diff options
Diffstat (limited to 'tools/include')
| -rw-r--r-- | tools/include/linux/filter.h | 20 | ||||
| -rw-r--r-- | tools/include/linux/numa.h | 16 | ||||
| -rw-r--r-- | tools/include/linux/rbtree.h | 52 | ||||
| -rw-r--r-- | tools/include/linux/rbtree_augmented.h | 60 | ||||
| -rw-r--r-- | tools/include/nolibc/nolibc.h | 2263 | ||||
| -rw-r--r-- | tools/include/uapi/asm-generic/unistd.h | 4 | ||||
| -rw-r--r-- | tools/include/uapi/asm/bitsperlong.h | 4 | ||||
| -rw-r--r-- | tools/include/uapi/drm/i915_drm.h | 8 | ||||
| -rw-r--r-- | tools/include/uapi/linux/bpf.h | 116 | ||||
| -rw-r--r-- | tools/include/uapi/linux/ethtool.h | 51 | ||||
| -rw-r--r-- | tools/include/uapi/linux/fs.h | 60 | ||||
| -rw-r--r-- | tools/include/uapi/linux/if_link.h | 20 | ||||
| -rw-r--r-- | tools/include/uapi/linux/if_xdp.h | 78 | ||||
| -rw-r--r-- | tools/include/uapi/linux/in.h | 10 | ||||
| -rw-r--r-- | tools/include/uapi/linux/kvm.h | 19 | ||||
| -rw-r--r-- | tools/include/uapi/linux/mount.h | 58 | ||||
| -rw-r--r-- | tools/include/uapi/linux/perf_event.h | 55 | ||||
| -rw-r--r-- | tools/include/uapi/linux/pkt_sched.h | 1163 | ||||
| -rw-r--r-- | tools/include/uapi/linux/prctl.h | 9 | ||||
| -rw-r--r-- | tools/include/uapi/linux/tc_act/tc_bpf.h | 2 | ||||
| -rw-r--r-- | tools/include/uapi/linux/vhost.h | 113 |
21 files changed, 3982 insertions, 199 deletions
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index af55acf73e75..cce0b02c0e28 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -199,6 +199,16 @@ .off = OFF, \ .imm = 0 }) +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ @@ -209,6 +219,16 @@ .off = OFF, \ .imm = IMM }) +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ diff --git a/tools/include/linux/numa.h b/tools/include/linux/numa.h new file mode 100644 index 000000000000..110b0e5d0fb0 --- /dev/null +++ b/tools/include/linux/numa.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NUMA_H +#define _LINUX_NUMA_H + + +#ifdef CONFIG_NODES_SHIFT +#define NODES_SHIFT CONFIG_NODES_SHIFT +#else +#define NODES_SHIFT 0 +#endif + +#define MAX_NUMNODES (1 << NODES_SHIFT) + +#define NUMA_NO_NODE (-1) + +#endif /* _LINUX_NUMA_H */ diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h index 112582253dd0..8e9ed4786269 100644 --- a/tools/include/linux/rbtree.h +++ b/tools/include/linux/rbtree.h @@ -43,13 +43,28 @@ struct rb_root { struct rb_node *rb_node; }; +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } #define rb_entry(ptr, type, member) container_of(ptr, type, member) -#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) +#define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ @@ -68,6 +83,12 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); +extern void rb_insert_color_cached(struct rb_node *, + struct rb_root_cached *, bool); +extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *); +/* Same as rb_first(), but O(1) */ +#define rb_first_cached(root) (root)->rb_leftmost + /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); @@ -75,6 +96,8 @@ extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); +extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, + struct rb_root_cached *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) @@ -90,12 +113,29 @@ static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) - -/* - * Handy for checking that we are not deleting an entry that is - * already in a list, found in block/{blk-throttle,cfq-iosched}.c, - * probably should be moved to lib/rbtree.c... +/** + * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of + * given type allowing the backing memory of @pos to be invalidated + * + * @pos: the 'type *' to use as a loop cursor. + * @n: another 'type *' to use as temporary storage + * @root: 'rb_root *' of the rbtree. + * @field: the name of the rb_node field within 'type'. + * + * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as + * list_for_each_entry_safe() and allows the iteration to continue independent + * of changes to @pos by the body of the loop. + * + * Note, however, that it cannot handle other modifications that re-order the + * rbtree it is iterating over. This includes calling rb_erase() on @pos, as + * rb_erase() may rebalance the tree, causing us to miss some nodes. */ +#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ + for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ + pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \ + typeof(*pos), field); 1; }); \ + pos = n) + static inline void rb_erase_init(struct rb_node *n, struct rb_root *root) { rb_erase(n, root); diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h index 43be941db695..d008e1404580 100644 --- a/tools/include/linux/rbtree_augmented.h +++ b/tools/include/linux/rbtree_augmented.h @@ -44,7 +44,9 @@ struct rb_augment_callbacks { void (*rotate)(struct rb_node *old, struct rb_node *new); }; -extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, +extern void __rb_insert_augmented(struct rb_node *node, + struct rb_root *root, + bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. @@ -60,7 +62,16 @@ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, root, augment->rotate); + __rb_insert_augmented(node, root, false, NULL, augment->rotate); +} + +static inline void +rb_insert_augmented_cached(struct rb_node *node, + struct rb_root_cached *root, bool newleft, + const struct rb_augment_callbacks *augment) +{ + __rb_insert_augmented(node, &root->rb_root, + newleft, &root->rb_leftmost, augment->rotate); } #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ @@ -93,7 +104,9 @@ rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ old->rbaugmented = rbcompute(old); \ } \ rbstatic const struct rb_augment_callbacks rbname = { \ - rbname ## _propagate, rbname ## _copy, rbname ## _rotate \ + .propagate = rbname ## _propagate, \ + .copy = rbname ## _copy, \ + .rotate = rbname ## _rotate \ }; @@ -126,11 +139,11 @@ __rb_change_child(struct rb_node *old, struct rb_node *new, { if (parent) { if (parent->rb_left == old) - parent->rb_left = new; + WRITE_ONCE(parent->rb_left, new); else - parent->rb_right = new; + WRITE_ONCE(parent->rb_right, new); } else - root->rb_node = new; + WRITE_ONCE(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, @@ -138,12 +151,17 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, + struct rb_node **leftmost, const struct rb_augment_callbacks *augment) { - struct rb_node *child = node->rb_right, *tmp = node->rb_left; + struct rb_node *child = node->rb_right; + struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; + if (leftmost && node == *leftmost) + *leftmost = rb_next(node); + if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) @@ -170,6 +188,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, tmp = parent; } else { struct rb_node *successor = child, *child2; + tmp = child->rb_left; if (!tmp) { /* @@ -183,6 +202,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, */ parent = successor; child2 = successor->rb_right; + augment->copy(node, successor); } else { /* @@ -204,19 +224,23 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, successor = tmp; tmp = tmp->rb_left; } while (tmp); - parent->rb_left = child2 = successor->rb_right; - successor->rb_right = child; + child2 = successor->rb_right; + WRITE_ONCE(parent->rb_left, child2); + WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); + augment->copy(node, successor); augment->propagate(parent, successor); } - successor->rb_left = tmp = node->rb_left; + tmp = node->rb_left; + WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); + if (child2) { successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); @@ -237,9 +261,21 @@ static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); + struct rb_node *rebalance = __rb_erase_augmented(node, root, + NULL, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } -#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */ +static __always_inline void +rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, + const struct rb_augment_callbacks *augment) +{ + struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root, + &root->rb_leftmost, + augment); + if (rebalance) + __rb_erase_color(rebalance, &root->rb_root, augment->rotate); +} + +#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h new file mode 100644 index 000000000000..1708e9f9f8aa --- /dev/null +++ b/tools/include/nolibc/nolibc.h @@ -0,0 +1,2263 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* nolibc.h + * Copyright (C) 2017-2018 Willy Tarreau <w@1wt.eu> + */ + +/* + * This file is designed to be used as a libc alternative for minimal programs + * with very limited requirements. It consists of a small number of syscall and + * type definitions, and the minimal startup code needed to call main(). + * All syscalls are declared as static functions so that they can be optimized + * away by the compiler when not used. + * + * Syscalls are split into 3 levels: + * - The lower level is the arch-specific syscall() definition, consisting in + * assembly code in compound expressions. These are called my_syscall0() to + * my_syscall6() depending on the number of arguments. The MIPS + * implementation is limited to 5 arguments. All input arguments are cast + * to a long stored in a register. These expressions always return the + * syscall's return value as a signed long value which is often either a + * pointer or the negated errno value. + * + * - The second level is mostly architecture-independent. It is made of + * static functions called sys_<name>() which rely on my_syscallN() + * depending on the syscall definition. These functions are responsible + * for exposing the appropriate types for the syscall arguments (int, + * pointers, etc) and for setting the appropriate return type (often int). + * A few of them are architecture-specific because the syscalls are not all + * mapped exactly the same among architectures. For example, some archs do + * not implement select() and need pselect6() instead, so the sys_select() + * function will have to abstract this. + * + * - The third level is the libc call definition. It exposes the lower raw + * sys_<name>() calls in a way that looks like what a libc usually does, + * takes care of specific input values, and of setting errno upon error. + * There can be minor variations compared to standard libc calls. For + * example the open() call always takes 3 args here. + * + * The errno variable is declared static and unused. This way it can be + * optimized away if not used. However this means that a program made of + * multiple C files may observe different errno values (one per C file). For + * the type of programs this project targets it usually is not a problem. The + * resulting program may even be reduced by defining the NOLIBC_IGNORE_ERRNO + * macro, in which case the errno value will never be assigned. + * + * Some stdint-like integer types are defined. These are valid on all currently + * supported architectures, because signs are enforced, ints are assumed to be + * 32 bits, longs the size of a pointer and long long 64 bits. If more + * architectures have to be supported, this may need to be adapted. + * + * Some macro definitions like the O_* values passed to open(), and some + * structures like the sys_stat struct depend on the architecture. + * + * The definitions start with the architecture-specific parts, which are picked + * based on what the compiler knows about the target architecture, and are + * completed with the generic code. Since it is the compiler which sets the + * target architecture, cross-compiling normally works out of the box without + * having to specify anything. + * + * Finally some very common libc-level functions are provided. It is the case + * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing + * is currently provided regarding stdio emulation. + * + * The macro NOLIBC is always defined, so that it is possible for a program to + * check this macro to know if it is being built against and decide to disable + * some features or simply not to include some standard libc files. + * + * Ideally this file should be split in multiple files for easier long term + * maintenance, but provided as a single file as it is now, it's quite + * convenient to use. Maybe some variations involving a set of includes at the + * top could work. + * + * A simple static executable may be built this way : + * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + * -static -include nolibc.h -lgcc -o hello hello.c + * + * A very useful calling convention table may be found here : + * http://man7.org/linux/man-pages/man2/syscall.2.html + * + * This doc is quite convenient though not necessarily up to date : + * https://w3challs.com/syscalls/ + * + */ + +/* Some archs (at least aarch64) don't expose the regular syscalls anymore by + * default, either because they have an "_at" replacement, or because there are + * more modern alternatives. For now we'd rather still use them. + */ +#define __ARCH_WANT_SYSCALL_NO_AT +#define __ARCH_WANT_SYSCALL_NO_FLAGS +#define __ARCH_WANT_SYSCALL_DEPRECATED + +#include <asm/unistd.h> +#include <asm/ioctls.h> +#include <asm/errno.h> +#include <linux/fs.h> +#include <linux/loop.h> + +#define NOLIBC + +/* this way it will be removed if unused */ +static int errno; + +#ifndef NOLIBC_IGNORE_ERRNO +#define SET_ERRNO(v) do { errno = (v); } while (0) +#else +#define SET_ERRNO(v) do { } while (0) +#endif + +/* errno codes all ensure that they will not conflict with a valid pointer + * because they all correspond to the highest addressable memry page. + */ +#define MAX_ERRNO 4095 + +/* Declare a few quite common macros and types that usually are in stdlib.h, + * stdint.h, ctype.h, unistd.h and a few other common locations. + */ + +#define NULL ((void *)0) + +/* stdint types */ +typedef unsigned char uint8_t; +typedef signed char int8_t; +typedef unsigned short uint16_t; +typedef signed short int16_t; +typedef unsigned int uint32_t; +typedef signed int int32_t; +typedef unsigned long long uint64_t; +typedef signed long long int64_t; +typedef unsigned long size_t; +typedef signed long ssize_t; +typedef unsigned long uintptr_t; +typedef signed long intptr_t; +typedef signed long ptrdiff_t; + +/* for stat() */ +typedef unsigned int dev_t; +typedef unsigned long ino_t; +typedef unsigned int mode_t; +typedef signed int pid_t; +typedef unsigned int uid_t; +typedef unsigned int gid_t; +typedef unsigned long nlink_t; +typedef signed long off_t; +typedef signed long blksize_t; +typedef signed long blkcnt_t; +typedef signed long time_t; + +/* for poll() */ +struct pollfd { + int fd; + short int events; + short int revents; +}; + +/* for select() */ +struct timeval { + long tv_sec; + long tv_usec; +}; + +/* for pselect() */ +struct timespec { + long tv_sec; + long tv_nsec; +}; + +/* for gettimeofday() */ +struct timezone { + int tz_minuteswest; + int tz_dsttime; +}; + +/* for getdents64() */ +struct linux_dirent64 { + uint64_t d_ino; + int64_t d_off; + unsigned short d_reclen; + unsigned char d_type; + char d_name[]; +}; + +/* commonly an fd_set represents 256 FDs */ +#define FD_SETSIZE 256 +typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set; + +/* needed by wait4() */ +struct rusage { + struct timeval ru_utime; + struct timeval ru_stime; + long ru_maxrss; + long ru_ixrss; + long ru_idrss; + long ru_isrss; + long ru_minflt; + long ru_majflt; + long ru_nswap; + long ru_inblock; + long ru_oublock; + long ru_msgsnd; + long ru_msgrcv; + long ru_nsignals; + long ru_nvcsw; + long ru_nivcsw; +}; + +/* stat flags (WARNING, octal here) */ +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFBLK 0060000 +#define S_IFREG 0100000 +#define S_IFIFO 0010000 +#define S_IFLNK 0120000 +#define S_IFSOCK 0140000 +#define S_IFMT 0170000 + +#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) +#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) +#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) +#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) +#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) +#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) +#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) + +#define DT_UNKNOWN 0 +#define DT_FIFO 1 +#define DT_CHR 2 +#define DT_DIR 4 +#define DT_BLK 6 +#define DT_REG 8 +#define DT_LNK 10 +#define DT_SOCK 12 + +/* all the *at functions */ +#ifndef AT_FDWCD +#define AT_FDCWD -100 +#endif + +/* lseek */ +#define SEEK_SET 0 +#define SEEK_CUR 1 +#define SEEK_END 2 + +/* reboot */ +#define LINUX_REBOOT_MAGIC1 0xfee1dead +#define LINUX_REBOOT_MAGIC2 0x28121969 +#define LINUX_REBOOT_CMD_HALT 0xcdef0123 +#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc +#define LINUX_REBOOT_CMD_RESTART 0x01234567 +#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 + + +/* The format of the struct as returned by the libc to the application, which + * significantly differs from the format returned by the stat() syscall flavours. + */ +struct stat { + dev_t st_dev; /* ID of device containing file */ + ino_t st_ino; /* inode number */ + mode_t st_mode; /* protection */ + nlink_t st_nlink; /* number of hard links */ + uid_t st_uid; /* user ID of owner */ + gid_t st_gid; /* group ID of owner */ + dev_t st_rdev; /* device ID (if special file) */ + off_t st_size; /* total size, in bytes */ + blksize_t st_blksize; /* blocksize for file system I/O */ + blkcnt_t st_blocks; /* number of 512B blocks allocated */ + time_t st_atime; /* time of last access */ + time_t st_mtime; /* time of last modification */ + time_t st_ctime; /* time of last status change */ +}; + +#define WEXITSTATUS(status) (((status) & 0xff00) >> 8) +#define WIFEXITED(status) (((status) & 0x7f) == 0) + + +/* Below comes the architecture-specific code. For each architecture, we have + * the syscall declarations and the _start code definition. This is the only + * global part. On all architectures the kernel puts everything in the stack + * before jumping to _start just above us, without any return address (_start + * is not a function but an entry pint). So at the stack pointer we find argc. + * Then argv[] begins, and ends at the first NULL. Then we have envp which + * starts and ends with a NULL as well. So envp=argv+argc+1. + */ + +#if defined(__x86_64__) +/* Syscalls for x86_64 : + * - registers are 64-bit + * - syscall number is passed in rax + * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively + * - the system call is performed by calling the syscall instruction + * - syscall return comes in rax + * - rcx and r8..r11 may be clobbered, others are preserved. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + */ + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret) \ + : "0"(_num) \ + : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + register long _arg3 asm("rdx") = (long)(arg3); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + register long _arg3 asm("rdx") = (long)(arg3); \ + register long _arg4 asm("r10") = (long)(arg4); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret), "=r"(_arg4) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "rcx", "r8", "r9", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + register long _arg3 asm("rdx") = (long)(arg3); \ + register long _arg4 asm("r10") = (long)(arg4); \ + register long _arg5 asm("r8") = (long)(arg5); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "rcx", "r9", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _ret; \ + register long _num asm("rax") = (num); \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + register long _arg3 asm("rdx") = (long)(arg3); \ + register long _arg4 asm("r10") = (long)(arg4); \ + register long _arg5 asm("r8") = (long)(arg5); \ + register long _arg6 asm("r9") = (long)(arg6); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +/* startup code */ +asm(".section .text\n" + ".global _start\n" + "_start:\n" + "pop %rdi\n" // argc (first arg, %rdi) + "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) + "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) + "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned when + "sub $8, %rsp\n" // entering the callee + "call main\n" // main() returns the status code, we'll exit with it. + "movzb %al, %rdi\n" // retrieve exit code from 8 lower bits + "mov $60, %rax\n" // NR_exit == 60 + "syscall\n" // really exit + "hlt\n" // ensure it does not return + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, equivalent to stat64(). The + * syscall returns 116 bytes and stops in the middle of __unused. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned long st_nlink; + unsigned int st_mode; + unsigned int st_uid; + + unsigned int st_gid; + unsigned int __pad0; + unsigned long st_rdev; + long st_size; + long st_blksize; + + long st_blocks; + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + + unsigned long st_mtime_nsec; + unsigned long st_ctime; + unsigned long st_ctime_nsec; + long __unused[3]; +}; + +#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) +/* Syscalls for i386 : + * - mostly similar to x86_64 + * - registers are 32-bit + * - syscall number is passed in eax + * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively + * - all registers are preserved (except eax of course) + * - the system call is performed by calling int $0x80 + * - syscall return comes in eax + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, i386 supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + register long _arg1 asm("ebx") = (long)(arg1); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + register long _arg1 asm("ebx") = (long)(arg1); \ + register long _arg2 asm("ecx") = (long)(arg2); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + register long _arg1 asm("ebx") = (long)(arg1); \ + register long _arg2 asm("ecx") = (long)(arg2); \ + register long _arg3 asm("edx") = (long)(arg3); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + register long _arg1 asm("ebx") = (long)(arg1); \ + register long _arg2 asm("ecx") = (long)(arg2); \ + register long _arg3 asm("edx") = (long)(arg3); \ + register long _arg4 asm("esi") = (long)(arg4); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num asm("eax") = (num); \ + register long _arg1 asm("ebx") = (long)(arg1); \ + register long _arg2 asm("ecx") = (long)(arg2); \ + register long _arg3 asm("edx") = (long)(arg3); \ + register long _arg4 asm("esi") = (long)(arg4); \ + register long _arg5 asm("edi") = (long)(arg5); \ + \ + asm volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +/* startup code */ +asm(".section .text\n" + ".global _start\n" + "_start:\n" + "pop %eax\n" // argc (first arg, %eax) + "mov %esp, %ebx\n" // argv[] (second arg, %ebx) + "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) + "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned when + "push %ecx\n" // push all registers on the stack so that we + "push %ebx\n" // support both regparm and plain stack modes + "push %eax\n" + "call main\n" // main() returns the status code in %eax + "movzbl %al, %ebx\n" // retrieve exit code from lower 8 bits + "movl $1, %eax\n" // NR_exit == 1 + "int $0x80\n" // exit now + "hlt\n" // ensure it does not + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; + + unsigned long st_rdev; + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +#elif defined(__ARM_EABI__) +/* Syscalls for ARM in ARM or Thumb modes : + * - registers are 32-bit + * - stack is 8-byte aligned + * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) + * - syscall number is passed in r7 + * - arguments are in r0, r1, r2, r3, r4, r5 + * - the system call is performed by calling svc #0 + * - syscall return comes in r0. + * - only lr is clobbered. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, ARM supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0"); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0") = (long)(arg1); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0") = (long)(arg1); \ + register long _arg2 asm("r1") = (long)(arg2); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0") = (long)(arg1); \ + register long _arg2 asm("r1") = (long)(arg2); \ + register long _arg3 asm("r2") = (long)(arg3); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0") = (long)(arg1); \ + register long _arg2 asm("r1") = (long)(arg2); \ + register long _arg3 asm("r2") = (long)(arg3); \ + register long _arg4 asm("r3") = (long)(arg4); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num asm("r7") = (num); \ + register long _arg1 asm("r0") = (long)(arg1); \ + register long _arg2 asm("r1") = (long)(arg2); \ + register long _arg3 asm("r2") = (long)(arg3); \ + register long _arg4 asm("r3") = (long)(arg4); \ + register long _arg5 asm("r4") = (long)(arg5); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +/* startup code */ +asm(".section .text\n" + ".global _start\n" + "_start:\n" +#if defined(__THUMBEB__) || defined(__THUMBEL__) + /* We enter here in 32-bit mode but if some previous functions were in + * 16-bit mode, the assembler cannot know, so we need to tell it we're in + * 32-bit now, then switch to 16-bit (is there a better way to do it than + * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that + * it generates correct instructions. Note that we do not support thumb1. + */ + ".code 32\n" + "add r0, pc, #1\n" + "bx r0\n" + ".code 16\n" +#endif + "pop {%r0}\n" // argc was in the stack + "mov %r1, %sp\n" // argv = sp + "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... + "add %r2, %r2, $4\n" // ... + 4 + "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the + "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) + "bl main\n" // main() returns the status code, we'll exit with it. + "and %r0, %r0, $0xff\n" // limit exit code to 8 bits + "movs r7, $1\n" // NR_exit == 1 + "svc $0x00\n" + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). In big endian, the format + * differs as devices are returned as short only. + */ +struct sys_stat_struct { +#if defined(__ARMEB__) + unsigned short st_dev; + unsigned short __pad1; +#else + unsigned long st_dev; +#endif + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; +#if defined(__ARMEB__) + unsigned short st_rdev; + unsigned short __pad2; +#else + unsigned long st_rdev; +#endif + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +#elif defined(__aarch64__) +/* Syscalls for AARCH64 : + * - registers are 64-bit + * - stack is 16-byte aligned + * - syscall number is passed in x8 + * - arguments are in x0, x1, x2, x3, x4, x5 + * - the system call is performed by calling svc 0 + * - syscall return comes in x0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * + * On aarch64, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0"); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + register long _arg2 asm("x1") = (long)(arg2); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + register long _arg2 asm("x1") = (long)(arg2); \ + register long _arg3 asm("x2") = (long)(arg3); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + register long _arg2 asm("x1") = (long)(arg2); \ + register long _arg3 asm("x2") = (long)(arg3); \ + register long _arg4 asm("x3") = (long)(arg4); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + register long _arg2 asm("x1") = (long)(arg2); \ + register long _arg3 asm("x2") = (long)(arg3); \ + register long _arg4 asm("x3") = (long)(arg4); \ + register long _arg5 asm("x4") = (long)(arg5); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num asm("x8") = (num); \ + register long _arg1 asm("x0") = (long)(arg1); \ + register long _arg2 asm("x1") = (long)(arg2); \ + register long _arg3 asm("x2") = (long)(arg3); \ + register long _arg4 asm("x3") = (long)(arg4); \ + register long _arg5 asm("x4") = (long)(arg5); \ + register long _arg6 asm("x5") = (long)(arg6); \ + \ + asm volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +asm(".section .text\n" + ".global _start\n" + "_start:\n" + "ldr x0, [sp]\n" // argc (x0) was in the stack + "add x1, sp, 8\n" // argv (x1) = sp + "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... + "add x2, x2, 8\n" // + 8 (skip null) + "add x2, x2, x1\n" // + argv + "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee + "bl main\n" // main() returns the status code, we'll exit with it. + "and x0, x0, 0xff\n" // limit exit code to 8 bits + "mov x8, 93\n" // NR_exit == 93 + "svc #0\n" + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the newfstatat() syscall. Differs slightly from the + * x86_64's stat one by field ordering, so be careful. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + + unsigned long st_rdev; + unsigned long __pad1; + long st_size; + int st_blksize; + int __pad2; + + long st_blocks; + long st_atime; + unsigned long st_atime_nsec; + long st_mtime; + + unsigned long st_mtime_nsec; + long st_ctime; + unsigned long st_ctime_nsec; + unsigned int __unused[2]; +}; + +#elif defined(__mips__) && defined(_ABIO32) +/* Syscalls for MIPS ABI O32 : + * - WARNING! there's always a delayed slot! + * - WARNING again, the syntax is different, registers take a '$' and numbers + * do not. + * - registers are 32-bit + * - stack is 8-byte aligned + * - syscall number is passed in v0 (starts at 0xfa0). + * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to + * leave some room in the stack for the callee to save a0..a3 if needed. + * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are + * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as + * scall32-o32.S in the kernel sources. + * - the system call is performed by calling "syscall" + * - syscall return comes in v0, and register a3 needs to be checked to know + * if an error occured, in which case errno is in v0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + */ + +#define my_syscall0(num) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg4 asm("a3"); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "r"(_num) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg4 asm("a3"); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg4 asm("a3"); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3"); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3") = (long)(arg4); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num asm("v0") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3") = (long)(arg4); \ + register long _arg5 = (long)(arg5); \ + \ + asm volatile ( \ + "addiu $sp, $sp, -32\n" \ + "sw %7, 16($sp)\n" \ + "syscall\n " \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +/* startup code, note that it's called __start on MIPS */ +asm(".section .text\n" + ".set nomips16\n" + ".global __start\n" + ".set noreorder\n" + ".option pic0\n" + ".ent __start\n" + "__start:\n" + "lw $a0,($sp)\n" // argc was in the stack + "addiu $a1, $sp, 4\n" // argv = sp + 4 + "sll $a2, $a0, 2\n" // a2 = argc * 4 + "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... + "addiu $a2, $a2, 4\n" // ... + 4 + "li $t0, -8\n" + "and $sp, $sp, $t0\n" // sp must be 8-byte aligned + "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! + "jal main\n" // main() returns the status code, we'll exit with it. + "nop\n" // delayed slot + "and $a0, $v0, 0xff\n" // limit exit code to 8 bits + "li $v0, 4001\n" // NR_exit == 4001 + "syscall\n" + ".end __start\n" + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_APPEND 0x0008 +#define O_NONBLOCK 0x0080 +#define O_CREAT 0x0100 +#define O_TRUNC 0x0200 +#define O_EXCL 0x0400 +#define O_NOCTTY 0x0800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall. 88 bytes are returned by the + * syscall. + */ +struct sys_stat_struct { + unsigned int st_dev; + long st_pad1[3]; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + unsigned int st_rdev; + long st_pad2[2]; + long st_size; + long st_pad3; + long st_atime; + long st_atime_nsec; + long st_mtime; + long st_mtime_nsec; + long st_ctime; + long st_ctime_nsec; + long st_blksize; + long st_blocks; + long st_pad4[14]; +}; + +#endif + + +/* Below are the C functions used to declare the raw syscalls. They try to be + * architecture-agnostic, and return either a success or -errno. Declaring them + * static will lead to them being inlined in most cases, but it's still possible + * to reference them by a pointer if needed. + */ +static __attribute__((unused)) +void *sys_brk(void *addr) +{ + return (void *)my_syscall1(__NR_brk, addr); +} + +static __attribute__((noreturn,unused)) +void sys_exit(int status) +{ + my_syscall1(__NR_exit, status & 255); + while(1); // shut the "noreturn" warnings. +} + +static __attribute__((unused)) +int sys_chdir(const char *path) +{ + return my_syscall1(__NR_chdir, path); +} + +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); +#else + return my_syscall2(__NR_chmod, path, mode); +#endif +} + +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); +#else + return my_syscall3(__NR_chown, path, owner, group); +#endif +} + +static __attribute__((unused)) +int sys_chroot(const char *path) +{ + return my_syscall1(__NR_chroot, path); +} + +static __attribute__((unused)) +int sys_close(int fd) +{ + return my_syscall1(__NR_close, fd); +} + +static __attribute__((unused)) +int sys_dup(int fd) +{ + return my_syscall1(__NR_dup, fd); +} + +static __attribute__((unused)) +int sys_dup2(int old, int new) +{ + return my_syscall2(__NR_dup2, old, new); +} + +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)) +pid_t sys_fork(void) +{ + return my_syscall0(__NR_fork); +} + +static __attribute__((unused)) +int sys_fsync(int fd) +{ + return my_syscall1(__NR_fsync, fd); +} + +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)) +pid_t sys_getpgrp(void) +{ + return my_syscall0(__NR_getpgrp); +} + +static __attribute__((unused)) +pid_t sys_getpid(void) +{ + return my_syscall0(__NR_getpid); +} + +static __attribute__((unused)) +int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return my_syscall2(__NR_gettimeofday, tv, tz); +} + +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 sys_kill(pid_t pid, int signal) +{ + return my_syscall2(__NR_kill, pid, signal); +} + +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); +#else + return my_syscall2(__NR_link, old, new); +#endif +} + +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)) +int sys_mkdir(const char *path, mode_t mode) +{ +#ifdef __NR_mkdirat + return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode); +#else + return my_syscall2(__NR_mkdir, path, mode); +#endif +} + +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); +#else + return my_syscall3(__NR_mknod, path, mode, dev); +#endif +} + +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 sys_open(const char *path, int flags, mode_t mode) +{ +#ifdef __NR_openat + return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode); +#else + return my_syscall3(__NR_open, path, flags, mode); +#endif +} + +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 sys_poll(struct pollfd *fds, int nfds, int timeout) +{ + return my_syscall3(__NR_poll, fds, nfds, timeout); +} + +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 sys_reboot(int magic1, int magic2, int cmd, void *arg) +{ + return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg); +} + +static __attribute__((unused)) +int sys_sched_yield(void) +{ + return my_syscall0(__NR_sched_yield); +} + +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); +#else +#ifndef __NR__newselect +#define __NR__newselect __NR_select +#endif + return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); +#endif +} + +static __attribute__((unused)) +int sys_setpgid(pid_t pid, pid_t pgid) +{ + return my_syscall2(__NR_setpgid, pid, pgid); +} + +static __attribute__((unused)) +pid_t sys_setsid(void) +{ + return my_syscall0(__NR_setsid); +} + +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); +#else + ret = my_syscall2(__NR_stat, path, &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 sys_symlink(const char *old, const char *new) +{ +#ifdef __NR_symlinkat + return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new); +#else + return my_syscall2(__NR_symlink, old, new); +#endif +} + +static __attribute__((unused)) +mode_t sys_umask(mode_t mode) +{ + return my_syscall1(__NR_umask, mode); +} + +static __attribute__((unused)) +int sys_umount2(const char *path, int flags) +{ + return my_syscall2(__NR_umount2, path, flags); +} + +static __attribute__((unused)) +int sys_unlink(const char *path) +{ +#ifdef __NR_unlinkat + return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0); +#else + return my_syscall1(__NR_unlink, path); +#endif +} + +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 sys_waitpid(pid_t pid, int *status, int options) +{ + return sys_wait4(pid, status, options, 0); +} + +static __attribute__((unused)) +pid_t sys_wait(int *status) +{ + return sys_waitpid(-1, status, 0); +} + +static __attribute__((unused)) +ssize_t sys_write(int fd, const void *buf, size_t count) +{ + return my_syscall3(__NR_write, fd, buf, count); +} + + +/* Below are the libc-compatible syscalls which return x or -1 and set errno. + * They rely on the functions above. Similarly they're marked static so that it + * is possible to assign pointers to them if needed. + */ + +static __attribute__((unused)) +int brk(void *addr) +{ + void *ret = sys_brk(addr); + + if (!ret) { + SET_ERRNO(ENOMEM); + return -1; + } + return 0; +} + +static __attribute__((noreturn,unused)) +void exit(int status) +{ + sys_exit(status); +} + +static __attribute__((unused)) +int chdir(const char *path) +{ + int ret = sys_chdir(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +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; +} + +static __attribute__((unused)) +int chroot(const char *path) +{ + int ret = sys_chroot(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +int close(int fd) +{ + int ret = sys_close(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +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; +} + +static __attribute__((unused)) +pid_t fork(void) +{ + pid_t ret = sys_fork(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +int fsync(int fd) +{ + int ret = sys_fsync(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +static __attribute__((unused)) +pid_t getpgrp(void) +{ + pid_t ret = sys_getpgrp(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +pid_t getpid(void) +{ + pid_t ret = sys_getpid(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +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; +} + +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; +} + +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; +} + +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; +} + +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; +} + +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; +} + +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; +} + +static __attribute__((unused)) +int open(const char *path, int flags, mode_t mode) +{ + int ret = sys_open(path, flags, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +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; +} + +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; +} + +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; +} + +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; +} + +static __attribute__((unused)) +int sched_yield(void) +{ + int ret = sys_sched_yield(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +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; +} + +static __attribute__((unused)) +pid_t setsid(void) +{ + pid_t ret = sys_setsid(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +unsigned int sleep(unsigned int seconds) +{ + struct timeval my_timeval = { seconds, 0 }; + + if (sys_select(0, 0, 0, 0, &my_timeval) < 0) + return my_timeval.tv_sec + !!my_timeval.tv_usec; + else + return 0; +} + +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; +} + +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; +} + +static __attribute__((unused)) +int tcsetpgrp(int fd, pid_t pid) +{ + return ioctl(fd, TIOCSPGRP, &pid); +} + +static __attribute__((unused)) +mode_t umask(mode_t mode) +{ + return sys_umask(mode); +} + +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; +} + +static __attribute__((unused)) +int unlink(const char *path) +{ + int ret = sys_unlink(path); + + 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_waitpid(pid, status, options); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +pid_t wait(int *status) +{ + pid_t ret = sys_wait(status); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +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; +} + +/* some size-optimized reimplementations of a few common str* and mem* + * functions. They're marked static, except memcpy() and raise() which are used + * by libgcc on ARM, so they are marked weak instead in order not to cause an + * error when building a program made of multiple files (not recommended). + */ + +static __attribute__((unused)) +void *memmove(void *dst, const void *src, size_t len) +{ + ssize_t pos = (dst <= src) ? -1 : (long)len; + void *ret = dst; + + while (len--) { + pos += (dst <= src) ? 1 : -1; + ((char *)dst)[pos] = ((char *)src)[pos]; + } + return ret; +} + +static __attribute__((unused)) +void *memset(void *dst, int b, size_t len) +{ + char *p = dst; + + while (len--) + *(p++) = b; + return dst; +} + +static __attribute__((unused)) +int memcmp(const void *s1, const void *s2, size_t n) +{ + size_t ofs = 0; + char c1 = 0; + + while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + ofs++; + } + return c1; +} + +static __attribute__((unused)) +char *strcpy(char *dst, const char *src) +{ + char *ret = dst; + + while ((*dst++ = *src++)); + return ret; +} + +static __attribute__((unused)) +char *strchr(const char *s, int c) +{ + while (*s) { + if (*s == (char)c) + return (char *)s; + s++; + } + return NULL; +} + +static __attribute__((unused)) +char *strrchr(const char *s, int c) +{ + const char *ret = NULL; + + while (*s) { + if (*s == (char)c) + ret = s; + s++; + } + return (char *)ret; +} + +static __attribute__((unused)) +size_t nolibc_strlen(const char *str) +{ + size_t len; + + for (len = 0; str[len]; len++); + return len; +} + +#define strlen(str) ({ \ + __builtin_constant_p((str)) ? \ + __builtin_strlen((str)) : \ + nolibc_strlen((str)); \ +}) + +static __attribute__((unused)) +int isdigit(int c) +{ + return (unsigned int)(c - '0') <= 9; +} + +static __attribute__((unused)) +long atol(const char *s) +{ + unsigned long ret = 0; + unsigned long d; + int neg = 0; + + if (*s == '-') { + neg = 1; + s++; + } + + while (1) { + d = (*s++) - '0'; + if (d > 9) + break; + ret *= 10; + ret += d; + } + + return neg ? -ret : ret; +} + +static __attribute__((unused)) +int atoi(const char *s) +{ + return atol(s); +} + +static __attribute__((unused)) +const char *ltoa(long in) +{ + /* large enough for -9223372036854775808 */ + static char buffer[21]; + char *pos = buffer + sizeof(buffer) - 1; + int neg = in < 0; + unsigned long n = neg ? -in : in; + + *pos-- = '\0'; + do { + *pos-- = '0' + n % 10; + n /= 10; + if (pos < buffer) + return pos + 1; + } while (n); + + if (neg) + *pos-- = '-'; + return pos + 1; +} + +__attribute__((weak,unused)) +void *memcpy(void *dst, const void *src, size_t len) +{ + return memmove(dst, src, len); +} + +/* needed by libgcc for divide by zero */ +__attribute__((weak,unused)) +int raise(int signal) +{ + return kill(getpid(), signal); +} + +/* Here come a few helper functions */ + +static __attribute__((unused)) +void FD_ZERO(fd_set *set) +{ + memset(set, 0, sizeof(*set)); +} + +static __attribute__((unused)) +void FD_SET(int fd, fd_set *set) +{ + if (fd < 0 || fd >= FD_SETSIZE) + return; + set->fd32[fd / 32] |= 1 << (fd & 31); +} + +/* WARNING, it only deals with the 4096 first majors and 256 first minors */ +static __attribute__((unused)) +dev_t makedev(unsigned int major, unsigned int minor) +{ + return ((major & 0xfff) << 8) | (minor & 0xff); +} diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index c7f3321fbe43..d90127298f12 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -738,9 +738,11 @@ __SYSCALL(__NR_statx, sys_statx) __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) #define __NR_rseq 293 __SYSCALL(__NR_rseq, sys_rseq) +#define __NR_kexec_file_load 294 +__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) #undef __NR_syscalls -#define __NR_syscalls 294 +#define __NR_syscalls 295 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h index 8dd6aefdafa4..57aaeaf8e192 100644 --- a/tools/include/uapi/asm/bitsperlong.h +++ b/tools/include/uapi/asm/bitsperlong.h @@ -13,6 +13,10 @@ #include "../../arch/mips/include/uapi/asm/bitsperlong.h" #elif defined(__ia64__) #include "../../arch/ia64/include/uapi/asm/bitsperlong.h" +#elif defined(__riscv) +#include "../../arch/riscv/include/uapi/asm/bitsperlong.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/bitsperlong.h" #else #include <asm-generic/bitsperlong.h> #endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index a4446f452040..298b2e197744 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -412,6 +412,14 @@ typedef struct drm_i915_irq_wait { int irq_seq; } drm_i915_irq_wait_t; +/* + * Different modes of per-process Graphics Translation Table, + * see I915_PARAM_HAS_ALIASING_PPGTT + */ +#define I915_GEM_PPGTT_NONE 0 +#define I915_GEM_PPGTT_ALIASING 1 +#define I915_GEM_PPGTT_FULL 2 + /* Ioctl to query kernel params: */ #define I915_PARAM_IRQ_ACTIVE 1 diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 91c43884f295..3c38ac9a92a7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -14,6 +14,7 @@ /* Extended instruction set based on top of classic BPF */ /* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ @@ -266,6 +267,7 @@ enum bpf_attach_type { #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ /* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) @@ -2014,6 +2016,19 @@ union bpf_attr { * Only works if *skb* contains an IPv6 packet. Insert a * Segment Routing Header (**struct ipv6_sr_hdr**) inside * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to LWT_BPF_MAX_HEADROOM total + * bytes in all prepended headers. Please note that + * if skb_is_gso(skb) is true, no more than two headers + * can be prepended, and the inner header, if present, + * should be either GRE or UDP/GUE. + * + * BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of + * type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called + * by bpf programs of types BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT. * * A call to this helper is susceptible to change the underlaying * packet buffer. Therefore, at load time, all checks on pointers @@ -2327,6 +2342,30 @@ union bpf_attr { * "**y**". * Return * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in bpf_sock can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or NULL in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * + * Return + * A **struct bpf_tcp_sock** pointer on success, or NULL in + * case of failure. + * + * int bpf_skb_ecn_set_ce(struct sk_buf *skb) + * Description + * Sets ECN of IP header to ce (congestion encountered) if + * current value is ect (ECN capable). Works with IPv6 and IPv4. + * Return + * 1 if set, 0 if not set. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2421,7 +2460,12 @@ union bpf_attr { FN(map_peek_elem), \ FN(msg_push_data), \ FN(msg_pop_data), \ - FN(rc_pointer_rel), + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), \ + FN(skb_ecn_set_ce), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2494,7 +2538,8 @@ enum bpf_hdr_start_off { /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6, - BPF_LWT_ENCAP_SEG6_INLINE + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, }; #define __bpf_md_ptr(type, name) \ @@ -2540,6 +2585,8 @@ struct __sk_buff { __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); __u64 tstamp; __u32 wire_len; + __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); }; struct bpf_tunnel_key { @@ -2581,7 +2628,15 @@ enum bpf_ret_code { BPF_DROP = 2, /* 3-6 reserved */ BPF_REDIRECT = 7, - /* >127 are reserved for prog type specific return codes */ + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, }; struct bpf_sock { @@ -2591,14 +2646,52 @@ struct bpf_sock { __u32 protocol; __u32 mark; __u32 priority; - __u32 src_ip4; /* Allows 1,2,4-byte read. - * Stored in network byte order. + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __u32 dst_port; /* network byte order */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. */ - __u32 src_ip6[4]; /* Allows 1,2,4-byte read. - * Stored in network byte order. + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. */ - __u32 src_port; /* Allows 4-byte read. - * Stored in host byte order + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. */ }; @@ -2728,6 +2821,8 @@ struct bpf_prog_info { __u32 jited_line_info_rec_size; __u32 nr_prog_tags; __aligned_u64 prog_tags; + __u64 run_time_ns; + __u64 run_cnt; } __attribute__((aligned(8))); struct bpf_map_info { @@ -3054,4 +3149,7 @@ struct bpf_line_info { __u32 line_col; }; +struct bpf_spin_lock { + __u32 val; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h new file mode 100644 index 000000000000..c86c3e942df9 --- /dev/null +++ b/tools/include/uapi/linux/ethtool.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ethtool.h: Defines for Linux ethtool. + * + * Copyright (C) 1998 David S. Miller (davem@redhat.com) + * Copyright 2001 Jeff Garzik <jgarzik@pobox.com> + * Portions Copyright 2001 Sun Microsystems (thockin@sun.com) + * Portions Copyright 2002 Intel (eli.kupermann@intel.com, + * christopher.leech@intel.com, + * scott.feldman@intel.com) + * Portions Copyright (C) Sun Microsystems 2008 + */ + +#ifndef _UAPI_LINUX_ETHTOOL_H +#define _UAPI_LINUX_ETHTOOL_H + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/if_ether.h> + +#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */ + +/** + * struct ethtool_channels - configuring number of network channel + * @cmd: ETHTOOL_{G,S}CHANNELS + * @max_rx: Read only. Maximum number of receive channel the driver support. + * @max_tx: Read only. Maximum number of transmit channel the driver support. + * @max_other: Read only. Maximum number of other channel the driver support. + * @max_combined: Read only. Maximum number of combined channel the driver + * support. Set of queues RX, TX or other. + * @rx_count: Valid values are in the range 1 to the max_rx. + * @tx_count: Valid values are in the range 1 to the max_tx. + * @other_count: Valid values are in the range 1 to the max_other. + * @combined_count: Valid values are in the range 1 to the max_combined. + * + * This can be used to configure RX, TX and other channels. + */ + +struct ethtool_channels { + __u32 cmd; + __u32 max_rx; + __u32 max_tx; + __u32 max_other; + __u32 max_combined; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +#endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index a441ea1bfe6d..121e82ce296b 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -14,6 +14,11 @@ #include <linux/ioctl.h> #include <linux/types.h> +/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#if !defined(__KERNEL__) +#include <linux/mount.h> +#endif + /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change * the file limit at runtime and only root can increase the per-process @@ -101,57 +106,6 @@ struct inodes_stat_t { #define NR_FILE 8192 /* this can well be larger on a larger system */ - -/* - * These are the fs-independent mount-flags: up to 32 flags are supported - */ -#define MS_RDONLY 1 /* Mount read-only */ -#define MS_NOSUID 2 /* Ignore suid and sgid bits */ -#define MS_NODEV 4 /* Disallow access to device special files */ -#define MS_NOEXEC 8 /* Disallow program execution */ -#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ -#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ -#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ -#define MS_NOATIME 1024 /* Do not update access times. */ -#define MS_NODIRATIME 2048 /* Do not update directory access times */ -#define MS_BIND 4096 -#define MS_MOVE 8192 -#define MS_REC 16384 -#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. - MS_VERBOSE is deprecated. */ -#define MS_SILENT 32768 -#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define MS_UNBINDABLE (1<<17) /* change to unbindable */ -#define MS_PRIVATE (1<<18) /* change to private */ -#define MS_SLAVE (1<<19) /* change to slave */ -#define MS_SHARED (1<<20) /* change to shared */ -#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ -#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define MS_I_VERSION (1<<23) /* Update inode I_version field */ -#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ -#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define MS_SUBMOUNT (1<<26) -#define MS_NOREMOTELOCK (1<<27) -#define MS_NOSEC (1<<28) -#define MS_BORN (1<<29) -#define MS_ACTIVE (1<<30) -#define MS_NOUSER (1<<31) - -/* - * Superblock flags that can be altered by MS_REMOUNT - */ -#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ - MS_LAZYTIME) - -/* - * Old magic mount flag and mask - */ -#define MS_MGC_VAL 0xC0ED0000 -#define MS_MGC_MSK 0xffff0000 - /* * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR. */ @@ -269,7 +223,8 @@ struct fsxattr { #define FS_POLICY_FLAGS_PAD_16 0x02 #define FS_POLICY_FLAGS_PAD_32 0x03 #define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 +#define FS_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */ +#define FS_POLICY_FLAGS_VALID 0x07 /* Encryption algorithms */ #define FS_ENCRYPTION_MODE_INVALID 0 @@ -281,6 +236,7 @@ struct fsxattr { #define FS_ENCRYPTION_MODE_AES_128_CTS 6 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* Removed, do not use. */ #define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* Removed, do not use. */ +#define FS_ENCRYPTION_MODE_ADIANTUM 9 struct fscrypt_policy { __u8 version; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 1debfa42cba1..5b225ff63b48 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -288,6 +288,7 @@ enum { IFLA_BR_MCAST_IGMP_VERSION, IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, + IFLA_BR_MULTI_BOOLOPT, __IFLA_BR_MAX, }; @@ -533,6 +534,7 @@ enum { IFLA_VXLAN_LABEL, IFLA_VXLAN_GPE, IFLA_VXLAN_TTL_INHERIT, + IFLA_VXLAN_DF, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -542,6 +544,14 @@ struct ifla_vxlan_port_range { __be16 high; }; +enum ifla_vxlan_df { + VXLAN_DF_UNSET = 0, + VXLAN_DF_SET, + VXLAN_DF_INHERIT, + __VXLAN_DF_END, + VXLAN_DF_MAX = __VXLAN_DF_END - 1, +}; + /* GENEVE section */ enum { IFLA_GENEVE_UNSPEC, @@ -557,10 +567,19 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, IFLA_GENEVE_TTL_INHERIT, + IFLA_GENEVE_DF, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) +enum ifla_geneve_df { + GENEVE_DF_UNSET = 0, + GENEVE_DF_SET, + GENEVE_DF_INHERIT, + __GENEVE_DF_END, + GENEVE_DF_MAX = __GENEVE_DF_END - 1, +}; + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -906,6 +925,7 @@ enum { enum { LINK_XSTATS_TYPE_UNSPEC, LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, __LINK_XSTATS_TYPE_MAX }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h new file mode 100644 index 000000000000..caed8b1614ff --- /dev/null +++ b/tools/include/uapi/linux/if_xdp.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * if_xdp: XDP socket user-space interface + * Copyright(c) 2018 Intel Corporation. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#ifndef _LINUX_IF_XDP_H +#define _LINUX_IF_XDP_H + +#include <linux/types.h> + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM (1 << 0) +#define XDP_COPY (1 << 1) /* Force copy-mode */ +#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ + +struct sockaddr_xdp { + __u16 sxdp_family; + __u16 sxdp_flags; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; +}; + +struct xdp_ring_offset { + __u64 producer; + __u64 consumer; + __u64 desc; +}; + +struct xdp_mmap_offsets { + struct xdp_ring_offset rx; + struct xdp_ring_offset tx; + struct xdp_ring_offset fr; /* Fill */ + struct xdp_ring_offset cr; /* Completion */ +}; + +/* XDP socket options */ +#define XDP_MMAP_OFFSETS 1 +#define XDP_RX_RING 2 +#define XDP_TX_RING 3 +#define XDP_UMEM_REG 4 +#define XDP_UMEM_FILL_RING 5 +#define XDP_UMEM_COMPLETION_RING 6 +#define XDP_STATISTICS 7 + +struct xdp_umem_reg { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ +}; + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL + +/* Rx/Tx descriptor */ +struct xdp_desc { + __u64 addr; + __u32 len; + __u32 options; +}; + +/* UMEM descriptor is __u64 */ + +#endif /* _LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 48e8a225b985..a55cb8b10165 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -266,10 +266,14 @@ struct sockaddr_in { #define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) #define IN_MULTICAST(a) IN_CLASSD(a) -#define IN_MULTICAST_NET 0xF0000000 +#define IN_MULTICAST_NET 0xe0000000 -#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) -#define IN_BADCLASS(a) IN_EXPERIMENTAL((a)) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) +#define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) + +#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_CLASSE_NET 0xffffffff +#define IN_CLASSE_NSHIFT 0 /* Address to accept any incoming messages. */ #define INADDR_ANY ((unsigned long int) 0x00000000) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 2b7a652c9fa4..6d4ea4b6c922 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -492,6 +492,17 @@ struct kvm_dirty_log { }; }; +/* for KVM_CLEAR_DIRTY_LOG */ +struct kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; @@ -975,6 +986,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163 #define KVM_CAP_EXCEPTION_PAYLOAD 164 #define KVM_CAP_ARM_VM_IPA_SIZE 165 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 +#define KVM_CAP_HYPERV_CPUID 167 #ifdef KVM_CAP_IRQ_ROUTING @@ -1421,6 +1434,12 @@ struct kvm_enc_region { #define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) #define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) +/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */ +#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) + +/* Available with KVM_CAP_HYPERV_CPUID */ +#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h new file mode 100644 index 000000000000..3f9ec42510b0 --- /dev/null +++ b/tools/include/uapi/linux/mount.h @@ -0,0 +1,58 @@ +#ifndef _UAPI_LINUX_MOUNT_H +#define _UAPI_LINUX_MOUNT_H + +/* + * These are the fs-independent mount-flags: up to 32 flags are supported + * + * Usage of these is restricted within the kernel to core mount(2) code and + * callers of sys_mount() only. Filesystems should be using the SB_* + * equivalent instead. + */ +#define MS_RDONLY 1 /* Mount read-only */ +#define MS_NOSUID 2 /* Ignore suid and sgid bits */ +#define MS_NODEV 4 /* Disallow access to device special files */ +#define MS_NOEXEC 8 /* Disallow program execution */ +#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ +#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ +#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOATIME 1024 /* Do not update access times. */ +#define MS_NODIRATIME 2048 /* Do not update directory access times */ +#define MS_BIND 4096 +#define MS_MOVE 8192 +#define MS_REC 16384 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 +#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ +#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ +#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define MS_I_VERSION (1<<23) /* Update inode I_version field */ +#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define MS_SUBMOUNT (1<<26) +#define MS_NOREMOTELOCK (1<<27) +#define MS_NOSEC (1<<28) +#define MS_BORN (1<<29) +#define MS_ACTIVE (1<<30) +#define MS_NOUSER (1<<31) + +/* + * Superblock flags that can be altered by MS_REMOUNT + */ +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ + MS_LAZYTIME) + +/* + * Old magic mount flag and mask + */ +#define MS_MGC_VAL 0xC0ED0000 +#define MS_MGC_MSK 0xffff0000 + +#endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 9de8780ac8d9..7198ddd0c6b1 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -372,7 +372,9 @@ struct perf_event_attr { context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ - __reserved_1 : 35; + ksymbol : 1, /* include ksymbol events */ + bpf_event : 1, /* include bpf events */ + __reserved_1 : 33; union { __u32 wakeup_events; /* wakeup every n events */ @@ -445,8 +447,6 @@ struct perf_event_query_bpf { __u32 ids[0]; }; -#define perf_flags(attr) (*(&(attr)->read_format + 1)) - /* * Ioctls that can be done on a perf event fd: */ @@ -965,9 +965,58 @@ enum perf_event_type { */ PERF_RECORD_NAMESPACES = 16, + /* + * Record ksymbol register/unregister events: + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u32 len; + * u16 ksym_type; + * u16 flags; + * char name[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_KSYMBOL = 17, + + /* + * Record bpf events: + * enum perf_bpf_event_type { + * PERF_BPF_EVENT_UNKNOWN = 0, + * PERF_BPF_EVENT_PROG_LOAD = 1, + * PERF_BPF_EVENT_PROG_UNLOAD = 2, + * }; + * + * struct { + * struct perf_event_header header; + * u16 type; + * u16 flags; + * u32 id; + * u8 tag[BPF_TAG_SIZE]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_BPF_EVENT = 18, + PERF_RECORD_MAX, /* non-ABI */ }; +enum perf_record_ksymbol_type { + PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0, + PERF_RECORD_KSYMBOL_TYPE_BPF = 1, + PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ +}; + +#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) + +enum perf_bpf_event_type { + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ +}; + #define PERF_MAX_STACK_DEPTH 127 #define PERF_MAX_CONTEXTS_PER_STACK 8 diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h new file mode 100644 index 000000000000..0d18b1d1fbbc --- /dev/null +++ b/tools/include/uapi/linux/pkt_sched.h @@ -0,0 +1,1163 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_SCHED_H +#define __LINUX_PKT_SCHED_H + +#include <linux/types.h> + +/* Logical priority bands not depending on specific packet scheduler. + Every scheduler will map them to real traffic classes, if it has + no more precise mechanism to classify packets. + + These numbers have no special meaning, though their coincidence + with obsolete IPv6 values is not occasional :-). New IPv6 drafts + preferred full anarchy inspired by diffserv group. + + Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy + class, actually, as rule it will be handled with more care than + filler or even bulk. + */ + +#define TC_PRIO_BESTEFFORT 0 +#define TC_PRIO_FILLER 1 +#define TC_PRIO_BULK 2 +#define TC_PRIO_INTERACTIVE_BULK 4 +#define TC_PRIO_INTERACTIVE 6 +#define TC_PRIO_CONTROL 7 + +#define TC_PRIO_MAX 15 + +/* Generic queue statistics, available for all the elements. + Particular schedulers may have also their private records. + */ + +struct tc_stats { + __u64 bytes; /* Number of enqueued bytes */ + __u32 packets; /* Number of enqueued packets */ + __u32 drops; /* Packets dropped because of lack of resources */ + __u32 overlimits; /* Number of throttle events when this + * flow goes out of allocated bandwidth */ + __u32 bps; /* Current flow byte rate */ + __u32 pps; /* Current flow packet rate */ + __u32 qlen; + __u32 backlog; +}; + +struct tc_estimator { + signed char interval; + unsigned char ewma_log; +}; + +/* "Handles" + --------- + + All the traffic control objects have 32bit identifiers, or "handles". + + They can be considered as opaque numbers from user API viewpoint, + but actually they always consist of two fields: major and + minor numbers, which are interpreted by kernel specially, + that may be used by applications, though not recommended. + + F.e. qdisc handles always have minor number equal to zero, + classes (or flows) have major equal to parent qdisc major, and + minor uniquely identifying class inside qdisc. + + Macros to manipulate handles: + */ + +#define TC_H_MAJ_MASK (0xFFFF0000U) +#define TC_H_MIN_MASK (0x0000FFFFU) +#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK) +#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK) +#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK)) + +#define TC_H_UNSPEC (0U) +#define TC_H_ROOT (0xFFFFFFFFU) +#define TC_H_INGRESS (0xFFFFFFF1U) +#define TC_H_CLSACT TC_H_INGRESS + +#define TC_H_MIN_PRIORITY 0xFFE0U +#define TC_H_MIN_INGRESS 0xFFF2U +#define TC_H_MIN_EGRESS 0xFFF3U + +/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */ +enum tc_link_layer { + TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */ + TC_LINKLAYER_ETHERNET, + TC_LINKLAYER_ATM, +}; +#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */ + +struct tc_ratespec { + unsigned char cell_log; + __u8 linklayer; /* lower 4 bits */ + unsigned short overhead; + short cell_align; + unsigned short mpu; + __u32 rate; +}; + +#define TC_RTAB_SIZE 1024 + +struct tc_sizespec { + unsigned char cell_log; + unsigned char size_log; + short cell_align; + int overhead; + unsigned int linklayer; + unsigned int mpu; + unsigned int mtu; + unsigned int tsize; +}; + +enum { + TCA_STAB_UNSPEC, + TCA_STAB_BASE, + TCA_STAB_DATA, + __TCA_STAB_MAX +}; + +#define TCA_STAB_MAX (__TCA_STAB_MAX - 1) + +/* FIFO section */ + +struct tc_fifo_qopt { + __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */ +}; + +/* SKBPRIO section */ + +/* + * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1). + * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able + * to map one to one the DS field of IPV4 and IPV6 headers. + * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY. + */ + +#define SKBPRIO_MAX_PRIORITY 64 + +struct tc_skbprio_qopt { + __u32 limit; /* Queue length in packets. */ +}; + +/* PRIO section */ + +#define TCQ_PRIO_BANDS 16 +#define TCQ_MIN_PRIO_BANDS 2 + +struct tc_prio_qopt { + int bands; /* Number of bands */ + __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */ +}; + +/* MULTIQ section */ + +struct tc_multiq_qopt { + __u16 bands; /* Number of bands */ + __u16 max_bands; /* Maximum number of queues */ +}; + +/* PLUG section */ + +#define TCQ_PLUG_BUFFER 0 +#define TCQ_PLUG_RELEASE_ONE 1 +#define TCQ_PLUG_RELEASE_INDEFINITE 2 +#define TCQ_PLUG_LIMIT 3 + +struct tc_plug_qopt { + /* TCQ_PLUG_BUFFER: Inset a plug into the queue and + * buffer any incoming packets + * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head + * to beginning of the next plug. + * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue. + * Stop buffering packets until the next TCQ_PLUG_BUFFER + * command is received (just act as a pass-thru queue). + * TCQ_PLUG_LIMIT: Increase/decrease queue size + */ + int action; + __u32 limit; +}; + +/* TBF section */ + +struct tc_tbf_qopt { + struct tc_ratespec rate; + struct tc_ratespec peakrate; + __u32 limit; + __u32 buffer; + __u32 mtu; +}; + +enum { + TCA_TBF_UNSPEC, + TCA_TBF_PARMS, + TCA_TBF_RTAB, + TCA_TBF_PTAB, + TCA_TBF_RATE64, + TCA_TBF_PRATE64, + TCA_TBF_BURST, + TCA_TBF_PBURST, + TCA_TBF_PAD, + __TCA_TBF_MAX, +}; + +#define TCA_TBF_MAX (__TCA_TBF_MAX - 1) + + +/* TEQL section */ + +/* TEQL does not require any parameters */ + +/* SFQ section */ + +struct tc_sfq_qopt { + unsigned quantum; /* Bytes per round allocated to flow */ + int perturb_period; /* Period of hash perturbation */ + __u32 limit; /* Maximal packets in queue */ + unsigned divisor; /* Hash divisor */ + unsigned flows; /* Maximal number of flows */ +}; + +struct tc_sfqred_stats { + __u32 prob_drop; /* Early drops, below max threshold */ + __u32 forced_drop; /* Early drops, after max threshold */ + __u32 prob_mark; /* Marked packets, below max threshold */ + __u32 forced_mark; /* Marked packets, after max threshold */ + __u32 prob_mark_head; /* Marked packets, below max threshold */ + __u32 forced_mark_head;/* Marked packets, after max threshold */ +}; + +struct tc_sfq_qopt_v1 { + struct tc_sfq_qopt v0; + unsigned int depth; /* max number of packets per flow */ + unsigned int headdrop; +/* SFQRED parameters */ + __u32 limit; /* HARD maximal flow queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; + __u32 max_P; /* probability, high resolution */ +/* SFQRED stats */ + struct tc_sfqred_stats stats; +}; + + +struct tc_sfq_xstats { + __s32 allot; +}; + +/* RED section */ + +enum { + TCA_RED_UNSPEC, + TCA_RED_PARMS, + TCA_RED_STAB, + TCA_RED_MAX_P, + __TCA_RED_MAX, +}; + +#define TCA_RED_MAX (__TCA_RED_MAX - 1) + +struct tc_red_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; +#define TC_RED_ECN 1 +#define TC_RED_HARDDROP 2 +#define TC_RED_ADAPTATIVE 4 +}; + +struct tc_red_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ +}; + +/* GRED section */ + +#define MAX_DPs 16 + +enum { + TCA_GRED_UNSPEC, + TCA_GRED_PARMS, + TCA_GRED_STAB, + TCA_GRED_DPS, + TCA_GRED_MAX_P, + TCA_GRED_LIMIT, + TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */ + __TCA_GRED_MAX, +}; + +#define TCA_GRED_MAX (__TCA_GRED_MAX - 1) + +enum { + TCA_GRED_VQ_ENTRY_UNSPEC, + TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */ + __TCA_GRED_VQ_ENTRY_MAX, +}; +#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1) + +enum { + TCA_GRED_VQ_UNSPEC, + TCA_GRED_VQ_PAD, + TCA_GRED_VQ_DP, /* u32 */ + TCA_GRED_VQ_STAT_BYTES, /* u64 */ + TCA_GRED_VQ_STAT_PACKETS, /* u32 */ + TCA_GRED_VQ_STAT_BACKLOG, /* u32 */ + TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */ + TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */ + TCA_GRED_VQ_STAT_PDROP, /* u32 */ + TCA_GRED_VQ_STAT_OTHER, /* u32 */ + TCA_GRED_VQ_FLAGS, /* u32 */ + __TCA_GRED_VQ_MAX +}; + +#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1) + +struct tc_gred_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + __u32 DP; /* up to 2^32 DPs */ + __u32 backlog; + __u32 qave; + __u32 forced; + __u32 early; + __u32 other; + __u32 pdrop; + __u8 Wlog; /* log(W) */ + __u8 Plog; /* log(P_max/(qth_max-qth_min)) */ + __u8 Scell_log; /* cell size for idle damping */ + __u8 prio; /* prio of this VQ */ + __u32 packets; + __u32 bytesin; +}; + +/* gred setup */ +struct tc_gred_sopt { + __u32 DPs; + __u32 def_DP; + __u8 grio; + __u8 flags; + __u16 pad1; +}; + +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + TCA_CHOKE_MAX_P, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + +/* HTB section */ +#define TC_HTB_NUMPRIO 8 +#define TC_HTB_MAXDEPTH 8 +#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */ + +struct tc_htb_opt { + struct tc_ratespec rate; + struct tc_ratespec ceil; + __u32 buffer; + __u32 cbuffer; + __u32 quantum; + __u32 level; /* out only */ + __u32 prio; +}; +struct tc_htb_glob { + __u32 version; /* to match HTB/TC */ + __u32 rate2quantum; /* bps->quantum divisor */ + __u32 defcls; /* default class number */ + __u32 debug; /* debug flags */ + + /* stats */ + __u32 direct_pkts; /* count of non shaped packets */ +}; +enum { + TCA_HTB_UNSPEC, + TCA_HTB_PARMS, + TCA_HTB_INIT, + TCA_HTB_CTAB, + TCA_HTB_RTAB, + TCA_HTB_DIRECT_QLEN, + TCA_HTB_RATE64, + TCA_HTB_CEIL64, + TCA_HTB_PAD, + __TCA_HTB_MAX, +}; + +#define TCA_HTB_MAX (__TCA_HTB_MAX - 1) + +struct tc_htb_xstats { + __u32 lends; + __u32 borrows; + __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */ + __s32 tokens; + __s32 ctokens; +}; + +/* HFSC section */ + +struct tc_hfsc_qopt { + __u16 defcls; /* default class */ +}; + +struct tc_service_curve { + __u32 m1; /* slope of the first segment in bps */ + __u32 d; /* x-projection of the first segment in us */ + __u32 m2; /* slope of the second segment in bps */ +}; + +struct tc_hfsc_stats { + __u64 work; /* total work done */ + __u64 rtwork; /* work done by real-time criteria */ + __u32 period; /* current period */ + __u32 level; /* class level in hierarchy */ +}; + +enum { + TCA_HFSC_UNSPEC, + TCA_HFSC_RSC, + TCA_HFSC_FSC, + TCA_HFSC_USC, + __TCA_HFSC_MAX, +}; + +#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1) + + +/* CBQ section */ + +#define TC_CBQ_MAXPRIO 8 +#define TC_CBQ_MAXLEVEL 8 +#define TC_CBQ_DEF_EWMA 5 + +struct tc_cbq_lssopt { + unsigned char change; + unsigned char flags; +#define TCF_CBQ_LSS_BOUNDED 1 +#define TCF_CBQ_LSS_ISOLATED 2 + unsigned char ewma_log; + unsigned char level; +#define TCF_CBQ_LSS_FLAGS 1 +#define TCF_CBQ_LSS_EWMA 2 +#define TCF_CBQ_LSS_MAXIDLE 4 +#define TCF_CBQ_LSS_MINIDLE 8 +#define TCF_CBQ_LSS_OFFTIME 0x10 +#define TCF_CBQ_LSS_AVPKT 0x20 + __u32 maxidle; + __u32 minidle; + __u32 offtime; + __u32 avpkt; +}; + +struct tc_cbq_wrropt { + unsigned char flags; + unsigned char priority; + unsigned char cpriority; + unsigned char __reserved; + __u32 allot; + __u32 weight; +}; + +struct tc_cbq_ovl { + unsigned char strategy; +#define TC_CBQ_OVL_CLASSIC 0 +#define TC_CBQ_OVL_DELAY 1 +#define TC_CBQ_OVL_LOWPRIO 2 +#define TC_CBQ_OVL_DROP 3 +#define TC_CBQ_OVL_RCLASSIC 4 + unsigned char priority2; + __u16 pad; + __u32 penalty; +}; + +struct tc_cbq_police { + unsigned char police; + unsigned char __res1; + unsigned short __res2; +}; + +struct tc_cbq_fopt { + __u32 split; + __u32 defmap; + __u32 defchange; +}; + +struct tc_cbq_xstats { + __u32 borrows; + __u32 overactions; + __s32 avgidle; + __s32 undertime; +}; + +enum { + TCA_CBQ_UNSPEC, + TCA_CBQ_LSSOPT, + TCA_CBQ_WRROPT, + TCA_CBQ_FOPT, + TCA_CBQ_OVL_STRATEGY, + TCA_CBQ_RATE, + TCA_CBQ_RTAB, + TCA_CBQ_POLICE, + __TCA_CBQ_MAX, +}; + +#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) + +/* dsmark section */ + +enum { + TCA_DSMARK_UNSPEC, + TCA_DSMARK_INDICES, + TCA_DSMARK_DEFAULT_INDEX, + TCA_DSMARK_SET_TC_INDEX, + TCA_DSMARK_MASK, + TCA_DSMARK_VALUE, + __TCA_DSMARK_MAX, +}; + +#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1) + +/* ATM section */ + +enum { + TCA_ATM_UNSPEC, + TCA_ATM_FD, /* file/socket descriptor */ + TCA_ATM_PTR, /* pointer to descriptor - later */ + TCA_ATM_HDR, /* LL header */ + TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */ + TCA_ATM_ADDR, /* PVC address (for output only) */ + TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */ + __TCA_ATM_MAX, +}; + +#define TCA_ATM_MAX (__TCA_ATM_MAX - 1) + +/* Network emulator */ + +enum { + TCA_NETEM_UNSPEC, + TCA_NETEM_CORR, + TCA_NETEM_DELAY_DIST, + TCA_NETEM_REORDER, + TCA_NETEM_CORRUPT, + TCA_NETEM_LOSS, + TCA_NETEM_RATE, + TCA_NETEM_ECN, + TCA_NETEM_RATE64, + TCA_NETEM_PAD, + TCA_NETEM_LATENCY64, + TCA_NETEM_JITTER64, + TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, + __TCA_NETEM_MAX, +}; + +#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1) + +struct tc_netem_qopt { + __u32 latency; /* added delay (us) */ + __u32 limit; /* fifo limit (packets) */ + __u32 loss; /* random packet loss (0=none ~0=100%) */ + __u32 gap; /* re-ordering gap (0 for none) */ + __u32 duplicate; /* random packet dup (0=none ~0=100%) */ + __u32 jitter; /* random jitter in latency (us) */ +}; + +struct tc_netem_corr { + __u32 delay_corr; /* delay correlation */ + __u32 loss_corr; /* packet loss correlation */ + __u32 dup_corr; /* duplicate correlation */ +}; + +struct tc_netem_reorder { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_corrupt { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_rate { + __u32 rate; /* byte/s */ + __s32 packet_overhead; + __u32 cell_size; + __s32 cell_overhead; +}; + +struct tc_netem_slot { + __s64 min_delay; /* nsec */ + __s64 max_delay; + __s32 max_packets; + __s32 max_bytes; + __s64 dist_delay; /* nsec */ + __s64 dist_jitter; /* nsec */ +}; + +enum { + NETEM_LOSS_UNSPEC, + NETEM_LOSS_GI, /* General Intuitive - 4 state model */ + NETEM_LOSS_GE, /* Gilbert Elliot models */ + __NETEM_LOSS_MAX +}; +#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) + +/* State transition probabilities for 4 state model */ +struct tc_netem_gimodel { + __u32 p13; + __u32 p31; + __u32 p32; + __u32 p14; + __u32 p23; +}; + +/* Gilbert-Elliot models */ +struct tc_netem_gemodel { + __u32 p; + __u32 r; + __u32 h; + __u32 k1; +}; + +#define NETEM_DIST_SCALE 8192 +#define NETEM_DIST_MAX 16384 + +/* DRR */ + +enum { + TCA_DRR_UNSPEC, + TCA_DRR_QUANTUM, + __TCA_DRR_MAX +}; + +#define TCA_DRR_MAX (__TCA_DRR_MAX - 1) + +struct tc_drr_stats { + __u32 deficit; +}; + +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +enum { + TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */ + TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */ + __TC_MQPRIO_HW_OFFLOAD_MAX +}; + +#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) + +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + +/* SFB */ + +enum { + TCA_SFB_UNSPEC, + TCA_SFB_PARMS, + __TCA_SFB_MAX, +}; + +#define TCA_SFB_MAX (__TCA_SFB_MAX - 1) + +/* + * Note: increment, decrement are Q0.16 fixed-point values. + */ +struct tc_sfb_qopt { + __u32 rehash_interval; /* delay between hash move, in ms */ + __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */ + __u32 max; /* max len of qlen_min */ + __u32 bin_size; /* maximum queue length per bin */ + __u32 increment; /* probability increment, (d1 in Blue) */ + __u32 decrement; /* probability decrement, (d2 in Blue) */ + __u32 limit; /* max SFB queue length */ + __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */ + __u32 penalty_burst; +}; + +struct tc_sfb_xstats { + __u32 earlydrop; + __u32 penaltydrop; + __u32 bucketdrop; + __u32 queuedrop; + __u32 childdrop; /* drops in child qdisc */ + __u32 marked; + __u32 maxqlen; + __u32 maxprob; + __u32 avgprob; +}; + +#define SFB_MAX_PROB 0xFFFF + +/* QFQ */ +enum { + TCA_QFQ_UNSPEC, + TCA_QFQ_WEIGHT, + TCA_QFQ_LMAX, + __TCA_QFQ_MAX +}; + +#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1) + +struct tc_qfq_stats { + __u32 weight; + __u32 lmax; +}; + +/* CODEL */ + +enum { + TCA_CODEL_UNSPEC, + TCA_CODEL_TARGET, + TCA_CODEL_LIMIT, + TCA_CODEL_INTERVAL, + TCA_CODEL_ECN, + TCA_CODEL_CE_THRESHOLD, + __TCA_CODEL_MAX +}; + +#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1) + +struct tc_codel_xstats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 count; /* how many drops we've done since the last time we + * entered dropping state + */ + __u32 lastcount; /* count at entry to dropping state */ + __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */ + __s32 drop_next; /* time to drop next packet */ + __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */ + __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */ + __u32 dropping; /* are we in dropping state ? */ + __u32 ce_mark; /* number of CE marked packets because of ce_threshold */ +}; + +/* FQ_CODEL */ + +enum { + TCA_FQ_CODEL_UNSPEC, + TCA_FQ_CODEL_TARGET, + TCA_FQ_CODEL_LIMIT, + TCA_FQ_CODEL_INTERVAL, + TCA_FQ_CODEL_ECN, + TCA_FQ_CODEL_FLOWS, + TCA_FQ_CODEL_QUANTUM, + TCA_FQ_CODEL_CE_THRESHOLD, + TCA_FQ_CODEL_DROP_BATCH_SIZE, + TCA_FQ_CODEL_MEMORY_LIMIT, + __TCA_FQ_CODEL_MAX +}; + +#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1) + +enum { + TCA_FQ_CODEL_XSTATS_QDISC, + TCA_FQ_CODEL_XSTATS_CLASS, +}; + +struct tc_fq_codel_qd_stats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 drop_overlimit; /* number of time max qdisc + * packet limit was hit + */ + __u32 ecn_mark; /* number of packets we ECN marked + * instead of being dropped + */ + __u32 new_flow_count; /* number of time packets + * created a 'new flow' + */ + __u32 new_flows_len; /* count of flows in new list */ + __u32 old_flows_len; /* count of flows in old list */ + __u32 ce_mark; /* packets above ce_threshold */ + __u32 memory_usage; /* in bytes */ + __u32 drop_overmemory; +}; + +struct tc_fq_codel_cl_stats { + __s32 deficit; + __u32 ldelay; /* in-queue delay seen by most recently + * dequeued packet + */ + __u32 count; + __u32 lastcount; + __u32 dropping; + __s32 drop_next; +}; + +struct tc_fq_codel_xstats { + __u32 type; + union { + struct tc_fq_codel_qd_stats qdisc_stats; + struct tc_fq_codel_cl_stats class_stats; + }; +}; + +/* FQ */ + +enum { + TCA_FQ_UNSPEC, + + TCA_FQ_PLIMIT, /* limit of total number of packets in queue */ + + TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */ + + TCA_FQ_QUANTUM, /* RR quantum */ + + TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */ + + TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */ + + TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */ + + TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */ + + TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */ + + TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */ + + TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */ + + TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */ + + TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */ + + __TCA_FQ_MAX +}; + +#define TCA_FQ_MAX (__TCA_FQ_MAX - 1) + +struct tc_fq_qd_stats { + __u64 gc_flows; + __u64 highprio_packets; + __u64 tcp_retrans; + __u64 throttled; + __u64 flows_plimit; + __u64 pkts_too_long; + __u64 allocation_errors; + __s64 time_next_delayed_flow; + __u32 flows; + __u32 inactive_flows; + __u32 throttled_flows; + __u32 unthrottle_latency_ns; + __u64 ce_mark; /* packets above ce_threshold */ +}; + +/* Heavy-Hitter Filter */ + +enum { + TCA_HHF_UNSPEC, + TCA_HHF_BACKLOG_LIMIT, + TCA_HHF_QUANTUM, + TCA_HHF_HH_FLOWS_LIMIT, + TCA_HHF_RESET_TIMEOUT, + TCA_HHF_ADMIT_BYTES, + TCA_HHF_EVICT_TIMEOUT, + TCA_HHF_NON_HH_WEIGHT, + __TCA_HHF_MAX +}; + +#define TCA_HHF_MAX (__TCA_HHF_MAX - 1) + +struct tc_hhf_xstats { + __u32 drop_overlimit; /* number of times max qdisc packet limit + * was hit + */ + __u32 hh_overlimit; /* number of times max heavy-hitters was hit */ + __u32 hh_tot_count; /* number of captured heavy-hitters so far */ + __u32 hh_cur_count; /* number of current heavy-hitters */ +}; + +/* PIE */ +enum { + TCA_PIE_UNSPEC, + TCA_PIE_TARGET, + TCA_PIE_LIMIT, + TCA_PIE_TUPDATE, + TCA_PIE_ALPHA, + TCA_PIE_BETA, + TCA_PIE_ECN, + TCA_PIE_BYTEMODE, + __TCA_PIE_MAX +}; +#define TCA_PIE_MAX (__TCA_PIE_MAX - 1) + +struct tc_pie_xstats { + __u32 prob; /* current probability */ + __u32 delay; /* current delay in ms */ + __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */ + __u32 packets_in; /* total number of packets enqueued */ + __u32 dropped; /* packets dropped due to pie_action */ + __u32 overlimit; /* dropped due to lack of space in queue */ + __u32 maxq; /* maximum queue size */ + __u32 ecn_mark; /* packets marked with ecn*/ +}; + +/* CBS */ +struct tc_cbs_qopt { + __u8 offload; + __u8 _pad[3]; + __s32 hicredit; + __s32 locredit; + __s32 idleslope; + __s32 sendslope; +}; + +enum { + TCA_CBS_UNSPEC, + TCA_CBS_PARMS, + __TCA_CBS_MAX, +}; + +#define TCA_CBS_MAX (__TCA_CBS_MAX - 1) + + +/* ETF */ +struct tc_etf_qopt { + __s32 delta; + __s32 clockid; + __u32 flags; +#define TC_ETF_DEADLINE_MODE_ON BIT(0) +#define TC_ETF_OFFLOAD_ON BIT(1) +}; + +enum { + TCA_ETF_UNSPEC, + TCA_ETF_PARMS, + __TCA_ETF_MAX, +}; + +#define TCA_ETF_MAX (__TCA_ETF_MAX - 1) + + +/* CAKE */ +enum { + TCA_CAKE_UNSPEC, + TCA_CAKE_PAD, + TCA_CAKE_BASE_RATE64, + TCA_CAKE_DIFFSERV_MODE, + TCA_CAKE_ATM, + TCA_CAKE_FLOW_MODE, + TCA_CAKE_OVERHEAD, + TCA_CAKE_RTT, + TCA_CAKE_TARGET, + TCA_CAKE_AUTORATE, + TCA_CAKE_MEMORY, + TCA_CAKE_NAT, + TCA_CAKE_RAW, + TCA_CAKE_WASH, + TCA_CAKE_MPU, + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, + __TCA_CAKE_MAX +}; +#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) + +enum { + __TCA_CAKE_STATS_INVALID, + TCA_CAKE_STATS_PAD, + TCA_CAKE_STATS_CAPACITY_ESTIMATE64, + TCA_CAKE_STATS_MEMORY_LIMIT, + TCA_CAKE_STATS_MEMORY_USED, + TCA_CAKE_STATS_AVG_NETOFF, + TCA_CAKE_STATS_MIN_NETLEN, + TCA_CAKE_STATS_MAX_NETLEN, + TCA_CAKE_STATS_MIN_ADJLEN, + TCA_CAKE_STATS_MAX_ADJLEN, + TCA_CAKE_STATS_TIN_STATS, + TCA_CAKE_STATS_DEFICIT, + TCA_CAKE_STATS_COBALT_COUNT, + TCA_CAKE_STATS_DROPPING, + TCA_CAKE_STATS_DROP_NEXT_US, + TCA_CAKE_STATS_P_DROP, + TCA_CAKE_STATS_BLUE_TIMER_US, + __TCA_CAKE_STATS_MAX +}; +#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) + +enum { + __TCA_CAKE_TIN_STATS_INVALID, + TCA_CAKE_TIN_STATS_PAD, + TCA_CAKE_TIN_STATS_SENT_PACKETS, + TCA_CAKE_TIN_STATS_SENT_BYTES64, + TCA_CAKE_TIN_STATS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS, + TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64, + TCA_CAKE_TIN_STATS_BACKLOG_PACKETS, + TCA_CAKE_TIN_STATS_BACKLOG_BYTES, + TCA_CAKE_TIN_STATS_THRESHOLD_RATE64, + TCA_CAKE_TIN_STATS_TARGET_US, + TCA_CAKE_TIN_STATS_INTERVAL_US, + TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS, + TCA_CAKE_TIN_STATS_WAY_MISSES, + TCA_CAKE_TIN_STATS_WAY_COLLISIONS, + TCA_CAKE_TIN_STATS_PEAK_DELAY_US, + TCA_CAKE_TIN_STATS_AVG_DELAY_US, + TCA_CAKE_TIN_STATS_BASE_DELAY_US, + TCA_CAKE_TIN_STATS_SPARSE_FLOWS, + TCA_CAKE_TIN_STATS_BULK_FLOWS, + TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS, + TCA_CAKE_TIN_STATS_MAX_SKBLEN, + TCA_CAKE_TIN_STATS_FLOW_QUANTUM, + __TCA_CAKE_TIN_STATS_MAX +}; +#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1) +#define TC_CAKE_MAX_TINS (8) + +enum { + CAKE_FLOW_NONE = 0, + CAKE_FLOW_SRC_IP, + CAKE_FLOW_DST_IP, + CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */ + CAKE_FLOW_FLOWS, + CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */ + CAKE_FLOW_MAX, +}; + +enum { + CAKE_DIFFSERV_DIFFSERV3 = 0, + CAKE_DIFFSERV_DIFFSERV4, + CAKE_DIFFSERV_DIFFSERV8, + CAKE_DIFFSERV_BESTEFFORT, + CAKE_DIFFSERV_PRECEDENCE, + CAKE_DIFFSERV_MAX +}; + +enum { + CAKE_ACK_NONE = 0, + CAKE_ACK_FILTER, + CAKE_ACK_AGGRESSIVE, + CAKE_ACK_MAX +}; + +enum { + CAKE_ATM_NONE = 0, + CAKE_ATM_ATM, + CAKE_ATM_PTM, + CAKE_ATM_MAX +}; + + +/* TAPRIO */ +enum { + TC_TAPRIO_CMD_SET_GATES = 0x00, + TC_TAPRIO_CMD_SET_AND_HOLD = 0x01, + TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02, +}; + +enum { + TCA_TAPRIO_SCHED_ENTRY_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */ + TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */ + __TCA_TAPRIO_SCHED_ENTRY_MAX, +}; +#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1) + +/* The format for schedule entry list is: + * [TCA_TAPRIO_SCHED_ENTRY_LIST] + * [TCA_TAPRIO_SCHED_ENTRY] + * [TCA_TAPRIO_SCHED_ENTRY_CMD] + * [TCA_TAPRIO_SCHED_ENTRY_GATES] + * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] + */ +enum { + TCA_TAPRIO_SCHED_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY, + __TCA_TAPRIO_SCHED_MAX, +}; + +#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1) + +enum { + TCA_TAPRIO_ATTR_UNSPEC, + TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ + TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */ + TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ + TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ + TCA_TAPRIO_PAD, + __TCA_TAPRIO_ATTR_MAX, +}; + +#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index b17201edfa09..094bb03b9cc2 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -219,5 +219,14 @@ struct prctl_mm_map { # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) + +/* Reset arm64 pointer authentication keys */ +#define PR_PAC_RESET_KEYS 54 +# define PR_PAC_APIAKEY (1UL << 0) +# define PR_PAC_APIBKEY (1UL << 1) +# define PR_PAC_APDAKEY (1UL << 2) +# define PR_PAC_APDBKEY (1UL << 3) +# define PR_PAC_APGAKEY (1UL << 4) #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h index 6e89a5df49a4..653c4f94f76e 100644 --- a/tools/include/uapi/linux/tc_act/tc_bpf.h +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -13,8 +13,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_BPF 13 - struct tc_act_bpf { tc_gen; }; diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 84c3de89696a..40d028eed645 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -11,94 +11,9 @@ * device configuration. */ +#include <linux/vhost_types.h> #include <linux/types.h> -#include <linux/compiler.h> #include <linux/ioctl.h> -#include <linux/virtio_config.h> -#include <linux/virtio_ring.h> - -struct vhost_vring_state { - unsigned int index; - unsigned int num; -}; - -struct vhost_vring_file { - unsigned int index; - int fd; /* Pass -1 to unbind from file. */ - -}; - -struct vhost_vring_addr { - unsigned int index; - /* Option flags. */ - unsigned int flags; - /* Flag values: */ - /* Whether log address is valid. If set enables logging. */ -#define VHOST_VRING_F_LOG 0 - - /* Start of array of descriptors (virtually contiguous) */ - __u64 desc_user_addr; - /* Used structure address. Must be 32 bit aligned */ - __u64 used_user_addr; - /* Available structure address. Must be 16 bit aligned */ - __u64 avail_user_addr; - /* Logging support. */ - /* Log writes to used structure, at offset calculated from specified - * address. Address must be 32 bit aligned. */ - __u64 log_guest_addr; -}; - -/* no alignment requirement */ -struct vhost_iotlb_msg { - __u64 iova; - __u64 size; - __u64 uaddr; -#define VHOST_ACCESS_RO 0x1 -#define VHOST_ACCESS_WO 0x2 -#define VHOST_ACCESS_RW 0x3 - __u8 perm; -#define VHOST_IOTLB_MISS 1 -#define VHOST_IOTLB_UPDATE 2 -#define VHOST_IOTLB_INVALIDATE 3 -#define VHOST_IOTLB_ACCESS_FAIL 4 - __u8 type; -}; - -#define VHOST_IOTLB_MSG 0x1 -#define VHOST_IOTLB_MSG_V2 0x2 - -struct vhost_msg { - int type; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_msg_v2 { - __u32 type; - __u32 reserved; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_memory_region { - __u64 guest_phys_addr; - __u64 memory_size; /* bytes */ - __u64 userspace_addr; - __u64 flags_padding; /* No flags are currently specified. */ -}; - -/* All region addresses and sizes must be 4K aligned. */ -#define VHOST_PAGE_SIZE 0x1000 - -struct vhost_memory { - __u32 nregions; - __u32 padding; - struct vhost_memory_region regions[0]; -}; /* ioctls */ @@ -186,31 +101,7 @@ struct vhost_memory { * device. This can be used to stop the ring (e.g. for migration). */ #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file) -/* Feature bits */ -/* Log all write descriptors. Can be changed while device is active. */ -#define VHOST_F_LOG_ALL 26 -/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ -#define VHOST_NET_F_VIRTIO_NET_HDR 27 - -/* VHOST_SCSI specific definitions */ - -/* - * Used by QEMU userspace to ensure a consistent vhost-scsi ABI. - * - * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate + - * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage - * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target. - * All the targets under vhost_wwpn can be seen and used by guset. - */ - -#define VHOST_SCSI_ABI_VERSION 1 - -struct vhost_scsi_target { - int abi_version; - char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */ - unsigned short vhost_tpgt; - unsigned short reserved; -}; +/* VHOST_SCSI specific defines */ #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target) #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target) |