Merge tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Increase size limits for to-be-sent skb frag allocations. This
     allows tun, tap devices and packet sockets to better cope with
     large writes operations

   - Store netdevs in an xarray, to simplify iterating over netdevs

   - Refactor nexthop selection for multipath routes

   - Improve sched class lifetime handling

   - Add backup nexthop ID support for bridge

   - Implement drop reasons support in openvswitch

   - Several data races annotations and fixes

   - Constify the sk parameter of routing functions

   - Prepend kernel version to netconsole message

  Protocols:

   - Implement support for TCP probing the peer being under memory
     pressure

   - Remove hard coded limitation on IPv6 specific info placement inside
     the socket struct

   - Get rid of sysctl_tcp_adv_win_scale and use an auto-estimated per
     socket scaling factor

   - Scaling-up the IPv6 expired route GC via a separated list of
     expiring routes

   - In-kernel support for the TLS alert protocol

   - Better support for UDP reuseport with connected sockets

   - Add NEXT-C-SID support for SRv6 End.X behavior, reducing the SR
     header size

   - Get rid of additional ancillary per MPTCP connection struct socket

   - Implement support for BPF-based MPTCP packet schedulers

   - Format MPTCP subtests selftests results in TAP

   - Several new SMC 2.1 features including unique experimental options,
     max connections per lgr negotiation, max links per lgr negotiation

  BPF:

   - Multi-buffer support in AF_XDP

   - Add multi uprobe BPF links for attaching multiple uprobes and usdt
     probes, which is significantly faster and saves extra fds

   - Implement an fd-based tc BPF attach API (TCX) and BPF link support
     on top of it

   - Add SO_REUSEPORT support for TC bpf_sk_assign

   - Support new instructions from cpu v4 to simplify the generated code
     and feature completeness, for x86, arm64, riscv64

   - Support defragmenting IPv(4|6) packets in BPF

   - Teach verifier actual bounds of bpf_get_smp_processor_id() and fix
     perf+libbpf issue related to custom section handling

   - Introduce bpf map element count and enable it for all program types

   - Add a BPF hook in sys_socket() to change the protocol ID from
     IPPROTO_TCP to IPPROTO_MPTCP to cover migration for legacy

   - Introduce bpf_me_mcache_free_rcu() and fix OOM under stress

   - Add uprobe support for the bpf_get_func_ip helper

   - Check skb ownership against full socket

   - Support for up to 12 arguments in BPF trampoline

   - Extend link_info for kprobe_multi and perf_event links

  Netfilter:

   - Speed-up process exit by aborting ruleset validation if a fatal
     signal is pending

   - Allow NLA_POLICY_MASK to be used with BE16/BE32 types

  Driver API:

   - Page pool optimizations, to improve data locality and cache usage

   - Introduce ndo_hwtstamp_get() and ndo_hwtstamp_set() to avoid the
     need for raw ioctl() handling in drivers

   - Simplify genetlink dump operations (doit/dumpit) providing them the
     common information already populated in struct genl_info

   - Extend and use the yaml devlink specs to [re]generate the split ops

   - Introduce devlink selective dumps, to allow SF filtering SF based
     on handle and other attributes

   - Add yaml netlink spec for netlink-raw families, allow route, link
     and address related queries via the ynl tool

   - Remove phylink legacy mode support

   - Support offload LED blinking to phy

   - Add devlink port function attributes for IPsec

  New hardware / drivers:

   - Ethernet:
      - Broadcom ASP 2.0 (72165) ethernet controller
      - MediaTek MT7988 SoC
      - Texas Instruments AM654 SoC
      - Texas Instruments IEP driver
      - Atheros qca8081 phy
      - Marvell 88Q2110 phy
      - NXP TJA1120 phy

   - WiFi:
      - MediaTek mt7981 support

   - Can:
      - Kvaser SmartFusion2 PCI Express devices
      - Allwinner T113 controllers
      - Texas Instruments tcan4552/4553 chips

   - Bluetooth:
      - Intel Gale Peak
      - Qualcomm WCN3988 and WCN7850
      - NXP AW693 and IW624
      - Mediatek MT2925

  Drivers:

   - Ethernet NICs:
      - nVidia/Mellanox:
         - mlx5:
            - support UDP encapsulation in packet offload mode
            - IPsec packet offload support in eswitch mode
            - improve aRFS observability by adding new set of counters
            - extends MACsec offload support to cover RoCE traffic
            - dynamic completion EQs
         - mlx4:
            - convert to use auxiliary bus instead of custom interface
              logic
      - Intel
         - ice:
            - implement switchdev bridge offload, even for LAG
              interfaces
            - implement SRIOV support for LAG interfaces
         - igc:
            - add support for multiple in-flight TX timestamps
      - Broadcom:
         - bnxt:
            - use the unified RX page pool buffers for XDP and non-XDP
            - use the NAPI skb allocation cache
      - OcteonTX2:
         - support Round Robin scheduling HTB offload
         - TC flower offload support for SPI field
      - Freescale:
         - add XDP_TX feature support
      - AMD:
         - ionic: add support for PCI FLR event
         - sfc:
            - basic conntrack offload
            - introduce eth, ipv4 and ipv6 pedit offloads
      - ST Microelectronics:
         - stmmac: maximze PTP timestamping resolution

   - Virtual NICs:
      - Microsoft vNIC:
         - batch ringing RX queue doorbell on receiving packets
         - add page pool for RX buffers
      - Virtio vNIC:
         - add per queue interrupt coalescing support
      - Google vNIC:
         - add queue-page-list mode support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add port range matching tc-flower offload
         - permit enslavement to netdevices with uppers

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - convert to phylink_pcs
      - Renesas:
         - r8A779fx: add speed change support
         - rzn1: enables vlan support

   - Ethernet PHYs:
      - convert mv88e6xxx to phylink_pcs

   - WiFi:
      - Qualcomm Wi-Fi 7 (ath12k):
         - extremely High Throughput (EHT) PHY support
      - RealTek (rtl8xxxu):
         - enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU),
           RTL8192EU and RTL8723BU
      - RealTek (rtw89):
         - Introduce Time Averaged SAR (TAS) support

   - Connector:
      - support for event filtering"

* tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1806 commits)
  net: ethernet: mtk_wed: minor change in wed_{tx,rx}info_show
  net: ethernet: mtk_wed: add some more info in wed_txinfo_show handler
  net: stmmac: clarify difference between "interface" and "phy_interface"
  r8152: add vendor/device ID pair for D-Link DUB-E250
  devlink: move devlink_notify_register/unregister() to dev.c
  devlink: move small_ops definition into netlink.c
  devlink: move tracepoint definitions into core.c
  devlink: push linecard related code into separate file
  devlink: push rate related code into separate file
  devlink: push trap related code into separate file
  devlink: use tracepoint_enabled() helper
  devlink: push region related code into separate file
  devlink: push param related code into separate file
  devlink: push resource related code into separate file
  devlink: push dpipe related code into separate file
  devlink: move and rename devlink_dpipe_send_and_alloc_skb() helper
  devlink: push shared buffer related code into separate file
  devlink: push port related code into separate file
  devlink: push object register/unregister notifications into separate helpers
  inet: fix IP_TRANSPARENT error handling
  ...

1 files changed, 100 insertions, 12 deletions

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 44b037646865..4dbc21f604f2 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -228,16 +228,39 @@ static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg,
 	return xpcs_write(xpcs, dev, DW_VENDOR | reg, val);
 }
 
-static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg)
+int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg)
 {
 	return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg);
 }
 
-static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
+int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
 {
 	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
 }
 
+static int xpcs_dev_flag(struct dw_xpcs *xpcs)
+{
+	int ret, oui;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID1);
+	if (ret < 0)
+		return ret;
+
+	oui = ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID2);
+	if (ret < 0)
+		return ret;
+
+	ret = (ret >> 10) & 0x3F;
+	oui |= ret << 16;
+
+	if (oui == DW_OUI_WX)
+		xpcs->dev_flag = DW_DEV_TXGBE;
+
+	return 0;
+}
+
 static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev)
 {
 	/* Poll until the reset bit clears (50ms per retry == 0.6 sec) */
@@ -660,7 +683,10 @@ EXPORT_SYMBOL_GPL(xpcs_config_eee);
 static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 				      unsigned int neg_mode)
 {
-	int ret, mdio_ctrl;
+	int ret, mdio_ctrl, tx_conf;
+
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_CL37_BP | DW_EN_VSMMD1);
 
 	/* For AN for C37 SGMII mode, the settings are :-
 	 * 1) VR_MII_MMD_CTRL Bit(12) [AN_ENABLE] = 0b (Disable SGMII AN in case
@@ -697,9 +723,15 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 	ret |= (DW_VR_MII_PCS_MODE_C37_SGMII <<
 		DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT &
 		DW_VR_MII_PCS_MODE_MASK);
-	ret |= (DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII <<
-		DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT &
-		DW_VR_MII_TX_CONFIG_MASK);
+	if (xpcs->dev_flag == DW_DEV_TXGBE) {
+		ret |= DW_VR_MII_AN_CTRL_8BIT;
+		/* Hardware requires it to be PHY side SGMII */
+		tx_conf = DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII;
+	} else {
+		tx_conf = DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII;
+	}
+	ret |= tx_conf << DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT &
+		DW_VR_MII_TX_CONFIG_MASK;
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_CTRL, ret);
 	if (ret < 0)
 		return ret;
@@ -713,6 +745,9 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs,
 	else
 		ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		ret |= DW_VR_MII_DIG_CTRL1_PHY_MODE_CTRL;
+
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret);
 	if (ret < 0)
 		return ret;
@@ -732,6 +767,9 @@ static int xpcs_config_aneg_c37_1000basex(struct dw_xpcs *xpcs,
 	int ret, mdio_ctrl, adv;
 	bool changed = 0;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE)
+		xpcs_write_vpcs(xpcs, DW_VR_XS_PCS_DIG_CTRL1, DW_CL37_BP | DW_EN_VSMMD1);
+
 	/* According to Chap 7.12, to set 1000BASE-X C37 AN, AN must
 	 * be disabled first:-
 	 * 1) VR_MII_MMD_CTRL Bit(12)[AN_ENABLE] = 0b
@@ -753,6 +791,8 @@ static int xpcs_config_aneg_c37_1000basex(struct dw_xpcs *xpcs,
 		return ret;
 
 	ret &= ~DW_VR_MII_PCS_MODE_MASK;
+	if (!xpcs->pcs.poll)
+		ret |= DW_VR_MII_AN_INTR_EN;
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_CTRL, ret);
 	if (ret < 0)
 		return ret;
@@ -818,6 +858,12 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
 	if (!compat)
 		return -ENODEV;
 
+	if (xpcs->dev_flag == DW_DEV_TXGBE) {
+		ret = txgbe_xpcs_switch_mode(xpcs, interface);
+		if (ret)
+			return ret;
+	}
+
 	switch (compat->an_mode) {
 	case DW_10GBASER:
 		break;
@@ -977,6 +1023,33 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
 			state->duplex = DUPLEX_FULL;
 		else
 			state->duplex = DUPLEX_HALF;
+	} else if (ret == DW_VR_MII_AN_STS_C37_ANCMPLT_INTR) {
+		int speed, duplex;
+
+		state->link = true;
+
+		speed = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1);
+		if (speed < 0)
+			return speed;
+
+		speed &= SGMII_SPEED_SS13 | SGMII_SPEED_SS6;
+		if (speed == SGMII_SPEED_SS6)
+			state->speed = SPEED_1000;
+		else if (speed == SGMII_SPEED_SS13)
+			state->speed = SPEED_100;
+		else if (speed == 0)
+			state->speed = SPEED_10;
+
+		duplex = xpcs_read(xpcs, MDIO_MMD_VEND2, MII_ADVERTISE);
+		if (duplex < 0)
+			return duplex;
+
+		if (duplex & DW_FULL_DUPLEX)
+			state->duplex = DUPLEX_FULL;
+		else if (duplex & DW_HALF_DUPLEX)
+			state->duplex = DUPLEX_HALF;
+
+		xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS, 0);
 	}
 
 	return 0;
@@ -1000,6 +1073,17 @@ static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs,
 		if (bmsr < 0)
 			return bmsr;
 
+		/* Clear AN complete interrupt */
+		if (!xpcs->pcs.poll) {
+			int an_intr;
+
+			an_intr = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
+			if (an_intr & DW_VR_MII_AN_STS_C37_ANCMPLT_INTR) {
+				an_intr &= ~DW_VR_MII_AN_STS_C37_ANCMPLT_INTR;
+				xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS, an_intr);
+			}
+		}
+
 		phylink_mii_c22_pcs_decode_state(state, bmsr, lpa);
 	}
 
@@ -1284,16 +1368,20 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
 			goto out;
 		}
 
+		ret = xpcs_dev_flag(xpcs);
+		if (ret)
+			goto out;
+
 		xpcs->pcs.ops = &xpcs_phylink_ops;
 		xpcs->pcs.neg_mode = true;
-		if (compat->an_mode == DW_10GBASER)
-			return xpcs;
 
-		xpcs->pcs.poll = true;
+		if (xpcs->dev_flag != DW_DEV_TXGBE) {
+			xpcs->pcs.poll = true;
 
-		ret = xpcs_soft_reset(xpcs, compat);
-		if (ret)
-			goto out;
+			ret = xpcs_soft_reset(xpcs, compat);
+			if (ret)
+				goto out;
+		}
 
 		return xpcs;
 	}