qed: Add Multi-TC RoCE support

RoCE qps use a pair of physical queues (pq) received from the Queue Manager
(QM) - an offload queue (OFLD) and a low latency queue (LLT). The QM block
creates a pq for each TC, and allows RoCE qps to ask for a pq with a
specific TC. As a result, qps with different VLAN priorities can be mapped
to different TCs, and employ features such as PFC and ETS.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 121 insertions, 32 deletions

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index f916f139f80e..a60e1c8d470a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -338,6 +338,9 @@ struct qed_hw_info {
 	u8				offload_tc;
 	bool				offload_tc_set;
 
+	bool				multi_tc_roce_en;
+#define IS_QED_MULTI_TC_ROCE(p_hwfn) (((p_hwfn)->hw_info.multi_tc_roce_en))
+
 	u32				concrete_fid;
 	u16				opaque_fid;
 	u16				ovlan;
@@ -400,8 +403,8 @@ struct qed_qm_info {
 	u16				start_pq;
 	u8				start_vport;
 	u16				 pure_lb_pq;
-	u16				offload_pq;
-	u16				low_latency_pq;
+	u16				first_ofld_pq;
+	u16				first_llt_pq;
 	u16				pure_ack_pq;
 	u16				ooo_pq;
 	u16				first_vf_pq;
@@ -882,11 +885,14 @@ void qed_set_fw_mac_addr(__le16 *fw_msb,
 #define PQ_FLAGS_OFLD   (BIT(5))
 #define PQ_FLAGS_VFS    (BIT(6))
 #define PQ_FLAGS_LLT    (BIT(7))
+#define PQ_FLAGS_MTC    (BIT(8))
 
 /* physical queue index for cm context intialization */
 u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
 u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index a8e768342ad7..d1ae11ab7927 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -215,6 +215,8 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 		break;
 	case QED_PCI_ETH_ROCE:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+		if (IS_QED_MULTI_TC_ROCE(p_hwfn))
+			flags |= PQ_FLAGS_MTC;
 		break;
 	case QED_PCI_ETH_IWARP:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_ACK | PQ_FLAGS_OOO |
@@ -241,6 +243,16 @@ static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
 	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
 }
 
+static u8 qed_init_qm_get_num_mtc_tcs(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+	if (!(PQ_FLAGS_MTC & pq_flags))
+		return 1;
+
+	return qed_init_qm_get_num_tcs(p_hwfn);
+}
+
 #define NUM_DEFAULT_RLS 1
 
 static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
@@ -282,8 +294,11 @@ static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
 	       (!!(PQ_FLAGS_MCOS & pq_flags)) *
 	       qed_init_qm_get_num_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
-	       (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
-	       (!!(PQ_FLAGS_LLT & pq_flags)) +
+	       (!!(PQ_FLAGS_ACK & pq_flags)) +
+	       (!!(PQ_FLAGS_OFLD & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
+	       (!!(PQ_FLAGS_LLT & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
 }
 
@@ -474,9 +489,9 @@ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
 	case PQ_FLAGS_ACK:
 		return &qm_info->pure_ack_pq;
 	case PQ_FLAGS_OFLD:
-		return &qm_info->offload_pq;
+		return &qm_info->first_ofld_pq;
 	case PQ_FLAGS_LLT:
-		return &qm_info->low_latency_pq;
+		return &qm_info->first_llt_pq;
 	case PQ_FLAGS_VFS:
 		return &qm_info->first_vf_pq;
 	default:
@@ -525,6 +540,28 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
 	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
 }
 
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u16 first_ofld_pq, pq_offset;
+
+	first_ofld_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
+
+	return first_ofld_pq + pq_offset;
+}
+
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u16 first_llt_pq, pq_offset;
+
+	first_llt_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LLT);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
+
+	return first_llt_pq + pq_offset;
+}
+
 /* Functions for creating specific types of pqs */
 static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
 {
@@ -560,6 +597,20 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
 		       PQ_INIT_SHARE_VPORT);
 }
 
+static void qed_init_qm_mtc_pqs(struct qed_hwfn *p_hwfn)
+{
+	u8 num_tcs = qed_init_qm_get_num_mtc_tcs(p_hwfn);
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 tc;
+
+	/* override pq's TC if offload TC is set */
+	for (tc = 0; tc < num_tcs; tc++)
+		qed_init_qm_pq(p_hwfn, qm_info,
+			       qed_is_offload_tc_set(p_hwfn) ?
+			       p_hwfn->hw_info.offload_tc : tc,
+			       PQ_INIT_SHARE_VPORT);
+}
+
 static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 {
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
@@ -568,8 +619,7 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
-		       PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -580,8 +630,7 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
-		       PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -664,12 +713,19 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
 		return -EINVAL;
 	}
 
-	if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
-		DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
-		return -EINVAL;
+	if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+		return 0;
+
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
+		p_hwfn->hw_info.multi_tc_roce_en = 0;
+		DP_NOTICE(p_hwfn,
+			  "multi-tc roce was disabled to reduce requested amount of pqs\n");
+		if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+			return 0;
 	}
 
-	return 0;
+	DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+	return -EINVAL;
 }
 
 static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
@@ -683,11 +739,13 @@ static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
 	/* top level params */
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
-		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, llt_pq %d, pure_ack_pq %d\n",
 		   qm_info->start_pq,
 		   qm_info->start_vport,
 		   qm_info->pure_lb_pq,
-		   qm_info->offload_pq, qm_info->pure_ack_pq);
+		   qm_info->first_ofld_pq,
+		   qm_info->first_llt_pq,
+		   qm_info->pure_ack_pq);
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
 		   "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
@@ -2920,6 +2978,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		p_hwfn->hw_info.personality = protocol;
 	}
 
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn))
+		p_hwfn->hw_info.multi_tc_roce_en = 1;
+
 	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
 	p_hwfn->hw_info.num_active_tc = 1;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index ada4c1810864..7d7a64c55ff1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -44,8 +44,10 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/if_vlan.h>
 #include "qed.h"
 #include "qed_cxt.h"
+#include "qed_dcbx.h"
 #include "qed_hsi.h"
 #include "qed_hw.h"
 #include "qed_init_ops.h"
@@ -231,16 +233,33 @@ static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
+static u8 qed_roce_get_qp_tc(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+{
+	u8 pri, tc = 0;
+
+	if (qp->vlan_id) {
+		pri = (qp->vlan_id & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+		tc = qed_dcbx_get_priority_tc(p_hwfn, pri);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u tc: %u (vlan priority %s)\n",
+		   qp->icid, tc, qp->vlan_id ? "enabled" : "disabled");
+
+	return tc;
+}
+
 static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -324,12 +343,17 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -345,11 +369,6 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
-		   "rc = %d regular physical queue = 0x%x\n", rc,
-		   regular_latency_queue);
-
 	if (rc)
 		goto err;
 
@@ -375,12 +394,13 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -453,12 +473,17 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid =
 	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -471,9 +496,6 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc);
-
 	if (rc)
 		goto err;