Merge branch 'vln-ocelot-fixes'

Vladimir Oltean says:

====================
VLAN fixes for Ocelot driver

This is a collection of patches I've gathered over the past several
months.

Patches 1-6/14 are supporting patches for selftests.

Patch 9/14 fixes PTP TX from a VLAN upper of a VLAN-aware bridge port
when using the "ocelot-8021q" tagging protocol. Patch 7/14 is its
supporting selftest.

Patch 10/14 fixes the QoS class used by PTP in the same case as above.
It is hard to quantify - there is no selftest.

Patch 11/14 fixes potential data corruption during PTP TX in the same
case as above. Again, there is no selftest.

Patch 13/14 fixes RX in the same case as above - 8021q upper of a
VLAN-aware bridge port, with the "ocelot-8021q" tagging protocol. Patch
12/14 is a supporting patch for this in the DSA core, and 7/14 is also
its selftest.

Patch 14/14 ensures that VLAN-aware bridges offloaded to Ocelot only
react to the ETH_P_8021Q TPID, and treat absolutely everything else as
VLAN-untagged, including ETH_P_8021AD. Patch 8/14 is the supporting
selftest.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/dsa/ocelot/felix.c

@@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds,
 	return cpu_dp->index;
 }
 
+/**
+ * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after
+ *				    vlan_filtering change
+ * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed
+ * @vlan_filtering: Current bridge VLAN filtering setting
+ *
+ * Source port identification for tag_8021q is done using VCAP ES0 rules on the
+ * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as
+ * either:
+ * - push_inner_tag=0: the inner tag is never pushed into the frame
+ *		       (and we lose info about the classified VLAN). This is
+ *		       good when the classified VLAN is a discardable quantity
+ *		       for the software RX path: it is either set to
+ *		       OCELOT_STANDALONE_PVID, or to
+ *		       ocelot_vlan_unaware_pvid(bridge).
+ * - push_inner_tag=1: the inner tag is always pushed. This is good when the
+ *		       classified VLAN is not a discardable quantity (the port
+ *		       is under a VLAN-aware bridge, and software needs to
+ *		       continue processing the packet in the same VLAN as the
+ *		       hardware).
+ * The point is that what is good for a VLAN-unaware port is not good for a
+ * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in
+ * sync with the VLAN filtering state of the port.
+ */
+static void
+felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule,
+			       bool vlan_filtering)
+{
+	if (vlan_filtering)
+		outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG;
+	else
+		outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG;
+}
+
 /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that
  * the tagger can perform RX source port identification.
  */
 static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
-				       int upstream, u16 vid)
+				       int upstream, u16 vid,
+				       bool vlan_filtering)
 {
 	struct ocelot_vcap_filter *outer_tagging_rule;
 	struct ocelot *ocelot = ds->priv;
@@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
 	outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD;
 	outer_tagging_rule->action.tag_a_vid_sel = 1;
 	outer_tagging_rule->action.vid_a_val = vid;
+	felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+	outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q;
+	/* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also
+	 * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to
+	 * the classified VID, which we need to see in the DSA tagger's receive
+	 * path. Note: the inner tag is only visible in the packet when pushed
+	 * (push_inner_tag == OCELOT_ES0_TAG).
+	 */
 
 	err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL);
 	if (err)
@@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid)
 static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 				    u16 flags)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_port *cpu_dp;
 	int err;
 
@@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 	 * membership, which we aren't. So we don't need to add any VCAP filter
 	 * for the CPU port.
 	 */
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_port_is_user(dp))
 		return 0;
 
 	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
-		err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+		err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+						  dsa_port_is_vlan_filtering(dp));
 		if (err)
 			return err;
 	}
@@ -258,10 +303,11 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 
 static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_port *cpu_dp;
 	int err;
 
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_port_is_user(dp))
 		return 0;
 
 	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
@@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 
 del_tx_failed:
 	dsa_switch_for_each_cpu_port(cpu_dp, ds)
-		felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+		felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+					    dsa_port_is_vlan_filtering(dp));
 
 	return err;
 }
 
+static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port,
+					   bool vlan_filtering)
+{
+	struct ocelot_vcap_filter *outer_tagging_rule;
+	struct ocelot_vcap_block *block_vcap_es0;
+	struct ocelot *ocelot = ds->priv;
+	struct dsa_port *cpu_dp;
+	unsigned long cookie;
+	int err;
+
+	block_vcap_es0 = &ocelot->block[VCAP_ES0];
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port,
+							  cpu_dp->index);
+
+		outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0,
+									 cookie, false);
+
+		felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+
+		err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int felix_trap_get_cpu_port(struct dsa_switch *ds,
 				   const struct ocelot_vcap_filter *trap)
 {
@@ -528,7 +604,19 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds)
 	 * so we need to be careful that there are no extra frames to be
 	 * dequeued over MMIO, since we would never know to discard them.
 	 */
+	ocelot_lock_xtr_grp_bh(ocelot, 0);
 	ocelot_drain_cpu_queue(ocelot, 0);
+	ocelot_unlock_xtr_grp_bh(ocelot, 0);
+
+	/* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info
+	 * about whether the received packets were VLAN-tagged on the wire,
+	 * since they are always tagged on egress towards the CPU port.
+	 *
+	 * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges,
+	 * we must work around the fallout by untagging in software to make
+	 * untagged reception work more or less as expected.
+	 */
+	ds->untag_vlan_aware_bridge_pvid = true;
 
 	return 0;
 }
@@ -554,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds)
 		ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index);
 
 	dsa_tag_8021q_unregister(ds);
+
+	ds->untag_vlan_aware_bridge_pvid = false;
 }
 
 static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds)
@@ -1008,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 				struct netlink_ext_ack *extack)
 {
 	struct ocelot *ocelot = ds->priv;
+	bool using_tag_8021q;
+	struct felix *felix;
+	int err;
 
-	return ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+	err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+	if (err)
+		return err;
+
+	felix = ocelot_to_felix(ocelot);
+	using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q;
+	if (using_tag_8021q) {
+		err = felix_update_tag_8021q_rx_rules(ds, port, enabled);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int felix_vlan_add(struct dsa_switch *ds, int port,
@@ -1518,6 +1623,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 	int port = xmit_work->dp->index;
 	int retries = 10;
 
+	ocelot_lock_inj_grp(ocelot, 0);
+
 	do {
 		if (ocelot_can_inject(ocelot, 0))
 			break;
@@ -1526,6 +1633,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 	} while (--retries);
 
 	if (!retries) {
+		ocelot_unlock_inj_grp(ocelot, 0);
 		dev_err(ocelot->dev, "port %d failed to inject skb\n",
 			port);
 		ocelot_port_purge_txtstamp_skb(ocelot, port, skb);
@@ -1535,6 +1643,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 
 	ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
 
+	ocelot_unlock_inj_grp(ocelot, 0);
+
 	consume_skb(skb);
 	kfree(xmit_work);
 }
@@ -1694,6 +1804,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
 	if (!felix->info->quirk_no_xtr_irq)
 		return false;
 
+	ocelot_lock_xtr_grp(ocelot, grp);
+
 	while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
 		struct sk_buff *skb;
 		unsigned int type;
@@ -1730,6 +1842,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
 		ocelot_drain_cpu_queue(ocelot, 0);
 	}
 
+	ocelot_unlock_xtr_grp(ocelot, grp);
+
 	return true;
 }
 

drivers/net/ethernet/mscc/ocelot_fdma.c

@@ -665,8 +665,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,
 
 	ifh = skb_push(skb, OCELOT_TAG_LEN);
 	skb_put(skb, ETH_FCS_LEN);
-	memset(ifh, 0, OCELOT_TAG_LEN);
-	ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
+	ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
 
 	return 0;
 }

drivers/net/ethernet/mscc/ocelot_vcap.c

@@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix,
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc);
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc);
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged);
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid);
 	vcap_key_set(vcap, &data, VCAP_IS1_HK_VID,
 		     tag->vid.value, tag->vid.mask);
 	vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP,

drivers/net/ethernet/mscc/ocelot_vsc7514.c

@@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 	struct ocelot *ocelot = arg;
 	int grp = 0, err;
 
+	ocelot_lock_xtr_grp(ocelot, grp);
+
 	while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
 		struct sk_buff *skb;
 
@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 	if (err < 0)
 		ocelot_drain_cpu_queue(ocelot, 0);
 
+	ocelot_unlock_xtr_grp(ocelot, grp);
+
 	return IRQ_HANDLED;
 }
 

include/linux/dsa/ocelot.h

@@ -5,6 +5,8 @@
 #ifndef _NET_DSA_TAG_OCELOT_H
 #define _NET_DSA_TAG_OCELOT_H
 
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/kthread.h>
 #include <linux/packing.h>
 #include <linux/skbuff.h>
@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
 	return rew_op;
 }
 
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+					     struct net_device *br,
+					     u64 *vlan_tci, u64 *tag_type)
+{
+	struct vlan_ethhdr *hdr;
+	u16 proto, tci;
+
+	if (!br || !br_vlan_enabled(br)) {
+		*vlan_tci = 0;
+		*tag_type = IFH_TAG_TYPE_C;
+		return;
+	}
+
+	hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+	br_vlan_get_proto(br, &proto);
+
+	if (ntohs(hdr->h_vlan_proto) == proto) {
+		vlan_remove_tag(skb, &tci);
+		*vlan_tci = tci;
+	} else {
+		rcu_read_lock();
+		br_vlan_get_pvid_rcu(br, &tci);
+		rcu_read_unlock();
+		*vlan_tci = tci;
+	}
+
+	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
 #endif

include/net/dsa.h

@@ -403,14 +403,18 @@ struct dsa_switch {
 	 */
 	u32			configure_vlan_while_not_filtering:1;
 
-	/* If the switch driver always programs the CPU port as egress tagged
-	 * despite the VLAN configuration indicating otherwise, then setting
-	 * @untag_bridge_pvid will force the DSA receive path to pop the
-	 * bridge's default_pvid VLAN tagged frames to offer a consistent
-	 * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge
-	 * device.
+	/* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames.
+	 * DEPRECATED: Do NOT set this field in new drivers. Instead look at
+	 * the dsa_software_vlan_untag() comments.
 	 */
 	u32			untag_bridge_pvid:1;
+	/* Pop the default_pvid of VLAN-aware bridge ports from tagged frames.
+	 * Useful if the switch cannot preserve the VLAN tag as seen on the
+	 * wire for user port ingress, and chooses to send all frames as
+	 * VLAN-tagged to the CPU, including those which were originally
+	 * untagged.
+	 */
+	u32			untag_vlan_aware_bridge_pvid:1;
 
 	/* Let DSA manage the FDB entries towards the
 	 * CPU, based on the software bridge database.

include/soc/mscc/ocelot.h

@@ -813,6 +813,9 @@ struct ocelot {
 	const u32 *const		*map;
 	struct list_head		stats_regions;
 
+	spinlock_t			inj_lock;
+	spinlock_t			xtr_lock;
+
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
 	int				packet_buffer_size;
 	int				num_frame_refs;
@@ -966,10 +969,17 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
 			      u32 val, u32 reg, u32 offset);
 
 /* Packet I/O */
+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp);
 bool ocelot_can_inject(struct ocelot *ocelot, int grp);
 void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 			      u32 rew_op, struct sk_buff *skb);
-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag);
+void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
+			  u32 rew_op, struct sk_buff *skb);
 int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb);
 void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp);
 void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,

include/soc/mscc/ocelot_vcap.h

@@ -13,6 +13,7 @@
  */
 #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port))
 #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port)		(port)
+#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port)		((ocelot)->num_phys_ports + (port))
 #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port)		(port)
 #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port)		((ocelot)->num_phys_ports + (port))
 #define OCELOT_VCAP_IS2_MRP_TRAP(ocelot)			((ocelot)->num_phys_ports * 2)
@@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan {
 	struct ocelot_vcap_u8  pcp;    /* PCP (3 bit) */
 	enum ocelot_vcap_bit dei;    /* DEI */
 	enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */
+	enum ocelot_vcap_bit tpid;
 };
 
 struct ocelot_vcap_key_etype {

net/dsa/tag.c

@@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	p = netdev_priv(skb->dev);
 
-	if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
-		nskb = dsa_untag_bridge_pvid(skb);
+	if (unlikely(cpu_dp->ds->untag_bridge_pvid ||
+		     cpu_dp->ds->untag_vlan_aware_bridge_pvid)) {
+		nskb = dsa_software_vlan_untag(skb);
 		if (!nskb) {
 			kfree_skb(skb);
 			return 0;

net/dsa/tag.h

@@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev,
 	return NULL;
 }
 
-/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged
- * frames as untagged, since the bridge will not untag them.
+/**
+ * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge can process tagged packets. Software like STP/PTP may not. The
+ * bridge can also process untagged packets, to the same effect as if they were
+ * tagged with the PVID of the ingress port. So packets tagged with the PVID of
+ * the bridge port must be software-untagged, to support both use cases.
  */
-static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
+static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb,
+							struct net_device *br,
+							u16 vid)
 {
-	struct dsa_port *dp = dsa_user_to_port(skb->dev);
-	struct net_device *br = dsa_port_bridge_dev_get(dp);
-	struct net_device *dev = skb->dev;
-	struct net_device *upper_dev;
-	u16 vid, pvid, proto;
+	u16 pvid, proto;
 	int err;
 
-	if (!br || br_vlan_enabled(br))
-		return skb;
-
 	err = br_vlan_get_proto(br, &proto);
 	if (err)
-		return skb;
+		return;
 
-	/* Move VLAN tag from data to hwaccel */
-	if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
-		skb = skb_vlan_untag(skb);
-		if (!skb)
-			return NULL;
-	}
+	err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
+	if (err)
+		return;
 
-	if (!skb_vlan_tag_present(skb))
-		return skb;
+	if (vid == pvid && skb->vlan_proto == htons(proto))
+		__vlan_hwaccel_clear_tag(skb);
+}
 
-	vid = skb_vlan_tag_get_id(skb);
+/**
+ * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run
+ * on the plain port, or on a VLAN upper interface). Maybe packets are coming
+ * to software as tagged with a driver-defined VID which is NOT equal to the
+ * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration
+ * should NOT be committed to hardware). DSA needs a method for this private
+ * VID to be communicated by software to it, and if packets are tagged with it,
+ * software-untag them. Note: the private VID may be different per bridge, to
+ * support the FDB isolation use case.
+ *
+ * FIXME: this is currently implemented based on the broken assumption that
+ * the "private VID" used by the driver in VLAN-unaware mode is equal to the
+ * bridge PVID. It should not be, except for a coincidence; the bridge PVID is
+ * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that
+ * this function removes is wrong.
+ *
+ * All users of ds->untag_bridge_pvid should fix their drivers, if necessary,
+ * to make the two independent. Only then, if there still remains a need to
+ * strip the private VID from packets, then a new ds->ops->get_private_vid()
+ * API shall be introduced to communicate to DSA what this VID is, which needs
+ * to be stripped here.
+ */
+static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb,
+							  struct net_device *br,
+							  u16 vid)
+{
+	struct net_device *upper_dev;
+	u16 pvid, proto;
+	int err;
 
-	/* We already run under an RCU read-side critical section since
-	 * we are called from netif_receive_skb_list_internal().
-	 */
-	err = br_vlan_get_pvid_rcu(dev, &pvid);
+	err = br_vlan_get_proto(br, &proto);
 	if (err)
-		return skb;
+		return;
 
-	if (vid != pvid)
-		return skb;
+	err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
+	if (err)
+		return;
+
+	if (vid != pvid || skb->vlan_proto != htons(proto))
+		return;
 
 	/* The sad part about attempting to untag from DSA is that we
 	 * don't know, unless we check, if the skb will end up in
@@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
 	 * definitely keep the tag, to make sure it keeps working.
 	 */
 	upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid);
-	if (upper_dev)
+	if (!upper_dev)
+		__vlan_hwaccel_clear_tag(skb);
+}
+
+/**
+ * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path
+ * @skb: Pointer to socket buffer (packet)
+ *
+ * Receive path method for switches which cannot avoid tagging all packets
+ * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or
+ * ds->untag_vlan_aware_bridge_pvid is set to true.
+ *
+ * As a side effect of this method, any VLAN tag from the skb head is moved
+ * to hwaccel.
+ */
+static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb)
+{
+	struct dsa_port *dp = dsa_user_to_port(skb->dev);
+	struct net_device *br = dsa_port_bridge_dev_get(dp);
+	u16 vid;
+
+	/* software untagging for standalone ports not yet necessary */
+	if (!br)
 		return skb;
 
-	__vlan_hwaccel_clear_tag(skb);
+	/* Move VLAN tag from data to hwaccel */
+	if (!skb_vlan_tag_present(skb)) {
+		skb = skb_vlan_untag(skb);
+		if (!skb)
+			return NULL;
+	}
+
+	if (!skb_vlan_tag_present(skb))
+		return skb;
+
+	vid = skb_vlan_tag_get_id(skb);
+
+	if (br_vlan_enabled(br)) {
+		if (dp->ds->untag_vlan_aware_bridge_pvid)
+			dsa_software_untag_vlan_aware_bridge(skb, br, vid);
+	} else {
+		if (dp->ds->untag_bridge_pvid)
+			dsa_software_untag_vlan_unaware_bridge(skb, br, vid);
+	}
 
 	return skb;
 }

net/dsa/tag_ocelot.c

@@ -8,40 +8,6 @@
 #define OCELOT_NAME	"ocelot"
 #define SEVILLE_NAME	"seville"
 
-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the
- * payload and move it into the DSA tag, which will make the switch classify
- * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
- * which is the pvid of standalone and VLAN-unaware bridge ports.
- */
-static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp,
-				      u64 *vlan_tci, u64 *tag_type)
-{
-	struct net_device *br = dsa_port_bridge_dev_get(dp);
-	struct vlan_ethhdr *hdr;
-	u16 proto, tci;
-
-	if (!br || !br_vlan_enabled(br)) {
-		*vlan_tci = 0;
-		*tag_type = IFH_TAG_TYPE_C;
-		return;
-	}
-
-	hdr = skb_vlan_eth_hdr(skb);
-	br_vlan_get_proto(br, &proto);
-
-	if (ntohs(hdr->h_vlan_proto) == proto) {
-		vlan_remove_tag(skb, &tci);
-		*vlan_tci = tci;
-	} else {
-		rcu_read_lock();
-		br_vlan_get_pvid_rcu(br, &tci);
-		rcu_read_unlock();
-		*vlan_tci = tci;
-	}
-
-	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
-}
-
 static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 			       __be32 ifh_prefix, void **ifh)
 {
@@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 	u32 rew_op = 0;
 	u64 qos_class;
 
-	ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type);
+	ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci,
+				  &tag_type);
 
 	qos_class = netdev_get_num_tc(netdev) ?
 		    netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;

tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh

 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -142,6 +142,58 @@ extern_learn()
 	bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null
 }
 
+other_tpid()
+{
+	local mac=de:ad:be:ef:13:37
+
+	# Test that packets with TPID 802.1ad VID 3 + TPID 802.1Q VID 5 are
+	# classified as untagged by a bridge with vlan_protocol 802.1Q, and
+	# are processed in the PVID of the ingress port (here 1). Not VID 3,
+	# and not VID 5.
+	RET=0
+
+	tc qdisc add dev $h2 clsact
+	tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+		flower dst_mac $mac action drop
+	ip link set $h2 promisc on
+	ethtool -K $h2 rx-vlan-filter off rx-vlan-stag-filter off
+
+	$MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+	sleep 1
+
+	# Match on 'self' addresses as well, for those drivers which
+	# do not push their learned addresses to the bridge software
+	# database
+	bridge -j fdb show $swp1 | \
+		jq -e ".[] | select(.mac == \"$(mac_get $h1)\") | select(.vlan == 1)" &> /dev/null
+	check_err $? "FDB entry was not learned when it should"
+
+	log_test "FDB entry in PVID for VLAN-tagged with other TPID"
+
+	RET=0
+	tc -j -s filter show dev $h2 ingress \
+		| jq -e ".[] | select(.options.handle == 101) \
+		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
+	check_err $? "Packet was not forwarded when it should"
+	log_test "Reception of VLAN with other TPID as untagged"
+
+	bridge vlan del dev $swp1 vid 1
+
+	$MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+	sleep 1
+
+	RET=0
+	tc -j -s filter show dev $h2 ingress \
+		| jq -e ".[] | select(.options.handle == 101) \
+		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
+	check_err $? "Packet was forwarded when should not"
+	log_test "Reception of VLAN with other TPID as untagged (no PVID)"
+
+	bridge vlan add dev $swp1 vid 1 pvid untagged
+	ip link set $h2 promisc off
+	tc qdisc del dev $h2 clsact
+}
+
 trap cleanup EXIT
 
 setup_prepare

tools/testing/selftests/net/forwarding/lib.sh

@@ -500,6 +500,11 @@ check_err_fail()
 	fi
 }
 
+xfail()
+{
+	FAIL_TO_XFAIL=yes "$@"
+}
+
 xfail_on_slow()
 {
 	if [[ $KSFT_MACHINE_SLOW = yes ]]; then
@@ -1113,6 +1118,39 @@ mac_get()
 	ip -j link show dev $if_name | jq -r '.[]["address"]'
 }
 
+ether_addr_to_u64()
+{
+	local addr="$1"
+	local order="$((1 << 40))"
+	local val=0
+	local byte
+
+	addr="${addr//:/ }"
+
+	for byte in $addr; do
+		byte="0x$byte"
+		val=$((val + order * byte))
+		order=$((order >> 8))
+	done
+
+	printf "0x%x" $val
+}
+
+u64_to_ether_addr()
+{
+	local val=$1
+	local byte
+	local i
+
+	for ((i = 40; i >= 0; i -= 8)); do
+		byte=$(((val & (0xff << i)) >> i))
+		printf "%02x" $byte
+		if [ $i -ne 0 ]; then
+			printf ":"
+		fi
+	done
+}
+
 ipv6_lladdr_get()
 {
 	local if_name=$1
@@ -2229,3 +2267,22 @@ absval()
 
 	echo $((v > 0 ? v : -v))
 }
+
+has_unicast_flt()
+{
+	local dev=$1; shift
+	local mac_addr=$(mac_get $dev)
+	local tmp=$(ether_addr_to_u64 $mac_addr)
+	local promisc
+
+	ip link set $dev up
+	ip link add link $dev name macvlan-tmp type macvlan mode private
+	ip link set macvlan-tmp address $(u64_to_ether_addr $((tmp + 1)))
+	ip link set macvlan-tmp up
+
+	promisc=$(ip -j -d link show dev $dev | jq -r '.[].promiscuity')
+
+	ip link del macvlan-tmp
+
+	[[ $promisc == 1 ]] && echo "no" || echo "yes"
+}