From d279f1f8c64711ca986c3121c8ec811b892932f0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 11 Dec 2017 11:39:03 -0800 Subject: bpf/tracing: add a bpf test for new ioctl query interface Added a subtest in test_progs. The tracepoint is sched/sched_switch. Multiple bpf programs are attached to this tracepoint and the query interface is exercised. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/perf_event.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'tools/include') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 362493a2f950..f2c354d5f519 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -418,6 +418,27 @@ struct perf_event_attr { __u16 __reserved_2; /* align to __u64 */ }; +/* + * Structure used by below PERF_EVENT_IOC_QUERY_BPF command + * to query bpf programs attached to the same perf tracepoint + * as the given perf event. + */ +struct perf_event_query_bpf { + /* + * The below ids array length + */ + __u32 ids_len; + /* + * Set by the kernel to indicate the number of + * available programs + */ + __u32 prog_cnt; + /* + * User provided buffer to store program ids + */ + __u32 ids[0]; +}; + #define perf_flags(attr) (*(&(attr)->read_format + 1)) /* @@ -433,6 +454,7 @@ struct perf_event_attr { #define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) #define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) #define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, -- cgit v1.2.3 From 965de87e54b803223bff703ea6b2a76c056695ae Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 11 Dec 2017 11:36:49 -0500 Subject: samples/bpf: add a test for bpf_override_return This adds a basic test for bpf_override_return to verify it works. We override the main function for mounting a btrfs fs so it'll return -ENOMEM and then make sure that trying to mount a btrfs fs will fail. Acked-by: Alexei Starovoitov Acked-by: Ingo Molnar Signed-off-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- samples/bpf/Makefile | 4 ++++ samples/bpf/test_override_return.sh | 15 +++++++++++++++ samples/bpf/tracex7_kern.c | 16 ++++++++++++++++ samples/bpf/tracex7_user.c | 28 ++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 7 ++++++- tools/testing/selftests/bpf/bpf_helpers.h | 3 ++- 6 files changed, 71 insertions(+), 2 deletions(-) create mode 100755 samples/bpf/test_override_return.sh create mode 100644 samples/bpf/tracex7_kern.c create mode 100644 samples/bpf/tracex7_user.c (limited to 'tools/include') diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index adeaa1302f34..4fb944a7ecf8 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -12,6 +12,7 @@ hostprogs-y += tracex3 hostprogs-y += tracex4 hostprogs-y += tracex5 hostprogs-y += tracex6 +hostprogs-y += tracex7 hostprogs-y += test_probe_write_user hostprogs-y += trace_output hostprogs-y += lathist @@ -58,6 +59,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o +tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o @@ -101,6 +103,7 @@ always += tracex3_kern.o always += tracex4_kern.o always += tracex5_kern.o always += tracex6_kern.o +always += tracex7_kern.o always += sock_flags_kern.o always += test_probe_write_user_kern.o always += trace_output_kern.o @@ -155,6 +158,7 @@ HOSTLOADLIBES_tracex3 += -lelf HOSTLOADLIBES_tracex4 += -lelf -lrt HOSTLOADLIBES_tracex5 += -lelf HOSTLOADLIBES_tracex6 += -lelf +HOSTLOADLIBES_tracex7 += -lelf HOSTLOADLIBES_test_cgrp2_sock2 += -lelf HOSTLOADLIBES_load_sock_ops += -lelf HOSTLOADLIBES_test_probe_write_user += -lelf diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh new file mode 100755 index 000000000000..e68b9ee6814b --- /dev/null +++ b/samples/bpf/test_override_return.sh @@ -0,0 +1,15 @@ +#!/bin/bash + +rm -f testfile.img +dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1 +DEVICE=$(losetup --show -f testfile.img) +mkfs.btrfs -f $DEVICE +mkdir tmpmnt +./tracex7 $DEVICE +if [ $? -eq 0 ] +then + echo "SUCCESS!" +else + echo "FAILED!" +fi +losetup -d $DEVICE diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c new file mode 100644 index 000000000000..1ab308a43e0f --- /dev/null +++ b/samples/bpf/tracex7_kern.c @@ -0,0 +1,16 @@ +#include +#include +#include +#include "bpf_helpers.h" + +SEC("kprobe/open_ctree") +int bpf_prog1(struct pt_regs *ctx) +{ + unsigned long rc = -12; + + bpf_override_return(ctx, rc); + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c new file mode 100644 index 000000000000..8a52ac492e8b --- /dev/null +++ b/samples/bpf/tracex7_user.c @@ -0,0 +1,28 @@ +#define _GNU_SOURCE + +#include +#include +#include +#include "libbpf.h" +#include "bpf_load.h" + +int main(int argc, char **argv) +{ + FILE *f; + char filename[256]; + char command[256]; + int ret; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + snprintf(command, 256, "mount %s tmpmnt/", argv[1]); + f = popen(command, "r"); + ret = pclose(f); + + return ret ? 0 : 1; +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4c223ab30293..cf446c25c0ec 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -677,6 +677,10 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return : 0 on success or negative error code + * + * int bpf_override_return(pt_regs, rc) + * @pt_regs: pointer to struct pt_regs + * @rc: the return value to set */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -736,7 +740,8 @@ union bpf_attr { FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ FN(perf_prog_read_value), \ - FN(getsockopt), + FN(getsockopt), \ + FN(override_return), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index fd9a17fa8a8b..33cb00e46c49 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -82,7 +82,8 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, static int (*bpf_perf_prog_read_value)(void *ctx, void *buf, unsigned int buf_size) = (void *) BPF_FUNC_perf_prog_read_value; - +static int (*bpf_override_return)(void *ctx, unsigned long rc) = + (void *) BPF_FUNC_override_return; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions -- cgit v1.2.3 From 48cca7e44f9f8268fdcd4351e2f19ff2275119d1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Dec 2017 17:55:10 -0800 Subject: libbpf: add support for bpf_call - recognize relocation emitted by llvm - since all regular function will be kept in .text section and llvm takes care of pc-relative offsets in bpf_call instruction simply copy all of .text to relevant program section while adjusting bpf_call instructions in program section to point to newly copied body of instructions from .text - do so for all programs in the elf file - set all programs types to the one passed to bpf_prog_load() Note for elf files with multiple programs that use different functions in .text section we need to do 'linker' style logic. This work is still TBD Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 6 ++ tools/lib/bpf/bpf.h | 2 +- tools/lib/bpf/libbpf.c | 170 ++++++++++++++++++++++++++++++----------- 3 files changed, 134 insertions(+), 44 deletions(-) (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cf446c25c0ec..db1b0923a308 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -197,8 +197,14 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6534889e2b2f..9f44c196931e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -40,7 +40,7 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, __u32 map_flags); /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE 65536 +#define BPF_LOG_BUF_SIZE (256 * 1024) int bpf_load_program_name(enum bpf_prog_type type, const char *name, const struct bpf_insn *insns, size_t insns_cnt, const char *license, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 65d0d0aff4fa..5b83875b3594 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -174,12 +174,19 @@ struct bpf_program { char *name; char *section_name; struct bpf_insn *insns; - size_t insns_cnt; + size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct { + struct reloc_desc { + enum { + RELO_LD64, + RELO_CALL, + } type; int insn_idx; - int map_idx; + union { + int map_idx; + int text_off; + }; } *reloc_desc; int nr_reloc; @@ -234,6 +241,7 @@ struct bpf_object { } *reloc; int nr_reloc; int maps_shndx; + int text_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -375,9 +383,13 @@ bpf_object__init_prog_names(struct bpf_object *obj) size_t pi, si; for (pi = 0; pi < obj->nr_programs; pi++) { - char *name = NULL; + const char *name = NULL; prog = &obj->programs[pi]; + if (prog->idx == obj->efile.text_shndx) { + name = ".text"; + goto skip_search; + } for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; si++) { @@ -405,7 +417,7 @@ bpf_object__init_prog_names(struct bpf_object *obj) prog->section_name); return -EINVAL; } - +skip_search: prog->name = strdup(name); if (!prog->name) { pr_warning("failed to allocate memory for prog sym %s\n", @@ -795,6 +807,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if ((sh.sh_type == SHT_PROGBITS) && (sh.sh_flags & SHF_EXECINSTR) && (data->d_size > 0)) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; err = bpf_object__add_program(obj, data->d_buf, data->d_size, name, idx); if (err) { @@ -856,11 +870,14 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } static int -bpf_program__collect_reloc(struct bpf_program *prog, - size_t nr_maps, GElf_Shdr *shdr, - Elf_Data *data, Elf_Data *symbols, - int maps_shndx, struct bpf_map *maps) +bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, + Elf_Data *data, struct bpf_object *obj) { + Elf_Data *symbols = obj->efile.symbols; + int text_shndx = obj->efile.text_shndx; + int maps_shndx = obj->efile.maps_shndx; + struct bpf_map *maps = obj->maps; + size_t nr_maps = obj->nr_maps; int i, nrels; pr_debug("collecting relocating info for: '%s'\n", @@ -893,8 +910,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } + pr_debug("relo for %ld value %ld name %d\n", + rel.r_info >> 32, sym.st_value, sym.st_name); - if (sym.st_shndx != maps_shndx) { + if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", prog->section_name, sym.st_shndx); return -LIBBPF_ERRNO__RELOC; @@ -903,6 +922,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, insn_idx = rel.r_offset / sizeof(struct bpf_insn); pr_debug("relocation: insn_idx=%u\n", insn_idx); + if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { + if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { + pr_warning("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + prog->reloc_desc[i].type = RELO_CALL; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].text_off = sym.st_value; + continue; + } + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", insn_idx, insns[insn_idx].code); @@ -924,6 +954,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } + prog->reloc_desc[i].type = RELO_LD64; prog->reloc_desc[i].insn_idx = insn_idx; prog->reloc_desc[i].map_idx = map_idx; } @@ -962,28 +993,77 @@ bpf_object__create_maps(struct bpf_object *obj) return 0; } +static int +bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, + struct reloc_desc *relo) +{ + struct bpf_insn *insn, *new_insn; + struct bpf_program *text; + size_t new_cnt; + + if (relo->type != RELO_CALL) + return -LIBBPF_ERRNO__RELOC; + + if (prog->idx == obj->efile.text_shndx) { + pr_warning("relo in .text insn %d into off %d\n", + relo->insn_idx, relo->text_off); + return -LIBBPF_ERRNO__RELOC; + } + + if (prog->main_prog_cnt == 0) { + text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); + if (!text) { + pr_warning("no .text section found yet relo into text exist\n"); + return -LIBBPF_ERRNO__RELOC; + } + new_cnt = prog->insns_cnt + text->insns_cnt; + new_insn = realloc(prog->insns, new_cnt * sizeof(*insn)); + if (!new_insn) { + pr_warning("oom in prog realloc\n"); + return -ENOMEM; + } + memcpy(new_insn + prog->insns_cnt, text->insns, + text->insns_cnt * sizeof(*insn)); + prog->insns = new_insn; + prog->main_prog_cnt = prog->insns_cnt; + prog->insns_cnt = new_cnt; + } + insn = &prog->insns[relo->insn_idx]; + insn->imm += prog->main_prog_cnt - relo->insn_idx; + pr_debug("added %zd insn from %s to prog %s\n", + text->insns_cnt, text->section_name, prog->section_name); + return 0; +} + static int bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) { - int i; + int i, err; if (!prog || !prog->reloc_desc) return 0; for (i = 0; i < prog->nr_reloc; i++) { - int insn_idx, map_idx; - struct bpf_insn *insns = prog->insns; + if (prog->reloc_desc[i].type == RELO_LD64) { + struct bpf_insn *insns = prog->insns; + int insn_idx, map_idx; - insn_idx = prog->reloc_desc[i].insn_idx; - map_idx = prog->reloc_desc[i].map_idx; + insn_idx = prog->reloc_desc[i].insn_idx; + map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { - pr_warning("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; + if (insn_idx >= (int)prog->insns_cnt) { + pr_warning("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + insns[insn_idx].imm = obj->maps[map_idx].fd; + } else { + err = bpf_program__reloc_text(prog, obj, + &prog->reloc_desc[i]); + if (err) + return err; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - insns[insn_idx].imm = obj->maps[map_idx].fd; } zfree(&prog->reloc_desc); @@ -1026,7 +1106,6 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) Elf_Data *data = obj->efile.reloc[i].data; int idx = shdr->sh_info; struct bpf_program *prog; - size_t nr_maps = obj->nr_maps; if (shdr->sh_type != SHT_REL) { pr_warning("internal error at %d\n", __LINE__); @@ -1040,11 +1119,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return -LIBBPF_ERRNO__RELOC; } - err = bpf_program__collect_reloc(prog, nr_maps, + err = bpf_program__collect_reloc(prog, shdr, data, - obj->efile.symbols, - obj->efile.maps_shndx, - obj->maps); + obj); if (err) return err; } @@ -1197,6 +1274,8 @@ bpf_object__load_progs(struct bpf_object *obj) int err; for (i = 0; i < obj->nr_programs; i++) { + if (obj->programs[i].idx == obj->efile.text_shndx) + continue; err = bpf_program__load(&obj->programs[i], obj->license, obj->kern_version); @@ -1859,7 +1938,7 @@ long libbpf_get_error(const void *ptr) int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd) { - struct bpf_program *prog; + struct bpf_program *prog, *first_prog = NULL; struct bpf_object *obj; int err; @@ -1867,25 +1946,30 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, if (IS_ERR(obj)) return -ENOENT; - prog = bpf_program__next(NULL, obj); - if (!prog) { - bpf_object__close(obj); - return -ENOENT; - } - - /* - * If type is not specified, try to guess it based on - * section name. - */ - if (type == BPF_PROG_TYPE_UNSPEC) { - type = bpf_program__guess_type(prog); + bpf_object__for_each_program(prog, obj) { + /* + * If type is not specified, try to guess it based on + * section name. + */ if (type == BPF_PROG_TYPE_UNSPEC) { - bpf_object__close(obj); - return -EINVAL; + type = bpf_program__guess_type(prog); + if (type == BPF_PROG_TYPE_UNSPEC) { + bpf_object__close(obj); + return -EINVAL; + } } + + bpf_program__set_type(prog, type); + if (prog->idx != obj->efile.text_shndx && !first_prog) + first_prog = prog; + } + + if (!first_prog) { + pr_warning("object file doesn't contain bpf program\n"); + bpf_object__close(obj); + return -ENOENT; } - bpf_program__set_type(prog, type); err = bpf_object__load(obj); if (err) { bpf_object__close(obj); @@ -1893,6 +1977,6 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, } *pobj = obj; - *prog_fd = bpf_program__fd(prog); + *prog_fd = bpf_program__fd(first_prog); return 0; } -- cgit v1.2.3 From 675fc275a3a2d905535207237402c6d8dcb5fa4b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 27 Dec 2017 18:39:09 -0800 Subject: bpf: offload: report device information for offloaded programs Report to the user ifindex and namespace information of offloaded programs. If device has disappeared return -ENODEV. Specify the namespace using dev/inode combination. CC: Eric W. Biederman Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 3 +++ kernel/bpf/offload.c | 59 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 +++++ tools/include/uapi/linux/bpf.h | 3 +++ 5 files changed, 73 insertions(+) (limited to 'tools/include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9a916ab34299..7810ae57b357 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -531,6 +531,8 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); +int bpf_prog_offload_info_fill(struct bpf_prog_info *info, + struct bpf_prog *prog); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 69eabfcb9bdb..f2f8b36e2ad4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -921,6 +921,9 @@ struct bpf_prog_info { __u32 nr_map_ids; __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u64 netns_dev; + __u64 netns_ino; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index e4f1668a021c..040d4e0edf3f 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -16,9 +16,11 @@ #include #include #include +#include #include #include #include +#include #include #include @@ -176,6 +178,63 @@ int bpf_prog_offload_compile(struct bpf_prog *prog) return bpf_prog_offload_translate(prog); } +struct ns_get_path_bpf_prog_args { + struct bpf_prog *prog; + struct bpf_prog_info *info; +}; + +static struct ns_common *bpf_prog_offload_info_fill_ns(void *private_data) +{ + struct ns_get_path_bpf_prog_args *args = private_data; + struct bpf_prog_aux *aux = args->prog->aux; + struct ns_common *ns; + struct net *net; + + rtnl_lock(); + down_read(&bpf_devs_lock); + + if (aux->offload) { + args->info->ifindex = aux->offload->netdev->ifindex; + net = dev_net(aux->offload->netdev); + get_net(net); + ns = &net->ns; + } else { + args->info->ifindex = 0; + ns = NULL; + } + + up_read(&bpf_devs_lock); + rtnl_unlock(); + + return ns; +} + +int bpf_prog_offload_info_fill(struct bpf_prog_info *info, + struct bpf_prog *prog) +{ + struct ns_get_path_bpf_prog_args args = { + .prog = prog, + .info = info, + }; + struct inode *ns_inode; + struct path ns_path; + void *res; + + res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args); + if (IS_ERR(res)) { + if (!info->ifindex) + return -ENODEV; + return PTR_ERR(res); + } + + ns_inode = ns_path.dentry->d_inode; + info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev); + info->netns_ino = ns_inode->i_ino; + path_put(&ns_path); + + return 0; +} + const struct bpf_prog_ops bpf_offload_prog_ops = { }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e02dafa6f402..ebf0fb23e237 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1707,6 +1707,12 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + if (bpf_prog_is_dev_bound(prog->aux)) { + err = bpf_prog_offload_info_fill(&info, prog); + if (err) + return err; + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index db1b0923a308..4e8c60acfa32 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -921,6 +921,9 @@ struct bpf_prog_info { __u32 nr_map_ids; __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u64 netns_dev; + __u64 netns_ino; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From a38845729ea3985db5d2544ec3ef3dc8f6313a27 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:09 -0800 Subject: bpf: offload: add map offload infrastructure BPF map offload follow similar path to program offload. At creation time users may specify ifindex of the device on which they want to create the map. Map will be validated by the kernel's .map_alloc_check callback and device driver will be called for the actual allocation. Map will have an empty set of operations associated with it (save for alloc and free callbacks). The real device callbacks are kept in map->offload->dev_ops because they have slightly different signatures. Map operations are called in process context so the driver may communicate with HW freely, msleep(), wait() etc. Map alloc and free callbacks are muxed via existing .ndo_bpf, and are always called with rtnl lock held. Maps and programs are guaranteed to be destroyed before .ndo_uninit (i.e. before unregister_netdev() returns). Map callbacks are invoked with bpf_devs_lock *read* locked, drivers must take care of exclusive locking if necessary. All offload-specific branches are marked with unlikely() (through bpf_map_is_dev_bound()), given that branch penalty will be negligible compared to IO anyway, and we don't want to penalize SW path unnecessarily. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 59 +++++++++++++ include/linux/netdevice.h | 6 ++ include/uapi/linux/bpf.h | 1 + kernel/bpf/offload.c | 188 +++++++++++++++++++++++++++++++++++++++-- kernel/bpf/syscall.c | 44 ++++++++-- kernel/bpf/verifier.c | 7 ++ tools/include/uapi/linux/bpf.h | 1 + 7 files changed, 293 insertions(+), 13 deletions(-) (limited to 'tools/include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9fff1ace1d8e..5c2c104dc2c5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -74,6 +74,33 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offloaded_map; + +struct bpf_map_dev_ops { + int (*map_get_next_key)(struct bpf_offloaded_map *map, + void *key, void *next_key); + int (*map_lookup_elem)(struct bpf_offloaded_map *map, + void *key, void *value); + int (*map_update_elem)(struct bpf_offloaded_map *map, + void *key, void *value, u64 flags); + int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); +}; + +struct bpf_offloaded_map { + struct bpf_map map; + struct net_device *netdev; + const struct bpf_map_dev_ops *dev_ops; + void *dev_priv; + struct list_head offloads; +}; + +static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) +{ + return container_of(map, struct bpf_offloaded_map, map); +} + +extern const struct bpf_map_ops bpf_map_offload_ops; + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -369,6 +396,7 @@ int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); +void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -556,6 +584,15 @@ void bpf_prog_offload_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); +int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); +int bpf_map_offload_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags); +int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); +int bpf_map_offload_get_next_key(struct bpf_map *map, + void *key, void *next_key); + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); @@ -563,6 +600,14 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return aux->offload_requested; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return unlikely(map->ops == &bpf_map_offload_ops); +} + +struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); +void bpf_map_offload_map_free(struct bpf_map *map); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -574,6 +619,20 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return false; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return false; +} + +static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void bpf_map_offload_map_free(struct bpf_map *map) +{ +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef7b348e8498..0b3ab42d50fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -804,6 +804,8 @@ enum bpf_netdev_command { BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, + BPF_OFFLOAD_MAP_ALLOC, + BPF_OFFLOAD_MAP_FREE, }; struct bpf_prog_offload_ops; @@ -834,6 +836,10 @@ struct netdev_bpf { struct { struct bpf_prog *prog; } offload; + /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ + struct { + struct bpf_offloaded_map *offmap; + }; }; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 395d261948de..7c2259e8bc54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -245,6 +245,7 @@ union bpf_attr { * BPF_F_NUMA_NODE is set). */ char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index cdd1e19a668b..453785fa1881 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -24,11 +24,13 @@ #include #include -/* Protects bpf_prog_offload_devs and offload members of all progs. +/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members + * of all progs. * RTNL lock cannot be taken when holding this lock. */ static DECLARE_RWSEM(bpf_devs_lock); static LIST_HEAD(bpf_prog_offload_devs); +static LIST_HEAD(bpf_map_offload_devs); static int bpf_dev_offload_check(struct net_device *netdev) { @@ -250,11 +252,186 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, const struct bpf_prog_ops bpf_offload_prog_ops = { }; +static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, + enum bpf_netdev_command cmd) +{ + struct netdev_bpf data = {}; + struct net_device *netdev; + + ASSERT_RTNL(); + + data.command = cmd; + data.offmap = offmap; + /* Caller must make sure netdev is valid */ + netdev = offmap->netdev; + + return netdev->netdev_ops->ndo_bpf(netdev, &data); +} + +struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_offloaded_map *offmap; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + if (attr->map_type != BPF_MAP_TYPE_HASH) + return ERR_PTR(-EINVAL); + + offmap = kzalloc(sizeof(*offmap), GFP_USER); + if (!offmap) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&offmap->map, attr); + + rtnl_lock(); + down_write(&bpf_devs_lock); + offmap->netdev = __dev_get_by_index(net, attr->map_ifindex); + err = bpf_dev_offload_check(offmap->netdev); + if (err) + goto err_unlock; + + err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC); + if (err) + goto err_unlock; + + list_add_tail(&offmap->offloads, &bpf_map_offload_devs); + up_write(&bpf_devs_lock); + rtnl_unlock(); + + return &offmap->map; + +err_unlock: + up_write(&bpf_devs_lock); + rtnl_unlock(); + kfree(offmap); + return ERR_PTR(err); +} + +static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) +{ + WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); + /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ + bpf_map_free_id(&offmap->map, true); + list_del_init(&offmap->offloads); + offmap->netdev = NULL; +} + +void bpf_map_offload_map_free(struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + + rtnl_lock(); + down_write(&bpf_devs_lock); + if (offmap->netdev) + __bpf_map_offload_destroy(offmap); + up_write(&bpf_devs_lock); + rtnl_unlock(); + + kfree(offmap); +} + +int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_lookup_elem(offmap, key, value); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_update_elem(offmap, key, value, + flags); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_delete_elem(offmap, key); + up_read(&bpf_devs_lock); + + return ret; +} + +int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_offloaded_map *offmap = map_to_offmap(map); + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + if (offmap->netdev) + ret = offmap->dev_ops->map_get_next_key(offmap, key, next_key); + up_read(&bpf_devs_lock); + + return ret; +} + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap; + struct bpf_prog_offload *offload; + bool ret; + + if (!!bpf_prog_is_dev_bound(prog->aux) != !!bpf_map_is_dev_bound(map)) + return false; + if (!bpf_prog_is_dev_bound(prog->aux)) + return true; + + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + offmap = map_to_offmap(map); + + ret = offload && offload->netdev == offmap->netdev; + up_read(&bpf_devs_lock); + + return ret; +} + +static void bpf_offload_orphan_all_progs(struct net_device *netdev) +{ + struct bpf_prog_offload *offload, *tmp; + + list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads) + if (offload->netdev == netdev) + __bpf_prog_offload_destroy(offload->prog); +} + +static void bpf_offload_orphan_all_maps(struct net_device *netdev) +{ + struct bpf_offloaded_map *offmap, *tmp; + + list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads) + if (offmap->netdev == netdev) + __bpf_map_offload_destroy(offmap); +} + static int bpf_offload_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); - struct bpf_prog_offload *offload, *tmp; ASSERT_RTNL(); @@ -265,11 +442,8 @@ static int bpf_offload_notification(struct notifier_block *notifier, break; down_write(&bpf_devs_lock); - list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, - offloads) { - if (offload->netdev == netdev) - __bpf_prog_offload_destroy(offload->prog); - } + bpf_offload_orphan_all_progs(netdev); + bpf_offload_orphan_all_maps(netdev); up_write(&bpf_devs_lock); break; default: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a3f726bb42ea..c691b9e972e3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -94,6 +94,11 @@ static int check_uarg_tail_zero(void __user *uaddr, return 0; } +const struct bpf_map_ops bpf_map_offload_ops = { + .map_alloc = bpf_map_offload_map_alloc, + .map_free = bpf_map_offload_map_free, +}; + static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { const struct bpf_map_ops *ops; @@ -111,6 +116,8 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) if (err) return ERR_PTR(err); } + if (attr->map_ifindex) + ops = &bpf_map_offload_ops; map = ops->map_alloc(attr); if (IS_ERR(map)) return map; @@ -208,16 +215,25 @@ static int bpf_map_alloc_id(struct bpf_map *map) return id > 0 ? 0 : id; } -static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { unsigned long flags; + /* Offloaded maps are removed from the IDR store when their device + * disappears - even if someone holds an fd to them they are unusable, + * the memory is gone, all ops will fail; they are simply waiting for + * refcnt to drop to be freed. + */ + if (!map->id) + return; + if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); + map->id = 0; if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); @@ -397,7 +413,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_name +#define BPF_MAP_CREATE_LAST_FIELD map_ifindex /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -585,8 +601,10 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -673,7 +691,10 @@ static int map_update_elem(union bpf_attr *attr) goto free_value; /* Need to create a kthread, thus must support schedule */ - if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_update_elem(map, key, value, attr->flags); + goto out; + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } @@ -750,6 +771,11 @@ static int map_delete_elem(union bpf_attr *attr) goto err_put; } + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_delete_elem(map, key); + goto out; + } + preempt_disable(); __this_cpu_inc(bpf_prog_active); rcu_read_lock(); @@ -757,7 +783,7 @@ static int map_delete_elem(union bpf_attr *attr) rcu_read_unlock(); __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_delete_elem(map, ufd, key); kfree(key); @@ -807,9 +833,15 @@ static int map_get_next_key(union bpf_attr *attr) if (!next_key) goto free_key; + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_get_next_key(map, key, next_key); + goto out; + } + rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); +out: if (err) goto free_next_key; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 48b61caa94cb..ceabb394d2dc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4816,6 +4816,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } } + + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && + !bpf_offload_dev_match(prog, map)) { + verbose(env, "offload device mismatch between prog and map\n"); + return -EINVAL; + } + return 0; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4e8c60acfa32..69f96af4a569 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -245,6 +245,7 @@ union bpf_attr { * BPF_F_NUMA_NODE is set). */ char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ -- cgit v1.2.3 From e7b2823a582a5bca5ee47644f448e317178e8824 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 18 Jan 2018 17:49:08 +0100 Subject: bpf: Sync kernel ABI header with tooling header Update tools/include/uapi/linux/bpf.h to bring it in sync with include/uapi/linux/bpf.h. The listed commits forgot to update it. Fixes: 02dd3291b2f0 ("bpf: finally expose xdp_rxq_info to XDP bpf-programs") Fixes: f19397a5c656 ("bpf: Add access to snd_cwnd and others in sock_ops") Fixes: 06ef0ccb5a36 ("bpf/cgroup: fix a verification error for a CGROUP_DEVICE type prog") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 69f96af4a569..7c2259e8bc54 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -900,6 +900,9 @@ struct xdp_md { __u32 data; __u32 data_end; __u32 data_meta; + /* Below access go through struct xdp_rxq_info */ + __u32 ingress_ifindex; /* rxq->dev->ifindex */ + __u32 rx_queue_index; /* rxq->queue_index */ }; enum sk_action { @@ -956,6 +959,12 @@ struct bpf_sock_ops { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ }; /* List of known BPF sock_ops operators. @@ -1010,7 +1019,8 @@ struct bpf_perf_event_value { #define BPF_DEVCG_DEV_CHAR (1ULL << 1) struct bpf_cgroup_dev_ctx { - __u32 access_type; /* (access << 16) | type */ + /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ + __u32 access_type; __u32 major; __u32 minor; }; -- cgit v1.2.3 From 52775b33bb5072fbc07b02c0cf4fe8da1f7ee7cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 17 Jan 2018 19:13:28 -0800 Subject: bpf: offload: report device information about offloaded maps Tell user space about device on which the map was created. Unfortunate reality of user ABI makes sharing this code with program offload difficult but the information is the same. Signed-off-by: Jakub Kicinski Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 3 +++ kernel/bpf/offload.c | 55 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 +++++ tools/include/uapi/linux/bpf.h | 3 +++ 5 files changed, 69 insertions(+) (limited to 'tools/include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 025b1c2f8053..66df387106de 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -586,6 +586,8 @@ void bpf_prog_offload_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); +int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); + int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 74dc4dc98681..406c19d6016b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -938,6 +938,9 @@ struct bpf_map_info { __u32 max_entries; __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u64 netns_dev; + __u64 netns_ino; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 2657976aec2a..c9401075b58c 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -413,6 +413,61 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key) return ret; } +struct ns_get_path_bpf_map_args { + struct bpf_offloaded_map *offmap; + struct bpf_map_info *info; +}; + +static struct ns_common *bpf_map_offload_info_fill_ns(void *private_data) +{ + struct ns_get_path_bpf_map_args *args = private_data; + struct ns_common *ns; + struct net *net; + + rtnl_lock(); + down_read(&bpf_devs_lock); + + if (args->offmap->netdev) { + args->info->ifindex = args->offmap->netdev->ifindex; + net = dev_net(args->offmap->netdev); + get_net(net); + ns = &net->ns; + } else { + args->info->ifindex = 0; + ns = NULL; + } + + up_read(&bpf_devs_lock); + rtnl_unlock(); + + return ns; +} + +int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct ns_get_path_bpf_map_args args = { + .offmap = map_to_offmap(map), + .info = info, + }; + struct inode *ns_inode; + struct path ns_path; + void *res; + + res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args); + if (IS_ERR(res)) { + if (!info->ifindex) + return -ENODEV; + return PTR_ERR(res); + } + + ns_inode = ns_path.dentry->d_inode; + info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev); + info->netns_ino = ns_inode->i_ino; + path_put(&ns_path); + + return 0; +} + bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) { struct bpf_offloaded_map *offmap; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 97a825ffc763..5bdb0cc84ad2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1801,6 +1801,12 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.map_flags = map->map_flags; memcpy(info.name, map->name, sizeof(map->name)); + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_info_fill(&info, map); + if (err) + return err; + } + if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7c2259e8bc54..af1f49ad8b88 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -938,6 +938,9 @@ struct bpf_map_info { __u32 max_entries; __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u64 netns_dev; + __u64 netns_ino; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops -- cgit v1.2.3 From d6d4f60c3a0933852dcc40a2142d93027ea1da76 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Thu, 25 Jan 2018 16:14:16 -0800 Subject: bpf: add selftest for tcpbpf Added a selftest for tcpbpf (sock_ops) that checks that the appropriate callbacks occured and that it can access tcp_sock fields and that their values are correct. Run with command: ./test_tcpbpf_user Adding the flag "-d" will show why it did not pass. Signed-off-by: Lawrence Brakmo Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 86 ++++++++++++++++- tools/testing/selftests/bpf/Makefile | 4 +- tools/testing/selftests/bpf/bpf_helpers.h | 2 + tools/testing/selftests/bpf/tcp_client.py | 51 ++++++++++ tools/testing/selftests/bpf/tcp_server.py | 83 ++++++++++++++++ tools/testing/selftests/bpf/test_tcpbpf.h | 16 ++++ tools/testing/selftests/bpf/test_tcpbpf_kern.c | 118 +++++++++++++++++++++++ tools/testing/selftests/bpf/test_tcpbpf_user.c | 126 +++++++++++++++++++++++++ 8 files changed, 480 insertions(+), 6 deletions(-) create mode 100755 tools/testing/selftests/bpf/tcp_client.py create mode 100755 tools/testing/selftests/bpf/tcp_server.py create mode 100644 tools/testing/selftests/bpf/test_tcpbpf.h create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_kern.c create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_user.c (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index af1f49ad8b88..db6bdc375126 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -17,7 +17,7 @@ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ -#define BPF_DW 0x18 /* double word */ +#define BPF_DW 0x18 /* double word (64-bit) */ #define BPF_XADD 0xc0 /* exclusive add */ /* alu/jmp fields */ @@ -642,6 +642,14 @@ union bpf_attr { * @optlen: length of optval in bytes * Return: 0 or negative error * + * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) + * Set callback flags for sock_ops + * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct + * @flags: flags value + * Return: 0 for no error + * -EINVAL if there is no full tcp socket + * bits in flags that are not supported by current kernel + * * int bpf_skb_adjust_room(skb, len_diff, mode, flags) * Grow or shrink room in sk_buff. * @skb: pointer to skb @@ -748,7 +756,8 @@ union bpf_attr { FN(perf_event_read_value), \ FN(perf_prog_read_value), \ FN(getsockopt), \ - FN(override_return), + FN(override_return), \ + FN(sock_ops_cb_flags_set), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -952,8 +961,9 @@ struct bpf_map_info { struct bpf_sock_ops { __u32 op; union { - __u32 reply; - __u32 replylong[4]; + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ }; __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -968,8 +978,39 @@ struct bpf_sock_ops { */ __u32 snd_cwnd; __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; }; +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + * supported cb flags + */ + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -1003,6 +1044,43 @@ enum { * a congestion threshold. RTTs above * this indicate congestion */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum { + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + + BPF_TCP_MAX_STATES /* Leave at the end! */ }; #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 3a44b655d852..98688352208b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -14,13 +14,13 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i LDLIBS += -lcap -lelf -lrt TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align test_verifier_log test_dev_cgroup + test_align test_verifier_log test_dev_cgroup test_tcpbpf_user TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ - sample_map_ret0.o + sample_map_ret0.o test_tcpbpf_kern.o TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \ test_offload.py diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 33cb00e46c49..dde2c11d7771 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -71,6 +71,8 @@ static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_getsockopt; +static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) = + (void *) BPF_FUNC_sock_ops_cb_flags_set; static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; static int (*bpf_sock_map_update)(void *map, void *key, void *value, diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py new file mode 100755 index 000000000000..481dccdf140c --- /dev/null +++ b/tools/testing/selftests/bpf/tcp_client.py @@ -0,0 +1,51 @@ +#!/usr/bin/env python2 +# +# SPDX-License-Identifier: GPL-2.0 +# + +import sys, os, os.path, getopt +import socket, time +import subprocess +import select + +def read(sock, n): + buf = '' + while len(buf) < n: + rem = n - len(buf) + try: s = sock.recv(rem) + except (socket.error), e: return '' + buf += s + return buf + +def send(sock, s): + total = len(s) + count = 0 + while count < total: + try: n = sock.send(s) + except (socket.error), e: n = 0 + if n == 0: + return count; + count += n + return count + + +serverPort = int(sys.argv[1]) +HostName = socket.gethostname() + +# create active socket +sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) +try: + sock.connect((HostName, serverPort)) +except socket.error as e: + sys.exit(1) + +buf = '' +n = 0 +while n < 1000: + buf += '+' + n += 1 + +sock.settimeout(1); +n = send(sock, buf) +n = read(sock, 500) +sys.exit(0) diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py new file mode 100755 index 000000000000..bc454d7d0be2 --- /dev/null +++ b/tools/testing/selftests/bpf/tcp_server.py @@ -0,0 +1,83 @@ +#!/usr/bin/env python2 +# +# SPDX-License-Identifier: GPL-2.0 +# + +import sys, os, os.path, getopt +import socket, time +import subprocess +import select + +def read(sock, n): + buf = '' + while len(buf) < n: + rem = n - len(buf) + try: s = sock.recv(rem) + except (socket.error), e: return '' + buf += s + return buf + +def send(sock, s): + total = len(s) + count = 0 + while count < total: + try: n = sock.send(s) + except (socket.error), e: n = 0 + if n == 0: + return count; + count += n + return count + + +SERVER_PORT = 12877 +MAX_PORTS = 2 + +serverPort = SERVER_PORT +serverSocket = None + +HostName = socket.gethostname() + +# create passive socket +serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) +host = socket.gethostname() + +try: serverSocket.bind((host, 0)) +except socket.error as msg: + print 'bind fails: ', msg + +sn = serverSocket.getsockname() +serverPort = sn[1] + +cmdStr = ("./tcp_client.py %d &") % (serverPort) +os.system(cmdStr) + +buf = '' +n = 0 +while n < 500: + buf += '.' + n += 1 + +serverSocket.listen(MAX_PORTS) +readList = [serverSocket] + +while True: + readyRead, readyWrite, inError = \ + select.select(readList, [], [], 2) + + if len(readyRead) > 0: + waitCount = 0 + for sock in readyRead: + if sock == serverSocket: + (clientSocket, address) = serverSocket.accept() + address = str(address[0]) + readList.append(clientSocket) + else: + sock.settimeout(1); + s = read(sock, 1000) + n = send(sock, buf) + sock.close() + serverSocket.close() + sys.exit(0) + else: + print 'Select timeout!' + sys.exit(1) diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h new file mode 100644 index 000000000000..2fe43289943c --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _TEST_TCPBPF_H +#define _TEST_TCPBPF_H + +struct tcpbpf_globals { + __u32 event_map; + __u32 total_retrans; + __u32 data_segs_in; + __u32 data_segs_out; + __u32 bad_cb_test_rv; + __u32 good_cb_test_rv; + __u64 bytes_received; + __u64 bytes_acked; +}; +#endif diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c new file mode 100644 index 000000000000..66bf71541903 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_tcpbpf.h" + +struct bpf_map_def SEC("maps") global_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct tcpbpf_globals), + .max_entries = 2, +}; + +static inline void update_event_map(int event) +{ + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (gp == NULL) { + struct tcpbpf_globals g = {0}; + + g.event_map |= (1 << event); + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } else { + g = *gp; + g.event_map |= (1 << event); + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } +} + +int _version SEC("version") = 1; + +SEC("sockops") +int bpf_testcb(struct bpf_sock_ops *skops) +{ + int rv = -1; + int bad_call_rv = 0; + int good_call_rv = 0; + int op; + int v = 0; + + op = (int) skops->op; + + update_event_map(op); + + switch (op) { + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + /* Test failure to set largest cb flag (assumes not defined) */ + bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80); + /* Set callback */ + good_call_rv = bpf_sock_ops_cb_flags_set(skops, + BPF_SOCK_OPS_STATE_CB_FLAG); + /* Update results */ + { + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.bad_cb_test_rv = bad_call_rv; + g.good_cb_test_rv = good_call_rv; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + /* Set callback */ +// good_call_rv = bpf_sock_ops_cb_flags_set(skops, +// BPF_SOCK_OPS_STATE_CB_FLAG); + skops->sk_txhash = 0x12345f; + v = 0xff; + rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, + sizeof(v)); + break; + case BPF_SOCK_OPS_RTO_CB: + break; + case BPF_SOCK_OPS_RETRANS_CB: + break; + case BPF_SOCK_OPS_STATE_CB: + if (skops->args[1] == BPF_TCP_CLOSE) { + __u32 key = 0; + struct tcpbpf_globals g, *gp; + + gp = bpf_map_lookup_elem(&global_map, &key); + if (!gp) + break; + g = *gp; + g.total_retrans = skops->total_retrans; + g.data_segs_in = skops->data_segs_in; + g.data_segs_out = skops->data_segs_out; + g.bytes_received = skops->bytes_received; + g.bytes_acked = skops->bytes_acked; + bpf_map_update_elem(&global_map, &key, &g, + BPF_ANY); + } + break; + default: + rv = -1; + } + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c new file mode 100644 index 000000000000..95a370f3d378 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_util.h" +#include +#include "test_tcpbpf.h" + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) { + printf("%s:FAIL:map '%s' not found\n", test, name); + return -1; + } + return bpf_map__fd(map); +} + +#define SYSTEM(CMD) \ + do { \ + if (system(CMD)) { \ + printf("system(%s) FAILS!\n", CMD); \ + } \ + } while (0) + +int main(int argc, char **argv) +{ + const char *file = "test_tcpbpf_kern.o"; + struct tcpbpf_globals g = {0}; + int cg_fd, prog_fd, map_fd; + bool debug_flag = false; + int error = EXIT_FAILURE; + struct bpf_object *obj; + char cmd[100], *dir; + struct stat buffer; + __u32 key = 0; + int pid; + int rv; + + if (argc > 1 && strcmp(argv[1], "-d") == 0) + debug_flag = true; + + dir = "/tmp/cgroupv2/foo"; + + if (stat(dir, &buffer) != 0) { + SYSTEM("mkdir -p /tmp/cgroupv2"); + SYSTEM("mount -t cgroup2 none /tmp/cgroupv2"); + SYSTEM("mkdir -p /tmp/cgroupv2/foo"); + } + pid = (int) getpid(); + sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid); + SYSTEM(cmd); + + cg_fd = open(dir, O_DIRECTORY, O_RDONLY); + if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { + printf("FAILED: load_bpf_file failed for: %s\n", file); + goto err; + } + + rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (rv) { + printf("FAILED: bpf_prog_attach: %d (%s)\n", + error, strerror(errno)); + goto err; + } + + SYSTEM("./tcp_server.py"); + + map_fd = bpf_find_map(__func__, obj, "global_map"); + if (map_fd < 0) + goto err; + + rv = bpf_map_lookup_elem(map_fd, &key, &g); + if (rv != 0) { + printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); + goto err; + } + + if (g.bytes_received != 501 || g.bytes_acked != 1002 || + g.data_segs_in != 1 || g.data_segs_out != 1 || + (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 || + g.good_cb_test_rv != 0) { + printf("FAILED: Wrong stats\n"); + if (debug_flag) { + printf("\n"); + printf("bytes_received: %d (expecting 501)\n", + (int)g.bytes_received); + printf("bytes_acked: %d (expecting 1002)\n", + (int)g.bytes_acked); + printf("data_segs_in: %d (expecting 1)\n", + g.data_segs_in); + printf("data_segs_out: %d (expecting 1)\n", + g.data_segs_out); + printf("event_map: 0x%x (at least 0x47e)\n", + g.event_map); + printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n", + g.bad_cb_test_rv); + printf("good_cb_test_rv:0x%x (expecting 0)\n", + g.good_cb_test_rv); + } + goto err; + } + printf("PASSED!\n"); + error = 0; +err: + bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); + return error; + +} -- cgit v1.2.3 From dc2b9f19e3bdaa87a7c3d123b8bba8a42d96d942 Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Tue, 30 Jan 2018 21:55:00 +0100 Subject: tools: add netlink.h and if_link.h in tools uapi The headers are necessary for libbpf compilation on system with older version of the headers. Signed-off-by: Eric Leblond Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/if_link.h | 943 +++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/netlink.h | 251 ++++++++++ tools/lib/bpf/Makefile | 6 + 3 files changed, 1200 insertions(+) create mode 100644 tools/include/uapi/linux/if_link.h create mode 100644 tools/include/uapi/linux/netlink.h (limited to 'tools/include') diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h new file mode 100644 index 000000000000..8616131e2c61 --- /dev/null +++ b/tools/include/uapi/linux/if_link.h @@ -0,0 +1,943 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include +#include + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ +}; + +/* The main device statistics structure */ +struct rtnl_link_stats64 { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ + __u64 multicast; /* multicast packets received */ + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; /* receiver ring buff overflow */ + __u64 rx_crc_errors; /* recved pkt with crc error */ + __u64 rx_frame_errors; /* recv'd frame alignment error */ + __u64 rx_fifo_errors; /* recv'r fifo overrun */ + __u64 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR section */ + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h new file mode 100644 index 000000000000..776bc92e9118 --- /dev/null +++ b/tools/include/uapi/linux/netlink.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include +#include /* for __kernel_sa_family_t */ +#include + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 83714ca1f22b..e6d5f8d1477f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -160,6 +160,12 @@ $(BPF_IN): force elfdep bpfdep @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \ + (diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \ + (diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf $(OUTPUT)libbpf.so: $(BPF_IN) -- cgit v1.2.3 From 0ade34c37012ea5c516d9aa4d19a56e9f40a55ed Mon Sep 17 00:00:00 2001 From: Clement Courbet Date: Tue, 6 Feb 2018 15:38:34 -0800 Subject: lib: optimize cpumask_next_and() We've measured that we spend ~0.6% of sys cpu time in cpumask_next_and(). It's essentially a joined iteration in search for a non-zero bit, which is currently implemented as a lookup join (find a nonzero bit on the lhs, lookup the rhs to see if it's set there). Implement a direct join (find a nonzero bit on the incrementally built join). Also add generic bitmap benchmarks in the new `test_find_bit` module for new function (see `find_next_and_bit` in [2] and [3] below). For cpumask_next_and, direct benchmarking shows that it's 1.17x to 14x faster with a geometric mean of 2.1 on 32 CPUs [1]. No impact on memory usage. Note that on Arm, the new pure-C implementation still outperforms the old one that uses a mix of C and asm (`find_next_bit`) [3]. [1] Approximate benchmark code: ``` unsigned long src1p[nr_cpumask_longs] = {pattern1}; unsigned long src2p[nr_cpumask_longs] = {pattern2}; for (/*a bunch of repetitions*/) { for (int n = -1; n <= nr_cpu_ids; ++n) { asm volatile("" : "+rm"(src1p)); // prevent any optimization asm volatile("" : "+rm"(src2p)); unsigned long result = cpumask_next_and(n, src1p, src2p); asm volatile("" : "+rm"(result)); } } ``` Results: pattern1 pattern2 time_before/time_after 0x0000ffff 0x0000ffff 1.65 0x0000ffff 0x00005555 2.24 0x0000ffff 0x00001111 2.94 0x0000ffff 0x00000000 14.0 0x00005555 0x0000ffff 1.67 0x00005555 0x00005555 1.71 0x00005555 0x00001111 1.90 0x00005555 0x00000000 6.58 0x00001111 0x0000ffff 1.46 0x00001111 0x00005555 1.49 0x00001111 0x00001111 1.45 0x00001111 0x00000000 3.10 0x00000000 0x0000ffff 1.18 0x00000000 0x00005555 1.18 0x00000000 0x00001111 1.17 0x00000000 0x00000000 1.25 ----------------------------- geo.mean 2.06 [2] test_find_next_bit, X86 (skylake) [ 3913.477422] Start testing find_bit() with random-filled bitmap [ 3913.477847] find_next_bit: 160868 cycles, 16484 iterations [ 3913.477933] find_next_zero_bit: 169542 cycles, 16285 iterations [ 3913.478036] find_last_bit: 201638 cycles, 16483 iterations [ 3913.480214] find_first_bit: 4353244 cycles, 16484 iterations [ 3913.480216] Start testing find_next_and_bit() with random-filled bitmap [ 3913.481074] find_next_and_bit: 89604 cycles, 8216 iterations [ 3913.481075] Start testing find_bit() with sparse bitmap [ 3913.481078] find_next_bit: 2536 cycles, 66 iterations [ 3913.481252] find_next_zero_bit: 344404 cycles, 32703 iterations [ 3913.481255] find_last_bit: 2006 cycles, 66 iterations [ 3913.481265] find_first_bit: 17488 cycles, 66 iterations [ 3913.481266] Start testing find_next_and_bit() with sparse bitmap [ 3913.481272] find_next_and_bit: 764 cycles, 1 iterations [3] test_find_next_bit, arm (v7 odroid XU3). [ 267.206928] Start testing find_bit() with random-filled bitmap [ 267.214752] find_next_bit: 4474 cycles, 16419 iterations [ 267.221850] find_next_zero_bit: 5976 cycles, 16350 iterations [ 267.229294] find_last_bit: 4209 cycles, 16419 iterations [ 267.279131] find_first_bit: 1032991 cycles, 16420 iterations [ 267.286265] Start testing find_next_and_bit() with random-filled bitmap [ 267.302386] find_next_and_bit: 2290 cycles, 8140 iterations [ 267.309422] Start testing find_bit() with sparse bitmap [ 267.316054] find_next_bit: 191 cycles, 66 iterations [ 267.322726] find_next_zero_bit: 8758 cycles, 32703 iterations [ 267.329803] find_last_bit: 84 cycles, 66 iterations [ 267.336169] find_first_bit: 4118 cycles, 66 iterations [ 267.342627] Start testing find_next_and_bit() with sparse bitmap [ 267.356919] find_next_and_bit: 91 cycles, 1 iterations [courbet@google.com: v6] Link: http://lkml.kernel.org/r/20171129095715.23430-1-courbet@google.com [geert@linux-m68k.org: m68k/bitops: always include ] Link: http://lkml.kernel.org/r/1512556816-28627-1-git-send-email-geert@linux-m68k.org Link: http://lkml.kernel.org/r/20171128131334.23491-1-courbet@google.com Signed-off-by: Clement Courbet Signed-off-by: Geert Uytterhoeven Cc: Yury Norov Cc: Geert Uytterhoeven Cc: Alexey Dobriyan Cc: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/bitops.h | 1 + arch/m68k/include/asm/bitops.h | 3 +- arch/unicore32/include/asm/bitops.h | 2 ++ include/asm-generic/bitops/find.h | 20 +++++++++++ include/linux/bitmap.h | 6 +++- lib/cpumask.c | 9 ++--- lib/find_bit.c | 59 ++++++++++++++++++++++++--------- lib/find_bit_benchmark.c | 25 +++++++++++++- tools/include/asm-generic/bitops/find.h | 16 +++++++++ tools/lib/find_bit.c | 39 ++++++++++++++++------ 10 files changed, 147 insertions(+), 33 deletions(-) (limited to 'tools/include') diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index ce5ee762ed66..4cab9bb823fb 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -338,6 +338,7 @@ static inline int find_next_bit_le(const void *p, int size, int offset) #endif +#include #include /* diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index dda58cfe8c22..93b47b1f6fb4 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -311,7 +311,6 @@ static inline int bfchg_mem_test_and_change_bit(int nr, * functions. */ #if defined(CONFIG_CPU_HAS_NO_BITFIELDS) -#include #include #else @@ -441,6 +440,8 @@ static inline unsigned long ffz(unsigned long word) #endif +#include + #ifdef __KERNEL__ #if defined(CONFIG_CPU_HAS_NO_BITFIELDS) diff --git a/arch/unicore32/include/asm/bitops.h b/arch/unicore32/include/asm/bitops.h index 401f597bc38c..c0cbdbe17168 100644 --- a/arch/unicore32/include/asm/bitops.h +++ b/arch/unicore32/include/asm/bitops.h @@ -44,4 +44,6 @@ static inline int fls(int x) #define find_first_bit find_first_bit #define find_first_zero_bit find_first_zero_bit +#include + #endif /* __UNICORE_BITOPS_H__ */ diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 1ba611e16fa0..8a1ee10014de 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -16,6 +16,22 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset); #endif +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +extern unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset); +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region @@ -55,8 +71,12 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size); #else /* CONFIG_GENERIC_FIND_FIRST_BIT */ +#ifndef find_first_bit #define find_first_bit(addr, size) find_next_bit((addr), (size), 0) +#endif +#ifndef find_first_zero_bit #define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) +#endif #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index d9bf699e0e7a..5f11fbdc27f8 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -88,8 +88,12 @@ * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr - * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit + * find_next_zero_bit(addr, nbits, bit) + * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit + * find_next_and_bit(addr1, addr2, nbits, bit) + * Same as find_next_bit, but in + * (*addr1 & *addr2) * */ diff --git a/lib/cpumask.c b/lib/cpumask.c index 35fe142ebb5e..beca6244671a 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -33,10 +33,11 @@ EXPORT_SYMBOL(cpumask_next); int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - while ((n = cpumask_next(n, src1p)) < nr_cpu_ids) - if (cpumask_test_cpu(n, src2p)) - break; - return n; + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); diff --git a/lib/find_bit.c b/lib/find_bit.c index 6ed74f78380c..ee3df93ba69a 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -21,22 +21,29 @@ #include #include -#if !defined(find_next_bit) || !defined(find_next_zero_bit) +#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ + !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit and - * find_next_zero_bit. The difference is the "invert" argument, which - * is XORed with each fetched word before searching it for one bits. + * This is a common helper function for find_next_bit, find_next_zero_bit, and + * find_next_and_bit. The differences are: + * - The "invert" argument, which is XORed with each fetched word before + * searching it for one bits. + * - The optional "addr2", which is anded with "addr1" if present. */ -static unsigned long _find_next_bit(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= BITMAP_FIRST_WORD_MASK(start); @@ -47,7 +54,10 @@ static unsigned long _find_next_bit(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(tmp), nbits); @@ -61,7 +71,7 @@ static unsigned long _find_next_bit(const unsigned long *addr, unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit); #endif @@ -70,11 +80,21 @@ EXPORT_SYMBOL(find_next_bit); unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit); #endif +#if !defined(find_next_and_bit) +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr1, addr2, size, offset, 0UL); +} +EXPORT_SYMBOL(find_next_and_bit); +#endif + #ifndef find_first_bit /* * Find the first set bit in a memory region. @@ -146,15 +166,19 @@ static inline unsigned long ext2_swab(const unsigned long y) } #if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) -static unsigned long _find_next_bit_le(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit_le(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start)); @@ -165,7 +189,10 @@ static unsigned long _find_next_bit_le(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(ext2_swab(tmp)), nbits); @@ -176,7 +203,7 @@ static unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, size, offset, ~0UL); + return _find_next_bit_le(addr, NULL, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif @@ -185,7 +212,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le); unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, size, offset, 0UL); + return _find_next_bit_le(addr, NULL, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit_le); #endif diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 67b19233c28f..5985a25e6cbc 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -35,6 +35,7 @@ #define SPARSE 500 static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata; +static DECLARE_BITMAP(bitmap2, BITMAP_LEN) __initdata; /* * This is Schlemiel the Painter's algorithm. It should be called after @@ -103,6 +104,22 @@ static int __init test_find_last_bit(const void *bitmap, unsigned long len) return 0; } +static int __init test_find_next_and_bit(const void *bitmap, + const void *bitmap2, unsigned long len) +{ + unsigned long i, cnt; + cycles_t cycles; + + cycles = get_cycles(); + for (cnt = i = 0; i < BITMAP_LEN; cnt++) + i = find_next_and_bit(bitmap, bitmap2, BITMAP_LEN, i+1); + cycles = get_cycles() - cycles; + pr_err("find_next_and_bit:\t\t%llu cycles, %ld iterations\n", + (u64)cycles, cnt); + + return 0; +} + static int __init find_bit_test(void) { unsigned long nbits = BITMAP_LEN / SPARSE; @@ -110,23 +127,29 @@ static int __init find_bit_test(void) pr_err("\nStart testing find_bit() with random-filled bitmap\n"); get_random_bytes(bitmap, sizeof(bitmap)); + get_random_bytes(bitmap2, sizeof(bitmap2)); test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); bitmap_zero(bitmap, BITMAP_LEN); + bitmap_zero(bitmap2, BITMAP_LEN); - while (nbits--) + while (nbits--) { __set_bit(prandom_u32() % BITMAP_LEN, bitmap); + __set_bit(prandom_u32() % BITMAP_LEN, bitmap2); + } test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); /* * Everything is OK. Return error just to let user run benchmark diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h index 9311fadaaab2..16ed1982cb34 100644 --- a/tools/include/asm-generic/bitops/find.h +++ b/tools/include/asm-generic/bitops/find.h @@ -16,6 +16,22 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset); #endif +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +extern unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset); +#endif + #ifndef find_next_zero_bit /** diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 42c15f906aac..a88bd507091e 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -22,22 +22,29 @@ #include #include -#if !defined(find_next_bit) +#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ + !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit and - * find_next_zero_bit. The difference is the "invert" argument, which - * is XORed with each fetched word before searching it for one bits. + * This is a common helper function for find_next_bit, find_next_zero_bit, and + * find_next_and_bit. The differences are: + * - The "invert" argument, which is XORed with each fetched word before + * searching it for one bits. + * - The optional "addr2", which is anded with "addr1" if present. */ -static unsigned long _find_next_bit(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= BITMAP_FIRST_WORD_MASK(start); @@ -48,7 +55,10 @@ static unsigned long _find_next_bit(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(tmp), nbits); @@ -62,7 +72,7 @@ static unsigned long _find_next_bit(const unsigned long *addr, unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL); } #endif @@ -104,6 +114,15 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL); +} +#endif + +#ifndef find_next_and_bit +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr1, addr2, size, offset, 0UL); } #endif -- cgit v1.2.3 From 8c88181ed452707f3815827225517b1964463b95 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 8 Feb 2018 12:48:12 +0100 Subject: bpf: Sync kernel ABI header with tooling header for bpf_common.h I recently fixed up a lot of commits that forgot to keep the tooling headers in sync. And then I forgot to do the same thing in commit cb5f7334d479 ("bpf: add comments to BPF ld/ldx sizes"). Let correct that before people notice ;-). Lawrence did partly fix/sync this for bpf.h in commit d6d4f60c3a09 ("bpf: add selftest for tcpbpf"). Fixes: cb5f7334d479 ("bpf: add comments to BPF ld/ldx sizes") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf_common.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h index 18be90725ab0..ee97668bdadb 100644 --- a/tools/include/uapi/linux/bpf_common.h +++ b/tools/include/uapi/linux/bpf_common.h @@ -15,9 +15,10 @@ /* ld/ldx fields */ #define BPF_SIZE(code) ((code) & 0x18) -#define BPF_W 0x00 -#define BPF_H 0x08 -#define BPF_B 0x10 +#define BPF_W 0x00 /* 32-bit */ +#define BPF_H 0x08 /* 16-bit */ +#define BPF_B 0x10 /* 8-bit */ +/* eBPF BPF_DW 0x18 64-bit */ #define BPF_MODE(code) ((code) & 0xe0) #define BPF_IMM 0x00 #define BPF_ABS 0x20 -- cgit v1.2.3 From f091f1d6a2b4840c9b631d6138f5354401347863 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 13 Feb 2018 12:54:58 +0100 Subject: tools/headers: Synchronize kernel ABI headers, v4.16-rc1 Sync the following tooling headers with the latest kernel version: tools/arch/powerpc/include/uapi/asm/kvm.h tools/arch/x86/include/asm/cpufeatures.h tools/include/uapi/drm/i915_drm.h tools/include/uapi/linux/if_link.h tools/include/uapi/linux/kvm.h All the changes are new ABI additions which don't impact their use in existing tooling. Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Namhyung Kim Cc: Jiri Olsa Cc: Stephen Rothwell Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/arch/powerpc/include/uapi/asm/kvm.h | 2 + tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/include/uapi/drm/i915_drm.h | 77 ++++++++++++++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/kvm.h | 90 +++++++++++++++++++++++++++++++ 5 files changed, 171 insertions(+) (limited to 'tools/include') diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 637b7263cb86..833ed9a16adf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) #define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) +#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index ac3c6503ca27..536ee4febd74 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -86,6 +86,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; +/* + * Different engines serve different roles, and there may be more than one + * engine serving each role. enum drm_i915_gem_engine_class provides a + * classification of the role of the engine, which may be used when requesting + * operations to be performed on a certain subset of engines, or for providing + * information about that group. + */ +enum drm_i915_gem_engine_class { + I915_ENGINE_CLASS_RENDER = 0, + I915_ENGINE_CLASS_COPY = 1, + I915_ENGINE_CLASS_VIDEO = 2, + I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + + I915_ENGINE_CLASS_INVALID = -1 +}; + +/** + * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 + * + */ + +enum drm_i915_pmu_engine_sample { + I915_SAMPLE_BUSY = 0, + I915_SAMPLE_WAIT = 1, + I915_SAMPLE_SEMA = 2 +}; + +#define I915_PMU_SAMPLE_BITS (4) +#define I915_PMU_SAMPLE_MASK (0xf) +#define I915_PMU_SAMPLE_INSTANCE_BITS (8) +#define I915_PMU_CLASS_SHIFT \ + (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS) + +#define __I915_PMU_ENGINE(class, instance, sample) \ + ((class) << I915_PMU_CLASS_SHIFT | \ + (instance) << I915_PMU_SAMPLE_BITS | \ + (sample)) + +#define I915_PMU_ENGINE_BUSY(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY) + +#define I915_PMU_ENGINE_WAIT(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT) + +#define I915_PMU_ENGINE_SEMA(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) + +#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) + +#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) +#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) +#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) +#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) + +#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use @@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 +/* + * Query whether every context (both per-file default and user created) is + * isolated (insofar as HW supports). If this parameter is not true, then + * freshly created contexts may inherit values from an existing context, + * rather than default HW values. If true, it also ensures (insofar as HW + * supports) that all state set by this context will not leak to any other + * context. + * + * As not every engine across every gen support contexts, the returned + * value reports the support of context isolation for individual engines by + * returning a bitmask of each engine class set to true if that class supports + * isolation. + */ +#define I915_PARAM_HAS_CONTEXT_ISOLATION 50 + +/* Frequency of the command streamer timestamps given by the *_TIMESTAMP + * registers. This used to be fixed per platform but from CNL onwards, this + * might vary depending on the parts. + */ +#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 + typedef struct drm_i915_getparam { __s32 param; /* diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8616131e2c61..6d9447700e18 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -163,6 +163,7 @@ enum { IFLA_IF_NETNSID, IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, __IFLA_MAX }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8fb90a0819c3..0fb5ef939732 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_CMMA_MIGRATION */ #define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -- cgit v1.2.3