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, 344 insertions, 0 deletions

diff --git a/drivers/spi/spi-dw-bt1.c b/drivers/spi/spi-dw-bt1.c
new file mode 100644
index 000000000..3fb89dee5
--- /dev/null
+++ b/drivers/spi/spi-dw-bt1.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+//
+// Authors:
+//   Ramil Zaripov <Ramil.Zaripov@baikalelectronics.ru>
+//   Serge Semin <Sergey.Semin@baikalelectronics.ru>
+//
+// Baikal-T1 DW APB SPI and System Boot SPI driver
+//
+
+#include <linux/clk.h>
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mux/consumer.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+#include <linux/spi/spi-mem.h>
+#include <linux/spi/spi.h>
+
+#include "spi-dw.h"
+
+#define BT1_BOOT_DIRMAP		0
+#define BT1_BOOT_REGS		1
+
+struct dw_spi_bt1 {
+	struct dw_spi		dws;
+	struct clk		*clk;
+	struct mux_control	*mux;
+
+#ifdef CONFIG_SPI_DW_BT1_DIRMAP
+	void __iomem		*map;
+	resource_size_t		map_len;
+#endif
+};
+#define to_dw_spi_bt1(_ctlr) \
+	container_of(spi_controller_get_devdata(_ctlr), struct dw_spi_bt1, dws)
+
+typedef int (*dw_spi_bt1_init_cb)(struct platform_device *pdev,
+				    struct dw_spi_bt1 *dwsbt1);
+
+#ifdef CONFIG_SPI_DW_BT1_DIRMAP
+
+static int dw_spi_bt1_dirmap_create(struct spi_mem_dirmap_desc *desc)
+{
+	struct dw_spi_bt1 *dwsbt1 = to_dw_spi_bt1(desc->mem->spi->controller);
+
+	if (!dwsbt1->map ||
+	    !dwsbt1->dws.mem_ops.supports_op(desc->mem, &desc->info.op_tmpl))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Make sure the requested region doesn't go out of the physically
+	 * mapped flash memory bounds and the operation is read-only.
+	 */
+	if (desc->info.offset + desc->info.length > dwsbt1->map_len ||
+	    desc->info.op_tmpl.data.dir != SPI_MEM_DATA_IN)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/*
+ * Directly mapped SPI memory region is only accessible in the dword chunks.
+ * That's why we have to create a dedicated read-method to copy data from there
+ * to the passed buffer.
+ */
+static void dw_spi_bt1_dirmap_copy_from_map(void *to, void __iomem *from, size_t len)
+{
+	size_t shift, chunk;
+	u32 data;
+
+	/*
+	 * We split the copying up into the next three stages: unaligned head,
+	 * aligned body, unaligned tail.
+	 */
+	shift = (size_t)from & 0x3;
+	if (shift) {
+		chunk = min_t(size_t, 4 - shift, len);
+		data = readl_relaxed(from - shift);
+		memcpy(to, (char *)&data + shift, chunk);
+		from += chunk;
+		to += chunk;
+		len -= chunk;
+	}
+
+	while (len >= 4) {
+		data = readl_relaxed(from);
+		memcpy(to, &data, 4);
+		from += 4;
+		to += 4;
+		len -= 4;
+	}
+
+	if (len) {
+		data = readl_relaxed(from);
+		memcpy(to, &data, len);
+	}
+}
+
+static ssize_t dw_spi_bt1_dirmap_read(struct spi_mem_dirmap_desc *desc,
+				      u64 offs, size_t len, void *buf)
+{
+	struct dw_spi_bt1 *dwsbt1 = to_dw_spi_bt1(desc->mem->spi->controller);
+	struct dw_spi *dws = &dwsbt1->dws;
+	struct spi_mem *mem = desc->mem;
+	struct dw_spi_cfg cfg;
+	int ret;
+
+	/*
+	 * Make sure the requested operation length is valid. Truncate the
+	 * length if it's greater than the length of the MMIO region.
+	 */
+	if (offs >= dwsbt1->map_len || !len)
+		return 0;
+
+	len = min_t(size_t, len, dwsbt1->map_len - offs);
+
+	/* Collect the controller configuration required by the operation */
+	cfg.tmode = DW_SPI_CTRLR0_TMOD_EPROMREAD;
+	cfg.dfs = 8;
+	cfg.ndf = 4;
+	cfg.freq = mem->spi->max_speed_hz;
+
+	/* Make sure the corresponding CS is de-asserted on transmission */
+	dw_spi_set_cs(mem->spi, false);
+
+	dw_spi_enable_chip(dws, 0);
+
+	dw_spi_update_config(dws, mem->spi, &cfg);
+
+	dw_spi_umask_intr(dws, DW_SPI_INT_RXFI);
+
+	dw_spi_enable_chip(dws, 1);
+
+	/*
+	 * Enable the transparent mode of the System Boot Controller.
+	 * The SPI core IO should have been locked before calling this method
+	 * so noone would be touching the controller' registers during the
+	 * dirmap operation.
+	 */
+	ret = mux_control_select(dwsbt1->mux, BT1_BOOT_DIRMAP);
+	if (ret)
+		return ret;
+
+	dw_spi_bt1_dirmap_copy_from_map(buf, dwsbt1->map + offs, len);
+
+	mux_control_deselect(dwsbt1->mux);
+
+	dw_spi_set_cs(mem->spi, true);
+
+	ret = dw_spi_check_status(dws, true);
+
+	return ret ?: len;
+}
+
+#endif /* CONFIG_SPI_DW_BT1_DIRMAP */
+
+static int dw_spi_bt1_std_init(struct platform_device *pdev,
+			       struct dw_spi_bt1 *dwsbt1)
+{
+	struct dw_spi *dws = &dwsbt1->dws;
+
+	dws->irq = platform_get_irq(pdev, 0);
+	if (dws->irq < 0)
+		return dws->irq;
+
+	dws->num_cs = 4;
+
+	/*
+	 * Baikal-T1 Normal SPI Controllers don't always keep up with full SPI
+	 * bus speed especially when it comes to the concurrent access to the
+	 * APB bus resources. Thus we have no choice but to set a constraint on
+	 * the SPI bus frequency for the memory operations which require to
+	 * read/write data as fast as possible.
+	 */
+	dws->max_mem_freq = 20000000U;
+
+	dw_spi_dma_setup_generic(dws);
+
+	return 0;
+}
+
+static int dw_spi_bt1_sys_init(struct platform_device *pdev,
+			       struct dw_spi_bt1 *dwsbt1)
+{
+	struct resource *mem __maybe_unused;
+	struct dw_spi *dws = &dwsbt1->dws;
+
+	/*
+	 * Baikal-T1 System Boot Controller is equipped with a mux, which
+	 * switches between the directly mapped SPI flash access mode and
+	 * IO access to the DW APB SSI registers. Note the mux controller
+	 * must be setup to preserve the registers being accessible by default
+	 * (on idle-state).
+	 */
+	dwsbt1->mux = devm_mux_control_get(&pdev->dev, NULL);
+	if (IS_ERR(dwsbt1->mux))
+		return PTR_ERR(dwsbt1->mux);
+
+	/*
+	 * Directly mapped SPI flash memory is a 16MB MMIO region, which can be
+	 * used to access a peripheral memory device just by reading/writing
+	 * data from/to it. Note the system APB bus will stall during each IO
+	 * from/to the dirmap region until the operation is finished. So don't
+	 * use it concurrently with time-critical tasks (like the SPI memory
+	 * operations implemented in the DW APB SSI driver).
+	 */
+#ifdef CONFIG_SPI_DW_BT1_DIRMAP
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (mem) {
+		dwsbt1->map = devm_ioremap_resource(&pdev->dev, mem);
+		if (!IS_ERR(dwsbt1->map)) {
+			dwsbt1->map_len = resource_size(mem);
+			dws->mem_ops.dirmap_create = dw_spi_bt1_dirmap_create;
+			dws->mem_ops.dirmap_read = dw_spi_bt1_dirmap_read;
+		} else {
+			dwsbt1->map = NULL;
+		}
+	}
+#endif /* CONFIG_SPI_DW_BT1_DIRMAP */
+
+	/*
+	 * There is no IRQ, no DMA and just one CS available on the System Boot
+	 * SPI controller.
+	 */
+	dws->irq = IRQ_NOTCONNECTED;
+	dws->num_cs = 1;
+
+	/*
+	 * Baikal-T1 System Boot SPI Controller doesn't keep up with the full
+	 * SPI bus speed due to relatively slow APB bus and races for it'
+	 * resources from different CPUs. The situation is worsen by a small
+	 * FIFOs depth (just 8 words). It works better in a single CPU mode
+	 * though, but still tends to be not fast enough at low CPU
+	 * frequencies.
+	 */
+	if (num_possible_cpus() > 1)
+		dws->max_mem_freq = 10000000U;
+	else
+		dws->max_mem_freq = 20000000U;
+
+	return 0;
+}
+
+static int dw_spi_bt1_probe(struct platform_device *pdev)
+{
+	dw_spi_bt1_init_cb init_func;
+	struct dw_spi_bt1 *dwsbt1;
+	struct resource *mem;
+	struct dw_spi *dws;
+	int ret;
+
+	dwsbt1 = devm_kzalloc(&pdev->dev, sizeof(struct dw_spi_bt1), GFP_KERNEL);
+	if (!dwsbt1)
+		return -ENOMEM;
+
+	dws = &dwsbt1->dws;
+
+	dws->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
+	if (IS_ERR(dws->regs))
+		return PTR_ERR(dws->regs);
+
+	dws->paddr = mem->start;
+
+	dwsbt1->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dwsbt1->clk))
+		return PTR_ERR(dwsbt1->clk);
+
+	ret = clk_prepare_enable(dwsbt1->clk);
+	if (ret)
+		return ret;
+
+	dws->bus_num = pdev->id;
+	dws->reg_io_width = 4;
+	dws->max_freq = clk_get_rate(dwsbt1->clk);
+	if (!dws->max_freq) {
+		ret = -EINVAL;
+		goto err_disable_clk;
+	}
+
+	init_func = device_get_match_data(&pdev->dev);
+	ret = init_func(pdev, dwsbt1);
+	if (ret)
+		goto err_disable_clk;
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = dw_spi_add_host(&pdev->dev, dws);
+	if (ret) {
+		pm_runtime_disable(&pdev->dev);
+		goto err_disable_clk;
+	}
+
+	platform_set_drvdata(pdev, dwsbt1);
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(dwsbt1->clk);
+
+	return ret;
+}
+
+static int dw_spi_bt1_remove(struct platform_device *pdev)
+{
+	struct dw_spi_bt1 *dwsbt1 = platform_get_drvdata(pdev);
+
+	dw_spi_remove_host(&dwsbt1->dws);
+
+	pm_runtime_disable(&pdev->dev);
+
+	clk_disable_unprepare(dwsbt1->clk);
+
+	return 0;
+}
+
+static const struct of_device_id dw_spi_bt1_of_match[] = {
+	{ .compatible = "baikal,bt1-ssi", .data = dw_spi_bt1_std_init},
+	{ .compatible = "baikal,bt1-sys-ssi", .data = dw_spi_bt1_sys_init},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, dw_spi_bt1_of_match);
+
+static struct platform_driver dw_spi_bt1_driver = {
+	.probe	= dw_spi_bt1_probe,
+	.remove	= dw_spi_bt1_remove,
+	.driver	= {
+		.name		= "bt1-sys-ssi",
+		.of_match_table	= dw_spi_bt1_of_match,
+	},
+};
+module_platform_driver(dw_spi_bt1_driver);
+
+MODULE_AUTHOR("Serge Semin <Sergey.Semin@baikalelectronics.ru>");
+MODULE_DESCRIPTION("Baikal-T1 System Boot SPI Controller driver");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(SPI_DW_CORE);