diff options
Diffstat (limited to 'tools')
66 files changed, 4452 insertions, 390 deletions
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index b3073ae84018..d16d289ade7a 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -136,7 +136,7 @@ endif BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool -BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o) +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o) $(OUTPUT)disasm.o OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 31ade77f5ef8..13b0aa789178 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -18,6 +18,7 @@ #include <sys/stat.h> #include <sys/mman.h> #include <bpf/btf.h> +#include <bpf/bpf_gen_internal.h> #include "json_writer.h" #include "main.h" @@ -106,8 +107,10 @@ static int codegen_datasec_def(struct bpf_object *obj, if (strcmp(sec_name, ".data") == 0) { sec_ident = "data"; + strip_mods = true; } else if (strcmp(sec_name, ".bss") == 0) { sec_ident = "bss"; + strip_mods = true; } else if (strcmp(sec_name, ".rodata") == 0) { sec_ident = "rodata"; strip_mods = true; @@ -129,6 +132,10 @@ static int codegen_datasec_def(struct bpf_object *obj, int need_off = sec_var->offset, align_off, align; __u32 var_type_id = var->type; + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + if (off > need_off) { p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", sec_name, i, need_off, off); @@ -268,6 +275,327 @@ static void codegen(const char *template, ...) free(s); } +static void print_hex(const char *data, int data_sz) +{ + int i, len; + + for (i = 0, len = 0; i < data_sz; i++) { + int w = data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)data[i]); + } +} + +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map); + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *tp_name; + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__%2$s__attach(struct %1$s *skel) \n\ + { \n\ + int prog_fd = skel->progs.%2$s.prog_fd; \n\ + ", obj_name, bpf_program__name(prog)); + + switch (bpf_program__get_type(prog)) { + case BPF_PROG_TYPE_RAW_TRACEPOINT: + tp_name = strchr(bpf_program__section_name(prog), '/') + 1; + printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + break; + case BPF_PROG_TYPE_TRACING: + printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n"); + break; + default: + printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); + break; + } + codegen("\ + \n\ + \n\ + if (fd > 0) \n\ + skel->links.%1$s_fd = fd; \n\ + return fd; \n\ + } \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *skel) \n\ + { \n\ + int ret = 0; \n\ + \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + ret = ret < 0 ? ret : %1$s__%2$s__attach(skel); \n\ + ", obj_name, bpf_program__name(prog)); + } + + codegen("\ + \n\ + return ret < 0 ? ret : 0; \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *skel) \n\ + { \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->links.%1$s_fd); \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + } \n\ + "); +} + +static void codegen_destroy(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + struct bpf_map *map; + + codegen("\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + %1$s__detach(skel); \n\ + ", + obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->progs.%1$s.prog_fd); \n\ + ", bpf_program__name(prog)); + } + + bpf_object__for_each_map(map, obj) { + const char * ident; + + ident = get_map_ident(map); + if (!ident) + continue; + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + printf("\tmunmap(skel->%1$s, %2$zd);\n", + ident, bpf_map_mmap_sz(map)); + codegen("\ + \n\ + skel_closenz(skel->maps.%1$s.map_fd); \n\ + ", ident); + } + codegen("\ + \n\ + free(skel); \n\ + } \n\ + ", + obj_name); +} + +static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) +{ + struct bpf_object_load_attr load_attr = {}; + DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); + struct bpf_map *map; + int err = 0; + + err = bpf_object__gen_loader(obj, &opts); + if (err) + return err; + + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; + + err = bpf_object__load_xattr(&load_attr); + if (err) { + p_err("failed to load object file"); + goto out; + } + /* If there was no error during load then gen_loader_opts + * are populated with the loader program. + */ + + /* finish generating 'struct skel' */ + codegen("\ + \n\ + }; \n\ + ", obj_name); + + + codegen_attach_detach(obj, obj_name); + + codegen_destroy(obj, obj_name); + + codegen("\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = calloc(sizeof(*skel), 1); \n\ + if (!skel) \n\ + goto cleanup; \n\ + skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ + ", + obj_name, opts.data_sz); + bpf_object__for_each_map(map, obj) { + const char *ident; + const void *mmap_data = NULL; + size_t mmap_size = 0; + + ident = get_map_ident(map); + if (!ident) + continue; + + if (!bpf_map__is_internal(map) || + !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + continue; + + codegen("\ + \n\ + skel->%1$s = \n\ + mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\ + MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\ + if (skel->%1$s == (void *) -1) \n\ + goto cleanup; \n\ + memcpy(skel->%1$s, (void *)\"\\ \n\ + ", ident, bpf_map_mmap_sz(map)); + mmap_data = bpf_map__initial_value(map, &mmap_size); + print_hex(mmap_data, mmap_size); + printf("\", %2$zd);\n" + "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n", + ident, mmap_size); + } + codegen("\ + \n\ + return skel; \n\ + cleanup: \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *skel) \n\ + { \n\ + struct bpf_load_and_run_opts opts = {}; \n\ + int err; \n\ + \n\ + opts.ctx = (struct bpf_loader_ctx *)skel; \n\ + opts.data_sz = %2$d; \n\ + opts.data = (void *)\"\\ \n\ + ", + obj_name, opts.data_sz); + print_hex(opts.data, opts.data_sz); + codegen("\ + \n\ + \"; \n\ + "); + + codegen("\ + \n\ + opts.insns_sz = %d; \n\ + opts.insns = (void *)\"\\ \n\ + ", + opts.insns_sz); + print_hex(opts.insns, opts.insns_sz); + codegen("\ + \n\ + \"; \n\ + err = bpf_load_and_run(&opts); \n\ + if (err < 0) \n\ + return err; \n\ + ", obj_name); + bpf_object__for_each_map(map, obj) { + const char *ident, *mmap_flags; + + ident = get_map_ident(map); + if (!ident) + continue; + + if (!bpf_map__is_internal(map) || + !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + continue; + if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) + mmap_flags = "PROT_READ"; + else + mmap_flags = "PROT_READ | PROT_WRITE"; + + printf("\tskel->%1$s =\n" + "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n" + "\t\t\tskel->maps.%1$s.map_fd, 0);\n", + ident, bpf_map_mmap_sz(map), mmap_flags); + } + codegen("\ + \n\ + return 0; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = %1$s__open(); \n\ + if (!skel) \n\ + return NULL; \n\ + if (%1$s__load(skel)) { \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + return skel; \n\ + } \n\ + ", obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + return err; +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; @@ -277,7 +605,7 @@ static int do_skeleton(int argc, char **argv) struct bpf_object *obj = NULL; const char *file, *ident; struct bpf_program *prog; - int fd, len, err = -1; + int fd, err = -1; struct bpf_map *map; struct btf *btf; struct stat st; @@ -359,7 +687,25 @@ static int do_skeleton(int argc, char **argv) } get_header_guard(header_guard, obj_name); - codegen("\ + if (use_loader) { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <stdlib.h> \n\ + #include <bpf/bpf.h> \n\ + #include <bpf/skel_internal.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_loader_ctx ctx; \n\ + ", + obj_name, header_guard + ); + } else { + codegen("\ \n\ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ \n\ @@ -375,7 +721,8 @@ static int do_skeleton(int argc, char **argv) struct bpf_object *obj; \n\ ", obj_name, header_guard - ); + ); + } if (map_cnt) { printf("\tstruct {\n"); @@ -383,7 +730,10 @@ static int do_skeleton(int argc, char **argv) ident = get_map_ident(map); if (!ident) continue; - printf("\t\tstruct bpf_map *%s;\n", ident); + if (use_loader) + printf("\t\tstruct bpf_map_desc %s;\n", ident); + else + printf("\t\tstruct bpf_map *%s;\n", ident); } printf("\t} maps;\n"); } @@ -391,14 +741,22 @@ static int do_skeleton(int argc, char **argv) if (prog_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_program *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tstruct bpf_prog_desc %s;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); } printf("\t} progs;\n"); printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_link *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tint %s_fd;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); } printf("\t} links;\n"); } @@ -409,6 +767,10 @@ static int do_skeleton(int argc, char **argv) if (err) goto out; } + if (use_loader) { + err = gen_trace(obj, obj_name, header_guard); + goto out; + } codegen("\ \n\ @@ -578,19 +940,7 @@ static int do_skeleton(int argc, char **argv) file_sz); /* embed contents of BPF object file */ - for (i = 0, len = 0; i < file_sz; i++) { - int w = obj_data[i] ? 4 : 2; - - len += w; - if (len > 78) { - printf("\\\n"); - len = w; - } - if (!obj_data[i]) - printf("\\0"); - else - printf("\\x%02x", (unsigned char)obj_data[i]); - } + print_hex(obj_data, file_sz); codegen("\ \n\ @@ -636,7 +986,7 @@ static int do_object(int argc, char **argv) while (argc) { file = GET_ARG(); - err = bpf_linker__add_file(linker, file); + err = bpf_linker__add_file(linker, file, NULL); if (err) { p_err("failed to link '%s': %s (%d)", file, strerror(err), err); goto out; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d9afb730136a..7f2817d97079 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -29,6 +29,7 @@ bool show_pinned; bool block_mount; bool verifier_logs; bool relaxed_maps; +bool use_loader; struct btf *base_btf; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; @@ -392,6 +393,7 @@ int main(int argc, char **argv) { "mapcompat", no_argument, NULL, 'm' }, { "nomount", no_argument, NULL, 'n' }, { "debug", no_argument, NULL, 'd' }, + { "use-loader", no_argument, NULL, 'L' }, { "base-btf", required_argument, NULL, 'B' }, { 0 } }; @@ -409,7 +411,7 @@ int main(int argc, char **argv) hash_init(link_table.table); opterr = 0; - while ((opt = getopt_long(argc, argv, "VhpjfmndB:", + while ((opt = getopt_long(argc, argv, "VhpjfLmndB:", options, NULL)) >= 0) { switch (opt) { case 'V': @@ -452,6 +454,9 @@ int main(int argc, char **argv) return -1; } break; + case 'L': + use_loader = true; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 76e91641262b..c1cf29798b99 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -90,6 +90,7 @@ extern bool show_pids; extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; +extern bool use_loader; extern struct btf *base_btf; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index da4846c9856a..cc48726740ad 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -16,6 +16,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/syscall.h> +#include <dirent.h> #include <linux/err.h> #include <linux/perf_event.h> @@ -24,6 +25,8 @@ #include <bpf/bpf.h> #include <bpf/btf.h> #include <bpf/libbpf.h> +#include <bpf/bpf_gen_internal.h> +#include <bpf/skel_internal.h> #include "cfg.h" #include "main.h" @@ -1499,7 +1502,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) set_max_rlimit(); obj = bpf_object__open_file(file, &open_opts); - if (IS_ERR_OR_NULL(obj)) { + if (libbpf_get_error(obj)) { p_err("failed to open object file"); goto err_free_reuse_maps; } @@ -1645,8 +1648,110 @@ err_free_reuse_maps: return -1; } +static int count_open_fds(void) +{ + DIR *dp = opendir("/proc/self/fd"); + struct dirent *de; + int cnt = -3; + + if (!dp) + return -1; + + while ((de = readdir(dp))) + cnt++; + + closedir(dp); + return cnt; +} + +static int try_loader(struct gen_loader_opts *gen) +{ + struct bpf_load_and_run_opts opts = {}; + struct bpf_loader_ctx *ctx; + int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc), + sizeof(struct bpf_prog_desc)); + int log_buf_sz = (1u << 24) - 1; + int err, fds_before, fd_delta; + char *log_buf; + + ctx = alloca(ctx_sz); + memset(ctx, 0, ctx_sz); + ctx->sz = ctx_sz; + ctx->log_level = 1; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + opts.ctx = ctx; + opts.data = gen->data; + opts.data_sz = gen->data_sz; + opts.insns = gen->insns; + opts.insns_sz = gen->insns_sz; + fds_before = count_open_fds(); + err = bpf_load_and_run(&opts); + fd_delta = count_open_fds() - fds_before; + if (err < 0) { + fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); + if (fd_delta) + fprintf(stderr, "loader prog leaked %d FDs\n", + fd_delta); + } + free(log_buf); + return err; +} + +static int do_loader(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); + DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); + struct bpf_object_load_attr load_attr = {}; + struct bpf_object *obj; + const char *file; + int err = 0; + + if (!REQ_ARGS(1)) + return -1; + file = GET_ARG(); + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(obj)) { + p_err("failed to open object file"); + goto err_close_obj; + } + + err = bpf_object__gen_loader(obj, &gen); + if (err) + goto err_close_obj; + + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; + + err = bpf_object__load_xattr(&load_attr); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (verifier_logs) { + struct dump_data dd = {}; + + kernel_syms_load(&dd); + dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false); + kernel_syms_destroy(&dd); + } + err = try_loader(&gen); +err_close_obj: + bpf_object__close(obj); + return err; +} + static int do_load(int argc, char **argv) { + if (use_loader) + return do_loader(argc, argv); return load_with_options(argc, argv, true); } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 6fc3e6f7f40c..f1f32e21d5cd 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -196,6 +196,9 @@ static const char *print_imm(void *private_data, else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[idx:%u]+%u", insn->imm, (insn + 1)->imm); else if (insn->src_reg == BPF_PSEUDO_FUNC) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "subprog[%+d]", insn->imm); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ec6d85a81744..418b9b813d65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -837,6 +837,7 @@ enum bpf_cmd { BPF_PROG_ATTACH, BPF_PROG_DETACH, BPF_PROG_TEST_RUN, + BPF_PROG_RUN = BPF_PROG_TEST_RUN, BPF_PROG_GET_NEXT_ID, BPF_MAP_GET_NEXT_ID, BPF_PROG_GET_FD_BY_ID, @@ -937,6 +938,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ }; enum bpf_attach_type { @@ -1097,8 +1099,8 @@ enum bpf_link_type { /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx * insn[1].imm: 0 * insn[0].off: 0 * insn[1].off: 0 @@ -1106,15 +1108,19 @@ enum bpf_link_type { * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -1314,6 +1320,8 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -4735,6 +4743,24 @@ union bpf_attr { * be zero-terminated except when **str_size** is 0. * * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + * + * long bpf_sys_close(u32 fd) + * Description + * Execute close syscall for given FD. + * Return + * A syscall result. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4903,6 +4929,9 @@ union bpf_attr { FN(check_mtu), \ FN(for_each_map_elem), \ FN(snprintf), \ + FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ + FN(sys_close), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 9b057cc7650a..430f6874fa41 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,3 +1,3 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \ - btf_dump.o ringbuf.o strset.o linker.o + btf_dump.o ringbuf.o strset.o linker.o gen_loader.o diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h new file mode 100644 index 000000000000..615400391e57 --- /dev/null +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __BPF_GEN_INTERNAL_H +#define __BPF_GEN_INTERNAL_H + +struct ksym_relo_desc { + const char *name; + int kind; + int insn_idx; +}; + +struct bpf_gen { + struct gen_loader_opts *opts; + void *data_start; + void *data_cur; + void *insn_start; + void *insn_cur; + ssize_t cleanup_label; + __u32 nr_progs; + __u32 nr_maps; + int log_level; + int error; + struct ksym_relo_desc *relos; + int relo_cnt; + char attach_target[128]; + int attach_kind; +}; + +void bpf_gen__init(struct bpf_gen *gen, int log_level); +int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__free(struct bpf_gen *gen); +void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); +void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx); +struct bpf_prog_load_params; +void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx); +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx); + +#endif diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c new file mode 100644 index 000000000000..8df718a6b142 --- /dev/null +++ b/tools/lib/bpf/gen_loader.c @@ -0,0 +1,729 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/filter.h> +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "hashmap.h" +#include "bpf_gen_internal.h" +#include "skel_internal.h" + +#define MAX_USED_MAPS 64 +#define MAX_USED_PROGS 32 + +/* The following structure describes the stack layout of the loader program. + * In addition R6 contains the pointer to context. + * R7 contains the result of the last sys_bpf command (typically error or FD). + * R9 contains the result of the last sys_close command. + * + * Naming convention: + * ctx - bpf program context + * stack - bpf program stack + * blob - bpf_attr-s, strings, insns, map data. + * All the bytes that loader prog will use for read/write. + */ +struct loader_stack { + __u32 btf_fd; + __u32 map_fd[MAX_USED_MAPS]; + __u32 prog_fd[MAX_USED_PROGS]; + __u32 inner_map_fd; +}; + +#define stack_off(field) \ + (__s16)(-sizeof(struct loader_stack) + offsetof(struct loader_stack, field)) + +#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) + +static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->insn_cur - gen->insn_start; + void *insn_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + insn_start = realloc(gen->insn_start, off + size); + if (!insn_start) { + gen->error = -ENOMEM; + free(gen->insn_start); + gen->insn_start = NULL; + return -ENOMEM; + } + gen->insn_start = insn_start; + gen->insn_cur = insn_start + off; + return 0; +} + +static int realloc_data_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->data_cur - gen->data_start; + void *data_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + data_start = realloc(gen->data_start, off + size); + if (!data_start) { + gen->error = -ENOMEM; + free(gen->data_start); + gen->data_start = NULL; + return -ENOMEM; + } + gen->data_start = data_start; + gen->data_cur = data_start + off; + return 0; +} + +static void emit(struct bpf_gen *gen, struct bpf_insn insn) +{ + if (realloc_insn_buf(gen, sizeof(insn))) + return; + memcpy(gen->insn_cur, &insn, sizeof(insn)); + gen->insn_cur += sizeof(insn); +} + +static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn insn2) +{ + emit(gen, insn1); + emit(gen, insn2); +} + +void bpf_gen__init(struct bpf_gen *gen, int log_level) +{ + size_t stack_sz = sizeof(struct loader_stack); + int i; + + gen->log_level = log_level; + /* save ctx pointer into R6 */ + emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); + + /* bzero stack */ + emit(gen, BPF_MOV64_REG(BPF_REG_1, BPF_REG_10)); + emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + + /* jump over cleanup code */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, + /* size of cleanup code below */ + (stack_sz / 4) * 3 + 2)); + + /* remember the label where all error branches will jump to */ + gen->cleanup_label = gen->insn_cur - gen->insn_start; + /* emit cleanup code: close all temp FDs */ + for (i = 0; i < stack_sz; i += 4) { + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + } + /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ + emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + emit(gen, BPF_EXIT_INSN()); +} + +static int add_data(struct bpf_gen *gen, const void *data, __u32 size) +{ + void *prev; + + if (realloc_data_buf(gen, size)) + return 0; + prev = gen->data_cur; + memcpy(gen->data_cur, data, size); + gen->data_cur += size; + return prev - gen->data_start; +} + +static int insn_bytes_to_bpf_size(__u32 sz) +{ + switch (sz) { + case 8: return BPF_DW; + case 4: return BPF_W; + case 2: return BPF_H; + case 1: return BPF_B; + default: return -1; + } +} + +/* *(u64 *)(blob + off) = (u64)(void *)(blob + data) */ +static void emit_rel_store(struct bpf_gen *gen, int off, int data) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, data)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); +} + +/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */ +static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off) +{ + emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10)); + emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off, + bool check_non_zero) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_6, ctx_off)); + if (check_non_zero) + /* If value in ctx is zero don't update the blob. + * For example: when ctx->map.max_entries == 0, keep default max_entries from bpf.c + */ + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2blob(struct bpf_gen *gen, int off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2ctx(struct bpf_gen *gen, int ctx_off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off)); +} + +static void emit_sys_bpf(struct bpf_gen *gen, int cmd, int attr, int attr_size) +{ + emit(gen, BPF_MOV64_IMM(BPF_REG_1, cmd)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, attr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, attr_size)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_bpf)); + /* remember the result in R7 */ + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); +} + +static bool is_simm16(__s64 value) +{ + return value == (__s64)(__s16)value; +} + +static void emit_check_err(struct bpf_gen *gen) +{ + __s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + + /* R7 contains result of last sys_bpf command. + * if (R7 < 0) goto cleanup; + */ + if (is_simm16(off)) { + emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, off)); + } else { + gen->error = -ERANGE; + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); + } +} + +/* reg1 and reg2 should not be R1 - R5. They can be R0, R6 - R10 */ +static void emit_debug(struct bpf_gen *gen, int reg1, int reg2, + const char *fmt, va_list args) +{ + char buf[1024]; + int addr, len, ret; + + if (!gen->log_level) + return; + ret = vsnprintf(buf, sizeof(buf), fmt, args); + if (ret < 1024 - 7 && reg1 >= 0 && reg2 < 0) + /* The special case to accommodate common debug_ret(): + * to avoid specifying BPF_REG_7 and adding " r=%%d" to + * prints explicitly. + */ + strcat(buf, " r=%d"); + len = strlen(buf) + 1; + addr = add_data(gen, buf, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, addr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + if (reg1 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_3, reg1)); + if (reg2 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_4, reg2)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_trace_printk)); +} + +static void debug_regs(struct bpf_gen *gen, int reg1, int reg2, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, reg1, reg2, fmt, args); + va_end(args); +} + +static void debug_ret(struct bpf_gen *gen, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, BPF_REG_7, -1, fmt, args); + va_end(args); +} + +static void __emit_sys_close(struct bpf_gen *gen) +{ + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, + /* 2 is the number of the following insns + * * 6 is additional insns in debug_regs + */ + 2 + (gen->log_level ? 6 : 0))); + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + debug_regs(gen, BPF_REG_9, BPF_REG_0, "close(%%d) = %%d"); +} + +static void emit_sys_close_stack(struct bpf_gen *gen, int stack_off) +{ + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, stack_off)); + __emit_sys_close(gen); +} + +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0)); + __emit_sys_close(gen); +} + +int bpf_gen__finish(struct bpf_gen *gen) +{ + int i; + + emit_sys_close_stack(gen, stack_off(btf_fd)); + for (i = 0; i < gen->nr_progs; i++) + move_stack2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * gen->nr_maps + + sizeof(struct bpf_prog_desc) * i + + offsetof(struct bpf_prog_desc, prog_fd), 4, + stack_off(prog_fd[i])); + for (i = 0; i < gen->nr_maps; i++) + move_stack2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * i + + offsetof(struct bpf_map_desc, map_fd), 4, + stack_off(map_fd[i])); + emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); + emit(gen, BPF_EXIT_INSN()); + pr_debug("gen: finish %d\n", gen->error); + if (!gen->error) { + struct gen_loader_opts *opts = gen->opts; + + opts->insns = gen->insn_start; + opts->insns_sz = gen->insn_cur - gen->insn_start; + opts->data = gen->data_start; + opts->data_sz = gen->data_cur - gen->data_start; + } + return gen->error; +} + +void bpf_gen__free(struct bpf_gen *gen) +{ + if (!gen) + return; + free(gen->data_start); + free(gen->insn_start); + free(gen); +} + +void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, + __u32 btf_raw_size) +{ + int attr_size = offsetofend(union bpf_attr, btf_log_level); + int btf_data, btf_load_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: load_btf: size %d\n", btf_raw_size); + btf_data = add_data(gen, btf_raw_data, btf_raw_size); + + attr.btf_size = btf_raw_size; + btf_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with a pointer to the BTF data */ + emit_rel_store(gen, attr_field(btf_load_attr, btf), btf_data); + /* emit BTF_LOAD command */ + emit_sys_bpf(gen, BPF_BTF_LOAD, btf_load_attr, attr_size); + debug_ret(gen, "btf_load size %d", btf_raw_size); + emit_check_err(gen); + /* remember btf_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, stack_off(btf_fd))); +} + +void bpf_gen__map_create(struct bpf_gen *gen, + struct bpf_create_map_attr *map_attr, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); + bool close_inner_map_fd = false; + int map_create_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + attr.map_type = map_attr->map_type; + attr.key_size = map_attr->key_size; + attr.value_size = map_attr->value_size; + attr.map_flags = map_attr->map_flags; + memcpy(attr.map_name, map_attr->name, + min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = map_attr->numa_node; + attr.map_ifindex = map_attr->map_ifindex; + attr.max_entries = map_attr->max_entries; + switch (attr.map_type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + break; + default: + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; + } + + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", + attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id); + + map_create_attr = add_data(gen, &attr, attr_size); + if (attr.btf_value_type_id) + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, + stack_off(btf_fd)); + switch (attr.map_type) { + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, + stack_off(inner_map_fd)); + close_inner_map_fd = true; + break; + default: + break; + } + /* conditionally update max_entries */ + if (map_idx >= 0) + move_ctx2blob(gen, attr_field(map_create_attr, max_entries), 4, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, max_entries), + true /* check that max_entries != 0 */); + /* emit MAP_CREATE command */ + emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); + debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", + attr.map_name, map_idx, map_attr->map_type, attr.value_size, + attr.btf_value_type_id); + emit_check_err(gen); + /* remember map_fd in the stack, if successful */ + if (map_idx < 0) { + /* This bpf_gen__map_create() function is called with map_idx >= 0 + * for all maps that libbpf loading logic tracks. + * It's called with -1 to create an inner map. + */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(inner_map_fd))); + } else if (map_idx != gen->nr_maps) { + gen->error = -EDOM; /* internal bug */ + return; + } else { + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(map_fd[map_idx]))); + gen->nr_maps++; + } + if (close_inner_map_fd) + emit_sys_close_stack(gen, stack_off(inner_map_fd)); +} + +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, + enum bpf_attach_type type) +{ + const char *prefix; + int kind, ret; + + btf_get_kernel_prefix_kind(type, &prefix, &kind); + gen->attach_kind = kind; + ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s", + prefix, attach_name); + if (ret == sizeof(gen->attach_target)) + gen->error = -ENOSPC; +} + +static void emit_find_attach_target(struct bpf_gen *gen) +{ + int name, len = strlen(gen->attach_target) + 1; + + pr_debug("gen: find_attach_tgt %s %d\n", gen->attach_target, gen->attach_kind); + name = add_data(gen, gen->attach_target, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, gen->attach_kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", + gen->attach_target, gen->attach_kind); + emit_check_err(gen); + /* if successful, btf_id is in lower 32-bit of R7 and + * btf_obj_fd is in upper 32-bit + */ +} + +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, + int insn_idx) +{ + struct ksym_relo_desc *relo; + + relo = libbpf_reallocarray(gen->relos, gen->relo_cnt + 1, sizeof(*relo)); + if (!relo) { + gen->error = -ENOMEM; + return; + } + gen->relos = relo; + relo += gen->relo_cnt; + relo->name = name; + relo->kind = kind; + relo->insn_idx = insn_idx; + gen->relo_cnt++; +} + +static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) +{ + int name, insn, len = strlen(relo->name) + 1; + + pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx); + name = add_data(gen, relo->name, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind); + emit_check_err(gen); + /* store btf_id into insn[insn_idx].imm */ + insn = insns + sizeof(struct bpf_insn) * relo->insn_idx + + offsetof(struct bpf_insn, imm); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, insn)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0)); + if (relo->kind == BTF_KIND_VAR) { + /* store btf_obj_fd into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + sizeof(struct bpf_insn))); + } +} + +static void emit_relos(struct bpf_gen *gen, int insns) +{ + int i; + + for (i = 0; i < gen->relo_cnt; i++) + emit_relo(gen, gen->relos + i, insns); +} + +static void cleanup_relos(struct bpf_gen *gen, int insns) +{ + int i, insn; + + for (i = 0; i < gen->relo_cnt; i++) { + if (gen->relos[i].kind != BTF_KIND_VAR) + continue; + /* close fd recorded in insn[insn_idx + 1].imm */ + insn = insns + + sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) + + offsetof(struct bpf_insn, imm); + emit_sys_close_blob(gen, insn); + } + if (gen->relo_cnt) { + free(gen->relos); + gen->relo_cnt = 0; + gen->relos = NULL; + } +} + +void bpf_gen__prog_load(struct bpf_gen *gen, + struct bpf_prog_load_params *load_attr, int prog_idx) +{ + int attr_size = offsetofend(union bpf_attr, fd_array); + int prog_load_attr, license, insns, func_info, line_info; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: prog_load: type %d insns_cnt %zd\n", + load_attr->prog_type, load_attr->insn_cnt); + /* add license string to blob of bytes */ + license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1); + /* add insns to blob of bytes */ + insns = add_data(gen, load_attr->insns, + load_attr->insn_cnt * sizeof(struct bpf_insn)); + + attr.prog_type = load_attr->prog_type; + attr.expected_attach_type = load_attr->expected_attach_type; + attr.attach_btf_id = load_attr->attach_btf_id; + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = 0; + attr.insn_cnt = (__u32)load_attr->insn_cnt; + attr.prog_flags = load_attr->prog_flags; + + attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_cnt = load_attr->func_info_cnt; + func_info = add_data(gen, load_attr->func_info, + attr.func_info_cnt * attr.func_info_rec_size); + + attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_cnt = load_attr->line_info_cnt; + line_info = add_data(gen, load_attr->line_info, + attr.line_info_cnt * attr.line_info_rec_size); + + memcpy(attr.prog_name, load_attr->name, + min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + prog_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with a pointer to license */ + emit_rel_store(gen, attr_field(prog_load_attr, license), license); + + /* populate union bpf_attr with a pointer to instructions */ + emit_rel_store(gen, attr_field(prog_load_attr, insns), insns); + + /* populate union bpf_attr with a pointer to func_info */ + emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info); + + /* populate union bpf_attr with a pointer to line_info */ + emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); + + /* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */ + emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array), + stack_off(map_fd[0])); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(prog_load_attr, prog_btf_fd), 4, + stack_off(btf_fd)); + if (gen->attach_kind) { + emit_find_attach_target(gen); + /* populate union bpf_attr with btf_id and btf_obj_fd found by helper */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, prog_load_attr)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_id))); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_obj_fd))); + } + emit_relos(gen, insns); + /* emit PROG_LOAD command */ + emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size); + debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); + /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ + cleanup_relos(gen, insns); + if (gen->attach_kind) + emit_sys_close_blob(gen, + attr_field(prog_load_attr, attach_btf_obj_fd)); + emit_check_err(gen); + /* remember prog_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(prog_fd[gen->nr_progs]))); + gen->nr_progs++; +} + +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, + __u32 value_size) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, value, key; + union bpf_attr attr; + int zero = 0; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_update_elem: idx %d\n", map_idx); + + value = add_data(gen, pvalue, value_size); + key = add_data(gen, &zero, sizeof(zero)); + + /* if (map_desc[map_idx].initial_value) + * copy_from_user(value, initial_value, value_size); + */ + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, initial_value))); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, value)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4, + stack_off(map_fd[map_idx])); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), value); + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "update_elem idx %d value_size %d", map_idx, value_size); + emit_check_err(gen); +} + +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, map_fd); + int map_freeze_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_freeze: idx %d\n", map_idx); + map_freeze_attr = add_data(gen, &attr, attr_size); + move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4, + stack_off(map_fd[map_idx])); + /* emit MAP_FREEZE command */ + emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size); + debug_ret(gen, "map_freeze"); + emit_check_err(gen); +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c41d9b2b59ac..69cd1a835ebd 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -54,6 +54,7 @@ #include "str_error.h" #include "libbpf_internal.h" #include "hashmap.h" +#include "bpf_gen_internal.h" #ifndef BPF_FS_MAGIC #define BPF_FS_MAGIC 0xcafe4a11 @@ -178,7 +179,7 @@ enum kern_feature_id { __FEAT_CNT, }; -static bool kernel_supports(enum kern_feature_id feat_id); +static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); enum reloc_type { RELO_LD64, @@ -432,6 +433,8 @@ struct bpf_object { bool loaded; bool has_subcalls; + struct bpf_gen *gen_loader; + /* * Information when doing elf related work. Only valid if fd * is valid. @@ -677,6 +680,11 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return -LIBBPF_ERRNO__FORMAT; } + if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name); + return -ENOTSUP; + } + pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n", sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz); @@ -700,13 +708,14 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, if (err) return err; - /* if function is a global/weak symbol, but has hidden - * visibility (STV_HIDDEN), mark its BTF FUNC as static to - * enable more permissive BPF verification mode with more - * outside context available to BPF verifier + /* if function is a global/weak symbol, but has restricted + * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC + * as static to enable more permissive BPF verification mode + * with more outside context available to BPF verifier */ if (GELF_ST_BIND(sym.st_info) != STB_LOCAL - && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN) + && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN + || GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL)) prog->mark_btf_static = true; nr_progs++; @@ -1794,7 +1803,6 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (!symbols) return -EINVAL; - scn = elf_sec_by_idx(obj, obj->efile.maps_shndx); data = elf_sec_data(obj, scn); if (!scn || !data) { @@ -1854,6 +1862,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION + || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); + return -ENOTSUP; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; map->sec_idx = sym.st_shndx; map->sec_offset = sym.st_value; @@ -2261,6 +2275,16 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def pr_debug("map '%s': found inner map definition.\n", map->name); } +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: return "global"; + case BTF_VAR_GLOBAL_EXTERN: return "extern"; + default: return "unknown"; + } +} + static int bpf_object__init_user_btf_map(struct bpf_object *obj, const struct btf_type *sec, int var_idx, int sec_idx, @@ -2293,10 +2317,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, btf_kind_str(var)); return -EINVAL; } - if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && - var_extra->linkage != BTF_VAR_STATIC) { - pr_warn("map '%s': unsupported var linkage %u.\n", - map_name, var_extra->linkage); + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED) { + pr_warn("map '%s': unsupported map linkage %s.\n", + map_name, btf_var_linkage_str(var_extra->linkage)); return -EOPNOTSUPP; } @@ -2443,20 +2466,20 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) static bool btf_needs_sanitization(struct bpf_object *obj) { - bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); - bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); - bool has_float = kernel_supports(FEAT_BTF_FLOAT); - bool has_func = kernel_supports(FEAT_BTF_FUNC); + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); return !has_func || !has_datasec || !has_func_global || !has_float; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { - bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); - bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); - bool has_float = kernel_supports(FEAT_BTF_FLOAT); - bool has_func = kernel_supports(FEAT_BTF_FUNC); + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); struct btf_type *t; int i, j, vlen; @@ -2637,7 +2660,7 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force) int err; /* btf_vmlinux could be loaded earlier */ - if (obj->btf_vmlinux) + if (obj->btf_vmlinux || obj->gen_loader) return 0; if (!force && !obj_needs_vmlinux_btf(obj)) @@ -2662,7 +2685,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (!obj->btf) return 0; - if (!kernel_supports(FEAT_BTF)) { + if (!kernel_supports(obj, FEAT_BTF)) { if (kernel_needs_btf(obj)) { err = -EOPNOTSUPP; goto report; @@ -2719,7 +2742,20 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) bpf_object__sanitize_btf(obj, kern_btf); } - err = btf__load(kern_btf); + if (obj->gen_loader) { + __u32 raw_size = 0; + const void *raw_data = btf__get_raw_data(kern_btf, &raw_size); + + if (!raw_data) + return -ENOMEM; + bpf_gen__load_btf(obj->gen_loader, raw_data, raw_size); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + btf__set_fd(kern_btf, 0); + } else { + err = btf__load(kern_btf); + } if (sanitize) { if (!err) { /* move fd to libbpf's BTF */ @@ -4293,11 +4329,17 @@ static struct kern_feature_desc { }, }; -static bool kernel_supports(enum kern_feature_id feat_id) +static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; int ret; + if (obj->gen_loader) + /* To generate loader program assume the latest kernel + * to avoid doing extra prog_load, map_create syscalls. + */ + return true; + if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { ret = feat->probe(); if (ret > 0) { @@ -4380,6 +4422,13 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; + if (obj->gen_loader) { + bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, + map->mmaped, map->def.value_size); + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) + bpf_gen__map_freeze(obj->gen_loader, map - obj->maps); + return 0; + } err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); if (err) { err = -errno; @@ -4405,14 +4454,14 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) static void bpf_map__destroy(struct bpf_map *map); -static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) +static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { struct bpf_create_map_attr create_attr; struct bpf_map_def *def = &map->def; memset(&create_attr, 0, sizeof(create_attr)); - if (kernel_supports(FEAT_PROG_NAME)) + if (kernel_supports(obj, FEAT_PROG_NAME)) create_attr.name = map->name; create_attr.map_ifindex = map->map_ifindex; create_attr.map_type = def->type; @@ -4453,7 +4502,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) if (map->inner_map) { int err; - err = bpf_object__create_map(obj, map->inner_map); + err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", map->name, err); @@ -4465,7 +4514,15 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) create_attr.inner_map_fd = map->inner_map_fd; } - map->fd = bpf_create_map_xattr(&create_attr); + if (obj->gen_loader) { + bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + map->fd = 0; + } else { + map->fd = bpf_create_map_xattr(&create_attr); + } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { char *cp, errmsg[STRERR_BUFSIZE]; @@ -4486,6 +4543,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) return -errno; if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { + if (obj->gen_loader) + map->inner_map->fd = -1; bpf_map__destroy(map->inner_map); zfree(&map->inner_map); } @@ -4493,11 +4552,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) return 0; } -static int init_map_slots(struct bpf_map *map) +static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) { const struct bpf_map *targ_map; unsigned int i; - int fd, err; + int fd, err = 0; for (i = 0; i < map->init_slots_sz; i++) { if (!map->init_slots[i]) @@ -4505,7 +4564,13 @@ static int init_map_slots(struct bpf_map *map) targ_map = map->init_slots[i]; fd = bpf_map__fd(targ_map); - err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (obj->gen_loader) { + pr_warn("// TODO map_update_elem: idx %ld key %d value==map_idx %ld\n", + map - obj->maps, i, targ_map - obj->maps); + return -ENOTSUP; + } else { + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + } if (err) { err = -errno; pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", @@ -4547,7 +4612,7 @@ bpf_object__create_maps(struct bpf_object *obj) pr_debug("map '%s': skipping creation (preset fd=%d)\n", map->name, map->fd); } else { - err = bpf_object__create_map(obj, map); + err = bpf_object__create_map(obj, map, false); if (err) goto err_out; @@ -4563,7 +4628,7 @@ bpf_object__create_maps(struct bpf_object *obj) } if (map->init_slots_sz) { - err = init_map_slots(map); + err = init_map_slots(obj, map); if (err < 0) { zclose(map->fd); goto err_out; @@ -4973,11 +5038,14 @@ static int load_module_btfs(struct bpf_object *obj) if (obj->btf_modules_loaded) return 0; + if (obj->gen_loader) + return 0; + /* don't do this again, even if we find no module BTFs */ obj->btf_modules_loaded = true; /* kernel too old to support module BTFs */ - if (!kernel_supports(FEAT_MODULE_BTF)) + if (!kernel_supports(obj, FEAT_MODULE_BTF)) return 0; while (true) { @@ -6120,6 +6188,12 @@ static int bpf_core_apply_relo(struct bpf_program *prog, if (str_is_empty(spec_str)) return -EINVAL; + if (prog->obj->gen_loader) { + pr_warn("// TODO core_relo: prog %ld insn[%d] %s %s kind %d\n", + prog - prog->obj->programs, relo->insn_off / 8, + local_name, spec_str, relo->kind); + return -ENOTSUP; + } err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); if (err) { pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", @@ -6371,19 +6445,34 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) switch (relo->type) { case RELO_LD64: - insn[0].src_reg = BPF_PSEUDO_MAP_FD; - insn[0].imm = obj->maps[relo->map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX; + insn[0].imm = relo->map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = obj->maps[relo->map_idx].fd; + } break; case RELO_DATA: - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[1].imm = insn[0].imm + relo->sym_off; - insn[0].imm = obj->maps[relo->map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = relo->map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[relo->map_idx].fd; + } break; case RELO_EXTERN_VAR: ext = &obj->externs[relo->sym_off]; if (ext->type == EXT_KCFG) { - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = obj->kconfig_map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + } insn[1].imm = ext->kcfg.data_off; } else /* EXT_KSYM */ { if (ext->ksym.type_id) { /* typed ksyms */ @@ -6402,11 +6491,15 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[0].imm = ext->ksym.kernel_btf_id; break; case RELO_SUBPROG_ADDR: - insn[0].src_reg = BPF_PSEUDO_FUNC; - /* will be handled as a follow up pass */ + if (insn[0].src_reg != BPF_PSEUDO_FUNC) { + pr_warn("prog '%s': relo #%d: bad insn\n", + prog->name, i); + return -EINVAL; + } + /* handled already */ break; case RELO_CALL: - /* will be handled as a follow up pass */ + /* handled already */ break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", @@ -6497,7 +6590,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj, /* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't * supprot func/line info */ - if (!obj->btf_ext || !kernel_supports(FEAT_BTF_FUNC)) + if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC)) return 0; /* only attempt func info relocation if main program's func_info @@ -6575,6 +6668,30 @@ static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, si sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); } +static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + int new_cnt = main_prog->nr_reloc + subprog->nr_reloc; + struct reloc_desc *relos; + int i; + + if (main_prog == subprog) + return 0; + relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); + if (!relos) + return -ENOMEM; + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); + + for (i = main_prog->nr_reloc; i < new_cnt; i++) + relos[i].insn_idx += subprog->sub_insn_off; + /* After insn_idx adjustment the 'relos' array is still sorted + * by insn_idx and doesn't break bsearch. + */ + main_prog->reloc_desc = relos; + main_prog->nr_reloc = new_cnt; + return 0; +} + static int bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *prog) @@ -6595,6 +6712,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, continue; relo = find_prog_insn_relo(prog, insn_idx); + if (relo && relo->type == RELO_EXTERN_FUNC) + /* kfunc relocations will be handled later + * in bpf_object__relocate_data() + */ + continue; if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) { pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n", prog->name, insn_idx, relo->type); @@ -6669,6 +6791,10 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", main_prog->name, subprog->insns_cnt, subprog->name); + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; err = bpf_object__reloc_code(obj, main_prog, subprog); if (err) return err; @@ -6798,11 +6924,25 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) return 0; } +static void +bpf_object__free_relocs(struct bpf_object *obj) +{ + struct bpf_program *prog; + int i; + + /* free up relocation descriptors */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + zfree(&prog->reloc_desc); + prog->nr_reloc = 0; + } +} + static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; - size_t i; + size_t i, j; int err; if (obj->btf_ext) { @@ -6813,23 +6953,32 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } - /* relocate data references first for all programs and sub-programs, - * as they don't change relative to code locations, so subsequent - * subprogram processing won't need to re-calculate any of them + + /* Before relocating calls pre-process relocations and mark + * few ld_imm64 instructions that points to subprogs. + * Otherwise bpf_object__reloc_code() later would have to consider + * all ld_imm64 insns as relocation candidates. That would + * reduce relocation speed, since amount of find_prog_insn_relo() + * would increase and most of them will fail to find a relo. */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_object__relocate_data(obj, prog); - if (err) { - pr_warn("prog '%s': failed to relocate data references: %d\n", - prog->name, err); - return err; + for (j = 0; j < prog->nr_reloc; j++) { + struct reloc_desc *relo = &prog->reloc_desc[j]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + + /* mark the insn, so it's recognized by insn_is_pseudo_func() */ + if (relo->type == RELO_SUBPROG_ADDR) + insn[0].src_reg = BPF_PSEUDO_FUNC; } } - /* now relocate subprogram calls and append used subprograms to main + + /* relocate subprogram calls and append used subprograms to main * programs; each copy of subprogram code needs to be relocated * differently for each main program, because its code location might - * have changed + * have changed. + * Append subprog relos to main programs to allow data relos to be + * processed after text is completely relocated. */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; @@ -6846,12 +6995,20 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } - /* free up relocation descriptors */ + /* Process data relos for main programs */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - zfree(&prog->reloc_desc); - prog->nr_reloc = 0; + if (prog_is_subprog(obj, prog)) + continue; + err = bpf_object__relocate_data(obj, prog); + if (err) { + pr_warn("prog '%s': failed to relocate data references: %d\n", + prog->name, err); + return err; + } } + if (!obj->gen_loader) + bpf_object__free_relocs(obj); return 0; } @@ -7040,6 +7197,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program enum bpf_func_id func_id; int i; + if (obj->gen_loader) + return 0; + for (i = 0; i < prog->insns_cnt; i++, insn++) { if (!insn_is_helper_call(insn, &func_id)) continue; @@ -7051,12 +7211,12 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program switch (func_id) { case BPF_FUNC_probe_read_kernel: case BPF_FUNC_probe_read_user: - if (!kernel_supports(FEAT_PROBE_READ_KERN)) + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) insn->imm = BPF_FUNC_probe_read; break; case BPF_FUNC_probe_read_kernel_str: case BPF_FUNC_probe_read_user_str: - if (!kernel_supports(FEAT_PROBE_READ_KERN)) + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) insn->imm = BPF_FUNC_probe_read_str; break; default: @@ -7091,12 +7251,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.prog_type = prog->type; /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def && + if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && prog->sec_def->is_exp_attach_type_optional) load_attr.expected_attach_type = 0; else load_attr.expected_attach_type = prog->expected_attach_type; - if (kernel_supports(FEAT_PROG_NAME)) + if (kernel_supports(prog->obj, FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insn_cnt = insns_cnt; @@ -7112,7 +7272,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(prog->obj); - if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) { + if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) { load_attr.prog_btf_fd = btf_fd; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; @@ -7124,6 +7284,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; + if (prog->obj->gen_loader) { + bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, + prog - prog->obj->programs); + *pfd = -1; + return 0; + } retry_load: if (log_buf_size) { log_buf = malloc(log_buf_size); @@ -7142,7 +7308,7 @@ retry_load: pr_debug("verifier log:\n%s", log_buf); if (prog->obj->rodata_map_idx >= 0 && - kernel_supports(FEAT_PROG_BIND_MAP)) { + kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) { struct bpf_map *rodata_map = &prog->obj->maps[prog->obj->rodata_map_idx]; @@ -7201,6 +7367,38 @@ out: return ret; } +static int bpf_program__record_externs(struct bpf_program *prog) +{ + struct bpf_object *obj = prog->obj; + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + struct reloc_desc *relo = &prog->reloc_desc[i]; + struct extern_desc *ext = &obj->externs[relo->sym_off]; + + switch (relo->type) { + case RELO_EXTERN_VAR: + if (ext->type != EXT_KSYM) + continue; + if (!ext->ksym.type_id) { + pr_warn("typeless ksym %s is not supported yet\n", + ext->name); + return -ENOTSUP; + } + bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR, + relo->insn_idx); + break; + case RELO_EXTERN_FUNC: + bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC, + relo->insn_idx); + break; + default: + continue; + } + } + return 0; +} + static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) @@ -7246,6 +7444,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) pr_warn("prog '%s': inconsistent nr(%d) != 1\n", prog->name, prog->instances.nr); } + if (prog->obj->gen_loader) + bpf_program__record_externs(prog); err = load_program(prog, prog->insns, prog->insns_cnt, license, kern_ver, &fd); if (!err) @@ -7322,6 +7522,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) if (err) return err; } + if (obj->gen_loader) + bpf_object__free_relocs(obj); return 0; } @@ -7500,11 +7702,11 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!kernel_supports(FEAT_GLOBAL_DATA)) { + if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) { pr_warn("kernel doesn't support global data\n"); return -ENOTSUP; } - if (!kernel_supports(FEAT_ARRAY_MMAP)) + if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -7702,6 +7904,12 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj) if (ext->type != EXT_KSYM || !ext->ksym.type_id) continue; + if (obj->gen_loader) { + ext->is_set = true; + ext->ksym.kernel_btf_obj_fd = 0; + ext->ksym.kernel_btf_id = 0; + continue; + } t = btf__type_by_id(obj->btf, ext->btf_id); if (btf_is_var(t)) err = bpf_object__resolve_ksym_var_btf_id(obj, ext); @@ -7816,6 +8024,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) return -EINVAL; } + if (obj->gen_loader) + bpf_gen__init(obj->gen_loader, attr->log_level); + err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); @@ -7826,6 +8037,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__relocate(obj, attr->target_btf_path); err = err ? : bpf_object__load_progs(obj, attr->log_level); + if (obj->gen_loader) { + /* reset FDs */ + btf__set_fd(obj->btf, -1); + for (i = 0; i < obj->nr_maps; i++) + obj->maps[i].fd = -1; + if (!err) + err = bpf_gen__finish(obj->gen_loader); + } + /* clean up module BTFs */ for (i = 0; i < obj->btf_module_cnt; i++) { close(obj->btf_modules[i].fd); @@ -8451,6 +8671,7 @@ void bpf_object__close(struct bpf_object *obj) if (obj->clear_priv) obj->clear_priv(obj, obj->priv); + bpf_gen__free(obj->gen_loader); bpf_object__elf_finish(obj); bpf_object__unload(obj); btf__free(obj->btf); @@ -8541,6 +8762,22 @@ void *bpf_object__priv(const struct bpf_object *obj) return obj ? obj->priv : ERR_PTR(-EINVAL); } +int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) +{ + struct bpf_gen *gen; + + if (!opts) + return -EFAULT; + if (!OPTS_VALID(opts, gen_loader_opts)) + return -EINVAL; + gen = calloc(sizeof(*gen), 1); + if (!gen) + return -ENOMEM; + gen->opts = opts; + obj->gen_loader = gen; + return 0; +} + static struct bpf_program * __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, bool forward) @@ -8887,6 +9124,8 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), + SEC_DEF("syscall", SYSCALL, + .is_sleepable = true), BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, @@ -9176,6 +9415,28 @@ invalid_prog: #define BTF_ITER_PREFIX "bpf_iter_" #define BTF_MAX_NAME_SIZE 128 +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind) +{ + switch (attach_type) { + case BPF_TRACE_RAW_TP: + *prefix = BTF_TRACE_PREFIX; + *kind = BTF_KIND_TYPEDEF; + break; + case BPF_LSM_MAC: + *prefix = BTF_LSM_PREFIX; + *kind = BTF_KIND_FUNC; + break; + case BPF_TRACE_ITER: + *prefix = BTF_ITER_PREFIX; + *kind = BTF_KIND_FUNC; + break; + default: + *prefix = ""; + *kind = BTF_KIND_FUNC; + } +} + static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind) { @@ -9196,21 +9457,11 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, static inline int find_attach_btf_id(struct btf *btf, const char *name, enum bpf_attach_type attach_type) { - int err; + const char *prefix; + int kind; - if (attach_type == BPF_TRACE_RAW_TP) - err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, - BTF_KIND_TYPEDEF); - else if (attach_type == BPF_LSM_MAC) - err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name, - BTF_KIND_FUNC); - else if (attach_type == BPF_TRACE_ITER) - err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name, - BTF_KIND_FUNC); - else - err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); - - return err; + btf_get_kernel_prefix_kind(attach_type, &prefix, &kind); + return find_btf_by_prefix_kind(btf, prefix, name, kind); } int libbpf_find_vmlinux_btf_id(const char *name, @@ -9309,7 +9560,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, __u32 attach_prog_fd = prog->attach_prog_fd; const char *name = prog->sec_name, *attach_name; const struct bpf_sec_def *sec = NULL; - int i, err; + int i, err = 0; if (!name) return -EINVAL; @@ -9344,7 +9595,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, } /* kernel/module BTF ID */ - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + if (prog->obj->gen_loader) { + bpf_gen__record_attach_target(prog->obj->gen_loader, attach_name, attach_type); + *btf_obj_fd = 0; + *btf_type_id = 1; + } else { + err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + } if (err) { pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err); return err; @@ -9501,6 +9758,14 @@ int bpf_map__set_initial_value(struct bpf_map *map, return 0; } +const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +{ + if (!map->mmaped) + return NULL; + *psize = map->def.value_size; + return map->mmaped; +} + bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index bec4e6a6e31d..d98523558f39 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -471,6 +471,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); +LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); @@ -498,6 +499,7 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); +/* XDP related API */ struct xdp_link_info { __u32 prog_id; __u32 drv_prog_id; @@ -520,6 +522,49 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +/* TC related API */ +enum bpf_tc_attach_point { + BPF_TC_INGRESS = 1 << 0, + BPF_TC_EGRESS = 1 << 1, + BPF_TC_CUSTOM = 1 << 2, +}; + +#define BPF_TC_PARENT(a, b) \ + ((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU)) + +enum bpf_tc_flags { + BPF_TC_F_REPLACE = 1 << 0, +}; + +struct bpf_tc_hook { + size_t sz; + int ifindex; + enum bpf_tc_attach_point attach_point; + __u32 parent; + size_t :0; +}; +#define bpf_tc_hook__last_field parent + +struct bpf_tc_opts { + size_t sz; + int prog_fd; + __u32 flags; + __u32 prog_id; + __u32 handle; + __u32 priority; + size_t :0; +}; +#define bpf_tc_opts__last_field priority + +LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); + /* Ring buffer APIs */ struct ring_buffer; @@ -756,6 +801,18 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); +struct gen_loader_opts { + size_t sz; /* size of this struct, for forward/backward compatiblity */ + const char *data; + const char *insns; + __u32 data_sz; + __u32 insns_sz; +}; + +#define gen_loader_opts__last_field insns_sz +LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, + struct gen_loader_opts *opts); + enum libbpf_tristate { TRI_NO = 0, TRI_YES = 1, @@ -768,10 +825,18 @@ struct bpf_linker_opts { }; #define bpf_linker_opts__last_field sz +struct bpf_linker_file_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; +}; +#define bpf_linker_file_opts__last_field sz + struct bpf_linker; LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); -LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename); +LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, + const char *filename, + const struct bpf_linker_file_opts *opts); LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index b9b29baf1df8..2abef6f17c06 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -359,6 +359,13 @@ LIBBPF_0.4.0 { bpf_linker__finalize; bpf_linker__free; bpf_linker__new; + bpf_map__initial_value; bpf_map__inner_map; + bpf_object__gen_loader; bpf_object__set_kversion; + bpf_tc_attach; + bpf_tc_detach; + bpf_tc_hook_create; + bpf_tc_hook_destroy; + bpf_tc_query; } LIBBPF_0.3.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index acbcf6c7bdf8..a2cc297edb99 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -263,6 +263,8 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, __u32 *off); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind); struct btf_ext_info { /* diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 9de084b1c699..b594a88620ce 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -158,7 +158,9 @@ struct bpf_linker { static int init_output_elf(struct bpf_linker *linker, const char *file); -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj); +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec); @@ -435,15 +437,19 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) return 0; } -int bpf_linker__add_file(struct bpf_linker *linker, const char *filename) +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) { struct src_obj obj = {}; int err = 0; + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return -EINVAL; + if (!linker->elf) return -EINVAL; - err = err ?: linker_load_obj_file(linker, filename, &obj); + err = err ?: linker_load_obj_file(linker, filename, opts, &obj); err = err ?: linker_append_sec_data(linker, &obj); err = err ?: linker_append_elf_syms(linker, &obj); err = err ?: linker_append_elf_relos(linker, &obj); @@ -529,7 +535,9 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) return sec; } -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj) +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj) { #if __BYTE_ORDER == __LITTLE_ENDIAN const int host_endianness = ELFDATA2LSB; @@ -1780,7 +1788,7 @@ static void sym_update_visibility(Elf64_Sym *sym, int sym_vis) /* libelf doesn't provide setters for ST_VISIBILITY, * but it is stored in the lower 2 bits of st_other */ - sym->st_other &= 0x03; + sym->st_other &= ~0x03; sym->st_other |= sym_vis; } diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index d2cb28e9ef52..47444588e0d2 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -4,7 +4,10 @@ #include <stdlib.h> #include <memory.h> #include <unistd.h> +#include <arpa/inet.h> #include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> #include <linux/rtnetlink.h> #include <sys/socket.h> #include <errno.h> @@ -73,9 +76,20 @@ cleanup: return ret; } -static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, - __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, - void *cookie) +static void libbpf_netlink_close(int sock) +{ + close(sock); +} + +enum { + NL_CONT, + NL_NEXT, + NL_DONE, +}; + +static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, + void *cookie) { bool multipart = true; struct nlmsgerr *err; @@ -84,6 +98,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, int len, ret; while (multipart) { +start: multipart = false; len = recv(sock, buf, sizeof(buf), 0); if (len < 0) { @@ -121,8 +136,16 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, } if (_fn) { ret = _fn(nh, fn, cookie); - if (ret) + switch (ret) { + case NL_CONT: + break; + case NL_NEXT: + goto start; + case NL_DONE: + return 0; + default: return ret; + } } } } @@ -131,72 +154,72 @@ done: return ret; } +static int libbpf_netlink_send_recv(struct nlmsghdr *nh, + __dump_nlmsg_t parse_msg, + libbpf_dump_nlmsg_t parse_attr, + void *cookie) +{ + __u32 nl_pid = 0; + int sock, ret; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + nh->nlmsg_pid = 0; + nh->nlmsg_seq = time(NULL); + + if (send(sock, nh, nh->nlmsg_len, 0) < 0) { + ret = -errno; + goto out; + } + + ret = libbpf_netlink_recv(sock, nl_pid, nh->nlmsg_seq, + parse_msg, parse_attr, cookie); +out: + libbpf_netlink_close(sock); + return ret; +} + static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, __u32 flags) { - int sock, seq = 0, ret; - struct nlattr *nla, *nla_xdp; + struct nlattr *nla; + int ret; struct { struct nlmsghdr nh; struct ifinfomsg ifinfo; char attrbuf[64]; } req; - __u32 nl_pid = 0; - - sock = libbpf_netlink_open(&nl_pid); - if (sock < 0) - return sock; memset(&req, 0, sizeof(req)); - req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; - req.nh.nlmsg_type = RTM_SETLINK; - req.nh.nlmsg_pid = 0; - req.nh.nlmsg_seq = ++seq; + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; req.ifinfo.ifi_family = AF_UNSPEC; - req.ifinfo.ifi_index = ifindex; - - /* started nested attribute for XDP */ - nla = (struct nlattr *)(((char *)&req) - + NLMSG_ALIGN(req.nh.nlmsg_len)); - nla->nla_type = NLA_F_NESTED | IFLA_XDP; - nla->nla_len = NLA_HDRLEN; - - /* add XDP fd */ - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FD; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); - memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); - nla->nla_len += nla_xdp->nla_len; - - /* if user passed in any flags, add those too */ + req.ifinfo.ifi_index = ifindex; + + nla = nlattr_begin_nested(&req.nh, sizeof(req), IFLA_XDP); + if (!nla) + return -EMSGSIZE; + ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; if (flags) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FLAGS; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); - memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); - nla->nla_len += nla_xdp->nla_len; + ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_FLAGS, &flags, + sizeof(flags)); + if (ret < 0) + return ret; } - if (flags & XDP_FLAGS_REPLACE) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd); - memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd)); - nla->nla_len += nla_xdp->nla_len; + ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_EXPECTED_FD, + &old_fd, sizeof(old_fd)); + if (ret < 0) + return ret; } + nlattr_end_nested(&req.nh, nla); - req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); - - if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { - ret = -errno; - goto cleanup; - } - ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL); - -cleanup: - close(sock); - return ret; + return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL); } int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, @@ -212,9 +235,7 @@ int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, flags |= XDP_FLAGS_REPLACE; } - return __bpf_set_link_xdp_fd_replace(ifindex, fd, - old_fd, - flags); + return __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags); } int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) @@ -231,6 +252,7 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) return -LIBBPF_ERRNO__NLPARSE; @@ -282,16 +304,21 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -static int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); - int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags) { struct xdp_id_md xdp_id = {}; - int sock, ret; - __u32 nl_pid = 0; __u32 mask; + int ret; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifm; + } req = { + .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nh.nlmsg_type = RTM_GETLINK, + .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; if (flags & ~XDP_FLAGS_MASK || !info_size) return -EINVAL; @@ -302,14 +329,11 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, if (flags && flags & mask) return -EINVAL; - sock = libbpf_netlink_open(&nl_pid); - if (sock < 0) - return sock; - xdp_id.ifindex = ifindex; xdp_id.flags = flags; - ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id); + ret = libbpf_netlink_send_recv(&req.nh, __dump_link_nlmsg, + get_xdp_info, &xdp_id); if (!ret) { size_t sz = min(info_size, sizeof(xdp_id.info)); @@ -317,7 +341,6 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, memset((void *) info + sz, 0, info_size - sz); } - close(sock); return ret; } @@ -349,24 +372,403 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) return ret; } -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +typedef int (*qdisc_config_t)(struct nlmsghdr *nh, struct tcmsg *t, + size_t maxsz); + +static int clsact_config(struct nlmsghdr *nh, struct tcmsg *t, size_t maxsz) { + t->tcm_parent = TC_H_CLSACT; + t->tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); + + return nlattr_add(nh, maxsz, TCA_KIND, "clsact", sizeof("clsact")); +} + +static int attach_point_to_config(struct bpf_tc_hook *hook, + qdisc_config_t *config) +{ + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + case BPF_TC_INGRESS | BPF_TC_EGRESS: + if (OPTS_GET(hook, parent, 0)) + return -EINVAL; + *config = &clsact_config; + return 0; + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point, + __u32 *parent) +{ + switch (attach_point) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + if (*parent) + return -EINVAL; + *parent = TC_H_MAKE(TC_H_CLSACT, + attach_point == BPF_TC_INGRESS ? + TC_H_MIN_INGRESS : TC_H_MIN_EGRESS); + break; + case BPF_TC_CUSTOM: + if (!*parent) + return -EINVAL; + break; + default: + return -EINVAL; + } + return 0; +} + +static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) +{ + qdisc_config_t config; + int ret; struct { - struct nlmsghdr nlh; - struct ifinfomsg ifm; - } req = { - .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), - .nlh.nlmsg_type = RTM_GETLINK, - .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, - .ifm.ifi_family = AF_PACKET, - }; - int seq = time(NULL); + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + ret = attach_point_to_config(hook, &config); + if (ret < 0) + return ret; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags; + req.nh.nlmsg_type = cmd; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); + + ret = config(&req.nh, &req.tc, sizeof(req)); + if (ret < 0) + return ret; + + return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL); +} + +static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE); +} + +static int tc_qdisc_delete(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_DELQDISC, 0); +} + +int bpf_tc_hook_create(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return -EINVAL; + + return tc_qdisc_create_excl(hook); +} - req.nlh.nlmsg_seq = seq; - if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush); + +int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return -EINVAL; + + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + return __bpf_tc_detach(hook, NULL, true); + case BPF_TC_INGRESS | BPF_TC_EGRESS: + return tc_qdisc_delete(hook); + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +struct bpf_cb_ctx { + struct bpf_tc_opts *opts; + bool processed; +}; + +static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb, + bool unicast) +{ + struct nlattr *tbb[TCA_BPF_MAX + 1]; + struct bpf_cb_ctx *info = cookie; + + if (!info || !info->opts) + return -EINVAL; + if (unicast && info->processed) + return -EINVAL; + if (!tb[TCA_OPTIONS]) + return NL_CONT; + + libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL); + if (!tbb[TCA_BPF_ID]) + return -EINVAL; + + OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID])); + OPTS_SET(info->opts, handle, tc->tcm_handle); + OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16); + + info->processed = true; + return unicast ? NL_NEXT : NL_DONE; +} + +static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct tcmsg *tc = NLMSG_DATA(nh); + struct nlattr *tb[TCA_MAX + 1]; + + libbpf_nla_parse(tb, TCA_MAX, + (struct nlattr *)((char *)tc + NLMSG_ALIGN(sizeof(*tc))), + NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL); + if (!tb[TCA_KIND]) + return NL_CONT; + return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO); +} + +static int tc_add_fd_and_name(struct nlmsghdr *nh, size_t maxsz, int fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + char name[256]; + int len, ret; + + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (ret < 0) + return ret; + + ret = nlattr_add(nh, maxsz, TCA_BPF_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id); + if (len < 0) return -errno; + if (len >= sizeof(name)) + return -ENAMETOOLONG; + return nlattr_add(nh, maxsz, TCA_BPF_NAME, name, len + 1); +} + +int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct nlattr *nla; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || !prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (flags & ~BPF_TC_F_REPLACE) + return -EINVAL; + + flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL; + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE | + NLM_F_ECHO | flags; + req.nh.nlmsg_type = RTM_NEWTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + nla = nlattr_begin_nested(&req.nh, sizeof(req), TCA_OPTIONS); + if (!nla) + return -EMSGSIZE; + ret = tc_add_fd_and_name(&req.nh, sizeof(req), prog_fd); + if (ret < 0) + return ret; + bpf_flags = TCA_BPF_FLAG_ACT_DIRECT; + ret = nlattr_add(&req.nh, sizeof(req), TCA_BPF_FLAGS, &bpf_flags, + sizeof(bpf_flags)); + if (ret < 0) + return ret; + nlattr_end_nested(&req.nh, nla); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info); + if (ret < 0) + return ret; + if (!info.processed) + return -ENOENT; + return ret; +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush) +{ + __u32 protocol = 0, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; - return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, - dump_link_nlmsg, cookie); + if (!hook || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (flags & ~BPF_TC_F_REPLACE) + return -EINVAL; + if (!flush) { + if (!handle || !priority) + return -EINVAL; + protocol = ETH_P_ALL; + } else { + if (handle || priority) + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_DELTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + if (!flush) { + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + } + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + if (!flush) { + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, + "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + } + + return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL); +} + +int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts) +{ + return !opts ? -EINVAL : __bpf_tc_detach(hook, opts, false); +} + +int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id || + !handle || !priority) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = RTM_GETTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info); + if (ret < 0) + return ret; + if (!info.processed) + return -ENOENT; + return ret; } diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 6cc3ac91690f..3c780ab6d022 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -10,7 +10,10 @@ #define __LIBBPF_NLATTR_H #include <stdint.h> +#include <string.h> +#include <errno.h> #include <linux/netlink.h> + /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -103,4 +106,49 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh); +static inline struct nlattr *nla_data(struct nlattr *nla) +{ + return (struct nlattr *)((char *)nla + NLA_HDRLEN); +} + +static inline struct nlattr *nh_tail(struct nlmsghdr *nh) +{ + return (struct nlattr *)((char *)nh + NLMSG_ALIGN(nh->nlmsg_len)); +} + +static inline int nlattr_add(struct nlmsghdr *nh, size_t maxsz, int type, + const void *data, int len) +{ + struct nlattr *nla; + + if (NLMSG_ALIGN(nh->nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > maxsz) + return -EMSGSIZE; + if (!!data != !!len) + return -EINVAL; + + nla = nh_tail(nh); + nla->nla_type = type; + nla->nla_len = NLA_HDRLEN + len; + if (data) + memcpy(nla_data(nla), data, len); + nh->nlmsg_len = NLMSG_ALIGN(nh->nlmsg_len) + NLA_ALIGN(nla->nla_len); + return 0; +} + +static inline struct nlattr *nlattr_begin_nested(struct nlmsghdr *nh, + size_t maxsz, int type) +{ + struct nlattr *tail; + + tail = nh_tail(nh); + if (nlattr_add(nh, maxsz, type | NLA_F_NESTED, NULL, 0)) + return NULL; + return tail; +} + +static inline void nlattr_end_nested(struct nlmsghdr *nh, struct nlattr *tail) +{ + tail->nla_len = (char *)nh_tail(nh) - (char *)tail; +} + #endif /* __LIBBPF_NLATTR_H */ diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h new file mode 100644 index 000000000000..b22b50c1b173 --- /dev/null +++ b/tools/lib/bpf/skel_internal.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __SKEL_INTERNAL_H +#define __SKEL_INTERNAL_H + +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/mman.h> + +/* This file is a base header for auto-generated *.lskel.h files. + * Its contents will change and may become part of auto-generation in the future. + * + * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent + * and will change from one version of libbpf to another and features + * requested during loader program generation. + */ +struct bpf_map_desc { + union { + /* input for the loader prog */ + struct { + __aligned_u64 initial_value; + __u32 max_entries; + }; + /* output of the loader prog */ + struct { + int map_fd; + }; + }; +}; +struct bpf_prog_desc { + int prog_fd; +}; + +struct bpf_loader_ctx { + size_t sz; + __u32 log_level; + __u32 log_size; + __u64 log_buf; +}; + +struct bpf_load_and_run_opts { + struct bpf_loader_ctx *ctx; + const void *data; + const void *insns; + __u32 data_sz; + __u32 insns_sz; + const char *errstr; +}; + +static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +static inline int skel_closenz(int fd) +{ + if (fd > 0) + return close(fd); + return -EINVAL; +} + +static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) +{ + int map_fd = -1, prog_fd = -1, key = 0, err; + union bpf_attr attr; + + map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, + opts->data_sz, 1, 0); + if (map_fd < 0) { + opts->errstr = "failed to create loader map"; + err = -errno; + goto out; + } + + err = bpf_map_update_elem(map_fd, &key, opts->data, 0); + if (err < 0) { + opts->errstr = "failed to update loader map"; + err = -errno; + goto out; + } + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SYSCALL; + attr.insns = (long) opts->insns; + attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + attr.license = (long) "Dual BSD/GPL"; + memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); + attr.fd_array = (long) &map_fd; + attr.log_level = opts->ctx->log_level; + attr.log_size = opts->ctx->log_size; + attr.log_buf = opts->ctx->log_buf; + attr.prog_flags = BPF_F_SLEEPABLE; + prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + if (prog_fd < 0) { + opts->errstr = "failed to load loader prog"; + err = -errno; + goto out; + } + + memset(&attr, 0, sizeof(attr)); + attr.test.prog_fd = prog_fd; + attr.test.ctx_in = (long) opts->ctx; + attr.test.ctx_size_in = opts->ctx->sz; + err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); + if (err < 0 || (int)attr.test.retval < 0) { + opts->errstr = "failed to execute loader prog"; + if (err < 0) + err = -errno; + else + err = (int)attr.test.retval; + goto out; + } + err = 0; +out: + if (map_fd >= 0) + close(map_fd); + if (prog_fd >= 0) + close(prog_fd); + return err; +} + +#endif diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 4866f6a21901..a030aa4a8a9e 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -30,6 +30,7 @@ test_sysctl xdping test_cpp *.skel.h +*.lskel.h /no_alu32 /bpf_gcc /tools diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 511259c2c6c5..525e4b3fb514 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -312,6 +312,10 @@ SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h +LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ + test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c +SKEL_BLACKLIST += $$(LSKELS) + test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o @@ -339,6 +343,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS) TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\ $$(TRUNNER_BPF_SRCS))) +TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS)) TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS)) TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) @@ -380,6 +385,14 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ +$(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) + $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$< + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o) + $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) + $(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ + $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o)) $(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps)) @@ -409,6 +422,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_OBJS) \ $(TRUNNER_BPF_SKELS) \ + $(TRUNNER_BPF_LSKELS) \ $(TRUNNER_BPF_SKELS_LINKED) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) @@ -516,6 +530,6 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature \ - $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko) + $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko) .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 21efe7bbf10d..ba0e1efe5a45 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -2,19 +2,19 @@ #include <test_progs.h> -#include "atomics.skel.h" +#include "atomics.lskel.h" static void test_add(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.add); - if (CHECK(IS_ERR(link), "attach(add)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__add__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(add)")) return; - prog_fd = bpf_program__fd(skel->progs.add); + prog_fd = skel->progs.add.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -33,20 +33,20 @@ static void test_add(struct atomics *skel) ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_sub(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.sub); - if (CHECK(IS_ERR(link), "attach(sub)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__sub__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(sub)")) return; - prog_fd = bpf_program__fd(skel->progs.sub); + prog_fd = skel->progs.sub.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run sub", @@ -66,20 +66,20 @@ static void test_sub(struct atomics *skel) ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_and(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.and); - if (CHECK(IS_ERR(link), "attach(and)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__and__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(and)")) return; - prog_fd = bpf_program__fd(skel->progs.and); + prog_fd = skel->progs.and.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run and", @@ -94,20 +94,20 @@ static void test_and(struct atomics *skel) ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_or(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.or); - if (CHECK(IS_ERR(link), "attach(or)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__or__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(or)")) return; - prog_fd = bpf_program__fd(skel->progs.or); + prog_fd = skel->progs.or.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run or", @@ -123,20 +123,20 @@ static void test_or(struct atomics *skel) ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_xor(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.xor); - if (CHECK(IS_ERR(link), "attach(xor)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__xor__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(xor)")) return; - prog_fd = bpf_program__fd(skel->progs.xor); + prog_fd = skel->progs.xor.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run xor", @@ -151,20 +151,20 @@ static void test_xor(struct atomics *skel) ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_cmpxchg(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.cmpxchg); - if (CHECK(IS_ERR(link), "attach(cmpxchg)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__cmpxchg__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) return; - prog_fd = bpf_program__fd(skel->progs.cmpxchg); + prog_fd = skel->progs.cmpxchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -180,20 +180,20 @@ static void test_cmpxchg(struct atomics *skel) ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_xchg(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.xchg); - if (CHECK(IS_ERR(link), "attach(xchg)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__xchg__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) return; - prog_fd = bpf_program__fd(skel->progs.xchg); + prog_fd = skel->progs.xchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -207,7 +207,7 @@ static void test_xchg(struct atomics *skel) ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result"); cleanup: - bpf_link__destroy(link); + close(link_fd); } void test_atomics(void) diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 109d0345a2be..91154c2ba256 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.skel.h" -#include "fexit_test.skel.h" +#include "fentry_test.lskel.h" +#include "fexit_test.lskel.h" void test_fentry_fexit(void) { @@ -26,7 +26,7 @@ void test_fentry_fexit(void) if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; - prog_fd = bpf_program__fd(fexit_skel->progs.test1); + prog_fd = fexit_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 7cb111b11995..174c89e7456e 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,13 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.skel.h" +#include "fentry_test.lskel.h" static int fentry_test(struct fentry_test *fentry_skel) { int err, prog_fd, i; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; __u64 *result; err = fentry_test__attach(fentry_skel); @@ -15,11 +15,11 @@ static int fentry_test(struct fentry_test *fentry_skel) return err; /* Check that already linked program can't be attached again. */ - link = bpf_program__attach(fentry_skel->progs.test1); - if (!ASSERT_ERR_PTR(link, "fentry_attach_link")) + link_fd = fentry_test__test1__attach(fentry_skel); + if (!ASSERT_LT(link_fd, 0, "fentry_attach_link")) return -1; - prog_fd = bpf_program__fd(fentry_skel->progs.test1); + prog_fd = fentry_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c index ccc7e8a34ab6..4e7f4b42ea29 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c @@ -6,7 +6,7 @@ #include <time.h> #include <sys/mman.h> #include <sys/syscall.h> -#include "fexit_sleep.skel.h" +#include "fexit_sleep.lskel.h" static int do_sleep(void *skel) { @@ -58,8 +58,8 @@ void test_fexit_sleep(void) * waiting for percpu_ref_kill to confirm). The other one * will be freed quickly. */ - close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry)); - close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit)); + close(fexit_skel->progs.nanosleep_fentry.prog_fd); + close(fexit_skel->progs.nanosleep_fexit.prog_fd); fexit_sleep__detach(fexit_skel); /* kill the thread to unwind sys_nanosleep stack through the trampoline */ diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 6792e41f7f69..af3dba726701 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -1,13 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fexit_test.skel.h" +#include "fexit_test.lskel.h" static int fexit_test(struct fexit_test *fexit_skel) { int err, prog_fd, i; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; __u64 *result; err = fexit_test__attach(fexit_skel); @@ -15,11 +15,11 @@ static int fexit_test(struct fexit_test *fexit_skel) return err; /* Check that already linked program can't be attached again. */ - link = bpf_program__attach(fexit_skel->progs.test1); - if (!ASSERT_ERR_PTR(link, "fexit_attach_link")) + link_fd = fexit_test__test1__attach(fexit_skel); + if (!ASSERT_LT(link_fd, 0, "fexit_attach_link")) return -1; - prog_fd = bpf_program__fd(fexit_skel->progs.test1); + prog_fd = fexit_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7fc0951ee75f..30a7b9b837bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <test_progs.h> #include <network_helpers.h> -#include "kfunc_call_test.skel.h" +#include "kfunc_call_test.lskel.h" #include "kfunc_call_test_subprog.skel.h" static void test_main(void) @@ -14,13 +14,13 @@ static void test_main(void) if (!ASSERT_OK_PTR(skel, "skel")) return; - prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1); + prog_fd = skel->progs.kfunc_call_test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); ASSERT_OK(err, "bpf_prog_test_run(test1)"); ASSERT_EQ(retval, 12, "test1-retval"); - prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2); + prog_fd = skel->progs.kfunc_call_test2.prog_fd; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); ASSERT_OK(err, "bpf_prog_test_run(test2)"); diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index 4c232b456479..2cd5cded543f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -4,7 +4,7 @@ #include <test_progs.h> #include <bpf/libbpf.h> #include <bpf/btf.h> -#include "test_ksyms_module.skel.h" +#include "test_ksyms_module.lskel.h" static int duration; diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index f9a8ae331963..a01788090c31 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -12,7 +12,7 @@ #include <sys/sysinfo.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> -#include "test_ringbuf.skel.h" +#include "test_ringbuf.lskel.h" #define EDONE 7777 @@ -94,9 +94,7 @@ void test_ringbuf(void) if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; - err = bpf_map__set_max_entries(skel->maps.ringbuf, page_size); - if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n")) - goto cleanup; + skel->maps.ringbuf.max_entries = page_size; err = test_ringbuf__load(skel); if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) @@ -151,7 +149,7 @@ void test_ringbuf(void) /* only trigger BPF program for current process */ skel->bss->pid = getpid(); - ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf), + ringbuf = ring_buffer__new(skel->maps.ringbuf.map_fd, process_sample, NULL, NULL); if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 7043e6ded0e6..a1eade51d440 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -2,7 +2,7 @@ #include <test_progs.h> #include "test_send_signal_kern.skel.h" -static volatile int sigusr1_received = 0; +int sigusr1_received = 0; static void sigusr1_handler(int signum) { diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index fe87b77af459..f6f130c99b8c 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -82,10 +82,8 @@ void test_skeleton(void) CHECK(data->out2 != 2, "res2", "got %lld != exp %d\n", data->out2, 2); CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3); CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4); - CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n", - bss->handler_out5.a, 5); - CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n", - bss->handler_out5.b, 6); + CHECK(bss->out5.a != 5, "res5", "got %d != exp %d\n", bss->out5.a, 5); + CHECK(bss->out5.b != 6, "res6", "got %lld != exp %d\n", bss->out5.b, 6); CHECK(bss->out6 != 14, "res7", "got %d != exp %d\n", bss->out6, 14); CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1", diff --git a/tools/testing/selftests/bpf/prog_tests/static_linked.c b/tools/testing/selftests/bpf/prog_tests/static_linked.c index 46556976dccc..5c4e3014e063 100644 --- a/tools/testing/selftests/bpf/prog_tests/static_linked.c +++ b/tools/testing/selftests/bpf/prog_tests/static_linked.c @@ -14,12 +14,7 @@ void test_static_linked(void) return; skel->rodata->rovar1 = 1; - skel->bss->static_var1 = 2; - skel->bss->static_var11 = 3; - skel->rodata->rovar2 = 4; - skel->bss->static_var2 = 5; - skel->bss->static_var22 = 6; err = test_static_linked__load(skel); if (!ASSERT_OK(err, "skel_load")) @@ -32,8 +27,8 @@ void test_static_linked(void) /* trigger */ usleep(1); - ASSERT_EQ(skel->bss->var1, 1 * 2 + 2 + 3, "var1"); - ASSERT_EQ(skel->bss->var2, 4 * 3 + 5 + 6, "var2"); + ASSERT_EQ(skel->data->var1, 1 * 2 + 2 + 3, "var1"); + ASSERT_EQ(skel->data->var2, 4 * 3 + 5 + 6, "var2"); cleanup: test_static_linked__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c new file mode 100644 index 000000000000..81e997a69f7a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "syscall.skel.h" + +struct args { + __u64 log_buf; + __u32 log_size; + int max_entries; + int map_fd; + int prog_fd; + int btf_fd; +}; + +void test_syscall(void) +{ + static char verifier_log[8192]; + struct args ctx = { + .max_entries = 1024, + .log_buf = (uintptr_t) verifier_log, + .log_size = sizeof(verifier_log), + }; + struct bpf_prog_test_run_attr tattr = { + .ctx_in = &ctx, + .ctx_size_in = sizeof(ctx), + }; + struct syscall *skel = NULL; + __u64 key = 12, value = 0; + int err; + + skel = syscall__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog); + err = bpf_prog_test_run_xattr(&tattr); + ASSERT_EQ(err, 0, "err"); + ASSERT_EQ(tattr.retval, 1, "retval"); + ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd"); + ASSERT_GT(ctx.prog_fd, 0, "ctx.prog_fd"); + ASSERT_OK(memcmp(verifier_log, "processed", sizeof("processed") - 1), + "verifier_log"); + + err = bpf_map_lookup_elem(ctx.map_fd, &key, &value); + ASSERT_EQ(err, 0, "map_lookup"); + ASSERT_EQ(value, 34, "map lookup value"); +cleanup: + syscall__destroy(skel); + if (ctx.prog_fd > 0) + close(ctx.prog_fd); + if (ctx.map_fd > 0) + close(ctx.map_fd); + if (ctx.btf_fd > 0) + close(ctx.btf_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c new file mode 100644 index 000000000000..4a505a5adf4d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/pkt_cls.h> + +#include "test_tc_bpf.skel.h" + +#define LO_IFINDEX 1 + +#define TEST_DECLARE_OPTS(__fd) \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_h, .handle = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_p, .priority = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_f, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hp, .handle = 1, .priority = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hf, .handle = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_pf, .priority = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpf, .handle = 1, .priority = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpi, .handle = 1, .priority = 1, .prog_id = 42); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpr, .handle = 1, .priority = 1, \ + .flags = BPF_TC_F_REPLACE); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpfi, .handle = 1, .priority = 1, .prog_fd = __fd, \ + .prog_id = 42); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_prio_max, .handle = 1, .priority = UINT16_MAX + 1); + +static int test_tc_bpf_basic(const struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd); + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int ret; + + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd")) + return ret; + + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + return ret; + + if (!ASSERT_EQ(opts.handle, 1, "handle set") || + !ASSERT_EQ(opts.priority, 1, "priority set") || + !ASSERT_EQ(opts.prog_id, info.id, "prog_id set")) + goto end; + + opts.prog_id = 0; + opts.flags = BPF_TC_F_REPLACE; + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach replace mode")) + goto end; + + opts.flags = opts.prog_fd = opts.prog_id = 0; + ret = bpf_tc_query(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_query")) + goto end; + + if (!ASSERT_EQ(opts.handle, 1, "handle set") || + !ASSERT_EQ(opts.priority, 1, "priority set") || + !ASSERT_EQ(opts.prog_id, info.id, "prog_id set")) + goto end; + +end: + opts.flags = opts.prog_fd = opts.prog_id = 0; + ret = bpf_tc_detach(hook, &opts); + ASSERT_OK(ret, "bpf_tc_detach"); + return ret; +} + +static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, attach_opts, .handle = 1, .priority = 1, .prog_fd = fd); + DECLARE_LIBBPF_OPTS(bpf_tc_hook, inv_hook, .attach_point = BPF_TC_INGRESS); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1); + int ret; + + ret = bpf_tc_hook_create(NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook = NULL")) + return -EINVAL; + + /* hook ifindex = 0 */ + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex == 0")) + return -EINVAL; + attach_opts.prog_id = 0; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex == 0")) + return -EINVAL; + + /* hook ifindex < 0 */ + inv_hook.ifindex = -1; + + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex < 0")) + return -EINVAL; + attach_opts.prog_id = 0; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex < 0")) + return -EINVAL; + + inv_hook.ifindex = LO_IFINDEX; + + /* hook.attach_point invalid */ + inv_hook.attach_point = 0xabcd; + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook.attach_point")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_INGRESS; + + /* hook.attach_point valid, but parent invalid */ + inv_hook.parent = TC_H_MAKE(1UL << 16, 10); + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_CUSTOM; + inv_hook.parent = 0; + /* These return EOPNOTSUPP instead of EINVAL as parent is checked after + * attach_point of the hook. + */ + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_INGRESS; + + /* detach */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_detach(NULL, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_detach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid opts = NULL")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpr); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid flags set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpf); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_fd set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_p); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid handle unset")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_h); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority unset")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority > UINT16_MAX")) + return -EINVAL; + } + + /* query */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_query(NULL, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_query(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid opts = NULL")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpr); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid flags set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpf); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_fd set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_p); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid handle unset")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_h); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority unset")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority > UINT16_MAX")) + return -EINVAL; + + /* when chain is not present, kernel returns -EINVAL */ + ret = bpf_tc_query(hook, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query valid handle, priority set")) + return -EINVAL; + } + + /* attach */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_attach(NULL, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_attach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid opts = NULL")) + return -EINVAL; + + opts_hp.flags = 42; + ret = bpf_tc_attach(hook, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid flags")) + return -EINVAL; + + ret = bpf_tc_attach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_fd unset")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_pf); + if (!ASSERT_OK(ret, "bpf_tc_attach valid handle unset")) + return -EINVAL; + opts_pf.prog_fd = opts_pf.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_pf), "bpf_tc_detach"); + + ret = bpf_tc_attach(hook, &opts_hf); + if (!ASSERT_OK(ret, "bpf_tc_attach valid priority unset")) + return -EINVAL; + opts_hf.prog_fd = opts_hf.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_hf), "bpf_tc_detach"); + + ret = bpf_tc_attach(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid priority > UINT16_MAX")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_f); + if (!ASSERT_OK(ret, "bpf_tc_attach valid both handle and priority unset")) + return -EINVAL; + opts_f.prog_fd = opts_f.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_f), "bpf_tc_detach"); + } + + return 0; +} + +void test_tc_bpf(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, + .attach_point = BPF_TC_INGRESS); + struct test_tc_bpf *skel = NULL; + bool hook_created = false; + int cls_fd, ret; + + skel = test_tc_bpf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load")) + return; + + cls_fd = bpf_program__fd(skel->progs.cls); + + ret = bpf_tc_hook_create(&hook); + if (ret == 0) + hook_created = true; + + ret = ret == -EEXIST ? 0 : ret; + if (!ASSERT_OK(ret, "bpf_tc_hook_create(BPF_TC_INGRESS)")) + goto end; + + hook.attach_point = BPF_TC_CUSTOM; + hook.parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + ret = bpf_tc_hook_create(&hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook.attach_point")) + goto end; + + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal ingress")) + goto end; + + ret = bpf_tc_hook_destroy(&hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook.attach_point")) + goto end; + + hook.attach_point = BPF_TC_INGRESS; + hook.parent = 0; + bpf_tc_hook_destroy(&hook); + + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal ingress")) + goto end; + + bpf_tc_hook_destroy(&hook); + + hook.attach_point = BPF_TC_EGRESS; + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal egress")) + goto end; + + bpf_tc_hook_destroy(&hook); + + ret = test_tc_bpf_api(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_bpf_api")) + goto end; + + bpf_tc_hook_destroy(&hook); + +end: + if (hook_created) { + hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&hook); + } + test_tc_bpf__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index 39b0decb1bb2..d39bc00feb45 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -3,7 +3,7 @@ #include <test_progs.h> -#include "trace_printk.skel.h" +#include "trace_printk.lskel.h" #define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" #define SEARCHMSG "testing,testing" @@ -21,6 +21,9 @@ void test_trace_printk(void) if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) return; + ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + skel->rodata->fmt[0] = 't'; + err = trace_printk__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c index ee49493dc125..400fdf8d6233 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -9,8 +9,8 @@ __u32 map1_id = 0, map2_id = 0; __u32 map1_accessed = 0, map2_accessed = 0; __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; -static volatile const __u32 print_len; -static volatile const __u32 ret1; +volatile const __u32 print_len; +volatile const __u32 ret1; SEC("iter/bpf_map") int dump_bpf_map(struct bpf_iter__bpf_map *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index a46a264ce24e..55e283050cab 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -109,10 +109,10 @@ int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location) return 0; } -static volatile struct { +struct { bool fentry_test_ok; bool fexit_test_ok; -} result; +} result = {}; SEC("fentry/eth_type_trans") int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev, diff --git a/tools/testing/selftests/bpf/progs/linked_maps1.c b/tools/testing/selftests/bpf/progs/linked_maps1.c index 52291515cc72..00bf1ca95986 100644 --- a/tools/testing/selftests/bpf/progs/linked_maps1.c +++ b/tools/testing/selftests/bpf/progs/linked_maps1.c @@ -75,7 +75,7 @@ int BPF_PROG(handler_exit1) val = bpf_map_lookup_elem(&map_weak, &key); if (val) output_weak1 = *val; - + return 0; } diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c new file mode 100644 index 000000000000..e550f728962d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <../../../tools/include/linux/filter.h> +#include <linux/btf.h> + +char _license[] SEC("license") = "GPL"; + +struct args { + __u64 log_buf; + __u32 log_size; + int max_entries; + int map_fd; + int prog_fd; + int btf_fd; +}; + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +static int btf_load(void) +{ + struct btf_blob { + struct btf_header btf_hdr; + __u32 types[8]; + __u32 str; + } raw_btf = { + .btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(__u32) * 8, + .str_off = sizeof(__u32) * 8, + .str_len = sizeof(__u32), + }, + .types = { + /* long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [1] */ + /* unsigned long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + }, + }; + static union bpf_attr btf_load_attr = { + .btf_size = sizeof(raw_btf), + }; + + btf_load_attr.btf = (long)&raw_btf; + return bpf_sys_bpf(BPF_BTF_LOAD, &btf_load_attr, sizeof(btf_load_attr)); +} + +SEC("syscall") +int bpf_prog(struct args *ctx) +{ + static char license[] = "GPL"; + static struct bpf_insn insns[] = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + static union bpf_attr map_create_attr = { + .map_type = BPF_MAP_TYPE_HASH, + .key_size = 8, + .value_size = 8, + .btf_key_type_id = 1, + .btf_value_type_id = 2, + }; + static union bpf_attr map_update_attr = { .map_fd = 1, }; + static __u64 key = 12; + static __u64 value = 34; + static union bpf_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .insn_cnt = sizeof(insns) / sizeof(insns[0]), + }; + int ret; + + ret = btf_load(); + if (ret <= 0) + return ret; + + ctx->btf_fd = ret; + map_create_attr.max_entries = ctx->max_entries; + map_create_attr.btf_fd = ret; + + prog_load_attr.license = (long) license; + prog_load_attr.insns = (long) insns; + prog_load_attr.log_buf = ctx->log_buf; + prog_load_attr.log_size = ctx->log_size; + prog_load_attr.log_level = 1; + + ret = bpf_sys_bpf(BPF_MAP_CREATE, &map_create_attr, sizeof(map_create_attr)); + if (ret <= 0) + return ret; + ctx->map_fd = ret; + insns[3].imm = ret; + + map_update_attr.map_fd = ret; + map_update_attr.key = (long) &key; + map_update_attr.value = (long) &value; + ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr)); + if (ret < 0) + return ret; + + ret = bpf_sys_bpf(BPF_PROG_LOAD, &prog_load_attr, sizeof(prog_load_attr)); + if (ret <= 0) + return ret; + ctx->prog_fd = ret; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 739dc2a51e74..910858fe078a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int count; +int count = 0; SEC("classifier/0") int bpf_func_0(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index f82075b47d7d..bd4be135c39d 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int selector; +int selector = 0; #define TAIL_FUNC(x) \ SEC("classifier/" #x) \ diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index ce5450744fd4..adf30a33064e 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int selector; +int selector = 0; #define TAIL_FUNC(x) \ SEC("classifier/" #x) \ diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 7b1c04183824..3cc4c12817b5 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -20,7 +20,7 @@ int subprog_tail(struct __sk_buff *skb) return 1; } -static volatile int count; +int count = 0; SEC("classifier/0") int bpf_func_0(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index 9a1b166b7fbe..77df6d4db895 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -9,7 +9,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int count; +int count = 0; __noinline int subprog_tail_2(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index c4a9bae96e75..71184af57749 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -11,8 +11,8 @@ char _license[] SEC("license") = "GPL"; /* Userspace will update with MTU it can see on device */ -static volatile const int GLOBAL_USER_MTU; -static volatile const __u32 GLOBAL_USER_IFINDEX; +volatile const int GLOBAL_USER_MTU; +volatile const __u32 GLOBAL_USER_IFINDEX; /* BPF-prog will update these with MTU values it can see */ __u32 global_bpf_mtu_xdp = 0; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index 3c1e042962e6..e2a5acc4785c 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -39,8 +39,8 @@ char _license[] SEC("license") = "Dual BSD/GPL"; /** * Destination port and IP used for UDP encapsulation. */ -static volatile const __be16 ENCAPSULATION_PORT; -static volatile const __be32 ENCAPSULATION_IP; +volatile const __be16 ENCAPSULATION_PORT; +volatile const __be32 ENCAPSULATION_IP; typedef struct { uint64_t processed_packets_total; diff --git a/tools/testing/selftests/bpf/progs/test_global_func_args.c b/tools/testing/selftests/bpf/progs/test_global_func_args.c index cae309538a9e..e712bf77daae 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func_args.c +++ b/tools/testing/selftests/bpf/progs/test_global_func_args.c @@ -8,7 +8,7 @@ struct S { int v; }; -static volatile struct S global_variable; +struct S global_variable = {}; struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index ecbeea2df259..fc8e8a34a3db 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -static volatile const struct { +const struct { unsigned a[4]; /* * if the struct's size is multiple of 16, compiler will put it into @@ -15,11 +15,11 @@ static volatile const struct { char _y; } rdonly_values = { .a = {2, 3, 4, 5} }; -static volatile struct { +struct { unsigned did_run; unsigned iters; unsigned sum; -} res; +} res = {}; SEC("raw_tracepoint/sys_enter:skip_loop") int skip_loop(struct pt_regs *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c index 6b3f288b7c63..eaa7d9dba0be 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -35,7 +35,7 @@ long prod_pos = 0; /* inner state */ long seq = 0; -SEC("tp/syscalls/sys_enter_getpgid") +SEC("fentry/__x64_sys_getpgid") int test_ringbuf(void *ctx) { int cur_pid = bpf_get_current_pid_tgid() >> 32; @@ -48,7 +48,7 @@ int test_ringbuf(void *ctx) sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0); if (!sample) { __sync_fetch_and_add(&dropped, 1); - return 1; + return 0; } sample->pid = pid; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c index 374ccef704e1..441fa1c552c8 100644 --- a/tools/testing/selftests/bpf/progs/test_skeleton.c +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -38,11 +38,11 @@ extern int LINUX_KERNEL_VERSION __kconfig; bool bpf_syscall = 0; int kern_ver = 0; +struct s out5 = {}; + SEC("raw_tp/sys_enter") int handler(const void *ctx) { - static volatile struct s out5; - out1 = in1; out2 = in2; out3 = in3; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf_single.c b/tools/testing/selftests/bpf/progs/test_snprintf_single.c index 402adaf344f9..3095837334d3 100644 --- a/tools/testing/selftests/bpf/progs/test_snprintf_single.c +++ b/tools/testing/selftests/bpf/progs/test_snprintf_single.c @@ -5,7 +5,7 @@ #include <bpf/bpf_helpers.h> /* The format string is filled from the userspace such that loading fails */ -static const char fmt[10]; +const char fmt[10]; SEC("raw_tp/sys_enter") int handler(const void *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a39eba9f5201..a1cc58b10c7c 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -28,8 +28,8 @@ struct { __type(value, unsigned int); } verdict_map SEC(".maps"); -static volatile bool test_sockmap; /* toggled by user-space */ -static volatile bool test_ingress; /* toggled by user-space */ +bool test_sockmap = false; /* toggled by user-space */ +bool test_ingress = false; /* toggled by user-space */ SEC("sk_skb/stream_parser") int prog_stream_parser(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c index ea1a6c4c7172..4f0b612e1661 100644 --- a/tools/testing/selftests/bpf/progs/test_static_linked1.c +++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c @@ -4,10 +4,10 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -/* 8-byte aligned .bss */ -static volatile long static_var1; -static volatile int static_var11; -int var1 = 0; +/* 8-byte aligned .data */ +static volatile long static_var1 = 2; +static volatile int static_var2 = 3; +int var1 = -1; /* 4-byte aligned .rodata */ const volatile int rovar1; @@ -21,7 +21,7 @@ static __noinline int subprog(int x) SEC("raw_tp/sys_enter") int handler1(const void *ctx) { - var1 = subprog(rovar1) + static_var1 + static_var11; + var1 = subprog(rovar1) + static_var1 + static_var2; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c index 54d8d1ab577c..766ebd502a60 100644 --- a/tools/testing/selftests/bpf/progs/test_static_linked2.c +++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c @@ -4,10 +4,10 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -/* 4-byte aligned .bss */ -static volatile int static_var2; -static volatile int static_var22; -int var2 = 0; +/* 4-byte aligned .data */ +static volatile int static_var1 = 5; +static volatile int static_var2 = 6; +int var2 = -1; /* 8-byte aligned .rodata */ const volatile long rovar2; @@ -21,7 +21,7 @@ static __noinline int subprog(int x) SEC("raw_tp/sys_enter") int handler2(const void *ctx) { - var2 = subprog(rovar2) + static_var2 + static_var22; + var2 = subprog(rovar2) + static_var1 + static_var2; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c index d3c5673c0218..b7c37ca09544 100644 --- a/tools/testing/selftests/bpf/progs/test_subprogs.c +++ b/tools/testing/selftests/bpf/progs/test_subprogs.c @@ -4,8 +4,18 @@ const char LICENSE[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array SEC(".maps"); + __noinline int sub1(int x) { + int key = 0; + + bpf_map_lookup_elem(&array, &key); return x + 1; } @@ -23,6 +33,9 @@ static __noinline int sub3(int z) static __noinline int sub4(int w) { + int key = 0; + + bpf_map_lookup_elem(&array, &key); return w + sub3(5) + sub1(6); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c new file mode 100644 index 000000000000..18a3a7ed924a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* Dummy prog to test TC-BPF API */ + +SEC("classifier") +int cls(struct __sk_buff *skb) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c index 8ca7f399b670..119582aa105a 100644 --- a/tools/testing/selftests/bpf/progs/trace_printk.c +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -10,11 +10,11 @@ char _license[] SEC("license") = "GPL"; int trace_printk_ret = 0; int trace_printk_ran = 0; -SEC("tp/raw_syscalls/sys_enter") +const char fmt[] = "Testing,testing %d\n"; + +SEC("fentry/__x64_sys_nanosleep") int sys_enter(void *ctx) { - static const char fmt[] = "testing,testing %d\n"; - trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), ++trace_printk_ran); return 0; diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh index 65f43a7ce9c9..1e9a4aff76a2 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh @@ -7,6 +7,8 @@ PORT_NUM_NETIFS=0 +declare -a unsplit + port_setup_prepare() { : @@ -20,12 +22,12 @@ port_cleanup() devlink port unsplit $port check_err $? "Did not unsplit $netdev" done + unsplit=() } split_all_ports() { local should_fail=$1; shift - local -a unsplit # Loop over the splittable netdevs and create tuples of netdev along # with its width. For example: diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh index 27de3d9ed08e..f4493ef9cca1 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh @@ -29,37 +29,38 @@ cleanup() get_prio_pg() { - __mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' | - grep buffer | sed 's/ \+/ /g' | cut -d' ' -f 2- + # Produces a string of numbers "<B0> <B1> ... <B7> ", where BX is number + # of buffer that priority X is mapped to. + dcb -j buffer show dev $swp | + jq -r '[.prio_buffer | .[] | tostring + " "] | add' } get_prio_pfc() { - __mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' | - grep enabled | sed 's/ \+/ /g' | cut -d' ' -f 2- + # Produces a string of numbers "<P0> <P1> ... <P7> ", where PX denotes + # whether priority X has PFC enabled (the value is 1) or disabled (0). + dcb -j pfc show dev $swp | + jq -r '[.prio_pfc | .[] | if . then "1 " else "0 " end] | add' } get_prio_tc() { - __mlnx_qos -i $swp | sed -n '/^tc/,$p' | - awk '/^tc/ { TC = $2 } - /priority:/ { PRIO[$2]=TC } - END { - for (i in PRIO) - printf("%d ", PRIO[i]) - }' + # Produces a string of numbers "<T0> <T1> ... <T7> ", where TC is number + # of TC that priority X is mapped to. + dcb -j ets show dev $swp | + jq -r '[.prio_tc | .[] | tostring + " "] | add' } get_buf_size() { local idx=$1; shift - __mlnx_qos -i $swp | grep Receive | sed 's/.*: //' | cut -d, -f $((idx + 1)) + dcb -j buffer show dev $swp | jq ".buffer_size[$idx]" } get_tot_size() { - __mlnx_qos -i $swp | grep Receive | sed 's/.*total_size=//' + dcb -j buffer show dev $swp | jq '.total_size' } check_prio_pg() @@ -121,18 +122,18 @@ test_dcb_ets() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,2,4,6,1,3,5,7 > /dev/null + dcb ets set dev $swp prio-tc 0:0 1:2 2:4 3:6 4:1 5:3 6:5 7:7 check_prio_pg "0 2 4 6 1 3 5 7 " check_prio_tc "0 2 4 6 1 3 5 7 " check_prio_pfc "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb ets set dev $swp prio-tc all:0 check_prio_pg "0 0 0 0 0 0 0 0 " check_prio_tc "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 &> /dev/null + dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6 2>/dev/null check_fail $? "prio2buffer accepted in DCB mode" log_test "Configuring headroom through ETS" @@ -174,7 +175,7 @@ test_pfc() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,1,2,3 > /dev/null + dcb ets set dev $swp prio-tc all:0 5:1 6:2 7:3 local buf0size=$(get_buf_size 0) local buf1size=$(get_buf_size 1) @@ -193,7 +194,7 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=0 > /dev/null + dcb pfc set dev $swp prio-pfc all:off 5:on 6:on 7:on delay 0 check_prio_pg "0 0 0 0 0 1 2 3 " check_prio_pfc "0 0 0 0 0 1 1 1 " @@ -210,7 +211,7 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=1000 > /dev/null + dcb pfc set dev $swp delay 1000 check_buf_size 0 "== $buf0size" check_buf_size 1 "> $buf1size" @@ -221,8 +222,8 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,0,0,0 --cable_len=0 > /dev/null - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb pfc set dev $swp prio-pfc all:off delay 0 + dcb ets set dev $swp prio-tc all:0 check_prio_pg "0 0 0 0 0 0 0 0 " check_prio_tc "0 0 0 0 0 0 0 0 " @@ -242,13 +243,13 @@ test_tc_priomap() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,1,2,3,4,5,6,7 > /dev/null + dcb ets set dev $swp prio-tc 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 check_prio_pg "0 1 2 3 4 5 6 7 " tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M check_prio_pg "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 > /dev/null + dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6 check_prio_pg "1 3 5 7 0 2 4 6 " tc qdisc delete dev $swp root @@ -256,9 +257,9 @@ test_tc_priomap() # Clean up. tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M - __mlnx_qos -i $swp --prio2buffer=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp prio-buffer all:0 tc qdisc delete dev $swp root - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb ets set dev $swp prio-tc all:0 log_test "TC: priomap" } @@ -270,12 +271,12 @@ test_tc_sizes() RET=0 - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null check_fail $? "buffer_size should fail before qdisc is added" tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_err $? "buffer_size should pass after qdisc is added" check_buf_size 0 "== $size" "set size: " @@ -283,26 +284,26 @@ test_tc_sizes() check_buf_size 0 "== $size" "set MTU: " mtu_restore $swp - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 # After replacing the qdisc for the same kind, buffer_size still has to # work. tc qdisc replace dev $swp root handle 1: bfifo limit 1M - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_buf_size 0 "== $size" "post replace, set size: " - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 # Likewise after replacing for a different kind. tc qdisc replace dev $swp root handle 2: prio bands 8 - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_buf_size 0 "== $size" "post replace different kind, set size: " tc qdisc delete dev $swp root - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null check_fail $? "buffer_size should fail after qdisc is deleted" log_test "TC: buffer size" @@ -363,10 +364,10 @@ test_tc_int_buf() tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M test_int_buf "TC: " - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size test_int_buf "TC+buffsize: " - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 tc qdisc delete dev $swp root } diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index 0bf76f13c030..faa51012cdac 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -82,17 +82,3 @@ bail_on_lldpad() fi fi } - -__mlnx_qos() -{ - local err - - mlnx_qos "$@" 2>/dev/null - err=$? - - if ((err)); then - echo "Error ($err) in mlnx_qos $@" >/dev/stderr - fi - - return $err -} diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 5c7700212f75..5d5622fc2758 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -171,7 +171,7 @@ switch_create() # assignment. tc qdisc replace dev $swp1 root handle 1: \ ets bands 8 strict 8 priomap 7 6 - __mlnx_qos -i $swp1 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp1 prio-buffer all:0 1:1 # $swp2 # ----- @@ -209,8 +209,8 @@ switch_create() # the lossless prio into a buffer of its own. Don't bother with buffer # sizes though, there is not going to be any pressure in the "backward" # direction. - __mlnx_qos -i $swp3 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp3 --pfc=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp3 prio-buffer all:0 1:1 + dcb pfc set dev $swp3 prio-pfc all:off 1:on # $swp4 # ----- @@ -226,11 +226,11 @@ switch_create() # Configure qdisc so that we can hand-tune headroom. tc qdisc replace dev $swp4 root handle 1: \ ets bands 8 strict 8 priomap 7 6 - __mlnx_qos -i $swp4 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 prio-buffer all:0 1:1 + dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB # bridges # ------- @@ -273,9 +273,9 @@ switch_destroy() # $swp4 # ----- - __mlnx_qos -i $swp4 --buffer_size=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --pfc=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 buffer-size all:0 + dcb pfc set dev $swp4 prio-pfc all:off + dcb buffer set dev $swp4 prio-buffer all:0 tc qdisc del dev $swp4 root devlink_tc_bind_pool_th_restore $swp4 1 ingress @@ -288,8 +288,8 @@ switch_destroy() # $swp3 # ----- - __mlnx_qos -i $swp3 --pfc=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp3 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb pfc set dev $swp3 prio-pfc all:off + dcb buffer set dev $swp3 prio-buffer all:0 tc qdisc del dev $swp3 root devlink_tc_bind_pool_th_restore $swp3 1 egress @@ -315,7 +315,7 @@ switch_destroy() # $swp1 # ----- - __mlnx_qos -i $swp1 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp1 prio-buffer all:0 tc qdisc del dev $swp1 root devlink_tc_bind_pool_th_restore $swp1 1 ingress diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 093bed088ad0..373d5f2a846e 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -234,15 +234,15 @@ __tc_sample_rate_test() psample_capture_start - ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \ + ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \ -B $dip -t udp dp=52768,sp=42768 -q psample_capture_stop pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l) - pct=$((100 * (pkts - 100) / 100)) + pct=$((100 * (pkts - 10000) / 10000)) (( -25 <= pct && pct <= 25)) - check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" + check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" log_test "tc sample rate ($desc)" @@ -587,15 +587,15 @@ __tc_sample_acl_rate_test() psample_capture_start - ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \ + ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q psample_capture_stop pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l) - pct=$((100 * (pkts - 100) / 100)) + pct=$((100 * (pkts - 10000) / 10000)) (( -25 <= pct && pct <= 25)) - check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" + check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" # Setup a filter that should not match any packet and make sure packets # are not sampled. diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 834066d465fc..2b5d6ff87373 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -18,6 +18,8 @@ import sys # +# Kselftest framework requirement - SKIP code is 4 +KSFT_SKIP=4 Port = collections.namedtuple('Port', 'bus_info name') @@ -239,7 +241,11 @@ def main(cmdline=None): assert stderr == "" devs = json.loads(stdout)['dev'] - dev = list(devs.keys())[0] + if devs: + dev = list(devs.keys())[0] + else: + print("no devlink device was found, test skipped") + sys.exit(KSFT_SKIP) cmd = "devlink dev show %s" % dev stdout, stderr = run_command(cmd) diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh new file mode 100755 index 000000000000..a15d21dc035a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -0,0 +1,364 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution between two paths when using custom hash policy. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------------+ +# | SW1 | | +# | $rp1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# | | +# | $rp11 + + $rp12 | +# | 192.0.2.1/28 | | 192.0.2.17/28 | +# | 2001:db8:2::1/64 | | 2001:db8:3::1/64 | +# +------------------|-------------|------------------+ +# | | +# +------------------|-------------|------------------+ +# | SW2 | | | +# | | | | +# | $rp21 + + $rp22 | +# | 192.0.2.2/28 192.0.2.18/28 | +# | 2001:db8:2::2/64 2001:db8:3::2/64 | +# | | +# | | +# | $rp2 + | +# | 203.0.113.1/24 | | +# | 2001:db8:4::1/64 | | +# +-------------------------|-------------------------+ +# | +# +-------------------------|------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:4::{2-fd}/64 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=8 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $rp1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $rp11 v$rp1 192.0.2.1/28 2001:db8:2::1/64 + __simple_if_init $rp12 v$rp1 192.0.2.17/28 2001:db8:3::1/64 + + ip route add vrf v$rp1 203.0.113.0/24 \ + nexthop via 192.0.2.2 dev $rp11 \ + nexthop via 192.0.2.18 dev $rp12 + + ip -6 route add vrf v$rp1 2001:db8:4::/64 \ + nexthop via 2001:db8:2::2 dev $rp11 \ + nexthop via 2001:db8:3::2 dev $rp12 +} + +sw1_destroy() +{ + ip -6 route del vrf v$rp1 2001:db8:4::/64 + + ip route del vrf v$rp1 203.0.113.0/24 + + __simple_if_fini $rp12 192.0.2.17/28 2001:db8:3::1/64 + __simple_if_fini $rp11 192.0.2.1/28 2001:db8:2::1/64 + simple_if_fini $rp1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $rp2 203.0.113.1/24 2001:db8:4::1/64 + __simple_if_init $rp21 v$rp2 192.0.2.2/28 2001:db8:2::2/64 + __simple_if_init $rp22 v$rp2 192.0.2.18/28 2001:db8:3::2/64 + + ip route add vrf v$rp2 198.51.100.0/24 \ + nexthop via 192.0.2.1 dev $rp21 \ + nexthop via 192.0.2.17 dev $rp22 + + ip -6 route add vrf v$rp2 2001:db8:1::/64 \ + nexthop via 2001:db8:2::1 dev $rp21 \ + nexthop via 2001:db8:3::1 dev $rp22 +} + +sw2_destroy() +{ + ip -6 route del vrf v$rp2 2001:db8:1::/64 + + ip route del vrf v$rp2 198.51.100.0/24 + + __simple_if_fini $rp22 192.0.2.18/28 2001:db8:3::2/64 + __simple_if_fini $rp21 192.0.2.2/28 2001:db8:2::2/64 + simple_if_fini $rp2 203.0.113.1/24 2001:db8:4::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:4::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:4::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:4::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + rp1=${NETIFS[p2]} + + rp11=${NETIFS[p3]} + rp21=${NETIFS[p4]} + + rp12=${NETIFS[p5]} + rp22=${NETIFS[p6]} + + rp2=${NETIFS[p7]} + + h2=${NETIFS[p8]} + + vrf_prepare + h1_create + sw1_create + sw2_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:4::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_rp11=$(link_stats_tx_packets_get $rp11) + local t0_rp12=$(link_stats_tx_packets_get $rp12) + + $send_flows + + local t1_rp11=$(link_stats_tx_packets_get $rp11) + local t1_rp12=$(link_stats_tx_packets_get $rp12) + + local d_rp11=$((t1_rp11 - t0_rp11)) + local d_rp12=$((t1_rp12 - t0_rp12)) + + local diff=$((d_rp12 - d_rp11)) + local sum=$((d_rp11 + d_rp12)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d_rp11 / $d_rp12" +} + +custom_hash_v4() +{ + log_info "Running IPv4 custom multipath hash tests" + + sysctl_set net.ipv4.fib_multipath_hash_policy 3 + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0001 + custom_hash_test "Source IP" "balanced" send_src_ipv4 + custom_hash_test "Source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0002 + custom_hash_test "Destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0010 + custom_hash_test "Source port" "balanced" send_src_udp4 + custom_hash_test "Source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0020 + custom_hash_test "Destination port" "balanced" send_dst_udp4 + custom_hash_test "Destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 + + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +custom_hash_v6() +{ + log_info "Running IPv6 custom multipath hash tests" + + sysctl_set net.ipv6.fib_multipath_hash_policy 3 + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0001 + custom_hash_test "Source IP" "balanced" send_src_ipv6 + custom_hash_test "Source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0002 + custom_hash_test "Destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0008 + custom_hash_test "Flowlabel" "balanced" send_flowlabel + custom_hash_test "Flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0010 + custom_hash_test "Source port" "balanced" send_src_udp6 + custom_hash_test "Source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0020 + custom_hash_test "Destination port" "balanced" send_dst_udp6 + custom_hash_test "Destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 + + sysctl_restore net.ipv6.fib_multipath_hash_policy +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + custom_hash_v4 + custom_hash_v6 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh new file mode 100755 index 000000000000..a73f52efcb6c --- /dev/null +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -0,0 +1,456 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution when there are multiple paths between an IPv4 GRE +# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts. +# Multiple routes are in the underlay network. With the default multipath +# policy, SW2 will only look at the outer IP addresses, hence only a single +# route would be used. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# | + g1 (gre) | +# | loc=192.0.2.1 | +# | rem=192.0.2.2 --. | +# | tos=inherit | | +# | v | +# | + $ul1 | +# | | 192.0.2.17/28 | +# +---------------------|----------------------+ +# | +# +---------------------|----------------------+ +# | SW2 | | +# | $ul21 + | +# | 192.0.2.18/28 | | +# | | | +# ! __________________+___ | +# | / \ | +# | | | | +# | + $ul22.111 (vlan) + $ul22.222 (vlan) | +# | | 192.0.2.33/28 | 192.0.2.49/28 | +# | | | | +# +--|----------------------|------------------+ +# | | +# +--|----------------------|------------------+ +# | | | | +# | + $ul32.111 (vlan) + $ul32.222 (vlan) | +# | | 192.0.2.34/28 | 192.0.2.50/28 | +# | | | | +# | \__________________+___/ | +# | | | +# | | | +# | $ul31 + | +# | 192.0.2.65/28 | SW3 | +# +---------------------|----------------------+ +# | +# +---------------------|----------------------+ +# | + $ul4 | +# | ^ 192.0.2.66/28 | +# | | | +# | + g2 (gre) | | +# | loc=192.0.2.2 | | +# | rem=192.0.2.1 --' | +# | tos=inherit | +# | | +# | $ol4 + | +# | 203.0.113.1/24 | | +# | 2001:db8:2::1/64 | SW4 | +# +-------------------------|------------------+ +# | +# +-------------------------|------+ +# | | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:2::{2-fd}/64 H2 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=10 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $ul1 v$ol1 192.0.2.17/28 + + tunnel_create g1 gre 192.0.2.1 192.0.2.2 tos inherit dev v$ol1 + __simple_if_init g1 v$ol1 192.0.2.1/32 + ip route add vrf v$ol1 192.0.2.2/32 via 192.0.2.18 + + ip route add vrf v$ol1 203.0.113.0/24 dev g1 + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1 +} + +sw1_destroy() +{ + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + + ip route del vrf v$ol1 192.0.2.2/32 + __simple_if_fini g1 192.0.2.1/32 + tunnel_destroy g1 + + __simple_if_fini $ul1 192.0.2.17/28 + simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $ul21 192.0.2.18/28 + __simple_if_init $ul22 v$ul21 + vlan_create $ul22 111 v$ul21 192.0.2.33/28 + vlan_create $ul22 222 v$ul21 192.0.2.49/28 + + ip route add vrf v$ul21 192.0.2.1/32 via 192.0.2.17 + ip route add vrf v$ul21 192.0.2.2/32 \ + nexthop via 192.0.2.34 \ + nexthop via 192.0.2.50 +} + +sw2_destroy() +{ + ip route del vrf v$ul21 192.0.2.2/32 + ip route del vrf v$ul21 192.0.2.1/32 + + vlan_destroy $ul22 222 + vlan_destroy $ul22 111 + __simple_if_fini $ul22 + simple_if_fini $ul21 192.0.2.18/28 +} + +sw3_create() +{ + simple_if_init $ul31 192.0.2.65/28 + __simple_if_init $ul32 v$ul31 + vlan_create $ul32 111 v$ul31 192.0.2.34/28 + vlan_create $ul32 222 v$ul31 192.0.2.50/28 + + ip route add vrf v$ul31 192.0.2.2/32 via 192.0.2.66 + ip route add vrf v$ul31 192.0.2.1/32 \ + nexthop via 192.0.2.33 \ + nexthop via 192.0.2.49 + + tc qdisc add dev $ul32 clsact + tc filter add dev $ul32 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul32 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass +} + +sw3_destroy() +{ + tc qdisc del dev $ul32 clsact + + ip route del vrf v$ul31 192.0.2.1/32 + ip route del vrf v$ul31 192.0.2.2/32 + + vlan_destroy $ul32 222 + vlan_destroy $ul32 111 + __simple_if_fini $ul32 + simple_if_fini $ul31 192.0.2.65/28 +} + +sw4_create() +{ + simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64 + __simple_if_init $ul4 v$ol4 192.0.2.66/28 + + tunnel_create g2 gre 192.0.2.2 192.0.2.1 tos inherit dev v$ol4 + __simple_if_init g2 v$ol4 192.0.2.2/32 + ip route add vrf v$ol4 192.0.2.1/32 via 192.0.2.65 + + ip route add vrf v$ol4 198.51.100.0/24 dev g2 + ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2 +} + +sw4_destroy() +{ + ip -6 route del vrf v$ol4 2001:db8:1::/64 + ip route del vrf v$ol4 198.51.100.0/24 + + ip route del vrf v$ol4 192.0.2.1/32 + __simple_if_fini g2 192.0.2.2/32 + tunnel_destroy g2 + + __simple_if_fini $ul4 192.0.2.66/28 + simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + ol1=${NETIFS[p2]} + ul1=${NETIFS[p3]} + + ul21=${NETIFS[p4]} + ul22=${NETIFS[p5]} + + ul32=${NETIFS[p6]} + ul31=${NETIFS[p7]} + + ul4=${NETIFS[p8]} + ol4=${NETIFS[p9]} + + h2=${NETIFS[p10]} + + vrf_prepare + h1_create + sw1_create + sw2_create + sw3_create + sw4_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw4_destroy + sw3_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_111=$(tc_rule_stats_get $ul32 111 ingress) + local t0_222=$(tc_rule_stats_get $ul32 222 ingress) + + $send_flows + + local t1_111=$(tc_rule_stats_get $ul32 111 ingress) + local t1_222=$(tc_rule_stats_get $ul32 222 ingress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + + local diff=$((d222 - d111)) + local sum=$((d111 + d222)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d111 / $d222" +} + +custom_hash_v4() +{ + log_info "Running IPv4 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv4 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp4 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp4 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 +} + +custom_hash_v6() +{ + log_info "Running IPv6 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv6 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0200 + custom_hash_test "Inner flowlabel" "balanced" send_flowlabel + custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp6 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp6 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + + sysctl_set net.ipv4.fib_multipath_hash_policy 3 + + custom_hash_v4 + custom_hash_v6 + + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh new file mode 100755 index 000000000000..8fea2c2e0b25 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -0,0 +1,458 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution when there are multiple paths between an IPv6 GRE +# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts. +# Multiple routes are in the underlay network. With the default multipath +# policy, SW2 will only look at the outer IP addresses, hence only a single +# route would be used. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# |+ g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 -. | +# | tos=inherit | | +# | v | +# | + $ul1 | +# | | 2001:db8:10::1/64 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul21 + | +# | 2001:db8:10::2/64 | | +# | | | +# ! __________________+___ | +# | / \ | +# | | | | +# | + $ul22.111 (vlan) + $ul22.222 (vlan) | +# | | 2001:db8:11::1/64 | 2001:db8:12::1/64 | +# | | | | +# +--|----------------------|-------------------+ +# | | +# +--|----------------------|-------------------+ +# | | | | +# | + $ul32.111 (vlan) + $ul32.222 (vlan) | +# | | 2001:db8:11::2/64 | 2001:db8:12::2/64 | +# | | | | +# | \__________________+___/ | +# | | | +# | | | +# | $ul31 + | +# | 2001:db8:13::1/64 | SW3 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | + $ul4 | +# | ^ 2001:db8:13::2/64 | +# | | | +# |+ g2 (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 -' | +# | tos=inherit | +# | | +# | $ol4 + | +# | 203.0.113.1/24 | | +# | 2001:db8:2::1/64 | SW4 | +# +-------------------------|-------------------+ +# | +# +-------------------------|------+ +# | | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:2::{2-fd}/64 H2 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=10 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $ul1 v$ol1 2001:db8:10::1/64 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + dev v$ol1 + __simple_if_init g1 v$ol1 2001:db8:3::1/128 + ip route add vrf v$ol1 2001:db8:3::2/128 via 2001:db8:10::2 + + ip route add vrf v$ol1 203.0.113.0/24 dev g1 + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1 +} + +sw1_destroy() +{ + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + + ip route del vrf v$ol1 2001:db8:3::2/128 + __simple_if_fini g1 2001:db8:3::1/128 + tunnel_destroy g1 + + __simple_if_fini $ul1 2001:db8:10::1/64 + simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $ul21 2001:db8:10::2/64 + __simple_if_init $ul22 v$ul21 + vlan_create $ul22 111 v$ul21 2001:db8:11::1/64 + vlan_create $ul22 222 v$ul21 2001:db8:12::1/64 + + ip -6 route add vrf v$ul21 2001:db8:3::1/128 via 2001:db8:10::1 + ip -6 route add vrf v$ul21 2001:db8:3::2/128 \ + nexthop via 2001:db8:11::2 \ + nexthop via 2001:db8:12::2 +} + +sw2_destroy() +{ + ip -6 route del vrf v$ul21 2001:db8:3::2/128 + ip -6 route del vrf v$ul21 2001:db8:3::1/128 + + vlan_destroy $ul22 222 + vlan_destroy $ul22 111 + __simple_if_fini $ul22 + simple_if_fini $ul21 2001:db8:10::2/64 +} + +sw3_create() +{ + simple_if_init $ul31 2001:db8:13::1/64 + __simple_if_init $ul32 v$ul31 + vlan_create $ul32 111 v$ul31 2001:db8:11::2/64 + vlan_create $ul32 222 v$ul31 2001:db8:12::2/64 + + ip -6 route add vrf v$ul31 2001:db8:3::2/128 via 2001:db8:13::2 + ip -6 route add vrf v$ul31 2001:db8:3::1/128 \ + nexthop via 2001:db8:11::1 \ + nexthop via 2001:db8:12::1 + + tc qdisc add dev $ul32 clsact + tc filter add dev $ul32 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul32 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass +} + +sw3_destroy() +{ + tc qdisc del dev $ul32 clsact + + ip -6 route del vrf v$ul31 2001:db8:3::1/128 + ip -6 route del vrf v$ul31 2001:db8:3::2/128 + + vlan_destroy $ul32 222 + vlan_destroy $ul32 111 + __simple_if_fini $ul32 + simple_if_fini $ul31 2001:db8:13::1/64 +} + +sw4_create() +{ + simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64 + __simple_if_init $ul4 v$ol4 2001:db8:13::2/64 + + tunnel_create g2 ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + dev v$ol4 + __simple_if_init g2 v$ol4 2001:db8:3::2/128 + ip -6 route add vrf v$ol4 2001:db8:3::1/128 via 2001:db8:13::1 + + ip route add vrf v$ol4 198.51.100.0/24 dev g2 + ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2 +} + +sw4_destroy() +{ + ip -6 route del vrf v$ol4 2001:db8:1::/64 + ip route del vrf v$ol4 198.51.100.0/24 + + ip -6 route del vrf v$ol4 2001:db8:3::1/128 + __simple_if_fini g2 2001:db8:3::2/128 + tunnel_destroy g2 + + __simple_if_fini $ul4 2001:db8:13::2/64 + simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + ol1=${NETIFS[p2]} + ul1=${NETIFS[p3]} + + ul21=${NETIFS[p4]} + ul22=${NETIFS[p5]} + + ul32=${NETIFS[p6]} + ul31=${NETIFS[p7]} + + ul4=${NETIFS[p8]} + ol4=${NETIFS[p9]} + + h2=${NETIFS[p10]} + + vrf_prepare + h1_create + sw1_create + sw2_create + sw3_create + sw4_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw4_destroy + sw3_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_111=$(tc_rule_stats_get $ul32 111 ingress) + local t0_222=$(tc_rule_stats_get $ul32 222 ingress) + + $send_flows + + local t1_111=$(tc_rule_stats_get $ul32 111 ingress) + local t1_222=$(tc_rule_stats_get $ul32 222 ingress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + + local diff=$((d222 - d111)) + local sum=$((d111 + d222)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d111 / $d222" +} + +custom_hash_v4() +{ + log_info "Running IPv4 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv4 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp4 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp4 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 +} + +custom_hash_v6() +{ + log_info "Running IPv6 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv6 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0200 + custom_hash_test "Inner flowlabel" "balanced" send_flowlabel + custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp6 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp6 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + + sysctl_set net.ipv6.fib_multipath_hash_policy 3 + + custom_hash_v4 + custom_hash_v6 + + sysctl_restore net.ipv6.fib_multipath_hash_policy +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index dbf0421986df..66354cdd5ce4 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -189,6 +189,15 @@ segmenttest 255.255.255.1 255.255.255.254 24 "assign and ping inside 255.255.255 route_test 240.5.6.7 240.5.6.1 255.1.2.1 255.1.2.3 24 "route between 240.5.6/24 and 255.1.2/24 (is allowed)" route_test 0.200.6.7 0.200.38.1 245.99.101.1 245.99.200.111 16 "route between 0.200/16 and 245.99/16 (is allowed)" # +# Test support for lowest address ending in .0 +segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (/24)" +# +# Test support for lowest address not ending in .0 +segmenttest 192.168.101.192 192.168.101.193 26 "assign and ping lowest address (/26)" +# +# Routing using lowest address as a gateway/endpoint +route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address" +# # ============================================== # ==== TESTS THAT CURRENTLY EXPECT FAILURE ===== # ============================================== @@ -202,14 +211,6 @@ segmenttest 255.255.255.1 255.255.255.255 16 "assigning 255.255.255.255 (is forb # Currently Linux does not allow this, so this should fail too segmenttest 127.99.4.5 127.99.4.6 16 "assign and ping inside 127/8 (is forbidden)" # -# Test support for lowest address -# Currently Linux does not allow this, so this should fail too -segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (is forbidden)" -# -# Routing using lowest address as a gateway/endpoint -# Currently Linux does not allow this, so this should fail too -route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address (is forbidden)" -# # Test support for unicast use of class D # Currently Linux does not allow this, so this should fail too segmenttest 225.1.2.3 225.1.2.200 24 "assign and ping class D address (is forbidden)" |