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, 368 insertions, 0 deletions

diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c
new file mode 100644
index 000000000..33856abd5
--- /dev/null
+++ b/drivers/soc/qcom/cmd-db.c
@@ -0,0 +1,368 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2016-2018, 2020, The Linux Foundation. All rights reserved. */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/types.h>
+
+#include <soc/qcom/cmd-db.h>
+
+#define NUM_PRIORITY		2
+#define MAX_SLV_ID		8
+#define SLAVE_ID_MASK		0x7
+#define SLAVE_ID_SHIFT		16
+
+/**
+ * struct entry_header: header for each entry in cmddb
+ *
+ * @id: resource's identifier
+ * @priority: unused
+ * @addr: the address of the resource
+ * @len: length of the data
+ * @offset: offset from :@data_offset, start of the data
+ */
+struct entry_header {
+	u8 id[8];
+	__le32 priority[NUM_PRIORITY];
+	__le32 addr;
+	__le16 len;
+	__le16 offset;
+};
+
+/**
+ * struct rsc_hdr: resource header information
+ *
+ * @slv_id: id for the resource
+ * @header_offset: entry's header at offset from the end of the cmd_db_header
+ * @data_offset: entry's data at offset from the end of the cmd_db_header
+ * @cnt: number of entries for HW type
+ * @version: MSB is major, LSB is minor
+ * @reserved: reserved for future use.
+ */
+struct rsc_hdr {
+	__le16 slv_id;
+	__le16 header_offset;
+	__le16 data_offset;
+	__le16 cnt;
+	__le16 version;
+	__le16 reserved[3];
+};
+
+/**
+ * struct cmd_db_header: The DB header information
+ *
+ * @version: The cmd db version
+ * @magic: constant expected in the database
+ * @header: array of resources
+ * @checksum: checksum for the header. Unused.
+ * @reserved: reserved memory
+ * @data: driver specific data
+ */
+struct cmd_db_header {
+	__le32 version;
+	u8 magic[4];
+	struct rsc_hdr header[MAX_SLV_ID];
+	__le32 checksum;
+	__le32 reserved;
+	u8 data[];
+};
+
+/**
+ * DOC: Description of the Command DB database.
+ *
+ * At the start of the command DB memory is the cmd_db_header structure.
+ * The cmd_db_header holds the version, checksum, magic key as well as an
+ * array for header for each slave (depicted by the rsc_header). Each h/w
+ * based accelerator is a 'slave' (shared resource) and has slave id indicating
+ * the type of accelerator. The rsc_header is the header for such individual
+ * slaves of a given type. The entries for each of these slaves begin at the
+ * rsc_hdr.header_offset. In addition each slave could have auxiliary data
+ * that may be needed by the driver. The data for the slave starts at the
+ * entry_header.offset to the location pointed to by the rsc_hdr.data_offset.
+ *
+ * Drivers have a stringified key to a slave/resource. They can query the slave
+ * information and get the slave id and the auxiliary data and the length of the
+ * data. Using this information, they can format the request to be sent to the
+ * h/w accelerator and request a resource state.
+ */
+
+static const u8 CMD_DB_MAGIC[] = { 0xdb, 0x30, 0x03, 0x0c };
+
+static bool cmd_db_magic_matches(const struct cmd_db_header *header)
+{
+	const u8 *magic = header->magic;
+
+	return memcmp(magic, CMD_DB_MAGIC, ARRAY_SIZE(CMD_DB_MAGIC)) == 0;
+}
+
+static struct cmd_db_header *cmd_db_header;
+
+static inline const void *rsc_to_entry_header(const struct rsc_hdr *hdr)
+{
+	u16 offset = le16_to_cpu(hdr->header_offset);
+
+	return cmd_db_header->data + offset;
+}
+
+static inline void *
+rsc_offset(const struct rsc_hdr *hdr, const struct entry_header *ent)
+{
+	u16 offset = le16_to_cpu(hdr->data_offset);
+	u16 loffset = le16_to_cpu(ent->offset);
+
+	return cmd_db_header->data + offset + loffset;
+}
+
+/**
+ * cmd_db_ready - Indicates if command DB is available
+ *
+ * Return: 0 on success, errno otherwise
+ */
+int cmd_db_ready(void)
+{
+	if (cmd_db_header == NULL)
+		return -EPROBE_DEFER;
+	else if (!cmd_db_magic_matches(cmd_db_header))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(cmd_db_ready);
+
+static int cmd_db_get_header(const char *id, const struct entry_header **eh,
+			     const struct rsc_hdr **rh)
+{
+	const struct rsc_hdr *rsc_hdr;
+	const struct entry_header *ent;
+	int ret, i, j;
+	u8 query[sizeof(ent->id)] __nonstring;
+
+	ret = cmd_db_ready();
+	if (ret)
+		return ret;
+
+	/*
+	 * Pad out query string to same length as in DB. NOTE: the output
+	 * query string is not necessarily '\0' terminated if it bumps up
+	 * against the max size. That's OK and expected.
+	 */
+	strncpy(query, id, sizeof(query));
+
+	for (i = 0; i < MAX_SLV_ID; i++) {
+		rsc_hdr = &cmd_db_header->header[i];
+		if (!rsc_hdr->slv_id)
+			break;
+
+		ent = rsc_to_entry_header(rsc_hdr);
+		for (j = 0; j < le16_to_cpu(rsc_hdr->cnt); j++, ent++) {
+			if (memcmp(ent->id, query, sizeof(ent->id)) == 0) {
+				if (eh)
+					*eh = ent;
+				if (rh)
+					*rh = rsc_hdr;
+				return 0;
+			}
+		}
+	}
+
+	return -ENODEV;
+}
+
+/**
+ * cmd_db_read_addr() - Query command db for resource id address.
+ *
+ * @id: resource id to query for address
+ *
+ * Return: resource address on success, 0 on error
+ *
+ * This is used to retrieve resource address based on resource
+ * id.
+ */
+u32 cmd_db_read_addr(const char *id)
+{
+	int ret;
+	const struct entry_header *ent;
+
+	ret = cmd_db_get_header(id, &ent, NULL);
+
+	return ret < 0 ? 0 : le32_to_cpu(ent->addr);
+}
+EXPORT_SYMBOL(cmd_db_read_addr);
+
+/**
+ * cmd_db_read_aux_data() - Query command db for aux data.
+ *
+ *  @id: Resource to retrieve AUX Data on
+ *  @len: size of data buffer returned
+ *
+ *  Return: pointer to data on success, error pointer otherwise
+ */
+const void *cmd_db_read_aux_data(const char *id, size_t *len)
+{
+	int ret;
+	const struct entry_header *ent;
+	const struct rsc_hdr *rsc_hdr;
+
+	ret = cmd_db_get_header(id, &ent, &rsc_hdr);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (len)
+		*len = le16_to_cpu(ent->len);
+
+	return rsc_offset(rsc_hdr, ent);
+}
+EXPORT_SYMBOL(cmd_db_read_aux_data);
+
+/**
+ * cmd_db_read_slave_id - Get the slave ID for a given resource address
+ *
+ * @id: Resource id to query the DB for version
+ *
+ * Return: cmd_db_hw_type enum on success, CMD_DB_HW_INVALID on error
+ */
+enum cmd_db_hw_type cmd_db_read_slave_id(const char *id)
+{
+	int ret;
+	const struct entry_header *ent;
+	u32 addr;
+
+	ret = cmd_db_get_header(id, &ent, NULL);
+	if (ret < 0)
+		return CMD_DB_HW_INVALID;
+
+	addr = le32_to_cpu(ent->addr);
+	return (addr >> SLAVE_ID_SHIFT) & SLAVE_ID_MASK;
+}
+EXPORT_SYMBOL(cmd_db_read_slave_id);
+
+#ifdef CONFIG_DEBUG_FS
+static int cmd_db_debugfs_dump(struct seq_file *seq, void *p)
+{
+	int i, j;
+	const struct rsc_hdr *rsc;
+	const struct entry_header *ent;
+	const char *name;
+	u16 len, version;
+	u8 major, minor;
+
+	seq_puts(seq, "Command DB DUMP\n");
+
+	for (i = 0; i < MAX_SLV_ID; i++) {
+		rsc = &cmd_db_header->header[i];
+		if (!rsc->slv_id)
+			break;
+
+		switch (le16_to_cpu(rsc->slv_id)) {
+		case CMD_DB_HW_ARC:
+			name = "ARC";
+			break;
+		case CMD_DB_HW_VRM:
+			name = "VRM";
+			break;
+		case CMD_DB_HW_BCM:
+			name = "BCM";
+			break;
+		default:
+			name = "Unknown";
+			break;
+		}
+
+		version = le16_to_cpu(rsc->version);
+		major = version >> 8;
+		minor = version;
+
+		seq_printf(seq, "Slave %s (v%u.%u)\n", name, major, minor);
+		seq_puts(seq, "-------------------------\n");
+
+		ent = rsc_to_entry_header(rsc);
+		for (j = 0; j < le16_to_cpu(rsc->cnt); j++, ent++) {
+			seq_printf(seq, "0x%05x: %*pEp", le32_to_cpu(ent->addr),
+				   (int)sizeof(ent->id), ent->id);
+
+			len = le16_to_cpu(ent->len);
+			if (len) {
+				seq_printf(seq, " [%*ph]",
+					   len, rsc_offset(rsc, ent));
+			}
+			seq_putc(seq, '\n');
+		}
+	}
+
+	return 0;
+}
+
+static int open_cmd_db_debugfs(struct inode *inode, struct file *file)
+{
+	return single_open(file, cmd_db_debugfs_dump, inode->i_private);
+}
+#endif
+
+static const struct file_operations cmd_db_debugfs_ops = {
+#ifdef CONFIG_DEBUG_FS
+	.open = open_cmd_db_debugfs,
+#endif
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int cmd_db_dev_probe(struct platform_device *pdev)
+{
+	struct reserved_mem *rmem;
+	int ret = 0;
+
+	rmem = of_reserved_mem_lookup(pdev->dev.of_node);
+	if (!rmem) {
+		dev_err(&pdev->dev, "failed to acquire memory region\n");
+		return -EINVAL;
+	}
+
+	cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WB);
+	if (!cmd_db_header) {
+		ret = -ENOMEM;
+		cmd_db_header = NULL;
+		return ret;
+	}
+
+	if (!cmd_db_magic_matches(cmd_db_header)) {
+		dev_err(&pdev->dev, "Invalid Command DB Magic\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_file("cmd-db", 0400, NULL, NULL, &cmd_db_debugfs_ops);
+
+	device_set_pm_not_required(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id cmd_db_match_table[] = {
+	{ .compatible = "qcom,cmd-db" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, cmd_db_match_table);
+
+static struct platform_driver cmd_db_dev_driver = {
+	.probe  = cmd_db_dev_probe,
+	.driver = {
+		   .name = "cmd-db",
+		   .of_match_table = cmd_db_match_table,
+		   .suppress_bind_attrs = true,
+	},
+};
+
+static int __init cmd_db_device_init(void)
+{
+	return platform_driver_register(&cmd_db_dev_driver);
+}
+arch_initcall(cmd_db_device_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Command DB Driver");
+MODULE_LICENSE("GPL v2");