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
  ...

7 files changed, 83 insertions, 40 deletions

diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 548285539752..d8ee15f1c7a9 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -101,8 +101,6 @@ config NET_DSA_TAG_RTL4_A
 
 config NET_DSA_TAG_OCELOT
 	tristate "Tag driver for Ocelot family of switches, using NPI port"
-	depends on MSCC_OCELOT_SWITCH_LIB || \
-		   (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST)
 	select PACKING
 	help
 	  Say Y or M if you want to enable NPI tagging for the Ocelot switches
@@ -114,8 +112,6 @@ config NET_DSA_TAG_OCELOT
 
 config NET_DSA_TAG_OCELOT_8021Q
 	tristate "Tag driver for Ocelot family of switches, using VLAN"
-	depends on MSCC_OCELOT_SWITCH_LIB || \
-	          (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST)
 	help
 	  Say Y or M if you want to enable support for tagging frames with a
 	  custom VLAN-based header. Frames that require timestamping, such as
@@ -138,7 +134,6 @@ config NET_DSA_TAG_LAN9303
 
 config NET_DSA_TAG_SJA1105
 	tristate "Tag driver for NXP SJA1105 switches"
-	depends on NET_DSA_SJA1105 || !NET_DSA_SJA1105
 	select PACKING
 	help
 	  Say Y or M if you want to enable support for tagging frames with the
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index b29262eee00b..da18094b5a04 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -170,7 +170,7 @@ void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num)
 	/* Check if the bridge is still in use, otherwise it is time
 	 * to clean it up so we can reuse this bridge_num later.
 	 */
-	if (!dsa_bridge_num_find(bridge_dev))
+	if (dsa_bridge_num_find(bridge_dev) < 0)
 		clear_bit(bridge_num, &dsa_fwd_offloading_bridges);
 }
 
@@ -811,7 +811,9 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds)
 		if (!dsa_is_cpu_port(ds, port))
 			continue;
 
+		rtnl_lock();
 		err = ds->ops->change_tag_protocol(ds, port, tag_ops->proto);
+		rtnl_unlock();
 		if (err) {
 			dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n",
 				tag_ops->name, ERR_PTR(err));
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 1c797ec8e2c2..6466d0539af9 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -168,7 +168,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 		if (extack._msg)
 			dev_err(ds->dev, "port %d: %s\n", info->port,
 				extack._msg);
-		if (err && err != EOPNOTSUPP)
+		if (err && err != -EOPNOTSUPP)
 			return err;
 	}
 
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index e5127b7d1c6a..b3da4b2ea11c 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -45,6 +45,7 @@
  *   6    6       2        2      4    2       N
  */
 
+#include <linux/dsa/mv88e6xxx.h>
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
@@ -129,12 +130,9 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
 	u8 tag_dev, tag_port;
 	enum dsa_cmd cmd;
 	u8 *dsa_header;
-	u16 pvid = 0;
-	int err;
 
 	if (skb->offload_fwd_mark) {
 		struct dsa_switch_tree *dst = dp->ds->dst;
-		struct net_device *br = dp->bridge_dev;
 
 		cmd = DSA_CMD_FORWARD;
 
@@ -144,19 +142,6 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
 		 */
 		tag_dev = dst->last_switch + 1 + dp->bridge_num;
 		tag_port = 0;
-
-		/* If we are offloading forwarding for a VLAN-unaware bridge,
-		 * inject packets to hardware using the bridge's pvid, since
-		 * that's where the packets ingressed from.
-		 */
-		if (!br_vlan_enabled(br)) {
-			/* Safe because __dev_queue_xmit() runs under
-			 * rcu_read_lock_bh()
-			 */
-			err = br_vlan_get_pvid_rcu(br, &pvid);
-			if (err)
-				return NULL;
-		}
 	} else {
 		cmd = DSA_CMD_FROM_CPU;
 		tag_dev = dp->ds->index;
@@ -180,16 +165,21 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
 			dsa_header[2] &= ~0x10;
 		}
 	} else {
+		struct net_device *br = dp->bridge_dev;
+		u16 vid;
+
+		vid = br ? MV88E6XXX_VID_BRIDGED : MV88E6XXX_VID_STANDALONE;
+
 		skb_push(skb, DSA_HLEN + extra);
 		dsa_alloc_etype_header(skb, DSA_HLEN + extra);
 
-		/* Construct untagged DSA tag. */
+		/* Construct DSA header from untagged frame. */
 		dsa_header = dsa_etype_header_pos_tx(skb) + extra;
 
 		dsa_header[0] = (cmd << 6) | tag_dev;
 		dsa_header[1] = tag_port << 3;
-		dsa_header[2] = pvid >> 8;
-		dsa_header[3] = pvid & 0xff;
+		dsa_header[2] = vid >> 8;
+		dsa_header[3] = vid & 0xff;
 	}
 
 	return skb;
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index 8025ed778d33..605b51ca6921 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -2,7 +2,6 @@
 /* Copyright 2019 NXP
  */
 #include <linux/dsa/ocelot.h>
-#include <soc/mscc/ocelot.h>
 #include "dsa_priv.h"
 
 static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c
index 59072930cb02..3412051981d7 100644
--- a/net/dsa/tag_ocelot_8021q.c
+++ b/net/dsa/tag_ocelot_8021q.c
@@ -9,10 +9,32 @@
  *   that on egress
  */
 #include <linux/dsa/8021q.h>
-#include <soc/mscc/ocelot.h>
-#include <soc/mscc/ocelot_ptp.h>
+#include <linux/dsa/ocelot.h>
 #include "dsa_priv.h"
 
+static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp,
+					 struct sk_buff *skb)
+{
+	struct felix_deferred_xmit_work *xmit_work;
+	struct felix_port *felix_port = dp->priv;
+
+	xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC);
+	if (!xmit_work)
+		return NULL;
+
+	/* Calls felix_port_deferred_xmit in felix.c */
+	kthread_init_work(&xmit_work->work, felix_port->xmit_work_fn);
+	/* Increase refcount so the kfree_skb in dsa_slave_xmit
+	 * won't really free the packet.
+	 */
+	xmit_work->dp = dp;
+	xmit_work->skb = skb_get(skb);
+
+	kthread_queue_work(felix_port->xmit_worker, &xmit_work->work);
+
+	return NULL;
+}
+
 static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 				   struct net_device *netdev)
 {
@@ -20,18 +42,10 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
 	u16 queue_mapping = skb_get_queue_mapping(skb);
 	u8 pcp = netdev_txq_to_tc(netdev, queue_mapping);
-	struct ocelot *ocelot = dp->ds->priv;
-	int port = dp->index;
-	u32 rew_op = 0;
+	struct ethhdr *hdr = eth_hdr(skb);
 
-	rew_op = ocelot_ptp_rew_op(skb);
-	if (rew_op) {
-		if (!ocelot_can_inject(ocelot, 0))
-			return NULL;
-
-		ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
-		return NULL;
-	}
+	if (ocelot_ptp_rew_op(skb) || is_link_local_ether_addr(hdr->h_dest))
+		return ocelot_defer_xmit(dp, skb);
 
 	return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q,
 			      ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index c054f48541c8..2edede9ddac9 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -4,6 +4,7 @@
 #include <linux/if_vlan.h>
 #include <linux/dsa/sja1105.h>
 #include <linux/dsa/8021q.h>
+#include <linux/skbuff.h>
 #include <linux/packing.h>
 #include "dsa_priv.h"
 
@@ -53,6 +54,11 @@
 #define SJA1110_TX_TRAILER_LEN			4
 #define SJA1110_MAX_PADDING_LEN			15
 
+enum sja1110_meta_tstamp {
+	SJA1110_META_TSTAMP_TX = 0,
+	SJA1110_META_TSTAMP_RX = 1,
+};
+
 /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */
 static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 {
@@ -520,6 +526,43 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 					      is_meta);
 }
 
+static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port,
+					u8 ts_id, enum sja1110_meta_tstamp dir,
+					u64 tstamp)
+{
+	struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct skb_shared_hwtstamps shwt = {0};
+	struct sja1105_port *sp = dp->priv;
+
+	if (!dsa_port_is_sja1105(dp))
+		return;
+
+	/* We don't care about RX timestamps on the CPU port */
+	if (dir == SJA1110_META_TSTAMP_RX)
+		return;
+
+	spin_lock(&sp->data->skb_txtstamp_queue.lock);
+
+	skb_queue_walk_safe(&sp->data->skb_txtstamp_queue, skb, skb_tmp) {
+		if (SJA1105_SKB_CB(skb)->ts_id != ts_id)
+			continue;
+
+		__skb_unlink(skb, &sp->data->skb_txtstamp_queue);
+		skb_match = skb;
+
+		break;
+	}
+
+	spin_unlock(&sp->data->skb_txtstamp_queue.lock);
+
+	if (WARN_ON(!skb_match))
+		return;
+
+	shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp));
+	skb_complete_tx_timestamp(skb_match, &shwt);
+}
+
 static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header)
 {
 	u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN;