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, 303 insertions, 0 deletions

diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
new file mode 100644
index 000000000..78a8a7545
--- /dev/null
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Xilinx Zynq MPSoC Power Management
+ *
+ *  Copyright (C) 2014-2019 Xilinx, Inc.
+ *
+ *  Davorin Mista <davorin.mista@aggios.com>
+ *  Jolly Shah <jollys@xilinx.com>
+ *  Rajan Vaja <rajan.vaja@xilinx.com>
+ */
+
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/suspend.h>
+
+#include <linux/firmware/xlnx-zynqmp.h>
+#include <linux/firmware/xlnx-event-manager.h>
+#include <linux/mailbox/zynqmp-ipi-message.h>
+
+/**
+ * struct zynqmp_pm_work_struct - Wrapper for struct work_struct
+ * @callback_work:	Work structure
+ * @args:		Callback arguments
+ */
+struct zynqmp_pm_work_struct {
+	struct work_struct callback_work;
+	u32 args[CB_ARG_CNT];
+};
+
+static struct zynqmp_pm_work_struct *zynqmp_pm_init_suspend_work;
+static struct mbox_chan *rx_chan;
+static bool event_registered;
+
+enum pm_suspend_mode {
+	PM_SUSPEND_MODE_FIRST = 0,
+	PM_SUSPEND_MODE_STD = PM_SUSPEND_MODE_FIRST,
+	PM_SUSPEND_MODE_POWER_OFF,
+};
+
+#define PM_SUSPEND_MODE_FIRST	PM_SUSPEND_MODE_STD
+
+static const char *const suspend_modes[] = {
+	[PM_SUSPEND_MODE_STD] = "standard",
+	[PM_SUSPEND_MODE_POWER_OFF] = "power-off",
+};
+
+static enum pm_suspend_mode suspend_mode = PM_SUSPEND_MODE_STD;
+
+static void zynqmp_pm_get_callback_data(u32 *buf)
+{
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+}
+
+static void suspend_event_callback(const u32 *payload, void *data)
+{
+	/* First element is callback API ID, others are callback arguments */
+	if (work_pending(&zynqmp_pm_init_suspend_work->callback_work))
+		return;
+
+	/* Copy callback arguments into work's structure */
+	memcpy(zynqmp_pm_init_suspend_work->args, &payload[1],
+	       sizeof(zynqmp_pm_init_suspend_work->args));
+
+	queue_work(system_unbound_wq, &zynqmp_pm_init_suspend_work->callback_work);
+}
+
+static irqreturn_t zynqmp_pm_isr(int irq, void *data)
+{
+	u32 payload[CB_PAYLOAD_SIZE];
+
+	zynqmp_pm_get_callback_data(payload);
+
+	/* First element is callback API ID, others are callback arguments */
+	if (payload[0] == PM_INIT_SUSPEND_CB) {
+		switch (payload[1]) {
+		case SUSPEND_SYSTEM_SHUTDOWN:
+			orderly_poweroff(true);
+			break;
+		case SUSPEND_POWER_REQUEST:
+			pm_suspend(PM_SUSPEND_MEM);
+			break;
+		default:
+			pr_err("%s Unsupported InitSuspendCb reason "
+				"code %d\n", __func__, payload[1]);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void ipi_receive_callback(struct mbox_client *cl, void *data)
+{
+	struct zynqmp_ipi_message *msg = (struct zynqmp_ipi_message *)data;
+	u32 payload[CB_PAYLOAD_SIZE];
+	int ret;
+
+	memcpy(payload, msg->data, sizeof(msg->len));
+	/* First element is callback API ID, others are callback arguments */
+	if (payload[0] == PM_INIT_SUSPEND_CB) {
+		if (work_pending(&zynqmp_pm_init_suspend_work->callback_work))
+			return;
+
+		/* Copy callback arguments into work's structure */
+		memcpy(zynqmp_pm_init_suspend_work->args, &payload[1],
+		       sizeof(zynqmp_pm_init_suspend_work->args));
+
+		queue_work(system_unbound_wq,
+			   &zynqmp_pm_init_suspend_work->callback_work);
+
+		/* Send NULL message to mbox controller to ack the message */
+		ret = mbox_send_message(rx_chan, NULL);
+		if (ret)
+			pr_err("IPI ack failed. Error %d\n", ret);
+	}
+}
+
+/**
+ * zynqmp_pm_init_suspend_work_fn - Initialize suspend
+ * @work:	Pointer to work_struct
+ *
+ * Bottom-half of PM callback IRQ handler.
+ */
+static void zynqmp_pm_init_suspend_work_fn(struct work_struct *work)
+{
+	struct zynqmp_pm_work_struct *pm_work =
+		container_of(work, struct zynqmp_pm_work_struct, callback_work);
+
+	if (pm_work->args[0] == SUSPEND_SYSTEM_SHUTDOWN) {
+		orderly_poweroff(true);
+	} else if (pm_work->args[0] == SUSPEND_POWER_REQUEST) {
+		pm_suspend(PM_SUSPEND_MEM);
+	} else {
+		pr_err("%s Unsupported InitSuspendCb reason code %d.\n",
+		       __func__, pm_work->args[0]);
+	}
+}
+
+static ssize_t suspend_mode_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	char *s = buf;
+	int md;
+
+	for (md = PM_SUSPEND_MODE_FIRST; md < ARRAY_SIZE(suspend_modes); md++)
+		if (suspend_modes[md]) {
+			if (md == suspend_mode)
+				s += sprintf(s, "[%s] ", suspend_modes[md]);
+			else
+				s += sprintf(s, "%s ", suspend_modes[md]);
+		}
+
+	/* Convert last space to newline */
+	if (s != buf)
+		*(s - 1) = '\n';
+	return (s - buf);
+}
+
+static ssize_t suspend_mode_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	int md, ret = -EINVAL;
+
+	for (md = PM_SUSPEND_MODE_FIRST; md < ARRAY_SIZE(suspend_modes); md++)
+		if (suspend_modes[md] &&
+		    sysfs_streq(suspend_modes[md], buf)) {
+			ret = 0;
+			break;
+		}
+
+	if (!ret && md != suspend_mode) {
+		ret = zynqmp_pm_set_suspend_mode(md);
+		if (likely(!ret))
+			suspend_mode = md;
+	}
+
+	return ret ? ret : count;
+}
+
+static DEVICE_ATTR_RW(suspend_mode);
+
+static int zynqmp_pm_probe(struct platform_device *pdev)
+{
+	int ret, irq;
+	u32 pm_api_version;
+	struct mbox_client *client;
+
+	zynqmp_pm_get_api_version(&pm_api_version);
+
+	/* Check PM API version number */
+	if (pm_api_version < ZYNQMP_PM_VERSION)
+		return -ENODEV;
+
+	/*
+	 * First try to use Xilinx Event Manager by registering suspend_event_callback
+	 * for suspend/shutdown event.
+	 * If xlnx_register_event() returns -EACCES (Xilinx Event Manager
+	 * is not available to use) or -ENODEV(Xilinx Event Manager not compiled),
+	 * then use ipi-mailbox or interrupt method.
+	 */
+	ret = xlnx_register_event(PM_INIT_SUSPEND_CB, 0, 0, false,
+				  suspend_event_callback, NULL);
+	if (!ret) {
+		zynqmp_pm_init_suspend_work = devm_kzalloc(&pdev->dev,
+							   sizeof(struct zynqmp_pm_work_struct),
+							   GFP_KERNEL);
+		if (!zynqmp_pm_init_suspend_work) {
+			xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0,
+					      suspend_event_callback, NULL);
+			return -ENOMEM;
+		}
+		event_registered = true;
+
+		INIT_WORK(&zynqmp_pm_init_suspend_work->callback_work,
+			  zynqmp_pm_init_suspend_work_fn);
+	} else if (ret != -EACCES && ret != -ENODEV) {
+		dev_err(&pdev->dev, "Failed to Register with Xilinx Event manager %d\n", ret);
+		return ret;
+	} else if (of_find_property(pdev->dev.of_node, "mboxes", NULL)) {
+		zynqmp_pm_init_suspend_work =
+			devm_kzalloc(&pdev->dev,
+				     sizeof(struct zynqmp_pm_work_struct),
+				     GFP_KERNEL);
+		if (!zynqmp_pm_init_suspend_work)
+			return -ENOMEM;
+
+		INIT_WORK(&zynqmp_pm_init_suspend_work->callback_work,
+			  zynqmp_pm_init_suspend_work_fn);
+		client = devm_kzalloc(&pdev->dev, sizeof(*client), GFP_KERNEL);
+		if (!client)
+			return -ENOMEM;
+
+		client->dev = &pdev->dev;
+		client->rx_callback = ipi_receive_callback;
+
+		rx_chan = mbox_request_channel_byname(client, "rx");
+		if (IS_ERR(rx_chan)) {
+			dev_err(&pdev->dev, "Failed to request rx channel\n");
+			return PTR_ERR(rx_chan);
+		}
+	} else if (of_find_property(pdev->dev.of_node, "interrupts", NULL)) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq <= 0)
+			return -ENXIO;
+
+		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+						zynqmp_pm_isr,
+						IRQF_NO_SUSPEND | IRQF_ONESHOT,
+						dev_name(&pdev->dev),
+						&pdev->dev);
+		if (ret) {
+			dev_err(&pdev->dev, "devm_request_threaded_irq '%d' "
+					    "failed with %d\n", irq, ret);
+			return ret;
+		}
+	} else {
+		dev_err(&pdev->dev, "Required property not found in DT node\n");
+		return -ENOENT;
+	}
+
+	ret = sysfs_create_file(&pdev->dev.kobj, &dev_attr_suspend_mode.attr);
+	if (ret) {
+		if (event_registered) {
+			xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback,
+					      NULL);
+			event_registered = false;
+		}
+		dev_err(&pdev->dev, "unable to create sysfs interface\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int zynqmp_pm_remove(struct platform_device *pdev)
+{
+	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_suspend_mode.attr);
+	if (event_registered)
+		xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback, NULL);
+
+	if (!rx_chan)
+		mbox_free_channel(rx_chan);
+
+	return 0;
+}
+
+static const struct of_device_id pm_of_match[] = {
+	{ .compatible = "xlnx,zynqmp-power", },
+	{ /* end of table */ },
+};
+MODULE_DEVICE_TABLE(of, pm_of_match);
+
+static struct platform_driver zynqmp_pm_platform_driver = {
+	.probe = zynqmp_pm_probe,
+	.remove = zynqmp_pm_remove,
+	.driver = {
+		.name = "zynqmp_power",
+		.of_match_table = pm_of_match,
+	},
+};
+module_platform_driver(zynqmp_pm_platform_driver);