bnxt_en: bnxt: add TC flower filter offload support

This patch adds support for offloading TC based flow
rules and actions for the 'flower' classifier in the bnxt_en driver.
It includes logic to parse flow rules and actions received from the
TC subsystem, store them and issue the corresponding
hwrm_cfa_flow_alloc/free FW cmds. L2/IPv4/IPv6 flows and drop,
redir, vlan push/pop actions are supported in this patch.

In this patch the hwrm_cfa_flow_xxx routines are just stubs.
The code for these routines is introduced in the next patch for easier
review. Also, the code to query the TC/flower action stats will
be introduced in a subsequent patch.

Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/Kconfig

@@ -212,6 +212,15 @@ config BNXT_SRIOV
 	  Virtualization support in the NetXtreme-C/E products. This
 	  allows for virtual function acceleration in virtual environments.
 
+config BNXT_FLOWER_OFFLOAD
+	bool "TC Flower offload support for NetXtreme-C/E"
+	depends on BNXT
+	default y
+	---help---
+	  This configuration parameter enables TC Flower packet classifier
+	  offload for eswitch.  This option enables SR-IOV switchdev eswitch
+	  offload.
+
 config BNXT_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default n

drivers/net/ethernet/broadcom/bnxt/Makefile

@@ -1,3 +1,3 @@
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -50,6 +50,7 @@
 #include <linux/bitmap.h>
 #include <linux/cpu_rmap.h>
 #include <linux/cpumask.h>
+#include <net/pkt_cls.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -59,6 +60,7 @@
 #include "bnxt_dcb.h"
 #include "bnxt_xdp.h"
 #include "bnxt_vfr.h"
+#include "bnxt_tc.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
 
@@ -7305,17 +7307,33 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	return 0;
 }
 
+static int bnxt_setup_flower(struct net_device *dev,
+			     struct tc_cls_flower_offload *cls_flower)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (BNXT_VF(bp))
+		return -EOPNOTSUPP;
+
+	return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, cls_flower);
+}
+
 static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_setup_flower(dev, type_data);
+	case TC_SETUP_MQPRIO: {
 		struct tc_mqprio_qopt *mqprio = type_data;
 
-	if (type != TC_SETUP_MQPRIO)
-		return -EOPNOTSUPP;
-
 		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
 		return bnxt_setup_mq_tc(dev, mqprio->num_tc);
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -7711,6 +7729,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
+	bnxt_shutdown_tc(bp);
 	cancel_work_sync(&bp->sp_task);
 	bp->sp_event = 0;
 
@@ -8102,9 +8121,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else
 		device_set_wakeup_capable(&pdev->dev, false);
 
+	if (BNXT_PF(bp))
+		bnxt_init_tc(bp);
+
 	rc = register_netdev(dev);
 	if (rc)
-		goto init_err_clr_int;
+		goto init_err_cleanup_tc;
 
 	if (BNXT_PF(bp))
 		bnxt_dl_register(bp);
@@ -8117,7 +8139,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-init_err_clr_int:
+init_err_cleanup_tc:
+	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -19,6 +19,7 @@
 #define DRV_VER_UPD	0
 
 #include <linux/interrupt.h>
+#include <linux/rhashtable.h>
 #include <net/devlink.h>
 #include <net/dst_metadata.h>
 #include <net/switchdev.h>
@@ -943,6 +944,27 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
 
+struct bnxt_tc_info {
+	bool				enabled;
+
+	/* hash table to store TC offloaded flows */
+	struct rhashtable		flow_table;
+	struct rhashtable_params	flow_ht_params;
+
+	/* hash table to store L2 keys of TC flows */
+	struct rhashtable		l2_table;
+	struct rhashtable_params	l2_ht_params;
+
+	/* lock to atomically add/del an l2 node when a flow is
+	 * added or deleted.
+	 */
+	struct mutex			lock;
+
+	/* Stat counter mask (width) */
+	u64				bytes_mask;
+	u64				packets_mask;
+};
+
 struct bnxt_vf_rep_stats {
 	u64			packets;
 	u64			bytes;
@@ -1289,6 +1311,7 @@ struct bnxt {
 	enum devlink_eswitch_mode eswitch_mode;
 	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
 	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
+	struct bnxt_tc_info	tc_info;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\

drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c

@@ -0,0 +1,602 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/if_vlan.h>
+#include <net/flow_dissector.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_sriov.h"
+#include "bnxt_tc.h"
+#include "bnxt_vfr.h"
+
+#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
+
+#define BNXT_FID_INVALID			0xffff
+#define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
+
+/* Return the dst fid of the func for flow forwarding
+ * For PFs: src_fid is the fid of the PF
+ * For VF-reps: src_fid the fid of the VF
+ */
+static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
+{
+	struct bnxt *bp;
+
+	/* check if dev belongs to the same switch */
+	if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) {
+		netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
+			    dev->ifindex);
+		return BNXT_FID_INVALID;
+	}
+
+	/* Is dev a VF-rep? */
+	if (dev != pf_bp->dev)
+		return bnxt_vf_rep_get_fid(dev);
+
+	bp = netdev_priv(dev);
+	return bp->pf.fw_fid;
+}
+
+static int bnxt_tc_parse_redir(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	int ifindex = tcf_mirred_ifindex(tc_act);
+	struct net_device *dev;
+	u16 dst_fid;
+
+	dev = __dev_get_by_index(dev_net(bp->dev), ifindex);
+	if (!dev) {
+		netdev_info(bp->dev, "no dev for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	/* find the FID from dev */
+	dst_fid = bnxt_flow_get_dst_fid(bp, dev);
+	if (dst_fid == BNXT_FID_INVALID) {
+		netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	actions->flags |= BNXT_TC_ACTION_FLAG_FWD;
+	actions->dst_fid = dst_fid;
+	actions->dst_dev = dev;
+	return 0;
+}
+
+static void bnxt_tc_parse_vlan(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_POP) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
+	} else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN;
+		actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act));
+		actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act);
+	}
+}
+
+static int bnxt_tc_parse_actions(struct bnxt *bp,
+				 struct bnxt_tc_actions *actions,
+				 struct tcf_exts *tc_exts)
+{
+	const struct tc_action *tc_act;
+	LIST_HEAD(tc_actions);
+	int rc;
+
+	if (!tcf_exts_has_actions(tc_exts)) {
+		netdev_info(bp->dev, "no actions");
+		return -EINVAL;
+	}
+
+	tcf_exts_to_list(tc_exts, &tc_actions);
+	list_for_each_entry(tc_act, &tc_actions, list) {
+		/* Drop action */
+		if (is_tcf_gact_shot(tc_act)) {
+			actions->flags |= BNXT_TC_ACTION_FLAG_DROP;
+			return 0; /* don't bother with other actions */
+		}
+
+		/* Redirect action */
+		if (is_tcf_mirred_egress_redirect(tc_act)) {
+			rc = bnxt_tc_parse_redir(bp, actions, tc_act);
+			if (rc)
+				return rc;
+			continue;
+		}
+
+		/* Push/pop VLAN */
+		if (is_tcf_vlan(tc_act)) {
+			bnxt_tc_parse_vlan(bp, actions, tc_act);
+			continue;
+		}
+	}
+
+	return 0;
+}
+
+#define GET_KEY(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->key)
+#define GET_MASK(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->mask)
+
+static int bnxt_tc_parse_flow(struct bnxt *bp,
+			      struct tc_cls_flower_offload *tc_flow_cmd,
+			      struct bnxt_tc_flow *flow)
+{
+	struct flow_dissector *dissector = tc_flow_cmd->dissector;
+	u16 addr_type = 0;
+
+	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
+	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
+	    (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
+		netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x",
+			    dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+		struct flow_dissector_key_basic *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+
+		flow->l2_key.ether_type = key->n_proto;
+		flow->l2_mask.ether_type = mask->n_proto;
+
+		if (key->n_proto == htons(ETH_P_IP) ||
+		    key->n_proto == htons(ETH_P_IPV6)) {
+			flow->l4_key.ip_proto = key->ip_proto;
+			flow->l4_mask.ip_proto = mask->ip_proto;
+		}
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+		struct flow_dissector_key_eth_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS;
+		ether_addr_copy(flow->l2_key.dmac, key->dst);
+		ether_addr_copy(flow->l2_mask.dmac, mask->dst);
+		ether_addr_copy(flow->l2_key.smac, key->src);
+		ether_addr_copy(flow->l2_mask.smac, mask->src);
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+		struct flow_dissector_key_vlan *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+
+		flow->l2_key.inner_vlan_tci =
+		   cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority));
+		flow->l2_mask.inner_vlan_tci =
+		   cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority)));
+		flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q);
+		flow->l2_mask.inner_vlan_tpid = htons(0xffff);
+		flow->l2_key.num_vlans = 1;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+		struct flow_dissector_key_ipv4_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS;
+		flow->l3_key.ipv4.daddr.s_addr = key->dst;
+		flow->l3_mask.ipv4.daddr.s_addr = mask->dst;
+		flow->l3_key.ipv4.saddr.s_addr = key->src;
+		flow->l3_mask.ipv4.saddr.s_addr = mask->src;
+	} else if (dissector_uses_key(dissector,
+				      FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_dissector_key_ipv6_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+		struct flow_dissector_key_ipv6_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS;
+		flow->l3_key.ipv6.daddr = key->dst;
+		flow->l3_mask.ipv6.daddr = mask->dst;
+		flow->l3_key.ipv6.saddr = key->src;
+		flow->l3_mask.ipv6.saddr = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+		struct flow_dissector_key_ports *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS;
+		flow->l4_key.ports.dport = key->dst;
+		flow->l4_mask.ports.dport = mask->dst;
+		flow->l4_key.ports.sport = key->src;
+		flow->l4_mask.ports.sport = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_dissector_key_icmp *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+		struct flow_dissector_key_icmp *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP;
+		flow->l4_key.icmp.type = key->type;
+		flow->l4_key.icmp.code = key->code;
+		flow->l4_mask.icmp.type = mask->type;
+		flow->l4_mask.icmp.code = mask->code;
+	}
+
+	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
+}
+
+static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
+{
+	return 0;
+}
+
+static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    __le16 ref_flow_handle, __le16 *flow_handle)
+{
+	return 0;
+}
+
+static int bnxt_tc_put_l2_node(struct bnxt *bp,
+			       struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_l2_node *l2_node = flow_node->l2_node;
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	/* remove flow_node from the L2 shared flow list */
+	list_del(&flow_node->l2_list_node);
+	if (--l2_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(&tc_info->l2_table, &l2_node->node,
+					     tc_info->l2_ht_params);
+		if (rc)
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_remove_fast: %d",
+				   __func__, rc);
+		kfree_rcu(l2_node, rcu);
+	}
+	return 0;
+}
+
+static struct bnxt_tc_l2_node *
+bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table,
+		    struct rhashtable_params ht_params,
+		    struct bnxt_tc_l2_key *l2_key)
+{
+	struct bnxt_tc_l2_node *l2_node;
+	int rc;
+
+	l2_node = rhashtable_lookup_fast(l2_table, l2_key, ht_params);
+	if (!l2_node) {
+		l2_node = kzalloc(sizeof(*l2_node), GFP_KERNEL);
+		if (!l2_node) {
+			rc = -ENOMEM;
+			return NULL;
+		}
+
+		l2_node->key = *l2_key;
+		rc = rhashtable_insert_fast(l2_table, &l2_node->node,
+					    ht_params);
+		if (rc) {
+			kfree(l2_node);
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_insert_fast: %d",
+				   __func__, rc);
+			return NULL;
+		}
+		INIT_LIST_HEAD(&l2_node->common_l2_flows);
+	}
+	return l2_node;
+}
+
+/* Get the ref_flow_handle for a flow by checking if there are any other
+ * flows that share the same L2 key as this flow.
+ */
+static int
+bnxt_tc_get_ref_flow_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+			    struct bnxt_tc_flow_node *flow_node,
+			    __le16 *ref_flow_handle)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_node *ref_flow_node;
+	struct bnxt_tc_l2_node *l2_node;
+
+	l2_node = bnxt_tc_get_l2_node(bp, &tc_info->l2_table,
+				      tc_info->l2_ht_params,
+				      &flow->l2_key);
+	if (!l2_node)
+		return -1;
+
+	/* If any other flow is using this l2_node, use it's flow_handle
+	 * as the ref_flow_handle
+	 */
+	if (l2_node->refcount > 0) {
+		ref_flow_node = list_first_entry(&l2_node->common_l2_flows,
+						 struct bnxt_tc_flow_node,
+						 l2_list_node);
+		*ref_flow_handle = ref_flow_node->flow_handle;
+	} else {
+		*ref_flow_handle = cpu_to_le16(0xffff);
+	}
+
+	/* Insert the l2_node into the flow_node so that subsequent flows
+	 * with a matching l2 key can use the flow_handle of this flow
+	 * as their ref_flow_handle
+	 */
+	flow_node->l2_node = l2_node;
+	list_add(&flow_node->l2_list_node, &l2_node->common_l2_flows);
+	l2_node->refcount++;
+	return 0;
+}
+
+/* After the flow parsing is done, this routine is used for checking
+ * if there are any aspects of the flow that prevent it from being
+ * offloaded.
+ */
+static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
+{
+	/* If L4 ports are specified then ip_proto must be TCP or UDP */
+	if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) &&
+	    (flow->l4_key.ip_proto != IPPROTO_TCP &&
+	     flow->l4_key.ip_proto != IPPROTO_UDP)) {
+		netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports",
+			    flow->l4_key.ip_proto);
+		return false;
+	}
+
+	return true;
+}
+
+static int __bnxt_tc_del_flow(struct bnxt *bp,
+			      struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	/* send HWRM cmd to free the flow-id */
+	bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle);
+
+	mutex_lock(&tc_info->lock);
+
+	/* release reference to l2 node */
+	bnxt_tc_put_l2_node(bp, flow_node);
+
+	mutex_unlock(&tc_info->lock);
+
+	rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d",
+			   __func__, rc);
+
+	kfree_rcu(flow_node, rcu);
+	return 0;
+}
+
+/* Add a new flow or replace an existing flow.
+ * Notes on locking:
+ * There are essentially two critical sections here.
+ * 1. while adding a new flow
+ *    a) lookup l2-key
+ *    b) issue HWRM cmd and get flow_handle
+ *    c) link l2-key with flow
+ * 2. while deleting a flow
+ *    a) unlinking l2-key from flow
+ * A lock is needed to protect these two critical sections.
+ *
+ * The hash-tables are already protected by the rhashtable API.
+ */
+static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_flow_node *new_node, *old_node;
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow *flow;
+	__le16 ref_flow_handle;
+	int rc;
+
+	/* allocate memory for the new flow and it's node */
+	new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
+	if (!new_node) {
+		rc = -ENOMEM;
+		goto done;
+	}
+	new_node->cookie = tc_flow_cmd->cookie;
+	flow = &new_node->flow;
+
+	rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow);
+	if (rc)
+		goto free_node;
+	flow->src_fid = src_fid;
+
+	if (!bnxt_tc_can_offload(bp, flow)) {
+		rc = -ENOSPC;
+		goto free_node;
+	}
+
+	/* If a flow exists with the same cookie, delete it */
+	old_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					  &tc_flow_cmd->cookie,
+					  tc_info->flow_ht_params);
+	if (old_node)
+		__bnxt_tc_del_flow(bp, old_node);
+
+	/* Check if the L2 part of the flow has been offloaded already.
+	 * If so, bump up it's refcnt and get it's reference handle.
+	 */
+	mutex_lock(&tc_info->lock);
+	rc = bnxt_tc_get_ref_flow_handle(bp, flow, new_node, &ref_flow_handle);
+	if (rc)
+		goto unlock;
+
+	/* send HWRM cmd to alloc the flow */
+	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
+				      &new_node->flow_handle);
+	if (rc)
+		goto put_l2;
+
+	/* add new flow to flow-table */
+	rc = rhashtable_insert_fast(&tc_info->flow_table, &new_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		goto hwrm_flow_free;
+
+	mutex_unlock(&tc_info->lock);
+	return 0;
+
+hwrm_flow_free:
+	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+put_l2:
+	bnxt_tc_put_l2_node(bp, new_node);
+unlock:
+	mutex_unlock(&tc_info->lock);
+free_node:
+	kfree(new_node);
+done:
+	netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d",
+		   __func__, tc_flow_cmd->cookie, rc);
+	return rc;
+}
+
+static int bnxt_tc_del_flow(struct bnxt *bp,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_node *flow_node;
+
+	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					   &tc_flow_cmd->cookie,
+					   tc_info->flow_ht_params);
+	if (!flow_node) {
+		netdev_info(bp->dev, "ERROR: no flow_node for cookie %lx",
+			    tc_flow_cmd->cookie);
+		return -EINVAL;
+	}
+
+	return __bnxt_tc_del_flow(bp, flow_node);
+}
+
+static int bnxt_tc_get_flow_stats(struct bnxt *bp,
+				  struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	return 0;
+}
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower)
+{
+	int rc = 0;
+
+	switch (cls_flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_DESTROY:
+		rc = bnxt_tc_del_flow(bp, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_STATS:
+		rc = bnxt_tc_get_flow_stats(bp, cls_flower);
+		break;
+	}
+	return rc;
+}
+
+static const struct rhashtable_params bnxt_tc_flow_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_flow_node, node),
+	.key_offset = offsetof(struct bnxt_tc_flow_node, cookie),
+	.key_len = sizeof(((struct bnxt_tc_flow_node *)0)->cookie),
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_l2_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_l2_node, node),
+	.key_offset = offsetof(struct bnxt_tc_l2_node, key),
+	.key_len = BNXT_TC_L2_KEY_LEN,
+	.automatic_shrinking = true
+};
+
+/* convert counter width in bits to a mask */
+#define mask(width)		((u64)~0 >> (64 - (width)))
+
+int bnxt_init_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800) {
+		netdev_warn(bp->dev,
+			    "Firmware does not support TC flower offload.\n");
+		return -ENOTSUPP;
+	}
+	mutex_init(&tc_info->lock);
+
+	/* Counter widths are programmed by FW */
+	tc_info->bytes_mask = mask(36);
+	tc_info->packets_mask = mask(28);
+
+	tc_info->flow_ht_params = bnxt_tc_flow_ht_params;
+	rc = rhashtable_init(&tc_info->flow_table, &tc_info->flow_ht_params);
+	if (rc)
+		return rc;
+
+	tc_info->l2_ht_params = bnxt_tc_l2_ht_params;
+	rc = rhashtable_init(&tc_info->l2_table, &tc_info->l2_ht_params);
+	if (rc)
+		goto destroy_flow_table;
+
+	tc_info->enabled = true;
+	bp->dev->hw_features |= NETIF_F_HW_TC;
+	bp->dev->features |= NETIF_F_HW_TC;
+	return 0;
+
+destroy_flow_table:
+	rhashtable_destroy(&tc_info->flow_table);
+	return rc;
+}
+
+void bnxt_shutdown_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+
+	if (!tc_info->enabled)
+		return;
+
+	rhashtable_destroy(&tc_info->flow_table);
+	rhashtable_destroy(&tc_info->l2_table);
+}
+
+#else
+#endif

drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h

@@ -0,0 +1,158 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_TC_H
+#define BNXT_TC_H
+
+#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
+
+/* Structs used for storing the filter/actions of the TC cmd.
+ */
+struct bnxt_tc_l2_key {
+	u8		dmac[ETH_ALEN];
+	u8		smac[ETH_ALEN];
+	__be16		inner_vlan_tpid;
+	__be16		inner_vlan_tci;
+	__be16		ether_type;
+	u8		num_vlans;
+};
+
+struct bnxt_tc_l3_key {
+	union {
+		struct {
+			struct in_addr daddr;
+			struct in_addr saddr;
+		} ipv4;
+		struct {
+			struct in6_addr daddr;
+			struct in6_addr saddr;
+		} ipv6;
+	};
+};
+
+struct bnxt_tc_l4_key {
+	u8  ip_proto;
+	union {
+		struct {
+			__be16 sport;
+			__be16 dport;
+		} ports;
+		struct {
+			u8 type;
+			u8 code;
+		} icmp;
+	};
+};
+
+struct bnxt_tc_actions {
+	u32				flags;
+#define BNXT_TC_ACTION_FLAG_FWD			BIT(0)
+#define BNXT_TC_ACTION_FLAG_FWD_VXLAN		BIT(1)
+#define BNXT_TC_ACTION_FLAG_PUSH_VLAN		BIT(3)
+#define BNXT_TC_ACTION_FLAG_POP_VLAN		BIT(4)
+#define BNXT_TC_ACTION_FLAG_DROP		BIT(5)
+
+	u16				dst_fid;
+	struct net_device		*dst_dev;
+	__be16				push_vlan_tpid;
+	__be16				push_vlan_tci;
+};
+
+struct bnxt_tc_flow_stats {
+	u64		packets;
+	u64		bytes;
+};
+
+struct bnxt_tc_flow {
+	u32				flags;
+#define BNXT_TC_FLOW_FLAGS_ETH_ADDRS		BIT(1)
+#define BNXT_TC_FLOW_FLAGS_IPV4_ADDRS		BIT(2)
+#define BNXT_TC_FLOW_FLAGS_IPV6_ADDRS		BIT(3)
+#define BNXT_TC_FLOW_FLAGS_PORTS		BIT(4)
+#define BNXT_TC_FLOW_FLAGS_ICMP			BIT(5)
+
+	/* flow applicable to pkts ingressing on this fid */
+	u16				src_fid;
+	struct bnxt_tc_l2_key		l2_key;
+	struct bnxt_tc_l2_key		l2_mask;
+	struct bnxt_tc_l3_key		l3_key;
+	struct bnxt_tc_l3_key		l3_mask;
+	struct bnxt_tc_l4_key		l4_key;
+	struct bnxt_tc_l4_key		l4_mask;
+
+	struct bnxt_tc_actions		actions;
+
+	/* updated stats accounting for hw-counter wrap-around */
+	struct bnxt_tc_flow_stats	stats;
+	/* previous snap-shot of stats */
+	struct bnxt_tc_flow_stats	prev_stats;
+	unsigned long			lastused; /* jiffies */
+};
+
+/* L2 hash table
+ * This data-struct is used for L2-flow table.
+ * The L2 part of a flow is stored in a hash table.
+ * A flow that shares the same L2 key/mask with an
+ * already existing flow must refer to it's flow handle.
+ */
+struct bnxt_tc_l2_node {
+	/* hash key: first 16b of key */
+#define BNXT_TC_L2_KEY_LEN			16
+	struct bnxt_tc_l2_key	key;
+	struct rhash_head	node;
+
+	/* a linked list of flows that share the same l2 key */
+	struct list_head	common_l2_flows;
+
+	/* number of flows sharing the l2 key */
+	u16			refcount;
+
+	struct rcu_head		rcu;
+};
+
+struct bnxt_tc_flow_node {
+	/* hash key: provided by TC */
+	unsigned long			cookie;
+	struct rhash_head		node;
+
+	struct bnxt_tc_flow		flow;
+
+	__le16				flow_handle;
+
+	/* L2 node in l2 hashtable that shares flow's l2 key */
+	struct bnxt_tc_l2_node		*l2_node;
+	/* for the shared_flows list maintained in l2_node */
+	struct list_head		l2_list_node;
+
+	struct rcu_head			rcu;
+};
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower);
+int bnxt_init_tc(struct bnxt *bp);
+void bnxt_shutdown_tc(struct bnxt *bp);
+
+#else /* CONFIG_BNXT_FLOWER_OFFLOAD */
+
+static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+				       struct tc_cls_flower_offload *cls_flower)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bnxt_init_tc(struct bnxt *bp)
+{
+	return 0;
+}
+
+static inline void bnxt_shutdown_tc(struct bnxt *bp)
+{
+}
+#endif /* CONFIG_BNXT_FLOWER_OFFLOAD */
+#endif /* BNXT_TC_H */

drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c

@@ -11,10 +11,12 @@
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/jhash.h>
+#include <net/pkt_cls.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_vfr.h"
+#include "bnxt_tc.h"
 
 #ifdef CONFIG_BNXT_SRIOV
 
@@ -113,6 +115,21 @@ bnxt_vf_rep_get_stats64(struct net_device *dev,
 	stats->tx_bytes = vf_rep->tx_stats.bytes;
 }
 
+static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+				void *type_data)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+	int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_tc_setup_flower(bp, vf_fid, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code)
 {
 	u16 vf_idx;
@@ -182,6 +199,7 @@ static const struct net_device_ops bnxt_vf_rep_netdev_ops = {
 	.ndo_stop		= bnxt_vf_rep_close,
 	.ndo_start_xmit		= bnxt_vf_rep_xmit,
 	.ndo_get_stats64	= bnxt_vf_rep_get_stats64,
+	.ndo_setup_tc		= bnxt_vf_rep_setup_tc,
 	.ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name
 };
 

drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h

@@ -45,6 +45,14 @@ void bnxt_vf_reps_open(struct bnxt *bp);
 void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb);
 struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code);
 
+static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+
+	return bp->pf.vf[vf_rep->vf_idx].fw_fid;
+}
+
 #else
 
 static inline int bnxt_dl_register(struct bnxt *bp)