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, 363 insertions, 0 deletions

diff --git a/arch/arm/mach-bcm/platsmp-brcmstb.c b/arch/arm/mach-bcm/platsmp-brcmstb.c
new file mode 100644
index 000000000..8989299eb
--- /dev/null
+++ b/arch/arm/mach-bcm/platsmp-brcmstb.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Broadcom STB CPU SMP and hotplug support for ARM
+ *
+ * Copyright (C) 2013-2014 Broadcom Corporation
+ */
+
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/printk.h>
+#include <linux/regmap.h>
+#include <linux/smp.h>
+#include <linux/mfd/syscon.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cp15.h>
+#include <asm/mach-types.h>
+#include <asm/smp_plat.h>
+
+enum {
+	ZONE_MAN_CLKEN_MASK		= BIT(0),
+	ZONE_MAN_RESET_CNTL_MASK	= BIT(1),
+	ZONE_MAN_MEM_PWR_MASK		= BIT(4),
+	ZONE_RESERVED_1_MASK		= BIT(5),
+	ZONE_MAN_ISO_CNTL_MASK		= BIT(6),
+	ZONE_MANUAL_CONTROL_MASK	= BIT(7),
+	ZONE_PWR_DN_REQ_MASK		= BIT(9),
+	ZONE_PWR_UP_REQ_MASK		= BIT(10),
+	ZONE_BLK_RST_ASSERT_MASK	= BIT(12),
+	ZONE_PWR_OFF_STATE_MASK		= BIT(25),
+	ZONE_PWR_ON_STATE_MASK		= BIT(26),
+	ZONE_DPG_PWR_STATE_MASK		= BIT(28),
+	ZONE_MEM_PWR_STATE_MASK		= BIT(29),
+	ZONE_RESET_STATE_MASK		= BIT(31),
+	CPU0_PWR_ZONE_CTRL_REG		= 1,
+	CPU_RESET_CONFIG_REG		= 2,
+};
+
+static void __iomem *cpubiuctrl_block;
+static void __iomem *hif_cont_block;
+static u32 cpu0_pwr_zone_ctrl_reg;
+static u32 cpu_rst_cfg_reg;
+static u32 hif_cont_reg;
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * We must quiesce a dying CPU before it can be killed by the boot CPU. Because
+ * one or more cache may be disabled, we must flush to ensure coherency. We
+ * cannot use traditional completion structures or spinlocks as they rely on
+ * coherency.
+ */
+static DEFINE_PER_CPU_ALIGNED(int, per_cpu_sw_state);
+
+static int per_cpu_sw_state_rd(u32 cpu)
+{
+	sync_cache_r(SHIFT_PERCPU_PTR(&per_cpu_sw_state, per_cpu_offset(cpu)));
+	return per_cpu(per_cpu_sw_state, cpu);
+}
+
+static void per_cpu_sw_state_wr(u32 cpu, int val)
+{
+	dmb();
+	per_cpu(per_cpu_sw_state, cpu) = val;
+	sync_cache_w(SHIFT_PERCPU_PTR(&per_cpu_sw_state, per_cpu_offset(cpu)));
+}
+#else
+static inline void per_cpu_sw_state_wr(u32 cpu, int val) { }
+#endif
+
+static void __iomem *pwr_ctrl_get_base(u32 cpu)
+{
+	void __iomem *base = cpubiuctrl_block + cpu0_pwr_zone_ctrl_reg;
+	base += (cpu_logical_map(cpu) * 4);
+	return base;
+}
+
+static u32 pwr_ctrl_rd(u32 cpu)
+{
+	void __iomem *base = pwr_ctrl_get_base(cpu);
+	return readl_relaxed(base);
+}
+
+static void pwr_ctrl_set(unsigned int cpu, u32 val, u32 mask)
+{
+	void __iomem *base = pwr_ctrl_get_base(cpu);
+	writel((readl(base) & mask) | val, base);
+}
+
+static void pwr_ctrl_clr(unsigned int cpu, u32 val, u32 mask)
+{
+	void __iomem *base = pwr_ctrl_get_base(cpu);
+	writel((readl(base) & mask) & ~val, base);
+}
+
+#define POLL_TMOUT_MS 500
+static int pwr_ctrl_wait_tmout(unsigned int cpu, u32 set, u32 mask)
+{
+	const unsigned long timeo = jiffies + msecs_to_jiffies(POLL_TMOUT_MS);
+	u32 tmp;
+
+	do {
+		tmp = pwr_ctrl_rd(cpu) & mask;
+		if (!set == !tmp)
+			return 0;
+	} while (time_before(jiffies, timeo));
+
+	tmp = pwr_ctrl_rd(cpu) & mask;
+	if (!set == !tmp)
+		return 0;
+
+	return -ETIMEDOUT;
+}
+
+static void cpu_rst_cfg_set(u32 cpu, int set)
+{
+	u32 val;
+	val = readl_relaxed(cpubiuctrl_block + cpu_rst_cfg_reg);
+	if (set)
+		val |= BIT(cpu_logical_map(cpu));
+	else
+		val &= ~BIT(cpu_logical_map(cpu));
+	writel_relaxed(val, cpubiuctrl_block + cpu_rst_cfg_reg);
+}
+
+static void cpu_set_boot_addr(u32 cpu, unsigned long boot_addr)
+{
+	const int reg_ofs = cpu_logical_map(cpu) * 8;
+	writel_relaxed(0, hif_cont_block + hif_cont_reg + reg_ofs);
+	writel_relaxed(boot_addr, hif_cont_block + hif_cont_reg + 4 + reg_ofs);
+}
+
+static void brcmstb_cpu_boot(u32 cpu)
+{
+	/* Mark this CPU as "up" */
+	per_cpu_sw_state_wr(cpu, 1);
+
+	/*
+	 * Set the reset vector to point to the secondary_startup
+	 * routine
+	 */
+	cpu_set_boot_addr(cpu, __pa_symbol(secondary_startup));
+
+	/* Unhalt the cpu */
+	cpu_rst_cfg_set(cpu, 0);
+}
+
+static void brcmstb_cpu_power_on(u32 cpu)
+{
+	/*
+	 * The secondary cores power was cut, so we must go through
+	 * power-on initialization.
+	 */
+	pwr_ctrl_set(cpu, ZONE_MAN_ISO_CNTL_MASK, 0xffffff00);
+	pwr_ctrl_set(cpu, ZONE_MANUAL_CONTROL_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_RESERVED_1_MASK, -1);
+
+	pwr_ctrl_set(cpu, ZONE_MAN_MEM_PWR_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 1, ZONE_MEM_PWR_STATE_MASK))
+		panic("ZONE_MEM_PWR_STATE_MASK set timeout");
+
+	pwr_ctrl_set(cpu, ZONE_MAN_CLKEN_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 1, ZONE_DPG_PWR_STATE_MASK))
+		panic("ZONE_DPG_PWR_STATE_MASK set timeout");
+
+	pwr_ctrl_clr(cpu, ZONE_MAN_ISO_CNTL_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_MAN_RESET_CNTL_MASK, -1);
+}
+
+static int brcmstb_cpu_get_power_state(u32 cpu)
+{
+	int tmp = pwr_ctrl_rd(cpu);
+	return (tmp & ZONE_RESET_STATE_MASK) ? 0 : 1;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void brcmstb_cpu_die(u32 cpu)
+{
+	v7_exit_coherency_flush(all);
+
+	per_cpu_sw_state_wr(cpu, 0);
+
+	/* Sit and wait to die */
+	wfi();
+
+	/* We should never get here... */
+	while (1)
+		;
+}
+
+static int brcmstb_cpu_kill(u32 cpu)
+{
+	/*
+	 * Ordinarily, the hardware forbids power-down of CPU0 (which is good
+	 * because it is the boot CPU), but this is not true when using BPCM
+	 * manual mode.  Consequently, we must avoid turning off CPU0 here to
+	 * ensure that TI2C master reset will work.
+	 */
+	if (cpu == 0) {
+		pr_warn("SMP: refusing to power off CPU0\n");
+		return 1;
+	}
+
+	while (per_cpu_sw_state_rd(cpu))
+		;
+
+	pwr_ctrl_set(cpu, ZONE_MANUAL_CONTROL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_RESET_CNTL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_CLKEN_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_MAN_ISO_CNTL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_MEM_PWR_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 0, ZONE_MEM_PWR_STATE_MASK))
+		panic("ZONE_MEM_PWR_STATE_MASK clear timeout");
+
+	pwr_ctrl_clr(cpu, ZONE_RESERVED_1_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 0, ZONE_DPG_PWR_STATE_MASK))
+		panic("ZONE_DPG_PWR_STATE_MASK clear timeout");
+
+	/* Flush pipeline before resetting CPU */
+	mb();
+
+	/* Assert reset on the CPU */
+	cpu_rst_cfg_set(cpu, 1);
+
+	return 1;
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int __init setup_hifcpubiuctrl_regs(struct device_node *np)
+{
+	int rc = 0;
+	char *name;
+	struct device_node *syscon_np = NULL;
+
+	name = "syscon-cpu";
+
+	syscon_np = of_parse_phandle(np, name, 0);
+	if (!syscon_np) {
+		pr_err("can't find phandle %s\n", name);
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+	cpubiuctrl_block = of_iomap(syscon_np, 0);
+	if (!cpubiuctrl_block) {
+		pr_err("iomap failed for cpubiuctrl_block\n");
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+	rc = of_property_read_u32_index(np, name, CPU0_PWR_ZONE_CTRL_REG,
+					&cpu0_pwr_zone_ctrl_reg);
+	if (rc) {
+		pr_err("failed to read 1st entry from %s property (%d)\n", name,
+			rc);
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+	rc = of_property_read_u32_index(np, name, CPU_RESET_CONFIG_REG,
+					&cpu_rst_cfg_reg);
+	if (rc) {
+		pr_err("failed to read 2nd entry from %s property (%d)\n", name,
+			rc);
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+cleanup:
+	of_node_put(syscon_np);
+	return rc;
+}
+
+static int __init setup_hifcont_regs(struct device_node *np)
+{
+	int rc = 0;
+	char *name;
+	struct device_node *syscon_np = NULL;
+
+	name = "syscon-cont";
+
+	syscon_np = of_parse_phandle(np, name, 0);
+	if (!syscon_np) {
+		pr_err("can't find phandle %s\n", name);
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+	hif_cont_block = of_iomap(syscon_np, 0);
+	if (!hif_cont_block) {
+		pr_err("iomap failed for hif_cont_block\n");
+		rc = -EINVAL;
+		goto cleanup;
+	}
+
+	/* Offset is at top of hif_cont_block */
+	hif_cont_reg = 0;
+
+cleanup:
+	of_node_put(syscon_np);
+	return rc;
+}
+
+static void __init brcmstb_cpu_ctrl_setup(unsigned int max_cpus)
+{
+	int rc;
+	struct device_node *np;
+	char *name;
+
+	name = "brcm,brcmstb-smpboot";
+	np = of_find_compatible_node(NULL, NULL, name);
+	if (!np) {
+		pr_err("can't find compatible node %s\n", name);
+		return;
+	}
+
+	rc = setup_hifcpubiuctrl_regs(np);
+	if (rc)
+		goto out_put_node;
+
+	rc = setup_hifcont_regs(np);
+	if (rc)
+		goto out_put_node;
+
+out_put_node:
+	of_node_put(np);
+}
+
+static int brcmstb_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	/* Missing the brcm,brcmstb-smpboot DT node? */
+	if (!cpubiuctrl_block || !hif_cont_block)
+		return -ENODEV;
+
+	/* Bring up power to the core if necessary */
+	if (brcmstb_cpu_get_power_state(cpu) == 0)
+		brcmstb_cpu_power_on(cpu);
+
+	brcmstb_cpu_boot(cpu);
+
+	return 0;
+}
+
+static const struct smp_operations brcmstb_smp_ops __initconst = {
+	.smp_prepare_cpus	= brcmstb_cpu_ctrl_setup,
+	.smp_boot_secondary	= brcmstb_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_kill		= brcmstb_cpu_kill,
+	.cpu_die		= brcmstb_cpu_die,
+#endif
+};
+
+CPU_METHOD_OF_DECLARE(brcmstb_smp, "brcm,brahma-b15", &brcmstb_smp_ops);