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, 419 insertions, 0 deletions

diff --git a/drivers/bus/bt1-apb.c b/drivers/bus/bt1-apb.c
new file mode 100644
index 000000000..63b1b4a76
--- /dev/null
+++ b/drivers/bus/bt1-apb.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+ *
+ * Authors:
+ *   Serge Semin <Sergey.Semin@baikalelectronics.ru>
+ *
+ * Baikal-T1 APB-bus driver
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/atomic.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/nmi.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+#include <linux/time64.h>
+#include <linux/clk.h>
+#include <linux/sysfs.h>
+
+#define APB_EHB_ISR			0x00
+#define APB_EHB_ISR_PENDING		BIT(0)
+#define APB_EHB_ISR_MASK		BIT(1)
+#define APB_EHB_ADDR			0x04
+#define APB_EHB_TIMEOUT			0x08
+
+#define APB_EHB_TIMEOUT_MIN		0x000003FFU
+#define APB_EHB_TIMEOUT_MAX		0xFFFFFFFFU
+
+/*
+ * struct bt1_apb - Baikal-T1 APB EHB private data
+ * @dev: Pointer to the device structure.
+ * @regs: APB EHB registers map.
+ * @res: No-device error injection memory region.
+ * @irq: Errors IRQ number.
+ * @rate: APB-bus reference clock rate.
+ * @pclk: APB-reference clock.
+ * @prst: APB domain reset line.
+ * @count: Number of errors detected.
+ */
+struct bt1_apb {
+	struct device *dev;
+
+	struct regmap *regs;
+	void __iomem *res;
+	int irq;
+
+	unsigned long rate;
+	struct clk *pclk;
+
+	struct reset_control *prst;
+
+	atomic_t count;
+};
+
+static const struct regmap_config bt1_apb_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = APB_EHB_TIMEOUT,
+	.fast_io = true
+};
+
+static inline unsigned long bt1_apb_n_to_timeout_us(struct bt1_apb *apb, u32 n)
+{
+	u64 timeout = (u64)n * USEC_PER_SEC;
+
+	do_div(timeout, apb->rate);
+
+	return timeout;
+
+}
+
+static inline unsigned long bt1_apb_timeout_to_n_us(struct bt1_apb *apb,
+						    unsigned long timeout)
+{
+	u64 n = (u64)timeout * apb->rate;
+
+	do_div(n, USEC_PER_SEC);
+
+	return n;
+
+}
+
+static irqreturn_t bt1_apb_isr(int irq, void *data)
+{
+	struct bt1_apb *apb = data;
+	u32 addr = 0;
+
+	regmap_read(apb->regs, APB_EHB_ADDR, &addr);
+
+	dev_crit_ratelimited(apb->dev,
+		"APB-bus fault %d: Slave access timeout at 0x%08x\n",
+		atomic_inc_return(&apb->count),
+		addr);
+
+	/*
+	 * Print backtrace on each CPU. This might be pointless if the fault
+	 * has happened on the same CPU as the IRQ handler is executed or
+	 * the other core proceeded further execution despite the error.
+	 * But if it's not, by looking at the trace we would get straight to
+	 * the cause of the problem.
+	 */
+	trigger_all_cpu_backtrace();
+
+	regmap_update_bits(apb->regs, APB_EHB_ISR, APB_EHB_ISR_PENDING, 0);
+
+	return IRQ_HANDLED;
+}
+
+static void bt1_apb_clear_data(void *data)
+{
+	struct bt1_apb *apb = data;
+	struct platform_device *pdev = to_platform_device(apb->dev);
+
+	platform_set_drvdata(pdev, NULL);
+}
+
+static struct bt1_apb *bt1_apb_create_data(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct bt1_apb *apb;
+	int ret;
+
+	apb = devm_kzalloc(dev, sizeof(*apb), GFP_KERNEL);
+	if (!apb)
+		return ERR_PTR(-ENOMEM);
+
+	ret = devm_add_action(dev, bt1_apb_clear_data, apb);
+	if (ret) {
+		dev_err(dev, "Can't add APB EHB data clear action\n");
+		return ERR_PTR(ret);
+	}
+
+	apb->dev = dev;
+	atomic_set(&apb->count, 0);
+	platform_set_drvdata(pdev, apb);
+
+	return apb;
+}
+
+static int bt1_apb_request_regs(struct bt1_apb *apb)
+{
+	struct platform_device *pdev = to_platform_device(apb->dev);
+	void __iomem *regs;
+
+	regs = devm_platform_ioremap_resource_byname(pdev, "ehb");
+	if (IS_ERR(regs)) {
+		dev_err(apb->dev, "Couldn't map APB EHB registers\n");
+		return PTR_ERR(regs);
+	}
+
+	apb->regs = devm_regmap_init_mmio(apb->dev, regs, &bt1_apb_regmap_cfg);
+	if (IS_ERR(apb->regs)) {
+		dev_err(apb->dev, "Couldn't create APB EHB regmap\n");
+		return PTR_ERR(apb->regs);
+	}
+
+	apb->res = devm_platform_ioremap_resource_byname(pdev, "nodev");
+	if (IS_ERR(apb->res))
+		dev_err(apb->dev, "Couldn't map reserved region\n");
+
+	return PTR_ERR_OR_ZERO(apb->res);
+}
+
+static int bt1_apb_request_rst(struct bt1_apb *apb)
+{
+	int ret;
+
+	apb->prst = devm_reset_control_get_optional_exclusive(apb->dev, "prst");
+	if (IS_ERR(apb->prst))
+		return dev_err_probe(apb->dev, PTR_ERR(apb->prst),
+				     "Couldn't get reset control line\n");
+
+	ret = reset_control_deassert(apb->prst);
+	if (ret)
+		dev_err(apb->dev, "Failed to deassert the reset line\n");
+
+	return ret;
+}
+
+static void bt1_apb_disable_clk(void *data)
+{
+	struct bt1_apb *apb = data;
+
+	clk_disable_unprepare(apb->pclk);
+}
+
+static int bt1_apb_request_clk(struct bt1_apb *apb)
+{
+	int ret;
+
+	apb->pclk = devm_clk_get(apb->dev, "pclk");
+	if (IS_ERR(apb->pclk))
+		return dev_err_probe(apb->dev, PTR_ERR(apb->pclk),
+				     "Couldn't get APB clock descriptor\n");
+
+	ret = clk_prepare_enable(apb->pclk);
+	if (ret) {
+		dev_err(apb->dev, "Couldn't enable the APB clock\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(apb->dev, bt1_apb_disable_clk, apb);
+	if (ret) {
+		dev_err(apb->dev, "Can't add APB EHB clocks disable action\n");
+		return ret;
+	}
+
+	apb->rate = clk_get_rate(apb->pclk);
+	if (!apb->rate) {
+		dev_err(apb->dev, "Invalid clock rate\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void bt1_apb_clear_irq(void *data)
+{
+	struct bt1_apb *apb = data;
+
+	regmap_update_bits(apb->regs, APB_EHB_ISR, APB_EHB_ISR_MASK, 0);
+}
+
+static int bt1_apb_request_irq(struct bt1_apb *apb)
+{
+	struct platform_device *pdev = to_platform_device(apb->dev);
+	int ret;
+
+	apb->irq = platform_get_irq(pdev, 0);
+	if (apb->irq < 0)
+		return apb->irq;
+
+	ret = devm_request_irq(apb->dev, apb->irq, bt1_apb_isr, IRQF_SHARED,
+			       "bt1-apb", apb);
+	if (ret) {
+		dev_err(apb->dev, "Couldn't request APB EHB IRQ\n");
+		return ret;
+	}
+
+	ret = devm_add_action(apb->dev, bt1_apb_clear_irq, apb);
+	if (ret) {
+		dev_err(apb->dev, "Can't add APB EHB IRQs clear action\n");
+		return ret;
+	}
+
+	/* Unmask IRQ and clear it' pending flag. */
+	regmap_update_bits(apb->regs, APB_EHB_ISR,
+			   APB_EHB_ISR_PENDING | APB_EHB_ISR_MASK,
+			   APB_EHB_ISR_MASK);
+
+	return 0;
+}
+
+static ssize_t count_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct bt1_apb *apb = dev_get_drvdata(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&apb->count));
+}
+static DEVICE_ATTR_RO(count);
+
+static ssize_t timeout_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct bt1_apb *apb = dev_get_drvdata(dev);
+	unsigned long timeout;
+	int ret;
+	u32 n;
+
+	ret = regmap_read(apb->regs, APB_EHB_TIMEOUT, &n);
+	if (ret)
+		return ret;
+
+	timeout = bt1_apb_n_to_timeout_us(apb, n);
+
+	return scnprintf(buf, PAGE_SIZE, "%lu\n", timeout);
+}
+
+static ssize_t timeout_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct bt1_apb *apb = dev_get_drvdata(dev);
+	unsigned long timeout;
+	int ret;
+	u32 n;
+
+	if (kstrtoul(buf, 0, &timeout) < 0)
+		return -EINVAL;
+
+	n = bt1_apb_timeout_to_n_us(apb, timeout);
+	n = clamp(n, APB_EHB_TIMEOUT_MIN, APB_EHB_TIMEOUT_MAX);
+
+	ret = regmap_write(apb->regs, APB_EHB_TIMEOUT, n);
+
+	return ret ?: count;
+}
+static DEVICE_ATTR_RW(timeout);
+
+static ssize_t inject_error_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	return scnprintf(buf, PAGE_SIZE, "Error injection: nodev irq\n");
+}
+
+static ssize_t inject_error_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *data, size_t count)
+{
+	struct bt1_apb *apb = dev_get_drvdata(dev);
+
+	/*
+	 * Either dummy read from the unmapped address in the APB IO area
+	 * or manually set the IRQ status.
+	 */
+	if (sysfs_streq(data, "nodev"))
+		readl(apb->res);
+	else if (sysfs_streq(data, "irq"))
+		regmap_update_bits(apb->regs, APB_EHB_ISR, APB_EHB_ISR_PENDING,
+				   APB_EHB_ISR_PENDING);
+	else
+		return -EINVAL;
+
+	return count;
+}
+static DEVICE_ATTR_RW(inject_error);
+
+static struct attribute *bt1_apb_sysfs_attrs[] = {
+	&dev_attr_count.attr,
+	&dev_attr_timeout.attr,
+	&dev_attr_inject_error.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(bt1_apb_sysfs);
+
+static void bt1_apb_remove_sysfs(void *data)
+{
+	struct bt1_apb *apb = data;
+
+	device_remove_groups(apb->dev, bt1_apb_sysfs_groups);
+}
+
+static int bt1_apb_init_sysfs(struct bt1_apb *apb)
+{
+	int ret;
+
+	ret = device_add_groups(apb->dev, bt1_apb_sysfs_groups);
+	if (ret) {
+		dev_err(apb->dev, "Failed to create EHB APB sysfs nodes\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(apb->dev, bt1_apb_remove_sysfs, apb);
+	if (ret)
+		dev_err(apb->dev, "Can't add APB EHB sysfs remove action\n");
+
+	return ret;
+}
+
+static int bt1_apb_probe(struct platform_device *pdev)
+{
+	struct bt1_apb *apb;
+	int ret;
+
+	apb = bt1_apb_create_data(pdev);
+	if (IS_ERR(apb))
+		return PTR_ERR(apb);
+
+	ret = bt1_apb_request_regs(apb);
+	if (ret)
+		return ret;
+
+	ret = bt1_apb_request_rst(apb);
+	if (ret)
+		return ret;
+
+	ret = bt1_apb_request_clk(apb);
+	if (ret)
+		return ret;
+
+	ret = bt1_apb_request_irq(apb);
+	if (ret)
+		return ret;
+
+	ret = bt1_apb_init_sysfs(apb);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct of_device_id bt1_apb_of_match[] = {
+	{ .compatible = "baikal,bt1-apb" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bt1_apb_of_match);
+
+static struct platform_driver bt1_apb_driver = {
+	.probe = bt1_apb_probe,
+	.driver = {
+		.name = "bt1-apb",
+		.of_match_table = bt1_apb_of_match
+	}
+};
+module_platform_driver(bt1_apb_driver);
+
+MODULE_AUTHOR("Serge Semin <Sergey.Semin@baikalelectronics.ru>");
+MODULE_DESCRIPTION("Baikal-T1 APB-bus driver");
+MODULE_LICENSE("GPL v2");