Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 890 insertions, 0 deletions

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
new file mode 100644
index 000000000..990c6b38f
--- /dev/null
+++ b/net/bridge/br_switchdev.c
@@ -0,0 +1,890 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/switchdev.h>
+
+#include "br_private.h"
+
+static struct static_key_false br_switchdev_tx_fwd_offload;
+
+static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p,
+					     const struct sk_buff *skb)
+{
+	if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload))
+		return false;
+
+	if (br_multicast_igmp_type(skb))
+		return false;
+
+	return test_bit(BR_TX_FWD_OFFLOAD_BIT, &p->flags) &&
+	       (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom);
+}
+
+bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb)
+{
+	if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload))
+		return false;
+
+	return BR_INPUT_SKB_CB(skb)->tx_fwd_offload;
+}
+
+void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb)
+{
+	skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb);
+}
+
+/* Mark the frame for TX forwarding offload if this egress port supports it */
+void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p,
+					     struct sk_buff *skb)
+{
+	if (nbp_switchdev_can_offload_tx_fwd(p, skb))
+		BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true;
+}
+
+/* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms
+ * that the skb has been already forwarded to, to avoid further cloning to
+ * other ports in the same hwdom by making nbp_switchdev_allowed_egress()
+ * return false.
+ */
+void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p,
+					      struct sk_buff *skb)
+{
+	if (nbp_switchdev_can_offload_tx_fwd(p, skb))
+		set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms);
+}
+
+void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
+			      struct sk_buff *skb)
+{
+	if (p->hwdom)
+		BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom;
+}
+
+bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
+				  const struct sk_buff *skb)
+{
+	struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb);
+
+	return !test_bit(p->hwdom, &cb->fwd_hwdoms) &&
+		(!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom);
+}
+
+/* Flags that can be offloaded to hardware */
+#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | BR_PORT_MAB | \
+				  BR_MCAST_FLOOD | BR_BCAST_FLOOD | BR_PORT_LOCKED | \
+				  BR_HAIRPIN_MODE | BR_ISOLATED | BR_MULTICAST_TO_UNICAST)
+
+int br_switchdev_set_port_flag(struct net_bridge_port *p,
+			       unsigned long flags,
+			       unsigned long mask,
+			       struct netlink_ext_ack *extack)
+{
+	struct switchdev_attr attr = {
+		.orig_dev = p->dev,
+	};
+	struct switchdev_notifier_port_attr_info info = {
+		.attr = &attr,
+	};
+	int err;
+
+	mask &= BR_PORT_FLAGS_HW_OFFLOAD;
+	if (!mask)
+		return 0;
+
+	attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS;
+	attr.u.brport_flags.val = flags;
+	attr.u.brport_flags.mask = mask;
+
+	err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev,
+				       &info.info, extack);
+	err = notifier_to_errno(err);
+	if (err == -EOPNOTSUPP)
+		return 0;
+
+	if (err) {
+		NL_SET_ERR_MSG_WEAK_MOD(extack,
+					"bridge flag offload is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
+	attr.flags = SWITCHDEV_F_DEFER;
+
+	err = switchdev_port_attr_set(p->dev, &attr, extack);
+	if (err) {
+		NL_SET_ERR_MSG_WEAK_MOD(extack,
+					"error setting offload flag on port");
+		return err;
+	}
+
+	return 0;
+}
+
+static void br_switchdev_fdb_populate(struct net_bridge *br,
+				      struct switchdev_notifier_fdb_info *item,
+				      const struct net_bridge_fdb_entry *fdb,
+				      const void *ctx)
+{
+	const struct net_bridge_port *p = READ_ONCE(fdb->dst);
+
+	item->addr = fdb->key.addr.addr;
+	item->vid = fdb->key.vlan_id;
+	item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+	item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags);
+	item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags);
+	item->locked = false;
+	item->info.dev = (!p || item->is_local) ? br->dev : p->dev;
+	item->info.ctx = ctx;
+}
+
+void
+br_switchdev_fdb_notify(struct net_bridge *br,
+			const struct net_bridge_fdb_entry *fdb, int type)
+{
+	struct switchdev_notifier_fdb_info item;
+
+	if (test_bit(BR_FDB_LOCKED, &fdb->flags))
+		return;
+
+	/* Entries with these flags were created using ndm_state == NUD_REACHABLE,
+	 * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something
+	 * equivalent to 'bridge fdb add ... master dynamic (sticky)'.
+	 * Drivers don't know how to deal with these, so don't notify them to
+	 * avoid confusing them.
+	 */
+	if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) &&
+	    !test_bit(BR_FDB_STATIC, &fdb->flags) &&
+	    !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags))
+		return;
+
+	br_switchdev_fdb_populate(br, &item, fdb, NULL);
+
+	switch (type) {
+	case RTM_DELNEIGH:
+		call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE,
+					 item.info.dev, &item.info, NULL);
+		break;
+	case RTM_NEWNEIGH:
+		call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE,
+					 item.info.dev, &item.info, NULL);
+		break;
+	}
+}
+
+int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
+			       bool changed, struct netlink_ext_ack *extack)
+{
+	struct switchdev_obj_port_vlan v = {
+		.obj.orig_dev = dev,
+		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+		.flags = flags,
+		.vid = vid,
+		.changed = changed,
+	};
+
+	return switchdev_port_obj_add(dev, &v.obj, extack);
+}
+
+int br_switchdev_port_vlan_no_foreign_add(struct net_device *dev, u16 vid, u16 flags,
+					  bool changed, struct netlink_ext_ack *extack)
+{
+	struct switchdev_obj_port_vlan v = {
+		.obj.orig_dev = dev,
+		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+		.obj.flags = SWITCHDEV_F_NO_FOREIGN,
+		.flags = flags,
+		.vid = vid,
+		.changed = changed,
+	};
+
+	return switchdev_port_obj_add(dev, &v.obj, extack);
+}
+
+int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
+{
+	struct switchdev_obj_port_vlan v = {
+		.obj.orig_dev = dev,
+		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+		.vid = vid,
+	};
+
+	return switchdev_port_obj_del(dev, &v.obj);
+}
+
+static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining)
+{
+	struct net_bridge *br = joining->br;
+	struct net_bridge_port *p;
+	int hwdom;
+
+	/* joining is yet to be added to the port list. */
+	list_for_each_entry(p, &br->port_list, list) {
+		if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) {
+			joining->hwdom = p->hwdom;
+			return 0;
+		}
+	}
+
+	hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1);
+	if (hwdom >= BR_HWDOM_MAX)
+		return -EBUSY;
+
+	set_bit(hwdom, &br->busy_hwdoms);
+	joining->hwdom = hwdom;
+	return 0;
+}
+
+static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving)
+{
+	struct net_bridge *br = leaving->br;
+	struct net_bridge_port *p;
+
+	/* leaving is no longer in the port list. */
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->hwdom == leaving->hwdom)
+			return;
+	}
+
+	clear_bit(leaving->hwdom, &br->busy_hwdoms);
+}
+
+static int nbp_switchdev_add(struct net_bridge_port *p,
+			     struct netdev_phys_item_id ppid,
+			     bool tx_fwd_offload,
+			     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (p->offload_count) {
+		/* Prevent unsupported configurations such as a bridge port
+		 * which is a bonding interface, and the member ports are from
+		 * different hardware switches.
+		 */
+		if (!netdev_phys_item_id_same(&p->ppid, &ppid)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Same bridge port cannot be offloaded by two physical switches");
+			return -EBUSY;
+		}
+
+		/* Tolerate drivers that call switchdev_bridge_port_offload()
+		 * more than once for the same bridge port, such as when the
+		 * bridge port is an offloaded bonding/team interface.
+		 */
+		p->offload_count++;
+
+		return 0;
+	}
+
+	p->ppid = ppid;
+	p->offload_count = 1;
+
+	err = nbp_switchdev_hwdom_set(p);
+	if (err)
+		return err;
+
+	if (tx_fwd_offload) {
+		set_bit(BR_TX_FWD_OFFLOAD_BIT, &p->flags);
+		static_branch_inc(&br_switchdev_tx_fwd_offload);
+	}
+
+	return 0;
+}
+
+static void nbp_switchdev_del(struct net_bridge_port *p)
+{
+	if (WARN_ON(!p->offload_count))
+		return;
+
+	p->offload_count--;
+
+	if (p->offload_count)
+		return;
+
+	if (p->hwdom)
+		nbp_switchdev_hwdom_put(p);
+
+	if (test_bit(BR_TX_FWD_OFFLOAD_BIT, &p->flags)) {
+		clear_bit(BR_TX_FWD_OFFLOAD_BIT, &p->flags);
+		static_branch_dec(&br_switchdev_tx_fwd_offload);
+	}
+}
+
+static int
+br_switchdev_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb,
+			    const struct net_bridge_fdb_entry *fdb,
+			    unsigned long action, const void *ctx)
+{
+	struct switchdev_notifier_fdb_info item;
+	int err;
+
+	br_switchdev_fdb_populate(br, &item, fdb, ctx);
+
+	err = nb->notifier_call(nb, action, &item);
+	return notifier_to_errno(err);
+}
+
+static int
+br_switchdev_fdb_replay(const struct net_device *br_dev, const void *ctx,
+			bool adding, struct notifier_block *nb)
+{
+	struct net_bridge_fdb_entry *fdb;
+	struct net_bridge *br;
+	unsigned long action;
+	int err = 0;
+
+	if (!nb)
+		return 0;
+
+	if (!netif_is_bridge_master(br_dev))
+		return -EINVAL;
+
+	br = netdev_priv(br_dev);
+
+	if (adding)
+		action = SWITCHDEV_FDB_ADD_TO_DEVICE;
+	else
+		action = SWITCHDEV_FDB_DEL_TO_DEVICE;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) {
+		err = br_switchdev_fdb_replay_one(br, nb, fdb, action, ctx);
+		if (err)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	return err;
+}
+
+static int br_switchdev_vlan_attr_replay(struct net_device *br_dev,
+					 const void *ctx,
+					 struct notifier_block *nb,
+					 struct netlink_ext_ack *extack)
+{
+	struct switchdev_notifier_port_attr_info attr_info = {
+		.info = {
+			.dev = br_dev,
+			.extack = extack,
+			.ctx = ctx,
+		},
+	};
+	struct net_bridge *br = netdev_priv(br_dev);
+	struct net_bridge_vlan_group *vg;
+	struct switchdev_attr attr;
+	struct net_bridge_vlan *v;
+	int err;
+
+	attr_info.attr = &attr;
+	attr.orig_dev = br_dev;
+
+	vg = br_vlan_group(br);
+	if (!vg)
+		return 0;
+
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (v->msti) {
+			attr.id = SWITCHDEV_ATTR_ID_VLAN_MSTI;
+			attr.u.vlan_msti.vid = v->vid;
+			attr.u.vlan_msti.msti = v->msti;
+
+			err = nb->notifier_call(nb, SWITCHDEV_PORT_ATTR_SET,
+						&attr_info);
+			err = notifier_to_errno(err);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int
+br_switchdev_vlan_replay_one(struct notifier_block *nb,
+			     struct net_device *dev,
+			     struct switchdev_obj_port_vlan *vlan,
+			     const void *ctx, unsigned long action,
+			     struct netlink_ext_ack *extack)
+{
+	struct switchdev_notifier_port_obj_info obj_info = {
+		.info = {
+			.dev = dev,
+			.extack = extack,
+			.ctx = ctx,
+		},
+		.obj = &vlan->obj,
+	};
+	int err;
+
+	err = nb->notifier_call(nb, action, &obj_info);
+	return notifier_to_errno(err);
+}
+
+static int br_switchdev_vlan_replay_group(struct notifier_block *nb,
+					  struct net_device *dev,
+					  struct net_bridge_vlan_group *vg,
+					  const void *ctx, unsigned long action,
+					  struct netlink_ext_ack *extack)
+{
+	struct net_bridge_vlan *v;
+	int err = 0;
+	u16 pvid;
+
+	if (!vg)
+		return 0;
+
+	pvid = br_get_pvid(vg);
+
+	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		struct switchdev_obj_port_vlan vlan = {
+			.obj.orig_dev = dev,
+			.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+			.flags = br_vlan_flags(v, pvid),
+			.vid = v->vid,
+		};
+
+		if (!br_vlan_should_use(v))
+			continue;
+
+		err = br_switchdev_vlan_replay_one(nb, dev, &vlan, ctx,
+						   action, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int br_switchdev_vlan_replay(struct net_device *br_dev,
+				    const void *ctx, bool adding,
+				    struct notifier_block *nb,
+				    struct netlink_ext_ack *extack)
+{
+	struct net_bridge *br = netdev_priv(br_dev);
+	struct net_bridge_port *p;
+	unsigned long action;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!nb)
+		return 0;
+
+	if (!netif_is_bridge_master(br_dev))
+		return -EINVAL;
+
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	err = br_switchdev_vlan_replay_group(nb, br_dev, br_vlan_group(br),
+					     ctx, action, extack);
+	if (err)
+		return err;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		struct net_device *dev = p->dev;
+
+		err = br_switchdev_vlan_replay_group(nb, dev,
+						     nbp_vlan_group(p),
+						     ctx, action, extack);
+		if (err)
+			return err;
+	}
+
+	if (adding) {
+		err = br_switchdev_vlan_attr_replay(br_dev, ctx, nb, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+struct br_switchdev_mdb_complete_info {
+	struct net_bridge_port *port;
+	struct br_ip ip;
+};
+
+static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *priv)
+{
+	struct br_switchdev_mdb_complete_info *data = priv;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port *port = data->port;
+	struct net_bridge *br = port->br;
+	u8 old_flags;
+
+	if (err == -EOPNOTSUPP)
+		goto out_free;
+
+	spin_lock_bh(&br->multicast_lock);
+	mp = br_mdb_ip_get(br, &data->ip);
+	if (!mp)
+		goto out;
+	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (p->key.port != port)
+			continue;
+
+		old_flags = p->flags;
+		br_multicast_set_pg_offload_flags(p, !err);
+		if (br_mdb_should_notify(br, old_flags ^ p->flags))
+			br_mdb_flag_change_notify(br->dev, mp, p);
+	}
+out:
+	spin_unlock_bh(&br->multicast_lock);
+out_free:
+	kfree(priv);
+}
+
+static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb,
+				      const struct net_bridge_mdb_entry *mp)
+{
+	if (mp->addr.proto == htons(ETH_P_IP))
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (mp->addr.proto == htons(ETH_P_IPV6))
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr);
+#endif
+	else
+		ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr);
+
+	mdb->vid = mp->addr.vid;
+}
+
+static void br_switchdev_host_mdb_one(struct net_device *dev,
+				      struct net_device *lower_dev,
+				      struct net_bridge_mdb_entry *mp,
+				      int type)
+{
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_ID_HOST_MDB,
+			.flags = SWITCHDEV_F_DEFER,
+			.orig_dev = dev,
+		},
+	};
+
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	switch (type) {
+	case RTM_NEWMDB:
+		switchdev_port_obj_add(lower_dev, &mdb.obj, NULL);
+		break;
+	case RTM_DELMDB:
+		switchdev_port_obj_del(lower_dev, &mdb.obj);
+		break;
+	}
+}
+
+static void br_switchdev_host_mdb(struct net_device *dev,
+				  struct net_bridge_mdb_entry *mp, int type)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter)
+		br_switchdev_host_mdb_one(dev, lower_dev, mp, type);
+}
+
+static int
+br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
+			    const struct switchdev_obj_port_mdb *mdb,
+			    unsigned long action, const void *ctx,
+			    struct netlink_ext_ack *extack)
+{
+	struct switchdev_notifier_port_obj_info obj_info = {
+		.info = {
+			.dev = dev,
+			.extack = extack,
+			.ctx = ctx,
+		},
+		.obj = &mdb->obj,
+	};
+	int err;
+
+	err = nb->notifier_call(nb, action, &obj_info);
+	return notifier_to_errno(err);
+}
+
+static int br_switchdev_mdb_queue_one(struct list_head *mdb_list,
+				      struct net_device *dev,
+				      unsigned long action,
+				      enum switchdev_obj_id id,
+				      const struct net_bridge_mdb_entry *mp,
+				      struct net_device *orig_dev)
+{
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = id,
+			.orig_dev = orig_dev,
+		},
+	};
+	struct switchdev_obj_port_mdb *pmdb;
+
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	if (action == SWITCHDEV_PORT_OBJ_ADD &&
+	    switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) {
+		/* This event is already in the deferred queue of
+		 * events, so this replay must be elided, lest the
+		 * driver receives duplicate events for it. This can
+		 * only happen when replaying additions, since
+		 * modifications are always immediately visible in
+		 * br->mdb_list, whereas actual event delivery may be
+		 * delayed.
+		 */
+		return 0;
+	}
+
+	pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC);
+	if (!pmdb)
+		return -ENOMEM;
+
+	list_add_tail(&pmdb->obj.list, mdb_list);
+	return 0;
+}
+
+void br_switchdev_mdb_notify(struct net_device *dev,
+			     struct net_bridge_mdb_entry *mp,
+			     struct net_bridge_port_group *pg,
+			     int type)
+{
+	struct br_switchdev_mdb_complete_info *complete_info;
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_ID_PORT_MDB,
+			.flags = SWITCHDEV_F_DEFER,
+		},
+	};
+
+	if (!pg)
+		return br_switchdev_host_mdb(dev, mp, type);
+
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	mdb.obj.orig_dev = pg->key.port->dev;
+	switch (type) {
+	case RTM_NEWMDB:
+		complete_info = kmalloc_obj(*complete_info, GFP_ATOMIC);
+		if (!complete_info)
+			break;
+		complete_info->port = pg->key.port;
+		complete_info->ip = mp->addr;
+		mdb.obj.complete_priv = complete_info;
+		mdb.obj.complete = br_switchdev_mdb_complete;
+		if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
+			kfree(complete_info);
+		break;
+	case RTM_DELMDB:
+		switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
+		break;
+	}
+}
+#endif
+
+static int
+br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev,
+			const void *ctx, bool adding, struct notifier_block *nb,
+			struct netlink_ext_ack *extack)
+{
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	const struct net_bridge_mdb_entry *mp;
+	struct switchdev_obj *obj, *tmp;
+	struct net_bridge *br;
+	unsigned long action;
+	LIST_HEAD(mdb_list);
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	if (!nb)
+		return 0;
+
+	if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev))
+		return -EINVAL;
+
+	br = netdev_priv(br_dev);
+
+	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		return 0;
+
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	/* br_switchdev_mdb_queue_one() will take care to not queue a
+	 * replay of an event that is already pending in the switchdev
+	 * deferred queue. In order to safely determine that, there
+	 * must be no new deferred MDB notifications enqueued for the
+	 * duration of the MDB scan. Therefore, grab the write-side
+	 * lock to avoid racing with any concurrent IGMP/MLD snooping.
+	 */
+	spin_lock_bh(&br->multicast_lock);
+
+	hlist_for_each_entry(mp, &br->mdb_list, mdb_node) {
+		struct net_bridge_port_group __rcu * const *pp;
+		const struct net_bridge_port_group *p;
+
+		if (mp->host_joined) {
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
+							 SWITCHDEV_OBJ_ID_HOST_MDB,
+							 mp, br_dev);
+			if (err) {
+				spin_unlock_bh(&br->multicast_lock);
+				goto out_free_mdb;
+			}
+		}
+
+		for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
+		     pp = &p->next) {
+			if (p->key.port->dev != dev)
+				continue;
+
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
+							 SWITCHDEV_OBJ_ID_PORT_MDB,
+							 mp, dev);
+			if (err) {
+				spin_unlock_bh(&br->multicast_lock);
+				goto out_free_mdb;
+			}
+		}
+	}
+
+	spin_unlock_bh(&br->multicast_lock);
+
+	list_for_each_entry(obj, &mdb_list, list) {
+		err = br_switchdev_mdb_replay_one(nb, dev,
+						  SWITCHDEV_OBJ_PORT_MDB(obj),
+						  action, ctx, extack);
+		if (err == -EOPNOTSUPP)
+			err = 0;
+		if (err)
+			goto out_free_mdb;
+	}
+
+out_free_mdb:
+	list_for_each_entry_safe(obj, tmp, &mdb_list, list) {
+		list_del(&obj->list);
+		kfree(SWITCHDEV_OBJ_PORT_MDB(obj));
+	}
+
+	if (err)
+		return err;
+#endif
+
+	return 0;
+}
+
+static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
+				   struct notifier_block *atomic_nb,
+				   struct notifier_block *blocking_nb,
+				   struct netlink_ext_ack *extack)
+{
+	struct net_device *br_dev = p->br->dev;
+	struct net_device *dev = p->dev;
+	int err;
+
+	err = br_switchdev_vlan_replay(br_dev, ctx, true, blocking_nb, extack);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
+	err = br_switchdev_mdb_replay(br_dev, dev, ctx, true, blocking_nb,
+				      extack);
+	if (err) {
+		/* -EOPNOTSUPP not propagated from MDB replay. */
+		return err;
+	}
+
+	err = br_switchdev_fdb_replay(br_dev, ctx, true, atomic_nb);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
+	return 0;
+}
+
+static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
+				      const void *ctx,
+				      struct notifier_block *atomic_nb,
+				      struct notifier_block *blocking_nb)
+{
+	struct net_device *br_dev = p->br->dev;
+	struct net_device *dev = p->dev;
+
+	br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb);
+
+	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
+
+	br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL);
+
+	/* Make sure that the device leaving this bridge has seen all
+	 * relevant events before it is disassociated. In the normal
+	 * case, when the device is directly attached to the bridge,
+	 * this is covered by del_nbp(). If the association was indirect
+	 * however, e.g. via a team or bond, and the device is leaving
+	 * that intermediate device, then the bridge port remains in
+	 * place.
+	 */
+	switchdev_deferred_process();
+}
+
+/* Let the bridge know that this port is offloaded, so that it can assign a
+ * switchdev hardware domain to it.
+ */
+int br_switchdev_port_offload(struct net_bridge_port *p,
+			      struct net_device *dev, const void *ctx,
+			      struct notifier_block *atomic_nb,
+			      struct notifier_block *blocking_nb,
+			      bool tx_fwd_offload,
+			      struct netlink_ext_ack *extack)
+{
+	struct netdev_phys_item_id ppid;
+	int err;
+
+	err = netif_get_port_parent_id(dev, &ppid, false);
+	if (err)
+		return err;
+
+	err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack);
+	if (err)
+		return err;
+
+	err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack);
+	if (err)
+		goto out_switchdev_del;
+
+	return 0;
+
+out_switchdev_del:
+	nbp_switchdev_del(p);
+
+	return err;
+}
+
+void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
+				 struct notifier_block *atomic_nb,
+				 struct notifier_block *blocking_nb)
+{
+	nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb);
+
+	nbp_switchdev_del(p);
+}
+
+int br_switchdev_port_replay(struct net_bridge_port *p,
+			     struct net_device *dev, const void *ctx,
+			     struct notifier_block *atomic_nb,
+			     struct notifier_block *blocking_nb,
+			     struct netlink_ext_ack *extack)
+{
+	return nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack);
+}