Merge tag 'net-5.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Current release - regressions:

   - dsa: bcm_sf2: fix array overrun in bcm_sf2_num_active_ports()

  Previous releases - regressions:

   - introduce a shutdown method to mdio device drivers, and make DSA
     switch drivers compatible with masters disappearing on shutdown;
     preventing infinite reference wait

   - fix issues in mdiobus users related to ->shutdown vs ->remove

   - virtio-net: fix pages leaking when building skb in big mode

   - xen-netback: correct success/error reporting for the
     SKB-with-fraglist

   - dsa: tear down devlink port regions when tearing down the devlink
     port on error

   - nexthop: fix division by zero while replacing a resilient group

   - hns3: check queue, vf, vlan ids range before using

  Previous releases - always broken:

   - napi: fix race against netpoll causing NAPI getting stuck

   - mlx4_en: ensure link operstate is updated even if link comes up
     before netdev registration

   - bnxt_en: fix TX timeout when TX ring size is set to the smallest

   - enetc: fix illegal access when reading affinity_hint; prevent oops
     on sysfs access

   - mtk_eth_soc: avoid creating duplicate offload entries

  Misc:

   - core: correct the sock::sk_lock.owned lockdep annotations"

* tag 'net-5.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (51 commits)
  atlantic: Fix issue in the pm resume flow.
  net/mlx4_en: Don't allow aRFS for encapsulated packets
  net: mscc: ocelot: fix forwarding from BLOCKING ports remaining enabled
  net: ethernet: mtk_eth_soc: avoid creating duplicate offload entries
  nfc: st-nci: Add SPI ID matching DT compatible
  MAINTAINERS: remove Guvenc Gulce as net/smc maintainer
  nexthop: Fix memory leaks in nexthop notification chain listeners
  mptcp: ensure tx skbs always have the MPTCP ext
  qed: rdma - don't wait for resources under hw error recovery flow
  s390/qeth: fix deadlock during failing recovery
  s390/qeth: Fix deadlock in remove_discipline
  s390/qeth: fix NULL deref in qeth_clear_working_pool_list()
  net: dsa: realtek: register the MDIO bus under devres
  net: dsa: don't allocate the slave_mii_bus using devres
  Doc: networking: Fox a typo in ice.rst
  net: dsa: fix dsa_tree_setup error path
  net/smc: fix 'workqueue leaked lock' in smc_conn_abort_work
  net/smc: add missing error check in smc_clc_prfx_set()
  net: hns3: fix a return value error in hclge_get_reset_status()
  net: hns3: check vlan id before using it
  ...

1 files changed, 106 insertions, 8 deletions

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index eef13cd20f19..b29262eee00b 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -429,6 +429,7 @@ static int dsa_port_setup(struct dsa_port *dp)
 {
 	struct devlink_port *dlp = &dp->devlink_port;
 	bool dsa_port_link_registered = false;
+	struct dsa_switch *ds = dp->ds;
 	bool dsa_port_enabled = false;
 	int err = 0;
 
@@ -438,6 +439,12 @@ static int dsa_port_setup(struct dsa_port *dp)
 	INIT_LIST_HEAD(&dp->fdbs);
 	INIT_LIST_HEAD(&dp->mdbs);
 
+	if (ds->ops->port_setup) {
+		err = ds->ops->port_setup(ds, dp->index);
+		if (err)
+			return err;
+	}
+
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
 		dsa_port_disable(dp);
@@ -480,8 +487,11 @@ static int dsa_port_setup(struct dsa_port *dp)
 		dsa_port_disable(dp);
 	if (err && dsa_port_link_registered)
 		dsa_port_link_unregister_of(dp);
-	if (err)
+	if (err) {
+		if (ds->ops->port_teardown)
+			ds->ops->port_teardown(ds, dp->index);
 		return err;
+	}
 
 	dp->setup = true;
 
@@ -533,11 +543,15 @@ static int dsa_port_devlink_setup(struct dsa_port *dp)
 static void dsa_port_teardown(struct dsa_port *dp)
 {
 	struct devlink_port *dlp = &dp->devlink_port;
+	struct dsa_switch *ds = dp->ds;
 	struct dsa_mac_addr *a, *tmp;
 
 	if (!dp->setup)
 		return;
 
+	if (ds->ops->port_teardown)
+		ds->ops->port_teardown(ds, dp->index);
+
 	devlink_port_type_clear(dlp);
 
 	switch (dp->type) {
@@ -581,6 +595,36 @@ static void dsa_port_devlink_teardown(struct dsa_port *dp)
 	dp->devlink_port_setup = false;
 }
 
+/* Destroy the current devlink port, and create a new one which has the UNUSED
+ * flavour. At this point, any call to ds->ops->port_setup has been already
+ * balanced out by a call to ds->ops->port_teardown, so we know that any
+ * devlink port regions the driver had are now unregistered. We then call its
+ * ds->ops->port_setup again, in order for the driver to re-create them on the
+ * new devlink port.
+ */
+static int dsa_port_reinit_as_unused(struct dsa_port *dp)
+{
+	struct dsa_switch *ds = dp->ds;
+	int err;
+
+	dsa_port_devlink_teardown(dp);
+	dp->type = DSA_PORT_TYPE_UNUSED;
+	err = dsa_port_devlink_setup(dp);
+	if (err)
+		return err;
+
+	if (ds->ops->port_setup) {
+		/* On error, leave the devlink port registered,
+		 * dsa_switch_teardown will clean it up later.
+		 */
+		err = ds->ops->port_setup(ds, dp->index);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int dsa_devlink_info_get(struct devlink *dl,
 				struct devlink_info_req *req,
 				struct netlink_ext_ack *extack)
@@ -836,7 +880,7 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 	devlink_params_publish(ds->devlink);
 
 	if (!ds->slave_mii_bus && ds->ops->phy_read) {
-		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
+		ds->slave_mii_bus = mdiobus_alloc();
 		if (!ds->slave_mii_bus) {
 			err = -ENOMEM;
 			goto teardown;
@@ -846,13 +890,16 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 
 		err = mdiobus_register(ds->slave_mii_bus);
 		if (err < 0)
-			goto teardown;
+			goto free_slave_mii_bus;
 	}
 
 	ds->setup = true;
 
 	return 0;
 
+free_slave_mii_bus:
+	if (ds->slave_mii_bus && ds->ops->phy_read)
+		mdiobus_free(ds->slave_mii_bus);
 teardown:
 	if (ds->ops->teardown)
 		ds->ops->teardown(ds);
@@ -877,8 +924,11 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 	if (!ds->setup)
 		return;
 
-	if (ds->slave_mii_bus && ds->ops->phy_read)
+	if (ds->slave_mii_bus && ds->ops->phy_read) {
 		mdiobus_unregister(ds->slave_mii_bus);
+		mdiobus_free(ds->slave_mii_bus);
+		ds->slave_mii_bus = NULL;
+	}
 
 	dsa_switch_unregister_notifier(ds);
 
@@ -938,12 +988,9 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 	list_for_each_entry(dp, &dst->ports, list) {
 		err = dsa_port_setup(dp);
 		if (err) {
-			dsa_port_devlink_teardown(dp);
-			dp->type = DSA_PORT_TYPE_UNUSED;
-			err = dsa_port_devlink_setup(dp);
+			err = dsa_port_reinit_as_unused(dp);
 			if (err)
 				goto teardown;
-			continue;
 		}
 	}
 
@@ -1048,6 +1095,7 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
 teardown_master:
 	dsa_tree_teardown_master(dst);
 teardown_switches:
+	dsa_tree_teardown_ports(dst);
 	dsa_tree_teardown_switches(dst);
 teardown_cpu_ports:
 	dsa_tree_teardown_cpu_ports(dst);
@@ -1562,3 +1610,53 @@ void dsa_unregister_switch(struct dsa_switch *ds)
 	mutex_unlock(&dsa2_mutex);
 }
 EXPORT_SYMBOL_GPL(dsa_unregister_switch);
+
+/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is
+ * blocking that operation from completion, due to the dev_hold taken inside
+ * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of
+ * the DSA master, so that the system can reboot successfully.
+ */
+void dsa_switch_shutdown(struct dsa_switch *ds)
+{
+	struct net_device *master, *slave_dev;
+	LIST_HEAD(unregister_list);
+	struct dsa_port *dp;
+
+	mutex_lock(&dsa2_mutex);
+	rtnl_lock();
+
+	list_for_each_entry(dp, &ds->dst->ports, list) {
+		if (dp->ds != ds)
+			continue;
+
+		if (!dsa_port_is_user(dp))
+			continue;
+
+		master = dp->cpu_dp->master;
+		slave_dev = dp->slave;
+
+		netdev_upper_dev_unlink(master, slave_dev);
+		/* Just unlinking ourselves as uppers of the master is not
+		 * sufficient. When the master net device unregisters, that will
+		 * also call dev_close, which we will catch as NETDEV_GOING_DOWN
+		 * and trigger a dev_close on our own devices (dsa_slave_close).
+		 * In turn, that will call dev_mc_unsync on the master's net
+		 * device. If the master is also a DSA switch port, this will
+		 * trigger dsa_slave_set_rx_mode which will call dev_mc_sync on
+		 * its own master. Lockdep will complain about the fact that
+		 * all cascaded masters have the same dsa_master_addr_list_lock_key,
+		 * which it normally would not do if the cascaded masters would
+		 * be in a proper upper/lower relationship, which we've just
+		 * destroyed.
+		 * To suppress the lockdep warnings, let's actually unregister
+		 * the DSA slave interfaces too, to avoid the nonsensical
+		 * multicast address list synchronization on shutdown.
+		 */
+		unregister_netdevice_queue(slave_dev, &unregister_list);
+	}
+	unregister_netdevice_many(&unregister_list);
+
+	rtnl_unlock();
+	mutex_unlock(&dsa2_mutex);
+}
+EXPORT_SYMBOL_GPL(dsa_switch_shutdown);