Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 887 insertions, 243 deletions

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 8a1da7e67707..b721a2009b50 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -20,37 +20,102 @@
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
 
-struct cfp_udf_layout {
-	u8 slices[UDF_NUM_SLICES];
+struct cfp_udf_slice_layout {
+	u8 slices[UDFS_PER_SLICE];
 	u32 mask_value;
+	u32 base_offset;
+};
 
+struct cfp_udf_layout {
+	struct cfp_udf_slice_layout udfs[UDF_NUM_SLICES];
 };
 
+static const u8 zero_slice[UDFS_PER_SLICE] = { };
+
 /* UDF slices layout for a TCPv4/UDPv4 specification */
 static const struct cfp_udf_layout udf_tcpip4_layout = {
-	.slices = {
-		/* End of L2, byte offset 12, src IP[0:15] */
-		CFG_UDF_EOL2 | 6,
-		/* End of L2, byte offset 14, src IP[16:31] */
-		CFG_UDF_EOL2 | 7,
-		/* End of L2, byte offset 16, dst IP[0:15] */
-		CFG_UDF_EOL2 | 8,
-		/* End of L2, byte offset 18, dst IP[16:31] */
-		CFG_UDF_EOL2 | 9,
-		/* End of L3, byte offset 0, src port */
-		CFG_UDF_EOL3 | 0,
-		/* End of L3, byte offset 2, dst port */
-		CFG_UDF_EOL3 | 1,
-		0, 0, 0
+	.udfs = {
+		[1] = {
+			.slices = {
+				/* End of L2, byte offset 12, src IP[0:15] */
+				CFG_UDF_EOL2 | 6,
+				/* End of L2, byte offset 14, src IP[16:31] */
+				CFG_UDF_EOL2 | 7,
+				/* End of L2, byte offset 16, dst IP[0:15] */
+				CFG_UDF_EOL2 | 8,
+				/* End of L2, byte offset 18, dst IP[16:31] */
+				CFG_UDF_EOL2 | 9,
+				/* End of L3, byte offset 0, src port */
+				CFG_UDF_EOL3 | 0,
+				/* End of L3, byte offset 2, dst port */
+				CFG_UDF_EOL3 | 1,
+				0, 0, 0
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_A_0_8_PORT_0 + UDF_SLICE_OFFSET,
+		},
+	},
+};
+
+/* UDF slices layout for a TCPv6/UDPv6 specification */
+static const struct cfp_udf_layout udf_tcpip6_layout = {
+	.udfs = {
+		[0] = {
+			.slices = {
+				/* End of L2, byte offset 8, src IP[0:15] */
+				CFG_UDF_EOL2 | 4,
+				/* End of L2, byte offset 10, src IP[16:31] */
+				CFG_UDF_EOL2 | 5,
+				/* End of L2, byte offset 12, src IP[32:47] */
+				CFG_UDF_EOL2 | 6,
+				/* End of L2, byte offset 14, src IP[48:63] */
+				CFG_UDF_EOL2 | 7,
+				/* End of L2, byte offset 16, src IP[64:79] */
+				CFG_UDF_EOL2 | 8,
+				/* End of L2, byte offset 18, src IP[80:95] */
+				CFG_UDF_EOL2 | 9,
+				/* End of L2, byte offset 20, src IP[96:111] */
+				CFG_UDF_EOL2 | 10,
+				/* End of L2, byte offset 22, src IP[112:127] */
+				CFG_UDF_EOL2 | 11,
+				/* End of L3, byte offset 0, src port */
+				CFG_UDF_EOL3 | 0,
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_B_0_8_PORT_0,
+		},
+		[3] = {
+			.slices = {
+				/* End of L2, byte offset 24, dst IP[0:15] */
+				CFG_UDF_EOL2 | 12,
+				/* End of L2, byte offset 26, dst IP[16:31] */
+				CFG_UDF_EOL2 | 13,
+				/* End of L2, byte offset 28, dst IP[32:47] */
+				CFG_UDF_EOL2 | 14,
+				/* End of L2, byte offset 30, dst IP[48:63] */
+				CFG_UDF_EOL2 | 15,
+				/* End of L2, byte offset 32, dst IP[64:79] */
+				CFG_UDF_EOL2 | 16,
+				/* End of L2, byte offset 34, dst IP[80:95] */
+				CFG_UDF_EOL2 | 17,
+				/* End of L2, byte offset 36, dst IP[96:111] */
+				CFG_UDF_EOL2 | 18,
+				/* End of L2, byte offset 38, dst IP[112:127] */
+				CFG_UDF_EOL2 | 19,
+				/* End of L3, byte offset 2, dst port */
+				CFG_UDF_EOL3 | 1,
+			},
+			.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
+			.base_offset = CORE_UDF_0_D_0_11_PORT_0,
+		},
 	},
-	.mask_value = L3_FRAMING_MASK | IPPROTO_MASK | IP_FRAG,
 };
 
 static inline unsigned int bcm_sf2_get_num_udf_slices(const u8 *layout)
 {
 	unsigned int i, count = 0;
 
-	for (i = 0; i < UDF_NUM_SLICES; i++) {
+	for (i = 0; i < UDFS_PER_SLICE; i++) {
 		if (layout[i] != 0)
 			count++;
 	}
@@ -58,15 +123,42 @@ static inline unsigned int bcm_sf2_get_num_udf_slices(const u8 *layout)
 	return count;
 }
 
+static inline u32 udf_upper_bits(unsigned int num_udf)
+{
+	return GENMASK(num_udf - 1, 0) >> (UDFS_PER_SLICE - 1);
+}
+
+static inline u32 udf_lower_bits(unsigned int num_udf)
+{
+	return (u8)GENMASK(num_udf - 1, 0);
+}
+
+static unsigned int bcm_sf2_get_slice_number(const struct cfp_udf_layout *l,
+					     unsigned int start)
+{
+	const struct cfp_udf_slice_layout *slice_layout;
+	unsigned int slice_idx;
+
+	for (slice_idx = start; slice_idx < UDF_NUM_SLICES; slice_idx++) {
+		slice_layout = &l->udfs[slice_idx];
+		if (memcmp(slice_layout->slices, zero_slice,
+			   sizeof(zero_slice)))
+			break;
+	}
+
+	return slice_idx;
+}
+
 static void bcm_sf2_cfp_udf_set(struct bcm_sf2_priv *priv,
-				unsigned int slice_num,
-				const u8 *layout)
+				const struct cfp_udf_layout *layout,
+				unsigned int slice_num)
 {
-	u32 offset = CORE_UDF_0_A_0_8_PORT_0 + slice_num * UDF_SLICE_OFFSET;
+	u32 offset = layout->udfs[slice_num].base_offset;
 	unsigned int i;
 
-	for (i = 0; i < UDF_NUM_SLICES; i++)
-		core_writel(priv, layout[i], offset + i * 4);
+	for (i = 0; i < UDFS_PER_SLICE; i++)
+		core_writel(priv, layout->udfs[slice_num].slices[i],
+			    offset + i * 4);
 }
 
 static int bcm_sf2_cfp_op(struct bcm_sf2_priv *priv, unsigned int op)
@@ -112,69 +204,177 @@ static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv)
 	return priv->num_cfp_rules - 1;
 }
 
-static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
-				struct ethtool_rx_flow_spec *fs)
+static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv,
+				   unsigned int rule_index,
+				   unsigned int port_num,
+				   unsigned int queue_num,
+				   bool fwd_map_change)
 {
-	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	struct ethtool_tcpip4_spec *v4_spec;
-	const struct cfp_udf_layout *layout;
-	unsigned int slice_num, rule_index;
-	unsigned int queue_num, port_num;
-	u8 ip_proto, ip_frag;
-	u8 num_udf;
-	u32 reg;
 	int ret;
+	u32 reg;
 
-	/* Check for unsupported extensions */
-	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->m_ext.vlan_etype || fs->m_ext.data[1]))
-		return -EINVAL;
+	/* Replace ARL derived destination with DST_MAP derived, define
+	 * which port and queue this should be forwarded to.
+	 */
+	if (fwd_map_change)
+		reg = CHANGE_FWRD_MAP_IB_REP_ARL |
+		      BIT(port_num + DST_MAP_IB_SHIFT) |
+		      CHANGE_TC | queue_num << NEW_TC_SHIFT;
+	else
+		reg = 0;
 
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    test_bit(fs->location, priv->cfp.used))
-		return -EBUSY;
+	core_writel(priv, reg, CORE_ACT_POL_DATA0);
 
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    fs->location > bcm_sf2_cfp_rule_size(priv))
-		return -EINVAL;
+	/* Set classification ID that needs to be put in Broadcom tag */
+	core_writel(priv, rule_index << CHAIN_ID_SHIFT, CORE_ACT_POL_DATA1);
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	core_writel(priv, 0, CORE_ACT_POL_DATA2);
 
-	/* We do not support discarding packets, check that the
-	 * destination port is enabled and that we are within the
-	 * number of ports supported by the switch
+	/* Configure policer RAM now */
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | ACT_POL_RAM);
+	if (ret) {
+		pr_err("Policer entry at %d failed\n", rule_index);
+		return ret;
+	}
+
+	/* Disable the policer */
+	core_writel(priv, POLICER_MODE_DISABLE, CORE_RATE_METER0);
+
+	/* Now the rate meter */
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | RATE_METER_RAM);
+	if (ret) {
+		pr_err("Meter entry at %d failed\n", rule_index);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv,
+				   struct ethtool_tcpip4_spec *v4_spec,
+				   unsigned int slice_num,
+				   bool mask)
+{
+	u32 reg, offset;
+
+	/* C-Tag		[31:24]
+	 * UDF_n_A8		[23:8]
+	 * UDF_n_A7		[7:0]
 	 */
-	port_num = fs->ring_cookie / 8;
+	reg = 0;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	core_writel(priv, reg, offset);
 
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
-	    !(BIT(port_num) & ds->enabled_port_mask) ||
-	    port_num >= priv->hw_params.num_ports)
-		return -EINVAL;
+	/* UDF_n_A7		[31:24]
+	 * UDF_n_A6		[23:8]
+	 * UDF_n_A5		[7:0]
+	 */
+	reg = be16_to_cpu(v4_spec->pdst) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A5		[31:24]
+	 * UDF_n_A4		[23:8]
+	 * UDF_n_A3		[7:0]
+	 */
+	reg = (be16_to_cpu(v4_spec->pdst) & 0xff) << 24 |
+	      (u32)be16_to_cpu(v4_spec->psrc) << 8 |
+	      (be32_to_cpu(v4_spec->ip4dst) & 0x0000ff00) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A3		[31:24]
+	 * UDF_n_A2		[23:8]
+	 * UDF_n_A1		[7:0]
+	 */
+	reg = (u32)(be32_to_cpu(v4_spec->ip4dst) & 0xff) << 24 |
+	      (u32)(be32_to_cpu(v4_spec->ip4dst) >> 16) << 8 |
+	      (be32_to_cpu(v4_spec->ip4src) & 0x0000ff00) >> 8;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	core_writel(priv, reg, offset);
+
+	/* UDF_n_A1		[31:24]
+	 * UDF_n_A0		[23:8]
+	 * Reserved		[7:4]
+	 * Slice ID		[3:2]
+	 * Slice valid		[1:0]
+	 */
+	reg = (u32)(be32_to_cpu(v4_spec->ip4src) & 0xff) << 24 |
+	      (u32)(be32_to_cpu(v4_spec->ip4src) >> 16) << 8 |
+	      SLICE_NUM(slice_num) | SLICE_VALID;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	core_writel(priv, reg, offset);
+}
+
+static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
+				     unsigned int port_num,
+				     unsigned int queue_num,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec;
+	const struct cfp_udf_layout *layout;
+	unsigned int slice_num, rule_index;
+	u8 ip_proto, ip_frag;
+	u8 num_udf;
+	u32 reg;
+	int ret;
 
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 		ip_proto = IPPROTO_TCP;
 		v4_spec = &fs->h_u.tcp_ip4_spec;
+		v4_m_spec = &fs->m_u.tcp_ip4_spec;
 		break;
 	case UDP_V4_FLOW:
 		ip_proto = IPPROTO_UDP;
 		v4_spec = &fs->h_u.udp_ip4_spec;
+		v4_m_spec = &fs->m_u.udp_ip4_spec;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	/* We only use one UDF slice for now */
-	slice_num = 1;
+	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+
+	/* Locate the first rule available */
+	if (fs->location == RX_CLS_LOC_ANY)
+		rule_index = find_first_zero_bit(priv->cfp.used,
+						 bcm_sf2_cfp_rule_size(priv));
+	else
+		rule_index = fs->location;
+
 	layout = &udf_tcpip4_layout;
-	num_udf = bcm_sf2_get_num_udf_slices(layout->slices);
+	/* We only use one UDF slice for now */
+	slice_num = bcm_sf2_get_slice_number(layout, 0);
+	if (slice_num == UDF_NUM_SLICES)
+		return -EINVAL;
+
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
 
 	/* Apply the UDF layout for this filter */
-	bcm_sf2_cfp_udf_set(priv, slice_num, layout->slices);
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
 
 	/* Apply to all packets received through this port */
 	core_writel(priv, BIT(port), CORE_CFP_DATA_PORT(7));
 
+	/* Source port map match */
+	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+
 	/* S-Tag status		[31:30]
 	 * C-Tag status		[29:28]
 	 * L2 framing		[27:26]
@@ -189,143 +389,398 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	 * Reserved		[1]
 	 * UDF_Valid[8]		[0]
 	 */
-	core_writel(priv, v4_spec->tos << 16 | ip_proto << 8 | ip_frag << 7,
+	core_writel(priv, v4_spec->tos << IPTOS_SHIFT |
+		    ip_proto << IPPROTO_SHIFT | ip_frag << IP_FRAG_SHIFT |
+		    udf_upper_bits(num_udf),
 		    CORE_CFP_DATA_PORT(6));
 
+	/* Mask with the specific layout for IPv4 packets */
+	core_writel(priv, layout->udfs[slice_num].mask_value |
+		    udf_upper_bits(num_udf), CORE_CFP_MASK_PORT(6));
+
 	/* UDF_Valid[7:0]	[31:24]
 	 * S-Tag		[23:8]
 	 * C-Tag		[7:0]
 	 */
-	core_writel(priv, GENMASK(num_udf - 1, 0) << 24, CORE_CFP_DATA_PORT(5));
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_DATA_PORT(5));
+
+	/* Mask all but valid UDFs */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5));
+
+	/* Program the match and the mask */
+	bcm_sf2_cfp_slice_ipv4(priv, v4_spec, slice_num, false);
+	bcm_sf2_cfp_slice_ipv4(priv, v4_m_spec, SLICE_NUM_MASK, true);
+
+	/* Insert into TCAM now */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
+	if (ret) {
+		pr_err("TCAM entry at addr %d failed\n", rule_index);
+		return ret;
+	}
+
+	/* Insert into Action and policer RAMs now */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port_num,
+				      queue_num, true);
+	if (ret)
+		return ret;
+
+	/* Turn on CFP for this rule now */
+	reg = core_readl(priv, CORE_CFP_CTL_REG);
+	reg |= BIT(port);
+	core_writel(priv, reg, CORE_CFP_CTL_REG);
+
+	/* Flag the rule as being used and return it */
+	set_bit(rule_index, priv->cfp.used);
+	set_bit(rule_index, priv->cfp.unique);
+	fs->location = rule_index;
+
+	return 0;
+}
+
+static void bcm_sf2_cfp_slice_ipv6(struct bcm_sf2_priv *priv,
+				   const __be32 *ip6_addr, const __be16 port,
+				   unsigned int slice_num,
+				   bool mask)
+{
+	u32 reg, tmp, val, offset;
 
 	/* C-Tag		[31:24]
-	 * UDF_n_A8		[23:8]
-	 * UDF_n_A7		[7:0]
+	 * UDF_n_B8		[23:8]	(port)
+	 * UDF_n_B7 (upper)	[7:0]	(addr[15:8])
 	 */
-	core_writel(priv, 0, CORE_CFP_DATA_PORT(4));
+	reg = be32_to_cpu(ip6_addr[3]);
+	val = (u32)be16_to_cpu(port) << 8 | ((reg >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A7		[31:24]
-	 * UDF_n_A6		[23:8]
-	 * UDF_n_A5		[7:0]
+	/* UDF_n_B7 (lower)	[31:24]	(addr[7:0])
+	 * UDF_n_B6		[23:8] (addr[31:16])
+	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
 	 */
-	core_writel(priv, be16_to_cpu(v4_spec->pdst) >> 8,
-		    CORE_CFP_DATA_PORT(3));
+	tmp = be32_to_cpu(ip6_addr[2]);
+	val = (u32)(reg & 0xff) << 24 | (u32)(reg >> 16) << 8 |
+	      ((tmp >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A5		[31:24]
-	 * UDF_n_A4		[23:8]
-	 * UDF_n_A3		[7:0]
+	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
+	 * UDF_n_B4		[23:8] (addr[63:48])
+	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
 	 */
-	reg = (be16_to_cpu(v4_spec->pdst) & 0xff) << 24 |
-	      (u32)be16_to_cpu(v4_spec->psrc) << 8 |
-	      (be32_to_cpu(v4_spec->ip4dst) & 0x0000ff00) >> 8;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(2));
+	reg = be32_to_cpu(ip6_addr[1]);
+	val = (u32)(tmp & 0xff) << 24 | (u32)(tmp >> 16) << 8 |
+	      ((reg >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A3		[31:24]
-	 * UDF_n_A2		[23:8]
-	 * UDF_n_A1		[7:0]
+	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
+	 * UDF_n_B2		[23:8] (addr[95:80])
+	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
 	 */
-	reg = (u32)(be32_to_cpu(v4_spec->ip4dst) & 0xff) << 24 |
-	      (u32)(be32_to_cpu(v4_spec->ip4dst) >> 16) << 8 |
-	      (be32_to_cpu(v4_spec->ip4src) & 0x0000ff00) >> 8;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(1));
+	tmp = be32_to_cpu(ip6_addr[0]);
+	val = (u32)(reg & 0xff) << 24 | (u32)(reg >> 16) << 8 |
+	      ((tmp >> 8) & 0xff);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	core_writel(priv, val, offset);
 
-	/* UDF_n_A1		[31:24]
-	 * UDF_n_A0		[23:8]
+	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
+	 * UDF_n_B0		[23:8] (addr[127:112])
 	 * Reserved		[7:4]
 	 * Slice ID		[3:2]
 	 * Slice valid		[1:0]
 	 */
-	reg = (u32)(be32_to_cpu(v4_spec->ip4src) & 0xff) << 24 |
-	      (u32)(be32_to_cpu(v4_spec->ip4src) >> 16) << 8 |
-	      SLICE_NUM(slice_num) | SLICE_VALID;
-	core_writel(priv, reg, CORE_CFP_DATA_PORT(0));
+	reg = (u32)(tmp & 0xff) << 24 | (u32)(tmp >> 16) << 8 |
+	       SLICE_NUM(slice_num) | SLICE_VALID;
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	core_writel(priv, reg, offset);
+}
 
-	/* Source port map match */
-	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
+				     unsigned int port_num,
+				     unsigned int queue_num,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec;
+	unsigned int slice_num, rule_index[2];
+	const struct cfp_udf_layout *layout;
+	u8 ip_proto, ip_frag;
+	int ret = 0;
+	u8 num_udf;
+	u32 reg;
 
-	/* Mask with the specific layout for IPv4 packets */
-	core_writel(priv, layout->mask_value, CORE_CFP_MASK_PORT(6));
+	switch (fs->flow_type & ~FLOW_EXT) {
+	case TCP_V6_FLOW:
+		ip_proto = IPPROTO_TCP;
+		v6_spec = &fs->h_u.tcp_ip6_spec;
+		v6_m_spec = &fs->m_u.tcp_ip6_spec;
+		break;
+	case UDP_V6_FLOW:
+		ip_proto = IPPROTO_UDP;
+		v6_spec = &fs->h_u.udp_ip6_spec;
+		v6_m_spec = &fs->m_u.udp_ip6_spec;
+		break;
+	default:
+		return -EINVAL;
+	}
 
-	/* Mask all but valid UDFs */
-	core_writel(priv, GENMASK(num_udf - 1, 0) << 24, CORE_CFP_MASK_PORT(5));
+	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
 
-	/* Mask all */
-	core_writel(priv, 0, CORE_CFP_MASK_PORT(4));
+	layout = &udf_tcpip6_layout;
+	slice_num = bcm_sf2_get_slice_number(layout, 0);
+	if (slice_num == UDF_NUM_SLICES)
+		return -EINVAL;
 
-	/* All other UDFs should be matched with the filter */
-	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(3));
-	core_writel(priv, 0xffffffff, CORE_CFP_MASK_PORT(2));
-	core_writel(priv, 0xffffffff, CORE_CFP_MASK_PORT(1));
-	core_writel(priv, 0xffffff0f, CORE_CFP_MASK_PORT(0));
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
 
-	/* Locate the first rule available */
+	/* Negotiate two indexes, one for the second half which we are chained
+	 * from, which is what we will return to user-space, and a second one
+	 * which is used to store its first half. That first half does not
+	 * allow any choice of placement, so it just needs to find the next
+	 * available bit. We return the second half as fs->location because
+	 * that helps with the rule lookup later on since the second half is
+	 * chained from its first half, we can easily identify IPv6 CFP rules
+	 * by looking whether they carry a CHAIN_ID.
+	 *
+	 * We also want the second half to have a lower rule_index than its
+	 * first half because the HW search is by incrementing addresses.
+	 */
 	if (fs->location == RX_CLS_LOC_ANY)
-		rule_index = find_first_zero_bit(priv->cfp.used,
-						 bcm_sf2_cfp_rule_size(priv));
+		rule_index[0] = find_first_zero_bit(priv->cfp.used,
+						    bcm_sf2_cfp_rule_size(priv));
 	else
-		rule_index = fs->location;
+		rule_index[0] = fs->location;
 
-	/* Insert into TCAM now */
-	bcm_sf2_cfp_rule_addr_set(priv, rule_index);
+	/* Flag it as used (cleared on error path) such that we can immediately
+	 * obtain a second one to chain from.
+	 */
+	set_bit(rule_index[0], priv->cfp.used);
 
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
-	if (ret) {
-		pr_err("TCAM entry at addr %d failed\n", rule_index);
-		return ret;
+	rule_index[1] = find_first_zero_bit(priv->cfp.used,
+					    bcm_sf2_cfp_rule_size(priv));
+	if (rule_index[1] > bcm_sf2_cfp_rule_size(priv)) {
+		ret = -ENOSPC;
+		goto out_err;
 	}
 
-	/* Replace ARL derived destination with DST_MAP derived, define
-	 * which port and queue this should be forwarded to.
-	 *
-	 * We have a small oddity where Port 6 just does not have a
-	 * valid bit here (so we subtract by one).
+	/* Apply the UDF layout for this filter */
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
+
+	/* Apply to all packets received through this port */
+	core_writel(priv, BIT(port), CORE_CFP_DATA_PORT(7));
+
+	/* Source port map match */
+	core_writel(priv, 0xff, CORE_CFP_MASK_PORT(7));
+
+	/* S-Tag status		[31:30]
+	 * C-Tag status		[29:28]
+	 * L2 framing		[27:26]
+	 * L3 framing		[25:24]
+	 * IP ToS		[23:16]
+	 * IP proto		[15:08]
+	 * IP Fragm		[7]
+	 * Non 1st frag		[6]
+	 * IP Authen		[5]
+	 * TTL range		[4:3]
+	 * PPPoE session	[2]
+	 * Reserved		[1]
+	 * UDF_Valid[8]		[0]
 	 */
-	queue_num = fs->ring_cookie % 8;
-	if (port_num >= 7)
-		port_num -= 1;
+	reg = 1 << L3_FRAMING_SHIFT | ip_proto << IPPROTO_SHIFT |
+		ip_frag << IP_FRAG_SHIFT | udf_upper_bits(num_udf);
+	core_writel(priv, reg, CORE_CFP_DATA_PORT(6));
 
-	reg = CHANGE_FWRD_MAP_IB_REP_ARL | BIT(port_num + DST_MAP_IB_SHIFT) |
-		CHANGE_TC | queue_num << NEW_TC_SHIFT;
+	/* Mask with the specific layout for IPv6 packets including
+	 * UDF_Valid[8]
+	 */
+	reg = layout->udfs[slice_num].mask_value | udf_upper_bits(num_udf);
+	core_writel(priv, reg, CORE_CFP_MASK_PORT(6));
 
-	core_writel(priv, reg, CORE_ACT_POL_DATA0);
+	/* UDF_Valid[7:0]	[31:24]
+	 * S-Tag		[23:8]
+	 * C-Tag		[7:0]
+	 */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_DATA_PORT(5));
 
-	/* Set classification ID that needs to be put in Broadcom tag */
-	core_writel(priv, rule_index << CHAIN_ID_SHIFT,
-		    CORE_ACT_POL_DATA1);
+	/* Mask all but valid UDFs */
+	core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5));
 
-	core_writel(priv, 0, CORE_ACT_POL_DATA2);
+	/* Slice the IPv6 source address and port */
+	bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6src, v6_spec->psrc,
+				slice_num, false);
+	bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6src, v6_m_spec->psrc,
+				slice_num, true);
 
-	/* Configure policer RAM now */
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | ACT_POL_RAM);
+	/* Insert into TCAM now because we need to insert a second rule */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index[0]);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
 	if (ret) {
-		pr_err("Policer entry at %d failed\n", rule_index);
-		return ret;
+		pr_err("TCAM entry at addr %d failed\n", rule_index[0]);
+		goto out_err;
 	}
 
-	/* Disable the policer */
-	core_writel(priv, POLICER_MODE_DISABLE, CORE_RATE_METER0);
+	/* Insert into Action and policer RAMs now */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num,
+				      queue_num, false);
+	if (ret)
+		goto out_err;
 
-	/* Now the rate meter */
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | RATE_METER_RAM);
+	/* Now deal with the second slice to chain this rule */
+	slice_num = bcm_sf2_get_slice_number(layout, slice_num + 1);
+	if (slice_num == UDF_NUM_SLICES) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices);
+
+	/* Apply the UDF layout for this filter */
+	bcm_sf2_cfp_udf_set(priv, layout, slice_num);
+
+	/* Chained rule, source port match is coming from the rule we are
+	 * chained from.
+	 */
+	core_writel(priv, 0, CORE_CFP_DATA_PORT(7));
+	core_writel(priv, 0, CORE_CFP_MASK_PORT(7));
+
+	/*
+	 * CHAIN ID		[31:24] chain to previous slice
+	 * Reserved		[23:20]
+	 * UDF_Valid[11:8]	[19:16]
+	 * UDF_Valid[7:0]	[15:8]
+	 * UDF_n_D11		[7:0]
+	 */
+	reg = rule_index[0] << 24 | udf_upper_bits(num_udf) << 16 |
+		udf_lower_bits(num_udf) << 8;
+	core_writel(priv, reg, CORE_CFP_DATA_PORT(6));
+
+	/* Mask all except chain ID, UDF Valid[8] and UDF Valid[7:0] */
+	reg = XCESS_ADDR_MASK << 24 | udf_upper_bits(num_udf) << 16 |
+		udf_lower_bits(num_udf) << 8;
+	core_writel(priv, reg, CORE_CFP_MASK_PORT(6));
+
+	/* Don't care */
+	core_writel(priv, 0, CORE_CFP_DATA_PORT(5));
+
+	/* Mask all */
+	core_writel(priv, 0, CORE_CFP_MASK_PORT(5));
+
+	bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6dst, v6_spec->pdst, slice_num,
+			       false);
+	bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6dst, v6_m_spec->pdst,
+			       SLICE_NUM_MASK, true);
+
+	/* Insert into TCAM now */
+	bcm_sf2_cfp_rule_addr_set(priv, rule_index[1]);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL);
 	if (ret) {
-		pr_err("Meter entry at %d failed\n", rule_index);
-		return ret;
+		pr_err("TCAM entry at addr %d failed\n", rule_index[1]);
+		goto out_err;
 	}
 
+	/* Insert into Action and policer RAMs now, set chain ID to
+	 * the one we are chained to
+	 */
+	ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num,
+				      queue_num, true);
+	if (ret)
+		goto out_err;
+
 	/* Turn on CFP for this rule now */
 	reg = core_readl(priv, CORE_CFP_CTL_REG);
 	reg |= BIT(port);
 	core_writel(priv, reg, CORE_CFP_CTL_REG);
 
-	/* Flag the rule as being used and return it */
-	set_bit(rule_index, priv->cfp.used);
-	fs->location = rule_index;
+	/* Flag the second half rule as being used now, return it as the
+	 * location, and flag it as unique while dumping rules
+	 */
+	set_bit(rule_index[1], priv->cfp.used);
+	set_bit(rule_index[1], priv->cfp.unique);
+	fs->location = rule_index[1];
 
-	return 0;
+	return ret;
+
+out_err:
+	clear_bit(rule_index[0], priv->cfp.used);
+	return ret;
 }
 
-static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
-				u32 loc)
+static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	unsigned int queue_num, port_num;
+	int ret = -EINVAL;
+
+	/* Check for unsupported extensions */
+	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
+	     fs->m_ext.data[1]))
+		return -EINVAL;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    test_bit(fs->location, priv->cfp.used))
+		return -EBUSY;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    fs->location > bcm_sf2_cfp_rule_size(priv))
+		return -EINVAL;
+
+	/* We do not support discarding packets, check that the
+	 * destination port is enabled and that we are within the
+	 * number of ports supported by the switch
+	 */
+	port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
+
+	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
+	    !dsa_is_user_port(ds, port_num) ||
+	    port_num >= priv->hw_params.num_ports)
+		return -EINVAL;
+	/*
+	 * We have a small oddity where Port 6 just does not have a
+	 * valid bit here (so we substract by one).
+	 */
+	queue_num = fs->ring_cookie % SF2_NUM_EGRESS_QUEUES;
+	if (port_num >= 7)
+		port_num -= 1;
+
+	switch (fs->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		ret = bcm_sf2_cfp_ipv4_rule_set(priv, port, port_num,
+						queue_num, fs);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = bcm_sf2_cfp_ipv6_rule_set(priv, port, port_num,
+						queue_num, fs);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
+				    u32 loc, u32 *next_loc)
 {
 	int ret;
 	u32 reg;
@@ -341,6 +796,14 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (ret)
 		return ret;
 
+	/* Check if this is possibly an IPv6 rule that would
+	 * indicate we need to delete its companion rule
+	 * as well
+	 */
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+	if (next_loc)
+		*next_loc = (reg >> 24) & CHAIN_ID_MASK;
+
 	/* Clear its valid bits */
 	reg = core_readl(priv, CORE_CFP_DATA_PORT(0));
 	reg &= ~SLICE_VALID;
@@ -352,10 +815,28 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 		return ret;
 
 	clear_bit(loc, priv->cfp.used);
+	clear_bit(loc, priv->cfp.unique);
 
 	return 0;
 }
 
+static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
+				u32 loc)
+{
+	u32 next_loc = 0;
+	int ret;
+
+	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
+	if (ret)
+		return ret;
+
+	/* If this was an IPv6 rule, delete is companion rule too */
+	if (next_loc)
+		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+
+	return ret;
+}
+
 static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 {
 	unsigned int i;
@@ -369,93 +850,63 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
-				struct ethtool_rxnfc *nfc, bool search)
+static int bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
+				    struct ethtool_tcpip4_spec *v4_spec,
+				    bool mask)
 {
-	struct ethtool_tcpip4_spec *v4_spec;
-	unsigned int queue_num;
+	u32 reg, offset, ipv4;
 	u16 src_dst_port;
-	u32 reg, ipv4;
-	int ret;
-
-	if (!search) {
-		bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
-
-		ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
-		if (ret)
-			return ret;
-
-		reg = core_readl(priv, CORE_ACT_POL_DATA0);
 
-		ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-		if (ret)
-			return ret;
-	} else {
-		reg = core_readl(priv, CORE_ACT_POL_DATA0);
-	}
-
-	/* Extract the destination port */
-	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
-				  DST_MAP_IB_MASK) - 1;
-
-	/* There is no Port 6, so we compensate for that here */
-	if (nfc->fs.ring_cookie >= 6)
-		nfc->fs.ring_cookie++;
-	nfc->fs.ring_cookie *= 8;
-
-	/* Extract the destination queue */
-	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
-	nfc->fs.ring_cookie += queue_num;
-
-	/* Extract the IP protocol */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		nfc->fs.flow_type = TCP_V4_FLOW;
-		v4_spec = &nfc->fs.h_u.tcp_ip4_spec;
-		break;
-	case IPPROTO_UDP:
-		nfc->fs.flow_type = UDP_V4_FLOW;
-		v4_spec = &nfc->fs.h_u.udp_ip4_spec;
-		break;
-	default:
-		/* Clear to exit the search process */
-		if (search)
-			core_readl(priv, CORE_CFP_DATA_PORT(7));
-		return -EINVAL;
-	}
-
-	v4_spec->tos = (reg >> 16) & IPPROTO_MASK;
-	nfc->fs.m_ext.data[0] = cpu_to_be32((reg >> 7) & 1);
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
 
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(3));
+	reg = core_readl(priv, offset);
 	/* src port [15:8] */
 	src_dst_port = reg << 8;
 
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(2));
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+
+	reg = core_readl(priv, offset);
 	/* src port [7:0] */
 	src_dst_port |= (reg >> 24);
 
 	v4_spec->pdst = cpu_to_be16(src_dst_port);
-	nfc->fs.m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
 	v4_spec->psrc = cpu_to_be16((u16)(reg >> 8));
-	nfc->fs.m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
 
 	/* IPv4 dst [15:8] */
 	ipv4 = (reg & 0xff) << 8;
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(1));
+
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+
+	reg = core_readl(priv, offset);
 	/* IPv4 dst [31:16] */
 	ipv4 |= ((reg >> 8) & 0xffff) << 16;
 	/* IPv4 dst [7:0] */
 	ipv4 |= (reg >> 24) & 0xff;
 	v4_spec->ip4dst = cpu_to_be32(ipv4);
-	nfc->fs.m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
 
 	/* IPv4 src [15:8] */
 	ipv4 = (reg & 0xff) << 8;
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(0));
 
-	if (!(reg & SLICE_VALID))
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	reg = core_readl(priv, offset);
+
+	/* Once the TCAM is programmed, the mask reflects the slice number
+	 * being matched, don't bother checking it when reading back the
+	 * mask spec
+	 */
+	if (!mask && !(reg & SLICE_VALID))
 		return -EINVAL;
 
 	/* IPv4 src [7:0] */
@@ -463,7 +914,233 @@ static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 	/* IPv4 src [31:16] */
 	ipv4 |= ((reg >> 8) & 0xffff) << 16;
 	v4_spec->ip4src = cpu_to_be32(ipv4);
-	nfc->fs.m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+
+	return 0;
+}
+
+static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
+				     struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *v4_spec = NULL, *v4_m_spec = NULL;
+	u32 reg;
+	int ret;
+
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
+	case IPPROTO_TCP:
+		fs->flow_type = TCP_V4_FLOW;
+		v4_spec = &fs->h_u.tcp_ip4_spec;
+		v4_m_spec = &fs->m_u.tcp_ip4_spec;
+		break;
+	case IPPROTO_UDP:
+		fs->flow_type = UDP_V4_FLOW;
+		v4_spec = &fs->h_u.udp_ip4_spec;
+		v4_m_spec = &fs->m_u.udp_ip4_spec;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	fs->m_ext.data[0] = cpu_to_be32((reg >> IP_FRAG_SHIFT) & 1);
+	v4_spec->tos = (reg >> IPTOS_SHIFT) & IPTOS_MASK;
+
+	ret = bcm_sf2_cfp_unslice_ipv4(priv, v4_spec, false);
+	if (ret)
+		return ret;
+
+	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
+}
+
+static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
+				     __be32 *ip6_addr, __be16 *port,
+				     bool mask)
+{
+	u32 reg, tmp, offset;
+
+	/* C-Tag		[31:24]
+	 * UDF_n_B8		[23:8] (port)
+	 * UDF_n_B7 (upper)	[7:0] (addr[15:8])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(4);
+	else
+		offset = CORE_CFP_DATA_PORT(4);
+	reg = core_readl(priv, offset);
+	*port = cpu_to_be32(reg) >> 8;
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B7 (lower)	[31:24] (addr[7:0])
+	 * UDF_n_B6		[23:8] (addr[31:16])
+	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(3);
+	else
+		offset = CORE_CFP_DATA_PORT(3);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[3] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
+	 * UDF_n_B4		[23:8] (addr[63:48])
+	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(2);
+	else
+		offset = CORE_CFP_DATA_PORT(2);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[2] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
+	 * UDF_n_B2		[23:8] (addr[95:80])
+	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(1);
+	else
+		offset = CORE_CFP_DATA_PORT(1);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[1] = cpu_to_be32(tmp);
+	tmp = (u32)(reg & 0xff) << 8;
+
+	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
+	 * UDF_n_B0		[23:8] (addr[127:112])
+	 * Reserved		[7:4]
+	 * Slice ID		[3:2]
+	 * Slice valid		[1:0]
+	 */
+	if (mask)
+		offset = CORE_CFP_MASK_PORT(0);
+	else
+		offset = CORE_CFP_DATA_PORT(0);
+	reg = core_readl(priv, offset);
+	tmp |= (reg >> 24) & 0xff;
+	tmp |= (u32)((reg >> 8) << 16);
+	ip6_addr[0] = cpu_to_be32(tmp);
+
+	if (!mask && !(reg & SLICE_VALID))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
+				     struct ethtool_rx_flow_spec *fs,
+				     u32 next_loc)
+{
+	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
+	u32 reg;
+	int ret;
+
+	/* UDPv6 and TCPv6 both use ethtool_tcpip6_spec so we are fine
+	 * assuming tcp_ip6_spec here being an union.
+	 */
+	v6_spec = &fs->h_u.tcp_ip6_spec;
+	v6_m_spec = &fs->m_u.tcp_ip6_spec;
+
+	/* Read the second half first */
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6dst, &v6_spec->pdst,
+				       false);
+	if (ret)
+		return ret;
+
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6dst,
+				       &v6_m_spec->pdst, true);
+	if (ret)
+		return ret;
+
+	/* Read last to avoid next entry clobbering the results during search
+	 * operations. We would not have the port enabled for this rule, so
+	 * don't bother checking it.
+	 */
+	(void)core_readl(priv, CORE_CFP_DATA_PORT(7));
+
+	/* The slice number is valid, so read the rule we are chained from now
+	 * which is our first half.
+	 */
+	bcm_sf2_cfp_rule_addr_set(priv, next_loc);
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
+	if (ret)
+		return ret;
+
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
+	case IPPROTO_TCP:
+		fs->flow_type = TCP_V6_FLOW;
+		break;
+	case IPPROTO_UDP:
+		fs->flow_type = UDP_V6_FLOW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6src, &v6_spec->psrc,
+				       false);
+	if (ret)
+		return ret;
+
+	return bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6src,
+					&v6_m_spec->psrc, true);
+}
+
+static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rxnfc *nfc)
+{
+	u32 reg, ipv4_or_chain_id;
+	unsigned int queue_num;
+	int ret;
+
+	bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
+	if (ret)
+		return ret;
+
+	reg = core_readl(priv, CORE_ACT_POL_DATA0);
+
+	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
+	if (ret)
+		return ret;
+
+	/* Extract the destination port */
+	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
+				  DST_MAP_IB_MASK) - 1;
+
+	/* There is no Port 6, so we compensate for that here */
+	if (nfc->fs.ring_cookie >= 6)
+		nfc->fs.ring_cookie++;
+	nfc->fs.ring_cookie *= SF2_NUM_EGRESS_QUEUES;
+
+	/* Extract the destination queue */
+	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
+	nfc->fs.ring_cookie += queue_num;
+
+	/* Extract the L3_FRAMING or CHAIN_ID */
+	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
+
+	/* With IPv6 rules this would contain a non-zero chain ID since
+	 * we reserve entry 0 and it cannot be used. So if we read 0 here
+	 * this means an IPv4 rule.
+	 */
+	ipv4_or_chain_id = (reg >> L3_FRAMING_SHIFT) & 0xff;
+	if (ipv4_or_chain_id == 0)
+		ret = bcm_sf2_cfp_ipv4_rule_get(priv, port, &nfc->fs);
+	else
+		ret = bcm_sf2_cfp_ipv6_rule_get(priv, port, &nfc->fs,
+						ipv4_or_chain_id);
+	if (ret)
+		return ret;
 
 	/* Read last to avoid next entry clobbering the results during search
 	 * operations
@@ -486,44 +1163,11 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 				    u32 *rule_locs)
 {
 	unsigned int index = 1, rules_cnt = 0;
-	int ret;
-	u32 reg;
 
-	/* Do not poll on OP_STR_DONE to be self-clearing for search
-	 * operations, we cannot use bcm_sf2_cfp_op here because it completes
-	 * on clearing OP_STR_DONE which won't clear until the entire search
-	 * operation is over.
-	 */
-	reg = core_readl(priv, CORE_CFP_ACC);
-	reg &= ~(XCESS_ADDR_MASK << XCESS_ADDR_SHIFT);
-	reg |= index << XCESS_ADDR_SHIFT;
-	reg &= ~(OP_SEL_MASK | RAM_SEL_MASK);
-	reg |= OP_SEL_SEARCH | TCAM_SEL | OP_STR_DONE;
-	core_writel(priv, reg, CORE_CFP_ACC);
-
-	do {
-		/* Wait for results to be ready */
-		reg = core_readl(priv, CORE_CFP_ACC);
-
-		/* Extract the address we are searching */
-		index = reg >> XCESS_ADDR_SHIFT;
-		index &= XCESS_ADDR_MASK;
-
-		/* We have a valid search result, so flag it accordingly */
-		if (reg & SEARCH_STS) {
-			ret = bcm_sf2_cfp_rule_get(priv, port, nfc, true);
-			if (ret)
-				continue;
-
-			rule_locs[rules_cnt] = index;
-			rules_cnt++;
-		}
-
-		/* Search is over break out */
-		if (!(reg & OP_STR_DONE))
-			break;
-
-	} while (index < priv->num_cfp_rules);
+	for_each_set_bit_from(index, priv->cfp.unique, priv->num_cfp_rules) {
+		rule_locs[rules_cnt] = index;
+		rules_cnt++;
+	}
 
 	/* Put the TCAM size here */
 	nfc->data = bcm_sf2_cfp_rule_size(priv);
@@ -543,13 +1187,13 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 	switch (nfc->cmd) {
 	case ETHTOOL_GRXCLSRLCNT:
 		/* Subtract the default, unusable rule */
-		nfc->rule_cnt = bitmap_weight(priv->cfp.used,
+		nfc->rule_cnt = bitmap_weight(priv->cfp.unique,
 					      priv->num_cfp_rules) - 1;
 		/* We support specifying rule locations */
 		nfc->data |= RX_CLS_LOC_SPECIAL;
 		break;
 	case ETHTOOL_GRXCLSRULE:
-		ret = bcm_sf2_cfp_rule_get(priv, port, nfc, false);
+		ret = bcm_sf2_cfp_rule_get(priv, port, nfc);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		ret = bcm_sf2_cfp_rule_get_all(priv, port, nfc, rule_locs);