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, 431 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
new file mode 100644
index 000000000..3fa8979ac
--- /dev/null
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -0,0 +1,431 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MPC83xx suspend support
+ *
+ * Author: Scott Wood <scottwood@freescale.com>
+ *
+ * Copyright (c) 2006-2007 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/pm.h>
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/wait.h>
+#include <linux/sched/signal.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/suspend.h>
+#include <linux/fsl_devices.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/export.h>
+
+#include <asm/reg.h>
+#include <asm/io.h>
+#include <asm/time.h>
+#include <asm/mpc6xx.h>
+#include <asm/switch_to.h>
+
+#include <sysdev/fsl_soc.h>
+
+#define PMCCR1_NEXT_STATE       0x0C /* Next state for power management */
+#define PMCCR1_NEXT_STATE_SHIFT 2
+#define PMCCR1_CURR_STATE       0x03 /* Current state for power management*/
+#define IMMR_SYSCR_OFFSET       0x100
+#define IMMR_RCW_OFFSET         0x900
+#define RCW_PCI_HOST            0x80000000
+
+void mpc83xx_enter_deep_sleep(phys_addr_t immrbase);
+
+struct mpc83xx_pmc {
+	u32 config;
+#define PMCCR_DLPEN 2 /* DDR SDRAM low power enable */
+#define PMCCR_SLPEN 1 /* System low power enable */
+
+	u32 event;
+	u32 mask;
+/* All but PMCI are deep-sleep only */
+#define PMCER_GPIO   0x100
+#define PMCER_PCI    0x080
+#define PMCER_USB    0x040
+#define PMCER_ETSEC1 0x020
+#define PMCER_ETSEC2 0x010
+#define PMCER_TIMER  0x008
+#define PMCER_INT1   0x004
+#define PMCER_INT2   0x002
+#define PMCER_PMCI   0x001
+#define PMCER_ALL    0x1FF
+
+	/* deep-sleep only */
+	u32 config1;
+#define PMCCR1_USE_STATE  0x80000000
+#define PMCCR1_PME_EN     0x00000080
+#define PMCCR1_ASSERT_PME 0x00000040
+#define PMCCR1_POWER_OFF  0x00000020
+
+	/* deep-sleep only */
+	u32 config2;
+};
+
+struct mpc83xx_rcw {
+	u32 rcwlr;
+	u32 rcwhr;
+};
+
+struct mpc83xx_clock {
+	u32 spmr;
+	u32 occr;
+	u32 sccr;
+};
+
+struct mpc83xx_syscr {
+	__be32 sgprl;
+	__be32 sgprh;
+	__be32 spridr;
+	__be32 :32;
+	__be32 spcr;
+	__be32 sicrl;
+	__be32 sicrh;
+};
+
+struct mpc83xx_saved {
+	u32 sicrl;
+	u32 sicrh;
+	u32 sccr;
+};
+
+struct pmc_type {
+	int has_deep_sleep;
+};
+
+static int has_deep_sleep, deep_sleeping;
+static int pmc_irq;
+static struct mpc83xx_pmc __iomem *pmc_regs;
+static struct mpc83xx_clock __iomem *clock_regs;
+static struct mpc83xx_syscr __iomem *syscr_regs;
+static struct mpc83xx_saved saved_regs;
+static int is_pci_agent, wake_from_pci;
+static phys_addr_t immrbase;
+static int pci_pm_state;
+static DECLARE_WAIT_QUEUE_HEAD(agent_wq);
+
+int fsl_deep_sleep(void)
+{
+	return deep_sleeping;
+}
+EXPORT_SYMBOL(fsl_deep_sleep);
+
+static int mpc83xx_change_state(void)
+{
+	u32 curr_state;
+	u32 reg_cfg1 = in_be32(&pmc_regs->config1);
+
+	if (is_pci_agent) {
+		pci_pm_state = (reg_cfg1 & PMCCR1_NEXT_STATE) >>
+		               PMCCR1_NEXT_STATE_SHIFT;
+		curr_state = reg_cfg1 & PMCCR1_CURR_STATE;
+
+		if (curr_state != pci_pm_state) {
+			reg_cfg1 &= ~PMCCR1_CURR_STATE;
+			reg_cfg1 |= pci_pm_state;
+			out_be32(&pmc_regs->config1, reg_cfg1);
+
+			wake_up(&agent_wq);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static irqreturn_t pmc_irq_handler(int irq, void *dev_id)
+{
+	u32 event = in_be32(&pmc_regs->event);
+	int ret = IRQ_NONE;
+
+	if (mpc83xx_change_state())
+		ret = IRQ_HANDLED;
+
+	if (event) {
+		out_be32(&pmc_regs->event, event);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void mpc83xx_suspend_restore_regs(void)
+{
+	out_be32(&syscr_regs->sicrl, saved_regs.sicrl);
+	out_be32(&syscr_regs->sicrh, saved_regs.sicrh);
+	out_be32(&clock_regs->sccr, saved_regs.sccr);
+}
+
+static void mpc83xx_suspend_save_regs(void)
+{
+	saved_regs.sicrl = in_be32(&syscr_regs->sicrl);
+	saved_regs.sicrh = in_be32(&syscr_regs->sicrh);
+	saved_regs.sccr = in_be32(&clock_regs->sccr);
+}
+
+static int mpc83xx_suspend_enter(suspend_state_t state)
+{
+	int ret = -EAGAIN;
+
+	/* Don't go to sleep if there's a race where pci_pm_state changes
+	 * between the agent thread checking it and the PM code disabling
+	 * interrupts.
+	 */
+	if (wake_from_pci) {
+		if (pci_pm_state != (deep_sleeping ? 3 : 2))
+			goto out;
+
+		out_be32(&pmc_regs->config1,
+		         in_be32(&pmc_regs->config1) | PMCCR1_PME_EN);
+	}
+
+	/* Put the system into low-power mode and the RAM
+	 * into self-refresh mode once the core goes to
+	 * sleep.
+	 */
+
+	out_be32(&pmc_regs->config, PMCCR_SLPEN | PMCCR_DLPEN);
+
+	/* If it has deep sleep (i.e. it's an 831x or compatible),
+	 * disable power to the core upon entering sleep mode.  This will
+	 * require going through the boot firmware upon a wakeup event.
+	 */
+
+	if (deep_sleeping) {
+		mpc83xx_suspend_save_regs();
+
+		out_be32(&pmc_regs->mask, PMCER_ALL);
+
+		out_be32(&pmc_regs->config1,
+		         in_be32(&pmc_regs->config1) | PMCCR1_POWER_OFF);
+
+		enable_kernel_fp();
+
+		mpc83xx_enter_deep_sleep(immrbase);
+
+		out_be32(&pmc_regs->config1,
+		         in_be32(&pmc_regs->config1) & ~PMCCR1_POWER_OFF);
+
+		out_be32(&pmc_regs->mask, PMCER_PMCI);
+
+		mpc83xx_suspend_restore_regs();
+	} else {
+		out_be32(&pmc_regs->mask, PMCER_PMCI);
+
+		mpc6xx_enter_standby();
+	}
+
+	ret = 0;
+
+out:
+	out_be32(&pmc_regs->config1,
+	         in_be32(&pmc_regs->config1) & ~PMCCR1_PME_EN);
+
+	return ret;
+}
+
+static void mpc83xx_suspend_end(void)
+{
+	deep_sleeping = 0;
+}
+
+static int mpc83xx_suspend_valid(suspend_state_t state)
+{
+	return state == PM_SUSPEND_STANDBY || state == PM_SUSPEND_MEM;
+}
+
+static int mpc83xx_suspend_begin(suspend_state_t state)
+{
+	switch (state) {
+		case PM_SUSPEND_STANDBY:
+			deep_sleeping = 0;
+			return 0;
+
+		case PM_SUSPEND_MEM:
+			if (has_deep_sleep)
+				deep_sleeping = 1;
+
+			return 0;
+
+		default:
+			return -EINVAL;
+	}
+}
+
+static int agent_thread_fn(void *data)
+{
+	while (1) {
+		wait_event_interruptible(agent_wq, pci_pm_state >= 2);
+		try_to_freeze();
+
+		if (signal_pending(current) || pci_pm_state < 2)
+			continue;
+
+		/* With a preemptible kernel (or SMP), this could race with
+		 * a userspace-driven suspend request.  It's probably best
+		 * to avoid mixing the two with such a configuration (or
+		 * else fix it by adding a mutex to state_store that we can
+		 * synchronize with).
+		 */
+
+		wake_from_pci = 1;
+
+		pm_suspend(pci_pm_state == 3 ? PM_SUSPEND_MEM :
+		                               PM_SUSPEND_STANDBY);
+
+		wake_from_pci = 0;
+	}
+
+	return 0;
+}
+
+static void mpc83xx_set_agent(void)
+{
+	out_be32(&pmc_regs->config1, PMCCR1_USE_STATE);
+	out_be32(&pmc_regs->mask, PMCER_PMCI);
+
+	kthread_run(agent_thread_fn, NULL, "PCI power mgt");
+}
+
+static int mpc83xx_is_pci_agent(void)
+{
+	struct mpc83xx_rcw __iomem *rcw_regs;
+	int ret;
+
+	rcw_regs = ioremap(get_immrbase() + IMMR_RCW_OFFSET,
+	                   sizeof(struct mpc83xx_rcw));
+
+	if (!rcw_regs)
+		return -ENOMEM;
+
+	ret = !(in_be32(&rcw_regs->rcwhr) & RCW_PCI_HOST);
+
+	iounmap(rcw_regs);
+	return ret;
+}
+
+static const struct platform_suspend_ops mpc83xx_suspend_ops = {
+	.valid = mpc83xx_suspend_valid,
+	.begin = mpc83xx_suspend_begin,
+	.enter = mpc83xx_suspend_enter,
+	.end = mpc83xx_suspend_end,
+};
+
+static struct pmc_type pmc_types[] = {
+	{
+		.has_deep_sleep = 1,
+	},
+	{
+		.has_deep_sleep = 0,
+	}
+};
+
+static const struct of_device_id pmc_match[] = {
+	{
+		.compatible = "fsl,mpc8313-pmc",
+		.data = &pmc_types[0],
+	},
+	{
+		.compatible = "fsl,mpc8349-pmc",
+		.data = &pmc_types[1],
+	},
+	{}
+};
+
+static int pmc_probe(struct platform_device *ofdev)
+{
+	struct device_node *np = ofdev->dev.of_node;
+	struct resource res;
+	const struct pmc_type *type;
+	int ret = 0;
+
+	type = of_device_get_match_data(&ofdev->dev);
+	if (!type)
+		return -EINVAL;
+
+	if (!of_device_is_available(np))
+		return -ENODEV;
+
+	has_deep_sleep = type->has_deep_sleep;
+	immrbase = get_immrbase();
+
+	is_pci_agent = mpc83xx_is_pci_agent();
+	if (is_pci_agent < 0)
+		return is_pci_agent;
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret)
+		return -ENODEV;
+
+	pmc_irq = irq_of_parse_and_map(np, 0);
+	if (pmc_irq) {
+		ret = request_irq(pmc_irq, pmc_irq_handler, IRQF_SHARED,
+		                  "pmc", ofdev);
+
+		if (ret)
+			return -EBUSY;
+	}
+
+	pmc_regs = ioremap(res.start, sizeof(*pmc_regs));
+
+	if (!pmc_regs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = of_address_to_resource(np, 1, &res);
+	if (ret) {
+		ret = -ENODEV;
+		goto out_pmc;
+	}
+
+	clock_regs = ioremap(res.start, sizeof(*clock_regs));
+
+	if (!clock_regs) {
+		ret = -ENOMEM;
+		goto out_pmc;
+	}
+
+	if (has_deep_sleep) {
+		syscr_regs = ioremap(immrbase + IMMR_SYSCR_OFFSET,
+				     sizeof(*syscr_regs));
+		if (!syscr_regs) {
+			ret = -ENOMEM;
+			goto out_syscr;
+		}
+	}
+
+	if (is_pci_agent)
+		mpc83xx_set_agent();
+
+	suspend_set_ops(&mpc83xx_suspend_ops);
+	return 0;
+
+out_syscr:
+	iounmap(clock_regs);
+out_pmc:
+	iounmap(pmc_regs);
+out:
+	if (pmc_irq)
+		free_irq(pmc_irq, ofdev);
+
+	return ret;
+}
+
+static struct platform_driver pmc_driver = {
+	.driver = {
+		.name = "mpc83xx-pmc",
+		.of_match_table = pmc_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = pmc_probe,
+};
+
+builtin_platform_driver(pmc_driver);