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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 195 insertions, 18 deletions

diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index d43737e6c3fb..1d96c9d4a8e9 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -13,6 +13,8 @@ static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 	const struct ethhdr *hdr = eth_hdr(skb);
 	u64 dmac = ether_addr_to_u64(hdr->h_dest);
 
+	if (ntohs(hdr->h_proto) == ETH_P_SJA1105_META)
+		return false;
 	if ((dmac & SJA1105_LINKLOCAL_FILTER_A_MASK) ==
 		    SJA1105_LINKLOCAL_FILTER_A)
 		return true;
@@ -22,15 +24,61 @@ static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 	return false;
 }
 
+struct sja1105_meta {
+	u64 tstamp;
+	u64 dmac_byte_4;
+	u64 dmac_byte_3;
+	u64 source_port;
+	u64 switch_id;
+};
+
+static void sja1105_meta_unpack(const struct sk_buff *skb,
+				struct sja1105_meta *meta)
+{
+	u8 *buf = skb_mac_header(skb) + ETH_HLEN;
+
+	/* UM10944.pdf section 4.2.17 AVB Parameters:
+	 * Structure of the meta-data follow-up frame.
+	 * It is in network byte order, so there are no quirks
+	 * while unpacking the meta frame.
+	 *
+	 * Also SJA1105 E/T only populates bits 23:0 of the timestamp
+	 * whereas P/Q/R/S does 32 bits. Since the structure is the
+	 * same and the E/T puts zeroes in the high-order byte, use
+	 * a unified unpacking command for both device series.
+	 */
+	packing(buf,     &meta->tstamp,     31, 0, 4, UNPACK, 0);
+	packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0);
+	packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0);
+	packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0);
+	packing(buf + 7, &meta->switch_id,   7, 0, 1, UNPACK, 0);
+}
+
+static inline bool sja1105_is_meta_frame(const struct sk_buff *skb)
+{
+	const struct ethhdr *hdr = eth_hdr(skb);
+	u64 smac = ether_addr_to_u64(hdr->h_source);
+	u64 dmac = ether_addr_to_u64(hdr->h_dest);
+
+	if (smac != SJA1105_META_SMAC)
+		return false;
+	if (dmac != SJA1105_META_DMAC)
+		return false;
+	if (ntohs(hdr->h_proto) != ETH_P_SJA1105_META)
+		return false;
+	return true;
+}
+
 /* This is the first time the tagger sees the frame on RX.
- * Figure out if we can decode it, and if we can, annotate skb->cb with how we
- * plan to do that, so we don't need to check again in the rcv function.
+ * Figure out if we can decode it.
  */
 static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev)
 {
+	if (!dsa_port_is_vlan_filtering(dev->dsa_ptr))
+		return true;
 	if (sja1105_is_link_local(skb))
 		return true;
-	if (!dsa_port_is_vlan_filtering(dev->dsa_ptr))
+	if (sja1105_is_meta_frame(skb))
 		return true;
 	return false;
 }
@@ -62,25 +110,152 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
 			     ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
 }
 
+static void sja1105_transfer_meta(struct sk_buff *skb,
+				  const struct sja1105_meta *meta)
+{
+	struct ethhdr *hdr = eth_hdr(skb);
+
+	hdr->h_dest[3] = meta->dmac_byte_3;
+	hdr->h_dest[4] = meta->dmac_byte_4;
+	SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp;
+}
+
+/* This is a simple state machine which follows the hardware mechanism of
+ * generating RX timestamps:
+ *
+ * After each timestampable skb (all traffic for which send_meta1 and
+ * send_meta0 is true, aka all MAC-filtered link-local traffic) a meta frame
+ * containing a partial timestamp is immediately generated by the switch and
+ * sent as a follow-up to the link-local frame on the CPU port.
+ *
+ * The meta frames have no unique identifier (such as sequence number) by which
+ * one may pair them to the correct timestampable frame.
+ * Instead, the switch has internal logic that ensures no frames are sent on
+ * the CPU port between a link-local timestampable frame and its corresponding
+ * meta follow-up. It also ensures strict ordering between ports (lower ports
+ * have higher priority towards the CPU port). For this reason, a per-port
+ * data structure is not needed/desirable.
+ *
+ * This function pairs the link-local frame with its partial timestamp from the
+ * meta follow-up frame. The full timestamp will be reconstructed later in a
+ * work queue.
+ */
+static struct sk_buff
+*sja1105_rcv_meta_state_machine(struct sk_buff *skb,
+				struct sja1105_meta *meta,
+				bool is_link_local,
+				bool is_meta)
+{
+	struct sja1105_port *sp;
+	struct dsa_port *dp;
+
+	dp = dsa_slave_to_port(skb->dev);
+	sp = dp->priv;
+
+	/* Step 1: A timestampable frame was received.
+	 * Buffer it until we get its meta frame.
+	 */
+	if (is_link_local && sp->data->hwts_rx_en) {
+		spin_lock(&sp->data->meta_lock);
+		/* Was this a link-local frame instead of the meta
+		 * that we were expecting?
+		 */
+		if (sp->data->stampable_skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Expected meta frame, is %12llx "
+					    "in the DSA master multicast filter?\n",
+					    SJA1105_META_DMAC);
+		}
+
+		/* Hold a reference to avoid dsa_switch_rcv
+		 * from freeing the skb.
+		 */
+		sp->data->stampable_skb = skb_get(skb);
+		spin_unlock(&sp->data->meta_lock);
+
+		/* Tell DSA we got nothing */
+		return NULL;
+
+	/* Step 2: The meta frame arrived.
+	 * Time to take the stampable skb out of the closet, annotate it
+	 * with the partial timestamp, and pretend that we received it
+	 * just now (basically masquerade the buffered frame as the meta
+	 * frame, which serves no further purpose).
+	 */
+	} else if (is_meta) {
+		struct sk_buff *stampable_skb;
+
+		spin_lock(&sp->data->meta_lock);
+
+		stampable_skb = sp->data->stampable_skb;
+		sp->data->stampable_skb = NULL;
+
+		/* Was this a meta frame instead of the link-local
+		 * that we were expecting?
+		 */
+		if (!stampable_skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Unexpected meta frame\n");
+			spin_unlock(&sp->data->meta_lock);
+			return NULL;
+		}
+
+		if (stampable_skb->dev != skb->dev) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Meta frame on wrong port\n");
+			spin_unlock(&sp->data->meta_lock);
+			return NULL;
+		}
+
+		/* Free the meta frame and give DSA the buffered stampable_skb
+		 * for further processing up the network stack.
+		 */
+		kfree_skb(skb);
+
+		skb = skb_copy(stampable_skb, GFP_ATOMIC);
+		if (!skb) {
+			dev_err_ratelimited(dp->ds->dev,
+					    "Failed to copy stampable skb\n");
+			return NULL;
+		}
+		sja1105_transfer_meta(skb, meta);
+		/* The cached copy will be freed now */
+		skb_unref(stampable_skb);
+
+		spin_unlock(&sp->data->meta_lock);
+	}
+
+	return skb;
+}
+
 static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 				   struct net_device *netdev,
 				   struct packet_type *pt)
 {
-	struct ethhdr *hdr = eth_hdr(skb);
-	u64 source_port, switch_id;
-	struct sk_buff *nskb;
+	struct sja1105_meta meta = {0};
+	int source_port, switch_id;
+	struct vlan_ethhdr *hdr;
 	u16 tpid, vid, tci;
+	bool is_link_local;
 	bool is_tagged;
+	bool is_meta;
 
-	nskb = dsa_8021q_rcv(skb, netdev, pt, &tpid, &tci);
-	is_tagged = (nskb && tpid == ETH_P_SJA1105);
-
-	skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-	vid = tci & VLAN_VID_MASK;
+	hdr = vlan_eth_hdr(skb);
+	tpid = ntohs(hdr->h_vlan_proto);
+	is_tagged = (tpid == ETH_P_SJA1105);
+	is_link_local = sja1105_is_link_local(skb);
+	is_meta = sja1105_is_meta_frame(skb);
 
 	skb->offload_fwd_mark = 1;
 
-	if (sja1105_is_link_local(skb)) {
+	if (is_tagged) {
+		/* Normal traffic path. */
+		tci = ntohs(hdr->h_vlan_TCI);
+		vid = tci & VLAN_VID_MASK;
+		source_port = dsa_8021q_rx_source_port(vid);
+		switch_id = dsa_8021q_rx_switch_id(vid);
+		skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	} else if (is_link_local) {
 		/* Management traffic path. Switch embeds the switch ID and
 		 * port ID into bytes of the destination MAC, courtesy of
 		 * the incl_srcpt options.
@@ -90,10 +265,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 		/* Clear the DMAC bytes that were mangled by the switch */
 		hdr->h_dest[3] = 0;
 		hdr->h_dest[4] = 0;
+	} else if (is_meta) {
+		sja1105_meta_unpack(skb, &meta);
+		source_port = meta.source_port;
+		switch_id = meta.switch_id;
 	} else {
-		/* Normal traffic path. */
-		source_port = dsa_8021q_rx_source_port(vid);
-		switch_id = dsa_8021q_rx_switch_id(vid);
+		return NULL;
 	}
 
 	skb->dev = dsa_master_find_slave(netdev, switch_id, source_port);
@@ -106,10 +283,10 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 	 * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN).
 	 */
 	if (is_tagged)
-		memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - VLAN_HLEN,
-			ETH_HLEN - VLAN_HLEN);
+		skb = dsa_8021q_remove_header(skb);
 
-	return skb;
+	return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local,
+					      is_meta);
 }
 
 static struct dsa_device_ops sja1105_netdev_ops = {