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 <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Sathya Perla

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_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)			\