netdev - [PATCH rdma-next 3/3] RDMA/bnxt_re: Add set_func

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1730800752-29925-4-git-send-email-selvin.xavier@broadcom.com>
Date: Tue,  5 Nov 2024 01:59:12 -0800
From: Selvin Xavier <selvin.xavier@...adcom.com>
To: leon@...nel.org,
	jgg@...pe.ca
Cc: linux-rdma@...r.kernel.org,
	netdev@...r.kernel.org,
	davem@...emloft.net,
	edumazet@...gle.com,
	kuba@...nel.org,
	pabeni@...hat.com,
	michael.chan@...adcom.com,
	andrew.gospodarek@...adcom.com,
	kalesh-anakkur.purayil@...adcom.com,
	Selvin Xavier <selvin.xavier@...adcom.com>
Subject: [PATCH rdma-next 3/3] RDMA/bnxt_re: Add set_func_resources support for P5/P7 adapters

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

Enable set_func_resources for P5 and P7 adapters to handle
VF resource distribution. Remove setting max resources per VF
during PF initialization. This change is required for firmwares
which does not support RoCE VF resource management by NIC driver.
The code is same for all adapters now.

Reviewed-by: Stephen Shi <stephen.shi@...adcom.com>
Reviewed-by: Rukhsana Ansari <rukhsana.ansari@...adcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@...adcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@...adcom.com>
---
 drivers/infiniband/hw/bnxt_re/main.c       | 11 ++++++-----
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 11 +----------
 2 files changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index dd528dd..cb61941 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -291,11 +291,12 @@ static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev)
 	 * available at this point.
 	 */
 	rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev);
-	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
-		bnxt_re_set_resource_limits(rdev);
-		bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw,
-					      &rdev->qplib_ctx);
-	}
+	if (!rdev->num_vfs)
+		return;
+
+	bnxt_re_set_resource_limits(rdev);
+	bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw,
+				      &rdev->qplib_ctx);
 }
 
 static void bnxt_re_shutdown(struct auxiliary_device *adev)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 005079b..7072991 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -851,10 +851,8 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 	 * shall setup this area for VF. Skipping the
 	 * HW programming
 	 */
-	if (is_virtfn)
+	if (is_virtfn || bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx))
 		goto skip_ctx_setup;
-	if (bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx))
-		goto config_vf_res;
 
 	lvl = ctx->qpc_tbl.level;
 	pgsz = bnxt_qplib_base_pg_size(&ctx->qpc_tbl);
@@ -898,13 +896,6 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 	req.number_of_srq = cpu_to_le32(ctx->srqc_tbl.max_elements);
 	req.number_of_cq = cpu_to_le32(ctx->cq_tbl.max_elements);
 
-config_vf_res:
-	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);
-
 skip_ctx_setup:
 	if (BNXT_RE_HW_RETX(rcfw->res->dattr->dev_cap_flags))
 		flags |= CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED;
-- 
2.5.5