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, 185 insertions, 0 deletions

diff --git a/drivers/thunderbolt/nhi_ops.c b/drivers/thunderbolt/nhi_ops.c
new file mode 100644
index 000000000..96da07e88
--- /dev/null
+++ b/drivers/thunderbolt/nhi_ops.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHI specific operations
+ *
+ * Copyright (C) 2019, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/suspend.h>
+
+#include "nhi.h"
+#include "nhi_regs.h"
+#include "tb.h"
+
+/* Ice Lake specific NHI operations */
+
+#define ICL_LC_MAILBOX_TIMEOUT	500 /* ms */
+
+static int check_for_device(struct device *dev, void *data)
+{
+	return tb_is_switch(dev);
+}
+
+static bool icl_nhi_is_device_connected(struct tb_nhi *nhi)
+{
+	struct tb *tb = pci_get_drvdata(nhi->pdev);
+	int ret;
+
+	ret = device_for_each_child(&tb->root_switch->dev, NULL,
+				    check_for_device);
+	return ret > 0;
+}
+
+static int icl_nhi_force_power(struct tb_nhi *nhi, bool power)
+{
+	u32 vs_cap;
+
+	/*
+	 * The Thunderbolt host controller is present always in Ice Lake
+	 * but the firmware may not be loaded and running (depending
+	 * whether there is device connected and so on). Each time the
+	 * controller is used we need to "Force Power" it first and wait
+	 * for the firmware to indicate it is up and running. This "Force
+	 * Power" is really not about actually powering on/off the
+	 * controller so it is accessible even if "Force Power" is off.
+	 *
+	 * The actual power management happens inside shared ACPI power
+	 * resources using standard ACPI methods.
+	 */
+	pci_read_config_dword(nhi->pdev, VS_CAP_22, &vs_cap);
+	if (power) {
+		vs_cap &= ~VS_CAP_22_DMA_DELAY_MASK;
+		vs_cap |= 0x22 << VS_CAP_22_DMA_DELAY_SHIFT;
+		vs_cap |= VS_CAP_22_FORCE_POWER;
+	} else {
+		vs_cap &= ~VS_CAP_22_FORCE_POWER;
+	}
+	pci_write_config_dword(nhi->pdev, VS_CAP_22, vs_cap);
+
+	if (power) {
+		unsigned int retries = 350;
+		u32 val;
+
+		/* Wait until the firmware tells it is up and running */
+		do {
+			pci_read_config_dword(nhi->pdev, VS_CAP_9, &val);
+			if (val & VS_CAP_9_FW_READY)
+				return 0;
+			usleep_range(3000, 3100);
+		} while (--retries);
+
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static void icl_nhi_lc_mailbox_cmd(struct tb_nhi *nhi, enum icl_lc_mailbox_cmd cmd)
+{
+	u32 data;
+
+	data = (cmd << VS_CAP_19_CMD_SHIFT) & VS_CAP_19_CMD_MASK;
+	pci_write_config_dword(nhi->pdev, VS_CAP_19, data | VS_CAP_19_VALID);
+}
+
+static int icl_nhi_lc_mailbox_cmd_complete(struct tb_nhi *nhi, int timeout)
+{
+	unsigned long end;
+	u32 data;
+
+	if (!timeout)
+		goto clear;
+
+	end = jiffies + msecs_to_jiffies(timeout);
+	do {
+		pci_read_config_dword(nhi->pdev, VS_CAP_18, &data);
+		if (data & VS_CAP_18_DONE)
+			goto clear;
+		usleep_range(1000, 1100);
+	} while (time_before(jiffies, end));
+
+	return -ETIMEDOUT;
+
+clear:
+	/* Clear the valid bit */
+	pci_write_config_dword(nhi->pdev, VS_CAP_19, 0);
+	return 0;
+}
+
+static void icl_nhi_set_ltr(struct tb_nhi *nhi)
+{
+	u32 max_ltr, ltr;
+
+	pci_read_config_dword(nhi->pdev, VS_CAP_16, &max_ltr);
+	max_ltr &= 0xffff;
+	/* Program the same value for both snoop and no-snoop */
+	ltr = max_ltr << 16 | max_ltr;
+	pci_write_config_dword(nhi->pdev, VS_CAP_15, ltr);
+}
+
+static int icl_nhi_suspend(struct tb_nhi *nhi)
+{
+	struct tb *tb = pci_get_drvdata(nhi->pdev);
+	int ret;
+
+	if (icl_nhi_is_device_connected(nhi))
+		return 0;
+
+	if (tb_switch_is_icm(tb->root_switch)) {
+		/*
+		 * If there is no device connected we need to perform
+		 * both: a handshake through LC mailbox and force power
+		 * down before entering D3.
+		 */
+		icl_nhi_lc_mailbox_cmd(nhi, ICL_LC_PREPARE_FOR_RESET);
+		ret = icl_nhi_lc_mailbox_cmd_complete(nhi, ICL_LC_MAILBOX_TIMEOUT);
+		if (ret)
+			return ret;
+	}
+
+	return icl_nhi_force_power(nhi, false);
+}
+
+static int icl_nhi_suspend_noirq(struct tb_nhi *nhi, bool wakeup)
+{
+	struct tb *tb = pci_get_drvdata(nhi->pdev);
+	enum icl_lc_mailbox_cmd cmd;
+
+	if (!pm_suspend_via_firmware())
+		return icl_nhi_suspend(nhi);
+
+	if (!tb_switch_is_icm(tb->root_switch))
+		return 0;
+
+	cmd = wakeup ? ICL_LC_GO2SX : ICL_LC_GO2SX_NO_WAKE;
+	icl_nhi_lc_mailbox_cmd(nhi, cmd);
+	return icl_nhi_lc_mailbox_cmd_complete(nhi, ICL_LC_MAILBOX_TIMEOUT);
+}
+
+static int icl_nhi_resume(struct tb_nhi *nhi)
+{
+	int ret;
+
+	ret = icl_nhi_force_power(nhi, true);
+	if (ret)
+		return ret;
+
+	icl_nhi_set_ltr(nhi);
+	return 0;
+}
+
+static void icl_nhi_shutdown(struct tb_nhi *nhi)
+{
+	icl_nhi_force_power(nhi, false);
+}
+
+const struct tb_nhi_ops icl_nhi_ops = {
+	.init = icl_nhi_resume,
+	.suspend_noirq = icl_nhi_suspend_noirq,
+	.resume_noirq = icl_nhi_resume,
+	.runtime_suspend = icl_nhi_suspend,
+	.runtime_resume = icl_nhi_resume,
+	.shutdown = icl_nhi_shutdown,
+};