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, 281 insertions, 0 deletions

diff --git a/drivers/usb/host/ehci-brcm.c b/drivers/usb/host/ehci-brcm.c
new file mode 100644
index 000000000..6a0f64c9e
--- /dev/null
+++ b/drivers/usb/host/ehci-brcm.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Broadcom */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/iopoll.h>
+
+#include "ehci.h"
+
+#define hcd_to_ehci_priv(h) ((struct brcm_priv *)hcd_to_ehci(h)->priv)
+
+struct brcm_priv {
+	struct clk *clk;
+};
+
+/*
+ * ehci_brcm_wait_for_sof
+ * Wait for start of next microframe, then wait extra delay microseconds
+ */
+static inline void ehci_brcm_wait_for_sof(struct ehci_hcd *ehci, u32 delay)
+{
+	u32 frame_idx = ehci_readl(ehci, &ehci->regs->frame_index);
+	u32 val;
+	int res;
+
+	/* Wait for next microframe (every 125 usecs) */
+	res = readl_relaxed_poll_timeout(&ehci->regs->frame_index, val,
+					 val != frame_idx, 1, 130);
+	if (res)
+		ehci_err(ehci, "Error waiting for SOF\n");
+	udelay(delay);
+}
+
+/*
+ * ehci_brcm_hub_control
+ * The EHCI controller has a bug where it can violate the SOF
+ * interval between the first two SOF's transmitted after resume
+ * if the resume occurs near the end of the microframe. This causees
+ * the controller to detect babble on the suspended port and
+ * will eventually cause the controller to reset the port.
+ * The fix is to Intercept the echi-hcd request to complete RESUME and
+ * align it to the start of the next microframe.
+ * See SWLINUX-1909 for more details
+ */
+static int ehci_brcm_hub_control(
+	struct usb_hcd	*hcd,
+	u16		typeReq,
+	u16		wValue,
+	u16		wIndex,
+	char		*buf,
+	u16		wLength)
+{
+	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
+	int		ports = HCS_N_PORTS(ehci->hcs_params);
+	u32 __iomem	*status_reg;
+	unsigned long flags;
+	int retval, irq_disabled = 0;
+	u32 temp;
+
+	temp = (wIndex & 0xff) - 1;
+	if (temp >= HCS_N_PORTS_MAX)	/* Avoid index-out-of-bounds warning */
+		temp = 0;
+	status_reg = &ehci->regs->port_status[temp];
+
+	/*
+	 * RESUME is cleared when GetPortStatus() is called 20ms after start
+	 * of RESUME
+	 */
+	if ((typeReq == GetPortStatus) &&
+	    (wIndex && wIndex <= ports) &&
+	    ehci->reset_done[wIndex-1] &&
+	    time_after_eq(jiffies, ehci->reset_done[wIndex-1]) &&
+	    (ehci_readl(ehci, status_reg) & PORT_RESUME)) {
+
+		/*
+		 * to make sure we are not interrupted until RESUME bit
+		 * is cleared, disable interrupts on current CPU
+		 */
+		ehci_dbg(ehci, "SOF alignment workaround\n");
+		irq_disabled = 1;
+		local_irq_save(flags);
+		ehci_brcm_wait_for_sof(ehci, 5);
+	}
+	retval = ehci_hub_control(hcd, typeReq, wValue, wIndex, buf, wLength);
+	if (irq_disabled)
+		local_irq_restore(flags);
+	return retval;
+}
+
+static int ehci_brcm_reset(struct usb_hcd *hcd)
+{
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+	int len;
+
+	ehci->big_endian_mmio = 1;
+
+	ehci->caps = (void __iomem *)hcd->regs;
+	len = HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase));
+	ehci->regs = (void __iomem *)(hcd->regs + len);
+
+	/* This fixes the lockup during reboot due to prior interrupts */
+	ehci_writel(ehci, CMD_RESET, &ehci->regs->command);
+	mdelay(10);
+
+	/*
+	 * SWLINUX-1705: Avoid OUT packet underflows during high memory
+	 *   bus usage
+	 */
+	ehci_writel(ehci, 0x00800040, &ehci->regs->brcm_insnreg[1]);
+	ehci_writel(ehci, 0x00000001, &ehci->regs->brcm_insnreg[3]);
+
+	return ehci_setup(hcd);
+}
+
+static struct hc_driver __read_mostly ehci_brcm_hc_driver;
+
+static const struct ehci_driver_overrides brcm_overrides __initconst = {
+	.reset = ehci_brcm_reset,
+	.extra_priv_size = sizeof(struct brcm_priv),
+};
+
+static int ehci_brcm_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res_mem;
+	struct brcm_priv *priv;
+	struct usb_hcd *hcd;
+	int irq;
+	int err;
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return irq ? irq : -EINVAL;
+
+	/* Hook the hub control routine to work around a bug */
+	ehci_brcm_hc_driver.hub_control = ehci_brcm_hub_control;
+
+	/* initialize hcd */
+	hcd = usb_create_hcd(&ehci_brcm_hc_driver, dev, dev_name(dev));
+	if (!hcd)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, hcd);
+	priv = hcd_to_ehci_priv(hcd);
+
+	priv->clk = devm_clk_get_optional(dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		err = PTR_ERR(priv->clk);
+		goto err_hcd;
+	}
+
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		goto err_hcd;
+
+	hcd->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res_mem);
+	if (IS_ERR(hcd->regs)) {
+		err = PTR_ERR(hcd->regs);
+		goto err_clk;
+	}
+	hcd->rsrc_start = res_mem->start;
+	hcd->rsrc_len = resource_size(res_mem);
+	err = usb_add_hcd(hcd, irq, IRQF_SHARED);
+	if (err)
+		goto err_clk;
+
+	device_wakeup_enable(hcd->self.controller);
+	device_enable_async_suspend(hcd->self.controller);
+
+	return 0;
+
+err_clk:
+	clk_disable_unprepare(priv->clk);
+err_hcd:
+	usb_put_hcd(hcd);
+
+	return err;
+}
+
+static int ehci_brcm_remove(struct platform_device *dev)
+{
+	struct usb_hcd *hcd = platform_get_drvdata(dev);
+	struct brcm_priv *priv = hcd_to_ehci_priv(hcd);
+
+	usb_remove_hcd(hcd);
+	clk_disable_unprepare(priv->clk);
+	usb_put_hcd(hcd);
+	return 0;
+}
+
+static int __maybe_unused ehci_brcm_suspend(struct device *dev)
+{
+	int ret;
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct brcm_priv *priv = hcd_to_ehci_priv(hcd);
+	bool do_wakeup = device_may_wakeup(dev);
+
+	ret = ehci_suspend(hcd, do_wakeup);
+	if (ret)
+		return ret;
+	clk_disable_unprepare(priv->clk);
+	return 0;
+}
+
+static int __maybe_unused ehci_brcm_resume(struct device *dev)
+{
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+	struct brcm_priv *priv = hcd_to_ehci_priv(hcd);
+	int err;
+
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
+	/*
+	 * SWLINUX-1705: Avoid OUT packet underflows during high memory
+	 *   bus usage
+	 */
+	ehci_writel(ehci, 0x00800040, &ehci->regs->brcm_insnreg[1]);
+	ehci_writel(ehci, 0x00000001, &ehci->regs->brcm_insnreg[3]);
+
+	ehci_resume(hcd, false);
+
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(ehci_brcm_pm_ops, ehci_brcm_suspend,
+		ehci_brcm_resume);
+
+static const struct of_device_id brcm_ehci_of_match[] = {
+	{ .compatible = "brcm,ehci-brcm-v2", },
+	{ .compatible = "brcm,bcm7445-ehci", },
+	{}
+};
+
+static struct platform_driver ehci_brcm_driver = {
+	.probe		= ehci_brcm_probe,
+	.remove		= ehci_brcm_remove,
+	.shutdown	= usb_hcd_platform_shutdown,
+	.driver		= {
+		.name	= "ehci-brcm",
+		.pm	= &ehci_brcm_pm_ops,
+		.of_match_table = brcm_ehci_of_match,
+	}
+};
+
+static int __init ehci_brcm_init(void)
+{
+	if (usb_disabled())
+		return -ENODEV;
+
+	ehci_init_driver(&ehci_brcm_hc_driver, &brcm_overrides);
+	return platform_driver_register(&ehci_brcm_driver);
+}
+module_init(ehci_brcm_init);
+
+static void __exit ehci_brcm_exit(void)
+{
+	platform_driver_unregister(&ehci_brcm_driver);
+}
+module_exit(ehci_brcm_exit);
+
+MODULE_ALIAS("platform:ehci-brcm");
+MODULE_DESCRIPTION("EHCI Broadcom STB driver");
+MODULE_AUTHOR("Al Cooper");
+MODULE_LICENSE("GPL");