net: remove phy_has_hwtstamp() -> phy_mii_ioctl() decision from converted drivers

It is desirable that the new .ndo_hwtstamp_set() API gives more
uniformity, less overhead and future flexibility w.r.t. the PHY
timestamping behavior.

Currently there are some drivers which allow PHY timestamping through
the procedure mentioned in Documentation/networking/timestamping.rst.
They don't do anything locally if phy_has_hwtstamp() is set, except for
lan966x which installs PTP packet traps.

Centralize that behavior in a new dev_set_hwtstamp_phylib() code
function, which calls either phy_mii_ioctl() for the phylib PHY,
or .ndo_hwtstamp_set() of the netdev, based on a single policy
(currently simplistic: phy_has_hwtstamp()).

Any driver converted to .ndo_hwtstamp_set() will automatically opt into
the centralized phylib timestamping policy. Unconverted drivers still
get to choose whether they let the PHY handle timestamping or not.

Netdev drivers with integrated PHY drivers that don't use phylib
presumably don't set dev->phydev, and those will always see
HWTSTAMP_SOURCE_NETDEV requests even when converted. The timestamping
policy will remain 100% up to them.

Signed-off-by: Vladimir Oltean <[e-mail]>
Reviewed-by: Jacob Keller <[e-mail]>
Tested-by: Horatiu Vultur <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/ethernet/freescale/fec_main.c

···
 			    struct kernel_hwtstamp_config *config)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phydev = ndev->phydev;
-
-	if (phy_has_hwtstamp(phydev))
-		return phy_mii_ioctl(phydev, config->ifr, SIOCGHWTSTAMP);
 
 	if (!netif_running(ndev))
 		return -EINVAL;
···
 			    struct netlink_ext_ack *extack)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct phy_device *phydev = ndev->phydev;
-
-	if (phy_has_hwtstamp(phydev))
-		return phy_mii_ioctl(phydev, config->ifr, SIOCSHWTSTAMP);
 
 	if (!netif_running(ndev))
 		return -EINVAL;

drivers/net/ethernet/microchip/lan966x/lan966x_main.c

···
 {
 	struct lan966x_port *port = netdev_priv(dev);
 
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
-
 	if (!port->lan966x->ptp)
 		return -EOPNOTSUPP;
 
···
 	struct lan966x_port *port = netdev_priv(dev);
 	int err;
 
+	if (cfg->source != HWTSTAMP_SOURCE_NETDEV &&
+	    cfg->source != HWTSTAMP_SOURCE_PHYLIB)
+		return -EOPNOTSUPP;
+
 	err = lan966x_ptp_setup_traps(port, cfg);
 	if (err)
 		return err;
 
-	if (phy_has_hwtstamp(dev->phydev)) {
-		err = phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
-		if (err)
+	if (cfg->source == HWTSTAMP_SOURCE_NETDEV) {
+		if (!port->lan966x->ptp)
+			return -EOPNOTSUPP;
+
+		err = lan966x_ptp_hwtstamp_set(port, cfg, extack);
+		if (err) {
 			lan966x_ptp_del_traps(port);
-		return err;
+			return err;
+		}
 	}
 
-	if (!port->lan966x->ptp)
-		return -EOPNOTSUPP;
-
-	return lan966x_ptp_hwtstamp_set(port, cfg, extack);
+	return 0;
 }
 
 static const struct net_device_ops lan966x_port_netdev_ops = {
···
 			 NETIF_F_HW_VLAN_STAG_TX |
 			 NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC;
+	dev->priv_flags |= IFF_SEE_ALL_HWTSTAMP_REQUESTS;
 	dev->needed_headroom = IFH_LEN_BYTES;
 
 	eth_hw_addr_gen(dev, lan966x->base_mac, p + 1);

drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c

···
 	struct sparx5_port *sparx5_port = netdev_priv(dev);
 	struct sparx5 *sparx5 = sparx5_port->sparx5;
 
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCGHWTSTAMP);
-
 	if (!sparx5->ptp)
 		return -EOPNOTSUPP;
 
···
 {
 	struct sparx5_port *sparx5_port = netdev_priv(dev);
 	struct sparx5 *sparx5 = sparx5_port->sparx5;
-
-	if (phy_has_hwtstamp(dev->phydev))
-		return phy_mii_ioctl(dev->phydev, cfg->ifr, SIOCSHWTSTAMP);
 
 	if (!sparx5->ptp)
 		return -EOPNOTSUPP;

include/linux/net_tstamp.h

···
 
 #include <uapi/linux/net_tstamp.h>
 
+enum hwtstamp_source {
+	HWTSTAMP_SOURCE_NETDEV,
+	HWTSTAMP_SOURCE_PHYLIB,
+};
+
 /**
  * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config
  *
···
  *	a legacy implementation of a lower driver
  * @copied_to_user: request was passed to a legacy implementation which already
  *	copied the ioctl request back to user space
+ * @source: indication whether timestamps should come from the netdev or from
+ *	an attached phylib PHY
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
···
 	int rx_filter;
 	struct ifreq *ifr;
 	bool copied_to_user;
+	enum hwtstamp_source source;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
···
 	cfg->flags = kernel_cfg->flags;
 	cfg->tx_type = kernel_cfg->tx_type;
 	cfg->rx_filter = kernel_cfg->rx_filter;
+}
+
+static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a,
+						  const struct kernel_hwtstamp_config *b)
+{
+	return a->flags != b->flags ||
+	       a->tx_type != b->tx_type ||
+	       a->rx_filter != b->rx_filter;
 }
 
 #endif /* _LINUX_NET_TIMESTAMPING_H_ */

include/linux/netdevice.h

···
  * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
  *	skb_headlen(skb) == 0 (data starts from frag0)
  * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN
+ * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to
+ *	ndo_hwtstamp_set() for all timestamp requests regardless of source,
+ *	even if those aren't HWTSTAMP_SOURCE_NETDEV.
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
···
 	IFF_NO_ADDRCONF			= BIT_ULL(30),
 	IFF_TX_SKB_NO_LINEAR		= BIT_ULL(31),
 	IFF_CHANGE_PROTO_DOWN		= BIT_ULL(32),
+	IFF_SEE_ALL_HWTSTAMP_REQUESTS	= BIT_ULL(33),
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN

net/core/dev_ioctl.c

···
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/net_tstamp.h>
+#include <linux/phylib_stubs.h>
 #include <linux/wireless.h>
 #include <linux/if_bridge.h>
 #include <net/dsa_stubs.h>
···
 	return ops->ndo_eth_ioctl(dev, ifr, cmd);
 }
 
+/**
+ * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC
+ *	or of attached phylib PHY
+ * @dev: Network device
+ * @cfg: Timestamping configuration structure
+ *
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev.
+ *
+ * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and
+ * there only exists a phydev->mii_ts->hwtstamp() method. So this will return
+ * -EOPNOTSUPP for phylib for now, which is still more accurate than letting
+ * the netdev handle the GET request.
+ */
+static int dev_get_hwtstamp_phylib(struct net_device *dev,
+				   struct kernel_hwtstamp_config *cfg)
+{
+	if (phy_has_hwtstamp(dev->phydev))
+		return phy_hwtstamp_get(dev->phydev, cfg);
+
+	return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
+}
+
 static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
···
 		return -ENODEV;
 
 	kernel_cfg.ifr = ifr;
-	err = ops->ndo_hwtstamp_get(dev, &kernel_cfg);
+	err = dev_get_hwtstamp_phylib(dev, &kernel_cfg);
 	if (err)
 		return err;
 
···
 
 		if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
 			return -EFAULT;
+	}
+
+	return 0;
+}
+
+/**
+ * dev_set_hwtstamp_phylib() - Change hardware timestamping of NIC
+ *	or of attached phylib PHY
+ * @dev: Network device
+ * @cfg: Timestamping configuration structure
+ * @extack: Netlink extended ack message structure, for error reporting
+ *
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev. If the netdev driver needs to perform specific actions even for PHY
+ * timestamping to work properly (a switch port must trap the timestamped
+ * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
+ * dev->priv_flags.
+ */
+static int dev_set_hwtstamp_phylib(struct net_device *dev,
+				   struct kernel_hwtstamp_config *cfg,
+				   struct netlink_ext_ack *extack)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	bool phy_ts = phy_has_hwtstamp(dev->phydev);
+	struct kernel_hwtstamp_config old_cfg = {};
+	bool changed = false;
+	int err;
+
+	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
+
+	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
+		if (err)
+			return err;
+
+		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
+		if (err) {
+			if (extack->_msg)
+				netdev_err(dev, "%s\n", extack->_msg);
+			return err;
+		}
+
+		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
+	}
+
+	if (phy_ts) {
+		err = phy_hwtstamp_set(dev->phydev, cfg, extack);
+		if (err) {
+			if (changed)
+				ops->ndo_hwtstamp_set(dev, &old_cfg, NULL);
+			return err;
+		}
 	}
 
 	return 0;
···
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	err = ops->ndo_hwtstamp_set(dev, &kernel_cfg, &extack);
-	if (err) {
-		if (extack._msg)
-			netdev_err(dev, "%s\n", extack._msg);
+	err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack);
+	if (err)
 		return err;
-	}
 
 	/* The driver may have modified the configuration, so copy the
 	 * updated version of it back to user space
···
 		return -ENODEV;
 
 	if (ops->ndo_hwtstamp_get)
-		return ops->ndo_hwtstamp_get(dev, kernel_cfg);
+		return dev_get_hwtstamp_phylib(dev, kernel_cfg);
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
···
 		return -ENODEV;
 
 	if (ops->ndo_hwtstamp_set)
-		return ops->ndo_hwtstamp_set(dev, kernel_cfg, extack);
+		return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);