[RFC PATCH net-next 0/8] Drop rtnl_lock from DSA .port_fdb_{add,del}

@@ -1170,6 +1170,56 @@ const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = {
 	},
 };
 
+#define SJA1105_DYNAMIC_CONFIG_SLEEP_US		10
+#define SJA1105_DYNAMIC_CONFIG_TIMEOUT_US	100000
+
+static int
+sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
+				  struct sja1105_dyn_cmd *cmd,
+				  const struct sja1105_dynamic_table_ops *ops)
+{
+	u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {};
+	int rc;
+
+	/* We don't _need_ to read the full entry, just the command area which
+	 * is a fixed SJA1105_SIZE_DYN_CMD. But our cmd_packing() API expects a
+	 * buffer that contains the full entry too. Additionally, our API
+	 * doesn't really know how many bytes into the buffer does the command
+	 * area really begin. So just read back the whole entry.
+	 */
+	rc = sja1105_xfer_buf(priv, SPI_READ, ops->addr, packed_buf,
+			      ops->packed_size);
+	if (rc)
+		return rc;
+
+	/* Unpack the command structure, and return it to the caller in case it
+	 * needs to perform further checks on it (VALIDENT).
+	 */
+	memset(cmd, 0, sizeof(*cmd));
+	ops->cmd_packing(packed_buf, cmd, UNPACK);
+
+	/* Hardware hasn't cleared VALID => still working on it */
+	return cmd->valid ? -EAGAIN : 0;
+}
+
+/* Poll the dynamic config entry's control area until the hardware has
+ * cleared the VALID bit, which means we have confirmation that it has
+ * finished processing the command.
+ */
+static int
+sja1105_dynamic_config_wait_complete(struct sja1105_private *priv,
+				     struct sja1105_dyn_cmd *cmd,
+				     const struct sja1105_dynamic_table_ops *ops)
+{
+	int rc;
+
+	return read_poll_timeout(sja1105_dynamic_config_poll_valid,
+				 rc, rc != -EAGAIN,
+				 SJA1105_DYNAMIC_CONFIG_SLEEP_US,
+				 SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
+				 false, priv, cmd, ops);
+}
+
 /* Provides read access to the settings through the dynamic interface
  * of the switch.
  * @blk_idx	is used as key to select from the sja1105_dynamic_table_ops.

@@ -1196,7 +1246,6 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
 	struct sja1105_dyn_cmd cmd = {0};
 	/* SPI payload buffer */
 	u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {0};
-	int retries = 3;
 	int rc;
 
 	if (blk_idx >= BLK_IDX_MAX_DYN)

@@ -1239,28 +1288,12 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
 	if (rc < 0)
 		return rc;
 
-	/* Loop until we have confirmation that hardware has finished
-	 * processing the command and has cleared the VALID field
-	 */
-	do {
-		memset(packed_buf, 0, ops->packed_size);
-
-		/* Retrieve the read operation's result */
-		rc = sja1105_xfer_buf(priv, SPI_READ, ops->addr, packed_buf,
-				      ops->packed_size);
-		if (rc < 0)
-			return rc;
-
-		cmd = (struct sja1105_dyn_cmd) {0};
-		ops->cmd_packing(packed_buf, &cmd, UNPACK);
-
-		if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY))
-			return -ENOENT;
-		cpu_relax();
-	} while (cmd.valid && --retries);
+	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
+	if (rc < 0)
+		return rc;
 
-	if (cmd.valid)
-		return -ETIMEDOUT;
+	if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY))
+		return -ENOENT;
 
 	/* Don't dereference possibly NULL pointer - maybe caller
 	 * only wanted to see whether the entry existed or not.

@@ -1321,6 +1354,10 @@ int sja1105_dynamic_config_write(struct sja1105_private *priv,
 	if (rc < 0)
 		return rc;
 
+	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
+	if (rc < 0)
+		return rc;
+
 	cmd = (struct sja1105_dyn_cmd) {0};
 	ops->cmd_packing(packed_buf, &cmd, UNPACK);
 	if (cmd.errors)

@@ -248,6 +248,8 @@ struct sja1105_private {
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
+	/* Serializes access to the dynamic config interface */
+	struct mutex dynamic_config_lock;
 	struct devlink_region **regions;
 	struct sja1105_cbs_entry *cbs;
 	struct mii_bus *mdio_base_t1;

@@ -1283,12 +1283,16 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
 		ops->entry_packing(packed_buf, entry, PACK);
 
 	/* Send SPI write operation: read config table entry */
+	mutex_lock(&priv->dynamic_config_lock);
 	rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
 			      ops->packed_size);
-	if (rc < 0)
+	if (rc < 0) {
+		mutex_unlock(&priv->dynamic_config_lock);
 		return rc;
+	}
 
 	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
+	mutex_unlock(&priv->dynamic_config_lock);
 	if (rc < 0)
 		return rc;
 

@@ -1349,12 +1353,16 @@ int sja1105_dynamic_config_write(struct sja1105_private *priv,
 		ops->entry_packing(packed_buf, entry, PACK);
 
 	/* Send SPI write operation: read config table entry */
+	mutex_lock(&priv->dynamic_config_lock);
 	rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
 			      ops->packed_size);
-	if (rc < 0)
+	if (rc < 0) {
+		mutex_unlock(&priv->dynamic_config_lock);
 		return rc;
+	}
 
 	rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
+	mutex_unlock(&priv->dynamic_config_lock);
 	if (rc < 0)
 		return rc;
 

@@ -3285,6 +3285,7 @@ static int sja1105_probe(struct spi_device *spi)
 	priv->ds = ds;
 
 	mutex_init(&priv->ptp_data.lock);
+	mutex_init(&priv->dynamic_config_lock);
 	mutex_init(&priv->mgmt_lock);
 
 	rc = sja1105_parse_dt(priv);

@@ -12958,6 +12958,7 @@ F:	include/linux/dsa/
 F:	include/linux/platform_data/dsa.h
 F:	include/net/dsa.h
 F:	net/dsa/
+F:	tools/testing/selftests/drivers/net/dsa/
 
 NETWORKING [GENERAL]
 M:	"David S. Miller" <davem@davemloft.net>

@@ -0,0 +1,48 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Bridge FDB entries can be offloaded to DSA switches without holding the
+# rtnl_mutex. Traditionally this mutex has conferred drivers implicit
+# serialization, which means their code paths are not well tested in the
+# presence of concurrency.
+# This test creates a background task that stresses the FDB by adding and
+# deleting an entry many times in a row without the rtnl_mutex held.
+# It then tests the driver resistance to concurrency by calling .ndo_fdb_dump
+# (with rtnl_mutex held) from a foreground task.
+# Since either the FDB dump or the additions/removals can fail, but the
+# additions and removals are performed in deferred as opposed to process
+# context, we cannot simply check for user space error codes.
+
+WAIT_TIME=1
+NUM_NETIFS=1
+REQUIRE_JQ="no"
+REQUIRE_MZ="no"
+NETIF_CREATE="no"
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/lib.sh
+
+cleanup() {
+	echo "Cleaning up"
+	ip link del br0
+	kill $pid
+	killall bash
+	echo "Please check kernel log for errors"
+}
+trap 'cleanup' EXIT
+
+eth=${NETIFS[p1]}
+
+ip link del br0 2&>1 >/dev/null || :
+ip link add br0 type bridge && ip link set $eth master br0
+
+(while :; do
+	bridge fdb add 00:01:02:03:04:05 dev $eth master static
+	bridge fdb del 00:01:02:03:04:05 dev $eth master static
+done) &
+pid=$!
+
+for i in $(seq 1 50); do
+	bridge fdb show > /dev/null
+	sleep 3
+	echo "$((${i} * 2))% complete..."
+done

@@ -285,6 +285,7 @@ struct dsa_port {
 	/* List of MAC addresses that must be forwarded on this port.
 	 * These are only valid on CPU ports and DSA links.
 	 */
+	struct mutex		addr_lists_lock;
 	struct list_head	fdbs;
 	struct list_head	mdbs;
 

@@ -435,6 +435,7 @@ static int dsa_port_setup(struct dsa_port *dp)
 	if (dp->setup)
 		return 0;
 
+	mutex_init(&dp->addr_lists_lock);
 	INIT_LIST_HEAD(&dp->fdbs);
 	INIT_LIST_HEAD(&dp->mdbs);
 

@@ -214,26 +214,30 @@ static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_mdb_add(ds, port, mdb);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
 	if (a) {
 		refcount_inc(&a->refcount);
-		return 0;
+		goto out;
 	}
 
 	a = kzalloc(sizeof(*a), GFP_KERNEL);
-	if (!a)
-		return -ENOMEM;
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = ds->ops->port_mdb_add(ds, port, mdb);
 	if (err) {
 		kfree(a);
-		return err;
+		goto out;
 	}
 
 	ether_addr_copy(a->addr, mdb->addr);

@@ -241,7 +245,10 @@ static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port,
 	refcount_set(&a->refcount, 1);
 	list_add_tail(&a->list, &dp->mdbs);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port,

@@ -249,29 +256,36 @@ static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_mdb_del(ds, port, mdb);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
-	if (!a)
-		return -ENOENT;
+	if (!a) {
+		err = -ENOENT;
+		goto out;
+	}
 
 	if (!refcount_dec_and_test(&a->refcount))
-		return 0;
+		goto out;
 
 	err = ds->ops->port_mdb_del(ds, port, mdb);
 	if (err) {
 		refcount_inc(&a->refcount);
-		return err;
+		goto out;
 	}
 
 	list_del(&a->list);
 	kfree(a);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,

@@ -279,26 +293,30 @@ static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_fdb_add(ds, port, addr, vid);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
 	if (a) {
 		refcount_inc(&a->refcount);
-		return 0;
+		goto out;
 	}
 
 	a = kzalloc(sizeof(*a), GFP_KERNEL);
-	if (!a)
-		return -ENOMEM;
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = ds->ops->port_fdb_add(ds, port, addr, vid);
 	if (err) {
 		kfree(a);
-		return err;
+		goto out;
 	}
 
 	ether_addr_copy(a->addr, addr);

@@ -306,7 +324,10 @@ static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
 	refcount_set(&a->refcount, 1);
 	list_add_tail(&a->list, &dp->fdbs);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port,

@@ -314,29 +335,36 @@ static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port,
 {
 	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_mac_addr *a;
-	int err;
+	int err = 0;
 
 	/* No need to bother with refcounting for user ports */
 	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
 		return ds->ops->port_fdb_del(ds, port, addr, vid);
 
+	mutex_lock(&dp->addr_lists_lock);
+
 	a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
-	if (!a)
-		return -ENOENT;
+	if (!a) {
+		err = -ENOENT;
+		goto out;
+	}
 
 	if (!refcount_dec_and_test(&a->refcount))
-		return 0;
+		goto out;
 
 	err = ds->ops->port_fdb_del(ds, port, addr, vid);
 	if (err) {
 		refcount_inc(&a->refcount);
-		return err;
+		goto out;
 	}
 
 	list_del(&a->list);
 	kfree(a);
 
-	return 0;
+out:
+	mutex_unlock(&dp->addr_lists_lock);
+
+	return err;
 }
 
 static int dsa_switch_host_fdb_add(struct dsa_switch *ds,

@@ -20,11 +20,13 @@ struct ocelot_mact_entry {
 	enum macaccess_entry_type type;
 };
 
+/* Must be called with &ocelot->mact_lock held */
 static inline u32 ocelot_mact_read_macaccess(struct ocelot *ocelot)
 {
 	return ocelot_read(ocelot, ANA_TABLES_MACACCESS);
 }
 
+/* Must be called with &ocelot->mact_lock held */
 static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
 {
 	u32 val;

@@ -36,6 +38,7 @@ static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
 		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
+/* Must be called with &ocelot->mact_lock held */
 static void ocelot_mact_select(struct ocelot *ocelot,
 			       const unsigned char mac[ETH_ALEN],
 			       unsigned int vid)

@@ -67,6 +70,7 @@ int ocelot_mact_learn(struct ocelot *ocelot, int port,
 		ANA_TABLES_MACACCESS_ENTRYTYPE(type) |
 		ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_LEARN);
 	unsigned int mc_ports;
+	int err;
 
 	/* Set MAC_CPU_COPY if the CPU port is used by a multicast entry */
 	if (type == ENTRYTYPE_MACv4)

@@ -79,18 +83,28 @@ int ocelot_mact_learn(struct ocelot *ocelot, int port,
 	if (mc_ports & BIT(ocelot->num_phys_ports))
 		cmd |= ANA_TABLES_MACACCESS_MAC_CPU_COPY;
 
+	mutex_lock(&ocelot->mact_lock);
+
 	ocelot_mact_select(ocelot, mac, vid);
 
 	/* Issue a write command */
 	ocelot_write(ocelot, cmd, ANA_TABLES_MACACCESS);
 
-	return ocelot_mact_wait_for_completion(ocelot);
+	err = ocelot_mact_wait_for_completion(ocelot);
+
+	mutex_unlock(&ocelot->mact_lock);
+
+	return err;
 }
 EXPORT_SYMBOL(ocelot_mact_learn);
 
 int ocelot_mact_forget(struct ocelot *ocelot,
 		       const unsigned char mac[ETH_ALEN], unsigned int vid)
 {
+	int err;
+
+	mutex_lock(&ocelot->mact_lock);
+
 	ocelot_mact_select(ocelot, mac, vid);
 
 	/* Issue a forget command */

@@ -98,7 +112,11 @@ int ocelot_mact_forget(struct ocelot *ocelot,
 		     ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_FORGET),
 		     ANA_TABLES_MACACCESS);
 
-	return ocelot_mact_wait_for_completion(ocelot);
+	err = ocelot_mact_wait_for_completion(ocelot);
+
+	mutex_unlock(&ocelot->mact_lock);
+
+	return err;
 }
 EXPORT_SYMBOL(ocelot_mact_forget);
 

@@ -114,7 +132,9 @@ static void ocelot_mact_init(struct ocelot *ocelot)
 		   | ANA_AGENCTRL_LEARN_IGNORE_VLAN,
 		   ANA_AGENCTRL);
 
-	/* Clear the MAC table */
+	/* Clear the MAC table. We are not concurrent with anyone, so
+	 * holding &ocelot->mact_lock is pointless.
+	 */
 	ocelot_write(ocelot, MACACCESS_CMD_INIT, ANA_TABLES_MACACCESS);
 }
 

@@ -1028,6 +1048,7 @@ int ocelot_port_fdb_do_dump(const unsigned char *addr, u16 vid,
 }
 EXPORT_SYMBOL(ocelot_port_fdb_do_dump);
 
+/* Must be called with &ocelot->mact_lock held */
 static int ocelot_mact_read(struct ocelot *ocelot, int port, int row, int col,
 			    struct ocelot_mact_entry *entry)
 {

@@ -1078,33 +1099,40 @@ static int ocelot_mact_read(struct ocelot *ocelot, int port, int row, int col,
 int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 		    dsa_fdb_dump_cb_t *cb, void *data)
 {
+	int err = 0;
 	int i, j;
 
+	/* We could take the lock just around ocelot_mact_read, but doing so
+	 * thousands of times in a row seems rather pointless and inefficient.
+	 */
+	mutex_lock(&ocelot->mact_lock);
+
 	/* Loop through all the mac tables entries. */
 	for (i = 0; i < ocelot->num_mact_rows; i++) {
 		for (j = 0; j < 4; j++) {
 			struct ocelot_mact_entry entry;
 			bool is_static;
-			int ret;
 
-			ret = ocelot_mact_read(ocelot, port, i, j, &entry);
+			err = ocelot_mact_read(ocelot, port, i, j, &entry);
 			/* If the entry is invalid (wrong port, invalid...),
 			 * skip it.
 			 */
-			if (ret == -EINVAL)
+			if (err == -EINVAL)
 				continue;
-			else if (ret)
-				return ret;
+			else if (err)
+				break;
 
 			is_static = (entry.type == ENTRYTYPE_LOCKED);
 
-			ret = cb(entry.mac, entry.vid, is_static, data);
-			if (ret)
-				return ret;
+			err = cb(entry.mac, entry.vid, is_static, data);
+			if (err)
+				break;
 		}
 	}
 
-	return 0;
+	mutex_unlock(&ocelot->mact_lock);
+
+	return err;
 }
 EXPORT_SYMBOL(ocelot_fdb_dump);
 

@@ -2085,6 +2113,7 @@ int ocelot_init(struct ocelot *ocelot)
 
 	mutex_init(&ocelot->stats_lock);
 	mutex_init(&ocelot->ptp_lock);
+	mutex_init(&ocelot->mact_lock);
 	spin_lock_init(&ocelot->ptp_clock_lock);
 	snprintf(queue_name, sizeof(queue_name), "%s-stats",
 		 dev_name(ocelot->dev));

@@ -674,6 +674,9 @@ struct ocelot {
 	struct delayed_work		stats_work;
 	struct workqueue_struct		*stats_queue;
 
+	/* Lock for serializing access to the MAC table */
+	struct mutex			mact_lock;
+
 	struct workqueue_struct		*owq;
 
 	u8				ptp:1;

@@ -2381,7 +2381,6 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
 
 	dp = dsa_to_port(ds, switchdev_work->port);
 
-	rtnl_lock();
 	switch (switchdev_work->event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 		if (switchdev_work->host_addr)

@@ -2416,7 +2415,6 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work)
 
 		break;
 	}
-	rtnl_unlock();
 
 	dev_put(switchdev_work->dev);
 	kfree(switchdev_work);

@@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work)
 	return queue_work(dsa_owq, work);
 }
 
+void dsa_flush_work(void)
+{
+	flush_workqueue(dsa_owq);
+}
+
 int dsa_devlink_param_get(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {

@@ -170,6 +170,8 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops);
 const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf);
 
 bool dsa_schedule_work(struct work_struct *work);
+void dsa_flush_work(void);
+
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
 
 static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops)

@@ -380,6 +380,8 @@ void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br)
 	switchdev_bridge_port_unoffload(brport_dev, dp,
 					&dsa_slave_switchdev_notifier,
 					&dsa_slave_switchdev_blocking_notifier);
+
+	dsa_flush_work();
 }
 
 void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br)

@@ -20,6 +20,8 @@ MC_CLI=${MC_CLI:=smcroutectl}
 PING_TIMEOUT=${PING_TIMEOUT:=5}
 WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
 INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
+REQUIRE_JQ=${REQUIRE_JQ:=yes}
+REQUIRE_MZ=${REQUIRE_MZ:=yes}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then

@@ -138,8 +140,12 @@ require_command()
 	fi
 }
 
-require_command jq
-require_command $MZ
+if [[ "$REQUIRE_JQ" = "yes" ]]; then
+	require_command jq
+fi
+if [[ "$REQUIRE_MZ" = "yes" ]]; then
+	require_command $MZ
+fi
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""