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, 347 insertions, 0 deletions

diff --git a/drivers/i2c/busses/i2c-tegra-bpmp.c b/drivers/i2c/busses/i2c-tegra-bpmp.c
new file mode 100644
index 000000000..95139985b
--- /dev/null
+++ b/drivers/i2c/busses/i2c-tegra-bpmp.c
@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * drivers/i2c/busses/i2c-tegra-bpmp.c
+ *
+ * Copyright (c) 2016 NVIDIA Corporation.  All rights reserved.
+ *
+ * Author: Shardar Shariff Md <smohammed@nvidia.com>
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include <soc/tegra/bpmp-abi.h>
+#include <soc/tegra/bpmp.h>
+
+/*
+ * Serialized I2C message header size is 6 bytes and includes address, flags
+ * and length
+ */
+#define SERIALI2C_HDR_SIZE 6
+
+struct tegra_bpmp_i2c {
+	struct i2c_adapter adapter;
+	struct device *dev;
+
+	struct tegra_bpmp *bpmp;
+	unsigned int bus;
+};
+
+/*
+ * Linux flags are translated to BPMP defined I2C flags that are used in BPMP
+ * firmware I2C driver to avoid any issues in future if Linux I2C flags are
+ * changed.
+ */
+static void tegra_bpmp_xlate_flags(u16 flags, u16 *out)
+{
+	if (flags & I2C_M_TEN)
+		*out |= SERIALI2C_TEN;
+
+	if (flags & I2C_M_RD)
+		*out |= SERIALI2C_RD;
+
+	if (flags & I2C_M_STOP)
+		*out |= SERIALI2C_STOP;
+
+	if (flags & I2C_M_NOSTART)
+		*out |= SERIALI2C_NOSTART;
+
+	if (flags & I2C_M_REV_DIR_ADDR)
+		*out |= SERIALI2C_REV_DIR_ADDR;
+
+	if (flags & I2C_M_IGNORE_NAK)
+		*out |= SERIALI2C_IGNORE_NAK;
+
+	if (flags & I2C_M_NO_RD_ACK)
+		*out |= SERIALI2C_NO_RD_ACK;
+
+	if (flags & I2C_M_RECV_LEN)
+		*out |= SERIALI2C_RECV_LEN;
+}
+
+/*
+ * The serialized I2C format is simply the following:
+ * [addr little-endian][flags little-endian][len little-endian][data if write]
+ * [addr little-endian][flags little-endian][len little-endian][data if write]
+ *  ...
+ *
+ * The flags are translated from Linux kernel representation to seriali2c
+ * representation. Any undefined flag being set causes an error.
+ *
+ * The data is there only for writes. Reads have the data transferred in the
+ * other direction, and thus data is not present.
+ *
+ * See deserialize_i2c documentation for the data format in the other direction.
+ */
+static void tegra_bpmp_serialize_i2c_msg(struct tegra_bpmp_i2c *i2c,
+					struct mrq_i2c_request *request,
+					struct i2c_msg *msgs,
+					unsigned int num)
+{
+	char *buf = request->xfer.data_buf;
+	unsigned int i, j, pos = 0;
+
+	for (i = 0; i < num; i++) {
+		struct i2c_msg *msg = &msgs[i];
+		u16 flags = 0;
+
+		tegra_bpmp_xlate_flags(msg->flags, &flags);
+
+		buf[pos++] = msg->addr & 0xff;
+		buf[pos++] = (msg->addr & 0xff00) >> 8;
+		buf[pos++] = flags & 0xff;
+		buf[pos++] = (flags & 0xff00) >> 8;
+		buf[pos++] = msg->len & 0xff;
+		buf[pos++] = (msg->len & 0xff00) >> 8;
+
+		if ((flags & SERIALI2C_RD) == 0) {
+			for (j = 0; j < msg->len; j++)
+				buf[pos++] = msg->buf[j];
+		}
+	}
+
+	request->xfer.data_size = pos;
+}
+
+/*
+ * The data in the BPMP -> CPU direction is composed of sequential blocks for
+ * those messages that have I2C_M_RD. So, for example, if you have:
+ *
+ * - !I2C_M_RD, len == 5, data == a0 01 02 03 04
+ * - !I2C_M_RD, len == 1, data == a0
+ * - I2C_M_RD, len == 2, data == [uninitialized buffer 1]
+ * - !I2C_M_RD, len == 1, data == a2
+ * - I2C_M_RD, len == 2, data == [uninitialized buffer 2]
+ *
+ * ...then the data in the BPMP -> CPU direction would be 4 bytes total, and
+ * would contain 2 bytes that will go to uninitialized buffer 1, and 2 bytes
+ * that will go to uninitialized buffer 2.
+ */
+static int tegra_bpmp_i2c_deserialize(struct tegra_bpmp_i2c *i2c,
+				      struct mrq_i2c_response *response,
+				      struct i2c_msg *msgs,
+				      unsigned int num)
+{
+	size_t size = response->xfer.data_size, len = 0, pos = 0;
+	char *buf = response->xfer.data_buf;
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		if (msgs[i].flags & I2C_M_RD)
+			len += msgs[i].len;
+
+	if (len != size)
+		return -EINVAL;
+
+	for (i = 0; i < num; i++) {
+		if (msgs[i].flags & I2C_M_RD) {
+			memcpy(msgs[i].buf, buf + pos, msgs[i].len);
+			pos += msgs[i].len;
+		}
+	}
+
+	return 0;
+}
+
+static int tegra_bpmp_i2c_msg_len_check(struct i2c_msg *msgs, unsigned int num)
+{
+	size_t tx_len = 0, rx_len = 0;
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		if (!(msgs[i].flags & I2C_M_RD))
+			tx_len += SERIALI2C_HDR_SIZE + msgs[i].len;
+
+	if (tx_len > TEGRA_I2C_IPC_MAX_IN_BUF_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < num; i++)
+		if ((msgs[i].flags & I2C_M_RD))
+			rx_len += msgs[i].len;
+
+	if (rx_len > TEGRA_I2C_IPC_MAX_OUT_BUF_SIZE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int tegra_bpmp_i2c_msg_xfer(struct tegra_bpmp_i2c *i2c,
+				   struct mrq_i2c_request *request,
+				   struct mrq_i2c_response *response,
+				   bool atomic)
+{
+	struct tegra_bpmp_message msg;
+	int err;
+
+	request->cmd = CMD_I2C_XFER;
+	request->xfer.bus_id = i2c->bus;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_I2C;
+	msg.tx.data = request;
+	msg.tx.size = sizeof(*request);
+	msg.rx.data = response;
+	msg.rx.size = sizeof(*response);
+
+	if (atomic)
+		err = tegra_bpmp_transfer_atomic(i2c->bpmp, &msg);
+	else
+		err = tegra_bpmp_transfer(i2c->bpmp, &msg);
+
+	if (err < 0) {
+		dev_err(i2c->dev, "failed to transfer message: %d\n", err);
+		return err;
+	}
+
+	if (msg.rx.ret != 0) {
+		if (msg.rx.ret == -BPMP_EAGAIN) {
+			dev_dbg(i2c->dev, "arbitration lost\n");
+			return -EAGAIN;
+		}
+
+		if (msg.rx.ret == -BPMP_ETIMEDOUT) {
+			dev_dbg(i2c->dev, "timeout\n");
+			return -ETIMEDOUT;
+		}
+
+		if (msg.rx.ret == -BPMP_ENXIO) {
+			dev_dbg(i2c->dev, "NAK\n");
+			return -ENXIO;
+		}
+
+		dev_err(i2c->dev, "transaction failed: %d\n", msg.rx.ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int tegra_bpmp_i2c_xfer_common(struct i2c_adapter *adapter,
+				      struct i2c_msg *msgs, int num,
+				      bool atomic)
+{
+	struct tegra_bpmp_i2c *i2c = i2c_get_adapdata(adapter);
+	struct mrq_i2c_response response;
+	struct mrq_i2c_request request;
+	int err;
+
+	err = tegra_bpmp_i2c_msg_len_check(msgs, num);
+	if (err < 0) {
+		dev_err(i2c->dev, "unsupported message length\n");
+		return err;
+	}
+
+	memset(&request, 0, sizeof(request));
+	memset(&response, 0, sizeof(response));
+
+	tegra_bpmp_serialize_i2c_msg(i2c, &request, msgs, num);
+	err = tegra_bpmp_i2c_msg_xfer(i2c, &request, &response, atomic);
+	if (err < 0) {
+		dev_err(i2c->dev, "failed to transfer message: %d\n", err);
+		return err;
+	}
+
+	err = tegra_bpmp_i2c_deserialize(i2c, &response, msgs, num);
+	if (err < 0) {
+		dev_err(i2c->dev, "failed to deserialize message: %d\n", err);
+		return err;
+	}
+
+	return num;
+}
+
+static int tegra_bpmp_i2c_xfer(struct i2c_adapter *adapter,
+			       struct i2c_msg *msgs, int num)
+{
+	return tegra_bpmp_i2c_xfer_common(adapter, msgs, num, false);
+}
+
+static int tegra_bpmp_i2c_xfer_atomic(struct i2c_adapter *adapter,
+				      struct i2c_msg *msgs, int num)
+{
+	return tegra_bpmp_i2c_xfer_common(adapter, msgs, num, true);
+}
+
+static u32 tegra_bpmp_i2c_func(struct i2c_adapter *adapter)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_10BIT_ADDR |
+	       I2C_FUNC_PROTOCOL_MANGLING | I2C_FUNC_NOSTART;
+}
+
+static const struct i2c_algorithm tegra_bpmp_i2c_algo = {
+	.master_xfer = tegra_bpmp_i2c_xfer,
+	.master_xfer_atomic = tegra_bpmp_i2c_xfer_atomic,
+	.functionality = tegra_bpmp_i2c_func,
+};
+
+static int tegra_bpmp_i2c_probe(struct platform_device *pdev)
+{
+	struct tegra_bpmp_i2c *i2c;
+	u32 value;
+	int err;
+
+	i2c = devm_kzalloc(&pdev->dev, sizeof(*i2c), GFP_KERNEL);
+	if (!i2c)
+		return -ENOMEM;
+
+	i2c->dev = &pdev->dev;
+
+	i2c->bpmp = dev_get_drvdata(pdev->dev.parent);
+	if (!i2c->bpmp)
+		return -ENODEV;
+
+	err = of_property_read_u32(pdev->dev.of_node, "nvidia,bpmp-bus-id",
+				   &value);
+	if (err < 0)
+		return err;
+
+	i2c->bus = value;
+
+	i2c_set_adapdata(&i2c->adapter, i2c);
+	i2c->adapter.owner = THIS_MODULE;
+	strscpy(i2c->adapter.name, "Tegra BPMP I2C adapter",
+		sizeof(i2c->adapter.name));
+	i2c->adapter.algo = &tegra_bpmp_i2c_algo;
+	i2c->adapter.dev.parent = &pdev->dev;
+	i2c->adapter.dev.of_node = pdev->dev.of_node;
+
+	platform_set_drvdata(pdev, i2c);
+
+	return i2c_add_adapter(&i2c->adapter);
+}
+
+static int tegra_bpmp_i2c_remove(struct platform_device *pdev)
+{
+	struct tegra_bpmp_i2c *i2c = platform_get_drvdata(pdev);
+
+	i2c_del_adapter(&i2c->adapter);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_bpmp_i2c_of_match[] = {
+	{ .compatible = "nvidia,tegra186-bpmp-i2c", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra_bpmp_i2c_of_match);
+
+static struct platform_driver tegra_bpmp_i2c_driver = {
+	.driver = {
+		.name = "tegra-bpmp-i2c",
+		.of_match_table = tegra_bpmp_i2c_of_match,
+	},
+	.probe = tegra_bpmp_i2c_probe,
+	.remove = tegra_bpmp_i2c_remove,
+};
+module_platform_driver(tegra_bpmp_i2c_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra BPMP I2C bus controller driver");
+MODULE_AUTHOR("Shardar Shariff Md <smohammed@nvidia.com>");
+MODULE_AUTHOR("Juha-Matti Tilli");
+MODULE_LICENSE("GPL v2");