From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 24 Oct 2021 20:17:51 +0300
Subject: net: mscc: ocelot: serialize access to the MAC table
Patch-mainline: v5.16-rc1
Git-commit: 2468346c5677919de288bee85a0fefbef70c1e4e
References: jsc#PED-1549

DSA would like to remove the rtnl_lock from its
SWITCHDEV_FDB_{ADD,DEL}_TO_DEVICE handlers, and the felix driver uses
the same MAC table functions as ocelot.

This means that the MAC table functions will no longer be implicitly
serialized with respect to each other by the rtnl_mutex, we need to add
a dedicated lock in ocelot for the non-atomic operations of selecting a
MAC table row, reading/writing what we want and polling for completion.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mscc/ocelot.c |   53 ++++++++++++++++++++++++++++---------
 include/soc/mscc/ocelot.h          |    3 ++
 2 files changed, 44 insertions(+), 12 deletions(-)

--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -20,11 +20,13 @@ struct ocelot_mact_entry {
 	enum macaccess_entry_type type;
 };
 
+/* Caller must hold &ocelot->mact_lock */
 static inline u32 ocelot_mact_read_macaccess(struct ocelot *ocelot)
 {
 	return ocelot_read(ocelot, ANA_TABLES_MACACCESS);
 }
 
+/* Caller must hold &ocelot->mact_lock */
 static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
 {
 	u32 val;
@@ -36,6 +38,7 @@ static inline int ocelot_mact_wait_for_c
 		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
+/* Caller must hold &ocelot->mact_lock */
 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 *oce
 		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 *oce
 	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 *oc
 		     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 ocel
 		   | 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);
 }
 
@@ -1020,6 +1040,7 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(ocelot_port_fdb_do_dump);
 
+/* Caller must hold &ocelot->mact_lock */
 static int ocelot_mact_read(struct ocelot *ocelot, int port, int row, int col,
 			    struct ocelot_mact_entry *entry)
 {
@@ -1070,33 +1091,40 @@ static int ocelot_mact_read(struct ocelo
 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);
 
@@ -2072,6 +2100,7 @@ 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);
 	spin_lock_init(&ocelot->ts_id_lock);
 	snprintf(queue_name, sizeof(queue_name), "%s-stats",
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -662,6 +662,9 @@ 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;