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, 329 insertions, 0 deletions

diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c
new file mode 100644
index 000000000..824cc1c03
--- /dev/null
+++ b/drivers/mtd/tests/mtd_nandecctest.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
+
+#include "mtd_test.h"
+
+/*
+ * Test the implementation for software ECC
+ *
+ * No actual MTD device is needed, So we don't need to warry about losing
+ * important data by human error.
+ *
+ * This covers possible patterns of corruption which can be reliably corrected
+ * or detected.
+ */
+
+#if IS_ENABLED(CONFIG_MTD_RAW_NAND)
+
+struct nand_ecc_test {
+	const char *name;
+	void (*prepare)(void *, void *, void *, void *, const size_t);
+	int (*verify)(void *, void *, void *, const size_t);
+};
+
+/*
+ * The reason for this __change_bit_le() instead of __change_bit() is to inject
+ * bit error properly within the region which is not a multiple of
+ * sizeof(unsigned long) on big-endian systems
+ */
+#ifdef __LITTLE_ENDIAN
+#define __change_bit_le(nr, addr) __change_bit(nr, addr)
+#elif defined(__BIG_ENDIAN)
+#define __change_bit_le(nr, addr) \
+		__change_bit((nr) ^ ((BITS_PER_LONG - 1) & ~0x7), addr)
+#else
+#error "Unknown byte order"
+#endif
+
+static void single_bit_error_data(void *error_data, void *correct_data,
+				size_t size)
+{
+	unsigned int offset = get_random_u32_below(size * BITS_PER_BYTE);
+
+	memcpy(error_data, correct_data, size);
+	__change_bit_le(offset, error_data);
+}
+
+static void double_bit_error_data(void *error_data, void *correct_data,
+				size_t size)
+{
+	unsigned int offset[2];
+
+	offset[0] = get_random_u32_below(size * BITS_PER_BYTE);
+	do {
+		offset[1] = get_random_u32_below(size * BITS_PER_BYTE);
+	} while (offset[0] == offset[1]);
+
+	memcpy(error_data, correct_data, size);
+
+	__change_bit_le(offset[0], error_data);
+	__change_bit_le(offset[1], error_data);
+}
+
+static unsigned int random_ecc_bit(size_t size)
+{
+	unsigned int offset = get_random_u32_below(3 * BITS_PER_BYTE);
+
+	if (size == 256) {
+		/*
+		 * Don't inject a bit error into the insignificant bits (16th
+		 * and 17th bit) in ECC code for 256 byte data block
+		 */
+		while (offset == 16 || offset == 17)
+			offset = get_random_u32_below(3 * BITS_PER_BYTE);
+	}
+
+	return offset;
+}
+
+static void single_bit_error_ecc(void *error_ecc, void *correct_ecc,
+				size_t size)
+{
+	unsigned int offset = random_ecc_bit(size);
+
+	memcpy(error_ecc, correct_ecc, 3);
+	__change_bit_le(offset, error_ecc);
+}
+
+static void double_bit_error_ecc(void *error_ecc, void *correct_ecc,
+				size_t size)
+{
+	unsigned int offset[2];
+
+	offset[0] = random_ecc_bit(size);
+	do {
+		offset[1] = random_ecc_bit(size);
+	} while (offset[0] == offset[1]);
+
+	memcpy(error_ecc, correct_ecc, 3);
+	__change_bit_le(offset[0], error_ecc);
+	__change_bit_le(offset[1], error_ecc);
+}
+
+static void no_bit_error(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	memcpy(error_data, correct_data, size);
+	memcpy(error_ecc, correct_ecc, 3);
+}
+
+static int no_bit_error_verify(void *error_data, void *error_ecc,
+				void *correct_data, const size_t size)
+{
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
+	unsigned char calc_ecc[3];
+	int ret;
+
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
+	if (ret == 0 && !memcmp(correct_data, error_data, size))
+		return 0;
+
+	return -EINVAL;
+}
+
+static void single_bit_error_in_data(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	single_bit_error_data(error_data, correct_data, size);
+	memcpy(error_ecc, correct_ecc, 3);
+}
+
+static void single_bit_error_in_ecc(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	memcpy(error_data, correct_data, size);
+	single_bit_error_ecc(error_ecc, correct_ecc, size);
+}
+
+static int single_bit_error_correct(void *error_data, void *error_ecc,
+				void *correct_data, const size_t size)
+{
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
+	unsigned char calc_ecc[3];
+	int ret;
+
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
+	if (ret == 1 && !memcmp(correct_data, error_data, size))
+		return 0;
+
+	return -EINVAL;
+}
+
+static void double_bit_error_in_data(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	double_bit_error_data(error_data, correct_data, size);
+	memcpy(error_ecc, correct_ecc, 3);
+}
+
+static void single_bit_error_in_data_and_ecc(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	single_bit_error_data(error_data, correct_data, size);
+	single_bit_error_ecc(error_ecc, correct_ecc, size);
+}
+
+static void double_bit_error_in_ecc(void *error_data, void *error_ecc,
+		void *correct_data, void *correct_ecc, const size_t size)
+{
+	memcpy(error_data, correct_data, size);
+	double_bit_error_ecc(error_ecc, correct_ecc, size);
+}
+
+static int double_bit_error_detect(void *error_data, void *error_ecc,
+				void *correct_data, const size_t size)
+{
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
+	unsigned char calc_ecc[3];
+	int ret;
+
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
+
+	return (ret == -EBADMSG) ? 0 : -EINVAL;
+}
+
+static const struct nand_ecc_test nand_ecc_test[] = {
+	{
+		.name = "no-bit-error",
+		.prepare = no_bit_error,
+		.verify = no_bit_error_verify,
+	},
+	{
+		.name = "single-bit-error-in-data-correct",
+		.prepare = single_bit_error_in_data,
+		.verify = single_bit_error_correct,
+	},
+	{
+		.name = "single-bit-error-in-ecc-correct",
+		.prepare = single_bit_error_in_ecc,
+		.verify = single_bit_error_correct,
+	},
+	{
+		.name = "double-bit-error-in-data-detect",
+		.prepare = double_bit_error_in_data,
+		.verify = double_bit_error_detect,
+	},
+	{
+		.name = "single-bit-error-in-data-and-ecc-detect",
+		.prepare = single_bit_error_in_data_and_ecc,
+		.verify = double_bit_error_detect,
+	},
+	{
+		.name = "double-bit-error-in-ecc-detect",
+		.prepare = double_bit_error_in_ecc,
+		.verify = double_bit_error_detect,
+	},
+};
+
+static void dump_data_ecc(void *error_data, void *error_ecc, void *correct_data,
+			void *correct_ecc, const size_t size)
+{
+	pr_info("hexdump of error data:\n");
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+			error_data, size, false);
+	print_hex_dump(KERN_INFO, "hexdump of error ecc: ",
+			DUMP_PREFIX_NONE, 16, 1, error_ecc, 3, false);
+
+	pr_info("hexdump of correct data:\n");
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+			correct_data, size, false);
+	print_hex_dump(KERN_INFO, "hexdump of correct ecc: ",
+			DUMP_PREFIX_NONE, 16, 1, correct_ecc, 3, false);
+}
+
+static int nand_ecc_test_run(const size_t size)
+{
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
+	int i;
+	int err = 0;
+	void *error_data;
+	void *error_ecc;
+	void *correct_data;
+	void *correct_ecc;
+
+	error_data = kmalloc(size, GFP_KERNEL);
+	error_ecc = kmalloc(3, GFP_KERNEL);
+	correct_data = kmalloc(size, GFP_KERNEL);
+	correct_ecc = kmalloc(3, GFP_KERNEL);
+
+	if (!error_data || !error_ecc || !correct_data || !correct_ecc) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	get_random_bytes(correct_data, size);
+	ecc_sw_hamming_calculate(correct_data, size, correct_ecc, sm_order);
+	for (i = 0; i < ARRAY_SIZE(nand_ecc_test); i++) {
+		nand_ecc_test[i].prepare(error_data, error_ecc,
+				correct_data, correct_ecc, size);
+		err = nand_ecc_test[i].verify(error_data, error_ecc,
+						correct_data, size);
+
+		if (err) {
+			pr_err("not ok - %s-%zd\n",
+				nand_ecc_test[i].name, size);
+			dump_data_ecc(error_data, error_ecc,
+				correct_data, correct_ecc, size);
+			break;
+		}
+		pr_info("ok - %s-%zd\n",
+			nand_ecc_test[i].name, size);
+
+		err = mtdtest_relax();
+		if (err)
+			break;
+	}
+error:
+	kfree(error_data);
+	kfree(error_ecc);
+	kfree(correct_data);
+	kfree(correct_ecc);
+
+	return err;
+}
+
+#else
+
+static int nand_ecc_test_run(const size_t size)
+{
+	return 0;
+}
+
+#endif
+
+static int __init ecc_test_init(void)
+{
+	int err;
+
+	err = nand_ecc_test_run(256);
+	if (err)
+		return err;
+
+	return nand_ecc_test_run(512);
+}
+
+static void __exit ecc_test_exit(void)
+{
+}
+
+module_init(ecc_test_init);
+module_exit(ecc_test_exit);
+
+MODULE_DESCRIPTION("NAND ECC function test module");
+MODULE_AUTHOR("Akinobu Mita");
+MODULE_LICENSE("GPL");