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, 338 insertions, 0 deletions

diff --git a/drivers/ptp/ptp_dte.c b/drivers/ptp/ptp_dte.c
new file mode 100644
index 000000000..7cc5a00e6
--- /dev/null
+++ b/drivers/ptp/ptp_dte.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2017 Broadcom
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/types.h>
+
+#define DTE_NCO_LOW_TIME_REG	0x00
+#define DTE_NCO_TIME_REG	0x04
+#define DTE_NCO_OVERFLOW_REG	0x08
+#define DTE_NCO_INC_REG		0x0c
+
+#define DTE_NCO_SUM2_MASK	0xffffffff
+#define DTE_NCO_SUM2_SHIFT	4ULL
+
+#define DTE_NCO_SUM3_MASK	0xff
+#define DTE_NCO_SUM3_SHIFT	36ULL
+#define DTE_NCO_SUM3_WR_SHIFT	8
+
+#define DTE_NCO_TS_WRAP_MASK	0xfff
+#define DTE_NCO_TS_WRAP_LSHIFT	32
+
+#define DTE_NCO_INC_DEFAULT	0x80000000
+#define DTE_NUM_REGS_TO_RESTORE	4
+
+/* Full wrap around is 44bits in ns (~4.887 hrs) */
+#define DTE_WRAP_AROUND_NSEC_SHIFT 44
+
+/* 44 bits NCO */
+#define DTE_NCO_MAX_NS	0xFFFFFFFFFFFLL
+
+/* 125MHz with 3.29 reg cfg */
+#define DTE_PPB_ADJ(ppb) (u32)(div64_u64((((u64)abs(ppb) * BIT(28)) +\
+				      62500000ULL), 125000000ULL))
+
+/* ptp dte priv structure */
+struct ptp_dte {
+	void __iomem *regs;
+	struct ptp_clock *ptp_clk;
+	struct ptp_clock_info caps;
+	struct device *dev;
+	u32 ts_ovf_last;
+	u32 ts_wrap_cnt;
+	spinlock_t lock;
+	u32 reg_val[DTE_NUM_REGS_TO_RESTORE];
+};
+
+static void dte_write_nco(void __iomem *regs, s64 ns)
+{
+	u32 sum2, sum3;
+
+	sum2 = (u32)((ns >> DTE_NCO_SUM2_SHIFT) & DTE_NCO_SUM2_MASK);
+	/* compensate for ignoring sum1 */
+	if (sum2 != DTE_NCO_SUM2_MASK)
+		sum2++;
+
+	/* to write sum3, bits [15:8] needs to be written */
+	sum3 = (u32)(((ns >> DTE_NCO_SUM3_SHIFT) & DTE_NCO_SUM3_MASK) <<
+		     DTE_NCO_SUM3_WR_SHIFT);
+
+	writel(0, (regs + DTE_NCO_LOW_TIME_REG));
+	writel(sum2, (regs + DTE_NCO_TIME_REG));
+	writel(sum3, (regs + DTE_NCO_OVERFLOW_REG));
+}
+
+static s64 dte_read_nco(void __iomem *regs)
+{
+	u32 sum2, sum3;
+	s64 ns;
+
+	/*
+	 * ignoring sum1 (4 bits) gives a 16ns resolution, which
+	 * works due to the async register read.
+	 */
+	sum3 = readl(regs + DTE_NCO_OVERFLOW_REG) & DTE_NCO_SUM3_MASK;
+	sum2 = readl(regs + DTE_NCO_TIME_REG);
+	ns = ((s64)sum3 << DTE_NCO_SUM3_SHIFT) |
+		 ((s64)sum2 << DTE_NCO_SUM2_SHIFT);
+
+	return ns;
+}
+
+static void dte_write_nco_delta(struct ptp_dte *ptp_dte, s64 delta)
+{
+	s64 ns;
+
+	ns = dte_read_nco(ptp_dte->regs);
+
+	/* handle wraparound conditions */
+	if ((delta < 0) && (abs(delta) > ns)) {
+		if (ptp_dte->ts_wrap_cnt) {
+			ns += DTE_NCO_MAX_NS + delta;
+			ptp_dte->ts_wrap_cnt--;
+		} else {
+			ns = 0;
+		}
+	} else {
+		ns += delta;
+		if (ns > DTE_NCO_MAX_NS) {
+			ptp_dte->ts_wrap_cnt++;
+			ns -= DTE_NCO_MAX_NS;
+		}
+	}
+
+	dte_write_nco(ptp_dte->regs, ns);
+
+	ptp_dte->ts_ovf_last = (ns >> DTE_NCO_TS_WRAP_LSHIFT) &
+			DTE_NCO_TS_WRAP_MASK;
+}
+
+static s64 dte_read_nco_with_ovf(struct ptp_dte *ptp_dte)
+{
+	u32 ts_ovf;
+	s64 ns = 0;
+
+	ns = dte_read_nco(ptp_dte->regs);
+
+	/*Timestamp overflow: 8 LSB bits of sum3, 4 MSB bits of sum2 */
+	ts_ovf = (ns >> DTE_NCO_TS_WRAP_LSHIFT) & DTE_NCO_TS_WRAP_MASK;
+
+	/* Check for wrap around */
+	if (ts_ovf < ptp_dte->ts_ovf_last)
+		ptp_dte->ts_wrap_cnt++;
+
+	ptp_dte->ts_ovf_last = ts_ovf;
+
+	/* adjust for wraparounds */
+	ns += (s64)(BIT_ULL(DTE_WRAP_AROUND_NSEC_SHIFT) * ptp_dte->ts_wrap_cnt);
+
+	return ns;
+}
+
+static int ptp_dte_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	s32 ppb = scaled_ppm_to_ppb(scaled_ppm);
+	u32 nco_incr;
+	unsigned long flags;
+	struct ptp_dte *ptp_dte = container_of(ptp, struct ptp_dte, caps);
+
+	if (abs(ppb) > ptp_dte->caps.max_adj) {
+		dev_err(ptp_dte->dev, "ppb adj too big\n");
+		return -EINVAL;
+	}
+
+	if (ppb < 0)
+		nco_incr = DTE_NCO_INC_DEFAULT - DTE_PPB_ADJ(ppb);
+	else
+		nco_incr = DTE_NCO_INC_DEFAULT + DTE_PPB_ADJ(ppb);
+
+	spin_lock_irqsave(&ptp_dte->lock, flags);
+	writel(nco_incr, ptp_dte->regs + DTE_NCO_INC_REG);
+	spin_unlock_irqrestore(&ptp_dte->lock, flags);
+
+	return 0;
+}
+
+static int ptp_dte_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	unsigned long flags;
+	struct ptp_dte *ptp_dte = container_of(ptp, struct ptp_dte, caps);
+
+	spin_lock_irqsave(&ptp_dte->lock, flags);
+	dte_write_nco_delta(ptp_dte, delta);
+	spin_unlock_irqrestore(&ptp_dte->lock, flags);
+
+	return 0;
+}
+
+static int ptp_dte_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	unsigned long flags;
+	struct ptp_dte *ptp_dte = container_of(ptp, struct ptp_dte, caps);
+
+	spin_lock_irqsave(&ptp_dte->lock, flags);
+	*ts = ns_to_timespec64(dte_read_nco_with_ovf(ptp_dte));
+	spin_unlock_irqrestore(&ptp_dte->lock, flags);
+
+	return 0;
+}
+
+static int ptp_dte_settime(struct ptp_clock_info *ptp,
+			     const struct timespec64 *ts)
+{
+	unsigned long flags;
+	struct ptp_dte *ptp_dte = container_of(ptp, struct ptp_dte, caps);
+
+	spin_lock_irqsave(&ptp_dte->lock, flags);
+
+	/* Disable nco increment */
+	writel(0, ptp_dte->regs + DTE_NCO_INC_REG);
+
+	dte_write_nco(ptp_dte->regs, timespec64_to_ns(ts));
+
+	/* reset overflow and wrap counter */
+	ptp_dte->ts_ovf_last = 0;
+	ptp_dte->ts_wrap_cnt = 0;
+
+	/* Enable nco increment */
+	writel(DTE_NCO_INC_DEFAULT, ptp_dte->regs + DTE_NCO_INC_REG);
+
+	spin_unlock_irqrestore(&ptp_dte->lock, flags);
+
+	return 0;
+}
+
+static int ptp_dte_enable(struct ptp_clock_info *ptp,
+			    struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct ptp_clock_info ptp_dte_caps = {
+	.owner		= THIS_MODULE,
+	.name		= "DTE PTP timer",
+	.max_adj	= 50000000,
+	.n_ext_ts	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.adjfine	= ptp_dte_adjfine,
+	.adjtime	= ptp_dte_adjtime,
+	.gettime64	= ptp_dte_gettime,
+	.settime64	= ptp_dte_settime,
+	.enable		= ptp_dte_enable,
+};
+
+static int ptp_dte_probe(struct platform_device *pdev)
+{
+	struct ptp_dte *ptp_dte;
+	struct device *dev = &pdev->dev;
+
+	ptp_dte = devm_kzalloc(dev, sizeof(struct ptp_dte), GFP_KERNEL);
+	if (!ptp_dte)
+		return -ENOMEM;
+
+	ptp_dte->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ptp_dte->regs))
+		return PTR_ERR(ptp_dte->regs);
+
+	spin_lock_init(&ptp_dte->lock);
+
+	ptp_dte->dev = dev;
+	ptp_dte->caps = ptp_dte_caps;
+	ptp_dte->ptp_clk = ptp_clock_register(&ptp_dte->caps, &pdev->dev);
+	if (IS_ERR(ptp_dte->ptp_clk)) {
+		dev_err(dev,
+			"%s: Failed to register ptp clock\n", __func__);
+		return PTR_ERR(ptp_dte->ptp_clk);
+	}
+
+	platform_set_drvdata(pdev, ptp_dte);
+
+	dev_info(dev, "ptp clk probe done\n");
+
+	return 0;
+}
+
+static int ptp_dte_remove(struct platform_device *pdev)
+{
+	struct ptp_dte *ptp_dte = platform_get_drvdata(pdev);
+	u8 i;
+
+	ptp_clock_unregister(ptp_dte->ptp_clk);
+
+	for (i = 0; i < DTE_NUM_REGS_TO_RESTORE; i++)
+		writel(0, ptp_dte->regs + (i * sizeof(u32)));
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int ptp_dte_suspend(struct device *dev)
+{
+	struct ptp_dte *ptp_dte = dev_get_drvdata(dev);
+	u8 i;
+
+	for (i = 0; i < DTE_NUM_REGS_TO_RESTORE; i++) {
+		ptp_dte->reg_val[i] =
+			readl(ptp_dte->regs + (i * sizeof(u32)));
+	}
+
+	/* disable the nco */
+	writel(0, ptp_dte->regs + DTE_NCO_INC_REG);
+
+	return 0;
+}
+
+static int ptp_dte_resume(struct device *dev)
+{
+	struct ptp_dte *ptp_dte = dev_get_drvdata(dev);
+	u8 i;
+
+	for (i = 0; i < DTE_NUM_REGS_TO_RESTORE; i++) {
+		if ((i * sizeof(u32)) != DTE_NCO_OVERFLOW_REG)
+			writel(ptp_dte->reg_val[i],
+				(ptp_dte->regs + (i * sizeof(u32))));
+		else
+			writel(((ptp_dte->reg_val[i] &
+				DTE_NCO_SUM3_MASK) << DTE_NCO_SUM3_WR_SHIFT),
+				(ptp_dte->regs + (i * sizeof(u32))));
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops ptp_dte_pm_ops = {
+	.suspend = ptp_dte_suspend,
+	.resume = ptp_dte_resume
+};
+
+#define PTP_DTE_PM_OPS	(&ptp_dte_pm_ops)
+#else
+#define PTP_DTE_PM_OPS	NULL
+#endif
+
+static const struct of_device_id ptp_dte_of_match[] = {
+	{ .compatible = "brcm,ptp-dte", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ptp_dte_of_match);
+
+static struct platform_driver ptp_dte_driver = {
+	.driver = {
+		.name = "ptp-dte",
+		.pm = PTP_DTE_PM_OPS,
+		.of_match_table = ptp_dte_of_match,
+	},
+	.probe    = ptp_dte_probe,
+	.remove   = ptp_dte_remove,
+};
+module_platform_driver(ptp_dte_driver);
+
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Broadcom DTE PTP Clock driver");
+MODULE_LICENSE("GPL v2");