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, 324 insertions, 0 deletions

diff --git a/drivers/soc/mediatek/mtk-devapc.c b/drivers/soc/mediatek/mtk-devapc.c
new file mode 100644
index 000000000..fc13334db
--- /dev/null
+++ b/drivers/soc/mediatek/mtk-devapc.c
@@ -0,0 +1,324 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 MediaTek Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#define VIO_MOD_TO_REG_IND(m)	((m) / 32)
+#define VIO_MOD_TO_REG_OFF(m)	((m) % 32)
+
+struct mtk_devapc_vio_dbgs {
+	union {
+		u32 vio_dbg0;
+		struct {
+			u32 mstid:16;
+			u32 dmnid:6;
+			u32 vio_w:1;
+			u32 vio_r:1;
+			u32 addr_h:4;
+			u32 resv:4;
+		} dbg0_bits;
+	};
+
+	u32 vio_dbg1;
+};
+
+struct mtk_devapc_regs_ofs {
+	/* reg offset */
+	u32 vio_mask_offset;
+	u32 vio_sta_offset;
+	u32 vio_dbg0_offset;
+	u32 vio_dbg1_offset;
+	u32 apc_con_offset;
+	u32 vio_shift_sta_offset;
+	u32 vio_shift_sel_offset;
+	u32 vio_shift_con_offset;
+};
+
+struct mtk_devapc_data {
+	/* numbers of violation index */
+	u32 vio_idx_num;
+	const struct mtk_devapc_regs_ofs *regs_ofs;
+};
+
+struct mtk_devapc_context {
+	struct device *dev;
+	void __iomem *infra_base;
+	struct clk *infra_clk;
+	const struct mtk_devapc_data *data;
+};
+
+static void clear_vio_status(struct mtk_devapc_context *ctx)
+{
+	void __iomem *reg;
+	int i;
+
+	reg = ctx->infra_base + ctx->data->regs_ofs->vio_sta_offset;
+
+	for (i = 0; i < VIO_MOD_TO_REG_IND(ctx->data->vio_idx_num) - 1; i++)
+		writel(GENMASK(31, 0), reg + 4 * i);
+
+	writel(GENMASK(VIO_MOD_TO_REG_OFF(ctx->data->vio_idx_num) - 1, 0),
+	       reg + 4 * i);
+}
+
+static void mask_module_irq(struct mtk_devapc_context *ctx, bool mask)
+{
+	void __iomem *reg;
+	u32 val;
+	int i;
+
+	reg = ctx->infra_base + ctx->data->regs_ofs->vio_mask_offset;
+
+	if (mask)
+		val = GENMASK(31, 0);
+	else
+		val = 0;
+
+	for (i = 0; i < VIO_MOD_TO_REG_IND(ctx->data->vio_idx_num) - 1; i++)
+		writel(val, reg + 4 * i);
+
+	val = readl(reg + 4 * i);
+	if (mask)
+		val |= GENMASK(VIO_MOD_TO_REG_OFF(ctx->data->vio_idx_num) - 1,
+			       0);
+	else
+		val &= ~GENMASK(VIO_MOD_TO_REG_OFF(ctx->data->vio_idx_num) - 1,
+				0);
+
+	writel(val, reg + 4 * i);
+}
+
+#define PHY_DEVAPC_TIMEOUT	0x10000
+
+/*
+ * devapc_sync_vio_dbg - do "shift" mechansim" to get full violation information.
+ *                       shift mechanism is depends on devapc hardware design.
+ *                       Mediatek devapc set multiple slaves as a group.
+ *                       When violation is triggered, violation info is kept
+ *                       inside devapc hardware.
+ *                       Driver should do shift mechansim to sync full violation
+ *                       info to VIO_DBGs registers.
+ *
+ */
+static int devapc_sync_vio_dbg(struct mtk_devapc_context *ctx)
+{
+	void __iomem *pd_vio_shift_sta_reg;
+	void __iomem *pd_vio_shift_sel_reg;
+	void __iomem *pd_vio_shift_con_reg;
+	int min_shift_group;
+	int ret;
+	u32 val;
+
+	pd_vio_shift_sta_reg = ctx->infra_base +
+			       ctx->data->regs_ofs->vio_shift_sta_offset;
+	pd_vio_shift_sel_reg = ctx->infra_base +
+			       ctx->data->regs_ofs->vio_shift_sel_offset;
+	pd_vio_shift_con_reg = ctx->infra_base +
+			       ctx->data->regs_ofs->vio_shift_con_offset;
+
+	/* Find the minimum shift group which has violation */
+	val = readl(pd_vio_shift_sta_reg);
+	if (!val)
+		return false;
+
+	min_shift_group = __ffs(val);
+
+	/* Assign the group to sync */
+	writel(0x1 << min_shift_group, pd_vio_shift_sel_reg);
+
+	/* Start syncing */
+	writel(0x1, pd_vio_shift_con_reg);
+
+	ret = readl_poll_timeout(pd_vio_shift_con_reg, val, val == 0x3, 0,
+				 PHY_DEVAPC_TIMEOUT);
+	if (ret) {
+		dev_err(ctx->dev, "%s: Shift violation info failed\n", __func__);
+		return false;
+	}
+
+	/* Stop syncing */
+	writel(0x0, pd_vio_shift_con_reg);
+
+	/* Write clear */
+	writel(0x1 << min_shift_group, pd_vio_shift_sta_reg);
+
+	return true;
+}
+
+/*
+ * devapc_extract_vio_dbg - extract full violation information after doing
+ *                          shift mechanism.
+ */
+static void devapc_extract_vio_dbg(struct mtk_devapc_context *ctx)
+{
+	struct mtk_devapc_vio_dbgs vio_dbgs;
+	void __iomem *vio_dbg0_reg;
+	void __iomem *vio_dbg1_reg;
+
+	vio_dbg0_reg = ctx->infra_base + ctx->data->regs_ofs->vio_dbg0_offset;
+	vio_dbg1_reg = ctx->infra_base + ctx->data->regs_ofs->vio_dbg1_offset;
+
+	vio_dbgs.vio_dbg0 = readl(vio_dbg0_reg);
+	vio_dbgs.vio_dbg1 = readl(vio_dbg1_reg);
+
+	/* Print violation information */
+	if (vio_dbgs.dbg0_bits.vio_w)
+		dev_info(ctx->dev, "Write Violation\n");
+	else if (vio_dbgs.dbg0_bits.vio_r)
+		dev_info(ctx->dev, "Read Violation\n");
+
+	dev_info(ctx->dev, "Bus ID:0x%x, Dom ID:0x%x, Vio Addr:0x%x\n",
+		 vio_dbgs.dbg0_bits.mstid, vio_dbgs.dbg0_bits.dmnid,
+		 vio_dbgs.vio_dbg1);
+}
+
+/*
+ * devapc_violation_irq - the devapc Interrupt Service Routine (ISR) will dump
+ *                        violation information including which master violates
+ *                        access slave.
+ */
+static irqreturn_t devapc_violation_irq(int irq_number, void *data)
+{
+	struct mtk_devapc_context *ctx = data;
+
+	while (devapc_sync_vio_dbg(ctx))
+		devapc_extract_vio_dbg(ctx);
+
+	clear_vio_status(ctx);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * start_devapc - unmask slave's irq to start receiving devapc violation.
+ */
+static void start_devapc(struct mtk_devapc_context *ctx)
+{
+	writel(BIT(31), ctx->infra_base + ctx->data->regs_ofs->apc_con_offset);
+
+	mask_module_irq(ctx, false);
+}
+
+/*
+ * stop_devapc - mask slave's irq to stop service.
+ */
+static void stop_devapc(struct mtk_devapc_context *ctx)
+{
+	mask_module_irq(ctx, true);
+
+	writel(BIT(2), ctx->infra_base + ctx->data->regs_ofs->apc_con_offset);
+}
+
+static const struct mtk_devapc_regs_ofs devapc_regs_ofs_mt6779 = {
+	.vio_mask_offset = 0x0,
+	.vio_sta_offset = 0x400,
+	.vio_dbg0_offset = 0x900,
+	.vio_dbg1_offset = 0x904,
+	.apc_con_offset = 0xF00,
+	.vio_shift_sta_offset = 0xF10,
+	.vio_shift_sel_offset = 0xF14,
+	.vio_shift_con_offset = 0xF20,
+};
+
+static const struct mtk_devapc_data devapc_mt6779 = {
+	.vio_idx_num = 511,
+	.regs_ofs = &devapc_regs_ofs_mt6779,
+};
+
+static const struct mtk_devapc_data devapc_mt8186 = {
+	.vio_idx_num = 519,
+	.regs_ofs = &devapc_regs_ofs_mt6779,
+};
+
+static const struct of_device_id mtk_devapc_dt_match[] = {
+	{
+		.compatible = "mediatek,mt6779-devapc",
+		.data = &devapc_mt6779,
+	}, {
+		.compatible = "mediatek,mt8186-devapc",
+		.data = &devapc_mt8186,
+	}, {
+	},
+};
+MODULE_DEVICE_TABLE(of, mtk_devapc_dt_match);
+
+static int mtk_devapc_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct mtk_devapc_context *ctx;
+	u32 devapc_irq;
+	int ret;
+
+	if (IS_ERR(node))
+		return -ENODEV;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->data = of_device_get_match_data(&pdev->dev);
+	ctx->dev = &pdev->dev;
+
+	ctx->infra_base = of_iomap(node, 0);
+	if (!ctx->infra_base)
+		return -EINVAL;
+
+	devapc_irq = irq_of_parse_and_map(node, 0);
+	if (!devapc_irq)
+		return -EINVAL;
+
+	ctx->infra_clk = devm_clk_get(&pdev->dev, "devapc-infra-clock");
+	if (IS_ERR(ctx->infra_clk))
+		return -EINVAL;
+
+	if (clk_prepare_enable(ctx->infra_clk))
+		return -EINVAL;
+
+	ret = devm_request_irq(&pdev->dev, devapc_irq, devapc_violation_irq,
+			       IRQF_TRIGGER_NONE, "devapc", ctx);
+	if (ret) {
+		clk_disable_unprepare(ctx->infra_clk);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, ctx);
+
+	start_devapc(ctx);
+
+	return 0;
+}
+
+static int mtk_devapc_remove(struct platform_device *pdev)
+{
+	struct mtk_devapc_context *ctx = platform_get_drvdata(pdev);
+
+	stop_devapc(ctx);
+
+	clk_disable_unprepare(ctx->infra_clk);
+
+	return 0;
+}
+
+static struct platform_driver mtk_devapc_driver = {
+	.probe = mtk_devapc_probe,
+	.remove = mtk_devapc_remove,
+	.driver = {
+		.name = "mtk-devapc",
+		.of_match_table = mtk_devapc_dt_match,
+	},
+};
+
+module_platform_driver(mtk_devapc_driver);
+
+MODULE_DESCRIPTION("Mediatek Device APC Driver");
+MODULE_AUTHOR("Neal Liu <neal.liu@mediatek.com>");
+MODULE_LICENSE("GPL");