Merge tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Introduce and use a single page frag cache for allocating small skb
     heads, clawing back the 10-20% performance regression in UDP flood
     test from previous fixes.

   - Run packets which already went thru HW coalescing thru SW GRO. This
     significantly improves TCP segment coalescing and simplifies
     deployments as different workloads benefit from HW or SW GRO.

   - Shrink the size of the base zero-copy send structure.

   - Move TCP init under a new slow / sleepable version of DO_ONCE().

  BPF:

   - Add BPF-specific, any-context-safe memory allocator.

   - Add helpers/kfuncs for PKCS#7 signature verification from BPF
     programs.

   - Define a new map type and related helpers for user space -> kernel
     communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF).

   - Allow targeting BPF iterators to loop through resources of one
     task/thread.

   - Add ability to call selected destructive functions. Expose
     crash_kexec() to allow BPF to trigger a kernel dump. Use
     CAP_SYS_BOOT check on the loading process to judge permissions.

   - Enable BPF to collect custom hierarchical cgroup stats efficiently
     by integrating with the rstat framework.

   - Support struct arguments for trampoline based programs. Only
     structs with size <= 16B and x86 are supported.

   - Invoke cgroup/connect{4,6} programs for unprivileged ICMP ping
     sockets (instead of just TCP and UDP sockets).

   - Add a helper for accessing CLOCK_TAI for time sensitive network
     related programs.

   - Support accessing network tunnel metadata's flags.

   - Make TCP SYN ACK RTO tunable by BPF programs with TCP Fast Open.

   - Add support for writing to Netfilter's nf_conn:mark.

  Protocols:

   - WiFi: more Extremely High Throughput (EHT) and Multi-Link Operation
     (MLO) work (802.11be, WiFi 7).

   - vsock: improve support for SO_RCVLOWAT.

   - SMC: support SO_REUSEPORT.

   - Netlink: define and document how to use netlink in a "modern" way.
     Support reporting missing attributes via extended ACK.

   - IPSec: support collect metadata mode for xfrm interfaces.

   - TCPv6: send consistent autoflowlabel in SYN_RECV state and RST
     packets.

   - TCP: introduce optional per-netns connection hash table to allow
     better isolation between namespaces (opt-in, at the cost of memory
     and cache pressure).

   - MPTCP: support TCP_FASTOPEN_CONNECT.

   - Add NEXT-C-SID support in Segment Routing (SRv6) End behavior.

   - Adjust IP_UNICAST_IF sockopt behavior for connected UDP sockets.

   - Open vSwitch:
      - Allow specifying ifindex of new interfaces.
      - Allow conntrack and metering in non-initial user namespace.

   - TLS: support the Korean ARIA-GCM crypto algorithm.

   - Remove DECnet support.

  Driver API:

   - Allow selecting the conduit interface used by each port in DSA
     switches, at runtime.

   - Ethernet Power Sourcing Equipment and Power Device support.

   - Add tc-taprio support for queueMaxSDU parameter, i.e. setting per
     traffic class max frame size for time-based packet schedules.

   - Support PHY rate matching - adapting between differing host-side
     and link-side speeds.

   - Introduce QUSGMII PHY mode and 1000BASE-KX interface mode.

   - Validate OF (device tree) nodes for DSA shared ports; make
     phylink-related properties mandatory on DSA and CPU ports.
     Enforcing more uniformity should allow transitioning to phylink.

   - Require that flash component name used during update matches one of
     the components for which version is reported by info_get().

   - Remove "weight" argument from driver-facing NAPI API as much as
     possible. It's one of those magic knobs which seemed like a good
     idea at the time but is too indirect to use in practice.

   - Support offload of TLS connections with 256 bit keys.

  New hardware / drivers:

   - Ethernet:
      - Microchip KSZ9896 6-port Gigabit Ethernet Switch
      - Renesas Ethernet AVB (EtherAVB-IF) Gen4 SoCs
      - Analog Devices ADIN1110 and ADIN2111 industrial single pair
        Ethernet (10BASE-T1L) MAC+PHY.
      - Rockchip RV1126 Gigabit Ethernet (a version of stmmac IP).

   - Ethernet SFPs / modules:
      - RollBall / Hilink / Turris 10G copper SFPs
      - HALNy GPON module

   - WiFi:
      - CYW43439 SDIO chipset (brcmfmac)
      - CYW89459 PCIe chipset (brcmfmac)
      - BCM4378 on Apple platforms (brcmfmac)

  Drivers:

   - CAN:
      - gs_usb: HW timestamp support

   - Ethernet PHYs:
      - lan8814: cable diagnostics

   - Ethernet NICs:
      - Intel (100G):
         - implement control of FCS/CRC stripping
         - port splitting via devlink
         - L2TPv3 filtering offload
      - nVidia/Mellanox:
         - tunnel offload for sub-functions
         - MACSec offload, w/ Extended packet number and replay window
           offload
         - significantly restructure, and optimize the AF_XDP support,
           align the behavior with other vendors
      - Huawei:
         - configuring DSCP map for traffic class selection
         - querying standard FEC statistics
         - querying SerDes lane number via ethtool
      - Marvell/Cavium:
         - egress priority flow control
         - MACSec offload
      - AMD/SolarFlare:
         - PTP over IPv6 and raw Ethernet
      - small / embedded:
         - ax88772: convert to phylink (to support SFP cages)
         - altera: tse: convert to phylink
         - ftgmac100: support fixed link
         - enetc: standard Ethtool counters
         - macb: ZynqMP SGMII dynamic configuration support
         - tsnep: support multi-queue and use page pool
         - lan743x: Rx IP & TCP checksum offload
         - igc: add xdp frags support to ndo_xdp_xmit

   - Ethernet high-speed switches:
      - Marvell (prestera):
         - support SPAN port features (traffic mirroring)
         - nexthop object offloading
      - Microchip (sparx5):
         - multicast forwarding offload
         - QoS queuing offload (tc-mqprio, tc-tbf, tc-ets)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - support RGMII cmode
      - NXP (felix):
         - standardized ethtool counters
      - Microchip (lan966x):
         - QoS queuing offload (tc-mqprio, tc-tbf, tc-cbs, tc-ets)
         - traffic policing and mirroring
         - link aggregation / bonding offload
         - QUSGMII PHY mode support

   - Qualcomm 802.11ax WiFi (ath11k):
      - cold boot calibration support on WCN6750
      - support to connect to a non-transmit MBSSID AP profile
      - enable remain-on-channel support on WCN6750
      - Wake-on-WLAN support for WCN6750
      - support to provide transmit power from firmware via nl80211
      - support to get power save duration for each client
      - spectral scan support for 160 MHz

   - MediaTek WiFi (mt76):
      - WiFi-to-Ethernet bridging offload for MT7986 chips

   - RealTek WiFi (rtw89):
      - P2P support"

* tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1864 commits)
  eth: pse: add missing static inlines
  once: rename _SLOW to _SLEEPABLE
  net: pse-pd: add regulator based PSE driver
  dt-bindings: net: pse-dt: add bindings for regulator based PoDL PSE controller
  ethtool: add interface to interact with Ethernet Power Equipment
  net: mdiobus: search for PSE nodes by parsing PHY nodes.
  net: mdiobus: fwnode_mdiobus_register_phy() rework error handling
  net: add framework to support Ethernet PSE and PDs devices
  dt-bindings: net: phy: add PoDL PSE property
  net: marvell: prestera: Propagate nh state from hw to kernel
  net: marvell: prestera: Add neighbour cache accounting
  net: marvell: prestera: add stub handler neighbour events
  net: marvell: prestera: Add heplers to interact with fib_notifier_info
  net: marvell: prestera: Add length macros for prestera_ip_addr
  net: marvell: prestera: add delayed wq and flush wq on deinit
  net: marvell: prestera: Add strict cleanup of fib arbiter
  net: marvell: prestera: Add cleanup of allocated fib_nodes
  net: marvell: prestera: Add router nexthops ABI
  eth: octeon: fix build after netif_napi_add() changes
  net/mlx5: E-Switch, Return EBUSY if can't get mode lock
  ...

1 files changed, 225 insertions, 29 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index b1b1b648e40c..22a5d2419084 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -205,7 +205,7 @@ nfp_get_drvinfo(struct nfp_app *app, struct pci_dev *pdev,
 {
 	char nsp_version[ETHTOOL_FWVERS_LEN] = {};
 
-	strlcpy(drvinfo->driver, dev_driver_string(&pdev->dev),
+	strscpy(drvinfo->driver, dev_driver_string(&pdev->dev),
 		sizeof(drvinfo->driver));
 	nfp_net_get_nspinfo(app, nsp_version);
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
@@ -222,18 +222,49 @@ nfp_net_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 	snprintf(vnic_version, sizeof(vnic_version), "%d.%d.%d.%d",
 		 nn->fw_ver.extend, nn->fw_ver.class,
 		 nn->fw_ver.major, nn->fw_ver.minor);
-	strlcpy(drvinfo->bus_info, pci_name(nn->pdev),
+	strscpy(drvinfo->bus_info, pci_name(nn->pdev),
 		sizeof(drvinfo->bus_info));
 
 	nfp_get_drvinfo(nn->app, nn->pdev, vnic_version, drvinfo);
 }
 
+static int
+nfp_net_nway_reset(struct net_device *netdev)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+	int err;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return -EOPNOTSUPP;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	err = nfp_eth_set_configured(port->app->cpp, eth_port->index, false);
+	if (err) {
+		netdev_info(netdev, "Link down failed: %d\n", err);
+		return err;
+	}
+
+	err = nfp_eth_set_configured(port->app->cpp, eth_port->index, true);
+	if (err) {
+		netdev_info(netdev, "Link up failed: %d\n", err);
+		return err;
+	}
+
+	netdev_info(netdev, "Link reset succeeded\n");
+	return 0;
+}
+
 static void
 nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 {
 	struct nfp_app *app = nfp_app_from_netdev(netdev);
 
-	strlcpy(drvinfo->bus_info, pci_name(app->pdev),
+	strscpy(drvinfo->bus_info, pci_name(app->pdev),
 		sizeof(drvinfo->bus_info));
 	nfp_get_drvinfo(app, app->pdev, "*", drvinfo);
 }
@@ -273,20 +304,11 @@ static int
 nfp_net_get_link_ksettings(struct net_device *netdev,
 			   struct ethtool_link_ksettings *cmd)
 {
-	static const u32 ls_to_ethtool[] = {
-		[NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED]	= 0,
-		[NFP_NET_CFG_STS_LINK_RATE_UNKNOWN]	= SPEED_UNKNOWN,
-		[NFP_NET_CFG_STS_LINK_RATE_1G]		= SPEED_1000,
-		[NFP_NET_CFG_STS_LINK_RATE_10G]		= SPEED_10000,
-		[NFP_NET_CFG_STS_LINK_RATE_25G]		= SPEED_25000,
-		[NFP_NET_CFG_STS_LINK_RATE_40G]		= SPEED_40000,
-		[NFP_NET_CFG_STS_LINK_RATE_50G]		= SPEED_50000,
-		[NFP_NET_CFG_STS_LINK_RATE_100G]	= SPEED_100000,
-	};
 	struct nfp_eth_table_port *eth_port;
 	struct nfp_port *port;
 	struct nfp_net *nn;
-	u32 sts, ls;
+	unsigned int speed;
+	u16 sts;
 
 	/* Init to unknowns */
 	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
@@ -299,8 +321,13 @@ nfp_net_get_link_ksettings(struct net_device *netdev,
 	if (eth_port) {
 		ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
-		cmd->base.autoneg = eth_port->aneg != NFP_ANEG_DISABLED ?
-			AUTONEG_ENABLE : AUTONEG_DISABLE;
+		if (eth_port->supp_aneg) {
+			ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+			if (eth_port->aneg == NFP_ANEG_AUTO) {
+				ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
+				cmd->base.autoneg = AUTONEG_ENABLE;
+			}
+		}
 		nfp_net_set_fec_link_mode(eth_port, cmd);
 	}
 
@@ -319,18 +346,15 @@ nfp_net_get_link_ksettings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	nn = netdev_priv(netdev);
 
-	sts = nn_readl(nn, NFP_NET_CFG_STS);
-
-	ls = FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts);
-	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED)
+	sts = nn_readw(nn, NFP_NET_CFG_STS);
+	speed = nfp_net_lr2speed(FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts));
+	if (!speed)
 		return -EOPNOTSUPP;
 
-	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNKNOWN ||
-	    ls >= ARRAY_SIZE(ls_to_ethtool))
-		return 0;
-
-	cmd->base.speed = ls_to_ethtool[ls];
-	cmd->base.duplex = DUPLEX_FULL;
+	if (speed != SPEED_UNKNOWN) {
+		cmd->base.speed = speed;
+		cmd->base.duplex = DUPLEX_FULL;
+	}
 
 	return 0;
 }
@@ -339,6 +363,7 @@ static int
 nfp_net_set_link_ksettings(struct net_device *netdev,
 			   const struct ethtool_link_ksettings *cmd)
 {
+	bool req_aneg = (cmd->base.autoneg == AUTONEG_ENABLE);
 	struct nfp_eth_table_port *eth_port;
 	struct nfp_port *port;
 	struct nfp_nsp *nsp;
@@ -358,13 +383,25 @@ nfp_net_set_link_ksettings(struct net_device *netdev,
 	if (IS_ERR(nsp))
 		return PTR_ERR(nsp);
 
-	err = __nfp_eth_set_aneg(nsp, cmd->base.autoneg == AUTONEG_ENABLE ?
-				 NFP_ANEG_AUTO : NFP_ANEG_DISABLED);
+	if (req_aneg && !eth_port->supp_aneg) {
+		netdev_warn(netdev, "Autoneg is not supported.\n");
+		err = -EOPNOTSUPP;
+		goto err_bad_set;
+	}
+
+	err = __nfp_eth_set_aneg(nsp, req_aneg ? NFP_ANEG_AUTO : NFP_ANEG_DISABLED);
 	if (err)
 		goto err_bad_set;
+
 	if (cmd->base.speed != SPEED_UNKNOWN) {
 		u32 speed = cmd->base.speed / eth_port->lanes;
 
+		if (req_aneg) {
+			netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n");
+			err = -EINVAL;
+			goto err_bad_set;
+		}
+
 		err = __nfp_eth_set_speed(nsp, speed);
 		if (err)
 			goto err_bad_set;
@@ -1008,7 +1045,7 @@ nfp_port_get_fecparam(struct net_device *netdev,
 		return 0;
 
 	param->fec = nfp_port_fec_nsp_to_ethtool(eth_port->fec_modes_supported);
-	param->active_fec = nfp_port_fec_nsp_to_ethtool(eth_port->fec);
+	param->active_fec = nfp_port_fec_nsp_to_ethtool(BIT(eth_port->act_fec));
 
 	return 0;
 }
@@ -1676,11 +1713,166 @@ static int nfp_net_set_phys_id(struct net_device *netdev,
 	return err;
 }
 
+#define NFP_EEPROM_LEN ETH_ALEN
+
+static int
+nfp_net_get_eeprom_len(struct net_device *netdev)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = __nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return 0;
+
+	return NFP_EEPROM_LEN;
+}
+
+static int
+nfp_net_get_nsp_hwindex(struct net_device *netdev,
+			struct nfp_nsp **nspptr,
+			u32 *index)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+	struct nfp_nsp *nsp;
+	int err;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = __nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return -EOPNOTSUPP;
+
+	nsp = nfp_nsp_open(port->app->cpp);
+	if (IS_ERR(nsp)) {
+		err = PTR_ERR(nsp);
+		netdev_err(netdev, "Failed to access the NSP: %d\n", err);
+		return err;
+	}
+
+	if (!nfp_nsp_has_hwinfo_lookup(nsp)) {
+		netdev_err(netdev, "NSP doesn't support PF MAC generation\n");
+		nfp_nsp_close(nsp);
+		return -EOPNOTSUPP;
+	}
+
+	*nspptr = nsp;
+	*index = eth_port->eth_index;
+
+	return 0;
+}
+
+static int
+nfp_net_get_port_mac_by_hwinfo(struct net_device *netdev,
+			       u8 *mac_addr)
+{
+	char hwinfo[32] = {};
+	struct nfp_nsp *nsp;
+	u32 index;
+	int err;
+
+	err = nfp_net_get_nsp_hwindex(netdev, &nsp, &index);
+	if (err)
+		return err;
+
+	snprintf(hwinfo, sizeof(hwinfo), "eth%u.mac", index);
+	err = nfp_nsp_hwinfo_lookup(nsp, hwinfo, sizeof(hwinfo));
+	nfp_nsp_close(nsp);
+	if (err) {
+		netdev_err(netdev, "Reading persistent MAC address failed: %d\n",
+			   err);
+		return -EOPNOTSUPP;
+	}
+
+	if (sscanf(hwinfo, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+		   &mac_addr[0], &mac_addr[1], &mac_addr[2],
+		   &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) {
+		netdev_err(netdev, "Can't parse persistent MAC address (%s)\n",
+			   hwinfo);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nfp_net_set_port_mac_by_hwinfo(struct net_device *netdev,
+			       u8 *mac_addr)
+{
+	char hwinfo[32] = {};
+	struct nfp_nsp *nsp;
+	u32 index;
+	int err;
+
+	err = nfp_net_get_nsp_hwindex(netdev, &nsp, &index);
+	if (err)
+		return err;
+
+	snprintf(hwinfo, sizeof(hwinfo),
+		 "eth%u.mac=%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+		 index, mac_addr[0], mac_addr[1], mac_addr[2], mac_addr[3],
+		 mac_addr[4], mac_addr[5]);
+
+	err = nfp_nsp_hwinfo_set(nsp, hwinfo, sizeof(hwinfo));
+	nfp_nsp_close(nsp);
+	if (err) {
+		netdev_err(netdev, "HWinfo set failed: %d, hwinfo: %s\n",
+			   err, hwinfo);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nfp_net_get_eeprom(struct net_device *netdev,
+		   struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	u8 buf[NFP_EEPROM_LEN] = {};
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	if (nfp_net_get_port_mac_by_hwinfo(netdev, buf))
+		return -EOPNOTSUPP;
+
+	eeprom->magic = nn->pdev->vendor | (nn->pdev->device << 16);
+	memcpy(bytes, buf + eeprom->offset, eeprom->len);
+
+	return 0;
+}
+
+static int
+nfp_net_set_eeprom(struct net_device *netdev,
+		   struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	u8 buf[NFP_EEPROM_LEN] = {};
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	if (eeprom->magic != (nn->pdev->vendor | nn->pdev->device << 16))
+		return -EINVAL;
+
+	if (nfp_net_get_port_mac_by_hwinfo(netdev, buf))
+		return -EOPNOTSUPP;
+
+	memcpy(buf + eeprom->offset, bytes, eeprom->len);
+	if (nfp_net_set_port_mac_by_hwinfo(netdev, buf))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
 	.get_drvinfo		= nfp_net_get_drvinfo,
+	.nway_reset             = nfp_net_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= nfp_net_get_ringparam,
 	.set_ringparam		= nfp_net_set_ringparam,
@@ -1699,6 +1891,9 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.set_dump		= nfp_app_set_dump,
 	.get_dump_flag		= nfp_app_get_dump_flag,
 	.get_dump_data		= nfp_app_get_dump_data,
+	.get_eeprom_len         = nfp_net_get_eeprom_len,
+	.get_eeprom             = nfp_net_get_eeprom,
+	.set_eeprom             = nfp_net_set_eeprom,
 	.get_module_info	= nfp_port_get_module_info,
 	.get_module_eeprom	= nfp_port_get_module_eeprom,
 	.get_coalesce           = nfp_net_get_coalesce,
@@ -1715,6 +1910,7 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 
 const struct ethtool_ops nfp_port_ethtool_ops = {
 	.get_drvinfo		= nfp_app_get_drvinfo,
+	.nway_reset             = nfp_net_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_strings		= nfp_port_get_strings,
 	.get_ethtool_stats	= nfp_port_get_stats,