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, 284 insertions, 0 deletions

diff --git a/drivers/phy/intel/phy-intel-lgm-emmc.c b/drivers/phy/intel/phy-intel-lgm-emmc.c
new file mode 100644
index 000000000..703aeb122
--- /dev/null
+++ b/drivers/phy/intel/phy-intel-lgm-emmc.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel eMMC PHY driver
+ * Copyright (C) 2019 Intel, Corp.
+ */
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+/* eMMC phy register definitions */
+#define EMMC_PHYCTRL0_REG	0xa8
+#define DR_TY_MASK		GENMASK(30, 28)
+#define DR_TY_SHIFT(x)		(((x) << 28) & DR_TY_MASK)
+#define OTAPDLYENA		BIT(14)
+#define OTAPDLYSEL_MASK		GENMASK(13, 10)
+#define OTAPDLYSEL_SHIFT(x)	(((x) << 10) & OTAPDLYSEL_MASK)
+
+#define EMMC_PHYCTRL1_REG	0xac
+#define PDB_MASK		BIT(0)
+#define PDB_SHIFT(x)		(((x) << 0) & PDB_MASK)
+#define ENDLL_MASK		BIT(7)
+#define ENDLL_SHIFT(x)		(((x) << 7) & ENDLL_MASK)
+
+#define EMMC_PHYCTRL2_REG	0xb0
+#define FRQSEL_25M		0
+#define FRQSEL_50M		1
+#define FRQSEL_100M		2
+#define FRQSEL_150M		3
+#define FRQSEL_MASK		GENMASK(24, 22)
+#define FRQSEL_SHIFT(x)		(((x) << 22) & FRQSEL_MASK)
+
+#define EMMC_PHYSTAT_REG	0xbc
+#define CALDONE_MASK		BIT(9)
+#define DLLRDY_MASK		BIT(8)
+#define IS_CALDONE(x)	((x) & CALDONE_MASK)
+#define IS_DLLRDY(x)	((x) & DLLRDY_MASK)
+
+struct intel_emmc_phy {
+	struct regmap *syscfg;
+	struct clk *emmcclk;
+};
+
+static int intel_emmc_phy_power(struct phy *phy, bool on_off)
+{
+	struct intel_emmc_phy *priv = phy_get_drvdata(phy);
+	unsigned int caldone;
+	unsigned int dllrdy;
+	unsigned int freqsel;
+	unsigned long rate;
+	int ret, quot;
+
+	/*
+	 * Keep phyctrl_pdb and phyctrl_endll low to allow
+	 * initialization of CALIO state M/C DFFs
+	 */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL1_REG, PDB_MASK,
+				 PDB_SHIFT(0));
+	if (ret) {
+		dev_err(&phy->dev, "CALIO power down bar failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Already finish power_off above */
+	if (!on_off)
+		return 0;
+
+	rate = clk_get_rate(priv->emmcclk);
+	quot = DIV_ROUND_CLOSEST(rate, 50000000);
+	if (quot > FRQSEL_150M)
+		dev_warn(&phy->dev, "Unsupported rate: %lu\n", rate);
+	freqsel = clamp_t(int, quot, FRQSEL_25M, FRQSEL_150M);
+
+	/*
+	 * According to the user manual, calpad calibration
+	 * cycle takes more than 2us without the minimal recommended
+	 * value, so we may need a little margin here
+	 */
+	udelay(5);
+
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL1_REG, PDB_MASK,
+				 PDB_SHIFT(1));
+	if (ret) {
+		dev_err(&phy->dev, "CALIO power down bar failed: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * According to the user manual, it asks driver to wait 5us for
+	 * calpad busy trimming. However it is documented that this value is
+	 * PVT(A.K.A process,voltage and temperature) relevant, so some
+	 * failure cases are found which indicates we should be more tolerant
+	 * to calpad busy trimming.
+	 */
+	ret = regmap_read_poll_timeout(priv->syscfg, EMMC_PHYSTAT_REG,
+				       caldone, IS_CALDONE(caldone),
+				       0, 50);
+	if (ret) {
+		dev_err(&phy->dev, "caldone failed, ret=%d\n", ret);
+		return ret;
+	}
+
+	/* Set the frequency of the DLL operation */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL2_REG, FRQSEL_MASK,
+				 FRQSEL_SHIFT(freqsel));
+	if (ret) {
+		dev_err(&phy->dev, "set the frequency of dll failed:%d\n", ret);
+		return ret;
+	}
+
+	/* Turn on the DLL */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL1_REG, ENDLL_MASK,
+				 ENDLL_SHIFT(1));
+	if (ret) {
+		dev_err(&phy->dev, "turn on the dll failed: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * After enabling analog DLL circuits docs say that we need 10.2 us if
+	 * our source clock is at 50 MHz and that lock time scales linearly
+	 * with clock speed.  If we are powering on the PHY and the card clock
+	 * is super slow (like 100 kHZ) this could take as long as 5.1 ms as
+	 * per the math: 10.2 us * (50000000 Hz / 100000 Hz) => 5.1 ms
+	 * Hopefully we won't be running at 100 kHz, but we should still make
+	 * sure we wait long enough.
+	 *
+	 * NOTE: There appear to be corner cases where the DLL seems to take
+	 * extra long to lock for reasons that aren't understood.  In some
+	 * extreme cases we've seen it take up to over 10ms (!).  We'll be
+	 * generous and give it 50ms.
+	 */
+	ret = regmap_read_poll_timeout(priv->syscfg,
+				       EMMC_PHYSTAT_REG,
+				       dllrdy, IS_DLLRDY(dllrdy),
+				       0, 50 * USEC_PER_MSEC);
+	if (ret) {
+		dev_err(&phy->dev, "dllrdy failed. ret=%d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int intel_emmc_phy_init(struct phy *phy)
+{
+	struct intel_emmc_phy *priv = phy_get_drvdata(phy);
+
+	/*
+	 * We purposely get the clock here and not in probe to avoid the
+	 * circular dependency problem. We expect:
+	 * - PHY driver to probe
+	 * - SDHCI driver to start probe
+	 * - SDHCI driver to register it's clock
+	 * - SDHCI driver to get the PHY
+	 * - SDHCI driver to init the PHY
+	 *
+	 * The clock is optional, so upon any error just return it like
+	 * any other error to user.
+	 *
+	 */
+	priv->emmcclk = clk_get_optional(&phy->dev, "emmcclk");
+	if (IS_ERR(priv->emmcclk)) {
+		dev_err(&phy->dev, "ERROR: getting emmcclk\n");
+		return PTR_ERR(priv->emmcclk);
+	}
+
+	return 0;
+}
+
+static int intel_emmc_phy_exit(struct phy *phy)
+{
+	struct intel_emmc_phy *priv = phy_get_drvdata(phy);
+
+	clk_put(priv->emmcclk);
+
+	return 0;
+}
+
+static int intel_emmc_phy_power_on(struct phy *phy)
+{
+	struct intel_emmc_phy *priv = phy_get_drvdata(phy);
+	int ret;
+
+	/* Drive impedance: 50 Ohm */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL0_REG, DR_TY_MASK,
+				 DR_TY_SHIFT(6));
+	if (ret) {
+		dev_err(&phy->dev, "ERROR set drive-impednce-50ohm: %d\n", ret);
+		return ret;
+	}
+
+	/* Output tap delay: disable */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL0_REG, OTAPDLYENA,
+				 0);
+	if (ret) {
+		dev_err(&phy->dev, "ERROR Set output tap delay : %d\n", ret);
+		return ret;
+	}
+
+	/* Output tap delay */
+	ret = regmap_update_bits(priv->syscfg, EMMC_PHYCTRL0_REG,
+				 OTAPDLYSEL_MASK, OTAPDLYSEL_SHIFT(4));
+	if (ret) {
+		dev_err(&phy->dev, "ERROR: output tap dly select: %d\n", ret);
+		return ret;
+	}
+
+	/* Power up eMMC phy analog blocks */
+	return intel_emmc_phy_power(phy, true);
+}
+
+static int intel_emmc_phy_power_off(struct phy *phy)
+{
+	/* Power down eMMC phy analog blocks */
+	return intel_emmc_phy_power(phy, false);
+}
+
+static const struct phy_ops ops = {
+	.init		= intel_emmc_phy_init,
+	.exit		= intel_emmc_phy_exit,
+	.power_on	= intel_emmc_phy_power_on,
+	.power_off	= intel_emmc_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static int intel_emmc_phy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct intel_emmc_phy *priv;
+	struct phy *generic_phy;
+	struct phy_provider *phy_provider;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	/* Get eMMC phy (accessed via chiptop) regmap */
+	priv->syscfg = syscon_regmap_lookup_by_phandle(np, "intel,syscon");
+	if (IS_ERR(priv->syscfg)) {
+		dev_err(dev, "failed to find syscon\n");
+		return PTR_ERR(priv->syscfg);
+	}
+
+	generic_phy = devm_phy_create(dev, np, &ops);
+	if (IS_ERR(generic_phy)) {
+		dev_err(dev, "failed to create PHY\n");
+		return PTR_ERR(generic_phy);
+	}
+
+	phy_set_drvdata(generic_phy, priv);
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct of_device_id intel_emmc_phy_dt_ids[] = {
+	{ .compatible = "intel,lgm-emmc-phy" },
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, intel_emmc_phy_dt_ids);
+
+static struct platform_driver intel_emmc_driver = {
+	.probe		= intel_emmc_phy_probe,
+	.driver		= {
+		.name	= "intel-emmc-phy",
+		.of_match_table = intel_emmc_phy_dt_ids,
+	},
+};
+
+module_platform_driver(intel_emmc_driver);
+
+MODULE_AUTHOR("Peter Harliman Liem <peter.harliman.liem@intel.com>");
+MODULE_DESCRIPTION("Intel eMMC PHY driver");
+MODULE_LICENSE("GPL v2");