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

 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_tc(struct net_device *dev, enum tc_setup_type type,
-			 void *type_data)
+static int bnxt_setup_flower(struct net_device *dev,
+			     struct tc_cls_flower_offload *cls_flower)
 {
-	struct tc_mqprio_qopt *mqprio = type_data;
+	struct bnxt *bp = netdev_priv(dev);
 
-	if (type != TC_SETUP_MQPRIO)
+	if (BNXT_VF(bp))
 		return -EOPNOTSUPP;
 
-	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	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;
+
+		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	return bnxt_setup_mq_tc(dev, mqprio->num_tc);
+		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.h

+/* 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)