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, 253 insertions, 0 deletions

diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c
new file mode 100644
index 000000000..1f2c5018b
--- /dev/null
+++ b/sound/soc/tegra/tegra_audio_graph_card.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// tegra_audio_graph_card.c - Audio Graph based Tegra Machine Driver
+//
+// Copyright (c) 2020-2021 NVIDIA CORPORATION.  All rights reserved.
+
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <sound/graph_card.h>
+#include <sound/pcm_params.h>
+
+#define MAX_PLLA_OUT0_DIV 128
+
+#define simple_to_tegra_priv(simple) \
+		container_of(simple, struct tegra_audio_priv, simple)
+
+enum srate_type {
+	/*
+	 * Sample rates multiple of 8000 Hz and below are supported:
+	 * ( 8000, 16000, 32000, 48000, 96000, 192000 Hz )
+	 */
+	x8_RATE,
+
+	/*
+	 * Sample rates multiple of 11025 Hz and below are supported:
+	 * ( 11025, 22050, 44100, 88200, 176400 Hz )
+	 */
+	x11_RATE,
+
+	NUM_RATE_TYPE,
+};
+
+struct tegra_audio_priv {
+	struct asoc_simple_priv simple;
+	struct clk *clk_plla_out0;
+	struct clk *clk_plla;
+};
+
+/* Tegra audio chip data */
+struct tegra_audio_cdata {
+	unsigned int plla_rates[NUM_RATE_TYPE];
+	unsigned int plla_out0_rates[NUM_RATE_TYPE];
+};
+
+/* Setup PLL clock as per the given sample rate */
+static int tegra_audio_graph_update_pll(struct snd_pcm_substream *substream,
+					struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
+	struct asoc_simple_priv *simple = snd_soc_card_get_drvdata(rtd->card);
+	struct tegra_audio_priv *priv = simple_to_tegra_priv(simple);
+	struct device *dev = rtd->card->dev;
+	const struct tegra_audio_cdata *data = of_device_get_match_data(dev);
+	unsigned int plla_rate, plla_out0_rate, bclk;
+	unsigned int srate = params_rate(params);
+	int err;
+
+	switch (srate) {
+	case 11025:
+	case 22050:
+	case 44100:
+	case 88200:
+	case 176400:
+		plla_out0_rate = data->plla_out0_rates[x11_RATE];
+		plla_rate = data->plla_rates[x11_RATE];
+		break;
+	case 8000:
+	case 16000:
+	case 32000:
+	case 48000:
+	case 96000:
+	case 192000:
+		plla_out0_rate = data->plla_out0_rates[x8_RATE];
+		plla_rate = data->plla_rates[x8_RATE];
+		break;
+	default:
+		dev_err(rtd->card->dev, "Unsupported sample rate %u\n",
+			srate);
+		return -EINVAL;
+	}
+
+	/*
+	 * Below is the clock relation:
+	 *
+	 *	PLLA
+	 *	  |
+	 *	  |--> PLLA_OUT0
+	 *		  |
+	 *		  |---> I2S modules
+	 *		  |
+	 *		  |---> DMIC modules
+	 *		  |
+	 *		  |---> DSPK modules
+	 *
+	 *
+	 * Default PLLA_OUT0 rate might be too high when I/O is running
+	 * at minimum PCM configurations. This may result in incorrect
+	 * clock rates and glitchy audio. The maximum divider is 128
+	 * and any thing higher than that won't work. Thus reduce PLLA_OUT0
+	 * to work for lower configurations.
+	 *
+	 * This problem is seen for I2S only, as DMIC and DSPK minimum
+	 * clock requirements are under allowed divider limits.
+	 */
+	bclk = srate * params_channels(params) * params_width(params);
+	if (div_u64(plla_out0_rate, bclk) > MAX_PLLA_OUT0_DIV)
+		plla_out0_rate >>= 1;
+
+	dev_dbg(rtd->card->dev,
+		"Update clock rates: PLLA(= %u Hz) and PLLA_OUT0(= %u Hz)\n",
+		plla_rate, plla_out0_rate);
+
+	/* Set PLLA rate */
+	err = clk_set_rate(priv->clk_plla, plla_rate);
+	if (err) {
+		dev_err(rtd->card->dev,
+			"Can't set plla rate for %u, err: %d\n",
+			plla_rate, err);
+		return err;
+	}
+
+	/* Set PLLA_OUT0 rate */
+	err = clk_set_rate(priv->clk_plla_out0, plla_out0_rate);
+	if (err) {
+		dev_err(rtd->card->dev,
+			"Can't set plla_out0 rate %u, err: %d\n",
+			plla_out0_rate, err);
+		return err;
+	}
+
+	return err;
+}
+
+static int tegra_audio_graph_hw_params(struct snd_pcm_substream *substream,
+				       struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
+	struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+	int err;
+
+	/*
+	 * This gets called for each DAI link (FE or BE) when DPCM is used.
+	 * We may not want to update PLLA rate for each call. So PLLA update
+	 * must be restricted to external I/O links (I2S, DMIC or DSPK) since
+	 * they actually depend on it. I/O modules update their clocks in
+	 * hw_param() of their respective component driver and PLLA rate
+	 * update here helps them to derive appropriate rates.
+	 *
+	 * TODO: When more HW accelerators get added (like sample rate
+	 * converter, volume gain controller etc., which don't really
+	 * depend on PLLA) we need a better way to filter here.
+	 */
+	if (cpu_dai->driver->ops && rtd->dai_link->no_pcm) {
+		err = tegra_audio_graph_update_pll(substream, params);
+		if (err)
+			return err;
+	}
+
+	return asoc_simple_hw_params(substream, params);
+}
+
+static const struct snd_soc_ops tegra_audio_graph_ops = {
+	.startup	= asoc_simple_startup,
+	.shutdown	= asoc_simple_shutdown,
+	.hw_params	= tegra_audio_graph_hw_params,
+};
+
+static int tegra_audio_graph_card_probe(struct snd_soc_card *card)
+{
+	struct asoc_simple_priv *simple = snd_soc_card_get_drvdata(card);
+	struct tegra_audio_priv *priv = simple_to_tegra_priv(simple);
+
+	priv->clk_plla = devm_clk_get(card->dev, "pll_a");
+	if (IS_ERR(priv->clk_plla)) {
+		dev_err(card->dev, "Can't retrieve clk pll_a\n");
+		return PTR_ERR(priv->clk_plla);
+	}
+
+	priv->clk_plla_out0 = devm_clk_get(card->dev, "plla_out0");
+	if (IS_ERR(priv->clk_plla_out0)) {
+		dev_err(card->dev, "Can't retrieve clk plla_out0\n");
+		return PTR_ERR(priv->clk_plla_out0);
+	}
+
+	return asoc_graph_card_probe(card);
+}
+
+static int tegra_audio_graph_probe(struct platform_device *pdev)
+{
+	struct tegra_audio_priv *priv;
+	struct device *dev = &pdev->dev;
+	struct snd_soc_card *card;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	card = simple_priv_to_card(&priv->simple);
+	card->driver_name = "tegra-ape";
+
+	card->probe = tegra_audio_graph_card_probe;
+
+	/* audio_graph_parse_of() depends on below */
+	card->component_chaining = 1;
+	priv->simple.ops = &tegra_audio_graph_ops;
+	priv->simple.force_dpcm = 1;
+
+	return audio_graph_parse_of(&priv->simple, dev);
+}
+
+static const struct tegra_audio_cdata tegra210_data = {
+	/* PLLA */
+	.plla_rates[x8_RATE] = 368640000,
+	.plla_rates[x11_RATE] = 338688000,
+	/* PLLA_OUT0 */
+	.plla_out0_rates[x8_RATE] = 49152000,
+	.plla_out0_rates[x11_RATE] = 45158400,
+};
+
+static const struct tegra_audio_cdata tegra186_data = {
+	/* PLLA */
+	.plla_rates[x8_RATE] = 245760000,
+	.plla_rates[x11_RATE] = 270950400,
+	/* PLLA_OUT0 */
+	.plla_out0_rates[x8_RATE] = 49152000,
+	.plla_out0_rates[x11_RATE] = 45158400,
+};
+
+static const struct of_device_id graph_of_tegra_match[] = {
+	{ .compatible = "nvidia,tegra210-audio-graph-card",
+	  .data = &tegra210_data },
+	{ .compatible = "nvidia,tegra186-audio-graph-card",
+	  .data = &tegra186_data },
+	{},
+};
+MODULE_DEVICE_TABLE(of, graph_of_tegra_match);
+
+static struct platform_driver tegra_audio_graph_card = {
+	.driver = {
+		.name = "tegra-audio-graph-card",
+		.pm = &snd_soc_pm_ops,
+		.of_match_table = graph_of_tegra_match,
+	},
+	.probe = tegra_audio_graph_probe,
+	.remove = asoc_simple_remove,
+};
+module_platform_driver(tegra_audio_graph_card);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ASoC Tegra Audio Graph Sound Card");
+MODULE_AUTHOR("Sameer Pujar <spujar@nvidia.com>");