Merge tag 'net-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Support HW queue leasing, allowing containers to be granted access
     to HW queues for zero-copy operations and AF_XDP

   - Number of code moves to help the compiler with inlining. Avoid
     output arguments for returning drop reason where possible

   - Rework drop handling within qdiscs to include more metadata about
     the reason and dropping qdisc in the tracepoints

   - Remove the rtnl_lock use from IP Multicast Routing

   - Pack size information into the Rx Flow Steering table pointer
     itself. This allows making the table itself a flat array of u32s,
     thus making the table allocation size a power of two

   - Report TCP delayed ack timer information via socket diag

   - Add ip_local_port_step_width sysctl to allow distributing the
     randomly selected ports more evenly throughout the allowed space

   - Add support for per-route tunsrc in IPv6 segment routing

   - Start work of switching sockopt handling to iov_iter

   - Improve dynamic recvbuf sizing in MPTCP, limit burstiness and avoid
     buffer size drifting up

   - Support MSG_EOR in MPTCP

   - Add stp_mode attribute to the bridge driver for STP mode selection.
     This addresses concerns about call_usermodehelper() usage

   - Remove UDP-Lite support (as announced in 2023)

   - Remove support for building IPv6 as a module. Remove the now
     unnecessary function calling indirection

  Cross-tree stuff:

   - Move Michael MIC code from generic crypto into wireless, it's
     considered insecure but some WiFi networks still need it

  Netfilter:

   - Switch nft_fib_ipv6 module to no longer need temporary dst_entry
     object allocations by using fib6_lookup() + RCU.

     Florian W reports this gets us ~13% higher packet rate

   - Convert IPVS's global __ip_vs_mutex to per-net service_mutex and
     switch the service tables to be per-net. Convert some code that
     walks the service lists to use RCU instead of the service_mutex

   - Add more opinionated input validation to lower security exposure

   - Make IPVS hash tables to be per-netns and resizable

  Wireless:

   - Finished assoc frame encryption/EPPKE/802.1X-over-auth

   - Radar detection improvements

   - Add 6 GHz incumbent signal detection APIs

   - Multi-link support for FILS, probe response templates and client
     probing

   - New APIs and mac80211 support for NAN (Neighbor Aware Networking,
     aka Wi-Fi Aware) so less work must be in firmware

  Driver API:

   - Add numerical ID for devlink instances (to avoid having to create
     fake bus/device pairs just to have an ID). Support shared devlink
     instances which span multiple PFs

   - Add standard counters for reporting pause storm events (implement
     in mlx5 and fbnic)

   - Add configuration API for completion writeback buffering (implement
     in mana)

   - Support driver-initiated change of RSS context sizes

   - Support DPLL monitoring input frequency (implement in zl3073x)

   - Support per-port resources in devlink (implement in mlx5)

  Misc:

   - Expand the YAML spec for Netfilter

  Drivers

   - Software:
      - macvlan: support multicast rx for bridge ports with shared
        source MAC address
      - team: decouple receive and transmit enablement for IEEE 802.3ad
        LACP "independent control"

   - Ethernet high-speed NICs:
      - nVidia/Mellanox:
         - support high order pages in zero-copy mode (for payload
           coalescing)
         - support multiple packets in a page (for systems with 64kB
           pages)
      - Broadcom 25-400GE (bnxt):
         - implement XDP RSS hash metadata extraction
         - add software fallback for UDP GSO, lowering the IOMMU cost
      - Broadcom 800GE (bnge):
         - add link status and configuration handling
         - add various HW and SW statistics
      - Marvell/Cavium:
         - NPC HW block support for cn20k
      - Huawei (hinic3):
         - add mailbox / control queue
         - add rx VLAN offload
         - add driver info and link management

   - Ethernet NICs:
      - Marvell/Aquantia:
         - support reading SFP module info on some AQC100 cards
      - Realtek PCI (r8169):
         - add support for RTL8125cp
      - Realtek USB (r8152):
         - support for the RTL8157 5Gbit chip
         - add 2500baseT EEE status/configuration support

   - Ethernet NICs embedded and off-the-shelf IP:
      - Synopsys (stmmac):
         - cleanup and reorganize SerDes handling and PCS support
         - cleanup descriptor handling and per-platform data
         - cleanup and consolidate MDIO defines and handling
         - shrink driver memory use for internal structures
         - improve Tx IRQ coalescing
         - improve TCP segmentation handling
         - add support for Spacemit K3
      - Cadence (macb):
         - support PHYs that have inband autoneg disabled with GEM
         - support IEEE 802.3az EEE
         - rework usrio capabilities and handling
      - AMD (xgbe):
         - improve power management for S0i3
         - improve TX resilience for link-down handling

   - Virtual:
      - Google cloud vNIC:
         - support larger ring sizes in DQO-QPL mode
         - improve HW-GRO handling
         - support UDP GSO for DQO format
      - PCIe NTB:
         - support queue count configuration

   - Ethernet PHYs:
      - automatically disable PHY autonomous EEE if MAC is in charge
      - Broadcom:
         - add BCM84891/BCM84892 support
      - Micrel:
         - support for LAN9645X internal PHY
      - Realtek:
         - add RTL8224 pair order support
         - support PHY LEDs on RTL8211F-VD
         - support spread spectrum clocking (SSC)
      - Maxlinear:
         - add PHY-level statistics via ethtool

   - Ethernet switches:
      - Maxlinear (mxl862xx):
         - support for bridge offloading
         - support for VLANs
         - support driver statistics

   - Bluetooth:
      - large number of fixes and new device IDs
      - Mediatek:
         - support MT6639 (MT7927)
         - support MT7902 SDIO

   - WiFi:
      - Intel (iwlwifi):
         - UNII-9 and continuing UHR work
      - MediaTek (mt76):
         - mt7996/mt7925 MLO fixes/improvements
         - mt7996 NPU support (HW eth/wifi traffic offload)
      - Qualcomm (ath12k):
         - monitor mode support on IPQ5332
         - basic hwmon temperature reporting
         - support IPQ5424
      - Realtek:
         - add USB RX aggregation to improve performance
         - add USB TX flow control by tracking in-flight URBs

   - Cellular:
      - IPA v5.2 support"

* tag 'net-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1561 commits)
  net: pse-pd: fix kernel-doc function name for pse_control_find_by_id()
  wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit
  wireguard: allowedips: remove redundant space
  tools: ynl: add sample for wireguard
  wireguard: allowedips: Use kfree_rcu() instead of call_rcu()
  MAINTAINERS: Add netkit selftest files
  selftests/net: Add additional test coverage in nk_qlease
  selftests/net: Split netdevsim tests from HW tests in nk_qlease
  tools/ynl: Make YnlFamily closeable as a context manager
  net: airoha: Add missing PPE configurations in airoha_ppe_hw_init()
  net: airoha: Fix VIP configuration for AN7583 SoC
  net: caif: clear client service pointer on teardown
  net: strparser: fix skb_head leak in strp_abort_strp()
  net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete()
  selftests/bpf: add test for xdp_master_redirect with bond not up
  net, bpf: fix null-ptr-deref in xdp_master_redirect() for down master
  net: airoha: Remove PCE_MC_EN_MASK bit in REG_FE_PCE_CFG configuration
  sctp: disable BH before calling udp_tunnel_xmit_skb()
  sctp: fix missing encap_port propagation for GSO fragments
  net: airoha: Rely on net_device pointer in ETS callbacks
  ...

1 files changed, 203 insertions, 1 deletions

diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c
index d7f7cc44c532..2ae70dcf82ec 100644
--- a/drivers/net/phy/bcm84881.c
+++ b/drivers/net/phy/bcm84881.c
@@ -20,6 +20,33 @@ enum {
 	MDIO_AN_C22 = 0xffe0,
 };
 
+/* BCM8489x LED controller (BCM84891L datasheet 2.4.1.58). Each pin has
+ * CTL bits in 0xA83B (stride 3: 2-bit CTL + 1-bit OE_N) plus MASK_LOW/
+ * MASK_EXT source selects. LED4 is firmware-controlled; always RMW.
+ */
+#define BCM8489X_LED_CTL		0xa83b
+#define BCM8489X_LED_CTL_ON(i)		(0x2 << ((i) * 3))
+#define BCM8489X_LED_CTL_MASK(i)	(0x3 << ((i) * 3))
+
+#define BCM8489X_LED_SRC_RX		BIT(1)
+#define BCM8489X_LED_SRC_TX		BIT(2)
+#define BCM8489X_LED_SRC_1000		BIT(3)	/* high only at 1000 */
+#define BCM8489X_LED_SRC_100_1000	BIT(4)	/* high at 100 and 1000 */
+#define BCM8489X_LED_SRC_FORCE		BIT(5)	/* always-1 source */
+#define BCM8489X_LED_SRC_10G		BIT(7)
+#define BCM8489X_LED_SRCX_2500		BIT(2)
+#define BCM8489X_LED_SRCX_5000		BIT(3)
+
+#define BCM8489X_MAX_LEDS		2
+
+static const struct {
+	u16 mask_low;
+	u16 mask_ext;
+} bcm8489x_led_regs[BCM8489X_MAX_LEDS] = {
+	{ 0xa82c, 0xa8ef },	/* LED1 */
+	{ 0xa82f, 0xa8f0 },	/* LED2 */
+};
+
 static int bcm84881_wait_init(struct phy_device *phydev)
 {
 	int val;
@@ -54,6 +81,142 @@ static int bcm84881_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+static int bcm8489x_config_init(struct phy_device *phydev)
+{
+	__set_bit(PHY_INTERFACE_MODE_USXGMII, phydev->possible_interfaces);
+
+	if (phydev->interface != PHY_INTERFACE_MODE_USXGMII)
+		return -ENODEV;
+
+	/* MDIO_CTRL1_LPOWER is set at boot on the tested platform. Does not
+	 * recur on ifdown/ifup, cable events, or link-partner advertisement
+	 * changes; clear it once.
+	 */
+	return phy_clear_bits_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1,
+				  MDIO_CTRL1_LPOWER);
+}
+
+static int bcm8489x_led_write(struct phy_device *phydev, u8 index,
+			      u16 low, u16 ext)
+{
+	int ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD,
+			    bcm8489x_led_regs[index].mask_low, low);
+	if (ret)
+		return ret;
+	ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD,
+			    bcm8489x_led_regs[index].mask_ext, ext);
+	if (ret)
+		return ret;
+	return phy_modify_mmd(phydev, MDIO_MMD_PMAPMD, BCM8489X_LED_CTL,
+			      BCM8489X_LED_CTL_MASK(index),
+			      (low | ext) ? BCM8489X_LED_CTL_ON(index) : 0);
+}
+
+static int bcm8489x_led_brightness_set(struct phy_device *phydev,
+				       u8 index, enum led_brightness value)
+{
+	if (index >= BCM8489X_MAX_LEDS)
+		return -EINVAL;
+
+	return bcm8489x_led_write(phydev, index,
+				  value ? BCM8489X_LED_SRC_FORCE : 0, 0);
+}
+
+static const unsigned long bcm8489x_supported_triggers =
+	BIT(TRIGGER_NETDEV_LINK) |
+	BIT(TRIGGER_NETDEV_LINK_100) |
+	BIT(TRIGGER_NETDEV_LINK_1000) |
+	BIT(TRIGGER_NETDEV_LINK_2500) |
+	BIT(TRIGGER_NETDEV_LINK_5000) |
+	BIT(TRIGGER_NETDEV_LINK_10000) |
+	BIT(TRIGGER_NETDEV_RX) |
+	BIT(TRIGGER_NETDEV_TX);
+
+static int bcm8489x_led_hw_is_supported(struct phy_device *phydev, u8 index,
+					unsigned long rules)
+{
+	if (index >= BCM8489X_MAX_LEDS)
+		return -EINVAL;
+
+	if (rules & ~bcm8489x_supported_triggers)
+		return -EOPNOTSUPP;
+
+	/* Source bit 4 lights at both 100 and 1000; "100 only" isn't
+	 * representable in hardware. Accept LINK_100 only alongside
+	 * LINK_1000 or LINK so the offload is precise.
+	 */
+	if ((rules & BIT(TRIGGER_NETDEV_LINK_100)) &&
+	    !(rules & (BIT(TRIGGER_NETDEV_LINK_1000) |
+		       BIT(TRIGGER_NETDEV_LINK))))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int bcm8489x_led_hw_control_set(struct phy_device *phydev, u8 index,
+				       unsigned long rules)
+{
+	u16 low = 0, ext = 0;
+
+	if (index >= BCM8489X_MAX_LEDS)
+		return -EINVAL;
+
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK)))
+		low |= BCM8489X_LED_SRC_100_1000;
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK)))
+		low |= BCM8489X_LED_SRC_1000;
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_2500) | BIT(TRIGGER_NETDEV_LINK)))
+		ext |= BCM8489X_LED_SRCX_2500;
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_5000) | BIT(TRIGGER_NETDEV_LINK)))
+		ext |= BCM8489X_LED_SRCX_5000;
+	if (rules & (BIT(TRIGGER_NETDEV_LINK_10000) | BIT(TRIGGER_NETDEV_LINK)))
+		low |= BCM8489X_LED_SRC_10G;
+	if (rules & BIT(TRIGGER_NETDEV_RX))
+		low |= BCM8489X_LED_SRC_RX;
+	if (rules & BIT(TRIGGER_NETDEV_TX))
+		low |= BCM8489X_LED_SRC_TX;
+
+	return bcm8489x_led_write(phydev, index, low, ext);
+}
+
+static int bcm8489x_led_hw_control_get(struct phy_device *phydev, u8 index,
+				       unsigned long *rules)
+{
+	int low, ext;
+
+	if (index >= BCM8489X_MAX_LEDS)
+		return -EINVAL;
+
+	low = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
+			   bcm8489x_led_regs[index].mask_low);
+	if (low < 0)
+		return low;
+	ext = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
+			   bcm8489x_led_regs[index].mask_ext);
+	if (ext < 0)
+		return ext;
+
+	*rules = 0;
+	if (low & BCM8489X_LED_SRC_100_1000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_100);
+	if (low & BCM8489X_LED_SRC_1000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_1000);
+	if (ext & BCM8489X_LED_SRCX_2500)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_2500);
+	if (ext & BCM8489X_LED_SRCX_5000)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_5000);
+	if (low & BCM8489X_LED_SRC_10G)
+		*rules |= BIT(TRIGGER_NETDEV_LINK_10000);
+	if (low & BCM8489X_LED_SRC_RX)
+		*rules |= BIT(TRIGGER_NETDEV_RX);
+	if (low & BCM8489X_LED_SRC_TX)
+		*rules |= BIT(TRIGGER_NETDEV_TX);
+
+	return 0;
+}
+
 static int bcm84881_probe(struct phy_device *phydev)
 {
 	/* This driver requires PMAPMD and AN blocks */
@@ -201,6 +364,15 @@ static int bcm84881_read_status(struct phy_device *phydev)
 		return 0;
 	}
 
+	/* BCM84891/92 on USXGMII: the host interface mode doesn't change
+	 * with copper speed (USXGMII symbol replication; the MAC receives
+	 * the negotiated copper speed, not 10G, so no rate adaptation).
+	 * Skip 0x4011; phy_resolve_aneg_linkmode() above already set the
+	 * speed. Only bcm8489x_config_init() allows USXGMII.
+	 */
+	if (phydev->interface == PHY_INTERFACE_MODE_USXGMII)
+		return genphy_c45_read_mdix(phydev);
+
 	/* Set the host link mode - we set the phy interface mode and
 	 * the speed according to this register so that downshift works.
 	 * We leave the duplex setting as per the resolution from the
@@ -256,6 +428,34 @@ static struct phy_driver bcm84881_drivers[] = {
 		.config_aneg	= bcm84881_config_aneg,
 		.aneg_done	= bcm84881_aneg_done,
 		.read_status	= bcm84881_read_status,
+	}, {
+		PHY_ID_MATCH_MODEL(0x35905080),
+		.name		= "Broadcom BCM84891",
+		.inband_caps	= bcm84881_inband_caps,
+		.config_init	= bcm8489x_config_init,
+		.probe		= bcm84881_probe,
+		.get_features	= bcm84881_get_features,
+		.config_aneg	= bcm84881_config_aneg,
+		.aneg_done	= bcm84881_aneg_done,
+		.read_status	= bcm84881_read_status,
+		.led_brightness_set = bcm8489x_led_brightness_set,
+		.led_hw_is_supported = bcm8489x_led_hw_is_supported,
+		.led_hw_control_set = bcm8489x_led_hw_control_set,
+		.led_hw_control_get = bcm8489x_led_hw_control_get,
+	}, {
+		PHY_ID_MATCH_MODEL(0x359050a0),
+		.name		= "Broadcom BCM84892",
+		.inband_caps	= bcm84881_inband_caps,
+		.config_init	= bcm8489x_config_init,
+		.probe		= bcm84881_probe,
+		.get_features	= bcm84881_get_features,
+		.config_aneg	= bcm84881_config_aneg,
+		.aneg_done	= bcm84881_aneg_done,
+		.read_status	= bcm84881_read_status,
+		.led_brightness_set = bcm8489x_led_brightness_set,
+		.led_hw_is_supported = bcm8489x_led_hw_is_supported,
+		.led_hw_control_set = bcm8489x_led_hw_control_set,
+		.led_hw_control_get = bcm8489x_led_hw_control_get,
 	},
 };
 
@@ -264,9 +464,11 @@ module_phy_driver(bcm84881_drivers);
 /* FIXME: module auto-loading for Clause 45 PHYs seems non-functional */
 static const struct mdio_device_id __maybe_unused bcm84881_tbl[] = {
 	{ 0xae025150, 0xfffffff0 },
+	{ PHY_ID_MATCH_MODEL(0x35905080) },
+	{ PHY_ID_MATCH_MODEL(0x359050a0) },
 	{ },
 };
 MODULE_AUTHOR("Russell King");
-MODULE_DESCRIPTION("Broadcom BCM84881 PHY driver");
+MODULE_DESCRIPTION("Broadcom BCM84881/BCM84891/BCM84892 PHY driver");
 MODULE_DEVICE_TABLE(mdio, bcm84881_tbl);
 MODULE_LICENSE("GPL");