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, 351 insertions, 0 deletions

diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
new file mode 100644
index 000000000..6e4ef7af2
--- /dev/null
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* PTP 1588 clock using the Renesas Ethernet AVB
+ *
+ * Copyright (C) 2013-2015 Renesas Electronics Corporation
+ * Copyright (C) 2015 Renesas Solutions Corp.
+ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com>
+ */
+
+#include "ravb.h"
+
+static int ravb_ptp_tcr_request(struct ravb_private *priv, u32 request)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+
+	error = ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+	if (error)
+		return error;
+
+	ravb_modify(ndev, GCCR, request, request);
+	return ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_time_read(struct ravb_private *priv, struct timespec64 *ts)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+
+	error = ravb_ptp_tcr_request(priv, GCCR_TCR_CAPTURE);
+	if (error)
+		return error;
+
+	ts->tv_nsec = ravb_read(ndev, GCT0);
+	ts->tv_sec  = ravb_read(ndev, GCT1) |
+		((s64)ravb_read(ndev, GCT2) << 32);
+
+	return 0;
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_time_write(struct ravb_private *priv,
+				const struct timespec64 *ts)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+	u32 gccr;
+
+	error = ravb_ptp_tcr_request(priv, GCCR_TCR_RESET);
+	if (error)
+		return error;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LTO)
+		return -EBUSY;
+	ravb_write(ndev, ts->tv_nsec, GTO0);
+	ravb_write(ndev, ts->tv_sec,  GTO1);
+	ravb_write(ndev, (ts->tv_sec >> 32) & 0xffff, GTO2);
+	ravb_write(ndev, gccr | GCCR_LTO, GCCR);
+
+	return 0;
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_update_compare(struct ravb_private *priv, u32 ns)
+{
+	struct net_device *ndev = priv->ndev;
+	/* When the comparison value (GPTC.PTCV) is in range of
+	 * [x-1 to x+1] (x is the configured increment value in
+	 * GTI.TIV), it may happen that a comparison match is
+	 * not detected when the timer wraps around.
+	 */
+	u32 gti_ns_plus_1 = (priv->ptp.current_addend >> 20) + 1;
+	u32 gccr;
+
+	if (ns < gti_ns_plus_1)
+		ns = gti_ns_plus_1;
+	else if (ns > 0 - gti_ns_plus_1)
+		ns = 0 - gti_ns_plus_1;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LPTC)
+		return -EBUSY;
+	ravb_write(ndev, ns, GPTC);
+	ravb_write(ndev, gccr | GCCR_LPTC, GCCR);
+
+	return 0;
+}
+
+/* PTP clock operations */
+static int ravb_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct net_device *ndev = priv->ndev;
+	unsigned long flags;
+	u32 addend;
+	u32 gccr;
+
+	addend = (u32)adjust_by_scaled_ppm(priv->ptp.default_addend,
+					   scaled_ppm);
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->ptp.current_addend = addend;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LTI) {
+		spin_unlock_irqrestore(&priv->lock, flags);
+		return -EBUSY;
+	}
+	ravb_write(ndev, addend & GTI_TIV, GTI);
+	ravb_write(ndev, gccr | GCCR_LTI, GCCR);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int ravb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct timespec64 ts;
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_read(priv, &ts);
+	if (!error) {
+		u64 now = ktime_to_ns(timespec64_to_ktime(ts));
+
+		ts = ns_to_timespec64(now + delta);
+		error = ravb_ptp_time_write(priv, &ts);
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_read(priv, ts);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_settime64(struct ptp_clock_info *ptp,
+			      const struct timespec64 *ts)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_write(priv, ts);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_extts(struct ptp_clock_info *ptp,
+			  struct ptp_extts_request *req, int on)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	const struct ravb_hw_info *info = priv->info;
+	struct net_device *ndev = priv->ndev;
+	unsigned long flags;
+
+	/* Reject requests with unsupported flags */
+	if (req->flags & ~(PTP_ENABLE_FEATURE |
+			   PTP_RISING_EDGE |
+			   PTP_FALLING_EDGE |
+			   PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
+	if (req->index)
+		return -EINVAL;
+
+	if (priv->ptp.extts[req->index] == on)
+		return 0;
+	priv->ptp.extts[req->index] = on;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (!info->irq_en_dis)
+		ravb_modify(ndev, GIC, GIC_PTCE, on ? GIC_PTCE : 0);
+	else if (on)
+		ravb_write(ndev, GIE_PTCS, GIE);
+	else
+		ravb_write(ndev, GID_PTCD, GID);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int ravb_ptp_perout(struct ptp_clock_info *ptp,
+			   struct ptp_perout_request *req, int on)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	const struct ravb_hw_info *info = priv->info;
+	struct net_device *ndev = priv->ndev;
+	struct ravb_ptp_perout *perout;
+	unsigned long flags;
+	int error = 0;
+
+	/* Reject requests with unsupported flags */
+	if (req->flags)
+		return -EOPNOTSUPP;
+
+	if (req->index)
+		return -EINVAL;
+
+	if (on) {
+		u64 start_ns;
+		u64 period_ns;
+
+		start_ns = req->start.sec * NSEC_PER_SEC + req->start.nsec;
+		period_ns = req->period.sec * NSEC_PER_SEC + req->period.nsec;
+
+		if (start_ns > U32_MAX) {
+			netdev_warn(ndev,
+				    "ptp: start value (nsec) is over limit. Maximum size of start is only 32 bits\n");
+			return -ERANGE;
+		}
+
+		if (period_ns > U32_MAX) {
+			netdev_warn(ndev,
+				    "ptp: period value (nsec) is over limit. Maximum size of period is only 32 bits\n");
+			return -ERANGE;
+		}
+
+		spin_lock_irqsave(&priv->lock, flags);
+
+		perout = &priv->ptp.perout[req->index];
+		perout->target = (u32)start_ns;
+		perout->period = (u32)period_ns;
+		error = ravb_ptp_update_compare(priv, (u32)start_ns);
+		if (!error) {
+			/* Unmask interrupt */
+			if (!info->irq_en_dis)
+				ravb_modify(ndev, GIC, GIC_PTME, GIC_PTME);
+			else
+				ravb_write(ndev, GIE_PTMS0, GIE);
+		}
+	} else	{
+		spin_lock_irqsave(&priv->lock, flags);
+
+		perout = &priv->ptp.perout[req->index];
+		perout->period = 0;
+
+		/* Mask interrupt */
+		if (!info->irq_en_dis)
+			ravb_modify(ndev, GIC, GIC_PTME, 0);
+		else
+			ravb_write(ndev, GID_PTMD0, GID);
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_enable(struct ptp_clock_info *ptp,
+			   struct ptp_clock_request *req, int on)
+{
+	switch (req->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return ravb_ptp_extts(ptp, &req->extts, on);
+	case PTP_CLK_REQ_PEROUT:
+		return ravb_ptp_perout(ptp, &req->perout, on);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct ptp_clock_info ravb_ptp_info = {
+	.owner		= THIS_MODULE,
+	.name		= "ravb clock",
+	.max_adj	= 50000000,
+	.n_ext_ts	= N_EXT_TS,
+	.n_per_out	= N_PER_OUT,
+	.adjfine	= ravb_ptp_adjfine,
+	.adjtime	= ravb_ptp_adjtime,
+	.gettime64	= ravb_ptp_gettime64,
+	.settime64	= ravb_ptp_settime64,
+	.enable		= ravb_ptp_enable,
+};
+
+/* Caller must hold the lock */
+void ravb_ptp_interrupt(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 gis = ravb_read(ndev, GIS);
+
+	gis &= ravb_read(ndev, GIC);
+	if (gis & GIS_PTCF) {
+		struct ptp_clock_event event;
+
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = 0;
+		event.timestamp = ravb_read(ndev, GCPT);
+		ptp_clock_event(priv->ptp.clock, &event);
+	}
+	if (gis & GIS_PTMF) {
+		struct ravb_ptp_perout *perout = priv->ptp.perout;
+
+		if (perout->period) {
+			perout->target += perout->period;
+			ravb_ptp_update_compare(priv, perout->target);
+		}
+	}
+
+	ravb_write(ndev, ~(gis | GIS_RESERVED), GIS);
+}
+
+void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	priv->ptp.info = ravb_ptp_info;
+
+	priv->ptp.default_addend = ravb_read(ndev, GTI);
+	priv->ptp.current_addend = priv->ptp.default_addend;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+	ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev);
+}
+
+void ravb_ptp_stop(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	ravb_write(ndev, 0, GIC);
+	ravb_write(ndev, 0, GIS);
+
+	ptp_clock_unregister(priv->ptp.clock);
+}