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, 269 insertions, 0 deletions

diff --git a/drivers/char/hw_random/cavium-rng-vf.c b/drivers/char/hw_random/cavium-rng-vf.c
new file mode 100644
index 000000000..c99c54cd9
--- /dev/null
+++ b/drivers/char/hw_random/cavium-rng-vf.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hardware Random Number Generator support.
+ * Cavium Thunder, Marvell OcteonTx/Tx2 processor families.
+ *
+ * Copyright (C) 2016 Cavium, Inc.
+ */
+
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+
+#include <asm/arch_timer.h>
+
+/* PCI device IDs */
+#define	PCI_DEVID_CAVIUM_RNG_PF		0xA018
+#define	PCI_DEVID_CAVIUM_RNG_VF		0xA033
+
+#define HEALTH_STATUS_REG		0x38
+
+/* RST device info */
+#define PCI_DEVICE_ID_RST_OTX2		0xA085
+#define RST_BOOT_REG			0x1600ULL
+#define CLOCK_BASE_RATE			50000000ULL
+#define MSEC_TO_NSEC(x)			(x * 1000000)
+
+struct cavium_rng {
+	struct hwrng ops;
+	void __iomem *result;
+	void __iomem *pf_regbase;
+	struct pci_dev *pdev;
+	u64  clock_rate;
+	u64  prev_error;
+	u64  prev_time;
+};
+
+static inline bool is_octeontx(struct pci_dev *pdev)
+{
+	if (midr_is_cpu_model_range(read_cpuid_id(), MIDR_THUNDERX_83XX,
+				    MIDR_CPU_VAR_REV(0, 0),
+				    MIDR_CPU_VAR_REV(3, 0)) ||
+	    midr_is_cpu_model_range(read_cpuid_id(), MIDR_THUNDERX_81XX,
+				    MIDR_CPU_VAR_REV(0, 0),
+				    MIDR_CPU_VAR_REV(3, 0)) ||
+	    midr_is_cpu_model_range(read_cpuid_id(), MIDR_THUNDERX,
+				    MIDR_CPU_VAR_REV(0, 0),
+				    MIDR_CPU_VAR_REV(3, 0)))
+		return true;
+
+	return false;
+}
+
+static u64 rng_get_coprocessor_clkrate(void)
+{
+	u64 ret = CLOCK_BASE_RATE * 16; /* Assume 800Mhz as default */
+	struct pci_dev *pdev;
+	void __iomem *base;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+			      PCI_DEVICE_ID_RST_OTX2, NULL);
+	if (!pdev)
+		goto error;
+
+	base = pci_ioremap_bar(pdev, 0);
+	if (!base)
+		goto error_put_pdev;
+
+	/* RST: PNR_MUL * 50Mhz gives clockrate */
+	ret = CLOCK_BASE_RATE * ((readq(base + RST_BOOT_REG) >> 33) & 0x3F);
+
+	iounmap(base);
+
+error_put_pdev:
+	pci_dev_put(pdev);
+
+error:
+	return ret;
+}
+
+static int check_rng_health(struct cavium_rng *rng)
+{
+	u64 cur_err, cur_time;
+	u64 status, cycles;
+	u64 time_elapsed;
+
+
+	/* Skip checking health for OcteonTx */
+	if (!rng->pf_regbase)
+		return 0;
+
+	status = readq(rng->pf_regbase + HEALTH_STATUS_REG);
+	if (status & BIT_ULL(0)) {
+		dev_err(&rng->pdev->dev, "HWRNG: Startup health test failed\n");
+		return -EIO;
+	}
+
+	cycles = status >> 1;
+	if (!cycles)
+		return 0;
+
+	cur_time = arch_timer_read_counter();
+
+	/* RNM_HEALTH_STATUS[CYCLES_SINCE_HEALTH_FAILURE]
+	 * Number of coprocessor cycles times 2 since the last failure.
+	 * This field doesn't get cleared/updated until another failure.
+	 */
+	cycles = cycles / 2;
+	cur_err = (cycles * 1000000000) / rng->clock_rate; /* In nanosec */
+
+	/* Ignore errors that happenned a long time ago, these
+	 * are most likely false positive errors.
+	 */
+	if (cur_err > MSEC_TO_NSEC(10)) {
+		rng->prev_error = 0;
+		rng->prev_time = 0;
+		return 0;
+	}
+
+	if (rng->prev_error) {
+		/* Calculate time elapsed since last error
+		 * '1' tick of CNTVCT is 10ns, since it runs at 100Mhz.
+		 */
+		time_elapsed = (cur_time - rng->prev_time) * 10;
+		time_elapsed += rng->prev_error;
+
+		/* Check if current error is a new one or the old one itself.
+		 * If error is a new one then consider there is a persistent
+		 * issue with entropy, declare hardware failure.
+		 */
+		if (cur_err < time_elapsed) {
+			dev_err(&rng->pdev->dev, "HWRNG failure detected\n");
+			rng->prev_error = cur_err;
+			rng->prev_time = cur_time;
+			return -EIO;
+		}
+	}
+
+	rng->prev_error = cur_err;
+	rng->prev_time = cur_time;
+	return 0;
+}
+
+/* Read data from the RNG unit */
+static int cavium_rng_read(struct hwrng *rng, void *dat, size_t max, bool wait)
+{
+	struct cavium_rng *p = container_of(rng, struct cavium_rng, ops);
+	unsigned int size = max;
+	int err = 0;
+
+	err = check_rng_health(p);
+	if (err)
+		return err;
+
+	while (size >= 8) {
+		*((u64 *)dat) = readq(p->result);
+		size -= 8;
+		dat += 8;
+	}
+	while (size > 0) {
+		*((u8 *)dat) = readb(p->result);
+		size--;
+		dat++;
+	}
+	return max;
+}
+
+static int cavium_map_pf_regs(struct cavium_rng *rng)
+{
+	struct pci_dev *pdev;
+
+	/* Health status is not supported on 83xx, skip mapping PF CSRs */
+	if (is_octeontx(rng->pdev)) {
+		rng->pf_regbase = NULL;
+		return 0;
+	}
+
+	pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+			      PCI_DEVID_CAVIUM_RNG_PF, NULL);
+	if (!pdev) {
+		pr_err("Cannot find RNG PF device\n");
+		return -EIO;
+	}
+
+	rng->pf_regbase = ioremap(pci_resource_start(pdev, 0),
+				  pci_resource_len(pdev, 0));
+	if (!rng->pf_regbase) {
+		dev_err(&pdev->dev, "Failed to map PF CSR region\n");
+		pci_dev_put(pdev);
+		return -ENOMEM;
+	}
+
+	pci_dev_put(pdev);
+
+	/* Get co-processor clock rate */
+	rng->clock_rate = rng_get_coprocessor_clkrate();
+
+	return 0;
+}
+
+/* Map Cavium RNG to an HWRNG object */
+static int cavium_rng_probe_vf(struct	pci_dev		*pdev,
+			 const struct	pci_device_id	*id)
+{
+	struct	cavium_rng *rng;
+	int	ret;
+
+	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
+	if (!rng)
+		return -ENOMEM;
+
+	rng->pdev = pdev;
+
+	/* Map the RNG result */
+	rng->result = pcim_iomap(pdev, 0, 0);
+	if (!rng->result) {
+		dev_err(&pdev->dev, "Error iomap failed retrieving result.\n");
+		return -ENOMEM;
+	}
+
+	rng->ops.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+				       "cavium-rng-%s", dev_name(&pdev->dev));
+	if (!rng->ops.name)
+		return -ENOMEM;
+
+	rng->ops.read    = cavium_rng_read;
+
+	pci_set_drvdata(pdev, rng);
+
+	/* Health status is available only at PF, hence map PF registers. */
+	ret = cavium_map_pf_regs(rng);
+	if (ret)
+		return ret;
+
+	ret = devm_hwrng_register(&pdev->dev, &rng->ops);
+	if (ret) {
+		dev_err(&pdev->dev, "Error registering device as HWRNG.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+/* Remove the VF */
+static void cavium_rng_remove_vf(struct pci_dev *pdev)
+{
+	struct cavium_rng *rng;
+
+	rng = pci_get_drvdata(pdev);
+	iounmap(rng->pf_regbase);
+}
+
+static const struct pci_device_id cavium_rng_vf_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CAVIUM_RNG_VF) },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, cavium_rng_vf_id_table);
+
+static struct pci_driver cavium_rng_vf_driver = {
+	.name		= "cavium_rng_vf",
+	.id_table	= cavium_rng_vf_id_table,
+	.probe		= cavium_rng_probe_vf,
+	.remove		= cavium_rng_remove_vf,
+};
+module_pci_driver(cavium_rng_vf_driver);
+
+MODULE_AUTHOR("Omer Khaliq <okhaliq@caviumnetworks.com>");
+MODULE_LICENSE("GPL v2");