cq->rdev;
 	int rc;
-	struct bnxt_qplib_nq *nq = cq->qplib_cq.nq;
+	struct bnxt_re_cq *cq;
+	struct bnxt_qplib_nq *nq;
+	struct bnxt_re_dev *rdev;
+
+	cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
+	rdev = cq->rdev;
+	nq = cq->qplib_cq.nq;
 
 	rc = bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -2308,12 +2312,11 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
 	if (!IS_ERR_OR_NULL(cq->umem))
 		ib_umem_release(cq->umem);
 
-	if (cq) {
-		kfree(cq->cql);
-		kfree(cq);
-	}
 	atomic_dec(&rdev->cq_count);
 	nq->budget--;
+	kfree(cq->cql);
+	kfree(cq);
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index aafc19a..d825df0 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -80,6 +80,79 @@
 static struct workqueue_struct *bnxt_re_wq;
 static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait);
 
+/* SR-IOV helper functions */
+
+static void bnxt_re_get_sriov_func_type(struct bnxt_re_dev *rdev)
+{
+	struct bnxt *bp;
+
+	bp = netdev_priv(rdev->en_dev->net);
+	if (BNXT_VF(bp))
+		rdev->is_virtfn = 1;
+}
+
+/* Set the maximum number of each resource that the driver actually wants
+ * to allocate. This may be up to the maximum number the firmware has
+ * reserved for the function. The driver may choose to allocate fewer
+ * resources than the firmware maximum.
+ */
+static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
+{
+	u32 vf_qps = 0, vf_srqs = 0, vf_cqs = 0, vf_mrws = 0, vf_gids = 0;
+	u32 i;
+	u32 vf_pct;
+	u32 num_vfs;
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+
+	rdev->qplib_ctx.qpc_count = min_t(u32, BNXT_RE_MAX_QPC_COUNT,
+					  dev_attr->max_qp);
+
+	rdev->qplib_ctx.mrw_count = BNXT_RE_MAX_MRW_COUNT_256K;
+	/* Use max_mr from fw since max_mrw does not get set */
+	rdev->qplib_ctx.mrw_count = min_t(u32, rdev->qplib_ctx.mrw_count,
+					  dev_attr->max_mr);
+	rdev->qplib_ctx.srqc_count = min_t(u32, BNXT_RE_MAX_SRQC_COUNT,
+					   dev_attr->max_srq);
+	rdev->qplib_ctx.cq_count = min_t(u32, BNXT_RE_MAX_CQ_COUNT,
+					 dev_attr->max_cq);
+
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
+		rdev->qplib_ctx.tqm_count[i] =
+		rdev->dev_attr.tqm_alloc_reqs[i];
+
+	if (rdev->num_vfs) {
+		/*
+		 * Reserve a set of resources for the PF. Divide the remaining
+		 * resources among the VFs
+		 */
+		vf_pct = 100 - BNXT_RE_PCT_RSVD_FOR_PF;
+		num_vfs = 100 * rdev->num_vfs;
+		vf_qps = (rdev->qplib_ctx.qpc_count * vf_pct) / num_vfs;
+		vf_srqs = (rdev->qplib_ctx.srqc_count * vf_pct) / num_vfs;
+		vf_cqs = (rdev->qplib_ctx.cq_count * vf_pct) / num_vfs;
+		/*
+		 * The driver allows many more MRs than other resources. If the
+		 * firmware does also, then reserve a fixed amount for the PF
+		 * and divide the rest among VFs. VFs may use many MRs for NFS
+		 * mounts, ISER, NVME applications, etc. If the firmware
+		 * severely restricts the number of MRs, then let PF have
+		 * half and divide the rest among VFs, as for the other
+		 * resource types.
+		 */
+		if (rdev->qplib_ctx.mrw_count < BNXT_RE_MAX_MRW_COUNT_64K)
+			vf_mrws = rdev->qplib_ctx.mrw_count * vf_pct / num_vfs;
+		else
+			vf_mrws = (rdev->qplib_ctx.mrw_count -
+				   BNXT_RE_RESVD_MR_FOR_PF) / rdev->num_vfs;
+		vf_gids = BNXT_RE_MAX_GID_PER_VF;
+	}
+	rdev->qplib_ctx.vf_res.max_mrw_per_vf = vf_mrws;
+	rdev->qplib_ctx.vf_res.max_gid_per_vf = vf_gids;
+	rdev->qplib_ctx.vf_res.max_qp_per_vf = vf_qps;
+	rdev->qplib_ctx.vf_res.max_srq_per_vf = vf_srqs;
+	rdev->qplib_ctx.vf_res.max_cq_per_vf = vf_cqs;
+}
+
 /* for handling bnxt_en callbacks later */
 static void bnxt_re_stop(void *p)
 {
@@ -91,6 +164,15 @@ static void bnxt_re_start(void *p)
 
 static void bnxt_re_sriov_config(void *p, int num_vfs)
 {
+	struct bnxt_re_dev *rdev = p;
+
+	if (!rdev)
+		return;
+
+	rdev->num_vfs = num_vfs;
+	bnxt_re_set_resource_limits(rdev);
+	bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw,
+				      &rdev->qplib_ctx);
 }
 
 static void bnxt_re_shutdown(void *p)
@@ -734,7 +816,8 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 
 	/* Configure and allocate resources for qplib */
 	rdev->qplib_res.rcfw = &rdev->rcfw;
-	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
+				     rdev->is_virtfn);
 	if (rc)
 		goto fail;
 
@@ -1035,19 +1118,6 @@ static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait)
 	}
 }
 
-static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
-{
-	u32 i;
-
-	rdev->qplib_ctx.qpc_count = BNXT_RE_MAX_QPC_COUNT;
-	rdev->qplib_ctx.mrw_count = BNXT_RE_MAX_MRW_COUNT;
-	rdev->qplib_ctx.srqc_count = BNXT_RE_MAX_SRQC_COUNT;
-	rdev->qplib_ctx.cq_count = BNXT_RE_MAX_CQ_COUNT;
-	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
-		rdev->qplib_ctx.tqm_count[i] =
-		rdev->dev_attr.tqm_alloc_reqs[i];
-}
-
 /* worker thread for polling periodic events. Now used for QoS programming*/
 static void bnxt_re_worker(struct work_struct *work)
 {
@@ -1070,6 +1140,9 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 	}
 	set_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
 
+	/* Check whether VF or PF */
+	bnxt_re_get_sriov_func_type(rdev);
+
 	rc = bnxt_re_request_msix(rdev);
 	if (rc) {
 		pr_err("Failed to get MSI-X vectors: %#x\n", rc);
@@ -1101,16 +1174,18 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 				(rdev->en_dev->pdev, &rdev->rcfw,
 				 rdev->msix_entries[BNXT_RE_AEQ_IDX].vector,
 				 rdev->msix_entries[BNXT_RE_AEQ_IDX].db_offset,
-				 0, &bnxt_re_aeq_handler);
+				 rdev->is_virtfn, &bnxt_re_aeq_handler);
 	if (rc) {
 		pr_err("Failed to enable RCFW channel: %#x\n", rc);
 		goto free_ring;
 	}
 
-	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
+				     rdev->is_virtfn);
 	if (rc)
 		goto disable_rcfw;
-	bnxt_re_set_resource_limits(rdev);
+	if (!rdev->is_virtfn)
+		bnxt_re_set_resource_limits(rdev);
 
 	rc = bnxt_qplib_alloc_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx, 0);
 	if (rc) {
@@ -1125,7 +1200,8 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 		goto free_ctx;
 	}
 
-	rc = bnxt_qplib_init_rcfw(&rdev->rcfw, &rdev->qplib_ctx, 0);
+	rc = bnxt_qplib_init_rcfw(&rdev->rcfw, &rdev->qplib_ctx,
+				  rdev->is_virtfn);
 	if (rc) {
 		pr_err("Failed to initialize RCFW: %#x\n", rc);
 		goto free_sctx;
@@ -1144,13 +1220,15 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 		goto fail;
 	}
 
-	rc = bnxt_re_setup_qos(rdev);
-	if (rc)
-		pr_info("RoCE priority not yet configured\n");
+	if (!rdev->is_virtfn) {
+		rc = bnxt_re_setup_qos(rdev);
+		if (rc)
+			pr_info("RoCE priority not yet configured\n");
 
-	INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker);
-	set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags);
-	schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
+		INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker);
+		set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags);
+		schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
+	}
 
 	/* Register ib dev */
 	rc = bnxt_re_register_ib(rdev);
@@ -1400,7 +1478,7 @@ static int __init bnxt_re_mod_init(void)
 
 static void __exit bnxt_re_mod_exit(void)
 {
-	struct bnxt_re_dev *rdev;
+	struct bnxt_re_dev *rdev, *next;
 	LIST_HEAD(to_be_deleted);
 
 	mutex_lock(&bnxt_re_dev_lock);
@@ -1408,8 +1486,11 @@ static void __exit bnxt_re_mod_exit(void)
 	if (!list_empty(&bnxt_re_dev_list))
 		list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
 	mutex_unlock(&bnxt_re_dev_lock);
-
-	list_for_each_entry(rdev, &to_be_deleted, list) {
+       /*
+	* Cleanup the devices in reverse order so that the VF device
+	* cleanup is done before PF cleanup
+	*/
+	list_for_each_entry_safe_reverse(rdev, next, &to_be_deleted, list) {
 		dev_info(rdev_to_dev(rdev), "Unregistering Device");
 		bnxt_re_dev_stop(rdev);
 		bnxt_re_ib_unreg(rdev, true);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 9543ce5..f5450b7 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -65,7 +65,7 @@ static bool bnxt_qplib_is_atomic_cap(struct bnxt_qplib_rcfw *rcfw)
 }
 
 int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
-			    struct bnxt_qplib_dev_attr *attr)
+			    struct bnxt_qplib_dev_attr *attr, bool vf)
 {
 	struct cmdq_query_func req;
 	struct creq_query_func_resp resp;
@@ -95,7 +95,8 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	/* Extract the context from the side buffer */
 	attr->max_qp = le32_to_cpu(sb->max_qp);
 	/* max_qp value reported by FW for PF doesn't include the QP1 for PF */
-	attr->max_qp += 1;
+	if (!vf)
+		attr->max_qp += 1;
 	attr->max_qp_rd_atom =
 		sb->max_qp_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ?
 		BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_rd_atom;
@@ -150,6 +151,38 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	return rc;
 }
 
+int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx)
+{
+	struct cmdq_set_func_resources req;
+	struct creq_set_func_resources_resp resp;
+	u16 cmd_flags = 0;
+	int rc = 0;
+
+	RCFW_CMD_PREP(req, SET_FUNC_RESOURCES, cmd_flags);
+
+	req.number_of_qp = cpu_to_le32(ctx->qpc_count);
+	req.number_of_mrw = cpu_to_le32(ctx->mrw_count);
+	req.number_of_srq =  cpu_to_le32(ctx->srqc_count);
+	req.number_of_cq = cpu_to_le32(ctx->cq_count);
+
+	req.max_qp_per_vf = cpu_to_le32(ctx->vf_res.max_qp_per_vf);
+	req.max_mrw_per_vf = cpu_to_le32(ctx->vf_res.max_mrw_per_vf);
+	req.max_srq_per_vf = cpu_to_le32(ctx->vf_res.max_srq_per_vf);
+	req.max_cq_per_vf = cpu_to_le32(ctx->vf_res.max_cq_per_vf);
+	req.max_gid_per_vf = cpu_to_le32(ctx->vf_res.max_gid_per_vf);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp,
+					  NULL, 0);
+	if (rc) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: Failed to set function resources");
+	}
+	return rc;
+}
+
 /* SGID */
 int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res,
 			struct bnxt_qplib_sgid_tbl *sgid_tbl, int index,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 1132258..51bb784 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -147,7 +147,10 @@ int bnxt_qplib_add_pkey(struct bnxt_qplib_res *res,
 			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 *pkey,
 			bool update);
 int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
-			    struct bnxt_qplib_dev_attr *attr);
+			    struct bnxt_qplib_dev_attr *attr, bool vf);
+int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx);
 int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah);
 int bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah);
 int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res,
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index c3cba606..f429fdb 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -1799,6 +1799,16 @@ struct cmdq_set_func_resources {
 	u8 resp_size;
 	u8 reserved8;
 	__le64 resp_addr;
+	__le32 number_of_qp;
+	__le32 number_of_mrw;
+	__le32 number_of_srq;
+	__le32 number_of_cq;
+	__le32 max_qp_per_vf;
+	__le32 max_mrw_per_vf;
+	__le32 max_srq_per_vf;
+	__le32 max_cq_per_vf;
+	__le32 max_gid_per_vf;
+	__le32 stat_ctx_id;
 };
 
 /* Read hardware resource context command (24 bytes) */
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html