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, 375 insertions, 0 deletions

diff --git a/sound/mips/snd-n64.c b/sound/mips/snd-n64.c
new file mode 100644
index 000000000..bff6d85b8
--- /dev/null
+++ b/sound/mips/snd-n64.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *   Sound driver for Nintendo 64.
+ *
+ *   Copyright 2021 Lauri Kasanen
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#include <sound/control.h>
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+
+MODULE_AUTHOR("Lauri Kasanen <cand@gmx.com>");
+MODULE_DESCRIPTION("N64 Audio");
+MODULE_LICENSE("GPL");
+
+#define AI_NTSC_DACRATE 48681812
+#define AI_STATUS_BUSY  (1 << 30)
+#define AI_STATUS_FULL  (1 << 31)
+
+#define AI_ADDR_REG 0
+#define AI_LEN_REG 1
+#define AI_CONTROL_REG 2
+#define AI_STATUS_REG 3
+#define AI_RATE_REG 4
+#define AI_BITCLOCK_REG 5
+
+#define MI_INTR_REG 2
+#define MI_MASK_REG 3
+
+#define MI_INTR_AI 0x04
+
+#define MI_MASK_CLR_AI 0x0010
+#define MI_MASK_SET_AI 0x0020
+
+
+struct n64audio {
+	u32 __iomem *ai_reg_base;
+	u32 __iomem *mi_reg_base;
+
+	void *ring_base;
+	dma_addr_t ring_base_dma;
+
+	struct snd_card *card;
+
+	struct {
+		struct snd_pcm_substream *substream;
+		int pos, nextpos;
+		u32 writesize;
+		u32 bufsize;
+		spinlock_t lock;
+	} chan;
+};
+
+static void n64audio_write_reg(struct n64audio *priv, const u8 reg, const u32 value)
+{
+	writel(value, priv->ai_reg_base + reg);
+}
+
+static void n64mi_write_reg(struct n64audio *priv, const u8 reg, const u32 value)
+{
+	writel(value, priv->mi_reg_base + reg);
+}
+
+static u32 n64mi_read_reg(struct n64audio *priv, const u8 reg)
+{
+	return readl(priv->mi_reg_base + reg);
+}
+
+static void n64audio_push(struct n64audio *priv)
+{
+	struct snd_pcm_runtime *runtime = priv->chan.substream->runtime;
+	unsigned long flags;
+	u32 count;
+
+	spin_lock_irqsave(&priv->chan.lock, flags);
+
+	count = priv->chan.writesize;
+
+	memcpy(priv->ring_base + priv->chan.nextpos,
+	       runtime->dma_area + priv->chan.nextpos, count);
+
+	/*
+	 * The hw registers are double-buffered, and the IRQ fires essentially
+	 * one period behind. The core only allows one period's distance, so we
+	 * keep a private DMA buffer to afford two.
+	 */
+	n64audio_write_reg(priv, AI_ADDR_REG, priv->ring_base_dma + priv->chan.nextpos);
+	barrier();
+	n64audio_write_reg(priv, AI_LEN_REG, count);
+
+	priv->chan.nextpos += count;
+	priv->chan.nextpos %= priv->chan.bufsize;
+
+	runtime->delay = runtime->period_size;
+
+	spin_unlock_irqrestore(&priv->chan.lock, flags);
+}
+
+static irqreturn_t n64audio_isr(int irq, void *dev_id)
+{
+	struct n64audio *priv = dev_id;
+	const u32 intrs = n64mi_read_reg(priv, MI_INTR_REG);
+	unsigned long flags;
+
+	// Check it's ours
+	if (!(intrs & MI_INTR_AI))
+		return IRQ_NONE;
+
+	n64audio_write_reg(priv, AI_STATUS_REG, 1);
+
+	if (priv->chan.substream && snd_pcm_running(priv->chan.substream)) {
+		spin_lock_irqsave(&priv->chan.lock, flags);
+
+		priv->chan.pos = priv->chan.nextpos;
+
+		spin_unlock_irqrestore(&priv->chan.lock, flags);
+
+		snd_pcm_period_elapsed(priv->chan.substream);
+		if (priv->chan.substream && snd_pcm_running(priv->chan.substream))
+			n64audio_push(priv);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static const struct snd_pcm_hardware n64audio_pcm_hw = {
+	.info = (SNDRV_PCM_INFO_MMAP |
+		 SNDRV_PCM_INFO_MMAP_VALID |
+		 SNDRV_PCM_INFO_INTERLEAVED |
+		 SNDRV_PCM_INFO_BLOCK_TRANSFER),
+	.formats =          SNDRV_PCM_FMTBIT_S16_BE,
+	.rates =            SNDRV_PCM_RATE_8000_48000,
+	.rate_min =         8000,
+	.rate_max =         48000,
+	.channels_min =     2,
+	.channels_max =     2,
+	.buffer_bytes_max = 32768,
+	.period_bytes_min = 1024,
+	.period_bytes_max = 32768,
+	.periods_min =      3,
+	// 3 periods lets the double-buffering hw read one buffer behind safely
+	.periods_max =      128,
+};
+
+static int hw_rule_period_size(struct snd_pcm_hw_params *params,
+			       struct snd_pcm_hw_rule *rule)
+{
+	struct snd_interval *c = hw_param_interval(params,
+						   SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
+	int changed = 0;
+
+	/*
+	 * The DMA unit has errata on (start + len) & 0x3fff == 0x2000.
+	 * This constraint makes sure that the period size is not a power of two,
+	 * which combined with dma_alloc_coherent aligning the buffer to the largest
+	 * PoT <= size guarantees it won't be hit.
+	 */
+
+	if (is_power_of_2(c->min)) {
+		c->min += 2;
+		changed = 1;
+	}
+	if (is_power_of_2(c->max)) {
+		c->max -= 2;
+		changed = 1;
+	}
+	if (snd_interval_checkempty(c)) {
+		c->empty = 1;
+		return -EINVAL;
+	}
+
+	return changed;
+}
+
+static int n64audio_pcm_open(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	int err;
+
+	runtime->hw = n64audio_pcm_hw;
+	err = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
+	if (err < 0)
+		return err;
+
+	err = snd_pcm_hw_constraint_step(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 2);
+	if (err < 0)
+		return err;
+
+	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+			    hw_rule_period_size, NULL, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int n64audio_pcm_prepare(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct n64audio *priv = substream->pcm->private_data;
+	u32 rate;
+
+	rate = ((2 * AI_NTSC_DACRATE / runtime->rate) + 1) / 2 - 1;
+
+	n64audio_write_reg(priv, AI_RATE_REG, rate);
+
+	rate /= 66;
+	if (rate > 16)
+		rate = 16;
+	n64audio_write_reg(priv, AI_BITCLOCK_REG, rate - 1);
+
+	spin_lock_irq(&priv->chan.lock);
+
+	/* Setup the pseudo-dma transfer pointers.  */
+	priv->chan.pos = 0;
+	priv->chan.nextpos = 0;
+	priv->chan.substream = substream;
+	priv->chan.writesize = snd_pcm_lib_period_bytes(substream);
+	priv->chan.bufsize = snd_pcm_lib_buffer_bytes(substream);
+
+	spin_unlock_irq(&priv->chan.lock);
+	return 0;
+}
+
+static int n64audio_pcm_trigger(struct snd_pcm_substream *substream,
+				int cmd)
+{
+	struct n64audio *priv = substream->pcm->private_data;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+		n64audio_push(substream->pcm->private_data);
+		n64audio_write_reg(priv, AI_CONTROL_REG, 1);
+		n64mi_write_reg(priv, MI_MASK_REG, MI_MASK_SET_AI);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+		n64audio_write_reg(priv, AI_CONTROL_REG, 0);
+		n64mi_write_reg(priv, MI_MASK_REG, MI_MASK_CLR_AI);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static snd_pcm_uframes_t n64audio_pcm_pointer(struct snd_pcm_substream *substream)
+{
+	struct n64audio *priv = substream->pcm->private_data;
+
+	return bytes_to_frames(substream->runtime,
+			       priv->chan.pos);
+}
+
+static int n64audio_pcm_close(struct snd_pcm_substream *substream)
+{
+	struct n64audio *priv = substream->pcm->private_data;
+
+	priv->chan.substream = NULL;
+
+	return 0;
+}
+
+static const struct snd_pcm_ops n64audio_pcm_ops = {
+	.open =		n64audio_pcm_open,
+	.prepare =	n64audio_pcm_prepare,
+	.trigger =	n64audio_pcm_trigger,
+	.pointer =	n64audio_pcm_pointer,
+	.close =	n64audio_pcm_close,
+};
+
+/*
+ * The target device is embedded and RAM-constrained. We save RAM
+ * by initializing in __init code that gets dropped late in boot.
+ * For the same reason there is no module or unloading support.
+ */
+static int __init n64audio_probe(struct platform_device *pdev)
+{
+	struct snd_card *card;
+	struct snd_pcm *pcm;
+	struct n64audio *priv;
+	int err, irq;
+
+	err = snd_card_new(&pdev->dev, SNDRV_DEFAULT_IDX1,
+			   SNDRV_DEFAULT_STR1,
+			   THIS_MODULE, sizeof(*priv), &card);
+	if (err < 0)
+		return err;
+
+	priv = card->private_data;
+
+	spin_lock_init(&priv->chan.lock);
+
+	priv->card = card;
+
+	priv->ring_base = dma_alloc_coherent(card->dev, 32 * 1024, &priv->ring_base_dma,
+					     GFP_DMA|GFP_KERNEL);
+	if (!priv->ring_base) {
+		err = -ENOMEM;
+		goto fail_card;
+	}
+
+	priv->mi_reg_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->mi_reg_base)) {
+		err = PTR_ERR(priv->mi_reg_base);
+		goto fail_dma_alloc;
+	}
+
+	priv->ai_reg_base = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(priv->ai_reg_base)) {
+		err = PTR_ERR(priv->ai_reg_base);
+		goto fail_dma_alloc;
+	}
+
+	err = snd_pcm_new(card, "N64 Audio", 0, 1, 0, &pcm);
+	if (err < 0)
+		goto fail_dma_alloc;
+
+	pcm->private_data = priv;
+	strcpy(pcm->name, "N64 Audio");
+
+	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &n64audio_pcm_ops);
+	snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC, card->dev, 0, 0);
+
+	strcpy(card->driver, "N64 Audio");
+	strcpy(card->shortname, "N64 Audio");
+	strcpy(card->longname, "N64 Audio");
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		err = -EINVAL;
+		goto fail_dma_alloc;
+	}
+	if (devm_request_irq(&pdev->dev, irq, n64audio_isr,
+				IRQF_SHARED, "N64 Audio", priv)) {
+		err = -EBUSY;
+		goto fail_dma_alloc;
+	}
+
+	err = snd_card_register(card);
+	if (err < 0)
+		goto fail_dma_alloc;
+
+	return 0;
+
+fail_dma_alloc:
+	dma_free_coherent(card->dev, 32 * 1024, priv->ring_base, priv->ring_base_dma);
+
+fail_card:
+	snd_card_free(card);
+	return err;
+}
+
+static struct platform_driver n64audio_driver = {
+	.driver = {
+		.name = "n64audio",
+	},
+};
+
+static int __init n64audio_init(void)
+{
+	return platform_driver_probe(&n64audio_driver, n64audio_probe);
+}
+
+module_init(n64audio_init);