Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 451 insertions, 0 deletions

diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
new file mode 100644
index 000000000..a8c3be4eb
--- /dev/null
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
@@ -0,0 +1,451 @@
+/***********************license start***************
+ * Author: Cavium Networks
+ *
+ * Contact: support@caviumnetworks.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (C) 2003-2018 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Networks for more information
+ ***********************license end**************************************/
+
+/*
+ * Functions for RGMII/GMII/MII initialization, configuration,
+ * and monitoring.
+ */
+#include <asm/octeon/octeon.h>
+
+#include <asm/octeon/cvmx-config.h>
+
+#include <asm/octeon/cvmx-pko.h>
+#include <asm/octeon/cvmx-helper.h>
+#include <asm/octeon/cvmx-helper-board.h>
+
+#include <asm/octeon/cvmx-npi-defs.h>
+#include <asm/octeon/cvmx-gmxx-defs.h>
+#include <asm/octeon/cvmx-asxx-defs.h>
+#include <asm/octeon/cvmx-dbg-defs.h>
+
+/*
+ * Probe RGMII ports and determine the number present
+ *
+ * @interface: Interface to probe
+ *
+ * Returns Number of RGMII/GMII/MII ports (0-4).
+ */
+int __cvmx_helper_rgmii_probe(int interface)
+{
+	int num_ports = 0;
+	union cvmx_gmxx_inf_mode mode;
+	mode.u64 = cvmx_read_csr(CVMX_GMXX_INF_MODE(interface));
+
+	if (mode.s.type) {
+		if (OCTEON_IS_MODEL(OCTEON_CN38XX)
+		    || OCTEON_IS_MODEL(OCTEON_CN58XX)) {
+			cvmx_dprintf("ERROR: RGMII initialize called in "
+				     "SPI interface\n");
+		} else if (OCTEON_IS_MODEL(OCTEON_CN31XX)
+			   || OCTEON_IS_MODEL(OCTEON_CN30XX)
+			   || OCTEON_IS_MODEL(OCTEON_CN50XX)) {
+			/*
+			 * On these chips "type" says we're in
+			 * GMII/MII mode. This limits us to 2 ports
+			 */
+			num_ports = 2;
+		} else {
+			cvmx_dprintf("ERROR: Unsupported Octeon model in %s\n",
+				     __func__);
+		}
+	} else {
+		if (OCTEON_IS_MODEL(OCTEON_CN38XX)
+		    || OCTEON_IS_MODEL(OCTEON_CN58XX)) {
+			num_ports = 4;
+		} else if (OCTEON_IS_MODEL(OCTEON_CN31XX)
+			   || OCTEON_IS_MODEL(OCTEON_CN30XX)
+			   || OCTEON_IS_MODEL(OCTEON_CN50XX)) {
+			num_ports = 3;
+		} else {
+			cvmx_dprintf("ERROR: Unsupported Octeon model in %s\n",
+				     __func__);
+		}
+	}
+	return num_ports;
+}
+
+/*
+ * Put an RGMII interface in loopback mode. Internal packets sent
+ * out will be received back again on the same port. Externally
+ * received packets will echo back out.
+ *
+ * @port:   IPD port number to loop.
+ */
+void cvmx_helper_rgmii_internal_loopback(int port)
+{
+	int interface = (port >> 4) & 1;
+	int index = port & 0xf;
+	uint64_t tmp;
+
+	union cvmx_gmxx_prtx_cfg gmx_cfg;
+	gmx_cfg.u64 = 0;
+	gmx_cfg.s.duplex = 1;
+	gmx_cfg.s.slottime = 1;
+	gmx_cfg.s.speed = 1;
+	cvmx_write_csr(CVMX_GMXX_TXX_CLK(index, interface), 1);
+	cvmx_write_csr(CVMX_GMXX_TXX_SLOT(index, interface), 0x200);
+	cvmx_write_csr(CVMX_GMXX_TXX_BURST(index, interface), 0x2000);
+	cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), gmx_cfg.u64);
+	tmp = cvmx_read_csr(CVMX_ASXX_PRT_LOOP(interface));
+	cvmx_write_csr(CVMX_ASXX_PRT_LOOP(interface), (1 << index) | tmp);
+	tmp = cvmx_read_csr(CVMX_ASXX_TX_PRT_EN(interface));
+	cvmx_write_csr(CVMX_ASXX_TX_PRT_EN(interface), (1 << index) | tmp);
+	tmp = cvmx_read_csr(CVMX_ASXX_RX_PRT_EN(interface));
+	cvmx_write_csr(CVMX_ASXX_RX_PRT_EN(interface), (1 << index) | tmp);
+	gmx_cfg.s.en = 1;
+	cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), gmx_cfg.u64);
+}
+
+/*
+ * Workaround ASX setup errata with CN38XX pass1
+ *
+ * @interface: Interface to setup
+ * @port:      Port to setup (0..3)
+ * @cpu_clock_hz:
+ *		    Chip frequency in Hertz
+ *
+ * Returns Zero on success, negative on failure
+ */
+static int __cvmx_helper_errata_asx_pass1(int interface, int port,
+					  int cpu_clock_hz)
+{
+	/* Set hi water mark as per errata GMX-4 */
+	if (cpu_clock_hz >= 325000000 && cpu_clock_hz < 375000000)
+		cvmx_write_csr(CVMX_ASXX_TX_HI_WATERX(port, interface), 12);
+	else if (cpu_clock_hz >= 375000000 && cpu_clock_hz < 437000000)
+		cvmx_write_csr(CVMX_ASXX_TX_HI_WATERX(port, interface), 11);
+	else if (cpu_clock_hz >= 437000000 && cpu_clock_hz < 550000000)
+		cvmx_write_csr(CVMX_ASXX_TX_HI_WATERX(port, interface), 10);
+	else if (cpu_clock_hz >= 550000000 && cpu_clock_hz < 687000000)
+		cvmx_write_csr(CVMX_ASXX_TX_HI_WATERX(port, interface), 9);
+	else
+		cvmx_dprintf("Illegal clock frequency (%d). "
+			"CVMX_ASXX_TX_HI_WATERX not set\n", cpu_clock_hz);
+	return 0;
+}
+
+/*
+ * Configure all of the ASX, GMX, and PKO registers required
+ * to get RGMII to function on the supplied interface.
+ *
+ * @interface: PKO Interface to configure (0 or 1)
+ *
+ * Returns Zero on success
+ */
+int __cvmx_helper_rgmii_enable(int interface)
+{
+	int num_ports = cvmx_helper_ports_on_interface(interface);
+	int port;
+	struct cvmx_sysinfo *sys_info_ptr = cvmx_sysinfo_get();
+	union cvmx_gmxx_inf_mode mode;
+	union cvmx_asxx_tx_prt_en asx_tx;
+	union cvmx_asxx_rx_prt_en asx_rx;
+
+	mode.u64 = cvmx_read_csr(CVMX_GMXX_INF_MODE(interface));
+
+	if (mode.s.en == 0)
+		return -1;
+	if ((OCTEON_IS_MODEL(OCTEON_CN38XX) ||
+	     OCTEON_IS_MODEL(OCTEON_CN58XX)) && mode.s.type == 1)
+		/* Ignore SPI interfaces */
+		return -1;
+
+	/* Configure the ASX registers needed to use the RGMII ports */
+	asx_tx.u64 = 0;
+	asx_tx.s.prt_en = cvmx_build_mask(num_ports);
+	cvmx_write_csr(CVMX_ASXX_TX_PRT_EN(interface), asx_tx.u64);
+
+	asx_rx.u64 = 0;
+	asx_rx.s.prt_en = cvmx_build_mask(num_ports);
+	cvmx_write_csr(CVMX_ASXX_RX_PRT_EN(interface), asx_rx.u64);
+
+	/* Configure the GMX registers needed to use the RGMII ports */
+	for (port = 0; port < num_ports; port++) {
+		/* Setting of CVMX_GMXX_TXX_THRESH has been moved to
+		   __cvmx_helper_setup_gmx() */
+
+		if (cvmx_octeon_is_pass1())
+			__cvmx_helper_errata_asx_pass1(interface, port,
+						       sys_info_ptr->
+						       cpu_clock_hz);
+		else {
+			/*
+			 * Configure more flexible RGMII preamble
+			 * checking. Pass 1 doesn't support this
+			 * feature.
+			 */
+			union cvmx_gmxx_rxx_frm_ctl frm_ctl;
+			frm_ctl.u64 =
+			    cvmx_read_csr(CVMX_GMXX_RXX_FRM_CTL
+					  (port, interface));
+			/* New field, so must be compile time */
+			frm_ctl.s.pre_free = 1;
+			cvmx_write_csr(CVMX_GMXX_RXX_FRM_CTL(port, interface),
+				       frm_ctl.u64);
+		}
+
+		/*
+		 * Each pause frame transmitted will ask for about 10M
+		 * bit times before resume.  If buffer space comes
+		 * available before that time has expired, an XON
+		 * pause frame (0 time) will be transmitted to restart
+		 * the flow.
+		 */
+		cvmx_write_csr(CVMX_GMXX_TXX_PAUSE_PKT_TIME(port, interface),
+			       20000);
+		cvmx_write_csr(CVMX_GMXX_TXX_PAUSE_PKT_INTERVAL
+			       (port, interface), 19000);
+
+		if (OCTEON_IS_MODEL(OCTEON_CN50XX)) {
+			cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(port, interface),
+				       16);
+			cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(port, interface),
+				       16);
+		} else {
+			cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(port, interface),
+				       24);
+			cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(port, interface),
+				       24);
+		}
+	}
+
+	__cvmx_helper_setup_gmx(interface, num_ports);
+
+	/* enable the ports now */
+	for (port = 0; port < num_ports; port++) {
+		union cvmx_gmxx_prtx_cfg gmx_cfg;
+
+		gmx_cfg.u64 =
+		    cvmx_read_csr(CVMX_GMXX_PRTX_CFG(port, interface));
+		gmx_cfg.s.en = 1;
+		cvmx_write_csr(CVMX_GMXX_PRTX_CFG(port, interface),
+			       gmx_cfg.u64);
+	}
+	__cvmx_interrupt_asxx_enable(interface);
+	__cvmx_interrupt_gmxx_enable(interface);
+
+	return 0;
+}
+
+/*
+ * Return the link state of an IPD/PKO port as returned by
+ * auto negotiation. The result of this function may not match
+ * Octeon's link config if auto negotiation has changed since
+ * the last call to cvmx_helper_link_set().
+ *
+ * @ipd_port: IPD/PKO port to query
+ *
+ * Returns Link state
+ */
+union cvmx_helper_link_info __cvmx_helper_rgmii_link_get(int ipd_port)
+{
+	int interface = cvmx_helper_get_interface_num(ipd_port);
+	int index = cvmx_helper_get_interface_index_num(ipd_port);
+	union cvmx_asxx_prt_loop asxx_prt_loop;
+
+	asxx_prt_loop.u64 = cvmx_read_csr(CVMX_ASXX_PRT_LOOP(interface));
+	if (asxx_prt_loop.s.int_loop & (1 << index)) {
+		/* Force 1Gbps full duplex on internal loopback */
+		union cvmx_helper_link_info result;
+		result.u64 = 0;
+		result.s.full_duplex = 1;
+		result.s.link_up = 1;
+		result.s.speed = 1000;
+		return result;
+	} else
+		return __cvmx_helper_board_link_get(ipd_port);
+}
+
+/*
+ * Configure an IPD/PKO port for the specified link state. This
+ * function does not influence auto negotiation at the PHY level.
+ * The passed link state must always match the link state returned
+ * by cvmx_helper_link_get().
+ *
+ * @ipd_port:  IPD/PKO port to configure
+ * @link_info: The new link state
+ *
+ * Returns Zero on success, negative on failure
+ */
+int __cvmx_helper_rgmii_link_set(int ipd_port,
+				 union cvmx_helper_link_info link_info)
+{
+	int result = 0;
+	int interface = cvmx_helper_get_interface_num(ipd_port);
+	int index = cvmx_helper_get_interface_index_num(ipd_port);
+	union cvmx_gmxx_prtx_cfg original_gmx_cfg;
+	union cvmx_gmxx_prtx_cfg new_gmx_cfg;
+	union cvmx_pko_mem_queue_qos pko_mem_queue_qos;
+	union cvmx_pko_mem_queue_qos pko_mem_queue_qos_save[16];
+	union cvmx_gmxx_tx_ovr_bp gmx_tx_ovr_bp;
+	union cvmx_gmxx_tx_ovr_bp gmx_tx_ovr_bp_save;
+	int i;
+
+	/* Ignore speed sets in the simulator */
+	if (cvmx_sysinfo_get()->board_type == CVMX_BOARD_TYPE_SIM)
+		return 0;
+
+	/* Read the current settings so we know the current enable state */
+	original_gmx_cfg.u64 =
+	    cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface));
+	new_gmx_cfg = original_gmx_cfg;
+
+	/* Disable the lowest level RX */
+	cvmx_write_csr(CVMX_ASXX_RX_PRT_EN(interface),
+		       cvmx_read_csr(CVMX_ASXX_RX_PRT_EN(interface)) &
+				     ~(1 << index));
+
+	memset(pko_mem_queue_qos_save, 0, sizeof(pko_mem_queue_qos_save));
+	/* Disable all queues so that TX should become idle */
+	for (i = 0; i < cvmx_pko_get_num_queues(ipd_port); i++) {
+		int queue = cvmx_pko_get_base_queue(ipd_port) + i;
+		cvmx_write_csr(CVMX_PKO_REG_READ_IDX, queue);
+		pko_mem_queue_qos.u64 = cvmx_read_csr(CVMX_PKO_MEM_QUEUE_QOS);
+		pko_mem_queue_qos.s.pid = ipd_port;
+		pko_mem_queue_qos.s.qid = queue;
+		pko_mem_queue_qos_save[i] = pko_mem_queue_qos;
+		pko_mem_queue_qos.s.qos_mask = 0;
+		cvmx_write_csr(CVMX_PKO_MEM_QUEUE_QOS, pko_mem_queue_qos.u64);
+	}
+
+	/* Disable backpressure */
+	gmx_tx_ovr_bp.u64 = cvmx_read_csr(CVMX_GMXX_TX_OVR_BP(interface));
+	gmx_tx_ovr_bp_save = gmx_tx_ovr_bp;
+	gmx_tx_ovr_bp.s.bp &= ~(1 << index);
+	gmx_tx_ovr_bp.s.en |= 1 << index;
+	cvmx_write_csr(CVMX_GMXX_TX_OVR_BP(interface), gmx_tx_ovr_bp.u64);
+	cvmx_read_csr(CVMX_GMXX_TX_OVR_BP(interface));
+
+	/*
+	 * Poll the GMX state machine waiting for it to become
+	 * idle. Preferably we should only change speed when it is
+	 * idle. If it doesn't become idle we will still do the speed
+	 * change, but there is a slight chance that GMX will
+	 * lockup.
+	 */
+	cvmx_write_csr(CVMX_NPI_DBG_SELECT,
+		       interface * 0x800 + index * 0x100 + 0x880);
+	CVMX_WAIT_FOR_FIELD64(CVMX_DBG_DATA, union cvmx_dbg_data, data & 7,
+			==, 0, 10000);
+	CVMX_WAIT_FOR_FIELD64(CVMX_DBG_DATA, union cvmx_dbg_data, data & 0xf,
+			==, 0, 10000);
+
+	/* Disable the port before we make any changes */
+	new_gmx_cfg.s.en = 0;
+	cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), new_gmx_cfg.u64);
+	cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface));
+
+	/* Set full/half duplex */
+	if (cvmx_octeon_is_pass1())
+		/* Half duplex is broken for 38XX Pass 1 */
+		new_gmx_cfg.s.duplex = 1;
+	else if (!link_info.s.link_up)
+		/* Force full duplex on down links */
+		new_gmx_cfg.s.duplex = 1;
+	else
+		new_gmx_cfg.s.duplex = link_info.s.full_duplex;
+
+	/* Set the link speed. Anything unknown is set to 1Gbps */
+	if (link_info.s.speed == 10) {
+		new_gmx_cfg.s.slottime = 0;
+		new_gmx_cfg.s.speed = 0;
+	} else if (link_info.s.speed == 100) {
+		new_gmx_cfg.s.slottime = 0;
+		new_gmx_cfg.s.speed = 0;
+	} else {
+		new_gmx_cfg.s.slottime = 1;
+		new_gmx_cfg.s.speed = 1;
+	}
+
+	/* Adjust the clocks */
+	if (link_info.s.speed == 10) {
+		cvmx_write_csr(CVMX_GMXX_TXX_CLK(index, interface), 50);
+		cvmx_write_csr(CVMX_GMXX_TXX_SLOT(index, interface), 0x40);
+		cvmx_write_csr(CVMX_GMXX_TXX_BURST(index, interface), 0);
+	} else if (link_info.s.speed == 100) {
+		cvmx_write_csr(CVMX_GMXX_TXX_CLK(index, interface), 5);
+		cvmx_write_csr(CVMX_GMXX_TXX_SLOT(index, interface), 0x40);
+		cvmx_write_csr(CVMX_GMXX_TXX_BURST(index, interface), 0);
+	} else {
+		cvmx_write_csr(CVMX_GMXX_TXX_CLK(index, interface), 1);
+		cvmx_write_csr(CVMX_GMXX_TXX_SLOT(index, interface), 0x200);
+		cvmx_write_csr(CVMX_GMXX_TXX_BURST(index, interface), 0x2000);
+	}
+
+	if (OCTEON_IS_MODEL(OCTEON_CN30XX) || OCTEON_IS_MODEL(OCTEON_CN50XX)) {
+		if ((link_info.s.speed == 10) || (link_info.s.speed == 100)) {
+			union cvmx_gmxx_inf_mode mode;
+			mode.u64 = cvmx_read_csr(CVMX_GMXX_INF_MODE(interface));
+
+	/*
+	 * Port	 .en  .type  .p0mii  Configuration
+	 * ----	 ---  -----  ------  -----------------------------------------
+	 *  X	   0	 X	X    All links are disabled.
+	 *  0	   1	 X	0    Port 0 is RGMII
+	 *  0	   1	 X	1    Port 0 is MII
+	 *  1	   1	 0	X    Ports 1 and 2 are configured as RGMII ports.
+	 *  1	   1	 1	X    Port 1: GMII/MII; Port 2: disabled. GMII or
+	 *			     MII port is selected by GMX_PRT1_CFG[SPEED].
+	 */
+
+			/* In MII mode, CLK_CNT = 1. */
+			if (((index == 0) && (mode.s.p0mii == 1))
+			    || ((index != 0) && (mode.s.type == 1))) {
+				cvmx_write_csr(CVMX_GMXX_TXX_CLK
+					       (index, interface), 1);
+			}
+		}
+	}
+
+	/* Do a read to make sure all setup stuff is complete */
+	cvmx_read_csr(CVMX_GMXX_PRTX_CFG(index, interface));
+
+	/* Save the new GMX setting without enabling the port */
+	cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), new_gmx_cfg.u64);
+
+	/* Enable the lowest level RX */
+	cvmx_write_csr(CVMX_ASXX_RX_PRT_EN(interface),
+		       cvmx_read_csr(CVMX_ASXX_RX_PRT_EN(interface)) | (1 <<
+									index));
+
+	/* Re-enable the TX path */
+	for (i = 0; i < cvmx_pko_get_num_queues(ipd_port); i++) {
+		int queue = cvmx_pko_get_base_queue(ipd_port) + i;
+		cvmx_write_csr(CVMX_PKO_REG_READ_IDX, queue);
+		cvmx_write_csr(CVMX_PKO_MEM_QUEUE_QOS,
+			       pko_mem_queue_qos_save[i].u64);
+	}
+
+	/* Restore backpressure */
+	cvmx_write_csr(CVMX_GMXX_TX_OVR_BP(interface), gmx_tx_ovr_bp_save.u64);
+
+	/* Restore the GMX enable state. Port config is complete */
+	new_gmx_cfg.s.en = original_gmx_cfg.s.en;
+	cvmx_write_csr(CVMX_GMXX_PRTX_CFG(index, interface), new_gmx_cfg.u64);
+
+	return result;
+}