Merge tag 'net-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Quite calm.

  The noisy DSA driver (embedded switches) changes, and adjustment to
  IPv6 IOAM behavior add to diffstat's bottom line but are not scary.

  Current release - regressions:

   - af_unix: rename UNIX-DGRAM to UNIX to maintain backwards
     compatibility

   - procfs: revert "add seq_puts() statement for dev_mcast", minor
     format change broke user space

  Current release - new code bugs:

   - dsa: fix bridge_num not getting cleared after ports leaving the
     bridge, resource leak

   - dsa: tag_dsa: send packets with TX fwd offload from VLAN-unaware
     bridges using VID 0, prevent packet drops if pvid is removed

   - dsa: mv88e6xxx: keep the pvid at 0 when VLAN-unaware, prevent HW
     getting confused about station to VLAN mapping

  Previous releases - regressions:

   - virtio-net: fix for skb_over_panic inside big mode

   - phy: do not shutdown PHYs in READY state

   - dsa: mv88e6xxx: don't use PHY_DETECT on internal PHY's, fix link
     LED staying lit after ifdown

   - mptcp: fix possible infinite wait on recvmsg(MSG_WAITALL)

   - mqprio: Correct stats in mqprio_dump_class_stats()

   - ice: fix deadlock for Tx timestamp tracking flush

   - stmmac: fix feature detection on old hardware

  Previous releases - always broken:

   - sctp: account stream padding length for reconf chunk

   - icmp: fix icmp_ext_echo_iio parsing in icmp_build_probe()

   - isdn: cpai: check ctr->cnr to avoid array index out of bound

   - isdn: mISDN: fix sleeping function called from invalid context

   - nfc: nci: fix potential UAF of rf_conn_info object

   - dsa: microchip: prevent ksz_mib_read_work from kicking back in
     after it's canceled in .remove and crashing

   - dsa: mv88e6xxx: isolate the ATU databases of standalone and bridged
     ports

   - dsa: sja1105, ocelot: break circular dependency between switch and
     tag drivers

   - dsa: felix: improve timestamping in presence of packe loss

   - mlxsw: thermal: fix out-of-bounds memory accesses

  Misc:

   - ipv6: ioam: move the check for undefined bits to improve
     interoperability"

* tag 'net-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (60 commits)
  icmp: fix icmp_ext_echo_iio parsing in icmp_build_probe
  MAINTAINERS: Update the devicetree documentation path of imx fec driver
  sctp: account stream padding length for reconf chunk
  mlxsw: thermal: Fix out-of-bounds memory accesses
  ethernet: s2io: fix setting mac address during resume
  NFC: digital: fix possible memory leak in digital_in_send_sdd_req()
  NFC: digital: fix possible memory leak in digital_tg_listen_mdaa()
  nfc: fix error handling of nfc_proto_register()
  Revert "net: procfs: add seq_puts() statement for dev_mcast"
  net: encx24j600: check error in devm_regmap_init_encx24j600
  net: korina: select CRC32
  net: arc: select CRC32
  net: dsa: felix: break at first CPU port during init and teardown
  net: dsa: tag_ocelot_8021q: fix inability to inject STP BPDUs into BLOCKING ports
  net: dsa: felix: purge skb from TX timestamping queue if it cannot be sent
  net: dsa: tag_ocelot_8021q: break circular dependency with ocelot switch lib
  net: dsa: tag_ocelot: break circular dependency with ocelot switch lib driver
  net: mscc: ocelot: cross-check the sequence id from the timestamp FIFO with the skb PTP header
  net: mscc: ocelot: deny TX timestamping of non-PTP packets
  net: mscc: ocelot: warn when a PTP IRQ is raised for an unknown skb
  ...

2 files changed, 73 insertions, 37 deletions

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 559177e6ded4..a08e4f530c1c 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -472,9 +472,9 @@ void ocelot_phylink_mac_link_down(struct ocelot *ocelot, int port,
 	    !(quirks & OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP))
 		ocelot_port_rmwl(ocelot_port,
 				 DEV_CLOCK_CFG_MAC_TX_RST |
-				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG_MAC_RX_RST,
 				 DEV_CLOCK_CFG_MAC_TX_RST |
-				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG_MAC_RX_RST,
 				 DEV_CLOCK_CFG);
 }
 EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_down);
@@ -569,49 +569,44 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_up);
 
-static void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
-					 struct sk_buff *clone)
+static int ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
+					struct sk_buff *clone)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	unsigned long flags;
+
+	spin_lock_irqsave(&ocelot->ts_id_lock, flags);
 
-	spin_lock(&ocelot_port->ts_id_lock);
+	if (ocelot_port->ptp_skbs_in_flight == OCELOT_MAX_PTP_ID ||
+	    ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) {
+		spin_unlock_irqrestore(&ocelot->ts_id_lock, flags);
+		return -EBUSY;
+	}
 
 	skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
 	/* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */
 	OCELOT_SKB_CB(clone)->ts_id = ocelot_port->ts_id;
-	ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4;
-	skb_queue_tail(&ocelot_port->tx_skbs, clone);
 
-	spin_unlock(&ocelot_port->ts_id_lock);
-}
+	ocelot_port->ts_id++;
+	if (ocelot_port->ts_id == OCELOT_MAX_PTP_ID)
+		ocelot_port->ts_id = 0;
 
-u32 ocelot_ptp_rew_op(struct sk_buff *skb)
-{
-	struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone;
-	u8 ptp_cmd = OCELOT_SKB_CB(skb)->ptp_cmd;
-	u32 rew_op = 0;
+	ocelot_port->ptp_skbs_in_flight++;
+	ocelot->ptp_skbs_in_flight++;
 
-	if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP && clone) {
-		rew_op = ptp_cmd;
-		rew_op |= OCELOT_SKB_CB(clone)->ts_id << 3;
-	} else if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) {
-		rew_op = ptp_cmd;
-	}
+	skb_queue_tail(&ocelot_port->tx_skbs, clone);
 
-	return rew_op;
+	spin_unlock_irqrestore(&ocelot->ts_id_lock, flags);
+
+	return 0;
 }
-EXPORT_SYMBOL(ocelot_ptp_rew_op);
 
-static bool ocelot_ptp_is_onestep_sync(struct sk_buff *skb)
+static bool ocelot_ptp_is_onestep_sync(struct sk_buff *skb,
+				       unsigned int ptp_class)
 {
 	struct ptp_header *hdr;
-	unsigned int ptp_class;
 	u8 msgtype, twostep;
 
-	ptp_class = ptp_classify_raw(skb);
-	if (ptp_class == PTP_CLASS_NONE)
-		return false;
-
 	hdr = ptp_parse_header(skb, ptp_class);
 	if (!hdr)
 		return false;
@@ -631,10 +626,20 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port,
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u8 ptp_cmd = ocelot_port->ptp_cmd;
+	unsigned int ptp_class;
+	int err;
+
+	/* Don't do anything if PTP timestamping not enabled */
+	if (!ptp_cmd)
+		return 0;
+
+	ptp_class = ptp_classify_raw(skb);
+	if (ptp_class == PTP_CLASS_NONE)
+		return -EINVAL;
 
 	/* Store ptp_cmd in OCELOT_SKB_CB(skb)->ptp_cmd */
 	if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) {
-		if (ocelot_ptp_is_onestep_sync(skb)) {
+		if (ocelot_ptp_is_onestep_sync(skb, ptp_class)) {
 			OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd;
 			return 0;
 		}
@@ -648,8 +653,12 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port,
 		if (!(*clone))
 			return -ENOMEM;
 
-		ocelot_port_add_txtstamp_skb(ocelot, port, *clone);
+		err = ocelot_port_add_txtstamp_skb(ocelot, port, *clone);
+		if (err)
+			return err;
+
 		OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd;
+		OCELOT_SKB_CB(*clone)->ptp_class = ptp_class;
 	}
 
 	return 0;
@@ -683,6 +692,17 @@ static void ocelot_get_hwtimestamp(struct ocelot *ocelot,
 	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
 }
 
+static bool ocelot_validate_ptp_skb(struct sk_buff *clone, u16 seqid)
+{
+	struct ptp_header *hdr;
+
+	hdr = ptp_parse_header(clone, OCELOT_SKB_CB(clone)->ptp_class);
+	if (WARN_ON(!hdr))
+		return false;
+
+	return seqid == ntohs(hdr->sequence_id);
+}
+
 void ocelot_get_txtstamp(struct ocelot *ocelot)
 {
 	int budget = OCELOT_PTP_QUEUE_SZ;
@@ -690,10 +710,10 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 	while (budget--) {
 		struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
 		struct skb_shared_hwtstamps shhwtstamps;
+		u32 val, id, seqid, txport;
 		struct ocelot_port *port;
 		struct timespec64 ts;
 		unsigned long flags;
-		u32 val, id, txport;
 
 		val = ocelot_read(ocelot, SYS_PTP_STATUS);
 
@@ -706,10 +726,17 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 		/* Retrieve the ts ID and Tx port */
 		id = SYS_PTP_STATUS_PTP_MESS_ID_X(val);
 		txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val);
+		seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val);
 
-		/* Retrieve its associated skb */
 		port = ocelot->ports[txport];
 
+		spin_lock(&ocelot->ts_id_lock);
+		port->ptp_skbs_in_flight--;
+		ocelot->ptp_skbs_in_flight--;
+		spin_unlock(&ocelot->ts_id_lock);
+
+		/* Retrieve its associated skb */
+try_again:
 		spin_lock_irqsave(&port->tx_skbs.lock, flags);
 
 		skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) {
@@ -722,12 +749,20 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 
 		spin_unlock_irqrestore(&port->tx_skbs.lock, flags);
 
+		if (WARN_ON(!skb_match))
+			continue;
+
+		if (!ocelot_validate_ptp_skb(skb_match, seqid)) {
+			dev_err_ratelimited(ocelot->dev,
+					    "port %d received stale TX timestamp for seqid %d, discarding\n",
+					    txport, seqid);
+			dev_kfree_skb_any(skb);
+			goto try_again;
+		}
+
 		/* Get the h/w timestamp */
 		ocelot_get_hwtimestamp(ocelot, &ts);
 
-		if (unlikely(!skb_match))
-			continue;
-
 		/* Set the timestamp into the skb */
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
@@ -1948,7 +1983,6 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	skb_queue_head_init(&ocelot_port->tx_skbs);
-	spin_lock_init(&ocelot_port->ts_id_lock);
 
 	/* Basic L2 initialization */
 
@@ -2081,6 +2115,7 @@ int ocelot_init(struct ocelot *ocelot)
 	mutex_init(&ocelot->stats_lock);
 	mutex_init(&ocelot->ptp_lock);
 	spin_lock_init(&ocelot->ptp_clock_lock);
+	spin_lock_init(&ocelot->ts_id_lock);
 	snprintf(queue_name, sizeof(queue_name), "%s-stats",
 		 dev_name(ocelot->dev));
 	ocelot->stats_queue = create_singlethread_workqueue(queue_name);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index e54b9fb2a97a..2545727fd5b2 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -8,6 +8,7 @@
  * Copyright 2020-2021 NXP
  */
 
+#include <linux/dsa/ocelot.h>
 #include <linux/if_bridge.h>
 #include <linux/of_net.h>
 #include <linux/phy/phy.h>
@@ -1625,7 +1626,7 @@ static int ocelot_port_phylink_create(struct ocelot *ocelot, int port,
 	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
 		ocelot_port_rmwl(ocelot_port, 0,
 				 DEV_CLOCK_CFG_MAC_TX_RST |
-				 DEV_CLOCK_CFG_MAC_TX_RST,
+				 DEV_CLOCK_CFG_MAC_RX_RST,
 				 DEV_CLOCK_CFG);
 
 	ocelot_port->phy_mode = phy_mode;