net: dsa: sja1105: implement TX timestamping for SJA1110

The TX timestamping procedure for SJA1105 is a bit unconventional
because the transmit procedure itself is unconventional.

Control packets (and therefore PTP as well) are transmitted to a
specific port in SJA1105 using "management routes" which must be written
over SPI to the switch. These are one-shot rules that match by
destination MAC address on traffic coming from the CPU port, and select
the precise destination port for that packet. So to transmit a packet
from NET_TX softirq context, we actually need to defer to a process
context so that we can perform that SPI write before we send the packet.
The DSA master dev_queue_xmit() runs in process context, and we poll
until the switch confirms it took the TX timestamp, then we annotate the
skb clone with that TX timestamp. This is why the sja1105 driver does
not need an skb queue for TX timestamping.

But the SJA1110 is a bit (not much!) more conventional, and you can
request 2-step TX timestamping through the DSA header, as well as give
the switch a cookie (timestamp ID) which it will give back to you when
it has the timestamp. So now we do need a queue for keeping the skb
clones until their TX timestamps become available.

The interesting part is that the metadata frames from SJA1105 haven't
disappeared completely. On SJA1105 they were used as follow-ups which
contained RX timestamps, but on SJA1110 they are actually TX completion
packets, which contain a variable (up to 32) array of timestamps.
Why an array? Because:
- not only is the TX timestamp on the egress port being communicated,
  but also the RX timestamp on the CPU port. Nice, but we don't care
  about that, so we ignore it.
- because a packet could be multicast to multiple egress ports, each
  port takes its own timestamp, and the TX completion packet contains
  the individual timestamps on each port.

This is unconventional because switches typically have a timestamping
FIFO and raise an interrupt, but this one doesn't. So the tagger needs
to detect and parse meta frames, and call into the main switch driver,
which pairs the timestamps with the skbs in the TX timestamping queue
which are waiting for one.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 52 insertions, 0 deletions

diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 37e1d64e07c6..9c2df9ece01b 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -25,6 +25,9 @@
 #define SJA1110_RX_TRAILER_SWITCH_ID(x)		(((x) & GENMASK(7, 4)) >> 4)
 #define SJA1110_RX_TRAILER_SRC_PORT(x)		((x) & GENMASK(3, 0))
 
+/* Meta frame format (for 2-step TX timestamps) */
+#define SJA1110_RX_HEADER_N_TS(x)		(((x) & GENMASK(8, 4)) >> 4)
+
 /* TX header */
 #define SJA1110_TX_HEADER_UPDATE_TC		BIT(14)
 #define SJA1110_TX_HEADER_TAKE_TS		BIT(13)
@@ -43,6 +46,8 @@
 #define SJA1110_TX_TRAILER_SWITCHID(x)		(((x) << 12) & GENMASK(15, 12))
 #define SJA1110_TX_TRAILER_DESTPORTS(x)		(((x) << 1) & GENMASK(11, 1))
 
+#define SJA1110_META_TSTAMP_SIZE		10
+
 #define SJA1110_HEADER_LEN			4
 #define SJA1110_RX_TRAILER_LEN			13
 #define SJA1110_TX_TRAILER_LEN			4
@@ -184,6 +189,7 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
 static struct sk_buff *sja1110_xmit(struct sk_buff *skb,
 				    struct net_device *netdev)
 {
+	struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone;
 	struct dsa_port *dp = dsa_slave_to_port(netdev);
 	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
 	u16 queue_mapping = skb_get_queue_mapping(skb);
@@ -221,6 +227,12 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb,
 	*tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) |
 				  SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) |
 				  SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index)));
+	if (clone) {
+		u8 ts_id = SJA1105_SKB_CB(clone)->ts_id;
+
+		*tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS);
+		*tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id));
+	}
 
 	return skb;
 }
@@ -423,6 +435,43 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 					      is_meta);
 }
 
+static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header)
+{
+	int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header);
+	int n_ts = SJA1110_RX_HEADER_N_TS(rx_header);
+	struct net_device *master = skb->dev;
+	struct dsa_port *cpu_dp;
+	u8 *buf = skb->data + 2;
+	struct dsa_switch *ds;
+	int i;
+
+	cpu_dp = master->dsa_ptr;
+	ds = dsa_switch_find(cpu_dp->dst->index, switch_id);
+	if (!ds) {
+		net_err_ratelimited("%s: cannot find switch id %d\n",
+				    master->name, switch_id);
+		return NULL;
+	}
+
+	for (i = 0; i <= n_ts; i++) {
+		u8 ts_id, source_port, dir;
+		u64 tstamp;
+
+		ts_id = buf[0];
+		source_port = (buf[1] & GENMASK(7, 4)) >> 4;
+		dir = (buf[1] & BIT(3)) >> 3;
+		tstamp = be64_to_cpu(*(__be64 *)(buf + 2));
+
+		sja1110_process_meta_tstamp(ds, source_port, ts_id, dir,
+					    tstamp);
+
+		buf += SJA1110_META_TSTAMP_SIZE;
+	}
+
+	/* Discard the meta frame, we've consumed the timestamps it contained */
+	return NULL;
+}
+
 static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb,
 							    int *source_port,
 							    int *switch_id)
@@ -439,6 +488,9 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb,
 	 */
 	rx_header = ntohs(*(__be16 *)skb->data);
 
+	if (rx_header & SJA1110_RX_HEADER_IS_METADATA)
+		return sja1110_rcv_meta(skb, rx_header);
+
 	/* Timestamp frame, we have a trailer */
 	if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) {
 		int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header);