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, 313 insertions, 0 deletions

diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c
new file mode 100644
index 000000000..5fa171087
--- /dev/null
+++ b/drivers/interconnect/qcom/osm-l3.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020-2021, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/interconnect-provider.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+
+#include <dt-bindings/interconnect/qcom,osm-l3.h>
+
+#include "sc7180.h"
+#include "sc7280.h"
+#include "sc8180x.h"
+#include "sdm845.h"
+#include "sm8150.h"
+#include "sm8250.h"
+
+#define LUT_MAX_ENTRIES			40U
+#define LUT_SRC				GENMASK(31, 30)
+#define LUT_L_VAL			GENMASK(7, 0)
+#define CLK_HW_DIV			2
+
+/* OSM Register offsets */
+#define REG_ENABLE			0x0
+#define OSM_LUT_ROW_SIZE		32
+#define OSM_REG_FREQ_LUT		0x110
+#define OSM_REG_PERF_STATE		0x920
+
+/* EPSS Register offsets */
+#define EPSS_LUT_ROW_SIZE		4
+#define EPSS_REG_L3_VOTE		0x90
+#define EPSS_REG_FREQ_LUT		0x100
+#define EPSS_REG_PERF_STATE		0x320
+
+#define OSM_L3_MAX_LINKS		1
+
+#define to_osm_l3_provider(_provider) \
+	container_of(_provider, struct qcom_osm_l3_icc_provider, provider)
+
+struct qcom_osm_l3_icc_provider {
+	void __iomem *base;
+	unsigned int max_state;
+	unsigned int reg_perf_state;
+	unsigned long lut_tables[LUT_MAX_ENTRIES];
+	struct icc_provider provider;
+};
+
+/**
+ * struct qcom_osm_l3_node - Qualcomm specific interconnect nodes
+ * @name: the node name used in debugfs
+ * @links: an array of nodes where we can go next while traversing
+ * @id: a unique node identifier
+ * @num_links: the total number of @links
+ * @buswidth: width of the interconnect between a node and the bus
+ */
+struct qcom_osm_l3_node {
+	const char *name;
+	u16 links[OSM_L3_MAX_LINKS];
+	u16 id;
+	u16 num_links;
+	u16 buswidth;
+};
+
+struct qcom_osm_l3_desc {
+	const struct qcom_osm_l3_node * const *nodes;
+	size_t num_nodes;
+	unsigned int lut_row_size;
+	unsigned int reg_freq_lut;
+	unsigned int reg_perf_state;
+};
+
+enum {
+	OSM_L3_MASTER_NODE = 10000,
+	OSM_L3_SLAVE_NODE,
+};
+
+#define DEFINE_QNODE(_name, _id, _buswidth, ...)			\
+	static const struct qcom_osm_l3_node _name = {			\
+		.name = #_name,						\
+		.id = _id,						\
+		.buswidth = _buswidth,					\
+		.num_links = ARRAY_SIZE(((int[]){ __VA_ARGS__ })),	\
+		.links = { __VA_ARGS__ },				\
+	}
+
+DEFINE_QNODE(osm_l3_master, OSM_L3_MASTER_NODE, 16, OSM_L3_SLAVE_NODE);
+DEFINE_QNODE(osm_l3_slave, OSM_L3_SLAVE_NODE, 16);
+
+static const struct qcom_osm_l3_node * const osm_l3_nodes[] = {
+	[MASTER_OSM_L3_APPS] = &osm_l3_master,
+	[SLAVE_OSM_L3] = &osm_l3_slave,
+};
+
+DEFINE_QNODE(epss_l3_master, OSM_L3_MASTER_NODE, 32, OSM_L3_SLAVE_NODE);
+DEFINE_QNODE(epss_l3_slave, OSM_L3_SLAVE_NODE, 32);
+
+static const struct qcom_osm_l3_node * const epss_l3_nodes[] = {
+	[MASTER_EPSS_L3_APPS] = &epss_l3_master,
+	[SLAVE_EPSS_L3_SHARED] = &epss_l3_slave,
+};
+
+static const struct qcom_osm_l3_desc osm_l3 = {
+	.nodes = osm_l3_nodes,
+	.num_nodes = ARRAY_SIZE(osm_l3_nodes),
+	.lut_row_size = OSM_LUT_ROW_SIZE,
+	.reg_freq_lut = OSM_REG_FREQ_LUT,
+	.reg_perf_state = OSM_REG_PERF_STATE,
+};
+
+static const struct qcom_osm_l3_desc epss_l3_perf_state = {
+	.nodes = epss_l3_nodes,
+	.num_nodes = ARRAY_SIZE(epss_l3_nodes),
+	.lut_row_size = EPSS_LUT_ROW_SIZE,
+	.reg_freq_lut = EPSS_REG_FREQ_LUT,
+	.reg_perf_state = EPSS_REG_PERF_STATE,
+};
+
+static const struct qcom_osm_l3_desc epss_l3_l3_vote = {
+	.nodes = epss_l3_nodes,
+	.num_nodes = ARRAY_SIZE(epss_l3_nodes),
+	.lut_row_size = EPSS_LUT_ROW_SIZE,
+	.reg_freq_lut = EPSS_REG_FREQ_LUT,
+	.reg_perf_state = EPSS_REG_L3_VOTE,
+};
+
+static int qcom_osm_l3_set(struct icc_node *src, struct icc_node *dst)
+{
+	struct qcom_osm_l3_icc_provider *qp;
+	struct icc_provider *provider;
+	const struct qcom_osm_l3_node *qn;
+	unsigned int index;
+	u64 rate;
+
+	qn = src->data;
+	provider = src->provider;
+	qp = to_osm_l3_provider(provider);
+
+	rate = icc_units_to_bps(dst->peak_bw);
+	do_div(rate, qn->buswidth);
+
+	for (index = 0; index < qp->max_state - 1; index++) {
+		if (qp->lut_tables[index] >= rate)
+			break;
+	}
+
+	writel_relaxed(index, qp->base + qp->reg_perf_state);
+
+	return 0;
+}
+
+static int qcom_osm_l3_remove(struct platform_device *pdev)
+{
+	struct qcom_osm_l3_icc_provider *qp = platform_get_drvdata(pdev);
+
+	icc_nodes_remove(&qp->provider);
+	icc_provider_del(&qp->provider);
+
+	return 0;
+}
+
+static int qcom_osm_l3_probe(struct platform_device *pdev)
+{
+	u32 info, src, lval, i, prev_freq = 0, freq;
+	static unsigned long hw_rate, xo_rate;
+	struct qcom_osm_l3_icc_provider *qp;
+	const struct qcom_osm_l3_desc *desc;
+	struct icc_onecell_data *data;
+	struct icc_provider *provider;
+	const struct qcom_osm_l3_node * const *qnodes;
+	struct icc_node *node;
+	size_t num_nodes;
+	struct clk *clk;
+	int ret;
+
+	clk = clk_get(&pdev->dev, "xo");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	xo_rate = clk_get_rate(clk);
+	clk_put(clk);
+
+	clk = clk_get(&pdev->dev, "alternate");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	hw_rate = clk_get_rate(clk) / CLK_HW_DIV;
+	clk_put(clk);
+
+	qp = devm_kzalloc(&pdev->dev, sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return -ENOMEM;
+
+	qp->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(qp->base))
+		return PTR_ERR(qp->base);
+
+	/* HW should be in enabled state to proceed */
+	if (!(readl_relaxed(qp->base + REG_ENABLE) & 0x1)) {
+		dev_err(&pdev->dev, "error hardware not enabled\n");
+		return -ENODEV;
+	}
+
+	desc = device_get_match_data(&pdev->dev);
+	if (!desc)
+		return -EINVAL;
+
+	qp->reg_perf_state = desc->reg_perf_state;
+
+	for (i = 0; i < LUT_MAX_ENTRIES; i++) {
+		info = readl_relaxed(qp->base + desc->reg_freq_lut +
+				     i * desc->lut_row_size);
+		src = FIELD_GET(LUT_SRC, info);
+		lval = FIELD_GET(LUT_L_VAL, info);
+		if (src)
+			freq = xo_rate * lval;
+		else
+			freq = hw_rate;
+
+		/* Two of the same frequencies signify end of table */
+		if (i > 0 && prev_freq == freq)
+			break;
+
+		dev_dbg(&pdev->dev, "index=%d freq=%d\n", i, freq);
+
+		qp->lut_tables[i] = freq;
+		prev_freq = freq;
+	}
+	qp->max_state = i;
+
+	qnodes = desc->nodes;
+	num_nodes = desc->num_nodes;
+
+	data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	provider = &qp->provider;
+	provider->dev = &pdev->dev;
+	provider->set = qcom_osm_l3_set;
+	provider->aggregate = icc_std_aggregate;
+	provider->xlate = of_icc_xlate_onecell;
+	INIT_LIST_HEAD(&provider->nodes);
+	provider->data = data;
+
+	ret = icc_provider_add(provider);
+	if (ret) {
+		dev_err(&pdev->dev, "error adding interconnect provider\n");
+		return ret;
+	}
+
+	for (i = 0; i < num_nodes; i++) {
+		size_t j;
+
+		node = icc_node_create(qnodes[i]->id);
+		if (IS_ERR(node)) {
+			ret = PTR_ERR(node);
+			goto err;
+		}
+
+		node->name = qnodes[i]->name;
+		/* Cast away const and add it back in qcom_osm_l3_set() */
+		node->data = (void *)qnodes[i];
+		icc_node_add(node, provider);
+
+		for (j = 0; j < qnodes[i]->num_links; j++)
+			icc_link_create(node, qnodes[i]->links[j]);
+
+		data->nodes[i] = node;
+	}
+	data->num_nodes = num_nodes;
+
+	platform_set_drvdata(pdev, qp);
+
+	return 0;
+err:
+	icc_nodes_remove(provider);
+	icc_provider_del(provider);
+
+	return ret;
+}
+
+static const struct of_device_id osm_l3_of_match[] = {
+	{ .compatible = "qcom,epss-l3", .data = &epss_l3_l3_vote },
+	{ .compatible = "qcom,osm-l3", .data = &osm_l3 },
+	{ .compatible = "qcom,sc7180-osm-l3", .data = &osm_l3 },
+	{ .compatible = "qcom,sc7280-epss-l3", .data = &epss_l3_perf_state },
+	{ .compatible = "qcom,sdm845-osm-l3", .data = &osm_l3 },
+	{ .compatible = "qcom,sm8150-osm-l3", .data = &osm_l3 },
+	{ .compatible = "qcom,sc8180x-osm-l3", .data = &osm_l3 },
+	{ .compatible = "qcom,sm8250-epss-l3", .data = &epss_l3_perf_state },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, osm_l3_of_match);
+
+static struct platform_driver osm_l3_driver = {
+	.probe = qcom_osm_l3_probe,
+	.remove = qcom_osm_l3_remove,
+	.driver = {
+		.name = "osm-l3",
+		.of_match_table = osm_l3_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+module_platform_driver(osm_l3_driver);
+
+MODULE_DESCRIPTION("Qualcomm OSM L3 interconnect driver");
+MODULE_LICENSE("GPL v2");