octeontx2-pf: Add support for HTB offload

This patch registers callbacks to support HTB offload.

Below are features supported,

- supports traffic shaping on the given class by honoring rate and ceil
configuration.

- supports traffic scheduling,  which prioritizes different types of
traffic based on strict priority values.

- supports the creation of leaf to inner classes such that parent node
rate limits apply to all child nodes.

Signed-off-by: Naveen Mamindlapalli <[email protected]>
Signed-off-by: Hariprasad Kelam <[email protected]>
Signed-off-by: Sunil Kovvuri Goutham <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Naveen Mamindlapalli

drivers/net/ethernet/marvell/octeontx2/af/common.h

@@ -142,7 +142,7 @@ enum nix_scheduler {
 
 #define TXSCH_RR_QTM_MAX		((1 << 24) - 1)
 #define TXSCH_TL1_DFLT_RR_QTM		TXSCH_RR_QTM_MAX
-#define TXSCH_TL1_DFLT_RR_PRIO		(0x1ull)
+#define TXSCH_TL1_DFLT_RR_PRIO		(0x7ull)
 #define CN10K_MAX_DWRR_WEIGHT          16384 /* Weight is 14bit on CN10K */
 
 /* Min/Max packet sizes, excluding FCS */

drivers/net/ethernet/marvell/octeontx2/nic/Makefile

@@ -8,7 +8,7 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o qos_sq.o
+               otx2_devlink.o qos_sq.o qos.o
 rvu_nicvf-y := otx2_vf.o otx2_devlink.o
 
 rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c

@@ -89,6 +89,11 @@ int otx2_update_sq_stats(struct otx2_nic *pfvf, int qidx)
 	if (!pfvf->qset.sq)
 		return 0;
 
+	if (qidx >= pfvf->hw.non_qos_queues) {
+		if (!test_bit(qidx - pfvf->hw.non_qos_queues, pfvf->qos.qos_sq_bmap))
+			return 0;
+	}
+
 	otx2_nix_sq_op_stats(&sq->stats, pfvf, qidx);
 	return 1;
 }

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h

@@ -1099,8 +1099,18 @@ static inline void otx2_qos_init(struct otx2_nic *pfvf, int qos_txqs)
 	struct otx2_hw *hw = &pfvf->hw;
 
 	hw->tc_tx_queues = qos_txqs;
+	INIT_LIST_HEAD(&pfvf->qos.qos_tree);
+	mutex_init(&pfvf->qos.qos_lock);
+}
+
+static inline void otx2_shutdown_qos(struct otx2_nic *pfvf)
+{
+	mutex_destroy(&pfvf->qos.qos_lock);
 }
 
 u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
 		      struct net_device *sb_dev);
+int otx2_get_txq_by_classid(struct otx2_nic *pfvf, u16 classid);
+void otx2_qos_config_txschq(struct otx2_nic *pfvf);
+void otx2_clean_qos_queues(struct otx2_nic *pfvf);
 #endif /* OTX2_COMMON_H */

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -1387,6 +1387,9 @@ static void otx2_free_sq_res(struct otx2_nic *pf)
 	otx2_sq_free_sqbs(pf);
 	for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) {
 		sq = &qset->sq[qidx];
+		/* Skip freeing Qos queues if they are not initialized */
+		if (!sq->sqe)
+			continue;
 		qmem_free(pf->dev, sq->sqe);
 		qmem_free(pf->dev, sq->tso_hdrs);
 		kfree(sq->sg);
@@ -1566,6 +1569,8 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 		otx2_pfc_txschq_stop(pf);
 #endif
 
+	otx2_clean_qos_queues(pf);
+
 	mutex_lock(&mbox->lock);
 	/* Disable backpressure */
 	if (!(pf->pcifunc & RVU_PFVF_FUNC_MASK))
@@ -1710,7 +1715,7 @@ int otx2_open(struct net_device *netdev)
 	if (!qset->cq)
 		goto err_free_mem;
 
-	qset->sq = kcalloc(pf->hw.non_qos_queues,
+	qset->sq = kcalloc(otx2_get_total_tx_queues(pf),
 			   sizeof(struct otx2_snd_queue), GFP_KERNEL);
 	if (!qset->sq)
 		goto err_free_mem;
@@ -1833,6 +1838,9 @@ int otx2_open(struct net_device *netdev)
 	/* 'intf_down' may be checked on any cpu */
 	smp_wmb();
 
+	/* Enable QoS configuration before starting tx queues */
+	otx2_qos_config_txschq(pf);
+
 	/* we have already received link status notification */
 	if (pf->linfo.link_up && !(pf->pcifunc & RVU_PFVF_FUNC_MASK))
 		otx2_handle_link_event(pf);
@@ -1986,14 +1994,48 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 }
 
+static int otx2_qos_select_htb_queue(struct otx2_nic *pf, struct sk_buff *skb,
+				     u16 htb_maj_id)
+{
+	u16 classid;
+
+	if ((TC_H_MAJ(skb->priority) >> 16) == htb_maj_id)
+		classid = TC_H_MIN(skb->priority);
+	else
+		classid = READ_ONCE(pf->qos.defcls);
+
+	if (!classid)
+		return 0;
+
+	return otx2_get_txq_by_classid(pf, classid);
+}
+
 u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
 		      struct net_device *sb_dev)
 {
-#ifdef CONFIG_DCB
 	struct otx2_nic *pf = netdev_priv(netdev);
+	bool qos_enabled;
+#ifdef CONFIG_DCB
 	u8 vlan_prio;
 #endif
+	int txq;
+
+	qos_enabled = (netdev->real_num_tx_queues > pf->hw.tx_queues) ? true : false;
+	if (unlikely(qos_enabled)) {
+		/* This smp_load_acquire() pairs with smp_store_release() in
+		 * otx2_qos_root_add() called from htb offload root creation
+		 */
+		u16 htb_maj_id = smp_load_acquire(&pf->qos.maj_id);
 
+		if (unlikely(htb_maj_id)) {
+			txq = otx2_qos_select_htb_queue(pf, skb, htb_maj_id);
+			if (txq > 0)
+				return txq;
+			goto process_pfc;
+		}
+	}
+
+process_pfc:
 #ifdef CONFIG_DCB
 	if (!skb_vlan_tag_present(skb))
 		goto pick_tx;
@@ -2007,7 +2049,11 @@ u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb,
 
 pick_tx:
 #endif
-	return netdev_pick_tx(netdev, skb, NULL);
+	txq = netdev_pick_tx(netdev, skb, NULL);
+	if (unlikely(qos_enabled))
+		return txq % pf->hw.tx_queues;
+
+	return txq;
 }
 EXPORT_SYMBOL(otx2_select_queue);
 
@@ -3121,6 +3167,7 @@ static void otx2_remove(struct pci_dev *pdev)
 	otx2_ptp_destroy(pf);
 	otx2_mcam_flow_del(pf);
 	otx2_shutdown_tc(pf);
+	otx2_shutdown_qos(pf);
 	otx2_detach_resources(&pf->mbox);
 	if (pf->hw.lmt_info)
 		free_percpu(pf->hw.lmt_info);

drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c

@@ -19,6 +19,7 @@
 
 #include "cn10k.h"
 #include "otx2_common.h"
+#include "qos.h"
 
 #define CN10K_MAX_BURST_MANTISSA	0x7FFFULL
 #define CN10K_MAX_BURST_SIZE		8453888ULL
@@ -132,8 +133,8 @@ static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp,
 	}
 }
 
-static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic,
-				       u64 maxrate, u32 burst)
+u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic,
+				u64 maxrate, u32 burst)
 {
 	u32 burst_exp, burst_mantissa;
 	u32 exp, mantissa, div_exp;
@@ -1109,6 +1110,8 @@ int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return otx2_setup_tc_block(netdev, type_data);
+	case TC_SETUP_QDISC_HTB:
+		return otx2_setup_tc_htb(netdev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}

drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c

@@ -760,6 +760,7 @@ static void otx2vf_remove(struct pci_dev *pdev)
 	otx2_ptp_destroy(vf);
 	otx2_mcam_flow_del(vf);
 	otx2_shutdown_tc(vf);
+	otx2_shutdown_qos(vf);
 	otx2vf_disable_mbox_intr(vf);
 	otx2_detach_resources(&vf->mbox);
 	free_percpu(vf->hw.lmt_info);