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, 220 insertions, 0 deletions

diff --git a/drivers/clk/mstar/clk-msc313-cpupll.c b/drivers/clk/mstar/clk-msc313-cpupll.c
new file mode 100644
index 000000000..a93e2dba0
--- /dev/null
+++ b/drivers/clk/mstar/clk-msc313-cpupll.c
@@ -0,0 +1,220 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Daniel Palmer <daniel@thingy.jp>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+
+/*
+ * This IP is not documented outside of the messy vendor driver.
+ * Below is what we think the registers look like based on looking at
+ * the vendor code and poking at the hardware:
+ *
+ * 0x140 -- LPF low. Seems to store one half of the clock transition
+ * 0x144 /
+ * 0x148 -- LPF high. Seems to store one half of the clock transition
+ * 0x14c /
+ * 0x150 -- vendor code says "toggle lpf enable"
+ * 0x154 -- mu?
+ * 0x15c -- lpf_update_count?
+ * 0x160 -- vendor code says "switch to LPF". Clock source config? Register bank?
+ * 0x164 -- vendor code says "from low to high" which seems to mean transition from LPF low to
+ * LPF high.
+ * 0x174 -- Seems to be the PLL lock status bit
+ * 0x180 -- Seems to be the current frequency, this might need to be populated by software?
+ * 0x184 /  The vendor driver uses these to set the initial value of LPF low
+ *
+ * Frequency seems to be calculated like this:
+ * (parent clock (432mhz) / register_magic_value) * 16 * 524288
+ * Only the lower 24 bits of the resulting value will be used. In addition, the
+ * PLL doesn't seem to be able to lock on frequencies lower than 220 MHz, as
+ * divisor 0xfb586f (220 MHz) works but 0xfb7fff locks up.
+ *
+ * Vendor values:
+ * frequency - register value
+ *
+ * 400000000  - 0x0067AE14
+ * 600000000  - 0x00451EB8,
+ * 800000000  - 0x0033D70A,
+ * 1000000000 - 0x002978d4,
+ */
+
+#define REG_LPF_LOW_L		0x140
+#define REG_LPF_LOW_H		0x144
+#define REG_LPF_HIGH_BOTTOM	0x148
+#define REG_LPF_HIGH_TOP	0x14c
+#define REG_LPF_TOGGLE		0x150
+#define REG_LPF_MYSTERYTWO	0x154
+#define REG_LPF_UPDATE_COUNT	0x15c
+#define REG_LPF_MYSTERYONE	0x160
+#define REG_LPF_TRANSITIONCTRL	0x164
+#define REG_LPF_LOCK		0x174
+#define REG_CURRENT		0x180
+
+#define LPF_LOCK_TIMEOUT	100000000
+
+#define MULTIPLIER_1		16
+#define MULTIPLIER_2		524288
+#define MULTIPLIER		(MULTIPLIER_1 * MULTIPLIER_2)
+
+struct msc313_cpupll {
+	void __iomem *base;
+	struct clk_hw clk_hw;
+};
+
+#define to_cpupll(_hw) container_of(_hw, struct msc313_cpupll, clk_hw)
+
+static u32 msc313_cpupll_reg_read32(struct msc313_cpupll *cpupll, unsigned int reg)
+{
+	u32 value;
+
+	value = ioread16(cpupll->base + reg + 4) << 16;
+	value |= ioread16(cpupll->base + reg);
+
+	return value;
+}
+
+static void msc313_cpupll_reg_write32(struct msc313_cpupll *cpupll, unsigned int reg, u32 value)
+{
+	u16 l = value & 0xffff, h = (value >> 16) & 0xffff;
+
+	iowrite16(l, cpupll->base + reg);
+	iowrite16(h, cpupll->base + reg + 4);
+}
+
+static void msc313_cpupll_setfreq(struct msc313_cpupll *cpupll, u32 regvalue)
+{
+	ktime_t timeout;
+
+	msc313_cpupll_reg_write32(cpupll, REG_LPF_HIGH_BOTTOM, regvalue);
+
+	iowrite16(0x1, cpupll->base + REG_LPF_MYSTERYONE);
+	iowrite16(0x6, cpupll->base + REG_LPF_MYSTERYTWO);
+	iowrite16(0x8, cpupll->base + REG_LPF_UPDATE_COUNT);
+	iowrite16(BIT(12), cpupll->base + REG_LPF_TRANSITIONCTRL);
+
+	iowrite16(0, cpupll->base + REG_LPF_TOGGLE);
+	iowrite16(1, cpupll->base + REG_LPF_TOGGLE);
+
+	timeout = ktime_add_ns(ktime_get(), LPF_LOCK_TIMEOUT);
+	while (!(ioread16(cpupll->base + REG_LPF_LOCK))) {
+		if (ktime_after(ktime_get(), timeout)) {
+			pr_err("timeout waiting for LPF_LOCK\n");
+			return;
+		}
+		cpu_relax();
+	}
+
+	iowrite16(0, cpupll->base + REG_LPF_TOGGLE);
+
+	msc313_cpupll_reg_write32(cpupll, REG_LPF_LOW_L, regvalue);
+}
+
+static unsigned long msc313_cpupll_frequencyforreg(u32 reg, unsigned long parent_rate)
+{
+	unsigned long long prescaled = ((unsigned long long)parent_rate) * MULTIPLIER;
+
+	if (prescaled == 0 || reg == 0)
+		return 0;
+	return DIV_ROUND_DOWN_ULL(prescaled, reg);
+}
+
+static u32 msc313_cpupll_regforfrequecy(unsigned long rate, unsigned long parent_rate)
+{
+	unsigned long long prescaled = ((unsigned long long)parent_rate) * MULTIPLIER;
+
+	if (prescaled == 0 || rate == 0)
+		return 0;
+	return DIV_ROUND_UP_ULL(prescaled, rate);
+}
+
+static unsigned long msc313_cpupll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+{
+	struct msc313_cpupll *cpupll = to_cpupll(hw);
+
+	return msc313_cpupll_frequencyforreg(msc313_cpupll_reg_read32(cpupll, REG_LPF_LOW_L),
+					     parent_rate);
+}
+
+static long msc313_cpupll_round_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long *parent_rate)
+{
+	u32 reg = msc313_cpupll_regforfrequecy(rate, *parent_rate);
+	long rounded = msc313_cpupll_frequencyforreg(reg, *parent_rate);
+
+	/*
+	 * This is my poor attempt at making sure the resulting
+	 * rate doesn't overshoot the requested rate.
+	 */
+	for (; rounded >= rate && reg > 0; reg--)
+		rounded = msc313_cpupll_frequencyforreg(reg, *parent_rate);
+
+	return rounded;
+}
+
+static int msc313_cpupll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate)
+{
+	struct msc313_cpupll *cpupll = to_cpupll(hw);
+	u32 reg = msc313_cpupll_regforfrequecy(rate, parent_rate);
+
+	msc313_cpupll_setfreq(cpupll, reg);
+
+	return 0;
+}
+
+static const struct clk_ops msc313_cpupll_ops = {
+	.recalc_rate	= msc313_cpupll_recalc_rate,
+	.round_rate	= msc313_cpupll_round_rate,
+	.set_rate	= msc313_cpupll_set_rate,
+};
+
+static const struct of_device_id msc313_cpupll_of_match[] = {
+	{ .compatible = "mstar,msc313-cpupll" },
+	{}
+};
+
+static int msc313_cpupll_probe(struct platform_device *pdev)
+{
+	struct clk_init_data clk_init = {};
+	struct clk_parent_data cpupll_parent = { .index	= 0 };
+	struct device *dev = &pdev->dev;
+	struct msc313_cpupll *cpupll;
+	int ret;
+
+	cpupll = devm_kzalloc(&pdev->dev, sizeof(*cpupll), GFP_KERNEL);
+	if (!cpupll)
+		return -ENOMEM;
+
+	cpupll->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(cpupll->base))
+		return PTR_ERR(cpupll->base);
+
+	/* LPF might not contain the current frequency so fix that up */
+	msc313_cpupll_reg_write32(cpupll, REG_LPF_LOW_L,
+				  msc313_cpupll_reg_read32(cpupll, REG_CURRENT));
+
+	clk_init.name = dev_name(dev);
+	clk_init.ops = &msc313_cpupll_ops;
+	clk_init.parent_data = &cpupll_parent;
+	clk_init.num_parents = 1;
+	cpupll->clk_hw.init = &clk_init;
+
+	ret = devm_clk_hw_register(dev, &cpupll->clk_hw);
+	if (ret)
+		return ret;
+
+	return devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get, &cpupll->clk_hw);
+}
+
+static struct platform_driver msc313_cpupll_driver = {
+	.driver = {
+		.name = "mstar-msc313-cpupll",
+		.of_match_table = msc313_cpupll_of_match,
+	},
+	.probe = msc313_cpupll_probe,
+};
+builtin_platform_driver(msc313_cpupll_driver);