net: txgbe: add FDIR ATR support

Add flow director ATR filter. ATR mode is enabled by default to filter
TCP packets.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Author: Jiawen Wu

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;
 
@@ -1271,18 +1278,20 @@ 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
  *  @wx: pointer to private structure
  *
  *  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);
 
 	return 0;
 }

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);

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)

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,

drivers/net/ethernet/wangxun/libwx/wx_type.h

@@ -503,6 +503,34 @@ 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 +580,9 @@ 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 +931,13 @@ 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 +976,7 @@ 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 */
 };
 
@@ -986,9 +1024,18 @@ 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;
@@ -1077,6 +1124,9 @@ 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);
 };
 

drivers/net/ethernet/wangxun/txgbe/Makefile

@@ -10,4 +10,5 @@ txgbe-objs := txgbe_main.o \
               txgbe_hw.o \
               txgbe_phy.o \
               txgbe_irq.o \
+              txgbe_fdir.o \
               txgbe_ethtool.o