diff options
Diffstat (limited to 'tools/include')
-rw-r--r-- | tools/include/linux/align.h | 12 | ||||
-rw-r--r-- | tools/include/linux/bitmap.h | 9 | ||||
-rw-r--r-- | tools/include/linux/bitops.h | 2 | ||||
-rw-r--r-- | tools/include/linux/compiler.h | 4 | ||||
-rw-r--r-- | tools/include/linux/filter.h | 18 | ||||
-rw-r--r-- | tools/include/linux/mm.h | 5 | ||||
-rw-r--r-- | tools/include/nolibc/stdlib.h | 2 | ||||
-rw-r--r-- | tools/include/nolibc/string.h | 46 | ||||
-rw-r--r-- | tools/include/nolibc/sys.h | 27 | ||||
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 44 | ||||
-rw-r--r-- | tools/include/uapi/linux/ethtool.h | 104 | ||||
-rw-r--r-- | tools/include/uapi/linux/kvm.h | 2 | ||||
-rw-r--r-- | tools/include/uapi/linux/memfd.h | 39 | ||||
-rw-r--r-- | tools/include/uapi/linux/netdev.h | 21 | ||||
-rw-r--r-- | tools/include/uapi/linux/userfaultfd.h | 386 |
15 files changed, 580 insertions, 141 deletions
diff --git a/tools/include/linux/align.h b/tools/include/linux/align.h new file mode 100644 index 000000000000..14e34ace80dd --- /dev/null +++ b/tools/include/linux/align.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _TOOLS_LINUX_ALIGN_H +#define _TOOLS_LINUX_ALIGN_H + +#include <uapi/linux/const.h> + +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +#endif /* _TOOLS_LINUX_ALIGN_H */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index f3566ea0f932..210c13b1b857 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -3,6 +3,7 @@ #define _TOOLS_LINUX_BITMAP_H #include <string.h> +#include <linux/align.h> #include <linux/bitops.h> #include <linux/find.h> #include <stdlib.h> @@ -25,13 +26,14 @@ bool __bitmap_intersects(const unsigned long *bitmap1, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + memset(dst, 0, bitmap_size(nbits)); } } @@ -83,7 +85,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, */ static inline unsigned long *bitmap_zalloc(int nbits) { - return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); + return calloc(1, bitmap_size(nbits)); } /* @@ -126,7 +128,6 @@ static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) static inline bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 7319f6ced108..272f15d0e434 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -20,6 +20,8 @@ #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 7b65566f3e42..8a63a9913495 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -58,6 +58,10 @@ #define noinline #endif +#ifndef __nocf_check +#define __nocf_check __attribute__((nocf_check)) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 736bdeccdfe4..65aa8ce142e5 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -111,6 +111,24 @@ .off = 0, \ .imm = IMM }) +/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ + +#define BPF_MOVSX64_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_MOVSX32_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index 7d73da098047..dc0fc7125bc3 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -2,8 +2,8 @@ #ifndef _TOOLS_LINUX_MM_H #define _TOOLS_LINUX_MM_H +#include <linux/align.h> #include <linux/mmzone.h> -#include <uapi/linux/const.h> #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) @@ -11,9 +11,6 @@ #define PHYS_ADDR_MAX (~(phys_addr_t)0) -#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) -#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) - #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) #define __va(x) ((void *)((unsigned long)(x))) diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index bacfd35c5156..5be9d3c7435a 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -185,7 +185,7 @@ void *realloc(void *old_ptr, size_t new_size) if (__builtin_expect(!ret, 0)) return NULL; - memcpy(ret, heap->user_p, heap->len); + memcpy(ret, heap->user_p, user_p_len); munmap(heap, heap->len); return ret; } diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index a01c69dd495f..f9ab28421e6d 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -123,7 +123,7 @@ char *strcpy(char *dst, const char *src) * thus itself, hence the asm() statement below that's meant to disable this * confusing practice. */ -static __attribute__((unused)) +__attribute__((weak,unused,section(".text.nolibc_strlen"))) size_t strlen(const char *str) { size_t len; @@ -187,22 +187,26 @@ char *strndup(const char *str, size_t maxlen) static __attribute__((unused)) size_t strlcat(char *dst, const char *src, size_t size) { - size_t len; - char c; - - for (len = 0; dst[len]; len++) - ; - - for (;;) { - c = *src; - if (len < size) - dst[len] = c; - if (!c) + size_t len = strnlen(dst, size); + + /* + * We want len < size-1. But as size is unsigned and can wrap + * around, we use len + 1 instead. + */ + while (len + 1 < size) { + dst[len] = *src; + if (*src == '\0') break; len++; src++; } + if (len < size) + dst[len] = '\0'; + + while (*src++) + len++; + return len; } @@ -210,16 +214,18 @@ static __attribute__((unused)) size_t strlcpy(char *dst, const char *src, size_t size) { size_t len; - char c; - for (len = 0;;) { - c = src[len]; - if (len < size) - dst[len] = c; - if (!c) - break; - len++; + for (len = 0; len < size; len++) { + dst[len] = src[len]; + if (!dst[len]) + return len; } + if (size) + dst[size-1] = '\0'; + + while (src[len]) + len++; + return len; } diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index dda9dffd1d74..7b82bc3cf107 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -22,6 +22,7 @@ #include <linux/stat.h> /* for statx() */ #include <linux/prctl.h> #include <linux/resource.h> +#include <linux/utsname.h> #include "arch.h" #include "errno.h" @@ -1140,6 +1141,32 @@ int umount2(const char *path, int flags) /* + * int uname(struct utsname *buf); + */ + +struct utsname { + char sysname[65]; + char nodename[65]; + char release[65]; + char version[65]; + char machine[65]; + char domainname[65]; +}; + +static __attribute__((unused)) +int sys_uname(struct utsname *buf) +{ + return my_syscall1(__NR_uname, buf); +} + +static __attribute__((unused)) +int uname(struct utsname *buf) +{ + return __sysret(sys_uname(buf)); +} + + +/* * int unlink(const char *path); */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c42b9f1bada..90706a47f6ff 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; @@ -1135,6 +1136,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, __MAX_BPF_LINK_TYPE, }; @@ -1662,8 +1664,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ @@ -3392,6 +3396,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -5020,7 +5028,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5506,7 +5514,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) @@ -6718,6 +6726,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); @@ -6936,6 +6948,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle @@ -7118,6 +7132,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7150,7 +7165,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ @@ -7195,8 +7210,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { @@ -7283,6 +7309,10 @@ struct bpf_timer { __u64 __opaque[2]; } __attribute__((aligned(8))); +struct bpf_wq { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + struct bpf_dynptr { __u64 __opaque[2]; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h deleted file mode 100644 index 47afae3895ec..000000000000 --- a/tools/include/uapi/linux/ethtool.h +++ /dev/null @@ -1,104 +0,0 @@ -/* 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; -}; - -#define ETHTOOL_FWVERS_LEN 32 -#define ETHTOOL_BUSINFO_LEN 32 -#define ETHTOOL_EROMVERS_LEN 32 - -/** - * struct ethtool_drvinfo - general driver and device information - * @cmd: Command number = %ETHTOOL_GDRVINFO - * @driver: Driver short name. This should normally match the name - * in its bus driver structure (e.g. pci_driver::name). Must - * not be an empty string. - * @version: Driver version string; may be an empty string - * @fw_version: Firmware version string; may be an empty string - * @erom_version: Expansion ROM version string; may be an empty string - * @bus_info: Device bus address. This should match the dev_name() - * string for the underlying bus device, if there is one. May be - * an empty string. - * @reserved2: Reserved for future use; see the note on reserved space. - * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and - * %ETHTOOL_SPFLAGS commands; also the number of strings in the - * %ETH_SS_PRIV_FLAGS set - * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS - * command; also the number of strings in the %ETH_SS_STATS set - * @testinfo_len: Number of results returned by the %ETHTOOL_TEST - * command; also the number of strings in the %ETH_SS_TEST set - * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM - * and %ETHTOOL_SEEPROM commands, in bytes - * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS - * command, in bytes - * - * Users can use the %ETHTOOL_GSSET_INFO command to get the number of - * strings in any string set (from Linux 2.6.34). - * - * Drivers should set at most @driver, @version, @fw_version and - * @bus_info in their get_drvinfo() implementation. The ethtool - * core fills in the other fields using other driver operations. - */ -struct ethtool_drvinfo { - __u32 cmd; - char driver[32]; - char version[32]; - char fw_version[ETHTOOL_FWVERS_LEN]; - char bus_info[ETHTOOL_BUSINFO_LEN]; - char erom_version[ETHTOOL_EROMVERS_LEN]; - char reserved2[12]; - __u32 n_priv_flags; - __u32 n_stats; - __u32 testinfo_len; - __u32 eedump_len; - __u32 regdump_len; -}; - -#define ETHTOOL_GDRVINFO 0x00000003 - -#endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 2190adbe3002..ea32b101b999 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1221,7 +1221,7 @@ struct kvm_vfio_spapr_tce { /* Available with KVM_CAP_SPAPR_RESIZE_HPT */ #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) #define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) -/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */ #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) /* Available with KVM_CAP_PPC_RADIX_MMU */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) diff --git a/tools/include/uapi/linux/memfd.h b/tools/include/uapi/linux/memfd.h new file mode 100644 index 000000000000..01c0324e7733 --- /dev/null +++ b/tools/include/uapi/linux/memfd.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_MEMFD_H +#define _LINUX_MEMFD_H + +#include <asm-generic/hugetlb_encode.h> + +/* flags for memfd_create(2) (unsigned int) */ +#define MFD_CLOEXEC 0x0001U +#define MFD_ALLOW_SEALING 0x0002U +#define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U + +/* + * Huge page size encoding when MFD_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB +#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB +#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + +#endif /* _LINUX_MEMFD_H */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index bb65ee840cda..a8188202413e 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -146,6 +146,27 @@ enum { NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, NETDEV_A_QSTATS_RX_ALLOC_FAIL, + NETDEV_A_QSTATS_RX_HW_DROPS, + NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, + NETDEV_A_QSTATS_RX_CSUM_NONE, + NETDEV_A_QSTATS_RX_CSUM_BAD, + NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_BYTES, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, + NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_HW_DROPS, + NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, + NETDEV_A_QSTATS_TX_CSUM_NONE, + NETDEV_A_QSTATS_TX_NEEDS_CSUM, + NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_BYTES, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, + NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_STOP, + NETDEV_A_QSTATS_TX_WAKE, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h new file mode 100644 index 000000000000..4283de22d5b6 --- /dev/null +++ b/tools/include/uapi/linux/userfaultfd.h @@ -0,0 +1,386 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * include/linux/userfaultfd.h + * + * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> + * Copyright (C) 2015 Red Hat, Inc. + * + */ + +#ifndef _LINUX_USERFAULTFD_H +#define _LINUX_USERFAULTFD_H + +#include <linux/types.h> + +/* ioctls for /dev/userfaultfd */ +#define USERFAULTFD_IOC 0xAA +#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00) + +/* + * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and + * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In + * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ + * means the userland is reading). + */ +#define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) +#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ + UFFD_FEATURE_EVENT_FORK | \ + UFFD_FEATURE_EVENT_REMAP | \ + UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_UNMAP | \ + UFFD_FEATURE_MISSING_HUGETLBFS | \ + UFFD_FEATURE_MISSING_SHMEM | \ + UFFD_FEATURE_SIGBUS | \ + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM | \ + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ + UFFD_FEATURE_WP_UNPOPULATED | \ + UFFD_FEATURE_POISON | \ + UFFD_FEATURE_WP_ASYNC | \ + UFFD_FEATURE_MOVE) +#define UFFD_API_IOCTLS \ + ((__u64)1 << _UFFDIO_REGISTER | \ + (__u64)1 << _UFFDIO_UNREGISTER | \ + (__u64)1 << _UFFDIO_API) +#define UFFD_API_RANGE_IOCTLS \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_ZEROPAGE | \ + (__u64)1 << _UFFDIO_MOVE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON) +#define UFFD_API_RANGE_IOCTLS_BASIC \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON) + +/* + * Valid ioctl command number range with this API is from 0x00 to + * 0x3F. UFFDIO_API is the fixed number, everything else can be + * changed by implementing a different UFFD_API. If sticking to the + * same UFFD_API more ioctl can be added and userland will be aware of + * which ioctl the running kernel implements through the ioctl command + * bitmask written by the UFFDIO_API. + */ +#define _UFFDIO_REGISTER (0x00) +#define _UFFDIO_UNREGISTER (0x01) +#define _UFFDIO_WAKE (0x02) +#define _UFFDIO_COPY (0x03) +#define _UFFDIO_ZEROPAGE (0x04) +#define _UFFDIO_MOVE (0x05) +#define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) +#define _UFFDIO_POISON (0x08) +#define _UFFDIO_API (0x3F) + +/* userfaultfd ioctl ids */ +#define UFFDIO 0xAA +#define UFFDIO_API _IOWR(UFFDIO, _UFFDIO_API, \ + struct uffdio_api) +#define UFFDIO_REGISTER _IOWR(UFFDIO, _UFFDIO_REGISTER, \ + struct uffdio_register) +#define UFFDIO_UNREGISTER _IOR(UFFDIO, _UFFDIO_UNREGISTER, \ + struct uffdio_range) +#define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \ + struct uffdio_range) +#define UFFDIO_COPY _IOWR(UFFDIO, _UFFDIO_COPY, \ + struct uffdio_copy) +#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \ + struct uffdio_zeropage) +#define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, \ + struct uffdio_move) +#define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ + struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) +#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \ + struct uffdio_poison) + +/* read() structure */ +struct uffd_msg { + __u8 event; + + __u8 reserved1; + __u16 reserved2; + __u32 reserved3; + + union { + struct { + __u64 flags; + __u64 address; + union { + __u32 ptid; + } feat; + } pagefault; + + struct { + __u32 ufd; + } fork; + + struct { + __u64 from; + __u64 to; + __u64 len; + } remap; + + struct { + __u64 start; + __u64 end; + } remove; + + struct { + /* unused reserved fields */ + __u64 reserved1; + __u64 reserved2; + __u64 reserved3; + } reserved; + } arg; +} __attribute__((packed)); + +/* + * Start at 0x12 and not at 0 to be more strict against bugs. + */ +#define UFFD_EVENT_PAGEFAULT 0x12 +#define UFFD_EVENT_FORK 0x13 +#define UFFD_EVENT_REMAP 0x14 +#define UFFD_EVENT_REMOVE 0x15 +#define UFFD_EVENT_UNMAP 0x16 + +/* flags for UFFD_EVENT_PAGEFAULT */ +#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ +#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ + +struct uffdio_api { + /* userland asks for an API number and the features to enable */ + __u64 api; + /* + * Kernel answers below with the all available features for + * the API, this notifies userland of which events and/or + * which flags for each event are enabled in the current + * kernel. + * + * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE + * are to be considered implicitly always enabled in all kernels as + * long as the uffdio_api.api requested matches UFFD_API. + * + * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER + * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on + * hugetlbfs virtual memory ranges. Adding or not adding + * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has + * no real functional effect after UFFDIO_API returns, but + * it's only useful for an initial feature set probe at + * UFFDIO_API time. There are two ways to use it: + * + * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the + * uffdio_api.features before calling UFFDIO_API, an error + * will be returned by UFFDIO_API on a kernel without + * hugetlbfs missing support + * + * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in + * uffdio_api.features and instead it will be set by the + * kernel in the uffdio_api.features if the kernel supports + * it, so userland can later check if the feature flag is + * present in uffdio_api.features after UFFDIO_API + * succeeded. + * + * UFFD_FEATURE_MISSING_SHMEM works the same as + * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem + * (i.e. tmpfs and other shmem based APIs). + * + * UFFD_FEATURE_SIGBUS feature means no page-fault + * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead + * a SIGBUS signal will be sent to the faulting process. + * + * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will + * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. + * + * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page + * faults would be provided and the offset within the page would not be + * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. + * + * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd + * write-protection mode will always apply to unpopulated pages + * (i.e. empty ptes). This will be the default behavior for shmem + * & hugetlbfs, so this flag only affects anonymous memory behavior + * when userfault write-protection mode is registered. + * + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection + * asynchronous mode is supported in which the write fault is + * automatically resolved and write-protection is un-set. + * It implies UFFD_FEATURE_WP_UNPOPULATED. + * + * UFFD_FEATURE_MOVE indicates that the kernel supports moving an + * existing page contents from userspace. + */ +#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) +#define UFFD_FEATURE_EVENT_FORK (1<<1) +#define UFFD_FEATURE_EVENT_REMAP (1<<2) +#define UFFD_FEATURE_EVENT_REMOVE (1<<3) +#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) +#define UFFD_FEATURE_MISSING_SHMEM (1<<5) +#define UFFD_FEATURE_EVENT_UNMAP (1<<6) +#define UFFD_FEATURE_SIGBUS (1<<7) +#define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) +#define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) +#define UFFD_FEATURE_WP_UNPOPULATED (1<<13) +#define UFFD_FEATURE_POISON (1<<14) +#define UFFD_FEATURE_WP_ASYNC (1<<15) +#define UFFD_FEATURE_MOVE (1<<16) + __u64 features; + + __u64 ioctls; +}; + +struct uffdio_range { + __u64 start; + __u64 len; +}; + +struct uffdio_register { + struct uffdio_range range; +#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) +#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) + __u64 mode; + + /* + * kernel answers which ioctl commands are available for the + * range, keep at the end as the last 8 bytes aren't read. + */ + __u64 ioctls; +}; + +struct uffdio_copy { + __u64 dst; + __u64 src; + __u64 len; +#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_COPY_MODE_WP will map the page write protected on + * the fly. UFFDIO_COPY_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_COPY_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * "copy" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 copy; +}; + +struct uffdio_zeropage { + struct uffdio_range range; +#define UFFDIO_ZEROPAGE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * "zeropage" is written by the ioctl and must be at the end: + * the copy_from_user will not read the last 8 bytes. + */ + __s64 zeropage; +}; + +struct uffdio_writeprotect { + struct uffdio_range range; +/* + * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range, + * unset the flag to undo protection of a range which was previously + * write protected. + * + * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up + * any wait thread after the operation succeeds. + * + * NOTE: Write protecting a region (WP=1) is unrelated to page faults, + * therefore DONTWAKE flag is meaningless with WP=1. Removing write + * protection (WP=0) in response to a page fault wakes the faulting + * task unless DONTWAKE is set. + */ +#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0) +#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1) + __u64 mode; +}; + +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_CONTINUE_MODE_WP will map the page write protected on + * the fly. UFFDIO_CONTINUE_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_CONTINUE_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + +struct uffdio_poison { + struct uffdio_range range; +#define UFFDIO_POISON_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 updated; +}; + +struct uffdio_move { + __u64 dst; + __u64 src; + __u64 len; + /* + * Especially if used to atomically remove memory from the + * address space the wake on the dst range is not needed. + */ +#define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0) +#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1) + __u64 mode; + /* + * "move" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 move; +}; + +/* + * Flags for the userfaultfd(2) system call itself. + */ + +/* + * Create a userfaultfd that can handle page faults only in user mode. + */ +#define UFFD_USER_MODE_ONLY 1 + +#endif /* _LINUX_USERFAULTFD_H */ |