Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster

Pull networking updates from Jakub Kicinski:
 "Not much excitement - a handful of large patchsets (devmem among them)
  did not make it in time.

  Core & protocols:

   - Use local_lock in addition to local_bh_disable() to protect per-CPU
     resources in networking, a step closer for local_bh_disable() not
     to act as a big lock on PREEMPT_RT

   - Use flex array for netdevice priv area, ensure its cache alignment

   - Add a sysctl knob to allow user to specify a default rto_min at
     socket init time. Bit of a big hammer but multiple companies were
     independently carrying such patch downstream so clearly it's useful

   - Support scheduling transmission of packets based on CLOCK_TAI

   - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned
     off using cpusets

   - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address

   - Allow configuration of multipath hash seed, to both allow
     synchronizing hashing of two routers, and preventing partial
     accidental sync

   - Improve TCP compliance with RFC 9293 for simultaneous connect()

   - Support sending NAT keepalives in IPsec ESP in UDP states.
     Userspace IKE daemon had to do this before, but the kernel can
     better keep track of it

   - Support sending supervision HSR frames with MAC addresses stored in
     ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled

   - Introduce IPPROTO_SMC for selecting SMC when socket is created

   - Allow UDP GSO transmit from devices with no checksum offload

   - openvswitch: add packet sampling via psample, separating the
     sampled traffic from "upcall" packets sent to user space for
     forwarding

   - nf_tables: shrink memory consumption for transaction objects

  Things we sprinkled into general kernel code:

   - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for
     QCA6390)           [ Already merged separately - Linus ]

   - Add IRQ information in sysfs for auxiliary bus

   - Introduce guard definition for local_lock

   - Add aligned flavor of __cacheline_group_{begin, end}() markings for
     grouping fields in structures

  BPF:

   - Notify user space (via epoll) when a struct_ops object is getting
     detached/unregistered

   - Add new kfuncs for a generic, open-coded bits iterator

   - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and
     bpf_list_head

   - Support resilient split BTF which cuts down on duplication and
     makes BTF as compact as possible WRT BTF from modules

   - Add support for dumping kfunc prototypes from BTF which enables
     both detecting as well as dumping compilable prototypes for kfuncs

   - riscv64 BPF JIT improvements in particular to add 12-argument
     support for BPF trampolines and to utilize bpf_prog_pack for the
     latter

   - Add the capability to offload the netfilter flowtable in XDP layer
     through kfuncs

  Driver API:

   - Allow users to configure IRQ tresholds between which automatic IRQ
     moderation can choose

   - Expand Power Sourcing (PoE) status with power, class and failure
     reason. Support setting power limits

   - Track additional RSS contexts in the core, make sure configuration
     changes don't break them

   - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated
     ESP data paths

   - Support updating firmware on SFP modules

  Tests and tooling:

   - mptcp: use net/lib.sh to manage netns

   - TCP-AO and TCP-MD5: replace debug prints used by tests with
     tracepoints

   - openvswitch: make test self-contained (don't depend on OvS CLI
     tools)

  Drivers:

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - increase the max total outstanding PTP TX packets to 4
         - add timestamping statistics support
         - implement netdev_queue_mgmt_ops
         - support new RSS context API
      - Intel (100G, ice, idpf):
         - implement FEC statistics and dumping signal quality indicators
         - support E825C products (with 56Gbps PHYs)
      - nVidia/Mellanox:
         - support HW-GRO
         - mlx4/mlx5: support per-queue statistics via netlink
         - obey the max number of EQs setting in sub-functions
      - AMD/Solarflare:
         - support new RSS context API
      - AMD/Pensando:
         - ionic: rework fix for doorbell miss to lower overhead and
           skip it on new HW
      - Wangxun:
         - txgbe: support Flow Director perfect filters

   - Ethernet NICs consumer, embedded and virtual:
      - Add driver for Tehuti Networks TN40xx chips
      - Add driver for Meta's internal NIC chips
      - Add driver for Ethernet MAC on Airoha EN7581 SoCs
      - Add driver for Renesas Ethernet-TSN devices
      - Google cloud vNIC:
         - flow steering support
      - Microsoft vNIC:
         - support page sizes other than 4KB on ARM64
      - vmware vNIC:
         - support latency measurement (update to version 9)
      - VirtIO net:
         - support for Byte Queue Limits
         - support configuring thresholds for automatic IRQ moderation
         - support for AF_XDP Rx zero-copy
      - Synopsys (stmmac):
         - support for STM32MP13 SoC
         - let platforms select the right PCS implementation
      - TI:
         - icssg-prueth: add multicast filtering support
         - icssg-prueth: enable PTP timestamping and PPS
      - Renesas:
         - ravb: improve Rx performance 30-400% by using page pool,
           theaded NAPI and timer-based IRQ coalescing
         - ravb: add MII support for R-Car V4M
      - Cadence (macb):
         - macb: add ARP support to Wake-On-LAN
      - Cortina:
         - use phylib for RX and TX pause configuration

   - Ethernet switches:
      - nVidia/Mellanox:
         - support configuration of multipath hash seed
         - report more accurate max MTU
         - use page_pool to improve Rx performance
      - MediaTek:
         - mt7530: add support for bridge port isolation
      - Qualcomm:
         - qca8k: add support for bridge port isolation
      - Microchip:
         - lan9371/2: add 100BaseTX PHY support
      - NXP:
         - vsc73xx: implement VLAN operations

   - Ethernet PHYs:
      - aquantia: enable support for aqr115c
      - aquantia: add support for PHY LEDs
      - realtek: add support for rtl8224 2.5Gbps PHY
      - xpcs: add memory-mapped device support
      - add BroadR-Reach link mode and support in Broadcom's PHY driver

   - CAN:
      - add document for ISO 15765-2 protocol support
      - mcp251xfd: workaround for erratum DS80000789E, use timestamps to
        catch when device returns incorrect FIFO status

   - WiFi:
      - mac80211/cfg80211:
         - parse Transmit Power Envelope (TPE) data in mac80211 instead
           of in drivers
         - improvements for 6 GHz regulatory flexibility
         - multi-link improvements
         - support multiple radios per wiphy
         - remove DEAUTH_NEED_MGD_TX_PREP flag
      - Intel (iwlwifi):
         - bump FW API to 91 for BZ/SC devices
         - report 64-bit radiotap timestamp
         - enable P2P low latency by default
         - handle Transmit Power Envelope (TPE) advertised by AP
         - remove support for older FW for new devices
         - fast resume (keeping the device configured)
         - mvm: re-enable Multi-Link Operation (MLO)
         - aggregation (A-MSDU) optimizations
      - MediaTek (mt76):
         - mt7925 Multi-Link Operation (MLO) support
      - Qualcomm (ath10k):
         - LED support for various chipsets
      - Qualcomm (ath12k):
         - remove unsupported Tx monitor handling
         - support channel 2 in 6 GHz band
         - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band
         - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID
           Advertisements (EMA)
         - support dynamic VLAN
         - add panic handler for resetting the firmware state
         - DebugFS support for datapath statistics
         - WCN7850: support for Wake on WLAN
      - Microchip (wilc1000):
         - read MAC address during probe to make it visible to user space
         - suspend/resume improvements
      - TI (wl18xx):
         - support newer firmware versions
      - RealTek (rtw89):
         - preparation for RTL8852BE-VT support
         - Wake on WLAN support for WiFi 6 chips
         - 36-bit PCI DMA support
      - RealTek (rtlwifi):
         - RTL8192DU support
      - Broadcom (brcmfmac):
         - Management Frame Protection support (to enable WPA3)

   - Bluetooth:
      - qualcomm: use the power sequencer for QCA6390
      - btusb: mediatek: add ISO data transmission functions
      - hci_bcm4377: add BCM4388 support
      - btintel: add support for BlazarU core
      - btintel: add support for Whale Peak2
      - btnxpuart: add support for AW693 A1 chipset
      - btnxpuart: add support for IW615 chipset
      - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"

* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits)
  eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering"
  tcp: Replace strncpy() with strscpy()
  wifi: ath12k: fix build vs old compiler
  tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child().
  eth: fbnic: Write the TCAM tables used for RSS control and Rx to host
  eth: fbnic: Add L2 address programming
  eth: fbnic: Add basic Rx handling
  eth: fbnic: Add basic Tx handling
  eth: fbnic: Add link detection
  eth: fbnic: Add initial messaging to notify FW of our presence
  eth: fbnic: Implement Rx queue alloc/start/stop/free
  eth: fbnic: Implement Tx queue alloc/start/stop/free
  eth: fbnic: Allocate a netdevice and napi vectors with queues
  eth: fbnic: Add FW communication mechanism
  eth: fbnic: Add message parsing for FW messages
  eth: fbnic: Add register init to set PCIe/Ethernet device config
  eth: fbnic: Allocate core device specific structures and devlink interface
  eth: fbnic: Add scaffolding for Meta's NIC driver
  PCI: Add Meta Platforms vendor ID
  net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK
  ...

6 files changed, 180 insertions, 12 deletions

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index cc3bec42ed8e..abe5921dde02 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -43,6 +43,11 @@ static const struct wx_stats wx_gstrings_stats[] = {
 	WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed),
 };
 
+static const struct wx_stats wx_gstrings_fdir_stats[] = {
+	WX_STAT("fdir_match", stats.fdirmatch),
+	WX_STAT("fdir_miss", stats.fdirmiss),
+};
+
 /* drivers allocates num_tx_queues and num_rx_queues symmetrically so
  * we set the num_rx_queues to evaluate to num_tx_queues. This is
  * used because we do not have a good way to get the max number of
@@ -55,13 +60,17 @@ static const struct wx_stats wx_gstrings_stats[] = {
 		(WX_NUM_TX_QUEUES + WX_NUM_RX_QUEUES) * \
 		(sizeof(struct wx_queue_stats) / sizeof(u64)))
 #define WX_GLOBAL_STATS_LEN  ARRAY_SIZE(wx_gstrings_stats)
+#define WX_FDIR_STATS_LEN  ARRAY_SIZE(wx_gstrings_fdir_stats)
 #define WX_STATS_LEN (WX_GLOBAL_STATS_LEN + WX_QUEUE_STATS_LEN)
 
 int wx_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct wx *wx = netdev_priv(netdev);
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return WX_STATS_LEN;
+		return (wx->mac.type == wx_mac_sp) ?
+			WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -70,6 +79,7 @@ EXPORT_SYMBOL(wx_get_sset_count);
 
 void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
+	struct wx *wx = netdev_priv(netdev);
 	u8 *p = data;
 	int i;
 
@@ -77,6 +87,10 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	case ETH_SS_STATS:
 		for (i = 0; i < WX_GLOBAL_STATS_LEN; i++)
 			ethtool_puts(&p, wx_gstrings_stats[i].stat_string);
+		if (wx->mac.type == wx_mac_sp) {
+			for (i = 0; i < WX_FDIR_STATS_LEN; i++)
+				ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string);
+		}
 		for (i = 0; i < netdev->num_tx_queues; i++) {
 			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
 			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
@@ -96,7 +110,7 @@ void wx_get_ethtool_stats(struct net_device *netdev,
 	struct wx *wx = netdev_priv(netdev);
 	struct wx_ring *ring;
 	unsigned int start;
-	int i, j;
+	int i, j, k;
 	char *p;
 
 	wx_update_stats(wx);
@@ -107,6 +121,13 @@ void wx_get_ethtool_stats(struct net_device *netdev,
 			   sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
 
+	if (wx->mac.type == wx_mac_sp) {
+		for (k = 0; k < WX_FDIR_STATS_LEN; k++) {
+			p = (char *)wx + wx_gstrings_fdir_stats[k].stat_offset;
+			data[i++] = *(u64 *)p;
+		}
+	}
+
 	for (j = 0; j < netdev->num_tx_queues; j++) {
 		ring = wx->tx_ring[j];
 		if (!ring) {
@@ -172,17 +193,21 @@ EXPORT_SYMBOL(wx_get_pause_stats);
 
 void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info)
 {
+	unsigned int stats_len = WX_STATS_LEN;
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_sp)
+		stats_len += WX_FDIR_STATS_LEN;
+
 	strscpy(info->driver, wx->driver_name, sizeof(info->driver));
 	strscpy(info->fw_version, wx->eeprom_id, sizeof(info->fw_version));
 	strscpy(info->bus_info, pci_name(wx->pdev), sizeof(info->bus_info));
 	if (wx->num_tx_queues <= WX_NUM_TX_QUEUES) {
-		info->n_stats = WX_STATS_LEN -
+		info->n_stats = stats_len -
 				   (WX_NUM_TX_QUEUES - wx->num_tx_queues) *
 				   (sizeof(struct wx_queue_stats) / sizeof(u64)) * 2;
 	} else {
-		info->n_stats = WX_STATS_LEN;
+		info->n_stats = stats_len;
 	}
 }
 EXPORT_SYMBOL(wx_get_drvinfo);
@@ -383,6 +408,9 @@ void wx_get_channels(struct net_device *dev,
 
 	/* record RSS queues */
 	ch->combined_count = wx->ring_feature[RING_F_RSS].indices;
+
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))
+		ch->combined_count = wx->ring_feature[RING_F_FDIR].indices;
 }
 EXPORT_SYMBOL(wx_get_channels);
 
@@ -400,6 +428,9 @@ int wx_set_channels(struct net_device *dev,
 	if (count > wx_max_channels(wx))
 		return -EINVAL;
 
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))
+		wx->ring_feature[RING_F_FDIR].limit = count;
+
 	wx->ring_feature[RING_F_RSS].limit = count;
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index d1b682ce9c6d..1bf9c38e4125 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1147,8 +1147,15 @@ static void wx_enable_rx(struct wx *wx)
 static void wx_set_rxpba(struct wx *wx)
 {
 	u32 rxpktsize, txpktsize, txpbthresh;
+	u32 pbsize = wx->mac.rx_pb_size;
 
-	rxpktsize = wx->mac.rx_pb_size << WX_RDB_PB_SZ_SHIFT;
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
+		if (test_bit(WX_FLAG_FDIR_HASH, wx->flags) ||
+		    test_bit(WX_FLAG_FDIR_PERFECT, wx->flags))
+			pbsize -= 64; /* Default 64KB */
+	}
+
+	rxpktsize = pbsize << WX_RDB_PB_SZ_SHIFT;
 	wr32(wx, WX_RDB_PB_SZ(0), rxpktsize);
 
 	/* Only support an equally distributed Tx packet buffer strategy. */
@@ -1261,7 +1268,7 @@ static void wx_configure_port(struct wx *wx)
  *  Stops the receive data path and waits for the HW to internally empty
  *  the Rx security block
  **/
-static int wx_disable_sec_rx_path(struct wx *wx)
+int wx_disable_sec_rx_path(struct wx *wx)
 {
 	u32 secrx;
 
@@ -1271,6 +1278,7 @@ static int wx_disable_sec_rx_path(struct wx *wx)
 	return read_poll_timeout(rd32, secrx, secrx & WX_RSC_ST_RSEC_RDY,
 				 1000, 40000, false, wx, WX_RSC_ST);
 }
+EXPORT_SYMBOL(wx_disable_sec_rx_path);
 
 /**
  *  wx_enable_sec_rx_path - Enables the receive data path
@@ -1278,11 +1286,12 @@ static int wx_disable_sec_rx_path(struct wx *wx)
  *
  *  Enables the receive data path.
  **/
-static void wx_enable_sec_rx_path(struct wx *wx)
+void wx_enable_sec_rx_path(struct wx *wx)
 {
 	wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_RX_DIS, 0);
 	WX_WRITE_FLUSH(wx);
 }
+EXPORT_SYMBOL(wx_enable_sec_rx_path);
 
 static void wx_vlan_strip_control(struct wx *wx, bool enable)
 {
@@ -1499,6 +1508,13 @@ static void wx_configure_tx_ring(struct wx *wx,
 		txdctl |= ring->count / 128 << WX_PX_TR_CFG_TR_SIZE_SHIFT;
 	txdctl |= 0x20 << WX_PX_TR_CFG_WTHRESH_SHIFT;
 
+	ring->atr_count = 0;
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) &&
+	    test_bit(WX_FLAG_FDIR_HASH, wx->flags))
+		ring->atr_sample_rate = wx->atr_sample_rate;
+	else
+		ring->atr_sample_rate = 0;
+
 	/* reinitialize tx_buffer_info */
 	memset(ring->tx_buffer_info, 0,
 	       sizeof(struct wx_tx_buffer) * ring->count);
@@ -1732,7 +1748,9 @@ void wx_configure(struct wx *wx)
 
 	wx_set_rx_mode(wx->netdev);
 	wx_restore_vlan(wx);
-	wx_enable_sec_rx_path(wx);
+
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))
+		wx->configure_fdir(wx);
 
 	wx_configure_tx(wx);
 	wx_configure_rx(wx);
@@ -1959,6 +1977,7 @@ int wx_sw_init(struct wx *wx)
 	}
 
 	bitmap_zero(wx->state, WX_STATE_NBITS);
+	bitmap_zero(wx->flags, WX_PF_FLAGS_NBITS);
 	wx->misc_irq_domain = false;
 
 	return 0;
@@ -2334,6 +2353,11 @@ void wx_update_stats(struct wx *wx)
 	hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT);
 	hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT);
 
+	if (wx->mac.type == wx_mac_sp) {
+		hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH);
+		hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS);
+	}
+
 	for (i = 0; i < wx->mac.max_rx_queues; i++)
 		hwstats->qmprc += rd32(wx, WX_PX_MPRC(i));
 }
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 9e219fa717a2..11fb33349482 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -28,6 +28,8 @@ void wx_mac_set_default_filter(struct wx *wx, u8 *addr);
 void wx_flush_sw_mac_table(struct wx *wx);
 int wx_set_mac(struct net_device *netdev, void *p);
 void wx_disable_rx(struct wx *wx);
+int wx_disable_sec_rx_path(struct wx *wx);
+void wx_enable_sec_rx_path(struct wx *wx);
 void wx_set_rx_mode(struct net_device *netdev);
 int wx_change_mtu(struct net_device *netdev, int new_mtu);
 void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 81bedc8ee8d4..1eecba984f3b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -148,10 +148,11 @@ static struct wx_dec_ptype wx_ptype_lookup[256] = {
 	[0xFD] = WX_PTT(IP, IPV6, IGMV, IPV6, SCTP, PAY4),
 };
 
-static struct wx_dec_ptype wx_decode_ptype(const u8 ptype)
+struct wx_dec_ptype wx_decode_ptype(const u8 ptype)
 {
 	return wx_ptype_lookup[ptype];
 }
+EXPORT_SYMBOL(wx_decode_ptype);
 
 /* wx_test_staterr - tests bits in Rx descriptor status and error fields */
 static __le32 wx_test_staterr(union wx_rx_desc *rx_desc,
@@ -1453,6 +1454,7 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 				      struct wx_ring *tx_ring)
 {
+	struct wx *wx = netdev_priv(tx_ring->netdev);
 	u16 count = TXD_USE_COUNT(skb_headlen(skb));
 	struct wx_tx_buffer *first;
 	u8 hdr_len = 0, ptype;
@@ -1498,6 +1500,10 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 		goto out_drop;
 	else if (!tso)
 		wx_tx_csum(tx_ring, first, ptype);
+
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate)
+		wx->atr(tx_ring, first, ptype);
+
 	wx_tx_map(tx_ring, first, hdr_len);
 
 	return NETDEV_TX_OK;
@@ -1574,8 +1580,27 @@ static void wx_set_rss_queues(struct wx *wx)
 	f = &wx->ring_feature[RING_F_RSS];
 	f->indices = f->limit;
 
-	wx->num_rx_queues = f->limit;
-	wx->num_tx_queues = f->limit;
+	if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)))
+		goto out;
+
+	clear_bit(WX_FLAG_FDIR_HASH, wx->flags);
+
+	/* Use Flow Director in addition to RSS to ensure the best
+	 * distribution of flows across cores, even when an FDIR flow
+	 * isn't matched.
+	 */
+	if (f->indices > 1) {
+		f = &wx->ring_feature[RING_F_FDIR];
+
+		f->indices = f->limit;
+
+		if (!(test_bit(WX_FLAG_FDIR_PERFECT, wx->flags)))
+			set_bit(WX_FLAG_FDIR_HASH, wx->flags);
+	}
+
+out:
+	wx->num_rx_queues = f->indices;
+	wx->num_tx_queues = f->indices;
 }
 
 static void wx_set_num_queues(struct wx *wx)
@@ -2684,6 +2709,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	netdev_features_t changed = netdev->features ^ features;
 	struct wx *wx = netdev_priv(netdev);
+	bool need_reset = false;
 
 	if (features & NETIF_F_RXHASH) {
 		wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN,
@@ -2701,6 +2727,36 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 	else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER))
 		wx_set_rx_mode(netdev);
 
+	if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)))
+		return 0;
+
+	/* Check if Flow Director n-tuple support was enabled or disabled.  If
+	 * the state changed, we need to reset.
+	 */
+	switch (features & NETIF_F_NTUPLE) {
+	case NETIF_F_NTUPLE:
+		/* turn off ATR, enable perfect filters and reset */
+		if (!(test_and_set_bit(WX_FLAG_FDIR_PERFECT, wx->flags)))
+			need_reset = true;
+
+		clear_bit(WX_FLAG_FDIR_HASH, wx->flags);
+		break;
+	default:
+		/* turn off perfect filters, enable ATR and reset */
+		if (test_and_clear_bit(WX_FLAG_FDIR_PERFECT, wx->flags))
+			need_reset = true;
+
+		/* We cannot enable ATR if RSS is disabled */
+		if (wx->ring_feature[RING_F_RSS].limit <= 1)
+			break;
+
+		set_bit(WX_FLAG_FDIR_HASH, wx->flags);
+		break;
+	}
+
+	if (need_reset)
+		wx->do_reset(netdev);
+
 	return 0;
 }
 EXPORT_SYMBOL(wx_set_features);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index c41b29ea812f..fdeb0c315b75 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -7,6 +7,7 @@
 #ifndef _WX_LIB_H_
 #define _WX_LIB_H_
 
+struct wx_dec_ptype wx_decode_ptype(const u8 ptype);
 void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count);
 u16 wx_desc_unused(struct wx_ring *ring);
 netdev_tx_t wx_xmit_frame(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 0df7f5712b6f..1d57b047817b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -157,6 +157,8 @@
 #define WX_RDB_RA_CTL_RSS_IPV6_TCP   BIT(21)
 #define WX_RDB_RA_CTL_RSS_IPV4_UDP   BIT(22)
 #define WX_RDB_RA_CTL_RSS_IPV6_UDP   BIT(23)
+#define WX_RDB_FDIR_MATCH            0x19558
+#define WX_RDB_FDIR_MISS             0x1955C
 
 /******************************* PSR Registers *******************************/
 /* psr control */
@@ -503,6 +505,34 @@ enum WX_MSCA_CMD_value {
 #define WX_PTYPE_TYP_TCP             0x04
 #define WX_PTYPE_TYP_SCTP            0x05
 
+/* Packet type non-ip values */
+enum wx_l2_ptypes {
+	WX_PTYPE_L2_ABORTED = (WX_PTYPE_PKT_MAC),
+	WX_PTYPE_L2_MAC = (WX_PTYPE_PKT_MAC | WX_PTYPE_TYP_MAC),
+
+	WX_PTYPE_L2_IPV4_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IPFRAG),
+	WX_PTYPE_L2_IPV4 = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IP),
+	WX_PTYPE_L2_IPV4_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_UDP),
+	WX_PTYPE_L2_IPV4_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_TCP),
+	WX_PTYPE_L2_IPV4_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_SCTP),
+	WX_PTYPE_L2_IPV6_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 |
+				 WX_PTYPE_TYP_IPFRAG),
+	WX_PTYPE_L2_IPV6 = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 |
+			    WX_PTYPE_TYP_IP),
+	WX_PTYPE_L2_IPV6_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 |
+				WX_PTYPE_TYP_UDP),
+	WX_PTYPE_L2_IPV6_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 |
+				WX_PTYPE_TYP_TCP),
+	WX_PTYPE_L2_IPV6_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 |
+				 WX_PTYPE_TYP_SCTP),
+
+	WX_PTYPE_L2_TUN4_MAC = (WX_PTYPE_TUN_IPV4 | WX_PTYPE_PKT_IGM),
+	WX_PTYPE_L2_TUN6_MAC = (WX_PTYPE_TUN_IPV6 | WX_PTYPE_PKT_IGM),
+};
+
+#define WX_PTYPE_PKT(_pt)            ((_pt) & 0x30)
+#define WX_PTYPE_TYPL4(_pt)          ((_pt) & 0x07)
+
 #define WX_RXD_PKTTYPE(_rxd) \
 	((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF)
 #define WX_RXD_IPV6EX(_rxd) \
@@ -552,6 +582,9 @@ enum wx_tx_flags {
 	WX_TX_FLAGS_OUTER_IPV4	= 0x100,
 	WX_TX_FLAGS_LINKSEC	= 0x200,
 	WX_TX_FLAGS_IPSEC	= 0x400,
+
+	/* software defined flags */
+	WX_TX_FLAGS_SW_VLAN	= 0x40,
 };
 
 /* VLAN info */
@@ -900,7 +933,13 @@ struct wx_ring {
 					 */
 	u16 next_to_use;
 	u16 next_to_clean;
-	u16 next_to_alloc;
+	union {
+		u16 next_to_alloc;
+		struct {
+			u8 atr_sample_rate;
+			u8 atr_count;
+		};
+	};
 
 	struct wx_queue_stats stats;
 	struct u64_stats_sync syncp;
@@ -939,6 +978,7 @@ struct wx_ring_feature {
 enum wx_ring_f_enum {
 	RING_F_NONE = 0,
 	RING_F_RSS,
+	RING_F_FDIR,
 	RING_F_ARRAY_SIZE  /* must be last in enum set */
 };
 
@@ -980,15 +1020,26 @@ struct wx_hw_stats {
 	u64 crcerrs;
 	u64 rlec;
 	u64 qmprc;
+	u64 fdirmatch;
+	u64 fdirmiss;
 };
 
 enum wx_state {
 	WX_STATE_RESETTING,
 	WX_STATE_NBITS,		/* must be last */
 };
+
+enum wx_pf_flags {
+	WX_FLAG_FDIR_CAPABLE,
+	WX_FLAG_FDIR_HASH,
+	WX_FLAG_FDIR_PERFECT,
+	WX_PF_FLAGS_NBITS               /* must be last */
+};
+
 struct wx {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	DECLARE_BITMAP(state, WX_STATE_NBITS);
+	DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS);
 
 	void *priv;
 	u8 __iomem *hw_addr;
@@ -1078,6 +1129,9 @@ struct wx {
 	u64 hw_csum_rx_error;
 	u64 alloc_rx_buff_failed;
 
+	u32 atr_sample_rate;
+	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);
+	void (*configure_fdir)(struct wx *wx);
 	void (*do_reset)(struct net_device *netdev);
 };