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, 1249 insertions, 0 deletions

diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
new file mode 100644
index 000000000..78473d34e
--- /dev/null
+++ b/tools/include/nolibc/sys.h
@@ -0,0 +1,1249 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Syscall definitions for NOLIBC (those in man(2))
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SYS_H
+#define _NOLIBC_SYS_H
+
+#include <stdarg.h>
+#include "std.h"
+
+/* system includes */
+#include <asm/unistd.h>
+#include <asm/signal.h>  // for SIGCHLD
+#include <asm/ioctls.h>
+#include <asm/mman.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+#include <linux/time.h>
+
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+
+
+/* Functions in this file only describe syscalls. They're declared static so
+ * that the compiler usually decides to inline them while still being allowed
+ * to pass a pointer to one of their instances. Each syscall exists in two
+ * versions:
+ *   - the "internal" ones, which matches the raw syscall interface at the
+ *     kernel level, which may sometimes slightly differ from the documented
+ *     libc-level ones. For example most of them return either a valid value
+ *     or -errno. All of these are prefixed with "sys_". They may be called
+ *     by non-portable applications if desired.
+ *
+ *   - the "exported" ones, whose interface must closely match the one
+ *     documented in man(2), that applications are supposed to expect. These
+ *     ones rely on the internal ones, and set errno.
+ *
+ * Each syscall will be defined with the two functions, sorted in alphabetical
+ * order applied to the exported names.
+ *
+ * In case of doubt about the relevance of a function here, only those which
+ * set errno should be defined here. Wrappers like those appearing in man(3)
+ * should not be placed here.
+ */
+
+
+/*
+ * int brk(void *addr);
+ * void *sbrk(intptr_t inc)
+ */
+
+static __attribute__((unused))
+void *sys_brk(void *addr)
+{
+	return (void *)my_syscall1(__NR_brk, addr);
+}
+
+static __attribute__((unused))
+int brk(void *addr)
+{
+	void *ret = sys_brk(addr);
+
+	if (!ret) {
+		SET_ERRNO(ENOMEM);
+		return -1;
+	}
+	return 0;
+}
+
+static __attribute__((unused))
+void *sbrk(intptr_t inc)
+{
+	void *ret;
+
+	/* first call to find current end */
+	if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
+		return ret + inc;
+
+	SET_ERRNO(ENOMEM);
+	return (void *)-1;
+}
+
+
+/*
+ * int chdir(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chdir(const char *path)
+{
+	return my_syscall1(__NR_chdir, path);
+}
+
+static __attribute__((unused))
+int chdir(const char *path)
+{
+	int ret = sys_chdir(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chmod(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_chmod(const char *path, mode_t mode)
+{
+#ifdef __NR_fchmodat
+	return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
+#elif defined(__NR_chmod)
+	return my_syscall2(__NR_chmod, path, mode);
+#else
+#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod()
+#endif
+}
+
+static __attribute__((unused))
+int chmod(const char *path, mode_t mode)
+{
+	int ret = sys_chmod(path, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chown(const char *path, uid_t owner, gid_t group);
+ */
+
+static __attribute__((unused))
+int sys_chown(const char *path, uid_t owner, gid_t group)
+{
+#ifdef __NR_fchownat
+	return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
+#elif defined(__NR_chown)
+	return my_syscall3(__NR_chown, path, owner, group);
+#else
+#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown()
+#endif
+}
+
+static __attribute__((unused))
+int chown(const char *path, uid_t owner, gid_t group)
+{
+	int ret = sys_chown(path, owner, group);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chroot(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chroot(const char *path)
+{
+	return my_syscall1(__NR_chroot, path);
+}
+
+static __attribute__((unused))
+int chroot(const char *path)
+{
+	int ret = sys_chroot(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int close(int fd);
+ */
+
+static __attribute__((unused))
+int sys_close(int fd)
+{
+	return my_syscall1(__NR_close, fd);
+}
+
+static __attribute__((unused))
+int close(int fd)
+{
+	int ret = sys_close(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup(int fd);
+ */
+
+static __attribute__((unused))
+int sys_dup(int fd)
+{
+	return my_syscall1(__NR_dup, fd);
+}
+
+static __attribute__((unused))
+int dup(int fd)
+{
+	int ret = sys_dup(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup2(int old, int new);
+ */
+
+static __attribute__((unused))
+int sys_dup2(int old, int new)
+{
+#ifdef __NR_dup3
+	return my_syscall3(__NR_dup3, old, new, 0);
+#elif defined(__NR_dup2)
+	return my_syscall2(__NR_dup2, old, new);
+#else
+#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2()
+#endif
+}
+
+static __attribute__((unused))
+int dup2(int old, int new)
+{
+	int ret = sys_dup2(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup3(int old, int new, int flags);
+ */
+
+#ifdef __NR_dup3
+static __attribute__((unused))
+int sys_dup3(int old, int new, int flags)
+{
+	return my_syscall3(__NR_dup3, old, new, flags);
+}
+
+static __attribute__((unused))
+int dup3(int old, int new, int flags)
+{
+	int ret = sys_dup3(old, new, flags);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+#endif
+
+
+/*
+ * int execve(const char *filename, char *const argv[], char *const envp[]);
+ */
+
+static __attribute__((unused))
+int sys_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	return my_syscall3(__NR_execve, filename, argv, envp);
+}
+
+static __attribute__((unused))
+int execve(const char *filename, char *const argv[], char *const envp[])
+{
+	int ret = sys_execve(filename, argv, envp);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * void exit(int status);
+ */
+
+static __attribute__((noreturn,unused))
+void sys_exit(int status)
+{
+	my_syscall1(__NR_exit, status & 255);
+	while(1); // shut the "noreturn" warnings.
+}
+
+static __attribute__((noreturn,unused))
+void exit(int status)
+{
+	sys_exit(status);
+}
+
+
+/*
+ * pid_t fork(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+#ifdef __NR_clone
+	/* note: some archs only have clone() and not fork(). Different archs
+	 * have a different API, but most archs have the flags on first arg and
+	 * will not use the rest with no other flag.
+	 */
+	return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
+#elif defined(__NR_fork)
+	return my_syscall0(__NR_fork);
+#else
+#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork()
+#endif
+}
+
+static __attribute__((unused))
+pid_t fork(void)
+{
+	pid_t ret = sys_fork();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int fsync(int fd);
+ */
+
+static __attribute__((unused))
+int sys_fsync(int fd)
+{
+	return my_syscall1(__NR_fsync, fd);
+}
+
+static __attribute__((unused))
+int fsync(int fd)
+{
+	int ret = sys_fsync(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int getdents64(int fd, struct linux_dirent64 *dirp, int count);
+ */
+
+static __attribute__((unused))
+int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+	return my_syscall3(__NR_getdents64, fd, dirp, count);
+}
+
+static __attribute__((unused))
+int getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+	int ret = sys_getdents64(fd, dirp, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t getpgid(pid_t pid);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgid(pid_t pid)
+{
+	return my_syscall1(__NR_getpgid, pid);
+}
+
+static __attribute__((unused))
+pid_t getpgid(pid_t pid)
+{
+	pid_t ret = sys_getpgid(pid);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t getpgrp(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgrp(void)
+{
+	return sys_getpgid(0);
+}
+
+static __attribute__((unused))
+pid_t getpgrp(void)
+{
+	return sys_getpgrp();
+}
+
+
+/*
+ * pid_t getpid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpid(void)
+{
+	return my_syscall0(__NR_getpid);
+}
+
+static __attribute__((unused))
+pid_t getpid(void)
+{
+	return sys_getpid();
+}
+
+
+/*
+ * pid_t getppid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getppid(void)
+{
+	return my_syscall0(__NR_getppid);
+}
+
+static __attribute__((unused))
+pid_t getppid(void)
+{
+	return sys_getppid();
+}
+
+
+/*
+ * pid_t gettid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+	return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
+pid_t gettid(void)
+{
+	return sys_gettid();
+}
+
+
+/*
+ * int gettimeofday(struct timeval *tv, struct timezone *tz);
+ */
+
+static __attribute__((unused))
+int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	return my_syscall2(__NR_gettimeofday, tv, tz);
+}
+
+static __attribute__((unused))
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	int ret = sys_gettimeofday(tv, tz);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int ioctl(int fd, unsigned long req, void *value);
+ */
+
+static __attribute__((unused))
+int sys_ioctl(int fd, unsigned long req, void *value)
+{
+	return my_syscall3(__NR_ioctl, fd, req, value);
+}
+
+static __attribute__((unused))
+int ioctl(int fd, unsigned long req, void *value)
+{
+	int ret = sys_ioctl(fd, req, value);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+/*
+ * int kill(pid_t pid, int signal);
+ */
+
+static __attribute__((unused))
+int sys_kill(pid_t pid, int signal)
+{
+	return my_syscall2(__NR_kill, pid, signal);
+}
+
+static __attribute__((unused))
+int kill(pid_t pid, int signal)
+{
+	int ret = sys_kill(pid, signal);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int link(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_link(const char *old, const char *new)
+{
+#ifdef __NR_linkat
+	return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
+#elif defined(__NR_link)
+	return my_syscall2(__NR_link, old, new);
+#else
+#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link()
+#endif
+}
+
+static __attribute__((unused))
+int link(const char *old, const char *new)
+{
+	int ret = sys_link(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * off_t lseek(int fd, off_t offset, int whence);
+ */
+
+static __attribute__((unused))
+off_t sys_lseek(int fd, off_t offset, int whence)
+{
+	return my_syscall3(__NR_lseek, fd, offset, whence);
+}
+
+static __attribute__((unused))
+off_t lseek(int fd, off_t offset, int whence)
+{
+	off_t ret = sys_lseek(fd, offset, whence);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int mkdir(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_mkdir(const char *path, mode_t mode)
+{
+#ifdef __NR_mkdirat
+	return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
+#elif defined(__NR_mkdir)
+	return my_syscall2(__NR_mkdir, path, mode);
+#else
+#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir()
+#endif
+}
+
+static __attribute__((unused))
+int mkdir(const char *path, mode_t mode)
+{
+	int ret = sys_mkdir(path, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int mknod(const char *path, mode_t mode, dev_t dev);
+ */
+
+static __attribute__((unused))
+long sys_mknod(const char *path, mode_t mode, dev_t dev)
+{
+#ifdef __NR_mknodat
+	return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
+#elif defined(__NR_mknod)
+	return my_syscall3(__NR_mknod, path, mode, dev);
+#else
+#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod()
+#endif
+}
+
+static __attribute__((unused))
+int mknod(const char *path, mode_t mode, dev_t dev)
+{
+	int ret = sys_mknod(path, mode, dev);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+#ifndef MAP_SHARED
+#define MAP_SHARED		0x01	/* Share changes */
+#define MAP_PRIVATE		0x02	/* Changes are private */
+#define MAP_SHARED_VALIDATE	0x03	/* share + validate extension flags */
+#endif
+
+#ifndef MAP_FAILED
+#define MAP_FAILED ((void *)-1)
+#endif
+
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+	       off_t offset)
+{
+#ifndef my_syscall6
+	/* Function not implemented. */
+	return (void *)-ENOSYS;
+#else
+
+	int n;
+
+#if defined(__NR_mmap2)
+	n = __NR_mmap2;
+	offset >>= 12;
+#else
+	n = __NR_mmap;
+#endif
+
+	return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset);
+#endif
+}
+
+static __attribute__((unused))
+void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset)
+{
+	void *ret = sys_mmap(addr, length, prot, flags, fd, offset);
+
+	if ((unsigned long)ret >= -4095UL) {
+		SET_ERRNO(-(long)ret);
+		ret = MAP_FAILED;
+	}
+	return ret;
+}
+
+static __attribute__((unused))
+int sys_munmap(void *addr, size_t length)
+{
+	return my_syscall2(__NR_munmap, addr, length);
+}
+
+static __attribute__((unused))
+int munmap(void *addr, size_t length)
+{
+	int ret = sys_munmap(addr, length);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+/*
+ * int mount(const char *source, const char *target,
+ *           const char *fstype, unsigned long flags,
+ *           const void *data);
+ */
+static __attribute__((unused))
+int sys_mount(const char *src, const char *tgt, const char *fst,
+                     unsigned long flags, const void *data)
+{
+	return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
+}
+
+static __attribute__((unused))
+int mount(const char *src, const char *tgt,
+          const char *fst, unsigned long flags,
+          const void *data)
+{
+	int ret = sys_mount(src, tgt, fst, flags, data);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int open(const char *path, int flags[, mode_t mode]);
+ */
+
+static __attribute__((unused))
+int sys_open(const char *path, int flags, mode_t mode)
+{
+#ifdef __NR_openat
+	return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
+#elif defined(__NR_open)
+	return my_syscall3(__NR_open, path, flags, mode);
+#else
+#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open()
+#endif
+}
+
+static __attribute__((unused))
+int open(const char *path, int flags, ...)
+{
+	mode_t mode = 0;
+	int ret;
+
+	if (flags & O_CREAT) {
+		va_list args;
+
+		va_start(args, flags);
+		mode = va_arg(args, mode_t);
+		va_end(args);
+	}
+
+	ret = sys_open(path, flags, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int pivot_root(const char *new, const char *old);
+ */
+
+static __attribute__((unused))
+int sys_pivot_root(const char *new, const char *old)
+{
+	return my_syscall2(__NR_pivot_root, new, old);
+}
+
+static __attribute__((unused))
+int pivot_root(const char *new, const char *old)
+{
+	int ret = sys_pivot_root(new, old);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int poll(struct pollfd *fds, int nfds, int timeout);
+ */
+
+static __attribute__((unused))
+int sys_poll(struct pollfd *fds, int nfds, int timeout)
+{
+#if defined(__NR_ppoll)
+	struct timespec t;
+
+	if (timeout >= 0) {
+		t.tv_sec  = timeout / 1000;
+		t.tv_nsec = (timeout % 1000) * 1000000;
+	}
+	return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL);
+#elif defined(__NR_poll)
+	return my_syscall3(__NR_poll, fds, nfds, timeout);
+#else
+#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll()
+#endif
+}
+
+static __attribute__((unused))
+int poll(struct pollfd *fds, int nfds, int timeout)
+{
+	int ret = sys_poll(fds, nfds, timeout);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * ssize_t read(int fd, void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_read(int fd, void *buf, size_t count)
+{
+	return my_syscall3(__NR_read, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t read(int fd, void *buf, size_t count)
+{
+	ssize_t ret = sys_read(fd, buf, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int reboot(int cmd);
+ * <cmd> is among LINUX_REBOOT_CMD_*
+ */
+
+static __attribute__((unused))
+ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
+{
+	return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
+}
+
+static __attribute__((unused))
+int reboot(int cmd)
+{
+	int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int sched_yield(void);
+ */
+
+static __attribute__((unused))
+int sys_sched_yield(void)
+{
+	return my_syscall0(__NR_sched_yield);
+}
+
+static __attribute__((unused))
+int sched_yield(void)
+{
+	int ret = sys_sched_yield();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int select(int nfds, fd_set *read_fds, fd_set *write_fds,
+ *            fd_set *except_fds, struct timeval *timeout);
+ */
+
+static __attribute__((unused))
+int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
+	struct sel_arg_struct {
+		unsigned long n;
+		fd_set *r, *w, *e;
+		struct timeval *t;
+	} arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
+	return my_syscall1(__NR_select, &arg);
+#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
+	struct timespec t;
+
+	if (timeout) {
+		t.tv_sec  = timeout->tv_sec;
+		t.tv_nsec = timeout->tv_usec * 1000;
+	}
+	return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
+#elif defined(__NR__newselect) || defined(__NR_select)
+#ifndef __NR__newselect
+#define __NR__newselect __NR_select
+#endif
+	return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
+#else
+#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select()
+#endif
+}
+
+static __attribute__((unused))
+int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+	int ret = sys_select(nfds, rfds, wfds, efds, timeout);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int setpgid(pid_t pid, pid_t pgid);
+ */
+
+static __attribute__((unused))
+int sys_setpgid(pid_t pid, pid_t pgid)
+{
+	return my_syscall2(__NR_setpgid, pid, pgid);
+}
+
+static __attribute__((unused))
+int setpgid(pid_t pid, pid_t pgid)
+{
+	int ret = sys_setpgid(pid, pgid);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t setsid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_setsid(void)
+{
+	return my_syscall0(__NR_setsid);
+}
+
+static __attribute__((unused))
+pid_t setsid(void)
+{
+	pid_t ret = sys_setsid();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int stat(const char *path, struct stat *buf);
+ * Warning: the struct stat's layout is arch-dependent.
+ */
+
+static __attribute__((unused))
+int sys_stat(const char *path, struct stat *buf)
+{
+	struct sys_stat_struct stat;
+	long ret;
+
+#ifdef __NR_newfstatat
+	/* only solution for arm64 */
+	ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
+#elif defined(__NR_stat)
+	ret = my_syscall2(__NR_stat, path, &stat);
+#else
+#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat()
+#endif
+	buf->st_dev     = stat.st_dev;
+	buf->st_ino     = stat.st_ino;
+	buf->st_mode    = stat.st_mode;
+	buf->st_nlink   = stat.st_nlink;
+	buf->st_uid     = stat.st_uid;
+	buf->st_gid     = stat.st_gid;
+	buf->st_rdev    = stat.st_rdev;
+	buf->st_size    = stat.st_size;
+	buf->st_blksize = stat.st_blksize;
+	buf->st_blocks  = stat.st_blocks;
+	buf->st_atime   = stat.st_atime;
+	buf->st_mtime   = stat.st_mtime;
+	buf->st_ctime   = stat.st_ctime;
+	return ret;
+}
+
+static __attribute__((unused))
+int stat(const char *path, struct stat *buf)
+{
+	int ret = sys_stat(path, buf);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int symlink(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_symlink(const char *old, const char *new)
+{
+#ifdef __NR_symlinkat
+	return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
+#elif defined(__NR_symlink)
+	return my_syscall2(__NR_symlink, old, new);
+#else
+#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink()
+#endif
+}
+
+static __attribute__((unused))
+int symlink(const char *old, const char *new)
+{
+	int ret = sys_symlink(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * mode_t umask(mode_t mode);
+ */
+
+static __attribute__((unused))
+mode_t sys_umask(mode_t mode)
+{
+	return my_syscall1(__NR_umask, mode);
+}
+
+static __attribute__((unused))
+mode_t umask(mode_t mode)
+{
+	return sys_umask(mode);
+}
+
+
+/*
+ * int umount2(const char *path, int flags);
+ */
+
+static __attribute__((unused))
+int sys_umount2(const char *path, int flags)
+{
+	return my_syscall2(__NR_umount2, path, flags);
+}
+
+static __attribute__((unused))
+int umount2(const char *path, int flags)
+{
+	int ret = sys_umount2(path, flags);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int unlink(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_unlink(const char *path)
+{
+#ifdef __NR_unlinkat
+	return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
+#elif defined(__NR_unlink)
+	return my_syscall1(__NR_unlink, path);
+#else
+#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink()
+#endif
+}
+
+static __attribute__((unused))
+int unlink(const char *path)
+{
+	int ret = sys_unlink(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t wait(int *status);
+ * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage);
+ * pid_t waitpid(pid_t pid, int *status, int options);
+ */
+
+static __attribute__((unused))
+pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+	return my_syscall4(__NR_wait4, pid, status, options, rusage);
+}
+
+static __attribute__((unused))
+pid_t wait(int *status)
+{
+	pid_t ret = sys_wait4(-1, status, 0, NULL);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+static __attribute__((unused))
+pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+	pid_t ret = sys_wait4(pid, status, options, rusage);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+static __attribute__((unused))
+pid_t waitpid(pid_t pid, int *status, int options)
+{
+	pid_t ret = sys_wait4(pid, status, options, NULL);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * ssize_t write(int fd, const void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_write(int fd, const void *buf, size_t count)
+{
+	return my_syscall3(__NR_write, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t write(int fd, const void *buf, size_t count)
+{
+	ssize_t ret = sys_write(fd, buf, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_SYS_H */