Date:   Tue, 29 Nov 2022 16:12:19 +0200
From:   Vladimir Oltean <vladimir.oltean@....com>
To:     netdev@...r.kernel.org
Cc:     Ioana Ciornei <ioana.ciornei@....com>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        Russell King <linux@...linux.org.uk>,
        linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH net-next 10/12] net: dpaa2-eth: serialize changes to priv->mac with a mutex

The dpaa2 architecture permits dynamic connections between objects on
the fsl-mc bus, specifically between a DPNI object (represented by a
struct net_device) and a DPMAC object (represented by a struct phylink).

The DPNI driver is notified when those connections are created/broken
through the dpni_irq0_handler_thread() method. To ensure that ethtool
operations, as well as netdev up/down operations serialize with the
connection/disconnection of the DPNI with a DPMAC,
dpni_irq0_handler_thread() takes the rtnl_lock() to block those other
operations from taking place.

There is code called by dpaa2_mac_connect() which wants to acquire the
rtnl_mutex once again, see phylink_create() -> phylink_register_sfp() ->
sfp_bus_add_upstream() -> rtnl_lock(). So the strategy doesn't quite
work out, even though it's fairly simple.

Create a different strategy, where all code paths in the dpaa2-eth
driver access priv->mac only while they are holding priv->mac_lock.
The phylink instance is not created or connected to the PHY under the
priv->mac_lock, but only assigned to priv->mac then. This will eliminate
the reliance on the rtnl_mutex.

Add lockdep annotations and put comments where holding the lock is not
necessary, and priv->mac can be dereferenced freely.

Signed-off-by: Vladimir Oltean <vladimir.oltean@....com>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 43 ++++++++++++--
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.h  |  6 ++
 .../ethernet/freescale/dpaa2/dpaa2-ethtool.c  | 58 +++++++++++++++----
 3 files changed, 91 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index b77d292cd960..3ed54c147e98 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2147,8 +2147,11 @@ static int dpaa2_eth_link_state_update(struct dpaa2_eth_priv *priv)
 
 	/* When we manage the MAC/PHY using phylink there is no need
 	 * to manually update the netif_carrier.
+	 * We can avoid locking because we are called from the "link changed"
+	 * IRQ handler, which is the same as the "endpoint changed" IRQ handler
+	 * (the writer to priv->mac), so we cannot race with it.
 	 */
-	if (dpaa2_eth_is_type_phy(priv))
+	if (dpaa2_mac_is_type_phy(priv->mac))
 		goto out;
 
 	/* Chech link state; speed / duplex changes are not treated yet */
@@ -2179,6 +2182,8 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 
 	dpaa2_eth_seed_pools(priv);
 
+	mutex_lock(&priv->mac_lock);
+
 	if (!dpaa2_eth_is_type_phy(priv)) {
 		/* We'll only start the txqs when the link is actually ready;
 		 * make sure we don't race against the link up notification,
@@ -2197,6 +2202,7 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 
 	err = dpni_enable(priv->mc_io, 0, priv->mc_token);
 	if (err < 0) {
+		mutex_unlock(&priv->mac_lock);
 		netdev_err(net_dev, "dpni_enable() failed\n");
 		goto enable_err;
 	}
@@ -2204,6 +2210,8 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 	if (dpaa2_eth_is_type_phy(priv))
 		dpaa2_mac_start(priv->mac);
 
+	mutex_unlock(&priv->mac_lock);
+
 	return 0;
 
 enable_err:
@@ -2275,6 +2283,8 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 	int dpni_enabled = 0;
 	int retries = 10;
 
+	mutex_lock(&priv->mac_lock);
+
 	if (dpaa2_eth_is_type_phy(priv)) {
 		dpaa2_mac_stop(priv->mac);
 	} else {
@@ -2282,6 +2292,8 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 		netif_carrier_off(net_dev);
 	}
 
+	mutex_unlock(&priv->mac_lock);
+
 	/* On dpni_disable(), the MC firmware will:
 	 * - stop MAC Rx and wait for all Rx frames to be enqueued to software
 	 * - cut off WRIOP dequeues from egress FQs and wait until transmission
@@ -2607,12 +2619,20 @@ static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	int err;
 
 	if (cmd == SIOCSHWTSTAMP)
 		return dpaa2_eth_ts_ioctl(dev, rq, cmd);
 
-	if (dpaa2_eth_is_type_phy(priv))
-		return phylink_mii_ioctl(priv->mac->phylink, rq, cmd);
+	mutex_lock(&priv->mac_lock);
+
+	if (dpaa2_eth_is_type_phy(priv)) {
+		err = phylink_mii_ioctl(priv->mac->phylink, rq, cmd);
+		mutex_unlock(&priv->mac_lock);
+		return err;
+	}
+
+	mutex_unlock(&priv->mac_lock);
 
 	return -EOPNOTSUPP;
 }
@@ -4639,7 +4659,9 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 		}
 	}
 
+	mutex_lock(&priv->mac_lock);
 	priv->mac = mac;
+	mutex_unlock(&priv->mac_lock);
 
 	return 0;
 
@@ -4652,9 +4674,12 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 
 static void dpaa2_eth_disconnect_mac(struct dpaa2_eth_priv *priv)
 {
-	struct dpaa2_mac *mac = priv->mac;
+	struct dpaa2_mac *mac;
 
+	mutex_lock(&priv->mac_lock);
+	mac = priv->mac;
 	priv->mac = NULL;
+	mutex_unlock(&priv->mac_lock);
 
 	if (!mac)
 		return;
@@ -4673,6 +4698,7 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg)
 	struct fsl_mc_device *dpni_dev = to_fsl_mc_device(dev);
 	struct net_device *net_dev = dev_get_drvdata(dev);
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	bool had_mac;
 	int err;
 
 	err = dpni_get_irq_status(dpni_dev->mc_io, 0, dpni_dev->mc_handle,
@@ -4690,7 +4716,12 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg)
 		dpaa2_eth_update_tx_fqids(priv);
 
 		rtnl_lock();
-		if (dpaa2_eth_has_mac(priv))
+		/* We can avoid locking because the "endpoint changed" IRQ
+		 * handler is the only one who changes priv->mac at runtime,
+		 * so we are not racing with anyone.
+		 */
+		had_mac = !!priv->mac;
+		if (had_mac)
 			dpaa2_eth_disconnect_mac(priv);
 		else
 			dpaa2_eth_connect_mac(priv);
@@ -4792,6 +4823,8 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	priv->net_dev = net_dev;
 	SET_NETDEV_DEVLINK_PORT(net_dev, &priv->devlink_port);
 
+	mutex_init(&priv->mac_lock);
+
 	priv->iommu_domain = iommu_get_domain_for_dev(dev);
 
 	priv->tx_tstamp_type = HWTSTAMP_TX_OFF;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 04270ae44d84..d56d7a13262e 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -615,6 +615,8 @@ struct dpaa2_eth_priv {
 #endif
 
 	struct dpaa2_mac *mac;
+	/* Serializes changes to priv->mac */
+	struct mutex		mac_lock;
 	struct workqueue_struct	*dpaa2_ptp_wq;
 	struct work_struct	tx_onestep_tstamp;
 	struct sk_buff_head	tx_skbs;
@@ -768,11 +770,15 @@ static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv)
 
 static inline bool dpaa2_eth_is_type_phy(struct dpaa2_eth_priv *priv)
 {
+	lockdep_assert_held(&priv->mac_lock);
+
 	return dpaa2_mac_is_type_phy(priv->mac);
 }
 
 static inline bool dpaa2_eth_has_mac(struct dpaa2_eth_priv *priv)
 {
+	lockdep_assert_held(&priv->mac_lock);
+
 	return priv->mac ? true : false;
 }
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index bd87aa9ef686..e80e9388c71f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -85,11 +85,16 @@ static void dpaa2_eth_get_drvinfo(struct net_device *net_dev,
 static int dpaa2_eth_nway_reset(struct net_device *net_dev)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	int err = -EOPNOTSUPP;
+
+	mutex_lock(&priv->mac_lock);
 
 	if (dpaa2_eth_is_type_phy(priv))
-		return phylink_ethtool_nway_reset(priv->mac->phylink);
+		err = phylink_ethtool_nway_reset(priv->mac->phylink);
+
+	mutex_unlock(&priv->mac_lock);
 
-	return -EOPNOTSUPP;
+	return err;
 }
 
 static int
@@ -97,10 +102,18 @@ dpaa2_eth_get_link_ksettings(struct net_device *net_dev,
 			     struct ethtool_link_ksettings *link_settings)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	int err;
 
-	if (dpaa2_eth_is_type_phy(priv))
-		return phylink_ethtool_ksettings_get(priv->mac->phylink,
-						     link_settings);
+	mutex_lock(&priv->mac_lock);
+
+	if (dpaa2_eth_is_type_phy(priv)) {
+		err = phylink_ethtool_ksettings_get(priv->mac->phylink,
+						    link_settings);
+		mutex_unlock(&priv->mac_lock);
+		return err;
+	}
+
+	mutex_unlock(&priv->mac_lock);
 
 	link_settings->base.autoneg = AUTONEG_DISABLE;
 	if (!(priv->link_state.options & DPNI_LINK_OPT_HALF_DUPLEX))
@@ -115,11 +128,17 @@ dpaa2_eth_set_link_ksettings(struct net_device *net_dev,
 			     const struct ethtool_link_ksettings *link_settings)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	int err = -EOPNOTSUPP;
 
-	if (!dpaa2_eth_is_type_phy(priv))
-		return -EOPNOTSUPP;
+	mutex_lock(&priv->mac_lock);
+
+	if (dpaa2_eth_is_type_phy(priv))
+		err = phylink_ethtool_ksettings_set(priv->mac->phylink,
+						    link_settings);
 
-	return phylink_ethtool_ksettings_set(priv->mac->phylink, link_settings);
+	mutex_unlock(&priv->mac_lock);
+
+	return err;
 }
 
 static void dpaa2_eth_get_pauseparam(struct net_device *net_dev,
@@ -128,11 +147,16 @@ static void dpaa2_eth_get_pauseparam(struct net_device *net_dev,
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	u64 link_options = priv->link_state.options;
 
+	mutex_lock(&priv->mac_lock);
+
 	if (dpaa2_eth_is_type_phy(priv)) {
 		phylink_ethtool_get_pauseparam(priv->mac->phylink, pause);
+		mutex_unlock(&priv->mac_lock);
 		return;
 	}
 
+	mutex_unlock(&priv->mac_lock);
+
 	pause->rx_pause = dpaa2_eth_rx_pause_enabled(link_options);
 	pause->tx_pause = dpaa2_eth_tx_pause_enabled(link_options);
 	pause->autoneg = AUTONEG_DISABLE;
@@ -151,9 +175,17 @@ static int dpaa2_eth_set_pauseparam(struct net_device *net_dev,
 		return -EOPNOTSUPP;
 	}
 
-	if (dpaa2_eth_is_type_phy(priv))
-		return phylink_ethtool_set_pauseparam(priv->mac->phylink,
-						      pause);
+	mutex_lock(&priv->mac_lock);
+
+	if (dpaa2_eth_is_type_phy(priv)) {
+		err = phylink_ethtool_set_pauseparam(priv->mac->phylink,
+						     pause);
+		mutex_unlock(&priv->mac_lock);
+		return err;
+	}
+
+	mutex_unlock(&priv->mac_lock);
+
 	if (pause->autoneg)
 		return -EOPNOTSUPP;
 
@@ -309,8 +341,12 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	}
 	*(data + i++) = buf_cnt_total;
 
+	mutex_lock(&priv->mac_lock);
+
 	if (dpaa2_eth_has_mac(priv))
 		dpaa2_mac_get_ethtool_stats(priv->mac, data + i);
+
+	mutex_unlock(&priv->mac_lock);
 }
 
 static int dpaa2_eth_prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
-- 
2.34.1

Powered by blists - more mailing lists