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, 329 insertions, 0 deletions

diff --git a/drivers/clk/clk-highbank.c b/drivers/clk/clk-highbank.c
new file mode 100644
index 000000000..2a0cea294
--- /dev/null
+++ b/drivers/clk/clk-highbank.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2011-2012 Calxeda, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#define HB_PLL_LOCK_500		0x20000000
+#define HB_PLL_LOCK		0x10000000
+#define HB_PLL_DIVF_SHIFT	20
+#define HB_PLL_DIVF_MASK	0x0ff00000
+#define HB_PLL_DIVQ_SHIFT	16
+#define HB_PLL_DIVQ_MASK	0x00070000
+#define HB_PLL_DIVR_SHIFT	8
+#define HB_PLL_DIVR_MASK	0x00001f00
+#define HB_PLL_RANGE_SHIFT	4
+#define HB_PLL_RANGE_MASK	0x00000070
+#define HB_PLL_BYPASS		0x00000008
+#define HB_PLL_RESET		0x00000004
+#define HB_PLL_EXT_BYPASS	0x00000002
+#define HB_PLL_EXT_ENA		0x00000001
+
+#define HB_PLL_VCO_MIN_FREQ	2133000000
+#define HB_PLL_MAX_FREQ		HB_PLL_VCO_MIN_FREQ
+#define HB_PLL_MIN_FREQ		(HB_PLL_VCO_MIN_FREQ / 64)
+
+#define HB_A9_BCLK_DIV_MASK	0x00000006
+#define HB_A9_BCLK_DIV_SHIFT	1
+#define HB_A9_PCLK_DIV		0x00000001
+
+struct hb_clk {
+        struct clk_hw	hw;
+	void __iomem	*reg;
+	char *parent_name;
+};
+#define to_hb_clk(p) container_of(p, struct hb_clk, hw)
+
+static int clk_pll_prepare(struct clk_hw *hwclk)
+	{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 reg;
+
+	reg = readl(hbclk->reg);
+	reg &= ~HB_PLL_RESET;
+	writel(reg, hbclk->reg);
+
+	while ((readl(hbclk->reg) & HB_PLL_LOCK) == 0)
+		;
+	while ((readl(hbclk->reg) & HB_PLL_LOCK_500) == 0)
+		;
+
+	return 0;
+}
+
+static void clk_pll_unprepare(struct clk_hw *hwclk)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 reg;
+
+	reg = readl(hbclk->reg);
+	reg |= HB_PLL_RESET;
+	writel(reg, hbclk->reg);
+}
+
+static int clk_pll_enable(struct clk_hw *hwclk)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 reg;
+
+	reg = readl(hbclk->reg);
+	reg |= HB_PLL_EXT_ENA;
+	writel(reg, hbclk->reg);
+
+	return 0;
+}
+
+static void clk_pll_disable(struct clk_hw *hwclk)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 reg;
+
+	reg = readl(hbclk->reg);
+	reg &= ~HB_PLL_EXT_ENA;
+	writel(reg, hbclk->reg);
+}
+
+static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk,
+					 unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	unsigned long divf, divq, vco_freq, reg;
+
+	reg = readl(hbclk->reg);
+	if (reg & HB_PLL_EXT_BYPASS)
+		return parent_rate;
+
+	divf = (reg & HB_PLL_DIVF_MASK) >> HB_PLL_DIVF_SHIFT;
+	divq = (reg & HB_PLL_DIVQ_MASK) >> HB_PLL_DIVQ_SHIFT;
+	vco_freq = parent_rate * (divf + 1);
+
+	return vco_freq / (1 << divq);
+}
+
+static void clk_pll_calc(unsigned long rate, unsigned long ref_freq,
+			u32 *pdivq, u32 *pdivf)
+{
+	u32 divq, divf;
+	unsigned long vco_freq;
+
+	if (rate < HB_PLL_MIN_FREQ)
+		rate = HB_PLL_MIN_FREQ;
+	if (rate > HB_PLL_MAX_FREQ)
+		rate = HB_PLL_MAX_FREQ;
+
+	for (divq = 1; divq <= 6; divq++) {
+		if ((rate * (1 << divq)) >= HB_PLL_VCO_MIN_FREQ)
+			break;
+	}
+
+	vco_freq = rate * (1 << divq);
+	divf = (vco_freq + (ref_freq / 2)) / ref_freq;
+	divf--;
+
+	*pdivq = divq;
+	*pdivf = divf;
+}
+
+static long clk_pll_round_rate(struct clk_hw *hwclk, unsigned long rate,
+			       unsigned long *parent_rate)
+{
+	u32 divq, divf;
+	unsigned long ref_freq = *parent_rate;
+
+	clk_pll_calc(rate, ref_freq, &divq, &divf);
+
+	return (ref_freq * (divf + 1)) / (1 << divq);
+}
+
+static int clk_pll_set_rate(struct clk_hw *hwclk, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 divq, divf;
+	u32 reg;
+
+	clk_pll_calc(rate, parent_rate, &divq, &divf);
+
+	reg = readl(hbclk->reg);
+	if (divf != ((reg & HB_PLL_DIVF_MASK) >> HB_PLL_DIVF_SHIFT)) {
+		/* Need to re-lock PLL, so put it into bypass mode */
+		reg |= HB_PLL_EXT_BYPASS;
+		writel(reg | HB_PLL_EXT_BYPASS, hbclk->reg);
+
+		writel(reg | HB_PLL_RESET, hbclk->reg);
+		reg &= ~(HB_PLL_DIVF_MASK | HB_PLL_DIVQ_MASK);
+		reg |= (divf << HB_PLL_DIVF_SHIFT) | (divq << HB_PLL_DIVQ_SHIFT);
+		writel(reg | HB_PLL_RESET, hbclk->reg);
+		writel(reg, hbclk->reg);
+
+		while ((readl(hbclk->reg) & HB_PLL_LOCK) == 0)
+			;
+		while ((readl(hbclk->reg) & HB_PLL_LOCK_500) == 0)
+			;
+		reg |= HB_PLL_EXT_ENA;
+		reg &= ~HB_PLL_EXT_BYPASS;
+	} else {
+		writel(reg | HB_PLL_EXT_BYPASS, hbclk->reg);
+		reg &= ~HB_PLL_DIVQ_MASK;
+		reg |= divq << HB_PLL_DIVQ_SHIFT;
+		writel(reg | HB_PLL_EXT_BYPASS, hbclk->reg);
+	}
+	writel(reg, hbclk->reg);
+
+	return 0;
+}
+
+static const struct clk_ops clk_pll_ops = {
+	.prepare = clk_pll_prepare,
+	.unprepare = clk_pll_unprepare,
+	.enable = clk_pll_enable,
+	.disable = clk_pll_disable,
+	.recalc_rate = clk_pll_recalc_rate,
+	.round_rate = clk_pll_round_rate,
+	.set_rate = clk_pll_set_rate,
+};
+
+static unsigned long clk_cpu_periphclk_recalc_rate(struct clk_hw *hwclk,
+						   unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 div = (readl(hbclk->reg) & HB_A9_PCLK_DIV) ? 8 : 4;
+	return parent_rate / div;
+}
+
+static const struct clk_ops a9periphclk_ops = {
+	.recalc_rate = clk_cpu_periphclk_recalc_rate,
+};
+
+static unsigned long clk_cpu_a9bclk_recalc_rate(struct clk_hw *hwclk,
+						unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 div = (readl(hbclk->reg) & HB_A9_BCLK_DIV_MASK) >> HB_A9_BCLK_DIV_SHIFT;
+
+	return parent_rate / (div + 2);
+}
+
+static const struct clk_ops a9bclk_ops = {
+	.recalc_rate = clk_cpu_a9bclk_recalc_rate,
+};
+
+static unsigned long clk_periclk_recalc_rate(struct clk_hw *hwclk,
+					     unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 div;
+
+	div = readl(hbclk->reg) & 0x1f;
+	div++;
+	div *= 2;
+
+	return parent_rate / div;
+}
+
+static long clk_periclk_round_rate(struct clk_hw *hwclk, unsigned long rate,
+				   unsigned long *parent_rate)
+{
+	u32 div;
+
+	div = *parent_rate / rate;
+	div++;
+	div &= ~0x1;
+
+	return *parent_rate / div;
+}
+
+static int clk_periclk_set_rate(struct clk_hw *hwclk, unsigned long rate,
+				unsigned long parent_rate)
+{
+	struct hb_clk *hbclk = to_hb_clk(hwclk);
+	u32 div;
+
+	div = parent_rate / rate;
+	if (div & 0x1)
+		return -EINVAL;
+
+	writel(div >> 1, hbclk->reg);
+	return 0;
+}
+
+static const struct clk_ops periclk_ops = {
+	.recalc_rate = clk_periclk_recalc_rate,
+	.round_rate = clk_periclk_round_rate,
+	.set_rate = clk_periclk_set_rate,
+};
+
+static void __init hb_clk_init(struct device_node *node, const struct clk_ops *ops, unsigned long clkflags)
+{
+	u32 reg;
+	struct hb_clk *hb_clk;
+	const char *clk_name = node->name;
+	const char *parent_name;
+	struct clk_init_data init;
+	struct device_node *srnp;
+	int rc;
+
+	rc = of_property_read_u32(node, "reg", &reg);
+	if (WARN_ON(rc))
+		return;
+
+	hb_clk = kzalloc(sizeof(*hb_clk), GFP_KERNEL);
+	if (WARN_ON(!hb_clk))
+		return;
+
+	/* Map system registers */
+	srnp = of_find_compatible_node(NULL, NULL, "calxeda,hb-sregs");
+	hb_clk->reg = of_iomap(srnp, 0);
+	of_node_put(srnp);
+	BUG_ON(!hb_clk->reg);
+	hb_clk->reg += reg;
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = ops;
+	init.flags = clkflags;
+	parent_name = of_clk_get_parent_name(node, 0);
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	hb_clk->hw.init = &init;
+
+	rc = clk_hw_register(NULL, &hb_clk->hw);
+	if (WARN_ON(rc)) {
+		kfree(hb_clk);
+		return;
+	}
+	of_clk_add_hw_provider(node, of_clk_hw_simple_get, &hb_clk->hw);
+}
+
+static void __init hb_pll_init(struct device_node *node)
+{
+	hb_clk_init(node, &clk_pll_ops, 0);
+}
+CLK_OF_DECLARE(hb_pll, "calxeda,hb-pll-clock", hb_pll_init);
+
+static void __init hb_a9periph_init(struct device_node *node)
+{
+	hb_clk_init(node, &a9periphclk_ops, 0);
+}
+CLK_OF_DECLARE(hb_a9periph, "calxeda,hb-a9periph-clock", hb_a9periph_init);
+
+static void __init hb_a9bus_init(struct device_node *node)
+{
+	hb_clk_init(node, &a9bclk_ops, CLK_IS_CRITICAL);
+}
+CLK_OF_DECLARE(hb_a9bus, "calxeda,hb-a9bus-clock", hb_a9bus_init);
+
+static void __init hb_emmc_init(struct device_node *node)
+{
+	hb_clk_init(node, &periclk_ops, 0);
+}
+CLK_OF_DECLARE(hb_emmc, "calxeda,hb-emmc-clock", hb_emmc_init);