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, 341 insertions, 0 deletions

diff --git a/drivers/crypto/hisilicon/trng/trng.c b/drivers/crypto/hisilicon/trng/trng.c
new file mode 100644
index 000000000..97e500db0
--- /dev/null
+++ b/drivers/crypto/hisilicon/trng/trng.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 HiSilicon Limited. */
+
+#include <linux/acpi.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/random.h>
+#include <crypto/internal/rng.h>
+
+#define HISI_TRNG_REG		0x00F0
+#define HISI_TRNG_BYTES		4
+#define HISI_TRNG_QUALITY	512
+#define HISI_TRNG_VERSION	0x01B8
+#define HISI_TRNG_VER_V1	GENMASK(31, 0)
+#define SLEEP_US		10
+#define TIMEOUT_US		10000
+#define SW_DRBG_NUM_SHIFT	2
+#define SW_DRBG_KEY_BASE	0x082C
+#define SW_DRBG_SEED(n)         (SW_DRBG_KEY_BASE - ((n) << SW_DRBG_NUM_SHIFT))
+#define SW_DRBG_SEED_REGS_NUM	12
+#define SW_DRBG_SEED_SIZE	48
+#define SW_DRBG_BLOCKS		0x0830
+#define SW_DRBG_INIT		0x0834
+#define SW_DRBG_GEN		0x083c
+#define SW_DRBG_STATUS		0x0840
+#define SW_DRBG_BLOCKS_NUM	4095
+#define SW_DRBG_DATA_BASE	0x0850
+#define SW_DRBG_DATA_NUM	4
+#define SW_DRBG_DATA(n)		(SW_DRBG_DATA_BASE - ((n) << SW_DRBG_NUM_SHIFT))
+#define SW_DRBG_BYTES		16
+#define SW_DRBG_ENABLE_SHIFT	12
+#define SEED_SHIFT_24		24
+#define SEED_SHIFT_16		16
+#define SEED_SHIFT_8		8
+
+struct hisi_trng_list {
+	struct mutex lock;
+	struct list_head list;
+	bool is_init;
+};
+
+struct hisi_trng {
+	void __iomem *base;
+	struct hisi_trng_list *trng_list;
+	struct list_head list;
+	struct hwrng rng;
+	u32 ver;
+	bool is_used;
+	struct mutex mutex;
+};
+
+struct hisi_trng_ctx {
+	struct hisi_trng *trng;
+};
+
+static atomic_t trng_active_devs;
+static struct hisi_trng_list trng_devices;
+
+static void hisi_trng_set_seed(struct hisi_trng *trng, const u8 *seed)
+{
+	u32 val, seed_reg, i;
+
+	for (i = 0; i < SW_DRBG_SEED_SIZE;
+	     i += SW_DRBG_SEED_SIZE / SW_DRBG_SEED_REGS_NUM) {
+		val = seed[i] << SEED_SHIFT_24;
+		val |= seed[i + 1UL] << SEED_SHIFT_16;
+		val |= seed[i + 2UL] << SEED_SHIFT_8;
+		val |= seed[i + 3UL];
+
+		seed_reg = (i >> SW_DRBG_NUM_SHIFT) % SW_DRBG_SEED_REGS_NUM;
+		writel(val, trng->base + SW_DRBG_SEED(seed_reg));
+	}
+}
+
+static int hisi_trng_seed(struct crypto_rng *tfm, const u8 *seed,
+			  unsigned int slen)
+{
+	struct hisi_trng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct hisi_trng *trng = ctx->trng;
+	u32 val = 0;
+	int ret = 0;
+
+	if (slen < SW_DRBG_SEED_SIZE) {
+		pr_err("slen(%u) is not matched with trng(%d)\n", slen,
+			SW_DRBG_SEED_SIZE);
+		return -EINVAL;
+	}
+
+	writel(0x0, trng->base + SW_DRBG_BLOCKS);
+	hisi_trng_set_seed(trng, seed);
+
+	writel(SW_DRBG_BLOCKS_NUM | (0x1 << SW_DRBG_ENABLE_SHIFT),
+	       trng->base + SW_DRBG_BLOCKS);
+	writel(0x1, trng->base + SW_DRBG_INIT);
+
+	ret = readl_relaxed_poll_timeout(trng->base + SW_DRBG_STATUS,
+					val, val & BIT(0), SLEEP_US, TIMEOUT_US);
+	if (ret)
+		pr_err("fail to init trng(%d)\n", ret);
+
+	return ret;
+}
+
+static int hisi_trng_generate(struct crypto_rng *tfm, const u8 *src,
+			      unsigned int slen, u8 *dstn, unsigned int dlen)
+{
+	struct hisi_trng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct hisi_trng *trng = ctx->trng;
+	u32 data[SW_DRBG_DATA_NUM];
+	u32 currsize = 0;
+	u32 val = 0;
+	int ret;
+	u32 i;
+
+	if (dlen > SW_DRBG_BLOCKS_NUM * SW_DRBG_BYTES || dlen == 0) {
+		pr_err("dlen(%d) exceeds limit(%d)!\n", dlen,
+			SW_DRBG_BLOCKS_NUM * SW_DRBG_BYTES);
+		return -EINVAL;
+	}
+
+	do {
+		ret = readl_relaxed_poll_timeout(trng->base + SW_DRBG_STATUS,
+		     val, val & BIT(1), SLEEP_US, TIMEOUT_US);
+		if (ret) {
+			pr_err("fail to generate random number(%d)!\n", ret);
+			break;
+		}
+
+		for (i = 0; i < SW_DRBG_DATA_NUM; i++)
+			data[i] = readl(trng->base + SW_DRBG_DATA(i));
+
+		if (dlen - currsize >= SW_DRBG_BYTES) {
+			memcpy(dstn + currsize, data, SW_DRBG_BYTES);
+			currsize += SW_DRBG_BYTES;
+		} else {
+			memcpy(dstn + currsize, data, dlen - currsize);
+			currsize = dlen;
+		}
+
+		writel(0x1, trng->base + SW_DRBG_GEN);
+	} while (currsize < dlen);
+
+	return ret;
+}
+
+static int hisi_trng_init(struct crypto_tfm *tfm)
+{
+	struct hisi_trng_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct hisi_trng *trng;
+	int ret = -EBUSY;
+
+	mutex_lock(&trng_devices.lock);
+	list_for_each_entry(trng, &trng_devices.list, list) {
+		if (!trng->is_used) {
+			trng->is_used = true;
+			ctx->trng = trng;
+			ret = 0;
+			break;
+		}
+	}
+	mutex_unlock(&trng_devices.lock);
+
+	return ret;
+}
+
+static void hisi_trng_exit(struct crypto_tfm *tfm)
+{
+	struct hisi_trng_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mutex_lock(&trng_devices.lock);
+	ctx->trng->is_used = false;
+	mutex_unlock(&trng_devices.lock);
+}
+
+static int hisi_trng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct hisi_trng *trng;
+	int currsize = 0;
+	u32 val = 0;
+	int ret;
+
+	trng = container_of(rng, struct hisi_trng, rng);
+
+	do {
+		ret = readl_poll_timeout(trng->base + HISI_TRNG_REG, val,
+					 val, SLEEP_US, TIMEOUT_US);
+		if (ret)
+			return currsize;
+
+		if (max - currsize >= HISI_TRNG_BYTES) {
+			memcpy(buf + currsize, &val, HISI_TRNG_BYTES);
+			currsize += HISI_TRNG_BYTES;
+			if (currsize == max)
+				return currsize;
+			continue;
+		}
+
+		/* copy remaining bytes */
+		memcpy(buf + currsize, &val, max - currsize);
+		currsize = max;
+	} while (currsize < max);
+
+	return currsize;
+}
+
+static struct rng_alg hisi_trng_alg = {
+	.generate = hisi_trng_generate,
+	.seed =	hisi_trng_seed,
+	.seedsize = SW_DRBG_SEED_SIZE,
+	.base = {
+		.cra_name = "stdrng",
+		.cra_driver_name = "hisi_stdrng",
+		.cra_priority = 300,
+		.cra_ctxsize = sizeof(struct hisi_trng_ctx),
+		.cra_module = THIS_MODULE,
+		.cra_init = hisi_trng_init,
+		.cra_exit = hisi_trng_exit,
+	},
+};
+
+static void hisi_trng_add_to_list(struct hisi_trng *trng)
+{
+	mutex_lock(&trng_devices.lock);
+	list_add_tail(&trng->list, &trng_devices.list);
+	mutex_unlock(&trng_devices.lock);
+}
+
+static int hisi_trng_del_from_list(struct hisi_trng *trng)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&trng_devices.lock);
+	if (!trng->is_used) {
+		list_del(&trng->list);
+		ret = 0;
+	}
+	mutex_unlock(&trng_devices.lock);
+
+	return ret;
+}
+
+static int hisi_trng_probe(struct platform_device *pdev)
+{
+	struct hisi_trng *trng;
+	int ret;
+
+	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
+	if (!trng)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, trng);
+
+	trng->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(trng->base))
+		return PTR_ERR(trng->base);
+
+	trng->is_used = false;
+	trng->ver = readl(trng->base + HISI_TRNG_VERSION);
+	if (!trng_devices.is_init) {
+		INIT_LIST_HEAD(&trng_devices.list);
+		mutex_init(&trng_devices.lock);
+		trng_devices.is_init = true;
+	}
+
+	hisi_trng_add_to_list(trng);
+	if (trng->ver != HISI_TRNG_VER_V1 &&
+	    atomic_inc_return(&trng_active_devs) == 1) {
+		ret = crypto_register_rng(&hisi_trng_alg);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"failed to register crypto(%d)\n", ret);
+			atomic_dec_return(&trng_active_devs);
+			goto err_remove_from_list;
+		}
+	}
+
+	trng->rng.name = pdev->name;
+	trng->rng.read = hisi_trng_read;
+	trng->rng.quality = HISI_TRNG_QUALITY;
+	ret = devm_hwrng_register(&pdev->dev, &trng->rng);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register hwrng: %d!\n", ret);
+		goto err_crypto_unregister;
+	}
+
+	return ret;
+
+err_crypto_unregister:
+	if (trng->ver != HISI_TRNG_VER_V1 &&
+	    atomic_dec_return(&trng_active_devs) == 0)
+		crypto_unregister_rng(&hisi_trng_alg);
+
+err_remove_from_list:
+	hisi_trng_del_from_list(trng);
+	return ret;
+}
+
+static int hisi_trng_remove(struct platform_device *pdev)
+{
+	struct hisi_trng *trng = platform_get_drvdata(pdev);
+
+	/* Wait until the task is finished */
+	while (hisi_trng_del_from_list(trng))
+		;
+
+	if (trng->ver != HISI_TRNG_VER_V1 &&
+	    atomic_dec_return(&trng_active_devs) == 0)
+		crypto_unregister_rng(&hisi_trng_alg);
+
+	return 0;
+}
+
+static const struct acpi_device_id hisi_trng_acpi_match[] = {
+	{ "HISI02B3", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, hisi_trng_acpi_match);
+
+static struct platform_driver hisi_trng_driver = {
+	.probe		= hisi_trng_probe,
+	.remove         = hisi_trng_remove,
+	.driver		= {
+		.name	= "hisi-trng-v2",
+		.acpi_match_table = ACPI_PTR(hisi_trng_acpi_match),
+	},
+};
+
+module_platform_driver(hisi_trng_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Weili Qian <qianweili@huawei.com>");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>");
+MODULE_DESCRIPTION("HiSilicon true random number generator V2 driver");