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, 730 insertions, 0 deletions

diff --git a/drivers/hte/hte-tegra194.c b/drivers/hte/hte-tegra194.c
new file mode 100644
index 000000000..49a27af22
--- /dev/null
+++ b/drivers/hte/hte-tegra194.c
@@ -0,0 +1,730 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021-2022 NVIDIA Corporation
+ *
+ * Author: Dipen Patel <dipenp@nvidia.com>
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/hte.h>
+#include <linux/uaccess.h>
+#include <linux/gpio/driver.h>
+#include <linux/gpio/consumer.h>
+
+#define HTE_SUSPEND	0
+
+/* HTE source clock TSC is 31.25MHz */
+#define HTE_TS_CLK_RATE_HZ	31250000ULL
+#define HTE_CLK_RATE_NS		32
+#define HTE_TS_NS_SHIFT	__builtin_ctz(HTE_CLK_RATE_NS)
+
+#define NV_AON_SLICE_INVALID	-1
+#define NV_LINES_IN_SLICE	32
+
+/* AON HTE line map For slice 1 */
+#define NV_AON_HTE_SLICE1_IRQ_GPIO_28	12
+#define NV_AON_HTE_SLICE1_IRQ_GPIO_29	13
+
+/* AON HTE line map For slice 2 */
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_0	0
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_1	1
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_2	2
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_3	3
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_4	4
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_5	5
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_6	6
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_7	7
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_8	8
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_9	9
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_10	10
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_11	11
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_12	12
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_13	13
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_14	14
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_15	15
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_16	16
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_17	17
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_18	18
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_19	19
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_20	20
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_21	21
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_22	22
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_23	23
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_24	24
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_25	25
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_26	26
+#define NV_AON_HTE_SLICE2_IRQ_GPIO_27	27
+
+#define HTE_TECTRL		0x0
+#define HTE_TETSCH		0x4
+#define HTE_TETSCL		0x8
+#define HTE_TESRC		0xC
+#define HTE_TECCV		0x10
+#define HTE_TEPCV		0x14
+#define HTE_TECMD		0x1C
+#define HTE_TESTATUS		0x20
+#define HTE_SLICE0_TETEN	0x40
+#define HTE_SLICE1_TETEN	0x60
+
+#define HTE_SLICE_SIZE		(HTE_SLICE1_TETEN - HTE_SLICE0_TETEN)
+
+#define HTE_TECTRL_ENABLE_ENABLE	0x1
+
+#define HTE_TECTRL_OCCU_SHIFT		0x8
+#define HTE_TECTRL_INTR_SHIFT		0x1
+#define HTE_TECTRL_INTR_ENABLE		0x1
+
+#define HTE_TESRC_SLICE_SHIFT		16
+#define HTE_TESRC_SLICE_DEFAULT_MASK	0xFF
+
+#define HTE_TECMD_CMD_POP		0x1
+
+#define HTE_TESTATUS_OCCUPANCY_SHIFT	8
+#define HTE_TESTATUS_OCCUPANCY_MASK	0xFF
+
+enum tegra_hte_type {
+	HTE_TEGRA_TYPE_GPIO = 1U << 0,
+	HTE_TEGRA_TYPE_LIC = 1U << 1,
+};
+
+struct hte_slices {
+	u32 r_val;
+	unsigned long flags;
+	/* to prevent lines mapped to same slice updating its register */
+	spinlock_t s_lock;
+};
+
+struct tegra_hte_line_mapped {
+	int slice;
+	u32 bit_index;
+};
+
+struct tegra_hte_line_data {
+	unsigned long flags;
+	void *data;
+};
+
+struct tegra_hte_data {
+	enum tegra_hte_type type;
+	u32 map_sz;
+	u32 sec_map_sz;
+	const struct tegra_hte_line_mapped *map;
+	const struct tegra_hte_line_mapped *sec_map;
+};
+
+struct tegra_hte_soc {
+	int hte_irq;
+	u32 itr_thrshld;
+	u32 conf_rval;
+	struct hte_slices *sl;
+	const struct tegra_hte_data *prov_data;
+	struct tegra_hte_line_data *line_data;
+	struct hte_chip *chip;
+	struct gpio_chip *c;
+	void __iomem *regs;
+};
+
+static const struct tegra_hte_line_mapped tegra194_aon_gpio_map[] = {
+	/* gpio, slice, bit_index */
+	/* AA port */
+	[0]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_11},
+	[1]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_10},
+	[2]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_9},
+	[3]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_8},
+	[4]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_7},
+	[5]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_6},
+	[6]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_5},
+	[7]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_4},
+	/* BB port */
+	[8]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_3},
+	[9]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_2},
+	[10] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_1},
+	[11] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_0},
+	/* CC port */
+	[12] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_22},
+	[13] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_21},
+	[14] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_20},
+	[15] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_19},
+	[16] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_18},
+	[17] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_17},
+	[18] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_16},
+	[19] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_15},
+	/* DD port */
+	[20] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_14},
+	[21] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_13},
+	[22] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_12},
+	/* EE port */
+	[23] = {1, NV_AON_HTE_SLICE1_IRQ_GPIO_29},
+	[24] = {1, NV_AON_HTE_SLICE1_IRQ_GPIO_28},
+	[25] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_27},
+	[26] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_26},
+	[27] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_25},
+	[28] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_24},
+	[29] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_23},
+};
+
+static const struct tegra_hte_line_mapped tegra194_aon_gpio_sec_map[] = {
+	/* gpio, slice, bit_index */
+	/* AA port */
+	[0]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_11},
+	[1]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_10},
+	[2]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_9},
+	[3]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_8},
+	[4]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_7},
+	[5]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_6},
+	[6]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_5},
+	[7]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_4},
+	/* BB port */
+	[8]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_3},
+	[9]  = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_2},
+	[10] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_1},
+	[11] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_0},
+	[12]  = {NV_AON_SLICE_INVALID, 0},
+	[13]  = {NV_AON_SLICE_INVALID, 0},
+	[14] = {NV_AON_SLICE_INVALID, 0},
+	[15] = {NV_AON_SLICE_INVALID, 0},
+	/* CC port */
+	[16] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_22},
+	[17] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_21},
+	[18] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_20},
+	[19] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_19},
+	[20] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_18},
+	[21] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_17},
+	[22] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_16},
+	[23] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_15},
+	/* DD port */
+	[24] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_14},
+	[25] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_13},
+	[26] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_12},
+	[27] = {NV_AON_SLICE_INVALID, 0},
+	[28] = {NV_AON_SLICE_INVALID, 0},
+	[29] = {NV_AON_SLICE_INVALID, 0},
+	[30] = {NV_AON_SLICE_INVALID, 0},
+	[31] = {NV_AON_SLICE_INVALID, 0},
+	/* EE port */
+	[32] = {1, NV_AON_HTE_SLICE1_IRQ_GPIO_29},
+	[33] = {1, NV_AON_HTE_SLICE1_IRQ_GPIO_28},
+	[34] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_27},
+	[35] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_26},
+	[36] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_25},
+	[37] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_24},
+	[38] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_23},
+	[39] = {NV_AON_SLICE_INVALID, 0},
+};
+
+static const struct tegra_hte_data aon_hte = {
+	.map_sz = ARRAY_SIZE(tegra194_aon_gpio_map),
+	.map = tegra194_aon_gpio_map,
+	.sec_map_sz = ARRAY_SIZE(tegra194_aon_gpio_sec_map),
+	.sec_map = tegra194_aon_gpio_sec_map,
+	.type = HTE_TEGRA_TYPE_GPIO,
+};
+
+static const struct tegra_hte_data lic_hte = {
+	.map_sz = 0,
+	.map = NULL,
+	.type = HTE_TEGRA_TYPE_LIC,
+};
+
+static inline u32 tegra_hte_readl(struct tegra_hte_soc *hte, u32 reg)
+{
+	return readl(hte->regs + reg);
+}
+
+static inline void tegra_hte_writel(struct tegra_hte_soc *hte, u32 reg,
+				    u32 val)
+{
+	writel(val, hte->regs + reg);
+}
+
+static int tegra_hte_map_to_line_id(u32 eid,
+				    const struct tegra_hte_line_mapped *m,
+				    u32 map_sz, u32 *mapped)
+{
+
+	if (m) {
+		if (eid > map_sz)
+			return -EINVAL;
+		if (m[eid].slice == NV_AON_SLICE_INVALID)
+			return -EINVAL;
+
+		*mapped = (m[eid].slice << 5) + m[eid].bit_index;
+	} else {
+		*mapped = eid;
+	}
+
+	return 0;
+}
+
+static int tegra_hte_line_xlate(struct hte_chip *gc,
+				const struct of_phandle_args *args,
+				struct hte_ts_desc *desc, u32 *xlated_id)
+{
+	int ret = 0;
+	u32 line_id;
+	struct tegra_hte_soc *gs;
+	const struct tegra_hte_line_mapped *map = NULL;
+	u32 map_sz = 0;
+
+	if (!gc || !desc || !xlated_id)
+		return -EINVAL;
+
+	if (args) {
+		if (gc->of_hte_n_cells < 1)
+			return -EINVAL;
+
+		if (args->args_count != gc->of_hte_n_cells)
+			return -EINVAL;
+
+		desc->attr.line_id = args->args[0];
+	}
+
+	gs = gc->data;
+	if (!gs || !gs->prov_data)
+		return -EINVAL;
+
+	/*
+	 *
+	 * There are two paths GPIO consumers can take as follows:
+	 * 1) The consumer (gpiolib-cdev for example) which uses GPIO global
+	 * number which gets assigned run time.
+	 * 2) The consumer passing GPIO from the DT which is assigned
+	 * statically for example by using TEGRA194_AON_GPIO gpio DT binding.
+	 *
+	 * The code below addresses both the consumer use cases and maps into
+	 * HTE/GTE namespace.
+	 */
+	if (gs->prov_data->type == HTE_TEGRA_TYPE_GPIO && !args) {
+		line_id = desc->attr.line_id - gs->c->base;
+		map = gs->prov_data->map;
+		map_sz = gs->prov_data->map_sz;
+	} else if (gs->prov_data->type == HTE_TEGRA_TYPE_GPIO && args) {
+		line_id = desc->attr.line_id;
+		map = gs->prov_data->sec_map;
+		map_sz = gs->prov_data->sec_map_sz;
+	} else {
+		line_id = desc->attr.line_id;
+	}
+
+	ret = tegra_hte_map_to_line_id(line_id, map, map_sz, xlated_id);
+	if (ret < 0) {
+		dev_err(gc->dev, "line_id:%u mapping failed\n",
+			desc->attr.line_id);
+		return ret;
+	}
+
+	if (*xlated_id > gc->nlines)
+		return -EINVAL;
+
+	dev_dbg(gc->dev, "requested id:%u, xlated id:%u\n",
+		desc->attr.line_id, *xlated_id);
+
+	return 0;
+}
+
+static int tegra_hte_line_xlate_plat(struct hte_chip *gc,
+				     struct hte_ts_desc *desc, u32 *xlated_id)
+{
+	return tegra_hte_line_xlate(gc, NULL, desc, xlated_id);
+}
+
+static int tegra_hte_en_dis_common(struct hte_chip *chip, u32 line_id, bool en)
+{
+	u32 slice, sl_bit_shift, line_bit, val, reg;
+	struct tegra_hte_soc *gs;
+
+	sl_bit_shift = __builtin_ctz(HTE_SLICE_SIZE);
+
+	if (!chip)
+		return -EINVAL;
+
+	gs = chip->data;
+
+	if (line_id > chip->nlines) {
+		dev_err(chip->dev,
+			"line id: %u is not supported by this controller\n",
+			line_id);
+		return -EINVAL;
+	}
+
+	slice = line_id >> sl_bit_shift;
+	line_bit = line_id & (HTE_SLICE_SIZE - 1);
+	reg = (slice << sl_bit_shift) + HTE_SLICE0_TETEN;
+
+	spin_lock(&gs->sl[slice].s_lock);
+
+	if (test_bit(HTE_SUSPEND, &gs->sl[slice].flags)) {
+		spin_unlock(&gs->sl[slice].s_lock);
+		dev_dbg(chip->dev, "device suspended");
+		return -EBUSY;
+	}
+
+	val = tegra_hte_readl(gs, reg);
+	if (en)
+		val = val | (1 << line_bit);
+	else
+		val = val & (~(1 << line_bit));
+	tegra_hte_writel(gs, reg, val);
+
+	spin_unlock(&gs->sl[slice].s_lock);
+
+	dev_dbg(chip->dev, "line: %u, slice %u, line_bit %u, reg:0x%x\n",
+		line_id, slice, line_bit, reg);
+
+	return 0;
+}
+
+static int tegra_hte_enable(struct hte_chip *chip, u32 line_id)
+{
+	if (!chip)
+		return -EINVAL;
+
+	return tegra_hte_en_dis_common(chip, line_id, true);
+}
+
+static int tegra_hte_disable(struct hte_chip *chip, u32 line_id)
+{
+	if (!chip)
+		return -EINVAL;
+
+	return tegra_hte_en_dis_common(chip, line_id, false);
+}
+
+static int tegra_hte_request(struct hte_chip *chip, struct hte_ts_desc *desc,
+			     u32 line_id)
+{
+	int ret;
+	struct tegra_hte_soc *gs;
+	struct hte_line_attr *attr;
+
+	if (!chip || !chip->data || !desc)
+		return -EINVAL;
+
+	gs = chip->data;
+	attr = &desc->attr;
+
+	if (gs->prov_data->type == HTE_TEGRA_TYPE_GPIO) {
+		if (!attr->line_data)
+			return -EINVAL;
+
+		ret = gpiod_enable_hw_timestamp_ns(attr->line_data,
+						   attr->edge_flags);
+		if (ret)
+			return ret;
+
+		gs->line_data[line_id].data = attr->line_data;
+		gs->line_data[line_id].flags = attr->edge_flags;
+	}
+
+	return tegra_hte_en_dis_common(chip, line_id, true);
+}
+
+static int tegra_hte_release(struct hte_chip *chip, struct hte_ts_desc *desc,
+			     u32 line_id)
+{
+	struct tegra_hte_soc *gs;
+	struct hte_line_attr *attr;
+	int ret;
+
+	if (!chip || !chip->data || !desc)
+		return -EINVAL;
+
+	gs = chip->data;
+	attr = &desc->attr;
+
+	if (gs->prov_data->type == HTE_TEGRA_TYPE_GPIO) {
+		ret = gpiod_disable_hw_timestamp_ns(attr->line_data,
+						    gs->line_data[line_id].flags);
+		if (ret)
+			return ret;
+
+		gs->line_data[line_id].data = NULL;
+		gs->line_data[line_id].flags = 0;
+	}
+
+	return tegra_hte_en_dis_common(chip, line_id, false);
+}
+
+static int tegra_hte_clk_src_info(struct hte_chip *chip,
+				  struct hte_clk_info *ci)
+{
+	(void)chip;
+
+	if (!ci)
+		return -EINVAL;
+
+	ci->hz = HTE_TS_CLK_RATE_HZ;
+	ci->type = CLOCK_MONOTONIC;
+
+	return 0;
+}
+
+static int tegra_hte_get_level(struct tegra_hte_soc *gs, u32 line_id)
+{
+	struct gpio_desc *desc;
+
+	if (gs->prov_data->type == HTE_TEGRA_TYPE_GPIO) {
+		desc = gs->line_data[line_id].data;
+		if (desc)
+			return gpiod_get_raw_value(desc);
+	}
+
+	return -1;
+}
+
+static void tegra_hte_read_fifo(struct tegra_hte_soc *gs)
+{
+	u32 tsh, tsl, src, pv, cv, acv, slice, bit_index, line_id;
+	u64 tsc;
+	struct hte_ts_data el;
+
+	while ((tegra_hte_readl(gs, HTE_TESTATUS) >>
+		HTE_TESTATUS_OCCUPANCY_SHIFT) &
+		HTE_TESTATUS_OCCUPANCY_MASK) {
+		tsh = tegra_hte_readl(gs, HTE_TETSCH);
+		tsl = tegra_hte_readl(gs, HTE_TETSCL);
+		tsc = (((u64)tsh << 32) | tsl);
+
+		src = tegra_hte_readl(gs, HTE_TESRC);
+		slice = (src >> HTE_TESRC_SLICE_SHIFT) &
+			    HTE_TESRC_SLICE_DEFAULT_MASK;
+
+		pv = tegra_hte_readl(gs, HTE_TEPCV);
+		cv = tegra_hte_readl(gs, HTE_TECCV);
+		acv = pv ^ cv;
+		while (acv) {
+			bit_index = __builtin_ctz(acv);
+			line_id = bit_index + (slice << 5);
+			el.tsc = tsc << HTE_TS_NS_SHIFT;
+			el.raw_level = tegra_hte_get_level(gs, line_id);
+			hte_push_ts_ns(gs->chip, line_id, &el);
+			acv &= ~BIT(bit_index);
+		}
+		tegra_hte_writel(gs, HTE_TECMD, HTE_TECMD_CMD_POP);
+	}
+}
+
+static irqreturn_t tegra_hte_isr(int irq, void *dev_id)
+{
+	struct tegra_hte_soc *gs = dev_id;
+	(void)irq;
+
+	tegra_hte_read_fifo(gs);
+
+	return IRQ_HANDLED;
+}
+
+static bool tegra_hte_match_from_linedata(const struct hte_chip *chip,
+					  const struct hte_ts_desc *hdesc)
+{
+	struct tegra_hte_soc *hte_dev = chip->data;
+
+	if (!hte_dev || (hte_dev->prov_data->type != HTE_TEGRA_TYPE_GPIO))
+		return false;
+
+	return hte_dev->c == gpiod_to_chip(hdesc->attr.line_data);
+}
+
+static const struct of_device_id tegra_hte_of_match[] = {
+	{ .compatible = "nvidia,tegra194-gte-lic", .data = &lic_hte},
+	{ .compatible = "nvidia,tegra194-gte-aon", .data = &aon_hte},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra_hte_of_match);
+
+static const struct hte_ops g_ops = {
+	.request = tegra_hte_request,
+	.release = tegra_hte_release,
+	.enable = tegra_hte_enable,
+	.disable = tegra_hte_disable,
+	.get_clk_src_info = tegra_hte_clk_src_info,
+};
+
+static void tegra_gte_disable(void *data)
+{
+	struct platform_device *pdev = data;
+	struct tegra_hte_soc *gs = dev_get_drvdata(&pdev->dev);
+
+	tegra_hte_writel(gs, HTE_TECTRL, 0);
+}
+
+static int tegra_get_gpiochip_from_name(struct gpio_chip *chip, void *data)
+{
+	return !strcmp(chip->label, data);
+}
+
+static int tegra_hte_probe(struct platform_device *pdev)
+{
+	int ret;
+	u32 i, slices, val = 0;
+	u32 nlines;
+	struct device *dev;
+	struct tegra_hte_soc *hte_dev;
+	struct hte_chip *gc;
+
+	dev = &pdev->dev;
+
+	ret = of_property_read_u32(dev->of_node, "nvidia,slices", &slices);
+	if (ret != 0) {
+		dev_err(dev, "Could not read slices\n");
+		return -EINVAL;
+	}
+	nlines = slices << 5;
+
+	hte_dev = devm_kzalloc(dev, sizeof(*hte_dev), GFP_KERNEL);
+	if (!hte_dev)
+		return -ENOMEM;
+
+	gc = devm_kzalloc(dev, sizeof(*gc), GFP_KERNEL);
+	if (!gc)
+		return -ENOMEM;
+
+	dev_set_drvdata(&pdev->dev, hte_dev);
+	hte_dev->prov_data = of_device_get_match_data(&pdev->dev);
+
+	hte_dev->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(hte_dev->regs))
+		return PTR_ERR(hte_dev->regs);
+
+	ret = of_property_read_u32(dev->of_node, "nvidia,int-threshold",
+				   &hte_dev->itr_thrshld);
+	if (ret != 0)
+		hte_dev->itr_thrshld = 1;
+
+	hte_dev->sl = devm_kcalloc(dev, slices, sizeof(*hte_dev->sl),
+				   GFP_KERNEL);
+	if (!hte_dev->sl)
+		return -ENOMEM;
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
+		dev_err_probe(dev, ret, "failed to get irq\n");
+		return ret;
+	}
+	hte_dev->hte_irq = ret;
+	ret = devm_request_irq(dev, hte_dev->hte_irq, tegra_hte_isr, 0,
+			       dev_name(dev), hte_dev);
+	if (ret < 0) {
+		dev_err(dev, "request irq failed.\n");
+		return ret;
+	}
+
+	gc->nlines = nlines;
+	gc->ops = &g_ops;
+	gc->dev = dev;
+	gc->data = hte_dev;
+	gc->xlate_of = tegra_hte_line_xlate;
+	gc->xlate_plat = tegra_hte_line_xlate_plat;
+	gc->of_hte_n_cells = 1;
+
+	if (hte_dev->prov_data &&
+	    hte_dev->prov_data->type == HTE_TEGRA_TYPE_GPIO) {
+		hte_dev->line_data = devm_kcalloc(dev, nlines,
+						  sizeof(*hte_dev->line_data),
+						  GFP_KERNEL);
+		if (!hte_dev->line_data)
+			return -ENOMEM;
+
+		gc->match_from_linedata = tegra_hte_match_from_linedata;
+
+		hte_dev->c = gpiochip_find("tegra194-gpio-aon",
+					   tegra_get_gpiochip_from_name);
+		if (!hte_dev->c)
+			return dev_err_probe(dev, -EPROBE_DEFER,
+					     "wait for gpio controller\n");
+	}
+
+	hte_dev->chip = gc;
+
+	ret = devm_hte_register_chip(hte_dev->chip);
+	if (ret) {
+		dev_err(gc->dev, "hte chip register failed");
+		return ret;
+	}
+
+	for (i = 0; i < slices; i++) {
+		hte_dev->sl[i].flags = 0;
+		spin_lock_init(&hte_dev->sl[i].s_lock);
+	}
+
+	val = HTE_TECTRL_ENABLE_ENABLE |
+	      (HTE_TECTRL_INTR_ENABLE << HTE_TECTRL_INTR_SHIFT) |
+	      (hte_dev->itr_thrshld << HTE_TECTRL_OCCU_SHIFT);
+	tegra_hte_writel(hte_dev, HTE_TECTRL, val);
+
+	ret = devm_add_action_or_reset(&pdev->dev, tegra_gte_disable, pdev);
+	if (ret)
+		return ret;
+
+	dev_dbg(gc->dev, "lines: %d, slices:%d", gc->nlines, slices);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_hte_resume_early(struct device *dev)
+{
+	u32 i;
+	struct tegra_hte_soc *gs = dev_get_drvdata(dev);
+	u32 slices = gs->chip->nlines / NV_LINES_IN_SLICE;
+	u32 sl_bit_shift = __builtin_ctz(HTE_SLICE_SIZE);
+
+	tegra_hte_writel(gs, HTE_TECTRL, gs->conf_rval);
+
+	for (i = 0; i < slices; i++) {
+		spin_lock(&gs->sl[i].s_lock);
+		tegra_hte_writel(gs,
+				 ((i << sl_bit_shift) + HTE_SLICE0_TETEN),
+				 gs->sl[i].r_val);
+		clear_bit(HTE_SUSPEND, &gs->sl[i].flags);
+		spin_unlock(&gs->sl[i].s_lock);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_hte_suspend_late(struct device *dev)
+{
+	u32 i;
+	struct tegra_hte_soc *gs = dev_get_drvdata(dev);
+	u32 slices = gs->chip->nlines / NV_LINES_IN_SLICE;
+	u32 sl_bit_shift = __builtin_ctz(HTE_SLICE_SIZE);
+
+	gs->conf_rval = tegra_hte_readl(gs, HTE_TECTRL);
+	for (i = 0; i < slices; i++) {
+		spin_lock(&gs->sl[i].s_lock);
+		gs->sl[i].r_val = tegra_hte_readl(gs,
+				((i << sl_bit_shift) + HTE_SLICE0_TETEN));
+		set_bit(HTE_SUSPEND, &gs->sl[i].flags);
+		spin_unlock(&gs->sl[i].s_lock);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops tegra_hte_pm = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(tegra_hte_suspend_late,
+				     tegra_hte_resume_early)
+};
+
+static struct platform_driver tegra_hte_driver = {
+	.probe = tegra_hte_probe,
+	.driver = {
+		.name = "tegra_hte",
+		.pm = &tegra_hte_pm,
+		.of_match_table = tegra_hte_of_match,
+	},
+};
+
+module_platform_driver(tegra_hte_driver);
+
+MODULE_AUTHOR("Dipen Patel <dipenp@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra HTE (Hardware Timestamping Engine) driver");
+MODULE_LICENSE("GPL");