diff options
Diffstat (limited to 'tools')
620 files changed, 27226 insertions, 5715 deletions
diff --git a/tools/arch/loongarch/include/uapi/asm/bitsperlong.h b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..d4e32b3d4843 --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_LOONGARCH_BITSPERLONG_H +#define __ASM_LOONGARCH_BITSPERLONG_H + +#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8) + +#include <asm-generic/bitsperlong.h> + +#endif /* __ASM_LOONGARCH_BITSPERLONG_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 60a89dba01b6..2712d5e03e2e 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -1,16 +1,25 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NR_perf_event_open -# define __NR_perf_event_open 336 +#ifndef __NR_execve +#define __NR_execve 11 #endif -#ifndef __NR_futex -# define __NR_futex 240 +#ifndef __NR_getppid +#define __NR_getppid 64 +#endif +#ifndef __NR_getpgid +#define __NR_getpgid 132 #endif #ifndef __NR_gettid -# define __NR_gettid 224 +#define __NR_gettid 224 +#endif +#ifndef __NR_futex +#define __NR_futex 240 #endif #ifndef __NR_getcpu -# define __NR_getcpu 318 +#define __NR_getcpu 318 +#endif +#ifndef __NR_perf_event_open +#define __NR_perf_event_open 336 #endif #ifndef __NR_setns -# define __NR_setns 346 +#define __NR_setns 346 #endif diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index cb52a3a8b8fc..a6f7fe84d4df 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -1,16 +1,25 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NR_perf_event_open -# define __NR_perf_event_open 298 +#ifndef __NR_execve +#define __NR_execve 59 #endif -#ifndef __NR_futex -# define __NR_futex 202 +#ifndef __NR_getppid +#define __NR_getppid 110 +#endif +#ifndef __NR_getpgid +#define __NR_getpgid 121 #endif #ifndef __NR_gettid -# define __NR_gettid 186 +#define __NR_gettid 186 #endif -#ifndef __NR_getcpu -# define __NR_getcpu 309 +#ifndef __NR_futex +#define __NR_futex 202 +#endif +#ifndef __NR_perf_event_open +#define __NR_perf_event_open 298 #endif #ifndef __NR_setns #define __NR_setns 308 #endif +#ifndef __NR_getcpu +#define __NR_getcpu 309 +#endif diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh index 6183b36c6846..1603801cf126 100755 --- a/tools/bootconfig/scripts/ftrace2bconf.sh +++ b/tools/bootconfig/scripts/ftrace2bconf.sh @@ -93,7 +93,7 @@ referred_vars() { } event_is_enabled() { # enable-file - test -f $1 & grep -q "1" $1 + test -f $1 && grep -q "1" $1 } per_event_options() { # event-dir diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index f610e184ce02..681fbcc5ed50 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -53,7 +53,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) $@ install_headers + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" $@ install_headers $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -215,7 +215,8 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ - -g -O2 -Wall -target bpf -c $< -o $@ + -g -O2 -Wall -fno-stack-protector \ + -target bpf -c $< -o $@ $(Q)$(LLVM_STRIP) -g $@ $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP) @@ -293,3 +294,6 @@ FORCE: .PHONY: all FORCE bootstrap clean install-bin install uninstall .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all + +# Delete partially updated (corrupted) files on error +.DELETE_ON_ERROR: diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 352290ba7b29..91fcb75babe3 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -537,7 +537,7 @@ static bool btf_is_kernel_module(__u32 btf_id) len = sizeof(btf_info); btf_info.name = ptr_to_u64(btf_name); btf_info.name_len = sizeof(btf_name); - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); close(btf_fd); if (err) { p_err("can't get BTF (ID %u) object info: %s", btf_id, strerror(errno)); @@ -606,7 +606,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) return -1; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info: %s", strerror(errno)); goto done; @@ -789,7 +789,10 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, } memset(info, 0, *len); - err = bpf_obj_get_info_by_fd(fd, info, len); + if (type == BPF_OBJ_PROG) + err = bpf_prog_get_info_by_fd(fd, info, len); + else + err = bpf_map_get_info_by_fd(fd, info, len); close(fd); if (err) { p_err("can't get %s info: %s", names[type], @@ -931,7 +934,7 @@ show_btf(int fd, struct hashmap *btf_prog_table, int err; memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get BTF object info: %s", strerror(errno)); return -1; @@ -943,7 +946,7 @@ show_btf(int fd, struct hashmap *btf_prog_table, info.name = ptr_to_u64(name); len = sizeof(info); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get BTF object info: %s", strerror(errno)); return -1; diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index eda71fdfe95a..e7f6ec3a8f35 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -57,7 +57,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, if (prog_fd < 0) goto print; - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (err) goto print; @@ -70,7 +70,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, info.func_info_rec_size = finfo_rec_size; info.func_info = ptr_to_u64(&finfo); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (err) goto print; diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index b46a998d8f8d..ac846b0805b4 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -82,7 +82,7 @@ static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) if (fd < 0) return; - err = bpf_obj_get_info_by_fd(fd, &btf_info, &btf_len); + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_len); if (err) goto out; @@ -108,7 +108,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, if (prog_fd < 0) return -1; - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { close(prog_fd); return -1; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 620032042576..5a73ccf14332 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -353,7 +353,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, info.func_info_rec_size = sizeof(finfo); info.func_info = ptr_to_u64(&finfo); - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) goto copy_name; prog_btf = btf__load_from_kernel_by_id(info.btf_id); @@ -488,7 +488,7 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, goto out_close; memset(&pinned_info, 0, sizeof(pinned_info)); - if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len)) + if (bpf_prog_get_info_by_fd(fd, &pinned_info, &len)) goto out_close; path = strdup(fpath); @@ -756,7 +756,7 @@ static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) goto err_close_fds; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info (%u): %s", id, strerror(errno)); @@ -916,7 +916,7 @@ static int map_fd_by_name(char *name, int **fds) goto err_close_fds; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info (%u): %s", id, strerror(errno)); @@ -1026,7 +1026,8 @@ exit_free: return fd; } -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len) { int err; int fd; @@ -1035,7 +1036,7 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) if (fd < 0) return -1; - err = bpf_obj_get_info_by_fd(fd, info, info_len); + err = bpf_map_get_info_by_fd(fd, info, info_len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 36cf0f1517c9..da16e6a27ccc 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -486,16 +486,16 @@ static void probe_kernel_image_config(const char *define_prefix) } } -end_parse: - if (file) - gzclose(file); - for (i = 0; i < ARRAY_SIZE(options); i++) { if (define_prefix && !options[i].macro_dump) continue; print_kernel_option(options[i].name, values[i], define_prefix); free(values[i]); } + +end_parse: + if (file) + gzclose(file); } static bool probe_bpf_syscall(const char *define_prefix) diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 6f4cfe01cad4..f985b79cca27 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -145,7 +145,7 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info) return prog_fd; memset(info, 0, sizeof(*info)); - err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + err = bpf_prog_get_info_by_fd(prog_fd, info, &len); if (err) p_err("can't get prog info: %s", strerror(errno)); close(prog_fd); @@ -327,7 +327,7 @@ static int do_show_link(int fd) memset(&info, 0, sizeof(info)); again: - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_link_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get link info: %s", strerror(errno)); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index a84224b6a604..0ef373cef4c7 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -168,7 +168,8 @@ int prog_parse_fd(int *argc, char ***argv); int prog_parse_fds(int *argc, char ***argv, int **fds); int map_parse_fd(int *argc, char ***argv); int map_parse_fds(int *argc, char ***argv, int **fds); -int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); +int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, + __u32 *info_len); struct bpf_prog_linfo; #if defined(HAVE_LLVM_SUPPORT) || defined(HAVE_LIBBFD_SUPPORT) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 88911d3aa2d9..aaeb8939e137 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -638,7 +638,7 @@ static int do_show_subset(int argc, char **argv) if (json_output && nb_fds > 1) jsonw_start_array(json_wtr); /* root array */ for (i = 0; i < nb_fds; i++) { - err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); @@ -708,7 +708,7 @@ static int do_show(int argc, char **argv) break; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -764,7 +764,7 @@ static int maps_have_btf(int *fds, int nb_fds) int err, i; for (i = 0; i < nb_fds; i++) { - err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + err = bpf_map_get_info_by_fd(fds[i], &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); return -1; @@ -925,7 +925,7 @@ static int do_dump(int argc, char **argv) if (wtr && nb_fds > 1) jsonw_start_array(wtr); /* root array */ for (i = 0; i < nb_fds; i++) { - if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + if (bpf_map_get_info_by_fd(fds[i], &info, &len)) { p_err("can't get map info: %s", strerror(errno)); break; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index cfc9fdc1e863..afbe3ec342c8 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -198,7 +198,7 @@ static void show_prog_maps(int fd, __u32 num_maps) info.nr_map_ids = num_maps; info.map_ids = ptr_to_u64(map_ids); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err || !info.nr_map_ids) return; @@ -231,7 +231,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) memset(&prog_info, 0, sizeof(prog_info)); prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) return NULL; @@ -248,7 +248,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) prog_info.map_ids = ptr_to_u64(map_ids); prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) goto free_map_ids; @@ -259,7 +259,7 @@ static void *find_metadata(int prog_fd, struct bpf_map_info *map_info) memset(map_info, 0, sizeof(*map_info)); map_info_len = sizeof(*map_info); - ret = bpf_obj_get_info_by_fd(map_fd, map_info, &map_info_len); + ret = bpf_map_get_info_by_fd(map_fd, map_info, &map_info_len); if (ret < 0) { close(map_fd); goto free_map_ids; @@ -580,7 +580,7 @@ static int show_prog(int fd) __u32 len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_prog_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info: %s", strerror(errno)); return -1; @@ -949,7 +949,7 @@ static int do_dump(int argc, char **argv) for (i = 0; i < nb_fds; i++) { memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); if (err) { p_err("can't get prog info: %s", strerror(errno)); break; @@ -961,7 +961,7 @@ static int do_dump(int argc, char **argv) break; } - err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len); + err = bpf_prog_get_info_by_fd(fds[i], &info, &info_len); if (err) { p_err("can't get prog info: %s", strerror(errno)); break; @@ -2170,9 +2170,9 @@ static char *profile_target_name(int tgt_fd) char *name = NULL; int err; - err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); if (err) { - p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd); + p_err("failed to get info for prog FD %d", tgt_fd); goto out; } @@ -2183,7 +2183,7 @@ static char *profile_target_name(int tgt_fd) func_info_rec_size = info.func_info_rec_size; if (info.nr_func_info == 0) { - p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd); + p_err("found 0 func_info for prog FD %d", tgt_fd); goto out; } @@ -2192,7 +2192,7 @@ static char *profile_target_name(int tgt_fd) info.func_info_rec_size = func_info_rec_size; info.func_info = ptr_to_u64(&func_info); - err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(tgt_fd, &info, &info_len); if (err) { p_err("failed to get func_info for prog FD %d", tgt_fd); goto out; @@ -2233,10 +2233,38 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); @@ -2255,17 +2283,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 903b80ff4e9a..b389f4830e11 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -151,7 +151,7 @@ static int get_next_struct_ops_map(const char *name, int *res_fd, return -1; } - err = bpf_obj_get_info_by_fd(fd, info, &info_len); + err = bpf_map_get_info_by_fd(fd, info, &info_len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); @@ -262,7 +262,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, goto done; } - if (bpf_obj_get_info_by_fd(fd, info, &info_len)) { + if (bpf_map_get_info_by_fd(fd, info, &info_len)) { p_err("can't get map info: %s", strerror(errno)); res.nr_errs++; goto done; @@ -522,7 +522,7 @@ static int do_register(int argc, char **argv) bpf_link__disconnect(link); bpf_link__destroy(link); - if (!bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, + if (!bpf_map_get_info_by_fd(bpf_map__fd(map), &info, &info_len)) p_info("Registered %s %s id %u", get_kern_struct_ops_name(&info), diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build index ae82da03f9bf..077de3829c72 100644 --- a/tools/bpf/resolve_btfids/Build +++ b/tools/bpf/resolve_btfids/Build @@ -1,3 +1,5 @@ +hostprogs := resolve_btfids + resolve_btfids-y += main.o resolve_btfids-y += rbtree.o resolve_btfids-y += zalloc.o @@ -7,4 +9,4 @@ resolve_btfids-y += str_error_r.o $(OUTPUT)%.o: ../../lib/%.c FORCE $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) + $(call if_changed_dep,host_cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 19a3112e271a..ac548a7baa73 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -17,15 +17,15 @@ else MAKEFLAGS=--no-print-directory endif -# always use the host compiler -AR = $(HOSTAR) -CC = $(HOSTCC) -LD = $(HOSTLD) -ARCH = $(HOSTARCH) +# Overrides for the prepare step libraries. +HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ + CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" + RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar CROSS_COMPILE = -CFLAGS := $(KBUILD_HOSTCFLAGS) -LDFLAGS := $(KBUILD_HOSTLDFLAGS) OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -35,51 +35,64 @@ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ BPFOBJ := $(OUTPUT)/libbpf/libbpf.a LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a +SUBCMD_OUT := $(abspath $(dir $(SUBCMDOBJ)))/ LIBBPF_DESTDIR := $(LIBBPF_OUT) LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include +SUBCMD_DESTDIR := $(SUBCMD_OUT) +SUBCMD_INCLUDE := $(SUBCMD_DESTDIR)include + BINARY := $(OUTPUT)/resolve_btfids BINARY_IN := $(BINARY)-in.o all: $(BINARY) +prepare: $(BPFOBJ) $(SUBCMDOBJ) + $(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT): $(call msg,MKDIR,,$@) $(Q)mkdir -p $(@) $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd - $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(SUBCMD_OUT) \ + DESTDIR=$(SUBCMD_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ + $(abspath $@) install_headers $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ + DESTDIR=$(LIBBPF_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ $(abspath $@) install_headers -CFLAGS += -g \ +LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) + +HOSTCFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ - -I$(SUBCMD_SRC) + -I$(SUBCMD_INCLUDE) \ + $(LIBELF_FLAGS) -LIBS = -lelf -lz +LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT CFLAGS Q +export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include -$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT) +$(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) - $(Q)$(CC) $(BINARY_IN) $(LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) + $(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) clean_objects := $(wildcard $(OUTPUT)/*.o \ $(OUTPUT)/.*.o.cmd \ $(OUTPUT)/.*.o.d \ $(LIBBPF_OUT) \ $(LIBBPF_DESTDIR) \ - $(OUTPUT)/libsubcmd \ + $(SUBCMD_OUT) \ + $(SUBCMD_DESTDIR) \ $(OUTPUT)/resolve_btfids) ifneq ($(clean_objects),) @@ -96,4 +109,4 @@ tags: FORCE: -.PHONY: all FORCE clean tags +.PHONY: all FORCE clean tags prepare diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 80cd7843c677..77058174082d 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -75,7 +75,7 @@ #include <linux/err.h> #include <bpf/btf.h> #include <bpf/libbpf.h> -#include <parse-options.h> +#include <subcmd/parse-options.h> #define BTF_IDS_SECTION ".BTF_ids" #define BTF_ID "__BTF_ID__" diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 8b3d87b82b7a..47acf6936516 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -13,6 +13,8 @@ BPF_DESTDIR := $(BPFOBJ_OUTPUT) BPF_INCLUDE := $(BPF_DESTDIR)/include INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) +CFLAGS += $(EXTRA_CFLAGS) +LDFLAGS += $(EXTRA_LDFLAGS) # Try to detect best kernel BTF source KERNEL_REL := $(shell uname -r) diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 715092fc6a23..89430338a3d9 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -53,6 +53,7 @@ build-file := $(dir)/Build quiet_cmd_flex = FLEX $@ quiet_cmd_bison = BISON $@ +quiet_cmd_test = TEST $@ # Create directory unless it exists quiet_cmd_mkdir = MKDIR $(dir $@) diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py index 706ab27666a4..e81c3017ada9 100644 --- a/tools/cgroup/memcg_shrinker.py +++ b/tools/cgroup/memcg_shrinker.py @@ -5,7 +5,6 @@ import os import argparse -import sys def scan_cgroups(cgroup_root): @@ -44,7 +43,7 @@ def main(): cgroups = scan_cgroups("/sys/fs/cgroup/") shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/") - shrinkers = sorted(shrinkers, reverse = True, key = lambda x: x[0]) + shrinkers.sort(reverse = True, key = lambda x: x[0]) n = 0 for s in shrinkers: diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 8d35893b2fa8..6a00a6eecaef 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -264,6 +264,7 @@ int iioutils_get_param_float(float *output, const char *param_name, if (fscanf(sysfsfp, "%f", output) != 1) ret = errno ? -errno : -ENODATA; + fclose(sysfsfp); break; } error_free_filename: @@ -345,9 +346,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); goto error_close_dir; } @@ -357,7 +358,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_close_dir; } if (ret == 1) @@ -365,11 +365,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_close_dir; } - free(filename); } *ci_array = malloc(sizeof(**ci_array) * (*counter)); @@ -395,9 +393,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } @@ -405,20 +403,17 @@ int build_channel_array(const char *device_dir, int buffer_idx, errno = 0; if (fscanf(sysfsfp, "%i", ¤t_enabled) != 1) { ret = errno ? -errno : -ENODATA; - free(filename); count--; goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } if (!current_enabled) { - free(filename); count--; continue; } @@ -429,7 +424,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, strlen(ent->d_name) - strlen("_en")); if (!current->name) { - free(filename); ret = -ENOMEM; count--; goto error_cleanup_array; @@ -439,7 +433,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, ret = iioutils_break_up_name(current->name, ¤t->generic_name); if (ret) { - free(filename); free(current->name); count--; goto error_cleanup_array; @@ -450,17 +443,16 @@ int build_channel_array(const char *device_dir, int buffer_idx, scan_el_dir, current->name); if (ret < 0) { - free(filename); ret = -ENOMEM; goto error_cleanup_array; } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - fprintf(stderr, "failed to open %s\n", - filename); - free(filename); + fprintf(stderr, "failed to open %s/%s_index\n", + scan_el_dir, current->name); goto error_cleanup_array; } @@ -470,17 +462,14 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_cleanup_array; } - free(filename); /* Find the scale */ ret = iioutils_get_param_float(¤t->scale, "scale", diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h index f68baf8f395f..383baddef701 100644 --- a/tools/include/nolibc/arch-aarch64.h +++ b/tools/include/nolibc/arch-aarch64.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_AARCH64_H #define _NOLIBC_ARCH_AARCH64_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - /* The struct returned by the newfstatat() syscall. Differs slightly from the * x86_64's stat one by field ordering, so be careful. */ @@ -181,19 +169,31 @@ struct sys_stat_struct { _arg1; \ }) -/* startup code */ -__asm__ (".section .text\n" - ".weak _start\n" - "_start:\n" - "ldr x0, [sp]\n" // argc (x0) was in the stack - "add x1, sp, 8\n" // argv (x1) = sp - "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... - "add x2, x2, 8\n" // + 8 (skip null) - "add x2, x2, x1\n" // + argv - "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee - "bl main\n" // main() returns the status code, we'll exit with it. - "mov x8, 93\n" // NR_exit == 93 - "svc #0\n" - ""); +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); +/* startup code */ +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + "ldr x0, [sp]\n" // argc (x0) was in the stack + "add x1, sp, 8\n" // argv (x1) = sp + "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... + "add x2, x2, 8\n" // + 8 (skip null) + "add x2, x2, x1\n" // + argv + "adrp x3, environ\n" // x3 = &environ (high bits) + "str x2, [x3, #:lo12:environ]\n" // store envp into environ + "mov x4, x2\n" // search for auxv (follows NULL after last env) + "0:\n" + "ldr x5, [x4], 8\n" // x5 = *x4; x4 += 8 + "cbnz x5, 0b\n" // and stop at NULL after last env + "adrp x3, _auxv\n" // x3 = &_auxv (high bits) + "str x4, [x3, #:lo12:_auxv]\n" // store x4 into _auxv + "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee + "bl main\n" // main() returns the status code, we'll exit with it. + "mov x8, 93\n" // NR_exit == 93 + "svc #0\n" + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_AARCH64_H diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h index f31be8e967d6..42499f23e73c 100644 --- a/tools/include/nolibc/arch-arm.h +++ b/tools/include/nolibc/arch-arm.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_ARM_H #define _NOLIBC_ARCH_ARM_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). In big endian, the format * differs as devices are returned as short only. @@ -70,20 +58,44 @@ struct sys_stat_struct { * don't have to experience issues with register constraints. * - the syscall number is always specified last in order to allow to force * some registers before (gcc refuses a %-register at the last position). + * - in thumb mode without -fomit-frame-pointer, r7 is also used to store the + * frame pointer, and we cannot directly assign it as a register variable, + * nor can we clobber it. Instead we assign the r6 register and swap it + * with r7 before calling svc, and r6 is marked as clobbered. + * We're just using any regular register which we assign to r7 after saving + * it. * * Also, ARM supports the old_select syscall if newselect is not available */ #define __ARCH_WANT_SYS_OLD_SELECT +#if (defined(__THUMBEB__) || defined(__THUMBEL__)) && \ + !defined(NOLIBC_OMIT_FRAME_POINTER) +/* swap r6,r7 needed in Thumb mode since we can't use nor clobber r7 */ +#define _NOLIBC_SYSCALL_REG "r6" +#define _NOLIBC_THUMB_SET_R7 "eor r7, r6\neor r6, r7\neor r7, r6\n" +#define _NOLIBC_THUMB_RESTORE_R7 "mov r7, r6\n" + +#else /* we're in ARM mode */ +/* in Arm mode we can directly use r7 */ +#define _NOLIBC_SYSCALL_REG "r7" +#define _NOLIBC_THUMB_SET_R7 "" +#define _NOLIBC_THUMB_RESTORE_R7 "" + +#endif /* end THUMB */ + #define my_syscall0(num) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0"); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_num) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r"(_num) \ + : "r"(_arg1), \ + "r"(_num) \ : "memory", "cc", "lr" \ ); \ _arg1; \ @@ -91,12 +103,14 @@ struct sys_stat_struct { #define my_syscall1(num, arg1) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r"(_arg1) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ : "r"(_arg1), \ "r"(_num) \ : "memory", "cc", "lr" \ @@ -106,13 +120,15 @@ struct sys_stat_struct { #define my_syscall2(num, arg1, arg2) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r"(_arg1) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ : "r"(_arg1), "r"(_arg2), \ "r"(_num) \ : "memory", "cc", "lr" \ @@ -122,14 +138,16 @@ struct sys_stat_struct { #define my_syscall3(num, arg1, arg2, arg3) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ register long _arg3 __asm__ ("r2") = (long)(arg3); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r"(_arg1) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ "r"(_num) \ : "memory", "cc", "lr" \ @@ -139,15 +157,17 @@ struct sys_stat_struct { #define my_syscall4(num, arg1, arg2, arg3, arg4) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ register long _arg3 __asm__ ("r2") = (long)(arg3); \ register long _arg4 __asm__ ("r3") = (long)(arg4); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r"(_arg1) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ "r"(_num) \ : "memory", "cc", "lr" \ @@ -157,7 +177,7 @@ struct sys_stat_struct { #define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ ({ \ - register long _num __asm__ ("r7") = (num); \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ register long _arg1 __asm__ ("r0") = (long)(arg1); \ register long _arg2 __asm__ ("r1") = (long)(arg2); \ register long _arg3 __asm__ ("r2") = (long)(arg3); \ @@ -165,8 +185,10 @@ struct sys_stat_struct { register long _arg5 __asm__ ("r4") = (long)(arg5); \ \ __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ "svc #0\n" \ - : "=r" (_arg1) \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ "r"(_num) \ : "memory", "cc", "lr" \ @@ -174,31 +196,47 @@ struct sys_stat_struct { _arg1; \ }) +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + /* startup code */ -__asm__ (".section .text\n" - ".weak _start\n" - "_start:\n" -#if defined(__THUMBEB__) || defined(__THUMBEL__) - /* We enter here in 32-bit mode but if some previous functions were in - * 16-bit mode, the assembler cannot know, so we need to tell it we're in - * 32-bit now, then switch to 16-bit (is there a better way to do it than - * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that - * it generates correct instructions. Note that we do not support thumb1. - */ - ".code 32\n" - "add r0, pc, #1\n" - "bx r0\n" - ".code 16\n" -#endif - "pop {%r0}\n" // argc was in the stack - "mov %r1, %sp\n" // argv = sp - "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... - "add %r2, %r2, $4\n" // ... + 4 - "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the - "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) - "bl main\n" // main() returns the status code, we'll exit with it. - "movs r7, $1\n" // NR_exit == 1 - "svc $0x00\n" - ""); +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + "pop {%r0}\n" // argc was in the stack + "mov %r1, %sp\n" // argv = sp + + "add %r2, %r0, $1\n" // envp = (argc + 1) ... + "lsl %r2, %r2, $2\n" // * 4 ... + "add %r2, %r2, %r1\n" // + argv + "ldr %r3, 1f\n" // r3 = &environ (see below) + "str %r2, [r3]\n" // store envp into environ + + "mov r4, r2\n" // search for auxv (follows NULL after last env) + "0:\n" + "mov r5, r4\n" // r5 = r4 + "add r4, r4, #4\n" // r4 += 4 + "ldr r5,[r5]\n" // r5 = *r5 = *(r4-4) + "cmp r5, #0\n" // and stop at NULL after last env + "bne 0b\n" + "ldr %r3, 2f\n" // r3 = &_auxv (low bits) + "str r4, [r3]\n" // store r4 into _auxv + + "mov %r3, $8\n" // AAPCS : sp must be 8-byte aligned in the + "neg %r3, %r3\n" // callee, and bl doesn't push (lr=pc) + "and %r3, %r3, %r1\n" // so we do sp = r1(=sp) & r3(=-8); + "mov %sp, %r3\n" // + + "bl main\n" // main() returns the status code, we'll exit with it. + "movs r7, $1\n" // NR_exit == 1 + "svc $0x00\n" + ".align 2\n" // below are the pointers to a few variables + "1:\n" + ".word environ\n" + "2:\n" + ".word _auxv\n" + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_ARM_H diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index d7e7212346e2..e8d0cf545bf1 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_I386_H #define _NOLIBC_ARCH_I386_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). */ @@ -190,6 +178,9 @@ struct sys_stat_struct { _eax; \ }) +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + /* startup code */ /* * i386 System V ABI mandates: @@ -197,23 +188,32 @@ struct sys_stat_struct { * 2) The deepest stack frame should be set to zero * */ -__asm__ (".section .text\n" - ".weak _start\n" - "_start:\n" - "pop %eax\n" // argc (first arg, %eax) - "mov %esp, %ebx\n" // argv[] (second arg, %ebx) - "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before - "sub $4, %esp\n" // the call instruction (args are aligned) - "push %ecx\n" // push all registers on the stack so that we - "push %ebx\n" // support both regparm and plain stack modes - "push %eax\n" - "call main\n" // main() returns the status code in %eax - "mov %eax, %ebx\n" // retrieve exit code (32-bit int) - "movl $1, %eax\n" // NR_exit == 1 - "int $0x80\n" // exit now - "hlt\n" // ensure it does not - ""); +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + "pop %eax\n" // argc (first arg, %eax) + "mov %esp, %ebx\n" // argv[] (second arg, %ebx) + "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) + "mov %ecx, environ\n" // save environ + "xor %ebp, %ebp\n" // zero the stack frame + "mov %ecx, %edx\n" // search for auxv (follows NULL after last env) + "0:\n" + "add $4, %edx\n" // search for auxv using edx, it follows the + "cmp -4(%edx), %ebp\n" // ... NULL after last env (ebp is zero here) + "jnz 0b\n" + "mov %edx, _auxv\n" // save it into _auxv + "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before + "sub $4, %esp\n" // the call instruction (args are aligned) + "push %ecx\n" // push all registers on the stack so that we + "push %ebx\n" // support both regparm and plain stack modes + "push %eax\n" + "call main\n" // main() returns the status code in %eax + "mov %eax, %ebx\n" // retrieve exit code (32-bit int) + "movl $1, %eax\n" // NR_exit == 1 + "int $0x80\n" // exit now + "hlt\n" // ensure it does not + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_I386_H diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 7380093ba9e7..bf83432d23ed 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_MIPS_H #define _NOLIBC_ARCH_MIPS_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_APPEND 0x0008 -#define O_NONBLOCK 0x0080 -#define O_CREAT 0x0100 -#define O_TRUNC 0x0200 -#define O_EXCL 0x0400 -#define O_NOCTTY 0x0800 -#define O_DIRECTORY 0x10000 - /* The struct returned by the stat() syscall. 88 bytes are returned by the * syscall. */ @@ -188,30 +176,49 @@ struct sys_stat_struct { _arg4 ? -_num : _num; \ }) +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + /* startup code, note that it's called __start on MIPS */ -__asm__ (".section .text\n" - ".weak __start\n" - ".set nomips16\n" - ".set push\n" - ".set noreorder\n" - ".option pic0\n" - ".ent __start\n" - "__start:\n" - "lw $a0,($sp)\n" // argc was in the stack - "addiu $a1, $sp, 4\n" // argv = sp + 4 - "sll $a2, $a0, 2\n" // a2 = argc * 4 - "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... - "addiu $a2, $a2, 4\n" // ... + 4 - "li $t0, -8\n" - "and $sp, $sp, $t0\n" // sp must be 8-byte aligned - "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! - "jal main\n" // main() returns the status code, we'll exit with it. - "nop\n" // delayed slot - "move $a0, $v0\n" // retrieve 32-bit exit code from v0 - "li $v0, 4001\n" // NR_exit == 4001 - "syscall\n" - ".end __start\n" - ".set pop\n" - ""); +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __start(void) +{ + __asm__ volatile ( + //".set nomips16\n" + ".set push\n" + ".set noreorder\n" + ".option pic0\n" + //".ent __start\n" + //"__start:\n" + "lw $a0,($sp)\n" // argc was in the stack + "addiu $a1, $sp, 4\n" // argv = sp + 4 + "sll $a2, $a0, 2\n" // a2 = argc * 4 + "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... + "addiu $a2, $a2, 4\n" // ... + 4 + "lui $a3, %hi(environ)\n" // load environ into a3 (hi) + "addiu $a3, %lo(environ)\n" // load environ into a3 (lo) + "sw $a2,($a3)\n" // store envp(a2) into environ + + "move $t0, $a2\n" // iterate t0 over envp, look for NULL + "0:" // do { + "lw $a3, ($t0)\n" // a3=*(t0); + "bne $a3, $0, 0b\n" // } while (a3); + "addiu $t0, $t0, 4\n" // delayed slot: t0+=4; + "lui $a3, %hi(_auxv)\n" // load _auxv into a3 (hi) + "addiu $a3, %lo(_auxv)\n" // load _auxv into a3 (lo) + "sw $t0, ($a3)\n" // store t0 into _auxv + + "li $t0, -8\n" + "and $sp, $sp, $t0\n" // sp must be 8-byte aligned + "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! + "jal main\n" // main() returns the status code, we'll exit with it. + "nop\n" // delayed slot + "move $a0, $v0\n" // retrieve 32-bit exit code from v0 + "li $v0, 4001\n" // NR_exit == 4001 + "syscall\n" + //".end __start\n" + ".set pop\n" + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_MIPS_H diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index a3bdd9803f8c..e197fcb10ac0 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_RISCV_H #define _NOLIBC_ARCH_RISCV_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - struct sys_stat_struct { unsigned long st_dev; /* Device. */ unsigned long st_ino; /* File serial number. */ @@ -182,23 +170,39 @@ struct sys_stat_struct { _arg1; \ }) +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + /* startup code */ -__asm__ (".section .text\n" - ".weak _start\n" - "_start:\n" - ".option push\n" - ".option norelax\n" - "lla gp, __global_pointer$\n" - ".option pop\n" - "lw a0, 0(sp)\n" // argc (a0) was in the stack - "add a1, sp, "SZREG"\n" // argv (a1) = sp - "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... - "add a2, a2, "SZREG"\n" // + SZREG (skip null) - "add a2,a2,a1\n" // + argv - "andi sp,a1,-16\n" // sp must be 16-byte aligned - "call main\n" // main() returns the status code, we'll exit with it. - "li a7, 93\n" // NR_exit == 93 - "ecall\n" - ""); +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + ".option push\n" + ".option norelax\n" + "lla gp, __global_pointer$\n" + ".option pop\n" + "lw a0, 0(sp)\n" // argc (a0) was in the stack + "add a1, sp, "SZREG"\n" // argv (a1) = sp + "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... + "add a2, a2, "SZREG"\n" // + SZREG (skip null) + "add a2,a2,a1\n" // + argv + + "add a3, a2, zero\n" // iterate a3 over envp to find auxv (after NULL) + "0:\n" // do { + "ld a4, 0(a3)\n" // a4 = *a3; + "add a3, a3, "SZREG"\n" // a3 += sizeof(void*); + "bne a4, zero, 0b\n" // } while (a4); + "lui a4, %hi(_auxv)\n" // a4 = &_auxv (high bits) + "sd a3, %lo(_auxv)(a4)\n" // store a3 into _auxv + + "lui a3, %hi(environ)\n" // a3 = &environ (high bits) + "sd a2,%lo(environ)(a3)\n" // store envp(a2) into environ + "andi sp,a1,-16\n" // sp must be 16-byte aligned + "call main\n" // main() returns the status code, we'll exit with it. + "li a7, 93\n" // NR_exit == 93 + "ecall\n" + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_RISCV_H diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h new file mode 100644 index 000000000000..6b0e54ed543d --- /dev/null +++ b/tools/include/nolibc/arch-s390.h @@ -0,0 +1,226 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * s390 specific definitions for NOLIBC + */ + +#ifndef _NOLIBC_ARCH_S390_H +#define _NOLIBC_ARCH_S390_H +#include <asm/unistd.h> + +/* The struct returned by the stat() syscall, equivalent to stat64(). The + * syscall returns 116 bytes and stops in the middle of __unused. + */ + +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned long st_nlink; + unsigned int st_mode; + unsigned int st_uid; + unsigned int st_gid; + unsigned int __pad1; + unsigned long st_rdev; + unsigned long st_size; + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long st_blksize; + long st_blocks; + unsigned long __unused[3]; +}; + +/* Syscalls for s390: + * - registers are 64-bit + * - syscall number is passed in r1 + * - arguments are in r2-r7 + * - the system call is performed by calling the svc instruction + * - syscall return value is in r2 + * - r1 and r2 are clobbered, others are preserved. + * + * Link s390 ABI: https://github.com/IBM/s390x-abi + * + */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _rc __asm__ ("2"); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "=d"(_rc) \ + : "d"(_num) \ + : "memory", "cc" \ + ); \ + _rc; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + register long _arg2 __asm__ ("3") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_arg2), "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + register long _arg2 __asm__ ("3") = (long)(arg2); \ + register long _arg3 __asm__ ("4") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_arg2), "d"(_arg3), "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + register long _arg2 __asm__ ("3") = (long)(arg2); \ + register long _arg3 __asm__ ("4") = (long)(arg3); \ + register long _arg4 __asm__ ("5") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + register long _arg2 __asm__ ("3") = (long)(arg2); \ + register long _arg3 __asm__ ("4") = (long)(arg3); \ + register long _arg4 __asm__ ("5") = (long)(arg4); \ + register long _arg5 __asm__ ("6") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \ + "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("1") = (num); \ + register long _arg1 __asm__ ("2") = (long)(arg1); \ + register long _arg2 __asm__ ("3") = (long)(arg2); \ + register long _arg3 __asm__ ("4") = (long)(arg3); \ + register long _arg4 __asm__ ("5") = (long)(arg4); \ + register long _arg5 __asm__ ("6") = (long)(arg5); \ + register long _arg6 __asm__ ("7") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "svc 0\n" \ + : "+d"(_arg1) \ + : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \ + "d"(_arg6), "d"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + +/* startup code */ +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + "lg %r2,0(%r15)\n" /* argument count */ + "la %r3,8(%r15)\n" /* argument pointers */ + + "xgr %r0,%r0\n" /* r0 will be our NULL value */ + /* search for envp */ + "lgr %r4,%r3\n" /* start at argv */ + "0:\n" + "clg %r0,0(%r4)\n" /* entry zero? */ + "la %r4,8(%r4)\n" /* advance pointer */ + "jnz 0b\n" /* no -> test next pointer */ + /* yes -> r4 now contains start of envp */ + "larl %r1,environ\n" + "stg %r4,0(%r1)\n" + + /* search for auxv */ + "lgr %r5,%r4\n" /* start at envp */ + "1:\n" + "clg %r0,0(%r5)\n" /* entry zero? */ + "la %r5,8(%r5)\n" /* advance pointer */ + "jnz 1b\n" /* no -> test next pointer */ + "larl %r1,_auxv\n" /* yes -> store value in _auxv */ + "stg %r5,0(%r1)\n" + + "aghi %r15,-160\n" /* allocate new stackframe */ + "xc 0(8,%r15),0(%r15)\n" /* clear backchain */ + "brasl %r14,main\n" /* ret value of main is arg to exit */ + "lghi %r1,1\n" /* __NR_exit */ + "svc 0\n" + ); + __builtin_unreachable(); +} + +struct s390_mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +static __attribute__((unused)) +void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, + off_t offset) +{ + struct s390_mmap_arg_struct args = { + .addr = (unsigned long)addr, + .len = (unsigned long)length, + .prot = prot, + .flags = flags, + .fd = fd, + .offset = (unsigned long)offset + }; + + return (void *)my_syscall1(__NR_mmap, &args); +} +#define sys_mmap sys_mmap +#endif // _NOLIBC_ARCH_S390_H diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index 0e1e9eb8545d..17f6751208e7 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -7,18 +7,6 @@ #ifndef _NOLIBC_ARCH_X86_64_H #define _NOLIBC_ARCH_X86_64_H -/* O_* macros for fcntl/open are architecture-specific */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - /* The struct returned by the stat() syscall, equivalent to stat64(). The * syscall returns 116 bytes and stops in the middle of __unused. */ @@ -190,6 +178,9 @@ struct sys_stat_struct { _ret; \ }) +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + /* startup code */ /* * x86-64 System V ABI mandates: @@ -197,19 +188,28 @@ struct sys_stat_struct { * 2) The deepest stack frame should be zero (the %rbp). * */ -__asm__ (".section .text\n" - ".weak _start\n" - "_start:\n" - "pop %rdi\n" // argc (first arg, %rdi) - "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) - "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call - "call main\n" // main() returns the status code, we'll exit with it. - "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %eax\n" // NR_exit == 60 - "syscall\n" // really exit - "hlt\n" // ensure it does not return - ""); +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + "pop %rdi\n" // argc (first arg, %rdi) + "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) + "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) + "mov %rdx, environ\n" // save environ + "xor %ebp, %ebp\n" // zero the stack frame + "mov %rdx, %rax\n" // search for auxv (follows NULL after last env) + "0:\n" + "add $8, %rax\n" // search for auxv using rax, it follows the + "cmp -8(%rax), %rbp\n" // ... NULL after last env (rbp is zero here) + "jnz 0b\n" + "mov %rax, _auxv\n" // save it into _auxv + "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call + "call main\n" // main() returns the status code, we'll exit with it. + "mov %eax, %edi\n" // retrieve exit code (32 bit) + "mov $60, %eax\n" // NR_exit == 60 + "syscall\n" // really exit + "hlt\n" // ensure it does not return + ); + __builtin_unreachable(); +} #endif // _NOLIBC_ARCH_X86_64_H diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 4c6992321b0d..78b067a4fa47 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -27,6 +27,8 @@ #include "arch-mips.h" #elif defined(__riscv) #include "arch-riscv.h" +#elif defined(__s390x__) +#include "arch-s390.h" #endif #endif /* _NOLIBC_ARCH_H */ diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h index 9dc4919c769b..a44486ff0477 100644 --- a/tools/include/nolibc/errno.h +++ b/tools/include/nolibc/errno.h @@ -9,11 +9,9 @@ #include <asm/errno.h> -/* this way it will be removed if unused */ -static int errno; - #ifndef NOLIBC_IGNORE_ERRNO #define SET_ERRNO(v) do { errno = (v); } while (0) +int errno __attribute__((weak)); #else #define SET_ERRNO(v) do { } while (0) #endif diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index a24000d1e822..894c955d027e 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -12,6 +12,7 @@ #include "types.h" #include "sys.h" #include "string.h" +#include <linux/auxvec.h> struct nolibc_heap { size_t len; @@ -109,6 +110,32 @@ char *getenv(const char *name) } static __attribute__((unused)) +unsigned long getauxval(unsigned long type) +{ + const unsigned long *auxv = _auxv; + unsigned long ret; + + if (!auxv) + return 0; + + while (1) { + if (!auxv[0] && !auxv[1]) { + ret = 0; + break; + } + + if (auxv[0] == type) { + ret = auxv[1]; + break; + } + + auxv += 2; + } + + return ret; +} + +static __attribute__((unused)) void *malloc(size_t len) { struct nolibc_heap *heap; diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 78473d34e27c..b5f8cd35c03b 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -11,6 +11,7 @@ #include "std.h" /* system includes */ +#include <asm/fcntl.h> // for O_* #include <asm/unistd.h> #include <asm/signal.h> // for SIGCHLD #include <asm/ioctls.h> @@ -18,6 +19,7 @@ #include <linux/fs.h> #include <linux/loop.h> #include <linux/time.h> +#include <linux/auxvec.h> #include "arch.h" #include "errno.h" @@ -498,6 +500,26 @@ pid_t gettid(void) return sys_gettid(); } +static unsigned long getauxval(unsigned long key); + +/* + * long getpagesize(void); + */ + +static __attribute__((unused)) +long getpagesize(void) +{ + long ret; + + ret = getauxval(AT_PAGESZ); + if (!ret) { + SET_ERRNO(ENOENT); + return -1; + } + + return ret; +} + /* * int gettimeofday(struct timeval *tv, struct timezone *tz); @@ -686,6 +708,7 @@ int mknod(const char *path, mode_t mode, dev_t dev) #define MAP_FAILED ((void *)-1) #endif +#ifndef sys_mmap static __attribute__((unused)) void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) @@ -707,6 +730,7 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset); #endif } +#endif static __attribute__((unused)) void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h index d7dfeab0d71a..ff52668abf8c 100644 --- a/tools/include/uapi/asm/bpf_perf_event.h +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -6,6 +6,8 @@ #include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" #elif defined(__riscv) #include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h" +#elif defined(__loongarch__) +#include "../../arch/loongarch/include/uapi/asm/bpf_perf_event.h" #else #include <uapi/asm-generic/bpf_perf_event.h> #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 464ca3f01fe7..62ce1f5d1b1d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1156,6 +1156,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ @@ -2001,6 +2006,9 @@ union bpf_attr { * sending the packet. This flag was added for GRE * encapsulation, but might be used with other protocols * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. * * Here is a typical usage on the transmit path: * @@ -2644,6 +2652,11 @@ union bpf_attr { * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the * L2 type as Ethernet. * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -2788,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see @@ -3121,6 +3134,11 @@ union bpf_attr { * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -5764,6 +5782,7 @@ enum { BPF_F_ZERO_CSUM_TX = (1ULL << 1), BPF_F_DONT_FRAGMENT = (1ULL << 2), BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), }; /* BPF_FUNC_skb_get_tunnel_key flags. */ @@ -5803,6 +5822,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { @@ -6734,6 +6755,7 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), }; enum { @@ -6901,6 +6923,17 @@ struct bpf_list_node { __u64 :64; } __attribute__((aligned(8))); +struct bpf_rb_root { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 :64; + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..588391447bfb --- /dev/null +++ b/tools/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * offloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index b8e457c841ab..7ba3e81274e8 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -14,8 +14,8 @@ #include "tracing_path.h" static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; -static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing"; -static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events"; +static char tracing_path[PATH_MAX] = "/sys/kernel/tracing"; +static char tracing_events_path[PATH_MAX] = "/sys/kernel/tracing/events"; static void __tracing_path_set(const char *tracing, const char *mountpoint) { diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9aff98f42a3d..e750b6f5fcc3 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1044,6 +1044,26 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) return libbpf_err_errno(err); } +int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(prog_fd, info, info_len); +} + +int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(map_fd, info, info_len); +} + +int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(btf_fd, info, info_len); +} + +int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(link_fd, info, info_len); +} + int bpf_raw_tracepoint_open(const char *name, int prog_fd) { const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 7468978d3c27..9ed9bceb4111 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -386,6 +386,15 @@ LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id, const struct bpf_get_fd_by_id_opts *opts); LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); +/* Type-safe variants of bpf_obj_get_info_by_fd(). The callers still needs to + * pass info_len, which should normally be + * sizeof(struct bpf_{prog,map,btf,link}_info), in order to be compatible with + * different libbpf and kernel versions. + */ +LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len); +LIBBPF_API int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len); +LIBBPF_API int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len); +LIBBPF_API int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len); struct bpf_prog_query_opts { size_t sz; /* size of this struct for forward/backward compatibility */ diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 496e6a8ee0dc..1ac57bb7ac55 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -364,7 +364,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_INTO() */ #define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) @@ -400,7 +400,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ #define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_str, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index d37c4fe2849d..5ec1871acb2f 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -109,7 +109,7 @@ * This is a variable-specific variant of more global barrier(). */ #ifndef barrier_var -#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#define barrier_var(var) asm volatile("" : "+r"(var)) #endif /* diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 2972dc25ff72..6db88f41fa0d 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -32,6 +32,9 @@ #elif defined(__TARGET_ARCH_arc) #define bpf_target_arc #define bpf_target_defined +#elif defined(__TARGET_ARCH_loongarch) + #define bpf_target_loongarch + #define bpf_target_defined #else /* Fall back to what the compiler says */ @@ -62,6 +65,9 @@ #elif defined(__arc__) #define bpf_target_arc #define bpf_target_defined +#elif defined(__loongarch__) + #define bpf_target_loongarch + #define bpf_target_defined #endif /* no compiler target */ #endif @@ -72,6 +78,10 @@ #if defined(bpf_target_x86) +/* + * https://en.wikipedia.org/wiki/X86_calling_conventions#System_V_AMD64_ABI + */ + #if defined(__KERNEL__) || defined(__VMLINUX_H__) #define __PT_PARM1_REG di @@ -79,25 +89,40 @@ #define __PT_PARM3_REG dx #define __PT_PARM4_REG cx #define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 +/* + * Syscall uses r10 for PARM4. See arch/x86/entry/entry_64.S:entry_SYSCALL_64 + * comments in Linux sources. And refer to syscall(2) manpage. + */ +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG sp #define __PT_FP_REG bp #define __PT_RC_REG ax #define __PT_SP_REG sp #define __PT_IP_REG ip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #else #ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ #define __PT_PARM1_REG eax #define __PT_PARM2_REG edx #define __PT_PARM3_REG ecx -/* i386 kernel is built with -mregparm=3 */ -#define __PT_PARM4_REG __unsupported__ -#define __PT_PARM5_REG __unsupported__ +/* i386 syscall ABI is very different, refer to syscall(2) manpage */ +#define __PT_PARM1_SYSCALL_REG ebx +#define __PT_PARM2_SYSCALL_REG ecx +#define __PT_PARM3_SYSCALL_REG edx +#define __PT_PARM4_SYSCALL_REG esi +#define __PT_PARM5_SYSCALL_REG edi +#define __PT_PARM6_SYSCALL_REG ebp + #define __PT_RET_REG esp #define __PT_FP_REG ebp #define __PT_RC_REG eax @@ -111,14 +136,20 @@ #define __PT_PARM3_REG rdx #define __PT_PARM4_REG rcx #define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG rsp #define __PT_FP_REG rbp #define __PT_RC_REG rax #define __PT_SP_REG rsp #define __PT_IP_REG rip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #endif /* __i386__ */ @@ -126,6 +157,10 @@ #elif defined(bpf_target_s390) +/* + * https://github.com/IBM/s390x-abi/releases/download/v1.6/lzsabi_s390x.pdf + */ + struct pt_regs___s390 { unsigned long orig_gpr2; }; @@ -137,21 +172,41 @@ struct pt_regs___s390 { #define __PT_PARM3_REG gprs[4] #define __PT_PARM4_REG gprs[5] #define __PT_PARM5_REG gprs[6] -#define __PT_RET_REG grps[14] + +#define __PT_PARM1_SYSCALL_REG orig_gpr2 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG gprs[7] +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG) + +#define __PT_RET_REG gprs[14] #define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG gprs[2] #define __PT_SP_REG gprs[15] #define __PT_IP_REG psw.addr -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs32/aapcs32.rst#machine-registers + */ + #define __PT_PARM1_REG uregs[0] #define __PT_PARM2_REG uregs[1] #define __PT_PARM3_REG uregs[2] #define __PT_PARM4_REG uregs[3] -#define __PT_PARM5_REG uregs[4] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM6_SYSCALL_REG uregs[5] +#define __PT_PARM7_SYSCALL_REG uregs[6] + #define __PT_RET_REG uregs[14] #define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG uregs[0] @@ -160,6 +215,10 @@ struct pt_regs___s390 { #elif defined(bpf_target_arm64) +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#machine-registers + */ + struct pt_regs___arm64 { unsigned long orig_x0; }; @@ -171,21 +230,49 @@ struct pt_regs___arm64 { #define __PT_PARM3_REG regs[2] #define __PT_PARM4_REG regs[3] #define __PT_PARM5_REG regs[4] +#define __PT_PARM6_REG regs[5] +#define __PT_PARM7_REG regs[6] +#define __PT_PARM8_REG regs[7] + +#define __PT_PARM1_SYSCALL_REG orig_x0 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG) + #define __PT_RET_REG regs[30] #define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG regs[0] #define __PT_SP_REG sp #define __PT_IP_REG pc -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) +/* + * N64 ABI is assumed right now. + * https://en.wikipedia.org/wiki/MIPS_architecture#Calling_conventions + */ + #define __PT_PARM1_REG regs[4] #define __PT_PARM2_REG regs[5] #define __PT_PARM3_REG regs[6] #define __PT_PARM4_REG regs[7] #define __PT_PARM5_REG regs[8] +#define __PT_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG /* only N32/N64 */ +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG /* only N32/N64 */ + #define __PT_RET_REG regs[31] #define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG regs[2] @@ -194,26 +281,58 @@ struct pt_regs___arm64 { #elif defined(bpf_target_powerpc) +/* + * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf (page 3-14, + * section "Function Calling Sequence") + */ + #define __PT_PARM1_REG gpr[3] #define __PT_PARM2_REG gpr[4] #define __PT_PARM3_REG gpr[5] #define __PT_PARM4_REG gpr[6] #define __PT_PARM5_REG gpr[7] +#define __PT_PARM6_REG gpr[8] +#define __PT_PARM7_REG gpr[9] +#define __PT_PARM8_REG gpr[10] + +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG orig_gpr3 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#if !defined(__arch64__) +#define __PT_PARM7_SYSCALL_REG __PT_PARM7_REG /* only powerpc (not powerpc64) */ +#endif + #define __PT_RET_REG regs[31] #define __PT_FP_REG __unsupported__ #define __PT_RC_REG gpr[3] #define __PT_SP_REG sp #define __PT_IP_REG nip -/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_sparc) +/* + * https://en.wikipedia.org/wiki/Calling_convention#SPARC + */ + #define __PT_PARM1_REG u_regs[UREG_I0] #define __PT_PARM2_REG u_regs[UREG_I1] #define __PT_PARM3_REG u_regs[UREG_I2] #define __PT_PARM4_REG u_regs[UREG_I3] #define __PT_PARM5_REG u_regs[UREG_I4] +#define __PT_PARM6_REG u_regs[UREG_I5] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG u_regs[UREG_I7] #define __PT_FP_REG __unsupported__ #define __PT_RC_REG u_regs[UREG_I0] @@ -227,22 +346,42 @@ struct pt_regs___arm64 { #elif defined(bpf_target_riscv) +/* + * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions + */ + #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 #define __PT_PARM2_REG a1 #define __PT_PARM3_REG a2 #define __PT_PARM4_REG a3 #define __PT_PARM5_REG a4 +#define __PT_PARM6_REG a5 +#define __PT_PARM7_REG a6 +#define __PT_PARM8_REG a7 + +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG ra #define __PT_FP_REG s0 #define __PT_RC_REG a0 #define __PT_SP_REG sp #define __PT_IP_REG pc -/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_arc) +/* + * Section "Function Calling Sequence" (page 24): + * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf + */ + /* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG scratch.r0 @@ -250,13 +389,55 @@ struct pt_regs___arm64 { #define __PT_PARM3_REG scratch.r2 #define __PT_PARM4_REG scratch.r3 #define __PT_PARM5_REG scratch.r4 +#define __PT_PARM6_REG scratch.r5 +#define __PT_PARM7_REG scratch.r6 +#define __PT_PARM8_REG scratch.r7 + +/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG scratch.blink -#define __PT_FP_REG __unsupported__ +#define __PT_FP_REG scratch.fp #define __PT_RC_REG scratch.r0 #define __PT_SP_REG scratch.sp #define __PT_IP_REG scratch.ret -/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ + +#elif defined(bpf_target_loongarch) + +/* + * https://docs.kernel.org/loongarch/introduction.html + * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html + */ + +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */ #define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG regs[1] +#define __PT_FP_REG regs[22] +#define __PT_RC_REG regs[4] +#define __PT_SP_REG regs[3] +#define __PT_IP_REG csr_era #endif @@ -264,16 +445,49 @@ struct pt_regs___arm64 { struct pt_regs; -/* allow some architecutres to override `struct pt_regs` */ +/* allow some architectures to override `struct pt_regs` */ #ifndef __PT_REGS_CAST #define __PT_REGS_CAST(x) (x) #endif +/* + * Different architectures support different number of arguments passed + * through registers. i386 supports just 3, some arches support up to 8. + */ +#ifndef __PT_PARM4_REG +#define __PT_PARM4_REG __unsupported__ +#endif +#ifndef __PT_PARM5_REG +#define __PT_PARM5_REG __unsupported__ +#endif +#ifndef __PT_PARM6_REG +#define __PT_PARM6_REG __unsupported__ +#endif +#ifndef __PT_PARM7_REG +#define __PT_PARM7_REG __unsupported__ +#endif +#ifndef __PT_PARM8_REG +#define __PT_PARM8_REG __unsupported__ +#endif +/* + * Similarly, syscall-specific conventions might differ between function call + * conventions within each architecutre. All supported architectures pass + * either 6 or 7 syscall arguments in registers. + * + * See syscall(2) manpage for succinct table with information on each arch. + */ +#ifndef __PT_PARM7_SYSCALL_REG +#define __PT_PARM7_SYSCALL_REG __unsupported__ +#endif + #define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) #define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) #define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) #define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) #define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) +#define PT_REGS_PARM6(x) (__PT_REGS_CAST(x)->__PT_PARM6_REG) +#define PT_REGS_PARM7(x) (__PT_REGS_CAST(x)->__PT_PARM7_REG) +#define PT_REGS_PARM8(x) (__PT_REGS_CAST(x)->__PT_PARM8_REG) #define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) #define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) #define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) @@ -285,6 +499,9 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) +#define PT_REGS_PARM6_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_REG) +#define PT_REGS_PARM7_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_REG) +#define PT_REGS_PARM8_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM8_REG) #define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) #define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) #define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) @@ -311,24 +528,33 @@ struct pt_regs; #endif #ifndef PT_REGS_PARM1_SYSCALL -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#define PT_REGS_PARM1_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM2_SYSCALL +#define PT_REGS_PARM2_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM2_SYSCALL_REG) +#define PT_REGS_PARM2_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM3_SYSCALL +#define PT_REGS_PARM3_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM3_SYSCALL_REG) +#define PT_REGS_PARM3_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_SYSCALL_REG) #endif -#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) -#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) #ifndef PT_REGS_PARM4_SYSCALL -#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#define PT_REGS_PARM4_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM4_SYSCALL_REG) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_SYSCALL_REG) #endif -#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) - -#ifndef PT_REGS_PARM1_CORE_SYSCALL -#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#ifndef PT_REGS_PARM5_SYSCALL +#define PT_REGS_PARM5_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM5_SYSCALL_REG) +#define PT_REGS_PARM5_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_SYSCALL_REG) #endif -#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) -#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) -#ifndef PT_REGS_PARM4_CORE_SYSCALL -#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#ifndef PT_REGS_PARM6_SYSCALL +#define PT_REGS_PARM6_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM6_SYSCALL_REG) +#define PT_REGS_PARM6_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM7_SYSCALL +#define PT_REGS_PARM7_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM7_SYSCALL_REG) +#define PT_REGS_PARM7_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_SYSCALL_REG) #endif -#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) #else /* defined(bpf_target_defined) */ @@ -337,6 +563,9 @@ struct pt_regs; #define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -348,6 +577,9 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -362,12 +594,16 @@ struct pt_regs; #define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #endif /* defined(bpf_target_defined) */ @@ -553,6 +789,9 @@ struct pt_regs; #define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) #define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) #define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx) +#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx) +#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx) #define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) /* @@ -609,6 +848,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) #define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) #define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) #define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs) +#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs) #define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) /* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ @@ -618,6 +859,8 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) #define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) #define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) #define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs) #define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) /* @@ -667,4 +910,11 @@ ____##name(struct pt_regs *ctx, ##args) #define BPF_KPROBE_SYSCALL BPF_KSYSCALL +/* BPF_UPROBE and BPF_URETPROBE are identical to BPF_KPROBE and BPF_KRETPROBE, + * but are named way less confusingly for SEC("uprobe") and SEC("uretprobe") + * use cases. + */ +#define BPF_UPROBE(name, args...) BPF_KPROBE(name, ##args) +#define BPF_URETPROBE(name, args...) BPF_KRETPROBE(name, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 71e165b09ed5..9181d36118d2 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -688,8 +688,21 @@ int btf__align_of(const struct btf *btf, __u32 id) if (align <= 0) return libbpf_err(align); max_align = max(max_align, align); + + /* if field offset isn't aligned according to field + * type's alignment, then struct must be packed + */ + if (btf_member_bitfield_size(t, i) == 0 && + (m->offset % (8 * align)) != 0) + return 1; } + /* if struct/union size isn't a multiple of its alignment, + * then struct must be packed + */ + if ((t->size % max_align) != 0) + return 1; + return max_align; } default: @@ -990,7 +1003,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, err = 0; if (!btf_data) { - err = -ENOENT; + pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path); + err = -ENODATA; goto done; } btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); @@ -1336,9 +1350,9 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) void *ptr; int err; - /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + /* we won't know btf_size until we call bpf_btf_get_info_by_fd(). so * let's start with a sane default - 4KiB here - and resize it only if - * bpf_obj_get_info_by_fd() needs a bigger buffer. + * bpf_btf_get_info_by_fd() needs a bigger buffer. */ last_size = 4096; ptr = malloc(last_size); @@ -1348,7 +1362,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); btf_info.btf_size = last_size; - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); if (!err && btf_info.btf_size > last_size) { void *temp_ptr; @@ -1366,7 +1380,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) btf_info.btf = ptr_to_u64(ptr); btf_info.btf_size = last_size; - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); } if (err || btf_info.btf_size > last_size) { diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index deb2bc9a0a7b..580985ee5545 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -13,6 +13,7 @@ #include <ctype.h> #include <endian.h> #include <errno.h> +#include <limits.h> #include <linux/err.h> #include <linux/btf.h> #include <linux/kernel.h> @@ -833,14 +834,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { const struct btf_member *m; - int align, i, bit_sz; + int max_align = 1, align, i, bit_sz; __u16 vlen; - align = btf__align_of(btf, id); - /* size of a non-packed struct has to be a multiple of its alignment*/ - if (align && t->size % align) - return true; - m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ @@ -849,8 +845,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, bit_sz = btf_member_bitfield_size(t, i); if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; + max_align = max(align, max_align); } - + /* size of a non-packed struct has to be a multiple of its alignment */ + if (t->size % max_align != 0) + return true; /* * if original struct was marked as packed, but its layout is * naturally aligned, we'll detect that it's not packed @@ -858,44 +857,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, return false; } -static int chip_away_bits(int total, int at_most) -{ - return total % at_most ? : at_most; -} - static void btf_dump_emit_bit_padding(const struct btf_dump *d, - int cur_off, int m_off, int m_bit_sz, - int align, int lvl) + int cur_off, int next_off, int next_align, + bool in_bitfield, int lvl) { - int off_diff = m_off - cur_off; - int ptr_bits = d->ptr_sz * 8; + const struct { + const char *name; + int bits; + } pads[] = { + {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} + }; + int new_off, pad_bits, bits, i; + const char *pad_type; + + if (cur_off >= next_off) + return; /* no gap */ + + /* For filling out padding we want to take advantage of + * natural alignment rules to minimize unnecessary explicit + * padding. First, we find the largest type (among long, int, + * short, or char) that can be used to force naturally aligned + * boundary. Once determined, we'll use such type to fill in + * the remaining padding gap. In some cases we can rely on + * compiler filling some gaps, but sometimes we need to force + * alignment to close natural alignment with markers like + * `long: 0` (this is always the case for bitfields). Note + * that even if struct itself has, let's say 4-byte alignment + * (i.e., it only uses up to int-aligned types), using `long: + * X;` explicit padding doesn't actually change struct's + * overall alignment requirements, but compiler does take into + * account that type's (long, in this example) natural + * alignment requirements when adding implicit padding. We use + * this fact heavily and don't worry about ruining correct + * struct alignment requirement. + */ + for (i = 0; i < ARRAY_SIZE(pads); i++) { + pad_bits = pads[i].bits; + pad_type = pads[i].name; - if (off_diff <= 0) - /* no gap */ - return; - if (m_bit_sz == 0 && off_diff < align * 8) - /* natural padding will take care of a gap */ - return; + new_off = roundup(cur_off, pad_bits); + if (new_off <= next_off) + break; + } - while (off_diff > 0) { - const char *pad_type; - int pad_bits; - - if (ptr_bits > 32 && off_diff > 32) { - pad_type = "long"; - pad_bits = chip_away_bits(off_diff, ptr_bits); - } else if (off_diff > 16) { - pad_type = "int"; - pad_bits = chip_away_bits(off_diff, 32); - } else if (off_diff > 8) { - pad_type = "short"; - pad_bits = chip_away_bits(off_diff, 16); - } else { - pad_type = "char"; - pad_bits = chip_away_bits(off_diff, 8); + if (new_off > cur_off && new_off <= next_off) { + /* We need explicit `<type>: 0` aligning mark if next + * field is right on alignment offset and its + * alignment requirement is less strict than <type>'s + * alignment (so compiler won't naturally align to the + * offset we expect), or if subsequent `<type>: X`, + * will actually completely fit in the remaining hole, + * making compiler basically ignore `<type>: X` + * completely. + */ + if (in_bitfield || + (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) || + (new_off != next_off && next_off - new_off <= new_off - cur_off)) + /* but for bitfields we'll emit explicit bit count */ + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, + in_bitfield ? new_off - cur_off : 0); + cur_off = new_off; + } + + /* Now we know we start at naturally aligned offset for a chosen + * padding type (long, int, short, or char), and so the rest is just + * a straightforward filling of remaining padding gap with full + * `<type>: sizeof(<type>);` markers, except for the last one, which + * might need smaller than sizeof(<type>) padding. + */ + while (cur_off != next_off) { + bits = min(next_off - cur_off, pad_bits); + if (bits == pad_bits) { + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + cur_off += bits; + continue; + } + /* For the remainder padding that doesn't cover entire + * pad_type bit length, we pick the smallest necessary type. + * This is pure aesthetics, we could have just used `long`, + * but having smallest necessary one communicates better the + * scale of the padding gap. + */ + for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) { + pad_type = pads[i].name; + pad_bits = pads[i].bits; + if (pad_bits < bits) + continue; + + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits); + cur_off += bits; + break; } - btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); - off_diff -= pad_bits; } } @@ -915,9 +967,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, { const struct btf_member *m = btf_members(t); bool is_struct = btf_is_struct(t); - int align, i, packed, off = 0; + bool packed, prev_bitfield = false; + int align, i, off = 0; __u16 vlen = btf_vlen(t); + align = btf__align_of(d->btf, id); packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; btf_dump_printf(d, "%s%s%s {", @@ -927,41 +981,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, for (i = 0; i < vlen; i++, m++) { const char *fname; - int m_off, m_sz; + int m_off, m_sz, m_align; + bool in_bitfield; fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf__align_of(d->btf, m->type); + m_align = packed ? 1 : btf__align_of(d->btf, m->type); + + in_bitfield = prev_bitfield && m_sz != 0; - btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); + btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); btf_dump_emit_type_decl(d, m->type, fname, lvl + 1); if (m_sz) { btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; + prev_bitfield = true; } else { m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; + prev_bitfield = false; } + btf_dump_printf(d, ";"); } /* pad at the end, if necessary */ - if (is_struct) { - align = packed ? 1 : btf__align_of(d->btf, id); - btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, - lvl + 1); - } + if (is_struct) + btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1); /* * Keep `struct empty {}` on a single line, * only print newline when there are regular or padding fields. */ - if (vlen || t->size) + if (vlen || t->size) { btf_dump_printf(d, "\n"); - btf_dump_printf(d, "%s}", pfx(lvl)); + btf_dump_printf(d, "%s}", pfx(lvl)); + } else { + btf_dump_printf(d, "}"); + } if (packed) btf_dump_printf(d, " __attribute__((packed))"); } @@ -1073,6 +1133,43 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, else btf_dump_emit_enum64_val(d, t, lvl, vlen); btf_dump_printf(d, "\n%s}", pfx(lvl)); + + /* special case enums with special sizes */ + if (t->size == 1) { + /* one-byte enums can be forced with mode(byte) attribute */ + btf_dump_printf(d, " __attribute__((mode(byte)))"); + } else if (t->size == 8 && d->ptr_sz == 8) { + /* enum can be 8-byte sized if one of the enumerator values + * doesn't fit in 32-bit integer, or by adding mode(word) + * attribute (but probably only on 64-bit architectures); do + * our best here to try to satisfy the contract without adding + * unnecessary attributes + */ + bool needs_word_mode; + + if (btf_is_enum(t)) { + /* enum can't represent 64-bit values, so we need word mode */ + needs_word_mode = true; + } else { + /* enum64 needs mode(word) if none of its values has + * non-zero upper 32-bits (which means that all values + * fit in 32-bit integers and won't cause compiler to + * bump enum to be 64-bit naturally + */ + int i; + + needs_word_mode = true; + for (i = 0; i < vlen; i++) { + if (btf_enum64(t)[i].val_hi32 != 0) { + needs_word_mode = false; + break; + } + } + } + if (needs_word_mode) + btf_dump_printf(d, " __attribute__((mode(word)))"); + } + } static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2a82f49ce16f..05c4db355f28 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -34,7 +34,6 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> -#include <linux/version.h> #include <sys/epoll.h> #include <sys/ioctl.h> #include <sys/mman.h> @@ -870,42 +869,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -__u32 get_kernel_version(void) -{ - /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, - * but Ubuntu provides /proc/version_signature file, as described at - * https://ubuntu.com/kernel, with an example contents below, which we - * can use to get a proper LINUX_VERSION_CODE. - * - * Ubuntu 5.4.0-12.15-generic 5.4.8 - * - * In the above, 5.4.8 is what kernel is actually expecting, while - * uname() call will return 5.4.0 in info.release. - */ - const char *ubuntu_kver_file = "/proc/version_signature"; - __u32 major, minor, patch; - struct utsname info; - - if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { - FILE *f; - - f = fopen(ubuntu_kver_file, "r"); - if (f) { - if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { - fclose(f); - return KERNEL_VERSION(major, minor, patch); - } - fclose(f); - } - /* something went wrong, fall back to uname() approach */ - } - - uname(&info); - if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) - return 0; - return KERNEL_VERSION(major, minor, patch); -} - static const struct btf_member * find_member_by_offset(const struct btf_type *t, __u32 bit_offset) { @@ -4382,7 +4345,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) char *new_name; memset(&info, 0, len); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(fd, &info); if (err) @@ -4766,7 +4729,7 @@ static int probe_module_btf(void) * kernel's module BTF support coincides with support for * name/name_len fields in struct bpf_btf_info. */ - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); close(fd); return !err; } @@ -4929,7 +4892,7 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) int err; memset(&map_info, 0, map_info_len); - err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); + err = bpf_map_get_info_by_fd(map_fd, &map_info, &map_info_len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); if (err) { @@ -5474,7 +5437,7 @@ static int load_module_btfs(struct bpf_object *obj) info.name = ptr_to_u64(name); info.name_len = sizeof(name); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { err = -errno; pr_warn("failed to get BTF object #%d info: %d\n", id, err); @@ -7355,7 +7318,7 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) if (!bpf_map__is_internal(m)) continue; if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) - m->def.map_flags ^= BPF_F_MMAPABLE; + m->def.map_flags &= ~BPF_F_MMAPABLE; } return 0; @@ -8605,6 +8568,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), }; @@ -9066,9 +9030,9 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) int err; memset(&info, 0, info_len); - err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { - pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", + pr_warn("failed bpf_prog_get_info_by_fd for FD %d: %d\n", attach_prog_fd, err); return err; } @@ -9903,7 +9867,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, char errmsg[STRERR_BUFSIZE]; int type, pfd; - if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) + if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) return -EINVAL; memset(&attr, 0, attr_sz); @@ -9994,9 +9958,16 @@ static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, const char *kfunc_name, size_t offset) { static int index = 0; + int i; snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, __sync_fetch_and_add(&index, 1)); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } } static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, @@ -11702,17 +11673,22 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; struct perf_event_attr attr; + __u32 sample_period; if (!OPTS_VALID(opts, perf_buffer_opts)) return libbpf_err_ptr(-EINVAL); + sample_period = OPTS_GET(opts, sample_period, 1); + if (!sample_period) + sample_period = 1; + memset(&attr, 0, attr_sz); attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; + attr.sample_period = sample_period; + attr.wakeup_events = sample_period; p.attr = &attr; p.sample_cb = sample_cb; @@ -11765,7 +11741,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, /* best-effort sanity checks */ memset(&map, 0, sizeof(map)); map_info_len = sizeof(map); - err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + err = bpf_map_get_info_by_fd(map_fd, &map, &map_info_len); if (err) { err = -errno; /* if BPF_OBJ_GET_INFO_BY_FD is supported, will return diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index eee883f007f9..2efd80f6f7b9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -96,6 +96,12 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); +/** + * @brief **libbpf_set_print()** sets user-provided log callback function to + * be used for libbpf warnings and informational messages. + * @param fn The log print function. If NULL, libbpf won't print anything. + * @return Pointer to old print function. + */ LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ @@ -174,6 +180,14 @@ struct bpf_object_open_opts { }; #define bpf_object_open_opts__last_field kernel_log_level +/** + * @brief **bpf_object__open()** creates a bpf_object by opening + * the BPF ELF object file pointed to by the passed path and loading it + * into memory. + * @param path BPF object file path. + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object *bpf_object__open(const char *path); /** @@ -203,16 +217,46 @@ LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); -/* Load/unload object into/from kernel */ +/** + * @brief **bpf_object__load()** loads BPF object into kernel. + * @param obj Pointer to a valid BPF object instance returned by + * **bpf_object__open*()** APIs + * @return 0, on success; negative error code, otherwise, error code is + * stored in errno + */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); -LIBBPF_API void bpf_object__close(struct bpf_object *object); +/** + * @brief **bpf_object__close()** closes a BPF object and releases all + * resources. + * @param obj Pointer to a valid BPF object + */ +LIBBPF_API void bpf_object__close(struct bpf_object *obj); -/* pin_maps and unpin_maps can both be called with a NULL path, in which case - * they will use the pin_path attribute of each map (and ignore all maps that - * don't have a pin_path set). +/** + * @brief **bpf_object__pin_maps()** pins each map contained within + * the BPF object at the passed directory. + * @param obj Pointer to a valid BPF object + * @param path A directory where maps should be pinned. + * @return 0, on success; negative error code, otherwise + * + * If `path` is NULL `bpf_map__pin` (which is being used on each map) + * will use the pin_path attribute of each map. In this case, maps that + * don't have a pin_path set will be ignored. */ LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); + +/** + * @brief **bpf_object__unpin_maps()** unpins each map contained within + * the BPF object found in the passed directory. + * @param obj Pointer to a valid BPF object + * @param path A directory where pinned maps should be searched for. + * @return 0, on success; negative error code, otherwise + * + * If `path` is NULL `bpf_map__unpin` (which is being used on each map) + * will use the pin_path attribute of each map. In this case, maps that + * don't have a pin_path set will be ignored. + */ LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, @@ -823,10 +867,57 @@ LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize * @return true, if the map is an internal map; false, otherwise */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); + +/** + * @brief **bpf_map__set_pin_path()** sets the path attribute that tells where the + * BPF map should be pinned. This does not actually create the 'pin'. + * @param map The bpf_map + * @param path The path + * @return 0, on success; negative error, otherwise + */ LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); + +/** + * @brief **bpf_map__pin_path()** gets the path attribute that tells where the + * BPF map should be pinned. + * @param map The bpf_map + * @return The path string; which can be NULL + */ LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_pinned()** tells the caller whether or not the + * passed map has been pinned via a 'pin' file. + * @param map The bpf_map + * @return true, if the map is pinned; false, otherwise + */ LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); + +/** + * @brief **bpf_map__pin()** creates a file that serves as a 'pin' + * for the BPF map. This increments the reference count on the + * BPF map which will keep the BPF map loaded even after the + * userspace process which loaded it has exited. + * @param map The bpf_map to pin + * @param path A file path for the 'pin' + * @return 0, on success; negative error, otherwise + * + * If `path` is NULL the maps `pin_path` attribute will be used. If this is + * also NULL, an error will be returned and the map will not be pinned. + */ LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); + +/** + * @brief **bpf_map__unpin()** removes the file that serves as a + * 'pin' for the BPF map. + * @param map The bpf_map to unpin + * @param path A file path for the 'pin' + * @return 0, on success; negative error, otherwise + * + * The `path` parameter can be NULL, in which case the `pin_path` + * map attribute is unpinned. If both the `path` parameter and + * `pin_path` map attribute are set, they must be equal. + */ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); @@ -957,9 +1048,10 @@ struct bpf_xdp_query_opts { __u32 hw_prog_id; /* output */ __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ + __u64 feature_flags; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field attach_mode +#define bpf_xdp_query_opts__last_field feature_flags LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); @@ -1039,7 +1131,8 @@ struct user_ring_buffer_opts { #define user_ring_buffer_opts__last_field sz -/* @brief **user_ring_buffer__new()** creates a new instance of a user ring +/** + * @brief **user_ring_buffer__new()** creates a new instance of a user ring * buffer. * * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map. @@ -1050,7 +1143,8 @@ struct user_ring_buffer_opts { LIBBPF_API struct user_ring_buffer * user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); -/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the +/** + * @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the * user ring buffer. * @param rb A pointer to a user ring buffer. * @param size The size of the sample, in bytes. @@ -1070,7 +1164,8 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); */ LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size); -/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the +/** + * @brief **user_ring_buffer__reserve_blocking()** reserves a record in the * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes * available. * @param rb The user ring buffer. @@ -1114,7 +1209,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms); -/* @brief **user_ring_buffer__submit()** submits a previously reserved sample +/** + * @brief **user_ring_buffer__submit()** submits a previously reserved sample * into the ring buffer. * @param rb The user ring buffer. * @param sample A reserved sample. @@ -1124,7 +1220,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, */ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample); -/* @brief **user_ring_buffer__discard()** discards a previously reserved sample. +/** + * @brief **user_ring_buffer__discard()** discards a previously reserved sample. * @param rb The user ring buffer. * @param sample A reserved sample. * @@ -1133,7 +1230,8 @@ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *samp */ LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample); -/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously +/** + * @brief **user_ring_buffer__free()** frees a ring buffer that was previously * created with **user_ring_buffer__new()**. * @param rb The user ring buffer being freed. */ @@ -1149,8 +1247,10 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { size_t sz; + __u32 sample_period; + size_t :0; }; -#define perf_buffer_opts__last_field sz +#define perf_buffer_opts__last_field sample_period /** * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 71bf5691a689..50dde1f6521e 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -382,3 +382,11 @@ LIBBPF_1.1.0 { user_ring_buffer__reserve_blocking; user_ring_buffer__submit; } LIBBPF_1.0.0; + +LIBBPF_1.2.0 { + global: + bpf_btf_get_info_by_fd; + bpf_link_get_info_by_fd; + bpf_map_get_info_by_fd; + bpf_prog_get_info_by_fd; +} LIBBPF_1.1.0; diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index 96f67a772a1b..6b180172ec6b 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -39,14 +39,14 @@ static const char *libbpf_strerror_table[NR_ERRNO] = { int libbpf_strerror(int err, char *buf, size_t size) { + int ret; + if (!buf || !size) return libbpf_err(-EINVAL); err = err > 0 ? err : -err; if (err < __LIBBPF_ERRNO__START) { - int ret; - ret = strerror_r(err, buf, size); buf[size - 1] = '\0'; return libbpf_err_errno(ret); @@ -56,12 +56,20 @@ int libbpf_strerror(int err, char *buf, size_t size) const char *msg; msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; - snprintf(buf, size, "%s", msg); + ret = snprintf(buf, size, "%s", msg); buf[size - 1] = '\0'; + /* The length of the buf and msg is positive. + * A negative number may be returned only when the + * size exceeds INT_MAX. Not likely to appear. + */ + if (ret >= size) + return libbpf_err(-ERANGE); return 0; } - snprintf(buf, size, "Unknown libbpf error %d", err); + ret = snprintf(buf, size, "Unknown libbpf error %d", err); buf[size - 1] = '\0'; + if (ret >= size) + return libbpf_err(-ERANGE); return libbpf_err(-ENOENT); } diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 377642ff51fc..fbaf68335394 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -20,8 +20,8 @@ /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -/* prevent accidental re-addition of reallocarray() */ -#pragma GCC poison reallocarray +/* prevent accidental re-addition of reallocarray()/strlcpy() */ +#pragma GCC poison reallocarray strlcpy #include "libbpf.h" #include "btf.h" @@ -543,6 +543,7 @@ static inline int ensure_good_fd(int fd) fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); saved_errno = errno; close(old_fd); + errno = saved_errno; if (fd < 0) { pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno); errno = saved_errno; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b44fcbb4b42e..4f3bc968ff8e 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -12,11 +12,94 @@ #include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> +#include <linux/version.h> #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" +/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ +static __u32 get_ubuntu_kernel_version(void) +{ + const char *ubuntu_kver_file = "/proc/version_signature"; + __u32 major, minor, patch; + int ret; + FILE *f; + + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) + return 0; + + f = fopen(ubuntu_kver_file, "r"); + if (!f) + return 0; + + ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch); + fclose(f); + if (ret != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release. + * Instead, it is provided in info.version. An example content of + * Debian 10 looks like the below. + * + * utsname::release 4.19.0-22-amd64 + * utsname::version #1 SMP Debian 4.19.260-1 (2022-09-29) + * + * In the above, 4.19.260 is what kernel is actually expecting, while + * uname() call will return 4.19.0 in info.release. + */ +static __u32 get_debian_kernel_version(struct utsname *info) +{ + __u32 major, minor, patch; + char *p; + + p = strstr(info->version, "Debian "); + if (!p) { + /* This is not a Debian kernel. */ + return 0; + } + + if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +__u32 get_kernel_version(void) +{ + __u32 major, minor, patch, version; + struct utsname info; + + /* Check if this is an Ubuntu kernel. */ + version = get_ubuntu_kernel_version(); + if (version != 0) + return version; + + uname(&info); + + /* Check if this is a Debian kernel. */ + version = get_debian_kernel_version(&info); + if (version != 0) + return version; + + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + static int probe_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insns_cnt, char *log_buf, size_t log_buf_sz) diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index e944f5bce728..1fd2eeac5cfc 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 1 +#define LIBBPF_MINOR_VERSION 2 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 35104580870c..1653e7a8b0a1 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -9,6 +9,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> #include <linux/rtnetlink.h> +#include <linux/netdev.h> #include <sys/socket.h> #include <errno.h> #include <time.h> @@ -39,9 +40,15 @@ struct xdp_id_md { int ifindex; __u32 flags; struct xdp_link_info info; + __u64 feature_flags; }; -static int libbpf_netlink_open(__u32 *nl_pid) +struct xdp_features_md { + int ifindex; + __u64 flags; +}; + +static int libbpf_netlink_open(__u32 *nl_pid, int proto) { struct sockaddr_nl sa; socklen_t addrlen; @@ -51,7 +58,7 @@ static int libbpf_netlink_open(__u32 *nl_pid) memset(&sa, 0, sizeof(sa)); sa.nl_family = AF_NETLINK; - sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto); if (sock < 0) return -errno; @@ -212,14 +219,14 @@ done: } static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, - __dump_nlmsg_t parse_msg, + int proto, __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); + sock = libbpf_netlink_open(&nl_pid, proto); if (sock < 0) return sock; @@ -238,6 +245,43 @@ out: return ret; } +static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1]; + __u16 *id = cookie; + + libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + if (!tb[CTRL_ATTR_FAMILY_ID]) + return NL_CONT; + + *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]); + return NL_DONE; +} + +static int libbpf_netlink_resolve_genl_family_id(const char *name, + __u16 len, __u16 *id) +{ + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN), + .nh.nlmsg_type = GENL_ID_CTRL, + .nh.nlmsg_flags = NLM_F_REQUEST, + .gnl.cmd = CTRL_CMD_GETFAMILY, + .gnl.version = 2, + }; + int err; + + err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len); + if (err < 0) + return err; + + return libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_genl_family_id, NULL, id); +} + static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, __u32 flags) { @@ -271,7 +315,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, } nlattr_end_nested(&req, nla); - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) @@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } +static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[NETDEV_CMD_MAX + 1]; + struct xdp_features_md *md = cookie; + __u32 ifindex; + + libbpf_nla_parse(tb, NETDEV_CMD_MAX, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + + if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES]) + return NL_CONT; + + ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]); + if (ifindex != md->ifindex) + return NL_CONT; + + md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + return NL_DONE; +} + int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { struct libbpf_nla_req req = { @@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) .ifinfo.ifi_family = AF_PACKET, }; struct xdp_id_md xdp_id = {}; + struct xdp_features_md md = { + .ifindex = ifindex, + }; + __u16 id; int err; if (!OPTS_VALID(opts, bpf_xdp_query_opts)) @@ -382,7 +453,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) xdp_id.ifindex = ifindex; xdp_id.flags = xdp_flags; - err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg, get_xdp_info, &xdp_id); if (err) return libbpf_err(err); @@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); + if (!OPTS_HAS(opts, feature_flags)) + return 0; + + err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id); + if (err < 0) + return libbpf_err(err); + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = id; + req.gnl.cmd = NETDEV_CMD_DEV_GET; + req.gnl.version = 2; + + err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex)); + if (err < 0) + return libbpf_err(err); + + err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_xdp_features, NULL, &md); + if (err) + return libbpf_err(err); + + opts->feature_flags = md.flags; + return 0; } @@ -493,7 +589,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) if (ret < 0) return ret; - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) @@ -593,7 +689,7 @@ static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) int len, ret; memset(&info, 0, info_len); - ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + ret = bpf_prog_get_info_by_fd(fd, &info, &info_len); if (ret < 0) return ret; @@ -673,7 +769,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) @@ -739,7 +836,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook, return ret; } - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_tc_detach(const struct bpf_tc_hook *hook, @@ -804,7 +901,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 3900d052ed19..975e265eab3b 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -178,7 +178,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) hlen += nlmsg_len(&err->msg); attr = (struct nlattr *) ((void *) err + hlen); - alen = nlh->nlmsg_len - hlen; + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 4d15ae2ff812..d92d1c1de700 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -14,6 +14,7 @@ #include <errno.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/genetlink.h> /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -58,6 +59,7 @@ struct libbpf_nla_req { union { struct ifinfomsg ifinfo; struct tcmsg tc; + struct genlmsghdr gnl; }; char buf[128]; }; @@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) return *(uint8_t *)libbpf_nla_data(nla); } +static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla) +{ + return *(uint16_t *)libbpf_nla_data(nla); +} + static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) { return *(uint32_t *)libbpf_nla_data(nla); } +static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla) +{ + return *(uint64_t *)libbpf_nla_data(nla); +} + static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) { return (const char *)libbpf_nla_data(nla); diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 47855af25f3b..02199364db13 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -83,7 +83,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", @@ -359,7 +359,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index fdfd235e52c4..0bd4c135acc2 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -130,7 +130,10 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) if (!spec) return -ESRCH; - if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 11a1d2d4f681..8e7085238470 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -1007,6 +1007,36 @@ order. Equivalently, where the rmw relation links the read and write events making up each atomic update. This is what the LKMM's "atomic" axiom says. +Atomic rmw updates play one more role in the LKMM: They can form "rmw +sequences". An rmw sequence is simply a bunch of atomic updates where +each update reads from the previous one. Written using events, it +looks like this: + + Z0 ->rf Y1 ->rmw Z1 ->rf ... ->rf Yn ->rmw Zn, + +where Z0 is some store event and n can be any number (even 0, in the +degenerate case). We write this relation as: Z0 ->rmw-sequence Zn. +Note that this implies Z0 and Zn are stores to the same variable. + +Rmw sequences have a special property in the LKMM: They can extend the +cumul-fence relation. That is, if we have: + + U ->cumul-fence X -> rmw-sequence Y + +then also U ->cumul-fence Y. Thinking about this in terms of the +operational model, U ->cumul-fence X says that the store U propagates +to each CPU before the store X does. Then the fact that X and Y are +linked by an rmw sequence means that U also propagates to each CPU +before Y does. In an analogous way, rmw sequences can also extend +the w-post-bounded relation defined below in the PLAIN ACCESSES AND +DATA RACES section. + +(The notion of rmw sequences in the LKMM is similar to, but not quite +the same as, that of release sequences in the C11 memory model. They +were added to the LKMM to fix an obscure bug; without them, atomic +updates with full-barrier semantics did not always guarantee ordering +at least as strong as atomic updates with release-barrier semantics.) + THE PRESERVED PROGRAM ORDER RELATION: ppo ----------------------------------------- @@ -2545,7 +2575,7 @@ smp_store_release() -- which is basically how the Linux kernel treats them. Although we said that plain accesses are not linked by the ppo -relation, they do contribute to it indirectly. Namely, when there is +relation, they do contribute to it indirectly. Firstly, when there is an address dependency from a marked load R to a plain store W, followed by smp_wmb() and then a marked store W', the LKMM creates a ppo link from R to W'. The reasoning behind this is perhaps a little @@ -2554,6 +2584,13 @@ for this source code in which W' could execute before R. Just as with pre-bounding by address dependencies, it is possible for the compiler to undermine this relation if sufficient care is not taken. +Secondly, plain accesses can carry dependencies: If a data dependency +links a marked load R to a store W, and the store is read by a load R' +from the same thread, then the data loaded by R' depends on the data +loaded originally by R. Thus, if R' is linked to any access X by a +dependency, R is also linked to access X by the same dependency, even +if W' or R' (or both!) are plain. + There are a few oddball fences which need special treatment: smp_mb__before_atomic(), smp_mb__after_atomic(), and smp_mb__after_spinlock(). The LKMM uses fence events with special diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell index 5be86b1025e8..70a9073dec3e 100644 --- a/tools/memory-model/linux-kernel.bell +++ b/tools/memory-model/linux-kernel.bell @@ -82,3 +82,9 @@ flag ~empty different-values(srcu-rscs) as srcu-bad-nesting let Marked = (~M) | IW | Once | Release | Acquire | domain(rmw) | range(rmw) | LKR | LKW | UL | LF | RL | RU let Plain = M \ Marked + +(* Redefine dependencies to include those carried through plain accesses *) +let carry-dep = (data ; rfi)* +let addr = carry-dep ; addr +let ctrl = carry-dep ; ctrl +let data = carry-dep ; data diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat index d70315fddef6..07f884f9b2bf 100644 --- a/tools/memory-model/linux-kernel.cat +++ b/tools/memory-model/linux-kernel.cat @@ -74,8 +74,9 @@ let ppo = to-r | to-w | fence | (po-unlock-lock-po & int) (* Propagation: Ordering from release operations and strong fences. *) let A-cumul(r) = (rfe ; [Marked])? ; r +let rmw-sequence = (rf ; rmw)* let cumul-fence = [Marked] ; (A-cumul(strong-fence | po-rel) | wmb | - po-unlock-lock-po) ; [Marked] + po-unlock-lock-po) ; [Marked] ; rmw-sequence let prop = [Marked] ; (overwrite & ext)? ; cumul-fence* ; [Marked] ; rfe? ; [Marked] @@ -174,7 +175,7 @@ let vis = cumul-fence* ; rfe? ; [Marked] ; let w-pre-bounded = [Marked] ; (addr | fence)? let r-pre-bounded = [Marked] ; (addr | nonrw-fence | ([R4rmb] ; fencerel(Rmb) ; [~Noreturn]))? -let w-post-bounded = fence? ; [Marked] +let w-post-bounded = fence? ; [Marked] ; rmw-sequence let r-post-bounded = (nonrw-fence | ([~Noreturn] ; fencerel(Rmb) ; [R4rmb]))? ; [Marked] diff --git a/tools/memory-model/litmus-tests/dep+plain.litmus b/tools/memory-model/litmus-tests/dep+plain.litmus new file mode 100644 index 000000000000..ebf84daa9a59 --- /dev/null +++ b/tools/memory-model/litmus-tests/dep+plain.litmus @@ -0,0 +1,31 @@ +C dep+plain + +(* + * Result: Never + * + * This litmus test demonstrates that in LKMM, plain accesses + * carry dependencies much like accesses to registers: + * The data stored to *z1 and *z2 by P0() originates from P0()'s + * READ_ONCE(), and therefore using that data to compute the + * conditional of P0()'s if-statement creates a control dependency + * from that READ_ONCE() to P0()'s WRITE_ONCE(). + *) + +{} + +P0(int *x, int *y, int *z1, int *z2) +{ + int a = READ_ONCE(*x); + *z1 = a; + *z2 = *z1; + if (*z2 == 1) + WRITE_ONCE(*y, 1); +} + +P1(int *x, int *y) +{ + int r = smp_load_acquire(y); + smp_store_release(x, r); +} + +exists (x=1 /\ y=1) diff --git a/tools/vm/.gitignore b/tools/mm/.gitignore index 922879f93fc8..922879f93fc8 100644 --- a/tools/vm/.gitignore +++ b/tools/mm/.gitignore diff --git a/tools/vm/Makefile b/tools/mm/Makefile index 9860622cbb15..6c1da51f4177 100644 --- a/tools/vm/Makefile +++ b/tools/mm/Makefile @@ -8,8 +8,8 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api LIBS = $(LIB_DIR)/libapi.a -CFLAGS = -Wall -Wextra -I../lib/ -LDFLAGS = $(LIBS) +CFLAGS += -Wall -Wextra -I../lib/ +LDFLAGS += $(LIBS) all: $(TARGETS) diff --git a/tools/vm/page-types.c b/tools/mm/page-types.c index 381dcc00cb62..381dcc00cb62 100644 --- a/tools/vm/page-types.c +++ b/tools/mm/page-types.c diff --git a/tools/vm/page_owner_sort.c b/tools/mm/page_owner_sort.c index ce860ab94162..7c2ac124cdc8 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -246,15 +246,16 @@ static int search_pattern(regex_t *pattern, char *pattern_str, char *buf) return 0; } -static void check_regcomp(regex_t *pattern, const char *regex) +static bool check_regcomp(regex_t *pattern, const char *regex) { int err; err = regcomp(pattern, regex, REG_EXTENDED | REG_NEWLINE); if (err != 0 || pattern->re_nsub != 1) { fprintf(stderr, "Invalid pattern %s code %d\n", regex, err); - exit(1); + return false; } + return true; } static char **explode(char sep, const char *str, int *size) @@ -494,28 +495,28 @@ static bool is_need(char *buf) return true; } -static void add_list(char *buf, int len, char *ext_buf) +static bool add_list(char *buf, int len, char *ext_buf) { if (list_size != 0 && len == list[list_size-1].len && memcmp(buf, list[list_size-1].txt, len) == 0) { list[list_size-1].num++; list[list_size-1].page_num += get_page_num(buf); - return; + return true; } if (list_size == max_size) { fprintf(stderr, "max_size too small??\n"); - exit(1); + return false; } if (!is_need(buf)) - return; + return true; list[list_size].pid = get_pid(buf); list[list_size].tgid = get_tgid(buf); list[list_size].comm = get_comm(buf); list[list_size].txt = malloc(len+1); if (!list[list_size].txt) { fprintf(stderr, "Out of memory\n"); - exit(1); + return false; } memcpy(list[list_size].txt, buf, len); list[list_size].txt[len] = 0; @@ -534,6 +535,7 @@ static void add_list(char *buf, int len, char *ext_buf) printf("loaded %d\r", list_size); fflush(stdout); } + return true; } static bool parse_cull_args(const char *arg_str) @@ -790,12 +792,19 @@ int main(int argc, char **argv) exit(1); } - check_regcomp(&order_pattern, "order\\s*([0-9]*),"); - check_regcomp(&pid_pattern, "pid\\s*([0-9]*),"); - check_regcomp(&tgid_pattern, "tgid\\s*([0-9]*) "); - check_regcomp(&comm_pattern, "tgid\\s*[0-9]*\\s*\\((.*)\\),\\s*ts"); - check_regcomp(&ts_nsec_pattern, "ts\\s*([0-9]*)\\s*ns,"); - check_regcomp(&free_ts_nsec_pattern, "free_ts\\s*([0-9]*)\\s*ns"); + if (!check_regcomp(&order_pattern, "order\\s*([0-9]*),")) + goto out_order; + if (!check_regcomp(&pid_pattern, "pid\\s*([0-9]*),")) + goto out_pid; + if (!check_regcomp(&tgid_pattern, "tgid\\s*([0-9]*) ")) + goto out_tgid; + if (!check_regcomp(&comm_pattern, "tgid\\s*[0-9]*\\s*\\((.*)\\),\\s*ts")) + goto out_comm; + if (!check_regcomp(&ts_nsec_pattern, "ts\\s*([0-9]*)\\s*ns,")) + goto out_ts; + if (!check_regcomp(&free_ts_nsec_pattern, "free_ts\\s*([0-9]*)\\s*ns")) + goto out_free_ts; + fstat(fileno(fin), &st); max_size = st.st_size / 100; /* hack ... */ @@ -804,7 +813,7 @@ int main(int argc, char **argv) ext_buf = malloc(BUF_SIZE); if (!list || !buf || !ext_buf) { fprintf(stderr, "Out of memory\n"); - exit(1); + goto out_free; } for ( ; ; ) { @@ -812,7 +821,8 @@ int main(int argc, char **argv) if (buf_len < 0) break; - add_list(buf, buf_len, ext_buf); + if (!add_list(buf, buf_len, ext_buf)) + goto out_free; } printf("loaded %d\n", list_size); @@ -862,11 +872,26 @@ int main(int argc, char **argv) fprintf(fout, "\n"); } } - regfree(&order_pattern); - regfree(&pid_pattern); - regfree(&tgid_pattern); - regfree(&comm_pattern); - regfree(&ts_nsec_pattern); + +out_free: + if (ext_buf) + free(ext_buf); + if (buf) + free(buf); + if (list) + free(list); +out_free_ts: regfree(&free_ts_nsec_pattern); +out_ts: + regfree(&ts_nsec_pattern); +out_comm: + regfree(&comm_pattern); +out_tgid: + regfree(&tgid_pattern); +out_pid: + regfree(&pid_pattern); +out_order: + regfree(&order_pattern); + return 0; } diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/mm/slabinfo-gnuplot.sh index 873a892147e5..873a892147e5 100644 --- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/mm/slabinfo-gnuplot.sh diff --git a/tools/vm/slabinfo.c b/tools/mm/slabinfo.c index cfaeaea71042..cfaeaea71042 100644 --- a/tools/vm/slabinfo.c +++ b/tools/mm/slabinfo.c diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py new file mode 100755 index 000000000000..db410b74d539 --- /dev/null +++ b/tools/net/ynl/cli.py @@ -0,0 +1,52 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: BSD-3-Clause + +import argparse +import json +import pprint +import time + +from lib import YnlFamily + + +def main(): + parser = argparse.ArgumentParser(description='YNL CLI sample') + parser.add_argument('--spec', dest='spec', type=str, required=True) + parser.add_argument('--schema', dest='schema', type=str) + parser.add_argument('--no-schema', action='store_true') + parser.add_argument('--json', dest='json_text', type=str) + parser.add_argument('--do', dest='do', type=str) + parser.add_argument('--dump', dest='dump', type=str) + parser.add_argument('--sleep', dest='sleep', type=int) + parser.add_argument('--subscribe', dest='ntf', type=str) + args = parser.parse_args() + + if args.no_schema: + args.schema = '' + + attrs = {} + if args.json_text: + attrs = json.loads(args.json_text) + + ynl = YnlFamily(args.spec, args.schema) + + if args.ntf: + ynl.ntf_subscribe(args.ntf) + + if args.sleep: + time.sleep(args.sleep) + + if args.do: + reply = ynl.do(args.do, attrs) + pprint.PrettyPrinter().pprint(reply) + if args.dump: + reply = ynl.dump(args.dump, attrs) + pprint.PrettyPrinter().pprint(reply) + + if args.ntf: + ynl.check_ntf() + pprint.PrettyPrinter().pprint(ynl.async_msg_queue) + + +if __name__ == "__main__": + main() diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore new file mode 100644 index 000000000000..c18dd8d83cee --- /dev/null +++ b/tools/net/ynl/lib/.gitignore @@ -0,0 +1 @@ +__pycache__/ diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py new file mode 100644 index 000000000000..3c73f59eabab --- /dev/null +++ b/tools/net/ynl/lib/__init__.py @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: BSD-3-Clause + +from .nlspec import SpecAttr, SpecAttrSet, SpecFamily, SpecOperation +from .ynl import YnlFamily + +__all__ = ["SpecAttr", "SpecAttrSet", "SpecFamily", "SpecOperation", + "YnlFamily"] diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py new file mode 100644 index 000000000000..71da568e2c28 --- /dev/null +++ b/tools/net/ynl/lib/nlspec.py @@ -0,0 +1,308 @@ +# SPDX-License-Identifier: BSD-3-Clause + +import collections +import importlib +import os +import yaml + + +# To be loaded dynamically as needed +jsonschema = None + + +class SpecElement: + """Netlink spec element. + + Abstract element of the Netlink spec. Implements the dictionary interface + for access to the raw spec. Supports iterative resolution of dependencies + across elements and class inheritance levels. The elements of the spec + may refer to each other, and although loops should be very rare, having + to maintain correct ordering of instantiation is painful, so the resolve() + method should be used to perform parts of init which require access to + other parts of the spec. + + Attributes: + yaml raw spec as loaded from the spec file + family back reference to the full family + + name name of the entity as listed in the spec (optional) + ident_name name which can be safely used as identifier in code (optional) + """ + def __init__(self, family, yaml): + self.yaml = yaml + self.family = family + + if 'name' in self.yaml: + self.name = self.yaml['name'] + self.ident_name = self.name.replace('-', '_') + + self._super_resolved = False + family.add_unresolved(self) + + def __getitem__(self, key): + return self.yaml[key] + + def __contains__(self, key): + return key in self.yaml + + def get(self, key, default=None): + return self.yaml.get(key, default) + + def resolve_up(self, up): + if not self._super_resolved: + up.resolve() + self._super_resolved = True + + def resolve(self): + pass + + +class SpecAttr(SpecElement): + """ Single Netlink atttribute type + + Represents a single attribute type within an attr space. + + Attributes: + value numerical ID when serialized + attr_set Attribute Set containing this attr + """ + def __init__(self, family, attr_set, yaml, value): + super().__init__(family, yaml) + + self.value = value + self.attr_set = attr_set + self.is_multi = yaml.get('multi-attr', False) + + +class SpecAttrSet(SpecElement): + """ Netlink Attribute Set class. + + Represents a ID space of attributes within Netlink. + + Note that unlike other elements, which expose contents of the raw spec + via the dictionary interface Attribute Set exposes attributes by name. + + Attributes: + attrs ordered dict of all attributes (indexed by name) + attrs_by_val ordered dict of all attributes (indexed by value) + subset_of parent set if this is a subset, otherwise None + """ + def __init__(self, family, yaml): + super().__init__(family, yaml) + + self.subset_of = self.yaml.get('subset-of', None) + + self.attrs = collections.OrderedDict() + self.attrs_by_val = collections.OrderedDict() + + val = 0 + for elem in self.yaml['attributes']: + if 'value' in elem: + val = elem['value'] + + attr = self.new_attr(elem, val) + self.attrs[attr.name] = attr + self.attrs_by_val[attr.value] = attr + val += 1 + + def new_attr(self, elem, value): + return SpecAttr(self.family, self, elem, value) + + def __getitem__(self, key): + return self.attrs[key] + + def __contains__(self, key): + return key in self.attrs + + def __iter__(self): + yield from self.attrs + + def items(self): + return self.attrs.items() + + +class SpecOperation(SpecElement): + """Netlink Operation + + Information about a single Netlink operation. + + Attributes: + value numerical ID when serialized, None if req/rsp values differ + + req_value numerical ID when serialized, user -> kernel + rsp_value numerical ID when serialized, user <- kernel + is_call bool, whether the operation is a call + is_async bool, whether the operation is a notification + is_resv bool, whether the operation does not exist (it's just a reserved ID) + attr_set attribute set name + + yaml raw spec as loaded from the spec file + """ + def __init__(self, family, yaml, req_value, rsp_value): + super().__init__(family, yaml) + + self.value = req_value if req_value == rsp_value else None + self.req_value = req_value + self.rsp_value = rsp_value + + self.is_call = 'do' in yaml or 'dump' in yaml + self.is_async = 'notify' in yaml or 'event' in yaml + self.is_resv = not self.is_async and not self.is_call + + # Added by resolve: + self.attr_set = None + delattr(self, "attr_set") + + def resolve(self): + self.resolve_up(super()) + + if 'attribute-set' in self.yaml: + attr_set_name = self.yaml['attribute-set'] + elif 'notify' in self.yaml: + msg = self.family.msgs[self.yaml['notify']] + attr_set_name = msg['attribute-set'] + elif self.is_resv: + attr_set_name = '' + else: + raise Exception(f"Can't resolve attribute set for op '{self.name}'") + if attr_set_name: + self.attr_set = self.family.attr_sets[attr_set_name] + + +class SpecFamily(SpecElement): + """ Netlink Family Spec class. + + Netlink family information loaded from a spec (e.g. in YAML). + Takes care of unfolding implicit information which can be skipped + in the spec itself for brevity. + + The class can be used like a dictionary to access the raw spec + elements but that's usually a bad idea. + + Attributes: + proto protocol type (e.g. genetlink) + + attr_sets dict of attribute sets + msgs dict of all messages (index by name) + msgs_by_value dict of all messages (indexed by name) + ops dict of all valid requests / responses + """ + def __init__(self, spec_path, schema_path=None): + with open(spec_path, "r") as stream: + spec = yaml.safe_load(stream) + + self._resolution_list = [] + + super().__init__(self, spec) + + self.proto = self.yaml.get('protocol', 'genetlink') + + if schema_path is None: + schema_path = os.path.dirname(os.path.dirname(spec_path)) + f'/{self.proto}.yaml' + if schema_path: + global jsonschema + + with open(schema_path, "r") as stream: + schema = yaml.safe_load(stream) + + if jsonschema is None: + jsonschema = importlib.import_module("jsonschema") + + jsonschema.validate(self.yaml, schema) + + self.attr_sets = collections.OrderedDict() + self.msgs = collections.OrderedDict() + self.req_by_value = collections.OrderedDict() + self.rsp_by_value = collections.OrderedDict() + self.ops = collections.OrderedDict() + + last_exception = None + while len(self._resolution_list) > 0: + resolved = [] + unresolved = self._resolution_list + self._resolution_list = [] + + for elem in unresolved: + try: + elem.resolve() + except (KeyError, AttributeError) as e: + self._resolution_list.append(elem) + last_exception = e + continue + + resolved.append(elem) + + if len(resolved) == 0: + raise last_exception + + def new_attr_set(self, elem): + return SpecAttrSet(self, elem) + + def new_operation(self, elem, req_val, rsp_val): + return SpecOperation(self, elem, req_val, rsp_val) + + def add_unresolved(self, elem): + self._resolution_list.append(elem) + + def _dictify_ops_unified(self): + val = 0 + for elem in self.yaml['operations']['list']: + if 'value' in elem: + val = elem['value'] + + op = self.new_operation(elem, val, val) + val += 1 + + self.msgs[op.name] = op + + def _dictify_ops_directional(self): + req_val = rsp_val = 0 + for elem in self.yaml['operations']['list']: + if 'notify' in elem: + if 'value' in elem: + rsp_val = elem['value'] + req_val_next = req_val + rsp_val_next = rsp_val + 1 + req_val = None + elif 'do' in elem or 'dump' in elem: + mode = elem['do'] if 'do' in elem else elem['dump'] + + v = mode.get('request', {}).get('value', None) + if v: + req_val = v + v = mode.get('reply', {}).get('value', None) + if v: + rsp_val = v + + rsp_inc = 1 if 'reply' in mode else 0 + req_val_next = req_val + 1 + rsp_val_next = rsp_val + rsp_inc + else: + raise Exception("Can't parse directional ops") + + op = self.new_operation(elem, req_val, rsp_val) + req_val = req_val_next + rsp_val = rsp_val_next + + self.msgs[op.name] = op + + def resolve(self): + self.resolve_up(super()) + + for elem in self.yaml['attribute-sets']: + attr_set = self.new_attr_set(elem) + self.attr_sets[elem['name']] = attr_set + + msg_id_model = self.yaml['operations'].get('enum-model', 'unified') + if msg_id_model == 'unified': + self._dictify_ops_unified() + elif msg_id_model == 'directional': + self._dictify_ops_directional() + + for op in self.msgs.values(): + if op.req_value is not None: + self.req_by_value[op.req_value] = op + if op.rsp_value is not None: + self.rsp_by_value[op.rsp_value] = op + if not op.is_async and 'attribute-set' in op: + self.ops[op.name] = op diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py new file mode 100644 index 000000000000..1c7411ee04dc --- /dev/null +++ b/tools/net/ynl/lib/ynl.py @@ -0,0 +1,528 @@ +# SPDX-License-Identifier: BSD-3-Clause + +import functools +import os +import random +import socket +import struct +import yaml + +from .nlspec import SpecFamily + +# +# Generic Netlink code which should really be in some library, but I can't quickly find one. +# + + +class Netlink: + # Netlink socket + SOL_NETLINK = 270 + + NETLINK_ADD_MEMBERSHIP = 1 + NETLINK_CAP_ACK = 10 + NETLINK_EXT_ACK = 11 + + # Netlink message + NLMSG_ERROR = 2 + NLMSG_DONE = 3 + + NLM_F_REQUEST = 1 + NLM_F_ACK = 4 + NLM_F_ROOT = 0x100 + NLM_F_MATCH = 0x200 + NLM_F_APPEND = 0x800 + + NLM_F_CAPPED = 0x100 + NLM_F_ACK_TLVS = 0x200 + + NLM_F_DUMP = NLM_F_ROOT | NLM_F_MATCH + + NLA_F_NESTED = 0x8000 + NLA_F_NET_BYTEORDER = 0x4000 + + NLA_TYPE_MASK = NLA_F_NESTED | NLA_F_NET_BYTEORDER + + # Genetlink defines + NETLINK_GENERIC = 16 + + GENL_ID_CTRL = 0x10 + + # nlctrl + CTRL_CMD_GETFAMILY = 3 + + CTRL_ATTR_FAMILY_ID = 1 + CTRL_ATTR_FAMILY_NAME = 2 + CTRL_ATTR_MAXATTR = 5 + CTRL_ATTR_MCAST_GROUPS = 7 + + CTRL_ATTR_MCAST_GRP_NAME = 1 + CTRL_ATTR_MCAST_GRP_ID = 2 + + # Extack types + NLMSGERR_ATTR_MSG = 1 + NLMSGERR_ATTR_OFFS = 2 + NLMSGERR_ATTR_COOKIE = 3 + NLMSGERR_ATTR_POLICY = 4 + NLMSGERR_ATTR_MISS_TYPE = 5 + NLMSGERR_ATTR_MISS_NEST = 6 + + +class NlAttr: + def __init__(self, raw, offset): + self._len, self._type = struct.unpack("HH", raw[offset:offset + 4]) + self.type = self._type & ~Netlink.NLA_TYPE_MASK + self.payload_len = self._len + self.full_len = (self.payload_len + 3) & ~3 + self.raw = raw[offset + 4:offset + self.payload_len] + + def as_u8(self): + return struct.unpack("B", self.raw)[0] + + def as_u16(self): + return struct.unpack("H", self.raw)[0] + + def as_u32(self): + return struct.unpack("I", self.raw)[0] + + def as_u64(self): + return struct.unpack("Q", self.raw)[0] + + def as_strz(self): + return self.raw.decode('ascii')[:-1] + + def as_bin(self): + return self.raw + + def __repr__(self): + return f"[type:{self.type} len:{self._len}] {self.raw}" + + +class NlAttrs: + def __init__(self, msg): + self.attrs = [] + + offset = 0 + while offset < len(msg): + attr = NlAttr(msg, offset) + offset += attr.full_len + self.attrs.append(attr) + + def __iter__(self): + yield from self.attrs + + def __repr__(self): + msg = '' + for a in self.attrs: + if msg: + msg += '\n' + msg += repr(a) + return msg + + +class NlMsg: + def __init__(self, msg, offset, attr_space=None): + self.hdr = msg[offset:offset + 16] + + self.nl_len, self.nl_type, self.nl_flags, self.nl_seq, self.nl_portid = \ + struct.unpack("IHHII", self.hdr) + + self.raw = msg[offset + 16:offset + self.nl_len] + + self.error = 0 + self.done = 0 + + extack_off = None + if self.nl_type == Netlink.NLMSG_ERROR: + self.error = struct.unpack("i", self.raw[0:4])[0] + self.done = 1 + extack_off = 20 + elif self.nl_type == Netlink.NLMSG_DONE: + self.done = 1 + extack_off = 4 + + self.extack = None + if self.nl_flags & Netlink.NLM_F_ACK_TLVS and extack_off: + self.extack = dict() + extack_attrs = NlAttrs(self.raw[extack_off:]) + for extack in extack_attrs: + if extack.type == Netlink.NLMSGERR_ATTR_MSG: + self.extack['msg'] = extack.as_strz() + elif extack.type == Netlink.NLMSGERR_ATTR_MISS_TYPE: + self.extack['miss-type'] = extack.as_u32() + elif extack.type == Netlink.NLMSGERR_ATTR_MISS_NEST: + self.extack['miss-nest'] = extack.as_u32() + elif extack.type == Netlink.NLMSGERR_ATTR_OFFS: + self.extack['bad-attr-offs'] = extack.as_u32() + else: + if 'unknown' not in self.extack: + self.extack['unknown'] = [] + self.extack['unknown'].append(extack) + + if attr_space: + # We don't have the ability to parse nests yet, so only do global + if 'miss-type' in self.extack and 'miss-nest' not in self.extack: + miss_type = self.extack['miss-type'] + if miss_type in attr_space.attrs_by_val: + spec = attr_space.attrs_by_val[miss_type] + desc = spec['name'] + if 'doc' in spec: + desc += f" ({spec['doc']})" + self.extack['miss-type'] = desc + + def __repr__(self): + msg = f"nl_len = {self.nl_len} ({len(self.raw)}) nl_flags = 0x{self.nl_flags:x} nl_type = {self.nl_type}\n" + if self.error: + msg += '\terror: ' + str(self.error) + if self.extack: + msg += '\textack: ' + repr(self.extack) + return msg + + +class NlMsgs: + def __init__(self, data, attr_space=None): + self.msgs = [] + + offset = 0 + while offset < len(data): + msg = NlMsg(data, offset, attr_space=attr_space) + offset += msg.nl_len + self.msgs.append(msg) + + def __iter__(self): + yield from self.msgs + + +genl_family_name_to_id = None + + +def _genl_msg(nl_type, nl_flags, genl_cmd, genl_version, seq=None): + # we prepend length in _genl_msg_finalize() + if seq is None: + seq = random.randint(1, 1024) + nlmsg = struct.pack("HHII", nl_type, nl_flags, seq, 0) + genlmsg = struct.pack("bbH", genl_cmd, genl_version, 0) + return nlmsg + genlmsg + + +def _genl_msg_finalize(msg): + return struct.pack("I", len(msg) + 4) + msg + + +def _genl_load_families(): + with socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, Netlink.NETLINK_GENERIC) as sock: + sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) + + msg = _genl_msg(Netlink.GENL_ID_CTRL, + Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK | Netlink.NLM_F_DUMP, + Netlink.CTRL_CMD_GETFAMILY, 1) + msg = _genl_msg_finalize(msg) + + sock.send(msg, 0) + + global genl_family_name_to_id + genl_family_name_to_id = dict() + + while True: + reply = sock.recv(128 * 1024) + nms = NlMsgs(reply) + for nl_msg in nms: + if nl_msg.error: + print("Netlink error:", nl_msg.error) + return + if nl_msg.done: + return + + gm = GenlMsg(nl_msg) + fam = dict() + for attr in gm.raw_attrs: + if attr.type == Netlink.CTRL_ATTR_FAMILY_ID: + fam['id'] = attr.as_u16() + elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME: + fam['name'] = attr.as_strz() + elif attr.type == Netlink.CTRL_ATTR_MAXATTR: + fam['maxattr'] = attr.as_u32() + elif attr.type == Netlink.CTRL_ATTR_MCAST_GROUPS: + fam['mcast'] = dict() + for entry in NlAttrs(attr.raw): + mcast_name = None + mcast_id = None + for entry_attr in NlAttrs(entry.raw): + if entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_NAME: + mcast_name = entry_attr.as_strz() + elif entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_ID: + mcast_id = entry_attr.as_u32() + if mcast_name and mcast_id is not None: + fam['mcast'][mcast_name] = mcast_id + if 'name' in fam and 'id' in fam: + genl_family_name_to_id[fam['name']] = fam + + +class GenlMsg: + def __init__(self, nl_msg): + self.nl = nl_msg + + self.hdr = nl_msg.raw[0:4] + self.raw = nl_msg.raw[4:] + + self.genl_cmd, self.genl_version, _ = struct.unpack("bbH", self.hdr) + + self.raw_attrs = NlAttrs(self.raw) + + def __repr__(self): + msg = repr(self.nl) + msg += f"\tgenl_cmd = {self.genl_cmd} genl_ver = {self.genl_version}\n" + for a in self.raw_attrs: + msg += '\t\t' + repr(a) + '\n' + return msg + + +class GenlFamily: + def __init__(self, family_name): + self.family_name = family_name + + global genl_family_name_to_id + if genl_family_name_to_id is None: + _genl_load_families() + + self.genl_family = genl_family_name_to_id[family_name] + self.family_id = genl_family_name_to_id[family_name]['id'] + + +# +# YNL implementation details. +# + + +class YnlFamily(SpecFamily): + def __init__(self, def_path, schema=None): + super().__init__(def_path, schema) + + self.include_raw = False + + self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, Netlink.NETLINK_GENERIC) + self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) + self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1) + + self._types = dict() + + for elem in self.yaml.get('definitions', []): + self._types[elem['name']] = elem + + self.async_msg_ids = set() + self.async_msg_queue = [] + + for msg in self.msgs.values(): + if msg.is_async: + self.async_msg_ids.add(msg.rsp_value) + + for op_name, op in self.ops.items(): + bound_f = functools.partial(self._op, op_name) + setattr(self, op.ident_name, bound_f) + + self.family = GenlFamily(self.yaml['name']) + + def ntf_subscribe(self, mcast_name): + if mcast_name not in self.family.genl_family['mcast']: + raise Exception(f'Multicast group "{mcast_name}" not present in the family') + + self.sock.bind((0, 0)) + self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, + self.family.genl_family['mcast'][mcast_name]) + + def _add_attr(self, space, name, value): + attr = self.attr_sets[space][name] + nl_type = attr.value + if attr["type"] == 'nest': + nl_type |= Netlink.NLA_F_NESTED + attr_payload = b'' + for subname, subvalue in value.items(): + attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) + elif attr["type"] == 'flag': + attr_payload = b'' + elif attr["type"] == 'u32': + attr_payload = struct.pack("I", int(value)) + elif attr["type"] == 'string': + attr_payload = str(value).encode('ascii') + b'\x00' + elif attr["type"] == 'binary': + attr_payload = value + else: + raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') + + pad = b'\x00' * ((4 - len(attr_payload) % 4) % 4) + return struct.pack('HH', len(attr_payload) + 4, nl_type) + attr_payload + pad + + def _decode_enum(self, rsp, attr_spec): + raw = rsp[attr_spec['name']] + enum = self._types[attr_spec['enum']] + i = attr_spec.get('value-start', 0) + if 'enum-as-flags' in attr_spec and attr_spec['enum-as-flags']: + value = set() + while raw: + if raw & 1: + value.add(enum['entries'][i]) + raw >>= 1 + i += 1 + else: + value = enum['entries'][raw - i] + rsp[attr_spec['name']] = value + + def _decode(self, attrs, space): + attr_space = self.attr_sets[space] + rsp = dict() + for attr in attrs: + attr_spec = attr_space.attrs_by_val[attr.type] + if attr_spec["type"] == 'nest': + subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) + decoded = subdict + elif attr_spec['type'] == 'u8': + decoded = attr.as_u8() + elif attr_spec['type'] == 'u32': + decoded = attr.as_u32() + elif attr_spec['type'] == 'u64': + decoded = attr.as_u64() + elif attr_spec["type"] == 'string': + decoded = attr.as_strz() + elif attr_spec["type"] == 'binary': + decoded = attr.as_bin() + elif attr_spec["type"] == 'flag': + decoded = True + else: + raise Exception(f'Unknown {attr.type} {attr_spec["name"]} {attr_spec["type"]}') + + if not attr_spec.is_multi: + rsp[attr_spec['name']] = decoded + elif attr_spec.name in rsp: + rsp[attr_spec.name].append(decoded) + else: + rsp[attr_spec.name] = [decoded] + + if 'enum' in attr_spec: + self._decode_enum(rsp, attr_spec) + return rsp + + def _decode_extack_path(self, attrs, attr_set, offset, target): + for attr in attrs: + attr_spec = attr_set.attrs_by_val[attr.type] + if offset > target: + break + if offset == target: + return '.' + attr_spec.name + + if offset + attr.full_len <= target: + offset += attr.full_len + continue + if attr_spec['type'] != 'nest': + raise Exception(f"Can't dive into {attr.type} ({attr_spec['name']}) for extack") + offset += 4 + subpath = self._decode_extack_path(NlAttrs(attr.raw), + self.attr_sets[attr_spec['nested-attributes']], + offset, target) + if subpath is None: + return None + return '.' + attr_spec.name + subpath + + return None + + def _decode_extack(self, request, attr_space, extack): + if 'bad-attr-offs' not in extack: + return + + genl_req = GenlMsg(NlMsg(request, 0, attr_space=attr_space)) + path = self._decode_extack_path(genl_req.raw_attrs, attr_space, + 20, extack['bad-attr-offs']) + if path: + del extack['bad-attr-offs'] + extack['bad-attr'] = path + + def handle_ntf(self, nl_msg, genl_msg): + msg = dict() + if self.include_raw: + msg['nlmsg'] = nl_msg + msg['genlmsg'] = genl_msg + op = self.rsp_by_value[genl_msg.genl_cmd] + msg['name'] = op['name'] + msg['msg'] = self._decode(genl_msg.raw_attrs, op.attr_set.name) + self.async_msg_queue.append(msg) + + def check_ntf(self): + while True: + try: + reply = self.sock.recv(128 * 1024, socket.MSG_DONTWAIT) + except BlockingIOError: + return + + nms = NlMsgs(reply) + for nl_msg in nms: + if nl_msg.error: + print("Netlink error in ntf!?", os.strerror(-nl_msg.error)) + print(nl_msg) + continue + if nl_msg.done: + print("Netlink done while checking for ntf!?") + continue + + gm = GenlMsg(nl_msg) + if gm.genl_cmd not in self.async_msg_ids: + print("Unexpected msg id done while checking for ntf", gm) + continue + + self.handle_ntf(nl_msg, gm) + + def _op(self, method, vals, dump=False): + op = self.ops[method] + + nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK + if dump: + nl_flags |= Netlink.NLM_F_DUMP + + req_seq = random.randint(1024, 65535) + msg = _genl_msg(self.family.family_id, nl_flags, op.req_value, 1, req_seq) + for name, value in vals.items(): + msg += self._add_attr(op.attr_set.name, name, value) + msg = _genl_msg_finalize(msg) + + self.sock.send(msg, 0) + + done = False + rsp = [] + while not done: + reply = self.sock.recv(128 * 1024) + nms = NlMsgs(reply, attr_space=op.attr_set) + for nl_msg in nms: + if nl_msg.extack: + self._decode_extack(msg, op.attr_set, nl_msg.extack) + + if nl_msg.error: + print("Netlink error:", os.strerror(-nl_msg.error)) + print(nl_msg) + return + if nl_msg.done: + if nl_msg.extack: + print("Netlink warning:") + print(nl_msg) + done = True + break + + gm = GenlMsg(nl_msg) + # Check if this is a reply to our request + if nl_msg.nl_seq != req_seq or gm.genl_cmd != op.rsp_value: + if gm.genl_cmd in self.async_msg_ids: + self.handle_ntf(nl_msg, gm) + continue + else: + print('Unexpected message: ' + repr(gm)) + continue + + rsp.append(self._decode(gm.raw_attrs, op.attr_set.name)) + + if not rsp: + return None + if not dump and len(rsp) == 1: + return rsp[0] + return rsp + + def do(self, method, vals): + return self._op(method, vals) + + def dump(self, method, vals): + return self._op(method, vals, dump=True) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py new file mode 100755 index 000000000000..274e9c566f61 --- /dev/null +++ b/tools/net/ynl/ynl-gen-c.py @@ -0,0 +1,2357 @@ +#!/usr/bin/env python3 + +import argparse +import collections +import os +import yaml + +from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation + + +def c_upper(name): + return name.upper().replace('-', '_') + + +def c_lower(name): + return name.lower().replace('-', '_') + + +class BaseNlLib: + def get_family_id(self): + return 'ys->family_id' + + def parse_cb_run(self, cb, data, is_dump=False, indent=1): + ind = '\n\t\t' + '\t' * indent + ' ' + if is_dump: + return f"mnl_cb_run2(ys->rx_buf, len, 0, 0, {cb}, {data},{ind}ynl_cb_array, NLMSG_MIN_TYPE)" + else: + return f"mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid,{ind}{cb}, {data},{ind}" + \ + "ynl_cb_array, NLMSG_MIN_TYPE)" + + +class Type(SpecAttr): + def __init__(self, family, attr_set, attr, value): + super().__init__(family, attr_set, attr, value) + + self.attr = attr + self.attr_set = attr_set + self.type = attr['type'] + self.checks = attr.get('checks', {}) + + if 'len' in attr: + self.len = attr['len'] + if 'nested-attributes' in attr: + self.nested_attrs = attr['nested-attributes'] + if self.nested_attrs == family.name: + self.nested_render_name = f"{family.name}" + else: + self.nested_render_name = f"{family.name}_{c_lower(self.nested_attrs)}" + + self.c_name = c_lower(self.name) + if self.c_name in _C_KW: + self.c_name += '_' + + # Added by resolve(): + self.enum_name = None + delattr(self, "enum_name") + + def resolve(self): + self.enum_name = f"{self.attr_set.name_prefix}{self.name}" + self.enum_name = c_upper(self.enum_name) + + def is_multi_val(self): + return None + + def is_scalar(self): + return self.type in {'u8', 'u16', 'u32', 'u64', 's32', 's64'} + + def presence_type(self): + return 'bit' + + def presence_member(self, space, type_filter): + if self.presence_type() != type_filter: + return + + if self.presence_type() == 'bit': + pfx = '__' if space == 'user' else '' + return f"{pfx}u32 {self.c_name}:1;" + + if self.presence_type() == 'len': + pfx = '__' if space == 'user' else '' + return f"{pfx}u32 {self.c_name}_len;" + + def _complex_member_type(self, ri): + return None + + def free_needs_iter(self): + return False + + def free(self, ri, var, ref): + if self.is_multi_val() or self.presence_type() == 'len': + ri.cw.p(f'free({var}->{ref}{self.c_name});') + + def arg_member(self, ri): + member = self._complex_member_type(ri) + if member: + return [member + ' *' + self.c_name] + raise Exception(f"Struct member not implemented for class type {self.type}") + + def struct_member(self, ri): + if self.is_multi_val(): + ri.cw.p(f"unsigned int n_{self.c_name};") + member = self._complex_member_type(ri) + if member: + ptr = '*' if self.is_multi_val() else '' + ri.cw.p(f"{member} {ptr}{self.c_name};") + return + members = self.arg_member(ri) + for one in members: + ri.cw.p(one + ';') + + def _attr_policy(self, policy): + return '{ .type = ' + policy + ', }' + + def attr_policy(self, cw): + policy = c_upper('nla-' + self.attr['type']) + + spec = self._attr_policy(policy) + cw.p(f"\t[{self.enum_name}] = {spec},") + + def _attr_typol(self): + raise Exception(f"Type policy not implemented for class type {self.type}") + + def attr_typol(self, cw): + typol = self._attr_typol() + cw.p(f'[{self.enum_name}] = {"{"} .name = "{self.name}", {typol}{"}"},') + + def _attr_put_line(self, ri, var, line): + if self.presence_type() == 'bit': + ri.cw.p(f"if ({var}->_present.{self.c_name})") + elif self.presence_type() == 'len': + ri.cw.p(f"if ({var}->_present.{self.c_name}_len)") + ri.cw.p(f"{line};") + + def _attr_put_simple(self, ri, var, put_type): + line = f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name})" + self._attr_put_line(ri, var, line) + + def attr_put(self, ri, var): + raise Exception(f"Put not implemented for class type {self.type}") + + def _attr_get(self, ri, var): + raise Exception(f"Attr get not implemented for class type {self.type}") + + def attr_get(self, ri, var, first): + lines, init_lines, local_vars = self._attr_get(ri, var) + if type(lines) is str: + lines = [lines] + if type(init_lines) is str: + init_lines = [init_lines] + + kw = 'if' if first else 'else if' + ri.cw.block_start(line=f"{kw} (mnl_attr_get_type(attr) == {self.enum_name})") + if local_vars: + for local in local_vars: + ri.cw.p(local) + ri.cw.nl() + + if not self.is_multi_val(): + ri.cw.p("if (ynl_attr_validate(yarg, attr))") + ri.cw.p("return MNL_CB_ERROR;") + if self.presence_type() == 'bit': + ri.cw.p(f"{var}->_present.{self.c_name} = 1;") + + if init_lines: + ri.cw.nl() + for line in init_lines: + ri.cw.p(line) + + for line in lines: + ri.cw.p(line) + ri.cw.block_end() + + def _setter_lines(self, ri, member, presence): + raise Exception(f"Setter not implemented for class type {self.type}") + + def setter(self, ri, space, direction, deref=False, ref=None): + ref = (ref if ref else []) + [self.c_name] + var = "req" + member = f"{var}->{'.'.join(ref)}" + + code = [] + presence = '' + for i in range(0, len(ref)): + presence = f"{var}->{'.'.join(ref[:i] + [''])}_present.{ref[i]}" + if self.presence_type() == 'bit': + code.append(presence + ' = 1;') + code += self._setter_lines(ri, member, presence) + + ri.cw.write_func('static inline void', + f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}", + body=code, + args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri)) + + +class TypeUnused(Type): + def presence_type(self): + return '' + + def _attr_typol(self): + return '.type = YNL_PT_REJECT, ' + + def attr_policy(self, cw): + pass + + +class TypePad(Type): + def presence_type(self): + return '' + + def _attr_typol(self): + return '.type = YNL_PT_REJECT, ' + + def attr_policy(self, cw): + pass + + +class TypeScalar(Type): + def __init__(self, family, attr_set, attr, value): + super().__init__(family, attr_set, attr, value) + + self.byte_order_comment = '' + if 'byte-order' in attr: + self.byte_order_comment = f" /* {attr['byte-order']} */" + + # Added by resolve(): + self.is_bitfield = None + delattr(self, "is_bitfield") + self.type_name = None + delattr(self, "type_name") + + def resolve(self): + self.resolve_up(super()) + + if 'enum-as-flags' in self.attr and self.attr['enum-as-flags']: + self.is_bitfield = True + elif 'enum' in self.attr: + self.is_bitfield = self.family.consts[self.attr['enum']]['type'] == 'flags' + else: + self.is_bitfield = False + + if 'enum' in self.attr and not self.is_bitfield: + self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}" + else: + self.type_name = '__' + self.type + + def _mnl_type(self): + t = self.type + # mnl does not have a helper for signed types + if t[0] == 's': + t = 'u' + t[1:] + return t + + def _attr_policy(self, policy): + if 'flags-mask' in self.checks or self.is_bitfield: + if self.is_bitfield: + mask = self.family.consts[self.attr['enum']].get_mask() + else: + flags = self.family.consts[self.checks['flags-mask']] + flag_cnt = len(flags['entries']) + mask = (1 << flag_cnt) - 1 + return f"NLA_POLICY_MASK({policy}, 0x{mask:x})" + elif 'min' in self.checks: + return f"NLA_POLICY_MIN({policy}, {self.checks['min']})" + elif 'enum' in self.attr: + enum = self.family.consts[self.attr['enum']] + cnt = len(enum['entries']) + return f"NLA_POLICY_MAX({policy}, {cnt - 1})" + return super()._attr_policy(policy) + + def _attr_typol(self): + return f'.type = YNL_PT_U{self.type[1:]}, ' + + def arg_member(self, ri): + return [f'{self.type_name} {self.c_name}{self.byte_order_comment}'] + + def attr_put(self, ri, var): + self._attr_put_simple(ri, var, self._mnl_type()) + + def _attr_get(self, ri, var): + return f"{var}->{self.c_name} = mnl_attr_get_{self._mnl_type()}(attr);", None, None + + def _setter_lines(self, ri, member, presence): + return [f"{member} = {self.c_name};"] + + +class TypeFlag(Type): + def arg_member(self, ri): + return [] + + def _attr_typol(self): + return '.type = YNL_PT_FLAG, ' + + def attr_put(self, ri, var): + self._attr_put_line(ri, var, f"mnl_attr_put(nlh, {self.enum_name}, 0, NULL)") + + def _attr_get(self, ri, var): + return [], None, None + + def _setter_lines(self, ri, member, presence): + return [] + + +class TypeString(Type): + def arg_member(self, ri): + return [f"const char *{self.c_name}"] + + def presence_type(self): + return 'len' + + def struct_member(self, ri): + ri.cw.p(f"char *{self.c_name};") + + def _attr_typol(self): + return f'.type = YNL_PT_NUL_STR, ' + + def _attr_policy(self, policy): + mem = '{ .type = ' + policy + if 'max-len' in self.checks: + mem += ', .len = ' + str(self.checks['max-len']) + mem += ', }' + return mem + + def attr_policy(self, cw): + if self.checks.get('unterminated-ok', False): + policy = 'NLA_STRING' + else: + policy = 'NLA_NUL_STRING' + + spec = self._attr_policy(policy) + cw.p(f"\t[{self.enum_name}] = {spec},") + + def attr_put(self, ri, var): + self._attr_put_simple(ri, var, 'strz') + + def _attr_get(self, ri, var): + len_mem = var + '->_present.' + self.c_name + '_len' + return [f"{len_mem} = len;", + f"{var}->{self.c_name} = malloc(len + 1);", + f"memcpy({var}->{self.c_name}, mnl_attr_get_str(attr), len);", + f"{var}->{self.c_name}[len] = 0;"], \ + ['len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr));'], \ + ['unsigned int len;'] + + def _setter_lines(self, ri, member, presence): + return [f"free({member});", + f"{presence}_len = strlen({self.c_name});", + f"{member} = malloc({presence}_len + 1);", + f'memcpy({member}, {self.c_name}, {presence}_len);', + f'{member}[{presence}_len] = 0;'] + + +class TypeBinary(Type): + def arg_member(self, ri): + return [f"const void *{self.c_name}", 'size_t len'] + + def presence_type(self): + return 'len' + + def struct_member(self, ri): + ri.cw.p(f"void *{self.c_name};") + + def _attr_typol(self): + return f'.type = YNL_PT_BINARY,' + + def _attr_policy(self, policy): + mem = '{ ' + if len(self.checks) == 1 and 'min-len' in self.checks: + mem += '.len = ' + str(self.checks['min-len']) + elif len(self.checks) == 0: + mem += '.type = NLA_BINARY' + else: + raise Exception('One or more of binary type checks not implemented, yet') + mem += ', }' + return mem + + def attr_put(self, ri, var): + self._attr_put_line(ri, var, f"mnl_attr_put(nlh, {self.enum_name}, " + + f"{var}->_present.{self.c_name}_len, {var}->{self.c_name})") + + def _attr_get(self, ri, var): + len_mem = var + '->_present.' + self.c_name + '_len' + return [f"{len_mem} = len;", + f"{var}->{self.c_name} = malloc(len);", + f"memcpy({var}->{self.c_name}, mnl_attr_get_payload(attr), len);"], \ + ['len = mnl_attr_get_payload_len(attr);'], \ + ['unsigned int len;'] + + def _setter_lines(self, ri, member, presence): + return [f"free({member});", + f"{member} = malloc({presence}_len);", + f'memcpy({member}, {self.c_name}, {presence}_len);'] + + +class TypeNest(Type): + def _complex_member_type(self, ri): + return f"struct {self.nested_render_name}" + + def free(self, ri, var, ref): + ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name});') + + def _attr_typol(self): + return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' + + def _attr_policy(self, policy): + return 'NLA_POLICY_NESTED(' + self.nested_render_name + '_nl_policy)' + + def attr_put(self, ri, var): + self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " + + f"{self.enum_name}, &{var}->{self.c_name})") + + def _attr_get(self, ri, var): + get_lines = [f"{self.nested_render_name}_parse(&parg, attr);"] + init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;", + f"parg.data = &{var}->{self.c_name};"] + return get_lines, init_lines, None + + def setter(self, ri, space, direction, deref=False, ref=None): + ref = (ref if ref else []) + [self.c_name] + + for _, attr in ri.family.pure_nested_structs[self.nested_attrs].member_list(): + attr.setter(ri, self.nested_attrs, direction, deref=deref, ref=ref) + + +class TypeMultiAttr(Type): + def is_multi_val(self): + return True + + def presence_type(self): + return 'count' + + def _complex_member_type(self, ri): + if 'type' not in self.attr or self.attr['type'] == 'nest': + return f"struct {self.nested_render_name}" + elif self.attr['type'] in scalars: + scalar_pfx = '__' if ri.ku_space == 'user' else '' + return scalar_pfx + self.attr['type'] + else: + raise Exception(f"Sub-type {self.attr['type']} not supported yet") + + def free_needs_iter(self): + return 'type' not in self.attr or self.attr['type'] == 'nest' + + def free(self, ri, var, ref): + if 'type' not in self.attr or self.attr['type'] == 'nest': + ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)") + ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);') + + def _attr_typol(self): + if 'type' not in self.attr or self.attr['type'] == 'nest': + return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' + elif self.attr['type'] in scalars: + return f".type = YNL_PT_U{self.attr['type'][1:]}, " + else: + raise Exception(f"Sub-type {self.attr['type']} not supported yet") + + def _attr_get(self, ri, var): + return f'{var}->n_{self.c_name}++;', None, None + + +class TypeArrayNest(Type): + def is_multi_val(self): + return True + + def presence_type(self): + return 'count' + + def _complex_member_type(self, ri): + if 'sub-type' not in self.attr or self.attr['sub-type'] == 'nest': + return f"struct {self.nested_render_name}" + elif self.attr['sub-type'] in scalars: + scalar_pfx = '__' if ri.ku_space == 'user' else '' + return scalar_pfx + self.attr['sub-type'] + else: + raise Exception(f"Sub-type {self.attr['sub-type']} not supported yet") + + def _attr_typol(self): + return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' + + def _attr_get(self, ri, var): + local_vars = ['const struct nlattr *attr2;'] + get_lines = [f'attr_{self.c_name} = attr;', + 'mnl_attr_for_each_nested(attr2, attr)', + f'\t{var}->n_{self.c_name}++;'] + return get_lines, None, local_vars + + +class TypeNestTypeValue(Type): + def _complex_member_type(self, ri): + return f"struct {self.nested_render_name}" + + def _attr_typol(self): + return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' + + def _attr_get(self, ri, var): + prev = 'attr' + tv_args = '' + get_lines = [] + local_vars = [] + init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;", + f"parg.data = &{var}->{self.c_name};"] + if 'type-value' in self.attr: + tv_names = [c_lower(x) for x in self.attr["type-value"]] + local_vars += [f'const struct nlattr *attr_{", *attr_".join(tv_names)};'] + local_vars += [f'__u32 {", ".join(tv_names)};'] + for level in self.attr["type-value"]: + level = c_lower(level) + get_lines += [f'attr_{level} = mnl_attr_get_payload({prev});'] + get_lines += [f'{level} = mnl_attr_get_type(attr_{level});'] + prev = 'attr_' + level + + tv_args = f", {', '.join(tv_names)}" + + get_lines += [f"{self.nested_render_name}_parse(&parg, {prev}{tv_args});"] + return get_lines, init_lines, local_vars + + +class Struct: + def __init__(self, family, space_name, type_list=None, inherited=None): + self.family = family + self.space_name = space_name + self.attr_set = family.attr_sets[space_name] + # Use list to catch comparisons with empty sets + self._inherited = inherited if inherited is not None else [] + self.inherited = [] + + self.nested = type_list is None + if family.name == c_lower(space_name): + self.render_name = f"{family.name}" + else: + self.render_name = f"{family.name}_{c_lower(space_name)}" + self.struct_name = 'struct ' + self.render_name + self.ptr_name = self.struct_name + ' *' + + self.request = False + self.reply = False + + self.attr_list = [] + self.attrs = dict() + if type_list: + for t in type_list: + self.attr_list.append((t, self.attr_set[t]),) + else: + for t in self.attr_set: + self.attr_list.append((t, self.attr_set[t]),) + + max_val = 0 + self.attr_max_val = None + for name, attr in self.attr_list: + if attr.value >= max_val: + max_val = attr.value + self.attr_max_val = attr + self.attrs[name] = attr + + def __iter__(self): + yield from self.attrs + + def __getitem__(self, key): + return self.attrs[key] + + def member_list(self): + return self.attr_list + + def set_inherited(self, new_inherited): + if self._inherited != new_inherited: + raise Exception("Inheriting different members not supported") + self.inherited = [c_lower(x) for x in sorted(self._inherited)] + + +class EnumEntry: + def __init__(self, enum_set, yaml, prev, value_start): + if isinstance(yaml, str): + self.name = yaml + yaml = {} + self.doc = '' + else: + self.name = yaml['name'] + self.doc = yaml.get('doc', '') + + self.yaml = yaml + self.enum_set = enum_set + self.c_name = c_upper(enum_set.value_pfx + self.name) + + if 'value' in yaml: + self.value = yaml['value'] + if prev: + self.value_change = (self.value != prev.value + 1) + elif prev: + self.value_change = False + self.value = prev.value + 1 + else: + self.value = value_start + self.value_change = (self.value != 0) + + self.value_change = self.value_change or self.enum_set['type'] == 'flags' + + def __getitem__(self, key): + return self.yaml[key] + + def __contains__(self, key): + return key in self.yaml + + def has_doc(self): + return bool(self.doc) + + # raw value, i.e. the id in the enum, unlike user value which is a mask for flags + def raw_value(self): + return self.value + + # user value, same as raw value for enums, for flags it's the mask + def user_value(self): + if self.enum_set['type'] == 'flags': + return 1 << self.value + else: + return self.value + + +class EnumSet: + def __init__(self, family, yaml): + self.yaml = yaml + self.family = family + + self.render_name = c_lower(family.name + '-' + yaml['name']) + self.enum_name = 'enum ' + self.render_name + + self.value_pfx = yaml.get('name-prefix', f"{family.name}-{yaml['name']}-") + + self.type = yaml['type'] + + prev_entry = None + value_start = self.yaml.get('value-start', 0) + self.entries = {} + self.entry_list = [] + for entry in self.yaml['entries']: + e = EnumEntry(self, entry, prev_entry, value_start) + self.entries[e.name] = e + self.entry_list.append(e) + prev_entry = e + + def __getitem__(self, key): + return self.yaml[key] + + def __contains__(self, key): + return key in self.yaml + + def has_doc(self): + if 'doc' in self.yaml: + return True + for entry in self.entry_list: + if entry.has_doc(): + return True + return False + + def get_mask(self): + mask = 0 + idx = self.yaml.get('value-start', 0) + for _ in self.entry_list: + mask |= 1 << idx + idx += 1 + return mask + + +class AttrSet(SpecAttrSet): + def __init__(self, family, yaml): + super().__init__(family, yaml) + + if self.subset_of is None: + if 'name-prefix' in yaml: + pfx = yaml['name-prefix'] + elif self.name == family.name: + pfx = family.name + '-a-' + else: + pfx = f"{family.name}-a-{self.name}-" + self.name_prefix = c_upper(pfx) + self.max_name = c_upper(self.yaml.get('attr-max-name', f"{self.name_prefix}max")) + else: + self.name_prefix = family.attr_sets[self.subset_of].name_prefix + self.max_name = family.attr_sets[self.subset_of].max_name + + # Added by resolve: + self.c_name = None + delattr(self, "c_name") + + def resolve(self): + self.c_name = c_lower(self.name) + if self.c_name in _C_KW: + self.c_name += '_' + if self.c_name == self.family.c_name: + self.c_name = '' + + def new_attr(self, elem, value): + if 'multi-attr' in elem and elem['multi-attr']: + return TypeMultiAttr(self.family, self, elem, value) + elif elem['type'] in scalars: + return TypeScalar(self.family, self, elem, value) + elif elem['type'] == 'unused': + return TypeUnused(self.family, self, elem, value) + elif elem['type'] == 'pad': + return TypePad(self.family, self, elem, value) + elif elem['type'] == 'flag': + return TypeFlag(self.family, self, elem, value) + elif elem['type'] == 'string': + return TypeString(self.family, self, elem, value) + elif elem['type'] == 'binary': + return TypeBinary(self.family, self, elem, value) + elif elem['type'] == 'nest': + return TypeNest(self.family, self, elem, value) + elif elem['type'] == 'array-nest': + return TypeArrayNest(self.family, self, elem, value) + elif elem['type'] == 'nest-type-value': + return TypeNestTypeValue(self.family, self, elem, value) + else: + raise Exception(f"No typed class for type {elem['type']}") + + +class Operation(SpecOperation): + def __init__(self, family, yaml, req_value, rsp_value): + super().__init__(family, yaml, req_value, rsp_value) + + if req_value != rsp_value: + raise Exception("Directional messages not supported by codegen") + + self.render_name = family.name + '_' + c_lower(self.name) + + self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \ + ('dump' in yaml and 'request' in yaml['dump']) + + # Added by resolve: + self.enum_name = None + delattr(self, "enum_name") + + def resolve(self): + self.resolve_up(super()) + + if not self.is_async: + self.enum_name = self.family.op_prefix + c_upper(self.name) + else: + self.enum_name = self.family.async_op_prefix + c_upper(self.name) + + def add_notification(self, op): + if 'notify' not in self.yaml: + self.yaml['notify'] = dict() + self.yaml['notify']['reply'] = self.yaml['do']['reply'] + self.yaml['notify']['cmds'] = [] + self.yaml['notify']['cmds'].append(op) + + +class Family(SpecFamily): + def __init__(self, file_name): + # Added by resolve: + self.c_name = None + delattr(self, "c_name") + self.op_prefix = None + delattr(self, "op_prefix") + self.async_op_prefix = None + delattr(self, "async_op_prefix") + self.mcgrps = None + delattr(self, "mcgrps") + self.consts = None + delattr(self, "consts") + self.hooks = None + delattr(self, "hooks") + + super().__init__(file_name) + + self.fam_key = c_upper(self.yaml.get('c-family-name', self.yaml["name"] + '_FAMILY_NAME')) + self.ver_key = c_upper(self.yaml.get('c-version-name', self.yaml["name"] + '_FAMILY_VERSION')) + + if 'definitions' not in self.yaml: + self.yaml['definitions'] = [] + + if 'uapi-header' in self.yaml: + self.uapi_header = self.yaml['uapi-header'] + else: + self.uapi_header = f"linux/{self.name}.h" + + def resolve(self): + self.resolve_up(super()) + + if self.yaml.get('protocol', 'genetlink') not in {'genetlink', 'genetlink-c', 'genetlink-legacy'}: + raise Exception("Codegen only supported for genetlink") + + self.c_name = c_lower(self.name) + if 'name-prefix' in self.yaml['operations']: + self.op_prefix = c_upper(self.yaml['operations']['name-prefix']) + else: + self.op_prefix = c_upper(self.yaml['name'] + '-cmd-') + if 'async-prefix' in self.yaml['operations']: + self.async_op_prefix = c_upper(self.yaml['operations']['async-prefix']) + else: + self.async_op_prefix = self.op_prefix + + self.mcgrps = self.yaml.get('mcast-groups', {'list': []}) + + self.consts = dict() + + self.hooks = dict() + for when in ['pre', 'post']: + self.hooks[when] = dict() + for op_mode in ['do', 'dump']: + self.hooks[when][op_mode] = dict() + self.hooks[when][op_mode]['set'] = set() + self.hooks[when][op_mode]['list'] = [] + + # dict space-name -> 'request': set(attrs), 'reply': set(attrs) + self.root_sets = dict() + # dict space-name -> set('request', 'reply') + self.pure_nested_structs = dict() + self.all_notify = dict() + + self._mock_up_events() + + self._dictify() + self._load_root_sets() + self._load_nested_sets() + self._load_all_notify() + self._load_hooks() + + self.kernel_policy = self.yaml.get('kernel-policy', 'split') + if self.kernel_policy == 'global': + self._load_global_policy() + + def new_attr_set(self, elem): + return AttrSet(self, elem) + + def new_operation(self, elem, req_value, rsp_value): + return Operation(self, elem, req_value, rsp_value) + + # Fake a 'do' equivalent of all events, so that we can render their response parsing + def _mock_up_events(self): + for op in self.yaml['operations']['list']: + if 'event' in op: + op['do'] = { + 'reply': { + 'attributes': op['event']['attributes'] + } + } + + def _dictify(self): + for elem in self.yaml['definitions']: + if elem['type'] == 'enum' or elem['type'] == 'flags': + self.consts[elem['name']] = EnumSet(self, elem) + else: + self.consts[elem['name']] = elem + + ntf = [] + for msg in self.msgs.values(): + if 'notify' in msg: + ntf.append(msg) + for n in ntf: + self.ops[n['notify']].add_notification(n) + + def _load_root_sets(self): + for op_name, op in self.ops.items(): + if 'attribute-set' not in op: + continue + + req_attrs = set() + rsp_attrs = set() + for op_mode in ['do', 'dump']: + if op_mode in op and 'request' in op[op_mode]: + req_attrs.update(set(op[op_mode]['request']['attributes'])) + if op_mode in op and 'reply' in op[op_mode]: + rsp_attrs.update(set(op[op_mode]['reply']['attributes'])) + + if op['attribute-set'] not in self.root_sets: + self.root_sets[op['attribute-set']] = {'request': req_attrs, 'reply': rsp_attrs} + else: + self.root_sets[op['attribute-set']]['request'].update(req_attrs) + self.root_sets[op['attribute-set']]['reply'].update(rsp_attrs) + + def _load_nested_sets(self): + for root_set, rs_members in self.root_sets.items(): + for attr, spec in self.attr_sets[root_set].items(): + if 'nested-attributes' in spec: + inherit = set() + nested = spec['nested-attributes'] + if nested not in self.root_sets: + self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) + if attr in rs_members['request']: + self.pure_nested_structs[nested].request = True + if attr in rs_members['reply']: + self.pure_nested_structs[nested].reply = True + + if 'type-value' in spec: + if nested in self.root_sets: + raise Exception("Inheriting members to a space used as root not supported") + inherit.update(set(spec['type-value'])) + elif spec['type'] == 'array-nest': + inherit.add('idx') + self.pure_nested_structs[nested].set_inherited(inherit) + + def _load_all_notify(self): + for op_name, op in self.ops.items(): + if not op: + continue + + if 'notify' in op: + self.all_notify[op_name] = op['notify']['cmds'] + + def _load_global_policy(self): + global_set = set() + attr_set_name = None + for op_name, op in self.ops.items(): + if not op: + continue + if 'attribute-set' not in op: + continue + + if attr_set_name is None: + attr_set_name = op['attribute-set'] + if attr_set_name != op['attribute-set']: + raise Exception('For a global policy all ops must use the same set') + + for op_mode in ['do', 'dump']: + if op_mode in op: + global_set.update(op[op_mode].get('request', [])) + + self.global_policy = [] + self.global_policy_set = attr_set_name + for attr in self.attr_sets[attr_set_name]: + if attr in global_set: + self.global_policy.append(attr) + + def _load_hooks(self): + for op in self.ops.values(): + for op_mode in ['do', 'dump']: + if op_mode not in op: + continue + for when in ['pre', 'post']: + if when not in op[op_mode]: + continue + name = op[op_mode][when] + if name in self.hooks[when][op_mode]['set']: + continue + self.hooks[when][op_mode]['set'].add(name) + self.hooks[when][op_mode]['list'].append(name) + + +class RenderInfo: + def __init__(self, cw, family, ku_space, op, op_name, op_mode, attr_set=None): + self.family = family + self.nl = cw.nlib + self.ku_space = ku_space + self.op = op + self.op_name = op_name + self.op_mode = op_mode + + # 'do' and 'dump' response parsing is identical + if op_mode != 'do' and 'dump' in op and 'do' in op and 'reply' in op['do'] and \ + op["do"]["reply"] == op["dump"]["reply"]: + self.type_consistent = True + else: + self.type_consistent = op_mode == 'event' + + self.attr_set = attr_set + if not self.attr_set: + self.attr_set = op['attribute-set'] + + if op: + self.type_name = c_lower(op_name) + else: + self.type_name = c_lower(attr_set) + + self.cw = cw + + self.struct = dict() + for op_dir in ['request', 'reply']: + if op and op_dir in op[op_mode]: + self.struct[op_dir] = Struct(family, self.attr_set, + type_list=op[op_mode][op_dir]['attributes']) + if op_mode == 'event': + self.struct['reply'] = Struct(family, self.attr_set, type_list=op['event']['attributes']) + + +class CodeWriter: + def __init__(self, nlib, out_file): + self.nlib = nlib + + self._nl = False + self._silent_block = False + self._ind = 0 + self._out = out_file + + @classmethod + def _is_cond(cls, line): + return line.startswith('if') or line.startswith('while') or line.startswith('for') + + def p(self, line, add_ind=0): + if self._nl: + self._out.write('\n') + self._nl = False + ind = self._ind + if line[-1] == ':': + ind -= 1 + if self._silent_block: + ind += 1 + self._silent_block = line.endswith(')') and CodeWriter._is_cond(line) + if add_ind: + ind += add_ind + self._out.write('\t' * ind + line + '\n') + + def nl(self): + self._nl = True + + def block_start(self, line=''): + if line: + line = line + ' ' + self.p(line + '{') + self._ind += 1 + + def block_end(self, line=''): + if line and line[0] not in {';', ','}: + line = ' ' + line + self._ind -= 1 + self.p('}' + line) + + def write_doc_line(self, doc, indent=True): + words = doc.split() + line = ' *' + for word in words: + if len(line) + len(word) >= 79: + self.p(line) + line = ' *' + if indent: + line += ' ' + line += ' ' + word + self.p(line) + + def write_func_prot(self, qual_ret, name, args=None, doc=None, suffix=''): + if not args: + args = ['void'] + + if doc: + self.p('/*') + self.p(' * ' + doc) + self.p(' */') + + oneline = qual_ret + if qual_ret[-1] != '*': + oneline += ' ' + oneline += f"{name}({', '.join(args)}){suffix}" + + if len(oneline) < 80: + self.p(oneline) + return + + v = qual_ret + if len(v) > 3: + self.p(v) + v = '' + elif qual_ret[-1] != '*': + v += ' ' + v += name + '(' + ind = '\t' * (len(v) // 8) + ' ' * (len(v) % 8) + delta_ind = len(v) - len(ind) + v += args[0] + i = 1 + while i < len(args): + next_len = len(v) + len(args[i]) + if v[0] == '\t': + next_len += delta_ind + if next_len > 76: + self.p(v + ',') + v = ind + else: + v += ', ' + v += args[i] + i += 1 + self.p(v + ')' + suffix) + + def write_func_lvar(self, local_vars): + if not local_vars: + return + + if type(local_vars) is str: + local_vars = [local_vars] + + local_vars.sort(key=len, reverse=True) + for var in local_vars: + self.p(var) + self.nl() + + def write_func(self, qual_ret, name, body, args=None, local_vars=None): + self.write_func_prot(qual_ret=qual_ret, name=name, args=args) + self.write_func_lvar(local_vars=local_vars) + + self.block_start() + for line in body: + self.p(line) + self.block_end() + + def writes_defines(self, defines): + longest = 0 + for define in defines: + if len(define[0]) > longest: + longest = len(define[0]) + longest = ((longest + 8) // 8) * 8 + for define in defines: + line = '#define ' + define[0] + line += '\t' * ((longest - len(define[0]) + 7) // 8) + if type(define[1]) is int: + line += str(define[1]) + elif type(define[1]) is str: + line += '"' + define[1] + '"' + self.p(line) + + def write_struct_init(self, members): + longest = max([len(x[0]) for x in members]) + longest += 1 # because we prepend a . + longest = ((longest + 8) // 8) * 8 + for one in members: + line = '.' + one[0] + line += '\t' * ((longest - len(one[0]) - 1 + 7) // 8) + line += '= ' + one[1] + ',' + self.p(line) + + +scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64'} + +direction_to_suffix = { + 'reply': '_rsp', + 'request': '_req', + '': '' +} + +op_mode_to_wrapper = { + 'do': '', + 'dump': '_list', + 'notify': '_ntf', + 'event': '', +} + +_C_KW = { + 'do' +} + + +def rdir(direction): + if direction == 'reply': + return 'request' + if direction == 'request': + return 'reply' + return direction + + +def op_prefix(ri, direction, deref=False): + suffix = f"_{ri.type_name}" + + if not ri.op_mode or ri.op_mode == 'do': + suffix += f"{direction_to_suffix[direction]}" + else: + if direction == 'request': + suffix += '_req_dump' + else: + if ri.type_consistent: + if deref: + suffix += f"{direction_to_suffix[direction]}" + else: + suffix += op_mode_to_wrapper[ri.op_mode] + else: + suffix += '_rsp' + suffix += '_dump' if deref else '_list' + + return f"{ri.family['name']}{suffix}" + + +def type_name(ri, direction, deref=False): + return f"struct {op_prefix(ri, direction, deref=deref)}" + + +def print_prototype(ri, direction, terminate=True, doc=None): + suffix = ';' if terminate else '' + + fname = ri.op.render_name + if ri.op_mode == 'dump': + fname += '_dump' + + args = ['struct ynl_sock *ys'] + if 'request' in ri.op[ri.op_mode]: + args.append(f"{type_name(ri, direction)} *" + f"{direction_to_suffix[direction][1:]}") + + ret = 'int' + if 'reply' in ri.op[ri.op_mode]: + ret = f"{type_name(ri, rdir(direction))} *" + + ri.cw.write_func_prot(ret, fname, args, doc=doc, suffix=suffix) + + +def print_req_prototype(ri): + print_prototype(ri, "request", doc=ri.op['doc']) + + +def print_dump_prototype(ri): + print_prototype(ri, "request") + + +def put_typol_fwd(cw, struct): + cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;') + + +def put_typol(cw, struct): + type_max = struct.attr_set.max_name + cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =') + + for _, arg in struct.member_list(): + arg.attr_typol(cw) + + cw.block_end(line=';') + cw.nl() + + cw.block_start(line=f'struct ynl_policy_nest {struct.render_name}_nest =') + cw.p(f'.max_attr = {type_max},') + cw.p(f'.table = {struct.render_name}_policy,') + cw.block_end(line=';') + cw.nl() + + +def put_req_nested(ri, struct): + func_args = ['struct nlmsghdr *nlh', + 'unsigned int attr_type', + f'{struct.ptr_name}obj'] + + ri.cw.write_func_prot('int', f'{struct.render_name}_put', func_args) + ri.cw.block_start() + ri.cw.write_func_lvar('struct nlattr *nest;') + + ri.cw.p("nest = mnl_attr_nest_start(nlh, attr_type);") + + for _, arg in struct.member_list(): + arg.attr_put(ri, "obj") + + ri.cw.p("mnl_attr_nest_end(nlh, nest);") + + ri.cw.nl() + ri.cw.p('return 0;') + ri.cw.block_end() + ri.cw.nl() + + +def _multi_parse(ri, struct, init_lines, local_vars): + if struct.nested: + iter_line = "mnl_attr_for_each_nested(attr, nested)" + else: + iter_line = "mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr))" + + array_nests = set() + multi_attrs = set() + needs_parg = False + for arg, aspec in struct.member_list(): + if aspec['type'] == 'array-nest': + local_vars.append(f'const struct nlattr *attr_{aspec.c_name};') + array_nests.add(arg) + if 'multi-attr' in aspec: + multi_attrs.add(arg) + needs_parg |= 'nested-attributes' in aspec + if array_nests or multi_attrs: + local_vars.append('int i;') + if needs_parg: + local_vars.append('struct ynl_parse_arg parg;') + init_lines.append('parg.ys = yarg->ys;') + + ri.cw.block_start() + ri.cw.write_func_lvar(local_vars) + + for line in init_lines: + ri.cw.p(line) + ri.cw.nl() + + for arg in struct.inherited: + ri.cw.p(f'dst->{arg} = {arg};') + + ri.cw.nl() + ri.cw.block_start(line=iter_line) + + first = True + for _, arg in struct.member_list(): + arg.attr_get(ri, 'dst', first=first) + first = False + + ri.cw.block_end() + ri.cw.nl() + + for anest in sorted(array_nests): + aspec = struct[anest] + + ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p('i = 0;') + ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") + ri.cw.block_start(line=f"mnl_attr_for_each_nested(attr, attr_{aspec.c_name})") + ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];") + ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr, mnl_attr_get_type(attr)))") + ri.cw.p('return MNL_CB_ERROR;') + ri.cw.p('i++;') + ri.cw.block_end() + ri.cw.block_end() + ri.cw.nl() + + for anest in sorted(multi_attrs): + aspec = struct[anest] + ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p('i = 0;') + if 'nested-attributes' in aspec: + ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") + ri.cw.block_start(line=iter_line) + ri.cw.block_start(line=f"if (mnl_attr_get_type(attr) == {aspec.enum_name})") + if 'nested-attributes' in aspec: + ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];") + ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr))") + ri.cw.p('return MNL_CB_ERROR;') + elif aspec['type'] in scalars: + t = aspec['type'] + if t[0] == 's': + t = 'u' + t[1:] + ri.cw.p(f"dst->{aspec.c_name}[i] = mnl_attr_get_{t}(attr);") + else: + raise Exception('Nest parsing type not supported yet') + ri.cw.p('i++;') + ri.cw.block_end() + ri.cw.block_end() + ri.cw.block_end() + ri.cw.nl() + + if struct.nested: + ri.cw.p('return 0;') + else: + ri.cw.p('return MNL_CB_OK;') + ri.cw.block_end() + ri.cw.nl() + + +def parse_rsp_nested(ri, struct): + func_args = ['struct ynl_parse_arg *yarg', + 'const struct nlattr *nested'] + for arg in struct.inherited: + func_args.append('__u32 ' + arg) + + local_vars = ['const struct nlattr *attr;', + f'{struct.ptr_name}dst = yarg->data;'] + init_lines = [] + + ri.cw.write_func_prot('int', f'{struct.render_name}_parse', func_args) + + _multi_parse(ri, struct, init_lines, local_vars) + + +def parse_rsp_msg(ri, deref=False): + if 'reply' not in ri.op[ri.op_mode] and ri.op_mode != 'event': + return + + func_args = ['const struct nlmsghdr *nlh', + 'void *data'] + + local_vars = [f'{type_name(ri, "reply", deref=deref)} *dst;', + 'struct ynl_parse_arg *yarg = data;', + 'const struct nlattr *attr;'] + init_lines = ['dst = yarg->data;'] + + ri.cw.write_func_prot('int', f'{op_prefix(ri, "reply", deref=deref)}_parse', func_args) + + _multi_parse(ri, ri.struct["reply"], init_lines, local_vars) + + +def print_req(ri): + ret_ok = '0' + ret_err = '-1' + direction = "request" + local_vars = ['struct nlmsghdr *nlh;', + 'int len, err;'] + + if 'reply' in ri.op[ri.op_mode]: + ret_ok = 'rsp' + ret_err = 'NULL' + local_vars += [f'{type_name(ri, rdir(direction))} *rsp;', + 'struct ynl_parse_arg yarg = { .ys = ys, };'] + + print_prototype(ri, direction, terminate=False) + ri.cw.block_start() + ri.cw.write_func_lvar(local_vars) + + ri.cw.p(f"nlh = ynl_gemsg_start_req(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);") + + ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;") + if 'reply' in ri.op[ri.op_mode]: + ri.cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + ri.cw.nl() + for _, attr in ri.struct["request"].member_list(): + attr.attr_put(ri, "req") + ri.cw.nl() + + ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') + ri.cw.p('if (err < 0)') + ri.cw.p(f"return {ret_err};") + ri.cw.nl() + ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') + ri.cw.p('if (len < 0)') + ri.cw.p(f"return {ret_err};") + ri.cw.nl() + + if 'reply' in ri.op[ri.op_mode]: + ri.cw.p('rsp = calloc(1, sizeof(*rsp));') + ri.cw.p('yarg.data = rsp;') + ri.cw.nl() + ri.cw.p(f"err = {ri.nl.parse_cb_run(op_prefix(ri, 'reply') + '_parse', '&yarg', False)};") + ri.cw.p('if (err < 0)') + ri.cw.p('goto err_free;') + ri.cw.nl() + + ri.cw.p('err = ynl_recv_ack(ys, err);') + ri.cw.p('if (err)') + ri.cw.p('goto err_free;') + ri.cw.nl() + ri.cw.p(f"return {ret_ok};") + ri.cw.nl() + ri.cw.p('err_free:') + + if 'reply' in ri.op[ri.op_mode]: + ri.cw.p(f"{call_free(ri, rdir(direction), 'rsp')}") + ri.cw.p(f"return {ret_err};") + ri.cw.block_end() + + +def print_dump(ri): + direction = "request" + print_prototype(ri, direction, terminate=False) + ri.cw.block_start() + local_vars = ['struct ynl_dump_state yds = {};', + 'struct nlmsghdr *nlh;', + 'int len, err;'] + + for var in local_vars: + ri.cw.p(f'{var}') + ri.cw.nl() + + ri.cw.p('yds.ys = ys;') + ri.cw.p(f"yds.alloc_sz = sizeof({type_name(ri, rdir(direction))});") + ri.cw.p(f"yds.cb = {op_prefix(ri, 'reply', deref=True)}_parse;") + ri.cw.p(f"yds.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + ri.cw.nl() + ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);") + + if "request" in ri.op[ri.op_mode]: + ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;") + ri.cw.nl() + for _, attr in ri.struct["request"].member_list(): + attr.attr_put(ri, "req") + ri.cw.nl() + + ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') + ri.cw.p('if (err < 0)') + ri.cw.p('return NULL;') + ri.cw.nl() + + ri.cw.block_start(line='do') + ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') + ri.cw.p('if (len < 0)') + ri.cw.p('goto free_list;') + ri.cw.nl() + ri.cw.p(f"err = {ri.nl.parse_cb_run('ynl_dump_trampoline', '&yds', False, indent=2)};") + ri.cw.p('if (err < 0)') + ri.cw.p('goto free_list;') + ri.cw.block_end(line='while (err > 0);') + ri.cw.nl() + + ri.cw.p('return yds.first;') + ri.cw.nl() + ri.cw.p('free_list:') + ri.cw.p(call_free(ri, rdir(direction), 'yds.first')) + ri.cw.p('return NULL;') + ri.cw.block_end() + + +def call_free(ri, direction, var): + return f"{op_prefix(ri, direction)}_free({var});" + + +def free_arg_name(direction): + if direction: + return direction_to_suffix[direction][1:] + return 'obj' + + +def print_free_prototype(ri, direction, suffix=';'): + name = op_prefix(ri, direction) + arg = free_arg_name(direction) + ri.cw.write_func_prot('void', f"{name}_free", [f"struct {name} *{arg}"], suffix=suffix) + + +def _print_type(ri, direction, struct): + suffix = f'_{ri.type_name}{direction_to_suffix[direction]}' + + if ri.op_mode == 'dump': + suffix += '_dump' + + ri.cw.block_start(line=f"struct {ri.family['name']}{suffix}") + + meta_started = False + for _, attr in struct.member_list(): + for type_filter in ['len', 'bit']: + line = attr.presence_member(ri.ku_space, type_filter) + if line: + if not meta_started: + ri.cw.block_start(line=f"struct") + meta_started = True + ri.cw.p(line) + if meta_started: + ri.cw.block_end(line='_present;') + ri.cw.nl() + + for arg in struct.inherited: + ri.cw.p(f"__u32 {arg};") + + for _, attr in struct.member_list(): + attr.struct_member(ri) + + ri.cw.block_end(line=';') + ri.cw.nl() + + +def print_type(ri, direction): + _print_type(ri, direction, ri.struct[direction]) + + +def print_type_full(ri, struct): + _print_type(ri, "", struct) + + +def print_type_helpers(ri, direction, deref=False): + print_free_prototype(ri, direction) + + if ri.ku_space == 'user' and direction == 'request': + for _, attr in ri.struct[direction].member_list(): + attr.setter(ri, ri.attr_set, direction, deref=deref) + ri.cw.nl() + + +def print_req_type_helpers(ri): + print_type_helpers(ri, "request") + + +def print_rsp_type_helpers(ri): + if 'reply' not in ri.op[ri.op_mode]: + return + print_type_helpers(ri, "reply") + + +def print_parse_prototype(ri, direction, terminate=True): + suffix = "_rsp" if direction == "reply" else "_req" + term = ';' if terminate else '' + + ri.cw.write_func_prot('void', f"{ri.op.render_name}{suffix}_parse", + ['const struct nlattr **tb', + f"struct {ri.op.render_name}{suffix} *req"], + suffix=term) + + +def print_req_type(ri): + print_type(ri, "request") + + +def print_rsp_type(ri): + if (ri.op_mode == 'do' or ri.op_mode == 'dump') and 'reply' in ri.op[ri.op_mode]: + direction = 'reply' + elif ri.op_mode == 'event': + direction = 'reply' + else: + return + print_type(ri, direction) + + +def print_wrapped_type(ri): + ri.cw.block_start(line=f"{type_name(ri, 'reply')}") + if ri.op_mode == 'dump': + ri.cw.p(f"{type_name(ri, 'reply')} *next;") + elif ri.op_mode == 'notify' or ri.op_mode == 'event': + ri.cw.p('__u16 family;') + ri.cw.p('__u8 cmd;') + ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);") + ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));") + ri.cw.block_end(line=';') + ri.cw.nl() + print_free_prototype(ri, 'reply') + ri.cw.nl() + + +def _free_type_members_iter(ri, struct): + for _, attr in struct.member_list(): + if attr.free_needs_iter(): + ri.cw.p('unsigned int i;') + ri.cw.nl() + break + + +def _free_type_members(ri, var, struct, ref=''): + for _, attr in struct.member_list(): + attr.free(ri, var, ref) + + +def _free_type(ri, direction, struct): + var = free_arg_name(direction) + + print_free_prototype(ri, direction, suffix='') + ri.cw.block_start() + _free_type_members_iter(ri, struct) + _free_type_members(ri, var, struct) + if direction: + ri.cw.p(f'free({var});') + ri.cw.block_end() + ri.cw.nl() + + +def free_rsp_nested(ri, struct): + _free_type(ri, "", struct) + + +def print_rsp_free(ri): + if 'reply' not in ri.op[ri.op_mode]: + return + _free_type(ri, 'reply', ri.struct['reply']) + + +def print_dump_type_free(ri): + sub_type = type_name(ri, 'reply') + + print_free_prototype(ri, 'reply', suffix='') + ri.cw.block_start() + ri.cw.p(f"{sub_type} *next = rsp;") + ri.cw.nl() + ri.cw.block_start(line='while (next)') + _free_type_members_iter(ri, ri.struct['reply']) + ri.cw.p('rsp = next;') + ri.cw.p('next = rsp->next;') + ri.cw.nl() + + _free_type_members(ri, 'rsp', ri.struct['reply'], ref='obj.') + ri.cw.p(f'free(rsp);') + ri.cw.block_end() + ri.cw.block_end() + ri.cw.nl() + + +def print_ntf_type_free(ri): + print_free_prototype(ri, 'reply', suffix='') + ri.cw.block_start() + _free_type_members_iter(ri, ri.struct['reply']) + _free_type_members(ri, 'rsp', ri.struct['reply'], ref='obj.') + ri.cw.p(f'free(rsp);') + ri.cw.block_end() + ri.cw.nl() + + +def print_ntf_parse_prototype(family, cw, suffix=';'): + cw.write_func_prot('struct ynl_ntf_base_type *', f"{family['name']}_ntf_parse", + ['struct ynl_sock *ys'], suffix=suffix) + + +def print_ntf_type_parse(family, cw, ku_mode): + print_ntf_parse_prototype(family, cw, suffix='') + cw.block_start() + cw.write_func_lvar(['struct genlmsghdr *genlh;', + 'struct nlmsghdr *nlh;', + 'struct ynl_parse_arg yarg = { .ys = ys, };', + 'struct ynl_ntf_base_type *rsp;', + 'int len, err;', + 'mnl_cb_t parse;']) + cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') + cw.p('if (len < (ssize_t)(sizeof(*nlh) + sizeof(*genlh)))') + cw.p('return NULL;') + cw.nl() + cw.p('nlh = (struct nlmsghdr *)ys->rx_buf;') + cw.p('genlh = mnl_nlmsg_get_payload(nlh);') + cw.nl() + cw.block_start(line='switch (genlh->cmd)') + for ntf_op in sorted(family.all_notify.keys()): + op = family.ops[ntf_op] + ri = RenderInfo(cw, family, ku_mode, op, ntf_op, "notify") + for ntf in op['notify']['cmds']: + cw.p(f"case {ntf.enum_name}:") + cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'notify')}));") + cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") + cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") + cw.p('break;') + for op_name, op in family.ops.items(): + if 'event' not in op: + continue + ri = RenderInfo(cw, family, ku_mode, op, op_name, "event") + cw.p(f"case {op.enum_name}:") + cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'event')}));") + cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") + cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") + cw.p('break;') + cw.p('default:') + cw.p('ynl_error_unknown_notification(ys, genlh->cmd);') + cw.p('return NULL;') + cw.block_end() + cw.nl() + cw.p('yarg.data = rsp->data;') + cw.nl() + cw.p(f"err = {cw.nlib.parse_cb_run('parse', '&yarg', True)};") + cw.p('if (err < 0)') + cw.p('goto err_free;') + cw.nl() + cw.p('rsp->family = nlh->nlmsg_type;') + cw.p('rsp->cmd = genlh->cmd;') + cw.p('return rsp;') + cw.nl() + cw.p('err_free:') + cw.p('free(rsp);') + cw.p('return NULL;') + cw.block_end() + cw.nl() + + +def print_req_policy_fwd(cw, struct, ri=None, terminate=True): + if terminate and ri and kernel_can_gen_family_struct(struct.family): + return + + if terminate: + prefix = 'extern ' + else: + if kernel_can_gen_family_struct(struct.family) and ri: + prefix = 'static ' + else: + prefix = '' + + suffix = ';' if terminate else ' = {' + + max_attr = struct.attr_max_val + if ri: + name = ri.op.render_name + if ri.op.dual_policy: + name += '_' + ri.op_mode + else: + name = struct.render_name + cw.p(f"{prefix}const struct nla_policy {name}_nl_policy[{max_attr.enum_name} + 1]{suffix}") + + +def print_req_policy(cw, struct, ri=None): + print_req_policy_fwd(cw, struct, ri=ri, terminate=False) + for _, arg in struct.member_list(): + arg.attr_policy(cw) + cw.p("};") + + +def kernel_can_gen_family_struct(family): + return family.proto == 'genetlink' + + +def print_kernel_op_table_fwd(family, cw, terminate): + exported = not kernel_can_gen_family_struct(family) + + if not terminate or exported: + cw.p(f"/* Ops table for {family.name} */") + + pol_to_struct = {'global': 'genl_small_ops', + 'per-op': 'genl_ops', + 'split': 'genl_split_ops'} + struct_type = pol_to_struct[family.kernel_policy] + + if family.kernel_policy == 'split': + cnt = 0 + for op in family.ops.values(): + if 'do' in op: + cnt += 1 + if 'dump' in op: + cnt += 1 + else: + cnt = len(family.ops) + + qual = 'static const' if not exported else 'const' + line = f"{qual} struct {struct_type} {family.name}_nl_ops[{cnt}]" + if terminate: + cw.p(f"extern {line};") + else: + cw.block_start(line=line + ' =') + + if not terminate: + return + + cw.nl() + for name in family.hooks['pre']['do']['list']: + cw.write_func_prot('int', c_lower(name), + ['const struct genl_split_ops *ops', + 'struct sk_buff *skb', 'struct genl_info *info'], suffix=';') + for name in family.hooks['post']['do']['list']: + cw.write_func_prot('void', c_lower(name), + ['const struct genl_split_ops *ops', + 'struct sk_buff *skb', 'struct genl_info *info'], suffix=';') + for name in family.hooks['pre']['dump']['list']: + cw.write_func_prot('int', c_lower(name), + ['struct netlink_callback *cb'], suffix=';') + for name in family.hooks['post']['dump']['list']: + cw.write_func_prot('int', c_lower(name), + ['struct netlink_callback *cb'], suffix=';') + + cw.nl() + + for op_name, op in family.ops.items(): + if op.is_async: + continue + + if 'do' in op: + name = c_lower(f"{family.name}-nl-{op_name}-doit") + cw.write_func_prot('int', name, + ['struct sk_buff *skb', 'struct genl_info *info'], suffix=';') + + if 'dump' in op: + name = c_lower(f"{family.name}-nl-{op_name}-dumpit") + cw.write_func_prot('int', name, + ['struct sk_buff *skb', 'struct netlink_callback *cb'], suffix=';') + cw.nl() + + +def print_kernel_op_table_hdr(family, cw): + print_kernel_op_table_fwd(family, cw, terminate=True) + + +def print_kernel_op_table(family, cw): + print_kernel_op_table_fwd(family, cw, terminate=False) + if family.kernel_policy == 'global' or family.kernel_policy == 'per-op': + for op_name, op in family.ops.items(): + if op.is_async: + continue + + cw.block_start() + members = [('cmd', op.enum_name)] + if 'dont-validate' in op: + members.append(('validate', + ' | '.join([c_upper('genl-dont-validate-' + x) + for x in op['dont-validate']])), ) + for op_mode in ['do', 'dump']: + if op_mode in op: + name = c_lower(f"{family.name}-nl-{op_name}-{op_mode}it") + members.append((op_mode + 'it', name)) + if family.kernel_policy == 'per-op': + struct = Struct(family, op['attribute-set'], + type_list=op['do']['request']['attributes']) + + name = c_lower(f"{family.name}-{op_name}-nl-policy") + members.append(('policy', name)) + members.append(('maxattr', struct.attr_max_val.enum_name)) + if 'flags' in op: + members.append(('flags', ' | '.join([c_upper('genl-' + x) for x in op['flags']]))) + cw.write_struct_init(members) + cw.block_end(line=',') + elif family.kernel_policy == 'split': + cb_names = {'do': {'pre': 'pre_doit', 'post': 'post_doit'}, + 'dump': {'pre': 'start', 'post': 'done'}} + + for op_name, op in family.ops.items(): + for op_mode in ['do', 'dump']: + if op.is_async or op_mode not in op: + continue + + cw.block_start() + members = [('cmd', op.enum_name)] + if 'dont-validate' in op: + members.append(('validate', + ' | '.join([c_upper('genl-dont-validate-' + x) + for x in op['dont-validate']])), ) + name = c_lower(f"{family.name}-nl-{op_name}-{op_mode}it") + if 'pre' in op[op_mode]: + members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre']))) + members.append((op_mode + 'it', name)) + if 'post' in op[op_mode]: + members.append((cb_names[op_mode]['post'], c_lower(op[op_mode]['post']))) + if 'request' in op[op_mode]: + struct = Struct(family, op['attribute-set'], + type_list=op[op_mode]['request']['attributes']) + + if op.dual_policy: + name = c_lower(f"{family.name}-{op_name}-{op_mode}-nl-policy") + else: + name = c_lower(f"{family.name}-{op_name}-nl-policy") + members.append(('policy', name)) + members.append(('maxattr', struct.attr_max_val.enum_name)) + flags = (op['flags'] if 'flags' in op else []) + ['cmd-cap-' + op_mode] + members.append(('flags', ' | '.join([c_upper('genl-' + x) for x in flags]))) + cw.write_struct_init(members) + cw.block_end(line=',') + + cw.block_end(line=';') + cw.nl() + + +def print_kernel_mcgrp_hdr(family, cw): + if not family.mcgrps['list']: + return + + cw.block_start('enum') + for grp in family.mcgrps['list']: + grp_id = c_upper(f"{family.name}-nlgrp-{grp['name']},") + cw.p(grp_id) + cw.block_end(';') + cw.nl() + + +def print_kernel_mcgrp_src(family, cw): + if not family.mcgrps['list']: + return + + cw.block_start('static const struct genl_multicast_group ' + family.name + '_nl_mcgrps[] =') + for grp in family.mcgrps['list']: + name = grp['name'] + grp_id = c_upper(f"{family.name}-nlgrp-{name}") + cw.p('[' + grp_id + '] = { "' + name + '", },') + cw.block_end(';') + cw.nl() + + +def print_kernel_family_struct_hdr(family, cw): + if not kernel_can_gen_family_struct(family): + return + + cw.p(f"extern struct genl_family {family.name}_nl_family;") + cw.nl() + + +def print_kernel_family_struct_src(family, cw): + if not kernel_can_gen_family_struct(family): + return + + cw.block_start(f"struct genl_family {family.name}_nl_family __ro_after_init =") + cw.p('.name\t\t= ' + family.fam_key + ',') + cw.p('.version\t= ' + family.ver_key + ',') + cw.p('.netnsok\t= true,') + cw.p('.parallel_ops\t= true,') + cw.p('.module\t\t= THIS_MODULE,') + if family.kernel_policy == 'per-op': + cw.p(f'.ops\t\t= {family.name}_nl_ops,') + cw.p(f'.n_ops\t\t= ARRAY_SIZE({family.name}_nl_ops),') + elif family.kernel_policy == 'split': + cw.p(f'.split_ops\t= {family.name}_nl_ops,') + cw.p(f'.n_split_ops\t= ARRAY_SIZE({family.name}_nl_ops),') + if family.mcgrps['list']: + cw.p(f'.mcgrps\t\t= {family.name}_nl_mcgrps,') + cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.name}_nl_mcgrps),') + cw.block_end(';') + + +def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'): + start_line = 'enum' + if enum_name in obj: + if obj[enum_name]: + start_line = 'enum ' + c_lower(obj[enum_name]) + elif ckey and ckey in obj: + start_line = 'enum ' + family.name + '_' + c_lower(obj[ckey]) + cw.block_start(line=start_line) + + +def render_uapi(family, cw): + hdr_prot = f"_UAPI_LINUX_{family.name.upper()}_H" + cw.p('#ifndef ' + hdr_prot) + cw.p('#define ' + hdr_prot) + cw.nl() + + defines = [(family.fam_key, family["name"]), + (family.ver_key, family.get('version', 1))] + cw.writes_defines(defines) + cw.nl() + + defines = [] + for const in family['definitions']: + if const['type'] != 'const': + cw.writes_defines(defines) + defines = [] + cw.nl() + + # Write kdoc for enum and flags (one day maybe also structs) + if const['type'] == 'enum' or const['type'] == 'flags': + enum = family.consts[const['name']] + + if enum.has_doc(): + cw.p('/**') + doc = '' + if 'doc' in enum: + doc = ' - ' + enum['doc'] + cw.write_doc_line(enum.enum_name + doc) + for entry in enum.entry_list: + if entry.has_doc(): + doc = '@' + entry.c_name + ': ' + entry['doc'] + cw.write_doc_line(doc) + cw.p(' */') + + uapi_enum_start(family, cw, const, 'name') + name_pfx = const.get('name-prefix', f"{family.name}-{const['name']}-") + for entry in enum.entry_list: + suffix = ',' + if entry.value_change: + suffix = f" = {entry.user_value()}" + suffix + cw.p(entry.c_name + suffix) + + if const.get('render-max', False): + cw.nl() + max_name = c_upper(name_pfx + 'max') + cw.p('__' + max_name + ',') + cw.p(max_name + ' = (__' + max_name + ' - 1)') + cw.block_end(line=';') + cw.nl() + elif const['type'] == 'const': + defines.append([c_upper(family.get('c-define-name', + f"{family.name}-{const['name']}")), + const['value']]) + + if defines: + cw.writes_defines(defines) + cw.nl() + + max_by_define = family.get('max-by-define', False) + + for _, attr_set in family.attr_sets.items(): + if attr_set.subset_of: + continue + + cnt_name = c_upper(family.get('attr-cnt-name', f"__{attr_set.name_prefix}MAX")) + max_value = f"({cnt_name} - 1)" + + val = 0 + uapi_enum_start(family, cw, attr_set.yaml, 'enum-name') + for _, attr in attr_set.items(): + suffix = ',' + if attr.value != val: + suffix = f" = {attr.value}," + val = attr.value + val += 1 + cw.p(attr.enum_name + suffix) + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{attr_set.max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {attr_set.max_name} {max_value}") + cw.nl() + + # Commands + separate_ntf = 'async-prefix' in family['operations'] + + max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX")) + cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX")) + max_value = f"({cnt_name} - 1)" + + uapi_enum_start(family, cw, family['operations'], 'enum-name') + for op in family.msgs.values(): + if separate_ntf and ('notify' in op or 'event' in op): + continue + + suffix = ',' + if 'value' in op: + suffix = f" = {op['value']}," + cw.p(op.enum_name + suffix) + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + if separate_ntf: + uapi_enum_start(family, cw, family['operations'], enum_name='async-enum') + for op in family.msgs.values(): + if separate_ntf and not ('notify' in op or 'event' in op): + continue + + suffix = ',' + if 'value' in op: + suffix = f" = {op['value']}," + cw.p(op.enum_name + suffix) + cw.block_end(line=';') + cw.nl() + + # Multicast + defines = [] + for grp in family.mcgrps['list']: + name = grp['name'] + defines.append([c_upper(grp.get('c-define-name', f"{family.name}-mcgrp-{name}")), + f'{name}']) + cw.nl() + if defines: + cw.writes_defines(defines) + cw.nl() + + cw.p(f'#endif /* {hdr_prot} */') + + +def find_kernel_root(full_path): + sub_path = '' + while True: + sub_path = os.path.join(os.path.basename(full_path), sub_path) + full_path = os.path.dirname(full_path) + maintainers = os.path.join(full_path, "MAINTAINERS") + if os.path.exists(maintainers): + return full_path, sub_path[:-1] + + +def main(): + parser = argparse.ArgumentParser(description='Netlink simple parsing generator') + parser.add_argument('--mode', dest='mode', type=str, required=True) + parser.add_argument('--spec', dest='spec', type=str, required=True) + parser.add_argument('--header', dest='header', action='store_true', default=None) + parser.add_argument('--source', dest='header', action='store_false') + parser.add_argument('--user-header', nargs='+', default=[]) + parser.add_argument('-o', dest='out_file', type=str) + args = parser.parse_args() + + out_file = open(args.out_file, 'w+') if args.out_file else os.sys.stdout + + if args.header is None: + parser.error("--header or --source is required") + + try: + parsed = Family(args.spec) + except yaml.YAMLError as exc: + print(exc) + os.sys.exit(1) + return + + cw = CodeWriter(BaseNlLib(), out_file) + + _, spec_kernel = find_kernel_root(args.spec) + if args.mode == 'uapi': + cw.p('/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */') + else: + if args.header: + cw.p('/* SPDX-License-Identifier: BSD-3-Clause */') + else: + cw.p('// SPDX-License-Identifier: BSD-3-Clause') + cw.p("/* Do not edit directly, auto-generated from: */") + cw.p(f"/*\t{spec_kernel} */") + cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") + cw.nl() + + if args.mode == 'uapi': + render_uapi(parsed, cw) + return + + hdr_prot = f"_LINUX_{parsed.name.upper()}_GEN_H" + if args.header: + cw.p('#ifndef ' + hdr_prot) + cw.p('#define ' + hdr_prot) + cw.nl() + + if args.mode == 'kernel': + cw.p('#include <net/netlink.h>') + cw.p('#include <net/genetlink.h>') + cw.nl() + if not args.header: + if args.out_file: + cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') + cw.nl() + headers = [parsed.uapi_header] + for definition in parsed['definitions']: + if 'header' in definition: + headers.append(definition['header']) + for one in headers: + cw.p(f"#include <{one}>") + cw.nl() + + if args.mode == "user": + if not args.header: + cw.p("#include <stdlib.h>") + cw.p("#include <stdio.h>") + cw.p("#include <string.h>") + cw.p("#include <libmnl/libmnl.h>") + cw.p("#include <linux/genetlink.h>") + cw.nl() + for one in args.user_header: + cw.p(f'#include "{one}"') + else: + cw.p('struct ynl_sock;') + cw.nl() + + if args.mode == "kernel": + if args.header: + for _, struct in sorted(parsed.pure_nested_structs.items()): + if struct.request: + cw.p('/* Common nested types */') + break + for attr_set, struct in sorted(parsed.pure_nested_structs.items()): + if struct.request: + print_req_policy_fwd(cw, struct) + cw.nl() + + if parsed.kernel_policy == 'global': + cw.p(f"/* Global operation policy for {parsed.name} */") + + struct = Struct(parsed, parsed.global_policy_set, type_list=parsed.global_policy) + print_req_policy_fwd(cw, struct) + cw.nl() + + if parsed.kernel_policy in {'per-op', 'split'}: + for op_name, op in parsed.ops.items(): + if 'do' in op and 'event' not in op: + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + print_req_policy_fwd(cw, ri.struct['request'], ri=ri) + cw.nl() + + print_kernel_op_table_hdr(parsed, cw) + print_kernel_mcgrp_hdr(parsed, cw) + print_kernel_family_struct_hdr(parsed, cw) + else: + for _, struct in sorted(parsed.pure_nested_structs.items()): + if struct.request: + cw.p('/* Common nested types */') + break + for attr_set, struct in sorted(parsed.pure_nested_structs.items()): + if struct.request: + print_req_policy(cw, struct) + cw.nl() + + if parsed.kernel_policy == 'global': + cw.p(f"/* Global operation policy for {parsed.name} */") + + struct = Struct(parsed, parsed.global_policy_set, type_list=parsed.global_policy) + print_req_policy(cw, struct) + cw.nl() + + for op_name, op in parsed.ops.items(): + if parsed.kernel_policy in {'per-op', 'split'}: + for op_mode in ['do', 'dump']: + if op_mode in op and 'request' in op[op_mode]: + cw.p(f"/* {op.enum_name} - {op_mode} */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, op_mode) + print_req_policy(cw, ri.struct['request'], ri=ri) + cw.nl() + + print_kernel_op_table(parsed, cw) + print_kernel_mcgrp_src(parsed, cw) + print_kernel_family_struct_src(parsed, cw) + + if args.mode == "user": + has_ntf = False + if args.header: + cw.p('/* Common nested types */') + for attr_set, struct in sorted(parsed.pure_nested_structs.items()): + ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + print_type_full(ri, struct) + + for op_name, op in parsed.ops.items(): + cw.p(f"/* ============== {op.enum_name} ============== */") + + if 'do' in op and 'event' not in op: + cw.p(f"/* {op.enum_name} - do */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + print_req_type(ri) + print_req_type_helpers(ri) + cw.nl() + print_rsp_type(ri) + print_rsp_type_helpers(ri) + cw.nl() + print_req_prototype(ri) + cw.nl() + + if 'dump' in op: + cw.p(f"/* {op.enum_name} - dump */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'dump') + if 'request' in op['dump']: + print_req_type(ri) + print_req_type_helpers(ri) + if not ri.type_consistent: + print_rsp_type(ri) + print_wrapped_type(ri) + print_dump_prototype(ri) + cw.nl() + + if 'notify' in op: + cw.p(f"/* {op.enum_name} - notify */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') + has_ntf = True + if not ri.type_consistent: + raise Exception('Only notifications with consistent types supported') + print_wrapped_type(ri) + + if 'event' in op: + ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'event') + cw.p(f"/* {op.enum_name} - event */") + print_rsp_type(ri) + cw.nl() + print_wrapped_type(ri) + + if has_ntf: + cw.p('/* --------------- Common notification parsing --------------- */') + print_ntf_parse_prototype(parsed, cw) + cw.nl() + else: + cw.p('/* Policies */') + for name, _ in parsed.attr_sets.items(): + struct = Struct(parsed, name) + put_typol_fwd(cw, struct) + cw.nl() + + for name, _ in parsed.attr_sets.items(): + struct = Struct(parsed, name) + put_typol(cw, struct) + + cw.p('/* Common nested types */') + for attr_set, struct in sorted(parsed.pure_nested_structs.items()): + ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + + free_rsp_nested(ri, struct) + if struct.request: + put_req_nested(ri, struct) + if struct.reply: + parse_rsp_nested(ri, struct) + + for op_name, op in parsed.ops.items(): + cw.p(f"/* ============== {op.enum_name} ============== */") + if 'do' in op and 'event' not in op: + cw.p(f"/* {op.enum_name} - do */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + print_rsp_free(ri) + parse_rsp_msg(ri) + print_req(ri) + cw.nl() + + if 'dump' in op: + cw.p(f"/* {op.enum_name} - dump */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "dump") + if not ri.type_consistent: + parse_rsp_msg(ri, deref=True) + print_dump_type_free(ri) + print_dump(ri) + cw.nl() + + if 'notify' in op: + cw.p(f"/* {op.enum_name} - notify */") + ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') + has_ntf = True + if not ri.type_consistent: + raise Exception('Only notifications with consistent types supported') + print_ntf_type_free(ri) + + if 'event' in op: + cw.p(f"/* {op.enum_name} - event */") + has_ntf = True + + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + parse_rsp_msg(ri) + + ri = RenderInfo(cw, parsed, args.mode, op, op_name, "event") + print_ntf_type_free(ri) + + if has_ntf: + cw.p('/* --------------- Common notification parsing --------------- */') + print_ntf_type_parse(parsed, cw, args.mode) + + if args.header: + cw.p(f'#endif /* {hdr_prot} */') + + +if __name__ == "__main__": + main() diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh new file mode 100755 index 000000000000..43989ae48ed0 --- /dev/null +++ b/tools/net/ynl/ynl-regen.sh @@ -0,0 +1,30 @@ +#!/bin/bash +# SPDX-License-Identifier: BSD-3-Clause + +TOOL=$(dirname $(realpath $0))/ynl-gen-c.py + +force= + +while [ ! -z "$1" ]; do + case "$1" in + -f ) force=yes; shift ;; + * ) echo "Unrecognized option '$1'"; exit 1 ;; + esac +done + +KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) + +files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\)') +for f in $files; do + # params: 0 1 2 3 + # $YAML YNL-GEN kernel $mode + params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + + if [ $f -nt ${params[0]} -a -z "$force" ]; then + echo -e "\tSKIP $f" + continue + fi + + echo -e "\tGEN ${params[2]}\t$f" + $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} -o $f +done diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5822de376d9a..f937be1afe65 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1237,6 +1237,8 @@ static const char *uaccess_safe_builtin[] = { "__tsan_atomic64_compare_exchange_val", "__tsan_atomic_thread_fence", "__tsan_atomic_signal_fence", + "__tsan_unaligned_read16", + "__tsan_unaligned_write16", /* KCOV */ "write_comp_data", "check_kcov_mode", diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 05806ecfc33c..f533e76fb480 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -38,6 +38,7 @@ arch/*/include/generated/ trace/beauty/generated/ pmu-events/pmu-events.c pmu-events/jevents +pmu-events/metric_test.log feature/ libapi/ libbpf/ diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 0916bbfe64cb..a97f95825b14 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -1,4 +1,5 @@ i synthesize instructions events + y synthesize cycles events b synthesize branches events (branch misses for Arm SPE) c synthesize branches events (calls only) r synthesize branches events (returns only) @@ -25,7 +26,7 @@ A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) - The default is all events i.e. the same as --itrace=ibxwpe, + The default is all events i.e. the same as --itrace=iybxwpe, except for perf script where it is --itrace=ce In addition, the period (default 100000, except for perf script where it is 1) diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index a0529c7fa5ef..f04f0eaded98 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -18,7 +18,7 @@ COMMON OPTIONS -------------- -r:: --repeat=:: -Specify amount of times to repeat the run (default 10). +Specify number of times to repeat the run (default 10). -f:: --format=:: diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 5c5eb2def83e..856f0dfb8e5a 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -22,7 +22,11 @@ you to track down the cacheline contentions. On Intel, the tool is based on load latency and precise store facility events provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling with thresholding feature. On AMD, the tool uses IBS op pmu (due to hardware -limitations, perf c2c is not supported on Zen3 cpus). +limitations, perf c2c is not supported on Zen3 cpus). On Arm64 it uses SPE to +sample load and store operations, therefore hardware and kernel support is +required. See linkperf:perf-arm-spe[1] for a setup guide. Due to the +statistical nature of Arm SPE sampling, not every memory operation will be +sampled. These events provide: - memory address of the access @@ -121,11 +125,17 @@ REPORT OPTIONS perf c2c record --call-graph lbr. Disabled by default. In common cases with call stack overflows, it can recreate better call stacks than the default lbr call stack - output. But this approach is not full proof. There can be cases + output. But this approach is not foolproof. There can be cases where it creates incorrect call stacks from incorrect matches. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +--double-cl:: + Group the detection of shared cacheline events into double cacheline + granularity. Some architectures have an Adjacent Cacheline Prefetch + feature, which causes cacheline sharing to behave like the cacheline + size is doubled. + C2C RECORD ---------- The perf c2c record command setup options related to HITM cacheline analysis @@ -333,4 +343,4 @@ Check Joe's blog on c2c tool for detailed use case explanation: SEE ALSO -------- -linkperf:perf-record[1], linkperf:perf-mem[1] +linkperf:perf-record[1], linkperf:perf-mem[1], linkperf:perf-arm-spe[1] diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 7b6ccd2fa3bf..4c90cc176f81 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -101,12 +101,12 @@ data is available you can use the 'perf script' tool with all itrace sampling options, which will list all the samples. perf record -e intel_pt//u ls - perf script --itrace=ibxwpe + perf script --itrace=iybxwpe An interesting field that is not printed by default is 'flags' which can be displayed as follows: - perf script --itrace=ibxwpe -F+flags + perf script --itrace=iybxwpe -F+flags The flags are "bcrosyiABExghDt" which stand for branch, call, return, conditional, system, asynchronous, interrupt, transaction abort, trace begin, trace end, @@ -147,16 +147,17 @@ displayed as follows: There are two ways that instructions-per-cycle (IPC) can be calculated depending on the recording. -If the 'cyc' config term (see config terms section below) was used, then IPC is -calculated using the cycle count from CYC packets, otherwise MTC packets are -used - refer to the 'mtc' config term. When MTC is used, however, the values -are less accurate because the timing is less accurate. +If the 'cyc' config term (see config terms section below) was used, then IPC +and cycle events are calculated using the cycle count from CYC packets, otherwise +MTC packets are used - refer to the 'mtc' config term. When MTC is used, however, +the values are less accurate because the timing is less accurate. Because Intel PT does not update the cycle count on every branch or instruction, the values will often be zero. When there are values, they will be the number of instructions and number of cycles since the last update, and thus represent -the average IPC since the last IPC for that event type. Note IPC for "branches" -events is calculated separately from IPC for "instructions" events. +the average IPC cycle count since the last IPC for that event type. +Note IPC for "branches" events is calculated separately from IPC for "instructions" +events. Even with the 'cyc' config term, it is possible to produce IPC information for every change of timestamp, but at the expense of accuracy. That is selected by @@ -900,11 +901,12 @@ Having no option is the same as which, in turn, is the same as - --itrace=cepwx + --itrace=cepwxy The letters are: i synthesize "instructions" events + y synthesize "cycles" events b synthesize "branches" events x synthesize "transactions" events w synthesize "ptwrite" events @@ -927,6 +929,16 @@ The letters are: "Instructions" events look like they were recorded by "perf record -e instructions". +"Cycles" events look like they were recorded by "perf record -e cycles" +(ie., the default). Note that even with CYC packets enabled and no sampling, +these are not fully accurate, since CYC packets are not emitted for each +instruction, only when some other event (like an indirect branch, or a +TNT packet representing multiple branches) happens causes a packet to +be emitted. Thus, it is more effective for attributing cycles to functions +(and possibly basic blocks) than to individual instructions, although it +is not even perfect for functions (although it becomes better if the noretcomp +option is active). + "Branches" events look like they were recorded by "perf record -e branches". "c" and "r" can be combined to get calls and returns. @@ -934,9 +946,9 @@ and "r" can be combined to get calls and returns. 'flags' field can be used in perf script to determine whether the event is a transaction start, commit or abort. -Note that "instructions", "branches" and "transactions" events depend on code -flow packets which can be disabled by using the config term "branch=0". Refer -to the config terms section above. +Note that "instructions", "cycles", "branches" and "transactions" events +depend on code flow packets which can be disabled by using the config term +"branch=0". Refer to the config terms section above. "ptwrite" events record the payload of the ptwrite instruction and whether "fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are @@ -1821,6 +1833,36 @@ Can be compiled and traced: $ +Pipe mode +--------- +Pipe mode is a problem for Intel PT and possibly other auxtrace users. +It's not recommended to use a pipe as data output with Intel PT because +of the following reason. + +Essentially the auxtrace buffers do not behave like the regular perf +event buffers. That is because the head and tail are updated by +software, but in the auxtrace case the data is written by hardware. +So the head and tail do not get updated as data is written. + +In the Intel PT case, the head and tail are updated only when the trace +is disabled by software, for example: + - full-trace, system wide : when buffer passes watermark + - full-trace, not system-wide : when buffer passes watermark or + context switches + - snapshot mode : as above but also when a snapshot is made + - sample mode : as above but also when a sample is made + +That means finished-round ordering doesn't work. An auxtrace buffer +can turn up that has data that extends back in time, possibly to the +very beginning of tracing. + +For a perf.data file, that problem is solved by going through the trace +and queuing up the auxtrace buffers in advance. + +For pipe mode, the order of events and timestamps can presumably +be messed up. + + EXAMPLE ------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index c5a3cb0f57c7..d5f78e125efe 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -232,7 +232,7 @@ This can be overridden by setting the kernel.perf_event_paranoid sysctl to -1, which allows non root to use these events. For accessing trace point events perf needs to have read access to -/sys/kernel/debug/tracing, even when perf_event_paranoid is in a relaxed +/sys/kernel/tracing, even when perf_event_paranoid is in a relaxed setting. TRACING diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 0f9f720e599d..37aae194a2a1 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -172,6 +172,11 @@ CONTENTION OPTIONS --lock-addr:: Show lock contention stat by address +-o:: +--lock-owner:: + Show lock contention stat by owners. Implies --threads and + requires --use-bpf. + -Y:: --type-filter=<value>:: Show lock contention only for given lock types (comma separated list). @@ -187,6 +192,12 @@ CONTENTION OPTIONS --lock-filter=<value>:: Show lock contention only for given lock addresses or names (comma separated list). +-S:: +--callstack-filter=<value>:: + Show lock contention only if the callstack contains the given string. + Note that it matches the substring so 'rq' would match both 'raw_spin_rq_lock' + and 'irq_enter_rcu'. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 005c95580b1e..19862572e3f2 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -23,6 +23,11 @@ Note that on Intel systems the memory latency reported is the use-latency, not the pure load (or store latency). Use latency includes any pipeline queueing delays in addition to the memory subsystem latency. +On Arm64 this uses SPE to sample load and store operations, therefore hardware +and kernel support is required. See linkperf:perf-arm-spe[1] for a setup guide. +Due to the statistical nature of SPE sampling, not every memory operation will +be sampled. + OPTIONS ------- <command>...:: @@ -93,4 +98,4 @@ all perf record options. SEE ALSO -------- -linkperf:perf-record[1], linkperf:perf-report[1] +linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1] diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 7f8e8ba3a787..5c43a6edc0e5 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -222,7 +222,7 @@ probe syntax, 'SRC' means the source file path, 'ALN' is start line number, and 'ALN2' is end line number in the file. It is also possible to specify how many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good for searching a specific function when several functions share same name. -So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. +So, "source.c:100-120" shows lines between 100th to 120th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. LAZY MATCHING ------------- diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 4fa509b15948..c242e8da6b1a 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -115,6 +115,8 @@ OPTIONS - p_stage_cyc: On powerpc, this presents the number of cycles spent in a pipeline stage. And currently supported only on powerpc. - addr: (Full) virtual address of the sampled instruction + - retire_lat: On X86, this reports pipeline stall of this instruction compared + to the previous instruction in cycles. And currently supported only on X86 By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) @@ -507,7 +509,7 @@ include::itrace.txt[] perf record --call-graph lbr. Disabled by default. In common cases with call stack overflows, it can recreate better call stacks than the default lbr call stack - output. But this approach is not full proof. There can be cases + output. But this approach is not foolproof. There can be cases where it creates incorrect call stacks from incorrect matches. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index fa4f39d305a7..5b479f5e62ff 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -55,7 +55,7 @@ Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. The format file for the sched_wakeup event defines the following fields -(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): +(see /sys/kernel/tracing/events/sched/sched_wakeup/format): ---- format: diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index cf4b7f4b625a..6a8581012e16 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -319,7 +319,7 @@ So those are the essential steps in writing and running a script. The process can be generalized to any tracepoint or set of tracepoints you're interested in - basically find the tracepoint(s) you're interested in by looking at the list of available events shown by -'perf list' and/or look in /sys/kernel/debug/tracing/events/ for +'perf list' and/or look in /sys/kernel/tracing/events/ for detailed event and field info, record the corresponding trace data using 'perf record', passing it the list of interesting events, generate a skeleton script using 'perf script -g python' and modify the @@ -449,7 +449,7 @@ Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. The format file for the sched_wakeup event defines the following fields -(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): +(see /sys/kernel/tracing/events/sched/sched_wakeup/format): ---- format: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 68e37de5fae4..777a0d8ba7d1 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -134,7 +134,7 @@ OPTIONS srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat, - machine_pid, vcpu. + machine_pid, vcpu, cgroup, retire_lat. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -231,6 +231,9 @@ OPTIONS perf inject to insert a perf.data file recorded inside a virtual machine into a perf.data file recorded on the host at the same time. + The cgroup fields requires sample having the cgroup id which is saved + when "--all-cgroups" option is passed to 'perf record'. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. @@ -502,7 +505,7 @@ include::itrace.txt[] perf record --call-graph lbr. Disabled by default. In common cases with call stack overflows, it can recreate better call stacks than the default lbr call stack - output. But this approach is not full proof. There can be cases + output. But this approach is not foolproof. There can be cases where it creates incorrect call stacks from incorrect matches. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index b329c65d7f40..951a2f262872 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -34,3 +34,6 @@ OPTIONS -F:: --dont-fork:: Do not fork child for each test, run all tests within single process. + +--dso:: + Specify a DSO for the "Symbols" test. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index e534d709cc5a..c60e615b7183 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -334,7 +334,7 @@ use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'. callgraph. The option must be used with --call-graph lbr recording. Disabled by default. In common cases with call stack overflows, it can recreate better call stacks than the default lbr call stack - output. But this approach is not full proof. There can be cases + output. But this approach is not foolproof. There can be cases where it creates incorrect call stacks from incorrect matches. The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 5b8784675903..3519a0139026 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1208,10 +1208,6 @@ ifneq ($(NO_LIBTRACEEVENT),1) LIBTRACEEVENT_VERSION_CPP := $(shell expr $(LIBTRACEEVENT_VERSION_1) \* 255 \* 255 + $(LIBTRACEEVENT_VERSION_2) \* 255 + $(LIBTRACEEVENT_VERSION_3)) CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP) $(call detected,CONFIG_LIBTRACEEVENT) - LIBTRACEEVENT_VERSION_WITH_TEP_FIELD_IS_RELATIVE := $(shell expr 1 \* 255 \* 255 + 5 \* 255 + 0) # 1.5.0 - ifeq ($(shell test $(LIBTRACEEVENT_VERSION_CPP) -gt $(LIBTRACEEVENT_VERSION_WITH_TEP_FIELD_IS_RELATIVE); echo $$?),0) - CFLAGS += -DHAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - endif else dummy := $(warning Warning: libtraceevent is missing limiting functionality, please install libtraceevent-dev/libtraceevent-devel) endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b7d9c4206230..bac9272682b7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1103,6 +1103,7 @@ clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $( $(OUTPUT)util/intel-pt-decoder/inat-tables.c \ $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ $(OUTPUT)pmu-events/pmu-events.c \ + $(OUTPUT)pmu-events/metric_test.log \ $(OUTPUT)$(fadvise_advice_array) \ $(OUTPUT)$(fsconfig_arrays) \ $(OUTPUT)$(fsmount_arrays) \ diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index deeb163999ce..adec6c9ee11d 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -55,17 +55,16 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err) { - const char *sysfs = sysfs__mountpoint(); struct perf_pmu **hisi_ptt_pmus = NULL; struct dirent *dent; char path[PATH_MAX]; DIR *dir = NULL; int idx = 0; - snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); dir = opendir(path); if (!dir) { - pr_err("can't read directory '%s'\n", EVENT_SOURCE_DEVICE_PATH); + pr_err("can't read directory '%s'\n", path); *err = -EINVAL; return NULL; } diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index a346d5f3dafa..7f71c8a237ff 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -53,7 +53,17 @@ static const char * const metadata_etmv4_ro[] = { [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2", [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8", [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus", - [CS_ETE_TRCDEVARCH] = "mgmt/trcdevarch" + [CS_ETMV4_TS_SOURCE] = "ts_source", +}; + +static const char * const metadata_ete_ro[] = { + [CS_ETE_TRCIDR0] = "trcidr/trcidr0", + [CS_ETE_TRCIDR1] = "trcidr/trcidr1", + [CS_ETE_TRCIDR2] = "trcidr/trcidr2", + [CS_ETE_TRCIDR8] = "trcidr/trcidr8", + [CS_ETE_TRCAUTHSTATUS] = "mgmt/trcauthstatus", + [CS_ETE_TRCDEVARCH] = "mgmt/trcdevarch", + [CS_ETE_TS_SOURCE] = "ts_source", }; static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); @@ -273,9 +283,15 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, ret = perf_pmu__scan_file(pmu, path, "%x", &hash); if (ret != 1) { - pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n", - sink, evsel__name(evsel), errno, - str_error_r(errno, msg, sizeof(msg))); + if (errno == ENOENT) + pr_err("Couldn't find sink \"%s\" on event %s\n" + "Missing kernel or device support?\n\n" + "Hint: An appropriate sink will be picked automatically if one isn't specified.\n", + sink, evsel__name(evsel)); + else + pr_err("Failed to set sink \"%s\" on event %s with %d (%s)\n", + sink, evsel__name(evsel), errno, + str_error_r(errno, msg, sizeof(msg))); return ret; } @@ -605,6 +621,32 @@ static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path) return val; } +static int cs_etm_get_ro_signed(struct perf_pmu *pmu, int cpu, const char *path) +{ + char pmu_path[PATH_MAX]; + int scan; + int val = 0; + + /* Get RO metadata from sysfs */ + snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path); + + scan = perf_pmu__scan_file(pmu, pmu_path, "%d", &val); + if (scan != 1) + pr_err("%s: error reading: %s\n", __func__, pmu_path); + + return val; +} + +static bool cs_etm_pmu_path_exists(struct perf_pmu *pmu, int cpu, const char *path) +{ + char pmu_path[PATH_MAX]; + + /* Get RO metadata from sysfs */ + snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path); + + return perf_pmu__file_exists(pmu, pmu_path); +} + #define TRCDEVARCH_ARCHPART_SHIFT 0 #define TRCDEVARCH_ARCHPART_MASK GENMASK(11, 0) #define TRCDEVARCH_ARCHPART(x) (((x) & TRCDEVARCH_ARCHPART_MASK) >> TRCDEVARCH_ARCHPART_SHIFT) @@ -617,7 +659,7 @@ static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; - int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETE_TRCDEVARCH]); + int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]); /* * ETE if ARCHVER is 5 (ARCHVER is 4 for ETM) and ARCHPART is 0xA13. @@ -646,6 +688,51 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, metadata_etmv4_ro[CS_ETMV4_TRCIDR8]); data[CS_ETMV4_TRCAUTHSTATUS] = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCAUTHSTATUS]); + + /* Kernels older than 5.19 may not expose ts_source */ + if (cs_etm_pmu_path_exists(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TS_SOURCE])) + data[CS_ETMV4_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TS_SOURCE]); + else { + pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", + cpu); + data[CS_ETMV4_TS_SOURCE] = (__u64) -1; + } +} + +static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, int cpu) +{ + struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + /* Get trace configuration register */ + data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr); + /* Get traceID from the framework */ + data[CS_ETE_TRCTRACEIDR] = coresight_get_trace_id(cpu); + /* Get read-only information from sysFS */ + data[CS_ETE_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCIDR0]); + data[CS_ETE_TRCIDR1] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCIDR1]); + data[CS_ETE_TRCIDR2] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCIDR2]); + data[CS_ETE_TRCIDR8] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCIDR8]); + data[CS_ETE_TRCAUTHSTATUS] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCAUTHSTATUS]); + /* ETE uses the same registers as ETMv4 plus TRCDEVARCH */ + data[CS_ETE_TRCDEVARCH] = cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TRCDEVARCH]); + + /* Kernels older than 5.19 may not expose ts_source */ + if (cs_etm_pmu_path_exists(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TS_SOURCE])) + data[CS_ETE_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu, + metadata_ete_ro[CS_ETE_TS_SOURCE]); + else { + pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", + cpu); + data[CS_ETE_TS_SOURCE] = (__u64) -1; + } } static void cs_etm_get_metadata(int cpu, u32 *offset, @@ -661,11 +748,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset, /* first see what kind of tracer this cpu is affined to */ if (cs_etm_is_ete(itr, cpu)) { magic = __perf_cs_ete_magic; - /* ETE uses the same registers as ETMv4 plus TRCDEVARCH */ - cs_etm_save_etmv4_header(&info->priv[*offset], itr, cpu); - info->priv[*offset + CS_ETE_TRCDEVARCH] = - cs_etm_get_ro(cs_etm_pmu, cpu, - metadata_etmv4_ro[CS_ETE_TRCDEVARCH]); + cs_etm_save_ete_header(&info->priv[*offset], itr, cpu); /* How much space was used */ increment = CS_ETE_PRIV_MAX; diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 477e513972a4..fa143acb4c8d 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -3,8 +3,10 @@ #include <internal/cpumap.h> #include "../../../util/cpumap.h" #include "../../../util/pmu.h" +#include <api/fs/fs.h> +#include <math.h> -const struct pmu_events_table *pmu_events_table__find(void) +static struct perf_pmu *pmu__find_core_pmu(void) { struct perf_pmu *pmu = NULL; @@ -19,8 +21,46 @@ const struct pmu_events_table *pmu_events_table__find(void) if (pmu->cpus->nr != cpu__max_cpu().cpu) return NULL; - return perf_pmu__find_table(pmu); + return pmu; } + return NULL; +} + +const struct pmu_metrics_table *pmu_metrics_table__find(void) +{ + struct perf_pmu *pmu = pmu__find_core_pmu(); + + if (pmu) + return perf_pmu__find_metrics_table(pmu); return NULL; } + +const struct pmu_events_table *pmu_events_table__find(void) +{ + struct perf_pmu *pmu = pmu__find_core_pmu(); + + if (pmu) + return perf_pmu__find_events_table(pmu); + + return NULL; +} + +double perf_pmu__cpu_slots_per_cycle(void) +{ + char path[PATH_MAX]; + unsigned long long slots = 0; + struct perf_pmu *pmu = pmu__find_core_pmu(); + + if (pmu) { + perf_pmu__pathname_scnprintf(path, sizeof(path), + pmu->name, "caps/slots"); + /* + * The value of slots is not greater than 32 bits, but sysfs__read_int + * can't read value with 0x prefix, so use sysfs__read_ull instead. + */ + sysfs__read_ull(path, &slots); + } + + return slots ? (double)slots : NAN; +} diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index e8fe36b10d20..78eef77d8a8d 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -40,11 +40,11 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return bufp; } -int arch_get_runtimeparam(const struct pmu_event *pe) +int arch_get_runtimeparam(const struct pmu_metric *pm) { int count; char path[PATH_MAX] = "/devices/hv_24x7/interface/"; - atoi(pe->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); + atoi(pm->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); return sysfs__read_int(path, &count) < 0 ? 1 : count; } diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c index 690c7c07e90d..a061e8619267 100644 --- a/tools/perf/arch/x86/tests/sample-parsing.c +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -27,8 +27,10 @@ static bool samples_same(const struct perf_sample *s1, const struct perf_sample *s2, u64 type) { - if (type & PERF_SAMPLE_WEIGHT_STRUCT) + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { COMP(ins_lat); + COMP(retire_lat); + } return true; } @@ -48,6 +50,7 @@ static int do_test(u64 sample_type) struct perf_sample sample = { .weight = 101, .ins_lat = 102, + .retire_lat = 103, }; struct perf_sample sample_out; size_t i, sz, bufsz; diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index a3acefe6d0c6..e4288d09f3a0 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -89,6 +89,7 @@ void arch_perf_parse_sample_weight(struct perf_sample *data, else { data->weight = weight.var1_dw; data->ins_lat = weight.var2_w; + data->retire_lat = weight.var3_w; } } @@ -100,5 +101,25 @@ void arch_perf_synthesize_sample_weight(const struct perf_sample *data, if (type & PERF_SAMPLE_WEIGHT_STRUCT) { *array &= 0xffffffff; *array |= ((u64)data->ins_lat << 32); + *array |= ((u64)data->retire_lat << 48); } } + +const char *arch_perf_header_entry(const char *se_header) +{ + if (!strcmp(se_header, "Local Pipeline Stage Cycle")) + return "Local Retire Latency"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Retire Latency"; + + return se_header; +} + +int arch_support_sort_key(const char *sort_key) +{ + if (!strcmp(sort_key, "p_stage_cyc")) + return 1; + if (!strcmp(sort_key, "local_p_stage_cyc")) + return 1; + return 0; +} diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 74d69db1ea99..358340b34243 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -15,8 +15,6 @@ #include "../../../util/pmu.h" #include "../../../util/fncache.h" -#define TEMPLATE_ALIAS "%s/bus/event_source/devices/%s/alias" - struct pmu_alias { char *name; char *alias; @@ -72,18 +70,14 @@ static int setup_pmu_alias_list(void) char path[PATH_MAX]; DIR *dir; struct dirent *dent; - const char *sysfs = sysfs__mountpoint(); struct pmu_alias *pmu_alias; char buf[MAX_PMU_NAME_LEN]; FILE *file; int ret = -ENOMEM; - if (!sysfs) + if (!perf_pmu__event_source_devices_scnprintf(path, sizeof(path))) return -1; - snprintf(path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); - dir = opendir(path); if (!dir) return -errno; @@ -93,9 +87,7 @@ static int setup_pmu_alias_list(void) !strcmp(dent->d_name, "..")) continue; - snprintf(path, PATH_MAX, - TEMPLATE_ALIAS, sysfs, dent->d_name); - + perf_pmu__pathname_scnprintf(path, sizeof(path), dent->d_name, "alias"); if (!file_available(path)) continue; diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index a5d49b3b6a09..e43893151a3e 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -22,6 +22,8 @@ int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv); int bench_sched_pipe(int argc, const char **argv); int bench_syscall_basic(int argc, const char **argv); +int bench_syscall_getpgid(int argc, const char **argv); +int bench_syscall_execve(int argc, const char **argv); int bench_mem_memcpy(int argc, const char **argv); int bench_mem_memset(int argc, const char **argv); int bench_mem_find_bit(int argc, const char **argv); diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index 9b751016f4b6..fe79f7f3091e 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -14,6 +14,7 @@ #include <sys/time.h> #include <sys/syscall.h> #include <sys/types.h> +#include <sys/wait.h> #include <unistd.h> #include <stdlib.h> @@ -30,25 +31,77 @@ static const char * const bench_syscall_usage[] = { NULL }; -int bench_syscall_basic(int argc, const char **argv) +static void test_execve(void) +{ + const char *pathname = "/bin/true"; + char *const argv[] = { (char *)pathname, NULL }; + pid_t pid = fork(); + + if (pid < 0) { + fprintf(stderr, "fork failed\n"); + exit(1); + } else if (pid == 0) { + execve(pathname, argv, NULL); + fprintf(stderr, "execve /bin/true failed\n"); + exit(1); + } else { + if (waitpid(pid, NULL, 0) < 0) { + fprintf(stderr, "waitpid failed\n"); + exit(1); + } + } +} + +static int bench_syscall_common(int argc, const char **argv, int syscall) { struct timeval start, stop, diff; unsigned long long result_usec = 0; + const char *name = NULL; int i; argc = parse_options(argc, argv, options, bench_syscall_usage, 0); gettimeofday(&start, NULL); - for (i = 0; i < loops; i++) - getppid(); + for (i = 0; i < loops; i++) { + switch (syscall) { + case __NR_getppid: + getppid(); + break; + case __NR_getpgid: + getpgid(0); + break; + case __NR_execve: + test_execve(); + /* Only loop 10000 times to save time */ + if (i == 10000) + loops = 10000; + break; + default: + break; + } + } gettimeofday(&stop, NULL); timersub(&stop, &start, &diff); + switch (syscall) { + case __NR_getppid: + name = "getppid()"; + break; + case __NR_getpgid: + name = "getpgid()"; + break; + case __NR_execve: + name = "execve()"; + break; + default: + break; + } + switch (bench_format) { case BENCH_FORMAT_DEFAULT: - printf("# Executed %'d getppid() calls\n", loops); + printf("# Executed %'d %s calls\n", loops, name); result_usec = diff.tv_sec * 1000000; result_usec += diff.tv_usec; @@ -79,3 +132,18 @@ int bench_syscall_basic(int argc, const char **argv) return 0; } + +int bench_syscall_basic(int argc, const char **argv) +{ + return bench_syscall_common(argc, argv, __NR_getppid); +} + +int bench_syscall_getpgid(int argc, const char **argv) +{ + return bench_syscall_common(argc, argv, __NR_getpgid); +} + +int bench_syscall_execve(int argc, const char **argv) +{ + return bench_syscall_common(argc, argv, __NR_execve); +} diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 334ab897aae3..814e9afc86f6 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -52,6 +52,8 @@ static struct bench sched_benchmarks[] = { static struct bench syscall_benchmarks[] = { { "basic", "Benchmark for basic getppid(2) calls", bench_syscall_basic }, + { "getpgid", "Benchmark for getpgid(2) calls", bench_syscall_getpgid }, + { "execve", "Benchmark for execve(2) calls", bench_syscall_execve }, { "all", "Run all syscall benchmarks", NULL }, { NULL, NULL, NULL }, }; @@ -150,7 +152,7 @@ unsigned int bench_repeat = 10; /* default number of times to repeat the run */ static const struct option bench_options[] = { OPT_STRING('f', "format", &bench_format_str, "default|simple", "Specify the output formatting style"), - OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"), + OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify number of times to repeat the run"), OPT_END() }; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 52d94c7dd836..56974eae0638 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -524,7 +524,7 @@ static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, char buf[20]; if (he->mem_info) - addr = cl_address(he->mem_info->daddr.addr); + addr = cl_address(he->mem_info->daddr.addr, chk_double_cl); return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr)); } @@ -562,7 +562,7 @@ static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, char buf[20]; if (he->mem_info) - addr = cl_offset(he->mem_info->daddr.al_addr); + addr = cl_offset(he->mem_info->daddr.al_addr, chk_double_cl); return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr)); } @@ -574,9 +574,10 @@ offset_cmp(struct perf_hpp_fmt *fmt __maybe_unused, uint64_t l = 0, r = 0; if (left->mem_info) - l = cl_offset(left->mem_info->daddr.addr); + l = cl_offset(left->mem_info->daddr.addr, chk_double_cl); + if (right->mem_info) - r = cl_offset(right->mem_info->daddr.addr); + r = cl_offset(right->mem_info->daddr.addr, chk_double_cl); return (int64_t)(r - l); } @@ -2590,7 +2591,7 @@ perf_c2c_cacheline_browser__title(struct hist_browser *browser, he = cl_browser->he; if (he->mem_info) - addr = cl_address(he->mem_info->daddr.addr); + addr = cl_address(he->mem_info->daddr.addr, chk_double_cl); scnprintf(bf, size, "Cacheline 0x%lx", addr); return 0; @@ -2788,15 +2789,16 @@ static int ui_quirks(void) if (!c2c.use_stdio) { dim_offset.width = 5; dim_offset.header = header_offset_tui; - nodestr = "CL"; + nodestr = chk_double_cl ? "Double-CL" : "CL"; } dim_percent_costly_snoop.header = percent_costly_snoop_header[c2c.display]; /* Fix the zero line for dcacheline column. */ - buf = fill_line("Cacheline", dim_dcacheline.width + - dim_dcacheline_node.width + - dim_dcacheline_count.width + 4); + buf = fill_line(chk_double_cl ? "Double-Cacheline" : "Cacheline", + dim_dcacheline.width + + dim_dcacheline_node.width + + dim_dcacheline_count.width + 4); if (!buf) return -ENOMEM; @@ -3037,6 +3039,7 @@ static int perf_c2c__report(int argc, const char **argv) OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_BOOLEAN(0, "stitch-lbr", &c2c.stitch_lbr, "Enable LBR callgraph stitching approach"), + OPT_BOOLEAN(0, "double-cl", &chk_double_cl, "Detect adjacent cacheline false sharing"), OPT_PARENT(c2c_options), OPT_END() }; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 3f4e4dd5abf3..f8182417b734 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -215,14 +215,14 @@ static int perf_event__repipe_event_update(struct perf_tool *tool, #ifdef HAVE_AUXTRACE_SUPPORT -static int copy_bytes(struct perf_inject *inject, int fd, off_t size) +static int copy_bytes(struct perf_inject *inject, struct perf_data *data, off_t size) { char buf[4096]; ssize_t ssz; int ret; while (size > 0) { - ssz = read(fd, buf, min(size, (off_t)sizeof(buf))); + ssz = perf_data__read(data, buf, min(size, (off_t)sizeof(buf))); if (ssz < 0) return -errno; ret = output_bytes(inject, buf, ssz); @@ -260,7 +260,7 @@ static s64 perf_event__repipe_auxtrace(struct perf_session *session, ret = output_bytes(inject, event, event->header.size); if (ret < 0) return ret; - ret = copy_bytes(inject, perf_data__fd(session->data), + ret = copy_bytes(inject, session->data, event->auxtrace.size); } else { ret = output_bytes(inject, event, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 8ae0a1535293..f3029742b800 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -653,7 +653,6 @@ static const struct { { "__GFP_HIGHMEM", "HM" }, { "GFP_DMA32", "D32" }, { "__GFP_HIGH", "H" }, - { "__GFP_ATOMIC", "_A" }, { "__GFP_IO", "I" }, { "__GFP_FS", "F" }, { "__GFP_NOWARN", "NWR" }, diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 137d73edb541..791f513ae5b4 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -99,8 +99,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi const char *scale_unit __maybe_unused, bool deprecated, const char *event_type_desc, const char *desc, const char *long_desc, - const char *encoding_desc, - const char *metric_name, const char *metric_expr) + const char *encoding_desc) { struct print_state *print_state = ps; int pos; @@ -159,10 +158,6 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi if (print_state->detailed && encoding_desc) { printf("%*s", 8, ""); wordwrap(encoding_desc, 8, pager_get_columns(), 0); - if (metric_name) - printf(" MetricName: %s", metric_name); - if (metric_expr) - printf(" MetricExpr: %s", metric_expr); putchar('\n'); } } @@ -308,8 +303,7 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic, const char *scale_unit, bool deprecated, const char *event_type_desc, const char *desc, const char *long_desc, - const char *encoding_desc, - const char *metric_name, const char *metric_expr) + const char *encoding_desc) { struct json_print_state *print_state = ps; bool need_sep = false; @@ -366,16 +360,6 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic, encoding_desc); need_sep = true; } - if (metric_name) { - fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", - metric_name); - need_sep = true; - } - if (metric_expr) { - fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", - metric_expr); - need_sep = true; - } printf("%s}", need_sep ? "\n" : ""); strbuf_release(&buf); } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 506c2fe42d52..054997edd98b 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -58,16 +58,28 @@ static struct rb_root thread_stats; static bool combine_locks; static bool show_thread_stats; static bool show_lock_addrs; +static bool show_lock_owner; static bool use_bpf; static unsigned long bpf_map_entries = 10240; static int max_stack_depth = CONTENTION_STACK_DEPTH; static int stack_skip = CONTENTION_STACK_SKIP; static int print_nr_entries = INT_MAX / 2; +static LIST_HEAD(callstack_filters); + +struct callstack_filter { + struct list_head list; + char name[]; +}; static struct lock_filter filters; static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR; +static bool needs_callstack(void) +{ + return verbose > 0 || !list_empty(&callstack_filters); +} + static struct thread_stat *thread_stat_find(u32 tid) { struct rb_node *node; @@ -454,7 +466,7 @@ static struct lock_stat *pop_from_result(void) return container_of(node, struct lock_stat, rb); } -static struct lock_stat *lock_stat_find(u64 addr) +struct lock_stat *lock_stat_find(u64 addr) { struct hlist_head *entry = lockhashentry(addr); struct lock_stat *ret; @@ -466,7 +478,7 @@ static struct lock_stat *lock_stat_find(u64 addr) return NULL; } -static struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) { struct hlist_head *entry = lockhashentry(addr); struct lock_stat *ret, *new; @@ -498,6 +510,34 @@ alloc_failed: return NULL; } +bool match_callstack_filter(struct machine *machine, u64 *callstack) +{ + struct map *kmap; + struct symbol *sym; + u64 ip; + + if (list_empty(&callstack_filters)) + return true; + + for (int i = 0; i < max_stack_depth; i++) { + struct callstack_filter *filter; + + if (!callstack || !callstack[i]) + break; + + ip = callstack[i]; + sym = machine__find_kernel_symbol(machine, ip, &kmap); + if (sym == NULL) + continue; + + list_for_each_entry(filter, &callstack_filters, list) { + if (strstr(sym->name, filter->name)) + return true; + } + } + return false; +} + struct trace_lock_handler { /* it's used on CONFIG_LOCKDEP */ int (*acquire_event)(struct evsel *evsel, @@ -1059,12 +1099,6 @@ static int report_lock_contention_begin_event(struct evsel *evsel, ls = lock_stat_findnew(key, name, flags); if (!ls) return -ENOMEM; - - if (aggr_mode == LOCK_AGGR_CALLER && verbose > 0) { - ls->callstack = get_callstack(sample, max_stack_depth); - if (ls->callstack == NULL) - return -ENOMEM; - } } if (filters.nr_types) { @@ -1095,6 +1129,22 @@ static int report_lock_contention_begin_event(struct evsel *evsel, return 0; } + if (needs_callstack()) { + u64 *callstack = get_callstack(sample, max_stack_depth); + if (callstack == NULL) + return -ENOMEM; + + if (!match_callstack_filter(machine, callstack)) { + free(callstack); + return 0; + } + + if (ls->callstack == NULL) + ls->callstack = callstack; + else + free(callstack); + } + ts = thread_stat_findnew(sample->tid); if (!ts) return -ENOMEM; @@ -1567,7 +1617,8 @@ static void print_contention_result(struct lock_contention *con) switch (aggr_mode) { case LOCK_AGGR_TASK: - pr_info(" %10s %s\n\n", "pid", "comm"); + pr_info(" %10s %s\n\n", "pid", + show_lock_owner ? "owner" : "comm"); break; case LOCK_AGGR_CALLER: pr_info(" %10s %s\n\n", "type", "caller"); @@ -1607,7 +1658,8 @@ static void print_contention_result(struct lock_contention *con) case LOCK_AGGR_TASK: pid = st->addr; t = perf_session__findnew(session, pid); - pr_info(" %10d %s\n", pid, thread__comm_str(t)); + pr_info(" %10d %s\n", + pid, pid == -1 ? "Unknown" : thread__comm_str(t)); break; case LOCK_AGGR_ADDR: pr_info(" %016llx %s\n", (unsigned long long)st->addr, @@ -1719,6 +1771,37 @@ static void sighandler(int sig __maybe_unused) { } +static int check_lock_contention_options(const struct option *options, + const char * const *usage) + +{ + if (show_thread_stats && show_lock_addrs) { + pr_err("Cannot use thread and addr mode together\n"); + parse_options_usage(usage, options, "threads", 0); + parse_options_usage(NULL, options, "lock-addr", 0); + return -1; + } + + if (show_lock_owner && !use_bpf) { + pr_err("Lock owners are available only with BPF\n"); + parse_options_usage(usage, options, "lock-owner", 0); + parse_options_usage(NULL, options, "use-bpf", 0); + return -1; + } + + if (show_lock_owner && show_lock_addrs) { + pr_err("Cannot use owner and addr mode together\n"); + parse_options_usage(usage, options, "lock-owner", 0); + parse_options_usage(NULL, options, "lock-addr", 0); + return -1; + } + + if (show_lock_owner) + show_thread_stats = true; + + return 0; +} + static int __cmd_contention(int argc, const char **argv) { int err = -EINVAL; @@ -1743,6 +1826,8 @@ static int __cmd_contention(int argc, const char **argv) .max_stack = max_stack_depth, .stack_skip = stack_skip, .filters = &filters, + .save_callstack = needs_callstack(), + .owner = show_lock_owner, }; session = perf_session__new(use_bpf ? NULL : &data, &eops); @@ -1756,6 +1841,9 @@ static int __cmd_contention(int argc, const char **argv) con.aggr_mode = aggr_mode = show_thread_stats ? LOCK_AGGR_TASK : show_lock_addrs ? LOCK_AGGR_ADDR : LOCK_AGGR_CALLER; + if (con.aggr_mode == LOCK_AGGR_CALLER) + con.save_callstack = true; + /* for lock function check */ symbol_conf.sort_by_name = true; symbol_conf.allow_aliases = true; @@ -2123,6 +2211,33 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char * return ret; } +static int parse_call_stack(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) +{ + char *s, *tmp, *tok; + int ret = 0; + + s = strdup(str); + if (s == NULL) + return -1; + + for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { + struct callstack_filter *entry; + + entry = malloc(sizeof(*entry) + strlen(tok) + 1); + if (entry == NULL) { + pr_err("Memory allocation failure\n"); + return -1; + } + + strcpy(entry->name, tok); + list_add_tail(&entry->list, &callstack_filters); + } + + free(s); + return ret; +} + int cmd_lock(int argc, const char **argv) { const struct option lock_options[] = { @@ -2190,6 +2305,9 @@ int cmd_lock(int argc, const char **argv) "Filter specific type of locks", parse_lock_type), OPT_CALLBACK('L', "lock-filter", NULL, "ADDRS/NAMES", "Filter specific address/symbol of locks", parse_lock_addr), + OPT_CALLBACK('S', "callstack-filter", NULL, "NAMES", + "Filter specific function in the callstack", parse_call_stack), + OPT_BOOLEAN('o', "lock-owner", &show_lock_owner, "show lock owners instead of waiters"), OPT_PARENT(lock_options) }; @@ -2260,14 +2378,9 @@ int cmd_lock(int argc, const char **argv) contention_usage, 0); } - if (show_thread_stats && show_lock_addrs) { - pr_err("Cannot use thread and addr mode together\n"); - parse_options_usage(contention_usage, contention_options, - "threads", 0); - parse_options_usage(NULL, contention_options, - "lock-addr", 0); + if (check_lock_contention_options(contention_options, + contention_usage) < 0) return -1; - } rc = __cmd_contention(argc, argv); } else { diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index ed73d0b89ca2..e72f6cea76f7 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -383,9 +383,18 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs) /* Note that it is possible to skip all events because of blacklist */ if (event) { +#ifndef HAVE_LIBTRACEEVENT + pr_info("\nperf is not linked with libtraceevent, to use the new probe you can use tracefs:\n\n"); + pr_info("\tcd /sys/kernel/tracing/\n"); + pr_info("\techo 1 > events/%s/%s/enable\n", group, event); + pr_info("\techo 1 > tracing_on\n"); + pr_info("\tcat trace_pipe\n"); + pr_info("\tBefore removing the probe, echo 0 > events/%s/%s/enable\n", group, event); +#else /* Show how to use the event. */ pr_info("\nYou can now use it in all perf tools, such as:\n\n"); pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event); +#endif } out_cleanup: diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 29dcd454b8e2..8374117e66f6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -154,6 +154,7 @@ struct record { struct perf_tool tool; struct record_opts opts; u64 bytes_written; + u64 thread_bytes_written; struct perf_data data; struct auxtrace_record *itr; struct evlist *evlist; @@ -226,14 +227,7 @@ static bool switch_output_time(struct record *rec) static u64 record__bytes_written(struct record *rec) { - int t; - u64 bytes_written = rec->bytes_written; - struct record_thread *thread_data = rec->thread_data; - - for (t = 0; t < rec->nr_threads; t++) - bytes_written += thread_data[t].bytes_written; - - return bytes_written; + return rec->bytes_written + rec->thread_bytes_written; } static bool record__output_max_size_exceeded(struct record *rec) @@ -255,10 +249,12 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused, return -1; } - if (map && map->file) + if (map && map->file) { thread->bytes_written += size; - else + rec->thread_bytes_written += size; + } else { rec->bytes_written += size; + } if (record__output_max_size_exceeded(rec) && !done) { fprintf(stderr, "[ perf record: perf size limit reached (%" PRIu64 " KB)," diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 69394ac0a20d..a792214d1af8 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -59,6 +59,7 @@ #include "util/dlfilter.h" #include "util/record.h" #include "util/util.h" +#include "util/cgroup.h" #include "perf.h" #include <linux/ctype.h> @@ -130,6 +131,8 @@ enum perf_output_field { PERF_OUTPUT_BRSTACKINSNLEN = 1ULL << 36, PERF_OUTPUT_MACHINE_PID = 1ULL << 37, PERF_OUTPUT_VCPU = 1ULL << 38, + PERF_OUTPUT_CGROUP = 1ULL << 39, + PERF_OUTPUT_RETIRE_LAT = 1ULL << 40, }; struct perf_script { @@ -200,6 +203,8 @@ struct output_option { {.str = "brstackinsnlen", .field = PERF_OUTPUT_BRSTACKINSNLEN}, {.str = "machine_pid", .field = PERF_OUTPUT_MACHINE_PID}, {.str = "vcpu", .field = PERF_OUTPUT_VCPU}, + {.str = "cgroup", .field = PERF_OUTPUT_CGROUP}, + {.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT}, }; enum { @@ -275,7 +280,7 @@ static struct { PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE | - PERF_OUTPUT_INS_LAT, + PERF_OUTPUT_INS_LAT | PERF_OUTPUT_RETIRE_LAT, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -542,6 +547,16 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_INS_LAT)) return -EINVAL; + if (PRINT_FIELD(CGROUP) && + evsel__check_stype(evsel, PERF_SAMPLE_CGROUP, "CGROUP", PERF_OUTPUT_CGROUP)) { + pr_err("Hint: run 'perf record --all-cgroups ...'\n"); + return -EINVAL; + } + + if (PRINT_FIELD(RETIRE_LAT) && + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_RETIRE_LAT)) + return -EINVAL; + return 0; } @@ -880,12 +895,13 @@ mispred_str(struct branch_entry *br) static int print_bstack_flags(FILE *fp, struct branch_entry *br) { - return fprintf(fp, "/%c/%c/%c/%d/%s ", + return fprintf(fp, "/%c/%c/%c/%d/%s/%s ", mispred_str(br), br->flags.in_tx ? 'X' : '-', br->flags.abort ? 'A' : '-', br->flags.cycles, - get_branch_type(br)); + get_branch_type(br), + br->flags.spec ? branch_spec_desc(br->flags.spec) : "-"); } static int perf_sample__fprintf_brstack(struct perf_sample *sample, @@ -1301,7 +1317,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, goto out; /* - * Print final block upto sample + * Print final block up to sample * * Due to pipeline delays the LBRs might be missing a branch * or two, which can result in very large or negative blocks @@ -2178,6 +2194,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(INS_LAT)) fprintf(fp, "%16" PRIu16, sample->ins_lat); + if (PRINT_FIELD(RETIRE_LAT)) + fprintf(fp, "%16" PRIu16, sample->retire_lat); + if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL; @@ -2220,6 +2239,17 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(CODE_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); + if (PRINT_FIELD(CGROUP)) { + const char *cgrp_name; + struct cgroup *cgrp = cgroup__find(machine->env, + sample->cgroup); + if (cgrp != NULL) + cgrp_name = cgrp->name; + else + cgrp_name = "unknown"; + fprintf(fp, " %s", cgrp_name); + } + perf_sample__fprintf_ipc(sample, attr, fp); fprintf(fp, "\n"); @@ -3856,7 +3886,7 @@ int cmd_script(int argc, const char **argv) "brstacksym,flags,data_src,weight,bpf-output,brstackinsn," "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth," "phys_addr,metric,misc,srccode,ipc,tod,data_page_size," - "code_page_size,ins_lat", + "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9f3e4b257516..5d18a5a6f662 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2524,7 +2524,6 @@ int cmd_stat(int argc, const char **argv) &stat_config.metric_events); zfree(&metrics); } - perf_stat__collect_metric_expr(evsel_list); perf_stat__init_shadow_stats(); if (add_default_attributes()) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d21fe0f32a6d..610fb60b1c0d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2731,10 +2731,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, offset = format_field__intval(field, sample, evsel->needs_swap); syscall_arg.len = offset >> 16; offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif } val = (uintptr_t)(sample->raw_data + offset); diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index fdf75d45efff..978249d7868c 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -165,7 +165,12 @@ __perf_main () local cur1=${COMP_WORDS[COMP_CWORD]} local raw_evts=$($cmd list --raw-dump) - local arr s tmp result + local arr s tmp result cpu_evts + + # aarch64 doesn't have /sys/bus/event_source/devices/cpu/events + if [[ `uname -m` != aarch64 ]]; then + cpu_evts=$(ls /sys/bus/event_source/devices/cpu/events) + fi if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then OLD_IFS="$IFS" @@ -183,9 +188,9 @@ __perf_main () fi done - evts=${result}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${result}" "${cpu_evts} else - evts=${raw_evts}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${raw_evts}" "${cpu_evts} fi if [[ "$cur1" == , ]]; then diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 15b9e8fdbffa..150765f2baee 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -6,10 +6,16 @@ JDIR_TEST = pmu-events/arch/test JSON_TEST = $(shell [ -d $(JDIR_TEST) ] && \ find $(JDIR_TEST) -name '*.json') JEVENTS_PY = pmu-events/jevents.py +METRIC_PY = pmu-events/metric.py +METRIC_TEST_PY = pmu-events/metric_test.py +EMPTY_PMU_EVENTS_C = pmu-events/empty-pmu-events.c +PMU_EVENTS_C = $(OUTPUT)pmu-events/pmu-events.c +METRIC_TEST_LOG = $(OUTPUT)pmu-events/metric_test.log ifeq ($(JEVENTS_ARCH),) JEVENTS_ARCH=$(SRCARCH) endif +JEVENTS_MODEL ?= all # # Locate/process JSON files in pmu-events/arch/ @@ -17,11 +23,15 @@ endif # ifeq ($(NO_JEVENTS),1) -$(OUTPUT)pmu-events/pmu-events.c: pmu-events/empty-pmu-events.c +$(PMU_EVENTS_C): $(EMPTY_PMU_EVENTS_C) $(call rule_mkdir) $(Q)$(call echo-cmd,gen)cp $< $@ else -$(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JSON_TEST) $(JEVENTS_PY) pmu-events/metric.py +$(METRIC_TEST_LOG): $(METRIC_TEST_PY) $(METRIC_PY) $(call rule_mkdir) - $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) pmu-events/arch $@ + $(Q)$(call echo-cmd,test)$(PYTHON) $< 2> $@ || (cat $@ && false) + +$(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) + $(call rule_mkdir) + $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@ endif diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json new file mode 100644 index 000000000000..8ad15b726dca --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json @@ -0,0 +1,273 @@ +[ + { + "ArchStdEvent": "FRONTEND_BOUND", + "MetricExpr": "((stall_slot_frontend) if (#slots - 5) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)" + }, + { + "ArchStdEvent": "BAD_SPECULATION", + "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))" + }, + { + "ArchStdEvent": "RETIRING", + "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))" + }, + { + "ArchStdEvent": "BACKEND_BOUND" + }, + { + "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", + "BriefDescription": "The rate of L1D TLB refill to the overall L1D TLB lookups", + "MetricGroup": "TLB", + "MetricName": "l1d_tlb_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", + "BriefDescription": "The rate of L1I TLB refill to the overall L1I TLB lookups", + "MetricGroup": "TLB", + "MetricName": "l1i_tlb_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", + "BriefDescription": "The rate of L2D TLB refill to the overall L2D TLB lookups", + "MetricGroup": "TLB", + "MetricName": "l2_tlb_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "The rate of TLB Walks per kilo instructions for data accesses", + "MetricGroup": "TLB", + "MetricName": "dtlb_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "DTLB_WALK / L1D_TLB", + "BriefDescription": "The rate of DTLB Walks to the overall L1D TLB lookups", + "MetricGroup": "TLB", + "MetricName": "dtlb_walk_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "The rate of TLB Walks per kilo instructions for instruction accesses", + "MetricGroup": "TLB", + "MetricName": "itlb_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "ITLB_WALK / L1I_TLB", + "BriefDescription": "The rate of ITLB Walks to the overall L1I TLB lookups", + "MetricGroup": "TLB", + "MetricName": "itlb_walk_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "The rate of L1 I-Cache misses per kilo instructions", + "MetricGroup": "Cache", + "MetricName": "l1i_cache_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", + "BriefDescription": "The rate of L1 I-Cache misses to the overall L1 I-Cache", + "MetricGroup": "Cache", + "MetricName": "l1i_cache_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "The rate of L1 D-Cache misses per kilo instructions", + "MetricGroup": "Cache", + "MetricName": "l1d_cache_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", + "BriefDescription": "The rate of L1 D-Cache misses to the overall L1 D-Cache", + "MetricGroup": "Cache", + "MetricName": "l1d_cache_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "The rate of L2 D-Cache misses per kilo instructions", + "MetricGroup": "Cache", + "MetricName": "l2d_cache_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", + "BriefDescription": "The rate of L2 D-Cache misses to the overall L2 D-Cache", + "MetricGroup": "Cache", + "MetricName": "l2d_cache_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "L3D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "The rate of L3 D-Cache misses per kilo instructions", + "MetricGroup": "Cache", + "MetricName": "l3d_cache_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "L3D_CACHE_REFILL / L3D_CACHE", + "BriefDescription": "The rate of L3 D-Cache misses to the overall L3 D-Cache", + "MetricGroup": "Cache", + "MetricName": "l3d_cache_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", + "BriefDescription": "The rate of LL Cache read misses per kilo instructions", + "MetricGroup": "Cache", + "MetricName": "ll_cache_read_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", + "BriefDescription": "The rate of LL Cache read misses to the overall LL Cache read", + "MetricGroup": "Cache", + "MetricName": "ll_cache_read_miss_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", + "BriefDescription": "The rate of LL Cache read hit to the overall LL Cache read", + "MetricGroup": "Cache", + "MetricName": "ll_cache_read_hit_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", + "BriefDescription": "The rate of branches mis-predicted per kilo instructions", + "MetricGroup": "Branch", + "MetricName": "branch_mpki", + "ScaleUnit": "1MPKI" + }, + { + "MetricExpr": "BR_RETIRED / INST_RETIRED * 1000", + "BriefDescription": "The rate of branches retired per kilo instructions", + "MetricGroup": "Branch", + "MetricName": "branch_pki", + "ScaleUnit": "1PKI" + }, + { + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", + "BriefDescription": "The rate of branches mis-predited to the overall branches", + "MetricGroup": "Branch", + "MetricName": "branch_miss_pred_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "instructions / CPU_CYCLES", + "BriefDescription": "The average number of instructions executed for each cycle.", + "MetricGroup": "PEutilization", + "MetricName": "ipc" + }, + { + "MetricExpr": "ipc / 5", + "BriefDescription": "IPC percentage of peak. The peak of IPC is 5.", + "MetricGroup": "PEutilization", + "MetricName": "ipc_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "INST_RETIRED / CPU_CYCLES", + "BriefDescription": "Architecturally executed Instructions Per Cycle (IPC)", + "MetricGroup": "PEutilization", + "MetricName": "retired_ipc" + }, + { + "MetricExpr": "INST_SPEC / CPU_CYCLES", + "BriefDescription": "Speculatively executed Instructions Per Cycle (IPC)", + "MetricGroup": "PEutilization", + "MetricName": "spec_ipc" + }, + { + "MetricExpr": "OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)", + "MetricGroup": "PEutilization", + "MetricName": "retired_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "1 - OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)", + "MetricGroup": "PEutilization", + "MetricName": "wasted_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (#slots - 5) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))", + "BriefDescription": "The truly effective ratio of micro-operations executed by the CPU, which means that misprediction and stall are not included", + "MetricGroup": "PEutilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "LD_SPEC / INST_SPEC", + "BriefDescription": "The rate of load instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "load_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "ST_SPEC / INST_SPEC", + "BriefDescription": "The rate of store instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "store_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "DP_SPEC / INST_SPEC", + "BriefDescription": "The rate of integer data-processing instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "data_process_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "ASE_SPEC / INST_SPEC", + "BriefDescription": "The rate of advanced SIMD instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "advanced_simd_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "VFP_SPEC / INST_SPEC", + "BriefDescription": "The rate of floating point instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "float_point_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "CRYPTO_SPEC / INST_SPEC", + "BriefDescription": "The rate of crypto instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "crypto_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "BR_IMMED_SPEC / INST_SPEC", + "BriefDescription": "The rate of branch immediate instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "branch_immed_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "BR_RETURN_SPEC / INST_SPEC", + "BriefDescription": "The rate of procedure return instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "branch_return_spec_rate", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "BR_INDIRECT_SPEC / INST_SPEC", + "BriefDescription": "The rate of indirect branch instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "InstructionMix", + "MetricName": "branch_indirect_spec_rate", + "ScaleUnit": "100%" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/sbsa.json b/tools/perf/pmu-events/arch/arm64/sbsa.json new file mode 100644 index 000000000000..f678c37ea9c3 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/sbsa.json @@ -0,0 +1,30 @@ +[ + { + "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)", + "BriefDescription": "Frontend bound L1 topdown metric", + "MetricGroup": "TopdownL1", + "MetricName": "frontend_bound", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "(1 - op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))", + "BriefDescription": "Bad speculation L1 topdown metric", + "MetricGroup": "TopdownL1", + "MetricName": "bad_speculation", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "(op_retired / op_spec) * (1 - stall_slot / (#slots * cpu_cycles))", + "BriefDescription": "Retiring L1 topdown metric", + "MetricGroup": "TopdownL1", + "MetricName": "retiring", + "ScaleUnit": "100%" + }, + { + "MetricExpr": "stall_slot_backend / (#slots * cpu_cycles)", + "BriefDescription": "Backend Bound L1 topdown metric", + "MetricGroup": "TopdownL1", + "MetricName": "backend_bound", + "ScaleUnit": "100%" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json index b57526fa44f2..6f53583a0c62 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -15,7 +15,7 @@ { "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason", "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL", - "MetricGroup": "CPI", + "MetricGroup": "CPI;CPI_STALL_RATIO", "MetricName": "DISPATCHED_CPI" }, { @@ -147,13 +147,13 @@ { "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason", "MetricExpr": "PM_ISSUE_STALL / PM_RUN_INST_CMPL", - "MetricGroup": "CPI", + "MetricGroup": "CPI;CPI_STALL_RATIO", "MetricName": "ISSUE_STALL_CPI" }, { "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units", "MetricExpr": "PM_EXEC_STALL / PM_RUN_INST_CMPL", - "MetricGroup": "CPI", + "MetricGroup": "CPI;CPI_STALL_RATIO", "MetricName": "EXECUTION_STALL_CPI" }, { @@ -309,7 +309,7 @@ { "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because the thread was blocked", "MetricExpr": "PM_CMPL_STALL / PM_RUN_INST_CMPL", - "MetricGroup": "CPI", + "MetricGroup": "CPI;CPI_STALL_RATIO", "MetricName": "COMPLETION_STALL_CPI" }, { diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index 7d0de1a2860b..a771e4b6bec5 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -265,7 +265,7 @@ "BriefDescription": "Load Missed L1, counted at finish time." }, { - "EventCode": "0x400FA", + "EventCode": "0x500FA", "EventName": "PM_RUN_INST_CMPL", "BriefDescription": "Completed PowerPC instructions gated by the run latch." } diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 711a4ef05fdf..5facdac6fe8e 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -21,7 +21,7 @@ GenuineIntel-6-A[AC],v1.00,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v17,sandybridge,core -GenuineIntel-6-8F,v1.09,sapphirerapids,core +GenuineIntel-6-(8F|CF),v1.09,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v14,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v53,skylake,core GenuineIntel-6-55-[01234],v1.28,skylakex,core diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 480e8f0d30c8..a938b74cf487 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -11,7 +11,7 @@ #include <string.h> #include <stddef.h> -static const struct pmu_event pme_test_soc_cpu[] = { +static const struct pmu_event pmu_events__test_soc_cpu[] = { { .name = "l3_cache_rd", .event = "event=0x40", @@ -106,6 +106,14 @@ static const struct pmu_event pme_test_soc_cpu[] = { .topic = "branch", }, { + .name = 0, + .event = 0, + .desc = 0, + }, +}; + +static const struct pmu_metric pmu_metrics__test_soc_cpu[] = { + { .metric_expr = "1 / IPC", .metric_name = "CPI", }, @@ -170,9 +178,8 @@ static const struct pmu_event pme_test_soc_cpu[] = { .metric_name = "L1D_Cache_Fill_BW", }, { - .name = 0, - .event = 0, - .desc = 0, + .metric_expr = 0, + .metric_name = 0, }, }; @@ -181,6 +188,11 @@ struct pmu_events_table { const struct pmu_event *entries; }; +/* Struct used to make the PMU metric table implementation opaque to callers. */ +struct pmu_metrics_table { + const struct pmu_metric *entries; +}; + /* * Map a CPU to its table of PMU events. The CPU is identified by the * cpuid field, which is an arch-specific identifier for the CPU. @@ -192,7 +204,8 @@ struct pmu_events_table { struct pmu_events_map { const char *arch; const char *cpuid; - const struct pmu_events_table table; + const struct pmu_events_table event_table; + const struct pmu_metrics_table metric_table; }; /* @@ -203,12 +216,14 @@ static const struct pmu_events_map pmu_events_map[] = { { .arch = "testarch", .cpuid = "testcpu", - .table = { pme_test_soc_cpu }, + .event_table = { pmu_events__test_soc_cpu }, + .metric_table = { pmu_metrics__test_soc_cpu }, }, { .arch = 0, .cpuid = 0, - .table = { 0 }, + .event_table = { 0 }, + .metric_table = { 0 }, }, }; @@ -254,9 +269,7 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = { int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, void *data) { - for (const struct pmu_event *pe = &table->entries[0]; - pe->name || pe->metric_group || pe->metric_name; - pe++) { + for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) { int ret = fn(pe, table, data); if (ret) @@ -265,7 +278,19 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_ev return 0; } -const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu) +int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, + void *data) +{ + for (const struct pmu_metric *pm = &table->entries[0]; pm->metric_expr; pm++) { + int ret = fn(pm, table, data); + + if (ret) + return ret; + } + return 0; +} + +const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) { const struct pmu_events_table *table = NULL; char *cpuid = perf_pmu__getcpuid(pmu); @@ -285,7 +310,35 @@ const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu) break; if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->table; + table = &map->event_table; + break; + } + } + free(cpuid); + return table; +} + +const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu) +{ + const struct pmu_metrics_table *table = NULL; + char *cpuid = perf_pmu__getcpuid(pmu); + int i; + + /* on some platforms which uses cpus map, cpuid can be NULL for + * PMUs other than CORE PMUs. + */ + if (!cpuid) + return NULL; + + i = 0; + for (;;) { + const struct pmu_events_map *map = &pmu_events_map[i++]; + + if (!map->cpuid) + break; + + if (!strcmp_cpuid_str(map->cpuid, cpuid)) { + table = &map->metric_table; break; } } @@ -299,17 +352,39 @@ const struct pmu_events_table *find_core_events_table(const char *arch, const ch tables->arch; tables++) { if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) - return &tables->table; + return &tables->event_table; + } + return NULL; +} + +const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid) +{ + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) + return &tables->metric_table; } return NULL; } int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data) { + for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { + int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + + if (ret) + return ret; + } + return 0; +} + +int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data) +{ for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_events_table_for_each_event(&tables->table, fn, data); + int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -340,3 +415,8 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data) } return 0; } + +int pmu_for_each_sys_metric(pmu_metric_iter_fn fn __maybe_unused, void *data __maybe_unused) +{ + return 0; +} diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 4c398e0eeb2f..2bcd07ce609f 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -3,6 +3,7 @@ """Convert directories of JSON events to C code.""" import argparse import csv +from functools import lru_cache import json import metric import os @@ -12,30 +13,47 @@ import collections # Global command line arguments. _args = None +# List of regular event tables. +_event_tables = [] # List of event tables generated from "/sys" directories. _sys_event_tables = [] +# List of regular metric tables. +_metric_tables = [] +# List of metric tables generated from "/sys" directories. +_sys_metric_tables = [] +# Mapping between sys event table names and sys metric table names. +_sys_event_table_to_metric_table_mapping = {} # Map from an event name to an architecture standard # JsonEvent. Architecture standard events are in json files in the top # f'{_args.starting_dir}/{_args.arch}' directory. _arch_std_events = {} -# Track whether an events table is currently being defined and needs closing. -_close_table = False # Events to write out when the table is closed _pending_events = [] +# Name of events table to be written out +_pending_events_tblname = None +# Metrics to write out when the table is closed +_pending_metrics = [] +# Name of metrics table to be written out +_pending_metrics_tblname = None # Global BigCString shared by all structures. _bcs = None # Order specific JsonEvent attributes will be visited. _json_event_attributes = [ # cmp_sevent related attributes. - 'name', 'pmu', 'topic', 'desc', 'metric_name', 'metric_group', + 'name', 'pmu', 'topic', 'desc', # Seems useful, put it early. 'event', # Short things in alphabetical order. 'aggr_mode', 'compat', 'deprecated', 'perpkg', 'unit', # Longer things (the last won't be iterated over during decompress). - 'metric_constraint', 'metric_expr', 'long_desc' + 'long_desc' ] +# Attributes that are in pmu_metric rather than pmu_event. +_json_metric_attributes = [ + 'metric_name', 'metric_group', 'metric_constraint', 'metric_expr', 'desc', + 'long_desc', 'unit', 'compat', 'aggr_mode' +] def removesuffix(s: str, suffix: str) -> str: """Remove the suffix from a string @@ -46,14 +64,16 @@ def removesuffix(s: str, suffix: str) -> str: return s[0:-len(suffix)] if s.endswith(suffix) else s -def file_name_to_table_name(parents: Sequence[str], dirname: str) -> str: +def file_name_to_table_name(prefix: str, parents: Sequence[str], + dirname: str) -> str: """Generate a C table name from directory names.""" - tblname = 'pme' + tblname = prefix for p in parents: tblname += '_' + p tblname += '_' + dirname return tblname.replace('-', '_') + def c_len(s: str) -> int: """Return the length of s a C string @@ -271,7 +291,7 @@ class JsonEvent: self.metric_constraint = jd.get('MetricConstraint') self.metric_expr = None if 'MetricExpr' in jd: - self.metric_expr = metric.ParsePerfJson(jd['MetricExpr']).Simplify() + self.metric_expr = metric.ParsePerfJson(jd['MetricExpr']).Simplify() arch_std = jd.get('ArchStdEvent') if precise and self.desc and '(Precise Event)' not in self.desc: @@ -320,35 +340,46 @@ class JsonEvent: s += f'\t{attr} = {value},\n' return s + '}' - def build_c_string(self) -> str: + def build_c_string(self, metric: bool) -> str: s = '' - for attr in _json_event_attributes: + for attr in _json_metric_attributes if metric else _json_event_attributes: x = getattr(self, attr) - if x and attr == 'metric_expr': + if metric and x and attr == 'metric_expr': # Convert parsed metric expressions into a string. Slashes # must be doubled in the file. x = x.ToPerfJson().replace('\\', '\\\\') s += f'{x}\\000' if x else '\\000' return s - def to_c_string(self) -> str: + def to_c_string(self, metric: bool) -> str: """Representation of the event as a C struct initializer.""" - s = self.build_c_string() + s = self.build_c_string(metric) return f'{{ { _bcs.offsets[s] } }}, /* {s} */\n' +@lru_cache(maxsize=None) def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]: """Read json events from the specified file.""" - try: - result = json.load(open(path), object_hook=JsonEvent) + events = json.load(open(path), object_hook=JsonEvent) except BaseException as err: print(f"Exception processing {path}") raise - for event in result: + metrics: list[Tuple[str, metric.Expression]] = [] + for event in events: event.topic = topic - return result + if event.metric_name and '-' not in event.metric_name: + metrics.append((event.metric_name, event.metric_expr)) + updates = metric.RewriteMetricsInTermsOfOthers(metrics) + if updates: + for event in events: + if event.metric_name in updates: + # print(f'Updated {event.metric_name} from\n"{event.metric_expr}"\n' + # f'to\n"{updates[event.metric_name]}"') + event.metric_expr = updates[event.metric_name] + + return events def preprocess_arch_std_files(archpath: str) -> None: """Read in all architecture standard events.""" @@ -358,26 +389,20 @@ def preprocess_arch_std_files(archpath: str) -> None: for event in read_json_events(item.path, topic=''): if event.name: _arch_std_events[event.name.lower()] = event - - -def print_events_table_prefix(tblname: str) -> None: - """Called when a new events table is started.""" - global _close_table - if _close_table: - raise IOError('Printing table prefix but last table has no suffix') - _args.output_file.write(f'static const struct compact_pmu_event {tblname}[] = {{\n') - _close_table = True + if event.metric_name: + _arch_std_events[event.metric_name.lower()] = event def add_events_table_entries(item: os.DirEntry, topic: str) -> None: """Add contents of file to _pending_events table.""" - if not _close_table: - raise IOError('Table entries missing prefix') for e in read_json_events(item.path, topic): - _pending_events.append(e) + if e.name: + _pending_events.append(e) + if e.metric_name: + _pending_metrics.append(e) -def print_events_table_suffix() -> None: +def print_pending_events() -> None: """Optionally close events table.""" def event_cmp_key(j: JsonEvent) -> Tuple[bool, str, str, str, str]: @@ -389,17 +414,58 @@ def print_events_table_suffix() -> None: return (j.desc is not None, fix_none(j.topic), fix_none(j.name), fix_none(j.pmu), fix_none(j.metric_name)) - global _close_table - if not _close_table: + global _pending_events + if not _pending_events: return - global _pending_events + global _pending_events_tblname + if _pending_events_tblname.endswith('_sys'): + global _sys_event_tables + _sys_event_tables.append(_pending_events_tblname) + else: + global event_tables + _event_tables.append(_pending_events_tblname) + + _args.output_file.write( + f'static const struct compact_pmu_event {_pending_events_tblname}[] = {{\n') + for event in sorted(_pending_events, key=event_cmp_key): - _args.output_file.write(event.to_c_string()) - _pending_events = [] + _args.output_file.write(event.to_c_string(metric=False)) + _pending_events = [] + + _args.output_file.write('};\n\n') + +def print_pending_metrics() -> None: + """Optionally close metrics table.""" + + def metric_cmp_key(j: JsonEvent) -> Tuple[bool, str, str]: + def fix_none(s: Optional[str]) -> str: + if s is None: + return '' + return s + + return (j.desc is not None, fix_none(j.pmu), fix_none(j.metric_name)) + + global _pending_metrics + if not _pending_metrics: + return + + global _pending_metrics_tblname + if _pending_metrics_tblname.endswith('_sys'): + global _sys_metric_tables + _sys_metric_tables.append(_pending_metrics_tblname) + else: + global metric_tables + _metric_tables.append(_pending_metrics_tblname) + + _args.output_file.write( + f'static const struct compact_pmu_event {_pending_metrics_tblname}[] = {{\n') + + for metric in sorted(_pending_metrics, key=metric_cmp_key): + _args.output_file.write(metric.to_c_string(metric=True)) + _pending_metrics = [] _args.output_file.write('};\n\n') - _close_table = False def get_topic(topic: str) -> str: if topic.endswith('metrics.json'): @@ -423,12 +489,13 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None: topic = get_topic(item.name) for event in read_json_events(item.path, topic): - _bcs.add(event.build_c_string()) + if event.name: + _bcs.add(event.build_c_string(metric=False)) + if event.metric_name: + _bcs.add(event.build_c_string(metric=True)) def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None: """Process a JSON file during the main walk.""" - global _sys_event_tables - def is_leaf_dir(path: str) -> bool: for item in os.scandir(path): if item.is_dir(): @@ -437,12 +504,16 @@ def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None: # model directory, reset topic if item.is_dir() and is_leaf_dir(item.path): - print_events_table_suffix() + print_pending_events() + print_pending_metrics() + + global _pending_events_tblname + _pending_events_tblname = file_name_to_table_name('pmu_events_', parents, item.name) + global _pending_metrics_tblname + _pending_metrics_tblname = file_name_to_table_name('pmu_metrics_', parents, item.name) - tblname = file_name_to_table_name(parents, item.name) if item.name == 'sys': - _sys_event_tables.append(tblname) - print_events_table_prefix(tblname) + _sys_event_table_to_metric_table_mapping[_pending_events_tblname] = _pending_metrics_tblname return # base dir or too deep @@ -467,6 +538,12 @@ struct pmu_events_table { size_t length; }; +/* Struct used to make the PMU metric table implementation opaque to callers. */ +struct pmu_metrics_table { + const struct compact_pmu_event *entries; + size_t length; +}; + /* * Map a CPU to its table of PMU events. The CPU is identified by the * cpuid field, which is an arch-specific identifier for the CPU. @@ -478,7 +555,8 @@ struct pmu_events_table { struct pmu_events_map { const char *arch; const char *cpuid; - struct pmu_events_table table; + struct pmu_events_table event_table; + struct pmu_metrics_table metric_table; }; /* @@ -492,9 +570,13 @@ const struct pmu_events_map pmu_events_map[] = { _args.output_file.write("""{ \t.arch = "testarch", \t.cpuid = "testcpu", -\t.table = { -\t.entries = pme_test_soc_cpu, -\t.length = ARRAY_SIZE(pme_test_soc_cpu), +\t.event_table = { +\t\t.entries = pmu_events__test_soc_cpu, +\t\t.length = ARRAY_SIZE(pmu_events__test_soc_cpu), +\t}, +\t.metric_table = { +\t\t.entries = pmu_metrics__test_soc_cpu, +\t\t.length = ARRAY_SIZE(pmu_metrics__test_soc_cpu), \t} }, """) @@ -505,14 +587,31 @@ const struct pmu_events_map pmu_events_map[] = { for row in table: # Skip the first row or any row beginning with #. if not first and len(row) > 0 and not row[0].startswith('#'): - tblname = file_name_to_table_name([], row[2].replace('/', '_')) + event_tblname = file_name_to_table_name('pmu_events_', [], row[2].replace('/', '_')) + if event_tblname in _event_tables: + event_size = f'ARRAY_SIZE({event_tblname})' + else: + event_tblname = 'NULL' + event_size = '0' + metric_tblname = file_name_to_table_name('pmu_metrics_', [], row[2].replace('/', '_')) + if metric_tblname in _metric_tables: + metric_size = f'ARRAY_SIZE({metric_tblname})' + else: + metric_tblname = 'NULL' + metric_size = '0' + if event_size == '0' and metric_size == '0': + continue cpuid = row[0].replace('\\', '\\\\') _args.output_file.write(f"""{{ \t.arch = "{arch}", \t.cpuid = "{cpuid}", -\t.table = {{ -\t\t.entries = {tblname}, -\t\t.length = ARRAY_SIZE({tblname}) +\t.event_table = {{ +\t\t.entries = {event_tblname}, +\t\t.length = {event_size} +\t}}, +\t.metric_table = {{ +\t\t.entries = {metric_tblname}, +\t\t.length = {metric_size} \t}} }}, """) @@ -521,7 +620,8 @@ const struct pmu_events_map pmu_events_map[] = { _args.output_file.write("""{ \t.arch = 0, \t.cpuid = 0, -\t.table = { 0, 0 }, +\t.event_table = { 0, 0 }, +\t.metric_table = { 0, 0 }, } }; """) @@ -532,14 +632,36 @@ def print_system_mapping_table() -> None: _args.output_file.write(""" struct pmu_sys_events { \tconst char *name; -\tstruct pmu_events_table table; +\tstruct pmu_events_table event_table; +\tstruct pmu_metrics_table metric_table; }; static const struct pmu_sys_events pmu_sys_event_tables[] = { """) + printed_metric_tables = [] for tblname in _sys_event_tables: _args.output_file.write(f"""\t{{ -\t\t.table = {{ +\t\t.event_table = {{ +\t\t\t.entries = {tblname}, +\t\t\t.length = ARRAY_SIZE({tblname}) +\t\t}},""") + metric_tblname = _sys_event_table_to_metric_table_mapping[tblname] + if metric_tblname in _sys_metric_tables: + _args.output_file.write(f""" +\t\t.metric_table = {{ +\t\t\t.entries = {metric_tblname}, +\t\t\t.length = ARRAY_SIZE({metric_tblname}) +\t\t}},""") + printed_metric_tables.append(metric_tblname) + _args.output_file.write(f""" +\t\t.name = \"{tblname}\", +\t}}, +""") + for tblname in _sys_metric_tables: + if tblname in printed_metric_tables: + continue + _args.output_file.write(f"""\t{{ +\t\t.metric_table = {{ \t\t\t.entries = {tblname}, \t\t\t.length = ARRAY_SIZE({tblname}) \t\t}}, @@ -547,11 +669,12 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = { \t}}, """) _args.output_file.write("""\t{ -\t\t.table = { 0, 0 } +\t\t.event_table = { 0, 0 }, +\t\t.metric_table = { 0, 0 }, \t}, }; -static void decompress(int offset, struct pmu_event *pe) +static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) @@ -564,6 +687,19 @@ static void decompress(int offset, struct pmu_event *pe) _args.output_file.write('\twhile (*p++);') _args.output_file.write("""} +static void decompress_metric(int offset, struct pmu_metric *pm) +{ +\tconst char *p = &big_c_string[offset]; +""") + for attr in _json_metric_attributes: + _args.output_file.write(f""" +\tpm->{attr} = (*p == '\\0' ? NULL : p); +""") + if attr == _json_metric_attributes[-1]: + continue + _args.output_file.write('\twhile (*p++);') + _args.output_file.write("""} + int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, void *data) @@ -572,7 +708,9 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table, struct pmu_event pe; int ret; - decompress(table->entries[i].offset, &pe); + decompress_event(table->entries[i].offset, &pe); + if (!pe.name) + continue; ret = fn(&pe, table, data); if (ret) return ret; @@ -580,7 +718,25 @@ int pmu_events_table_for_each_event(const struct pmu_events_table *table, return 0; } -const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu) +int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, + pmu_metric_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->length; i++) { + struct pmu_metric pm; + int ret; + + decompress_metric(table->entries[i].offset, &pm); + if (!pm.metric_expr) + continue; + ret = fn(&pm, table, data); + if (ret) + return ret; + } + return 0; +} + +const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) { const struct pmu_events_table *table = NULL; char *cpuid = perf_pmu__getcpuid(pmu); @@ -599,7 +755,34 @@ const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu) break; if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->table; + table = &map->event_table; + break; + } + } + free(cpuid); + return table; +} + +const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu) +{ + const struct pmu_metrics_table *table = NULL; + char *cpuid = perf_pmu__getcpuid(pmu); + int i; + + /* on some platforms which uses cpus map, cpuid can be NULL for + * PMUs other than CORE PMUs. + */ + if (!cpuid) + return NULL; + + i = 0; + for (;;) { + const struct pmu_events_map *map = &pmu_events_map[i++]; + if (!map->arch) + break; + + if (!strcmp_cpuid_str(map->cpuid, cpuid)) { + table = &map->metric_table; break; } } @@ -613,7 +796,18 @@ const struct pmu_events_table *find_core_events_table(const char *arch, const ch tables->arch; tables++) { if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) - return &tables->table; + return &tables->event_table; + } + return NULL; +} + +const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid) +{ + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + if (!strcmp(tables->arch, arch) && !strcmp_cpuid_str(tables->cpuid, cpuid)) + return &tables->metric_table; } return NULL; } @@ -623,7 +817,20 @@ int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data) for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) { - int ret = pmu_events_table_for_each_event(&tables->table, fn, data); + int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + + if (ret) + return ret; + } + return 0; +} + +int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data) +{ + for (const struct pmu_events_map *tables = &pmu_events_map[0]; + tables->arch; + tables++) { + int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -637,7 +844,7 @@ const struct pmu_events_table *find_sys_events_table(const char *name) tables->name; tables++) { if (!strcmp(tables->name, name)) - return &tables->table; + return &tables->event_table; } return NULL; } @@ -647,7 +854,20 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data) for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; tables->name; tables++) { - int ret = pmu_events_table_for_each_event(&tables->table, fn, data); + int ret = pmu_events_table_for_each_event(&tables->event_table, fn, data); + + if (ret) + return ret; + } + return 0; +} + +int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data) +{ + for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + tables->name; + tables++) { + int ret = pmu_metrics_table_for_each_metric(&tables->metric_table, fn, data); if (ret) return ret; @@ -670,12 +890,24 @@ def main() -> None: action: Callable[[Sequence[str], os.DirEntry], None]) -> None: """Replicate the directory/file walking behavior of C's file tree walk.""" for item in os.scandir(path): + if _args.model != 'all' and item.is_dir(): + # Check if the model matches one in _args.model. + if len(parents) == _args.model.split(',')[0].count('/'): + # We're testing the correct directory. + item_path = '/'.join(parents) + ('/' if len(parents) > 0 else '') + item.name + if 'test' not in item_path and item_path not in _args.model.split(','): + continue action(parents, item) if item.is_dir(): ftw(item.path, parents + [item.name], action) ap = argparse.ArgumentParser() ap.add_argument('arch', help='Architecture name like x86') + ap.add_argument('model', help='''Select a model such as skylake to +reduce the code size. Normally set to "all". For architectures like +ARM64 with an implementor/model, the model must include the implementor +such as "arm/cortex-a34".''', + default='all') ap.add_argument( 'starting_dir', type=dir_path, @@ -721,7 +953,8 @@ struct compact_pmu_event { for arch in archs: arch_path = f'{_args.starting_dir}/{arch}' ftw(arch_path, [], process_one_file) - print_events_table_suffix() + print_pending_events() + print_pending_metrics() print_mapping_table(archs) print_system_mapping_table() diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 4797ed4fd817..77ea6ff98538 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -4,7 +4,7 @@ import ast import decimal import json import re -from typing import Dict, List, Optional, Set, Union +from typing import Dict, List, Optional, Set, Tuple, Union class Expression: @@ -26,6 +26,9 @@ class Expression: """Returns true when two expressions are the same.""" raise NotImplementedError() + def Substitute(self, name: str, expression: 'Expression') -> 'Expression': + raise NotImplementedError() + def __str__(self) -> str: return self.ToPerfJson() @@ -186,6 +189,15 @@ class Operator(Expression): other.lhs) and self.rhs.Equals(other.rhs) return False + def Substitute(self, name: str, expression: Expression) -> Expression: + if self.Equals(expression): + return Event(name) + lhs = self.lhs.Substitute(name, expression) + rhs = None + if self.rhs: + rhs = self.rhs.Substitute(name, expression) + return Operator(self.operator, lhs, rhs) + class Select(Expression): """Represents a select ternary in the parse tree.""" @@ -225,6 +237,14 @@ class Select(Expression): other.false_val) and self.true_val.Equals(other.true_val) return False + def Substitute(self, name: str, expression: Expression) -> Expression: + if self.Equals(expression): + return Event(name) + true_val = self.true_val.Substitute(name, expression) + cond = self.cond.Substitute(name, expression) + false_val = self.false_val.Substitute(name, expression) + return Select(true_val, cond, false_val) + class Function(Expression): """A function in an expression like min, max, d_ratio.""" @@ -261,10 +281,21 @@ class Function(Expression): def Equals(self, other: Expression) -> bool: if isinstance(other, Function): - return self.fn == other.fn and self.lhs.Equals( - other.lhs) and self.rhs.Equals(other.rhs) + result = self.fn == other.fn and self.lhs.Equals(other.lhs) + if self.rhs: + result = result and self.rhs.Equals(other.rhs) + return result return False + def Substitute(self, name: str, expression: Expression) -> Expression: + if self.Equals(expression): + return Event(name) + lhs = self.lhs.Substitute(name, expression) + rhs = None + if self.rhs: + rhs = self.rhs.Substitute(name, expression) + return Function(self.fn, lhs, rhs) + def _FixEscapes(s: str) -> str: s = re.sub(r'([^\\]),', r'\1\\,', s) @@ -291,6 +322,9 @@ class Event(Expression): def Equals(self, other: Expression) -> bool: return isinstance(other, Event) and self.name == other.name + def Substitute(self, name: str, expression: Expression) -> Expression: + return self + class Constant(Expression): """A constant within the expression tree.""" @@ -315,6 +349,9 @@ class Constant(Expression): def Equals(self, other: Expression) -> bool: return isinstance(other, Constant) and self.value == other.value + def Substitute(self, name: str, expression: Expression) -> Expression: + return self + class Literal(Expression): """A runtime literal within the expression tree.""" @@ -334,6 +371,9 @@ class Literal(Expression): def Equals(self, other: Expression) -> bool: return isinstance(other, Literal) and self.value == other.value + def Substitute(self, name: str, expression: Expression) -> Expression: + return self + def min(lhs: Union[int, float, Expression], rhs: Union[int, float, Expression]) -> Function: @@ -459,6 +499,7 @@ class MetricGroup: class _RewriteIfExpToSelect(ast.NodeTransformer): + """Transformer to convert if-else nodes to Select expressions.""" def visit_IfExp(self, node): # pylint: disable=invalid-name @@ -496,7 +537,37 @@ def ParsePerfJson(orig: str) -> Expression: for kw in keywords: py = re.sub(rf'Event\(r"{kw}"\)', kw, py) - parsed = ast.parse(py, mode='eval') + try: + parsed = ast.parse(py, mode='eval') + except SyntaxError as e: + raise SyntaxError(f'Parsing expression:\n{orig}') from e _RewriteIfExpToSelect().visit(parsed) parsed = ast.fix_missing_locations(parsed) return _Constify(eval(compile(parsed, orig, 'eval'))) + + +def RewriteMetricsInTermsOfOthers(metrics: List[Tuple[str, Expression]] + )-> Dict[str, Expression]: + """Shorten metrics by rewriting in terms of others. + + Args: + metrics (list): pairs of metric names and their expressions. + Returns: + Dict: mapping from a metric name to a shortened expression. + """ + updates: Dict[str, Expression] = dict() + for outer_name, outer_expression in metrics: + updated = outer_expression + while True: + for inner_name, inner_expression in metrics: + if inner_name.lower() == outer_name.lower(): + continue + if inner_name in updates: + inner_expression = updates[inner_name] + updated = updated.Substitute(inner_name, inner_expression) + if updated.Equals(outer_expression): + break + if outer_name in updates and updated.Equals(updates[outer_name]): + break + updates[outer_name] = updated + return updates diff --git a/tools/perf/pmu-events/metric_test.py b/tools/perf/pmu-events/metric_test.py index 15315d0f716c..40a3c7d8b2bc 100644..100755 --- a/tools/perf/pmu-events/metric_test.py +++ b/tools/perf/pmu-events/metric_test.py @@ -1,8 +1,11 @@ +#!/usr/bin/env python3 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) import unittest from metric import Constant from metric import Event +from metric import Expression from metric import ParsePerfJson +from metric import RewriteMetricsInTermsOfOthers class TestMetricExpressions(unittest.TestCase): @@ -87,8 +90,8 @@ class TestMetricExpressions(unittest.TestCase): after = r'min((a + b if c > 1 else c + d), e + f)' self.assertEqual(ParsePerfJson(before).ToPerfJson(), after) - before =3D r'a if b else c if d else e' - after =3D r'(a if b else (c if d else e))' + before = r'a if b else c if d else e' + after = r'(a if b else (c if d else e))' self.assertEqual(ParsePerfJson(before).ToPerfJson(), after) def test_ToPython(self): @@ -153,5 +156,13 @@ class TestMetricExpressions(unittest.TestCase): after = '0 * SLOTS' self.assertEqual(ParsePerfJson(before).Simplify().ToPerfJson(), after) + def test_RewriteMetricsInTermsOfOthers(self): + Expression.__eq__ = lambda e1, e2: e1.Equals(e2) + before = [('m1', ParsePerfJson('a + b + c + d')), + ('m2', ParsePerfJson('a + b + c'))] + after = {'m1': ParsePerfJson('m2 + d')} + self.assertEqual(RewriteMetricsInTermsOfOthers(before), after) + Expression.__eq__ = None + if __name__ == '__main__': unittest.main() diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index fe343c4d8016..b7d4a66b8ad2 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -23,27 +23,47 @@ struct pmu_event { const char *unit; const char *perpkg; const char *aggr_mode; - const char *metric_expr; + const char *deprecated; +}; + +struct pmu_metric { const char *metric_name; const char *metric_group; - const char *deprecated; + const char *metric_expr; + const char *unit; + const char *compat; + const char *aggr_mode; const char *metric_constraint; + const char *desc; + const char *long_desc; }; struct pmu_events_table; +struct pmu_metrics_table; typedef int (*pmu_event_iter_fn)(const struct pmu_event *pe, const struct pmu_events_table *table, void *data); +typedef int (*pmu_metric_iter_fn)(const struct pmu_metric *pm, + const struct pmu_metrics_table *table, + void *data); + int pmu_events_table_for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, void *data); +int pmu_metrics_table_for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, + void *data); -const struct pmu_events_table *perf_pmu__find_table(struct perf_pmu *pmu); +const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu); +const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu); const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid); +const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid); int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data); +int pmu_for_each_core_metric(pmu_metric_iter_fn fn, void *data); const struct pmu_events_table *find_sys_events_table(const char *name); +const struct pmu_metrics_table *find_sys_metrics_table(const char *name); int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data); +int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data); #endif diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py index b6af1dd5f816..cf7ce8229a6c 100755 --- a/tools/perf/scripts/python/flamegraph.py +++ b/tools/perf/scripts/python/flamegraph.py @@ -19,12 +19,34 @@ # pylint: disable=missing-function-docstring from __future__ import print_function -import sys -import os -import io import argparse +import hashlib +import io import json +import os import subprocess +import sys +import urllib.request + +minimal_html = """<head> + <link rel="stylesheet" type="text/css" href="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.css"> +</head> +<body> + <div id="chart"></div> + <script type="text/javascript" src="https://d3js.org/d3.v7.js"></script> + <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/d3-flamegraph.min.js"></script> + <script type="text/javascript"> + const stacks = [/** @flamegraph_json **/]; + // Note, options is unused. + const options = [/** @options_json **/]; + + var chart = flamegraph(); + d3.select("#chart") + .datum(stacks[0]) + .call(chart); + </script> +</body> +""" # pylint: disable=too-few-public-methods class Node: @@ -50,16 +72,6 @@ class FlameGraphCLI: self.args = args self.stack = Node("all", "root") - if self.args.format == "html" and \ - not os.path.isfile(self.args.template): - print("Flame Graph template {} does not exist. Please install " - "the js-d3-flame-graph (RPM) or libjs-d3-flame-graph (deb) " - "package, specify an existing flame graph template " - "(--template PATH) or another output format " - "(--format FORMAT).".format(self.args.template), - file=sys.stderr) - sys.exit(1) - @staticmethod def get_libtype_from_dso(dso): """ @@ -128,16 +140,63 @@ class FlameGraphCLI: } options_json = json.dumps(options) + template_md5sum = None + if self.args.format == "html": + if os.path.isfile(self.args.template): + template = f"file://{self.args.template}" + else: + if not self.args.allow_download: + print(f"""Warning: Flame Graph template '{self.args.template}' +does not exist. To avoid this please install a package such as the +js-d3-flame-graph or libjs-d3-flame-graph, specify an existing flame +graph template (--template PATH) or use another output format (--format +FORMAT).""", + file=sys.stderr) + if self.args.input == "-": + print("""Not attempting to download Flame Graph template as script command line +input is disabled due to using live mode. If you want to download the +template retry without live mode. For example, use 'perf record -a -g +-F 99 sleep 60' and 'perf script report flamegraph'. Alternatively, +download the template from: +https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/d3-flamegraph-base.html +and place it at: +/usr/share/d3-flame-graph/d3-flamegraph-base.html""", + file=sys.stderr) + quit() + s = None + while s != "y" and s != "n": + s = input("Do you wish to download a template from cdn.jsdelivr.net? (this warning can be suppressed with --allow-download) [yn] ").lower() + if s == "n": + quit() + template = "https://cdn.jsdelivr.net/npm/d3-flame-graph@4.1.3/dist/templates/d3-flamegraph-base.html" + template_md5sum = "143e0d06ba69b8370b9848dcd6ae3f36" + try: - with io.open(self.args.template, encoding="utf-8") as template: - output_str = ( - template.read() - .replace("/** @options_json **/", options_json) - .replace("/** @flamegraph_json **/", stacks_json) - ) - except IOError as err: - print("Error reading template file: {}".format(err), file=sys.stderr) - sys.exit(1) + with urllib.request.urlopen(template) as template: + output_str = "".join([ + l.decode("utf-8") for l in template.readlines() + ]) + except Exception as err: + print(f"Error reading template {template}: {err}\n" + "a minimal flame graph will be generated", file=sys.stderr) + output_str = minimal_html + template_md5sum = None + + if template_md5sum: + download_md5sum = hashlib.md5(output_str.encode("utf-8")).hexdigest() + if download_md5sum != template_md5sum: + s = None + while s != "y" and s != "n": + s = input(f"""Unexpected template md5sum. +{download_md5sum} != {template_md5sum}, for: +{output_str} +continue?[yn] """).lower() + if s == "n": + quit() + + output_str = output_str.replace("/** @options_json **/", options_json) + output_str = output_str.replace("/** @flamegraph_json **/", stacks_json) + output_fn = self.args.output or "flamegraph.html" else: output_str = stacks_json @@ -172,6 +231,10 @@ if __name__ == "__main__": choices=["blue-green", "orange"]) parser.add_argument("-i", "--input", help=argparse.SUPPRESS) + parser.add_argument("--allow-download", + default=False, + action="store_true", + help="allow unprompted downloading of HTML template") cli_args = parser.parse_args() cli = FlameGraphCLI(cli_args) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 90fd1eb317bb..fb9ac5dc4079 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -68,6 +68,7 @@ perf-y += perf-time-to-tsc.o perf-y += dlfilter-test.o perf-y += sigtrap.o perf-y += event_groups.o +perf-y += symbols.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c index 7981c69ed1b4..b638cc99d5ae 100644 --- a/tools/perf/tests/bpf-script-example.c +++ b/tools/perf/tests/bpf-script-example.c @@ -43,7 +43,7 @@ struct { __type(value, int); } flip_table SEC(".maps"); -SEC("func=do_epoll_wait") +SEC("syscalls:sys_enter_epoll_pwait") int bpf_func__SyS_epoll_pwait(void *ctx) { int ind =0; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 17c023823713..ae9223f27cfb 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -23,7 +23,7 @@ #define NR_ITERS 111 #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" -#ifdef HAVE_LIBBPF_SUPPORT +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) #include <linux/bpf.h> #include <bpf/bpf.h> @@ -126,6 +126,10 @@ static int do_test(struct bpf_object *obj, int (*func)(void), err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL); parse_events_error__exit(&parse_error); + if (err == -ENODATA) { + pr_debug("Failed to add events selected by BPF, debuginfo package not installed\n"); + return TEST_SKIP; + } if (err || list_empty(&parse_state.list)) { pr_debug("Failed to add events selected by BPF\n"); return TEST_FAIL; @@ -330,10 +334,10 @@ static int test__bpf(int i) static int test__basic_bpf_test(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { -#ifdef HAVE_LIBBPF_SUPPORT +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) return test__bpf(0); #else - pr_debug("Skip BPF test because BPF support is not compiled\n"); + pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); return TEST_SKIP; #endif } @@ -341,10 +345,10 @@ static int test__basic_bpf_test(struct test_suite *test __maybe_unused, static int test__bpf_pinning(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { -#ifdef HAVE_LIBBPF_SUPPORT +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) return test__bpf(1); #else - pr_debug("Skip BPF test because BPF support is not compiled\n"); + pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); return TEST_SKIP; #endif } @@ -352,30 +356,30 @@ static int test__bpf_pinning(struct test_suite *test __maybe_unused, static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { -#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) && defined(HAVE_LIBTRACEEVENT) return test__bpf(2); #else - pr_debug("Skip BPF test because BPF support is not compiled\n"); + pr_debug("Skip BPF test because BPF or libtraceevent support is not compiled\n"); return TEST_SKIP; #endif } static struct test_case bpf_tests[] = { -#ifdef HAVE_LIBBPF_SUPPORT +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_LIBTRACEEVENT) TEST_CASE("Basic BPF filtering", basic_bpf_test), TEST_CASE_REASON("BPF pinning", bpf_pinning, "clang isn't installed or environment missing BPF support"), #ifdef HAVE_BPF_PROLOGUE TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, - "clang isn't installed or environment missing BPF support"), + "clang/debuginfo isn't installed or environment missing BPF support"), #else TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), #endif #else - TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in"), - TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in"), - TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), + TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in or missing libtraceevent support"), + TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in or missing libtraceevent support"), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in or missing libtraceevent support"), #endif { .name = NULL, } }; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index cfa61493c750..35cc3807cc9e 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -31,6 +31,7 @@ #include "builtin-test-list.h" static bool dont_fork; +const char *dso_to_test; struct test_suite *__weak arch_tests[] = { NULL, @@ -117,6 +118,7 @@ static struct test_suite *generic_tests[] = { &suite__dlfilter, &suite__sigtrap, &suite__event_groups, + &suite__symbols, NULL, }; @@ -521,6 +523,7 @@ int cmd_test(int argc, const char **argv) OPT_BOOLEAN('F', "dont-fork", &dont_fork, "Do not fork for testcase"), OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"), + OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"), OPT_END() }; const char * const test_subcommands[] = { "list", NULL }; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index afdca7f2959f..ee983b677a6a 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -67,6 +67,7 @@ int test_dwarf_unwind__compare(void *p1, void *p2); int test_dwarf_unwind__krava_3(struct thread *thread); int test_dwarf_unwind__krava_2(struct thread *thread); int test_dwarf_unwind__krava_1(struct thread *thread); +int test__dwarf_unwind(struct test_suite *test, int subtest); #define MAX_STACK 8 @@ -195,8 +196,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *th return ret; } -static int test__dwarf_unwind(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) +noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct machine *machine; struct thread *thread; diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 51fb5f34c1dd..672a27f37060 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -180,13 +180,13 @@ static int expand_metric_events(void) struct evlist *evlist; struct rblist metric_events; const char metric_str[] = "CPI"; - const struct pmu_events_table *pme_test; + const struct pmu_metrics_table *pme_test; evlist = evlist__new(); TEST_ASSERT_VAL("failed to get evlist", evlist); rblist__init(&metric_events); - pme_test = find_core_events_table("testarch", "testcpu"); + pme_test = find_core_metrics_table("testarch", "testcpu"); ret = metricgroup__parse_groups_test(evlist, pme_test, metric_str, false, false, &metric_events); if (ret < 0) { diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 21b7ac00d798..9fec6040950c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -72,7 +72,7 @@ static int __compute_metric(const char *name, struct value *vals, struct rblist metric_events = { .nr_entries = 0, }; - const struct pmu_events_table *pme_test; + const struct pmu_metrics_table *pme_test; struct perf_cpu_map *cpus; struct runtime_stat st; struct evlist *evlist; @@ -96,7 +96,7 @@ static int __compute_metric(const char *name, struct value *vals, runtime_stat__init(&st); /* Parse the metric into metric_events list. */ - pme_test = find_core_events_table("testarch", "testcpu"); + pme_test = find_core_metrics_table("testarch", "testcpu"); err = metricgroup__parse_groups_test(evlist, pme_test, name, false, false, &metric_events); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index a9f2330f6257..accf44b3d968 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -337,36 +337,12 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event return -1; } - if (!is_same(e1->metric_expr, e2->metric_expr)) { - pr_debug2("testing event e1 %s: mismatched metric_expr, %s vs %s\n", - e1->name, e1->metric_expr, e2->metric_expr); - return -1; - } - - if (!is_same(e1->metric_name, e2->metric_name)) { - pr_debug2("testing event e1 %s: mismatched metric_name, %s vs %s\n", - e1->name, e1->metric_name, e2->metric_name); - return -1; - } - - if (!is_same(e1->metric_group, e2->metric_group)) { - pr_debug2("testing event e1 %s: mismatched metric_group, %s vs %s\n", - e1->name, e1->metric_group, e2->metric_group); - return -1; - } - if (!is_same(e1->deprecated, e2->deprecated)) { pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", e1->name, e1->deprecated, e2->deprecated); return -1; } - if (!is_same(e1->metric_constraint, e2->metric_constraint)) { - pr_debug2("testing event e1 %s: mismatched metric_constant, %s vs %s\n", - e1->name, e1->metric_constraint, e2->metric_constraint); - return -1; - } - return 0; } @@ -432,9 +408,6 @@ static int test__pmu_event_table_core_callback(const struct pmu_event *pe, struct perf_pmu_test_event const **test_event_table; bool found = false; - if (!pe->name) - return 0; - if (pe->pmu) test_event_table = &uncore_events[0]; else @@ -496,7 +469,8 @@ static int test__pmu_event_table_sys_callback(const struct pmu_event *pe, static int test__pmu_event_table(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - const struct pmu_events_table *sys_event_table = find_sys_events_table("pme_test_soc_sys"); + const struct pmu_events_table *sys_event_table = + find_sys_events_table("pmu_events__test_soc_sys"); const struct pmu_events_table *table = find_core_events_table("testarch", "testcpu"); int map_events = 0, expected_events, err; @@ -840,7 +814,8 @@ struct metric { struct metric_ref metric_ref; }; -static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_events_table *table, +static int test__parsing_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table, void *data) { int *failures = data; @@ -854,10 +829,10 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e }; int err = 0; - if (!pe->metric_expr) + if (!pm->metric_expr) return 0; - pr_debug("Found metric '%s'\n", pe->metric_name); + pr_debug("Found metric '%s'\n", pm->metric_name); (*failures)++; /* @@ -877,14 +852,14 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e perf_evlist__set_maps(&evlist->core, cpus, NULL); runtime_stat__init(&st); - err = metricgroup__parse_groups_test(evlist, table, pe->metric_name, + err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, false, false, &metric_events); if (err) { - if (!strcmp(pe->metric_name, "M1") || !strcmp(pe->metric_name, "M2") || - !strcmp(pe->metric_name, "M3")) { + if (!strcmp(pm->metric_name, "M1") || !strcmp(pm->metric_name, "M2") || + !strcmp(pm->metric_name, "M3")) { (*failures)--; - pr_debug("Expected broken metric %s skipping\n", pe->metric_name); + pr_debug("Expected broken metric %s skipping\n", pm->metric_name); err = 0; } goto out_err; @@ -912,7 +887,7 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e struct metric_expr *mexp; list_for_each_entry (mexp, &me->head, nd) { - if (strcmp(mexp->metric_name, pe->metric_name)) + if (strcmp(mexp->metric_name, pm->metric_name)) continue; pr_debug("Result %f\n", test_generic_metric(mexp, 0, &st)); err = 0; @@ -921,11 +896,11 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e } } } - pr_debug("Didn't find parsed metric %s", pe->metric_name); + pr_debug("Didn't find parsed metric %s", pm->metric_name); err = 1; out_err: if (err) - pr_debug("Broken metric %s\n", pe->metric_name); + pr_debug("Broken metric %s\n", pm->metric_name); /* ... cleanup. */ metricgroup__rblist_exit(&metric_events); @@ -941,8 +916,8 @@ static int test__parsing(struct test_suite *test __maybe_unused, { int failures = 0; - pmu_for_each_core_event(test__parsing_callback, &failures); - pmu_for_each_sys_event(test__parsing_callback, &failures); + pmu_for_each_core_metric(test__parsing_callback, &failures); + pmu_for_each_sys_metric(test__parsing_callback, &failures); return failures == 0 ? TEST_OK : TEST_FAIL; } @@ -975,6 +950,7 @@ static int metric_parse_fake(const char *metric_name, const char *str) pr_debug("expr__ctx_new failed"); return TEST_FAIL; } + ctx->sctx.is_test = true; if (expr__find_ids(str, NULL, ctx) < 0) { pr_err("expr__find_ids failed\n"); return -1; @@ -1021,14 +997,11 @@ out: return ret; } -static int test__parsing_fake_callback(const struct pmu_event *pe, - const struct pmu_events_table *table __maybe_unused, +static int test__parsing_fake_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, void *data __maybe_unused) { - if (!pe->metric_expr) - return 0; - - return metric_parse_fake(pe->metric_name, pe->metric_expr); + return metric_parse_fake(pm->metric_name, pm->metric_expr); } /* @@ -1047,11 +1020,11 @@ static int test__parsing_fake(struct test_suite *test __maybe_unused, return err; } - err = pmu_for_each_core_event(test__parsing_fake_callback, NULL); + err = pmu_for_each_core_metric(test__parsing_fake_callback, NULL); if (err) return err; - return pmu_for_each_sys_event(test__parsing_fake_callback, NULL); + return pmu_for_each_sys_metric(test__parsing_fake_callback, NULL); } static struct test_case pmu_events_tests[] = { diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 927c7f0cc4cc..25a3f6cece50 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -37,7 +37,7 @@ * in branch_stack variable. */ #define BS_EXPECTED_BE 0xa000d00000000000 -#define BS_EXPECTED_LE 0xd5000000 +#define BS_EXPECTED_LE 0x1aa00000000 #define FLAG(s) s->branch_stack->entries[i].flags static bool samples_same(const struct perf_sample *s1, diff --git a/tools/perf/tests/shell/buildid.sh b/tools/perf/tests/shell/buildid.sh index aaf851108ca3..0ce22ea0a7f1 100755 --- a/tools/perf/tests/shell/buildid.sh +++ b/tools/perf/tests/shell/buildid.sh @@ -66,7 +66,9 @@ check() esac echo "build id: ${id}" - link=${build_id_dir}/.build-id/${id:0:2}/${id:2} + id_file=${id#??} + id_dir=${id%$id_file} + link=$build_id_dir/.build-id/$id_dir/$id_file echo "link: ${link}" if [ ! -h $link ]; then @@ -74,7 +76,7 @@ check() exit 1 fi - file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf + file=${build_id_dir}/.build-id/$id_dir/`readlink ${link}`/elf echo "file: ${file}" # Check for file permission of original file @@ -130,20 +132,22 @@ test_record() { data=$(mktemp /tmp/perf.data.XXX) build_id_dir=$(mktemp -d /tmp/perf.debug.XXX) - log=$(mktemp /tmp/perf.log.XXX) + log_out=$(mktemp /tmp/perf.log.out.XXX) + log_err=$(mktemp /tmp/perf.log.err.XXX) perf="perf --buildid-dir ${build_id_dir}" echo "running: perf record $@" - ${perf} record --buildid-all -o ${data} $@ &> ${log} + ${perf} record --buildid-all -o ${data} $@ 1>${log_out} 2>${log_err} if [ $? -ne 0 ]; then echo "failed: record $@" - echo "see log: ${log}" + echo "see log: ${log_err}" exit 1 fi - check ${@: -1} + args="$*" + check ${args##* } - rm -f ${log} + rm -f ${log_out} ${log_err} rm -rf ${build_id_dir} rm -rf ${data} } diff --git a/tools/perf/tests/shell/lib/coresight.sh b/tools/perf/tests/shell/lib/coresight.sh index 45a1477256b6..6c3d34ec64d8 100644 --- a/tools/perf/tests/shell/lib/coresight.sh +++ b/tools/perf/tests/shell/lib/coresight.sh @@ -58,9 +58,9 @@ perf_dump_aux_verify() { # compiler may produce different code depending on the compiler and # optimization options, so this is rough just to see if we're # either missing almost all the data or all of it - ATOM_FX_NUM=`grep I_ATOM_F "$DUMP" | wc -l` - ASYNC_NUM=`grep I_ASYNC "$DUMP" | wc -l` - TRACE_INFO_NUM=`grep I_TRACE_INFO "$DUMP" | wc -l` + ATOM_FX_NUM=$(grep -c I_ATOM_F "$DUMP") + ASYNC_NUM=$(grep -c I_ASYNC "$DUMP") + TRACE_INFO_NUM=$(grep -c I_TRACE_INFO "$DUMP") rm -f "$DUMP" # Arguments provide minimums for a pass @@ -96,18 +96,18 @@ perf_dump_aux_tid_verify() { # The TID test tools will print a TID per stdout line that are being # tested - TIDS=`cat "$2"` + TIDS=$(cat "$2") # Scan the perf report to find the TIDs that are actually CID in hex # and build a list of the ones found - FOUND_TIDS=`perf report --stdio --dump -i "$1" | \ + FOUND_TIDS=$(perf report --stdio --dump -i "$1" | \ grep -o "CID=0x[0-9a-z]\+" | sed 's/CID=//g' | \ - uniq | sort | uniq` + uniq | sort | uniq) # No CID=xxx found - maybe your kernel is reporting these as # VMID=xxx so look there if test -z "$FOUND_TIDS"; then - FOUND_TIDS=`perf report --stdio --dump -i "$1" | \ + FOUND_TIDS=$(perf report --stdio --dump -i "$1" | \ grep -o "VMID=0x[0-9a-z]\+" | sed 's/VMID=//g' | \ - uniq | sort | uniq` + uniq | sort | uniq) fi # Iterate over the list of TIDs that the test says it has and find @@ -116,7 +116,7 @@ perf_dump_aux_tid_verify() { for TID2 in $TIDS; do FOUND="" for TIDHEX in $FOUND_TIDS; do - TID=`printf "%i" $TIDHEX` + TID=$(printf "%i" $TIDHEX) if test "$TID" -eq "$TID2"; then FOUND="y" break diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index ed0a3972c4c8..60c5e34f90c4 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -22,3 +22,11 @@ skip_if_no_debuginfo() { add_probe_vfs_getname -v 2>&1 | grep -E -q "^(Failed to find the path for the kernel|Debuginfo-analysis is not supported)|(file has no debug information)" && return 2 return 1 } + +# check if perf is compiled with libtraceevent support +skip_no_probe_record_support() { + if [ $had_vfs_getname -eq 1 ] ; then + perf record --dry-run -e $1 2>&1 | grep "libtraceevent is necessary for tracepoint support" && return 2 + return 1 + fi +} diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index b05f1b1ca6c8..be5fcafb26aa 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -128,7 +128,7 @@ test_type_filter() echo "Testing perf lock contention --type-filter (w/ spinlock)" perf lock contention -i ${perfdata} -Y spinlock -q 2> ${result} if [ $(grep -c -v spinlock "${result}") != "0" ]; then - echo "[Fail] Recorded should not have non-spinlocks:" $(cat "${result}") + echo "[Fail] Recorded result should not have non-spinlocks:" $(cat "${result}") err=1 exit fi @@ -139,7 +139,7 @@ test_type_filter() perf lock con -a -b -Y spinlock -q -- perf bench sched messaging > /dev/null 2> ${result} if [ $(grep -c -v spinlock "${result}") != "0" ]; then - echo "[Fail] Recorded should not have non-spinlocks:" $(cat "${result}") + echo "[Fail] BPF result should not have non-spinlocks:" $(cat "${result}") err=1 exit fi @@ -160,7 +160,7 @@ test_lock_filter() local type=$(head -1 "${result}" | awk '{ print $8 }' | sed -e 's/:.*//') if [ $(grep -c -v "${type}" "${result}") != "0" ]; then - echo "[Fail] Recorded should not have non-${type} locks:" $(cat "${result}") + echo "[Fail] Recorded result should not have non-${type} locks:" $(cat "${result}") err=1 exit fi @@ -171,7 +171,63 @@ test_lock_filter() perf lock con -a -b -L tasklist_lock -q -- perf bench sched messaging > /dev/null 2> ${result} if [ $(grep -c -v "${type}" "${result}") != "0" ]; then - echo "[Fail] Recorded should not have non-${type} locks:" $(cat "${result}") + echo "[Fail] BPF result should not have non-${type} locks:" $(cat "${result}") + err=1 + exit + fi +} + +test_stack_filter() +{ + echo "Testing perf lock contention --callstack-filter (w/ unix_stream)" + perf lock contention -i ${perfdata} -v -q 2> ${result} + if [ $(grep -c unix_stream "${result}") == "0" ]; then + echo "[Skip] Could not find 'unix_stream'" + return + fi + + perf lock contention -i ${perfdata} -E 1 -S unix_stream -q 2> ${result} + if [ $(cat "${result}" | wc -l) != "1" ]; then + echo "[Fail] Recorded result should have a lock from unix_stream:" $(cat "${result}") + err=1 + exit + fi + + if ! perf lock con -b true > /dev/null 2>&1 ; then + return + fi + + perf lock con -a -b -S unix_stream -E 1 -q -- perf bench sched messaging > /dev/null 2> ${result} + if [ $(cat "${result}" | wc -l) != "1" ]; then + echo "[Fail] BPF result should have a lock from unix_stream:" $(cat "${result}") + err=1 + exit + fi +} + +test_aggr_task_stack_filter() +{ + echo "Testing perf lock contention --callstack-filter with task aggregation" + perf lock contention -i ${perfdata} -v -q 2> ${result} + if [ $(grep -c unix_stream "${result}") == "0" ]; then + echo "[Skip] Could not find 'unix_stream'" + return + fi + + perf lock contention -i ${perfdata} -t -E 1 -S unix_stream -q 2> ${result} + if [ $(cat "${result}" | wc -l) != "1" ]; then + echo "[Fail] Recorded result should have a task from unix_stream:" $(cat "${result}") + err=1 + exit + fi + + if ! perf lock con -b true > /dev/null 2>&1 ; then + return + fi + + perf lock con -a -b -t -S unix_stream -E 1 -q -- perf bench sched messaging > /dev/null 2> ${result} + if [ $(cat "${result}" | wc -l) != "1" ]; then + echo "[Fail] BPF result should have a task from unix_stream:" $(cat "${result}") err=1 exit fi @@ -186,5 +242,7 @@ test_aggr_task test_aggr_addr test_type_filter test_lock_filter +test_stack_filter +test_aggr_task_stack_filter exit ${err} diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 57e7a6a470c9..b4149b2db4c6 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -11,6 +11,7 @@ # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 . $(dirname $0)/lib/probe.sh +. $(dirname $0)/lib/probe_vfs_getname.sh libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 @@ -57,7 +58,17 @@ trace_libc_inet_pton_backtrace() { perf_data=`mktemp -u /tmp/perf.data.XXX` perf_script=`mktemp -u /tmp/perf.script.XXX` + + # Check presence of libtraceevent support to run perf record + skip_no_probe_record_support "$event_name/$eventattr/" + [ $? -eq 2 ] && return 2 + perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + # check if perf data file got created in above step. + if [ ! -e $perf_data ]; then + printf "FAIL: perf record failed to create \"%s\" \n" "$perf_data" + return 1 + fi perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script exec 3<$perf_script diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh index 7f83b2715b9a..1341437e1bd9 100755 --- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -17,6 +17,9 @@ skip_if_no_perf_probe || exit 2 record_open_file() { echo "Recording open file:" + # Check presence of libtraceevent support to run perf record + skip_no_probe_record_support "probe:vfs_getname*" + [ $? -eq 2 ] && return 2 perf record -o ${perfdata} -e probe:vfs_getname\* touch $file } diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh index 6e79349e42be..22e9cb294b40 100755 --- a/tools/perf/tests/shell/stat_all_metrics.sh +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -11,7 +11,7 @@ for m in $(perf list --raw-dump metrics); do continue fi # Failed so try system wide. - result=$(perf stat -M "$m" -a true 2>&1) + result=$(perf stat -M "$m" -a sleep 0.01 2>&1) if [[ "$result" =~ "${m:0:50}" ]] then continue diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index 59195eb80052..1c49d8293003 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -30,14 +30,14 @@ test_user_branches() { # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL set -x - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL$" $TMPDIR/perf.script - grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET$" $TMPDIR/perf.script - grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET$" $TMPDIR/perf.script - grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND$" $TMPDIR/perf.script - grep -E -m1 "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND$" $TMPDIR/perf.script + grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$" $TMPDIR/perf.script + grep -E -m1 "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$" $TMPDIR/perf.script set +x # some branch types are still not being tested: @@ -57,7 +57,7 @@ test_filter() { # fail if we find any branch type that doesn't match any of the expected ones # also consider UNKNOWN branch types (-) - if grep -E -vm1 "^[^ ]*/($expect|-|( *))$" $TMPDIR/perf.script; then + if grep -E -vm1 "^[^ ]*/($expect|-|( *))/.*$" $TMPDIR/perf.script; then return 1 fi } diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index f5ed7b1af419..4ddb17cb83c5 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -620,6 +620,22 @@ test_event_trace() return 0 } +test_pipe() +{ + echo "--- Test with pipe mode ---" + # Check if it works with pipe + if ! perf_record_no_bpf -o- -e intel_pt//u uname | perf report -q -i- --itrace=i10000 ; then + echo "perf record + report failed with pipe mode" + return 1 + fi + if ! perf_record_no_bpf -o- -e intel_pt//u uname | perf inject -b > /dev/null ; then + echo "perf record + inject failed with pipe mode" + return 1 + fi + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -647,6 +663,7 @@ test_virtual_lbr || ret=$? ; count_result $ret ; ret=0 test_power_event || ret=$? ; count_result $ret ; ret=0 test_no_tnt || ret=$? ; count_result $ret ; ret=0 test_event_trace || ret=$? ; count_result $ret ; ret=0 +test_pipe || ret=$? ; count_result $ret ; ret=0 cleanup diff --git a/tools/perf/tests/symbols.c b/tools/perf/tests/symbols.c new file mode 100644 index 000000000000..057b16df6416 --- /dev/null +++ b/tools/perf/tests/symbols.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <linux/string.h> +#include <sys/mman.h> +#include <limits.h> +#include "debug.h" +#include "dso.h" +#include "machine.h" +#include "thread.h" +#include "symbol.h" +#include "map.h" +#include "util.h" +#include "tests.h" + +struct test_info { + struct machine *machine; + struct thread *thread; +}; + +static int init_test_info(struct test_info *ti) +{ + ti->machine = machine__new_host(); + if (!ti->machine) { + pr_debug("machine__new_host() failed!\n"); + return TEST_FAIL; + } + + /* Create a dummy thread */ + ti->thread = machine__findnew_thread(ti->machine, 100, 100); + if (!ti->thread) { + pr_debug("machine__findnew_thread() failed!\n"); + return TEST_FAIL; + } + + return TEST_OK; +} + +static void exit_test_info(struct test_info *ti) +{ + thread__put(ti->thread); + machine__delete(ti->machine); +} + +static void get_test_dso_filename(char *filename, size_t max_sz) +{ + if (dso_to_test) + strlcpy(filename, dso_to_test, max_sz); + else + perf_exe(filename, max_sz); +} + +static int create_map(struct test_info *ti, char *filename, struct map **map_p) +{ + /* Create a dummy map at 0x100000 */ + *map_p = map__new(ti->machine, 0x100000, 0xffffffff, 0, NULL, + PROT_EXEC, 0, NULL, filename, ti->thread); + if (!*map_p) { + pr_debug("Failed to create map!"); + return TEST_FAIL; + } + + return TEST_OK; +} + +static int test_dso(struct dso *dso) +{ + struct symbol *last_sym = NULL; + struct rb_node *nd; + int ret = TEST_OK; + + /* dso__fprintf() prints all the symbols */ + if (verbose > 1) + dso__fprintf(dso, stderr); + + for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) { + struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + + if (sym->type != STT_FUNC && sym->type != STT_GNU_IFUNC) + continue; + + /* Check for overlapping function symbols */ + if (last_sym && sym->start < last_sym->end) { + pr_debug("Overlapping symbols:\n"); + symbol__fprintf(last_sym, stderr); + symbol__fprintf(sym, stderr); + ret = TEST_FAIL; + } + /* Check for zero-length function symbol */ + if (sym->start == sym->end) { + pr_debug("Zero-length symbol:\n"); + symbol__fprintf(sym, stderr); + ret = TEST_FAIL; + } + last_sym = sym; + } + + return ret; +} + +static int test_file(struct test_info *ti, char *filename) +{ + struct map *map = NULL; + int ret, nr; + + pr_debug("Testing %s\n", filename); + + ret = create_map(ti, filename, &map); + if (ret != TEST_OK) + return ret; + + nr = dso__load(map->dso, map); + if (nr < 0) { + pr_debug("dso__load() failed!\n"); + ret = TEST_FAIL; + goto out_put; + } + + if (nr == 0) { + pr_debug("DSO has no symbols!\n"); + ret = TEST_SKIP; + goto out_put; + } + + ret = test_dso(map->dso); +out_put: + map__put(map); + + return ret; +} + +static int test__symbols(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + char filename[PATH_MAX]; + struct test_info ti; + int ret; + + ret = init_test_info(&ti); + if (ret != TEST_OK) + return ret; + + get_test_dso_filename(filename, sizeof(filename)); + + ret = test_file(&ti, filename); + + exit_test_info(&ti); + + return ret; +} + +DEFINE_SUITE("Symbols", symbols); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index fb4b5ad4dd0f..9a0f3904e53d 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -148,6 +148,7 @@ DECLARE_SUITE(perf_time_to_tsc); DECLARE_SUITE(dlfilter); DECLARE_SUITE(sigtrap); DECLARE_SUITE(event_groups); +DECLARE_SUITE(symbols); /* * PowerPC and S390 do not support creation of instruction breakpoints using the @@ -208,4 +209,6 @@ DECLARE_WORKLOAD(sqrtloop); DECLARE_WORKLOAD(brstack); DECLARE_WORKLOAD(datasym); +extern const char *dso_to_test; + #endif /* TESTS_H */ diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c index 29193b75717e..af05269c2eb8 100644 --- a/tools/perf/tests/workloads/thloop.c +++ b/tools/perf/tests/workloads/thloop.c @@ -20,7 +20,7 @@ static void sighandler(int sig __maybe_unused) noinline void test_loop(void) { while (!done) - count++; + __atomic_fetch_add(&count, 1, __ATOMIC_RELAXED); } static void *thfunc(void *arg) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 79b9498886a2..918b501f9bd8 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -154,7 +154,10 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o -perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o + +ifeq ($(CONFIG_LIBTRACEEVENT),y) + perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o +endif ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 091987dd3966..40dcedfd75cd 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -68,7 +68,11 @@ static u64 arm_spe_calc_ip(int index, u64 payload) /* Clean highest byte */ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); } else { - pr_err("unsupported address packet index: 0x%x\n", index); + static u32 seen_idx = 0; + if (!(seen_idx & BIT(index))) { + seen_idx |= BIT(index); + pr_warning("ignoring unsupported address packet index: 0x%x\n", index); + } } return payload; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 2f311189c6e8..fed4741f372e 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -422,16 +422,18 @@ static int arm_spe_pkt_desc_addr(const struct arm_spe_pkt *packet, int ch, pat; u64 payload = packet->payload; int err = 0; + static const char *idx_name[] = {"PC", "TGT", "VA", "PA", "PBT"}; switch (idx) { case SPE_ADDR_PKT_HDR_INDEX_INS: case SPE_ADDR_PKT_HDR_INDEX_BRANCH: + case SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH: ns = !!SPE_ADDR_PKT_GET_NS(payload); el = SPE_ADDR_PKT_GET_EL(payload); payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); arm_spe_pkt_out_string(&err, &buf, &buf_len, "%s 0x%llx el%d ns=%d", - (idx == 1) ? "TGT" : "PC", payload, el, ns); + idx_name[idx], payload, el, ns); break; case SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT: arm_spe_pkt_out_string(&err, &buf, &buf_len, diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index 9b970e7bf1e2..f75ed3a8a050 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -65,6 +65,7 @@ struct arm_spe_pkt { #define SPE_ADDR_PKT_HDR_INDEX_BRANCH 0x1 #define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT 0x2 #define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS 0x3 +#define SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH 0x4 /* Address packet payload */ #define SPE_ADDR_PKT_ADDR_BYTE7_SHIFT 56 diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index c2e323cd7d49..498ff7f24463 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1133,6 +1133,9 @@ int auxtrace_queue_data(struct perf_session *session, bool samples, bool events) if (auxtrace__dont_decode(session)) return 0; + if (perf_data__is_pipe(session->data)) + return 0; + if (!session->auxtrace || !session->auxtrace->queue_data) return -EINVAL; @@ -1391,6 +1394,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->calls = true; } else { synth_opts->instructions = true; + synth_opts->cycles = true; synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; } @@ -1479,7 +1483,11 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, for (p = str; *p;) { switch (*p++) { case 'i': - synth_opts->instructions = true; + case 'y': + if (p[-1] == 'y') + synth_opts->cycles = true; + else + synth_opts->instructions = true; while (*p == ' ' || *p == ',') p += 1; if (isdigit(*p)) { @@ -1638,7 +1646,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, } } out: - if (synth_opts->instructions) { + if (synth_opts->instructions || synth_opts->cycles) { if (!period_type_set) synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 2cf63d377831..29eb82dff574 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -71,6 +71,9 @@ enum itrace_period_type { * @inject: indicates the event (not just the sample) must be fully synthesized * because 'perf inject' will write it out * @instructions: whether to synthesize 'instructions' events + * @cycles: whether to synthesize 'cycles' events + * (not fully accurate, since CYC packets are only emitted + * together with other events, such as branches) * @branches: whether to synthesize 'branches' events * (branch misses only for Arm SPE) * @transactions: whether to synthesize events for transactions @@ -119,6 +122,7 @@ struct itrace_synth_opts { bool default_no_sample; bool inject; bool instructions; + bool cycles; bool branches; bool transactions; bool ptwrites; @@ -643,6 +647,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, #define ITRACE_HELP \ " i[period]: synthesize instructions events\n" \ +" y[period]: synthesize cycles events (same period as i)\n" \ " b: synthesize branches events (branch misses for Arm SPE)\n" \ " c: synthesize branches events (calls only)\n" \ " r: synthesize branches events (returns only)\n" \ @@ -674,7 +679,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, " A: approximate IPC\n" \ " Z: prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \ " PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \ -" concatenate multiple options. Default is ibxwpe or cewp\n" +" concatenate multiple options. Default is iybxwpe or cewp\n" static inline void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts, diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 0236334fd69b..fadcacb9d501 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -34,13 +34,15 @@ int lock_contention_prepare(struct lock_contention *con) bpf_map__set_max_entries(skel->maps.lock_stat, con->map_nr_entries); bpf_map__set_max_entries(skel->maps.tstamp, con->map_nr_entries); - if (con->aggr_mode == LOCK_AGGR_TASK) { + if (con->aggr_mode == LOCK_AGGR_TASK) bpf_map__set_max_entries(skel->maps.task_data, con->map_nr_entries); - bpf_map__set_max_entries(skel->maps.stacks, 1); - } else { + else bpf_map__set_max_entries(skel->maps.task_data, 1); + + if (con->save_callstack) bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries); - } + else + bpf_map__set_max_entries(skel->maps.stacks, 1); if (target__has_cpu(target)) ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus); @@ -146,6 +148,8 @@ int lock_contention_prepare(struct lock_contention *con) /* these don't work well if in the rodata section */ skel->bss->stack_skip = con->stack_skip; skel->bss->aggr_mode = con->aggr_mode; + skel->bss->needs_callstack = con->save_callstack; + skel->bss->lock_owner = con->owner; lock_contention_bpf__attach(skel); return 0; @@ -163,9 +167,70 @@ int lock_contention_stop(void) return 0; } +static const char *lock_contention_get_name(struct lock_contention *con, + struct contention_key *key, + u64 *stack_trace) +{ + int idx = 0; + u64 addr; + const char *name = ""; + static char name_buf[KSYM_NAME_LEN]; + struct symbol *sym; + struct map *kmap; + struct machine *machine = con->machine; + + if (con->aggr_mode == LOCK_AGGR_TASK) { + struct contention_task_data task; + int pid = key->pid; + int task_fd = bpf_map__fd(skel->maps.task_data); + + /* do not update idle comm which contains CPU number */ + if (pid) { + struct thread *t = __machine__findnew_thread(machine, /*pid=*/-1, pid); + + if (t == NULL) + return name; + if (!bpf_map_lookup_elem(task_fd, &pid, &task) && + thread__set_comm(t, task.comm, /*timestamp=*/0)) + name = task.comm; + } + return name; + } + + if (con->aggr_mode == LOCK_AGGR_ADDR) { + sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap); + if (sym) + name = sym->name; + return name; + } + + /* LOCK_AGGR_CALLER: skip lock internal functions */ + while (machine__is_lock_function(machine, stack_trace[idx]) && + idx < con->max_stack - 1) + idx++; + + addr = stack_trace[idx]; + sym = machine__find_kernel_symbol(machine, addr, &kmap); + + if (sym) { + unsigned long offset; + + offset = kmap->map_ip(kmap, addr) - sym->start; + + if (offset == 0) + return sym->name; + + snprintf(name_buf, sizeof(name_buf), "%s+%#lx", sym->name, offset); + } else { + snprintf(name_buf, sizeof(name_buf), "%#lx", (unsigned long)addr); + } + + return name_buf; +} + int lock_contention_read(struct lock_contention *con) { - int fd, stack, task_fd, err = 0; + int fd, stack, err = 0; struct contention_key *prev_key, key; struct contention_data data = {}; struct lock_stat *st = NULL; @@ -175,7 +240,6 @@ int lock_contention_read(struct lock_contention *con) fd = bpf_map__fd(skel->maps.lock_stat); stack = bpf_map__fd(skel->maps.stacks); - task_fd = bpf_map__fd(skel->maps.task_data); con->lost = skel->bss->lost; @@ -195,98 +259,75 @@ int lock_contention_read(struct lock_contention *con) prev_key = NULL; while (!bpf_map_get_next_key(fd, prev_key, &key)) { - struct map *kmap; - struct symbol *sym; - int idx = 0; - s32 stack_id; + s64 ls_key; + const char *name; /* to handle errors in the loop body */ err = -1; bpf_map_lookup_elem(fd, &key, &data); - st = zalloc(sizeof(*st)); - if (st == NULL) - break; - - st->nr_contended = data.count; - st->wait_time_total = data.total_time; - st->wait_time_max = data.max_time; - st->wait_time_min = data.min_time; - - if (data.count) - st->avg_wait_time = data.total_time / data.count; - - st->flags = data.flags; - st->addr = key.aggr_key; + if (con->save_callstack) { + bpf_map_lookup_elem(stack, &key.stack_id, stack_trace); - if (con->aggr_mode == LOCK_AGGR_TASK) { - struct contention_task_data task; - struct thread *t; - int pid = key.aggr_key; + if (!match_callstack_filter(machine, stack_trace)) + goto next; + } - /* do not update idle comm which contains CPU number */ - if (st->addr) { - bpf_map_lookup_elem(task_fd, &pid, &task); - t = __machine__findnew_thread(machine, /*pid=*/-1, pid); - thread__set_comm(t, task.comm, /*timestamp=*/0); - } + switch (con->aggr_mode) { + case LOCK_AGGR_CALLER: + ls_key = key.stack_id; + break; + case LOCK_AGGR_TASK: + ls_key = key.pid; + break; + case LOCK_AGGR_ADDR: + ls_key = key.lock_addr; + break; + default: goto next; } - if (con->aggr_mode == LOCK_AGGR_ADDR) { - sym = machine__find_kernel_symbol(machine, st->addr, &kmap); - if (sym) - st->name = strdup(sym->name); + st = lock_stat_find(ls_key); + if (st != NULL) { + st->wait_time_total += data.total_time; + if (st->wait_time_max < data.max_time) + st->wait_time_max = data.max_time; + if (st->wait_time_min > data.min_time) + st->wait_time_min = data.min_time; + + st->nr_contended += data.count; + if (st->nr_contended) + st->avg_wait_time = st->wait_time_total / st->nr_contended; goto next; } - stack_id = key.aggr_key; - bpf_map_lookup_elem(stack, &stack_id, stack_trace); - - /* skip lock internal functions */ - while (machine__is_lock_function(machine, stack_trace[idx]) && - idx < con->max_stack - 1) - idx++; - - st->addr = stack_trace[idx]; - sym = machine__find_kernel_symbol(machine, st->addr, &kmap); - - if (sym) { - unsigned long offset; - int ret = 0; - - offset = kmap->map_ip(kmap, st->addr) - sym->start; + name = lock_contention_get_name(con, &key, stack_trace); + st = lock_stat_findnew(ls_key, name, data.flags); + if (st == NULL) + break; - if (offset) - ret = asprintf(&st->name, "%s+%#lx", sym->name, offset); - else - st->name = strdup(sym->name); + st->nr_contended = data.count; + st->wait_time_total = data.total_time; + st->wait_time_max = data.max_time; + st->wait_time_min = data.min_time; - if (ret < 0 || st->name == NULL) - break; - } else if (asprintf(&st->name, "%#lx", (unsigned long)st->addr) < 0) { - break; - } + if (data.count) + st->avg_wait_time = data.total_time / data.count; - if (verbose > 0) { + if (con->save_callstack) { st->callstack = memdup(stack_trace, stack_size); if (st->callstack == NULL) break; } + next: - hlist_add_head(&st->hash_entry, con->result); prev_key = &key; - /* we're fine now, reset the values */ - st = NULL; + /* we're fine now, reset the error */ err = 0; } free(stack_trace); - if (st) { - free(st->name); - free(st); - } return err; } diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index ad0ca5d50557..e6007eaeda1a 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -10,6 +10,14 @@ /* default buffer size */ #define MAX_ENTRIES 10240 +/* lock contention flags from include/trace/events/lock.h */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) + struct tstamp_data { __u64 timestamp; __u64 lock; @@ -76,13 +84,23 @@ struct { __uint(max_entries, 1); } addr_filter SEC(".maps"); +struct rw_semaphore___old { + struct task_struct *owner; +} __attribute__((preserve_access_index)); + +struct rw_semaphore___new { + atomic_long_t owner; +} __attribute__((preserve_access_index)); + /* control flags */ int enabled; int has_cpu; int has_task; int has_type; int has_addr; +int needs_callstack; int stack_skip; +int lock_owner; /* determine the key of lock stat */ int aggr_mode; @@ -131,17 +149,59 @@ static inline int can_record(u64 *ctx) return 1; } -static inline void update_task_data(__u32 pid) +static inline int update_task_data(struct task_struct *task) { struct contention_task_data *p; + int pid, err; + + err = bpf_core_read(&pid, sizeof(pid), &task->pid); + if (err) + return -1; p = bpf_map_lookup_elem(&task_data, &pid); if (p == NULL) { - struct contention_task_data data; + struct contention_task_data data = {}; - bpf_get_current_comm(data.comm, sizeof(data.comm)); + BPF_CORE_READ_STR_INTO(&data.comm, task, comm); bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST); } + + return 0; +} + +#ifndef __has_builtin +# define __has_builtin(x) 0 +#endif + +static inline struct task_struct *get_lock_owner(__u64 lock, __u32 flags) +{ + struct task_struct *task; + __u64 owner = 0; + + if (flags & LCB_F_MUTEX) { + struct mutex *mutex = (void *)lock; + owner = BPF_CORE_READ(mutex, owner.counter); + } else if (flags == LCB_F_READ || flags == LCB_F_WRITE) { +#if __has_builtin(bpf_core_type_matches) + if (bpf_core_type_matches(struct rw_semaphore___old)) { + struct rw_semaphore___old *rwsem = (void *)lock; + owner = (unsigned long)BPF_CORE_READ(rwsem, owner); + } else if (bpf_core_type_matches(struct rw_semaphore___new)) { + struct rw_semaphore___new *rwsem = (void *)lock; + owner = BPF_CORE_READ(rwsem, owner.counter); + } +#else + /* assume new struct */ + struct rw_semaphore *rwsem = (void *)lock; + owner = BPF_CORE_READ(rwsem, owner.counter); +#endif + } + + if (!owner) + return NULL; + + task = (void *)(owner & ~7UL); + return task; } SEC("tp_btf/contention_begin") @@ -173,11 +233,31 @@ int contention_begin(u64 *ctx) pelem->lock = (__u64)ctx[0]; pelem->flags = (__u32)ctx[1]; - if (aggr_mode == LOCK_AGGR_CALLER) { + if (needs_callstack) { pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip); if (pelem->stack_id < 0) lost++; + } else if (aggr_mode == LOCK_AGGR_TASK) { + struct task_struct *task; + + if (lock_owner) { + task = get_lock_owner(pelem->lock, pelem->flags); + + /* The flags is not used anymore. Pass the owner pid. */ + if (task) + pelem->flags = BPF_CORE_READ(task, pid); + else + pelem->flags = -1U; + + } else { + task = bpf_get_current_task_btf(); + } + + if (task) { + if (update_task_data(task) < 0 && lock_owner) + pelem->flags = -1U; + } } return 0; @@ -188,7 +268,7 @@ int contention_end(u64 *ctx) { __u32 pid; struct tstamp_data *pelem; - struct contention_key key; + struct contention_key key = {}; struct contention_data *data; __u64 duration; @@ -204,14 +284,20 @@ int contention_end(u64 *ctx) switch (aggr_mode) { case LOCK_AGGR_CALLER: - key.aggr_key = pelem->stack_id; + key.stack_id = pelem->stack_id; break; case LOCK_AGGR_TASK: - key.aggr_key = pid; - update_task_data(pid); + if (lock_owner) + key.pid = pelem->flags; + else + key.pid = pid; + if (needs_callstack) + key.stack_id = pelem->stack_id; break; case LOCK_AGGR_ADDR: - key.aggr_key = pelem->lock; + key.lock_addr = pelem->lock; + if (needs_callstack) + key.stack_id = pelem->stack_id; break; default: /* should not happen */ diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index ce71cf1a7e1e..3d35fd4407ac 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -4,7 +4,9 @@ #define UTIL_BPF_SKEL_LOCK_DATA_H struct contention_key { - u64 aggr_key; /* can be stack_id, pid or lock addr */ + u32 stack_id; + u32 pid; + u64 lock_addr; }; #define TASK_COMM_LEN 16 diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index 6d38238481d3..378f16a24751 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -212,3 +212,18 @@ int branch_type_str(struct branch_type_stat *st, char *bf, int size) return printed; } + +const char *branch_spec_desc(int spec) +{ + const char *branch_spec_outcomes[PERF_BR_SPEC_MAX] = { + "N/A", + "SPEC_WRONG_PATH", + "NON_SPEC_CORRECT_PATH", + "SPEC_CORRECT_PATH", + }; + + if (spec >= 0 && spec < PERF_BR_SPEC_MAX) + return branch_spec_outcomes[spec]; + + return NULL; +} diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index 3ed792db1125..e41bfffe2217 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -89,4 +89,6 @@ const char *get_branch_type(struct branch_entry *e); void branch_type_stat_display(FILE *fp, struct branch_type_stat *st); int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize); +const char *branch_spec_desc(int spec); + #endif /* _PERF_BRANCH_H */ diff --git a/tools/perf/util/cacheline.h b/tools/perf/util/cacheline.h index dec8c0fb1f4a..fe6d5b60a031 100644 --- a/tools/perf/util/cacheline.h +++ b/tools/perf/util/cacheline.h @@ -6,16 +6,31 @@ int __pure cacheline_size(void); -static inline u64 cl_address(u64 address) + +/* + * Some architectures have 'Adjacent Cacheline Prefetch' feature, + * which performs like the cacheline size being doubled. + */ +static inline u64 cl_address(u64 address, bool double_cl) { + u64 size = cacheline_size(); + + if (double_cl) + size *= 2; + /* return the cacheline of the address */ - return (address & ~(cacheline_size() - 1)); + return (address & ~(size - 1)); } -static inline u64 cl_offset(u64 address) +static inline u64 cl_offset(u64 address, bool double_cl) { - /* return the cacheline of the address */ - return (address & (cacheline_size() - 1)); + u64 size = cacheline_size(); + + if (double_cl) + size *= 2; + + /* return the offset inside cacheline */ + return (address & (size - 1)); } #endif // PERF_CACHELINE_H diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index cd978c240e0d..bfb13306d82c 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -481,7 +481,6 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, nr_cgroups++; if (metric_events) { - perf_stat__collect_metric_expr(tmp_list); if (metricgroup__copy_metric_events(tmp_list, cgrp, metric_events, &orig_metric_events) < 0) diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 1a3ff6449158..e08797c3cdbc 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -422,8 +422,6 @@ void numa_topology__delete(struct numa_topology *tp) static int load_hybrid_node(struct hybrid_topology_node *node, struct perf_pmu *pmu) { - const char *sysfs; - char path[PATH_MAX]; char *buf = NULL, *p; FILE *fp; size_t len = 0; @@ -432,12 +430,7 @@ static int load_hybrid_node(struct hybrid_topology_node *node, if (!node->pmu_name) return -1; - sysfs = sysfs__mountpoint(); - if (!sysfs) - goto err; - - snprintf(path, PATH_MAX, CPUS_TEMPLATE_CPU, sysfs, pmu->name); - fp = fopen(path, "r"); + fp = perf_pmu__open_file(pmu, "cpus"); if (!fp) goto err; diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c index 597542410854..5f48b756c4cf 100644 --- a/tools/perf/util/cs-etm-base.c +++ b/tools/perf/util/cs-etm-base.c @@ -36,7 +36,22 @@ static const char * const cs_etmv4_priv_fmts[] = { [CS_ETMV4_TRCIDR2] = " TRCIDR2 %llx\n", [CS_ETMV4_TRCIDR8] = " TRCIDR8 %llx\n", [CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", - [CS_ETE_TRCDEVARCH] = " TRCDEVARCH %llx\n" + [CS_ETMV4_TS_SOURCE] = " TS_SOURCE %lld\n", +}; + +static const char * const cs_ete_priv_fmts[] = { + [CS_ETM_MAGIC] = " Magic number %llx\n", + [CS_ETM_CPU] = " CPU %lld\n", + [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", + [CS_ETE_TRCCONFIGR] = " TRCCONFIGR %llx\n", + [CS_ETE_TRCTRACEIDR] = " TRCTRACEIDR %llx\n", + [CS_ETE_TRCIDR0] = " TRCIDR0 %llx\n", + [CS_ETE_TRCIDR1] = " TRCIDR1 %llx\n", + [CS_ETE_TRCIDR2] = " TRCIDR2 %llx\n", + [CS_ETE_TRCIDR8] = " TRCIDR8 %llx\n", + [CS_ETE_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", + [CS_ETE_TRCDEVARCH] = " TRCDEVARCH %llx\n", + [CS_ETE_TS_SOURCE] = " TS_SOURCE %lld\n", }; static const char * const param_unk_fmt = @@ -96,19 +111,22 @@ static int cs_etm__print_cpu_metadata_v1(u64 *val, int *offset) else fprintf(stdout, cs_etm_priv_fmts[j], val[i]); } - } else if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) { - /* - * ETE and ETMv4 can be printed in the same block because the number of parameters - * is saved and they share the list of parameter names. ETE is also only supported - * in V1 files. - */ + } else if (magic == __perf_cs_etmv4_magic) { for (j = 0; j < total_params; j++, i++) { /* if newer record - could be excess params */ - if (j >= CS_ETE_PRIV_MAX) + if (j >= CS_ETMV4_PRIV_MAX) fprintf(stdout, param_unk_fmt, j, val[i]); else fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); } + } else if (magic == __perf_cs_ete_magic) { + for (j = 0; j < total_params; j++, i++) { + /* if newer record - could be excess params */ + if (j >= CS_ETE_PRIV_MAX) + fprintf(stdout, param_unk_fmt, j, val[i]); + else + fprintf(stdout, cs_ete_priv_fmts[j], val[i]); + } } else { /* failure - note bad magic value and error out */ fprintf(stdout, magic_unk_fmt, magic); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 31fa3b45134a..d0e521dfcf35 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -30,6 +30,15 @@ #endif #endif +/* + * Assume a maximum of 0.1ns elapsed per instruction. This would be the + * case with a theoretical 10GHz core executing 1 instruction per cycle. + * Used to estimate the sample time for synthesized instructions because + * Coresight only emits a timestamp for a range of instructions rather + * than per instruction. + */ +const u32 INSTR_PER_NS = 10; + struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); @@ -112,6 +121,20 @@ int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue, return 1; } +/* + * Calculate the number of nanoseconds elapsed. + * + * instr_count is updated in place with the remainder of the instructions + * which didn't make up a whole nanosecond. + */ +static u32 cs_etm_decoder__dec_instr_count_to_ns(u32 *instr_count) +{ + const u32 instr_copy = *instr_count; + + *instr_count %= INSTR_PER_NS; + return instr_copy / INSTR_PER_NS; +} + static int cs_etm_decoder__gen_etmv3_config(struct cs_etm_trace_params *params, ocsd_etmv3_cfg *config) { @@ -260,15 +283,17 @@ cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq, struct cs_etm_packet_queue *packet_queue, const uint8_t trace_chan_id) { + u64 estimated_ts; + /* No timestamp packet has been received, nothing to do */ - if (!packet_queue->cs_timestamp) + if (!packet_queue->next_cs_timestamp) return OCSD_RESP_CONT; - packet_queue->cs_timestamp = packet_queue->next_cs_timestamp; + estimated_ts = packet_queue->cs_timestamp + + cs_etm_decoder__dec_instr_count_to_ns(&packet_queue->instr_count); - /* Estimate the timestamp for the next range packet */ - packet_queue->next_cs_timestamp += packet_queue->instr_count; - packet_queue->instr_count = 0; + /* Estimated TS can never be higher than the next real one in the trace */ + packet_queue->cs_timestamp = min(packet_queue->next_cs_timestamp, estimated_ts); /* Tell the front end which traceid_queue needs attention */ cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id); @@ -283,6 +308,8 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, const ocsd_trc_index_t indx) { struct cs_etm_packet_queue *packet_queue; + u64 converted_timestamp; + u64 estimated_first_ts; /* First get the packet queue for this traceID */ packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id); @@ -290,17 +317,28 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, return OCSD_RESP_FATAL_SYS_ERR; /* + * Coresight timestamps are raw timer values which need to be scaled to ns. Assume + * 0 is a bad value so don't try to convert it. + */ + converted_timestamp = elem->timestamp ? + cs_etm__convert_sample_time(etmq, elem->timestamp) : 0; + + /* * We've seen a timestamp packet before - simply record the new value. * Function do_soft_timestamp() will report the value to the front end, * hence asking the decoder to keep decoding rather than stopping. */ - if (packet_queue->cs_timestamp) { - packet_queue->next_cs_timestamp = elem->timestamp; + if (packet_queue->next_cs_timestamp) { + /* + * What was next is now where new ranges start from, overwriting + * any previous estimate in cs_timestamp + */ + packet_queue->cs_timestamp = packet_queue->next_cs_timestamp; + packet_queue->next_cs_timestamp = converted_timestamp; return OCSD_RESP_CONT; } - - if (!elem->timestamp) { + if (!converted_timestamp) { /* * Zero timestamps can be seen due to misconfiguration or hardware bugs. * Warn once, and don't try to subtract instr_count as it would result in an @@ -312,7 +350,7 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, ". Decoding may be improved by prepending 'Z' to your current --itrace arguments.\n", indx); - } else if (packet_queue->instr_count > elem->timestamp) { + } else if (packet_queue->instr_count / INSTR_PER_NS > converted_timestamp) { /* * Sanity check that the elem->timestamp - packet_queue->instr_count would not * result in an underflow. Warn and clamp at 0 if it would. @@ -325,11 +363,14 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, * or a discontinuity. Since timestamps packets are generated *after* * range packets have been generated, we need to estimate the time at * which instructions started by subtracting the number of instructions - * executed to the timestamp. + * executed to the timestamp. Don't estimate earlier than the last used + * timestamp though. */ - packet_queue->cs_timestamp = elem->timestamp - packet_queue->instr_count; + estimated_first_ts = converted_timestamp - + (packet_queue->instr_count / INSTR_PER_NS); + packet_queue->cs_timestamp = max(packet_queue->cs_timestamp, estimated_first_ts); } - packet_queue->next_cs_timestamp = elem->timestamp; + packet_queue->next_cs_timestamp = converted_timestamp; packet_queue->instr_count = 0; /* Tell the front end which traceid_queue needs attention */ @@ -342,7 +383,6 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, static void cs_etm_decoder__reset_timestamp(struct cs_etm_packet_queue *packet_queue) { - packet_queue->cs_timestamp = 0; packet_queue->next_cs_timestamp = 0; packet_queue->instr_count = 0; } @@ -604,6 +644,9 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( case OCSD_GEN_TRC_ELEM_CUSTOM: case OCSD_GEN_TRC_ELEM_SYNC_MARKER: case OCSD_GEN_TRC_ELEM_MEMTRANS: +#if (OCSD_VER_NUM >= 0x010400) + case OCSD_GEN_TRC_ELEM_INSTRUMENTATION: +#endif default: break; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 33303d03c2fa..f65bac5ddbdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -35,6 +35,7 @@ #include "tool.h" #include "thread.h" #include "thread-stack.h" +#include "tsc.h" #include <tools/libc_compat.h> #include "util/synthetic-events.h" @@ -46,10 +47,12 @@ struct cs_etm_auxtrace { struct perf_session *session; struct machine *machine; struct thread *unknown_thread; + struct perf_tsc_conversion tc; u8 timeless_decoding; u8 snapshot_mode; u8 data_queued; + u8 has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */ int num_cpu; u64 latest_kernel_timestamp; @@ -464,12 +467,12 @@ static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params, u64 **metadata = etm->metadata; t_params[idx].protocol = CS_ETM_PROTO_ETE; - t_params[idx].ete.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0]; - t_params[idx].ete.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1]; - t_params[idx].ete.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2]; - t_params[idx].ete.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8]; - t_params[idx].ete.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR]; - t_params[idx].ete.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR]; + t_params[idx].ete.reg_idr0 = metadata[idx][CS_ETE_TRCIDR0]; + t_params[idx].ete.reg_idr1 = metadata[idx][CS_ETE_TRCIDR1]; + t_params[idx].ete.reg_idr2 = metadata[idx][CS_ETE_TRCIDR2]; + t_params[idx].ete.reg_idr8 = metadata[idx][CS_ETE_TRCIDR8]; + t_params[idx].ete.reg_configr = metadata[idx][CS_ETE_TRCCONFIGR]; + t_params[idx].ete.reg_traceidr = metadata[idx][CS_ETE_TRCTRACEIDR]; t_params[idx].ete.reg_devarch = metadata[idx][CS_ETE_TRCDEVARCH]; } @@ -1161,6 +1164,30 @@ static void cs_etm__copy_insn(struct cs_etm_queue *etmq, sample->insn_len, (void *)sample->insn); } +u64 cs_etm__convert_sample_time(struct cs_etm_queue *etmq, u64 cs_timestamp) +{ + struct cs_etm_auxtrace *etm = etmq->etm; + + if (etm->has_virtual_ts) + return tsc_to_perf_time(cs_timestamp, &etm->tc); + else + return cs_timestamp; +} + +static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) +{ + struct cs_etm_auxtrace *etm = etmq->etm; + struct cs_etm_packet_queue *packet_queue = &tidq->packet_queue; + + if (etm->timeless_decoding) + return 0; + else if (etm->has_virtual_ts) + return packet_queue->cs_timestamp; + else + return etm->latest_kernel_timestamp; +} + static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 addr, u64 period) @@ -1174,8 +1201,9 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, event->sample.header.misc = cs_etm__cpu_mode(etmq, addr); event->sample.header.size = sizeof(struct perf_event_header); - if (!etm->timeless_decoding) - sample.time = etm->latest_kernel_timestamp; + /* Set time field based on etm auxtrace config. */ + sample.time = cs_etm__resolve_sample_time(etmq, tidq); + sample.ip = addr; sample.pid = tidq->pid; sample.tid = tidq->tid; @@ -1232,8 +1260,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, event->sample.header.misc = cs_etm__cpu_mode(etmq, ip); event->sample.header.size = sizeof(struct perf_event_header); - if (!etm->timeless_decoding) - sample.time = etm->latest_kernel_timestamp; + /* Set time field based on etm auxtrace config. */ + sample.time = cs_etm__resolve_sample_time(etmq, tidq); + sample.ip = ip; sample.pid = tidq->pid; sample.tid = tidq->tid; @@ -2746,12 +2775,42 @@ static int cs_etm__queue_aux_records(struct perf_session *session) return 0; } +#define HAS_PARAM(j, type, param) (metadata[(j)][CS_ETM_NR_TRC_PARAMS] <= \ + (CS_##type##_##param - CS_ETM_COMMON_BLK_MAX_V1)) + +/* + * Loop through the ETMs and complain if we find at least one where ts_source != 1 (virtual + * timestamps). + */ +static bool cs_etm__has_virtual_ts(u64 **metadata, int num_cpu) +{ + int j; + + for (j = 0; j < num_cpu; j++) { + switch (metadata[j][CS_ETM_MAGIC]) { + case __perf_cs_etmv4_magic: + if (HAS_PARAM(j, ETMV4, TS_SOURCE) || metadata[j][CS_ETMV4_TS_SOURCE] != 1) + return false; + break; + case __perf_cs_ete_magic: + if (HAS_PARAM(j, ETE, TS_SOURCE) || metadata[j][CS_ETE_TS_SOURCE] != 1) + return false; + break; + default: + /* Unknown / unsupported magic number. */ + return false; + } + } + return true; +} + int cs_etm__process_auxtrace_info_full(union perf_event *event, struct perf_session *session) { struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; struct int_node *inode; + struct perf_record_time_conv *tc = &session->time_conv; int event_header_size = sizeof(struct perf_event_header); int total_size = auxtrace_info->header.size; int priv_size = 0; @@ -2886,6 +2945,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->auxtrace_type = auxtrace_info->type; etm->timeless_decoding = cs_etm__is_timeless_decoding(etm); + /* Use virtual timestamps if all ETMs report ts_source = 1 */ + etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu); + + if (!etm->has_virtual_ts) + ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n" + "The time field of the samples will not be set accurately.\n\n"); + etm->auxtrace.process_event = cs_etm__process_event; etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event; etm->auxtrace.flush_events = cs_etm__flush_events; @@ -2915,6 +2981,15 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, goto err_delete_thread; } + etm->tc.time_shift = tc->time_shift; + etm->tc.time_mult = tc->time_mult; + etm->tc.time_zero = tc->time_zero; + if (event_contains(*tc, time_cycles)) { + etm->tc.time_cycles = tc->time_cycles; + etm->tc.time_mask = tc->time_mask; + etm->tc.cap_user_time_zero = tc->cap_user_time_zero; + etm->tc.cap_user_time_short = tc->cap_user_time_short; + } err = cs_etm__synth_events(etm, session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 5da50d5dae6b..98a4f7113d2f 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -71,6 +71,7 @@ enum { CS_ETMV4_TRCIDR2, CS_ETMV4_TRCIDR8, CS_ETMV4_TRCAUTHSTATUS, + CS_ETMV4_TS_SOURCE, CS_ETMV4_PRIV_MAX, }; @@ -82,7 +83,17 @@ enum { * added in header V1 */ enum { - CS_ETE_TRCDEVARCH = CS_ETMV4_PRIV_MAX, + /* Dynamic, configurable parameters */ + CS_ETE_TRCCONFIGR = CS_ETM_COMMON_BLK_MAX_V1, + CS_ETE_TRCTRACEIDR, + /* RO, taken from sysFS */ + CS_ETE_TRCIDR0, + CS_ETE_TRCIDR1, + CS_ETE_TRCIDR2, + CS_ETE_TRCIDR8, + CS_ETE_TRCAUTHSTATUS, + CS_ETE_TRCDEVARCH, + CS_ETE_TS_SOURCE, CS_ETE_PRIV_MAX }; @@ -181,7 +192,7 @@ struct cs_etm_packet_queue { u32 head; u32 tail; u32 instr_count; - u64 cs_timestamp; + u64 cs_timestamp; /* Timestamp from trace data, converted to ns if possible */ u64 next_cs_timestamp; struct cs_etm_packet packet_buffer[CS_ETM_PACKET_MAX_BUFFER]; }; @@ -220,6 +231,7 @@ struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id); int cs_etm__process_auxtrace_info_full(union perf_event *event __maybe_unused, struct perf_session *session __maybe_unused); +u64 cs_etm__convert_sample_time(struct cs_etm_queue *etmq, u64 cs_timestamp); #else static inline int cs_etm__process_auxtrace_info_full(union perf_event *event __maybe_unused, diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index b842273458b8..2b732bccabad 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -322,10 +322,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, offset = tmp_val; len = offset >> 16; offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(flags)) offset += fmtf->offset + fmtf->size; -#endif } if (flags & TEP_FIELD_IS_ARRAY) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 190e818a0717..88378c4c5dd9 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -19,12 +19,19 @@ #include "debug.h" #include "print_binary.h" #include "target.h" +#include "trace-event.h" #include "ui/helpline.h" #include "ui/ui.h" #include "util/parse-sublevel-options.h" #include <linux/ctype.h> +#ifdef HAVE_LIBTRACEEVENT +#include <traceevent/event-parse.h> +#else +#define LIBTRACEEVENT_VERSION 0 +#endif + int verbose; int debug_peo_args; bool dump_trace = false, quiet = false; @@ -228,6 +235,14 @@ int perf_debug_option(const char *str) /* Allow only verbose value in range (0, 10), otherwise set 0. */ verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose; +#if LIBTRACEEVENT_VERSION >= MAKE_LIBTRACEEVENT_VERSION(1, 3, 0) + if (verbose == 1) + tep_set_loglevel(TEP_LOG_INFO); + else if (verbose == 2) + tep_set_loglevel(TEP_LOG_DEBUG); + else if (verbose >= 3) + tep_set_loglevel(TEP_LOG_ALL); +#endif return 0; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 999dd1700502..51e8ce6edddc 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -285,8 +285,6 @@ void evsel__init(struct evsel *evsel, evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; - evsel->metric_expr = NULL; - evsel->metric_name = NULL; evsel->metric_events = NULL; evsel->per_pkg_mask = NULL; evsel->collect_stat = false; @@ -2319,7 +2317,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value) * abort:1 //transaction abort * cycles:16 //cycle count to last branch * type:4 //branch type - * reserved:40 + * spec:2 //branch speculation info + * new_type:4 //additional branch type + * priv:3 //privilege level + * reserved:31 * } * } * @@ -2335,7 +2336,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value) new_val |= bitfield_swap(value, 3, 1); new_val |= bitfield_swap(value, 4, 16); new_val |= bitfield_swap(value, 20, 4); - new_val |= bitfield_swap(value, 24, 40); + new_val |= bitfield_swap(value, 24, 2); + new_val |= bitfield_swap(value, 26, 4); + new_val |= bitfield_swap(value, 30, 3); + new_val |= bitfield_swap(value, 33, 31); } else { new_val = bitfield_swap(value, 63, 1); new_val |= bitfield_swap(value, 62, 1); @@ -2343,7 +2347,10 @@ u64 evsel__bitfield_swap_branch_flags(u64 value) new_val |= bitfield_swap(value, 60, 1); new_val |= bitfield_swap(value, 44, 16); new_val |= bitfield_swap(value, 40, 4); - new_val |= bitfield_swap(value, 0, 40); + new_val |= bitfield_swap(value, 38, 2); + new_val |= bitfield_swap(value, 34, 4); + new_val |= bitfield_swap(value, 31, 3); + new_val |= bitfield_swap(value, 0, 31); } return new_val; @@ -2784,10 +2791,8 @@ void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(sample->raw_data + field->offset); offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif } return sample->raw_data + offset; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d572be41b960..24cb807ef6ce 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -105,8 +105,6 @@ struct evsel { * metric fields are similar, but needs more care as they can have * references to other metric (evsel). */ - const char * metric_expr; - const char * metric_name; struct evsel **metric_events; struct evsel *metric_leader; diff --git a/tools/perf/util/evswitch.h b/tools/perf/util/evswitch.h index fd30460b6218..8ffdbe526d98 100644 --- a/tools/perf/util/evswitch.h +++ b/tools/perf/util/evswitch.h @@ -22,9 +22,9 @@ bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel); #define OPTS_EVSWITCH(evswitch) \ OPT_STRING(0, "switch-on", &(evswitch)->on_name, \ - "event", "Consider events after the ocurrence of this event"), \ + "event", "Consider events after the occurrence of this event"), \ OPT_STRING(0, "switch-off", &(evswitch)->off_name, \ - "event", "Stop considering events after the ocurrence of this event"), \ + "event", "Stop considering events after the occurrence of this event"), \ OPT_BOOLEAN(0, "show-on-off-events", &(evswitch)->show_on_off_events, \ "Show the on/off switch events, used with --switch-on and --switch-off") diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 00dcde35e0d3..c1da20b868db 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -19,6 +19,7 @@ #include <linux/zalloc.h> #include <ctype.h> #include <math.h> +#include "pmu.h" #ifdef PARSER_DEBUG extern int expr_debug; @@ -448,6 +449,10 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx result = topology->core_cpus_lists; goto out; } + if (!strcmp("#slots", literal)) { + result = perf_pmu__cpu_slots_per_cycle(); + goto out; + } pr_err("Unrecognized literal '%s'", literal); out: diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 029271540fb0..eaa44b24c555 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -9,6 +9,7 @@ struct expr_scanner_ctx { char *user_requested_cpu_list; int runtime; bool system_wide; + bool is_test; }; struct expr_parse_ctx { diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index d47de5f270a8..4fbf353e78e7 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -87,9 +87,11 @@ static int literal(yyscan_t scanner, const struct expr_scanner_ctx *sctx) YYSTYPE *yylval = expr_get_lval(scanner); yylval->num = expr__get_literal(expr_get_text(scanner), sctx); - if (isnan(yylval->num)) - return EXPR_ERROR; - + if (isnan(yylval->num)) { + if (!sctx->is_test) + return EXPR_ERROR; + yylval->num = 1; + } return LITERAL; } %} diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 6d3921627e33..955c1b9dc6a4 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -5,6 +5,7 @@ */ #include <inttypes.h> +#include <linux/perf_event.h> #include <stdio.h> #include <stdbool.h> #include <errno.h> @@ -98,6 +99,10 @@ struct intel_pt { u64 instructions_sample_type; u64 instructions_id; + bool sample_cycles; + u64 cycles_sample_type; + u64 cycles_id; + bool sample_branches; u32 branches_filter; u64 branches_sample_type; @@ -214,6 +219,8 @@ struct intel_pt_queue { u64 ipc_cyc_cnt; u64 last_in_insn_cnt; u64 last_in_cyc_cnt; + u64 last_cy_insn_cnt; + u64 last_cy_cyc_cnt; u64 last_br_insn_cnt; u64 last_br_cyc_cnt; unsigned int cbr_seen; @@ -1319,7 +1326,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, if (pt->filts.cnt > 0) params.pgd_ip = intel_pt_pgd_ip; - if (pt->synth_opts.instructions) { + if (pt->synth_opts.instructions || pt->synth_opts.cycles) { if (pt->synth_opts.period) { switch (pt->synth_opts.period_type) { case PERF_ITRACE_PERIOD_INSTRUCTIONS: @@ -1830,6 +1837,33 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) pt->instructions_sample_type); } +static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + u64 period = 0; + + if (ptq->sample_ipc) + period = ptq->ipc_cyc_cnt - ptq->last_cy_cyc_cnt; + + if (!period || intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->cycles_id; + sample.stream_id = ptq->pt->cycles_id; + sample.period = period; + + sample.cyc_cnt = period; + sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_cy_insn_cnt; + ptq->last_cy_insn_cnt = ptq->ipc_insn_cnt; + ptq->last_cy_cyc_cnt = ptq->ipc_cyc_cnt; + + return intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type); +} + static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; @@ -2598,10 +2632,17 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) } } - if (pt->sample_instructions && (state->type & INTEL_PT_INSTRUCTION)) { - err = intel_pt_synth_instruction_sample(ptq); - if (err) - return err; + if (state->type & INTEL_PT_INSTRUCTION) { + if (pt->sample_instructions) { + err = intel_pt_synth_instruction_sample(ptq); + if (err) + return err; + } + if (pt->sample_cycles) { + err = intel_pt_synth_cycle_sample(ptq); + if (err) + return err; + } } if (pt->sample_transactions && (state->type & INTEL_PT_TRANSACTION)) { @@ -3731,6 +3772,22 @@ static int intel_pt_synth_events(struct intel_pt *pt, id += 1; } + if (pt->synth_opts.cycles) { + attr.config = PERF_COUNT_HW_CPU_CYCLES; + if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS) + attr.sample_period = + intel_pt_ns_to_ticks(pt, pt->synth_opts.period); + else + attr.sample_period = pt->synth_opts.period; + err = intel_pt_synth_event(session, "cycles", &attr, id); + if (err) + return err; + pt->sample_cycles = true; + pt->cycles_sample_type = attr.sample_type; + pt->cycles_id = id; + id += 1; + } + attr.sample_type &= ~(u64)PERF_SAMPLE_PERIOD; attr.sample_period = 1; @@ -4379,6 +4436,12 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_setup_pebs_events(pt); + if (perf_data__is_pipe(session->data)) { + pr_warning("WARNING: Intel PT with pipe mode is not recommended.\n" + " The output cannot relied upon. In particular,\n" + " timestamps and the order of events may be incorrect.\n"); + } + if (pt->sampling_mode || list_empty(&session->auxtrace_index)) err = auxtrace_queue_data(session, true, true); else diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 650ffe336f3a..4e8e243a6e4b 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -531,14 +531,37 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, pr_debug("llvm compiling command template: %s\n", template); + /* + * Below, substitute control characters for values that can cause the + * echo to misbehave, then substitute the values back. + */ err = -ENOMEM; - if (asprintf(&command_echo, "echo -n \"%s\"", template) < 0) + if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0) goto errout; +#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0) + for (char *p = command_echo; *p; p++) { + SWAP_CHAR('<', '\001'); + SWAP_CHAR('>', '\002'); + SWAP_CHAR('"', '\003'); + SWAP_CHAR('\'', '\004'); + SWAP_CHAR('|', '\005'); + SWAP_CHAR('&', '\006'); + SWAP_CHAR('\a', '"'); + } err = read_from_pipe(command_echo, (void **) &command_out, NULL); if (err) goto errout; + for (char *p = command_out; *p; p++) { + SWAP_CHAR('\001', '<'); + SWAP_CHAR('\002', '>'); + SWAP_CHAR('\003', '"'); + SWAP_CHAR('\004', '\''); + SWAP_CHAR('\005', '|'); + SWAP_CHAR('\006', '&'); + } +#undef SWAP_CHAR pr_debug("llvm compiling command : %s\n", command_out); err = read_from_pipe(template, &obj_buf, &obj_buf_sz); diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index b99e83fccf5c..040b618b2215 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -65,6 +65,11 @@ struct lock_stat { */ #define MAX_LOCK_DEPTH 48 +struct lock_stat *lock_stat_find(u64 addr); +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags); + +bool match_callstack_filter(struct machine *machine, u64 *callstack); + /* * struct lock_seq_stat: * Place to put on state of one lock sequence @@ -128,6 +133,8 @@ struct lock_contention { int max_stack; int stack_skip; int aggr_mode; + int owner; + bool save_callstack; }; #ifdef HAVE_BPF_SKEL diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index b9c273ed080a..f3559be95541 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -167,14 +167,14 @@ static void metricgroup___watchdog_constraint_hint(const char *name, bool foot) " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } -static bool metricgroup__has_constraint(const struct pmu_event *pe) +static bool metricgroup__has_constraint(const struct pmu_metric *pm) { - if (!pe->metric_constraint) + if (!pm->metric_constraint) return false; - if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") && + if (!strcmp(pm->metric_constraint, "NO_NMI_WATCHDOG") && sysctl__nmi_watchdog_enabled()) { - metricgroup___watchdog_constraint_hint(pe->metric_name, false); + metricgroup___watchdog_constraint_hint(pm->metric_name, false); return true; } @@ -193,7 +193,7 @@ static void metric__free(struct metric *m) free(m); } -static struct metric *metric__new(const struct pmu_event *pe, +static struct metric *metric__new(const struct pmu_metric *pm, const char *modifier, bool metric_no_group, int runtime, @@ -210,15 +210,15 @@ static struct metric *metric__new(const struct pmu_event *pe, if (!m->pctx) goto out_err; - m->metric_name = pe->metric_name; + m->metric_name = pm->metric_name; m->modifier = NULL; if (modifier) { m->modifier = strdup(modifier); if (!m->modifier) goto out_err; } - m->metric_expr = pe->metric_expr; - m->metric_unit = pe->unit; + m->metric_expr = pm->metric_expr; + m->metric_unit = pm->unit; m->pctx->sctx.user_requested_cpu_list = NULL; if (user_requested_cpu_list) { m->pctx->sctx.user_requested_cpu_list = strdup(user_requested_cpu_list); @@ -227,7 +227,7 @@ static struct metric *metric__new(const struct pmu_event *pe, } m->pctx->sctx.runtime = runtime; m->pctx->sctx.system_wide = system_wide; - m->has_constraint = metric_no_group || metricgroup__has_constraint(pe); + m->has_constraint = metric_no_group || metricgroup__has_constraint(pm); m->metric_refs = NULL; m->evlist = NULL; @@ -348,10 +348,10 @@ static bool match_metric(const char *n, const char *list) return false; } -static bool match_pe_metric(const struct pmu_event *pe, const char *metric) +static bool match_pm_metric(const struct pmu_metric *pm, const char *metric) { - return match_metric(pe->metric_group, metric) || - match_metric(pe->metric_name, metric); + return match_metric(pm->metric_group, metric) || + match_metric(pm->metric_name, metric); } /** struct mep - RB-tree node for building printing information. */ @@ -420,13 +420,13 @@ static struct mep *mep_lookup(struct rblist *groups, const char *metric_group, return NULL; } -static int metricgroup__add_to_mep_groups(const struct pmu_event *pe, +static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm, struct rblist *groups) { const char *g; char *omg, *mg; - mg = strdup(pe->metric_group ?: "No_group"); + mg = strdup(pm->metric_group ?: "No_group"); if (!mg) return -ENOMEM; omg = mg; @@ -435,15 +435,15 @@ static int metricgroup__add_to_mep_groups(const struct pmu_event *pe, g = skip_spaces(g); if (strlen(g)) - me = mep_lookup(groups, g, pe->metric_name); + me = mep_lookup(groups, g, pm->metric_name); else - me = mep_lookup(groups, "No_group", pe->metric_name); + me = mep_lookup(groups, "No_group", pm->metric_name); if (me) { - me->metric_desc = pe->desc; - me->metric_long_desc = pe->long_desc; - me->metric_expr = pe->metric_expr; - me->metric_unit = pe->unit; + me->metric_desc = pm->desc; + me->metric_long_desc = pm->long_desc; + me->metric_expr = pm->metric_expr; + me->metric_unit = pm->unit; } } free(omg); @@ -452,64 +452,61 @@ static int metricgroup__add_to_mep_groups(const struct pmu_event *pe, } struct metricgroup_iter_data { - pmu_event_iter_fn fn; + pmu_metric_iter_fn fn; void *data; }; -static int metricgroup__sys_event_iter(const struct pmu_event *pe, - const struct pmu_events_table *table, +static int metricgroup__sys_event_iter(const struct pmu_metric *pm, + const struct pmu_metrics_table *table, void *data) { struct metricgroup_iter_data *d = data; struct perf_pmu *pmu = NULL; - if (!pe->metric_expr || !pe->compat) + if (!pm->metric_expr || !pm->compat) return 0; while ((pmu = perf_pmu__scan(pmu))) { - if (!pmu->id || strcmp(pmu->id, pe->compat)) + if (!pmu->id || strcmp(pmu->id, pm->compat)) continue; - return d->fn(pe, table, d->data); + return d->fn(pm, table, d->data); } return 0; } -static int metricgroup__add_to_mep_groups_callback(const struct pmu_event *pe, - const struct pmu_events_table *table __maybe_unused, - void *vdata) +static int metricgroup__add_to_mep_groups_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *vdata) { struct rblist *groups = vdata; - if (!pe->metric_name) - return 0; - - return metricgroup__add_to_mep_groups(pe, groups); + return metricgroup__add_to_mep_groups(pm, groups); } void metricgroup__print(const struct print_callbacks *print_cb, void *print_state) { struct rblist groups; - const struct pmu_events_table *table; + const struct pmu_metrics_table *table; struct rb_node *node, *next; rblist__init(&groups); groups.node_new = mep_new; groups.node_cmp = mep_cmp; groups.node_delete = mep_delete; - table = pmu_events_table__find(); + table = pmu_metrics_table__find(); if (table) { - pmu_events_table_for_each_event(table, - metricgroup__add_to_mep_groups_callback, - &groups); + pmu_metrics_table_for_each_metric(table, + metricgroup__add_to_mep_groups_callback, + &groups); } { struct metricgroup_iter_data data = { .fn = metricgroup__add_to_mep_groups_callback, .data = &groups, }; - pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); + pmu_for_each_sys_metric(metricgroup__sys_event_iter, &data); } for (node = rb_first_cached(&groups.entries); node; node = next) { @@ -743,7 +740,7 @@ static int metricgroup__build_event_string(struct strbuf *events, #undef RETURN_IF_NON_ZERO } -int __weak arch_get_runtimeparam(const struct pmu_event *pe __maybe_unused) +int __weak arch_get_runtimeparam(const struct pmu_metric *pm __maybe_unused) { return 1; } @@ -768,22 +765,22 @@ struct metricgroup_add_iter_data { bool system_wide; struct metric *root_metric; const struct visited_metric *visited; - const struct pmu_events_table *table; + const struct pmu_metrics_table *table; }; static bool metricgroup__find_metric(const char *metric, - const struct pmu_events_table *table, - struct pmu_event *pe); + const struct pmu_metrics_table *table, + struct pmu_metric *pm); static int add_metric(struct list_head *metric_list, - const struct pmu_event *pe, + const struct pmu_metric *pm, const char *modifier, bool metric_no_group, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, const struct visited_metric *visited, - const struct pmu_events_table *table); + const struct pmu_metrics_table *table); /** * resolve_metric - Locate metrics within the root metric and recursively add @@ -810,16 +807,16 @@ static int resolve_metric(struct list_head *metric_list, bool system_wide, struct metric *root_metric, const struct visited_metric *visited, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { struct hashmap_entry *cur; size_t bkt; struct to_resolve { /* The metric to resolve. */ - struct pmu_event pe; + struct pmu_metric pm; /* * The key in the IDs map, this may differ from in case, - * etc. from pe->metric_name. + * etc. from pm->metric_name. */ const char *key; } *pending = NULL; @@ -830,15 +827,15 @@ static int resolve_metric(struct list_head *metric_list, * the pending array. */ hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) { - struct pmu_event pe; + struct pmu_metric pm; - if (metricgroup__find_metric(cur->pkey, table, &pe)) { + if (metricgroup__find_metric(cur->pkey, table, &pm)) { pending = realloc(pending, (pending_cnt + 1) * sizeof(struct to_resolve)); if (!pending) return -ENOMEM; - memcpy(&pending[pending_cnt].pe, &pe, sizeof(pe)); + memcpy(&pending[pending_cnt].pm, &pm, sizeof(pm)); pending[pending_cnt].key = cur->pkey; pending_cnt++; } @@ -853,7 +850,7 @@ static int resolve_metric(struct list_head *metric_list, * context. */ for (i = 0; i < pending_cnt; i++) { - ret = add_metric(metric_list, &pending[i].pe, modifier, metric_no_group, + ret = add_metric(metric_list, &pending[i].pm, modifier, metric_no_group, user_requested_cpu_list, system_wide, root_metric, visited, table); if (ret) @@ -867,7 +864,7 @@ static int resolve_metric(struct list_head *metric_list, /** * __add_metric - Add a metric to metric_list. * @metric_list: The list the metric is added to. - * @pe: The pmu_event containing the metric to be added. + * @pm: The pmu_metric containing the metric to be added. * @modifier: if non-null event modifiers like "u". * @metric_no_group: Should events written to events be grouped "{}" or * global. Grouping is the default but due to multiplexing the @@ -884,7 +881,7 @@ static int resolve_metric(struct list_head *metric_list, * architecture perf is running upon. */ static int __add_metric(struct list_head *metric_list, - const struct pmu_event *pe, + const struct pmu_metric *pm, const char *modifier, bool metric_no_group, int runtime, @@ -892,19 +889,19 @@ static int __add_metric(struct list_head *metric_list, bool system_wide, struct metric *root_metric, const struct visited_metric *visited, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { const struct visited_metric *vm; int ret; bool is_root = !root_metric; struct visited_metric visited_node = { - .name = pe->metric_name, + .name = pm->metric_name, .parent = visited, }; for (vm = visited; vm; vm = vm->parent) { - if (!strcmp(pe->metric_name, vm->name)) { - pr_err("failed: recursion detected for %s\n", pe->metric_name); + if (!strcmp(pm->metric_name, vm->name)) { + pr_err("failed: recursion detected for %s\n", pm->metric_name); return -1; } } @@ -914,7 +911,7 @@ static int __add_metric(struct list_head *metric_list, * This metric is the root of a tree and may reference other * metrics that are added recursively. */ - root_metric = metric__new(pe, modifier, metric_no_group, runtime, + root_metric = metric__new(pm, modifier, metric_no_group, runtime, user_requested_cpu_list, system_wide); if (!root_metric) return -ENOMEM; @@ -929,7 +926,7 @@ static int __add_metric(struct list_head *metric_list, */ if (root_metric->metric_refs) { for (; root_metric->metric_refs[cnt].metric_name; cnt++) { - if (!strcmp(pe->metric_name, + if (!strcmp(pm->metric_name, root_metric->metric_refs[cnt].metric_name)) return 0; } @@ -947,8 +944,8 @@ static int __add_metric(struct list_head *metric_list, * need to change them, so there's no need to create * our own copy. */ - root_metric->metric_refs[cnt].metric_name = pe->metric_name; - root_metric->metric_refs[cnt].metric_expr = pe->metric_expr; + root_metric->metric_refs[cnt].metric_name = pm->metric_name; + root_metric->metric_refs[cnt].metric_expr = pm->metric_expr; /* Null terminate array. */ root_metric->metric_refs[cnt+1].metric_name = NULL; @@ -959,7 +956,7 @@ static int __add_metric(struct list_head *metric_list, * For both the parent and referenced metrics, we parse * all the metric's IDs and add it to the root context. */ - if (expr__find_ids(pe->metric_expr, NULL, root_metric->pctx) < 0) { + if (expr__find_ids(pm->metric_expr, NULL, root_metric->pctx) < 0) { /* Broken metric. */ ret = -EINVAL; } else { @@ -981,57 +978,57 @@ static int __add_metric(struct list_head *metric_list, struct metricgroup__find_metric_data { const char *metric; - struct pmu_event *pe; + struct pmu_metric *pm; }; -static int metricgroup__find_metric_callback(const struct pmu_event *pe, - const struct pmu_events_table *table __maybe_unused, +static int metricgroup__find_metric_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, void *vdata) { struct metricgroup__find_metric_data *data = vdata; - if (!match_metric(pe->metric_name, data->metric)) + if (!match_metric(pm->metric_name, data->metric)) return 0; - memcpy(data->pe, pe, sizeof(*pe)); + memcpy(data->pm, pm, sizeof(*pm)); return 1; } static bool metricgroup__find_metric(const char *metric, - const struct pmu_events_table *table, - struct pmu_event *pe) + const struct pmu_metrics_table *table, + struct pmu_metric *pm) { struct metricgroup__find_metric_data data = { .metric = metric, - .pe = pe, + .pm = pm, }; - return pmu_events_table_for_each_event(table, metricgroup__find_metric_callback, &data) + return pmu_metrics_table_for_each_metric(table, metricgroup__find_metric_callback, &data) ? true : false; } static int add_metric(struct list_head *metric_list, - const struct pmu_event *pe, + const struct pmu_metric *pm, const char *modifier, bool metric_no_group, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, const struct visited_metric *visited, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { int ret = 0; - pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name); + pr_debug("metric expr %s for %s\n", pm->metric_expr, pm->metric_name); - if (!strstr(pe->metric_expr, "?")) { - ret = __add_metric(metric_list, pe, modifier, metric_no_group, 0, + if (!strstr(pm->metric_expr, "?")) { + ret = __add_metric(metric_list, pm, modifier, metric_no_group, 0, user_requested_cpu_list, system_wide, root_metric, visited, table); } else { int j, count; - count = arch_get_runtimeparam(pe); + count = arch_get_runtimeparam(pm); /* This loop is added to create multiple * events depend on count value and add @@ -1039,7 +1036,7 @@ static int add_metric(struct list_head *metric_list, */ for (j = 0; j < count && !ret; j++) - ret = __add_metric(metric_list, pe, modifier, metric_no_group, j, + ret = __add_metric(metric_list, pm, modifier, metric_no_group, j, user_requested_cpu_list, system_wide, root_metric, visited, table); } @@ -1047,17 +1044,17 @@ static int add_metric(struct list_head *metric_list, return ret; } -static int metricgroup__add_metric_sys_event_iter(const struct pmu_event *pe, - const struct pmu_events_table *table __maybe_unused, - void *data) +static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *data) { struct metricgroup_add_iter_data *d = data; int ret; - if (!match_pe_metric(pe, d->metric_name)) + if (!match_pm_metric(pm, d->metric_name)) return 0; - ret = add_metric(d->metric_list, pe, d->modifier, d->metric_no_group, + ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group, d->user_requested_cpu_list, d->system_wide, d->root_metric, d->visited, d->table); if (ret) @@ -1107,19 +1104,19 @@ struct metricgroup__add_metric_data { bool has_match; }; -static int metricgroup__add_metric_callback(const struct pmu_event *pe, - const struct pmu_events_table *table, +static int metricgroup__add_metric_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table, void *vdata) { struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pe->metric_expr && - (match_metric(pe->metric_group, data->metric_name) || - match_metric(pe->metric_name, data->metric_name))) { + if (pm->metric_expr && + (match_metric(pm->metric_group, data->metric_name) || + match_metric(pm->metric_name, data->metric_name))) { data->has_match = true; - ret = add_metric(data->list, pe, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); } @@ -1146,7 +1143,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { LIST_HEAD(list); int ret; @@ -1166,8 +1163,8 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier * Iterate over all metrics seeing if metric matches either the * name or group. When it does add the metric to the list. */ - ret = pmu_events_table_for_each_event(table, metricgroup__add_metric_callback, - &data); + ret = pmu_metrics_table_for_each_metric(table, metricgroup__add_metric_callback, + &data); if (ret) goto out; @@ -1189,7 +1186,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier }, }; - pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); + pmu_for_each_sys_metric(metricgroup__sys_event_iter, &data); } /* End of pmu events. */ if (!has_match) @@ -1222,7 +1219,7 @@ out: static int metricgroup__add_metric_list(const char *list, bool metric_no_group, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { char *list_itr, *list_copy, *metric_name, *modifier; int ret, count = 0; @@ -1432,7 +1429,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, bool system_wide, struct perf_pmu *fake_pmu, struct rblist *metric_events_list, - const struct pmu_events_table *table) + const struct pmu_metrics_table *table) { struct evlist *combined_evlist = NULL; LIST_HEAD(metric_list); @@ -1580,7 +1577,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool system_wide, struct rblist *metric_events) { - const struct pmu_events_table *table = pmu_events_table__find(); + const struct pmu_metrics_table *table = pmu_metrics_table__find(); if (!table) return -EINVAL; @@ -1591,7 +1588,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, } int metricgroup__parse_groups_test(struct evlist *evlist, - const struct pmu_events_table *table, + const struct pmu_metrics_table *table, const char *str, bool metric_no_group, bool metric_no_merge, @@ -1603,16 +1600,16 @@ int metricgroup__parse_groups_test(struct evlist *evlist, &perf_pmu__fake, metric_events, table); } -static int metricgroup__has_metric_callback(const struct pmu_event *pe, - const struct pmu_events_table *table __maybe_unused, +static int metricgroup__has_metric_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, void *vdata) { const char *metric = vdata; - if (!pe->metric_expr) + if (!pm->metric_expr) return 0; - if (match_metric(pe->metric_name, metric)) + if (match_metric(pm->metric_name, metric)) return 1; return 0; @@ -1620,13 +1617,13 @@ static int metricgroup__has_metric_callback(const struct pmu_event *pe, bool metricgroup__has_metric(const char *metric) { - const struct pmu_events_table *table = pmu_events_table__find(); + const struct pmu_metrics_table *table = pmu_metrics_table__find(); if (!table) return false; - return pmu_events_table_for_each_event(table, metricgroup__has_metric_callback, - (void *)metric) ? true : false; + return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, + (void *)metric) ? true : false; } int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 0013cf582173..84030321a057 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -73,7 +73,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool system_wide, struct rblist *metric_events); int metricgroup__parse_groups_test(struct evlist *evlist, - const struct pmu_events_table *table, + const struct pmu_metrics_table *table, const char *str, bool metric_no_group, bool metric_no_merge, @@ -81,7 +81,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist, void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); bool metricgroup__has_metric(const char *metric); -int arch_get_runtimeparam(const struct pmu_event *pe __maybe_unused); +int arch_get_runtimeparam(const struct pmu_metric *pm); void metricgroup__rblist_exit(struct rblist *metric_events); int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 21cce83462b3..0336ff27c15f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1570,8 +1570,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; - evsel->metric_expr = info.metric_expr; - evsel->metric_name = info.metric_name; return 0; } diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index ac3227ba769c..b59ba825ddc9 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -193,8 +193,7 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state, /*scale_unit=*/NULL, /*deprecated=*/NULL, "PFM event", info->desc, /*long_desc=*/NULL, - /*encoding_desc=*/buf->buf, - /*metric_name=*/NULL, /*metric_expr=*/NULL); + /*encoding_desc=*/buf->buf); pfm_for_each_event_attr(j, info) { pfm_event_attr_info_t ainfo; @@ -224,8 +223,7 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state, /*scale_unit=*/NULL, /*deprecated=*/NULL, "PFM event", ainfo.desc, /*long_desc=*/NULL, - /*encoding_desc=*/buf->buf, - /*metric_name=*/NULL, /*metric_expr=*/NULL); + /*encoding_desc=*/buf->buf); } } } diff --git a/tools/perf/util/pmu-hybrid.c b/tools/perf/util/pmu-hybrid.c index f51ccaac60ee..38628805a952 100644 --- a/tools/perf/util/pmu-hybrid.c +++ b/tools/perf/util/pmu-hybrid.c @@ -20,32 +20,15 @@ LIST_HEAD(perf_pmu__hybrid_pmus); bool perf_pmu__hybrid_mounted(const char *name) { - char path[PATH_MAX]; - const char *sysfs; - FILE *file; - int n, cpu; + int cpu; + char pmu_name[PATH_MAX]; + struct perf_pmu pmu = {.name = pmu_name}; if (strncmp(name, "cpu_", 4)) return false; - sysfs = sysfs__mountpoint(); - if (!sysfs) - return false; - - snprintf(path, PATH_MAX, CPUS_TEMPLATE_CPU, sysfs, name); - if (!file_available(path)) - return false; - - file = fopen(path, "r"); - if (!file) - return false; - - n = fscanf(file, "%u", &cpu); - fclose(file); - if (n <= 0) - return false; - - return true; + strlcpy(pmu_name, name, sizeof(pmu_name)); + return perf_pmu__scan_file(&pmu, "cpus", "%u", &cpu) > 0; } struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 2bdeb89352e7..c256b29defad 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -19,6 +19,7 @@ #include <regex.h> #include <perf/cpumap.h> #include <fnmatch.h> +#include <math.h> #include "debug.h" #include "evsel.h" #include "pmu.h" @@ -107,14 +108,10 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) static int pmu_format(const char *name, struct list_head *format) { char path[PATH_MAX]; - const char *sysfs = sysfs__mountpoint(); - if (!sysfs) + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), name, "format")) return -1; - snprintf(path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name); - if (!file_available(path)) return 0; @@ -283,10 +280,6 @@ static void perf_pmu_update_alias(struct perf_pmu_alias *old, perf_pmu_assign_str(old->name, "long_desc", &old->long_desc, &newalias->long_desc); perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic); - perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr, - &newalias->metric_expr); - perf_pmu_assign_str(old->name, "metric_name", &old->metric_name, - &newalias->metric_name); perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str); old->scale = newalias->scale; old->per_pkg = newalias->per_pkg; @@ -302,8 +295,6 @@ void perf_pmu_free_alias(struct perf_pmu_alias *newalias) zfree(&newalias->long_desc); zfree(&newalias->topic); zfree(&newalias->str); - zfree(&newalias->metric_expr); - zfree(&newalias->metric_name); zfree(&newalias->pmu_name); parse_events_terms__purge(&newalias->terms); free(newalias); @@ -340,16 +331,13 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, int num; char newval[256]; char *long_desc = NULL, *topic = NULL, *unit = NULL, *perpkg = NULL, - *metric_expr = NULL, *metric_name = NULL, *deprecated = NULL, - *pmu_name = NULL; + *deprecated = NULL, *pmu_name = NULL; if (pe) { long_desc = (char *)pe->long_desc; topic = (char *)pe->topic; unit = (char *)pe->unit; perpkg = (char *)pe->perpkg; - metric_expr = (char *)pe->metric_expr; - metric_name = (char *)pe->metric_name; deprecated = (char *)pe->deprecated; pmu_name = (char *)pe->pmu; } @@ -404,8 +392,6 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, perf_pmu__parse_snapshot(alias, dir, name); } - alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL; - alias->metric_name = metric_name ? strdup(metric_name): NULL; alias->desc = desc ? strdup(desc) : NULL; alias->long_desc = long_desc ? strdup(long_desc) : desc ? strdup(desc) : NULL; @@ -513,14 +499,10 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) static int pmu_aliases(const char *name, struct list_head *head) { char path[PATH_MAX]; - const char *sysfs = sysfs__mountpoint(); - if (!sysfs) + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), name, "events")) return -1; - snprintf(path, PATH_MAX, - "%s/bus/event_source/devices/%s/events", sysfs, name); - if (!file_available(path)) return 0; @@ -554,52 +536,16 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, return 0; } -/* - * Reading/parsing the default pmu type value, which should be - * located at: - * /sys/bus/event_source/devices/<dev>/type as sysfs attribute. - */ -static int pmu_type(const char *name, __u32 *type) -{ - char path[PATH_MAX]; - FILE *file; - int ret = 0; - const char *sysfs = sysfs__mountpoint(); - - if (!sysfs) - return -1; - - snprintf(path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name); - - if (access(path, R_OK) < 0) - return -1; - - file = fopen(path, "r"); - if (!file) - return -EINVAL; - - if (1 != fscanf(file, "%u", type)) - ret = -1; - - fclose(file); - return ret; -} - /* Add all pmus in sysfs to pmu list: */ static void pmu_read_sysfs(void) { char path[PATH_MAX]; DIR *dir; struct dirent *dent; - const char *sysfs = sysfs__mountpoint(); - if (!sysfs) + if (!perf_pmu__event_source_devices_scnprintf(path, sizeof(path))) return; - snprintf(path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); - dir = opendir(path); if (!dir) return; @@ -614,45 +560,29 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct perf_cpu_map *__pmu_cpumask(const char *path) -{ - FILE *file; - struct perf_cpu_map *cpus; - - file = fopen(path, "r"); - if (!file) - return NULL; - - cpus = perf_cpu_map__read(file); - fclose(file); - return cpus; -} - /* * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ -#define SYS_TEMPLATE_ID "./bus/event_source/devices/%s/identifier" -#define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" - static struct perf_cpu_map *pmu_cpumask(const char *name) { - char path[PATH_MAX]; struct perf_cpu_map *cpus; - const char *sysfs = sysfs__mountpoint(); const char *templates[] = { - CPUS_TEMPLATE_UNCORE, - CPUS_TEMPLATE_CPU, + "cpumask", + "cpus", NULL }; const char **template; + char pmu_name[PATH_MAX]; + struct perf_pmu pmu = {.name = pmu_name}; + FILE *file; - if (!sysfs) - return NULL; - + strlcpy(pmu_name, name, sizeof(pmu_name)); for (template = templates; *template; template++) { - snprintf(path, PATH_MAX, *template, sysfs, name); - cpus = __pmu_cpumask(path); + file = perf_pmu__open_file(&pmu, *template); + if (!file) + continue; + cpus = perf_cpu_map__read(file); if (cpus) return cpus; } @@ -663,13 +593,11 @@ static struct perf_cpu_map *pmu_cpumask(const char *name) static bool pmu_is_uncore(const char *name) { char path[PATH_MAX]; - const char *sysfs; if (perf_pmu__hybrid_mounted(name)) return false; - sysfs = sysfs__mountpoint(); - snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); + perf_pmu__pathname_scnprintf(path, sizeof(path), name, "cpumask"); return file_available(path); } @@ -678,9 +606,9 @@ static char *pmu_id(const char *name) char path[PATH_MAX], *str; size_t len; - snprintf(path, PATH_MAX, SYS_TEMPLATE_ID, name); + perf_pmu__pathname_scnprintf(path, sizeof(path), name, "identifier"); - if (sysfs__read_str(path, &str, &len) < 0) + if (filename__read_str(path, &str, &len) < 0) return NULL; str[len - 1] = 0; /* remove line feed */ @@ -696,14 +624,9 @@ static char *pmu_id(const char *name) static int is_arm_pmu_core(const char *name) { char path[PATH_MAX]; - const char *sysfs = sysfs__mountpoint(); - if (!sysfs) + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), name, "cpus")) return 0; - - /* Look for cpu sysfs (specific to arm) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", - sysfs, name); return file_available(path); } @@ -729,7 +652,12 @@ char *perf_pmu__getcpuid(struct perf_pmu *pmu) __weak const struct pmu_events_table *pmu_events_table__find(void) { - return perf_pmu__find_table(NULL); + return perf_pmu__find_events_table(NULL); +} + +__weak const struct pmu_metrics_table *pmu_metrics_table__find(void) +{ + return perf_pmu__find_metrics_table(NULL); } /* @@ -822,9 +750,6 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, struct pmu_add_cpu_aliases_map_data *data = vdata; const char *pname = pe->pmu ? pe->pmu : data->cpu_name; - if (!pe->name) - return 0; - if (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->name)) goto new_alias; @@ -860,7 +785,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) { const struct pmu_events_table *table; - table = perf_pmu__find_table(pmu); + table = perf_pmu__find_events_table(pmu); if (!table) return; @@ -879,12 +804,6 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, struct pmu_sys_event_iter_data *idata = data; struct perf_pmu *pmu = idata->pmu; - if (!pe->name) { - if (pe->metric_group || pe->metric_name) - return 0; - return -EINVAL; - } - if (!pe->compat || !pe->pmu) return 0; @@ -931,16 +850,11 @@ pmu_find_alias_name(const char *name __maybe_unused) return NULL; } -static int pmu_max_precise(const char *name) +static int pmu_max_precise(struct perf_pmu *pmu) { - char path[PATH_MAX]; int max_precise = -1; - scnprintf(path, PATH_MAX, - "bus/event_source/devices/%s/caps/max_precise", - name); - - sysfs__read_int(path, &max_precise); + perf_pmu__scan_file(pmu, "caps/max_precise", "%d", &max_precise); return max_precise; } @@ -969,11 +883,8 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name) return NULL; /* - * Check the type first to avoid unnecessary work. + * Check the aliases first to avoid unnecessary work. */ - if (pmu_type(name, &type)) - return NULL; - if (pmu_aliases(name, &aliases)) return NULL; @@ -983,9 +894,14 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name) pmu->cpus = pmu_cpumask(name); pmu->name = strdup(name); + if (!pmu->name) goto err; + /* Read type, and ensure that type value is successfully assigned (return 1) */ + if (perf_pmu__scan_file(pmu, "type", "%u", &type) != 1) + goto err; + alias_name = pmu_find_alias_name(name); if (alias_name) { pmu->alias_name = strdup(alias_name); @@ -997,7 +913,7 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name) pmu->is_uncore = pmu_is_uncore(name); if (pmu->is_uncore) pmu->id = pmu_id(name); - pmu->max_precise = pmu_max_precise(name); + pmu->max_precise = pmu_max_precise(pmu); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); @@ -1469,8 +1385,6 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->unit = NULL; info->scale = 0.0; info->snapshot = false; - info->metric_expr = NULL; - info->metric_name = NULL; list_for_each_entry_safe(term, h, head_terms, list) { alias = pmu_find_alias(pmu, term); @@ -1486,8 +1400,6 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (alias->per_pkg) info->per_pkg = true; - info->metric_expr = alias->metric_expr; - info->metric_name = alias->metric_name; list_del_init(&term->list); parse_events_term__delete(term); @@ -1703,8 +1615,7 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) for (j = 0; j < len; j++) { const char *name, *alias = NULL, *scale_unit = NULL, *desc = NULL, *long_desc = NULL, - *encoding_desc = NULL, *topic = NULL, - *metric_name = NULL, *metric_expr = NULL; + *encoding_desc = NULL, *topic = NULL; bool deprecated = false; size_t buf_used; @@ -1742,8 +1653,6 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, "%s/%s/", aliases[j].pmu->name, aliases[j].event->str) + 1; - metric_name = aliases[j].event->metric_name; - metric_expr = aliases[j].event->metric_expr; deprecated = aliases[j].event->deprecated; } print_cb->print_event(print_state, @@ -1756,9 +1665,7 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) "Kernel PMU event", desc, long_desc, - encoding_desc, - metric_name, - metric_expr); + encoding_desc); } if (printed && pager_in_use()) printf("\n"); @@ -1783,19 +1690,14 @@ bool pmu_have_event(const char *pname, const char *name) return false; } -static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) +FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) { char path[PATH_MAX]; - const char *sysfs; - sysfs = sysfs__mountpoint(); - if (!sysfs) + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, name) || + !file_available(path)) return NULL; - snprintf(path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name); - if (!file_available(path)) - return NULL; return fopen(path, "r"); } @@ -1816,6 +1718,16 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return ret; } +bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name) +{ + char path[PATH_MAX]; + + if (!perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, name)) + return false; + + return file_available(path); +} + static int perf_pmu__new_caps(struct list_head *list, char *name, char *value) { struct perf_pmu_caps *caps = zalloc(sizeof(*caps)); @@ -1849,7 +1761,6 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) { struct stat st; char caps_path[PATH_MAX]; - const char *sysfs = sysfs__mountpoint(); DIR *caps_dir; struct dirent *evt_ent; @@ -1858,12 +1769,9 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) pmu->nr_caps = 0; - if (!sysfs) + if (!perf_pmu__pathname_scnprintf(caps_path, sizeof(caps_path), pmu->name, "caps")) return -1; - snprintf(caps_path, PATH_MAX, - "%s" EVENT_SOURCE_DEVICE_PATH "%s/caps", sysfs, pmu->name); - if (stat(caps_path, &st) < 0) { pmu->caps_initialized = true; return 0; /* no error if caps does not exist */ @@ -1993,3 +1901,36 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, *ucpus_ptr = unmatched_cpus; return 0; } + +double __weak perf_pmu__cpu_slots_per_cycle(void) +{ + return NAN; +} + +int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size) +{ + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return 0; + return scnprintf(pathname, size, "%s/bus/event_source/devices/", sysfs); +} + +/* + * Fill 'buf' with the path to a file or folder in 'pmu_name' in + * sysfs. For example if pmu_name = "cs_etm" and 'filename' = "format" + * then pathname will be filled with + * "/sys/bus/event_source/devices/cs_etm/format" + * + * Return 0 if the sysfs mountpoint couldn't be found or if no + * characters were written. + */ +int perf_pmu__pathname_scnprintf(char *buf, size_t size, + const char *pmu_name, const char *filename) +{ + char base_path[PATH_MAX]; + + if (!perf_pmu__event_source_devices_scnprintf(base_path, sizeof(base_path))) + return 0; + return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 69ca0004f94f..6b770f17eb86 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -7,6 +7,7 @@ #include <linux/perf_event.h> #include <linux/list.h> #include <stdbool.h> +#include <stdio.h> #include "parse-events.h" #include "pmu-events/pmu-events.h" @@ -22,8 +23,6 @@ enum { }; #define PERF_PMU_FORMAT_BITS 64 -#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" -#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" #define MAX_PMU_NAME_LEN 128 struct perf_event_attr; @@ -133,8 +132,6 @@ extern struct perf_pmu perf_pmu__fake; struct perf_pmu_info { const char *unit; - const char *metric_expr; - const char *metric_name; double scale; bool per_pkg; bool snapshot; @@ -188,13 +185,6 @@ struct perf_pmu_alias { * default. */ bool deprecated; - /** - * @metric_expr: A metric expression associated with an event. Doing - * this makes little sense due to scale and unit applying to both. - */ - char *metric_expr; - /** @metric_name: A name for the metric. unit applying to both. */ - char *metric_name; /** @pmu_name: The name copied from struct perf_pmu. */ char *pmu_name; }; @@ -231,6 +221,8 @@ bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); +bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name); + int perf_pmu__test(void); struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); @@ -239,6 +231,7 @@ void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu, char *perf_pmu__getcpuid(struct perf_pmu *pmu); const struct pmu_events_table *pmu_events_table__find(void); +const struct pmu_metrics_table *pmu_metrics_table__find(void); bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); @@ -259,4 +252,10 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, char *pmu_find_real_name(const char *name); char *pmu_find_alias_name(const char *name); +double perf_pmu__cpu_slots_per_cycle(void); +int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); +int perf_pmu__pathname_scnprintf(char *buf, size_t size, + const char *pmu_name, const char *filename); +FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); + #endif /* __PMU_H */ diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 2646ae18d9f9..62e9ea7dcf40 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -101,9 +101,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb, void *print "Tracepoint event", /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); } free(dir_path); free(evt_namelist); @@ -195,9 +193,7 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) "SDT event", /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); free(evt_name); } @@ -255,9 +251,7 @@ int print_hwcache_events(const struct print_callbacks *print_cb, void *print_sta event_type_descriptors[PERF_TYPE_HW_CACHE], /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); } strlist__delete(evt_name_list); return 0; @@ -277,9 +271,7 @@ void print_tool_events(const struct print_callbacks *print_cb, void *print_state "Tool event", /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); } } @@ -331,9 +323,7 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta event_type_descriptors[type], /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); } strlist__delete(evt_name_list); } @@ -364,9 +354,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) event_type_descriptors[PERF_TYPE_RAW], /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); print_cb->print_event(print_state, /*topic=*/NULL, @@ -378,9 +366,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) event_type_descriptors[PERF_TYPE_RAW], "(see 'man perf-list' on how to encode it)", /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); print_cb->print_event(print_state, /*topic=*/NULL, @@ -392,9 +378,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) event_type_descriptors[PERF_TYPE_BREAKPOINT], /*desc=*/NULL, /*long_desc=*/NULL, - /*encoding_desc=*/NULL, - /*metric_name=*/NULL, - /*metric_expr=*/NULL); + /*encoding_desc=*/NULL); print_tracepoint_events(print_cb, print_state); diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h index c237e53c4487..716dcf4b4859 100644 --- a/tools/perf/util/print-events.h +++ b/tools/perf/util/print-events.h @@ -16,8 +16,7 @@ struct print_callbacks { const char *scale_unit, bool deprecated, const char *event_type_desc, const char *desc, const char *long_desc, - const char *encoding_desc, - const char *metric_name, const char *metric_expr); + const char *encoding_desc); void (*print_metric)(void *print_state, const char *group, const char *name, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 0c24bc7afbca..881d94f65a6b 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -917,7 +917,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, dinfo = open_debuginfo(pev->target, pev->nsi, !need_dwarf); if (!dinfo) { if (need_dwarf) - return -ENOENT; + return -ENODATA; pr_debug("Could not open debuginfo. Try to use symbols.\n"); return 0; } @@ -956,7 +956,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs == 0) { /* No error but failed to find probe point. */ pr_warning("Probe point '%s' not found.\n", synthesize_perf_probe_point(&pev->point)); - return -ENOENT; + return -ENODEV; } else if (ntevs < 0) { /* Error path : ntevs < 0 */ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 212031b97910..42e8b813d010 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -20,6 +20,7 @@ #include "stat.h" #include "metricgroup.h" #include "util/env.h" +#include "util/pmu.h" #include <internal/lib.h> #include "util.h" @@ -76,14 +77,7 @@ const char *perf_env__arch(struct perf_env *env __maybe_unused) } /* - * Add this one here not to drag util/stat-shadow.c - */ -void perf_stat__collect_metric_expr(struct evlist *evsel_list) -{ -} - -/* - * This one is needed not to drag the PMU bandwagon, jevents generated + * These ones are needed not to drag the PMU bandwagon, jevents generated * pmu_sys_event_tables, etc and evsel__find_pmu() is used so far just for * doing per PMU perf_event_attr.exclude_guest handling, not really needed, so * far, for the perf python binding known usecases, revisit if this become @@ -94,6 +88,11 @@ struct perf_pmu *evsel__find_pmu(struct evsel *evsel __maybe_unused) return NULL; } +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) +{ + return EOF; +} + /* * Add this one here not to drag util/metricgroup.c */ @@ -442,10 +441,8 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) offset = val; len = offset >> 16; offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h index 60ec79d4eea4..33b08e0ac746 100644 --- a/tools/perf/util/sample.h +++ b/tools/perf/util/sample.h @@ -92,7 +92,10 @@ struct perf_sample { u8 cpumode; u16 misc; u16 ins_lat; - u16 p_stage_cyc; + union { + u16 p_stage_cyc; + u16 retire_lat; + }; bool no_hw_idx; /* No hw_idx collected in branch_stack */ char insn[MAX_INSN]; void *raw_data; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index c097b7934fd4..83fd2fd0ba16 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -393,10 +393,8 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(data + field->offset); offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif } else offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index e930f5f1f36d..2c2697c5d025 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -994,10 +994,8 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = val; len = offset >> 16; offset &= 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7c021c6cedb9..749d5b5c135b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1180,7 +1180,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) struct branch_entry *e = &entries[i]; if (!callstack) { - printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s\n", + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s %s\n", i, e->from, e->to, (unsigned short)e->flags.cycles, e->flags.mispred ? "M" : " ", @@ -1188,7 +1188,8 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) e->flags.abort ? "A" : " ", e->flags.in_tx ? "T" : " ", (unsigned)e->flags.reserved, - get_branch_type(e)); + get_branch_type(e), + e->flags.spec ? branch_spec_desc(e->flags.spec) : ""); } else { if (i == 0) { printf("..... %2"PRIu64": %016" PRIx64 "\n" @@ -1699,8 +1700,13 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_AUXTRACE_INFO: return tool->auxtrace_info(session, event); case PERF_RECORD_AUXTRACE: - /* setup for reading amidst mmap */ - lseek(fd, file_offset + event->header.size, SEEK_SET); + /* + * Setup for reading amidst mmap, but only when we + * are in 'file' mode. The 'pipe' fd is in proper + * place already. + */ + if (!perf_data__is_pipe(session->data)) + lseek(fd, file_offset + event->header.size, SEEK_SET); return tool->auxtrace(session, event); case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 37662cdec5ee..093a0c8b2e3d 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -28,6 +28,7 @@ #include "time-utils.h" #include "cgroup.h" #include "machine.h" +#include "trace-event.h" #include <linux/kernel.h> #include <linux/string.h> @@ -53,6 +54,13 @@ static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"}; /* + * Some architectures have Adjacent Cacheline Prefetch feature, which + * behaves like the cacheline size is doubled. Enable this flag to + * check things in double cacheline granularity. + */ +bool chk_double_cl; + +/* * Replaces all occurrences of a char used with the: * * -t, --field-separator @@ -1499,8 +1507,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) addr: /* al_addr does all the right addr - start + offset calculations */ - l = cl_address(left->mem_info->daddr.al_addr); - r = cl_address(right->mem_info->daddr.al_addr); + l = cl_address(left->mem_info->daddr.al_addr, chk_double_cl); + r = cl_address(right->mem_info->daddr.al_addr, chk_double_cl); if (l > r) return -1; if (l < r) return 1; @@ -1519,7 +1527,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if (he->mem_info) { struct map *map = he->mem_info->daddr.ms.map; - addr = cl_address(he->mem_info->daddr.al_addr); + addr = cl_address(he->mem_info->daddr.al_addr, chk_double_cl); ms = &he->mem_info->daddr.ms; /* print [s] for shared data mmaps */ @@ -2132,6 +2140,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc), DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc), DIM(SORT_ADDR, "addr", sort_addr), + DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc), + DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc), }; #undef DIM @@ -2667,10 +2677,8 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, tep_read_number_field(field, a->raw_data, &dyn); offset = dyn & 0xffff; size = (dyn >> 16) & 0xffff; -#ifdef HAVE_LIBTRACEEVENT_TEP_FIELD_IS_RELATIVE - if (field->flags & TEP_FIELD_IS_RELATIVE) + if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; -#endif /* record max width for output */ if (size > hde->dynamic_len) hde->dynamic_len = size; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 921715e6aec4..d79a100e5999 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -35,6 +35,7 @@ extern struct sort_entry sort_sym_from; extern struct sort_entry sort_sym_to; extern struct sort_entry sort_srcline; extern const char default_mem_sort_order[]; +extern bool chk_double_cl; struct res_sample { u64 time; @@ -237,6 +238,8 @@ enum sort_type { SORT_LOCAL_PIPELINE_STAGE_CYC, SORT_GLOBAL_PIPELINE_STAGE_CYC, SORT_ADDR, + SORT_LOCAL_RETIRE_LAT, + SORT_GLOBAL_RETIRE_LAT, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 8bd8b0142630..1b5cb20efd23 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -787,6 +787,51 @@ static void uniquify_counter(struct perf_stat_config *config, struct evsel *coun uniquify_event_name(counter); } +/** + * should_skip_zero_count() - Check if the event should print 0 values. + * @config: The perf stat configuration (including aggregation mode). + * @counter: The evsel with its associated cpumap. + * @id: The aggregation id that is being queried. + * + * Due to mismatch between the event cpumap or thread-map and the + * aggregation mode, sometimes it'd iterate the counter with the map + * which does not contain any values. + * + * For example, uncore events have dedicated CPUs to manage them, + * result for other CPUs should be zero and skipped. + * + * Return: %true if the value should NOT be printed, %false if the value + * needs to be printed like "<not counted>" or "<not supported>". + */ +static bool should_skip_zero_counter(struct perf_stat_config *config, + struct evsel *counter, + const struct aggr_cpu_id *id) +{ + struct perf_cpu cpu; + int idx; + + /* + * Skip value 0 when enabling --per-thread globally, + * otherwise it will have too many 0 output. + */ + if (config->aggr_mode == AGGR_THREAD && config->system_wide) + return true; + /* + * Skip value 0 when it's an uncore event and the given aggr id + * does not belong to the PMU cpumask. + */ + if (!counter->pmu || !counter->pmu->is_uncore) + return false; + + perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) { + struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu); + + if (aggr_cpu_id__equal(id, &own_id)) + return false; + } + return true; +} + static void print_counter_aggrdata(struct perf_stat_config *config, struct evsel *counter, int s, struct outstate *os) @@ -814,11 +859,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config, ena = aggr->counts.ena; run = aggr->counts.run; - /* - * Skip value 0 when enabling --per-thread globally, otherwise it will - * have too many 0 output. - */ - if (val == 0 && config->aggr_mode == AGGR_THREAD && config->system_wide) + if (val == 0 && should_skip_zero_counter(config, counter, &id)) return; if (!metric_only) { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index cadb2df23c87..806b32156459 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -311,7 +311,7 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; - } else if (counter->metric_leader) { + } else if (counter->metric_leader && !counter->merged_stat) { v = saved_value_lookup(counter->metric_leader, map_idx, true, STAT_NONE, 0, st, rsd.cgrp); v->metric_total += count; @@ -346,114 +346,6 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static struct evsel *perf_stat__find_event(struct evlist *evsel_list, - const char *name) -{ - struct evsel *c2; - - evlist__for_each_entry (evsel_list, c2) { - if (!strcasecmp(c2->name, name) && !c2->collect_stat) - return c2; - } - return NULL; -} - -/* Mark MetricExpr target events and link events using them to them. */ -void perf_stat__collect_metric_expr(struct evlist *evsel_list) -{ - struct evsel *counter, *leader, **metric_events, *oc; - bool found; - struct expr_parse_ctx *ctx; - struct hashmap_entry *cur; - size_t bkt; - int i; - - ctx = expr__ctx_new(); - if (!ctx) { - pr_debug("expr__ctx_new failed"); - return; - } - evlist__for_each_entry(evsel_list, counter) { - bool invalid = false; - - leader = evsel__leader(counter); - if (!counter->metric_expr) - continue; - - expr__ctx_clear(ctx); - metric_events = counter->metric_events; - if (!metric_events) { - if (expr__find_ids(counter->metric_expr, - counter->name, - ctx) < 0) - continue; - - metric_events = calloc(sizeof(struct evsel *), - hashmap__size(ctx->ids) + 1); - if (!metric_events) { - expr__ctx_free(ctx); - return; - } - counter->metric_events = metric_events; - } - - i = 0; - hashmap__for_each_entry(ctx->ids, cur, bkt) { - const char *metric_name = cur->pkey; - - found = false; - if (leader) { - /* Search in group */ - for_each_group_member (oc, leader) { - if (!strcasecmp(oc->name, - metric_name) && - !oc->collect_stat) { - found = true; - break; - } - } - } - if (!found) { - /* Search ignoring groups */ - oc = perf_stat__find_event(evsel_list, - metric_name); - } - if (!oc) { - /* Deduping one is good enough to handle duplicated PMUs. */ - static char *printed; - - /* - * Adding events automatically would be difficult, because - * it would risk creating groups that are not schedulable. - * perf stat doesn't understand all the scheduling constraints - * of events. So we ask the user instead to add the missing - * events. - */ - if (!printed || - strcasecmp(printed, metric_name)) { - fprintf(stderr, - "Add %s event to groups to get metric expression for %s\n", - metric_name, - counter->name); - free(printed); - printed = strdup(metric_name); - } - invalid = true; - continue; - } - metric_events[i++] = oc; - oc->collect_stat = true; - } - metric_events[i] = NULL; - if (invalid) { - free(metric_events); - counter->metric_events = NULL; - counter->metric_expr = NULL; - } - } - expr__ctx_free(ctx); -} - static double runtime_stat_avg(struct runtime_stat *st, enum stat_type type, int map_idx, struct runtime_stat_data *rsd) @@ -1299,10 +1191,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, color = NULL; print_metric(config, ctxp, color, "%8.1f%%", "Core Bound", core_bound * 100.); - } else if (evsel->metric_expr) { - generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, - evsel->name, evsel->metric_name, NULL, 1, - map_idx, out, st); } else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 499c3bf81333..b1c29156c560 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -257,7 +257,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct perf_stat_output_ctx *out, struct rblist *metric_events, struct runtime_stat *st); -void perf_stat__collect_metric_expr(struct evlist *); int evlist__alloc_stats(struct perf_stat_config *config, struct evlist *evlist, bool alloc_raw); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 96767d1b3f1c..41882ae8452e 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -323,15 +323,325 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) return demangled; } -#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) +struct rel_info { + u32 nr_entries; + u32 *sorted; + bool is_rela; + Elf_Data *reldata; + GElf_Rela rela; + GElf_Rel rel; +}; + +static u32 get_rel_symidx(struct rel_info *ri, u32 idx) +{ + idx = ri->sorted ? ri->sorted[idx] : idx; + if (ri->is_rela) { + gelf_getrela(ri->reldata, idx, &ri->rela); + return GELF_R_SYM(ri->rela.r_info); + } + gelf_getrel(ri->reldata, idx, &ri->rel); + return GELF_R_SYM(ri->rel.r_info); +} -#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) +static u64 get_rel_offset(struct rel_info *ri, u32 x) +{ + if (ri->is_rela) { + GElf_Rela rela; + + gelf_getrela(ri->reldata, x, &rela); + return rela.r_offset; + } else { + GElf_Rel rel; + + gelf_getrel(ri->reldata, x, &rel); + return rel.r_offset; + } +} + +static int rel_cmp(const void *a, const void *b, void *r) +{ + struct rel_info *ri = r; + u64 a_offset = get_rel_offset(ri, *(const u32 *)a); + u64 b_offset = get_rel_offset(ri, *(const u32 *)b); + + return a_offset < b_offset ? -1 : (a_offset > b_offset ? 1 : 0); +} + +static int sort_rel(struct rel_info *ri) +{ + size_t sz = sizeof(ri->sorted[0]); + u32 i; + + ri->sorted = calloc(ri->nr_entries, sz); + if (!ri->sorted) + return -1; + for (i = 0; i < ri->nr_entries; i++) + ri->sorted[i] = i; + qsort_r(ri->sorted, ri->nr_entries, sz, rel_cmp, ri); + return 0; +} + +/* + * For x86_64, the GNU linker is putting IFUNC information in the relocation + * addend. + */ +static bool addend_may_be_ifunc(GElf_Ehdr *ehdr, struct rel_info *ri) +{ + return ehdr->e_machine == EM_X86_64 && ri->is_rela && + GELF_R_TYPE(ri->rela.r_info) == R_X86_64_IRELATIVE; +} + +static bool get_ifunc_name(Elf *elf, struct dso *dso, GElf_Ehdr *ehdr, + struct rel_info *ri, char *buf, size_t buf_sz) +{ + u64 addr = ri->rela.r_addend; + struct symbol *sym; + GElf_Phdr phdr; + + if (!addend_may_be_ifunc(ehdr, ri)) + return false; + + if (elf_read_program_header(elf, addr, &phdr)) + return false; + + addr -= phdr.p_vaddr - phdr.p_offset; + + sym = dso__find_symbol_nocache(dso, addr); + + /* Expecting the address to be an IFUNC or IFUNC alias */ + if (!sym || sym->start != addr || (sym->type != STT_GNU_IFUNC && !sym->ifunc_alias)) + return false; + + snprintf(buf, buf_sz, "%s@plt", sym->name); + + return true; +} + +static void exit_rel(struct rel_info *ri) +{ + free(ri->sorted); +} + +static bool get_plt_sizes(struct dso *dso, GElf_Ehdr *ehdr, GElf_Shdr *shdr_plt, + u64 *plt_header_size, u64 *plt_entry_size) +{ + switch (ehdr->e_machine) { + case EM_ARM: + *plt_header_size = 20; + *plt_entry_size = 12; + return true; + case EM_AARCH64: + *plt_header_size = 32; + *plt_entry_size = 16; + return true; + case EM_SPARC: + *plt_header_size = 48; + *plt_entry_size = 12; + return true; + case EM_SPARCV9: + *plt_header_size = 128; + *plt_entry_size = 32; + return true; + case EM_386: + case EM_X86_64: + *plt_entry_size = shdr_plt->sh_entsize; + /* Size is 8 or 16, if not, assume alignment indicates size */ + if (*plt_entry_size != 8 && *plt_entry_size != 16) + *plt_entry_size = shdr_plt->sh_addralign == 8 ? 8 : 16; + *plt_header_size = *plt_entry_size; + break; + default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */ + *plt_header_size = shdr_plt->sh_entsize; + *plt_entry_size = shdr_plt->sh_entsize; + break; + } + if (*plt_entry_size) + return true; + pr_debug("Missing PLT entry size for %s\n", dso->long_name); + return false; +} + +static bool machine_is_x86(GElf_Half e_machine) +{ + return e_machine == EM_386 || e_machine == EM_X86_64; +} + +struct rela_dyn { + GElf_Addr offset; + u32 sym_idx; +}; + +struct rela_dyn_info { + struct dso *dso; + Elf_Data *plt_got_data; + u32 nr_entries; + struct rela_dyn *sorted; + Elf_Data *dynsym_data; + Elf_Data *dynstr_data; + Elf_Data *rela_dyn_data; +}; + +static void exit_rela_dyn(struct rela_dyn_info *di) +{ + free(di->sorted); +} + +static int cmp_offset(const void *a, const void *b) +{ + const struct rela_dyn *va = a; + const struct rela_dyn *vb = b; + + return va->offset < vb->offset ? -1 : (va->offset > vb->offset ? 1 : 0); +} + +static int sort_rela_dyn(struct rela_dyn_info *di) +{ + u32 i, n; + + di->sorted = calloc(di->nr_entries, sizeof(di->sorted[0])); + if (!di->sorted) + return -1; + + /* Get data for sorting: the offset and symbol index */ + for (i = 0, n = 0; i < di->nr_entries; i++) { + GElf_Rela rela; + u32 sym_idx; + + gelf_getrela(di->rela_dyn_data, i, &rela); + sym_idx = GELF_R_SYM(rela.r_info); + if (sym_idx) { + di->sorted[n].sym_idx = sym_idx; + di->sorted[n].offset = rela.r_offset; + n += 1; + } + } + + /* Sort by offset */ + di->nr_entries = n; + qsort(di->sorted, n, sizeof(di->sorted[0]), cmp_offset); + + return 0; +} + +static void get_rela_dyn_info(Elf *elf, GElf_Ehdr *ehdr, struct rela_dyn_info *di, Elf_Scn *scn) +{ + GElf_Shdr rela_dyn_shdr; + GElf_Shdr shdr; + + di->plt_got_data = elf_getdata(scn, NULL); + + scn = elf_section_by_name(elf, ehdr, &rela_dyn_shdr, ".rela.dyn", NULL); + if (!scn || !rela_dyn_shdr.sh_link || !rela_dyn_shdr.sh_entsize) + return; + + di->nr_entries = rela_dyn_shdr.sh_size / rela_dyn_shdr.sh_entsize; + di->rela_dyn_data = elf_getdata(scn, NULL); + + scn = elf_getscn(elf, rela_dyn_shdr.sh_link); + if (!scn || !gelf_getshdr(scn, &shdr) || !shdr.sh_link) + return; + + di->dynsym_data = elf_getdata(scn, NULL); + di->dynstr_data = elf_getdata(elf_getscn(elf, shdr.sh_link), NULL); + + if (!di->plt_got_data || !di->dynstr_data || !di->dynsym_data || !di->rela_dyn_data) + return; + + /* Sort into offset order */ + sort_rela_dyn(di); +} + +/* Get instruction displacement from a plt entry for x86_64 */ +static u32 get_x86_64_plt_disp(const u8 *p) +{ + u8 endbr64[] = {0xf3, 0x0f, 0x1e, 0xfa}; + int n = 0; + + /* Skip endbr64 */ + if (!memcmp(p, endbr64, sizeof(endbr64))) + n += sizeof(endbr64); + /* Skip bnd prefix */ + if (p[n] == 0xf2) + n += 1; + /* jmp with 4-byte displacement */ + if (p[n] == 0xff && p[n + 1] == 0x25) { + n += 2; + /* Also add offset from start of entry to end of instruction */ + return n + 4 + le32toh(*(const u32 *)(p + n)); + } + return 0; +} + +static bool get_plt_got_name(GElf_Shdr *shdr, size_t i, + struct rela_dyn_info *di, + char *buf, size_t buf_sz) +{ + struct rela_dyn vi, *vr; + const char *sym_name; + char *demangled; + GElf_Sym sym; + u32 disp; + + if (!di->sorted) + return false; + + disp = get_x86_64_plt_disp(di->plt_got_data->d_buf + i); + if (!disp) + return false; + + /* Compute target offset of the .plt.got entry */ + vi.offset = shdr->sh_offset + di->plt_got_data->d_off + i + disp; + + /* Find that offset in .rela.dyn (sorted by offset) */ + vr = bsearch(&vi, di->sorted, di->nr_entries, sizeof(di->sorted[0]), cmp_offset); + if (!vr) + return false; + + /* Get the associated symbol */ + gelf_getsym(di->dynsym_data, vr->sym_idx, &sym); + sym_name = elf_sym__name(&sym, di->dynstr_data); + demangled = demangle_sym(di->dso, 0, sym_name); + if (demangled != NULL) + sym_name = demangled; + + snprintf(buf, buf_sz, "%s@plt", sym_name); + + free(demangled); + + return *sym_name; +} + +static int dso__synthesize_plt_got_symbols(struct dso *dso, Elf *elf, + GElf_Ehdr *ehdr, + char *buf, size_t buf_sz) +{ + struct rela_dyn_info di = { .dso = dso }; + struct symbol *sym; + GElf_Shdr shdr; + Elf_Scn *scn; + int err = -1; + size_t i; + + scn = elf_section_by_name(elf, ehdr, &shdr, ".plt.got", NULL); + if (!scn || !shdr.sh_entsize) + return 0; + + if (ehdr->e_machine == EM_X86_64) + get_rela_dyn_info(elf, ehdr, &di, scn); + + for (i = 0; i < shdr.sh_size; i += shdr.sh_entsize) { + if (!get_plt_got_name(&shdr, i, &di, buf, buf_sz)) + snprintf(buf, buf_sz, "offset_%#" PRIx64 "@plt", (u64)shdr.sh_offset + i); + sym = symbol__new(shdr.sh_offset + i, shdr.sh_entsize, STB_GLOBAL, STT_FUNC, buf); + if (!sym) + goto out; + symbols__insert(&dso->symbols, sym); + } + err = 0; +out: + exit_rela_dyn(&di); + return err; +} /* * We need to check if we have a .dynsym, so that we can handle the @@ -342,56 +652,104 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) */ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss) { - uint32_t nr_rel_entries, idx; + uint32_t idx; GElf_Sym sym; u64 plt_offset, plt_header_size, plt_entry_size; - GElf_Shdr shdr_plt; - struct symbol *f; + GElf_Shdr shdr_plt, plt_sec_shdr; + struct symbol *f, *plt_sym; GElf_Shdr shdr_rel_plt, shdr_dynsym; - Elf_Data *reldata, *syms, *symstrs; + Elf_Data *syms, *symstrs; Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym; - size_t dynsym_idx; GElf_Ehdr ehdr; char sympltname[1024]; Elf *elf; - int nr = 0, symidx, err = 0; - - if (!ss->dynsym) - return 0; + int nr = 0, err = -1; + struct rel_info ri = { .is_rela = false }; + bool lazy_plt; elf = ss->elf; ehdr = ss->ehdr; - scn_dynsym = ss->dynsym; - shdr_dynsym = ss->dynshdr; - dynsym_idx = ss->dynsym_idx; + if (!elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL)) + return 0; + + /* + * A symbol from a previous section (e.g. .init) can have been expanded + * by symbols__fixup_end() to overlap .plt. Truncate it before adding + * a symbol for .plt header. + */ + f = dso__find_symbol_nocache(dso, shdr_plt.sh_offset); + if (f && f->start < shdr_plt.sh_offset && f->end > shdr_plt.sh_offset) + f->end = shdr_plt.sh_offset; + + if (!get_plt_sizes(dso, &ehdr, &shdr_plt, &plt_header_size, &plt_entry_size)) + return 0; + + /* Add a symbol for .plt header */ + plt_sym = symbol__new(shdr_plt.sh_offset, plt_header_size, STB_GLOBAL, STT_FUNC, ".plt"); + if (!plt_sym) + goto out_elf_end; + symbols__insert(&dso->symbols, plt_sym); - if (scn_dynsym == NULL) + /* Only x86 has .plt.got */ + if (machine_is_x86(ehdr.e_machine) && + dso__synthesize_plt_got_symbols(dso, elf, &ehdr, sympltname, sizeof(sympltname))) goto out_elf_end; + /* Only x86 has .plt.sec */ + if (machine_is_x86(ehdr.e_machine) && + elf_section_by_name(elf, &ehdr, &plt_sec_shdr, ".plt.sec", NULL)) { + if (!get_plt_sizes(dso, &ehdr, &plt_sec_shdr, &plt_header_size, &plt_entry_size)) + return 0; + /* Extend .plt symbol to entire .plt */ + plt_sym->end = plt_sym->start + shdr_plt.sh_size; + /* Use .plt.sec offset */ + plt_offset = plt_sec_shdr.sh_offset; + lazy_plt = false; + } else { + plt_offset = shdr_plt.sh_offset; + lazy_plt = true; + } + scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, ".rela.plt", NULL); if (scn_plt_rel == NULL) { scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, ".rel.plt", NULL); if (scn_plt_rel == NULL) - goto out_elf_end; + return 0; } - err = -1; + if (shdr_rel_plt.sh_type != SHT_RELA && + shdr_rel_plt.sh_type != SHT_REL) + return 0; - if (shdr_rel_plt.sh_link != dynsym_idx) - goto out_elf_end; + if (!shdr_rel_plt.sh_link) + return 0; - if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL) + if (shdr_rel_plt.sh_link == ss->dynsym_idx) { + scn_dynsym = ss->dynsym; + shdr_dynsym = ss->dynshdr; + } else if (shdr_rel_plt.sh_link == ss->symtab_idx) { + /* + * A static executable can have a .plt due to IFUNCs, in which + * case .symtab is used not .dynsym. + */ + scn_dynsym = ss->symtab; + shdr_dynsym = ss->symshdr; + } else { goto out_elf_end; + } + + if (!scn_dynsym) + return 0; /* * Fetch the relocation section to find the idxes to the GOT * and the symbols in the .dynsym they refer to. */ - reldata = elf_getdata(scn_plt_rel, NULL); - if (reldata == NULL) + ri.reldata = elf_getdata(scn_plt_rel, NULL); + if (!ri.reldata) goto out_elf_end; syms = elf_getdata(scn_dynsym, NULL); @@ -409,93 +767,57 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss) if (symstrs->d_size == 0) goto out_elf_end; - nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; - plt_offset = shdr_plt.sh_offset; - switch (ehdr.e_machine) { - case EM_ARM: - plt_header_size = 20; - plt_entry_size = 12; - break; + ri.nr_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; - case EM_AARCH64: - plt_header_size = 32; - plt_entry_size = 16; - break; + ri.is_rela = shdr_rel_plt.sh_type == SHT_RELA; - case EM_SPARC: - plt_header_size = 48; - plt_entry_size = 12; - break; - - case EM_SPARCV9: - plt_header_size = 128; - plt_entry_size = 32; - break; - - default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */ - plt_header_size = shdr_plt.sh_entsize; - plt_entry_size = shdr_plt.sh_entsize; - break; + if (lazy_plt) { + /* + * Assume a .plt with the same number of entries as the number + * of relocation entries is not lazy and does not have a header. + */ + if (ri.nr_entries * plt_entry_size == shdr_plt.sh_size) + dso__delete_symbol(dso, plt_sym); + else + plt_offset += plt_header_size; } - plt_offset += plt_header_size; - - if (shdr_rel_plt.sh_type == SHT_RELA) { - GElf_Rela pos_mem, *pos; - elf_section__for_each_rela(reldata, pos, pos_mem, idx, - nr_rel_entries) { - const char *elf_name = NULL; - char *demangled = NULL; - symidx = GELF_R_SYM(pos->r_info); - gelf_getsym(syms, symidx, &sym); + /* + * x86 doesn't insert IFUNC relocations in .plt order, so sort to get + * back in order. + */ + if (machine_is_x86(ehdr.e_machine) && sort_rel(&ri)) + goto out_elf_end; - elf_name = elf_sym__name(&sym, symstrs); - demangled = demangle_sym(dso, 0, elf_name); - if (demangled != NULL) - elf_name = demangled; - snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_name); - free(demangled); + for (idx = 0; idx < ri.nr_entries; idx++) { + const char *elf_name = NULL; + char *demangled = NULL; - f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, STT_FUNC, sympltname); - if (!f) - goto out_elf_end; + gelf_getsym(syms, get_rel_symidx(&ri, idx), &sym); - plt_offset += plt_entry_size; - symbols__insert(&dso->symbols, f); - ++nr; - } - } else if (shdr_rel_plt.sh_type == SHT_REL) { - GElf_Rel pos_mem, *pos; - elf_section__for_each_rel(reldata, pos, pos_mem, idx, - nr_rel_entries) { - const char *elf_name = NULL; - char *demangled = NULL; - symidx = GELF_R_SYM(pos->r_info); - gelf_getsym(syms, symidx, &sym); - - elf_name = elf_sym__name(&sym, symstrs); - demangled = demangle_sym(dso, 0, elf_name); - if (demangled != NULL) - elf_name = demangled; + elf_name = elf_sym__name(&sym, symstrs); + demangled = demangle_sym(dso, 0, elf_name); + if (demangled) + elf_name = demangled; + if (*elf_name) + snprintf(sympltname, sizeof(sympltname), "%s@plt", elf_name); + else if (!get_ifunc_name(elf, dso, &ehdr, &ri, sympltname, sizeof(sympltname))) snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_name); - free(demangled); + "offset_%#" PRIx64 "@plt", plt_offset); + free(demangled); - f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, STT_FUNC, sympltname); - if (!f) - goto out_elf_end; + f = symbol__new(plt_offset, plt_entry_size, STB_GLOBAL, STT_FUNC, sympltname); + if (!f) + goto out_elf_end; - plt_offset += plt_entry_size; - symbols__insert(&dso->symbols, f); - ++nr; - } + plt_offset += plt_entry_size; + symbols__insert(&dso->symbols, f); + ++nr; } err = 0; out_elf_end: + exit_rel(&ri); if (err == 0) return nr; pr_debug("%s: problems reading %s PLT info.\n", @@ -946,8 +1268,9 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + ss->symtab_idx = 0; ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", - NULL); + &ss->symtab_idx); if (ss->symshdr.sh_type != SHT_SYMTAB) ss->symtab = NULL; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a3a165ae933a..317c0706852f 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -201,10 +201,14 @@ again: continue; if (choose_best_symbol(curr, next) == SYMBOL_A) { + if (next->type == STT_GNU_IFUNC) + curr->ifunc_alias = true; rb_erase_cached(&next->rb_node, symbols); symbol__delete(next); goto again; } else { + if (curr->type == STT_GNU_IFUNC) + next->ifunc_alias = true; nd = rb_next(&curr->rb_node); rb_erase_cached(&curr->rb_node, symbols); symbol__delete(curr); @@ -556,6 +560,11 @@ struct symbol *dso__find_symbol(struct dso *dso, u64 addr) return dso->last_find_result.symbol; } +struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr) +{ + return symbols__find(&dso->symbols, addr); +} + struct symbol *dso__first_symbol(struct dso *dso) { return symbols__first(&dso->symbols); @@ -1368,10 +1377,23 @@ static int dso__load_kcore(struct dso *dso, struct map *map, /* Find the kernel map using the '_stext' symbol */ if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) { + u64 replacement_size = 0; + list_for_each_entry(new_map, &md.maps, node) { - if (stext >= new_map->start && stext < new_map->end) { + u64 new_size = new_map->end - new_map->start; + + if (!(stext >= new_map->start && stext < new_map->end)) + continue; + + /* + * On some architectures, ARM64 for example, the kernel + * text can get allocated inside of the vmalloc segment. + * Select the smallest matching segment, in case stext + * falls within more than one in the list. + */ + if (!replacement_map || new_size < replacement_size) { replacement_map = new_map; - break; + replacement_size = new_size; } } } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index f735108c4d4e..7558735543c2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -64,6 +64,8 @@ struct symbol { u8 inlined:1; /** Has symbol__annotate2 been performed. */ u8 annotate2:1; + /** Symbol is an alias of an STT_GNU_IFUNC */ + u8 ifunc_alias:1; /** Architecture specific. Unused except on PPC where it holds st_other. */ u8 arch_sym; /** The name of length namelen associated with the symbol. */ @@ -148,6 +150,7 @@ void dso__delete_symbol(struct dso *dso, struct symbol *sym); struct symbol *dso__find_symbol(struct dso *dso, u64 addr); +struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name); struct symbol *symbol__next_by_name(struct symbol *sym); diff --git a/tools/perf/util/symsrc.h b/tools/perf/util/symsrc.h index 2665b4bde751..edf82028c9e6 100644 --- a/tools/perf/util/symsrc.h +++ b/tools/perf/util/symsrc.h @@ -26,6 +26,7 @@ struct symsrc { GElf_Shdr opdshdr; Elf_Scn *symtab; + size_t symtab_idx; GElf_Shdr symshdr; Elf_Scn *dynsym; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 3ab6a92b1a6d..9ab9308ee80c 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2219,8 +2219,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 len = pos->long_name_len + 1; len = PERF_ALIGN(len, NAME_ALIGN); - memcpy(&ev.build_id.build_id, pos->bid.data, sizeof(pos->bid.data)); - ev.build_id.size = pos->bid.size; + ev.build_id.size = min(pos->bid.size, sizeof(pos->bid.data)); + memcpy(&ev.build_id.build_id, pos->bid.data, ev.build_id.size); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc | PERF_RECORD_MISC_BUILD_ID_SIZE; ev.build_id.pid = machine->pid; diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 9b3cd79cca12..a0cff184b1cd 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -21,6 +21,9 @@ struct trace_event { struct tep_plugin_list *plugin_list; }; +/* Computes a version number comparable with LIBTRACEEVENT_VERSION from Makefile.config. */ +#define MAKE_LIBTRACEEVENT_VERSION(a, b, c) ((a)*255*255+(b)*255+(c)) + typedef char *(tep_func_resolver_t)(void *priv, unsigned long long *addrp, char **modp); @@ -137,4 +140,20 @@ int common_lock_depth(struct scripting_context *context); #define SAMPLE_FLAGS_BUF_SIZE 64 int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz); +#if defined(LIBTRACEEVENT_VERSION) && LIBTRACEEVENT_VERSION >= MAKE_LIBTRACEEVENT_VERSION(1, 5, 0) +#include <traceevent/event-parse.h> + +static inline bool tep_field_is_relative(unsigned long flags) +{ + return (flags & TEP_FIELD_IS_RELATIVE) != 0; +} +#else +#include <linux/compiler.h> + +static inline bool tep_field_is_relative(unsigned long flags __maybe_unused) +{ + return false; +} +#endif + #endif /* _PERF_UTIL_TRACE_EVENT_H */ diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 0c6c7f456887..1c72d07cb9fe 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -5,7 +5,7 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) + -e s/riscv.*/riscv/ -e s/loongarch.*/loongarch/) ifndef ARCH ARCH := $(HOSTARCH) @@ -34,6 +34,15 @@ ifeq ($(ARCH),sh64) SRCARCH := sh endif +# Additional ARCH settings for loongarch +ifeq ($(ARCH),loongarch32) + SRCARCH := loongarch +endif + +ifeq ($(ARCH),loongarch64) + SRCARCH := loongarch +endif + LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) IS_64_BIT := 1 diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 0805f08af8b3..fba7bec96acd 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -10,6 +10,7 @@ ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready ldflags-y += --wrap=cxl_hdm_decode_init +ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=cxl_rcrb_to_component DRIVERS := ../../../drivers @@ -17,28 +18,34 @@ CXL_SRC := $(DRIVERS)/cxl CXL_CORE_SRC := $(DRIVERS)/cxl/core ccflags-y := -I$(srctree)/drivers/cxl/ ccflags-y += -D__mock=__weak +ccflags-y += -DTRACE_INCLUDE_PATH=$(CXL_CORE_SRC) -I$(srctree)/drivers/cxl/core/ obj-m += cxl_acpi.o cxl_acpi-y := $(CXL_SRC)/acpi.o cxl_acpi-y += mock_acpi.o cxl_acpi-y += config_check.o +cxl_acpi-y += cxl_acpi_test.o obj-m += cxl_pmem.o cxl_pmem-y := $(CXL_SRC)/pmem.o cxl_pmem-y += $(CXL_SRC)/security.o cxl_pmem-y += config_check.o +cxl_pmem-y += cxl_pmem_test.o obj-m += cxl_port.o cxl_port-y := $(CXL_SRC)/port.o cxl_port-y += config_check.o +cxl_port-y += cxl_port_test.o + obj-m += cxl_mem.o cxl_mem-y := $(CXL_SRC)/mem.o cxl_mem-y += config_check.o +cxl_mem-y += cxl_mem_test.o obj-m += cxl_core.o @@ -49,7 +56,9 @@ cxl_core-y += $(CXL_CORE_SRC)/memdev.o cxl_core-y += $(CXL_CORE_SRC)/mbox.o cxl_core-y += $(CXL_CORE_SRC)/pci.o cxl_core-y += $(CXL_CORE_SRC)/hdm.o +cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o cxl_core-y += config_check.o +cxl_core-y += cxl_core_test.o obj-m += test/ diff --git a/tools/testing/cxl/config_check.c b/tools/testing/cxl/config_check.c index c4c457e59841..99b56b5f6edf 100644 --- a/tools/testing/cxl/config_check.c +++ b/tools/testing/cxl/config_check.c @@ -7,6 +7,7 @@ void check(void) * These kconfig symbols must be set to "m" for cxl_test to load * and operate. */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_64BIT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_BUS)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_ACPI)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM)); diff --git a/tools/testing/cxl/cxl_acpi_test.c b/tools/testing/cxl/cxl_acpi_test.c new file mode 100644 index 000000000000..8602dc27c81c --- /dev/null +++ b/tools/testing/cxl/cxl_acpi_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_acpi); diff --git a/tools/testing/cxl/cxl_core_test.c b/tools/testing/cxl/cxl_core_test.c new file mode 100644 index 000000000000..464a9255e4d6 --- /dev/null +++ b/tools/testing/cxl/cxl_core_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_core); diff --git a/tools/testing/cxl/cxl_mem_test.c b/tools/testing/cxl/cxl_mem_test.c new file mode 100644 index 000000000000..ba7fb8a44288 --- /dev/null +++ b/tools/testing/cxl/cxl_mem_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_mem); diff --git a/tools/testing/cxl/cxl_pmem_test.c b/tools/testing/cxl/cxl_pmem_test.c new file mode 100644 index 000000000000..3fd884fae537 --- /dev/null +++ b/tools/testing/cxl/cxl_pmem_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_pmem); diff --git a/tools/testing/cxl/cxl_port_test.c b/tools/testing/cxl/cxl_port_test.c new file mode 100644 index 000000000000..be183917a9f6 --- /dev/null +++ b/tools/testing/cxl/cxl_port_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_port); diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild index 4e59e2c911f6..61d5f7bcddf9 100644 --- a/tools/testing/cxl/test/Kbuild +++ b/tools/testing/cxl/test/Kbuild @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := -I$(srctree)/drivers/cxl/ +ccflags-y := -I$(srctree)/drivers/cxl/ -I$(srctree)/drivers/cxl/core obj-m += cxl_test.o obj-m += cxl_mock.o diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 30ee680d38ff..bf00dc52fe96 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -9,6 +9,8 @@ #include <linux/pci.h> #include <linux/mm.h> #include <cxlmem.h> + +#include "../watermark.h" #include "mock.h" static int interleave_arithmetic; @@ -618,7 +620,8 @@ static struct acpi_pci_root *mock_acpi_pci_find_root(acpi_handle handle) return &mock_pci_root[host_bridge_index(adev)]; } -static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port) +static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) { struct cxl_hdm *cxlhdm = devm_kzalloc(&port->dev, sizeof(*cxlhdm), GFP_KERNEL); @@ -701,7 +704,144 @@ static int mock_decoder_reset(struct cxl_decoder *cxld) return 0; } -static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +static void default_mock_decoder(struct cxl_decoder *cxld) +{ + cxld->hpa_range = (struct range){ + .start = 0, + .end = -1, + }; + + cxld->interleave_ways = 1; + cxld->interleave_granularity = 256; + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->commit = mock_decoder_commit; + cxld->reset = mock_decoder_reset; +} + +static int first_decoder(struct device *dev, void *data) +{ + struct cxl_decoder *cxld; + + if (!is_switch_decoder(dev)) + return 0; + cxld = to_cxl_decoder(dev); + if (cxld->id == 0) + return 1; + return 0; +} + +static void mock_init_hdm_decoder(struct cxl_decoder *cxld) +{ + struct acpi_cedt_cfmws *window = mock_cfmws[0]; + struct platform_device *pdev = NULL; + struct cxl_endpoint_decoder *cxled; + struct cxl_switch_decoder *cxlsd; + struct cxl_port *port, *iter; + const int size = SZ_512M; + struct cxl_memdev *cxlmd; + struct cxl_dport *dport; + struct device *dev; + bool hb0 = false; + u64 base; + int i; + + if (is_endpoint_decoder(&cxld->dev)) { + cxled = to_cxl_endpoint_decoder(&cxld->dev); + cxlmd = cxled_to_memdev(cxled); + WARN_ON(!dev_is_platform(cxlmd->dev.parent)); + pdev = to_platform_device(cxlmd->dev.parent); + + /* check is endpoint is attach to host-bridge0 */ + port = cxled_to_port(cxled); + do { + if (port->uport == &cxl_host_bridge[0]->dev) { + hb0 = true; + break; + } + if (is_cxl_port(port->dev.parent)) + port = to_cxl_port(port->dev.parent); + else + port = NULL; + } while (port); + port = cxled_to_port(cxled); + } + + /* + * The first decoder on the first 2 devices on the first switch + * attached to host-bridge0 mock a fake / static RAM region. All + * other decoders are default disabled. Given the round robin + * assignment those devices are named cxl_mem.0, and cxl_mem.4. + * + * See 'cxl list -BMPu -m cxl_mem.0,cxl_mem.4' + */ + if (!hb0 || pdev->id % 4 || pdev->id > 4 || cxld->id > 0) { + default_mock_decoder(cxld); + return; + } + + base = window->base_hpa; + cxld->hpa_range = (struct range) { + .start = base, + .end = base + size - 1, + }; + + cxld->interleave_ways = 2; + eig_to_granularity(window->granularity, &cxld->interleave_granularity); + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->flags = CXL_DECODER_F_ENABLE; + cxled->state = CXL_DECODER_STATE_AUTO; + port->commit_end = cxld->id; + devm_cxl_dpa_reserve(cxled, 0, size / cxld->interleave_ways, 0); + cxld->commit = mock_decoder_commit; + cxld->reset = mock_decoder_reset; + + /* + * Now that endpoint decoder is set up, walk up the hierarchy + * and setup the switch and root port decoders targeting @cxlmd. + */ + iter = port; + for (i = 0; i < 2; i++) { + dport = iter->parent_dport; + iter = dport->port; + dev = device_find_child(&iter->dev, NULL, first_decoder); + /* + * Ancestor ports are guaranteed to be enumerated before + * @port, and all ports have at least one decoder. + */ + if (WARN_ON(!dev)) + continue; + cxlsd = to_cxl_switch_decoder(dev); + if (i == 0) { + /* put cxl_mem.4 second in the decode order */ + if (pdev->id == 4) + cxlsd->target[1] = dport; + else + cxlsd->target[0] = dport; + } else + cxlsd->target[0] = dport; + cxld = &cxlsd->cxld; + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->flags = CXL_DECODER_F_ENABLE; + iter->commit_end = 0; + /* + * Switch targets 2 endpoints, while host bridge targets + * one root port + */ + if (i == 0) + cxld->interleave_ways = 2; + else + cxld->interleave_ways = 1; + cxld->interleave_granularity = 256; + cxld->hpa_range = (struct range) { + .start = base, + .end = base + size - 1, + }; + put_device(dev); + } +} + +static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { struct cxl_port *port = cxlhdm->port; struct cxl_port *parent_port = to_cxl_port(port->dev.parent); @@ -746,16 +886,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) cxld = &cxled->cxld; } - cxld->hpa_range = (struct range) { - .start = 0, - .end = -1, - }; - - cxld->interleave_ways = min_not_zero(target_count, 1); - cxld->interleave_granularity = SZ_4K; - cxld->target_type = CXL_DECODER_EXPANDER; - cxld->commit = mock_decoder_commit; - cxld->reset = mock_decoder_reset; + mock_init_hdm_decoder(cxld); if (target_count) { rc = device_for_each_child(port->uport, &ctx, @@ -1119,6 +1250,12 @@ static __init int cxl_test_init(void) { int rc, i; + cxl_acpi_test(); + cxl_core_test(); + cxl_mem_test(); + cxl_pmem_test(); + cxl_port_test(); + register_cxl_mock_ops(&cxl_mock_ops); cxl_mock_pool = gen_pool_create(ilog2(SZ_2M), NUMA_NO_NODE); @@ -1135,11 +1272,9 @@ static __init int cxl_test_init(void) if (interleave_arithmetic == 1) { cfmws_start = CFMWS_XOR_ARRAY_START; cfmws_end = CFMWS_XOR_ARRAY_END; - dev_dbg(NULL, "cxl_test loading xor math option\n"); } else { cfmws_start = CFMWS_MOD_ARRAY_START; cfmws_end = CFMWS_MOD_ARRAY_END; - dev_dbg(NULL, "cxl_test loading modulo math option\n"); } rc = populate_cedt(); @@ -1326,7 +1461,7 @@ static __exit void cxl_test_exit(void) unregister_cxl_mock_ops(&cxl_mock_ops); } -module_param(interleave_arithmetic, int, 0000); +module_param(interleave_arithmetic, int, 0444); MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1"); module_init(cxl_test_init); module_exit(cxl_test_exit); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 5e4ecd93f1d2..9263b04d35f7 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -9,6 +9,8 @@ #include <linux/bits.h> #include <cxlmem.h> +#include "trace.h" + #define LSA_SIZE SZ_128K #define DEV_SIZE SZ_2G #define EFFECT(x) (1U << x) @@ -67,6 +69,26 @@ static struct { #define PASS_TRY_LIMIT 3 +#define CXL_TEST_EVENT_CNT_MAX 15 + +/* Set a number of events to return at a time for simulation. */ +#define CXL_TEST_EVENT_CNT 3 + +struct mock_event_log { + u16 clear_idx; + u16 cur_idx; + u16 nr_events; + u16 nr_overflow; + u16 overflow_reset; + struct cxl_event_record_raw *events[CXL_TEST_EVENT_CNT_MAX]; +}; + +struct mock_event_store { + struct cxl_dev_state *cxlds; + struct mock_event_log mock_logs[CXL_EVENT_TYPE_MAX]; + u32 ev_status; +}; + struct cxl_mockmem_data { void *lsa; u32 security_state; @@ -74,9 +96,317 @@ struct cxl_mockmem_data { u8 master_pass[NVDIMM_PASSPHRASE_LEN]; int user_limit; int master_limit; + struct mock_event_store mes; + u8 event_buf[SZ_4K]; +}; + +static struct mock_event_log *event_find_log(struct device *dev, int log_type) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + + if (log_type >= CXL_EVENT_TYPE_MAX) + return NULL; + return &mdata->mes.mock_logs[log_type]; +} +static struct cxl_event_record_raw *event_get_current(struct mock_event_log *log) +{ + return log->events[log->cur_idx]; +} + +static void event_reset_log(struct mock_event_log *log) +{ + log->cur_idx = 0; + log->clear_idx = 0; + log->nr_overflow = log->overflow_reset; +} + +/* Handle can never be 0 use 1 based indexing for handle */ +static u16 event_get_clear_handle(struct mock_event_log *log) +{ + return log->clear_idx + 1; +} + +/* Handle can never be 0 use 1 based indexing for handle */ +static __le16 event_get_cur_event_handle(struct mock_event_log *log) +{ + u16 cur_handle = log->cur_idx + 1; + + return cpu_to_le16(cur_handle); +} + +static bool event_log_empty(struct mock_event_log *log) +{ + return log->cur_idx == log->nr_events; +} + +static void mes_add_event(struct mock_event_store *mes, + enum cxl_event_log_type log_type, + struct cxl_event_record_raw *event) +{ + struct mock_event_log *log; + + if (WARN_ON(log_type >= CXL_EVENT_TYPE_MAX)) + return; + + log = &mes->mock_logs[log_type]; + + if ((log->nr_events + 1) > CXL_TEST_EVENT_CNT_MAX) { + log->nr_overflow++; + log->overflow_reset = log->nr_overflow; + return; + } + + log->events[log->nr_events] = event; + log->nr_events++; +} + +static int mock_get_event(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_get_event_payload *pl; + struct mock_event_log *log; + u16 nr_overflow; + u8 log_type; + int i; + + if (cmd->size_in != sizeof(log_type)) + return -EINVAL; + + if (cmd->size_out < struct_size(pl, records, CXL_TEST_EVENT_CNT)) + return -EINVAL; + + log_type = *((u8 *)cmd->payload_in); + if (log_type >= CXL_EVENT_TYPE_MAX) + return -EINVAL; + + memset(cmd->payload_out, 0, cmd->size_out); + + log = event_find_log(cxlds->dev, log_type); + if (!log || event_log_empty(log)) + return 0; + + pl = cmd->payload_out; + + for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) { + memcpy(&pl->records[i], event_get_current(log), + sizeof(pl->records[i])); + pl->records[i].hdr.handle = event_get_cur_event_handle(log); + log->cur_idx++; + } + + pl->record_count = cpu_to_le16(i); + if (!event_log_empty(log)) + pl->flags |= CXL_GET_EVENT_FLAG_MORE_RECORDS; + + if (log->nr_overflow) { + u64 ns; + + pl->flags |= CXL_GET_EVENT_FLAG_OVERFLOW; + pl->overflow_err_count = cpu_to_le16(nr_overflow); + ns = ktime_get_real_ns(); + ns -= 5000000000; /* 5s ago */ + pl->first_overflow_timestamp = cpu_to_le64(ns); + ns = ktime_get_real_ns(); + ns -= 1000000000; /* 1s ago */ + pl->last_overflow_timestamp = cpu_to_le64(ns); + } + + return 0; +} + +static int mock_clear_event(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_clear_event_payload *pl = cmd->payload_in; + struct mock_event_log *log; + u8 log_type = pl->event_log; + u16 handle; + int nr; + + if (log_type >= CXL_EVENT_TYPE_MAX) + return -EINVAL; + + log = event_find_log(cxlds->dev, log_type); + if (!log) + return 0; /* No mock data in this log */ + + /* + * This check is technically not invalid per the specification AFAICS. + * (The host could 'guess' handles and clear them in order). + * However, this is not good behavior for the host so test it. + */ + if (log->clear_idx + pl->nr_recs > log->cur_idx) { + dev_err(cxlds->dev, + "Attempting to clear more events than returned!\n"); + return -EINVAL; + } + + /* Check handle order prior to clearing events */ + for (nr = 0, handle = event_get_clear_handle(log); + nr < pl->nr_recs; + nr++, handle++) { + if (handle != le16_to_cpu(pl->handles[nr])) { + dev_err(cxlds->dev, "Clearing events out of order\n"); + return -EINVAL; + } + } + + if (log->nr_overflow) + log->nr_overflow = 0; + + /* Clear events */ + log->clear_idx += pl->nr_recs; + return 0; +} + +static void cxl_mock_event_trigger(struct device *dev) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + struct mock_event_store *mes = &mdata->mes; + int i; + + for (i = CXL_EVENT_TYPE_INFO; i < CXL_EVENT_TYPE_MAX; i++) { + struct mock_event_log *log; + + log = event_find_log(dev, i); + if (log) + event_reset_log(log); + } + + cxl_mem_get_event_records(mes->cxlds, mes->ev_status); +} + +struct cxl_event_record_raw maint_needed = { + .hdr = { + .id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xa5b6), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, +}; + +struct cxl_event_record_raw hardware_replace = { + .hdr = { + .id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xb6a5), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, +}; + +struct cxl_event_gen_media gen_media = { + .hdr = { + .id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6), + .length = sizeof(struct cxl_event_gen_media), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x2000), + .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, + .transaction_type = CXL_GMER_TRANS_HOST_WRITE, + /* .validity_flags = <set below> */ + .channel = 1, + .rank = 30 +}; + +struct cxl_event_dram dram = { + .hdr = { + .id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24), + .length = sizeof(struct cxl_event_dram), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x8000), + .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, + .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, + /* .validity_flags = <set below> */ + .channel = 1, + .bank_group = 5, + .bank = 2, + .column = {0xDE, 0xAD}, }; +struct cxl_event_mem_module mem_module = { + .hdr = { + .id = UUID_INIT(0xfe927475, 0xdd59, 0x4339, + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74), + .length = sizeof(struct cxl_event_mem_module), + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .event_type = CXL_MMER_TEMP_CHANGE, + .info = { + .health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED, + .media_status = CXL_DHI_MS_ALL_DATA_LOST, + .add_status = (CXL_DHI_AS_CRITICAL << 2) | + (CXL_DHI_AS_WARNING << 4) | + (CXL_DHI_AS_WARNING << 5), + .device_temp = { 0xDE, 0xAD}, + .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + } +}; + +static void cxl_mock_add_event_logs(struct mock_event_store *mes) +{ + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + &gen_media.validity_flags); + + put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + &dram.validity_flags); + + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, + (struct cxl_event_record_raw *)&gen_media); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, + (struct cxl_event_record_raw *)&mem_module); + mes->ev_status |= CXLDEV_EVENT_STATUS_INFO; + + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &maint_needed); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&dram); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&gen_media); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&mem_module); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&dram); + /* Overflow this log */ + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes->ev_status |= CXLDEV_EVENT_STATUS_FAIL; + + mes_add_event(mes, CXL_EVENT_TYPE_FATAL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FATAL, + (struct cxl_event_record_raw *)&dram); + mes->ev_status |= CXLDEV_EVENT_STATUS_FATAL; +} + static int mock_gsl(struct cxl_mbox_cmd *cmd) { if (cmd->size_out < sizeof(mock_gsl_payload)) @@ -582,6 +912,12 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_GET_PARTITION_INFO: rc = mock_partition_info(cxlds, cmd); break; + case CXL_MBOX_OP_GET_EVENT_RECORD: + rc = mock_get_event(cxlds, cmd); + break; + case CXL_MBOX_OP_CLEAR_EVENT_RECORD: + rc = mock_clear_event(cxlds, cmd); + break; case CXL_MBOX_OP_SET_LSA: rc = mock_set_lsa(cxlds, cmd); break; @@ -628,6 +964,15 @@ static bool is_rcd(struct platform_device *pdev) return !!id->driver_data; } +static ssize_t event_trigger_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + cxl_mock_event_trigger(dev); + return count; +} +static DEVICE_ATTR_WO(event_trigger); + static int cxl_mock_mem_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -655,6 +1000,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) cxlds->serial = pdev->id; cxlds->mbox_send = cxl_mock_mbox_send; cxlds->payload_size = SZ_4K; + cxlds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf; if (is_rcd(pdev)) { cxlds->rcd = true; cxlds->component_reg_phys = CXL_RESOURCE_NONE; @@ -672,10 +1018,15 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + mdata->mes.cxlds = cxlds; + cxl_mock_add_event_logs(&mdata->mes); + cxlmd = devm_cxl_add_memdev(cxlds); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); + cxl_mem_get_event_records(cxlds, CXLDEV_EVENT_STATUS_ALL); + return 0; } @@ -714,6 +1065,7 @@ static DEVICE_ATTR_RW(security_lock); static struct attribute *cxl_mock_mem_attrs[] = { &dev_attr_security_lock.attr, + &dev_attr_event_trigger.attr, NULL }; ATTRIBUTE_GROUPS(cxl_mock_mem); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 5dface08e0de..c4e53f22e421 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -131,16 +131,18 @@ __wrap_nvdimm_bus_register(struct device *dev, } EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register); -struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port) +struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) + { int index; struct cxl_hdm *cxlhdm; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport)) - cxlhdm = ops->devm_cxl_setup_hdm(port); + cxlhdm = ops->devm_cxl_setup_hdm(port, info); else - cxlhdm = devm_cxl_setup_hdm(port); + cxlhdm = devm_cxl_setup_hdm(port, info); put_cxl_mock_ops(index); return cxlhdm; @@ -162,16 +164,17 @@ int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, CXL); -int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { int rc, index; struct cxl_port *port = cxlhdm->port; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport)) - rc = ops->devm_cxl_enumerate_decoders(cxlhdm); + rc = ops->devm_cxl_enumerate_decoders(cxlhdm, info); else - rc = devm_cxl_enumerate_decoders(cxlhdm); + rc = devm_cxl_enumerate_decoders(cxlhdm, info); put_cxl_mock_ops(index); return rc; @@ -209,7 +212,8 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds) EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, CXL); int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, - struct cxl_hdm *cxlhdm) + struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); @@ -217,13 +221,29 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_hdm_decode_init(cxlds, cxlhdm); + rc = cxl_hdm_decode_init(cxlds, cxlhdm, info); put_cxl_mock_ops(index); return rc; } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL); +int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, + struct cxl_endpoint_dvsec_info *info) +{ + int rc = 0, index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_dev(dev)) + rc = 0; + else + rc = cxl_dvsec_rr_decode(dev, dvsec, info); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, CXL); + resource_size_t __wrap_cxl_rcrb_to_component(struct device *dev, resource_size_t rcrb, enum cxl_rcrb which) diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h index ef33f159375e..bef8817b01f2 100644 --- a/tools/testing/cxl/test/mock.h +++ b/tools/testing/cxl/test/mock.h @@ -23,9 +23,11 @@ struct cxl_mock_ops { bool (*is_mock_port)(struct device *dev); bool (*is_mock_dev)(struct device *dev); int (*devm_cxl_port_enumerate_dports)(struct cxl_port *port); - struct cxl_hdm *(*devm_cxl_setup_hdm)(struct cxl_port *port); + struct cxl_hdm *(*devm_cxl_setup_hdm)( + struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port); - int (*devm_cxl_enumerate_decoders)(struct cxl_hdm *hdm); + int (*devm_cxl_enumerate_decoders)( + struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info); }; void register_cxl_mock_ops(struct cxl_mock_ops *ops); diff --git a/tools/testing/cxl/watermark.h b/tools/testing/cxl/watermark.h new file mode 100644 index 000000000000..9d81d4a5f6be --- /dev/null +++ b/tools/testing/cxl/watermark.h @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#ifndef _TEST_CXL_WATERMARK_H_ +#define _TEST_CXL_WATERMARK_H_ +#include <linux/module.h> +#include <linux/printk.h> + +int cxl_acpi_test(void); +int cxl_core_test(void); +int cxl_mem_test(void); +int cxl_pmem_test(void); +int cxl_port_test(void); + +/* + * dummy routine for cxl_test to validate it is linking to the properly + * mocked module and not the standard one from the base tree. + */ +#define cxl_test_watermark(x) \ +int x##_test(void) \ +{ \ + pr_debug("%s for cxl_test\n", KBUILD_MODNAME); \ + return 0; \ +} \ +EXPORT_SYMBOL(x##_test) +#endif /* _TEST_CXL_WATERMARK_H_ */ diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index ac59999ed3de..829f5bdfd2e4 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -178,6 +178,7 @@ my $store_failures; my $store_successes; my $test_name; my $timeout; +my $run_timeout; my $connect_timeout; my $config_bisect_exec; my $booted_timeout; @@ -340,6 +341,7 @@ my %option_map = ( "STORE_SUCCESSES" => \$store_successes, "TEST_NAME" => \$test_name, "TIMEOUT" => \$timeout, + "RUN_TIMEOUT" => \$run_timeout, "CONNECT_TIMEOUT" => \$connect_timeout, "CONFIG_BISECT_EXEC" => \$config_bisect_exec, "BOOTED_TIMEOUT" => \$booted_timeout, @@ -1495,7 +1497,8 @@ sub reboot { # Still need to wait for the reboot to finish wait_for_monitor($time, $reboot_success_line); - + } + if ($powercycle || $time) { end_monitor; } } @@ -1535,6 +1538,11 @@ sub dodie { return if ($in_die); $in_die = 1; + if ($monitor_cnt) { + # restore terminal settings + system("stty $stty_orig"); + } + my $i = $iteration; doprint "CRITICAL FAILURE... [TEST $i] ", @_, "\n"; @@ -1581,11 +1589,6 @@ sub dodie { "Your test started at $script_start_time has failed with:\n@_\n", $log_file); } - if ($monitor_cnt) { - # restore terminal settings - system("stty $stty_orig"); - } - if (defined($post_test)) { run_command $post_test; } @@ -1857,6 +1860,14 @@ sub run_command { $command =~ s/\$SSH_USER/$ssh_user/g; $command =~ s/\$MACHINE/$machine/g; + if (!defined($timeout)) { + $timeout = $run_timeout; + } + + if (!defined($timeout)) { + $timeout = -1; # tell wait_for_input to wait indefinitely + } + doprint("$command ... "); $start_time = time; @@ -1883,13 +1894,10 @@ sub run_command { while (1) { my $fp = \*CMD; - if (defined($timeout)) { - doprint "timeout = $timeout\n"; - } my $line = wait_for_input($fp, $timeout); if (!defined($line)) { my $now = time; - if (defined($timeout) && (($now - $start_time) >= $timeout)) { + if ($timeout >= 0 && (($now - $start_time) >= $timeout)) { doprint "Hit timeout of $timeout, killing process\n"; $hit_timeout = 1; kill 9, $pid; @@ -2061,6 +2069,11 @@ sub wait_for_input { $time = $timeout; } + if ($time < 0) { + # Negative number means wait indefinitely + undef $time; + } + $rin = ''; vec($rin, fileno($fp), 1) = 1; vec($rin, fileno(\*STDIN), 1) = 1; @@ -4200,6 +4213,9 @@ sub send_email { } sub cancel_test { + if ($monitor_cnt) { + end_monitor; + } if ($email_when_canceled) { my $name = get_test_name; send_email("KTEST: Your [$name] test was cancelled", diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index 2d0fe15a096d..f43477a9b857 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -817,6 +817,11 @@ # is issued instead of a reboot. # CONNECT_TIMEOUT = 25 +# The timeout in seconds for how long to wait for any running command +# to timeout. If not defined, it will let it go indefinitely. +# (default undefined) +#RUN_TIMEOUT = 600 + # In between tests, a reboot of the box may occur, and this # is the time to wait for the console after it stops producing # output. Some machines may not produce a large lag on reboot diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 43fbe96318fe..741f15420467 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -77,11 +77,8 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, config_start = time.time() success = linux.build_reconfig(request.build_dir, request.make_options) config_end = time.time() - if not success: - return KunitResult(KunitStatus.CONFIG_FAILURE, - config_end - config_start) - return KunitResult(KunitStatus.SUCCESS, - config_end - config_start) + status = KunitStatus.SUCCESS if success else KunitStatus.CONFIG_FAILURE + return KunitResult(status, config_end - config_start) def build_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitBuildRequest) -> KunitResult: @@ -92,14 +89,8 @@ def build_tests(linux: kunit_kernel.LinuxSourceTree, request.build_dir, request.make_options) build_end = time.time() - if not success: - return KunitResult(KunitStatus.BUILD_FAILURE, - build_end - build_start) - if not success: - return KunitResult(KunitStatus.BUILD_FAILURE, - build_end - build_start) - return KunitResult(KunitStatus.SUCCESS, - build_end - build_start) + status = KunitStatus.SUCCESS if success else KunitStatus.BUILD_FAILURE + return KunitResult(status, build_end - build_start) def config_and_build_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitBuildRequest) -> KunitResult: @@ -145,7 +136,7 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - tests = _list_tests(linux, request) if request.run_isolated == 'test': filter_globs = tests - if request.run_isolated == 'suite': + elif request.run_isolated == 'suite': filter_globs = _suites_from_test_list(tests) # Apply the test-part of the user's glob, if present. if '.' in request.filter_glob: @@ -395,6 +386,95 @@ def tree_from_args(cli_args: argparse.Namespace) -> kunit_kernel.LinuxSourceTree extra_qemu_args=qemu_args) +def run_handler(cli_args): + if not os.path.exists(cli_args.build_dir): + os.mkdir(cli_args.build_dir) + + linux = tree_from_args(cli_args) + request = KunitRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options, + jobs=cli_args.jobs, + raw_output=cli_args.raw_output, + json=cli_args.json, + timeout=cli_args.timeout, + filter_glob=cli_args.filter_glob, + kernel_args=cli_args.kernel_args, + run_isolated=cli_args.run_isolated) + result = run_tests(linux, request) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + + +def config_handler(cli_args): + if cli_args.build_dir and ( + not os.path.exists(cli_args.build_dir)): + os.mkdir(cli_args.build_dir) + + linux = tree_from_args(cli_args) + request = KunitConfigRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options) + result = config_tests(linux, request) + stdout.print_with_timestamp(( + 'Elapsed time: %.3fs\n') % ( + result.elapsed_time)) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + + +def build_handler(cli_args): + linux = tree_from_args(cli_args) + request = KunitBuildRequest(build_dir=cli_args.build_dir, + make_options=cli_args.make_options, + jobs=cli_args.jobs) + result = config_and_build_tests(linux, request) + stdout.print_with_timestamp(( + 'Elapsed time: %.3fs\n') % ( + result.elapsed_time)) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + + +def exec_handler(cli_args): + linux = tree_from_args(cli_args) + exec_request = KunitExecRequest(raw_output=cli_args.raw_output, + build_dir=cli_args.build_dir, + json=cli_args.json, + timeout=cli_args.timeout, + filter_glob=cli_args.filter_glob, + kernel_args=cli_args.kernel_args, + run_isolated=cli_args.run_isolated) + result = exec_tests(linux, exec_request) + stdout.print_with_timestamp(( + 'Elapsed time: %.3fs\n') % (result.elapsed_time)) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + + +def parse_handler(cli_args): + if cli_args.file is None: + sys.stdin.reconfigure(errors='backslashreplace') # pytype: disable=attribute-error + kunit_output = sys.stdin + else: + with open(cli_args.file, 'r', errors='backslashreplace') as f: + kunit_output = f.read().splitlines() + # We know nothing about how the result was created! + metadata = kunit_json.Metadata() + request = KunitParseRequest(raw_output=cli_args.raw_output, + json=cli_args.json) + result, _ = parse_tests(request, metadata, kunit_output) + if result.status != KunitStatus.SUCCESS: + sys.exit(1) + + +subcommand_handlers_map = { + 'run': run_handler, + 'config': config_handler, + 'build': build_handler, + 'exec': exec_handler, + 'parse': parse_handler +} + + def main(argv): parser = argparse.ArgumentParser( description='Helps writing and running KUnit tests.') @@ -438,78 +518,14 @@ def main(argv): if get_kernel_root_path(): os.chdir(get_kernel_root_path()) - if cli_args.subcommand == 'run': - if not os.path.exists(cli_args.build_dir): - os.mkdir(cli_args.build_dir) - - linux = tree_from_args(cli_args) - request = KunitRequest(build_dir=cli_args.build_dir, - make_options=cli_args.make_options, - jobs=cli_args.jobs, - raw_output=cli_args.raw_output, - json=cli_args.json, - timeout=cli_args.timeout, - filter_glob=cli_args.filter_glob, - kernel_args=cli_args.kernel_args, - run_isolated=cli_args.run_isolated) - result = run_tests(linux, request) - if result.status != KunitStatus.SUCCESS: - sys.exit(1) - elif cli_args.subcommand == 'config': - if cli_args.build_dir and ( - not os.path.exists(cli_args.build_dir)): - os.mkdir(cli_args.build_dir) - - linux = tree_from_args(cli_args) - request = KunitConfigRequest(build_dir=cli_args.build_dir, - make_options=cli_args.make_options) - result = config_tests(linux, request) - stdout.print_with_timestamp(( - 'Elapsed time: %.3fs\n') % ( - result.elapsed_time)) - if result.status != KunitStatus.SUCCESS: - sys.exit(1) - elif cli_args.subcommand == 'build': - linux = tree_from_args(cli_args) - request = KunitBuildRequest(build_dir=cli_args.build_dir, - make_options=cli_args.make_options, - jobs=cli_args.jobs) - result = config_and_build_tests(linux, request) - stdout.print_with_timestamp(( - 'Elapsed time: %.3fs\n') % ( - result.elapsed_time)) - if result.status != KunitStatus.SUCCESS: - sys.exit(1) - elif cli_args.subcommand == 'exec': - linux = tree_from_args(cli_args) - exec_request = KunitExecRequest(raw_output=cli_args.raw_output, - build_dir=cli_args.build_dir, - json=cli_args.json, - timeout=cli_args.timeout, - filter_glob=cli_args.filter_glob, - kernel_args=cli_args.kernel_args, - run_isolated=cli_args.run_isolated) - result = exec_tests(linux, exec_request) - stdout.print_with_timestamp(( - 'Elapsed time: %.3fs\n') % (result.elapsed_time)) - if result.status != KunitStatus.SUCCESS: - sys.exit(1) - elif cli_args.subcommand == 'parse': - if cli_args.file is None: - sys.stdin.reconfigure(errors='backslashreplace') # pytype: disable=attribute-error - kunit_output = sys.stdin - else: - with open(cli_args.file, 'r', errors='backslashreplace') as f: - kunit_output = f.read().splitlines() - # We know nothing about how the result was created! - metadata = kunit_json.Metadata() - request = KunitParseRequest(raw_output=cli_args.raw_output, - json=cli_args.json) - result, _ = parse_tests(request, metadata, kunit_output) - if result.status != KunitStatus.SUCCESS: - sys.exit(1) - else: + subcomand_handler = subcommand_handlers_map.get(cli_args.subcommand, None) + + if subcomand_handler is None: parser.print_help() + return + + subcomand_handler(cli_args) + if __name__ == '__main__': main(sys.argv[1:]) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 81fa7ec2e66a..958ee9bdb316 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -173,11 +173,11 @@ static noinline void check_new_node(struct maple_tree *mt) if (!MAPLE_32BIT) { if (i >= 35) - e = i - 35; + e = i - 34; else if (i >= 5) - e = i - 5; + e = i - 4; else if (i >= 2) - e = i - 2; + e = i - 1; } else { if (i >= 4) e = i - 4; @@ -305,17 +305,17 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 2); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); /* Check the limit of pop/push/pop */ mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 2); /* Request */ @@ -323,14 +323,14 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_alloc_req(&mas)); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mas_push_node(&mas, mn); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); @@ -35342,7 +35342,7 @@ static noinline void check_prealloc(struct maple_tree *mt) for (i = 0; i <= max; i++) mtree_test_store_range(mt, i * 10, i * 10 + 5, &i); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35351,18 +35351,18 @@ static noinline void check_prealloc(struct maple_tree *mt) allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35370,25 +35370,25 @@ static noinline void check_prealloc(struct maple_tree *mt) mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35397,12 +35397,12 @@ static noinline void check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != allocated); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35410,21 +35410,21 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35432,14 +35432,14 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); mas_destroy(&mas); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35447,7 +35447,7 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 41b649452560..13a6837a0c6b 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -26,6 +26,7 @@ TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio +TARGETS += hid TARGETS += intel_pstate TARGETS += iommu TARGETS += ipc @@ -85,7 +86,7 @@ TARGETS += tmpfs TARGETS += tpm2 TARGETS += user TARGETS += vDSO -TARGETS += vm +TARGETS += mm TARGETS += x86 TARGETS += zram #Please keep the TARGETS list alphabetically sorted @@ -236,8 +237,8 @@ ifdef INSTALL_PATH @# included in the generated runlist. for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - [ ! -d $(INSTALL_PATH)/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ - echo -ne "Emit Tests for $$TARGET\n"; \ + [ ! -d $(INSTALL_PATH)/$$TARGET ] && printf "Skipping non-existent dir: $$TARGET\n" && continue; \ + printf "Emit Tests for $$TARGET\n"; \ $(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET COLLECTION=$$TARGET \ -C $$TARGET emit_tests >> $(TEST_LIST); \ done; diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index a8c0383878d3..901949db80ad 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -8,13 +8,15 @@ LDLIBS += -lasound endif CFLAGS += -L$(OUTPUT) -Wl,-rpath=./ +LDLIBS+=-lpthread + OVERRIDE_TARGETS = 1 TEST_GEN_PROGS := mixer-test pcm-test TEST_GEN_PROGS_EXTENDED := libatest.so -TEST_FILES := conf.d +TEST_FILES := conf.d pcm-test.conf include ../lib.mk diff --git a/tools/testing/selftests/alsa/alsa-local.h b/tools/testing/selftests/alsa/alsa-local.h index 65f197ea9773..de030dc23bd1 100644 --- a/tools/testing/selftests/alsa/alsa-local.h +++ b/tools/testing/selftests/alsa/alsa-local.h @@ -12,6 +12,7 @@ snd_config_t *get_alsalib_config(void); +snd_config_t *conf_load_from_file(const char *filename); void conf_load(void); void conf_free(void); snd_config_t *conf_by_card(int card); @@ -20,5 +21,7 @@ int conf_get_count(snd_config_t *root, const char *key1, const char *key2); const char *conf_get_string(snd_config_t *root, const char *key1, const char *key2, const char *def); long conf_get_long(snd_config_t *root, const char *key1, const char *key2, long def); int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int def); +void conf_get_string_array(snd_config_t *root, const char *key1, const char *key2, + const char **array, int array_size, const char *def); #endif /* __ALSA_LOCAL_H */ diff --git a/tools/testing/selftests/alsa/conf.c b/tools/testing/selftests/alsa/conf.c index c7ffc8f04195..d7aafe5a1993 100644 --- a/tools/testing/selftests/alsa/conf.c +++ b/tools/testing/selftests/alsa/conf.c @@ -125,7 +125,7 @@ static int dump_config_tree(snd_config_t *top) snd_output_close(out); } -static snd_config_t *load(const char *filename) +snd_config_t *conf_load_from_file(const char *filename) { snd_config_t *dst; snd_input_t *input; @@ -235,7 +235,7 @@ static bool test_filename1(int card, const char *filename, const char *sysfs_car snd_config_t *config, *sysfs_config, *card_config, *sysfs_card_config, *node; snd_config_iterator_t i, next; - config = load(filename); + config = conf_load_from_file(filename); if (snd_config_search(config, "sysfs", &sysfs_config) || snd_config_get_type(sysfs_config) != SND_CONFIG_TYPE_COMPOUND) ksft_exit_fail_msg("Missing global sysfs block in filename %s\n", filename); @@ -446,3 +446,25 @@ int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int de ksft_exit_fail_msg("key '%s'.'%s' is not an bool\n", key1, key2); return !!ret; } + +void conf_get_string_array(snd_config_t *root, const char *key1, const char *key2, + const char **array, int array_size, const char *def) +{ + snd_config_t *cfg; + char buf[16]; + int ret, index; + + ret = conf_get_by_keys(root, key1, key2, &cfg); + if (ret == -ENOENT) + cfg = NULL; + else if (ret < 0) + ksft_exit_fail_msg("key '%s'.'%s' search error: %s\n", key1, key2, snd_strerror(ret)); + for (index = 0; index < array_size; index++) { + if (cfg == NULL) { + array[index] = def; + } else { + sprintf(buf, "%i", index); + array[index] = conf_get_string(cfg, buf, NULL, def); + } + } +} diff --git a/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf b/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf index 9eca985e0c08..5b40a916295d 100644 --- a/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf +++ b/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf @@ -39,25 +39,30 @@ card.hda { # pcm.0.0 { PLAYBACK { - # - # Uncomment to override values for specific tests - # - #test_name1 { - # access RW_INTERLEAVED - # format S16_LE - # rate 48000 - # channels 2 - # period_size 512 - # buffer_size 4096 - #} - #test_name2 { - # access RW_INTERLEAVED - # format S16_LE - # rate 48000 - # channels 2 - # period_size 24000 - # buffer_size 192000 - #} + test.time1 { + access RW_INTERLEAVED # can be omitted - default + format S16_LE # can be omitted - default + rate 48000 # can be omitted - default + channels 2 # can be omitted - default + period_size 512 + buffer_size 4096 + } + test.time2 { + access RW_INTERLEAVED + format S16_LE + rate 48000 + channels 2 + period_size 24000 + buffer_size 192000 + } + test.time3 { + access RW_INTERLEAVED + format S16_LE + rate 44100 + channels 2 + period_size 24000 + buffer_size 192000 + } } CAPTURE { # use default tests, check for the presence diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index f293c7d81009..58b525a4a32c 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -15,12 +15,21 @@ #include <stdbool.h> #include <errno.h> #include <assert.h> +#include <pthread.h> #include "../kselftest.h" #include "alsa-local.h" typedef struct timespec timestamp_t; +struct card_data { + int card; + pthread_t thread; + struct card_data *next; +}; + +struct card_data *card_list = NULL; + struct pcm_data { snd_pcm_t *handle; int card; @@ -31,19 +40,19 @@ struct pcm_data { struct pcm_data *next; }; -int num_pcms = 0; struct pcm_data *pcm_list = NULL; int num_missing = 0; struct pcm_data *pcm_missing = NULL; -struct time_test_def { - const char *cfg_prefix; - const char *format; - long rate; - long channels; - long period_size; - long buffer_size; +snd_config_t *default_pcm_config; + +/* Lock while reporting results since kselftest doesn't */ +pthread_mutex_t results_lock = PTHREAD_MUTEX_INITIALIZER; + +enum test_class { + TEST_CLASS_DEFAULT, + TEST_CLASS_SYSTEM, }; void timestamp_now(timestamp_t *tstamp) @@ -146,6 +155,7 @@ static void find_pcms(void) snd_ctl_t *handle; snd_pcm_info_t *pcm_info; snd_config_t *config, *card_config, *pcm_config; + struct card_data *card_data; snd_pcm_info_alloca(&pcm_info); @@ -167,6 +177,13 @@ static void find_pcms(void) card_config = conf_by_card(card); + card_data = calloc(1, sizeof(*card_data)); + if (!card_data) + ksft_exit_fail_msg("Out of memory\n"); + card_data->card = card; + card_data->next = card_list; + card_list = card_data; + dev = -1; while (1) { if (snd_ctl_pcm_next_device(handle, &dev) < 0) @@ -209,7 +226,6 @@ static void find_pcms(void) pcm_data->pcm_config = conf_get_subtree(card_config, key, NULL); pcm_data->next = pcm_list; pcm_list = pcm_data; - num_pcms++; } } } @@ -228,45 +244,64 @@ static void find_pcms(void) snd_config_delete(config); } -static void test_pcm_time1(struct pcm_data *data, - const struct time_test_def *test) +static void test_pcm_time(struct pcm_data *data, enum test_class class, + const char *test_name, snd_config_t *pcm_cfg) { char name[64], key[128], msg[256]; const char *cs; int i, err; snd_pcm_t *handle = NULL; snd_pcm_access_t access = SND_PCM_ACCESS_RW_INTERLEAVED; - snd_pcm_format_t format; + snd_pcm_format_t format, old_format; + const char *alt_formats[8]; unsigned char *samples = NULL; snd_pcm_sframes_t frames; long long ms; long rate, channels, period_size, buffer_size; - unsigned int rchannels; unsigned int rrate; snd_pcm_uframes_t rperiod_size, rbuffer_size, start_threshold; timestamp_t tstamp; - bool pass = false, automatic = true; + bool pass = false; snd_pcm_hw_params_t *hw_params; snd_pcm_sw_params_t *sw_params; - bool skip = false; + const char *test_class_name; + bool skip = true; + const char *desc; + + switch (class) { + case TEST_CLASS_DEFAULT: + test_class_name = "default"; + break; + case TEST_CLASS_SYSTEM: + test_class_name = "system"; + break; + default: + ksft_exit_fail_msg("Unknown test class %d\n", class); + break; + } + + desc = conf_get_string(pcm_cfg, "description", NULL, NULL); + if (desc) + ksft_print_msg("%s.%s.%d.%d.%d.%s - %s\n", + test_class_name, test_name, + data->card, data->device, data->subdevice, + snd_pcm_stream_name(data->stream), + desc); + snd_pcm_hw_params_alloca(&hw_params); snd_pcm_sw_params_alloca(&sw_params); - cs = conf_get_string(data->pcm_config, test->cfg_prefix, "format", test->format); + cs = conf_get_string(pcm_cfg, "format", NULL, "S16_LE"); format = snd_pcm_format_value(cs); if (format == SND_PCM_FORMAT_UNKNOWN) ksft_exit_fail_msg("Wrong format '%s'\n", cs); - rate = conf_get_long(data->pcm_config, test->cfg_prefix, "rate", test->rate); - channels = conf_get_long(data->pcm_config, test->cfg_prefix, "channels", test->channels); - period_size = conf_get_long(data->pcm_config, test->cfg_prefix, "period_size", test->period_size); - buffer_size = conf_get_long(data->pcm_config, test->cfg_prefix, "buffer_size", test->buffer_size); - - automatic = strcmp(test->format, snd_pcm_format_name(format)) == 0 && - test->rate == rate && - test->channels == channels && - test->period_size == period_size && - test->buffer_size == buffer_size; + conf_get_string_array(pcm_cfg, "alt_formats", NULL, + alt_formats, ARRAY_SIZE(alt_formats), NULL); + rate = conf_get_long(pcm_cfg, "rate", NULL, 48000); + channels = conf_get_long(pcm_cfg, "channels", NULL, 2); + period_size = conf_get_long(pcm_cfg, "period_size", NULL, 4096); + buffer_size = conf_get_long(pcm_cfg, "buffer_size", NULL, 16384); samples = malloc((rate * channels * snd_pcm_format_physical_width(format)) / 8); if (!samples) @@ -296,32 +331,39 @@ static void test_pcm_time1(struct pcm_data *data, snd_pcm_access_name(access), snd_strerror(err)); goto __close; } + i = -1; __format: err = snd_pcm_hw_params_set_format(handle, hw_params, format); if (err < 0) { - if (automatic && format == SND_PCM_FORMAT_S16_LE) { - format = SND_PCM_FORMAT_S32_LE; - ksft_print_msg("%s.%d.%d.%d.%s.%s format S16_LE -> S32_LE\n", - test->cfg_prefix, - data->card, data->device, data->subdevice, - snd_pcm_stream_name(data->stream), - snd_pcm_access_name(access)); + i++; + if (i < ARRAY_SIZE(alt_formats) && alt_formats[i]) { + old_format = format; + format = snd_pcm_format_value(alt_formats[i]); + if (format != SND_PCM_FORMAT_UNKNOWN) { + ksft_print_msg("%s.%d.%d.%d.%s.%s format %s -> %s\n", + test_name, + data->card, data->device, data->subdevice, + snd_pcm_stream_name(data->stream), + snd_pcm_access_name(access), + snd_pcm_format_name(old_format), + snd_pcm_format_name(format)); + samples = realloc(samples, (rate * channels * + snd_pcm_format_physical_width(format)) / 8); + if (!samples) + ksft_exit_fail_msg("Out of memory\n"); + snd_pcm_format_set_silence(format, samples, rate * channels); + goto __format; + } } snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_format %s: %s", snd_pcm_format_name(format), snd_strerror(err)); goto __close; } - rchannels = channels; - err = snd_pcm_hw_params_set_channels_near(handle, hw_params, &rchannels); + err = snd_pcm_hw_params_set_channels(handle, hw_params, channels); if (err < 0) { snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_channels %ld: %s", channels, snd_strerror(err)); goto __close; } - if (rchannels != channels) { - snprintf(msg, sizeof(msg), "channels unsupported %ld != %ld", channels, rchannels); - skip = true; - goto __close; - } rrate = rate; err = snd_pcm_hw_params_set_rate_near(handle, hw_params, &rrate, 0); if (err < 0) { @@ -329,8 +371,7 @@ __format: goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate unsupported %ld != %ld", rate, rrate); - skip = true; + snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); goto __close; } rperiod_size = period_size; @@ -377,8 +418,8 @@ __format: goto __close; } - ksft_print_msg("%s.%d.%d.%d.%s hw_params.%s.%s.%ld.%ld.%ld.%ld sw_params.%ld\n", - test->cfg_prefix, + ksft_print_msg("%s.%s.%d.%d.%d.%s hw_params.%s.%s.%ld.%ld.%ld.%ld sw_params.%ld\n", + test_class_name, test_name, data->card, data->device, data->subdevice, snd_pcm_stream_name(data->stream), snd_pcm_access_name(access), @@ -387,6 +428,9 @@ __format: (long)rperiod_size, (long)rbuffer_size, (long)start_threshold); + /* Set all the params, actually run the test */ + skip = false; + timestamp_now(&tstamp); for (i = 0; i < 4; i++) { if (data->stream == SND_PCM_STREAM_PLAYBACK) { @@ -426,48 +470,120 @@ __format: msg[0] = '\0'; pass = true; __close: - if (!skip) { - ksft_test_result(pass, "%s.%d.%d.%d.%s%s%s\n", - test->cfg_prefix, + pthread_mutex_lock(&results_lock); + + switch (class) { + case TEST_CLASS_SYSTEM: + test_class_name = "system"; + /* + * Anything specified as specific to this system + * should always be supported. + */ + ksft_test_result(!skip, "%s.%s.%d.%d.%d.%s.params\n", + test_class_name, test_name, + data->card, data->device, data->subdevice, + snd_pcm_stream_name(data->stream)); + break; + default: + break; + } + + if (!skip) + ksft_test_result(pass, "%s.%s.%d.%d.%d.%s%s%s\n", + test_class_name, test_name, data->card, data->device, data->subdevice, snd_pcm_stream_name(data->stream), msg[0] ? " " : "", msg); - } else { - ksft_test_result_skip("%s.%d.%d.%d.%s%s%s\n", - test->cfg_prefix, - data->card, data->device, - data->subdevice, - snd_pcm_stream_name(data->stream), - msg[0] ? " " : "", msg); - } + else + ksft_test_result_skip("%s.%s.%d.%d.%d.%s%s%s\n", + test_class_name, test_name, + data->card, data->device, data->subdevice, + snd_pcm_stream_name(data->stream), + msg[0] ? " " : "", msg); + + pthread_mutex_unlock(&results_lock); + free(samples); if (handle) snd_pcm_close(handle); } -static const struct time_test_def time_tests[] = { - /* name format rate chan period buffer */ - { "8k.1.big", "S16_LE", 8000, 2, 8000, 32000 }, - { "8k.2.big", "S16_LE", 8000, 2, 8000, 32000 }, - { "44k1.2.big", "S16_LE", 44100, 2, 22050, 192000 }, - { "48k.2.small", "S16_LE", 48000, 2, 512, 4096 }, - { "48k.2.big", "S16_LE", 48000, 2, 24000, 192000 }, - { "48k.6.big", "S16_LE", 48000, 6, 48000, 576000 }, - { "96k.2.big", "S16_LE", 96000, 2, 48000, 192000 }, -}; +void run_time_tests(struct pcm_data *pcm, enum test_class class, + snd_config_t *cfg) +{ + const char *test_name, *test_type; + snd_config_t *pcm_cfg; + snd_config_iterator_t i, next; + + if (!cfg) + return; + + cfg = conf_get_subtree(cfg, "test", NULL); + if (cfg == NULL) + return; + + snd_config_for_each(i, next, cfg) { + pcm_cfg = snd_config_iterator_entry(i); + if (snd_config_get_id(pcm_cfg, &test_name) < 0) + ksft_exit_fail_msg("snd_config_get_id\n"); + test_type = conf_get_string(pcm_cfg, "type", NULL, "time"); + if (strcmp(test_type, "time") == 0) + test_pcm_time(pcm, class, test_name, pcm_cfg); + else + ksft_exit_fail_msg("unknown test type '%s'\n", test_type); + } +} + +void *card_thread(void *data) +{ + struct card_data *card = data; + struct pcm_data *pcm; + + for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) { + if (pcm->card != card->card) + continue; + + run_time_tests(pcm, TEST_CLASS_DEFAULT, default_pcm_config); + run_time_tests(pcm, TEST_CLASS_SYSTEM, pcm->pcm_config); + } + + return 0; +} int main(void) { + struct card_data *card; struct pcm_data *pcm; - int i; + snd_config_t *global_config, *cfg, *pcm_cfg; + int num_pcm_tests = 0, num_tests, num_std_pcm_tests; + int ret; + void *thread_ret; ksft_print_header(); + global_config = conf_load_from_file("pcm-test.conf"); + default_pcm_config = conf_get_subtree(global_config, "pcm", NULL); + if (default_pcm_config == NULL) + ksft_exit_fail_msg("default pcm test configuration (pcm compound) is missing\n"); + conf_load(); find_pcms(); - ksft_set_plan(num_missing + num_pcms * ARRAY_SIZE(time_tests)); + num_std_pcm_tests = conf_get_count(default_pcm_config, "test", NULL); + + for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) { + num_pcm_tests += num_std_pcm_tests; + cfg = pcm->pcm_config; + if (cfg == NULL) + continue; + /* Setting params is reported as a separate test */ + num_tests = conf_get_count(cfg, "test", NULL) * 2; + if (num_tests > 0) + num_pcm_tests += num_tests; + } + + ksft_set_plan(num_missing + num_pcm_tests); for (pcm = pcm_missing; pcm != NULL; pcm = pcm->next) { ksft_test_result(false, "test.missing.%d.%d.%d.%s\n", @@ -475,12 +591,25 @@ int main(void) snd_pcm_stream_name(pcm->stream)); } - for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) { - for (i = 0; i < ARRAY_SIZE(time_tests); i++) { - test_pcm_time1(pcm, &time_tests[i]); + for (card = card_list; card != NULL; card = card->next) { + ret = pthread_create(&card->thread, NULL, card_thread, card); + if (ret != 0) { + ksft_exit_fail_msg("Failed to create card %d thread: %d (%s)\n", + card->card, ret, + strerror(errno)); + } + } + + for (card = card_list; card != NULL; card = card->next) { + ret = pthread_join(card->thread, &thread_ret); + if (ret != 0) { + ksft_exit_fail_msg("Failed to join card %d thread: %d (%s)\n", + card->card, ret, + strerror(errno)); } } + snd_config_delete(global_config); conf_free(); ksft_exit_pass(); diff --git a/tools/testing/selftests/alsa/pcm-test.conf b/tools/testing/selftests/alsa/pcm-test.conf new file mode 100644 index 000000000000..71bd3f78a6f2 --- /dev/null +++ b/tools/testing/selftests/alsa/pcm-test.conf @@ -0,0 +1,63 @@ +pcm.test.time1 { + description "8kHz mono large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 8000 + channels 1 + period_size 8000 + buffer_size 32000 +} +pcm.test.time2 { + description "8kHz stereo large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 8000 + channels 2 + period_size 8000 + buffer_size 32000 +} +pcm.test.time3 { + description "44.1kHz stereo large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 44100 + channels 2 + period_size 22500 + buffer_size 192000 +} +pcm.test.time4 { + description "48kHz stereo small periods" + format S16_LE + alt_formats [ S32_LE ] + rate 48000 + channels 2 + period_size 512 + buffer_size 4096 +} +pcm.test.time5 { + description "48kHz stereo large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 48000 + channels 2 + period_size 24000 + buffer_size 192000 +} +pcm.test.time6 { + description "48kHz 6 channel large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 48000 + channels 2 + period_size 48000 + buffer_size 576000 +} +pcm.test.time7 { + description "96kHz stereo large periods" + format S16_LE + alt_formats [ S32_LE ] + rate 96000 + channels 2 + period_size 48000 + buffer_size 192000 +} diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 50a70220ba6c..48f56c86ad45 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -3,7 +3,7 @@ # A proper top_srcdir is needed by KSFT(lib.mk) top_srcdir = $(realpath ../../../../../) -CFLAGS += -I$(top_srcdir)/usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := fp-stress \ sve-ptrace sve-probe-vls \ diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile index 41cb75070511..6d29cfde43a2 100644 --- a/tools/testing/selftests/arm64/tags/Makefile +++ b/tools/testing/selftests/arm64/tags/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := tags_test TEST_PROGS := run_tags_test.sh diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 401a75844cc0..116fecf80ca1 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -47,3 +47,5 @@ test_cpp xskxceiver xdp_redirect_multi xdp_synproxy +xdp_hw_metadata +xdp_features diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 3fc3e54b19aa..b89eb87034e4 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -1,89 +1,24 @@ # TEMPORARY # Alphabetical order -atomics # attach(add): actual -524 <= expected 0 (trampoline) bloom_filter_map # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) bpf_cookie # failed to open_and_load program: -524 (trampoline) -bpf_iter_setsockopt # JIT does not support calling kernel function (kfunc) bpf_loop # attaches to __x64_sys_nanosleep -bpf_mod_race # BPF trampoline -bpf_nf # JIT does not support calling kernel function -bpf_tcp_ca # JIT does not support calling kernel function (kfunc) -cb_refs # expected error message unexpected error: -524 (trampoline) -cgroup_hierarchical_stats # JIT does not support calling kernel function (kfunc) -cgrp_kfunc # JIT does not support calling kernel function cgrp_local_storage # prog_attach unexpected error: -524 (trampoline) -core_read_macros # unknown func bpf_probe_read#4 (overlapping) -d_path # failed to auto-attach program 'prog_stat': -524 (trampoline) -decap_sanity # JIT does not support calling kernel function (kfunc) -deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline) -fentry_fexit # fentry attach failed: -524 (trampoline) -fentry_test # fentry_first_attach unexpected error: -524 (trampoline) -fexit_bpf2bpf # freplace_attach_trace unexpected error: -524 (trampoline) fexit_sleep # fexit_skel_load fexit skeleton failed (trampoline) -fexit_stress # fexit attach failed prog 0 failed: -524 (trampoline) -fexit_test # fexit_first_attach unexpected error: -524 (trampoline) -get_func_args_test # trampoline -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (trampoline) get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace) -htab_update # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call # 'bpf_prog_active': not found in kernel BTF (?) -kfunc_dynptr_param # JIT does not support calling kernel function (kfunc) kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test # relies on fentry ksyms_module # test_ksyms_module__open_and_load unexpected error: -9 (?) ksyms_module_libbpf # JIT does not support calling kernel function (kfunc) ksyms_module_lskel # test_ksyms_module_lskel__open_and_load unexpected error: -9 (?) -libbpf_get_fd_by_id_opts # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -linked_list # JIT does not support calling kernel function (kfunc) -lookup_key # JIT does not support calling kernel function (kfunc) -lru_bug # prog 'printk': failed to auto-attach: -524 -map_kptr # failed to open_and_load program: -524 (trampoline) -modify_return # modify_return attach failed: -524 (trampoline) module_attach # skel_attach skeleton attach failed: -524 (trampoline) -mptcp -netcnt # failed to load BPF skeleton 'netcnt_prog': -7 (?) -probe_user # check_kprobe_res wrong kprobe res from probe read (?) -rcu_read_lock # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) -recursion # skel_attach unexpected error: -524 (trampoline) ringbuf # skel_load skeleton load failed (?) -select_reuseport # intermittently fails on new s390x setup -send_signal # intermittently fails to receive signal -setget_sockopt # attach unexpected error: -524 (trampoline) -sk_assign # Can't read on server: Invalid argument (?) -sk_lookup # endianness problem -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (trampoline) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (trampoline) -socket_cookie # prog_attach unexpected error: -524 (trampoline) stacktrace_build_id # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2 (?) -tailcalls # tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls (?) -task_kfunc # JIT does not support calling kernel function -task_local_storage # failed to auto-attach program 'trace_exit_creds': -524 (trampoline) -test_bpffs # bpffs test failed 255 (iterator) -test_bprm_opts # failed to auto-attach program 'secure_exec': -524 (trampoline) -test_ima # failed to auto-attach program 'ima': -524 (trampoline) -test_local_storage # failed to auto-attach program 'unlink_hook': -524 (trampoline) test_lsm # attach unexpected error: -524 (trampoline) -test_overhead # attach_fentry unexpected error: -524 (trampoline) -test_profiler # unknown func bpf_probe_read_str#45 (overlapping) -timer # failed to auto-attach program 'test1': -524 (trampoline) -timer_crash # trampoline -timer_mim # failed to auto-attach program 'test1': -524 (trampoline) -trace_ext # failed to auto-attach program 'test_pkt_md_access_new': -524 (trampoline) trace_printk # trace_printk__load unexpected error: -2 (errno 2) (?) trace_vprintk # trace_vprintk__open_and_load unexpected error: -9 (?) -tracing_struct # failed to auto-attach: -524 (trampoline) -trampoline_count # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -type_cast # JIT does not support calling kernel function unpriv_bpf_disabled # fentry user_ringbuf # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3 (?) verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) -verify_pkcs7_sig # JIT does not support calling kernel function (kfunc) -vmlinux # failed to auto-attach program 'handle__fentry': -524 (trampoline) -xdp_adjust_tail # case-128 err 0 errno 28 retval 1 size 128 expect-size 3520 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_bpf2bpf # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_do_redirect # prog_run_max_size unexpected error: -22 (errno 22) -xdp_synproxy # JIT does not support calling kernel function (kfunc) -xfrm_info # JIT does not support calling kernel function (kfunc) +xdp_metadata # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c22c43bbee19..b677dcd0b77a 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -22,10 +22,11 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= +SAN_LDFLAGS ?= $(SAN_CFLAGS) CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) -LDFLAGS += $(SAN_CFLAGS) +LDFLAGS += $(SAN_LDFLAGS) LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang @@ -73,7 +74,8 @@ TEST_PROGS := test_kmod.sh \ test_bpftool.sh \ test_bpftool_metadata.sh \ test_doc_build.sh \ - test_xsk.sh + test_xsk.sh \ + test_xdp_features.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ @@ -83,7 +85,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ - xskxceiver xdp_redirect_multi xdp_synproxy veristat + xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ + xdp_features TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file TEST_GEN_FILES += liburandom_read.so @@ -149,14 +152,13 @@ endif # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. $(notdir $(TEST_GEN_PROGS) \ - $(TEST_PROGS) \ - $(TEST_PROGS_EXTENDED) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; # sort removes libbpf duplicates when not cross-building -MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \ - $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids \ +MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \ + $(BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/bpftool \ + $(HOST_BUILD_DIR)/resolve_btfids \ $(RUNQSLOWER_OUTPUT) $(INCLUDE_DIR)) $(MAKE_DIRS): $(call msg,MKDIR,,$@) @@ -181,14 +183,15 @@ endif # do not fail. Static builds leave urandom_read relying on system-wide shared libraries. $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c $(call msg,LIB,,$@) - $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS) \ + $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) \ + $^ $(filter-out -static,$(LDLIBS)) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -fPIC -shared -o $@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so $(call msg,BINARY,,$@) $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ - liburandom_read.so $(LDLIBS) \ + -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -Wl,-rpath=. -o $@ @@ -205,16 +208,26 @@ $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_tes $(Q)cp bpf_testmod/bpf_testmod.ko $@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool +ifneq ($(CROSS_COMPILE),) +CROSS_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool +TRUNNER_BPFTOOL := $(CROSS_BPFTOOL) +USE_BOOTSTRAP := "" +else +TRUNNER_BPFTOOL := $(DEFAULT_BPFTOOL) +USE_BOOTSTRAP := "bootstrap/" +endif $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ -TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) +TEST_GEN_PROGS_EXTENDED += $(TRUNNER_BPFTOOL) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) @@ -240,19 +253,30 @@ $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(OUTPUT)/xsk.o: $(BPFOBJ) -$(OUTPUT)/xskxceiver: $(OUTPUT)/xsk.o BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \ EXTRA_CFLAGS='-g -O0' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \ prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin +ifneq ($(CROSS_COMPILE),) +$(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ + $(BPFOBJ) | $(BUILD_DIR)/bpftool + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ + ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) \ + EXTRA_CFLAGS='-g -O0' \ + OUTPUT=$(BUILD_DIR)/bpftool/ \ + LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/ \ + LIBBPF_DESTDIR=$(SCRATCH_DIR)/ \ + prefix= DESTDIR=$(SCRATCH_DIR)/ install-bin +endif + all: docs docs: @@ -269,7 +293,8 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(APIDIR)/linux/bpf.h \ | $(BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ - EXTRA_CFLAGS='-g -O0' \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers ifneq ($(BPFOBJ),$(HOST_BPFOBJ)) @@ -278,7 +303,8 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ | $(HOST_BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \ EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \ - OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \ + OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ + CC="$(HOSTCC)" LD="$(HOSTLD)" \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif @@ -299,7 +325,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(TOOLSDIR)/lib/ctype.c \ $(TOOLSDIR)/lib/str_error_r.c $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ - CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \ + CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) @@ -383,6 +409,9 @@ linked_maps.skel.h-deps := linked_maps1.bpf.o linked_maps2.bpf.o test_subskeleton.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o test_subskeleton.bpf.o test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o +xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o +xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o +xdp_features.skel.h-deps := xdp_features.bpf.o LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps))) @@ -513,11 +542,13 @@ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ $(RESOLVE_BTFIDS) \ + $(TRUNNER_BPFTOOL) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@ - $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool + $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/$(USE_BOOTSTRAP)bpftool \ + $(OUTPUT)/$(if $2,$2/)bpftool endef @@ -527,7 +558,7 @@ TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ btf_helpers.c flow_dissector_load.h \ - cap_helpers.c test_loader.c + cap_helpers.c test_loader.c xsk.c TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ @@ -576,6 +607,18 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ +$(OUTPUT)/xskxceiver: xskxceiver.c $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT) + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + +$(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xdp_hw_metadata.skel.h | $(OUTPUT) + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + +$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT) + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) @@ -595,6 +638,7 @@ $(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h $(OUTPUT)/bench_bpf_hashmap_full_update.o: $(OUTPUT)/bpf_hashmap_full_update_bench.skel.h $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h +$(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -609,7 +653,9 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_strncmp.o \ $(OUTPUT)/bench_bpf_hashmap_full_update.o \ $(OUTPUT)/bench_local_storage.o \ - $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o + $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \ + $(OUTPUT)/bench_bpf_hashmap_lookup.o \ + # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ @@ -626,3 +672,6 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ liburandom_read.so) .PHONY: docs docs-clean + +# Delete partially updated (corrupted) files on error +.DELETE_ON_ERROR: diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index c1f20a147462..0b2a53bb8460 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -16,6 +16,7 @@ struct env env = { .warmup_sec = 1, .duration_sec = 5, .affinity = false, + .quiet = false, .consumer_cnt = 1, .producer_cnt = 1, }; @@ -262,6 +263,7 @@ static const struct argp_option opts[] = { { "consumers", 'c', "NUM", 0, "Number of consumer threads"}, { "verbose", 'v', NULL, 0, "Verbose debug output"}, { "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"}, + { "quiet", 'q', NULL, 0, "Be more quiet"}, { "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0, "Set of CPUs for producer threads; implies --affinity"}, { "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0, @@ -275,6 +277,7 @@ extern struct argp bench_bpf_loop_argp; extern struct argp bench_local_storage_argp; extern struct argp bench_local_storage_rcu_tasks_trace_argp; extern struct argp bench_strncmp_argp; +extern struct argp bench_hashmap_lookup_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -284,13 +287,15 @@ static const struct argp_child bench_parsers[] = { { &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 }, { &bench_local_storage_rcu_tasks_trace_argp, 0, "local_storage RCU Tasks Trace slowdown benchmark", 0 }, + { &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 }, {}, }; +/* Make pos_args global, so that we can run argp_parse twice, if necessary */ +static int pos_args; + static error_t parse_arg(int key, char *arg, struct argp_state *state) { - static int pos_args; - switch (key) { case 'v': env.verbose = true; @@ -329,6 +334,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) case 'a': env.affinity = true; break; + case 'q': + env.quiet = true; + break; case ARG_PROD_AFFINITY_SET: env.affinity = true; if (parse_num_list(arg, &env.prod_cpus.cpus, @@ -359,7 +367,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) return 0; } -static void parse_cmdline_args(int argc, char **argv) +static void parse_cmdline_args_init(int argc, char **argv) { static const struct argp argp = { .options = opts, @@ -369,9 +377,25 @@ static void parse_cmdline_args(int argc, char **argv) }; if (argp_parse(&argp, argc, argv, 0, NULL, NULL)) exit(1); - if (!env.list && !env.bench_name) { - argp_help(&argp, stderr, ARGP_HELP_DOC, "bench"); - exit(1); +} + +static void parse_cmdline_args_final(int argc, char **argv) +{ + struct argp_child bench_parsers[2] = {}; + const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + .children = bench_parsers, + }; + + /* Parse arguments the second time with the correct set of parsers */ + if (bench->argp) { + bench_parsers[0].argp = bench->argp; + bench_parsers[0].header = bench->name; + pos_args = 0; + if (argp_parse(&argp, argc, argv, 0, NULL, NULL)) + exit(1); } } @@ -490,6 +514,7 @@ extern const struct bench bench_local_storage_cache_seq_get; extern const struct bench bench_local_storage_cache_interleaved_get; extern const struct bench bench_local_storage_cache_hashmap_control; extern const struct bench bench_local_storage_tasks_trace; +extern const struct bench bench_bpf_hashmap_lookup; static const struct bench *benchs[] = { &bench_count_global, @@ -529,17 +554,17 @@ static const struct bench *benchs[] = { &bench_local_storage_cache_interleaved_get, &bench_local_storage_cache_hashmap_control, &bench_local_storage_tasks_trace, + &bench_bpf_hashmap_lookup, }; -static void setup_benchmark() +static void find_benchmark(void) { - int i, err; + int i; if (!env.bench_name) { fprintf(stderr, "benchmark name is not specified\n"); exit(1); } - for (i = 0; i < ARRAY_SIZE(benchs); i++) { if (strcmp(benchs[i]->name, env.bench_name) == 0) { bench = benchs[i]; @@ -550,8 +575,14 @@ static void setup_benchmark() fprintf(stderr, "benchmark '%s' not found\n", env.bench_name); exit(1); } +} - printf("Setting up benchmark '%s'...\n", bench->name); +static void setup_benchmark(void) +{ + int i, err; + + if (!env.quiet) + printf("Setting up benchmark '%s'...\n", bench->name); state.producers = calloc(env.producer_cnt, sizeof(*state.producers)); state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers)); @@ -597,7 +628,8 @@ static void setup_benchmark() next_cpu(&env.prod_cpus)); } - printf("Benchmark '%s' started.\n", bench->name); + if (!env.quiet) + printf("Benchmark '%s' started.\n", bench->name); } static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER; @@ -621,7 +653,7 @@ static void collect_measurements(long delta_ns) { int main(int argc, char **argv) { - parse_cmdline_args(argc, argv); + parse_cmdline_args_init(argc, argv); if (env.list) { int i; @@ -633,6 +665,9 @@ int main(int argc, char **argv) return 0; } + find_benchmark(); + parse_cmdline_args_final(argc, argv); + setup_benchmark(); setup_timer(); diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index d748255877e2..402729c6a3ac 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -24,6 +24,7 @@ struct env { bool verbose; bool list; bool affinity; + bool quiet; int consumer_cnt; int producer_cnt; struct cpu_set prod_cpus; @@ -47,6 +48,7 @@ struct bench_res { struct bench { const char *name; + const struct argp *argp; void (*validate)(void); void (*setup)(void); void *(*producer_thread)(void *ctx); diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c index 5bcb8a8cdeb2..7c8ccc108313 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c +++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c @@ -428,6 +428,7 @@ static void *consumer(void *input) const struct bench bench_bloom_lookup = { .name = "bloom-lookup", + .argp = &bench_bloom_map_argp, .validate = validate, .setup = bloom_lookup_setup, .producer_thread = producer, @@ -439,6 +440,7 @@ const struct bench bench_bloom_lookup = { const struct bench bench_bloom_update = { .name = "bloom-update", + .argp = &bench_bloom_map_argp, .validate = validate, .setup = bloom_update_setup, .producer_thread = producer, @@ -450,6 +452,7 @@ const struct bench bench_bloom_update = { const struct bench bench_bloom_false_positive = { .name = "bloom-false-positive", + .argp = &bench_bloom_map_argp, .validate = validate, .setup = false_positive_setup, .producer_thread = producer, @@ -461,6 +464,7 @@ const struct bench bench_bloom_false_positive = { const struct bench bench_hashmap_without_bloom = { .name = "hashmap-without-bloom", + .argp = &bench_bloom_map_argp, .validate = validate, .setup = hashmap_no_bloom_setup, .producer_thread = producer, @@ -472,6 +476,7 @@ const struct bench bench_hashmap_without_bloom = { const struct bench bench_hashmap_with_bloom = { .name = "hashmap-with-bloom", + .argp = &bench_bloom_map_argp, .validate = validate, .setup = hashmap_with_bloom_setup, .producer_thread = producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c index cec51e0ff4b8..75abe8137b6c 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Bytedance */ -#include <argp.h> #include "bench.h" #include "bpf_hashmap_full_update_bench.skel.h" #include "bpf_util.h" @@ -68,7 +67,7 @@ static void setup(void) bpf_map_update_elem(map_fd, &i, &i, BPF_ANY); } -void hashmap_report_final(struct bench_res res[], int res_cnt) +static void hashmap_report_final(struct bench_res res[], int res_cnt) { unsigned int nr_cpus = bpf_num_possible_cpus(); int i; @@ -85,7 +84,7 @@ void hashmap_report_final(struct bench_res res[], int res_cnt) } const struct bench bench_bpf_hashmap_full_update = { - .name = "bpf-hashmap-ful-update", + .name = "bpf-hashmap-full-update", .validate = validate, .setup = setup, .producer_thread = producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c new file mode 100644 index 000000000000..8dbb02f75cff --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include <sys/random.h> +#include <argp.h> +#include "bench.h" +#include "bpf_hashmap_lookup.skel.h" +#include "bpf_util.h" + +/* BPF triggering benchmarks */ +static struct ctx { + struct bpf_hashmap_lookup *skel; +} ctx; + +/* only available to kernel, so define it here */ +#define BPF_MAX_LOOPS (1<<23) + +#define MAX_KEY_SIZE 1024 /* the size of the key map */ + +static struct { + __u32 key_size; + __u32 map_flags; + __u32 max_entries; + __u32 nr_entries; + __u32 nr_loops; +} args = { + .key_size = 4, + .map_flags = 0, + .max_entries = 1000, + .nr_entries = 500, + .nr_loops = 1000000, +}; + +enum { + ARG_KEY_SIZE = 8001, + ARG_MAP_FLAGS, + ARG_MAX_ENTRIES, + ARG_NR_ENTRIES, + ARG_NR_LOOPS, +}; + +static const struct argp_option opts[] = { + { "key_size", ARG_KEY_SIZE, "KEY_SIZE", 0, + "The hashmap key size (max 1024)"}, + { "map_flags", ARG_MAP_FLAGS, "MAP_FLAGS", 0, + "The hashmap flags passed to BPF_MAP_CREATE"}, + { "max_entries", ARG_MAX_ENTRIES, "MAX_ENTRIES", 0, + "The hashmap max entries"}, + { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0, + "The number of entries to insert/lookup"}, + { "nr_loops", ARG_NR_LOOPS, "NR_LOOPS", 0, + "The number of loops for the benchmark"}, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + long ret; + + switch (key) { + case ARG_KEY_SIZE: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > MAX_KEY_SIZE) { + fprintf(stderr, "invalid key_size"); + argp_usage(state); + } + args.key_size = ret; + break; + case ARG_MAP_FLAGS: + ret = strtol(arg, NULL, 0); + if (ret < 0 || ret > UINT_MAX) { + fprintf(stderr, "invalid map_flags"); + argp_usage(state); + } + args.map_flags = ret; + break; + case ARG_MAX_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "invalid max_entries"); + argp_usage(state); + } + args.max_entries = ret; + break; + case ARG_NR_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "invalid nr_entries"); + argp_usage(state); + } + args.nr_entries = ret; + break; + case ARG_NR_LOOPS: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > BPF_MAX_LOOPS) { + fprintf(stderr, "invalid nr_loops: %ld (min=1 max=%u)\n", + ret, BPF_MAX_LOOPS); + argp_usage(state); + } + args.nr_loops = ret; + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +const struct argp bench_hashmap_lookup_argp = { + .options = opts, + .parser = parse_arg, +}; + +static void validate(void) +{ + if (env.consumer_cnt != 1) { + fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + exit(1); + } + + if (args.nr_entries > args.max_entries) { + fprintf(stderr, "args.nr_entries is too big! (max %u, got %u)\n", + args.max_entries, args.nr_entries); + exit(1); + } +} + +static void *producer(void *input) +{ + while (true) { + /* trigger the bpf program */ + syscall(__NR_getpgid); + } + return NULL; +} + +static void *consumer(void *input) +{ + return NULL; +} + +static void measure(struct bench_res *res) +{ +} + +static inline void patch_key(u32 i, u32 *key) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + *key = i + 1; +#else + *key = __builtin_bswap32(i + 1); +#endif + /* the rest of key is random */ +} + +static void setup(void) +{ + struct bpf_link *link; + int map_fd; + int ret; + int i; + + setup_libbpf(); + + ctx.skel = bpf_hashmap_lookup__open(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + bpf_map__set_max_entries(ctx.skel->maps.hash_map_bench, args.max_entries); + bpf_map__set_key_size(ctx.skel->maps.hash_map_bench, args.key_size); + bpf_map__set_value_size(ctx.skel->maps.hash_map_bench, 8); + bpf_map__set_map_flags(ctx.skel->maps.hash_map_bench, args.map_flags); + + ctx.skel->bss->nr_entries = args.nr_entries; + ctx.skel->bss->nr_loops = args.nr_loops / args.nr_entries; + + if (args.key_size > 4) { + for (i = 1; i < args.key_size/4; i++) + ctx.skel->bss->key[i] = 2654435761 * i; + } + + ret = bpf_hashmap_lookup__load(ctx.skel); + if (ret) { + bpf_hashmap_lookup__destroy(ctx.skel); + fprintf(stderr, "failed to load map: %s", strerror(-ret)); + exit(1); + } + + /* fill in the hash_map */ + map_fd = bpf_map__fd(ctx.skel->maps.hash_map_bench); + for (u64 i = 0; i < args.nr_entries; i++) { + patch_key(i, ctx.skel->bss->key); + bpf_map_update_elem(map_fd, ctx.skel->bss->key, &i, BPF_ANY); + } + + link = bpf_program__attach(ctx.skel->progs.benchmark); + if (!link) { + fprintf(stderr, "failed to attach program!\n"); + exit(1); + } +} + +static inline double events_from_time(u64 time) +{ + if (time) + return args.nr_loops * 1000000000llu / time / 1000000.0L; + + return 0; +} + +static int compute_events(u64 *times, double *events_mean, double *events_stddev, u64 *mean_time) +{ + int i, n = 0; + + *events_mean = 0; + *events_stddev = 0; + *mean_time = 0; + + for (i = 0; i < 32; i++) { + if (!times[i]) + break; + *mean_time += times[i]; + *events_mean += events_from_time(times[i]); + n += 1; + } + if (!n) + return 0; + + *mean_time /= n; + *events_mean /= n; + + if (n > 1) { + for (i = 0; i < n; i++) { + double events_i = *events_mean - events_from_time(times[i]); + *events_stddev += events_i * events_i / (n - 1); + } + *events_stddev = sqrt(*events_stddev); + } + + return n; +} + +static void hashmap_report_final(struct bench_res res[], int res_cnt) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + double events_mean, events_stddev; + u64 mean_time; + int i, n; + + for (i = 0; i < nr_cpus; i++) { + n = compute_events(ctx.skel->bss->percpu_times[i], &events_mean, + &events_stddev, &mean_time); + if (n == 0) + continue; + + if (env.quiet) { + /* we expect only one cpu to be present */ + if (env.affinity) + printf("%.3lf\n", events_mean); + else + printf("cpu%02d %.3lf\n", i, events_mean); + } else { + printf("cpu%02d: lookup %.3lfM ± %.3lfM events/sec" + " (approximated from %d samples of ~%lums)\n", + i, events_mean, 2*events_stddev, + n, mean_time / 1000000); + } + } +} + +const struct bench bench_bpf_hashmap_lookup = { + .name = "bpf-hashmap-lookup", + .argp = &bench_hashmap_lookup_argp, + .validate = validate, + .setup = setup, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = NULL, + .report_final = hashmap_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c index d0a6572bfab6..d8a0394e10b1 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c @@ -95,6 +95,7 @@ static void setup(void) const struct bench bench_bpf_loop = { .name = "bpf-loop", + .argp = &bench_bpf_loop_argp, .validate = validate, .setup = setup, .producer_thread = producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage.c b/tools/testing/selftests/bpf/benchs/bench_local_storage.c index 5a378c84e81f..d4b2817306d4 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage.c @@ -255,6 +255,7 @@ static void *producer(void *input) */ const struct bench bench_local_storage_cache_seq_get = { .name = "local-storage-cache-seq-get", + .argp = &bench_local_storage_argp, .validate = validate, .setup = local_storage_cache_get_setup, .producer_thread = producer, @@ -266,6 +267,7 @@ const struct bench bench_local_storage_cache_seq_get = { const struct bench bench_local_storage_cache_interleaved_get = { .name = "local-storage-cache-int-get", + .argp = &bench_local_storage_argp, .validate = validate, .setup = local_storage_cache_get_interleaved_setup, .producer_thread = producer, @@ -277,6 +279,7 @@ const struct bench bench_local_storage_cache_interleaved_get = { const struct bench bench_local_storage_cache_hashmap_control = { .name = "local-storage-cache-hashmap-control", + .argp = &bench_local_storage_argp, .validate = validate, .setup = hashmap_setup, .producer_thread = producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c index 43f109d93130..d5eb5587f2aa 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c @@ -12,17 +12,14 @@ static struct { __u32 nr_procs; __u32 kthread_pid; - bool quiet; } args = { .nr_procs = 1000, .kthread_pid = 0, - .quiet = false, }; enum { ARG_NR_PROCS = 7000, ARG_KTHREAD_PID = 7001, - ARG_QUIET = 7002, }; static const struct argp_option opts[] = { @@ -30,8 +27,6 @@ static const struct argp_option opts[] = { "Set number of user processes to spin up"}, { "kthread_pid", ARG_KTHREAD_PID, "PID", 0, "Pid of rcu_tasks_trace kthread for ticks tracking"}, - { "quiet", ARG_QUIET, "{0,1}", 0, - "If true, don't report progress"}, {}, }; @@ -56,14 +51,6 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } args.kthread_pid = ret; break; - case ARG_QUIET: - ret = strtol(arg, NULL, 10); - if (ret < 0 || ret > 1) { - fprintf(stderr, "invalid quiet %ld\n", ret); - argp_usage(state); - } - args.quiet = ret; - break; break; default: return ARGP_ERR_UNKNOWN; @@ -230,7 +217,7 @@ static void report_progress(int iter, struct bench_res *res, long delta_ns) exit(1); } - if (args.quiet) + if (env.quiet) return; printf("Iter %d\t avg tasks_trace grace period latency\t%lf ns\n", @@ -271,6 +258,7 @@ static void report_final(struct bench_res res[], int res_cnt) */ const struct bench bench_local_storage_tasks_trace = { .name = "local-storage-tasks-trace", + .argp = &bench_local_storage_rcu_tasks_trace_argp, .validate = validate, .setup = local_storage_tasks_trace_setup, .producer_thread = producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index c2554f9695ff..fc91fdac4faa 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -518,6 +518,7 @@ static void *perfbuf_custom_consumer(void *input) const struct bench bench_rb_libbpf = { .name = "rb-libbpf", + .argp = &bench_ringbufs_argp, .validate = bufs_validate, .setup = ringbuf_libbpf_setup, .producer_thread = bufs_sample_producer, @@ -529,6 +530,7 @@ const struct bench bench_rb_libbpf = { const struct bench bench_rb_custom = { .name = "rb-custom", + .argp = &bench_ringbufs_argp, .validate = bufs_validate, .setup = ringbuf_custom_setup, .producer_thread = bufs_sample_producer, @@ -540,6 +542,7 @@ const struct bench bench_rb_custom = { const struct bench bench_pb_libbpf = { .name = "pb-libbpf", + .argp = &bench_ringbufs_argp, .validate = bufs_validate, .setup = perfbuf_libbpf_setup, .producer_thread = bufs_sample_producer, @@ -551,6 +554,7 @@ const struct bench bench_pb_libbpf = { const struct bench bench_pb_custom = { .name = "pb-custom", + .argp = &bench_ringbufs_argp, .validate = bufs_validate, .setup = perfbuf_libbpf_setup, .producer_thread = bufs_sample_producer, diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c index 494b591c0289..d3fad2ba6916 100644 --- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c +++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c @@ -140,6 +140,7 @@ static void strncmp_measure(struct bench_res *res) const struct bench bench_strncmp_no_helper = { .name = "strncmp-no-helper", + .argp = &bench_strncmp_argp, .validate = strncmp_validate, .setup = strncmp_no_helper_setup, .producer_thread = strncmp_producer, @@ -151,6 +152,7 @@ const struct bench bench_strncmp_no_helper = { const struct bench bench_strncmp_helper = { .name = "strncmp-helper", + .argp = &bench_strncmp_argp, .validate = strncmp_validate, .setup = strncmp_helper_setup, .producer_thread = strncmp_producer, diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh index 1e2de838f9fa..cd2efd3fdef3 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh @@ -6,6 +6,6 @@ source ./benchs/run_common.sh set -eufo pipefail nr_threads=`expr $(cat /proc/cpuinfo | grep "processor"| wc -l) - 1` -summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-ful-update) +summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-full-update) printf "$summary" printf "\n" diff --git a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh index 5dac1f02892c..3e8a969f2096 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh @@ -8,4 +8,4 @@ if [ -z $kthread_pid ]; then exit 1 fi -./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet 1 local-storage-tasks-trace +./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet local-storage-tasks-trace diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 424f7bbbfe9b..dbd2c729781a 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -65,4 +65,28 @@ extern struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ks */ extern struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; +/* Description + * Remove 'node' from rbtree with root 'root' + * Returns + * Pointer to the removed node, or NULL if 'root' didn't contain 'node' + */ +extern struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, + struct bpf_rb_node *node) __ksym; + +/* Description + * Add 'node' to rbtree with root 'root' using comparator 'less' + * Returns + * Nothing + */ +extern void bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node, + bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) __ksym; + +/* Description + * Return the first (leftmost) node in input tree + * Returns + * Pointer to the node, which is _not_ removed from the tree. If the tree + * contains no nodes, returns NULL. + */ +extern struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 5085fea3cac5..46500636d8cd 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -59,7 +59,7 @@ bpf_testmod_test_struct_arg_5(void) { return bpf_testmod_test_struct_arg_result; } -noinline void +__bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c index f472d28ad11a..16f1671e4bde 100644 --- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c @@ -18,7 +18,7 @@ static __u32 get_map_id_from_fd(int map_fd) uint32_t info_len = sizeof(map_info); int ret; - ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + ret = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len); CHECK(ret < 0, "Finding map info failed", "error:%s\n", strerror(errno)); diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h index 0ab1c88041cd..2d4a58e4e39c 100644 --- a/tools/testing/selftests/bpf/netcnt_common.h +++ b/tools/testing/selftests/bpf/netcnt_common.h @@ -8,11 +8,11 @@ /* sizeof(struct bpf_local_storage_elem): * - * It really is about 128 bytes on x86_64, but allocate more to account for - * possible layout changes, different architectures, etc. + * It is about 128 bytes on x86_64 and 512 bytes on s390x, but allocate more to + * account for possible layout changes, different architectures, etc. * The kernel will wrap up to PAGE_SIZE internally anyway. */ -#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 256 +#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 768 /* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */ #define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE (0xFFFF - \ diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index 9566d9d2f6ee..56374c8b5436 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -33,8 +33,8 @@ void test_attach_probe(void) struct test_attach_probe* skel; ssize_t uprobe_offset, ref_ctr_offset; struct bpf_link *uprobe_err_link; + FILE *devnull; bool legacy; - char *mem; /* Check if new-style kprobe/uprobe API is supported. * Kernels that support new FD-based kprobe and uprobe BPF attachment @@ -147,7 +147,7 @@ void test_attach_probe(void) /* test attach by name for a library function, using the library * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo(). */ - uprobe_opts.func_name = "malloc"; + uprobe_opts.func_name = "fopen"; uprobe_opts.retprobe = false; skel->links.handle_uprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2, @@ -157,7 +157,7 @@ void test_attach_probe(void) if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2")) goto cleanup; - uprobe_opts.func_name = "free"; + uprobe_opts.func_name = "fclose"; uprobe_opts.retprobe = true; skel->links.handle_uretprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2, @@ -195,8 +195,8 @@ void test_attach_probe(void) usleep(1); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(1); - free(mem); + devnull = fopen("/dev/null", "r"); + fclose(devnull); /* trigger & validate uprobe & uretprobe */ trigger_func(); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 2be2d61954bc..26b2d1bffdfd 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -472,6 +472,7 @@ static void lsm_subtest(struct test_bpf_cookie *skel) int prog_fd; int lsm_fd = -1; LIBBPF_OPTS(bpf_link_create_opts, link_opts); + int err; skel->bss->lsm_res = 0; @@ -482,8 +483,9 @@ static void lsm_subtest(struct test_bpf_cookie *skel) if (!ASSERT_GE(lsm_fd, 0, "lsm.link_create")) goto cleanup; - stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) goto cleanup; usleep(1); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 3af6450763e9..1f02168103dd 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -195,8 +195,8 @@ static void check_bpf_link_info(const struct bpf_program *prog) return; info_len = sizeof(info); - err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &info, &info_len); - ASSERT_OK(err, "bpf_obj_get_info_by_fd"); + err = bpf_link_get_info_by_fd(bpf_link__fd(link), &info, &info_len); + ASSERT_OK(err, "bpf_link_get_info_by_fd"); ASSERT_EQ(info.iter.task.tid, getpid(), "check_task_tid"); bpf_link__destroy(link); @@ -684,13 +684,13 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) /* setup filtering map_id in bpf program */ map_info_len = sizeof(map_info); - err = bpf_obj_get_info_by_fd(map1_fd, &map_info, &map_info_len); + err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len); if (CHECK(err, "get_map_info", "get map info failed: %s\n", strerror(errno))) goto free_map2; skel->bss->map1_id = map_info.id; - err = bpf_obj_get_info_by_fd(map2_fd, &map_info, &map_info_len); + err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len); if (CHECK(err, "get_map_info", "get map info failed: %s\n", strerror(errno))) goto free_map2; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index e1c1e521cca2..675b90b15280 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -44,7 +44,7 @@ void serial_test_bpf_obj_id(void) CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno); - /* Check bpf_obj_get_info_by_fd() */ + /* Check bpf_map_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { now = time(NULL); @@ -79,7 +79,7 @@ void serial_test_bpf_obj_id(void) /* Check getting map info */ info_len = sizeof(struct bpf_map_info) * 2; bzero(&map_infos[i], info_len); - err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], + err = bpf_map_get_info_by_fd(map_fds[i], &map_infos[i], &info_len); if (CHECK(err || map_infos[i].type != BPF_MAP_TYPE_ARRAY || @@ -118,8 +118,8 @@ void serial_test_bpf_obj_id(void) err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts); if (CHECK_FAIL(err)) goto done; - err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i], - &info_len); + err = bpf_prog_get_info_by_fd(prog_fds[i], &prog_infos[i], + &info_len); load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + (prog_infos[i].load_time / nsec_per_sec); if (CHECK(err || @@ -161,8 +161,8 @@ void serial_test_bpf_obj_id(void) bzero(&link_infos[i], info_len); link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name); link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); - err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), - &link_infos[i], &info_len); + err = bpf_link_get_info_by_fd(bpf_link__fd(links[i]), + &link_infos[i], &info_len); if (CHECK(err || link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || link_infos[i].prog_id != prog_infos[i].id || @@ -217,7 +217,7 @@ void serial_test_bpf_obj_id(void) * prog_info.map_ids = NULL */ prog_info.nr_map_ids = 1; - err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len); if (CHECK(!err || errno != EFAULT, "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)", err, errno, EFAULT)) @@ -228,7 +228,7 @@ void serial_test_bpf_obj_id(void) saved_map_id = *(int *)((long)prog_infos[i].map_ids); prog_info.map_ids = prog_infos[i].map_ids; prog_info.nr_map_ids = 2; - err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len); prog_infos[i].jited_prog_insns = 0; prog_infos[i].xlated_prog_insns = 0; CHECK(err || info_len != sizeof(struct bpf_prog_info) || @@ -277,7 +277,7 @@ void serial_test_bpf_obj_id(void) if (CHECK_FAIL(err)) goto done; - err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len); CHECK(err || info_len != sizeof(struct bpf_map_info) || memcmp(&map_info, &map_infos[i], info_len) || array_value != array_magic_value, @@ -322,7 +322,7 @@ void serial_test_bpf_obj_id(void) nr_id_found++; - err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len); + err = bpf_link_get_info_by_fd(link_fd, &link_info, &info_len); cmp_res = memcmp(&link_info, &link_infos[i], offsetof(struct bpf_link_info, raw_tracepoint)); CHECK(err || info_len != sizeof(link_info) || cmp_res, diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index de1b5b9eb93a..cbb600be943d 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4422,7 +4422,7 @@ static int test_big_btf_info(unsigned int test_num) info->btf = ptr_to_u64(user_btf); info->btf_size = raw_btf_size; - err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + err = bpf_btf_get_info_by_fd(btf_fd, info, &info_len); if (CHECK(!err, "!err")) { err = -1; goto done; @@ -4435,7 +4435,7 @@ static int test_big_btf_info(unsigned int test_num) * to userspace. */ info_garbage.garbage = 0; - err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); + err = bpf_btf_get_info_by_fd(btf_fd, info, &info_len); if (CHECK(err || info_len != sizeof(*info), "err:%d errno:%d info_len:%u sizeof(*info):%zu", err, errno, info_len, sizeof(*info))) { @@ -4499,7 +4499,7 @@ static int test_btf_id(unsigned int test_num) /* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */ info_len = sizeof(info[0]); - err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len); + err = bpf_btf_get_info_by_fd(btf_fd[0], &info[0], &info_len); if (CHECK(err, "errno:%d", errno)) { err = -1; goto done; @@ -4512,7 +4512,7 @@ static int test_btf_id(unsigned int test_num) } ret = 0; - err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len); + err = bpf_btf_get_info_by_fd(btf_fd[1], &info[1], &info_len); if (CHECK(err || info[0].id != info[1].id || info[0].btf_size != info[1].btf_size || (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)), @@ -4535,7 +4535,7 @@ static int test_btf_id(unsigned int test_num) } info_len = sizeof(map_info); - err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len); if (CHECK(err || map_info.btf_id != info[0].id || map_info.btf_key_type_id != 1 || map_info.btf_value_type_id != 2, "err:%d errno:%d info.id:%u btf_id:%u btf_key_type_id:%u btf_value_type_id:%u", @@ -4638,7 +4638,7 @@ static void do_test_get_info(unsigned int test_num) info.btf_size = user_btf_size; ret = 0; - err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len); + err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len); if (CHECK(err || !info.id || info_len != sizeof(info) || info.btf_size != raw_btf_size || (ret = memcmp(raw_btf, user_btf, expected_nbytes)), @@ -4755,7 +4755,7 @@ static void do_test_file(unsigned int test_num) /* get necessary program info */ info_len = sizeof(struct bpf_prog_info); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); @@ -4787,7 +4787,7 @@ static void do_test_file(unsigned int test_num) info.func_info_rec_size = rec_size; info.func_info = ptr_to_u64(func_info); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); @@ -6405,7 +6405,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test, /* get necessary lens */ info_len = sizeof(struct bpf_prog_info); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); return -1; @@ -6435,7 +6435,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test, info.nr_func_info = nr_func_info; info.func_info_rec_size = rec_size; info.func_info = ptr_to_u64(func_info); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); err = -1; @@ -6499,7 +6499,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test, nr_jited_func_lens = nr_jited_ksyms; info_len = sizeof(struct bpf_prog_info); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err < 0, "err:%d errno:%d", err, errno)) { err = -1; goto done; @@ -6573,7 +6573,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test, info.jited_func_lens = ptr_to_u64(jited_func_lens); } - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); /* * Only recheck the info.*line_info* fields. diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index eb90a6b8850d..a8b53b8736f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -14,7 +14,7 @@ static __u32 bpf_map_id(struct bpf_map *map) int err; memset(&info, 0, info_len); - err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + err = bpf_map_get_info_by_fd(bpf_map__fd(map), &info, &info_len); if (err) return 0; return info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c index 973f0c5af965..b3f7985c8504 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c @@ -8,9 +8,6 @@ #include "cgrp_kfunc_failure.skel.h" #include "cgrp_kfunc_success.skel.h" -static size_t log_buf_sz = 1 << 20; /* 1 MB */ -static char obj_log_buf[1048576]; - static struct cgrp_kfunc_success *open_load_cgrp_kfunc_skel(void) { struct cgrp_kfunc_success *skel; @@ -89,65 +86,6 @@ static const char * const success_tests[] = { "test_cgrp_get_ancestors", }; -static struct { - const char *prog_name; - const char *expected_err_msg; -} failure_tests[] = { - {"cgrp_kfunc_acquire_untrusted", "R1 must be referenced or trusted"}, - {"cgrp_kfunc_acquire_fp", "arg#0 pointer type STRUCT cgroup must point"}, - {"cgrp_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"}, - {"cgrp_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"}, - {"cgrp_kfunc_acquire_null", "arg#0 pointer type STRUCT cgroup must point"}, - {"cgrp_kfunc_acquire_unreleased", "Unreleased reference"}, - {"cgrp_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"}, - {"cgrp_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"}, - {"cgrp_kfunc_get_null", "arg#0 expected pointer to map value"}, - {"cgrp_kfunc_xchg_unreleased", "Unreleased reference"}, - {"cgrp_kfunc_get_unreleased", "Unreleased reference"}, - {"cgrp_kfunc_release_untrusted", "arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket"}, - {"cgrp_kfunc_release_fp", "arg#0 pointer type STRUCT cgroup must point"}, - {"cgrp_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"}, - {"cgrp_kfunc_release_unacquired", "release kernel function bpf_cgroup_release expects"}, -}; - -static void verify_fail(const char *prog_name, const char *expected_err_msg) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - struct cgrp_kfunc_failure *skel; - int err, i; - - opts.kernel_log_buf = obj_log_buf; - opts.kernel_log_size = log_buf_sz; - opts.kernel_log_level = 1; - - skel = cgrp_kfunc_failure__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "cgrp_kfunc_failure__open_opts")) - goto cleanup; - - for (i = 0; i < ARRAY_SIZE(failure_tests); i++) { - struct bpf_program *prog; - const char *curr_name = failure_tests[i].prog_name; - - prog = bpf_object__find_program_by_name(skel->obj, curr_name); - if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) - goto cleanup; - - bpf_program__set_autoload(prog, !strcmp(curr_name, prog_name)); - } - - err = cgrp_kfunc_failure__load(skel); - if (!ASSERT_ERR(err, "unexpected load success")) - goto cleanup; - - if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) { - fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg); - fprintf(stderr, "Verifier output: %s\n", obj_log_buf); - } - -cleanup: - cgrp_kfunc_failure__destroy(skel); -} - void test_cgrp_kfunc(void) { int i, err; @@ -163,12 +101,7 @@ void test_cgrp_kfunc(void) run_success_test(success_tests[i]); } - for (i = 0; i < ARRAY_SIZE(failure_tests); i++) { - if (!test__start_subtest(failure_tests[i].prog_name)) - continue; - - verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg); - } + RUN_TESTS(cgrp_kfunc_failure); cleanup: cleanup_cgroup_environment(); diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 33a2776737e7..2cc759956e3b 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -16,7 +16,7 @@ struct socket_cookie { __u64 cookie_key; - __u32 cookie_value; + __u64 cookie_value; }; static void test_tp_btf(int cgroup_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 12f4395f18b3..5338d2ea0460 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -59,7 +59,7 @@ static void test_check_mtu_xdp_attach(void) memset(&link_info, 0, sizeof(link_info)); fd = bpf_link__fd(link); - err = bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len); if (CHECK(err, "link_info", "failed: %d\n", err)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c new file mode 100644 index 000000000000..5fbe457c4ebe --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "cpumask_failure.skel.h" +#include "cpumask_success.skel.h" + +static const char * const cpumask_success_testcases[] = { + "test_alloc_free_cpumask", + "test_set_clear_cpu", + "test_setall_clear_cpu", + "test_first_firstzero_cpu", + "test_test_and_set_clear", + "test_and_or_xor", + "test_intersects_subset", + "test_copy_any_anyand", + "test_insert_leave", + "test_insert_remove_release", + "test_insert_kptr_get_release", +}; + +static void verify_success(const char *prog_name) +{ + struct cpumask_success *skel; + struct bpf_program *prog; + struct bpf_link *link = NULL; + pid_t child_pid; + int status; + + skel = cpumask_success__open(); + if (!ASSERT_OK_PTR(skel, "cpumask_success__open")) + return; + + skel->bss->pid = getpid(); + skel->bss->nr_cpus = libbpf_num_possible_cpus(); + + cpumask_success__load(skel); + if (!ASSERT_OK_PTR(skel, "cpumask_success__load")) + goto cleanup; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto cleanup; + + link = bpf_program__attach(prog); + if (!ASSERT_OK_PTR(link, "bpf_program__attach")) + goto cleanup; + + child_pid = fork(); + if (!ASSERT_GT(child_pid, -1, "child_pid")) + goto cleanup; + if (child_pid == 0) + _exit(0); + waitpid(child_pid, &status, 0); + ASSERT_OK(skel->bss->err, "post_wait_err"); + +cleanup: + bpf_link__destroy(link); + cpumask_success__destroy(skel); +} + +void test_cpumask(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cpumask_success_testcases); i++) { + if (!test__start_subtest(cpumask_success_testcases[i])) + continue; + + verify_success(cpumask_success_testcases[i]); + } + + RUN_TESTS(cpumask_failure); +} diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c index 0b2f73b88c53..2853883b7cbb 100644 --- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c +++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c @@ -80,6 +80,6 @@ fail: bpf_tc_hook_destroy(&qdisc_hook); close_netns(nstoken); } - system("ip netns del " NS_TEST " >& /dev/null"); + system("ip netns del " NS_TEST " &> /dev/null"); decap_sanity__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index c11832657d2b..f43fcb13d2c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ #include <test_progs.h> -#include "dummy_st_ops.skel.h" +#include "dummy_st_ops_success.skel.h" +#include "dummy_st_ops_fail.skel.h" #include "trace_dummy_st_ops.skel.h" /* Need to keep consistent with definition in include/linux/bpf.h */ @@ -11,17 +12,17 @@ struct bpf_dummy_ops_state { static void test_dummy_st_ops_attach(void) { - struct dummy_st_ops *skel; + struct dummy_st_ops_success *skel; struct bpf_link *link; - skel = dummy_st_ops__open_and_load(); + skel = dummy_st_ops_success__open_and_load(); if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) return; link = bpf_map__attach_struct_ops(skel->maps.dummy_1); ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach"); - dummy_st_ops__destroy(skel); + dummy_st_ops_success__destroy(skel); } static void test_dummy_init_ret_value(void) @@ -31,10 +32,10 @@ static void test_dummy_init_ret_value(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); - struct dummy_st_ops *skel; + struct dummy_st_ops_success *skel; int fd, err; - skel = dummy_st_ops__open_and_load(); + skel = dummy_st_ops_success__open_and_load(); if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) return; @@ -43,7 +44,7 @@ static void test_dummy_init_ret_value(void) ASSERT_OK(err, "test_run"); ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret"); - dummy_st_ops__destroy(skel); + dummy_st_ops_success__destroy(skel); } static void test_dummy_init_ptr_arg(void) @@ -58,10 +59,10 @@ static void test_dummy_init_ptr_arg(void) .ctx_size_in = sizeof(args), ); struct trace_dummy_st_ops *trace_skel; - struct dummy_st_ops *skel; + struct dummy_st_ops_success *skel; int fd, err; - skel = dummy_st_ops__open_and_load(); + skel = dummy_st_ops_success__open_and_load(); if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) return; @@ -91,7 +92,7 @@ static void test_dummy_init_ptr_arg(void) ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val"); done: - dummy_st_ops__destroy(skel); + dummy_st_ops_success__destroy(skel); trace_dummy_st_ops__destroy(trace_skel); } @@ -102,12 +103,12 @@ static void test_dummy_multiple_args(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); - struct dummy_st_ops *skel; + struct dummy_st_ops_success *skel; int fd, err; size_t i; char name[8]; - skel = dummy_st_ops__open_and_load(); + skel = dummy_st_ops_success__open_and_load(); if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) return; @@ -119,7 +120,28 @@ static void test_dummy_multiple_args(void) ASSERT_EQ(skel->bss->test_2_args[i], args[i], name); } - dummy_st_ops__destroy(skel); + dummy_st_ops_success__destroy(skel); +} + +static void test_dummy_sleepable(void) +{ + __u64 args[1] = {0}; + LIBBPF_OPTS(bpf_test_run_opts, attr, + .ctx_in = args, + .ctx_size_in = sizeof(args), + ); + struct dummy_st_ops_success *skel; + int fd, err; + + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) + return; + + fd = bpf_program__fd(skel->progs.test_sleepable); + err = bpf_prog_test_run_opts(fd, &attr); + ASSERT_OK(err, "test_run"); + + dummy_st_ops_success__destroy(skel); } void test_dummy_st_ops(void) @@ -132,4 +154,8 @@ void test_dummy_st_ops(void) test_dummy_init_ptr_arg(); if (test__start_subtest("dummy_multiple_args")) test_dummy_multiple_args(); + if (test__start_subtest("dummy_sleepable")) + test_dummy_sleepable(); + + RUN_TESTS(dummy_st_ops_fail); } diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index 7faaf6d9e0d4..b99264ec0d9c 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -5,14 +5,10 @@ #include "dynptr_fail.skel.h" #include "dynptr_success.skel.h" -static struct { - const char *prog_name; - const char *expected_err_msg; -} dynptr_tests[] = { - /* success cases */ - {"test_read_write", NULL}, - {"test_data_slice", NULL}, - {"test_ringbuf", NULL}, +static const char * const success_tests[] = { + "test_read_write", + "test_data_slice", + "test_ringbuf", }; static void verify_success(const char *prog_name) @@ -53,11 +49,11 @@ void test_dynptr(void) { int i; - for (i = 0; i < ARRAY_SIZE(dynptr_tests); i++) { - if (!test__start_subtest(dynptr_tests[i].prog_name)) + for (i = 0; i < ARRAY_SIZE(success_tests); i++) { + if (!test__start_subtest(success_tests[i])) continue; - verify_success(dynptr_tests[i].prog_name); + verify_success(success_tests[i]); } RUN_TESTS(dynptr_fail); diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c index 2cb2085917e7..75f85d0fe74a 100644 --- a/tools/testing/selftests/bpf/prog_tests/enable_stats.c +++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c @@ -28,7 +28,7 @@ void test_enable_stats(void) prog_fd = bpf_program__fd(skel->progs.test_enable_stats); memset(&info, 0, info_len); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 20f5fa0fcec9..8ec73fdfcdab 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -79,7 +79,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, return; info_len = sizeof(prog_info); - err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len); + err = bpf_prog_get_info_by_fd(tgt_fd, &prog_info, &info_len); if (!ASSERT_OK(err, "tgt_fd_get_info")) goto close_prog; @@ -136,8 +136,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, info_len = sizeof(link_info); memset(&link_info, 0, sizeof(link_info)); - err = bpf_obj_get_info_by_fd(bpf_link__fd(link[i]), - &link_info, &info_len); + err = bpf_link_get_info_by_fd(bpf_link__fd(link[i]), + &link_info, &info_len); ASSERT_OK(err, "link_fd_get_info"); ASSERT_EQ(link_info.tracing.attach_type, bpf_program__expected_attach_type(prog[i]), @@ -417,7 +417,7 @@ static int find_prog_btf_id(const char *name, __u32 attach_prog_fd) struct btf *btf; int ret; - ret = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); + ret = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len); if (ret) return ret; @@ -483,12 +483,12 @@ static void test_fentry_to_cgroup_bpf(void) if (!ASSERT_GE(fentry_fd, 0, "load_fentry")) goto cleanup; - /* Make sure bpf_obj_get_info_by_fd works correctly when attaching + /* Make sure bpf_prog_get_info_by_fd works correctly when attaching * to another BPF program. */ - ASSERT_OK(bpf_obj_get_info_by_fd(fentry_fd, &info, &info_len), - "bpf_obj_get_info_by_fd"); + ASSERT_OK(bpf_prog_get_info_by_fd(fentry_fd, &info, &info_len), + "bpf_prog_get_info_by_fd"); ASSERT_EQ(info.btf_id, 0, "info.btf_id"); ASSERT_EQ(info.attach_btf_id, btf_id, "info.attach_btf_id"); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 5a7e6011f6bf..596536def43d 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -2,14 +2,19 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -/* that's kernel internal BPF_MAX_TRAMP_PROGS define */ -#define CNT 38 - void serial_test_fexit_stress(void) { - int fexit_fd[CNT] = {}; - int link_fd[CNT] = {}; - int err, i; + int bpf_max_tramp_links, err, i; + int *fd, *fexit_fd, *link_fd; + + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + fd = calloc(bpf_max_tramp_links * 2, sizeof(*fd)); + if (!ASSERT_OK_PTR(fd, "fd")) + return; + fexit_fd = fd; + link_fd = fd + bpf_max_tramp_links; const struct bpf_insn trace_program[] = { BPF_MOV64_IMM(BPF_REG_0, 0), @@ -28,7 +33,7 @@ void serial_test_fexit_stress(void) goto out; trace_opts.attach_btf_id = err; - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), @@ -44,10 +49,11 @@ void serial_test_fexit_stress(void) ASSERT_OK(err, "bpf_prog_test_run_opts"); out: - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { if (link_fd[i]) close(link_fd[i]); if (fexit_fd[i]) close(fexit_fd[i]); } + free(fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c new file mode 100644 index 000000000000..61ccddccf485 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <sys/types.h> +#include <net/if.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "fib_lookup.skel.h" + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto fail; \ + }) + +#define NS_TEST "fib_lookup_ns" +#define IPV6_IFACE_ADDR "face::face" +#define IPV6_NUD_FAILED_ADDR "face::1" +#define IPV6_NUD_STALE_ADDR "face::2" +#define IPV4_IFACE_ADDR "10.0.0.254" +#define IPV4_NUD_FAILED_ADDR "10.0.0.1" +#define IPV4_NUD_STALE_ADDR "10.0.0.2" +#define DMAC "11:11:11:11:11:11" +#define DMAC_INIT { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, } + +struct fib_lookup_test { + const char *desc; + const char *daddr; + int expected_ret; + int lookup_flags; + __u8 dmac[6]; +}; + +static const struct fib_lookup_test tests[] = { + { .desc = "IPv6 failed neigh", + .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_NO_NEIGH, }, + { .desc = "IPv6 stale neigh", + .daddr = IPV6_NUD_STALE_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .dmac = DMAC_INIT, }, + { .desc = "IPv6 skip neigh", + .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, }, + { .desc = "IPv4 failed neigh", + .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_NO_NEIGH, }, + { .desc = "IPv4 stale neigh", + .daddr = IPV4_NUD_STALE_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .dmac = DMAC_INIT, }, + { .desc = "IPv4 skip neigh", + .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, }, +}; + +static int ifindex; + +static int setup_netns(void) +{ + int err; + + SYS("ip link add veth1 type veth peer name veth2"); + SYS("ip link set dev veth1 up"); + + SYS("ip addr add %s/64 dev veth1 nodad", IPV6_IFACE_ADDR); + SYS("ip neigh add %s dev veth1 nud failed", IPV6_NUD_FAILED_ADDR); + SYS("ip neigh add %s dev veth1 lladdr %s nud stale", IPV6_NUD_STALE_ADDR, DMAC); + + SYS("ip addr add %s/24 dev veth1 nodad", IPV4_IFACE_ADDR); + SYS("ip neigh add %s dev veth1 nud failed", IPV4_NUD_FAILED_ADDR); + SYS("ip neigh add %s dev veth1 lladdr %s nud stale", IPV4_NUD_STALE_ADDR, DMAC); + + err = write_sysctl("/proc/sys/net/ipv4/conf/veth1/forwarding", "1"); + if (!ASSERT_OK(err, "write_sysctl(net.ipv4.conf.veth1.forwarding)")) + goto fail; + + err = write_sysctl("/proc/sys/net/ipv6/conf/veth1/forwarding", "1"); + if (!ASSERT_OK(err, "write_sysctl(net.ipv6.conf.veth1.forwarding)")) + goto fail; + + return 0; +fail: + return -1; +} + +static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) +{ + int ret; + + memset(params, 0, sizeof(*params)); + + params->l4_protocol = IPPROTO_TCP; + params->ifindex = ifindex; + + if (inet_pton(AF_INET6, daddr, params->ipv6_dst) == 1) { + params->family = AF_INET6; + ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src); + if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)")) + return -1; + return 0; + } + + ret = inet_pton(AF_INET, daddr, ¶ms->ipv4_dst); + if (!ASSERT_EQ(ret, 1, "convert IP[46] address")) + return -1; + params->family = AF_INET; + ret = inet_pton(AF_INET, IPV4_IFACE_ADDR, ¶ms->ipv4_src); + if (!ASSERT_EQ(ret, 1, "inet_pton(IPV4_IFACE_ADDR)")) + return -1; + + return 0; +} + +static void mac_str(char *b, const __u8 *mac) +{ + sprintf(b, "%02X:%02X:%02X:%02X:%02X:%02X", + mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]); +} + +void test_fib_lookup(void) +{ + struct bpf_fib_lookup *fib_params; + struct nstoken *nstoken = NULL; + struct __sk_buff skb = { }; + struct fib_lookup *skel; + int prog_fd, err, ret, i; + + /* The test does not use the skb->data, so + * use pkt_v6 for both v6 and v4 test. + */ + LIBBPF_OPTS(bpf_test_run_opts, run_opts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + ); + + skel = fib_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel open_and_load")) + return; + prog_fd = bpf_program__fd(skel->progs.fib_lookup); + + SYS("ip netns add %s", NS_TEST); + + nstoken = open_netns(NS_TEST); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto fail; + + if (setup_netns()) + goto fail; + + ifindex = if_nametoindex("veth1"); + skb.ifindex = ifindex; + fib_params = &skel->bss->fib_params; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + printf("Testing %s\n", tests[i].desc); + + if (set_lookup_params(fib_params, tests[i].daddr)) + continue; + skel->bss->fib_lookup_ret = -1; + skel->bss->lookup_flags = BPF_FIB_LOOKUP_OUTPUT | + tests[i].lookup_flags; + + err = bpf_prog_test_run_opts(prog_fd, &run_opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + continue; + + ASSERT_EQ(tests[i].expected_ret, skel->bss->fib_lookup_ret, + "fib_lookup_ret"); + + ret = memcmp(tests[i].dmac, fib_params->dmac, sizeof(tests[i].dmac)); + if (!ASSERT_EQ(ret, 0, "dmac not match")) { + char expected[18], actual[18]; + + mac_str(expected, tests[i].dmac); + mac_str(actual, fib_params->dmac); + printf("dmac expected %s actual %s\n", expected, actual); + } + } + +fail: + if (nstoken) + close_netns(nstoken); + system("ip netns del " NS_TEST " &> /dev/null"); + fib_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 7c79462d2702..9333f7346d15 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -60,9 +60,9 @@ static __u32 query_prog_id(int prog) __u32 info_len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(prog, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog, &info, &info_len); if (CHECK_FAIL(err || info_len != sizeof(info))) { - perror("bpf_obj_get_info_by_fd"); + perror("bpf_prog_get_info_by_fd"); return 0; } @@ -497,7 +497,7 @@ static void test_link_get_info(int netns, int prog1, int prog2) } info_len = sizeof(info); - err = bpf_obj_get_info_by_fd(link, &info, &info_len); + err = bpf_link_get_info_by_fd(link, &info, &info_len); if (CHECK_FAIL(err)) { perror("bpf_obj_get_info"); goto out_unlink; @@ -521,7 +521,7 @@ static void test_link_get_info(int netns, int prog1, int prog2) link_id = info.id; info_len = sizeof(info); - err = bpf_obj_get_info_by_fd(link, &info, &info_len); + err = bpf_link_get_info_by_fd(link, &info, &info_len); if (CHECK_FAIL(err)) { perror("bpf_obj_get_info"); goto out_unlink; @@ -546,7 +546,7 @@ static void test_link_get_info(int netns, int prog1, int prog2) netns = -1; info_len = sizeof(info); - err = bpf_obj_get_info_by_fd(link, &info, &info_len); + err = bpf_link_get_info_by_fd(link, &info, &info_len); if (CHECK_FAIL(err)) { perror("bpf_obj_get_info"); goto out_unlink; diff --git a/tools/testing/selftests/bpf/prog_tests/htab_reuse.c b/tools/testing/selftests/bpf/prog_tests/htab_reuse.c new file mode 100644 index 000000000000..a742dd994d60 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/htab_reuse.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <sched.h> +#include <stdbool.h> +#include <test_progs.h> +#include "htab_reuse.skel.h" + +struct htab_op_ctx { + int fd; + int loop; + bool stop; +}; + +struct htab_val { + unsigned int lock; + unsigned int data; +}; + +static void *htab_lookup_fn(void *arg) +{ + struct htab_op_ctx *ctx = arg; + int i = 0; + + while (i++ < ctx->loop && !ctx->stop) { + struct htab_val value; + unsigned int key; + + /* Use BPF_F_LOCK to use spin-lock in map value. */ + key = 7; + bpf_map_lookup_elem_flags(ctx->fd, &key, &value, BPF_F_LOCK); + } + + return NULL; +} + +static void *htab_update_fn(void *arg) +{ + struct htab_op_ctx *ctx = arg; + int i = 0; + + while (i++ < ctx->loop && !ctx->stop) { + struct htab_val value; + unsigned int key; + + key = 7; + value.lock = 0; + value.data = key; + bpf_map_update_elem(ctx->fd, &key, &value, BPF_F_LOCK); + bpf_map_delete_elem(ctx->fd, &key); + + key = 24; + value.lock = 0; + value.data = key; + bpf_map_update_elem(ctx->fd, &key, &value, BPF_F_LOCK); + bpf_map_delete_elem(ctx->fd, &key); + } + + return NULL; +} + +void test_htab_reuse(void) +{ + unsigned int i, wr_nr = 1, rd_nr = 4; + pthread_t tids[wr_nr + rd_nr]; + struct htab_reuse *skel; + struct htab_op_ctx ctx; + int err; + + skel = htab_reuse__open_and_load(); + if (!ASSERT_OK_PTR(skel, "htab_reuse__open_and_load")) + return; + + ctx.fd = bpf_map__fd(skel->maps.htab); + ctx.loop = 500; + ctx.stop = false; + + memset(tids, 0, sizeof(tids)); + for (i = 0; i < wr_nr; i++) { + err = pthread_create(&tids[i], NULL, htab_update_fn, &ctx); + if (!ASSERT_OK(err, "pthread_create")) { + ctx.stop = true; + goto reap; + } + } + for (i = 0; i < rd_nr; i++) { + err = pthread_create(&tids[i + wr_nr], NULL, htab_lookup_fn, &ctx); + if (!ASSERT_OK(err, "pthread_create")) { + ctx.stop = true; + goto reap; + } + } + +reap: + for (i = 0; i < wr_nr + rd_nr; i++) { + if (!tids[i]) + continue; + pthread_join(tids[i], NULL); + } + htab_reuse__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c new file mode 100644 index 000000000000..5639428607e6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <network_helpers.h> + +#include "jit_probe_mem.skel.h" + +void test_jit_probe_mem(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct jit_probe_mem *skel; + int ret; + + skel = jit_probe_mem__open_and_load(); + if (!ASSERT_OK_PTR(skel, "jit_probe_mem__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_jit_probe_mem), &opts); + ASSERT_OK(ret, "jit_probe_mem ret"); + ASSERT_OK(opts.retval, "jit_probe_mem opts.retval"); + ASSERT_EQ(skel->data->total_sum, 192, "jit_probe_mem total_sum"); + + jit_probe_mem__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index 73579370bfbd..c07991544a78 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -36,7 +36,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) "cb32_0 %x != %x\n", meta->cb32_0, cb.cb32[0])) return; - if (CHECK(pkt_v6->eth.h_proto != 0xdd86, "check_eth", + if (CHECK(pkt_v6->eth.h_proto != htons(ETH_P_IPV6), "check_eth", "h_proto %x\n", pkt_v6->eth.h_proto)) return; if (CHECK(pkt_v6->iph.nexthdr != 6, "check_ip", diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5af1ee8f0e6e..a543742cd7bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -72,10 +72,12 @@ static struct kfunc_test_params kfunc_tests[] = { /* success cases */ TC_TEST(kfunc_call_test1, 12), TC_TEST(kfunc_call_test2, 3), + TC_TEST(kfunc_call_test4, -1234), TC_TEST(kfunc_call_test_ref_btf_id, 0), TC_TEST(kfunc_call_test_get_mem, 42), SYSCALL_TEST(kfunc_syscall_test, 0), SYSCALL_NULL_CTX_TEST(kfunc_syscall_test_null, 0), + TC_TEST(kfunc_call_test_static_unused_arg, 0), }; struct syscall_test_args { diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index a9229260a6ce..8cd298b78e44 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -10,17 +10,11 @@ #include <test_progs.h> #include "test_kfunc_dynptr_param.skel.h" -static size_t log_buf_sz = 1048576; /* 1 MB */ -static char obj_log_buf[1048576]; - static struct { const char *prog_name; - const char *expected_verifier_err_msg; int expected_runtime_err; } kfunc_dynptr_tests[] = { - {"not_valid_dynptr", "Expected an initialized dynptr as arg #1", 0}, - {"not_ptr_to_stack", "arg#0 expected pointer to stack or dynptr_ptr", 0}, - {"dynptr_data_null", NULL, -EBADMSG}, + {"dynptr_data_null", -EBADMSG}, }; static bool kfunc_not_supported; @@ -38,29 +32,15 @@ static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, return 0; } -static void verify_fail(const char *prog_name, const char *expected_err_msg) +static bool has_pkcs7_kfunc_support(void) { struct test_kfunc_dynptr_param *skel; - LIBBPF_OPTS(bpf_object_open_opts, opts); libbpf_print_fn_t old_print_cb; - struct bpf_program *prog; int err; - opts.kernel_log_buf = obj_log_buf; - opts.kernel_log_size = log_buf_sz; - opts.kernel_log_level = 1; - - skel = test_kfunc_dynptr_param__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "test_kfunc_dynptr_param__open_opts")) - goto cleanup; - - prog = bpf_object__find_program_by_name(skel->obj, prog_name); - if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) - goto cleanup; - - bpf_program__set_autoload(prog, true); - - bpf_map__set_max_entries(skel->maps.ringbuf, getpagesize()); + skel = test_kfunc_dynptr_param__open(); + if (!ASSERT_OK_PTR(skel, "test_kfunc_dynptr_param__open")) + return false; kfunc_not_supported = false; @@ -72,26 +52,18 @@ static void verify_fail(const char *prog_name, const char *expected_err_msg) fprintf(stderr, "%s:SKIP:bpf_verify_pkcs7_signature() kfunc not supported\n", __func__); - test__skip(); - goto cleanup; - } - - if (!ASSERT_ERR(err, "unexpected load success")) - goto cleanup; - - if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) { - fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg); - fprintf(stderr, "Verifier output: %s\n", obj_log_buf); + test_kfunc_dynptr_param__destroy(skel); + return false; } -cleanup: test_kfunc_dynptr_param__destroy(skel); + + return true; } static void verify_success(const char *prog_name, int expected_runtime_err) { struct test_kfunc_dynptr_param *skel; - libbpf_print_fn_t old_print_cb; struct bpf_program *prog; struct bpf_link *link; __u32 next_id; @@ -103,21 +75,7 @@ static void verify_success(const char *prog_name, int expected_runtime_err) skel->bss->pid = getpid(); - bpf_map__set_max_entries(skel->maps.ringbuf, getpagesize()); - - kfunc_not_supported = false; - - old_print_cb = libbpf_set_print(libbpf_print_cb); err = test_kfunc_dynptr_param__load(skel); - libbpf_set_print(old_print_cb); - - if (err < 0 && kfunc_not_supported) { - fprintf(stderr, - "%s:SKIP:bpf_verify_pkcs7_signature() kfunc not supported\n", - __func__); - test__skip(); - goto cleanup; - } if (!ASSERT_OK(err, "test_kfunc_dynptr_param__load")) goto cleanup; @@ -147,15 +105,15 @@ void test_kfunc_dynptr_param(void) { int i; + if (!has_pkcs7_kfunc_support()) + return; + for (i = 0; i < ARRAY_SIZE(kfunc_dynptr_tests); i++) { if (!test__start_subtest(kfunc_dynptr_tests[i].prog_name)) continue; - if (kfunc_dynptr_tests[i].expected_verifier_err_msg) - verify_fail(kfunc_dynptr_tests[i].prog_name, - kfunc_dynptr_tests[i].expected_verifier_err_msg); - else - verify_success(kfunc_dynptr_tests[i].prog_name, - kfunc_dynptr_tests[i].expected_runtime_err); + verify_success(kfunc_dynptr_tests[i].prog_name, + kfunc_dynptr_tests[i].expected_runtime_err); } + RUN_TESTS(test_kfunc_dynptr_param); } diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index c6f37e825f11..113dba349a57 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -322,7 +322,7 @@ static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) return strcmp((const char *) key1, (const char *) key2) == 0; } -static int get_syms(char ***symsp, size_t *cntp) +static int get_syms(char ***symsp, size_t *cntp, bool kernel) { size_t cap = 0, cnt = 0, i; char *name = NULL, **syms = NULL; @@ -349,8 +349,9 @@ static int get_syms(char ***symsp, size_t *cntp) } while (fgets(buf, sizeof(buf), f)) { - /* skip modules */ - if (strchr(buf, '[')) + if (kernel && strchr(buf, '[')) + continue; + if (!kernel && !strchr(buf, '[')) continue; free(name); @@ -404,7 +405,7 @@ error: return err; } -void serial_test_kprobe_multi_bench_attach(void) +static void test_kprobe_multi_bench_attach(bool kernel) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); struct kprobe_multi_empty *skel = NULL; @@ -415,7 +416,7 @@ void serial_test_kprobe_multi_bench_attach(void) char **syms = NULL; size_t cnt = 0, i; - if (!ASSERT_OK(get_syms(&syms, &cnt), "get_syms")) + if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms")) return; skel = kprobe_multi_empty__open_and_load(); @@ -453,6 +454,14 @@ cleanup: } } +void serial_test_kprobe_multi_bench_attach(void) +{ + if (test__start_subtest("kernel")) + test_kprobe_multi_bench_attach(true); + if (test__start_subtest("modules")) + test_kprobe_multi_bench_attach(false); +} + void test_kprobe_multi_test(void) { if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c index 25e5dfa9c315..a3f238f51d05 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c @@ -29,9 +29,9 @@ void test_libbpf_get_fd_by_id_opts(void) if (!ASSERT_OK(ret, "test_libbpf_get_fd_by_id_opts__attach")) goto close_prog; - ret = bpf_obj_get_info_by_fd(bpf_map__fd(skel->maps.data_input), + ret = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.data_input), &info_m, &len); - if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd")) + if (!ASSERT_OK(ret, "bpf_map_get_info_by_fd")) goto close_prog; fd = bpf_map_get_fd_by_id(info_m.id); diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 9a7d4c47af63..0ed8132ce1c3 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -58,12 +58,12 @@ static struct { TEST(inner_map, pop_front) TEST(inner_map, pop_back) #undef TEST - { "map_compat_kprobe", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_kretprobe", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_tp", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_perf", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_raw_tp", "tracing progs cannot use bpf_list_head yet" }, - { "map_compat_raw_tp_w", "tracing progs cannot use bpf_list_head yet" }, + { "map_compat_kprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_kretprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_perf", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_raw_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, + { "map_compat_raw_tp_w", "tracing progs cannot use bpf_{list_head,rb_root} yet" }, { "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" }, { "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" }, { "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" }, @@ -78,8 +78,6 @@ static struct { { "direct_write_head", "direct access to bpf_list_head is disallowed" }, { "direct_read_node", "direct access to bpf_list_node is disallowed" }, { "direct_write_node", "direct access to bpf_list_node is disallowed" }, - { "write_after_push_front", "only read is supported" }, - { "write_after_push_back", "only read is supported" }, { "use_after_unlock_push_front", "invalid mem access 'scalar'" }, { "use_after_unlock_push_back", "invalid mem access 'scalar'" }, { "double_push_front", "arg#1 expected pointer to allocated object" }, @@ -717,6 +715,43 @@ static void test_btf(void) btf__free(btf); break; } + + while (test__start_subtest("btf: list_node and rb_node in same struct")) { + btf = init_btf(); + if (!ASSERT_OK_PTR(btf, "init_btf")) + break; + + id = btf__add_struct(btf, "bpf_rb_node", 24); + if (!ASSERT_EQ(id, 5, "btf__add_struct bpf_rb_node")) + break; + id = btf__add_struct(btf, "bar", 40); + if (!ASSERT_EQ(id, 6, "btf__add_struct bar")) + break; + err = btf__add_field(btf, "a", LIST_NODE, 0, 0); + if (!ASSERT_OK(err, "btf__add_field bar::a")) + break; + err = btf__add_field(btf, "c", 5, 128, 0); + if (!ASSERT_OK(err, "btf__add_field bar::c")) + break; + + id = btf__add_struct(btf, "foo", 20); + if (!ASSERT_EQ(id, 7, "btf__add_struct foo")) + break; + err = btf__add_field(btf, "a", LIST_HEAD, 0, 0); + if (!ASSERT_OK(err, "btf__add_field foo::a")) + break; + err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0); + if (!ASSERT_OK(err, "btf__add_field foo::b")) + break; + id = btf__add_decl_tag(btf, "contains:bar:a", 7, 0); + if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:bar:a")) + break; + + err = btf__load_into_kernel(btf); + ASSERT_EQ(err, -EINVAL, "check btf"); + btf__free(btf); + break; + } } void test_linked_list(void) diff --git a/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c index f117bfef68a1..130a3b21e467 100644 --- a/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c +++ b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c @@ -47,7 +47,8 @@ static __u32 query_prog_cnt(int cgroup_fd, const char *attach_func) fd = bpf_prog_get_fd_by_id(p.prog_ids[i]); ASSERT_GE(fd, 0, "prog_get_fd_by_id"); - ASSERT_OK(bpf_obj_get_info_by_fd(fd, &info, &info_len), "prog_info_by_fd"); + ASSERT_OK(bpf_prog_get_info_by_fd(fd, &info, &info_len), + "prog_info_by_fd"); close(fd); if (info.attach_btf_id == diff --git a/tools/testing/selftests/bpf/prog_tests/metadata.c b/tools/testing/selftests/bpf/prog_tests/metadata.c index 2c53eade88e3..8b67dfc10f5c 100644 --- a/tools/testing/selftests/bpf/prog_tests/metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/metadata.c @@ -16,7 +16,7 @@ static int duration; static int prog_holds_map(int prog_fd, int map_fd) { struct bpf_prog_info prog_info = {}; - struct bpf_prog_info map_info = {}; + struct bpf_map_info map_info = {}; __u32 prog_info_len; __u32 map_info_len; __u32 *map_ids; @@ -25,12 +25,12 @@ static int prog_holds_map(int prog_fd, int map_fd) int i; map_info_len = sizeof(map_info); - ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); + ret = bpf_map_get_info_by_fd(map_fd, &map_info, &map_info_len); if (ret) return -errno; prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) return -errno; @@ -44,7 +44,7 @@ static int prog_holds_map(int prog_fd, int map_fd) prog_info.map_ids = ptr_to_u64(map_ids); prog_info_len = sizeof(prog_info); - ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); + ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len); if (ret) { ret = -errno; goto free_map_ids; diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c index eb2feaac81fe..653b0a20fab9 100644 --- a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c @@ -488,7 +488,7 @@ static void run_test(struct migrate_reuseport_test_case *test_case, goto close_servers; } - /* Tie requests to the first four listners */ + /* Tie requests to the first four listeners */ err = start_clients(test_case); if (!ASSERT_OK(err, "start_clients")) goto close_clients; diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 37b002ca1167..a271d5a0f7ab 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -64,7 +64,7 @@ void test_mmap(void) /* get map's ID */ memset(&map_info, 0, map_info_sz); - err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz); + err = bpf_map_get_info_by_fd(data_map_fd, &map_info, &map_info_sz); if (CHECK(err, "map_get_info", "failed %d\n", errno)) goto cleanup; data_map_id = map_info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/nested_trust.c b/tools/testing/selftests/bpf/prog_tests/nested_trust.c new file mode 100644 index 000000000000..39886f58924e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/nested_trust.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "nested_trust_failure.skel.h" +#include "nested_trust_success.skel.h" + +void test_nested_trust(void) +{ + RUN_TESTS(nested_trust_success); + RUN_TESTS(nested_trust_failure); +} diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index 224eba6fef2e..3a25f1c743a1 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -54,7 +54,7 @@ void serial_test_perf_link(void) goto cleanup; memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len); + err = bpf_link_get_info_by_fd(link_fd, &info, &info_len); if (!ASSERT_OK(err, "link_get_info")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c index d95cee5867b7..c799a3c5ad1f 100644 --- a/tools/testing/selftests/bpf/prog_tests/pinning.c +++ b/tools/testing/selftests/bpf/prog_tests/pinning.c @@ -18,7 +18,7 @@ __u32 get_map_id(struct bpf_object *obj, const char *name) if (CHECK(!map, "find map", "NULL map")) return 0; - err = bpf_obj_get_info_by_fd(bpf_map__fd(map), + err = bpf_map_get_info_by_fd(bpf_map__fd(map), &map_info, &map_info_len); CHECK(err, "get map info", "err %d errno %d", err, errno); return map_info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c index 1ccd2bdf8fa8..01f1d1b6715a 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c @@ -12,7 +12,7 @@ static void check_run_cnt(int prog_fd, __u64 run_cnt) __u32 info_len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c new file mode 100644 index 000000000000..156fa95c42f6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include <network_helpers.h> + +#include "rbtree.skel.h" +#include "rbtree_fail.skel.h" +#include "rbtree_btf_fail__wrong_node_type.skel.h" +#include "rbtree_btf_fail__add_wrong_type.skel.h" + +static void test_rbtree_add_nodes(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct rbtree *skel; + int ret; + + skel = rbtree__open_and_load(); + if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_nodes), &opts); + ASSERT_OK(ret, "rbtree_add_nodes run"); + ASSERT_OK(opts.retval, "rbtree_add_nodes retval"); + ASSERT_EQ(skel->data->less_callback_ran, 1, "rbtree_add_nodes less_callback_ran"); + + rbtree__destroy(skel); +} + +static void test_rbtree_add_and_remove(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct rbtree *skel; + int ret; + + skel = rbtree__open_and_load(); + if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_and_remove), &opts); + ASSERT_OK(ret, "rbtree_add_and_remove"); + ASSERT_OK(opts.retval, "rbtree_add_and_remove retval"); + ASSERT_EQ(skel->data->removed_key, 5, "rbtree_add_and_remove first removed key"); + + rbtree__destroy(skel); +} + +static void test_rbtree_first_and_remove(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct rbtree *skel; + int ret; + + skel = rbtree__open_and_load(); + if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_first_and_remove), &opts); + ASSERT_OK(ret, "rbtree_first_and_remove"); + ASSERT_OK(opts.retval, "rbtree_first_and_remove retval"); + ASSERT_EQ(skel->data->first_data[0], 2, "rbtree_first_and_remove first rbtree_first()"); + ASSERT_EQ(skel->data->removed_key, 1, "rbtree_first_and_remove first removed key"); + ASSERT_EQ(skel->data->first_data[1], 4, "rbtree_first_and_remove second rbtree_first()"); + + rbtree__destroy(skel); +} + +void test_rbtree_success(void) +{ + if (test__start_subtest("rbtree_add_nodes")) + test_rbtree_add_nodes(); + if (test__start_subtest("rbtree_add_and_remove")) + test_rbtree_add_and_remove(); + if (test__start_subtest("rbtree_first_and_remove")) + test_rbtree_first_and_remove(); +} + +#define BTF_FAIL_TEST(suffix) \ +void test_rbtree_btf_fail__##suffix(void) \ +{ \ + struct rbtree_btf_fail__##suffix *skel; \ + \ + skel = rbtree_btf_fail__##suffix##__open_and_load(); \ + if (!ASSERT_ERR_PTR(skel, \ + "rbtree_btf_fail__" #suffix "__open_and_load unexpected success")) \ + rbtree_btf_fail__##suffix##__destroy(skel); \ +} + +#define RUN_BTF_FAIL_TEST(suffix) \ + if (test__start_subtest("rbtree_btf_fail__" #suffix)) \ + test_rbtree_btf_fail__##suffix(); + +BTF_FAIL_TEST(wrong_node_type); +BTF_FAIL_TEST(add_wrong_type); + +void test_rbtree_btf_fail(void) +{ + RUN_BTF_FAIL_TEST(wrong_node_type); + RUN_BTF_FAIL_TEST(add_wrong_type); +} + +void test_rbtree_fail(void) +{ + RUN_TESTS(rbtree_fail); +} diff --git a/tools/testing/selftests/bpf/prog_tests/recursion.c b/tools/testing/selftests/bpf/prog_tests/recursion.c index f3af2627b599..23552d3e3365 100644 --- a/tools/testing/selftests/bpf/prog_tests/recursion.c +++ b/tools/testing/selftests/bpf/prog_tests/recursion.c @@ -31,8 +31,8 @@ void test_recursion(void) bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key); ASSERT_EQ(skel->bss->pass2, 2, "pass2 == 2"); - err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_delete), - &prog_info, &prog_info_len); + err = bpf_prog_get_info_by_fd(bpf_program__fd(skel->progs.on_delete), + &prog_info, &prog_info_len); if (!ASSERT_OK(err, "get_prog_info")) goto out; ASSERT_EQ(prog_info.recursion_misses, 2, "recursion_misses"); diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c index 018611e6b248..7d4a9b3d3722 100644 --- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c @@ -4,6 +4,7 @@ #define _GNU_SOURCE #include <sched.h> #include <linux/socket.h> +#include <linux/tls.h> #include <net/if.h> #include "test_progs.h" @@ -83,6 +84,76 @@ static void test_udp(int family) ASSERT_EQ(bss->nr_binddev, 1, "nr_bind"); } +static void test_ktls(int family) +{ + struct tls12_crypto_info_aes_gcm_128 aes128; + struct setget_sockopt__bss *bss = skel->bss; + int cfd = -1, sfd = -1, fd = -1, ret; + char buf; + + memset(bss, 0, sizeof(*bss)); + + sfd = start_server(family, SOCK_STREAM, + family == AF_INET6 ? addr6_str : addr4_str, 0, 0); + if (!ASSERT_GE(sfd, 0, "start_server")) + return; + fd = connect_to_fd(sfd, 0); + if (!ASSERT_GE(fd, 0, "connect_to_fd")) + goto err_out; + + cfd = accept(sfd, NULL, 0); + if (!ASSERT_GE(cfd, 0, "accept")) + goto err_out; + + close(sfd); + sfd = -1; + + /* Setup KTLS */ + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (!ASSERT_OK(ret, "setsockopt")) + goto err_out; + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (!ASSERT_OK(ret, "setsockopt")) + goto err_out; + + memset(&aes128, 0, sizeof(aes128)); + aes128.info.version = TLS_1_2_VERSION; + aes128.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + ret = setsockopt(fd, SOL_TLS, TLS_TX, &aes128, sizeof(aes128)); + if (!ASSERT_OK(ret, "setsockopt")) + goto err_out; + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &aes128, sizeof(aes128)); + if (!ASSERT_OK(ret, "setsockopt")) + goto err_out; + + /* KTLS is enabled */ + + close(fd); + /* At this point, the cfd socket is at the CLOSE_WAIT state + * and still run TLS protocol. The test for + * BPF_TCP_CLOSE_WAIT should be run at this point. + */ + ret = read(cfd, &buf, sizeof(buf)); + ASSERT_EQ(ret, 0, "read"); + close(cfd); + + ASSERT_EQ(bss->nr_listen, 1, "nr_listen"); + ASSERT_EQ(bss->nr_connect, 1, "nr_connect"); + ASSERT_EQ(bss->nr_active, 1, "nr_active"); + ASSERT_EQ(bss->nr_passive, 1, "nr_passive"); + ASSERT_EQ(bss->nr_socket_post_create, 2, "nr_socket_post_create"); + ASSERT_EQ(bss->nr_binddev, 2, "nr_bind"); + ASSERT_EQ(bss->nr_fin_wait1, 1, "nr_fin_wait1"); + return; + +err_out: + close(fd); + close(cfd); + close(sfd); +} + void test_setget_sockopt(void) { cg_fd = test__join_cgroup(CG_NAME); @@ -118,6 +189,8 @@ void test_setget_sockopt(void) test_tcp(AF_INET); test_udp(AF_INET6); test_udp(AF_INET); + test_ktls(AF_INET6); + test_ktls(AF_INET); done: setget_sockopt__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3e190ed63976..1374b626a985 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -29,7 +29,23 @@ static int stop, duration; static bool configure_stack(void) { + char tc_version[128]; char tc_cmd[BUFSIZ]; + char *prog; + FILE *tc; + + /* Check whether tc is built with libbpf. */ + tc = popen("tc -V", "r"); + if (CHECK_FAIL(!tc)) + return false; + if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) + return false; + if (strstr(tc_version, ", libbpf ")) + prog = "test_sk_assign_libbpf.bpf.o"; + else + prog = "test_sk_assign.bpf.o"; + if (CHECK_FAIL(pclose(tc))) + return false; /* Move to a new networking namespace */ if (CHECK_FAIL(unshare(CLONE_NEWNET))) @@ -46,8 +62,8 @@ configure_stack(void) /* Load qdisc, BPF program */ if (CHECK_FAIL(system("tc qdisc add dev lo clsact"))) return false; - sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", - "direct-action object-file ./test_sk_assign.bpf.o", + sprintf(tc_cmd, "%s %s %s %s %s", "tc filter add dev lo ingress bpf", + "direct-action object-file", prog, "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", @@ -129,15 +145,12 @@ get_port(int fd) static ssize_t rcv_msg(int srv_client, int type) { - struct sockaddr_storage ss; char buf[BUFSIZ]; - socklen_t slen; if (type == SOCK_STREAM) return read(srv_client, &buf, sizeof(buf)); else - return recvfrom(srv_client, &buf, sizeof(buf), 0, - (struct sockaddr *)&ss, &slen); + return recvfrom(srv_client, &buf, sizeof(buf), 0, NULL, NULL); } static int diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0aa088900699..0ce25a967481 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -299,9 +299,9 @@ static __u32 query_prog_id(int prog_fd) __u32 info_len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") || - !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") || + !ASSERT_EQ(info_len, sizeof(info), "bpf_prog_get_info_by_fd")) return 0; return info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c index 18848c31e36f..f79fa5bc9a8d 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c @@ -9,9 +9,6 @@ #include "task_kfunc_failure.skel.h" #include "task_kfunc_success.skel.h" -static size_t log_buf_sz = 1 << 20; /* 1 MB */ -static char obj_log_buf[1048576]; - static struct task_kfunc_success *open_load_task_kfunc_skel(void) { struct task_kfunc_success *skel; @@ -83,67 +80,6 @@ static const char * const success_tests[] = { "test_task_from_pid_invalid", }; -static struct { - const char *prog_name; - const char *expected_err_msg; -} failure_tests[] = { - {"task_kfunc_acquire_untrusted", "R1 must be referenced or trusted"}, - {"task_kfunc_acquire_fp", "arg#0 pointer type STRUCT task_struct must point"}, - {"task_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"}, - {"task_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"}, - {"task_kfunc_acquire_null", "arg#0 pointer type STRUCT task_struct must point"}, - {"task_kfunc_acquire_unreleased", "Unreleased reference"}, - {"task_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"}, - {"task_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"}, - {"task_kfunc_get_null", "arg#0 expected pointer to map value"}, - {"task_kfunc_xchg_unreleased", "Unreleased reference"}, - {"task_kfunc_get_unreleased", "Unreleased reference"}, - {"task_kfunc_release_untrusted", "arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket"}, - {"task_kfunc_release_fp", "arg#0 pointer type STRUCT task_struct must point"}, - {"task_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"}, - {"task_kfunc_release_unacquired", "release kernel function bpf_task_release expects"}, - {"task_kfunc_from_pid_no_null_check", "arg#0 is ptr_or_null_ expected ptr_ or socket"}, - {"task_kfunc_from_lsm_task_free", "reg type unsupported for arg#0 function"}, -}; - -static void verify_fail(const char *prog_name, const char *expected_err_msg) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - struct task_kfunc_failure *skel; - int err, i; - - opts.kernel_log_buf = obj_log_buf; - opts.kernel_log_size = log_buf_sz; - opts.kernel_log_level = 1; - - skel = task_kfunc_failure__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "task_kfunc_failure__open_opts")) - goto cleanup; - - for (i = 0; i < ARRAY_SIZE(failure_tests); i++) { - struct bpf_program *prog; - const char *curr_name = failure_tests[i].prog_name; - - prog = bpf_object__find_program_by_name(skel->obj, curr_name); - if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) - goto cleanup; - - bpf_program__set_autoload(prog, !strcmp(curr_name, prog_name)); - } - - err = task_kfunc_failure__load(skel); - if (!ASSERT_ERR(err, "unexpected load success")) - goto cleanup; - - if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) { - fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg); - fprintf(stderr, "Verifier output: %s\n", obj_log_buf); - } - -cleanup: - task_kfunc_failure__destroy(skel); -} - void test_task_kfunc(void) { int i; @@ -155,10 +91,5 @@ void test_task_kfunc(void) run_success_test(success_tests[i]); } - for (i = 0; i < ARRAY_SIZE(failure_tests); i++) { - if (!test__start_subtest(failure_tests[i].prog_name)) - continue; - - verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg); - } + RUN_TESTS(task_kfunc_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c index a176bd75a748..ea8537c54413 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c @@ -119,19 +119,19 @@ static void test_recursion(void) prog_fd = bpf_program__fd(skel->progs.on_lookup); memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); ASSERT_OK(err, "get prog info"); ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion"); prog_fd = bpf_program__fd(skel->progs.on_update); memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); ASSERT_OK(err, "get prog info"); ASSERT_EQ(info.recursion_misses, 0, "on_update prog recursion"); prog_fd = bpf_program__fd(skel->progs.on_enter); memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); ASSERT_OK(err, "get prog info"); ASSERT_EQ(info.recursion_misses, 0, "on_enter prog recursion"); @@ -221,7 +221,7 @@ static void test_nodeadlock(void) info_len = sizeof(info); prog_fd = bpf_program__fd(skel->progs.socket_post_create); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); ASSERT_OK(err, "get prog info"); ASSERT_EQ(info.recursion_misses, 0, "prog recursion"); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c index 4a505a5adf4d..e873766276d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c @@ -29,8 +29,8 @@ static int test_tc_bpf_basic(const struct bpf_tc_hook *hook, int fd) __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")) + ret = bpf_prog_get_info_by_fd(fd, &info, &info_len); + if (!ASSERT_OK(ret, "bpf_prog_get_info_by_fd")) return ret; ret = bpf_tc_attach(hook, &opts); diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c index c381faaae741..2900c5e9a016 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright 2022 Sony Group Corporation */ +#define _GNU_SOURCE +#include <fcntl.h> #include <sys/prctl.h> #include <test_progs.h> #include "bpf_syscall_macro.skel.h" @@ -13,6 +15,8 @@ void test_bpf_syscall_macro(void) unsigned long exp_arg3 = 13; unsigned long exp_arg4 = 14; unsigned long exp_arg5 = 15; + loff_t off_in, off_out; + ssize_t r; /* check whether it can open program */ skel = bpf_syscall_macro__open(); @@ -33,6 +37,7 @@ void test_bpf_syscall_macro(void) /* check whether args of syscall are copied correctly */ prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5); + #if defined(__aarch64__) || defined(__s390__) ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); #else @@ -68,6 +73,18 @@ void test_bpf_syscall_macro(void) ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4"); ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5"); + r = splice(-42, &off_in, 42, &off_out, 0x12340000, SPLICE_F_NONBLOCK); + err = -errno; + ASSERT_EQ(r, -1, "splice_res"); + ASSERT_EQ(err, -EBADF, "splice_err"); + + ASSERT_EQ(skel->bss->splice_fd_in, -42, "splice_arg1"); + ASSERT_EQ(skel->bss->splice_off_in, (__u64)&off_in, "splice_arg2"); + ASSERT_EQ(skel->bss->splice_fd_out, 42, "splice_arg3"); + ASSERT_EQ(skel->bss->splice_off_out, (__u64)&off_out, "splice_arg4"); + ASSERT_EQ(skel->bss->splice_len, 0x12340000, "splice_arg5"); + ASSERT_EQ(skel->bss->splice_flags, SPLICE_F_NONBLOCK, "splice_arg6"); + cleanup: bpf_syscall_macro__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 7295cc60f724..e0879df38639 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -1,104 +1,43 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include <test_progs.h> - -const char *err_str; -bool found; - -static int libbpf_debug_print(enum libbpf_print_level level, - const char *format, va_list args) -{ - char *log_buf; - - if (level != LIBBPF_WARN || - strcmp(format, "libbpf: \n%s\n")) { - vprintf(format, args); - return 0; - } - - log_buf = va_arg(args, char *); - if (!log_buf) - goto out; - if (err_str && strstr(log_buf, err_str) == 0) - found = true; -out: - printf(format, log_buf); - return 0; -} - -extern int extra_prog_load_log_flags; - -static int check_load(const char *file) -{ - struct bpf_object *obj = NULL; - struct bpf_program *prog; - int err; - - found = false; - - obj = bpf_object__open_file(file, NULL); - err = libbpf_get_error(obj); - if (err) - return err; - - prog = bpf_object__next_program(obj, NULL); - if (!prog) { - err = -ENOENT; - goto err_out; - } - - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); - bpf_program__set_log_level(prog, extra_prog_load_log_flags); - - err = bpf_object__load(obj); - -err_out: - bpf_object__close(obj); - return err; -} - -struct test_def { - const char *file; - const char *err_str; -}; +#include "test_global_func1.skel.h" +#include "test_global_func2.skel.h" +#include "test_global_func3.skel.h" +#include "test_global_func4.skel.h" +#include "test_global_func5.skel.h" +#include "test_global_func6.skel.h" +#include "test_global_func7.skel.h" +#include "test_global_func8.skel.h" +#include "test_global_func9.skel.h" +#include "test_global_func10.skel.h" +#include "test_global_func11.skel.h" +#include "test_global_func12.skel.h" +#include "test_global_func13.skel.h" +#include "test_global_func14.skel.h" +#include "test_global_func15.skel.h" +#include "test_global_func16.skel.h" +#include "test_global_func17.skel.h" +#include "test_global_func_ctx_args.skel.h" void test_test_global_funcs(void) { - struct test_def tests[] = { - { "test_global_func1.bpf.o", "combined stack size of 4 calls is 544" }, - { "test_global_func2.bpf.o" }, - { "test_global_func3.bpf.o", "the call stack of 8 frames" }, - { "test_global_func4.bpf.o" }, - { "test_global_func5.bpf.o", "expected pointer to ctx, but got PTR" }, - { "test_global_func6.bpf.o", "modified ctx ptr R2" }, - { "test_global_func7.bpf.o", "foo() doesn't return scalar" }, - { "test_global_func8.bpf.o" }, - { "test_global_func9.bpf.o" }, - { "test_global_func10.bpf.o", "invalid indirect read from stack" }, - { "test_global_func11.bpf.o", "Caller passes invalid args into func#1" }, - { "test_global_func12.bpf.o", "invalid mem access 'mem_or_null'" }, - { "test_global_func13.bpf.o", "Caller passes invalid args into func#1" }, - { "test_global_func14.bpf.o", "reference type('FWD S') size cannot be determined" }, - { "test_global_func15.bpf.o", "At program exit the register R0 has value" }, - { "test_global_func16.bpf.o", "invalid indirect read from stack" }, - { "test_global_func17.bpf.o", "Caller passes invalid args into func#1" }, - }; - libbpf_print_fn_t old_print_fn = NULL; - int err, i, duration = 0; - - old_print_fn = libbpf_set_print(libbpf_debug_print); - - for (i = 0; i < ARRAY_SIZE(tests); i++) { - const struct test_def *test = &tests[i]; - - if (!test__start_subtest(test->file)) - continue; - - err_str = test->err_str; - err = check_load(test->file); - CHECK_FAIL(!!err ^ !!err_str); - if (err_str) - CHECK(found, "", "expected string '%s'", err_str); - } - libbpf_set_print(old_print_fn); + RUN_TESTS(test_global_func1); + RUN_TESTS(test_global_func2); + RUN_TESTS(test_global_func3); + RUN_TESTS(test_global_func4); + RUN_TESTS(test_global_func5); + RUN_TESTS(test_global_func6); + RUN_TESTS(test_global_func7); + RUN_TESTS(test_global_func8); + RUN_TESTS(test_global_func9); + RUN_TESTS(test_global_func10); + RUN_TESTS(test_global_func11); + RUN_TESTS(test_global_func12); + RUN_TESTS(test_global_func13); + RUN_TESTS(test_global_func14); + RUN_TESTS(test_global_func15); + RUN_TESTS(test_global_func16); + RUN_TESTS(test_global_func17); + RUN_TESTS(test_global_func_ctx_args); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 244c01125126..16175d579bc7 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -75,7 +75,8 @@ static int test_lsm(struct lsm *skel) skel->bss->monitored_pid = getpid(); err = stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) return err; ASSERT_EQ(skel->bss->mprotect_count, 1, "mprotect_count"); diff --git a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c index a479080533db..770fcc3bb1ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c +++ b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c @@ -45,8 +45,9 @@ void serial_test_tp_attach_query(void) prog_info.xlated_prog_len = 0; prog_info.nr_map_ids = 0; info_len = sizeof(prog_info); - err = bpf_obj_get_info_by_fd(prog_fd[i], &prog_info, &info_len); - if (CHECK(err, "bpf_obj_get_info_by_fd", "err %d errno %d\n", + err = bpf_prog_get_info_by_fd(prog_fd[i], &prog_info, + &info_len); + if (CHECK(err, "bpf_prog_get_info_by_fd", "err %d errno %d\n", err, errno)) goto cleanup1; saved_prog_ids[i] = prog_info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 564b75bc087f..e91d0d1769f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -2,8 +2,6 @@ #define _GNU_SOURCE #include <test_progs.h> -#define MAX_TRAMP_PROGS 38 - struct inst { struct bpf_object *obj; struct bpf_link *link; @@ -37,14 +35,21 @@ void serial_test_trampoline_count(void) { char *file = "test_trampoline_count.bpf.o"; char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" }; - struct inst inst[MAX_TRAMP_PROGS + 1] = {}; + int bpf_max_tramp_links, err, i, prog_fd; struct bpf_program *prog; struct bpf_link *link; - int prog_fd, err, i; + struct inst *inst; LIBBPF_OPTS(bpf_test_run_opts, opts); + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + inst = calloc(bpf_max_tramp_links + 1, sizeof(*inst)); + if (!ASSERT_OK_PTR(inst, "inst")) + return; + /* attach 'allowed' trampoline programs */ - for (i = 0; i < MAX_TRAMP_PROGS; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]); if (!prog) goto cleanup; @@ -74,7 +79,7 @@ void serial_test_trampoline_count(void) if (!ASSERT_EQ(link, NULL, "ptr_is_null")) goto cleanup; - /* and finaly execute the probe */ + /* and finally execute the probe */ prog_fd = bpf_program__fd(prog); if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) goto cleanup; @@ -91,4 +96,5 @@ cleanup: bpf_link__destroy(inst[i].link); bpf_object__close(inst[i].obj); } + free(inst); } diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c index 1ed3cc2092db..8383a99f610f 100644 --- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -179,7 +179,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s ASSERT_EQ(bpf_prog_get_next_id(prog_id, &next), -EPERM, "prog_get_next_id_fails"); ASSERT_EQ(bpf_prog_get_next_id(0, &next), -EPERM, "prog_get_next_id_fails"); - if (ASSERT_OK(bpf_obj_get_info_by_fd(map_fds[0], &map_info, &map_info_len), + if (ASSERT_OK(bpf_map_get_info_by_fd(map_fds[0], &map_info, &map_info_len), "obj_get_info_by_fd")) { ASSERT_EQ(bpf_map_get_fd_by_id(map_info.id), -EPERM, "map_get_fd_by_id_fails"); ASSERT_EQ(bpf_map_get_next_id(map_info.id, &next), -EPERM, @@ -187,8 +187,8 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s } ASSERT_EQ(bpf_map_get_next_id(0, &next), -EPERM, "map_get_next_id_fails"); - if (ASSERT_OK(bpf_obj_get_info_by_fd(bpf_link__fd(skel->links.sys_nanosleep_enter), - &link_info, &link_info_len), + if (ASSERT_OK(bpf_link_get_info_by_fd(bpf_link__fd(skel->links.sys_nanosleep_enter), + &link_info, &link_info_len), "obj_get_info_by_fd")) { ASSERT_EQ(bpf_link_get_fd_by_id(link_info.id), -EPERM, "link_get_fd_by_id_fails"); ASSERT_EQ(bpf_link_get_next_id(link_info.id, &next), -EPERM, @@ -269,7 +269,7 @@ void test_unpriv_bpf_disabled(void) } prog_fd = bpf_program__fd(skel->progs.sys_nanosleep_enter); - ASSERT_OK(bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len), + ASSERT_OK(bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len), "obj_get_info_by_fd"); prog_id = prog_info.id; ASSERT_GT(prog_id, 0, "valid_prog_id"); diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c index 35b87c7ba5be..6558c857e620 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c @@ -3,20 +3,23 @@ #include <test_progs.h> #include "test_uprobe_autoattach.skel.h" +#include "progs/bpf_misc.h" /* uprobe attach point */ -static noinline int autoattach_trigger_func(int arg) +static noinline int autoattach_trigger_func(int arg1, int arg2, int arg3, + int arg4, int arg5, int arg6, + int arg7, int arg8) { asm volatile (""); - return arg + 1; + return arg1 + arg2 + arg3 + arg4 + arg5 + arg6 + arg7 + arg8 + 1; } void test_uprobe_autoattach(void) { + const char *devnull_str = "/dev/null"; struct test_uprobe_autoattach *skel; - int trigger_val = 100, trigger_ret; - size_t malloc_sz = 1; - char *mem; + int trigger_ret; + FILE *devnull; skel = test_uprobe_autoattach__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -28,23 +31,45 @@ void test_uprobe_autoattach(void) skel->bss->test_pid = getpid(); /* trigger & validate uprobe & uretprobe */ - trigger_ret = autoattach_trigger_func(trigger_val); + trigger_ret = autoattach_trigger_func(1, 2, 3, 4, 5, 6, 7, 8); skel->bss->test_pid = getpid(); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(malloc_sz); + devnull = fopen(devnull_str, "r"); - ASSERT_EQ(skel->bss->uprobe_byname_parm1, trigger_val, "check_uprobe_byname_parm1"); + ASSERT_EQ(skel->bss->uprobe_byname_parm1, 1, "check_uprobe_byname_parm1"); ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran"); ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc"); + ASSERT_EQ(skel->bss->uretprobe_byname_ret, trigger_ret, "check_uretprobe_byname_ret"); ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran"); - ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1"); + ASSERT_EQ(skel->bss->uprobe_byname2_parm1, (__u64)(long)devnull_str, + "check_uprobe_byname2_parm1"); ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran"); - ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc"); + ASSERT_EQ(skel->bss->uretprobe_byname2_rc, (__u64)(long)devnull, + "check_uretprobe_byname2_rc"); ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran"); - free(mem); + ASSERT_EQ(skel->bss->a[0], 1, "arg1"); + ASSERT_EQ(skel->bss->a[1], 2, "arg2"); + ASSERT_EQ(skel->bss->a[2], 3, "arg3"); +#if FUNC_REG_ARG_CNT > 3 + ASSERT_EQ(skel->bss->a[3], 4, "arg4"); +#endif +#if FUNC_REG_ARG_CNT > 4 + ASSERT_EQ(skel->bss->a[4], 5, "arg5"); +#endif +#if FUNC_REG_ARG_CNT > 5 + ASSERT_EQ(skel->bss->a[5], 6, "arg6"); +#endif +#if FUNC_REG_ARG_CNT > 6 + ASSERT_EQ(skel->bss->a[6], 7, "arg7"); +#endif +#if FUNC_REG_ARG_CNT > 7 + ASSERT_EQ(skel->bss->a[7], 8, "arg8"); +#endif + + fclose(devnull); cleanup: test_uprobe_autoattach__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c index 9ad9da0f215e..56ed1eb9b527 100644 --- a/tools/testing/selftests/bpf/prog_tests/usdt.c +++ b/tools/testing/selftests/bpf/prog_tests/usdt.c @@ -314,6 +314,7 @@ static FILE *urand_spawn(int *pid) if (fscanf(f, "%d", pid) != 1) { pclose(f); + errno = EINVAL; return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c index dae68de285b9..3a13e102c149 100644 --- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c @@ -19,8 +19,6 @@ #include "../progs/test_user_ringbuf.h" -static size_t log_buf_sz = 1 << 20; /* 1 MB */ -static char obj_log_buf[1048576]; static const long c_sample_size = sizeof(struct sample) + BPF_RINGBUF_HDR_SZ; static const long c_ringbuf_size = 1 << 12; /* 1 small page */ static const long c_max_entries = c_ringbuf_size / c_sample_size; @@ -663,23 +661,6 @@ cleanup: user_ringbuf_success__destroy(skel); } -static struct { - const char *prog_name; - const char *expected_err_msg; -} failure_tests[] = { - /* failure cases */ - {"user_ringbuf_callback_bad_access1", "negative offset dynptr_ptr ptr"}, - {"user_ringbuf_callback_bad_access2", "dereference of modified dynptr_ptr ptr"}, - {"user_ringbuf_callback_write_forbidden", "invalid mem access 'dynptr_ptr'"}, - {"user_ringbuf_callback_null_context_write", "invalid mem access 'scalar'"}, - {"user_ringbuf_callback_null_context_read", "invalid mem access 'scalar'"}, - {"user_ringbuf_callback_discard_dynptr", "cannot release unowned const bpf_dynptr"}, - {"user_ringbuf_callback_submit_dynptr", "cannot release unowned const bpf_dynptr"}, - {"user_ringbuf_callback_invalid_return", "At callback return the register R0 has value"}, - {"user_ringbuf_callback_reinit_dynptr_mem", "Dynptr has to be an uninitialized dynptr"}, - {"user_ringbuf_callback_reinit_dynptr_ringbuf", "Dynptr has to be an uninitialized dynptr"}, -}; - #define SUCCESS_TEST(_func) { _func, #_func } static struct { @@ -700,42 +681,6 @@ static struct { SUCCESS_TEST(test_user_ringbuf_blocking_reserve), }; -static void verify_fail(const char *prog_name, const char *expected_err_msg) -{ - LIBBPF_OPTS(bpf_object_open_opts, opts); - struct bpf_program *prog; - struct user_ringbuf_fail *skel; - int err; - - opts.kernel_log_buf = obj_log_buf; - opts.kernel_log_size = log_buf_sz; - opts.kernel_log_level = 1; - - skel = user_ringbuf_fail__open_opts(&opts); - if (!ASSERT_OK_PTR(skel, "dynptr_fail__open_opts")) - goto cleanup; - - prog = bpf_object__find_program_by_name(skel->obj, prog_name); - if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) - goto cleanup; - - bpf_program__set_autoload(prog, true); - - bpf_map__set_max_entries(skel->maps.user_ringbuf, getpagesize()); - - err = user_ringbuf_fail__load(skel); - if (!ASSERT_ERR(err, "unexpected load success")) - goto cleanup; - - if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) { - fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg); - fprintf(stderr, "Verifier output: %s\n", obj_log_buf); - } - -cleanup: - user_ringbuf_fail__destroy(skel); -} - void test_user_ringbuf(void) { int i; @@ -747,10 +692,5 @@ void test_user_ringbuf(void) success_tests[i].test_callback(); } - for (i = 0; i < ARRAY_SIZE(failure_tests); i++) { - if (!test__start_subtest(failure_tests[i].prog_name)) - continue; - - verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg); - } + RUN_TESTS(user_ringbuf_fail); } diff --git a/tools/testing/selftests/bpf/prog_tests/verif_stats.c b/tools/testing/selftests/bpf/prog_tests/verif_stats.c index a47e7c0e1ffd..af4b95f57ac1 100644 --- a/tools/testing/selftests/bpf/prog_tests/verif_stats.c +++ b/tools/testing/selftests/bpf/prog_tests/verif_stats.c @@ -16,8 +16,9 @@ void test_verif_stats(void) if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load")) goto cleanup; - err = bpf_obj_get_info_by_fd(skel->progs.sys_enter.prog_fd, &info, &len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(skel->progs.sys_enter.prog_fd, + &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) goto cleanup; if (!ASSERT_GT(info.verified_insns, 0, "verified_insns")) diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c index 579d6ee83ce0..dd7f2bc70048 100644 --- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c @@ -61,6 +61,9 @@ static bool kfunc_not_supported; static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, va_list args) { + if (level == LIBBPF_WARN) + vprintf(fmt, args); + if (strcmp(fmt, "libbpf: extern (func ksym) '%s': not found in kernel or module BTFs\n")) return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 39973ea1ce43..f09505f8b038 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -76,10 +76,15 @@ static void test_xdp_adjust_tail_grow2(void) { const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; int max_grow, prog_fd; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__s390x__) + int tailroom = 512; +#else + int tailroom = 320; +#endif LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index 062fbc8c8e5e..d4cd9f873c14 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -18,7 +18,7 @@ void serial_test_xdp_attach(void) err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); if (CHECK_FAIL(err)) return; - err = bpf_obj_get_info_by_fd(fd1, &info, &len); + err = bpf_prog_get_info_by_fd(fd1, &info, &len); if (CHECK_FAIL(err)) goto out_1; id1 = info.id; @@ -28,7 +28,7 @@ void serial_test_xdp_attach(void) goto out_1; memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(fd2, &info, &len); + err = bpf_prog_get_info_by_fd(fd2, &info, &len); if (CHECK_FAIL(err)) goto out_2; id2 = info.id; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index f775a1613833..481626a875d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -33,8 +33,8 @@ static void test_xdp_with_cpumap_helpers(void) prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); map_fd = bpf_map__fd(skel->maps.cpu_map); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) goto out_close; val.bpf_prog.fd = prog_fd; @@ -85,8 +85,8 @@ static void test_xdp_with_cpumap_frags_helpers(void) frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); map_fd = bpf_map__fd(skel->maps.cpu_map); - err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(frags_prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) goto out_close; val.bpf_prog.fd = frags_prog_fd; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index ead40016c324..ce6812558287 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -35,8 +35,8 @@ static void test_xdp_with_devmap_helpers(void) dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); map_fd = bpf_map__fd(skel->maps.dm_ports); - err = bpf_obj_get_info_by_fd(dm_fd, &info, &len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) goto out_close; val.bpf_prog.fd = dm_fd; @@ -98,8 +98,8 @@ static void test_xdp_with_devmap_frags_helpers(void) dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); map_fd = bpf_map__fd(skel->maps.dm_ports); - err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len); - if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + err = bpf_prog_get_info_by_fd(dm_fd_frags, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) goto out_close; val.bpf_prog.fd = dm_fd_frags; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index a50971c6cf4a..2666c84dbd01 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -4,10 +4,12 @@ #include <net/if.h> #include <linux/if_ether.h> #include <linux/if_packet.h> +#include <linux/if_link.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <linux/udp.h> #include <bpf/bpf_endian.h> +#include <uapi/linux/netdev.h> #include "test_xdp_do_redirect.skel.h" #define SYS(fmt, ...) \ @@ -65,7 +67,11 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes */ +#if defined(__s390x__) +#define MAX_PKT_SIZE 3176 +#else #define MAX_PKT_SIZE 3368 +#endif static void test_max_pkt_size(int fd) { char data[MAX_PKT_SIZE + 1] = {}; @@ -92,7 +98,7 @@ void test_xdp_do_redirect(void) struct test_xdp_do_redirect *skel = NULL; struct nstoken *nstoken = NULL; struct bpf_link *link; - + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); struct xdp_md ctx_in = { .data = sizeof(__u32), .data_end = sizeof(data) }; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -153,6 +159,29 @@ void test_xdp_do_redirect(void) !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) goto out; + /* Check xdp features supported by veth driver */ + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_src query_opts.feature_flags")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags")) + goto out; + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ skel->rodata->ifindex_in = ifindex_src; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index cd3aa340e65e..1dbddcab87a8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -8,6 +8,7 @@ void serial_test_xdp_info(void) { __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; const char *file = "./xdp_dummy.bpf.o"; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); struct bpf_prog_info info = {}; struct bpf_object *obj; int err, prog_fd; @@ -33,7 +34,7 @@ void serial_test_xdp_info(void) if (CHECK_FAIL(err)) return; - err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) goto out_close; @@ -61,6 +62,13 @@ void serial_test_xdp_info(void) if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; + /* Check xdp features supported by lo device */ + opts.feature_flags = ~0; + err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts); + if (!ASSERT_OK(err, "bpf_xdp_query")) + goto out; + + ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags"); out: bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index 3e9d5c5521f0..e7e9f3c22edf 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -29,13 +29,13 @@ void serial_test_xdp_link(void) prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler); memset(&prog_info, 0, sizeof(prog_info)); - err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len); + err = bpf_prog_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len); if (!ASSERT_OK(err, "fd_info1")) goto cleanup; id1 = prog_info.id; memset(&prog_info, 0, sizeof(prog_info)); - err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len); + err = bpf_prog_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len); if (!ASSERT_OK(err, "fd_info2")) goto cleanup; id2 = prog_info.id; @@ -119,7 +119,8 @@ void serial_test_xdp_link(void) goto cleanup; memset(&link_info, 0, sizeof(link_info)); - err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + err = bpf_link_get_info_by_fd(bpf_link__fd(link), + &link_info, &link_info_len); if (!ASSERT_OK(err, "link_info")) goto cleanup; @@ -137,7 +138,8 @@ void serial_test_xdp_link(void) goto cleanup; memset(&link_info, 0, sizeof(link_info)); - err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + err = bpf_link_get_info_by_fd(bpf_link__fd(link), + &link_info, &link_info_len); ASSERT_OK(err, "link_info"); ASSERT_EQ(link_info.prog_id, id1, "link_prog_id"); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c new file mode 100644 index 000000000000..aa4beae99f4f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include "xdp_metadata.skel.h" +#include "xdp_metadata2.skel.h" +#include "xdp_metadata.h" +#include "xsk.h" + +#include <bpf/btf.h> +#include <linux/errqueue.h> +#include <linux/if_link.h> +#include <linux/net_tstamp.h> +#include <linux/udp.h> +#include <sys/mman.h> +#include <net/if.h> +#include <poll.h> + +#define TX_NAME "veTX" +#define RX_NAME "veRX" + +#define UDP_PAYLOAD_BYTES 4 + +#define AF_XDP_SOURCE_PORT 1234 +#define AF_XDP_CONSUMER_PORT 8080 + +#define UMEM_NUM 16 +#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE +#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM) +#define XDP_FLAGS XDP_FLAGS_DRV_MODE +#define QUEUE_ID 0 + +#define TX_ADDR "10.0.0.1" +#define RX_ADDR "10.0.0.2" +#define PREFIX_LEN "8" +#define FAMILY AF_INET + +#define SYS(cmd) ({ \ + if (!ASSERT_OK(system(cmd), (cmd))) \ + goto out; \ +}) + +struct xsk { + void *umem_area; + struct xsk_umem *umem; + struct xsk_ring_prod fill; + struct xsk_ring_cons comp; + struct xsk_ring_prod tx; + struct xsk_ring_cons rx; + struct xsk_socket *socket; +}; + +static int open_xsk(int ifindex, struct xsk *xsk) +{ + int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + const struct xsk_socket_config socket_config = { + .rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .bind_flags = XDP_COPY, + }; + const struct xsk_umem_config umem_config = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG, + }; + __u32 idx; + u64 addr; + int ret; + int i; + + xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (!ASSERT_NEQ(xsk->umem_area, MAP_FAILED, "mmap")) + return -1; + + ret = xsk_umem__create(&xsk->umem, + xsk->umem_area, UMEM_SIZE, + &xsk->fill, + &xsk->comp, + &umem_config); + if (!ASSERT_OK(ret, "xsk_umem__create")) + return ret; + + ret = xsk_socket__create(&xsk->socket, ifindex, QUEUE_ID, + xsk->umem, + &xsk->rx, + &xsk->tx, + &socket_config); + if (!ASSERT_OK(ret, "xsk_socket__create")) + return ret; + + /* First half of umem is for TX. This way address matches 1-to-1 + * to the completion queue index. + */ + + for (i = 0; i < UMEM_NUM / 2; i++) { + addr = i * UMEM_FRAME_SIZE; + printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr); + } + + /* Second half of umem is for RX. */ + + ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx); + if (!ASSERT_EQ(UMEM_NUM / 2, ret, "xsk_ring_prod__reserve")) + return ret; + if (!ASSERT_EQ(idx, 0, "fill idx != 0")) + return -1; + + for (i = 0; i < UMEM_NUM / 2; i++) { + addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE; + printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr); + *xsk_ring_prod__fill_addr(&xsk->fill, i) = addr; + } + xsk_ring_prod__submit(&xsk->fill, ret); + + return 0; +} + +static void close_xsk(struct xsk *xsk) +{ + if (xsk->umem) + xsk_umem__delete(xsk->umem); + if (xsk->socket) + xsk_socket__delete(xsk->socket); + munmap(xsk->umem_area, UMEM_SIZE); +} + +static void ip_csum(struct iphdr *iph) +{ + __u32 sum = 0; + __u16 *p; + int i; + + iph->check = 0; + p = (void *)iph; + for (i = 0; i < sizeof(*iph) / sizeof(*p); i++) + sum += p[i]; + + while (sum >> 16) + sum = (sum & 0xffff) + (sum >> 16); + + iph->check = ~sum; +} + +static int generate_packet(struct xsk *xsk, __u16 dst_port) +{ + struct xdp_desc *tx_desc; + struct udphdr *udph; + struct ethhdr *eth; + struct iphdr *iph; + void *data; + __u32 idx; + int ret; + + ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx); + if (!ASSERT_EQ(ret, 1, "xsk_ring_prod__reserve")) + return -1; + + tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx); + tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE; + printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr); + data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr); + + eth = data; + iph = (void *)(eth + 1); + udph = (void *)(iph + 1); + + memcpy(eth->h_dest, "\x00\x00\x00\x00\x00\x02", ETH_ALEN); + memcpy(eth->h_source, "\x00\x00\x00\x00\x00\x01", ETH_ALEN); + eth->h_proto = htons(ETH_P_IP); + + iph->version = 0x4; + iph->ihl = 0x5; + iph->tos = 0x9; + iph->tot_len = htons(sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES); + iph->id = 0; + iph->frag_off = 0; + iph->ttl = 0; + iph->protocol = IPPROTO_UDP; + ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)"); + ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)"); + ip_csum(iph); + + udph->source = htons(AF_XDP_SOURCE_PORT); + udph->dest = htons(dst_port); + udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES); + udph->check = 0; + + memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES); + + tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES; + xsk_ring_prod__submit(&xsk->tx, 1); + + ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0); + if (!ASSERT_GE(ret, 0, "sendto")) + return ret; + + return 0; +} + +static void complete_tx(struct xsk *xsk) +{ + __u32 idx; + __u64 addr; + + if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) { + addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx); + + printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr); + xsk_ring_cons__release(&xsk->comp, 1); + } +} + +static void refill_rx(struct xsk *xsk, __u64 addr) +{ + __u32 idx; + + if (ASSERT_EQ(xsk_ring_prod__reserve(&xsk->fill, 1, &idx), 1, "xsk_ring_prod__reserve")) { + printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr); + *xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr; + xsk_ring_prod__submit(&xsk->fill, 1); + } +} + +static int verify_xsk_metadata(struct xsk *xsk) +{ + const struct xdp_desc *rx_desc; + struct pollfd fds = {}; + struct xdp_meta *meta; + struct ethhdr *eth; + struct iphdr *iph; + __u64 comp_addr; + void *data; + __u64 addr; + __u32 idx; + int ret; + + ret = recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL); + if (!ASSERT_EQ(ret, 0, "recvfrom")) + return -1; + + fds.fd = xsk_socket__fd(xsk->socket); + fds.events = POLLIN; + + ret = poll(&fds, 1, 1000); + if (!ASSERT_GT(ret, 0, "poll")) + return -1; + + ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx); + if (!ASSERT_EQ(ret, 1, "xsk_ring_cons__peek")) + return -2; + + rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx); + comp_addr = xsk_umem__extract_addr(rx_desc->addr); + addr = xsk_umem__add_offset_to_addr(rx_desc->addr); + printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", + xsk, idx, rx_desc->addr, addr, comp_addr); + data = xsk_umem__get_data(xsk->umem_area, addr); + + /* Make sure we got the packet offset correctly. */ + + eth = data; + ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto"); + iph = (void *)(eth + 1); + ASSERT_EQ((int)iph->version, 4, "iph->version"); + + /* custom metadata */ + + meta = data - sizeof(struct xdp_meta); + + if (!ASSERT_NEQ(meta->rx_timestamp, 0, "rx_timestamp")) + return -1; + + if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) + return -1; + + xsk_ring_cons__release(&xsk->rx, 1); + refill_rx(xsk, comp_addr); + + return 0; +} + +void test_xdp_metadata(void) +{ + struct xdp_metadata2 *bpf_obj2 = NULL; + struct xdp_metadata *bpf_obj = NULL; + struct bpf_program *new_prog, *prog; + struct nstoken *tok = NULL; + __u32 queue_id = QUEUE_ID; + struct bpf_map *prog_arr; + struct xsk tx_xsk = {}; + struct xsk rx_xsk = {}; + __u32 val, key = 0; + int retries = 10; + int rx_ifindex; + int tx_ifindex; + int sock_fd; + int ret; + + /* Setup new networking namespace, with a veth pair. */ + + SYS("ip netns add xdp_metadata"); + tok = open_netns("xdp_metadata"); + SYS("ip link add numtxqueues 1 numrxqueues 1 " TX_NAME + " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1"); + SYS("ip link set dev " TX_NAME " address 00:00:00:00:00:01"); + SYS("ip link set dev " RX_NAME " address 00:00:00:00:00:02"); + SYS("ip link set dev " TX_NAME " up"); + SYS("ip link set dev " RX_NAME " up"); + SYS("ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME); + SYS("ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME); + + rx_ifindex = if_nametoindex(RX_NAME); + tx_ifindex = if_nametoindex(TX_NAME); + + /* Setup separate AF_XDP for TX and RX interfaces. */ + + ret = open_xsk(tx_ifindex, &tx_xsk); + if (!ASSERT_OK(ret, "open_xsk(TX_NAME)")) + goto out; + + ret = open_xsk(rx_ifindex, &rx_xsk); + if (!ASSERT_OK(ret, "open_xsk(RX_NAME)")) + goto out; + + bpf_obj = xdp_metadata__open(); + if (!ASSERT_OK_PTR(bpf_obj, "open skeleton")) + goto out; + + prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx"); + bpf_program__set_ifindex(prog, rx_ifindex); + bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY); + + if (!ASSERT_OK(xdp_metadata__load(bpf_obj), "load skeleton")) + goto out; + + /* Make sure we can't add dev-bound programs to prog maps. */ + prog_arr = bpf_object__find_map_by_name(bpf_obj->obj, "prog_arr"); + if (!ASSERT_OK_PTR(prog_arr, "no prog_arr map")) + goto out; + + val = bpf_program__fd(prog); + if (!ASSERT_ERR(bpf_map__update_elem(prog_arr, &key, sizeof(key), + &val, sizeof(val), BPF_ANY), + "update prog_arr")) + goto out; + + /* Attach BPF program to RX interface. */ + + ret = bpf_xdp_attach(rx_ifindex, + bpf_program__fd(bpf_obj->progs.rx), + XDP_FLAGS, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto out; + + sock_fd = xsk_socket__fd(rx_xsk.socket); + ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0); + if (!ASSERT_GE(ret, 0, "bpf_map_update_elem")) + goto out; + + /* Send packet destined to RX AF_XDP socket. */ + if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, + "generate AF_XDP_CONSUMER_PORT")) + goto out; + + /* Verify AF_XDP RX packet has proper metadata. */ + if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0, + "verify_xsk_metadata")) + goto out; + + complete_tx(&tx_xsk); + + /* Make sure freplace correctly picks up original bound device + * and doesn't crash. + */ + + bpf_obj2 = xdp_metadata2__open(); + if (!ASSERT_OK_PTR(bpf_obj2, "open skeleton")) + goto out; + + new_prog = bpf_object__find_program_by_name(bpf_obj2->obj, "freplace_rx"); + bpf_program__set_attach_target(new_prog, bpf_program__fd(prog), "rx"); + + if (!ASSERT_OK(xdp_metadata2__load(bpf_obj2), "load freplace skeleton")) + goto out; + + if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace")) + goto out; + + /* Send packet to trigger . */ + if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, + "generate freplace packet")) + goto out; + + while (!retries--) { + if (bpf_obj2->bss->called) + break; + usleep(10); + } + ASSERT_GT(bpf_obj2->bss->called, 0, "not called"); + +out: + close_xsk(&rx_xsk); + close_xsk(&tx_xsk); + xdp_metadata2__destroy(bpf_obj2); + xdp_metadata__destroy(bpf_obj); + if (tok) + close_netns(tok); + system("ip netns del xdp_metadata"); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c new file mode 100644 index 000000000000..1eb74ddca414 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); +} hash_map_bench SEC(".maps"); + +/* The number of slots to store times */ +#define NR_SLOTS 32 +#define NR_CPUS 256 +#define CPU_MASK (NR_CPUS-1) + +/* Configured by userspace */ +u64 nr_entries; +u64 nr_loops; +u32 __attribute__((__aligned__(8))) key[NR_CPUS]; + +/* Filled by us */ +u64 __attribute__((__aligned__(256))) percpu_times_index[NR_CPUS]; +u64 __attribute__((__aligned__(256))) percpu_times[NR_CPUS][NR_SLOTS]; + +static inline void patch_key(u32 i) +{ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + key[0] = i + 1; +#else + key[0] = __builtin_bswap32(i + 1); +#endif + /* the rest of key is random and is configured by userspace */ +} + +static int lookup_callback(__u32 index, u32 *unused) +{ + patch_key(index); + return bpf_map_lookup_elem(&hash_map_bench, key) ? 0 : 1; +} + +static int loop_lookup_callback(__u32 index, u32 *unused) +{ + return bpf_loop(nr_entries, lookup_callback, NULL, 0) ? 0 : 1; +} + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int benchmark(void *ctx) +{ + u32 cpu = bpf_get_smp_processor_id(); + u32 times_index; + u64 start_time; + + times_index = percpu_times_index[cpu & CPU_MASK] % NR_SLOTS; + start_time = bpf_ktime_get_ns(); + bpf_loop(nr_loops, loop_lookup_callback, NULL, 0); + percpu_times[cpu & CPU_MASK][times_index] = bpf_ktime_get_ns() - start_time; + percpu_times_index[cpu & CPU_MASK] += 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 4a01ea9113bf..14e28f991451 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -7,6 +7,13 @@ #define __success __attribute__((btf_decl_tag("comment:test_expect_success"))) #define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl))) +/* Convenience macro for use with 'asm volatile' blocks */ +#define __naked __attribute__((naked)) +#define __clobber_all "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "memory" +#define __clobber_common "r0", "r1", "r2", "r3", "r4", "r5", "memory" +#define __imm(name) [name]"i"(name) +#define __imm_addr(name) [name]"i"(&name) + #if defined(__TARGET_ARCH_x86) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__x64_" @@ -21,4 +28,29 @@ #define SYS_PREFIX "__se_" #endif +/* How many arguments are passed to function in register */ +#if defined(__TARGET_ARCH_x86) || defined(__x86_64__) +#define FUNC_REG_ARG_CNT 6 +#elif defined(__i386__) +#define FUNC_REG_ARG_CNT 3 +#elif defined(__TARGET_ARCH_s390) || defined(__s390x__) +#define FUNC_REG_ARG_CNT 5 +#elif defined(__TARGET_ARCH_arm) || defined(__arm__) +#define FUNC_REG_ARG_CNT 4 +#elif defined(__TARGET_ARCH_arm64) || defined(__aarch64__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_mips) || defined(__mips__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_powerpc) || defined(__powerpc__) || defined(__powerpc64__) +#define FUNC_REG_ARG_CNT 8 +#elif defined(__TARGET_ARCH_sparc) || defined(__sparc__) +#define FUNC_REG_ARG_CNT 6 +#elif defined(__TARGET_ARCH_riscv) || defined(__riscv__) +#define FUNC_REG_ARG_CNT 8 +#else +/* default to 5 for others */ +#define FUNC_REG_ARG_CNT 5 +#endif + + #endif diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c index e1e11897e99b..1a476d8ed354 100644 --- a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c +++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c @@ -81,4 +81,30 @@ int BPF_KSYSCALL(prctl_enter, int option, unsigned long arg2, return 0; } +__u64 splice_fd_in; +__u64 splice_off_in; +__u64 splice_fd_out; +__u64 splice_off_out; +__u64 splice_len; +__u64 splice_flags; + +SEC("ksyscall/splice") +int BPF_KSYSCALL(splice_enter, int fd_in, loff_t *off_in, int fd_out, + loff_t *off_out, size_t len, unsigned int flags) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + splice_fd_in = fd_in; + splice_off_in = (__u64)off_in; + splice_fd_out = fd_out; + splice_off_out = (__u64)off_out; + splice_len = len; + splice_flags = flags; + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c index e5560a656030..e01690618e1e 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c @@ -53,7 +53,7 @@ struct bitfields_only_mixed_types { */ /* ------ END-EXPECTED-OUTPUT ------ */ struct bitfield_mixed_with_others { - long: 4; /* char is enough as a backing field */ + char: 4; /* char is enough as a backing field */ int a: 4; /* 8-bit implicit padding */ short b; /* combined with previous bitfield */ diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c index e304b6204bd9..7998f27df7dd 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -58,7 +58,81 @@ union jump_code_union { } __attribute__((packed)); }; -/*------ END-EXPECTED-OUTPUT ------ */ +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct nested_packed_but_aligned_struct { + * int x1; + * int x2; + *}; + * + *struct outer_implicitly_packed_struct { + * char y1; + * struct nested_packed_but_aligned_struct y2; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct nested_packed_but_aligned_struct { + int x1; + int x2; +} __attribute__((packed)); + +struct outer_implicitly_packed_struct { + char y1; + struct nested_packed_but_aligned_struct y2; +}; +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct usb_ss_ep_comp_descriptor { + * char: 8; + * char bDescriptorType; + * char bMaxBurst; + * short wBytesPerInterval; + *}; + * + *struct usb_host_endpoint { + * long: 64; + * char: 8; + * struct usb_ss_ep_comp_descriptor ss_ep_comp; + * long: 0; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct usb_ss_ep_comp_descriptor { + char: 8; + char bDescriptorType; + char bMaxBurst; + int: 0; + short wBytesPerInterval; +} __attribute__((packed)); + +struct usb_host_endpoint { + long: 64; + char: 8; + struct usb_ss_ep_comp_descriptor ss_ep_comp; + long: 0; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct nested_packed_struct { + int a; + char b; +} __attribute__((packed)); + +struct outer_nonpacked_struct { + short a; + struct nested_packed_struct b; +}; + +struct outer_packed_struct { + short a; + struct nested_packed_struct b; +} __attribute__((packed)); + +/* ------ END-EXPECTED-OUTPUT ------ */ int f(struct { struct packed_trailing_space _1; @@ -69,6 +143,10 @@ int f(struct { union union_is_never_packed _6; union union_does_not_need_packing _7; union jump_code_union _8; + struct outer_implicitly_packed_struct _9; + struct usb_host_endpoint _10; + struct outer_nonpacked_struct _11; + struct outer_packed_struct _12; } *_) { return 0; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 7cb522d22a66..79276fbe454a 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -19,7 +19,7 @@ struct padded_implicitly { /* *struct padded_explicitly { * int a; - * int: 32; + * long: 0; * int b; *}; * @@ -28,41 +28,28 @@ struct padded_implicitly { struct padded_explicitly { int a; - int: 1; /* algo will explicitly pad with full 32 bits here */ + int: 1; /* algo will emit aligning `long: 0;` here */ int b; }; /* ----- START-EXPECTED-OUTPUT ----- */ -/* - *struct padded_a_lot { - * int a; - * long: 32; - * long: 64; - * long: 64; - * int b; - *}; - * - */ -/* ------ END-EXPECTED-OUTPUT ------ */ - struct padded_a_lot { int a; - /* 32 bit of implicit padding here, which algo will make explicit */ long: 64; long: 64; int b; }; +/* ------ END-EXPECTED-OUTPUT ------ */ + /* ----- START-EXPECTED-OUTPUT ----- */ /* *struct padded_cache_line { * int a; - * long: 32; * long: 64; * long: 64; * long: 64; * int b; - * long: 32; * long: 64; * long: 64; * long: 64; @@ -85,7 +72,7 @@ struct padded_cache_line { *struct zone { * int a; * short b; - * short: 16; + * long: 0; * struct zone_padding __pad__; *}; * @@ -108,6 +95,131 @@ struct padding_wo_named_members { long: 64; }; +struct padding_weird_1 { + int a; + long: 64; + short: 16; + short b; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padding_weird_2 { + * long: 56; + * char a; + * long: 56; + * char b; + * char: 8; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct padding_weird_2 { + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char a; + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char b; + char: 8; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +struct exact_1byte { + char x; +}; + +struct padded_1byte { + char: 8; +}; + +struct exact_2bytes { + short x; +}; + +struct padded_2bytes { + short: 16; +}; + +struct exact_4bytes { + int x; +}; + +struct padded_4bytes { + int: 32; +}; + +struct exact_8bytes { + long x; +}; + +struct padded_8bytes { + long: 64; +}; + +struct ff_periodic_effect { + int: 32; + short magnitude; + long: 0; + short phase; + long: 0; + int: 32; + int custom_len; + short *custom_data; +}; + +struct ib_wc { + long: 64; + long: 64; + int: 32; + int byte_len; + void *qp; + union {} ex; + long: 64; + int slid; + int wc_flags; + long: 64; + char smac[6]; + long: 0; + char network_hdr_type; +}; + +struct acpi_object_method { + long: 64; + char: 8; + char type; + short reference_count; + char flags; + short: 0; + char: 8; + char sync_level; + long: 64; + void *node; + void *aml_start; + union {} dispatch; + long: 64; + int aml_length; +}; + +struct nested_unpacked { + int x; +}; + +struct nested_packed { + struct nested_unpacked a; + char c; +} __attribute__((packed)); + +struct outer_mixed_but_unpacked { + struct nested_packed b1; + short a1; + struct nested_packed b2; +}; + /* ------ END-EXPECTED-OUTPUT ------ */ int f(struct { @@ -117,6 +229,20 @@ int f(struct { struct padded_cache_line _4; struct zone _5; struct padding_wo_named_members _6; + struct padding_weird_1 _7; + struct padding_weird_2 _8; + struct exact_1byte _100; + struct padded_1byte _101; + struct exact_2bytes _102; + struct padded_2bytes _103; + struct exact_4bytes _104; + struct padded_4bytes _105; + struct exact_8bytes _106; + struct padded_8bytes _107; + struct ff_periodic_effect _200; + struct ib_wc _201; + struct acpi_object_method _202; + struct outer_mixed_but_unpacked _203; } *_) { return 0; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c index 4ee4748133fe..ad21ee8c7e23 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -25,6 +25,39 @@ typedef enum { H = 2, } e3_t; +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *enum e_byte { + * EBYTE_1 = 0, + * EBYTE_2 = 1, + *} __attribute__((mode(byte))); + * + */ +/* ----- END-EXPECTED-OUTPUT ----- */ +enum e_byte { + EBYTE_1, + EBYTE_2, +} __attribute__((mode(byte))); + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *enum e_word { + * EWORD_1 = 0LL, + * EWORD_2 = 1LL, + *} __attribute__((mode(word))); + * + */ +/* ----- END-EXPECTED-OUTPUT ----- */ +enum e_word { + EWORD_1, + EWORD_2, +} __attribute__((mode(word))); /* force to use 8-byte backing for this enum */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +enum e_big { + EBIG_1 = 1000000000000ULL, +}; + typedef int int_t; typedef volatile const int * volatile const crazy_ptr_t; @@ -51,7 +84,7 @@ typedef void (*printf_fn_t)(const char *, ...); * typedef int (*fn_t)(int); * typedef char * const * (*fn_ptr2_t)(s_t, fn_t); * - * - `fn_complext_t`: pointer to a function returning struct and accepting + * - `fn_complex_t`: pointer to a function returning struct and accepting * union and struct. All structs and enum are anonymous and defined inline. * * - `signal_t: pointer to a function accepting a pointer to a function as an @@ -224,6 +257,9 @@ struct root_struct { enum e2 _2; e2_t _2_1; e3_t _2_2; + enum e_byte _100; + enum e_word _101; + enum e_big _102; struct struct_w_typedefs _3; anon_struct_t _7; struct struct_fwd *_8; diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c index a1369b5ebcf8..4ad7fe24966d 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c @@ -5,6 +5,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" #include "cgrp_kfunc_common.h" char _license[] SEC("license") = "GPL"; @@ -28,6 +29,7 @@ static struct __cgrps_kfunc_map_value *insert_lookup_cgrp(struct cgroup *cgrp) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") int BPF_PROG(cgrp_kfunc_acquire_untrusted, struct cgroup *cgrp, const char *path) { struct cgroup *acquired; @@ -45,6 +47,7 @@ int BPF_PROG(cgrp_kfunc_acquire_untrusted, struct cgroup *cgrp, const char *path } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 pointer type STRUCT cgroup must point") int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path) { struct cgroup *acquired, *stack_cgrp = (struct cgroup *)&path; @@ -57,6 +60,7 @@ int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path) } SEC("kretprobe/cgroup_destroy_locked") +__failure __msg("reg type unsupported for arg#0 function") int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp) { struct cgroup *acquired; @@ -69,6 +73,7 @@ int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("cgrp_kfunc_acquire_trusted_walked") int BPF_PROG(cgrp_kfunc_acquire_trusted_walked, struct cgroup *cgrp, const char *path) { struct cgroup *acquired; @@ -80,8 +85,8 @@ int BPF_PROG(cgrp_kfunc_acquire_trusted_walked, struct cgroup *cgrp, const char return 0; } - SEC("tp_btf/cgroup_mkdir") +__failure __msg("Possibly NULL pointer passed to trusted arg0") int BPF_PROG(cgrp_kfunc_acquire_null, struct cgroup *cgrp, const char *path) { struct cgroup *acquired; @@ -96,6 +101,7 @@ int BPF_PROG(cgrp_kfunc_acquire_null, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("Unreleased reference") int BPF_PROG(cgrp_kfunc_acquire_unreleased, struct cgroup *cgrp, const char *path) { struct cgroup *acquired; @@ -108,6 +114,7 @@ int BPF_PROG(cgrp_kfunc_acquire_unreleased, struct cgroup *cgrp, const char *pat } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(cgrp_kfunc_get_non_kptr_param, struct cgroup *cgrp, const char *path) { struct cgroup *kptr; @@ -123,6 +130,7 @@ int BPF_PROG(cgrp_kfunc_get_non_kptr_param, struct cgroup *cgrp, const char *pat } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(cgrp_kfunc_get_non_kptr_acquired, struct cgroup *cgrp, const char *path) { struct cgroup *kptr, *acquired; @@ -141,6 +149,7 @@ int BPF_PROG(cgrp_kfunc_get_non_kptr_acquired, struct cgroup *cgrp, const char * } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(cgrp_kfunc_get_null, struct cgroup *cgrp, const char *path) { struct cgroup *kptr; @@ -156,6 +165,7 @@ int BPF_PROG(cgrp_kfunc_get_null, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("Unreleased reference") int BPF_PROG(cgrp_kfunc_xchg_unreleased, struct cgroup *cgrp, const char *path) { struct cgroup *kptr; @@ -175,6 +185,7 @@ int BPF_PROG(cgrp_kfunc_xchg_unreleased, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("Unreleased reference") int BPF_PROG(cgrp_kfunc_get_unreleased, struct cgroup *cgrp, const char *path) { struct cgroup *kptr; @@ -194,6 +205,7 @@ int BPF_PROG(cgrp_kfunc_get_unreleased, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket") int BPF_PROG(cgrp_kfunc_release_untrusted, struct cgroup *cgrp, const char *path) { struct __cgrps_kfunc_map_value *v; @@ -209,6 +221,7 @@ int BPF_PROG(cgrp_kfunc_release_untrusted, struct cgroup *cgrp, const char *path } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 pointer type STRUCT cgroup must point") int BPF_PROG(cgrp_kfunc_release_fp, struct cgroup *cgrp, const char *path) { struct cgroup *acquired = (struct cgroup *)&path; @@ -220,6 +233,7 @@ int BPF_PROG(cgrp_kfunc_release_fp, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("arg#0 is ptr_or_null_ expected ptr_ or socket") int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path) { struct __cgrps_kfunc_map_value local, *v; @@ -251,6 +265,7 @@ int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path) } SEC("tp_btf/cgroup_mkdir") +__failure __msg("release kernel function bpf_cgroup_release expects") int BPF_PROG(cgrp_kfunc_release_unacquired, struct cgroup *cgrp, const char *path) { /* Cannot release trusted cgroup pointer which was not acquired. */ diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h new file mode 100644 index 000000000000..ad34f3b602be --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#ifndef _CPUMASK_COMMON_H +#define _CPUMASK_COMMON_H + +#include "errno.h" +#include <stdbool.h> + +int err; + +struct __cpumask_map_value { + struct bpf_cpumask __kptr_ref * cpumask; +}; + +struct array_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct __cpumask_map_value); + __uint(max_entries, 1); +} __cpumask_map SEC(".maps"); + +struct bpf_cpumask *bpf_cpumask_create(void) __ksym; +void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym; +struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym; +struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumask) __ksym; +u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; +void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_and(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_or(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_xor(struct bpf_cpumask *cpumask, + const struct cpumask *src1, + const struct cpumask *src2) __ksym; +bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; +void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; +u32 bpf_cpumask_any(const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) __ksym; + +static inline const struct cpumask *cast(struct bpf_cpumask *cpumask) +{ + return (const struct cpumask *)cpumask; +} + +static inline struct bpf_cpumask *create_cpumask(void) +{ + struct bpf_cpumask *cpumask; + + cpumask = bpf_cpumask_create(); + if (!cpumask) { + err = 1; + return NULL; + } + + if (!bpf_cpumask_empty(cast(cpumask))) { + err = 2; + bpf_cpumask_release(cpumask); + return NULL; + } + + return cpumask; +} + +static inline struct __cpumask_map_value *cpumask_map_value_lookup(void) +{ + u32 key = 0; + + return bpf_map_lookup_elem(&__cpumask_map, &key); +} + +static inline int cpumask_map_insert(struct bpf_cpumask *mask) +{ + struct __cpumask_map_value local, *v; + long status; + struct bpf_cpumask *old; + u32 key = 0; + + local.cpumask = NULL; + status = bpf_map_update_elem(&__cpumask_map, &key, &local, 0); + if (status) { + bpf_cpumask_release(mask); + return status; + } + + v = bpf_map_lookup_elem(&__cpumask_map, &key); + if (!v) { + bpf_cpumask_release(mask); + return -ENOENT; + } + + old = bpf_kptr_xchg(&v->cpumask, mask); + if (old) { + bpf_cpumask_release(old); + return -EEXIST; + } + + return 0; +} + +#endif /* _CPUMASK_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c new file mode 100644 index 000000000000..33e8e86dd090 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "cpumask_common.h" + +char _license[] SEC("license") = "GPL"; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(test_alloc_no_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + cpumask = create_cpumask(); + + /* cpumask is never released. */ + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("NULL pointer passed to trusted arg0") +int BPF_PROG(test_alloc_double_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + cpumask = create_cpumask(); + + /* cpumask is released twice. */ + bpf_cpumask_release(cpumask); + bpf_cpumask_release(cpumask); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("bpf_cpumask_acquire args#0 expected pointer to STRUCT bpf_cpumask") +int BPF_PROG(test_acquire_wrong_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + /* Can't acquire a non-struct bpf_cpumask. */ + cpumask = bpf_cpumask_acquire((struct bpf_cpumask *)task->cpus_ptr); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("bpf_cpumask_set_cpu args#1 expected pointer to STRUCT bpf_cpumask") +int BPF_PROG(test_mutate_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + /* Can't set the CPU of a non-struct bpf_cpumask. */ + bpf_cpumask_set_cpu(0, (struct bpf_cpumask *)task->cpus_ptr); + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(test_insert_remove_no_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) + return 0; + + v = cpumask_map_value_lookup(); + if (!v) + return 0; + + cpumask = bpf_kptr_xchg(&v->cpumask, NULL); + + /* cpumask is never released. */ + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") +int BPF_PROG(test_kptr_get_no_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) + return 0; + + v = cpumask_map_value_lookup(); + if (!v) + return 0; + + cpumask = bpf_cpumask_kptr_get(&v->cpumask); + + /* cpumask is never released. */ + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("NULL pointer passed to trusted arg0") +int BPF_PROG(test_cpumask_null, struct task_struct *task, u64 clone_flags) +{ + /* NULL passed to KF_TRUSTED_ARGS kfunc. */ + bpf_cpumask_empty(NULL); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c new file mode 100644 index 000000000000..1d38bc65d4b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "cpumask_common.h" + +char _license[] SEC("license") = "GPL"; + +int pid, nr_cpus; + +static bool is_test_task(void) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + return pid == cur_pid; +} + +static bool create_cpumask_set(struct bpf_cpumask **out1, + struct bpf_cpumask **out2, + struct bpf_cpumask **out3, + struct bpf_cpumask **out4) +{ + struct bpf_cpumask *mask1, *mask2, *mask3, *mask4; + + mask1 = create_cpumask(); + if (!mask1) + return false; + + mask2 = create_cpumask(); + if (!mask2) { + bpf_cpumask_release(mask1); + err = 3; + return false; + } + + mask3 = create_cpumask(); + if (!mask3) { + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + err = 4; + return false; + } + + mask4 = create_cpumask(); + if (!mask4) { + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(mask3); + err = 5; + return false; + } + + *out1 = mask1; + *out2 = mask2; + *out3 = mask3; + *out4 = mask4; + + return true; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_alloc_free_cpumask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_set_clear_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_set_cpu(0, cpumask); + if (!bpf_cpumask_test_cpu(0, cast(cpumask))) { + err = 3; + goto release_exit; + } + + bpf_cpumask_clear_cpu(0, cpumask); + if (bpf_cpumask_test_cpu(0, cast(cpumask))) { + err = 4; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_setall_clear_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + bpf_cpumask_setall(cpumask); + if (!bpf_cpumask_full(cast(cpumask))) { + err = 3; + goto release_exit; + } + + bpf_cpumask_clear(cpumask); + if (!bpf_cpumask_empty(cast(cpumask))) { + err = 4; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_first_firstzero_cpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (bpf_cpumask_first(cast(cpumask)) < nr_cpus) { + err = 3; + goto release_exit; + } + + if (bpf_cpumask_first_zero(cast(cpumask)) != 0) { + bpf_printk("first zero: %d", bpf_cpumask_first_zero(cast(cpumask))); + err = 4; + goto release_exit; + } + + bpf_cpumask_set_cpu(0, cpumask); + if (bpf_cpumask_first(cast(cpumask)) != 0) { + err = 5; + goto release_exit; + } + + if (bpf_cpumask_first_zero(cast(cpumask)) != 1) { + err = 6; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + + if (!is_test_task()) + return 0; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (bpf_cpumask_test_and_set_cpu(0, cpumask)) { + err = 3; + goto release_exit; + } + + if (!bpf_cpumask_test_and_set_cpu(0, cpumask)) { + err = 4; + goto release_exit; + } + + if (!bpf_cpumask_test_and_clear_cpu(0, cpumask)) { + err = 5; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(cpumask); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_and_or_xor, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + + if (bpf_cpumask_and(dst1, cast(mask1), cast(mask2))) { + err = 6; + goto release_exit; + } + if (!bpf_cpumask_empty(cast(dst1))) { + err = 7; + goto release_exit; + } + + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + if (!bpf_cpumask_test_cpu(0, cast(dst1))) { + err = 8; + goto release_exit; + } + if (!bpf_cpumask_test_cpu(1, cast(dst1))) { + err = 9; + goto release_exit; + } + + bpf_cpumask_xor(dst2, cast(mask1), cast(mask2)); + if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) { + err = 10; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_intersects_subset, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + if (bpf_cpumask_intersects(cast(mask1), cast(mask2))) { + err = 6; + goto release_exit; + } + + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + if (!bpf_cpumask_subset(cast(mask1), cast(dst1))) { + err = 7; + goto release_exit; + } + + if (!bpf_cpumask_subset(cast(mask2), cast(dst1))) { + err = 8; + goto release_exit; + } + + if (bpf_cpumask_subset(cast(dst1), cast(mask1))) { + err = 9; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2, *dst1, *dst2; + u32 cpu; + + if (!is_test_task()) + return 0; + + if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2)) + return 0; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); + + cpu = bpf_cpumask_any(cast(mask1)); + if (cpu != 0) { + err = 6; + goto release_exit; + } + + cpu = bpf_cpumask_any(cast(dst2)); + if (cpu < nr_cpus) { + err = 7; + goto release_exit; + } + + bpf_cpumask_copy(dst2, cast(dst1)); + if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) { + err = 8; + goto release_exit; + } + + cpu = bpf_cpumask_any(cast(dst2)); + if (cpu > 1) { + err = 9; + goto release_exit; + } + + cpu = bpf_cpumask_any_and(cast(mask1), cast(mask2)); + if (cpu < nr_cpus) { + err = 10; + goto release_exit; + } + +release_exit: + bpf_cpumask_release(mask1); + bpf_cpumask_release(mask2); + bpf_cpumask_release(dst1); + bpf_cpumask_release(dst2); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_insert_leave, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) + err = 3; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_insert_remove_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) { + err = 3; + return 0; + } + + v = cpumask_map_value_lookup(); + if (!v) { + err = 4; + return 0; + } + + cpumask = bpf_kptr_xchg(&v->cpumask, NULL); + if (cpumask) + bpf_cpumask_release(cpumask); + else + err = 5; + + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_insert_kptr_get_release, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *cpumask; + struct __cpumask_map_value *v; + + cpumask = create_cpumask(); + if (!cpumask) + return 0; + + if (cpumask_map_insert(cpumask)) { + err = 3; + return 0; + } + + v = cpumask_map_value_lookup(); + if (!v) { + err = 4; + return 0; + } + + cpumask = bpf_cpumask_kptr_get(&v->cpumask); + if (cpumask) + bpf_cpumask_release(cpumask); + else + err = 5; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c new file mode 100644 index 000000000000..0bf969a0b5ed --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops.s/test_2") +__failure __msg("attach to unsupported member test_2 of struct bpf_dummy_ops") +int BPF_PROG(test_unsupported_field_sleepable, + struct bpf_dummy_ops_state *state, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + /* Tries to mark an unsleepable field in struct bpf_dummy_ops as sleepable. */ + return 0; +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = NULL, + .test_2 = (void *)test_unsupported_field_sleepable, + .test_sleepable = (void *)NULL, +}; diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c index ead87edb75e2..1efa746c25dc 100644 --- a/tools/testing/selftests/bpf/progs/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c @@ -1,19 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct bpf_dummy_ops_state { - int val; -} __attribute__((preserve_access_index)); - -struct bpf_dummy_ops { - int (*test_1)(struct bpf_dummy_ops_state *state); - int (*test_2)(struct bpf_dummy_ops_state *state, int a1, unsigned short a2, - char a3, unsigned long a4); -}; - char _license[] SEC("license") = "GPL"; SEC("struct_ops/test_1") @@ -43,8 +33,15 @@ int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a return 0; } +SEC("struct_ops.s/test_sleepable") +int BPF_PROG(test_sleepable, struct bpf_dummy_ops_state *state) +{ + return 0; +} + SEC(".struct_ops") struct bpf_dummy_ops dummy_1 = { .test_1 = (void *)test_1, .test_2 = (void *)test_2, + .test_sleepable = (void *)test_sleepable, }; diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 78debc1b3820..aa5b69354b91 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -35,6 +35,13 @@ struct { __type(value, __u32); } array_map3 SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array_map4 SEC(".maps"); + struct sample { int pid; long value; @@ -67,7 +74,7 @@ static int get_map_val_dynptr(struct bpf_dynptr *ptr) * bpf_ringbuf_submit/discard_dynptr call */ SEC("?raw_tp") -__failure __msg("Unreleased reference id=1") +__failure __msg("Unreleased reference id=2") int ringbuf_missing_release1(void *ctx) { struct bpf_dynptr ptr; @@ -80,7 +87,7 @@ int ringbuf_missing_release1(void *ctx) } SEC("?raw_tp") -__failure __msg("Unreleased reference id=2") +__failure __msg("Unreleased reference id=4") int ringbuf_missing_release2(void *ctx) { struct bpf_dynptr ptr1, ptr2; @@ -382,7 +389,7 @@ int invalid_helper1(void *ctx) /* A dynptr can't be passed into a helper function at a non-zero offset */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("cannot pass in dynptr at an offset=-8") int invalid_helper2(void *ctx) { struct bpf_dynptr ptr; @@ -420,7 +427,7 @@ int invalid_write1(void *ctx) * offset */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("cannot overwrite referenced dynptr") int invalid_write2(void *ctx) { struct bpf_dynptr ptr; @@ -444,7 +451,7 @@ int invalid_write2(void *ctx) * non-const offset */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("cannot overwrite referenced dynptr") int invalid_write3(void *ctx) { struct bpf_dynptr ptr; @@ -476,7 +483,7 @@ static int invalid_write4_callback(__u32 index, void *data) * be invalidated as a dynptr */ SEC("?raw_tp") -__failure __msg("arg 1 is an unacquired reference") +__failure __msg("cannot overwrite referenced dynptr") int invalid_write4(void *ctx) { struct bpf_dynptr ptr; @@ -584,7 +591,7 @@ int invalid_read4(void *ctx) /* Initializing a dynptr on an offset should fail */ SEC("?raw_tp") -__failure __msg("invalid write to stack") +__failure __msg("cannot pass in dynptr at an offset=0") int invalid_offset(void *ctx) { struct bpf_dynptr ptr; @@ -623,7 +630,7 @@ static int release_twice_callback_fn(__u32 index, void *data) } /* Test that releasing a dynptr twice, where one of the releases happens - * within a calback function, fails + * within a callback function, fails */ SEC("?raw_tp") __failure __msg("arg 1 is an unacquired reference") @@ -653,3 +660,435 @@ int dynptr_from_mem_invalid_api(void *ctx) return 0; } + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_pruning_overwrite(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 0xeB9F; \ + r6 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto pjmp1; \ + goto pjmp2; \ + pjmp1: \ + *(u64 *)(r10 - 16) = r9; \ + pjmp2: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__success __msg("12: safe") __log_level(2) +int dynptr_pruning_stacksafe(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 0xeB9F; \ + r6 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto stjmp1; \ + goto stjmp2; \ + stjmp1: \ + r9 = r9; \ + stjmp2: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_pruning_type_confusion(struct __sk_buff *ctx) +{ + asm volatile ( + "r6 = %[array_map4] ll; \ + r7 = %[ringbuf] ll; \ + r1 = r6; \ + r2 = r10; \ + r2 += -8; \ + r9 = 0; \ + *(u64 *)(r2 + 0) = r9; \ + r3 = r10; \ + r3 += -24; \ + r9 = 0xeB9FeB9F; \ + *(u64 *)(r10 - 16) = r9; \ + *(u64 *)(r10 - 24) = r9; \ + r9 = 0; \ + r4 = 0; \ + r8 = r2; \ + call %[bpf_map_update_elem]; \ + r1 = r6; \ + r2 = r8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto tjmp1; \ + exit; \ + tjmp1: \ + r8 = r0; \ + r1 = r7; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + r0 = *(u64 *)(r0 + 0); \ + call %[bpf_ringbuf_reserve_dynptr]; \ + if r0 == 0 goto tjmp2; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + r8 = r8; \ + goto tjmp3; \ + tjmp2: \ + *(u64 *)(r10 - 8) = r9; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r8; \ + r1 += 8; \ + r2 = 0; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_dynptr_from_mem]; \ + tjmp3: \ + r1 = r10; \ + r1 += -16; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_map_update_elem), + __imm(bpf_map_lookup_elem), + __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_dynptr_from_mem), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(array_map4), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("dynptr has to be at a constant offset") __log_level(2) +int dynptr_var_off_overwrite(struct __sk_buff *ctx) +{ + asm volatile ( + "r9 = 16; \ + *(u32 *)(r10 - 4) = r9; \ + r8 = *(u32 *)(r10 - 4); \ + if r8 >= 0 goto vjmp1; \ + r0 = 1; \ + exit; \ + vjmp1: \ + if r8 <= 16 goto vjmp2; \ + r0 = 1; \ + exit; \ + vjmp2: \ + r8 &= 16; \ + r1 = %[ringbuf] ll; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -32; \ + r4 += r8; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + r9 = 0xeB9F; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r10; \ + r1 += -32; \ + r1 += r8; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm_addr(ringbuf) + : __clobber_all + ); + return 0; +} + +SEC("?tc") +__failure __msg("cannot overwrite referenced dynptr") __log_level(2) +int dynptr_partial_slot_invalidate(struct __sk_buff *ctx) +{ + asm volatile ( + "r6 = %[ringbuf] ll; \ + r7 = %[array_map4] ll; \ + r1 = r7; \ + r2 = r10; \ + r2 += -8; \ + r9 = 0; \ + *(u64 *)(r2 + 0) = r9; \ + r3 = r2; \ + r4 = 0; \ + r8 = r2; \ + call %[bpf_map_update_elem]; \ + r1 = r7; \ + r2 = r8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto sjmp1; \ + exit; \ + sjmp1: \ + r7 = r0; \ + r1 = r6; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -24; \ + call %[bpf_ringbuf_reserve_dynptr]; \ + *(u64 *)(r10 - 16) = r9; \ + r1 = r7; \ + r2 = 8; \ + r3 = 0; \ + r4 = r10; \ + r4 += -16; \ + call %[bpf_dynptr_from_mem]; \ + r1 = r10; \ + r1 += -512; \ + r2 = 488; \ + r3 = r10; \ + r3 += -24; \ + r4 = 0; \ + r5 = 0; \ + call %[bpf_dynptr_read]; \ + r8 = 1; \ + if r0 != 0 goto sjmp2; \ + r8 = 0; \ + sjmp2: \ + r1 = r10; \ + r1 += -24; \ + r2 = 0; \ + call %[bpf_ringbuf_discard_dynptr]; " + : + : __imm(bpf_map_update_elem), + __imm(bpf_map_lookup_elem), + __imm(bpf_ringbuf_reserve_dynptr), + __imm(bpf_ringbuf_discard_dynptr), + __imm(bpf_dynptr_from_mem), + __imm(bpf_dynptr_read), + __imm_addr(ringbuf), + __imm_addr(array_map4) + : __clobber_all + ); + return 0; +} + +/* Test that it is allowed to overwrite unreferenced dynptr. */ +SEC("?raw_tp") +__success +int dynptr_overwrite_unref(void *ctx) +{ + struct bpf_dynptr ptr; + + if (get_map_val_dynptr(&ptr)) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + + return 0; +} + +/* Test that slices are invalidated on reinitializing a dynptr. */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int dynptr_invalidate_slice_reinit(void *ctx) +{ + struct bpf_dynptr ptr; + __u8 *p; + + if (get_map_val_dynptr(&ptr)) + return 0; + p = bpf_dynptr_data(&ptr, 0, 1); + if (!p) + return 0; + if (get_map_val_dynptr(&ptr)) + return 0; + /* this should fail */ + return *p; +} + +/* Invalidation of dynptr slices on destruction of dynptr should not miss + * mem_or_null pointers. + */ +SEC("?raw_tp") +__failure __msg("R1 type=scalar expected=percpu_ptr_") +int dynptr_invalidate_slice_or_null(void *ctx) +{ + struct bpf_dynptr ptr; + __u8 *p; + + if (get_map_val_dynptr(&ptr)) + return 0; + + p = bpf_dynptr_data(&ptr, 0, 1); + *(__u8 *)&ptr = 0; + /* this should fail */ + bpf_this_cpu_ptr(p); + return 0; +} + +/* Destruction of dynptr should also any slices obtained from it */ +SEC("?raw_tp") +__failure __msg("R7 invalid mem access 'scalar'") +int dynptr_invalidate_slice_failure(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u8 *p1, *p2; + + if (get_map_val_dynptr(&ptr1)) + return 0; + if (get_map_val_dynptr(&ptr2)) + return 0; + + p1 = bpf_dynptr_data(&ptr1, 0, 1); + if (!p1) + return 0; + p2 = bpf_dynptr_data(&ptr2, 0, 1); + if (!p2) + return 0; + + *(__u8 *)&ptr1 = 0; + /* this should fail */ + return *p1; +} + +/* Invalidation of slices should be scoped and should not prevent dereferencing + * slices of another dynptr after destroying unrelated dynptr + */ +SEC("?raw_tp") +__success +int dynptr_invalidate_slice_success(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u8 *p1, *p2; + + if (get_map_val_dynptr(&ptr1)) + return 1; + if (get_map_val_dynptr(&ptr2)) + return 1; + + p1 = bpf_dynptr_data(&ptr1, 0, 1); + if (!p1) + return 1; + p2 = bpf_dynptr_data(&ptr2, 0, 1); + if (!p2) + return 1; + + *(__u8 *)&ptr1 = 0; + return *p2; +} + +/* Overwriting referenced dynptr should be rejected */ +SEC("?raw_tp") +__failure __msg("cannot overwrite referenced dynptr") +int dynptr_overwrite_ref(void *ctx) +{ + struct bpf_dynptr ptr; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr); + /* this should fail */ + if (get_map_val_dynptr(&ptr)) + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +/* Reject writes to dynptr slot from bpf_dynptr_read */ +SEC("?raw_tp") +__failure __msg("potential write to dynptr at off=-16") +int dynptr_read_into_slot(void *ctx) +{ + union { + struct { + char _pad[48]; + struct bpf_dynptr ptr; + }; + char buf[64]; + } data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &data.ptr); + /* this should fail */ + bpf_dynptr_read(data.buf, sizeof(data.buf), &data.ptr, 0, 0); + + return 0; +} + +/* Reject writes to dynptr slot for uninit arg */ +SEC("?raw_tp") +__failure __msg("potential write to dynptr at off=-16") +int uninit_write_into_slot(void *ctx) +{ + struct { + char buf[64]; + struct bpf_dynptr ptr; + } data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, 80, 0, &data.ptr); + /* this should fail */ + bpf_get_current_comm(data.buf, 80); + + return 0; +} + +static int callback(__u32 index, void *data) +{ + *(__u32 *)data = 123; + + return 0; +} + +/* If the dynptr is written into in a callback function, its data + * slices should be invalidated as well. + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int invalid_data_slices(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 *slice; + + if (get_map_val_dynptr(&ptr)) + return 0; + + slice = bpf_dynptr_data(&ptr, 0, sizeof(__u32)); + if (!slice) + return 0; + + bpf_loop(10, callback, &ptr, 0); + + /* this should fail */ + *slice = 1; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fib_lookup.c b/tools/testing/selftests/bpf/progs/fib_lookup.c new file mode 100644 index 000000000000..c4514dd58c62 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fib_lookup.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_tracing_net.h" + +struct bpf_fib_lookup fib_params = {}; +int fib_lookup_ret = 0; +int lookup_flags = 0; + +SEC("tc") +int fib_lookup(struct __sk_buff *skb) +{ + fib_lookup_ret = bpf_fib_lookup(skb, &fib_params, sizeof(fib_params), + lookup_flags); + + return TC_ACT_SHOT; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/htab_reuse.c b/tools/testing/selftests/bpf/progs/htab_reuse.c new file mode 100644 index 000000000000..7f7368cb3095 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/htab_reuse.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct htab_val { + struct bpf_spin_lock lock; + unsigned int data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 64); + __type(key, unsigned int); + __type(value, struct htab_val); + __uint(map_flags, BPF_F_NO_PREALLOC); +} htab SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c new file mode 100644 index 000000000000..2d2e61470794 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +static struct prog_test_ref_kfunc __kptr_ref *v; +long total_sum = -1; + +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; + +SEC("tc") +int test_jit_probe_mem(struct __sk_buff *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long zero = 0, sum; + + p = bpf_kfunc_call_test_acquire(&zero); + if (!p) + return 1; + + p = bpf_kptr_xchg(&v, p); + if (p) + goto release_out; + + /* Direct map value access of kptr, should be PTR_UNTRUSTED */ + p = v; + if (!p) + return 1; + + asm volatile ( + "r9 = %[p];" + "%[sum] = 0;" + + /* r8 = p->a */ + "r8 = *(u32 *)(r9 + 0);" + "%[sum] += r8;" + + /* r8 = p->b */ + "r8 = *(u32 *)(r9 + 4);" + "%[sum] += r8;" + + "r9 += 8;" + /* r9 = p->a */ + "r9 = *(u32 *)(r9 - 8);" + "%[sum] += r9;" + + : [sum] "=r"(sum) + : [p] "r"(p) + : "r8", "r9" + ); + + total_sum = sum; + return 0; +release_out: + bpf_kfunc_call_test_release(p); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index f636e50be259..7daa8f5720b9 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; @@ -16,6 +17,24 @@ extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; + +SEC("tc") +int kfunc_call_test4(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + long tmp; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + tmp = bpf_kfunc_call_test4(-3, -30, -200, -1000); + return (tmp >> 32) + tmp; +} SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) @@ -163,4 +182,14 @@ int kfunc_call_test_get_mem(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_static_unused_arg(struct __sk_buff *skb) +{ + + u32 expected = 5, actual; + + actual = bpf_kfunc_call_test_static_unused_arg(expected, 0xdeadbeef); + return actual != expected ? -1 : 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c index 4ad88da5cda2..4fa4a9b01bde 100644 --- a/tools/testing/selftests/bpf/progs/linked_list.c +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -260,7 +260,7 @@ int test_list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head { int ret; - ret = list_push_pop_multiple(lock ,head, false); + ret = list_push_pop_multiple(lock, head, false); if (ret) return ret; return list_push_pop_multiple(lock, head, true); diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index 1d9017240e19..69cdc07cba13 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -54,28 +54,44 @@ return 0; \ } -CHECK(kptr, push_front, &f->head); -CHECK(kptr, push_back, &f->head); CHECK(kptr, pop_front, &f->head); CHECK(kptr, pop_back, &f->head); -CHECK(global, push_front, &ghead); -CHECK(global, push_back, &ghead); CHECK(global, pop_front, &ghead); CHECK(global, pop_back, &ghead); -CHECK(map, push_front, &v->head); -CHECK(map, push_back, &v->head); CHECK(map, pop_front, &v->head); CHECK(map, pop_back, &v->head); -CHECK(inner_map, push_front, &iv->head); -CHECK(inner_map, push_back, &iv->head); CHECK(inner_map, pop_front, &iv->head); CHECK(inner_map, pop_back, &iv->head); #undef CHECK +#define CHECK(test, op, hexpr, nexpr) \ + SEC("?tc") \ + int test##_missing_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *, void *) = (void *)&bpf_list_##op; \ + p(hexpr, nexpr); \ + return 0; \ + } + +CHECK(kptr, push_front, &f->head, b); +CHECK(kptr, push_back, &f->head, b); + +CHECK(global, push_front, &ghead, f); +CHECK(global, push_back, &ghead, f); + +CHECK(map, push_front, &v->head, f); +CHECK(map, push_back, &v->head, f); + +CHECK(inner_map, push_front, &iv->head, f); +CHECK(inner_map, push_back, &iv->head, f); + +#undef CHECK + #define CHECK(test, op, lexpr, hexpr) \ SEC("?tc") \ int test##_incorrect_lock_##op(void *ctx) \ @@ -108,13 +124,49 @@ CHECK(inner_map, pop_back, &iv->head); CHECK(inner_map_global, op, &iv->lock, &ghead); \ CHECK(inner_map_map, op, &iv->lock, &v->head); -CHECK_OP(push_front); -CHECK_OP(push_back); CHECK_OP(pop_front); CHECK_OP(pop_back); #undef CHECK #undef CHECK_OP + +#define CHECK(test, op, lexpr, hexpr, nexpr) \ + SEC("?tc") \ + int test##_incorrect_lock_##op(void *ctx) \ + { \ + INIT; \ + void (*p)(void *, void*) = (void *)&bpf_list_##op; \ + bpf_spin_lock(lexpr); \ + p(hexpr, nexpr); \ + return 0; \ + } + +#define CHECK_OP(op) \ + CHECK(kptr_kptr, op, &f1->lock, &f2->head, b); \ + CHECK(kptr_global, op, &f1->lock, &ghead, f); \ + CHECK(kptr_map, op, &f1->lock, &v->head, f); \ + CHECK(kptr_inner_map, op, &f1->lock, &iv->head, f); \ + \ + CHECK(global_global, op, &glock2, &ghead, f); \ + CHECK(global_kptr, op, &glock, &f1->head, b); \ + CHECK(global_map, op, &glock, &v->head, f); \ + CHECK(global_inner_map, op, &glock, &iv->head, f); \ + \ + CHECK(map_map, op, &v->lock, &v2->head, f); \ + CHECK(map_kptr, op, &v->lock, &f2->head, b); \ + CHECK(map_global, op, &v->lock, &ghead, f); \ + CHECK(map_inner_map, op, &v->lock, &iv->head, f); \ + \ + CHECK(inner_map_inner_map, op, &iv->lock, &iv2->head, f); \ + CHECK(inner_map_kptr, op, &iv->lock, &f2->head, b); \ + CHECK(inner_map_global, op, &iv->lock, &ghead, f); \ + CHECK(inner_map_map, op, &iv->lock, &v->head, f); + +CHECK_OP(push_front); +CHECK_OP(push_back); + +#undef CHECK +#undef CHECK_OP #undef INIT SEC("?kprobe/xyz") @@ -304,34 +356,6 @@ int direct_write_node(void *ctx) } static __always_inline -int write_after_op(void (*push_op)(void *head, void *node)) -{ - struct foo *f; - - f = bpf_obj_new(typeof(*f)); - if (!f) - return 0; - bpf_spin_lock(&glock); - push_op(&ghead, &f->node); - f->data = 42; - bpf_spin_unlock(&glock); - - return 0; -} - -SEC("?tc") -int write_after_push_front(void *ctx) -{ - return write_after_op((void *)bpf_list_push_front); -} - -SEC("?tc") -int write_after_push_back(void *ctx) -{ - return write_after_op((void *)bpf_list_push_back); -} - -static __always_inline int use_after_unlock(void (*op)(void *head, void *node)) { struct foo *f; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index d8d8af623bc2..dc93887ed34c 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -6,9 +6,10 @@ #include "bpf_misc.h" #include "vmlinux.h" +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <errno.h> +#include <errno.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -164,8 +165,8 @@ int copy_test = 0; SEC("fentry.s/" SYS_PREFIX "sys_setdomainname") int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs) { - void *ptr = (void *)PT_REGS_PARM1(regs); - int len = PT_REGS_PARM2(regs); + void *ptr = (void *)PT_REGS_PARM1_SYSCALL(regs); + int len = PT_REGS_PARM2_SYSCALL(regs); int buf = 0; long ret; diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index eb8217803493..228ec45365a8 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -62,21 +62,23 @@ extern struct prog_test_ref_kfunc * bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **p, int a, int b) __ksym; extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) + static void test_kptr_unref(struct map_value *v) { struct prog_test_ref_kfunc *p; p = v->unref_ptr; /* store untrusted_ptr_or_null_ */ - v->unref_ptr = p; + WRITE_ONCE(v->unref_ptr, p); if (!p) return; if (p->a + p->b > 100) return; /* store untrusted_ptr_ */ - v->unref_ptr = p; + WRITE_ONCE(v->unref_ptr, p); /* store NULL */ - v->unref_ptr = NULL; + WRITE_ONCE(v->unref_ptr, NULL); } static void test_kptr_ref(struct map_value *v) @@ -85,7 +87,7 @@ static void test_kptr_ref(struct map_value *v) p = v->ref_ptr; /* store ptr_or_null_ */ - v->unref_ptr = p; + WRITE_ONCE(v->unref_ptr, p); if (!p) return; if (p->a + p->b > 100) @@ -99,7 +101,7 @@ static void test_kptr_ref(struct map_value *v) return; } /* store ptr_ */ - v->unref_ptr = p; + WRITE_ONCE(v->unref_ptr, p); bpf_kfunc_call_test_release(p); p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); diff --git a/tools/testing/selftests/bpf/progs/nested_trust_common.h b/tools/testing/selftests/bpf/progs/nested_trust_common.h new file mode 100644 index 000000000000..83d33931136e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_common.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#ifndef _NESTED_TRUST_COMMON_H +#define _NESTED_TRUST_COMMON_H + +#include <stdbool.h> + +bool bpf_cpumask_test_cpu(unsigned int cpu, const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; + +#endif /* _NESTED_TRUST_COMMON_H */ diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c new file mode 100644 index 000000000000..14aff7676436 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "nested_trust_common.h" + +char _license[] SEC("license") = "GPL"; + +/* Prototype for all of the program trace events below: + * + * TRACE_EVENT(task_newtask, + * TP_PROTO(struct task_struct *p, u64 clone_flags) + */ + +SEC("tp_btf/task_newtask") +__failure __msg("R2 must be referenced or trusted") +int BPF_PROG(test_invalid_nested_user_cpus, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_test_cpu(0, task->user_cpus_ptr); + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("R1 must have zero offset when passed to release func or trusted arg to kfunc") +int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_first_zero(&task->cpus_mask); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c new file mode 100644 index 000000000000..886ade4aa99d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#include "nested_trust_common.h" + +char _license[] SEC("license") = "GPL"; + +SEC("tp_btf/task_newtask") +__success +int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags) +{ + bpf_cpumask_test_cpu(0, task->cpus_ptr); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 7bd76b9e0f98..875513866032 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -156,10 +156,10 @@ probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max) { len = len < max ? len : max; if (len > 1) { - if (bpf_probe_read(dst, len, src)) + if (bpf_probe_read_kernel(dst, len, src)) return 0; } else if (len == 1) { - if (bpf_probe_read(dst, 1, src)) + if (bpf_probe_read_kernel(dst, 1, src)) return 0; } return len; @@ -216,7 +216,8 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, #endif for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) { filepart_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(cgroup_node, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(cgroup_node, name)); if (!cgroup_node) return payload; if (cgroup_node == cgroup_root_node) @@ -303,7 +304,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, cgroup_data->cgroup_full_length = 0; size_t cgroup_root_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(root_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(root_kernfs, name)); barrier_var(cgroup_root_length); if (cgroup_root_length <= MAX_PATH) { barrier_var(cgroup_root_length); @@ -312,7 +314,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, } size_t cgroup_proc_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(proc_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= MAX_PATH) { barrier_var(cgroup_proc_length); @@ -395,7 +398,8 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) arr_struct = bpf_map_lookup_elem(&data_heap, &zero); if (arr_struct == NULL) return 0; - bpf_probe_read(&arr_struct->array[0], sizeof(arr_struct->array[0]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[0], + sizeof(arr_struct->array[0]), kill_data); } else { int index = get_var_spid_index(arr_struct, spid); @@ -409,8 +413,9 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) #endif for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) if (arr_struct->array[i].meta.pid == 0) { - bpf_probe_read(&arr_struct->array[i], - sizeof(arr_struct->array[i]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[i], + sizeof(arr_struct->array[i]), + kill_data); bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -427,17 +432,17 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) if (delta_sec < STALE_INFO) { kill_data->kill_count++; kill_data->last_kill_time = bpf_ktime_get_ns(); - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } else { struct var_kill_data_t* kill_data = get_var_kill_data(ctx, spid, tpid, sig); if (kill_data == NULL) return 0; - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } } bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -487,8 +492,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload) #pragma unroll #endif for (int i = 0; i < MAX_PATH_DEPTH; i++) { - filepart_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp_dentry, d_name.name)); + filepart_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp_dentry, d_name.name)); barrier_var(filepart_length); if (filepart_length > MAX_PATH) break; @@ -572,7 +578,8 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, sysctl_data->sysctl_val_length = 0; sysctl_data->sysctl_path_length = 0; - size_t sysctl_val_length = bpf_probe_read_str(payload, CTL_MAXNAME, buf); + size_t sysctl_val_length = bpf_probe_read_kernel_str(payload, + CTL_MAXNAME, buf); barrier_var(sysctl_val_length); if (sysctl_val_length <= CTL_MAXNAME) { barrier_var(sysctl_val_length); @@ -580,8 +587,10 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, payload += sysctl_val_length; } - size_t sysctl_path_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp, f_path.dentry, d_name.name)); + size_t sysctl_path_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp, f_path.dentry, + d_name.name)); barrier_var(sysctl_path_length); if (sysctl_path_length <= MAX_PATH) { barrier_var(sysctl_path_length); @@ -638,7 +647,8 @@ int raw_tracepoint__sched_process_exit(void* ctx) struct var_kill_data_t* past_kill_data = &arr_struct->array[i]; if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) { - bpf_probe_read(kill_data, sizeof(*past_kill_data), past_kill_data); + bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data), + past_kill_data); void* payload = kill_data->payload; size_t offset = kill_data->payload_length; if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN) @@ -656,8 +666,10 @@ int raw_tracepoint__sched_process_exit(void* ctx) payload += comm_length; } - size_t cgroup_proc_length = bpf_probe_read_str(payload, KILL_TARGET_LEN, - BPF_CORE_READ(proc_kernfs, name)); + size_t cgroup_proc_length = + bpf_probe_read_kernel_str(payload, + KILL_TARGET_LEN, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= KILL_TARGET_LEN) { barrier_var(cgroup_proc_length); @@ -718,7 +730,8 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx) proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time); const char* filename = BPF_CORE_READ(bprm, filename); - size_t bin_path_length = bpf_probe_read_str(payload, MAX_FILENAME_LEN, filename); + size_t bin_path_length = + bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename); barrier_var(bin_path_length); if (bin_path_length <= MAX_FILENAME_LEN) { barrier_var(bin_path_length); @@ -922,7 +935,8 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry, filemod_data->payload); payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); - size_t len = bpf_probe_read_str(payload, MAX_FILEPATH_LENGTH, oldname); + size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH, + oldname); barrier_var(len); if (len <= MAX_FILEPATH_LENGTH) { barrier_var(len); diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c new file mode 100644 index 000000000000..e5db1a4287e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +long less_callback_ran = -1; +long removed_key = -1; +long first_data[2] = {-1, -1}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + less_callback_ran = 1; + + return node_a->key < node_b->key; +} + +static long __add_three(struct bpf_rb_root *root, struct bpf_spin_lock *lock) +{ + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + n->key = 5; + + m = bpf_obj_new(typeof(*m)); + if (!m) { + bpf_obj_drop(n); + return 2; + } + m->key = 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + bpf_spin_unlock(&glock); + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 3; + n->key = 3; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("tc") +long rbtree_add_nodes(void *ctx) +{ + return __add_three(&groot, &glock); +} + +SEC("tc") +long rbtree_add_and_remove(void *ctx) +{ + struct bpf_rb_node *res = NULL; + struct node_data *n, *m; + + n = bpf_obj_new(typeof(*n)); + if (!n) + goto err_out; + n->key = 5; + + m = bpf_obj_new(typeof(*m)); + if (!m) + goto err_out; + m->key = 3; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + res = bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + + n = container_of(res, struct node_data, node); + removed_key = n->key; + + bpf_obj_drop(n); + + return 0; +err_out: + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 1; +} + +SEC("tc") +long rbtree_first_and_remove(void *ctx) +{ + struct bpf_rb_node *res = NULL; + struct node_data *n, *m, *o; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + n->key = 3; + n->data = 4; + + m = bpf_obj_new(typeof(*m)); + if (!m) + goto err_out; + m->key = 5; + m->data = 6; + + o = bpf_obj_new(typeof(*o)); + if (!o) + goto err_out; + o->key = 1; + o->data = 2; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_rbtree_add(&groot, &m->node, less); + bpf_rbtree_add(&groot, &o->node, less); + + res = bpf_rbtree_first(&groot); + if (!res) { + bpf_spin_unlock(&glock); + return 2; + } + + o = container_of(res, struct node_data, node); + first_data[0] = o->data; + + res = bpf_rbtree_remove(&groot, &o->node); + bpf_spin_unlock(&glock); + + o = container_of(res, struct node_data, node); + removed_key = o->key; + + bpf_obj_drop(o); + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (!res) { + bpf_spin_unlock(&glock); + return 3; + } + + o = container_of(res, struct node_data, node); + first_data[1] = o->data; + bpf_spin_unlock(&glock); + + return 0; +err_out: + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c new file mode 100644 index 000000000000..60079b202c07 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +struct node_data { + int key; + int data; + struct bpf_rb_node node; +}; + +struct node_data2 { + int key; + struct bpf_rb_node node; + int data; +}; + +static bool less2(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data2 *node_a; + struct node_data2 *node_b; + + node_a = container_of(a, struct node_data2, node); + node_b = container_of(b, struct node_data2, node); + + return node_a->key < node_b->key; +} + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +SEC("tc") +long rbtree_api_add__add_wrong_type(void *ctx) +{ + struct node_data2 *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less2); + bpf_spin_unlock(&glock); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c new file mode 100644 index 000000000000..340f97da1084 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +/* BTF load should fail as bpf_rb_root __contains this type and points to + * 'node', but 'node' is not a bpf_rb_node + */ +struct node_data { + int key; + int data; + struct bpf_list_node node; +}; + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + + return node_a->key < node_b->key; +} + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); + +SEC("tc") +long rbtree_api_add__wrong_node_type(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_first(&groot); + bpf_spin_unlock(&glock); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c new file mode 100644 index 000000000000..bf3cba115897 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" +#include "bpf_misc.h" + +struct node_data { + long key; + long data; + struct bpf_rb_node node; +}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_rb_root groot __contains(node_data, node); +private(A) struct bpf_rb_root groot2 __contains(node_data, node); + +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + + return node_a->key < node_b->key; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_add(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_rbtree_add(&groot, &n->node, less); + return 0; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_remove(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_rbtree_remove(&groot, &n->node); + return 0; +} + +SEC("?tc") +__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root") +long rbtree_api_nolock_first(void *ctx) +{ + bpf_rbtree_first(&groot); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_remove_unadded_node(void *ctx) +{ + struct node_data *n, *m; + struct bpf_rb_node *res; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + m = bpf_obj_new(typeof(*m)); + if (!m) { + bpf_obj_drop(n); + return 1; + } + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + + /* This remove should pass verifier */ + res = bpf_rbtree_remove(&groot, &n->node); + n = container_of(res, struct node_data, node); + + /* This remove shouldn't, m isn't in an rbtree */ + res = bpf_rbtree_remove(&groot, &m->node); + m = container_of(res, struct node_data, node); + bpf_spin_unlock(&glock); + + if (n) + bpf_obj_drop(n); + if (m) + bpf_obj_drop(m); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=2 alloc_insn=11") +long rbtree_api_remove_no_drop(void *ctx) +{ + struct bpf_rb_node *res; + struct node_data *n; + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (!res) + goto unlock_err; + + res = bpf_rbtree_remove(&groot, res); + + n = container_of(res, struct node_data, node); + bpf_spin_unlock(&glock); + + /* bpf_obj_drop(n) is missing here */ + return 0; + +unlock_err: + bpf_spin_unlock(&glock); + return 1; +} + +SEC("?tc") +__failure __msg("arg#1 expected pointer to allocated object") +long rbtree_api_add_to_multiple_trees(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + + /* This add should fail since n already in groot's tree */ + bpf_rbtree_add(&groot2, &n->node, less); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_add_release_unlock_escape(void *ctx) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + /* After add() in previous critical section, n should be + * release_on_unlock and released after previous spin_unlock, + * so should not be possible to use it here + */ + bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_release_aliasing(void *ctx) +{ + struct node_data *n, *m, *o; + struct bpf_rb_node *res; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, less); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + + /* m and o point to the same node, + * but verifier doesn't know this + */ + res = bpf_rbtree_first(&groot); + if (!res) + return 1; + o = container_of(res, struct node_data, node); + + res = bpf_rbtree_first(&groot); + if (!res) + return 1; + m = container_of(res, struct node_data, node); + + bpf_rbtree_remove(&groot, &m->node); + /* This second remove shouldn't be possible. Retval of previous + * remove returns owning reference to m, which is the same + * node o's non-owning ref is pointing at + * + * In order to preserve property + * * owning ref must not be in rbtree + * * non-owning ref must be in rbtree + * + * o's ref must be invalidated after previous remove. Otherwise + * we'd have non-owning ref to node that isn't in rbtree, and + * verifier wouldn't be able to use type system to prevent remove + * of ref that already isn't in any tree. Would have to do runtime + * checks in that case. + */ + bpf_rbtree_remove(&groot, &o->node); + + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("rbtree_remove node input must be non-owning ref") +long rbtree_api_first_release_unlock_escape(void *ctx) +{ + struct bpf_rb_node *res; + struct node_data *n; + + bpf_spin_lock(&glock); + res = bpf_rbtree_first(&groot); + if (res) + n = container_of(res, struct node_data, node); + bpf_spin_unlock(&glock); + + bpf_spin_lock(&glock); + /* After first() in previous critical section, n should be + * release_on_unlock and released after previous spin_unlock, + * so should not be possible to use it here + */ + bpf_rbtree_remove(&groot, &n->node); + bpf_spin_unlock(&glock); + return 0; +} + +static bool less__bad_fn_call_add(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_add(&groot, &node_a->node, less); + + return node_a->key < node_b->key; +} + +static bool less__bad_fn_call_remove(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_remove(&groot, &node_a->node); + + return node_a->key < node_b->key; +} + +static bool less__bad_fn_call_first_unlock_after(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + bpf_rbtree_first(&groot); + bpf_spin_unlock(&glock); + + return node_a->key < node_b->key; +} + +static __always_inline +long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) +{ + struct node_data *n; + + n = bpf_obj_new(typeof(*n)); + if (!n) + return 1; + + bpf_spin_lock(&glock); + bpf_rbtree_add(&groot, &n->node, cb); + bpf_spin_unlock(&glock); + return 0; +} + +SEC("?tc") +__failure __msg("arg#1 expected pointer to allocated object") +long rbtree_api_add_bad_cb_bad_fn_call_add(void *ctx) +{ + return add_with_cb(less__bad_fn_call_add); +} + +SEC("?tc") +__failure __msg("rbtree_remove not allowed in rbtree cb") +long rbtree_api_add_bad_cb_bad_fn_call_remove(void *ctx) +{ + return add_with_cb(less__bad_fn_call_remove); +} + +SEC("?tc") +__failure __msg("can't spin_{lock,unlock} in rbtree cb") +long rbtree_api_add_bad_cb_bad_fn_call_first_unlock_after(void *ctx) +{ + return add_with_cb(less__bad_fn_call_first_unlock_after); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c index 9523333b8905..7a438600ae98 100644 --- a/tools/testing/selftests/bpf/progs/setget_sockopt.c +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -22,6 +22,7 @@ int nr_active; int nr_connect; int nr_binddev; int nr_socket_post_create; +int nr_fin_wait1; struct sockopt_test { int opt; @@ -386,6 +387,13 @@ int skops_sockopt(struct bpf_sock_ops *skops) nr_passive += !(bpf_test_sockopt(skops, sk) || test_tcp_maxseg(skops, sk) || test_tcp_saved_syn(skops, sk)); + bpf_sock_ops_cb_flags_set(skops, + skops->bpf_sock_ops_cb_flags | + BPF_SOCK_OPS_STATE_CB_FLAG); + break; + case BPF_SOCK_OPS_STATE_CB: + if (skops->args[1] == BPF_TCP_CLOSE_WAIT) + nr_fin_wait1 += !bpf_test_sockopt(skops, sk); break; } diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 753718595c26..e562be6356f3 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -135,7 +135,7 @@ struct strobe_value_loc { * tpidr_el0 for aarch64). * TLS_IMM_EXEC: absolute address of GOT entry containing offset * from thread pointer; - * TLS_GENERAL_DYN: absolute addres of double GOT entry + * TLS_GENERAL_DYN: absolute address of double GOT entry * containing tls_index_t struct; */ int64_t offset; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c index 1b47b94dbca0..f19d54eda4f1 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c @@ -5,6 +5,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" #include "task_kfunc_common.h" char _license[] SEC("license") = "GPL"; @@ -27,6 +28,7 @@ static struct __tasks_kfunc_map_value *insert_lookup_task(struct task_struct *ta } SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -44,6 +46,7 @@ int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_f } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 pointer type STRUCT task_struct must point") int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired, *stack_task = (struct task_struct *)&clone_flags; @@ -56,6 +59,7 @@ int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags) } SEC("kretprobe/free_task") +__failure __msg("reg type unsupported for arg#0 function") int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -68,6 +72,7 @@ int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64 } SEC("tp_btf/task_newtask") +__failure __msg("R1 must be referenced or trusted") int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -81,6 +86,7 @@ int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 cl SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -95,6 +101,7 @@ int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -107,6 +114,7 @@ int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_ } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(task_kfunc_get_non_kptr_param, struct task_struct *task, u64 clone_flags) { struct task_struct *kptr; @@ -122,6 +130,7 @@ int BPF_PROG(task_kfunc_get_non_kptr_param, struct task_struct *task, u64 clone_ } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(task_kfunc_get_non_kptr_acquired, struct task_struct *task, u64 clone_flags) { struct task_struct *kptr, *acquired; @@ -140,6 +149,7 @@ int BPF_PROG(task_kfunc_get_non_kptr_acquired, struct task_struct *task, u64 clo } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 expected pointer to map value") int BPF_PROG(task_kfunc_get_null, struct task_struct *task, u64 clone_flags) { struct task_struct *kptr; @@ -155,6 +165,7 @@ int BPF_PROG(task_kfunc_get_null, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_flags) { struct task_struct *kptr; @@ -174,6 +185,7 @@ int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_fla } SEC("tp_btf/task_newtask") +__failure __msg("Unreleased reference") int BPF_PROG(task_kfunc_get_unreleased, struct task_struct *task, u64 clone_flags) { struct task_struct *kptr; @@ -193,6 +205,7 @@ int BPF_PROG(task_kfunc_get_unreleased, struct task_struct *task, u64 clone_flag } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket") int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_flags) { struct __tasks_kfunc_map_value *v; @@ -208,6 +221,7 @@ int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_f } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 pointer type STRUCT task_struct must point") int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired = (struct task_struct *)&clone_flags; @@ -219,6 +233,7 @@ int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 is ptr_or_null_ expected ptr_ or socket") int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags) { struct __tasks_kfunc_map_value local, *v; @@ -251,6 +266,7 @@ int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +__failure __msg("release kernel function bpf_task_release expects") int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_flags) { /* Cannot release trusted task pointer which was not acquired. */ @@ -260,6 +276,7 @@ int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_ } SEC("tp_btf/task_newtask") +__failure __msg("arg#0 is ptr_or_null_ expected ptr_ or socket") int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired; @@ -273,6 +290,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl } SEC("lsm/task_free") +__failure __msg("reg type unsupported for arg#0 function") int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task) { struct task_struct *acquired; diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index a1e45fec8938..3b5dc34d23e9 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -92,18 +92,19 @@ int handle_uretprobe_byname(struct pt_regs *ctx) } SEC("uprobe") -int handle_uprobe_byname2(struct pt_regs *ctx) +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { - unsigned int size = PT_REGS_PARM1(ctx); + char mode_buf[2] = {}; - /* verify malloc size */ - if (size == 1) + /* verify fopen mode */ + bpf_probe_read_user(mode_buf, sizeof(mode_buf), mode); + if (mode_buf[0] == 'r' && mode_buf[1] == 0) uprobe_byname2_res = 7; return 0; } SEC("uretprobe") -int handle_uretprobe_byname2(struct pt_regs *ctx) +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { uretprobe_byname2_res = 8; return 0; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index 227e85e85dda..9fc603c9d673 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -34,6 +34,11 @@ __be16 dport = 0; int test_exist_lookup = -ENOENT; u32 test_exist_lookup_mark = 0; +enum nf_nat_manip_type___local { + NF_NAT_MANIP_SRC___local, + NF_NAT_MANIP_DST___local +}; + struct nf_conn; struct bpf_ct_opts___local { @@ -58,7 +63,7 @@ int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym; int bpf_ct_set_status(struct nf_conn *, u32) __ksym; int bpf_ct_change_status(struct nf_conn *, u32) __ksym; int bpf_ct_set_nat_info(struct nf_conn *, union nf_inet_addr *, - int port, enum nf_nat_manip_type) __ksym; + int port, enum nf_nat_manip_type___local) __ksym; static __always_inline void nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, @@ -157,10 +162,10 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, /* snat */ saddr.ip = bpf_get_prandom_u32(); - bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC); + bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local); /* dnat */ daddr.ip = bpf_get_prandom_u32(); - bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST); + bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local); ct_ins = bpf_ct_insert_entry(ct); if (ct_ins) { diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index 2833ad722cb7..66b304982245 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -600,7 +600,7 @@ static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, return TC_ACT_SHOT; } - /* Skip the remainig next hops (may be zero). */ + /* Skip the remaining next hops (may be zero). */ return skip_next_hops(pkt, encap->unigue.hop_count - encap->unigue.next_hop - 1); } @@ -610,8 +610,8 @@ static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, * * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) * - * clang will substitue a costant for sizeof, which allows the verifier - * to track it's value. Based on this, it can figure out the constant + * clang will substitute a constant for sizeof, which allows the verifier + * to track its value. Based on this, it can figure out the constant * return value, and calling code works while still being "generic" to * IPv4 and IPv6. */ diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c index 09ad5a4ebd1f..591104e79812 100644 --- a/tools/testing/selftests/bpf/progs/test_deny_namespace.c +++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c @@ -6,7 +6,7 @@ #include <linux/capability.h> struct kernel_cap_struct { - __u32 cap[_LINUX_CAPABILITY_U32S_3]; + __u64 val; } __attribute__((preserve_access_index)); struct cred { @@ -19,14 +19,13 @@ SEC("lsm.s/userns_create") int BPF_PROG(test_userns_create, const struct cred *cred, int ret) { struct kernel_cap_struct caps = cred->cap_effective; - int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN); - __u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN); + __u64 cap_mask = BIT_LL(CAP_SYS_ADMIN); if (ret) return 0; ret = -EPERM; - if (caps.cap[cap_index] & cap_mask) + if (caps.val & cap_mask) return 0; return -EPERM; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index 7b42dad187b8..23970a20b324 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -3,10 +3,9 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" -#ifndef MAX_STACK #define MAX_STACK (512 - 3 * 32 + 8) -#endif static __attribute__ ((noinline)) int f0(int var, struct __sk_buff *skb) @@ -39,7 +38,8 @@ int f3(int val, struct __sk_buff *skb, int var) } SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("combined stack size of 4 calls is 544") +int global_func1(struct __sk_buff *skb) { return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); } diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 97b7031d0e22..98327bdbbfd2 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct Small { int x; @@ -21,7 +22,8 @@ __noinline int foo(const struct Big *big) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("invalid indirect read from stack") +int global_func10(struct __sk_buff *skb) { const struct Small small = {.x = skb->len }; diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c index ef5277d982d9..283e036dc401 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func11.c +++ b/tools/testing/selftests/bpf/progs/test_global_func11.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct S { int x; @@ -13,7 +14,8 @@ __noinline int foo(const struct S *s) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("Caller passes invalid args into func#1") +int global_func11(struct __sk_buff *skb) { return foo((const void *)skb); } diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c index 62343527cc59..7f159d83c6f6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func12.c +++ b/tools/testing/selftests/bpf/progs/test_global_func12.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct S { int x; @@ -13,7 +14,8 @@ __noinline int foo(const struct S *s) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("invalid mem access 'mem_or_null'") +int global_func12(struct __sk_buff *skb) { const struct S s = {.x = skb->len }; diff --git a/tools/testing/selftests/bpf/progs/test_global_func13.c b/tools/testing/selftests/bpf/progs/test_global_func13.c index ff8897c1ac22..02ea80da75b5 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func13.c +++ b/tools/testing/selftests/bpf/progs/test_global_func13.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct S { int x; @@ -16,7 +17,8 @@ __noinline int foo(const struct S *s) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("Caller passes invalid args into func#1") +int global_func13(struct __sk_buff *skb) { const struct S *s = (const struct S *)(0xbedabeda); diff --git a/tools/testing/selftests/bpf/progs/test_global_func14.c b/tools/testing/selftests/bpf/progs/test_global_func14.c index 698c77199ebf..33b7d5efd7b2 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func14.c +++ b/tools/testing/selftests/bpf/progs/test_global_func14.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct S; @@ -14,7 +15,8 @@ __noinline int foo(const struct S *s) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("reference type('FWD S') size cannot be determined") +int global_func14(struct __sk_buff *skb) { return foo(NULL); diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c index c19c435988d5..b512d6a6c75e 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func15.c +++ b/tools/testing/selftests/bpf/progs/test_global_func15.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __noinline int foo(unsigned int *v) { @@ -12,7 +13,8 @@ __noinline int foo(unsigned int *v) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("At program exit the register R0 has value") +int global_func15(struct __sk_buff *skb) { unsigned int v = 1; diff --git a/tools/testing/selftests/bpf/progs/test_global_func16.c b/tools/testing/selftests/bpf/progs/test_global_func16.c index 0312d1e8d8c0..e7206304632e 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func16.c +++ b/tools/testing/selftests/bpf/progs/test_global_func16.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __noinline int foo(int (*arr)[10]) { @@ -12,7 +13,8 @@ __noinline int foo(int (*arr)[10]) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__failure __msg("invalid indirect read from stack") +int global_func16(struct __sk_buff *skb) { int array[10]; diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c index 2b8b9b8ba018..a32e11c7d933 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func17.c +++ b/tools/testing/selftests/bpf/progs/test_global_func17.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include <vmlinux.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __noinline int foo(int *p) { @@ -10,7 +11,8 @@ __noinline int foo(int *p) const volatile int i; SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("Caller passes invalid args into func#1") +int global_func17(struct __sk_buff *skb) { return foo((int *)&i); } diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c index 2c18d82923a2..3dce97fb52a4 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func2.c +++ b/tools/testing/selftests/bpf/progs/test_global_func2.c @@ -1,4 +1,45 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + #define MAX_STACK (512 - 3 * 32) -#include "test_global_func1.c" + +static __attribute__ ((noinline)) +int f0(int var, struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + return f0(0, skb) + skb->len; +} + +int f3(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb, 1); +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->ifindex * val * var; +} + +SEC("tc") +__success +int global_func2(struct __sk_buff *skb) +{ + return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c index 01bf8275dfd6..142b682d3c2f 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func3.c +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -3,6 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __attribute__ ((noinline)) int f1(struct __sk_buff *skb) @@ -46,20 +47,15 @@ int f7(struct __sk_buff *skb) return f6(skb); } -#ifndef NO_FN8 __attribute__ ((noinline)) int f8(struct __sk_buff *skb) { return f7(skb); } -#endif SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("the call stack of 8 frames") +int global_func3(struct __sk_buff *skb) { -#ifndef NO_FN8 return f8(skb); -#else - return f7(skb); -#endif } diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c index 610f75edf276..1733d87ad3f3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func4.c +++ b/tools/testing/selftests/bpf/progs/test_global_func4.c @@ -1,4 +1,55 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2020 Facebook */ -#define NO_FN8 -#include "test_global_func3.c" +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + val; +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + return f2(var, skb) + val; +} + +__attribute__ ((noinline)) +int f4(struct __sk_buff *skb) +{ + return f3(1, skb, 2); +} + +__attribute__ ((noinline)) +int f5(struct __sk_buff *skb) +{ + return f4(skb); +} + +__attribute__ ((noinline)) +int f6(struct __sk_buff *skb) +{ + return f5(skb); +} + +__attribute__ ((noinline)) +int f7(struct __sk_buff *skb) +{ + return f6(skb); +} + +SEC("tc") +__success +int global_func4(struct __sk_buff *skb) +{ + return f7(skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index 9248d03e0d06..cc55aedaf82d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -3,6 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __attribute__ ((noinline)) int f1(struct __sk_buff *skb) @@ -25,7 +26,8 @@ int f3(int val, struct __sk_buff *skb) } SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("expected pointer to ctx, but got PTR") +int global_func5(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); } diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c index af8c78bdfb25..46c38c8f2cf0 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func6.c +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -3,6 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __attribute__ ((noinline)) int f1(struct __sk_buff *skb) @@ -25,7 +26,8 @@ int f3(int val, struct __sk_buff *skb) } SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("modified ctx ptr R2") +int global_func6(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); } diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c index 6cb8e2f5254c..f182febfde3c 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func7.c +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -3,6 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __attribute__ ((noinline)) void foo(struct __sk_buff *skb) @@ -11,7 +12,8 @@ void foo(struct __sk_buff *skb) } SEC("tc") -int test_cls(struct __sk_buff *skb) +__failure __msg("foo() doesn't return scalar") +int global_func7(struct __sk_buff *skb) { foo(skb); return 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c index d55a6544b1ab..9b9c57fa2dd3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func8.c +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -3,6 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" __noinline int foo(struct __sk_buff *skb) { @@ -10,7 +11,8 @@ __noinline int foo(struct __sk_buff *skb) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__success +int global_func8(struct __sk_buff *skb) { if (!foo(skb)) return 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func9.c b/tools/testing/selftests/bpf/progs/test_global_func9.c index bd233ddede98..1f2cb0159b8d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func9.c +++ b/tools/testing/selftests/bpf/progs/test_global_func9.c @@ -2,6 +2,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" struct S { int x; @@ -74,7 +75,8 @@ __noinline int quuz(int **p) } SEC("cgroup_skb/ingress") -int test_cls(struct __sk_buff *skb) +__success +int global_func9(struct __sk_buff *skb) { int result = 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c new file mode 100644 index 000000000000..7faa8eef0598 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +static long stack[256]; + +/* + * KPROBE contexts + */ + +__weak int kprobe_typedef_ctx_subprog(bpf_user_pt_regs_t *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_typedef_ctx(void *ctx) +{ + return kprobe_typedef_ctx_subprog(ctx); +} + +#define pt_regs_struct_t typeof(*(__PT_REGS_CAST((struct pt_regs *)NULL))) + +__weak int kprobe_struct_ctx_subprog(pt_regs_struct_t *ctx) +{ + return bpf_get_stack((void *)ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_resolved_ctx(void *ctx) +{ + return kprobe_struct_ctx_subprog(ctx); +} + +/* this is current hack to make this work on old kernels */ +struct bpf_user_pt_regs_t {}; + +__weak int kprobe_workaround_ctx_subprog(struct bpf_user_pt_regs_t *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?kprobe") +__success +int kprobe_workaround_ctx(void *ctx) +{ + return kprobe_workaround_ctx_subprog(ctx); +} + +/* + * RAW_TRACEPOINT contexts + */ + +__weak int raw_tp_ctx_subprog(struct bpf_raw_tracepoint_args *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?raw_tp") +__success +int raw_tp_ctx(void *ctx) +{ + return raw_tp_ctx_subprog(ctx); +} + +/* + * RAW_TRACEPOINT_WRITABLE contexts + */ + +__weak int raw_tp_writable_ctx_subprog(struct bpf_raw_tracepoint_args *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?raw_tp") +__success +int raw_tp_writable_ctx(void *ctx) +{ + return raw_tp_writable_ctx_subprog(ctx); +} + +/* + * PERF_EVENT contexts + */ + +__weak int perf_event_ctx_subprog(struct bpf_perf_event_data *ctx) +{ + return bpf_get_stack(ctx, &stack, sizeof(stack), 0); +} + +SEC("?perf_event") +__success +int perf_event_ctx(void *ctx) +{ + return perf_event_ctx_subprog(ctx); +} diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index f4a8250329b2..2fbef3cc7ad8 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -10,6 +10,7 @@ #include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; extern void bpf_key_put(struct bpf_key *key) __ksym; @@ -19,6 +20,7 @@ extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, struct { __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); } ringbuf SEC(".maps"); struct { @@ -33,6 +35,7 @@ int err, pid; char _license[] SEC("license") = "GPL"; SEC("?lsm.s/bpf") +__failure __msg("cannot pass in dynptr at an offset=-8") int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) { unsigned long val; @@ -42,6 +45,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) } SEC("?lsm.s/bpf") +__failure __msg("arg#0 expected pointer to stack or dynptr_ptr") int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) { unsigned long val; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 98c6493d9b91..21b19b758c4e 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -16,6 +16,16 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#if defined(IPROUTE2_HAVE_LIBBPF) +/* Use a new-style map definition. */ +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_BY_NAME); + __uint(max_entries, 1); +} server_map SEC(".maps"); +#else /* Pin map under /sys/fs/bpf/tc/globals/<map name> */ #define PIN_GLOBAL_NS 2 @@ -35,6 +45,7 @@ struct { .max_elem = 1, .pinning = PIN_GLOBAL_NS, }; +#endif char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c new file mode 100644 index 000000000000..dcf46adfda04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define IPROUTE2_HAVE_LIBBPF +#include "test_sk_assign.c" diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c index f8e9256cf18d..a8d602d7c88a 100644 --- a/tools/testing/selftests/bpf/progs/test_subprogs.c +++ b/tools/testing/selftests/bpf/progs/test_subprogs.c @@ -47,7 +47,7 @@ static __noinline int sub5(int v) return sub1(v) - 1; /* compensates sub1()'s + 1 */ } -/* unfortunately verifier rejects `struct task_struct *t` as an unkown pointer +/* unfortunately verifier rejects `struct task_struct *t` as an unknown pointer * type, so we need to accept pointer as integer and then cast it inside the * function */ diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index a0e7762b1e5a..e6e678aa9874 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -38,6 +38,10 @@ static const int cfg_udp_src = 20000; #define VXLAN_FLAGS 0x8 #define VXLAN_VNI 1 +#ifndef NEXTHDR_DEST +#define NEXTHDR_DEST 60 +#endif + /* MPLS label 1000 with S bit (last label) set and ttl of 255. */ static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 | MPLS_LS_S_MASK | 0xff); @@ -363,6 +367,61 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, return TC_ACT_OK; } +static int encap_ipv6_ipip6(struct __sk_buff *skb) +{ + struct iphdr iph_inner; + struct v6hdr h_outer; + struct tcphdr tcph; + struct ethhdr eth; + __u64 flags; + int olen; + + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + /* filter only packets we want */ + if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2), + &tcph, sizeof(tcph)) < 0) + return TC_ACT_OK; + + if (tcph.dest != __bpf_constant_htons(cfg_port)) + return TC_ACT_OK; + + olen = sizeof(h_outer.ip); + + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; + + /* add room between mac and network header */ + if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) + return TC_ACT_SHOT; + + /* prepare new outer network header */ + memset(&h_outer.ip, 0, sizeof(h_outer.ip)); + h_outer.ip.version = 6; + h_outer.ip.hop_limit = iph_inner.ttl; + h_outer.ip.saddr.s6_addr[1] = 0xfd; + h_outer.ip.saddr.s6_addr[15] = 1; + h_outer.ip.daddr.s6_addr[1] = 0xfd; + h_outer.ip.daddr.s6_addr[15] = 2; + h_outer.ip.payload_len = iph_inner.tot_len; + h_outer.ip.nexthdr = IPPROTO_IPIP; + + /* store new outer network header */ + if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, + BPF_F_INVALIDATE_HASH) < 0) + return TC_ACT_SHOT; + + /* update eth->h_proto */ + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IPV6); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, __u16 l2_proto) { @@ -461,6 +520,15 @@ int __encap_ip6tnl_none(struct __sk_buff *skb) return TC_ACT_OK; } +SEC("encap_ipip6_none") +int __encap_ipip6_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv6_ipip6(skb); + else + return TC_ACT_OK; +} + SEC("encap_ip6gre_none") int __encap_ip6gre_none(struct __sk_buff *skb) { @@ -528,13 +596,33 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb) static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) { + __u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO; + struct ipv6_opt_hdr ip6_opt_hdr; struct gre_hdr greh; struct udphdr udph; int olen = len; switch (proto) { case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + case NEXTHDR_DEST: + if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr, + sizeof(ip6_opt_hdr)) < 0) + return TC_ACT_OK; + switch (ip6_opt_hdr.nexthdr) { + case IPPROTO_IPIP: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4; + break; + case IPPROTO_IPV6: + flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6; + break; + default: + return TC_ACT_OK; + } break; case IPPROTO_GRE: olen += sizeof(struct gre_hdr); @@ -569,8 +657,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) return TC_ACT_OK; } - if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, - BPF_F_ADJ_ROOM_FIXED_GSO)) + if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags)) return TC_ACT_SHOT; return TC_ACT_OK; diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 98af55f0bcd3..508da4a23c4f 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -82,6 +82,27 @@ int gre_set_tunnel(struct __sk_buff *skb) } SEC("tc") +int gre_set_tunnel_no_key(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER | + BPF_F_NO_TUNNEL_KEY); + if (ret < 0) { + log_err(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("tc") int gre_get_tunnel(struct __sk_buff *skb) { int ret; diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c index ab75522e2eeb..da4bf89d004c 100644 --- a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c @@ -6,18 +6,22 @@ #include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" int uprobe_byname_parm1 = 0; int uprobe_byname_ran = 0; int uretprobe_byname_rc = 0; +int uretprobe_byname_ret = 0; int uretprobe_byname_ran = 0; -size_t uprobe_byname2_parm1 = 0; +u64 uprobe_byname2_parm1 = 0; int uprobe_byname2_ran = 0; -char *uretprobe_byname2_rc = NULL; +u64 uretprobe_byname2_rc = 0; int uretprobe_byname2_ran = 0; int test_pid; +int a[8]; + /* This program cannot auto-attach, but that should not stop other * programs from attaching. */ @@ -28,44 +32,84 @@ int handle_uprobe_noautoattach(struct pt_regs *ctx) } SEC("uprobe//proc/self/exe:autoattach_trigger_func") -int handle_uprobe_byname(struct pt_regs *ctx) +int BPF_UPROBE(handle_uprobe_byname + , int arg1 + , int arg2 + , int arg3 +#if FUNC_REG_ARG_CNT > 3 + , int arg4 +#endif +#if FUNC_REG_ARG_CNT > 4 + , int arg5 +#endif +#if FUNC_REG_ARG_CNT > 5 + , int arg6 +#endif +#if FUNC_REG_ARG_CNT > 6 + , int arg7 +#endif +#if FUNC_REG_ARG_CNT > 7 + , int arg8 +#endif +) { uprobe_byname_parm1 = PT_REGS_PARM1_CORE(ctx); uprobe_byname_ran = 1; + + a[0] = arg1; + a[1] = arg2; + a[2] = arg3; +#if FUNC_REG_ARG_CNT > 3 + a[3] = arg4; +#endif +#if FUNC_REG_ARG_CNT > 4 + a[4] = arg5; +#endif +#if FUNC_REG_ARG_CNT > 5 + a[5] = arg6; +#endif +#if FUNC_REG_ARG_CNT > 6 + a[6] = arg7; +#endif +#if FUNC_REG_ARG_CNT > 7 + a[7] = arg8; +#endif return 0; } SEC("uretprobe//proc/self/exe:autoattach_trigger_func") -int handle_uretprobe_byname(struct pt_regs *ctx) +int BPF_URETPROBE(handle_uretprobe_byname, int ret) { uretprobe_byname_rc = PT_REGS_RC_CORE(ctx); + uretprobe_byname_ret = ret; uretprobe_byname_ran = 2; + return 0; } -SEC("uprobe/libc.so.6:malloc") -int handle_uprobe_byname2(struct pt_regs *ctx) +SEC("uprobe/libc.so.6:fopen") +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uprobe_byname2_parm1 = PT_REGS_PARM1_CORE(ctx); + uprobe_byname2_parm1 = (u64)(long)pathname; uprobe_byname2_ran = 3; return 0; } -SEC("uretprobe/libc.so.6:malloc") -int handle_uretprobe_byname2(struct pt_regs *ctx) +SEC("uretprobe/libc.so.6:fopen") +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uretprobe_byname2_rc = (char *)PT_REGS_RC_CORE(ctx); + uretprobe_byname2_rc = (u64)(long)ret; uretprobe_byname2_ran = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index ce419304ff1f..7748cc23de8a 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -59,10 +59,14 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) if (!data_val) return 0; - bpf_probe_read(&value, sizeof(value), &attr->value); - - bpf_copy_from_user(data_val, sizeof(struct data), - (void *)(unsigned long)value); + ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value); + if (ret) + return ret; + + ret = bpf_copy_from_user(data_val, sizeof(struct data), + (void *)(unsigned long)value); + if (ret) + return ret; if (data_val->data_len > sizeof(data_val->data)) return -EINVAL; diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index e9dfa0313d1b..4b8e37f7fd06 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -42,7 +42,7 @@ int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; @@ -60,7 +60,7 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 53b64c999450..297c260fc364 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -9,6 +9,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) void *data = (void *)(long)xdp->data; int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__TARGET_ARCH_s390) + int tailroom = 512; +#else + int tailroom = 320; +#endif /* Data length determine test case */ @@ -20,7 +26,7 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) offset = 128; } else if (data_len == 128) { /* Max tail grow 3520 */ - offset = 4096 - 256 - 320 - data_len; + offset = 4096 - 256 - tailroom - data_len; } else if (data_len == 9000) { offset = 10; } else if (data_len == 9001) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index 134768f6b788..4ddcb6dfe500 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -98,7 +98,7 @@ bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt) return true; } -/* Hint, VLANs are choosen to hit network-byte-order issues */ +/* Hint, VLANs are chosen to hit network-byte-order issues */ #define TESTVLAN 4011 /* 0xFAB */ // #define TO_VLAN 4000 /* 0xFA0 (hint 0xOA0 = 160) */ @@ -195,7 +195,7 @@ int xdp_prognum2(struct xdp_md *ctx) /* Moving Ethernet header, dest overlap with src, memmove handle this */ dest = data; - dest+= VLAN_HDR_SZ; + dest += VLAN_HDR_SZ; /* * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c index f3201dc69a60..03ee946c6bf7 100644 --- a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c +++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c @@ -16,6 +16,7 @@ struct sample { struct { __uint(type, BPF_MAP_TYPE_USER_RINGBUF); + __uint(max_entries, 4096); } user_ringbuf SEC(".maps"); struct { @@ -39,7 +40,8 @@ bad_access1(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to read before the pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("negative offset dynptr_ptr ptr") int user_ringbuf_callback_bad_access1(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, bad_access1, NULL, 0); @@ -61,7 +63,8 @@ bad_access2(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to read past the end of the pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("dereference of modified dynptr_ptr ptr") int user_ringbuf_callback_bad_access2(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, bad_access2, NULL, 0); @@ -80,7 +83,8 @@ write_forbidden(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to write to that pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("invalid mem access 'dynptr_ptr'") int user_ringbuf_callback_write_forbidden(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, write_forbidden, NULL, 0); @@ -99,7 +103,8 @@ null_context_write(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to write to that pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") int user_ringbuf_callback_null_context_write(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, null_context_write, NULL, 0); @@ -120,7 +125,8 @@ null_context_read(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to write to that pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") int user_ringbuf_callback_null_context_read(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, null_context_read, NULL, 0); @@ -139,7 +145,8 @@ try_discard_dynptr(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to read past the end of the pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("cannot release unowned const bpf_dynptr") int user_ringbuf_callback_discard_dynptr(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, try_discard_dynptr, NULL, 0); @@ -158,7 +165,8 @@ try_submit_dynptr(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to read past the end of the pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("cannot release unowned const bpf_dynptr") int user_ringbuf_callback_submit_dynptr(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, try_submit_dynptr, NULL, 0); @@ -175,7 +183,8 @@ invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context) /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should * not be able to write to that pointer. */ -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("At callback return the register R0 has value") int user_ringbuf_callback_invalid_return(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0); @@ -197,14 +206,16 @@ try_reinit_dynptr_ringbuf(struct bpf_dynptr *dynptr, void *context) return 0; } -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("Dynptr has to be an uninitialized dynptr") int user_ringbuf_callback_reinit_dynptr_mem(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_mem, NULL, 0); return 0; } -SEC("?raw_tp/") +SEC("?raw_tp") +__failure __msg("Dynptr has to be an uninitialized dynptr") int user_ringbuf_callback_reinit_dynptr_ringbuf(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_ringbuf, NULL, 0); diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c new file mode 100644 index 000000000000..87c247d56f72 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_features.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/netdev.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <asm-generic/errno-base.h> + +#include "xdp_features.h" + +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \ + (a).s6_addr32[1] == (b).s6_addr32[1] && \ + (a).s6_addr32[2] == (b).s6_addr32[2] && \ + (a).s6_addr32[3] == (b).s6_addr32[3]) + +struct net_device; +struct bpf_prog; + +struct xdp_cpumap_stats { + unsigned int redirect; + unsigned int pass; + unsigned int drop; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} dut_stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 1); +} cpu_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 1); +} dev_map SEC(".maps"); + +const volatile struct in6_addr tester_addr; +const volatile struct in6_addr dut_addr; + +static __always_inline int +xdp_process_echo_packet(struct xdp_md *xdp, bool dut) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + struct tlv_hdr *tlv; + struct udphdr *uh; + __be16 port; + __u8 *cmd; + + if (eh + 1 > (struct ethhdr *)data_end) + return -EINVAL; + + if (eh->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *ih = (struct iphdr *)(eh + 1); + __be32 saddr = dut ? tester_addr.s6_addr32[3] + : dut_addr.s6_addr32[3]; + __be32 daddr = dut ? dut_addr.s6_addr32[3] + : tester_addr.s6_addr32[3]; + + ih = (struct iphdr *)(eh + 1); + if (ih + 1 > (struct iphdr *)data_end) + return -EINVAL; + + if (saddr != ih->saddr) + return -EINVAL; + + if (daddr != ih->daddr) + return -EINVAL; + + if (ih->protocol != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih + 1); + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) { + struct in6_addr saddr = dut ? tester_addr : dut_addr; + struct in6_addr daddr = dut ? dut_addr : tester_addr; + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1); + + if (ih6 + 1 > (struct ipv6hdr *)data_end) + return -EINVAL; + + if (!ipv6_addr_equal(saddr, ih6->saddr)) + return -EINVAL; + + if (!ipv6_addr_equal(daddr, ih6->daddr)) + return -EINVAL; + + if (ih6->nexthdr != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih6 + 1); + } else { + return -EINVAL; + } + + if (uh + 1 > (struct udphdr *)data_end) + return -EINVAL; + + port = dut ? uh->dest : uh->source; + if (port != bpf_htons(DUT_ECHO_PORT)) + return -EINVAL; + + tlv = (struct tlv_hdr *)(uh + 1); + if (tlv + 1 > data_end) + return -EINVAL; + + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL; +} + +static __always_inline int +xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut) +{ + __u32 *val, key = 0; + + if (xdp_process_echo_packet(xdp, tx)) + return -EINVAL; + + if (dut) + val = bpf_map_lookup_elem(&dut_stats, &key); + else + val = bpf_map_lookup_elem(&stats, &key); + + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +/* Tester */ + +SEC("xdp") +int xdp_tester_check_tx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, false); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_tester_check_rx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, false, false); + + return XDP_PASS; +} + +/* DUT */ + +SEC("xdp") +int xdp_do_pass(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, true); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_do_drop(struct xdp_md *xdp) +{ + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + return XDP_DROP; +} + +SEC("xdp") +int xdp_do_aborted(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return XDP_ABORTED; +} + +SEC("xdp") +int xdp_do_tx(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return XDP_TX; +} + +SEC("xdp") +int xdp_do_redirect(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return bpf_redirect_map(&cpu_map, 0, 0); +} + +SEC("tp_btf/xdp_exception") +int BPF_PROG(xdp_exception, const struct net_device *dev, + const struct bpf_prog *xdp, __u32 act) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("tp_btf/xdp_cpumap_kthread") +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("xdp/cpumap") +int xdp_do_redirect_cpumap(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return bpf_redirect_map(&dev_map, 0, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c new file mode 100644 index 000000000000..4c55b4d79d3d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 256); + __type(key, __u32); + __type(value, __u32); +} xsk SEC(".maps"); + +extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, + __u64 *timestamp) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, + __u32 *hash) __ksym; + +SEC("xdp") +int rx(struct xdp_md *ctx) +{ + void *data, *data_meta, *data_end; + struct ipv6hdr *ip6h = NULL; + struct ethhdr *eth = NULL; + struct udphdr *udp = NULL; + struct iphdr *iph = NULL; + struct xdp_meta *meta; + int ret; + + data = (void *)(long)ctx->data; + data_end = (void *)(long)ctx->data_end; + eth = data; + if (eth + 1 < data_end) { + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + iph = (void *)(eth + 1); + if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP) + udp = (void *)(iph + 1); + } + if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + ip6h = (void *)(eth + 1); + if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP) + udp = (void *)(ip6h + 1); + } + if (udp && udp + 1 > data_end) + udp = NULL; + } + + if (!udp) + return XDP_PASS; + + if (udp->dest != bpf_htons(9091)) + return XDP_PASS; + + bpf_printk("forwarding UDP:9091 to AF_XDP"); + + ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (ret != 0) { + bpf_printk("bpf_xdp_adjust_meta returned %d", ret); + return XDP_PASS; + } + + data = (void *)(long)ctx->data; + data_meta = (void *)(long)ctx->data_meta; + meta = data_meta; + + if (meta + 1 > data) { + bpf_printk("bpf_xdp_adjust_meta doesn't appear to work"); + return XDP_PASS; + } + + if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) + bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); + else + meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ + + if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) + bpf_printk("populated rx_hash with %u", meta->rx_hash); + else + meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ + + return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c new file mode 100644 index 000000000000..77678b034389 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 4); + __type(key, __u32); + __type(value, __u32); +} xsk SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} prog_arr SEC(".maps"); + +extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, + __u64 *timestamp) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, + __u32 *hash) __ksym; + +SEC("xdp") +int rx(struct xdp_md *ctx) +{ + void *data, *data_meta; + struct xdp_meta *meta; + u64 timestamp = -1; + int ret; + + /* Reserve enough for all custom metadata. */ + + ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (ret != 0) + return XDP_DROP; + + data = (void *)(long)ctx->data; + data_meta = (void *)(long)ctx->data_meta; + + if (data_meta + sizeof(struct xdp_meta) > data) + return XDP_DROP; + + meta = data_meta; + + /* Export metadata. */ + + /* We expect veth bpf_xdp_metadata_rx_timestamp to return 0 HW + * timestamp, so put some non-zero value into AF_XDP frame for + * the userspace. + */ + bpf_xdp_metadata_rx_timestamp(ctx, ×tamp); + if (timestamp == 0) + meta->rx_timestamp = 1; + + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash); + + return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c new file mode 100644 index 000000000000..cf69d05451c3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "xdp_metadata.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, + __u32 *hash) __ksym; + +int called; + +SEC("freplace/rx") +int freplace_rx(struct xdp_md *ctx) +{ + u32 hash = 0; + /* Call _any_ metadata function to make sure we don't crash. */ + bpf_xdp_metadata_rx_hash(ctx, &hash); + called++; + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 736686e903f6..07d786329105 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -310,7 +310,7 @@ static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale, static __always_inline void values_inc_synacks(void) { __u32 key = 1; - __u32 *value; + __u64 *value; value = bpf_map_lookup_elem(&values, &key); if (value) diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c new file mode 100644 index 000000000000..744a01d0e57d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Intel */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, 1); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} xsk SEC(".maps"); + +static unsigned int idx; + +SEC("xdp") int xsk_def_prog(struct xdp_md *xdp) +{ + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + +SEC("xdp") int xsk_xdp_drop(struct xdp_md *xdp) +{ + /* Drop every other packet */ + if (idx++ % 2) + return XDP_DROP; + + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index 0bd9990e83fa..f4936834f76f 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -91,7 +91,7 @@ static void try_skeleton_template() skel.detach(); - /* destructor will destory underlying skeleton */ + /* destructor will destroy underlying skeleton */ } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index b73152822aa2..7fc00e423e4d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1275,7 +1275,7 @@ static void test_map_in_map(void) goto out_map_in_map; } - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err) { printf("Failed to get map info by fd %d: %d", fd, errno); diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 7cb1bc05e5cf..40cba8d368d9 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -1039,7 +1039,7 @@ try: offload = bpf_pinned("/sys/fs/bpf/offload") ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True) fail(ret == 0, "attached offloaded XDP program to drv") - check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args) + check_extack(err, "Using offloaded program without HW_MODE flag is not supported.", args) rm("/sys/fs/bpf/offload") sim.wait_for_flush() @@ -1088,12 +1088,12 @@ try: ret, _, err = sim.set_xdp(pinned, "offload", fail=False, include_stderr=True) fail(ret == 0, "Pinned program loaded for a different device accepted") - check_extack_nsim(err, "program bound to different dev.", args) + check_extack(err, "Program bound to different device.", args) simdev2.remove() ret, _, err = sim.set_xdp(pinned, "offload", fail=False, include_stderr=True) fail(ret == 0, "Pinned program loaded for a removed device accepted") - check_extack_nsim(err, "xdpoffload of non-bound program.", args) + check_extack(err, "Program bound to different device.", args) rm(pin_file) bpftool_prog_list_wait(expected=0) @@ -1334,12 +1334,12 @@ try: ret, _, err = simA.set_xdp(progB, "offload", force=True, JSON=False, fail=False, include_stderr=True) fail(ret == 0, "cross-ASIC program allowed") - check_extack_nsim(err, "program bound to different dev.", args) + check_extack(err, "Program bound to different device.", args) for d in simdevB.nsims: ret, _, err = d.set_xdp(progA, "offload", force=True, JSON=False, fail=False, include_stderr=True) fail(ret == 0, "cross-ASIC program allowed") - check_extack_nsim(err, "program bound to different dev.", args) + check_extack(err, "Program bound to different device.", args) start_test("Test multi-dev ASIC cross-dev map reuse...") diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 4716e38e153a..6d5e3022c75f 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -17,6 +17,7 @@ #include <sys/select.h> #include <sys/socket.h> #include <sys/un.h> +#include <bpf/btf.h> static bool verbose(void) { @@ -967,6 +968,43 @@ int write_sysctl(const char *sysctl, const char *value) return 0; } +int get_bpf_max_tramp_links_from(struct btf *btf) +{ + const struct btf_enum *e; + const struct btf_type *t; + __u32 i, type_cnt; + const char *name; + __u16 j, vlen; + + for (i = 1, type_cnt = btf__type_cnt(btf); i < type_cnt; i++) { + t = btf__type_by_id(btf, i); + if (!t || !btf_is_enum(t) || t->name_off) + continue; + e = btf_enum(t); + for (j = 0, vlen = btf_vlen(t); j < vlen; j++, e++) { + name = btf__str_by_offset(btf, e->name_off); + if (name && !strcmp(name, "BPF_MAX_TRAMP_LINKS")) + return e->val; + } + } + + return -1; +} + +int get_bpf_max_tramp_links(void) +{ + struct btf *vmlinux_btf; + int ret; + + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux btf")) + return -1; + ret = get_bpf_max_tramp_links_from(vmlinux_btf); + btf__free(vmlinux_btf); + + return ret; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { @@ -975,12 +1013,12 @@ void crash_handler(int signum) sz = backtrace(bt, ARRAY_SIZE(bt)); + if (env.stdout) + stdio_restore(); if (env.test) { env.test_state->error_cnt++; dump_test_log(env.test, env.test_state, true, false); } - if (env.stdout) - stdio_restore(); if (env.worker_id != -1) fprintf(stderr, "[%d]: ", env.worker_id); fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 3f058dfadbaf..d5d51ec97ec8 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -394,6 +394,8 @@ int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); +int get_bpf_max_tramp_links_from(struct btf *btf); +int get_bpf_max_tramp_links(void); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c index 3256de30f563..ed518d075d1d 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c @@ -93,7 +93,7 @@ int get_map_fd_by_prog_id(int prog_id) info.nr_map_ids = 1; info.map_ids = (__u64) (unsigned long) map_ids; - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { log_err("Failed to get info by prog fd %d", prog_fd); goto err; } diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 334bdfeab940..910044f08908 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -100,6 +100,9 @@ if [[ "$#" -eq "0" ]]; then echo "ipip" $0 ipv4 ipip none 100 + echo "ipip6" + $0 ipv4 ipip6 none 100 + echo "ip6ip6" $0 ipv6 ip6tnl none 100 @@ -224,6 +227,9 @@ elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then ttype="vxlan" targs="id 1 dstport 8472 udp6zerocsumrx" +elif [[ "$tuntype" == "ipip6" ]]; then + ttype="ip6tnl" + targs="" else ttype=$tuntype targs="" @@ -233,6 +239,9 @@ fi if [[ "${tuntype}" == "sit" ]]; then link_addr1="${ns1_v4}" link_addr2="${ns2_v4}" +elif [[ "${tuntype}" == "ipip6" ]]; then + link_addr1="${ns1_v6}" + link_addr2="${ns2_v6}" else link_addr1="${addr1}" link_addr2="${addr2}" @@ -287,12 +296,6 @@ else server_listen fi -# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3. -if [[ "${tuntype}" == "sit" ]]; then - echo OK - exit 0 -fi - # serverside, use BPF for decap ip netns exec "${ns2}" ip link del dev testtun0 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 5c8ef062f760..32df93747095 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -96,7 +96,7 @@ static int get_map_fd_by_prog_id(int prog_id, bool *xdp) info.nr_map_ids = 1; info.map_ids = (__u64)(unsigned long)map_ids; - if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) { + if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { log_err("Failed to get info by prog fd %d", prog_fd); goto err; } diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 2eaedc1d9ed3..06857b689c11 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -66,15 +66,20 @@ config_device() add_gre_tunnel() { + tun_key= + if [ -n "$1" ]; then + tun_key="key $1" + fi + # at_ns0 namespace ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ + ip link add dev $DEV_NS type $TYPE seq $tun_key \ local 172.16.1.100 remote 172.16.1.200 ip netns exec at_ns0 ip link set dev $DEV_NS up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 # root namespace - ip link add dev $DEV type $TYPE key 2 external + ip link add dev $DEV type $TYPE $tun_key external ip link set dev $DEV up ip addr add dev $DEV 10.1.1.200/24 } @@ -238,7 +243,7 @@ test_gre() check $TYPE config_device - add_gre_tunnel + add_gre_tunnel 2 attach_bpf $DEV gre_set_tunnel gre_get_tunnel ping $PING_ARG 10.1.1.100 check_err $? @@ -253,6 +258,30 @@ test_gre() echo -e ${GREEN}"PASS: $TYPE"${NC} } +test_gre_no_tunnel_key() +{ + TYPE=gre + DEV_NS=gre00 + DEV=gre11 + ret=0 + + check $TYPE + config_device + add_gre_tunnel + attach_bpf $DEV gre_set_tunnel_no_key gre_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + test_ip6gre() { TYPE=ip6gre @@ -589,6 +618,7 @@ cleanup() ip link del ipip6tnl11 2> /dev/null ip link del ip6ip6tnl11 2> /dev/null ip link del gretap11 2> /dev/null + ip link del gre11 2> /dev/null ip link del ip6gre11 2> /dev/null ip link del ip6gretap11 2> /dev/null ip link del geneve11 2> /dev/null @@ -641,6 +671,10 @@ bpf_tunnel_test() test_gre errors=$(( $errors + $? )) + echo "Testing GRE tunnel (without tunnel keys)..." + test_gre_no_tunnel_key + errors=$(( $errors + $? )) + echo "Testing IP6GRE tunnel..." test_ip6gre errors=$(( $errors + $? )) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 8c808551dfd7..8b9949bb833d 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -209,7 +209,7 @@ loop: insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_push), + BPF_FUNC_skb_vlan_push); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } @@ -220,7 +220,7 @@ loop: i++; insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_pop), + BPF_FUNC_skb_vlan_pop); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } @@ -1239,8 +1239,8 @@ static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt) __u32 xlated_prog_len; __u32 buf_element_size = sizeof(struct bpf_insn); - if (bpf_obj_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("bpf_obj_get_info_by_fd failed"); + if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { + perror("bpf_prog_get_info_by_fd failed"); return -1; } @@ -1261,8 +1261,8 @@ static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt) bzero(&info, sizeof(info)); info.xlated_prog_len = xlated_prog_len; info.xlated_prog_insns = (__u64)(unsigned long)*buf; - if (bpf_obj_get_info_by_fd(fd_prog, &info, &info_len)) { - perror("second bpf_obj_get_info_by_fd failed"); + if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { + perror("second bpf_prog_get_info_by_fd failed"); goto out_free_buf; } diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh new file mode 100755 index 000000000000..0aa71c4455c0 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_features.sh @@ -0,0 +1,107 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly NS="ns1-$(mktemp -u XXXXXX)" +readonly V0_IP4=10.10.0.11 +readonly V1_IP4=10.10.0.1 +readonly V0_IP6=2001:db8::11 +readonly V1_IP6=2001:db8::1 + +ret=1 + +setup() { + { + ip netns add ${NS} + + ip link add v1 type veth peer name v0 netns ${NS} + + ip link set v1 up + ip addr add $V1_IP4/24 dev v1 + ip addr add $V1_IP6/64 nodad dev v1 + ip -n ${NS} link set dev v0 up + ip -n ${NS} addr add $V0_IP4/24 dev v0 + ip -n ${NS} addr add $V0_IP6/64 nodad dev v0 + + # Enable XDP mode and disable checksum offload + ethtool -K v1 gro on + ethtool -K v1 tx-checksumming off + ip netns exec ${NS} ethtool -K v0 gro on + ip netns exec ${NS} ethtool -K v0 tx-checksumming off + } > /dev/null 2>&1 +} + +cleanup() { + ip link del v1 2> /dev/null + ip netns del ${NS} 2> /dev/null + [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null +} + +wait_for_dut_server() { + while sleep 1; do + ss -tlp | grep -q xdp_features + [ $? -eq 0 ] && break + done +} + +test_xdp_features() { + setup + + ## XDP_PASS + ./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_DROP + ./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_ABORTED + ./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_TX + ./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_TX \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_REDIRECT + ./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_NDO_XMIT + ./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + ret=$? + cleanup +} + +set -e +trap cleanup 2 3 6 9 + +test_xdp_features + +exit $ret diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index d821fd098504..b077cf58f825 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -24,8 +24,6 @@ # ----------- | ---------- # | vethX | --------- | vethY | # ----------- peer ---------- -# | | | -# namespaceX | namespaceY # # AF_XDP is an address family optimized for high performance packet processing, # it is XDP’s user-space interface. @@ -39,10 +37,9 @@ # Prerequisites setup by script: # # Set up veth interfaces as per the topology shown ^^: -# * setup two veth interfaces and one namespace -# ** veth<xxxx> in root namespace -# ** veth<yyyy> in af_xdp<xxxx> namespace -# ** namespace af_xdp<xxxx> +# * setup two veth interfaces +# ** veth<xxxx> +# ** veth<yyyy> # *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid # conflict with any existing interface # * tests the veth and xsk layers of the topology @@ -74,6 +71,9 @@ # Run and dump packet contents: # sudo ./test_xsk.sh -D # +# Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger: +# sudo ./test_xsk.sh -d +# # Run test suite for physical device in loopback mode # sudo ./test_xsk.sh -i IFACE @@ -81,11 +81,12 @@ ETH="" -while getopts "vDi:" flag +while getopts "vDi:d" flag do case "${flag}" in v) verbose=1;; D) dump_pkts=1;; + d) debug=1;; i) ETH=${OPTARG};; esac done @@ -99,28 +100,25 @@ VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head - VETH0=ve${VETH0_POSTFIX} VETH1_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4) VETH1=ve${VETH1_POSTFIX} -NS0=root -NS1=af_xdp${VETH1_POSTFIX} MTU=1500 trap ctrl_c INT function ctrl_c() { - cleanup_exit ${VETH0} ${VETH1} ${NS1} + cleanup_exit ${VETH0} ${VETH1} exit 1 } setup_vethPairs() { if [[ $verbose -eq 1 ]]; then - echo "setting up ${VETH0}: namespace: ${NS0}" + echo "setting up ${VETH0}" fi - ip netns add ${NS1} ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4 if [ -f /proc/net/if_inet6 ]; then echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6 fi if [[ $verbose -eq 1 ]]; then - echo "setting up ${VETH1}: namespace: ${NS1}" + echo "setting up ${VETH1}" fi if [[ $busy_poll -eq 1 ]]; then @@ -130,18 +128,15 @@ setup_vethPairs() { echo 200000 > /sys/class/net/${VETH1}/gro_flush_timeout fi - ip link set ${VETH1} netns ${NS1} - ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU} + ip link set ${VETH1} mtu ${MTU} ip link set ${VETH0} mtu ${MTU} - ip netns exec ${NS1} ip link set ${VETH1} up - ip netns exec ${NS1} ip link set dev lo up + ip link set ${VETH1} up ip link set ${VETH0} up } if [ ! -z $ETH ]; then VETH0=${ETH} VETH1=${ETH} - NS1="" else validate_root_exec validate_veth_support ${VETH0} @@ -151,7 +146,7 @@ else retval=$? if [ $retval -ne 0 ]; then test_status $retval "${TEST_NAME}" - cleanup_exit ${VETH0} ${VETH1} ${NS1} + cleanup_exit ${VETH0} ${VETH1} exit $retval fi fi @@ -174,10 +169,15 @@ statusList=() TEST_NAME="XSK_SELFTESTS_${VETH0}_SOFTIRQ" +if [[ $debug -eq 1 ]]; then + echo "-i" ${VETH0} "-i" ${VETH1} + exit +fi + exec_xskxceiver if [ -z $ETH ]; then - cleanup_exit ${VETH0} ${VETH1} ${NS1} + cleanup_exit ${VETH0} ${VETH1} fi TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL" busy_poll=1 @@ -190,7 +190,7 @@ exec_xskxceiver ## END TESTS if [ -z $ETH ]; then - cleanup_exit ${VETH0} ${VETH1} ${NS1} + cleanup_exit ${VETH0} ${VETH1} fi failures=0 diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 9695318e8132..6c44153755e6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -164,7 +164,7 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) int err; memset(info, 0, sizeof(*info)); - err = bpf_obj_get_info_by_fd(bpf_link__fd(link), info, &info_len); + err = bpf_link_get_info_by_fd(bpf_link__fd(link), info, &info_len); if (err) { printf("failed to get link info: %d\n", -errno); return 0; diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c index c2aa6f26738b..bf82b923c5fe 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c +++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c @@ -1,13 +1,14 @@ { "bounds checks mixing signed and unsigned, positive bounds", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), @@ -17,20 +18,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -40,20 +42,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 2", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -65,20 +68,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 3", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), @@ -89,20 +93,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 4", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1), BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), @@ -112,19 +117,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 5", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -135,17 +141,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 6", .insns = { + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_6, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), @@ -163,13 +172,14 @@ { "bounds checks mixing signed and unsigned, variant 7", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -179,19 +189,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 8", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -203,20 +214,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 9", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -228,19 +240,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 10", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -252,20 +265,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 11", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -278,20 +292,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 12", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -303,20 +318,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 13", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -331,7 +347,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, @@ -340,13 +356,14 @@ .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, offsetof(struct __sk_buff, mark)), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_MOV64_IMM(BPF_REG_8, 2), @@ -360,20 +377,21 @@ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, - .fixup_map_hash_8b = { 4 }, + .fixup_map_hash_8b = { 6 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 15", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -387,7 +405,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c new file mode 100644 index 000000000000..3af2501082b2 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c @@ -0,0 +1,67 @@ +{ + "BPF_ST_MEM stack imm non-zero", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 42), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, -42), + /* if value is tracked correctly R0 is zero */ + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + /* Use prog type that requires return value in range [0, 1] */ + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, + .runs = -1, +}, +{ + "BPF_ST_MEM stack imm zero", + .insns = { + /* mark stack 0000 0000 */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* read and sum a few bytes */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -8), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* if value is tracked correctly R0 is zero */ + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + /* Use prog type that requires return value in range [0, 1] */ + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, + .runs = -1, +}, +{ + "BPF_ST_MEM stack imm zero, variable offset", + .insns = { + /* set fp[-16], fp[-24] to zeros */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -24, 0), + /* r0 = random value in range [-32, -15] */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JLE, BPF_REG_0, 16, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 32), + /* fp[r0] = 0, make a variable offset write of zero, + * this should preserve zero marks on stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_10), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + /* r0 = fp[-20], if variable offset write was tracked correctly + * r0 would be a known zero. + */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_10, -20), + /* Would fail return code verification if r0 range is not tracked correctly. */ + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + /* Use prog type that requires return value in range [0, 1] */ + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, + .runs = -1, +}, diff --git a/tools/testing/selftests/bpf/verifier/sleepable.c b/tools/testing/selftests/bpf/verifier/sleepable.c new file mode 100644 index 000000000000..1f0d2bdc673f --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/sleepable.c @@ -0,0 +1,91 @@ +{ + "sleepable fentry accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .kfunc = "bpf_fentry_test1", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable fexit accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .kfunc = "bpf_fentry_test1", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable fmod_ret accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_MODIFY_RETURN, + .kfunc = "bpf_fentry_test1", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable iter accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_ITER, + .kfunc = "task", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable lsm accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_LSM, + .kfunc = "bpf", + .expected_attach_type = BPF_LSM_MAC, + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable uprobe accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_KPROBE, + .kfunc = "bpf_fentry_test1", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable raw tracepoint reject", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .kfunc = "sched_switch", + .result = REJECT, + .errstr = "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable", + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index f961b49b8ef4..83231456d3c5 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -144,7 +144,7 @@ static struct env { struct verif_stats *prog_stats; int prog_stat_cnt; - /* baseline_stats is allocated and used only in comparsion mode */ + /* baseline_stats is allocated and used only in comparison mode */ struct verif_stats *baseline_stats; int baseline_stat_cnt; @@ -882,7 +882,7 @@ static int process_obj(const char *filename) * that BPF object file is incomplete and has to be statically * linked into a final BPF object file; instead of bailing * out, report it into stderr, mark it as skipped, and - * proceeed + * proceed */ fprintf(stderr, "Failed to open '%s': %d\n", filename, -errno); env.files_skipped++; diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 316a56d680f2..685034528018 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -13,7 +13,7 @@ s390x) QEMU_BINARY=qemu-system-s390x QEMU_CONSOLE="ttyS1" QEMU_FLAGS=(-smp 2) - BZIMAGE="arch/s390/boot/compressed/vmlinux" + BZIMAGE="arch/s390/boot/vmlinux" ;; x86_64) QEMU_BINARY=qemu-system-x86_64 diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c new file mode 100644 index 000000000000..fce12165213b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.c @@ -0,0 +1,699 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/bpf.h> +#include <uapi/linux/netdev.h> +#include <linux/if_link.h> +#include <signal.h> +#include <argp.h> +#include <net/if.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <pthread.h> + +#include <network_helpers.h> + +#include "xdp_features.skel.h" +#include "xdp_features.h" + +#define RED(str) "\033[0;31m" str "\033[0m" +#define GREEN(str) "\033[0;32m" str "\033[0m" +#define YELLOW(str) "\033[0;33m" str "\033[0m" + +static struct env { + bool verbosity; + int ifindex; + bool is_tester; + struct { + enum netdev_xdp_act drv_feature; + enum xdp_action action; + } feature; + struct sockaddr_storage dut_ctrl_addr; + struct sockaddr_storage dut_addr; + struct sockaddr_storage tester_addr; +} env; + +#define BUFSIZE 128 + +void test__fail(void) { /* for network_helpers.c */ } + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbosity) + return 0; + return vfprintf(stderr, format, args); +} + +static volatile bool exiting; + +static void sig_handler(int sig) +{ + exiting = true; +} + +const char *argp_program_version = "xdp-features 0.0"; +const char argp_program_doc[] = +"XDP features detection application.\n" +"\n" +"XDP features application checks the XDP advertised features match detected ones.\n" +"\n" +"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n" +"\n" +"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n" +"\n" +"XDP features\n:" +"- XDP_PASS\n" +"- XDP_DROP\n" +"- XDP_ABORTED\n" +"- XDP_REDIRECT\n" +"- XDP_NDO_XMIT\n" +"- XDP_TX\n"; + +static const struct argp_option opts[] = { + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + { "tester", 't', NULL, 0, "Tester mode" }, + { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" }, + { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" }, + { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" }, + { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" }, + {}, +}; + +static int get_xdp_feature(const char *arg) +{ + if (!strcmp(arg, "XDP_PASS")) { + env.feature.action = XDP_PASS; + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + } else if (!strcmp(arg, "XDP_DROP")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_DROP; + } else if (!strcmp(arg, "XDP_ABORTED")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_ABORTED; + } else if (!strcmp(arg, "XDP_TX")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_TX; + } else if (!strcmp(arg, "XDP_REDIRECT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT; + env.feature.action = XDP_REDIRECT; + } else if (!strcmp(arg, "XDP_NDO_XMIT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + } else { + return -EINVAL; + } + + return 0; +} + +static char *get_xdp_feature_str(void) +{ + switch (env.feature.action) { + case XDP_PASS: + return YELLOW("XDP_PASS"); + case XDP_DROP: + return YELLOW("XDP_DROP"); + case XDP_ABORTED: + return YELLOW("XDP_ABORTED"); + case XDP_TX: + return YELLOW("XDP_TX"); + case XDP_REDIRECT: + return YELLOW("XDP_REDIRECT"); + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return YELLOW("XDP_NDO_XMIT"); + + return ""; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case 'v': + env.verbosity = true; + break; + case 't': + env.is_tester = true; + break; + case 'f': + if (get_xdp_feature(arg) < 0) { + fprintf(stderr, "Invalid xdp feature: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + case 'D': + if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT, + &env.dut_addr, NULL)) { + fprintf(stderr, "Invalid DUT address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'C': + if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL)) { + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'T': + if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) { + fprintf(stderr, "Invalid Tester address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case ARGP_KEY_ARG: + errno = 0; + if (strlen(arg) >= IF_NAMESIZE) { + fprintf(stderr, "Invalid device name: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + + env.ifindex = if_nametoindex(arg); + if (!env.ifindex) + env.ifindex = strtoul(arg, NULL, 0); + if (!env.ifindex) { + fprintf(stderr, + "Bad interface index or name (%d): %s\n", + errno, strerror(errno)); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, +}; + +static void set_env_default(void) +{ + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + env.feature.action = -EINVAL; + env.ifindex = -ENODEV; + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, + &env.dut_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL); +} + +static void *dut_echo_thread(void *arg) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + int sockfd = *(int *)arg; + + while (!exiting) { + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + struct sockaddr_storage addr; + socklen_t addrlen; + size_t n; + + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL, + (struct sockaddr *)&addr, &addrlen); + if (n != ntohs(tlv->len)) + continue; + + if (ntohs(tlv->type) != CMD_ECHO) + continue; + + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&addr, addrlen); + } + + pthread_exit((void *)0); + close(sockfd); + + return NULL; +} + +static int dut_run_echo_thread(pthread_t *t, int *sockfd) +{ + int err; + + sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL, + DUT_ECHO_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + /* start echo channel */ + err = pthread_create(t, NULL, dut_echo_thread, sockfd); + if (err) { + fprintf(stderr, "Failed creating dut_echo thread: %s\n", + strerror(-err)); + free_fds(sockfd, 1); + return -EINVAL; + } + + return 0; +} + +static int dut_attach_xdp_prog(struct xdp_features *skel, int flags) +{ + enum xdp_action action = env.feature.action; + struct bpf_program *prog; + unsigned int key = 0; + int err, fd = 0; + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) { + struct bpf_devmap_val entry = { + .ifindex = env.ifindex, + }; + + err = bpf_map__update_elem(skel->maps.dev_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap); + action = XDP_REDIRECT; + } + + switch (action) { + case XDP_TX: + prog = skel->progs.xdp_do_tx; + break; + case XDP_DROP: + prog = skel->progs.xdp_do_drop; + break; + case XDP_ABORTED: + prog = skel->progs.xdp_do_aborted; + break; + case XDP_PASS: + prog = skel->progs.xdp_do_pass; + break; + case XDP_REDIRECT: { + struct bpf_cpumap_val entry = { + .qsize = 2048, + .bpf_prog.fd = fd, + }; + + err = bpf_map__update_elem(skel->maps.cpu_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + prog = skel->progs.xdp_do_redirect; + break; + } + default: + return -EINVAL; + } + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) + fprintf(stderr, + "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + return err; +} + +static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val, + size_t val_size) +{ + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + size_t len; + + len = recv(sockfd, buf, bufsize, 0); + if (len != ntohs(tlv->len) || len < sizeof(*tlv)) + return -EINVAL; + + if (val) { + len -= sizeof(*tlv); + if (len > val_size) + return -ENOMEM; + + memcpy(val, tlv->data, len); + } + + return 0; +} + +static int dut_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + int state, err, *sockfd, ctrl_sockfd, echo_sockfd; + struct sockaddr_storage ctrl_addr; + pthread_t dut_thread; + socklen_t addrlen; + + sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL, + DUT_CTRL_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create DUT socket\n"); + return -errno; + } + + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen); + if (ctrl_sockfd < 0) { + fprintf(stderr, "Failed to accept connection on DUT socket\n"); + free_fds(sockfd, 1); + return -errno; + } + + /* CTRL loop */ + while (!exiting) { + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + + err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0); + if (err) + continue; + + switch (ntohs(tlv->type)) { + case CMD_START: { + if (state == CMD_START) + continue; + + state = CMD_START; + /* Load the XDP program on the DUT */ + err = dut_attach_xdp_prog(skel, flags); + if (err) + goto out; + + err = dut_run_echo_thread(&dut_thread, &echo_sockfd); + if (err < 0) + goto out; + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_STOP: + if (state != CMD_START) + break; + + state = CMD_STOP; + + exiting = true; + bpf_xdp_detach(env.ifindex, flags, NULL); + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + goto end_thread; + case CMD_GET_XDP_CAP: { + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + unsigned long long val; + size_t n; + + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE, + &opts); + if (err) { + fprintf(stderr, + "Failed to query XDP cap for ifindex %d\n", + env.ifindex); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(opts.feature_flags); + tlv->len = htons(n); + + val = htobe64(opts.feature_flags); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_GET_STATS: { + unsigned int key = 0, val; + size_t n; + + err = bpf_map__lookup_elem(skel->maps.dut_stats, + &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(val); + tlv->len = htons(n); + + val = htonl(val); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + default: + break; + } + } + +end_thread: + pthread_join(dut_thread, NULL); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(ctrl_sockfd); + free_fds(sockfd, 1); + + return err; +} + +static bool tester_collect_detected_cap(struct xdp_features *skel, + unsigned int dut_stats) +{ + unsigned int err, key = 0, val; + + if (!dut_stats) + return false; + + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + return false; + } + + switch (env.feature.action) { + case XDP_PASS: + case XDP_TX: + case XDP_REDIRECT: + return val > 0; + case XDP_DROP: + case XDP_ABORTED: + return val == 0; + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return val > 0; + + return false; +} + +static int send_and_recv_msg(int sockfd, enum test_commands cmd, void *val, + size_t val_size) +{ + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int err; + + tlv->type = htons(cmd); + tlv->len = htons(sizeof(*tlv)); + + err = send(sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + return err; + + err = recv_msg(sockfd, buf, BUFSIZE, val, val_size); + if (err < 0) + return err; + + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL; +} + +static int send_echo_msg(void) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int sockfd, n; + + sockfd = socket(AF_INET6, SOCK_DGRAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + tlv->type = htons(CMD_ECHO); + tlv->len = htons(sizeof(*tlv)); + + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr)); + close(sockfd); + + return n == ntohs(tlv->len) ? 0 : -EINVAL; +} + +static int tester_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + unsigned long long advertised_feature; + struct bpf_program *prog; + unsigned int stats; + int i, err, sockfd; + bool detected_cap; + + sockfd = socket(AF_INET6, SOCK_STREAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create tester socket\n"); + return -errno; + } + + if (settimeo(sockfd, 1000) < 0) + return -EINVAL; + + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr, + sizeof(env.dut_ctrl_addr)); + if (err) { + fprintf(stderr, "Failed to connect to the DUT\n"); + return -errno; + } + + err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature, + sizeof(advertised_feature)); + if (err < 0) { + close(sockfd); + return err; + } + + advertised_feature = be64toh(advertised_feature); + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT || + env.feature.action == XDP_TX) + prog = skel->progs.xdp_tester_check_tx; + else + prog = skel->progs.xdp_tester_check_rx; + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) { + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + goto out; + } + + err = send_and_recv_msg(sockfd, CMD_START, NULL, 0); + if (err) + goto out; + + for (i = 0; i < 10 && !exiting; i++) { + err = send_echo_msg(); + if (err < 0) + goto out; + + sleep(1); + } + + err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats)); + if (err) + goto out; + + /* stop the test */ + err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0); + /* send a new echo message to wake echo thread of the dut */ + send_echo_msg(); + + detected_cap = tester_collect_detected_cap(skel, ntohl(stats)); + + fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(), + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"), + env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED") + : RED("NOT ADVERTISED")); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(sockfd); + return err < 0 ? err : 0; +} + +int main(int argc, char **argv) +{ + struct xdp_features *skel; + int err; + + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + libbpf_set_print(libbpf_print_fn); + + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + + set_env_default(); + + /* Parse command line arguments */ + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + if (env.ifindex < 0) { + fprintf(stderr, "Invalid ifindex\n"); + return -ENODEV; + } + + /* Load and verify BPF application */ + skel = xdp_features__open(); + if (!skel) { + fprintf(stderr, "Failed to open and load BPF skeleton\n"); + return -EINVAL; + } + + skel->rodata->tester_addr = + ((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr; + skel->rodata->dut_addr = + ((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr; + + /* Load & verify BPF programs */ + err = xdp_features__load(skel); + if (err) { + fprintf(stderr, "Failed to load and verify BPF skeleton\n"); + goto cleanup; + } + + err = xdp_features__attach(skel); + if (err) { + fprintf(stderr, "Failed to attach BPF skeleton\n"); + goto cleanup; + } + + if (env.is_tester) { + /* Tester */ + fprintf(stdout, "Starting tester on device %d\n", env.ifindex); + err = tester_run(skel); + } else { + /* DUT */ + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex); + err = dut_run(skel); + } + +cleanup: + xdp_features__destroy(skel); + + return err < 0 ? -err : 0; +} diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h new file mode 100644 index 000000000000..2670c541713b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* test commands */ +enum test_commands { + CMD_STOP, /* CMD */ + CMD_START, /* CMD */ + CMD_ECHO, /* CMD */ + CMD_ACK, /* CMD + data */ + CMD_GET_XDP_CAP, /* CMD */ + CMD_GET_STATS, /* CMD */ +}; + +#define DUT_CTRL_PORT 12345 +#define DUT_ECHO_PORT 12346 + +struct tlv_hdr { + __be16 type; + __be16 len; + __u8 data[]; +}; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c new file mode 100644 index 000000000000..1c8acb68b977 --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -0,0 +1,445 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Reference program for verifying XDP metadata on real HW. Functional test + * only, doesn't test the performance. + * + * RX: + * - UDP 9091 packets are diverted into AF_XDP + * - Metadata verified: + * - rx_timestamp + * - rx_hash + * + * TX: + * - TBD + */ + +#include <test_progs.h> +#include <network_helpers.h> +#include "xdp_hw_metadata.skel.h" +#include "xsk.h" + +#include <error.h> +#include <linux/errqueue.h> +#include <linux/if_link.h> +#include <linux/net_tstamp.h> +#include <linux/udp.h> +#include <linux/sockios.h> +#include <sys/mman.h> +#include <net/if.h> +#include <poll.h> + +#include "xdp_metadata.h" + +#define UMEM_NUM 16 +#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE +#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM) +#define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE) + +struct xsk { + void *umem_area; + struct xsk_umem *umem; + struct xsk_ring_prod fill; + struct xsk_ring_cons comp; + struct xsk_ring_prod tx; + struct xsk_ring_cons rx; + struct xsk_socket *socket; +}; + +struct xdp_hw_metadata *bpf_obj; +struct xsk *rx_xsk; +const char *ifname; +int ifindex; +int rxq; + +void test__fail(void) { /* for network_helpers.c */ } + +static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) +{ + int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + const struct xsk_socket_config socket_config = { + .rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .bind_flags = XDP_COPY, + }; + const struct xsk_umem_config umem_config = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG, + }; + __u32 idx; + u64 addr; + int ret; + int i; + + xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (xsk->umem_area == MAP_FAILED) + return -ENOMEM; + + ret = xsk_umem__create(&xsk->umem, + xsk->umem_area, UMEM_SIZE, + &xsk->fill, + &xsk->comp, + &umem_config); + if (ret) + return ret; + + ret = xsk_socket__create(&xsk->socket, ifindex, queue_id, + xsk->umem, + &xsk->rx, + &xsk->tx, + &socket_config); + if (ret) + return ret; + + /* First half of umem is for TX. This way address matches 1-to-1 + * to the completion queue index. + */ + + for (i = 0; i < UMEM_NUM / 2; i++) { + addr = i * UMEM_FRAME_SIZE; + printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr); + } + + /* Second half of umem is for RX. */ + + ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx); + for (i = 0; i < UMEM_NUM / 2; i++) { + addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE; + printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr); + *xsk_ring_prod__fill_addr(&xsk->fill, i) = addr; + } + xsk_ring_prod__submit(&xsk->fill, ret); + + return 0; +} + +static void close_xsk(struct xsk *xsk) +{ + if (xsk->umem) + xsk_umem__delete(xsk->umem); + if (xsk->socket) + xsk_socket__delete(xsk->socket); + munmap(xsk->umem_area, UMEM_SIZE); +} + +static void refill_rx(struct xsk *xsk, __u64 addr) +{ + __u32 idx; + + if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) { + printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr); + *xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr; + xsk_ring_prod__submit(&xsk->fill, 1); + } +} + +static void verify_xdp_metadata(void *data) +{ + struct xdp_meta *meta; + + meta = data - sizeof(*meta); + + printf("rx_timestamp: %llu\n", meta->rx_timestamp); + printf("rx_hash: %u\n", meta->rx_hash); +} + +static void verify_skb_metadata(int fd) +{ + char cmsg_buf[1024]; + char packet_buf[128]; + + struct scm_timestamping *ts; + struct iovec packet_iov; + struct cmsghdr *cmsg; + struct msghdr hdr; + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_iov = &packet_iov; + hdr.msg_iovlen = 1; + packet_iov.iov_base = packet_buf; + packet_iov.iov_len = sizeof(packet_buf); + + hdr.msg_control = cmsg_buf; + hdr.msg_controllen = sizeof(cmsg_buf); + + if (recvmsg(fd, &hdr, 0) < 0) + error(1, errno, "recvmsg"); + + for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL; + cmsg = CMSG_NXTHDR(&hdr, cmsg)) { + + if (cmsg->cmsg_level != SOL_SOCKET) + continue; + + switch (cmsg->cmsg_type) { + case SCM_TIMESTAMPING: + ts = (struct scm_timestamping *)CMSG_DATA(cmsg); + if (ts->ts[2].tv_sec || ts->ts[2].tv_nsec) { + printf("found skb hwtstamp = %lu.%lu\n", + ts->ts[2].tv_sec, ts->ts[2].tv_nsec); + return; + } + break; + default: + break; + } + } + + printf("skb hwtstamp is not found!\n"); +} + +static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) +{ + const struct xdp_desc *rx_desc; + struct pollfd fds[rxq + 1]; + __u64 comp_addr; + __u64 addr; + __u32 idx; + int ret; + int i; + + for (i = 0; i < rxq; i++) { + fds[i].fd = xsk_socket__fd(rx_xsk[i].socket); + fds[i].events = POLLIN; + fds[i].revents = 0; + } + + fds[rxq].fd = server_fd; + fds[rxq].events = POLLIN; + fds[rxq].revents = 0; + + while (true) { + errno = 0; + ret = poll(fds, rxq + 1, 1000); + printf("poll: %d (%d)\n", ret, errno); + if (ret < 0) + break; + if (ret == 0) + continue; + + if (fds[rxq].revents) + verify_skb_metadata(server_fd); + + for (i = 0; i < rxq; i++) { + if (fds[i].revents == 0) + continue; + + struct xsk *xsk = &rx_xsk[i]; + + ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx); + printf("xsk_ring_cons__peek: %d\n", ret); + if (ret != 1) + continue; + + rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx); + comp_addr = xsk_umem__extract_addr(rx_desc->addr); + addr = xsk_umem__add_offset_to_addr(rx_desc->addr); + printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", + xsk, idx, rx_desc->addr, addr, comp_addr); + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr)); + xsk_ring_cons__release(&xsk->rx, 1); + refill_rx(xsk, comp_addr); + } + } + + return 0; +} + +struct ethtool_channels { + __u32 cmd; + __u32 max_rx; + __u32 max_tx; + __u32 max_other; + __u32 max_combined; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */ + +static int rxq_num(const char *ifname) +{ + struct ethtool_channels ch = { + .cmd = ETHTOOL_GCHANNELS, + }; + + struct ifreq ifr = { + .ifr_data = (void *)&ch, + }; + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + int fd, ret; + + fd = socket(AF_UNIX, SOCK_DGRAM, 0); + if (fd < 0) + error(1, errno, "socket"); + + ret = ioctl(fd, SIOCETHTOOL, &ifr); + if (ret < 0) + error(1, errno, "ioctl(SIOCETHTOOL)"); + + close(fd); + + return ch.rx_count + ch.combined_count; +} + +static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *cfg) +{ + struct ifreq ifr = { + .ifr_data = (void *)cfg, + }; + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + int fd, ret; + + fd = socket(AF_UNIX, SOCK_DGRAM, 0); + if (fd < 0) + error(1, errno, "socket"); + + ret = ioctl(fd, op, &ifr); + if (ret < 0) + error(1, errno, "ioctl(%d)", op); + + close(fd); +} + +static struct hwtstamp_config saved_hwtstamp_cfg; +static const char *saved_hwtstamp_ifname; + +static void hwtstamp_restore(void) +{ + hwtstamp_ioctl(SIOCSHWTSTAMP, saved_hwtstamp_ifname, &saved_hwtstamp_cfg); +} + +static void hwtstamp_enable(const char *ifname) +{ + struct hwtstamp_config cfg = { + .rx_filter = HWTSTAMP_FILTER_ALL, + }; + + hwtstamp_ioctl(SIOCGHWTSTAMP, ifname, &saved_hwtstamp_cfg); + saved_hwtstamp_ifname = strdup(ifname); + atexit(hwtstamp_restore); + + hwtstamp_ioctl(SIOCSHWTSTAMP, ifname, &cfg); +} + +static void cleanup(void) +{ + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); + int ret; + int i; + + if (bpf_obj) { + opts.old_prog_fd = bpf_program__fd(bpf_obj->progs.rx); + if (opts.old_prog_fd >= 0) { + printf("detaching bpf program....\n"); + ret = bpf_xdp_detach(ifindex, XDP_FLAGS, &opts); + if (ret) + printf("failed to detach XDP program: %d\n", ret); + } + } + + for (i = 0; i < rxq; i++) + close_xsk(&rx_xsk[i]); + + if (bpf_obj) + xdp_hw_metadata__destroy(bpf_obj); +} + +static void handle_signal(int sig) +{ + /* interrupting poll() is all we need */ +} + +static void timestamping_enable(int fd, int val) +{ + int ret; + + ret = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); + if (ret < 0) + error(1, errno, "setsockopt(SO_TIMESTAMPING)"); +} + +int main(int argc, char *argv[]) +{ + int server_fd = -1; + int ret; + int i; + + struct bpf_program *prog; + + if (argc != 2) { + fprintf(stderr, "pass device name\n"); + return -1; + } + + ifname = argv[1]; + ifindex = if_nametoindex(ifname); + rxq = rxq_num(ifname); + + printf("rxq: %d\n", rxq); + + hwtstamp_enable(ifname); + + rx_xsk = malloc(sizeof(struct xsk) * rxq); + if (!rx_xsk) + error(1, ENOMEM, "malloc"); + + for (i = 0; i < rxq; i++) { + printf("open_xsk(%s, %p, %d)\n", ifname, &rx_xsk[i], i); + ret = open_xsk(ifindex, &rx_xsk[i], i); + if (ret) + error(1, -ret, "open_xsk"); + + printf("xsk_socket__fd() -> %d\n", xsk_socket__fd(rx_xsk[i].socket)); + } + + printf("open bpf program...\n"); + bpf_obj = xdp_hw_metadata__open(); + if (libbpf_get_error(bpf_obj)) + error(1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open"); + + prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx"); + bpf_program__set_ifindex(prog, ifindex); + bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY); + + printf("load bpf program...\n"); + ret = xdp_hw_metadata__load(bpf_obj); + if (ret) + error(1, -ret, "xdp_hw_metadata__load"); + + printf("prepare skb endpoint...\n"); + server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 9092, 1000); + if (server_fd < 0) + error(1, errno, "start_server"); + timestamping_enable(server_fd, + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_RAW_HARDWARE); + + printf("prepare xsk map...\n"); + for (i = 0; i < rxq; i++) { + int sock_fd = xsk_socket__fd(rx_xsk[i].socket); + __u32 queue_id = i; + + printf("map[%d] = %d\n", queue_id, sock_fd); + ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0); + if (ret) + error(1, -ret, "bpf_map_update_elem"); + } + + printf("attach bpf program...\n"); + ret = bpf_xdp_attach(ifindex, + bpf_program__fd(bpf_obj->progs.rx), + XDP_FLAGS, NULL); + if (ret) + error(1, -ret, "bpf_xdp_attach"); + + signal(SIGINT, handle_signal); + ret = verify_metadata(rx_xsk, rxq, server_fd); + close(server_fd); + cleanup(); + if (ret) + error(1, -ret, "verify_metadata"); +} diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h new file mode 100644 index 000000000000..f6780fbb0a21 --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#pragma once + +#ifndef ETH_P_IP +#define ETH_P_IP 0x0800 +#endif + +#ifndef ETH_P_IPV6 +#define ETH_P_IPV6 0x86DD +#endif + +struct xdp_meta { + __u64 rx_timestamp; + __u32 rx_hash; +}; diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c index 410a1385a01d..ce68c342b56f 100644 --- a/tools/testing/selftests/bpf/xdp_synproxy.c +++ b/tools/testing/selftests/bpf/xdp_synproxy.c @@ -116,6 +116,7 @@ static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 * *tcpipopts = 0; *ports = NULL; *single = false; + *tc = false; while (true) { int opt; @@ -216,9 +217,10 @@ static int syncookie_attach(const char *argv0, unsigned int ifindex, bool tc) prog_fd = bpf_program__fd(prog); - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len); if (err < 0) { - fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err)); + fprintf(stderr, "Error: bpf_prog_get_info_by_fd: %s\n", + strerror(-err)); goto out; } attached_tc = tc; @@ -291,9 +293,10 @@ static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports }; info_len = sizeof(prog_info); - err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len); if (err != 0) { - fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err)); + fprintf(stderr, "Error: bpf_prog_get_info_by_fd: %s\n", + strerror(-err)); goto out; } @@ -316,9 +319,10 @@ static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports map_fd = err; info_len = sizeof(map_info); - err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len); if (err != 0) { - fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err)); + fprintf(stderr, "Error: bpf_map_get_info_by_fd: %s\n", + strerror(-err)); close(map_fd); goto err_close_map_fds; } diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c index 39d349509ba4..687d83e707f8 100644 --- a/tools/testing/selftests/bpf/xsk.c +++ b/tools/testing/selftests/bpf/xsk.c @@ -49,10 +49,7 @@ #define pr_warn(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__) -enum xsk_prog { - XSK_PROG_FALLBACK, - XSK_PROG_REDIRECT_FLAGS, -}; +#define XSKMAP_SIZE 1 struct xsk_umem { struct xsk_ring_prod *fill_save; @@ -74,43 +71,16 @@ struct xsk_ctx { int refcount; int ifindex; struct list_head list; - int prog_fd; - int link_fd; - int xsks_map_fd; - char ifname[IFNAMSIZ]; - bool has_bpf_link; }; struct xsk_socket { struct xsk_ring_cons *rx; struct xsk_ring_prod *tx; - __u64 outstanding_tx; struct xsk_ctx *ctx; struct xsk_socket_config config; int fd; }; -struct xsk_nl_info { - bool xdp_prog_attached; - int ifindex; - int fd; -}; - -/* Up until and including Linux 5.3 */ -struct xdp_ring_offset_v1 { - __u64 producer; - __u64 consumer; - __u64 desc; -}; - -/* Up until and including Linux 5.3 */ -struct xdp_mmap_offsets_v1 { - struct xdp_ring_offset_v1 rx; - struct xdp_ring_offset_v1 tx; - struct xdp_ring_offset_v1 fr; - struct xdp_ring_offset_v1 cr; -}; - int xsk_umem__fd(const struct xsk_umem *umem) { return umem ? umem->fd : -EINVAL; @@ -153,55 +123,17 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, if (!usr_cfg) { cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg->libbpf_flags = 0; - cfg->xdp_flags = 0; cfg->bind_flags = 0; return 0; } - if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) - return -EINVAL; - cfg->rx_size = usr_cfg->rx_size; cfg->tx_size = usr_cfg->tx_size; - cfg->libbpf_flags = usr_cfg->libbpf_flags; - cfg->xdp_flags = usr_cfg->xdp_flags; cfg->bind_flags = usr_cfg->bind_flags; return 0; } -static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off) -{ - struct xdp_mmap_offsets_v1 off_v1; - - /* getsockopt on a kernel <= 5.3 has no flags fields. - * Copy over the offsets to the correct places in the >=5.4 format - * and put the flags where they would have been on that kernel. - */ - memcpy(&off_v1, off, sizeof(off_v1)); - - off->rx.producer = off_v1.rx.producer; - off->rx.consumer = off_v1.rx.consumer; - off->rx.desc = off_v1.rx.desc; - off->rx.flags = off_v1.rx.consumer + sizeof(__u32); - - off->tx.producer = off_v1.tx.producer; - off->tx.consumer = off_v1.tx.consumer; - off->tx.desc = off_v1.tx.desc; - off->tx.flags = off_v1.tx.consumer + sizeof(__u32); - - off->fr.producer = off_v1.fr.producer; - off->fr.consumer = off_v1.fr.consumer; - off->fr.desc = off_v1.fr.desc; - off->fr.flags = off_v1.fr.consumer + sizeof(__u32); - - off->cr.producer = off_v1.cr.producer; - off->cr.consumer = off_v1.cr.consumer; - off->cr.desc = off_v1.cr.desc; - off->cr.flags = off_v1.cr.consumer + sizeof(__u32); -} - static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) { socklen_t optlen; @@ -215,11 +147,6 @@ static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) if (optlen == sizeof(*off)) return 0; - if (optlen == sizeof(struct xdp_mmap_offsets_v1)) { - xsk_mmap_offsets_v1(off); - return 0; - } - return -EINVAL; } @@ -340,531 +267,56 @@ out_umem_alloc: return err; } -struct xsk_umem_config_v1 { - __u32 fill_size; - __u32 comp_size; - __u32 frame_size; - __u32 frame_headroom; -}; - -static enum xsk_prog get_xsk_prog(void) -{ - enum xsk_prog detected = XSK_PROG_FALLBACK; - char data_in = 0, data_out; - struct bpf_insn insns[] = { - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_MOV64_IMM(BPF_REG_3, XDP_PASS), - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - BPF_EXIT_INSN(), - }; - LIBBPF_OPTS(bpf_test_run_opts, opts, - .data_in = &data_in, - .data_size_in = 1, - .data_out = &data_out, - ); - - int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns); - - map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (map_fd < 0) - return detected; - - insns[0].imm = map_fd; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); - if (prog_fd < 0) { - close(map_fd); - return detected; - } - - ret = bpf_prog_test_run_opts(prog_fd, &opts); - if (!ret && opts.retval == XDP_PASS) - detected = XSK_PROG_REDIRECT_FLAGS; - close(prog_fd); - close(map_fd); - return detected; -} - -static int xsk_load_xdp_prog(struct xsk_socket *xsk) -{ - static const int log_buf_size = 16 * 1024; - struct xsk_ctx *ctx = xsk->ctx; - char log_buf[log_buf_size]; - int prog_fd; - - /* This is the fallback C-program: - * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) - * { - * int ret, index = ctx->rx_queue_index; - * - * // A set entry here means that the correspnding queue_id - * // has an active AF_XDP socket bound to it. - * ret = bpf_redirect_map(&xsks_map, index, XDP_PASS); - * if (ret > 0) - * return ret; - * - * // Fallback for pre-5.3 kernels, not supporting default - * // action in the flags parameter. - * if (bpf_map_lookup_elem(&xsks_map, &index)) - * return bpf_redirect_map(&xsks_map, index, 0); - * return XDP_PASS; - * } - */ - struct bpf_insn prog[] = { - /* r2 = *(u32 *)(r1 + 16) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), - /* *(u32 *)(r10 - 4) = r2 */ - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_3, 2), - /* call bpf_redirect_map */ - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - /* if w0 != 0 goto pc+13 */ - BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13), - /* r2 = r10 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - /* r2 += -4 */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* call bpf_map_lookup_elem */ - BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), - /* r1 = r0 */ - BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - /* r0 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_0, 2), - /* if r1 == 0 goto pc+5 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), - /* r2 = *(u32 *)(r10 - 4) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = 0 */ - BPF_MOV64_IMM(BPF_REG_3, 0), - /* call bpf_redirect_map */ - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - /* The jumps are to this instruction */ - BPF_EXIT_INSN(), - }; - - /* This is the post-5.3 kernel C-program: - * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) - * { - * return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS); - * } - */ - struct bpf_insn prog_redirect_flags[] = { - /* r2 = *(u32 *)(r1 + 16) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_3, 2), - /* call bpf_redirect_map */ - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - BPF_EXIT_INSN(), - }; - size_t insns_cnt[] = {ARRAY_SIZE(prog), - ARRAY_SIZE(prog_redirect_flags), - }; - struct bpf_insn *progs[] = {prog, prog_redirect_flags}; - enum xsk_prog option = get_xsk_prog(); - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .log_buf = log_buf, - .log_size = log_buf_size, - ); - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause", - progs[option], insns_cnt[option], &opts); - if (prog_fd < 0) { - pr_warn("BPF log buffer:\n%s", log_buf); - return prog_fd; - } - - ctx->prog_fd = prog_fd; - return 0; -} - -static int xsk_create_bpf_link(struct xsk_socket *xsk) -{ - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); - struct xsk_ctx *ctx = xsk->ctx; - __u32 prog_id = 0; - int link_fd; - int err; - - err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id); - if (err) { - pr_warn("getting XDP prog id failed\n"); - return err; - } - - /* if there's a netlink-based XDP prog loaded on interface, bail out - * and ask user to do the removal by himself - */ - if (prog_id) { - pr_warn("Netlink-based XDP prog detected, please unload it in order to launch AF_XDP prog\n"); - return -EINVAL; - } - - opts.flags = xsk->config.xdp_flags & ~(XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_REPLACE); - - link_fd = bpf_link_create(ctx->prog_fd, ctx->ifindex, BPF_XDP, &opts); - if (link_fd < 0) { - pr_warn("bpf_link_create failed: %s\n", strerror(errno)); - return link_fd; - } - - ctx->link_fd = link_fd; - return 0; -} - -static int xsk_get_max_queues(struct xsk_socket *xsk) -{ - struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; - struct xsk_ctx *ctx = xsk->ctx; - struct ifreq ifr = {}; - int fd, err, ret; - - fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0); - if (fd < 0) - return -errno; - - ifr.ifr_data = (void *)&channels; - bpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ); - err = ioctl(fd, SIOCETHTOOL, &ifr); - if (err && errno != EOPNOTSUPP) { - ret = -errno; - goto out; - } - - if (err) { - /* If the device says it has no channels, then all traffic - * is sent to a single stream, so max queues = 1. - */ - ret = 1; - } else { - /* Take the max of rx, tx, combined. Drivers return - * the number of channels in different ways. - */ - ret = max(channels.max_rx, channels.max_tx); - ret = max(ret, (int)channels.max_combined); - } - -out: - close(fd); - return ret; -} - -static int xsk_create_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - int max_queues; - int fd; - - max_queues = xsk_get_max_queues(xsk); - if (max_queues < 0) - return max_queues; - - fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, NULL); - if (fd < 0) - return fd; - - ctx->xsks_map_fd = fd; - - return 0; -} - -static void xsk_delete_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - - bpf_map_delete_elem(ctx->xsks_map_fd, &ctx->queue_id); - close(ctx->xsks_map_fd); -} - -static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) -{ - __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); - __u32 map_len = sizeof(struct bpf_map_info); - struct bpf_prog_info prog_info = {}; - struct xsk_ctx *ctx = xsk->ctx; - struct bpf_map_info map_info; - int fd, err; - - err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); - if (err) - return err; - - num_maps = prog_info.nr_map_ids; - - map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids)); - if (!map_ids) - return -ENOMEM; - - memset(&prog_info, 0, prog_len); - prog_info.nr_map_ids = num_maps; - prog_info.map_ids = (__u64)(unsigned long)map_ids; - - err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); - if (err) - goto out_map_ids; - - ctx->xsks_map_fd = -1; - - for (i = 0; i < prog_info.nr_map_ids; i++) { - fd = bpf_map_get_fd_by_id(map_ids[i]); - if (fd < 0) - continue; - - memset(&map_info, 0, map_len); - err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len); - if (err) { - close(fd); - continue; - } - - if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) { - ctx->xsks_map_fd = fd; - break; - } - - close(fd); - } - - if (ctx->xsks_map_fd == -1) - err = -ENOENT; - -out_map_ids: - free(map_ids); - return err; -} - -static int xsk_set_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - - return bpf_map_update_elem(ctx->xsks_map_fd, &ctx->queue_id, - &xsk->fd, 0); -} - -static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd) +bool xsk_is_in_mode(u32 ifindex, int mode) { - struct bpf_link_info link_info; - __u32 link_len; - __u32 id = 0; - int err; - int fd; - - while (true) { - err = bpf_link_get_next_id(id, &id); - if (err) { - if (errno == ENOENT) { - err = 0; - break; - } - pr_warn("can't get next link: %s\n", strerror(errno)); - break; - } - - fd = bpf_link_get_fd_by_id(id); - if (fd < 0) { - if (errno == ENOENT) - continue; - pr_warn("can't get link by id (%u): %s\n", id, strerror(errno)); - err = -errno; - break; - } + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + int ret; - link_len = sizeof(struct bpf_link_info); - memset(&link_info, 0, link_len); - err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len); - if (err) { - pr_warn("can't get link info: %s\n", strerror(errno)); - close(fd); - break; - } - if (link_info.type == BPF_LINK_TYPE_XDP) { - if (link_info.xdp.ifindex == ifindex) { - *link_fd = fd; - if (prog_id) - *prog_id = link_info.prog_id; - break; - } - } - close(fd); + ret = bpf_xdp_query(ifindex, mode, &opts); + if (ret) { + printf("XDP mode query returned error %s\n", strerror(errno)); + return false; } - return err; -} + if (mode == XDP_FLAGS_DRV_MODE) + return opts.attach_mode == XDP_ATTACHED_DRV; + else if (mode == XDP_FLAGS_SKB_MODE) + return opts.attach_mode == XDP_ATTACHED_SKB; -static bool xsk_probe_bpf_link(void) -{ - LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE); - struct bpf_insn insns[2] = { - BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), - BPF_EXIT_INSN() - }; - int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns); - int ifindex_lo = 1; - bool ret = false; - int err; - - err = xsk_link_lookup(ifindex_lo, NULL, &link_fd); - if (err) - return ret; - - if (link_fd >= 0) - return true; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); - if (prog_fd < 0) - return ret; - - link_fd = bpf_link_create(prog_fd, ifindex_lo, BPF_XDP, &opts); - close(prog_fd); - - if (link_fd >= 0) { - ret = true; - close(link_fd); - } - - return ret; + return false; } -static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk) +int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags) { - char ifname[IFNAMSIZ]; - struct xsk_ctx *ctx; - char *interface; - - ctx = calloc(1, sizeof(*ctx)); - if (!ctx) - return -ENOMEM; - - interface = if_indextoname(ifindex, &ifname[0]); - if (!interface) { - free(ctx); - return -errno; - } - - ctx->ifindex = ifindex; - bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); - - xsk->ctx = ctx; - xsk->ctx->has_bpf_link = xsk_probe_bpf_link(); + int prog_fd; - return 0; + prog_fd = bpf_program__fd(prog); + return bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL); } -static int xsk_init_xdp_res(struct xsk_socket *xsk, - int *xsks_map_fd) +void xsk_detach_xdp_program(int ifindex, u32 xdp_flags) { - struct xsk_ctx *ctx = xsk->ctx; - int err; - - err = xsk_create_bpf_maps(xsk); - if (err) - return err; - - err = xsk_load_xdp_prog(xsk); - if (err) - goto err_load_xdp_prog; - - if (ctx->has_bpf_link) - err = xsk_create_bpf_link(xsk); - else - err = bpf_xdp_attach(xsk->ctx->ifindex, ctx->prog_fd, - xsk->config.xdp_flags, NULL); - - if (err) - goto err_attach_xdp_prog; - - if (!xsk->rx) - return err; - - err = xsk_set_bpf_maps(xsk); - if (err) - goto err_set_bpf_maps; - - return err; - -err_set_bpf_maps: - if (ctx->has_bpf_link) - close(ctx->link_fd); - else - bpf_xdp_detach(ctx->ifindex, 0, NULL); -err_attach_xdp_prog: - close(ctx->prog_fd); -err_load_xdp_prog: - xsk_delete_bpf_maps(xsk); - return err; + bpf_xdp_detach(ifindex, xdp_flags, NULL); } -static int xsk_lookup_xdp_res(struct xsk_socket *xsk, int *xsks_map_fd, int prog_id) +void xsk_clear_xskmap(struct bpf_map *map) { - struct xsk_ctx *ctx = xsk->ctx; - int err; - - ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (ctx->prog_fd < 0) { - err = -errno; - goto err_prog_fd; - } - err = xsk_lookup_bpf_maps(xsk); - if (err) - goto err_lookup_maps; - - if (!xsk->rx) - return err; - - err = xsk_set_bpf_maps(xsk); - if (err) - goto err_set_maps; + u32 index = 0; + int map_fd; - return err; - -err_set_maps: - close(ctx->xsks_map_fd); -err_lookup_maps: - close(ctx->prog_fd); -err_prog_fd: - if (ctx->has_bpf_link) - close(ctx->link_fd); - return err; + map_fd = bpf_map__fd(map); + bpf_map_delete_elem(map_fd, &index); } -static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, int *xsks_map_fd) +int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk) { - struct xsk_socket *xsk = _xdp; - struct xsk_ctx *ctx = xsk->ctx; - __u32 prog_id = 0; - int err; + int map_fd, sock_fd; + u32 index = 0; - if (ctx->has_bpf_link) - err = xsk_link_lookup(ctx->ifindex, &prog_id, &ctx->link_fd); - else - err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id); + map_fd = bpf_map__fd(map); + sock_fd = xsk_socket__fd(xsk); - if (err) - return err; - - err = !prog_id ? xsk_init_xdp_res(xsk, xsks_map_fd) : - xsk_lookup_xdp_res(xsk, xsks_map_fd, prog_id); - - if (!err && xsks_map_fd) - *xsks_map_fd = ctx->xsks_map_fd; - - return err; -} - -int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd) -{ - return __xsk_setup_xdp_prog(xsk, xsks_map_fd); + return bpf_map_update_elem(map_fd, &index, &sock_fd, 0); } static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex, @@ -913,7 +365,7 @@ out_free: static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, struct xsk_umem *umem, int ifindex, - const char *ifname, __u32 queue_id, + __u32 queue_id, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp) { @@ -940,51 +392,15 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, ctx->refcount = 1; ctx->umem = umem; ctx->queue_id = queue_id; - bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); ctx->fill = fill; ctx->comp = comp; list_add(&ctx->list, &umem->ctx_list); - ctx->has_bpf_link = xsk_probe_bpf_link(); return ctx; } -static void xsk_destroy_xsk_struct(struct xsk_socket *xsk) -{ - free(xsk->ctx); - free(xsk); -} - -int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd) -{ - xsk->ctx->xsks_map_fd = fd; - return xsk_set_bpf_maps(xsk); -} - -int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd) -{ - struct xsk_socket *xsk; - int res; - - xsk = calloc(1, sizeof(*xsk)); - if (!xsk) - return -ENOMEM; - - res = xsk_create_xsk_struct(ifindex, xsk); - if (res) { - free(xsk); - return -EINVAL; - } - - res = __xsk_setup_xdp_prog(xsk, xsks_map_fd); - - xsk_destroy_xsk_struct(xsk); - - return res; -} - int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, - const char *ifname, + int ifindex, __u32 queue_id, struct xsk_umem *umem, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, @@ -998,7 +414,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, struct xdp_mmap_offsets off; struct xsk_socket *xsk; struct xsk_ctx *ctx; - int err, ifindex; + int err; if (!umem || !xsk_ptr || !(rx || tx)) return -EFAULT; @@ -1013,13 +429,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, if (err) goto out_xsk_alloc; - xsk->outstanding_tx = 0; - ifindex = if_nametoindex(ifname); - if (!ifindex) { - err = -errno; - goto out_xsk_alloc; - } - if (umem->refcount++ > 0) { xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0); if (xsk->fd < 0) { @@ -1039,8 +448,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_socket; } - ctx = xsk_create_ctx(xsk, umem, ifindex, ifname, queue_id, - fill, comp); + ctx = xsk_create_ctx(xsk, umem, ifindex, queue_id, fill, comp); if (!ctx) { err = -ENOMEM; goto out_socket; @@ -1138,12 +546,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_mmap_tx; } - if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { - err = __xsk_setup_xdp_prog(xsk, NULL); - if (err) - goto out_mmap_tx; - } - *xsk_ptr = xsk; umem->fill_save = NULL; umem->comp_save = NULL; @@ -1167,7 +569,7 @@ out_xsk_alloc: return err; } -int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, +int xsk_socket__create(struct xsk_socket **xsk_ptr, int ifindex, __u32 queue_id, struct xsk_umem *umem, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *usr_config) @@ -1175,7 +577,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, if (!umem) return -EFAULT; - return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem, + return xsk_socket__create_shared(xsk_ptr, ifindex, queue_id, umem, rx, tx, umem->fill_save, umem->comp_save, usr_config); } @@ -1219,13 +621,6 @@ void xsk_socket__delete(struct xsk_socket *xsk) ctx = xsk->ctx; umem = ctx->umem; - if (ctx->refcount == 1) { - xsk_delete_bpf_maps(xsk); - close(ctx->prog_fd); - if (ctx->has_bpf_link) - close(ctx->link_fd); - } - xsk_put_ctx(ctx, true); err = xsk_get_mmap_offsets(xsk->fd, &off); diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 997723b0bfb2..04ed8b544712 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -23,77 +23,6 @@ extern "C" { #endif -/* This whole API has been deprecated and moved to libxdp that can be found at - * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so - * it should just be linking with libxdp instead of libbpf for this set of - * functionality. If not, please submit a bug report on the aforementioned page. - */ - -/* Load-Acquire Store-Release barriers used by the XDP socket - * library. The following macros should *NOT* be considered part of - * the xsk.h API, and is subject to change anytime. - * - * LIBRARY INTERNAL - */ - -#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x) -#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v) - -#if defined(__i386__) || defined(__x86_64__) -# define libbpf_smp_store_release(p, v) \ - do { \ - asm volatile("" : : : "memory"); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - asm volatile("" : : : "memory"); \ - ___p1; \ - }) -#elif defined(__aarch64__) -# define libbpf_smp_store_release(p, v) \ - asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory") -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1; \ - asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ - ___p1; \ - }) -#elif defined(__riscv) -# define libbpf_smp_store_release(p, v) \ - do { \ - asm volatile ("fence rw,w" : : : "memory"); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - asm volatile ("fence r,rw" : : : "memory"); \ - ___p1; \ - }) -#endif - -#ifndef libbpf_smp_store_release -#define libbpf_smp_store_release(p, v) \ - do { \ - __sync_synchronize(); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -#endif - -#ifndef libbpf_smp_load_acquire -#define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - __sync_synchronize(); \ - ___p1; \ - }) -#endif - -/* LIBRARY INTERNAL -- END */ - /* Do not access these members directly. Use the functions below. */ #define DEFINE_XSK_RING(name) \ struct name { \ @@ -168,7 +97,7 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) * this function. Without this optimization it whould have been * free_entries = r->cached_prod - r->cached_cons + r->size. */ - r->cached_cons = libbpf_smp_load_acquire(r->consumer); + r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE); r->cached_cons += r->size; return r->cached_cons - r->cached_prod; @@ -179,7 +108,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) __u32 entries = r->cached_prod - r->cached_cons; if (entries == 0) { - r->cached_prod = libbpf_smp_load_acquire(r->producer); + r->cached_prod = __atomic_load_n(r->producer, __ATOMIC_ACQUIRE); entries = r->cached_prod - r->cached_cons; } @@ -202,7 +131,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) /* Make sure everything has been written to the ring before indicating * this to the kernel by writing the producer pointer. */ - libbpf_smp_store_release(prod->producer, *prod->producer + nb); + __atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE); } static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) @@ -227,8 +156,7 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb) /* Make sure data has been read before indicating we are done * with the entries by updating the consumer pointer. */ - libbpf_smp_store_release(cons->consumer, *cons->consumer + nb); - + __atomic_store_n(cons->consumer, *cons->consumer + nb, __ATOMIC_RELEASE); } static inline void *xsk_umem__get_data(void *umem_area, __u64 addr) @@ -269,18 +197,15 @@ struct xsk_umem_config { __u32 flags; }; -int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd); -int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd); -int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd); - -/* Flags for the libbpf_flags field. */ -#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0) +int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags); +void xsk_detach_xdp_program(int ifindex, u32 xdp_flags); +int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk); +void xsk_clear_xskmap(struct bpf_map *map); +bool xsk_is_in_mode(u32 ifindex, int mode); struct xsk_socket_config { __u32 rx_size; __u32 tx_size; - __u32 libbpf_flags; - __u32 xdp_flags; __u16 bind_flags; }; @@ -291,13 +216,13 @@ int xsk_umem__create(struct xsk_umem **umem, struct xsk_ring_cons *comp, const struct xsk_umem_config *config); int xsk_socket__create(struct xsk_socket **xsk, - const char *ifname, __u32 queue_id, + int ifindex, __u32 queue_id, struct xsk_umem *umem, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *config); int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, - const char *ifname, + int ifindex, __u32 queue_id, struct xsk_umem *umem, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh index a0b71723a818..ae697a10a056 100755 --- a/tools/testing/selftests/bpf/xsk_prereqs.sh +++ b/tools/testing/selftests/bpf/xsk_prereqs.sh @@ -55,21 +55,13 @@ test_exit() clear_configs() { - if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then - [ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] && - { ip netns exec $3 ip link del $2; } - ip netns del $3 - fi - #Once we delete a veth pair node, the entire veth pair is removed, - #this is just to be cautious just incase the NS does not exist then - #veth node inside NS won't get removed so we explicitly remove it [ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] && { ip link del $1; } } cleanup_exit() { - clear_configs $1 $2 $3 + clear_configs $1 $2 } validate_ip_utility() @@ -83,7 +75,7 @@ exec_xskxceiver() ARGS+="-b " fi - ./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${ARGS} + ./${XSKOBJ} -i ${VETH0} -i ${VETH1} ${ARGS} retval=$? test_status $retval "${TEST_NAME}" diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 162d3a516f2c..a17655107a94 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -55,12 +55,11 @@ * Flow: * ----- * - Single process spawns two threads: Tx and Rx - * - Each of these two threads attach to a veth interface within their assigned - * namespaces - * - Each thread Creates one AF_XDP socket connected to a unique umem for each + * - Each of these two threads attach to a veth interface + * - Each thread creates one AF_XDP socket connected to a unique umem for each * veth interface - * - Tx thread Transmits 10k packets from veth<xxxx> to veth<yyyy> - * - Rx thread verifies if all 10k packets were received and delivered in-order, + * - Tx thread Transmits a number of packets from veth<xxxx> to veth<yyyy> + * - Rx thread verifies if all packets were received and delivered in-order, * and have the right content * * Enable/disable packet dump mode: @@ -97,18 +96,14 @@ #include <time.h> #include <unistd.h> #include <stdatomic.h> + +#include "xsk_xdp_progs.skel.h" #include "xsk.h" #include "xskxceiver.h" #include <bpf/bpf.h> #include <linux/filter.h> #include "../kselftest.h" -/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf. - * Until xskxceiver is either moved or re-writed into libxdp, suppress - * deprecation warnings in this file - */ -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; static const char *IP1 = "192.168.100.162"; @@ -269,6 +264,11 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); } +static u32 mode_to_xdp_flags(enum test_mode mode) +{ + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; +} + static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) { struct xsk_umem_config cfg = { @@ -322,15 +322,13 @@ static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_i xsk->umem = umem; cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; - cfg.xdp_flags = ifobject->xdp_flags; cfg.bind_flags = ifobject->bind_flags; if (shared) cfg.bind_flags |= XDP_SHARED_UMEM; txr = ifobject->tx_on ? &xsk->tx : NULL; rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg); + return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg); } static bool ifobj_zc_avail(struct ifobject *ifobject) @@ -350,7 +348,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) umem = calloc(1, sizeof(struct xsk_umem_info)); if (!umem) { munmap(bufs, umem_sz); - exit_with_error(-ENOMEM); + exit_with_error(ENOMEM); } umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; ret = xsk_configure_umem(umem, bufs, umem_sz); @@ -360,8 +358,6 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) xsk = calloc(1, sizeof(struct xsk_socket_info)); if (!xsk) goto out; - ifobject->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; - ifobject->xdp_flags |= XDP_FLAGS_DRV_MODE; ifobject->bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY; ifobject->rx_on = true; xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; @@ -399,28 +395,6 @@ static void usage(const char *prog) ksft_print_msg(str, prog); } -static int switch_namespace(const char *nsname) -{ - char fqns[26] = "/var/run/netns/"; - int nsfd; - - if (!nsname || strlen(nsname) == 0) - return -1; - - strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1); - nsfd = open(fqns, O_RDONLY); - - if (nsfd == -1) - exit_with_error(errno); - - if (setns(nsfd, 0) == -1) - exit_with_error(errno); - - print_verbose("NS switched: %s\n", nsname); - - return nsfd; -} - static bool validate_interface(struct ifobject *ifobj) { if (!strcmp(ifobj->ifname, "")) @@ -438,8 +412,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj opterr = 0; for (;;) { - char *sptr, *token; - c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index); if (c == -1) break; @@ -453,11 +425,13 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj else break; - sptr = strndupa(optarg, strlen(optarg)); - memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); - token = strsep(&sptr, ","); - if (token) - memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS); + memcpy(ifobj->ifname, optarg, + min_t(size_t, MAX_INTERFACE_NAME_CHARS, strlen(optarg))); + + ifobj->ifindex = if_nametoindex(ifobj->ifname); + if (!ifobj->ifindex) + exit_with_error(errno); + interface_nb++; break; case 'D': @@ -520,6 +494,10 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, test->total_steps = 1; test->nb_sockets = 1; test->fail = false; + test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; + test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; + test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; + test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk; } static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, @@ -538,12 +516,6 @@ static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, for (i = 0; i < MAX_INTERFACES; i++) { struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; - if (mode == TEST_MODE_SKB) - ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE; - else - ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE; - ifobj->bind_flags = XDP_USE_NEED_WAKEUP; if (mode == TEST_MODE_ZC) ifobj->bind_flags |= XDP_ZEROCOPY; @@ -565,6 +537,16 @@ static void test_spec_set_name(struct test_spec *test, const char *name) strncpy(test->name, name, MAX_TEST_NAME_SIZE); } +static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx, + struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx, + struct bpf_map *xskmap_tx) +{ + test->xdp_prog_rx = xdp_prog_rx; + test->xdp_prog_tx = xdp_prog_tx; + test->xskmap_rx = xskmap_rx; + test->xskmap_tx = xskmap_tx; +} + static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) @@ -767,7 +749,7 @@ static void pkt_dump(void *pkt, u32 len) struct ethhdr *ethhdr; struct udphdr *udphdr; struct iphdr *iphdr; - int payload, i; + u32 payload, i; ethhdr = pkt; iphdr = pkt + sizeof(*ethhdr); @@ -792,7 +774,7 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source)); fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest)); /*extract L5 frame */ - payload = *((uint32_t *)(pkt + PKT_HDR_SIZE)); + payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE))); fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload); fprintf(stdout, "---------------------------------------\n"); @@ -936,7 +918,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) if (ifobj->use_poll) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) - exit_with_error(-ret); + exit_with_error(errno); if (!ret) { if (!is_umem_valid(test->ifobj_tx)) @@ -963,7 +945,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) - exit_with_error(-ret); + exit_with_error(errno); } ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } @@ -1015,7 +997,7 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd if (timeout) { if (ret < 0) { ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, ret); + __func__, errno); return TEST_FAILURE; } if (ret == 0) @@ -1024,7 +1006,7 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd } if (ret <= 0) { ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, ret); + __func__, errno); return TEST_FAILURE; } } @@ -1240,7 +1222,7 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje { xsk_configure_socket(test, ifobject, test->ifobj_rx->umem, true); ifobject->xsk = &ifobject->xsk_arr[0]; - ifobject->xsk_map_fd = test->ifobj_rx->xsk_map_fd; + ifobject->xskmap = test->ifobj_rx->xskmap; memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); } @@ -1272,7 +1254,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, buffers_to_fill); + xsk_ring_prod__submit(&umem->fq, i); } static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) @@ -1280,10 +1262,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; LIBBPF_OPTS(bpf_xdp_query_opts, opts); - int ret, ifindex; void *bufs; - - ifobject->ns_fd = switch_namespace(ifobject->nsname); + int ret; if (ifobject->umem->unaligned_mode) mmap_flags |= MAP_HUGETLB; @@ -1308,33 +1288,9 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (!ifobject->rx_on) return; - ifindex = if_nametoindex(ifobject->ifname); - if (!ifindex) - exit_with_error(errno); - - ret = xsk_setup_xdp_prog_xsk(ifobject->xsk->xsk, &ifobject->xsk_map_fd); - if (ret) - exit_with_error(-ret); - - ret = bpf_xdp_query(ifindex, ifobject->xdp_flags, &opts); - if (ret) - exit_with_error(-ret); - - if (ifobject->xdp_flags & XDP_FLAGS_SKB_MODE) { - if (opts.attach_mode != XDP_ATTACHED_SKB) { - ksft_print_msg("ERROR: [%s] XDP prog not in SKB mode\n"); - exit_with_error(-EINVAL); - } - } else if (ifobject->xdp_flags & XDP_FLAGS_DRV_MODE) { - if (opts.attach_mode != XDP_ATTACHED_DRV) { - ksft_print_msg("ERROR: [%s] XDP prog not in DRV mode\n"); - exit_with_error(-EINVAL); - } - } - - ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd); + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); if (ret) - exit_with_error(-ret); + exit_with_error(errno); } static void *worker_testapp_validate_tx(void *arg) @@ -1367,14 +1323,17 @@ static void *worker_testapp_validate_rx(void *arg) struct test_spec *test = (struct test_spec *)arg; struct ifobject *ifobject = test->ifobj_rx; struct pollfd fds = { }; - int id = 0; int err; if (test->current_step == 1) { thread_common_ops(test, ifobject); } else { - bpf_map_delete_elem(ifobject->xsk_map_fd, &id); - xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd); + xsk_clear_xskmap(ifobject->xskmap); + err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); + if (err) { + printf("Error: Failed to update xskmap, error %s\n", strerror(-err)); + exit_with_error(-err); + } } fds.fd = xsk_socket__fd(ifobject->xsk->xsk); @@ -1412,84 +1371,106 @@ static void handler(int signum) pthread_exit(NULL); } -static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj, - enum test_type type) +static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj) { - bool old_shared_umem = ifobj->shared_umem; - pthread_t t0; - - if (pthread_barrier_init(&barr, NULL, 2)) - exit_with_error(errno); - - test->current_step++; - if (type == TEST_TYPE_POLL_RXQ_TMOUT) - pkt_stream_reset(ifobj->pkt_stream); - pkts_in_flight = 0; - - test->ifobj_rx->shared_umem = false; - test->ifobj_tx->shared_umem = false; + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; +} - signal(SIGUSR1, handler); - /* Spawn thread */ - pthread_create(&t0, NULL, ifobj->func_ptr, test); +static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, + struct bpf_map *xskmap, enum test_mode mode) +{ + int err; - if (type != TEST_TYPE_POLL_TXQ_TMOUT) - pthread_barrier_wait(&barr); + xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode)); + err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode)); + if (err) { + printf("Error attaching XDP program\n"); + exit_with_error(-err); + } - if (pthread_barrier_destroy(&barr)) - exit_with_error(errno); + if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC)) + if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) { + ksft_print_msg("ERROR: XDP prog not in DRV mode\n"); + exit_with_error(EINVAL); + } - pthread_kill(t0, SIGUSR1); - pthread_join(t0, NULL); + ifobj->xdp_prog = xdp_prog; + ifobj->xskmap = xskmap; + ifobj->mode = mode; +} - if (test->total_steps == test->current_step || test->fail) { - xsk_socket__delete(ifobj->xsk->xsk); - testapp_clean_xsk_umem(ifobj); - } +static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, + struct ifobject *ifobj_tx) +{ + if (xdp_prog_changed(test, ifobj_rx)) + xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); - test->ifobj_rx->shared_umem = old_shared_umem; - test->ifobj_tx->shared_umem = old_shared_umem; + if (!ifobj_tx || ifobj_tx->shared_umem) + return; - return !!test->fail; + if (xdp_prog_changed(test, ifobj_tx)) + xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); } -static int testapp_validate_traffic(struct test_spec *test) +static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1, + struct ifobject *ifobj2) { - struct ifobject *ifobj_tx = test->ifobj_tx; - struct ifobject *ifobj_rx = test->ifobj_rx; pthread_t t0, t1; - if (pthread_barrier_init(&barr, NULL, 2)) - exit_with_error(errno); + if (ifobj2) + if (pthread_barrier_init(&barr, NULL, 2)) + exit_with_error(errno); test->current_step++; - pkt_stream_reset(ifobj_rx->pkt_stream); + pkt_stream_reset(ifobj1->pkt_stream); pkts_in_flight = 0; + signal(SIGUSR1, handler); /*Spawn RX thread */ - pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); + pthread_create(&t0, NULL, ifobj1->func_ptr, test); - pthread_barrier_wait(&barr); - if (pthread_barrier_destroy(&barr)) - exit_with_error(errno); + if (ifobj2) { + pthread_barrier_wait(&barr); + if (pthread_barrier_destroy(&barr)) + exit_with_error(errno); - /*Spawn TX thread */ - pthread_create(&t1, NULL, ifobj_tx->func_ptr, test); + /*Spawn TX thread */ + pthread_create(&t1, NULL, ifobj2->func_ptr, test); - pthread_join(t1, NULL); - pthread_join(t0, NULL); + pthread_join(t1, NULL); + } + + if (!ifobj2) + pthread_kill(t0, SIGUSR1); + else + pthread_join(t0, NULL); if (test->total_steps == test->current_step || test->fail) { - xsk_socket__delete(ifobj_tx->xsk->xsk); - xsk_socket__delete(ifobj_rx->xsk->xsk); - testapp_clean_xsk_umem(ifobj_rx); - if (!ifobj_tx->shared_umem) - testapp_clean_xsk_umem(ifobj_tx); + if (ifobj2) + xsk_socket__delete(ifobj2->xsk->xsk); + xsk_socket__delete(ifobj1->xsk->xsk); + testapp_clean_xsk_umem(ifobj1); + if (ifobj2 && !ifobj2->shared_umem) + testapp_clean_xsk_umem(ifobj2); } return !!test->fail; } +static int testapp_validate_traffic(struct test_spec *test) +{ + struct ifobject *ifobj_rx = test->ifobj_rx; + struct ifobject *ifobj_tx = test->ifobj_tx; + + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); + return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); +} + +static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj) +{ + return __testapp_validate_traffic(test, ifobj, NULL); +} + static void testapp_teardown(struct test_spec *test) { int i; @@ -1525,7 +1506,7 @@ static void testapp_bidi(struct test_spec *test) print_verbose("Switching Tx/Rx vectors\n"); swap_directions(&test->ifobj_rx, &test->ifobj_tx); - testapp_validate_traffic(test); + __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); swap_directions(&test->ifobj_rx, &test->ifobj_tx); } @@ -1539,9 +1520,9 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; - ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd); + ret = xsk_update_xskmap(ifobj_rx->xskmap, ifobj_rx->xsk->xsk); if (ret) - exit_with_error(-ret); + exit_with_error(errno); } static void testapp_bpf_res(struct test_spec *test) @@ -1580,8 +1561,6 @@ static void testapp_stats_tx_invalid_descs(struct test_spec *test) pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); test->ifobj_tx->validation_func = validate_tx_invalid_descs; testapp_validate_traffic(test); - - pkt_stream_restore_default(test); } static void testapp_stats_rx_full(struct test_spec *test) @@ -1597,8 +1576,6 @@ static void testapp_stats_rx_full(struct test_spec *test) test->ifobj_rx->release_rx = false; test->ifobj_rx->validation_func = validate_rx_full; testapp_validate_traffic(test); - - pkt_stream_restore_default(test); } static void testapp_stats_fill_empty(struct test_spec *test) @@ -1613,8 +1590,6 @@ static void testapp_stats_fill_empty(struct test_spec *test) test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; testapp_validate_traffic(test); - - pkt_stream_restore_default(test); } /* Simple test */ @@ -1647,7 +1622,6 @@ static bool testapp_unaligned(struct test_spec *test) test->ifobj_rx->pkt_stream->use_addr_for_fill = true; testapp_validate_traffic(test); - pkt_stream_restore_default(test); return true; } @@ -1657,7 +1631,6 @@ static void testapp_single_pkt(struct test_spec *test) pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); testapp_validate_traffic(test); - pkt_stream_restore_default(test); } static void testapp_invalid_desc(struct test_spec *test) @@ -1698,7 +1671,51 @@ static void testapp_invalid_desc(struct test_spec *test) pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); testapp_validate_traffic(test); - pkt_stream_restore_default(test); +} + +static void testapp_xdp_drop(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_name(test, "XDP_DROP_HALF"); + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + pkt_stream_receive_half(test); + testapp_validate_traffic(test); +} + +static void testapp_poll_txq_tmout(struct test_spec *test) +{ + test_spec_set_name(test, "POLL_TXQ_FULL"); + + test->ifobj_tx->use_poll = true; + /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ + test->ifobj_tx->umem->frame_size = 2048; + pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); + testapp_validate_traffic_single_thread(test, test->ifobj_tx); +} + +static void testapp_poll_rxq_tmout(struct test_spec *test) +{ + test_spec_set_name(test, "POLL_RXQ_EMPTY"); + test->ifobj_rx->use_poll = true; + testapp_validate_traffic_single_thread(test, test->ifobj_rx); +} + +static int xsk_load_xdp_programs(struct ifobject *ifobj) +{ + ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); + if (libbpf_get_error(ifobj->xdp_progs)) + return libbpf_get_error(ifobj->xdp_progs); + + return 0; +} + +static void xsk_unload_xdp_programs(struct ifobject *ifobj) +{ + xsk_xdp_progs__destroy(ifobj->xdp_progs); } static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, @@ -1706,6 +1723,7 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * const u16 src_port, thread_func_t func_ptr) { struct in_addr ip; + int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); memcpy(ifobj->src_mac, src_mac, ETH_ALEN); @@ -1720,6 +1738,12 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * ifobj->src_port = src_port; ifobj->func_ptr = func_ptr; + + err = xsk_load_xdp_programs(ifobj); + if (err) { + printf("Error loading XDP program\n"); + exit_with_error(err); + } } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) @@ -1764,8 +1788,6 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ test->ifobj_rx->umem->frame_size = 2048; pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE); testapp_validate_traffic(test); - - pkt_stream_restore_default(test); break; case TEST_TYPE_RX_POLL: test->ifobj_rx->use_poll = true; @@ -1778,18 +1800,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ testapp_validate_traffic(test); break; case TEST_TYPE_POLL_TXQ_TMOUT: - test_spec_set_name(test, "POLL_TXQ_FULL"); - test->ifobj_tx->use_poll = true; - /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ - test->ifobj_tx->umem->frame_size = 2048; - pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - testapp_validate_traffic_single_thread(test, test->ifobj_tx, type); - pkt_stream_restore_default(test); + testapp_poll_txq_tmout(test); break; case TEST_TYPE_POLL_RXQ_TMOUT: - test_spec_set_name(test, "POLL_RXQ_EMPTY"); - test->ifobj_rx->use_poll = true; - testapp_validate_traffic_single_thread(test, test->ifobj_rx, type); + testapp_poll_rxq_tmout(test); break; case TEST_TYPE_ALIGNED_INV_DESC: test_spec_set_name(test, "ALIGNED_INV_DESC"); @@ -1818,6 +1832,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ case TEST_TYPE_HEADROOM: testapp_headroom(test); break; + case TEST_TYPE_XDP_DROP_HALF: + testapp_xdp_drop(test); + break; default: break; } @@ -1825,6 +1842,7 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ if (!test->fail) ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); + pkt_stream_restore_default(test); } static struct ifobject *ifobject_create(void) @@ -1843,8 +1861,6 @@ static struct ifobject *ifobject_create(void) if (!ifobj->umem) goto out_umem; - ifobj->ns_fd = -1; - return ifobj; out_umem: @@ -1856,14 +1872,12 @@ out_xsk_arr: static void ifobject_delete(struct ifobject *ifobj) { - if (ifobj->ns_fd != -1) - close(ifobj->ns_fd); free(ifobj->umem); free(ifobj->xsk_arr); free(ifobj); } -static bool is_xdp_supported(struct ifobject *ifobject) +static bool is_xdp_supported(int ifindex) { int flags = XDP_FLAGS_DRV_MODE; @@ -1872,7 +1886,6 @@ static bool is_xdp_supported(struct ifobject *ifobject) BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), BPF_EXIT_INSN() }; - int ifindex = if_nametoindex(ifobject->ifname); int prog_fd, insn_cnt = ARRAY_SIZE(insns); int err; @@ -1900,7 +1913,7 @@ int main(int argc, char **argv) int modes = TEST_MODE_SKB + 1; u32 i, j, failed_tests = 0; struct test_spec test; - bool shared_umem; + bool shared_netdev; /* Use libbpf 1.0 API mode */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL); @@ -1915,27 +1928,27 @@ int main(int argc, char **argv) setlocale(LC_ALL, ""); parse_command_line(ifobj_tx, ifobj_rx, argc, argv); - shared_umem = !strcmp(ifobj_tx->ifname, ifobj_rx->ifname); - ifobj_tx->shared_umem = shared_umem; - ifobj_rx->shared_umem = shared_umem; + shared_netdev = (ifobj_tx->ifindex == ifobj_rx->ifindex); + ifobj_tx->shared_umem = shared_netdev; + ifobj_rx->shared_umem = shared_netdev; if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) { usage(basename(argv[0])); ksft_exit_xfail(); } - init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, - worker_testapp_validate_tx); - init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, - worker_testapp_validate_rx); - - if (is_xdp_supported(ifobj_tx)) { + if (is_xdp_supported(ifobj_tx->ifindex)) { modes++; if (ifobj_zc_avail(ifobj_tx)) modes++; } + init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, + worker_testapp_validate_rx); + init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, + worker_testapp_validate_tx); + test_spec_init(&test, ifobj_tx, ifobj_rx, 0); tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE); @@ -1946,7 +1959,7 @@ int main(int argc, char **argv) ksft_set_plan(modes * TEST_TYPE_MAX); - for (i = 0; i < modes; i++) + for (i = 0; i < modes; i++) { for (j = 0; j < TEST_TYPE_MAX; j++) { test_spec_init(&test, ifobj_tx, ifobj_rx, i); run_pkt_test(&test, i, j); @@ -1955,9 +1968,12 @@ int main(int argc, char **argv) if (test.fail) failed_tests++; } + } pkt_stream_delete(tx_pkt_stream_default); pkt_stream_delete(rx_pkt_stream_default); + xsk_unload_xdp_programs(ifobj_tx); + xsk_unload_xdp_programs(ifobj_rx); ifobject_delete(ifobj_tx); ifobject_delete(ifobj_rx); diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index edb76d2def9f..3e8ec7d8ec32 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -5,6 +5,8 @@ #ifndef XSKXCEIVER_H_ #define XSKXCEIVER_H_ +#include "xsk_xdp_progs.skel.h" + #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -30,7 +32,6 @@ #define TEST_CONTINUE 1 #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 16 -#define MAX_INTERFACES_NAMESPACE_CHARS 16 #define MAX_SOCKETS 2 #define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 @@ -86,6 +87,7 @@ enum test_type { TEST_TYPE_STATS_RX_FULL, TEST_TYPE_STATS_FILL_EMPTY, TEST_TYPE_BPF_RES, + TEST_TYPE_XDP_DROP_HALF, TEST_TYPE_MAX }; @@ -133,18 +135,19 @@ typedef void *(*thread_func_t)(void *arg); struct ifobject { char ifname[MAX_INTERFACE_NAME_CHARS]; - char nsname[MAX_INTERFACES_NAMESPACE_CHARS]; struct xsk_socket_info *xsk; struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; thread_func_t func_ptr; validation_func_t validation_func; struct pkt_stream *pkt_stream; - int ns_fd; - int xsk_map_fd; + struct xsk_xdp_progs *xdp_progs; + struct bpf_map *xskmap; + struct bpf_program *xdp_prog; + enum test_mode mode; + int ifindex; u32 dst_ip; u32 src_ip; - u32 xdp_flags; u32 bind_flags; u16 src_port; u16 dst_port; @@ -164,6 +167,10 @@ struct test_spec { struct ifobject *ifobj_rx; struct pkt_stream *tx_pkt_stream_default; struct pkt_stream *rx_pkt_stream_default; + struct bpf_program *xdp_prog_rx; + struct bpf_program *xdp_prog_tx; + struct bpf_map *xskmap_rx; + struct bpf_map *xskmap_tx; u16 total_steps; u16 current_step; u16 nb_sockets; diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile index 79b19a2863a0..84832c369a2e 100644 --- a/tools/testing/selftests/clone3/Makefile +++ b/tools/testing/selftests/clone3/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -g -std=gnu99 -I../../../../usr/include/ +CFLAGS += -g -std=gnu99 $(KHDR_INCLUDES) LDLIBS += -lcap TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \ diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile index f6f2d6f473c6..ce262d097269 100644 --- a/tools/testing/selftests/core/Makefile +++ b/tools/testing/selftests/core/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ +CFLAGS += -g $(KHDR_INCLUDES) TEST_GEN_PROGS := close_range_test diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh index 48b7af6b022c..f3ffeb1343cf 100644 --- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh +++ b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh @@ -10,7 +10,7 @@ dmesg -C for file in "$DBGFS/"* do - echo "$(basename "$f")" > "$DBGFS/rm_contexts" + (echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null if dmesg | grep -q BUG then dmesg diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index db4942383a50..bcd4734ca094 100644 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -24,7 +24,7 @@ ensure_write_fail() content=$2 reason=$3 - if echo "$content" > "$file" + if (echo "$content" > "$file") 2> /dev/null then echo "writing $content to $file succeed ($fail_reason)" echo "expected failure because $reason" @@ -96,6 +96,34 @@ test_stats() done } +test_filter() +{ + filter_dir=$1 + ensure_file "$filter_dir/type" "exist" "600" + ensure_write_succ "$filter_dir/type" "anon" "valid input" + ensure_write_succ "$filter_dir/type" "memcg" "valid input" + ensure_write_fail "$filter_dir/type" "foo" "invalid input" + ensure_file "$filter_dir/matching" "exist" "600" + ensure_file "$filter_dir/memcg_path" "exist" "600" +} + +test_filters() +{ + filters_dir=$1 + ensure_dir "$filters_dir" "exist" + ensure_file "$filters_dir/nr_filters" "exist" "600" + ensure_write_succ "$filters_dir/nr_filters" "1" "valid input" + test_filter "$filters_dir/0" + + ensure_write_succ "$filters_dir/nr_filters" "2" "valid input" + test_filter "$filters_dir/0" + test_filter "$filters_dir/1" + + ensure_write_succ "$filters_dir/nr_filters" "0" "valid input" + ensure_dir "$filters_dir/0" "not_exist" + ensure_dir "$filters_dir/1" "not_exist" +} + test_watermarks() { watermarks_dir=$1 @@ -143,6 +171,7 @@ test_scheme() test_access_pattern "$scheme_dir/access_pattern" test_quotas "$scheme_dir/quotas" test_watermarks "$scheme_dir/watermarks" + test_filters "$scheme_dir/filters" test_stats "$scheme_dir/stats" test_tried_regions "$scheme_dir/tried_regions" } diff --git a/tools/testing/selftests/dmabuf-heaps/Makefile b/tools/testing/selftests/dmabuf-heaps/Makefile index 604b43ece15f..9e7e158d5fa3 100644 --- a/tools/testing/selftests/dmabuf-heaps/Makefile +++ b/tools/testing/selftests/dmabuf-heaps/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -static -O3 -Wl,-no-as-needed -Wall +CFLAGS += -static -O3 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) TEST_GEN_PROGS = dmabuf-heap diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index 29af27acd40e..890a8236a8ba 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -13,10 +13,9 @@ #include <sys/types.h> #include <linux/dma-buf.h> +#include <linux/dma-heap.h> #include <drm/drm.h> -#include "../../../../include/uapi/linux/dma-heap.h" - #define DEVPATH "/dev/dma_heap" static int check_vgem(int fd) diff --git a/tools/testing/selftests/drivers/dma-buf/Makefile b/tools/testing/selftests/drivers/dma-buf/Makefile index 79cb16b4e01a..441407bb0e80 100644 --- a/tools/testing/selftests/drivers/dma-buf/Makefile +++ b/tools/testing/selftests/drivers/dma-buf/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -I../../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := udmabuf diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh index 71066bc4b886..5492fa5550d7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh @@ -5,18 +5,18 @@ # prioritized according to the default priority specified at the port. # rx_octets_prio_* counters are used to verify the prioritization. # -# +-----------------------+ -# | H1 | -# | + $h1 | -# | | 192.0.2.1/28 | -# +----|------------------+ +# +----------------------------------+ +# | H1 | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|-----------------------------+ # | -# +----|------------------+ -# | SW | | -# | + $swp1 | -# | 192.0.2.2/28 | -# | APP=<prio>,1,0 | -# +-----------------------+ +# +----|-----------------------------+ +# | SW | | +# | + $swp1 | +# | 192.0.2.2/28 | +# | dcb app default-prio <prio> | +# +----------------------------------+ ALL_TESTS=" ping_ipv4 @@ -29,42 +29,6 @@ NUM_NETIFS=2 : ${HIT_TIMEOUT:=1000} # ms source $lib_dir/lib.sh -declare -a APP - -defprio_install() -{ - local dev=$1; shift - local prio=$1; shift - local app="app=$prio,1,0" - - lldptool -T -i $dev -V APP $app >/dev/null - lldpad_app_wait_set $dev - APP[$prio]=$app -} - -defprio_uninstall() -{ - local dev=$1; shift - local prio=$1; shift - local app=${APP[$prio]} - - lldptool -T -i $dev -V APP -d $app >/dev/null - lldpad_app_wait_del - unset APP[$prio] -} - -defprio_flush() -{ - local dev=$1; shift - local prio - - if ((${#APP[@]})); then - lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null - fi - lldpad_app_wait_del - APP=() -} - h1_create() { simple_if_init $h1 192.0.2.1/28 @@ -83,7 +47,7 @@ switch_create() switch_destroy() { - defprio_flush $swp1 + dcb app flush dev $swp1 default-prio ip addr del dev $swp1 192.0.2.2/28 ip link set dev $swp1 down } @@ -124,7 +88,7 @@ __test_defprio() RET=0 - defprio_install $swp1 $prio_install + dcb app add dev $swp1 default-prio $prio_install local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) mausezahn -q $h1 -d 100m -c 10 -t arp reply @@ -134,7 +98,7 @@ __test_defprio() check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $((t1 - t0))." log_test "Default priority $prio_install/$prio_observe" - defprio_uninstall $swp1 $prio_install + dcb app del dev $swp1 default-prio $prio_install } test_defprio() @@ -145,7 +109,7 @@ test_defprio() __test_defprio $prio $prio done - defprio_install $swp1 3 + dcb app add dev $swp1 default-prio 3 __test_defprio 0 3 __test_defprio 1 3 __test_defprio 2 3 @@ -153,7 +117,7 @@ test_defprio() __test_defprio 5 5 __test_defprio 6 6 __test_defprio 7 7 - defprio_uninstall $swp1 3 + dcb app del dev $swp1 default-prio 3 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 28a570006d4d..87c41f5727c9 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -20,7 +20,7 @@ # | SW | | | # | +-|----------------------------------------------------------------|-+ | # | | + $swp1 BR $swp2 + | | -# | | APP=0,5,10 .. 7,5,17 APP=0,5,20 .. 7,5,27 | | +# | | dcb dscp-prio 10:0...17:7 dcb dscp-prio 20:0...27:7 | | # | +--------------------------------------------------------------------+ | # +---------------------------------------------------------------------------+ @@ -62,16 +62,6 @@ h2_destroy() simple_if_fini $h2 192.0.2.2/28 } -dscp_map() -{ - local base=$1; shift - local prio - - for prio in {0..7}; do - echo app=$prio,5,$((base + prio)) - done -} - switch_create() { ip link add name br1 type bridge vlan_filtering 1 @@ -81,17 +71,14 @@ switch_create() ip link set dev $swp2 master br1 ip link set dev $swp2 up - lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null - lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null - lldpad_app_wait_set $swp1 - lldpad_app_wait_set $swp2 + dcb app add dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7 + dcb app add dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7 } switch_destroy() { - lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null - lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7 + dcb app del dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7 ip link set dev $swp2 down ip link set dev $swp2 nomaster diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh index 4cb2aa65278a..f6c23f84423e 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -94,16 +94,6 @@ h2_destroy() simple_if_fini $h2 192.0.2.18/28 } -dscp_map() -{ - local base=$1; shift - local prio - - for prio in {0..7}; do - echo app=$prio,5,$((base + prio)) - done -} - switch_create() { simple_if_init $swp1 192.0.2.2/28 @@ -112,17 +102,14 @@ switch_create() tc qdisc add dev $swp1 clsact tc qdisc add dev $swp2 clsact - lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null - lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null - lldpad_app_wait_set $swp1 - lldpad_app_wait_set $swp2 + dcb app add dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 } switch_destroy() { - lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null - lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + dcb app del dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 tc qdisc del dev $swp2 clsact tc qdisc del dev $swp1 clsact @@ -265,13 +252,11 @@ test_dscp_leftover() { echo "Test that last removed DSCP rule is deconfigured correctly" - lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null - lldpad_app_wait_del + dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 __test_update 0 zero - lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null - lldpad_app_wait_set $swp2 + dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index a08c02abde12..7f7d20f22207 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -17,6 +17,18 @@ SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/ DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/ DL_HANDLE=netdevsim/$DEV_NAME +wait_for_devlink() +{ + "$@" | grep -q $DL_HANDLE +} + +devlink_wait() +{ + local timeout=$1 + + busywait "$timeout" wait_for_devlink devlink dev +} + fw_flash_test() { RET=0 @@ -256,6 +268,9 @@ netns_reload_test() ip netns del testns2 ip netns del testns1 + # Wait until netns async cleanup is done. + devlink_wait 2000 + log_test "netns reload test" } @@ -348,6 +363,9 @@ resource_test() ip netns del testns2 ip netns del testns1 + # Wait until netns async cleanup is done. + devlink_wait 2000 + log_test "resource test" } diff --git a/tools/testing/selftests/drivers/s390x/uvdevice/Makefile b/tools/testing/selftests/drivers/s390x/uvdevice/Makefile index 891215a7dc8a..755d164384c4 100644 --- a/tools/testing/selftests/drivers/s390x/uvdevice/Makefile +++ b/tools/testing/selftests/drivers/s390x/uvdevice/Makefile @@ -11,10 +11,9 @@ else TEST_GEN_PROGS := test_uvdevice top_srcdir ?= ../../../../../.. -khdr_dir = $(top_srcdir)/usr/include LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include -CFLAGS += -Wall -Werror -static -I$(khdr_dir) -I$(LINUX_TOOL_ARCH_INCLUDE) +CFLAGS += -Wall -Werror -static $(KHDR_INCLUDES) -I$(LINUX_TOOL_ARCH_INCLUDE) include ../../../lib.mk diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile index 129880fb42d3..c647fd6a0446 100644 --- a/tools/testing/selftests/filesystems/Makefile +++ b/tools/testing/selftests/filesystems/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := devpts_pts TEST_GEN_PROGS_EXTENDED := dnotify_test diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile index 8af25ae96049..c2f7cef919c0 100644 --- a/tools/testing/selftests/filesystems/binderfs/Makefile +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ -pthread +CFLAGS += $(KHDR_INCLUDES) -pthread TEST_GEN_PROGS := binderfs_test binderfs_test: binderfs_test.c ../../kselftest.h ../../kselftest_harness.h diff --git a/tools/testing/selftests/filesystems/epoll/Makefile b/tools/testing/selftests/filesystems/epoll/Makefile index 78ae4aaf7141..0788a7dc8004 100644 --- a/tools/testing/selftests/filesystems/epoll/Makefile +++ b/tools/testing/selftests/filesystems/epoll/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) LDLIBS += -lpthread TEST_GEN_PROGS := epoll_wakeup_test diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc index fc1daac7f066..4f5e8c665156 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc @@ -22,6 +22,8 @@ check_error 'e:foo/^bar.1 syscalls/sys_enter_openat' # BAD_EVENT_NAME check_error 'e:foo/bar syscalls/sys_enter_openat arg=^dfd' # BAD_FETCH_ARG check_error 'e:foo/bar syscalls/sys_enter_openat ^arg=$foo' # BAD_ATTACH_ARG -check_error 'e:foo/bar syscalls/sys_enter_openat if ^' # NO_EP_FILTER +if grep -q '<attached-group>\.<attached-event>.*\[if <filter>\]' README; then + check_error 'e:foo/bar syscalls/sys_enter_openat if ^' # NO_EP_FILTER +fi exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc new file mode 100644 index 000000000000..e2ff3bf4df80 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -0,0 +1,58 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event filter function - test event filtering on functions +# requires: set_event events/kmem/kmem_cache_free/filter +# flags: instance + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test event filter function name" +echo 0 > tracing_on +echo 0 > events/enable +echo > trace +echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter +echo 1 > events/kmem/kmem_cache_free/enable +echo 1 > tracing_on +ls > /dev/null +echo 0 > events/kmem/kmem_cache_free/enable + +hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` + +if [ $hitcnt -eq 0 ]; then + exit_fail +fi + +if [ $misscnt -gt 0 ]; then + exit_fail +fi + +address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` + +echo "Test event filter function address" +echo 0 > tracing_on +echo 0 > events/enable +echo > trace +echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter +echo 1 > events/kmem/kmem_cache_free/enable +echo 1 > tracing_on +sleep 1 +echo 0 > events/kmem/kmem_cache_free/enable + +hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` + +if [ $hitcnt -eq 0 ]; then + exit_fail +fi + +if [ $misscnt -gt 0 ]; then + exit_fail +fi + +reset_events_filter + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index 3eea2abf68f9..2ad7d4b501cc 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -42,7 +42,7 @@ test_event_enabled() { while [ $check_times -ne 0 ]; do e=`cat $EVENT_ENABLE` - if [ "$e" == $val ]; then + if [ "$e" = $val ]; then return 0 fi sleep $SLEEP_TIME diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc new file mode 100644 index 000000000000..285b4770efad --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc @@ -0,0 +1,47 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Kprobe event char type argument +# requires: kprobe_events + +case `uname -m` in +x86_64) + ARG1=%di +;; +i[3456]86) + ARG1=%ax +;; +aarch64) + ARG1=%x0 +;; +arm*) + ARG1=%r0 +;; +ppc64*) + ARG1=%r3 +;; +ppc*) + ARG1=%r3 +;; +s390*) + ARG1=%r2 +;; +mips*) + ARG1=%r4 +;; +*) + echo "Please implement other architecture here" + exit_untested +esac + +: "Test get argument (1)" +echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char" > kprobe_events +echo 1 > events/kprobes/testprobe/enable +echo "p:test $FUNCTION_FORK" >> kprobe_events +grep -qe "testprobe.* arg1='t'" trace + +echo 0 > events/kprobes/testprobe/enable +: "Test get argument (2)" +echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):char arg2=+0(${ARG1}):char[4]" > kprobe_events +echo 1 > events/kprobes/testprobe/enable +echo "p:test $FUNCTION_FORK" >> kprobe_events +grep -qe "testprobe.* arg1='t' arg2={'t','e','s','t'}" trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 459741565222..a4f8e7c53c1f 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -28,6 +28,9 @@ s390*) mips*) ARG1=%r4 ;; +loongarch*) + ARG1=%r4 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index d4662c8cf407..1df61e13a812 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -40,6 +40,10 @@ mips*) GOODREG=%r4 BADREG=%r12 ;; +loongarch*) + GOODREG=%r4 + BADREG=%r12 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc index 624269c8d534..68425987a5dd 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc @@ -21,7 +21,7 @@ set_offs() { # prev target next # We have to decode symbol addresses to get correct offsets. # If the offset is not an instruction boundary, it cause -EILSEQ. -set_offs `grep -A1 -B1 ${TARGET_FUNC} /proc/kallsyms | cut -f 1 -d " " | xargs` +set_offs `grep -v __pfx_ /proc/kallsyms | grep -A1 -B1 ${TARGET_FUNC} | cut -f 1 -d " " | xargs` UINT_TEST=no # printf "%x" -1 returns (unsigned long)-1. diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc new file mode 100644 index 000000000000..755dbe94ccf4 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + + +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc index 2968cdc7df30..366f1f3ad906 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc @@ -70,6 +70,12 @@ grep "myevent[[:space:]]unsigned long var" synthetic_events echo "myevent char var[10]" > synthetic_events grep "myevent[[:space:]]char\[10\] var" synthetic_events +if grep -q 'long\[\]' README; then + # test stacktrace type + echo "myevent unsigned long[] var" > synthetic_events + grep "myevent[[:space:]]unsigned long\[\] var" synthetic_events +fi + do_reset exit 0 diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 5a0e0df8de9b..a392d0917b4e 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -INCLUDES := -I../include -I../../ -I../../../../../usr/include/ +INCLUDES := -I../include -I../../ $(KHDR_INCLUDES) CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES) LDLIBS := -lpthread -lrt diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 616ed4019655..e0884390447d 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -3,6 +3,6 @@ TEST_PROGS := gpio-mockup.sh gpio-sim.sh TEST_FILES := gpio-mockup-sysfs.sh TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev gpio-chip-info gpio-line-name -CFLAGS += -O2 -g -Wall -I../../../../usr/include/ $(KHDR_INCLUDES) +CFLAGS += -O2 -g -Wall $(KHDR_INCLUDES) include ../lib.mk diff --git a/tools/testing/selftests/hid/.gitignore b/tools/testing/selftests/hid/.gitignore new file mode 100644 index 000000000000..995af0670f69 --- /dev/null +++ b/tools/testing/selftests/hid/.gitignore @@ -0,0 +1,5 @@ +bpftool +*.skel.h +/tools +hid_bpf +results diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile new file mode 100644 index 000000000000..83e8f87d643a --- /dev/null +++ b/tools/testing/selftests/hid/Makefile @@ -0,0 +1,231 @@ +# SPDX-License-Identifier: GPL-2.0 + +# based on tools/testing/selftest/bpf/Makefile +include ../../../build/Build.include +include ../../../scripts/Makefile.arch +include ../../../scripts/Makefile.include + +CXX ?= $(CROSS_COMPILE)g++ + +HOSTPKG_CONFIG := pkg-config + +CFLAGS += -g -O0 -rdynamic -Wall -Werror -I$(KHDR_INCLUDES) -I$(OUTPUT) +LDLIBS += -lelf -lz -lrt -lpthread + +# Silence some warnings when compiled with clang +ifneq ($(LLVM),) +CFLAGS += -Wno-unused-command-line-argument +endif + +# Order correspond to 'make run_tests' order +TEST_GEN_PROGS = hid_bpf + +# Emit succinct information message describing current building step +# $1 - generic step name (e.g., CC, LINK, etc); +# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor]; +# $3 - target (assumed to be file); only file name will be emitted; +# $4 - optional extra arg, emitted as-is, if provided. +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +override define CLEAN + $(call msg,CLEAN) + $(Q)$(RM) -r $(TEST_GEN_PROGS) + $(Q)$(RM) -r $(EXTRA_CLEAN) +endef + +include ../lib.mk + +TOOLSDIR := $(top_srcdir)/tools +LIBDIR := $(TOOLSDIR)/lib +BPFDIR := $(LIBDIR)/bpf +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +INCLUDE_DIR := $(SCRATCH_DIR)/include +KHDR_INCLUDES := $(SCRATCH_DIR)/uapi/include +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a +ifneq ($(CROSS_COMPILE),) +HOST_BUILD_DIR := $(BUILD_DIR)/host +HOST_SCRATCH_DIR := $(OUTPUT)/host-tools +HOST_INCLUDE_DIR := $(HOST_SCRATCH_DIR)/include +else +HOST_BUILD_DIR := $(BUILD_DIR) +HOST_SCRATCH_DIR := $(SCRATCH_DIR) +HOST_INCLUDE_DIR := $(INCLUDE_DIR) +endif +HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a +RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +ifeq ($(VMLINUX_BTF),) +$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") +endif + +# Define simple and short `make test_progs`, `make test_sysctl`, etc targets +# to build individual tests. +# NOTE: Semicolon at the end is critical to override lib.mk's default static +# rule for binaries. +$(notdir $(TEST_GEN_PROGS)): %: $(OUTPUT)/% ; + +# sort removes libbpf duplicates when not cross-building +MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \ + $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids \ + $(INCLUDE_DIR)) +$(MAKE_DIRS): + $(call msg,MKDIR,,$@) + $(Q)mkdir -p $@ + +# LLVM's ld.lld doesn't support all the architectures, so use it only on x86 +ifeq ($(SRCARCH),x86) +LLD := lld +else +LLD := ld +endif + +DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool + +TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) + +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) + +BPFTOOL ?= $(DEFAULT_BPFTOOL) +$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ + $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ + EXTRA_CFLAGS='-g -O0' \ + OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ + LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ + LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \ + prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + | $(BUILD_DIR)/libbpf + $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +ifneq ($(BPFOBJ),$(HOST_BPFOBJ)) +$(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + | $(HOST_BUILD_DIR)/libbpf + $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \ + EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \ + OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \ + DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers +endif + +$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) +ifeq ($(VMLINUX_H),) + $(call msg,GEN,,$@) + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ +else + $(call msg,CP,,$@) + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(KHDR_INCLUDES)/linux/hid.h: $(top_srcdir)/include/uapi/linux/hid.h + $(MAKE) -C $(top_srcdir) INSTALL_HDR_PATH=$(SCRATCH_DIR)/uapi headers_install + +$(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ + $(TOOLSDIR)/bpf/resolve_btfids/main.c \ + $(TOOLSDIR)/lib/rbtree.c \ + $(TOOLSDIR)/lib/zalloc.c \ + $(TOOLSDIR)/lib/string.c \ + $(TOOLSDIR)/lib/ctype.c \ + $(TOOLSDIR)/lib/str_error_r.c + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ + CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \ + LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ + OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +# Determine target endianness. +IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ + grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__') +MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) +BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ + -I$(INCLUDE_DIR) + +CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ + -Wno-compare-distinct-pointer-types + +# Build BPF object using Clang +# $1 - input .c file +# $2 - output .o file +# $3 - CFLAGS +define CLANG_BPF_BUILD_RULE + $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) + $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2 +endef +# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 +define CLANG_NOALU32_BPF_BUILD_RULE + $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) + $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2 +endef +# Build BPF object using GCC +define GCC_BPF_BUILD_RULE + $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) + $(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2 +endef + +BPF_PROGS_DIR := progs +BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE +BPF_SRCS := $(notdir $(wildcard $(BPF_PROGS_DIR)/*.c)) +BPF_OBJS := $(patsubst %.c,$(OUTPUT)/%.bpf.o, $(BPF_SRCS)) +BPF_SKELS := $(patsubst %.c,$(OUTPUT)/%.skel.h, $(BPF_SRCS)) +TEST_GEN_FILES += $(BPF_OBJS) + +$(BPF_PROGS_DIR)-bpfobjs := y +$(BPF_OBJS): $(OUTPUT)/%.bpf.o: \ + $(BPF_PROGS_DIR)/%.c \ + $(wildcard $(BPF_PROGS_DIR)/*.h) \ + $(INCLUDE_DIR)/vmlinux.h \ + $(wildcard $(BPFDIR)/hid_bpf_*.h) \ + $(wildcard $(BPFDIR)/*.bpf.h) \ + | $(OUTPUT) $(BPFOBJ) + $(call $(BPF_BUILD_RULE),$<,$@, $(BPF_CFLAGS)) + +$(BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(OUTPUT) + $(call msg,GEN-SKEL,$(BINARY),$@) + $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $< + $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked1.o) name $(notdir $(<:.bpf.o=)) > $@ + +$(OUTPUT)/%.o: %.c $(BPF_SKELS) $(KHDR_INCLUDES)/linux/hid.h + $(call msg,CC,,$@) + $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ + +$(OUTPUT)/%: $(OUTPUT)/%.o + $(call msg,BINARY,,$@) + $(Q)$(LINK.c) $^ $(LDLIBS) -o $@ + +EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) feature bpftool \ + $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32) diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config new file mode 100644 index 000000000000..9c5a55abca6b --- /dev/null +++ b/tools/testing/selftests/hid/config @@ -0,0 +1,21 @@ +CONFIG_BPF_EVENTS=y +CONFIG_BPFILTER=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_JIT=y +CONFIG_BPF_KPROBE_OVERRIDE=y +CONFIG_BPF_LSM=y +CONFIG_BPF_PRELOAD_UMD=y +CONFIG_BPF_PRELOAD=y +CONFIG_BPF_STREAM_PARSER=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF=y +CONFIG_CGROUP_BPF=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS=y +CONFIG_FPROBE=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_FUNCTION_TRACER=y +CONFIG_HIDRAW=y +CONFIG_HID=y +CONFIG_INPUT_EVDEV=y +CONFIG_UHID=y diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common new file mode 100644 index 000000000000..0617275d93cc --- /dev/null +++ b/tools/testing/selftests/hid/config.common @@ -0,0 +1,241 @@ +CONFIG_9P_FS_POSIX_ACL=y +CONFIG_9P_FS_SECURITY=y +CONFIG_9P_FS=y +CONFIG_AUDIT=y +CONFIG_BINFMT_MISC=y +CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP=y +CONFIG_BLK_DEV_BSGLIB=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BLK_DEV_RAM_SIZE=16384 +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_BONDING=y +CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y +CONFIG_BOOTTIME_TRACING=y +CONFIG_BSD_DISKLABEL=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CGROUP_NET_CLASSID=y +CONFIG_CGROUP_NET_PRIO=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_WRITEBACK=y +CONFIG_CMA_AREAS=7 +CONFIG_CMA=y +CONFIG_COMPAT_32BIT_TIME=y +CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_IDLE_GOV_LADDER=y +CONFIG_CPUSETS=y +CONFIG_CRC_T10DIF=y +CONFIG_CRYPTO_BLAKE2B=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_CRYPTO_SEQIV=y +CONFIG_CRYPTO_XXHASH=y +CONFIG_DCB=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_CREDENTIALS=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEFAULT_FQ_CODEL=y +CONFIG_DEFAULT_RENO=y +CONFIG_DEFAULT_SECURITY_DAC=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DEVTMPFS=y +CONFIG_DMA_CMA=y +CONFIG_DNS_RESOLVER=y +CONFIG_EFI_STUB=y +CONFIG_EFI=y +CONFIG_EXPERT=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_FAIL_FUNCTION=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAULT_INJECTION=y +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_VESA=y +CONFIG_FB=y +CONFIG_FONT_8x16=y +CONFIG_FONT_MINI_4x6=y +CONFIG_FONTS=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FUSE_FS=y +CONFIG_FW_LOADER_USER_HELPER=y +CONFIG_GART_IOMMU=y +CONFIG_GENERIC_PHY=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_HPET=y +CONFIG_HUGETLBFS=y +CONFIG_HUGETLB_PAGE=y +CONFIG_HWPOISON_INJECT=y +CONFIG_HZ_1000=y +CONFIG_INET=y +CONFIG_INTEL_POWERCLAMP=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_NAT=y +CONFIG_IP6_NF_TARGET_MASQUERADE=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_IPV6_SUBTREES=y +CONFIG_IRQ_POLL=y +CONFIG_JUMP_LABEL=y +CONFIG_KARMA_PARTITION=y +CONFIG_KEXEC=y +CONFIG_KPROBES=y +CONFIG_KSM=y +CONFIG_LEGACY_VSYSCALL_NONE=y +CONFIG_LOG_BUF_SHIFT=21 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=0 +CONFIG_LOGO=y +CONFIG_LSM="selinux,bpf,integrity" +CONFIG_MAC_PARTITION=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_MCORE2=y +CONFIG_MEMCG=y +CONFIG_MEMORY_FAILURE=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_MODULES=y +CONFIG_NAMESPACES=y +CONFIG_NET_9P_VIRTIO=y +CONFIG_NET_9P=y +CONFIG_NET_ACT_BPF=y +CONFIG_NET_CLS_CGROUP=y +CONFIG_NETDEVICES=y +CONFIG_NET_EMATCH=y +CONFIG_NETFILTER_NETLINK_LOG=y +CONFIG_NETFILTER_NETLINK_QUEUE=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=y +CONFIG_NETFILTER_XT_MATCH_BPF=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_NAT=y +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=y +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NETLABEL=y +CONFIG_NET_SCH_DEFAULT=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_FQ_CODEL=y +CONFIG_NET_TC_SKB_EXT=y +CONFIG_NET_VRF=y +CONFIG_NET=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_NAT_MASQUERADE=y +CONFIG_NF_NAT=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NO_HZ=y +CONFIG_NR_CPUS=128 +CONFIG_NUMA_BALANCING=y +CONFIG_NUMA=y +CONFIG_NVMEM=y +CONFIG_OSF_PARTITION=y +CONFIG_OVERLAY_FS_INDEX=y +CONFIG_OVERLAY_FS_METACOPY=y +CONFIG_OVERLAY_FS_XINO_AUTO=y +CONFIG_OVERLAY_FS=y +CONFIG_PACKET=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_IOV=y +CONFIG_PCI_MSI=y +CONFIG_PCI=y +CONFIG_PHYSICAL_ALIGN=0x1000000 +CONFIG_POSIX_MQUEUE=y +CONFIG_POWER_SUPPLY=y +CONFIG_PREEMPT=y +CONFIG_PRINTK_TIME=y +CONFIG_PROC_KCORE=y +CONFIG_PROFILING=y +CONFIG_PROVE_LOCKING=y +CONFIG_PTP_1588_CLOCK=y +CONFIG_RC_DEVICES=y +CONFIG_RC_LOOPBACK=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_SCHEDSTATS=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DETECT_IRQ=y +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_NR_UARTS=32 +CONFIG_SERIAL_8250_RSA=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_NONSTANDARD=y +CONFIG_SERIO_LIBPS2=y +CONFIG_SGI_PARTITION=y +CONFIG_SMP=y +CONFIG_SOCK_CGROUP_DATA=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_SYNC_FILE=y +CONFIG_SYSVIPC=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_TASKSTATS=y +CONFIG_TASK_XACCT=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_MD5SIG=y +CONFIG_TLS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS=y +CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_TUN=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_UNIX=y +CONFIG_USER_NS=y +CONFIG_VALIDATE_FS_PARSER=y +CONFIG_VETH=y +CONFIG_VIRT_DRIVERS=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_FS=y +CONFIG_VIRTIO_NET=y +CONFIG_VIRTIO_PCI=y +CONFIG_VLAN_8021Q=y +CONFIG_XFRM_SUB_POLICY=y +CONFIG_XFRM_USER=y +CONFIG_ZEROPLUS_FF=y diff --git a/tools/testing/selftests/hid/config.x86_64 b/tools/testing/selftests/hid/config.x86_64 new file mode 100644 index 000000000000..a8721f403c21 --- /dev/null +++ b/tools/testing/selftests/hid/config.x86_64 @@ -0,0 +1,4 @@ +CONFIG_X86_ACPI_CPUFREQ=y +CONFIG_X86_CPUID=y +CONFIG_X86_MSR=y +CONFIG_X86_POWERNOW_K8=y diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c new file mode 100644 index 000000000000..2cf96f818f25 --- /dev/null +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -0,0 +1,869 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Red Hat */ +#include "hid.skel.h" + +#include "../kselftest_harness.h" + +#include <bpf/bpf.h> +#include <fcntl.h> +#include <fnmatch.h> +#include <dirent.h> +#include <poll.h> +#include <pthread.h> +#include <stdbool.h> +#include <linux/hidraw.h> +#include <linux/uhid.h> + +#define SHOW_UHID_DEBUG 0 + +static unsigned char rdesc[] = { + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x09, 0x21, /* Usage (Vendor Usage 0x21) */ + 0xa1, 0x01, /* COLLECTION (Application) */ + 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ + 0xa1, 0x00, /* COLLECTION (Physical) */ + 0x85, 0x02, /* REPORT_ID (2) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x08, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0xff, /* LOGICAL_MAXIMUM (255) */ + 0x95, 0x08, /* REPORT_COUNT (8) */ + 0x75, 0x08, /* REPORT_SIZE (8) */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ + 0xc0, /* END_COLLECTION */ + 0x09, 0x01, /* Usage (Vendor Usage 0x01) */ + 0xa1, 0x00, /* COLLECTION (Physical) */ + 0x85, 0x01, /* REPORT_ID (1) */ + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x03, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x81, 0x01, /* INPUT (Cnst,Var,Abs) */ + 0x05, 0x01, /* USAGE_PAGE (Generic Desktop) */ + 0x09, 0x30, /* USAGE (X) */ + 0x09, 0x31, /* USAGE (Y) */ + 0x15, 0x81, /* LOGICAL_MINIMUM (-127) */ + 0x25, 0x7f, /* LOGICAL_MAXIMUM (127) */ + 0x75, 0x10, /* REPORT_SIZE (16) */ + 0x95, 0x02, /* REPORT_COUNT (2) */ + 0x81, 0x06, /* INPUT (Data,Var,Rel) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x03, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x91, 0x02, /* Output (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x06, /* USAGE_MINIMUM (6) */ + 0x29, 0x08, /* USAGE_MAXIMUM (8) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0xb1, 0x02, /* Feature (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0xc0, /* END_COLLECTION */ + 0xc0, /* END_COLLECTION */ +}; + +static __u8 feature_data[] = { 1, 2 }; + +struct attach_prog_args { + int prog_fd; + unsigned int hid; + int retval; + int insert_head; +}; + +struct hid_hw_request_syscall_args { + __u8 data[10]; + unsigned int hid; + int retval; + size_t size; + enum hid_report_type type; + __u8 request_type; +}; + +#define ASSERT_OK(data) ASSERT_FALSE(data) +#define ASSERT_OK_PTR(ptr) ASSERT_NE(NULL, ptr) + +#define UHID_LOG(fmt, ...) do { \ + if (SHOW_UHID_DEBUG) \ + TH_LOG(fmt, ##__VA_ARGS__); \ +} while (0) + +static pthread_mutex_t uhid_started_mtx = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t uhid_started = PTHREAD_COND_INITIALIZER; + +/* no need to protect uhid_stopped, only one thread accesses it */ +static bool uhid_stopped; + +static int uhid_write(struct __test_metadata *_metadata, int fd, const struct uhid_event *ev) +{ + ssize_t ret; + + ret = write(fd, ev, sizeof(*ev)); + if (ret < 0) { + TH_LOG("Cannot write to uhid: %m"); + return -errno; + } else if (ret != sizeof(*ev)) { + TH_LOG("Wrong size written to uhid: %zd != %zu", + ret, sizeof(ev)); + return -EFAULT; + } else { + return 0; + } +} + +static int uhid_create(struct __test_metadata *_metadata, int fd, int rand_nb) +{ + struct uhid_event ev; + char buf[25]; + + sprintf(buf, "test-uhid-device-%d", rand_nb); + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_CREATE; + strcpy((char *)ev.u.create.name, buf); + ev.u.create.rd_data = rdesc; + ev.u.create.rd_size = sizeof(rdesc); + ev.u.create.bus = BUS_USB; + ev.u.create.vendor = 0x0001; + ev.u.create.product = 0x0a37; + ev.u.create.version = 0; + ev.u.create.country = 0; + + sprintf(buf, "%d", rand_nb); + strcpy((char *)ev.u.create.phys, buf); + + return uhid_write(_metadata, fd, &ev); +} + +static void uhid_destroy(struct __test_metadata *_metadata, int fd) +{ + struct uhid_event ev; + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_DESTROY; + + uhid_write(_metadata, fd, &ev); +} + +static int uhid_event(struct __test_metadata *_metadata, int fd) +{ + struct uhid_event ev, answer; + ssize_t ret; + + memset(&ev, 0, sizeof(ev)); + ret = read(fd, &ev, sizeof(ev)); + if (ret == 0) { + UHID_LOG("Read HUP on uhid-cdev"); + return -EFAULT; + } else if (ret < 0) { + UHID_LOG("Cannot read uhid-cdev: %m"); + return -errno; + } else if (ret != sizeof(ev)) { + UHID_LOG("Invalid size read from uhid-dev: %zd != %zu", + ret, sizeof(ev)); + return -EFAULT; + } + + switch (ev.type) { + case UHID_START: + pthread_mutex_lock(&uhid_started_mtx); + pthread_cond_signal(&uhid_started); + pthread_mutex_unlock(&uhid_started_mtx); + + UHID_LOG("UHID_START from uhid-dev"); + break; + case UHID_STOP: + uhid_stopped = true; + + UHID_LOG("UHID_STOP from uhid-dev"); + break; + case UHID_OPEN: + UHID_LOG("UHID_OPEN from uhid-dev"); + break; + case UHID_CLOSE: + UHID_LOG("UHID_CLOSE from uhid-dev"); + break; + case UHID_OUTPUT: + UHID_LOG("UHID_OUTPUT from uhid-dev"); + break; + case UHID_GET_REPORT: + UHID_LOG("UHID_GET_REPORT from uhid-dev"); + + answer.type = UHID_GET_REPORT_REPLY; + answer.u.get_report_reply.id = ev.u.get_report.id; + answer.u.get_report_reply.err = ev.u.get_report.rnum == 1 ? 0 : -EIO; + answer.u.get_report_reply.size = sizeof(feature_data); + memcpy(answer.u.get_report_reply.data, feature_data, sizeof(feature_data)); + + uhid_write(_metadata, fd, &answer); + + break; + case UHID_SET_REPORT: + UHID_LOG("UHID_SET_REPORT from uhid-dev"); + break; + default: + TH_LOG("Invalid event from uhid-dev: %u", ev.type); + } + + return 0; +} + +struct uhid_thread_args { + int fd; + struct __test_metadata *_metadata; +}; +static void *uhid_read_events_thread(void *arg) +{ + struct uhid_thread_args *args = (struct uhid_thread_args *)arg; + struct __test_metadata *_metadata = args->_metadata; + struct pollfd pfds[1]; + int fd = args->fd; + int ret = 0; + + pfds[0].fd = fd; + pfds[0].events = POLLIN; + + uhid_stopped = false; + + while (!uhid_stopped) { + ret = poll(pfds, 1, 100); + if (ret < 0) { + TH_LOG("Cannot poll for fds: %m"); + break; + } + if (pfds[0].revents & POLLIN) { + ret = uhid_event(_metadata, fd); + if (ret) + break; + } + } + + return (void *)(long)ret; +} + +static int uhid_start_listener(struct __test_metadata *_metadata, pthread_t *tid, int uhid_fd) +{ + struct uhid_thread_args args = { + .fd = uhid_fd, + ._metadata = _metadata, + }; + int err; + + pthread_mutex_lock(&uhid_started_mtx); + err = pthread_create(tid, NULL, uhid_read_events_thread, (void *)&args); + ASSERT_EQ(0, err) { + TH_LOG("Could not start the uhid thread: %d", err); + pthread_mutex_unlock(&uhid_started_mtx); + close(uhid_fd); + return -EIO; + } + pthread_cond_wait(&uhid_started, &uhid_started_mtx); + pthread_mutex_unlock(&uhid_started_mtx); + + return 0; +} + +static int uhid_send_event(struct __test_metadata *_metadata, int fd, __u8 *buf, size_t size) +{ + struct uhid_event ev; + + if (size > sizeof(ev.u.input.data)) + return -E2BIG; + + memset(&ev, 0, sizeof(ev)); + ev.type = UHID_INPUT2; + ev.u.input2.size = size; + + memcpy(ev.u.input2.data, buf, size); + + return uhid_write(_metadata, fd, &ev); +} + +static int setup_uhid(struct __test_metadata *_metadata, int rand_nb) +{ + int fd; + const char *path = "/dev/uhid"; + int ret; + + fd = open(path, O_RDWR | O_CLOEXEC); + ASSERT_GE(fd, 0) TH_LOG("open uhid-cdev failed; %d", fd); + + ret = uhid_create(_metadata, fd, rand_nb); + ASSERT_EQ(0, ret) { + TH_LOG("create uhid device failed: %d", ret); + close(fd); + } + + return fd; +} + +static bool match_sysfs_device(int dev_id, const char *workdir, struct dirent *dir) +{ + const char *target = "0003:0001:0A37.*"; + char phys[512]; + char uevent[1024]; + char temp[512]; + int fd, nread; + bool found = false; + + if (fnmatch(target, dir->d_name, 0)) + return false; + + /* we found the correct VID/PID, now check for phys */ + sprintf(uevent, "%s/%s/uevent", workdir, dir->d_name); + + fd = open(uevent, O_RDONLY | O_NONBLOCK); + if (fd < 0) + return false; + + sprintf(phys, "PHYS=%d", dev_id); + + nread = read(fd, temp, ARRAY_SIZE(temp)); + if (nread > 0 && (strstr(temp, phys)) != NULL) + found = true; + + close(fd); + + return found; +} + +static int get_hid_id(int dev_id) +{ + const char *workdir = "/sys/devices/virtual/misc/uhid"; + const char *str_id; + DIR *d; + struct dirent *dir; + int found = -1, attempts = 3; + + /* it would be nice to be able to use nftw, but the no_alu32 target doesn't support it */ + + while (found < 0 && attempts > 0) { + attempts--; + d = opendir(workdir); + if (d) { + while ((dir = readdir(d)) != NULL) { + if (!match_sysfs_device(dev_id, workdir, dir)) + continue; + + str_id = dir->d_name + sizeof("0003:0001:0A37."); + found = (int)strtol(str_id, NULL, 16); + + break; + } + closedir(d); + } + if (found < 0) + usleep(100000); + } + + return found; +} + +static int get_hidraw(int dev_id) +{ + const char *workdir = "/sys/devices/virtual/misc/uhid"; + char sysfs[1024]; + DIR *d, *subd; + struct dirent *dir, *subdir; + int i, found = -1; + + /* retry 5 times in case the system is loaded */ + for (i = 5; i > 0; i--) { + usleep(10); + d = opendir(workdir); + + if (!d) + continue; + + while ((dir = readdir(d)) != NULL) { + if (!match_sysfs_device(dev_id, workdir, dir)) + continue; + + sprintf(sysfs, "%s/%s/hidraw", workdir, dir->d_name); + + subd = opendir(sysfs); + if (!subd) + continue; + + while ((subdir = readdir(subd)) != NULL) { + if (fnmatch("hidraw*", subdir->d_name, 0)) + continue; + + found = atoi(subdir->d_name + strlen("hidraw")); + } + + closedir(subd); + + if (found > 0) + break; + } + closedir(d); + } + + return found; +} + +static int open_hidraw(int dev_id) +{ + int hidraw_number; + char hidraw_path[64] = { 0 }; + + hidraw_number = get_hidraw(dev_id); + if (hidraw_number < 0) + return hidraw_number; + + /* open hidraw node to check the other side of the pipe */ + sprintf(hidraw_path, "/dev/hidraw%d", hidraw_number); + return open(hidraw_path, O_RDWR | O_NONBLOCK); +} + +FIXTURE(hid_bpf) { + int dev_id; + int uhid_fd; + int hidraw_fd; + int hid_id; + pthread_t tid; + struct hid *skel; + int hid_links[3]; /* max number of programs loaded in a single test */ +}; +static void detach_bpf(FIXTURE_DATA(hid_bpf) * self) +{ + int i; + + if (self->hidraw_fd) + close(self->hidraw_fd); + self->hidraw_fd = 0; + + for (i = 0; i < ARRAY_SIZE(self->hid_links); i++) { + if (self->hid_links[i]) + close(self->hid_links[i]); + } + + hid__destroy(self->skel); + self->skel = NULL; +} + +FIXTURE_TEARDOWN(hid_bpf) { + void *uhid_err; + + uhid_destroy(_metadata, self->uhid_fd); + + detach_bpf(self); + pthread_join(self->tid, &uhid_err); +} +#define TEARDOWN_LOG(fmt, ...) do { \ + TH_LOG(fmt, ##__VA_ARGS__); \ + hid_bpf_teardown(_metadata, self, variant); \ +} while (0) + +FIXTURE_SETUP(hid_bpf) +{ + time_t t; + int err; + + /* initialize random number generator */ + srand((unsigned int)time(&t)); + + self->dev_id = rand() % 1024; + + self->uhid_fd = setup_uhid(_metadata, self->dev_id); + + /* locate the uev, self, variant);ent file of the created device */ + self->hid_id = get_hid_id(self->dev_id); + ASSERT_GT(self->hid_id, 0) + TEARDOWN_LOG("Could not locate uhid device id: %d", self->hid_id); + + err = uhid_start_listener(_metadata, &self->tid, self->uhid_fd); + ASSERT_EQ(0, err) TEARDOWN_LOG("could not start udev listener: %d", err); +} + +struct test_program { + const char *name; + int insert_head; +}; +#define LOAD_PROGRAMS(progs) \ + load_programs(progs, ARRAY_SIZE(progs), _metadata, self, variant) +#define LOAD_BPF \ + load_programs(NULL, 0, _metadata, self, variant) +static void load_programs(const struct test_program programs[], + const size_t progs_count, + struct __test_metadata *_metadata, + FIXTURE_DATA(hid_bpf) * self, + const FIXTURE_VARIANT(hid_bpf) * variant) +{ + int attach_fd, err = -EINVAL; + struct attach_prog_args args = { + .retval = -1, + }; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, tattr, + .ctx_in = &args, + .ctx_size_in = sizeof(args), + ); + + ASSERT_LE(progs_count, ARRAY_SIZE(self->hid_links)) + TH_LOG("too many programs are to be loaded"); + + /* open the bpf file */ + self->skel = hid__open(); + ASSERT_OK_PTR(self->skel) TEARDOWN_LOG("Error while calling hid__open"); + + for (int i = 0; i < progs_count; i++) { + struct bpf_program *prog; + + prog = bpf_object__find_program_by_name(*self->skel->skeleton->obj, + programs[i].name); + ASSERT_OK_PTR(prog) TH_LOG("can not find program by name '%s'", programs[i].name); + + bpf_program__set_autoload(prog, true); + } + + err = hid__load(self->skel); + ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); + + attach_fd = bpf_program__fd(self->skel->progs.attach_prog); + ASSERT_GE(attach_fd, 0) TH_LOG("locate attach_prog: %d", attach_fd); + + for (int i = 0; i < progs_count; i++) { + struct bpf_program *prog; + + prog = bpf_object__find_program_by_name(*self->skel->skeleton->obj, + programs[i].name); + ASSERT_OK_PTR(prog) TH_LOG("can not find program by name '%s'", programs[i].name); + + args.prog_fd = bpf_program__fd(prog); + args.hid = self->hid_id; + args.insert_head = programs[i].insert_head; + err = bpf_prog_test_run_opts(attach_fd, &tattr); + ASSERT_GE(args.retval, 0) + TH_LOG("attach_hid(%s): %d", programs[i].name, args.retval); + + self->hid_links[i] = args.retval; + } + + self->hidraw_fd = open_hidraw(self->dev_id); + ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw"); +} + +/* + * A simple test to see if the fixture is working fine. + * If this fails, none of the other tests will pass. + */ +TEST_F(hid_bpf, test_create_uhid) +{ +} + +/* + * Attach hid_first_event to the given uhid device, + * retrieve and open the matching hidraw node, + * inject one event in the uhid device, + * check that the program sees it and can change the data + */ +TEST_F(hid_bpf, raw_event) +{ + const struct test_program progs[] = { + { .name = "hid_first_event" }, + }; + __u8 buf[10] = {0}; + int err; + + LOAD_PROGRAMS(progs); + + /* check that the program is correctly loaded */ + ASSERT_EQ(self->skel->data->callback_check, 52) TH_LOG("callback_check1"); + ASSERT_EQ(self->skel->data->callback2_check, 52) TH_LOG("callback2_check1"); + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* check that hid_first_event() was executed */ + ASSERT_EQ(self->skel->data->callback_check, 42) TH_LOG("callback_check1"); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[2], 47); + + /* inject another event */ + memset(buf, 0, sizeof(buf)); + buf[0] = 1; + buf[1] = 47; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* check that hid_first_event() was executed */ + ASSERT_EQ(self->skel->data->callback_check, 47) TH_LOG("callback_check1"); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[2], 52); +} + +/* + * Ensures that we can attach/detach programs + */ +TEST_F(hid_bpf, test_attach_detach) +{ + const struct test_program progs[] = { + { .name = "hid_first_event" }, + { .name = "hid_second_event" }, + }; + __u8 buf[10] = {0}; + int err, link; + + LOAD_PROGRAMS(progs); + + link = self->hid_links[0]; + ASSERT_GT(link, 0) TH_LOG("HID-BPF link not created"); + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[2], 47); + + /* make sure both programs are run */ + ASSERT_EQ(buf[3], 52); + + /* pin the first program and immediately unpin it */ +#define PIN_PATH "/sys/fs/bpf/hid_first_event" + err = bpf_obj_pin(link, PIN_PATH); + ASSERT_OK(err) TH_LOG("error while calling bpf_obj_pin"); + remove(PIN_PATH); +#undef PIN_PATH + usleep(100000); + + /* detach the program */ + detach_bpf(self); + + self->hidraw_fd = open_hidraw(self->dev_id); + ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw"); + + /* inject another event */ + memset(buf, 0, sizeof(buf)); + buf[0] = 1; + buf[1] = 47; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw_no_bpf"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[1], 47); + ASSERT_EQ(buf[2], 0); + ASSERT_EQ(buf[3], 0); + + /* re-attach our program */ + + LOAD_PROGRAMS(progs); + + /* inject one event */ + memset(buf, 0, sizeof(buf)); + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 1); + ASSERT_EQ(buf[2], 47); + ASSERT_EQ(buf[3], 52); +} + +/* + * Attach hid_change_report_id to the given uhid device, + * retrieve and open the matching hidraw node, + * inject one event in the uhid device, + * check that the program sees it and can change the data + */ +TEST_F(hid_bpf, test_hid_change_report) +{ + const struct test_program progs[] = { + { .name = "hid_change_report_id" }, + }; + __u8 buf[10] = {0}; + int err; + + LOAD_PROGRAMS(progs); + + /* inject one event */ + buf[0] = 1; + buf[1] = 42; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 9) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[0], 2); + ASSERT_EQ(buf[1], 42); + ASSERT_EQ(buf[2], 0) TH_LOG("leftovers_from_previous_test"); +} + +/* + * Attach hid_user_raw_request to the given uhid device, + * call the bpf program from userspace + * check that the program is called and does the expected. + */ +TEST_F(hid_bpf, test_hid_user_raw_request_call) +{ + struct hid_hw_request_syscall_args args = { + .retval = -1, + .type = HID_FEATURE_REPORT, + .request_type = HID_REQ_GET_REPORT, + .size = 10, + }; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, tattrs, + .ctx_in = &args, + .ctx_size_in = sizeof(args), + ); + int err, prog_fd; + + LOAD_BPF; + + args.hid = self->hid_id; + args.data[0] = 1; /* report ID */ + + prog_fd = bpf_program__fd(self->skel->progs.hid_user_raw_request); + + err = bpf_prog_test_run_opts(prog_fd, &tattrs); + ASSERT_OK(err) TH_LOG("error while calling bpf_prog_test_run_opts"); + + ASSERT_EQ(args.retval, 2); + + ASSERT_EQ(args.data[1], 2); +} + +/* + * Attach hid_insert{0,1,2} to the given uhid device, + * retrieve and open the matching hidraw node, + * inject one event in the uhid device, + * check that the programs have been inserted in the correct order. + */ +TEST_F(hid_bpf, test_hid_attach_flags) +{ + const struct test_program progs[] = { + { + .name = "hid_test_insert2", + .insert_head = 0, + }, + { + .name = "hid_test_insert1", + .insert_head = 1, + }, + { + .name = "hid_test_insert3", + .insert_head = 0, + }, + }; + __u8 buf[10] = {0}; + int err; + + LOAD_PROGRAMS(progs); + + /* inject one event */ + buf[0] = 1; + uhid_send_event(_metadata, self->uhid_fd, buf, 6); + + /* read the data from hidraw */ + memset(buf, 0, sizeof(buf)); + err = read(self->hidraw_fd, buf, sizeof(buf)); + ASSERT_EQ(err, 6) TH_LOG("read_hidraw"); + ASSERT_EQ(buf[1], 1); + ASSERT_EQ(buf[2], 2); + ASSERT_EQ(buf[3], 3); +} + +/* + * Attach hid_rdesc_fixup to the given uhid device, + * retrieve and open the matching hidraw node, + * check that the hidraw report descriptor has been updated. + */ +TEST_F(hid_bpf, test_rdesc_fixup) +{ + struct hidraw_report_descriptor rpt_desc = {0}; + const struct test_program progs[] = { + { .name = "hid_rdesc_fixup" }, + }; + int err, desc_size; + + LOAD_PROGRAMS(progs); + + /* check that hid_rdesc_fixup() was executed */ + ASSERT_EQ(self->skel->data->callback2_check, 0x21); + + /* read the exposed report descriptor from hidraw */ + err = ioctl(self->hidraw_fd, HIDIOCGRDESCSIZE, &desc_size); + ASSERT_GE(err, 0) TH_LOG("error while reading HIDIOCGRDESCSIZE: %d", err); + + /* ensure the new size of the rdesc is bigger than the old one */ + ASSERT_GT(desc_size, sizeof(rdesc)); + + rpt_desc.size = desc_size; + err = ioctl(self->hidraw_fd, HIDIOCGRDESC, &rpt_desc); + ASSERT_GE(err, 0) TH_LOG("error while reading HIDIOCGRDESC: %d", err); + + ASSERT_EQ(rpt_desc.value[4], 0x42); +} + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + char buf[1024]; + + if (level == LIBBPF_DEBUG) + return 0; + + snprintf(buf, sizeof(buf), "# %s", format); + + vfprintf(stdout, buf, args); + return 0; +} + +static void __attribute__((constructor)) __constructor_order_last(void) +{ + if (!__constructor_order) + __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; +} + +int main(int argc, char **argv) +{ + /* Use libbpf 1.0 API mode */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + libbpf_set_print(libbpf_print_fn); + + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c new file mode 100644 index 000000000000..88c593f753b5 --- /dev/null +++ b/tools/testing/selftests/hid/progs/hid.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Red hat */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "hid_bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +struct attach_prog_args { + int prog_fd; + unsigned int hid; + int retval; + int insert_head; +}; + +__u64 callback_check = 52; +__u64 callback2_check = 52; + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_first_event, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *rw_data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 3 /* size */); + + if (!rw_data) + return 0; /* EPERM check */ + + callback_check = rw_data[1]; + + rw_data[2] = rw_data[1] + 5; + + return hid_ctx->size; +} + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_second_event, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *rw_data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 4 /* size */); + + if (!rw_data) + return 0; /* EPERM check */ + + rw_data[3] = rw_data[2] + 5; + + return hid_ctx->size; +} + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_change_report_id, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *rw_data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 3 /* size */); + + if (!rw_data) + return 0; /* EPERM check */ + + rw_data[0] = 2; + + return 9; +} + +SEC("syscall") +int attach_prog(struct attach_prog_args *ctx) +{ + ctx->retval = hid_bpf_attach_prog(ctx->hid, + ctx->prog_fd, + ctx->insert_head ? HID_BPF_FLAG_INSERT_HEAD : + HID_BPF_FLAG_NONE); + return 0; +} + +struct hid_hw_request_syscall_args { + /* data needs to come at offset 0 so we can use it in calls */ + __u8 data[10]; + unsigned int hid; + int retval; + size_t size; + enum hid_report_type type; + __u8 request_type; +}; + +SEC("syscall") +int hid_user_raw_request(struct hid_hw_request_syscall_args *args) +{ + struct hid_bpf_ctx *ctx; + const size_t size = args->size; + int i, ret = 0; + + if (size > sizeof(args->data)) + return -7; /* -E2BIG */ + + ctx = hid_bpf_allocate_context(args->hid); + if (!ctx) + return -1; /* EPERM check */ + + ret = hid_bpf_hw_request(ctx, + args->data, + size, + args->type, + args->request_type); + args->retval = ret; + + hid_bpf_release_context(ctx); + + return 0; +} + +static const __u8 rdesc[] = { + 0x05, 0x01, /* USAGE_PAGE (Generic Desktop) */ + 0x09, 0x32, /* USAGE (Z) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x81, 0x06, /* INPUT (Data,Var,Rel) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x01, /* USAGE_MINIMUM (1) */ + 0x29, 0x03, /* USAGE_MAXIMUM (3) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0x91, 0x02, /* Output (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0x06, 0x00, 0xff, /* Usage Page (Vendor Defined Page 1) */ + 0x19, 0x06, /* USAGE_MINIMUM (6) */ + 0x29, 0x08, /* USAGE_MAXIMUM (8) */ + 0x15, 0x00, /* LOGICAL_MINIMUM (0) */ + 0x25, 0x01, /* LOGICAL_MAXIMUM (1) */ + 0x95, 0x03, /* REPORT_COUNT (3) */ + 0x75, 0x01, /* REPORT_SIZE (1) */ + 0xb1, 0x02, /* Feature (Data,Var,Abs) */ + 0x95, 0x01, /* REPORT_COUNT (1) */ + 0x75, 0x05, /* REPORT_SIZE (5) */ + 0x91, 0x01, /* Output (Cnst,Var,Abs) */ + + 0xc0, /* END_COLLECTION */ + 0xc0, /* END_COLLECTION */ +}; + +SEC("?fmod_ret/hid_bpf_rdesc_fixup") +int BPF_PROG(hid_rdesc_fixup, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 4096 /* size */); + + if (!data) + return 0; /* EPERM check */ + + callback2_check = data[4]; + + /* insert rdesc at offset 73 */ + __builtin_memcpy(&data[73], rdesc, sizeof(rdesc)); + + /* Change Usage Vendor globally */ + data[4] = 0x42; + + return sizeof(rdesc) + 73; +} + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 4 /* size */); + + if (!data) + return 0; /* EPERM check */ + + /* we need to be run first */ + if (data[2] || data[3]) + return -1; + + data[1] = 1; + + return 0; +} + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_test_insert2, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 4 /* size */); + + if (!data) + return 0; /* EPERM check */ + + /* after insert0 and before insert2 */ + if (!data[1] || data[3]) + return -1; + + data[2] = 2; + + return 0; +} + +SEC("?fmod_ret/hid_bpf_device_event") +int BPF_PROG(hid_test_insert3, struct hid_bpf_ctx *hid_ctx) +{ + __u8 *data = hid_bpf_get_data(hid_ctx, 0 /* offset */, 4 /* size */); + + if (!data) + return 0; /* EPERM check */ + + /* at the end */ + if (!data[1] || !data[2]) + return -1; + + data[3] = 3; + + return 0; +} diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h new file mode 100644 index 000000000000..4fff31dbe0e7 --- /dev/null +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022 Benjamin Tissoires + */ + +#ifndef __HID_BPF_HELPERS_H +#define __HID_BPF_HELPERS_H + +/* following are kfuncs exported by HID for HID-BPF */ +extern __u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, + unsigned int offset, + const size_t __sz) __ksym; +extern int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, u32 flags) __ksym; +extern struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id) __ksym; +extern void hid_bpf_release_context(struct hid_bpf_ctx *ctx) __ksym; +extern int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, + __u8 *data, + size_t buf__sz, + enum hid_report_type type, + enum hid_class_request reqtype) __ksym; + +#endif /* __HID_BPF_HELPERS_H */ diff --git a/tools/testing/selftests/hid/vmtest.sh b/tools/testing/selftests/hid/vmtest.sh new file mode 100755 index 000000000000..90f34150f257 --- /dev/null +++ b/tools/testing/selftests/hid/vmtest.sh @@ -0,0 +1,284 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -u +set -e + +# This script currently only works for x86_64 +ARCH="$(uname -m)" +case "${ARCH}" in +x86_64) + QEMU_BINARY=qemu-system-x86_64 + BZIMAGE="arch/x86/boot/bzImage" + ;; +*) + echo "Unsupported architecture" + exit 1 + ;; +esac +DEFAULT_COMMAND="./hid_bpf" +SCRIPT_DIR="$(dirname $(realpath $0))" +OUTPUT_DIR="$SCRIPT_DIR/results" +KCONFIG_REL_PATHS=("${SCRIPT_DIR}/config" "${SCRIPT_DIR}/config.common" "${SCRIPT_DIR}/config.${ARCH}") +B2C_URL="https://gitlab.freedesktop.org/mupuf/boot2container/-/raw/master/vm2c.py" +NUM_COMPILE_JOBS="$(nproc)" +LOG_FILE_BASE="$(date +"hid_selftests.%Y-%m-%d_%H-%M-%S")" +LOG_FILE="${LOG_FILE_BASE}.log" +EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status" +CONTAINER_IMAGE="registry.fedoraproject.org/fedora:36" + +usage() +{ + cat <<EOF +Usage: $0 [-i] [-s] [-d <output_dir>] -- [<command>] + +<command> is the command you would normally run when you are in +tools/testing/selftests/bpf. e.g: + + $0 -- ./hid_bpf + +If no command is specified and a debug shell (-s) is not requested, +"${DEFAULT_COMMAND}" will be run by default. + +If you build your kernel using KBUILD_OUTPUT= or O= options, these +can be passed as environment variables to the script: + + O=<kernel_build_path> $0 -- ./hid_bpf + +or + + KBUILD_OUTPUT=<kernel_build_path> $0 -- ./hid_bpf + +Options: + + -u) Update the boot2container script to a newer version. + -d) Update the output directory (default: ${OUTPUT_DIR}) + -j) Number of jobs for compilation, similar to -j in make + (default: ${NUM_COMPILE_JOBS}) + -s) Instead of powering off the VM, start an interactive + shell. If <command> is specified, the shell runs after + the command finishes executing +EOF +} + +download() +{ + local file="$1" + + echo "Downloading $file..." >&2 + curl -Lsf "$file" -o "${@:2}" +} + +recompile_kernel() +{ + local kernel_checkout="$1" + local make_command="$2" + + cd "${kernel_checkout}" + + ${make_command} olddefconfig + ${make_command} +} + +update_selftests() +{ + local kernel_checkout="$1" + local selftests_dir="${kernel_checkout}/tools/testing/selftests/hid" + + cd "${selftests_dir}" + ${make_command} +} + +run_vm() +{ + local b2c="$1" + local kernel_bzimage="$2" + local command="$3" + local post_command="" + + if ! which "${QEMU_BINARY}" &> /dev/null; then + cat <<EOF +Could not find ${QEMU_BINARY} +Please install qemu or set the QEMU_BINARY environment variable. +EOF + exit 1 + fi + + # alpine (used in post-container requires the PATH to have /bin + export PATH=$PATH:/bin + + if [[ "${debug_shell}" != "yes" ]] + then + touch ${OUTPUT_DIR}/${LOG_FILE} + command="mount bpffs -t bpf /sys/fs/bpf/; set -o pipefail ; ${command} 2>&1 | tee ${OUTPUT_DIR}/${LOG_FILE}" + post_command="cat ${OUTPUT_DIR}/${LOG_FILE}" + else + command="mount bpffs -t bpf /sys/fs/bpf/; ${command}" + fi + + set +e + $b2c --command "${command}" \ + --kernel ${kernel_bzimage} \ + --workdir ${OUTPUT_DIR} \ + --image ${CONTAINER_IMAGE} + + echo $? > ${OUTPUT_DIR}/${EXIT_STATUS_FILE} + + set -e + + ${post_command} +} + +is_rel_path() +{ + local path="$1" + + [[ ${path:0:1} != "/" ]] +} + +do_update_kconfig() +{ + local kernel_checkout="$1" + local kconfig_file="$2" + + rm -f "$kconfig_file" 2> /dev/null + + for config in "${KCONFIG_REL_PATHS[@]}"; do + local kconfig_src="${config}" + cat "$kconfig_src" >> "$kconfig_file" + done +} + +update_kconfig() +{ + local kernel_checkout="$1" + local kconfig_file="$2" + + if [[ -f "${kconfig_file}" ]]; then + local local_modified="$(stat -c %Y "${kconfig_file}")" + + for config in "${KCONFIG_REL_PATHS[@]}"; do + local kconfig_src="${config}" + local src_modified="$(stat -c %Y "${kconfig_src}")" + # Only update the config if it has been updated after the + # previously cached config was created. This avoids + # unnecessarily compiling the kernel and selftests. + if [[ "${src_modified}" -gt "${local_modified}" ]]; then + do_update_kconfig "$kernel_checkout" "$kconfig_file" + # Once we have found one outdated configuration + # there is no need to check other ones. + break + fi + done + else + do_update_kconfig "$kernel_checkout" "$kconfig_file" + fi +} + +main() +{ + local script_dir="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" + local kernel_checkout=$(realpath "${script_dir}"/../../../../) + # By default the script searches for the kernel in the checkout directory but + # it also obeys environment variables O= and KBUILD_OUTPUT= + local kernel_bzimage="${kernel_checkout}/${BZIMAGE}" + local command="${DEFAULT_COMMAND}" + local update_b2c="no" + local debug_shell="no" + + while getopts ':hsud:j:' opt; do + case ${opt} in + u) + update_b2c="yes" + ;; + d) + OUTPUT_DIR="$OPTARG" + ;; + j) + NUM_COMPILE_JOBS="$OPTARG" + ;; + s) + command="/bin/sh" + debug_shell="yes" + ;; + h) + usage + exit 0 + ;; + \? ) + echo "Invalid Option: -$OPTARG" + usage + exit 1 + ;; + : ) + echo "Invalid Option: -$OPTARG requires an argument" + usage + exit 1 + ;; + esac + done + shift $((OPTIND -1)) + + # trap 'catch "$?"' EXIT + + if [[ "${debug_shell}" == "no" ]]; then + if [[ $# -eq 0 ]]; then + echo "No command specified, will run ${DEFAULT_COMMAND} in the vm" + else + command="$@" + + if [[ "${command}" == "/bin/bash" || "${command}" == "bash" ]] + then + debug_shell="yes" + fi + fi + fi + + local kconfig_file="${OUTPUT_DIR}/latest.config" + local make_command="make -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}" + + # Figure out where the kernel is being built. + # O takes precedence over KBUILD_OUTPUT. + if [[ "${O:=""}" != "" ]]; then + if is_rel_path "${O}"; then + O="$(realpath "${PWD}/${O}")" + fi + kernel_bzimage="${O}/${BZIMAGE}" + make_command="${make_command} O=${O}" + elif [[ "${KBUILD_OUTPUT:=""}" != "" ]]; then + if is_rel_path "${KBUILD_OUTPUT}"; then + KBUILD_OUTPUT="$(realpath "${PWD}/${KBUILD_OUTPUT}")" + fi + kernel_bzimage="${KBUILD_OUTPUT}/${BZIMAGE}" + make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}" + fi + + local b2c="${OUTPUT_DIR}/vm2c.py" + + echo "Output directory: ${OUTPUT_DIR}" + + mkdir -p "${OUTPUT_DIR}" + update_kconfig "${kernel_checkout}" "${kconfig_file}" + + recompile_kernel "${kernel_checkout}" "${make_command}" + + if [[ "${update_b2c}" == "no" && ! -f "${b2c}" ]]; then + echo "vm2c script not found in ${b2c}" + update_b2c="yes" + fi + + if [[ "${update_b2c}" == "yes" ]]; then + download $B2C_URL $b2c + chmod +x $b2c + fi + + update_selftests "${kernel_checkout}" "${make_command}" + run_vm $b2c "${kernel_bzimage}" "${command}" + if [[ "${debug_shell}" != "yes" ]]; then + echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}" + fi + + exit $(cat ${OUTPUT_DIR}/${EXIT_STATUS_FILE}) +} + +main "$@" diff --git a/tools/testing/selftests/iommu/Makefile b/tools/testing/selftests/iommu/Makefile index 7cb74d26f141..32c5fdfd0eef 100644 --- a/tools/testing/selftests/iommu/Makefile +++ b/tools/testing/selftests/iommu/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -Wall -O2 -Wno-unused-function -CFLAGS += -I../../../../include/uapi/ -CFLAGS += -I../../../../include/ +CFLAGS += $(KHDR_INCLUDES) CFLAGS += -D_GNU_SOURCE diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 8aa8a346cf22..fa08209268c4 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1259,7 +1259,7 @@ TEST_F(iommufd_mock_domain, user_copy) test_cmd_destroy_access_pages( access_cmd.id, access_cmd.access_pages.out_access_pages_id); - test_cmd_destroy_access(access_cmd.id) test_ioctl_destroy(ioas_id); + test_cmd_destroy_access(access_cmd.id); test_ioctl_destroy(ioas_id); } diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 1c4448a843a4..50e9c299fc4a 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -10,7 +10,7 @@ ifeq ($(ARCH),x86_64) CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif -CFLAGS += -I../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := msgque diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index b4d39f6b5124..59a1e5379018 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -I../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := kcmp_test diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh index 7424a1f5babc..4bc14d9e8ff1 100755 --- a/tools/testing/selftests/kselftest_deps.sh +++ b/tools/testing/selftests/kselftest_deps.sh @@ -12,9 +12,9 @@ usage() echo -e "Usage: $0 -[p] <compiler> [test_name]\n" echo -e "\tkselftest_deps.sh [-p] gcc" -echo -e "\tkselftest_deps.sh [-p] gcc vm" +echo -e "\tkselftest_deps.sh [-p] gcc mm" echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc" -echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc vm\n" +echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc mm\n" echo "- Should be run in selftests directory in the kernel repo." echo "- Checks if Kselftests can be built/cross-built on a system." echo "- Parses all test/sub-test Makefile to find library dependencies." @@ -120,7 +120,7 @@ l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ # Level 2 # Some tests have multiple valid LDLIBS lines for individual sub-tests # that need dependency checks. Find them and append them to the tests -# e.g: vm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread +# e.g: mm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread # Filter out VAR_LDLIBS to discard the following: # memfd/Makefile:$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) # Append space at the end of the list to append more tests. diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 25f4d54067c0..d8bff2005dfc 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -54,6 +54,7 @@ #define _GNU_SOURCE #endif #include <asm/types.h> +#include <ctype.h> #include <errno.h> #include <stdbool.h> #include <stdint.h> @@ -985,6 +986,127 @@ void __wait_for_test(struct __test_metadata *t) } } +static void test_harness_list_tests(void) +{ + struct __fixture_variant_metadata *v; + struct __fixture_metadata *f; + struct __test_metadata *t; + + for (f = __fixture_list; f; f = f->next) { + v = f->variant; + t = f->tests; + + if (f == __fixture_list) + fprintf(stderr, "%-20s %-25s %s\n", + "# FIXTURE", "VARIANT", "TEST"); + else + fprintf(stderr, "--------------------------------------------------------------------------------\n"); + + do { + fprintf(stderr, "%-20s %-25s %s\n", + t == f->tests ? f->name : "", + v ? v->name : "", + t ? t->name : ""); + + v = v ? v->next : NULL; + t = t ? t->next : NULL; + } while (v || t); + } +} + +static int test_harness_argv_check(int argc, char **argv) +{ + int opt; + + while ((opt = getopt(argc, argv, "hlF:f:V:v:t:T:r:")) != -1) { + switch (opt) { + case 'f': + case 'F': + case 'v': + case 'V': + case 't': + case 'T': + case 'r': + break; + case 'l': + test_harness_list_tests(); + return KSFT_SKIP; + case 'h': + default: + fprintf(stderr, + "Usage: %s [-h|-l] [-t|-T|-v|-V|-f|-F|-r name]\n" + "\t-h print help\n" + "\t-l list all tests\n" + "\n" + "\t-t name include test\n" + "\t-T name exclude test\n" + "\t-v name include variant\n" + "\t-V name exclude variant\n" + "\t-f name include fixture\n" + "\t-F name exclude fixture\n" + "\t-r name run specified test\n" + "\n" + "Test filter options can be specified " + "multiple times. The filtering stops\n" + "at the first match. For example to " + "include all tests from variant 'bla'\n" + "but not test 'foo' specify '-T foo -v bla'.\n" + "", argv[0]); + return opt == 'h' ? KSFT_SKIP : KSFT_FAIL; + } + } + + return KSFT_PASS; +} + +static bool test_enabled(int argc, char **argv, + struct __fixture_metadata *f, + struct __fixture_variant_metadata *v, + struct __test_metadata *t) +{ + unsigned int flen = 0, vlen = 0, tlen = 0; + bool has_positive = false; + int opt; + + optind = 1; + while ((opt = getopt(argc, argv, "F:f:V:v:t:T:r:")) != -1) { + has_positive |= islower(opt); + + switch (tolower(opt)) { + case 't': + if (!strcmp(t->name, optarg)) + return islower(opt); + break; + case 'f': + if (!strcmp(f->name, optarg)) + return islower(opt); + break; + case 'v': + if (!strcmp(v->name, optarg)) + return islower(opt); + break; + case 'r': + if (!tlen) { + flen = strlen(f->name); + vlen = strlen(v->name); + tlen = strlen(t->name); + } + if (strlen(optarg) == flen + 1 + vlen + !!vlen + tlen && + !strncmp(f->name, &optarg[0], flen) && + !strncmp(v->name, &optarg[flen + 1], vlen) && + !strncmp(t->name, &optarg[flen + 1 + vlen + !!vlen], tlen)) + return true; + break; + } + } + + /* + * If there are no positive tests then we assume user just wants + * exclusions and everything else is a pass. + */ + return !has_positive; +} + void __run_test(struct __fixture_metadata *f, struct __fixture_variant_metadata *variant, struct __test_metadata *t) @@ -1032,24 +1154,32 @@ void __run_test(struct __fixture_metadata *f, f->name, variant->name[0] ? "." : "", variant->name, t->name); } -static int test_harness_run(int __attribute__((unused)) argc, - char __attribute__((unused)) **argv) +static int test_harness_run(int argc, char **argv) { struct __fixture_variant_metadata no_variant = { .name = "", }; struct __fixture_variant_metadata *v; struct __fixture_metadata *f; struct __test_results *results; struct __test_metadata *t; - int ret = 0; + int ret; unsigned int case_count = 0, test_count = 0; unsigned int count = 0; unsigned int pass_count = 0; + ret = test_harness_argv_check(argc, argv); + if (ret != KSFT_PASS) + return ret; + for (f = __fixture_list; f; f = f->next) { for (v = f->variant ?: &no_variant; v; v = v->next) { - case_count++; + unsigned int old_tests = test_count; + for (t = f->tests; t; t = t->next) - test_count++; + if (test_enabled(argc, argv, f, v, t)) + test_count++; + + if (old_tests != test_count) + case_count++; } } @@ -1063,6 +1193,8 @@ static int test_harness_run(int __attribute__((unused)) argc, for (f = __fixture_list; f; f = f->next) { for (v = f->variant ?: &no_variant; v; v = v->next) { for (t = f->tests; t; t = t->next) { + if (!test_enabled(argc, argv, f, v, t)) + continue; count++; t->results = results; __run_test(f, v, t); diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 1750f91dd936..84a627c43795 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test @@ -200,6 +201,9 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ $(KHDR_INCLUDES) +ifeq ($(ARCH),s390) + CFLAGS += -march=z10 +endif no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 54680dc5887f..df10f1ffa20d 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -1112,8 +1112,6 @@ int main(int argc, char *argv[]) enum vm_mem_backing_src_type src_type; int opt; - setbuf(stdout, NULL); - src_type = DEFAULT_VM_MEM_SRC; while ((opt = getopt(argc, argv, "hm:s:")) != -1) { diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index 63ed533f73d6..d011b38e259e 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -1,3 +1,4 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index 9218bb5f44bf..fa65b908b13e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -85,61 +85,110 @@ #define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF /* HYPERV_CPUID_FEATURES.EAX */ -#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) -#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) -#define HV_MSR_SYNIC_AVAILABLE BIT(2) -#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) -#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) -#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) -#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) -#define HV_MSR_RESET_AVAILABLE BIT(7) -#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) -#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) -#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) -#define HV_ACCESS_FREQUENCY_MSRS BIT(11) -#define HV_ACCESS_REENLIGHTENMENT BIT(13) -#define HV_ACCESS_TSC_INVARIANT BIT(15) +#define HV_MSR_VP_RUNTIME_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 1) +#define HV_MSR_SYNIC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 2) +#define HV_MSR_SYNTIMER_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 3) +#define HV_MSR_APIC_ACCESS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 4) +#define HV_MSR_HYPERCALL_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 5) +#define HV_MSR_VP_INDEX_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 6) +#define HV_MSR_RESET_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 7) +#define HV_MSR_STAT_PAGES_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 9) +#define HV_MSR_GUEST_IDLE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 10) +#define HV_ACCESS_FREQUENCY_MSRS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 11) +#define HV_ACCESS_REENLIGHTENMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 13) +#define HV_ACCESS_TSC_INVARIANT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 15) /* HYPERV_CPUID_FEATURES.EBX */ -#define HV_CREATE_PARTITIONS BIT(0) -#define HV_ACCESS_PARTITION_ID BIT(1) -#define HV_ACCESS_MEMORY_POOL BIT(2) -#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) -#define HV_POST_MESSAGES BIT(4) -#define HV_SIGNAL_EVENTS BIT(5) -#define HV_CREATE_PORT BIT(6) -#define HV_CONNECT_PORT BIT(7) -#define HV_ACCESS_STATS BIT(8) -#define HV_DEBUGGING BIT(11) -#define HV_CPU_MANAGEMENT BIT(12) -#define HV_ISOLATION BIT(22) +#define HV_CREATE_PARTITIONS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 0) +#define HV_ACCESS_PARTITION_ID \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 1) +#define HV_ACCESS_MEMORY_POOL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 2) +#define HV_ADJUST_MESSAGE_BUFFERS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 3) +#define HV_POST_MESSAGES \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 4) +#define HV_SIGNAL_EVENTS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 5) +#define HV_CREATE_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 6) +#define HV_CONNECT_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 7) +#define HV_ACCESS_STATS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 8) +#define HV_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 11) +#define HV_CPU_MANAGEMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 12) +#define HV_ENABLE_EXTENDED_HYPERCALLS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 20) +#define HV_ISOLATION \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 22) /* HYPERV_CPUID_FEATURES.EDX */ -#define HV_X64_MWAIT_AVAILABLE BIT(0) -#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) -#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) -#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) +#define HV_X64_MWAIT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 1) +#define HV_X64_PERF_MONITOR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 3) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 11) +#define HV_STIMER_DIRECT_MODE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 19) /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ -#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) -#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) -#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) -#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) -#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) -#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +#define HV_X64_AS_SWITCH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 2) +#define HV_X64_APIC_ACCESS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 5) +#define HV_DEPRECATING_AEOI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 11) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ -#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) /* Hypercalls */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 @@ -166,6 +215,9 @@ #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 +/* Extended hypercalls */ +#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 + #define HV_FLUSH_ALL_PROCESSORS BIT(0) #define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) @@ -288,4 +340,7 @@ struct hyperv_test_pages { struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva); +/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ +#define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index b1a31de7108a..53ffa43c90db 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -19,6 +19,9 @@ #include "../kvm_util.h" +extern bool host_cpu_is_intel; +extern bool host_cpu_is_amd; + #define NMI_VECTOR 0x02 #define X86_EFLAGS_FIXED (1u << 1) @@ -137,6 +140,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) #define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) #define X86_FEATURE_LM KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 29) +#define X86_FEATURE_INVTSC KVM_X86_CPU_FEATURE(0x80000007, 0, EDX, 8) #define X86_FEATURE_RDPRU KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 4) #define X86_FEATURE_AMD_IBPB KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 12) #define X86_FEATURE_NPT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 0) @@ -554,6 +558,28 @@ static inline uint32_t this_cpu_model(void) return x86_model(this_cpu_fms()); } +static inline bool this_cpu_vendor_string_is(const char *vendor) +{ + const uint32_t *chunk = (const uint32_t *)vendor; + uint32_t eax, ebx, ecx, edx; + + cpuid(0, &eax, &ebx, &ecx, &edx); + return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); +} + +static inline bool this_cpu_is_intel(void) +{ + return this_cpu_vendor_string_is("GenuineIntel"); +} + +/* + * Exclude early K5 samples with a vendor string of "AMDisbetter!" + */ +static inline bool this_cpu_is_amd(void) +{ + return this_cpu_vendor_string_is("AuthenticAMD"); +} + static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, uint8_t reg, uint8_t lo, uint8_t hi) { @@ -690,9 +716,6 @@ static inline void cpu_relax(void) "hlt\n" \ ) -bool is_intel_cpu(void); -bool is_amd_cpu(void); - struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu); void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state); void kvm_x86_state_cleanup(struct kvm_x86_state *state); @@ -716,7 +739,7 @@ static inline void vcpu_msrs_set(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) int r = __vcpu_ioctl(vcpu, KVM_SET_MSRS, msrs); TEST_ASSERT(r == msrs->nmsrs, - "KVM_GET_MSRS failed, r: %i (failed on MSR %x)", + "KVM_SET_MSRS failed, r: %i (failed on MSR %x)", r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index); } static inline void vcpu_debugregs_get(struct kvm_vcpu *vcpu, diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c index 0b45ac593387..a7001e29dc06 100644 --- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -19,6 +19,7 @@ #include "kvm_util.h" #include "asm/kvm.h" #include "linux/kvm.h" +#include "kselftest.h" static void stats_test(int stats_fd) { @@ -51,7 +52,7 @@ static void stats_test(int stats_fd) /* Sanity check for other fields in header */ if (header.num_desc == 0) { - printf("No KVM stats defined!"); + ksft_print_msg("No KVM stats defined!\n"); return; } /* @@ -133,7 +134,7 @@ static void stats_test(int stats_fd) "Bucket size of stats (%s) is not zero", pdesc->name); } - size_data += pdesc->size * sizeof(*stats_data); + size_data = max(size_data, pdesc->offset + pdesc->size * sizeof(*stats_data)); } /* @@ -148,14 +149,6 @@ static void stats_test(int stats_fd) TEST_ASSERT(size_data >= header.num_desc * sizeof(*stats_data), "Data size is not correct"); - /* Check stats offset */ - for (i = 0; i < header.num_desc; ++i) { - pdesc = get_stats_descriptor(stats_desc, i, &header); - TEST_ASSERT(pdesc->offset < size_data, - "Invalid offset (%u) for stats: %s", - pdesc->offset, pdesc->name); - } - /* Allocate memory for stats data */ stats_data = malloc(size_data); TEST_ASSERT(stats_data, "Allocate memory for stats data"); @@ -224,9 +217,13 @@ int main(int argc, char *argv[]) max_vcpu = DEFAULT_NUM_VCPU; } + ksft_print_header(); + /* Check the extension for binary stats */ TEST_REQUIRE(kvm_has_cap(KVM_CAP_BINARY_STATS_FD)); + ksft_set_plan(max_vm); + /* Create VMs and VCPUs */ vms = malloc(sizeof(vms[0]) * max_vm); TEST_ASSERT(vms, "Allocate memory for storing VM pointers"); @@ -245,10 +242,12 @@ int main(int argc, char *argv[]) vm_stats_test(vms[i]); for (j = 0; j < max_vcpu; ++j) vcpu_stats_test(vcpus[i * max_vcpu + j]); + ksft_test_result_pass("vm%i\n", i); } for (i = 0; i < max_vm; ++i) kvm_vm_free(vms[i]); free(vms); - return 0; + + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index 820ac2d08c98..266f3876e10a 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -90,6 +90,7 @@ static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp) " hdrp->e_shentsize: %x\n" " expected: %zx", hdrp->e_shentsize, sizeof(Elf64_Shdr)); + close(fd); } /* VM ELF Load @@ -190,4 +191,5 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) phdr.p_filesz); } } + close(fd); } diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 99a575bbbc52..1df3ce4b16fd 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -127,7 +127,7 @@ void guest_modes_cmdline(const char *arg) mode_selected = true; } - mode = strtoul(optarg, NULL, 10); + mode = atoi_non_negative("Guest mode ID", arg); TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56d5ea949cbb..3ea24a5f4c43 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1844,6 +1844,7 @@ static struct exit_reason { {KVM_EXIT_X86_RDMSR, "RDMSR"}, {KVM_EXIT_X86_WRMSR, "WRMSR"}, {KVM_EXIT_XEN, "XEN"}, + {KVM_EXIT_HYPERV, "HYPERV"}, #ifdef KVM_EXIT_MEMORY_NOT_PRESENT {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, #endif @@ -1941,9 +1942,6 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); } -/* Arbitrary minimum physical address used for virtual translation tables. */ -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) { return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index acfa1d01e7df..ae1e573d94ce 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,6 +19,8 @@ #define MAX_NR_CPUID_ENTRIES 100 vm_vaddr_t exception_handlers; +bool host_cpu_is_amd; +bool host_cpu_is_intel; static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -113,7 +115,7 @@ static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) bool kvm_is_tdp_enabled(void) { - if (is_intel_cpu()) + if (host_cpu_is_intel) return get_kvm_intel_param_bool("ept"); else return get_kvm_amd_param_bool("npt"); @@ -555,6 +557,8 @@ static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) void kvm_arch_vm_post_create(struct kvm_vm *vm) { vm_create_irqchip(vm); + sync_global_to_guest(vm, host_cpu_is_intel); + sync_global_to_guest(vm, host_cpu_is_amd); } struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, @@ -1006,28 +1010,6 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state) free(state); } -static bool cpu_vendor_string_is(const char *vendor) -{ - const uint32_t *chunk = (const uint32_t *)vendor; - uint32_t eax, ebx, ecx, edx; - - cpuid(0, &eax, &ebx, &ecx, &edx); - return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); -} - -bool is_intel_cpu(void) -{ - return cpu_vendor_string_is("GenuineIntel"); -} - -/* - * Exclude early K5 samples with a vendor string of "AMDisbetter!" - */ -bool is_amd_cpu(void) -{ - return cpu_vendor_string_is("AuthenticAMD"); -} - void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { @@ -1162,9 +1144,15 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, { uint64_t r; - asm volatile("vmcall" + asm volatile("test %[use_vmmcall], %[use_vmmcall]\n\t" + "jnz 1f\n\t" + "vmcall\n\t" + "jmp 2f\n\t" + "1: vmmcall\n\t" + "2:" : "=a"(r) - : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3), + [use_vmmcall] "r" (host_cpu_is_amd)); return r; } @@ -1236,7 +1224,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ - if (!is_amd_cpu()) + if (!host_cpu_is_amd) return max_gfn; /* On parts with <40 physical address bits, the area is fully hidden */ @@ -1276,3 +1264,9 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) return get_kvm_intel_param_bool("unrestricted_guest"); } + +void kvm_selftest_arch_init(void) +{ + host_cpu_is_intel = this_cpu_is_intel(); + host_cpu_is_amd = this_cpu_is_amd(); +} diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e6587e193490..4210cd21d159 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -308,8 +308,6 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); TEST_ASSERT(data->hva_slots, "malloc() fail"); - data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code); - pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", data->nslots, data->pages_per_slot, rempages); @@ -349,6 +347,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, virt_map(data->vm, MEM_GPA, MEM_GPA, data->npages); sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + sync->guest_page_size = data->vm->page_size; atomic_init(&sync->start_flag, false); atomic_init(&sync->exit_flag, false); atomic_init(&sync->sync_flag, false); @@ -810,8 +809,6 @@ static bool test_execute(int nslots, uint64_t *maxslots, } sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); - - sync->guest_page_size = data->vm->page_size; if (tdata->prepare && !tdata->prepare(data, sync, maxslots)) { ret = false; diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 3fd81e58f40c..8e4b94d7b8dd 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -9,6 +9,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <pthread.h> #include <linux/bits.h> @@ -26,6 +27,7 @@ enum mop_target { enum mop_access_mode { READ, WRITE, + CMPXCHG, }; struct mop_desc { @@ -44,57 +46,67 @@ struct mop_desc { enum mop_access_mode mode; void *buf; uint32_t sida_offset; + void *old; + uint8_t old_value[16]; + bool *cmpxchg_success; uint8_t ar; uint8_t key; }; -static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc) +const uint8_t NO_KEY = 0xff; + +static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc *desc) { struct kvm_s390_mem_op ksmo = { - .gaddr = (uintptr_t)desc.gaddr, - .size = desc.size, - .buf = ((uintptr_t)desc.buf), + .gaddr = (uintptr_t)desc->gaddr, + .size = desc->size, + .buf = ((uintptr_t)desc->buf), .reserved = "ignored_ignored_ignored_ignored" }; - switch (desc.target) { + switch (desc->target) { case LOGICAL: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; break; case SIDA: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_SIDA_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_SIDA_WRITE; break; case ABSOLUTE: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE; + if (desc->mode == CMPXCHG) { + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_CMPXCHG; + ksmo.old_addr = (uint64_t)desc->old; + memcpy(desc->old_value, desc->old, desc->size); + } break; case INVALID: ksmo.op = -1; } - if (desc.f_check) + if (desc->f_check) ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY; - if (desc.f_inject) + if (desc->f_inject) ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION; - if (desc._set_flags) - ksmo.flags = desc.set_flags; - if (desc.f_key) { + if (desc->_set_flags) + ksmo.flags = desc->set_flags; + if (desc->f_key && desc->key != NO_KEY) { ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION; - ksmo.key = desc.key; + ksmo.key = desc->key; } - if (desc._ar) - ksmo.ar = desc.ar; + if (desc->_ar) + ksmo.ar = desc->ar; else ksmo.ar = 0; - if (desc._sida_offset) - ksmo.sida_offset = desc.sida_offset; + if (desc->_sida_offset) + ksmo.sida_offset = desc->sida_offset; return ksmo; } @@ -133,9 +145,13 @@ static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksm case KVM_S390_MEMOP_ABSOLUTE_WRITE: printf("ABSOLUTE, WRITE, "); break; + case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG: + printf("ABSOLUTE, CMPXCHG, "); + break; } - printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u", - ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key); + printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u, old_addr=%llx", + ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key, + ksmo->old_addr); if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY) printf(", CHECK_ONLY"); if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) @@ -145,24 +161,30 @@ static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksm puts(")"); } -static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) +static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, + struct mop_desc *desc) { struct kvm_vcpu *vcpu = info.vcpu; if (!vcpu) - vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); + return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); else - vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); + return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); } -static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) +static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, + struct mop_desc *desc) { - struct kvm_vcpu *vcpu = info.vcpu; + int r; - if (!vcpu) - return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); - else - return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); + r = err_memop_ioctl(info, ksmo, desc); + if (ksmo->op == KVM_S390_MEMOP_ABSOLUTE_CMPXCHG) { + if (desc->cmpxchg_success) { + int diff = memcmp(desc->old_value, desc->old, desc->size); + *desc->cmpxchg_success = !diff; + } + } + TEST_ASSERT(!r, __KVM_IOCTL_ERROR("KVM_S390_MEM_OP", r)); } #define MEMOP(err, info_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ @@ -183,9 +205,9 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) else \ __desc.gaddr = __desc.gaddr_v; \ } \ - __ksmo = ksmo_from_desc(__desc); \ + __ksmo = ksmo_from_desc(&__desc); \ print_memop(__info.vcpu, &__ksmo); \ - err##memop_ioctl(__info, &__ksmo); \ + err##memop_ioctl(__info, &__ksmo, &__desc); \ }) #define MOP(...) MEMOP(, __VA_ARGS__) @@ -199,6 +221,8 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) #define AR(a) ._ar = 1, .ar = (a) #define KEY(a) .f_key = 1, .key = (a) #define INJECT .f_inject = 1 +#define CMPXCHG_OLD(o) .old = (o) +#define CMPXCHG_SUCCESS(s) .cmpxchg_success = (s) #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) @@ -208,8 +232,8 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) -static uint8_t mem1[65536]; -static uint8_t mem2[65536]; +static uint8_t __aligned(PAGE_SIZE) mem1[65536]; +static uint8_t __aligned(PAGE_SIZE) mem2[65536]; struct test_default { struct kvm_vm *kvm_vm; @@ -241,6 +265,8 @@ enum stage { STAGE_SKEYS_SET, /* Guest copied memory (locations up to test case) */ STAGE_COPIED, + /* End of guest code reached */ + STAGE_DONE, }; #define HOST_SYNC(info_p, stage) \ @@ -252,6 +278,9 @@ enum stage { \ vcpu_run(__vcpu); \ get_ucall(__vcpu, &uc); \ + if (uc.cmd == UCALL_ABORT) { \ + REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu"); \ + } \ ASSERT_EQ(uc.cmd, UCALL_SYNC); \ ASSERT_EQ(uc.args[1], __stage); \ }) \ @@ -268,34 +297,66 @@ static void prepare_mem12(void) #define ASSERT_MEM_EQ(p1, p2, size) \ TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!") -#define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ -({ \ - struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ - enum mop_target __target = (mop_target_p); \ - uint32_t __size = (size); \ - \ - prepare_mem12(); \ - CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ - GADDR_V(mem1), ##__VA_ARGS__); \ - HOST_SYNC(__copy_cpu, STAGE_COPIED); \ - CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, \ - GADDR_V(mem2), ##__VA_ARGS__); \ - ASSERT_MEM_EQ(mem1, mem2, __size); \ -}) +static void default_write_read(struct test_info copy_cpu, struct test_info mop_cpu, + enum mop_target mop_target, uint32_t size, uint8_t key) +{ + prepare_mem12(); + CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, + GADDR_V(mem1), KEY(key)); + HOST_SYNC(copy_cpu, STAGE_COPIED); + CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size, + GADDR_V(mem2), KEY(key)); + ASSERT_MEM_EQ(mem1, mem2, size); +} -#define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ -({ \ - struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ - enum mop_target __target = (mop_target_p); \ - uint32_t __size = (size); \ - \ - prepare_mem12(); \ - CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ - GADDR_V(mem1)); \ - HOST_SYNC(__copy_cpu, STAGE_COPIED); \ - CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, ##__VA_ARGS__);\ - ASSERT_MEM_EQ(mem1, mem2, __size); \ -}) +static void default_read(struct test_info copy_cpu, struct test_info mop_cpu, + enum mop_target mop_target, uint32_t size, uint8_t key) +{ + prepare_mem12(); + CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, GADDR_V(mem1)); + HOST_SYNC(copy_cpu, STAGE_COPIED); + CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size, + GADDR_V(mem2), KEY(key)); + ASSERT_MEM_EQ(mem1, mem2, size); +} + +static void default_cmpxchg(struct test_default *test, uint8_t key) +{ + for (int size = 1; size <= 16; size *= 2) { + for (int offset = 0; offset < 16; offset += size) { + uint8_t __aligned(16) new[16] = {}; + uint8_t __aligned(16) old[16]; + bool succ; + + prepare_mem12(); + default_write_read(test->vcpu, test->vcpu, LOGICAL, 16, NO_KEY); + + memcpy(&old, mem1, 16); + MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset, + size, GADDR_V(mem1 + offset), + CMPXCHG_OLD(old + offset), + CMPXCHG_SUCCESS(&succ), KEY(key)); + HOST_SYNC(test->vcpu, STAGE_COPIED); + MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2)); + TEST_ASSERT(succ, "exchange of values should succeed"); + memcpy(mem1 + offset, new + offset, size); + ASSERT_MEM_EQ(mem1, mem2, 16); + + memcpy(&old, mem1, 16); + new[offset]++; + old[offset]++; + MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset, + size, GADDR_V(mem1 + offset), + CMPXCHG_OLD(old + offset), + CMPXCHG_SUCCESS(&succ), KEY(key)); + HOST_SYNC(test->vcpu, STAGE_COPIED); + MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2)); + TEST_ASSERT(!succ, "exchange of values should not succeed"); + ASSERT_MEM_EQ(mem1, mem2, 16); + ASSERT_MEM_EQ(&old, mem1, 16); + } + } +} static void guest_copy(void) { @@ -310,7 +371,7 @@ static void test_copy(void) HOST_SYNC(t.vcpu, STAGE_INITED); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, NO_KEY); kvm_vm_free(t.kvm_vm); } @@ -357,26 +418,268 @@ static void test_copy_key(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vm, no key */ - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, NO_KEY); /* vm/vcpu, machting key or key 0 */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(9)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(9)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 0); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 0); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9); /* * There used to be different code paths for key handling depending on * if the region crossed a page boundary. * There currently are not, but the more tests the merrier. */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(9)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(9)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 0); + default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 9); + default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 0); + default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 9); /* vm/vcpu, mismatching keys on read, but no fetch protection */ - DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(2)); - DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem1), KEY(2)); + default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2); + default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 2); + + kvm_vm_free(t.kvm_vm); +} + +static void test_cmpxchg_key(void) +{ + struct test_default t = test_default_init(guest_copy_key); + + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + default_cmpxchg(&t, NO_KEY); + default_cmpxchg(&t, 0); + default_cmpxchg(&t, 9); + + kvm_vm_free(t.kvm_vm); +} + +static __uint128_t cut_to_size(int size, __uint128_t val) +{ + switch (size) { + case 1: + return (uint8_t)val; + case 2: + return (uint16_t)val; + case 4: + return (uint32_t)val; + case 8: + return (uint64_t)val; + case 16: + return val; + } + GUEST_ASSERT_1(false, "Invalid size"); + return 0; +} + +static bool popcount_eq(__uint128_t a, __uint128_t b) +{ + unsigned int count_a, count_b; + + count_a = __builtin_popcountl((uint64_t)(a >> 64)) + + __builtin_popcountl((uint64_t)a); + count_b = __builtin_popcountl((uint64_t)(b >> 64)) + + __builtin_popcountl((uint64_t)b); + return count_a == count_b; +} + +static __uint128_t rotate(int size, __uint128_t val, int amount) +{ + unsigned int bits = size * 8; + + amount = (amount + bits) % bits; + val = cut_to_size(size, val); + return (val << (bits - amount)) | (val >> amount); +} + +const unsigned int max_block = 16; + +static void choose_block(bool guest, int i, int *size, int *offset) +{ + unsigned int rand; + + rand = i; + if (guest) { + rand = rand * 19 + 11; + *size = 1 << ((rand % 3) + 2); + rand = rand * 19 + 11; + *offset = (rand % max_block) & ~(*size - 1); + } else { + rand = rand * 17 + 5; + *size = 1 << (rand % 5); + rand = rand * 17 + 5; + *offset = (rand % max_block) & ~(*size - 1); + } +} + +static __uint128_t permutate_bits(bool guest, int i, int size, __uint128_t old) +{ + unsigned int rand; + int amount; + bool swap; + + rand = i; + rand = rand * 3 + 1; + if (guest) + rand = rand * 3 + 1; + swap = rand % 2 == 0; + if (swap) { + int i, j; + __uint128_t new; + uint8_t byte0, byte1; + + rand = rand * 3 + 1; + i = rand % size; + rand = rand * 3 + 1; + j = rand % size; + if (i == j) + return old; + new = rotate(16, old, i * 8); + byte0 = new & 0xff; + new &= ~0xff; + new = rotate(16, new, -i * 8); + new = rotate(16, new, j * 8); + byte1 = new & 0xff; + new = (new & ~0xff) | byte0; + new = rotate(16, new, -j * 8); + new = rotate(16, new, i * 8); + new = new | byte1; + new = rotate(16, new, -i * 8); + return new; + } + rand = rand * 3 + 1; + amount = rand % (size * 8); + return rotate(size, old, amount); +} + +static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t new) +{ + bool ret; + + switch (size) { + case 4: { + uint32_t old = *old_addr; + + asm volatile ("cs %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(uint32_t *)(target)) + : [new] "d" ((uint32_t)new) + : "cc" + ); + ret = old == (uint32_t)*old_addr; + *old_addr = old; + return ret; + } + case 8: { + uint64_t old = *old_addr; + + asm volatile ("csg %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(uint64_t *)(target)) + : [new] "d" ((uint64_t)new) + : "cc" + ); + ret = old == (uint64_t)*old_addr; + *old_addr = old; + return ret; + } + case 16: { + __uint128_t old = *old_addr; + + asm volatile ("cdsg %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(__uint128_t *)(target)) + : [new] "d" (new) + : "cc" + ); + ret = old == *old_addr; + *old_addr = old; + return ret; + } + } + GUEST_ASSERT_1(false, "Invalid size"); + return 0; +} + +const unsigned int cmpxchg_iter_outer = 100, cmpxchg_iter_inner = 10000; + +static void guest_cmpxchg_key(void) +{ + int size, offset; + __uint128_t old, new; + + set_storage_key_range(mem1, max_block, 0x10); + set_storage_key_range(mem2, max_block, 0x10); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (int i = 0; i < cmpxchg_iter_outer; i++) { + do { + old = 1; + } while (!_cmpxchg(16, mem1, &old, 0)); + for (int j = 0; j < cmpxchg_iter_inner; j++) { + choose_block(true, i + j, &size, &offset); + do { + new = permutate_bits(true, i + j, size, old); + } while (!_cmpxchg(size, mem2 + offset, &old, new)); + } + } + + GUEST_SYNC(STAGE_DONE); +} + +static void *run_guest(void *data) +{ + struct test_info *info = data; + + HOST_SYNC(*info, STAGE_DONE); + return NULL; +} + +static char *quad_to_char(__uint128_t *quad, int size) +{ + return ((char *)quad) + (sizeof(*quad) - size); +} + +static void test_cmpxchg_key_concurrent(void) +{ + struct test_default t = test_default_init(guest_cmpxchg_key); + int size, offset; + __uint128_t old, new; + bool success; + pthread_t thread; + + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, max_block, GADDR_V(mem2)); + pthread_create(&thread, NULL, run_guest, &t.vcpu); + + for (int i = 0; i < cmpxchg_iter_outer; i++) { + do { + old = 0; + new = 1; + MOP(t.vm, ABSOLUTE, CMPXCHG, &new, + sizeof(new), GADDR_V(mem1), + CMPXCHG_OLD(&old), + CMPXCHG_SUCCESS(&success), KEY(1)); + } while (!success); + for (int j = 0; j < cmpxchg_iter_inner; j++) { + choose_block(false, i + j, &size, &offset); + do { + new = permutate_bits(false, i + j, size, old); + MOP(t.vm, ABSOLUTE, CMPXCHG, quad_to_char(&new, size), + size, GADDR_V(mem2 + offset), + CMPXCHG_OLD(quad_to_char(&old, size)), + CMPXCHG_SUCCESS(&success), KEY(1)); + } while (!success); + } + } + + pthread_join(thread, NULL); + + MOP(t.vcpu, LOGICAL, READ, mem2, max_block, GADDR_V(mem2)); + TEST_ASSERT(popcount_eq(*(__uint128_t *)mem1, *(__uint128_t *)mem2), + "Must retain number of set bits"); kvm_vm_free(t.kvm_vm); } @@ -409,7 +712,7 @@ static void test_copy_key_storage_prot_override(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vcpu, mismatching keys, storage protection override in effect */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(2)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2); kvm_vm_free(t.kvm_vm); } @@ -422,8 +725,8 @@ static void test_copy_key_fetch_prot(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vm/vcpu, matching key, fetch protection in effect */ - DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(9)); - DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem2), KEY(9)); + default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9); + default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9); kvm_vm_free(t.kvm_vm); } @@ -454,9 +757,27 @@ static void test_errors_key(void) /* vm/vcpu, mismatching keys, fetch protection in effect */ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); - CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem1), KEY(2)); CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); - CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem1), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_cmpxchg_key(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + int i; + + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + for (i = 1; i <= 16; i *= 2) { + __uint128_t old = 0; + + ERR_PROT_MOP(t.vm, ABSOLUTE, CMPXCHG, mem2, i, GADDR_V(mem2), + CMPXCHG_OLD(&old), KEY(2)); + } kvm_vm_free(t.kvm_vm); } @@ -518,7 +839,7 @@ static void guest_copy_key_fetch_prot_override(void) GUEST_SYNC(STAGE_INITED); set_storage_key_range(0, PAGE_SIZE, 0x18); set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0); - asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0), [key] "r"(0x18) : "cc"); + asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0L), [key] "r"(0x18) : "cc"); GUEST_SYNC(STAGE_SKEYS_SET); for (;;) { @@ -606,7 +927,7 @@ static void test_errors_key_fetch_prot_override_enabled(void) /* * vcpu, mismatching keys on fetch, - * fetch protection override does not apply because memory range acceeded + * fetch protection override does not apply because memory range exceeded */ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2)); CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1, @@ -645,7 +966,9 @@ static void _test_errors_common(struct test_info info, enum mop_target target, i /* Bad guest address: */ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); - TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access"); + TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address with CHECK_ONLY"); + rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL)); + TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address on write"); /* Bad host address: */ rv = ERR_MOP(info, target, WRITE, 0, size, GADDR_V(mem1)); @@ -694,85 +1017,138 @@ static void test_errors(void) kvm_vm_free(t.kvm_vm); } -struct testdef { - const char *name; - void (*test)(void); - int extension; -} testlist[] = { - { - .name = "simple copy", - .test = test_copy, - }, - { - .name = "generic error checks", - .test = test_errors, - }, - { - .name = "copy with storage keys", - .test = test_copy_key, - .extension = 1, - }, - { - .name = "copy with key storage protection override", - .test = test_copy_key_storage_prot_override, - .extension = 1, - }, - { - .name = "copy with key fetch protection", - .test = test_copy_key_fetch_prot, - .extension = 1, - }, - { - .name = "copy with key fetch protection override", - .test = test_copy_key_fetch_prot_override, - .extension = 1, - }, - { - .name = "error checks with key", - .test = test_errors_key, - .extension = 1, - }, - { - .name = "termination", - .test = test_termination, - .extension = 1, - }, - { - .name = "error checks with key storage protection override", - .test = test_errors_key_storage_prot_override, - .extension = 1, - }, - { - .name = "error checks without key fetch prot override", - .test = test_errors_key_fetch_prot_override_not_enabled, - .extension = 1, - }, - { - .name = "error checks with key fetch prot override", - .test = test_errors_key_fetch_prot_override_enabled, - .extension = 1, - }, -}; +static void test_errors_cmpxchg(void) +{ + struct test_default t = test_default_init(guest_idle); + __uint128_t old; + int rv, i, power = 1; + + HOST_SYNC(t.vcpu, STAGE_INITED); + + for (i = 0; i < 32; i++) { + if (i == power) { + power *= 2; + continue; + } + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl allows bad size for cmpxchg"); + } + for (i = 1; i <= 16; i *= 2) { + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR((void *)~0xfffUL), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv > 0, "ioctl allows bad guest address for cmpxchg"); + } + for (i = 2; i <= 16; i *= 2) { + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1 + 1), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl allows bad alignment for cmpxchg"); + } + + kvm_vm_free(t.kvm_vm); +} int main(int argc, char *argv[]) { int extension_cap, idx; TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP)); + extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); - ksft_print_header(); + struct testdef { + const char *name; + void (*test)(void); + bool requirements_met; + } testlist[] = { + { + .name = "simple copy", + .test = test_copy, + .requirements_met = true, + }, + { + .name = "generic error checks", + .test = test_errors, + .requirements_met = true, + }, + { + .name = "copy with storage keys", + .test = test_copy_key, + .requirements_met = extension_cap > 0, + }, + { + .name = "cmpxchg with storage keys", + .test = test_cmpxchg_key, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "concurrently cmpxchg with storage keys", + .test = test_cmpxchg_key_concurrent, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "copy with key storage protection override", + .test = test_copy_key_storage_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "copy with key fetch protection", + .test = test_copy_key_fetch_prot, + .requirements_met = extension_cap > 0, + }, + { + .name = "copy with key fetch protection override", + .test = test_copy_key_fetch_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key", + .test = test_errors_key, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks for cmpxchg with key", + .test = test_errors_cmpxchg_key, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "error checks for cmpxchg", + .test = test_errors_cmpxchg, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "termination", + .test = test_termination, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key storage protection override", + .test = test_errors_key_storage_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks without key fetch prot override", + .test = test_errors_key_fetch_prot_override_not_enabled, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key fetch prot override", + .test = test_errors_key_fetch_prot_override_enabled, + .requirements_met = extension_cap > 0, + }, + }; + ksft_print_header(); ksft_set_plan(ARRAY_SIZE(testlist)); - extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { - if (extension_cap >= testlist[idx].extension) { + if (testlist[idx].requirements_met) { testlist[idx].test(); ksft_test_result_pass("%s\n", testlist[idx].name); } else { - ksft_test_result_skip("%s - extension level %d not supported\n", - testlist[idx].name, - testlist[idx].extension); + ksft_test_result_skip("%s - requirements not met (kernel has extension cap %#x)\n", + testlist[idx].name, extension_cap); } } diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c index 37c61f712fd5..e334844d6e1d 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -26,9 +26,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 32f7e09ef67c..0f728f05ea82 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -48,10 +48,10 @@ static void guest_main(void) const uint8_t *other_hypercall_insn; uint64_t ret; - if (is_intel_cpu()) { + if (host_cpu_is_intel) { native_hypercall_insn = vmx_vmcall; other_hypercall_insn = svm_vmmcall; - } else if (is_amd_cpu()) { + } else if (host_cpu_is_amd) { native_hypercall_insn = svm_vmmcall; other_hypercall_insn = vmx_vmcall; } else { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index d576bc8ce823..2ee0af0d449e 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -104,7 +104,7 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ /* Set Guest OS id to enable Hyper-V emulation */ GUEST_SYNC(1); - wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); GUEST_SYNC(2); check_tsc_msr_rdtsc(); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c new file mode 100644 index 000000000000..73af44d2167f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test Hyper-V extended hypercall, HV_EXT_CALL_QUERY_CAPABILITIES (0x8001), + * exit to userspace and receive result in guest. + * + * Negative tests are present in hyperv_features.c + * + * Copyright 2022 Google LLC + * Author: Vipin Sharma <vipinsh@google.com> + */ + +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" + +/* Any value is fine */ +#define EXT_CAPABILITIES 0xbull + +static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, + vm_vaddr_t out_pg_gva) +{ + uint64_t *output_gva; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, in_pg_gpa); + + output_gva = (uint64_t *)out_pg_gva; + + hyperv_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, in_pg_gpa, out_pg_gpa); + + /* TLFS states output will be a uint64_t value */ + GUEST_ASSERT_EQ(*output_gva, EXT_CAPABILITIES); + + GUEST_DONE(); +} + +int main(void) +{ + vm_vaddr_t hcall_out_page; + vm_vaddr_t hcall_in_page; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + uint64_t *outval; + struct ucall uc; + + /* Verify if extended hypercalls are supported */ + if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(), + HV_ENABLE_EXTENDED_HYPERCALLS)) { + print_skip("Extended calls not supported by the kernel"); + exit(KSFT_SKIP); + } + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + vcpu_set_hv_cpuid(vcpu); + + /* Hypercall input */ + hcall_in_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_in_page), 0x0, vm->page_size); + + /* Hypercall output */ + hcall_out_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_out_page), 0x0, vm->page_size); + + vcpu_args_set(vcpu, 3, addr_gva2gpa(vm, hcall_in_page), + addr_gva2gpa(vm, hcall_out_page), hcall_out_page); + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_HYPERV, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + outval = addr_gpa2hva(vm, run->hyperv.u.hcall.params[1]); + *outval = EXT_CAPABILITIES; + run->hyperv.u.hcall.result = HV_STATUS_SUCCESS; + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "arg1 = %ld, arg2 = %ld"); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 3163c3e8db0a..c5e3b39edd07 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,9 +13,17 @@ #include "processor.h" #include "hyperv.h" +/* + * HYPERV_CPUID_ENLIGHTMENT_INFO.EBX is not a 'feature' CPUID leaf + * but to activate the feature it is sufficient to set it to a non-zero + * value. Use BIT(0) for that. + */ +#define HV_PV_SPINLOCKS_TEST \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EBX, 0) + struct msr_data { uint32_t idx; - bool available; + bool fault_expected; bool write; u64 write_val; }; @@ -26,22 +34,46 @@ struct hcall_data { bool ud_expected; }; +static bool is_write_only_msr(uint32_t msr) +{ + return msr == HV_X64_MSR_EOI; +} + static void guest_msr(struct msr_data *msr) { - uint64_t ignored; - uint8_t vector; + uint8_t vector = 0; + uint64_t msr_val = 0; GUEST_ASSERT(msr->idx); - if (!msr->write) - vector = rdmsr_safe(msr->idx, &ignored); - else + if (msr->write) vector = wrmsr_safe(msr->idx, msr->write_val); - if (msr->available) - GUEST_ASSERT_2(!vector, msr->idx, vector); + if (!vector && (!msr->write || !is_write_only_msr(msr->idx))) + vector = rdmsr_safe(msr->idx, &msr_val); + + if (msr->fault_expected) + GUEST_ASSERT_3(vector == GP_VECTOR, msr->idx, vector, GP_VECTOR); else - GUEST_ASSERT_2(vector == GP_VECTOR, msr->idx, vector); + GUEST_ASSERT_3(!vector, msr->idx, vector, 0); + + if (vector || is_write_only_msr(msr->idx)) + goto done; + + if (msr->write) + GUEST_ASSERT_3(msr_val == msr->write_val, msr->idx, + msr_val, msr->write_val); + + /* Invariant TSC bit appears when TSC invariant control MSR is written to */ + if (msr->idx == HV_X64_MSR_TSC_INVARIANT_CONTROL) { + if (!this_cpu_has(HV_ACCESS_TSC_INVARIANT)) + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC)); + else + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC) == + !!(msr_val & HV_INVARIANT_TSC_EXPOSED)); + } + +done: GUEST_DONE(); } @@ -89,7 +121,6 @@ static void vcpu_reset_hv_cpuid(struct kvm_vcpu *vcpu) static void guest_test_msrs_access(void) { struct kvm_cpuid2 *prev_cpuid = NULL; - struct kvm_cpuid_entry2 *feat, *dbg; struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; @@ -97,6 +128,7 @@ static void guest_test_msrs_access(void) int stage = 0; vm_vaddr_t msr_gva; struct msr_data *msr; + bool has_invtsc = kvm_cpu_has(X86_FEATURE_INVTSC); while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_msr); @@ -116,9 +148,6 @@ static void guest_test_msrs_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); @@ -134,133 +163,139 @@ static void guest_test_msrs_access(void) * Only available when Hyper-V identification is set */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 1: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 2: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); /* * HV_X64_MSR_GUEST_OS_ID has to be written first to make * HV_X64_MSR_HYPERCALL available. */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 1; + msr->write = true; msr->write_val = HYPERV_LINUX_OS_ID; - msr->available = 1; + msr->fault_expected = false; break; case 3: msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 4: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 5: msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 6: - feat->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_RUNTIME_AVAILABLE); msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 7: /* Read only */ msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 8: msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 9: - feat->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_TIME_REF_COUNT_AVAILABLE); msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 10: /* Read only */ msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 11: msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 12: - feat->eax |= HV_MSR_VP_INDEX_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_INDEX_AVAILABLE); msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 13: /* Read only */ msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 14: msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 15: - feat->eax |= HV_MSR_RESET_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_RESET_AVAILABLE); msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 16: msr->idx = HV_X64_MSR_RESET; - msr->write = 1; + msr->write = true; + /* + * TODO: the test only writes '0' to HV_X64_MSR_RESET + * at the moment, writing some other value there will + * trigger real vCPU reset and the code is not prepared + * to handle it yet. + */ msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 17: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 18: - feat->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_REFERENCE_TSC_AVAILABLE); msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 19: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 20: msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 21: /* @@ -268,149 +303,185 @@ static void guest_test_msrs_access(void) * capability enabled and guest visible CPUID bit unset. */ msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 22: - feat->eax |= HV_MSR_SYNIC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNIC_AVAILABLE); msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 23: msr->idx = HV_X64_MSR_EOM; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 24: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 25: - feat->eax |= HV_MSR_SYNTIMER_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNTIMER_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 26: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 27: /* Direct mode test */ msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 0; + msr->fault_expected = true; break; case 28: - feat->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_STIMER_DIRECT_MODE_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 1; + msr->fault_expected = false; break; case 29: msr->idx = HV_X64_MSR_EOI; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 30: - feat->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_APIC_ACCESS_AVAILABLE); msr->idx = HV_X64_MSR_EOI; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 31: msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 32: - feat->eax |= HV_ACCESS_FREQUENCY_MSRS; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_FREQUENCY_MSRS); msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 33: /* Read only */ msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 34: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 35: - feat->eax |= HV_ACCESS_REENLIGHTENMENT; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_REENLIGHTENMENT); msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 36: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 37: /* Can only write '0' */ msr->idx = HV_X64_MSR_TSC_EMULATION_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 38: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 39: - feat->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE); msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 40: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 41: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 42: - feat->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_DEBUG_MSRS_AVAILABLE); + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 43: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 44: + /* MSR is not available when CPUID feature bit is unset */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = true; + break; + case 45: + /* MSR is vailable when CPUID feature bit is set */ + if (!has_invtsc) + continue; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT); + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = false; + break; + case 46: + /* Writing bits other than 0 is forbidden */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 0xdeadbeef; + msr->fault_expected = true; + break; + case 47: + /* Setting bit 0 enables the feature */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 1; + msr->fault_expected = false; + break; + + default: kvm_vm_free(vm); return; } @@ -429,7 +500,7 @@ static void guest_test_msrs_access(void) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "MSR = %lx, vector = %lx"); + REPORT_GUEST_ASSERT_3(uc, "MSR = %lx, arg1 = %lx, arg2 = %lx"); return; case UCALL_DONE: break; @@ -445,7 +516,6 @@ static void guest_test_msrs_access(void) static void guest_test_hcalls_access(void) { - struct kvm_cpuid_entry2 *feat, *recomm, *dbg; struct kvm_cpuid2 *prev_cpuid = NULL; struct kvm_vcpu *vcpu; struct kvm_run *run; @@ -480,15 +550,11 @@ static void guest_test_hcalls_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - recomm = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - run = vcpu->run; switch (stage) { case 0: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); hcall->control = 0xbeef; hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -498,7 +564,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 2: - feat->ebx |= HV_POST_MESSAGES; + vcpu_set_cpuid_feature(vcpu, HV_POST_MESSAGES); hcall->control = HVCALL_POST_MESSAGE; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -508,7 +574,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 4: - feat->ebx |= HV_SIGNAL_EVENTS; + vcpu_set_cpuid_feature(vcpu, HV_SIGNAL_EVENTS); hcall->control = HVCALL_SIGNAL_EVENT; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -518,12 +584,12 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; case 6: - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 7: - feat->ebx |= HV_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_OPERATION_DENIED; break; @@ -533,7 +599,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 9: - recomm->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; hcall->expect = HV_STATUS_SUCCESS; break; @@ -542,7 +608,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 11: - recomm->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; hcall->expect = HV_STATUS_SUCCESS; break; @@ -552,7 +618,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 13: - recomm->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_CLUSTER_IPI_RECOMMENDED); hcall->control = HVCALL_SEND_IPI; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -567,7 +633,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 16: - recomm->ebx = 0xfff; + vcpu_set_cpuid_feature(vcpu, HV_PV_SPINLOCKS_TEST); hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; hcall->expect = HV_STATUS_SUCCESS; break; @@ -577,12 +643,21 @@ static void guest_test_hcalls_access(void) hcall->ud_expected = true; break; case 18: - feat->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; hcall->ud_expected = false; hcall->expect = HV_STATUS_SUCCESS; break; case 19: + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 20: + vcpu_set_cpuid_feature(vcpu, HV_ENABLE_EXTENDED_HYPERCALLS); + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES | HV_HYPERCALL_FAST_BIT; + hcall->expect = HV_STATUS_INVALID_PARAMETER; + break; + case 21: kvm_vm_free(vm); return; } diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index fb02581953a3..ce1ccc4c1503 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -93,7 +93,7 @@ int main(void) { int warnings_before, warnings_after; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2de98fce7edd..bad7ef8c5b92 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -198,14 +198,15 @@ static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) static struct kvm_pmu_event_filter * -create_pmu_event_filter(const uint64_t event_list[], - int nevents, uint32_t action) +create_pmu_event_filter(const uint64_t event_list[], int nevents, + uint32_t action, uint32_t flags) { struct kvm_pmu_event_filter *f; int i; f = alloc_pmu_event_filter(nevents); f->action = action; + f->flags = flags; for (i = 0; i < nevents; i++) f->events[i] = event_list[i]; @@ -216,7 +217,7 @@ static struct kvm_pmu_event_filter *event_filter(uint32_t action) { return create_pmu_event_filter(event_list, ARRAY_SIZE(event_list), - action); + action, 0); } /* @@ -263,7 +264,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) struct kvm_pmu_event_filter *f; uint64_t count; - f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); count = test_with_filter(vcpu, f); free(f); @@ -363,7 +364,7 @@ static void test_pmu_config_disable(void (*guest_code)(void)) */ static bool use_intel_pmu(void) { - return is_intel_cpu() && + return host_cpu_is_intel && kvm_cpu_property(X86_PROPERTY_PMU_VERSION) && kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) && kvm_pmu_has(X86_PMU_FEATURE_BRANCH_INSNS_RETIRED); @@ -397,19 +398,378 @@ static bool use_amd_pmu(void) uint32_t family = kvm_cpu_family(); uint32_t model = kvm_cpu_model(); - return is_amd_cpu() && + return host_cpu_is_amd && (is_zen1(family, model) || is_zen2(family, model) || is_zen3(family, model)); } +/* + * "MEM_INST_RETIRED.ALL_LOADS", "MEM_INST_RETIRED.ALL_STORES", and + * "MEM_INST_RETIRED.ANY" from https://perfmon-events.intel.com/ + * supported on Intel Xeon processors: + * - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake. + */ +#define MEM_INST_RETIRED 0xD0 +#define MEM_INST_RETIRED_LOAD EVENT(MEM_INST_RETIRED, 0x81) +#define MEM_INST_RETIRED_STORE EVENT(MEM_INST_RETIRED, 0x82) +#define MEM_INST_RETIRED_LOAD_STORE EVENT(MEM_INST_RETIRED, 0x83) + +static bool supports_event_mem_inst_retired(void) +{ + uint32_t eax, ebx, ecx, edx; + + cpuid(1, &eax, &ebx, &ecx, &edx); + if (x86_family(eax) == 0x6) { + switch (x86_model(eax)) { + /* Sapphire Rapids */ + case 0x8F: + /* Ice Lake */ + case 0x6A: + /* Skylake */ + /* Cascade Lake */ + case 0x55: + return true; + } + } + + return false; +} + +/* + * "LS Dispatch", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + */ +#define LS_DISPATCH 0x29 +#define LS_DISPATCH_LOAD EVENT(LS_DISPATCH, BIT(0)) +#define LS_DISPATCH_STORE EVENT(LS_DISPATCH, BIT(1)) +#define LS_DISPATCH_LOAD_STORE EVENT(LS_DISPATCH, BIT(2)) + +#define INCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false) +#define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) + +struct perf_counter { + union { + uint64_t raw; + struct { + uint64_t loads:22; + uint64_t stores:22; + uint64_t loads_stores:20; + }; + }; +}; + +static uint64_t masked_events_guest_test(uint32_t msr_base) +{ + uint64_t ld0, ld1, st0, st1, ls0, ls1; + struct perf_counter c; + int val; + + /* + * The acutal value of the counters don't determine the outcome of + * the test. Only that they are zero or non-zero. + */ + ld0 = rdmsr(msr_base + 0); + st0 = rdmsr(msr_base + 1); + ls0 = rdmsr(msr_base + 2); + + __asm__ __volatile__("movl $0, %[v];" + "movl %[v], %%eax;" + "incl %[v];" + : [v]"+m"(val) :: "eax"); + + ld1 = rdmsr(msr_base + 0); + st1 = rdmsr(msr_base + 1); + ls1 = rdmsr(msr_base + 2); + + c.loads = ld1 - ld0; + c.stores = st1 - st0; + c.loads_stores = ls1 - ls0; + + return c.raw; +} + +static void intel_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + + wrmsr(MSR_P6_EVNTSEL0 + 0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD); + wrmsr(MSR_P6_EVNTSEL0 + 1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_STORE); + wrmsr(MSR_P6_EVNTSEL0 + 2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD_STORE); + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x7); + + r = masked_events_guest_test(MSR_IA32_PMC0); + + GUEST_SYNC(r); + } +} + +static void amd_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_K7_EVNTSEL0, 0); + wrmsr(MSR_K7_EVNTSEL1, 0); + wrmsr(MSR_K7_EVNTSEL2, 0); + + wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD); + wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_STORE); + wrmsr(MSR_K7_EVNTSEL2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD_STORE); + + r = masked_events_guest_test(MSR_K7_PERFCTR0); + + GUEST_SYNC(r); + } +} + +static struct perf_counter run_masked_events_test(struct kvm_vcpu *vcpu, + const uint64_t masked_events[], + const int nmasked_events) +{ + struct kvm_pmu_event_filter *f; + struct perf_counter r; + + f = create_pmu_event_filter(masked_events, nmasked_events, + KVM_PMU_EVENT_ALLOW, + KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + r.raw = test_with_filter(vcpu, f); + free(f); + + return r; +} + +/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ +#define MAX_FILTER_EVENTS 300 +#define MAX_TEST_EVENTS 10 + +#define ALLOW_LOADS BIT(0) +#define ALLOW_STORES BIT(1) +#define ALLOW_LOADS_STORES BIT(2) + +struct masked_events_test { + uint64_t intel_events[MAX_TEST_EVENTS]; + uint64_t intel_event_end; + uint64_t amd_events[MAX_TEST_EVENTS]; + uint64_t amd_event_end; + const char *msg; + uint32_t flags; +}; + +/* + * These are the test cases for the masked events tests. + * + * For each test, the guest enables 3 PMU counters (loads, stores, + * loads + stores). The filter is then set in KVM with the masked events + * provided. The test then verifies that the counters agree with which + * ones should be counting and which ones should be filtered. + */ +const struct masked_events_test test_cases[] = { + { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x81), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow loads.", + .flags = ALLOW_LOADS, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow stores.", + .flags = ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(2)), + }, + .msg = "Only allow loads + stores.", + .flags = ALLOW_LOADS_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, ~(BIT(0) | BIT(1)), 0), + }, + .msg = "Only allow loads and stores.", + .flags = ALLOW_LOADS | ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow loads and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFE, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow stores and loads + stores.", + .flags = ALLOW_STORES | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + }, + .msg = "Only allow loads, stores, and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_STORES | ALLOW_LOADS_STORES + }, +}; + +static int append_test_events(const struct masked_events_test *test, + uint64_t *events, int nevents) +{ + const uint64_t *evts; + int i; + + evts = use_intel_pmu() ? test->intel_events : test->amd_events; + for (i = 0; i < MAX_TEST_EVENTS; i++) { + if (evts[i] == 0) + break; + + events[nevents + i] = evts[i]; + } + + return nevents + i; +} + +static bool bool_eq(bool a, bool b) +{ + return a == b; +} + +static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, + int nevents) +{ + int ntests = ARRAY_SIZE(test_cases); + struct perf_counter c; + int i, n; + + for (i = 0; i < ntests; i++) { + const struct masked_events_test *test = &test_cases[i]; + + /* Do any test case events overflow MAX_TEST_EVENTS? */ + assert(test->intel_event_end == 0); + assert(test->amd_event_end == 0); + + n = append_test_events(test, events, nevents); + + c = run_masked_events_test(vcpu, events, n); + TEST_ASSERT(bool_eq(c.loads, test->flags & ALLOW_LOADS) && + bool_eq(c.stores, test->flags & ALLOW_STORES) && + bool_eq(c.loads_stores, + test->flags & ALLOW_LOADS_STORES), + "%s loads: %u, stores: %u, loads + stores: %u", + test->msg, c.loads, c.stores, c.loads_stores); + } +} + +static void add_dummy_events(uint64_t *events, int nevents) +{ + int i; + + for (i = 0; i < nevents; i++) { + int event_select = i % 0xFF; + bool exclude = ((i % 4) == 0); + + if (event_select == MEM_INST_RETIRED || + event_select == LS_DISPATCH) + event_select++; + + events[i] = KVM_PMU_ENCODE_MASKED_ENTRY(event_select, 0, + 0, exclude); + } +} + +static void test_masked_events(struct kvm_vcpu *vcpu) +{ + int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS; + uint64_t events[MAX_FILTER_EVENTS]; + + /* Run the test cases against a sparse PMU event filter. */ + run_masked_events_tests(vcpu, events, 0); + + /* Run the test cases against a dense PMU event filter. */ + add_dummy_events(events, MAX_FILTER_EVENTS); + run_masked_events_tests(vcpu, events, nevents); +} + +static int run_filter_test(struct kvm_vcpu *vcpu, const uint64_t *events, + int nevents, uint32_t flags) +{ + struct kvm_pmu_event_filter *f; + int r; + + f = create_pmu_event_filter(events, nevents, KVM_PMU_EVENT_ALLOW, flags); + r = __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); + free(f); + + return r; +} + +static void test_filter_ioctl(struct kvm_vcpu *vcpu) +{ + uint64_t e = ~0ul; + int r; + + /* + * Unfortunately having invalid bits set in event data is expected to + * pass when flags == 0 (bits other than eventsel+umask). + */ + r = run_filter_test(vcpu, &e, 1, 0); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); + + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r != 0, "Invalid PMU Event Filter is expected to fail"); + + e = KVM_PMU_ENCODE_MASKED_ENTRY(0xff, 0xff, 0xff, 0xf); + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); +} + int main(int argc, char *argv[]) { void (*guest_code)(void); - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); guest_code = use_intel_pmu() ? intel_guest_code : amd_guest_code; @@ -430,6 +790,17 @@ int main(int argc, char *argv[]) test_not_member_deny_list(vcpu); test_not_member_allow_list(vcpu); + if (use_intel_pmu() && + supports_event_mem_inst_retired() && + kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) >= 3) + vcpu2 = vm_vcpu_add(vm, 2, intel_masked_events_guest_code); + else if (use_amd_pmu()) + vcpu2 = vm_vcpu_add(vm, 2, amd_masked_events_guest_code); + + if (vcpu2) + test_masked_events(vcpu2); + test_filter_ioctl(vcpu); + kvm_vm_free(vm); test_pmu_config_disable(guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index 22d366c697f7..c9f67702f657 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -72,11 +72,16 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: - TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); + if (!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage + 1) + ksft_test_result_pass("stage %d passed\n", stage + 1); + else + ksft_test_result_fail( + "stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); return; case UCALL_DONE: + ksft_test_result_pass("stage %d passed\n", stage + 1); return; case UCALL_ABORT: REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); @@ -92,6 +97,9 @@ int main(void) struct kvm_vm *vm; uint64_t val; + ksft_print_header(); + ksft_set_plan(5); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; @@ -149,5 +157,5 @@ int main(void) kvm_vm_free(vm); - return 0; + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index 2641b286b4ed..ccdfa5dc1a4d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -111,7 +111,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index d7d37dae3eeb..396c13f42457 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -132,6 +132,59 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); } +static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) +{ + uint32_t apic_id, expected; + struct kvm_lapic_state xapic; + + vcpu_set_msr(vcpu, MSR_IA32_APICBASE, apic_base); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + + expected = apic_base & X2APIC_ENABLE ? vcpu->id : vcpu->id << 24; + apic_id = *((u32 *)&xapic.regs[APIC_ID]); + + TEST_ASSERT(apic_id == expected, + "APIC_ID not set back to %s format; wanted = %x, got = %x", + (apic_base & X2APIC_ENABLE) ? "x2APIC" : "xAPIC", + expected, apic_id); +} + +/* + * Verify that KVM switches the APIC_ID between xAPIC and x2APIC when userspace + * stuffs MSR_IA32_APICBASE. Setting the APIC_ID when x2APIC is enabled and + * when the APIC transitions for DISABLED to ENABLED is architectural behavior + * (on Intel), whereas the x2APIC => xAPIC transition behavior is KVM ABI since + * attempted to transition from x2APIC to xAPIC without disabling the APIC is + * architecturally disallowed. + */ +static void test_apic_id(void) +{ + const uint32_t NR_VCPUS = 3; + struct kvm_vcpu *vcpus[NR_VCPUS]; + uint64_t apic_base; + struct kvm_vm *vm; + int i; + + vm = vm_create_with_vcpus(NR_VCPUS, NULL, vcpus); + vm_enable_cap(vm, KVM_CAP_X2APIC_API, KVM_X2APIC_API_USE_32BIT_IDS); + + for (i = 0; i < NR_VCPUS; i++) { + apic_base = vcpu_get_msr(vcpus[i], MSR_IA32_APICBASE); + + TEST_ASSERT(apic_base & MSR_IA32_APICBASE_ENABLE, + "APIC not in ENABLED state at vCPU RESET"); + TEST_ASSERT(!(apic_base & X2APIC_ENABLE), + "APIC not in xAPIC mode at vCPU RESET"); + + __test_apic_id(vcpus[i], apic_base); + __test_apic_id(vcpus[i], apic_base | X2APIC_ENABLE); + __test_apic_id(vcpus[i], apic_base); + } + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct xapic_vcpu x = { @@ -157,4 +210,6 @@ int main(int argc, char *argv[]) virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); test_icr(&x); kvm_vm_free(vm); + + test_apic_id(); } diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 13c75dc18c10..5a3bf8f61417 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -19,9 +19,6 @@ #include <sys/eventfd.h> -/* Defined in include/linux/kvm_types.h */ -#define GPA_INVALID (~(ulong)0) - #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 @@ -412,21 +409,21 @@ static void *juggle_shinfo_state(void *arg) { struct kvm_vm *vm = (struct kvm_vm *)arg; - struct kvm_xen_hvm_attr cache_init = { + struct kvm_xen_hvm_attr cache_activate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE }; - struct kvm_xen_hvm_attr cache_destroy = { + struct kvm_xen_hvm_attr cache_deactivate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, - .u.shared_info.gfn = GPA_INVALID + .u.shared_info.gfn = KVM_XEN_INVALID_GFN }; for (;;) { - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate); pthread_testcancel(); - }; + } return NULL; } diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index d5dab986f612..b6c4be3faf7a 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -11,6 +11,7 @@ #include <fcntl.h> #include <linux/landlock.h> #include <sched.h> +#include <stdio.h> #include <string.h> #include <sys/capability.h> #include <sys/mount.h> @@ -89,6 +90,40 @@ static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; * └── s3d3 */ +static bool fgrep(FILE *const inf, const char *const str) +{ + char line[32]; + const int slen = strlen(str); + + while (!feof(inf)) { + if (!fgets(line, sizeof(line), inf)) + break; + if (strncmp(line, str, slen)) + continue; + + return true; + } + + return false; +} + +static bool supports_overlayfs(void) +{ + bool res; + FILE *const inf = fopen("/proc/filesystems", "r"); + + /* + * Consider that the filesystem is supported if we cannot get the + * supported ones. + */ + if (!inf) + return true; + + res = fgrep(inf, "nodev\toverlay\n"); + fclose(inf); + return res; +} + static void mkdir_parents(struct __test_metadata *const _metadata, const char *const path) { @@ -4001,6 +4036,9 @@ FIXTURE(layout2_overlay) {}; FIXTURE_SETUP(layout2_overlay) { + if (!supports_overlayfs()) + SKIP(return, "overlayfs is not supported"); + prepare_layout(_metadata); create_directory(_metadata, LOWER_BASE); @@ -4037,6 +4075,9 @@ FIXTURE_SETUP(layout2_overlay) FIXTURE_TEARDOWN(layout2_overlay) { + if (!supports_overlayfs()) + SKIP(return, "overlayfs is not supported"); + EXPECT_EQ(0, remove_path(lower_do1_fl3)); EXPECT_EQ(0, remove_path(lower_dl1_fl2)); EXPECT_EQ(0, remove_path(lower_fl1)); @@ -4068,6 +4109,9 @@ FIXTURE_TEARDOWN(layout2_overlay) TEST_F_FORK(layout2_overlay, no_restriction) { + if (!supports_overlayfs()) + SKIP(return, "overlayfs is not supported"); + ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY)); ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY)); ASSERT_EQ(0, test_open(lower_dl1_fl2, O_RDONLY)); @@ -4231,6 +4275,9 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) size_t i; const char *path_entry; + if (!supports_overlayfs()) + SKIP(return, "overlayfs is not supported"); + /* Sets rules on base directories (i.e. outside overlay scope). */ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base); ASSERT_LE(0, ruleset_fd); diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index c28ef98ff3ac..55e7871631a1 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -19,6 +19,12 @@ #include "common.h" +/* Copied from security/yama/yama_lsm.c */ +#define YAMA_SCOPE_DISABLED 0 +#define YAMA_SCOPE_RELATIONAL 1 +#define YAMA_SCOPE_CAPABILITY 2 +#define YAMA_SCOPE_NO_ATTACH 3 + static void create_domain(struct __test_metadata *const _metadata) { int ruleset_fd; @@ -60,6 +66,25 @@ static int test_ptrace_read(const pid_t pid) return 0; } +static int get_yama_ptrace_scope(void) +{ + int ret; + char buf[2] = {}; + const int fd = open("/proc/sys/kernel/yama/ptrace_scope", O_RDONLY); + + if (fd < 0) + return 0; + + if (read(fd, buf, 1) < 0) { + close(fd); + return -1; + } + + ret = atoi(buf); + close(fd); + return ret; +} + /* clang-format off */ FIXTURE(hierarchy) {}; /* clang-format on */ @@ -232,8 +257,51 @@ TEST_F(hierarchy, trace) pid_t child, parent; int status, err_proc_read; int pipe_child[2], pipe_parent[2]; + int yama_ptrace_scope; char buf_parent; long ret; + bool can_read_child, can_trace_child, can_read_parent, can_trace_parent; + + yama_ptrace_scope = get_yama_ptrace_scope(); + ASSERT_LE(0, yama_ptrace_scope); + + if (yama_ptrace_scope > YAMA_SCOPE_DISABLED) + TH_LOG("Incomplete tests due to Yama restrictions (scope %d)", + yama_ptrace_scope); + + /* + * can_read_child is true if a parent process can read its child + * process, which is only the case when the parent process is not + * isolated from the child with a dedicated Landlock domain. + */ + can_read_child = !variant->domain_parent; + + /* + * can_trace_child is true if a parent process can trace its child + * process. This depends on two conditions: + * - The parent process is not isolated from the child with a dedicated + * Landlock domain. + * - Yama allows tracing children (up to YAMA_SCOPE_RELATIONAL). + */ + can_trace_child = can_read_child && + yama_ptrace_scope <= YAMA_SCOPE_RELATIONAL; + + /* + * can_read_parent is true if a child process can read its parent + * process, which is only the case when the child process is not + * isolated from the parent with a dedicated Landlock domain. + */ + can_read_parent = !variant->domain_child; + + /* + * can_trace_parent is true if a child process can trace its parent + * process. This depends on two conditions: + * - The child process is not isolated from the parent with a dedicated + * Landlock domain. + * - Yama is disabled (YAMA_SCOPE_DISABLED). + */ + can_trace_parent = can_read_parent && + yama_ptrace_scope <= YAMA_SCOPE_DISABLED; /* * Removes all effective and permitted capabilities to not interfere @@ -264,16 +332,21 @@ TEST_F(hierarchy, trace) /* Waits for the parent to be in a domain, if any. */ ASSERT_EQ(1, read(pipe_parent[0], &buf_child, 1)); - /* Tests PTRACE_ATTACH and PTRACE_MODE_READ on the parent. */ + /* Tests PTRACE_MODE_READ on the parent. */ err_proc_read = test_ptrace_read(parent); + if (can_read_parent) { + EXPECT_EQ(0, err_proc_read); + } else { + EXPECT_EQ(EACCES, err_proc_read); + } + + /* Tests PTRACE_ATTACH on the parent. */ ret = ptrace(PTRACE_ATTACH, parent, NULL, 0); - if (variant->domain_child) { + if (can_trace_parent) { + EXPECT_EQ(0, ret); + } else { EXPECT_EQ(-1, ret); EXPECT_EQ(EPERM, errno); - EXPECT_EQ(EACCES, err_proc_read); - } else { - EXPECT_EQ(0, ret); - EXPECT_EQ(0, err_proc_read); } if (ret == 0) { ASSERT_EQ(parent, waitpid(parent, &status, 0)); @@ -283,11 +356,11 @@ TEST_F(hierarchy, trace) /* Tests child PTRACE_TRACEME. */ ret = ptrace(PTRACE_TRACEME); - if (variant->domain_parent) { + if (can_trace_child) { + EXPECT_EQ(0, ret); + } else { EXPECT_EQ(-1, ret); EXPECT_EQ(EPERM, errno); - } else { - EXPECT_EQ(0, ret); } /* @@ -296,7 +369,7 @@ TEST_F(hierarchy, trace) */ ASSERT_EQ(1, write(pipe_child[1], ".", 1)); - if (!variant->domain_parent) { + if (can_trace_child) { ASSERT_EQ(0, raise(SIGSTOP)); } @@ -321,7 +394,7 @@ TEST_F(hierarchy, trace) ASSERT_EQ(1, read(pipe_child[0], &buf_parent, 1)); /* Tests child PTRACE_TRACEME. */ - if (!variant->domain_parent) { + if (can_trace_child) { ASSERT_EQ(child, waitpid(child, &status, 0)); ASSERT_EQ(1, WIFSTOPPED(status)); ASSERT_EQ(0, ptrace(PTRACE_DETACH, child, NULL, 0)); @@ -331,17 +404,23 @@ TEST_F(hierarchy, trace) EXPECT_EQ(ESRCH, errno); } - /* Tests PTRACE_ATTACH and PTRACE_MODE_READ on the child. */ + /* Tests PTRACE_MODE_READ on the child. */ err_proc_read = test_ptrace_read(child); + if (can_read_child) { + EXPECT_EQ(0, err_proc_read); + } else { + EXPECT_EQ(EACCES, err_proc_read); + } + + /* Tests PTRACE_ATTACH on the child. */ ret = ptrace(PTRACE_ATTACH, child, NULL, 0); - if (variant->domain_parent) { + if (can_trace_child) { + EXPECT_EQ(0, ret); + } else { EXPECT_EQ(-1, ret); EXPECT_EQ(EPERM, errno); - EXPECT_EQ(EACCES, err_proc_read); - } else { - EXPECT_EQ(0, ret); - EXPECT_EQ(0, err_proc_read); } + if (ret == 0) { ASSERT_EQ(child, waitpid(child, &status, 0)); ASSERT_EQ(1, WIFSTOPPED(status)); diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile index 60826d7d37d4..471d83e61d95 100644 --- a/tools/testing/selftests/media_tests/Makefile +++ b/tools/testing/selftests/media_tests/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -CFLAGS += -I../ -I../../../../usr/include/ +CFLAGS += -I../ $(KHDR_INCLUDES) TEST_GEN_PROGS := media_device_test media_device_open video_device_test include ../lib.mk diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile index 34d1c81a2324..fc840e06ff56 100644 --- a/tools/testing/selftests/membarrier/Makefile +++ b/tools/testing/selftests/membarrier/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ +CFLAGS += -g $(KHDR_INCLUDES) LDLIBS += -lpthread TEST_GEN_PROGS := membarrier_test_single_thread \ diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 4da8b565fa32..163b6f68631c 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -1,8 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -D_FILE_OFFSET_BITS=64 -CFLAGS += -I../../../../include/uapi/ -CFLAGS += -I../../../../include/ -CFLAGS += -I../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := memfd_test TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c index be675002f918..93798c8c5d54 100644 --- a/tools/testing/selftests/memfd/fuse_test.c +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -22,6 +22,7 @@ #include <linux/falloc.h> #include <fcntl.h> #include <linux/memfd.h> +#include <linux/types.h> #include <sched.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 94df2692e6e4..ae71f15f790d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -28,12 +28,46 @@ #define MFD_DEF_SIZE 8192 #define STACK_SIZE 65536 +#define F_SEAL_EXEC 0x0020 + +#define F_WX_SEALS (F_SEAL_SHRINK | \ + F_SEAL_GROW | \ + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE | \ + F_SEAL_EXEC) + +#define MFD_NOEXEC_SEAL 0x0008U + /* * Default is not to test hugetlbfs */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; +static ssize_t fd2name(int fd, char *buf, size_t bufsize) +{ + char buf1[PATH_MAX]; + int size; + ssize_t nbytes; + + size = snprintf(buf1, PATH_MAX, "/proc/self/fd/%d", fd); + if (size < 0) { + printf("snprintf(%d) failed on %m\n", fd); + abort(); + } + + /* + * reserver one byte for string termination. + */ + nbytes = readlink(buf1, buf, bufsize-1); + if (nbytes == -1) { + printf("readlink(%s) failed %m\n", buf1); + abort(); + } + buf[nbytes] = '\0'; + return nbytes; +} + static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) { int r, fd; @@ -54,6 +88,37 @@ static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) return fd; } +static void sysctl_assert_write(const char *val) +{ + int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); + + if (fd < 0) { + printf("open sysctl failed\n"); + abort(); + } + + if (write(fd, val, strlen(val)) < 0) { + printf("write sysctl failed\n"); + abort(); + } +} + +static void sysctl_fail_write(const char *val) +{ + int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); + + if (fd < 0) { + printf("open sysctl failed\n"); + abort(); + } + + if (write(fd, val, strlen(val)) >= 0) { + printf("write sysctl %s succeeded, but failure expected\n", + val); + abort(); + } +} + static int mfd_assert_reopen_fd(int fd_in) { int fd; @@ -98,11 +163,14 @@ static unsigned int mfd_assert_get_seals(int fd) static void mfd_assert_has_seals(int fd, unsigned int seals) { + char buf[PATH_MAX]; + int nbytes; unsigned int s; + fd2name(fd, buf, PATH_MAX); s = mfd_assert_get_seals(fd); if (s != seals) { - printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd); + printf("%u != %u = GET_SEALS(%s)\n", seals, s, buf); abort(); } } @@ -594,6 +662,64 @@ static void mfd_fail_grow_write(int fd) } } +static void mfd_assert_mode(int fd, int mode) +{ + struct stat st; + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fstat(fd, &st) < 0) { + printf("fstat(%s) failed: %m\n", buf); + abort(); + } + + if ((st.st_mode & 07777) != mode) { + printf("fstat(%s) wrong file mode 0%04o, but expected 0%04o\n", + buf, (int)st.st_mode & 07777, mode); + abort(); + } +} + +static void mfd_assert_chmod(int fd, int mode) +{ + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fchmod(fd, mode) < 0) { + printf("fchmod(%s, 0%04o) failed: %m\n", buf, mode); + abort(); + } + + mfd_assert_mode(fd, mode); +} + +static void mfd_fail_chmod(int fd, int mode) +{ + struct stat st; + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fstat(fd, &st) < 0) { + printf("fstat(%s) failed: %m\n", buf); + abort(); + } + + if (fchmod(fd, mode) == 0) { + printf("fchmod(%s, 0%04o) didn't fail as expected\n", + buf, mode); + abort(); + } + + /* verify that file mode bits did not change */ + mfd_assert_mode(fd, st.st_mode & 07777); +} + static int idle_thread_fn(void *arg) { sigset_t set; @@ -671,6 +797,9 @@ static void test_create(void) mfd_fail_new("", ~0); mfd_fail_new("", 0x80000000U); + /* verify EXEC and NOEXEC_SEAL can't both be set */ + mfd_fail_new("", MFD_EXEC | MFD_NOEXEC_SEAL); + /* verify MFD_CLOEXEC is allowed */ fd = mfd_assert_new("", 0, MFD_CLOEXEC); close(fd); @@ -881,6 +1010,211 @@ static void test_seal_resize(void) } /* + * Test SEAL_EXEC + * Test fd is created with exec and allow sealing. + * chmod() cannot change x bits after sealing. + */ +static void test_exec_seal(void) +{ + int fd; + + printf("%s SEAL-EXEC\n", memfd_str); + + printf("%s Apply SEAL_EXEC\n", memfd_str); + fd = mfd_assert_new("kern_memfd_seal_exec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_EXEC); + + mfd_assert_mode(fd, 0777); + mfd_assert_chmod(fd, 0644); + + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_EXEC); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + + mfd_assert_chmod(fd, 0600); + mfd_fail_chmod(fd, 0777); + mfd_fail_chmod(fd, 0670); + mfd_fail_chmod(fd, 0605); + mfd_fail_chmod(fd, 0700); + mfd_fail_chmod(fd, 0100); + mfd_assert_chmod(fd, 0666); + mfd_assert_write(fd); + close(fd); + + printf("%s Apply ALL_SEALS\n", memfd_str); + fd = mfd_assert_new("kern_memfd_seal_exec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_EXEC); + + mfd_assert_mode(fd, 0777); + mfd_assert_chmod(fd, 0700); + + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_EXEC); + mfd_assert_has_seals(fd, F_WX_SEALS); + + mfd_fail_chmod(fd, 0711); + mfd_fail_chmod(fd, 0600); + mfd_fail_write(fd); + close(fd); +} + +/* + * Test EXEC_NO_SEAL + * Test fd is created with exec and not allow sealing. + */ +static void test_exec_no_seal(void) +{ + int fd; + + printf("%s EXEC_NO_SEAL\n", memfd_str); + + /* Create with EXEC but without ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_exec_no_sealing", + mfd_def_size, + MFD_CLOEXEC | MFD_EXEC); + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + mfd_assert_chmod(fd, 0666); + close(fd); +} + +/* + * Test memfd_create with MFD_NOEXEC flag + */ +static void test_noexec_seal(void) +{ + int fd; + + printf("%s NOEXEC_SEAL\n", memfd_str); + + /* Create with NOEXEC and ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); + + /* Create with NOEXEC but without ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); +} + +static void test_sysctl_child(void) +{ + int fd; + + printf("%s sysctl 0\n", memfd_str); + sysctl_assert_write("0"); + fd = mfd_assert_new("kern_memfd_sysctl_0", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, 0); + mfd_assert_chmod(fd, 0644); + close(fd); + + printf("%s sysctl 1\n", memfd_str); + sysctl_assert_write("1"); + fd = mfd_assert_new("kern_memfd_sysctl_1", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + sysctl_fail_write("0"); + close(fd); + + printf("%s sysctl 2\n", memfd_str); + sysctl_assert_write("2"); + mfd_fail_new("kern_memfd_sysctl_2", + MFD_CLOEXEC | MFD_ALLOW_SEALING); + sysctl_fail_write("0"); + sysctl_fail_write("1"); +} + +static int newpid_thread_fn(void *arg) +{ + test_sysctl_child(); + return 0; +} + +static void test_sysctl_child2(void) +{ + int fd; + + sysctl_fail_write("0"); + fd = mfd_assert_new("kern_memfd_sysctl_1", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); +} + +static int newpid_thread_fn2(void *arg) +{ + test_sysctl_child2(); + return 0; +} +static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(fn, + stack + STACK_SIZE, + SIGCHLD | flags, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_newpid_thread(pid_t pid) +{ + waitpid(pid, NULL, 0); +} + +/* + * Test sysctl + * A very basic sealing test to see whether setting/retrieving seals works. + */ +static void test_sysctl(void) +{ + int pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn); + + join_newpid_thread(pid); + + printf("%s child ns\n", memfd_str); + sysctl_assert_write("1"); + + pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); + join_newpid_thread(pid); +} + +/* * Test sharing via dup() * Test that seals are shared between dupped FDs and they're all equal. */ @@ -1053,6 +1387,9 @@ int main(int argc, char **argv) test_create(); test_basic(); + test_exec_seal(); + test_exec_no_seal(); + test_noexec_seal(); test_seal_write(); test_seal_future_write(); @@ -1074,6 +1411,8 @@ int main(int argc, char **argv) test_share_fork("SHARE-FORK", SHARED_FT_STR); join_idle_thread(pid); + test_sysctl(); + printf("memfd: DONE\n"); return 0; diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/mm/.gitignore index 1f8c36a9fa10..1f8c36a9fa10 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/mm/Makefile index 89c14e41bd43..c31d952cff68 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -1,11 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 -# Makefile for vm selftests +# Makefile for mm selftests -LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h +LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) +else +uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') +endif MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') # Without this, failed build products remain, with up-to-date timestamps, @@ -25,7 +29,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/usr/include $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test @@ -56,6 +60,7 @@ TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_PROGS += ksm_functional_tests +TEST_GEN_PROGS += mdwe_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index a5cb4b09a46c..a5cb4b09a46c 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh diff --git a/tools/testing/selftests/vm/check_config.sh b/tools/testing/selftests/mm/check_config.sh index bcba3af0acea..bcba3af0acea 100644 --- a/tools/testing/selftests/vm/check_config.sh +++ b/tools/testing/selftests/mm/check_config.sh diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 9b420140ba2b..9b420140ba2b 100644 --- a/tools/testing/selftests/vm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/mm/config index be087c4bc396..be087c4bc396 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/mm/config diff --git a/tools/testing/selftests/vm/cow.c b/tools/testing/selftests/mm/cow.c index 26f6ea3079e2..0eb2e8180aa5 100644 --- a/tools/testing/selftests/vm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -30,6 +30,13 @@ #include "../kselftest.h" #include "vm_util.h" +#ifndef MADV_PAGEOUT +#define MADV_PAGEOUT 21 +#endif +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif + static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -1178,6 +1185,228 @@ static int tests_per_anon_test_case(void) return tests; } +enum anon_thp_collapse_test { + ANON_THP_COLLAPSE_UNSHARED, + ANON_THP_COLLAPSE_FULLY_SHARED, + ANON_THP_COLLAPSE_LOWER_SHARED, + ANON_THP_COLLAPSE_UPPER_SHARED, +}; + +static void do_test_anon_thp_collapse(char *mem, size_t size, + enum anon_thp_collapse_test test) +{ + struct comm_pipes comm_pipes; + char buf; + int ret; + + ret = setup_comm_pipes(&comm_pipes); + if (ret) { + ksft_test_result_fail("pipe() failed\n"); + return; + } + + /* + * Trigger PTE-mapping the THP by temporarily mapping a single subpage + * R/O, such that we can try collapsing it later. + */ + ret = mprotect(mem + pagesize, pagesize, PROT_READ); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + /* Collapse before actually COW-sharing the page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* COW-share the full PTE-mapped THP. */ + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* Don't COW-share the upper part of the THP. */ + ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + /* Don't COW-share the lower part of the THP. */ + ret = madvise(mem, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + ret = fork(); + if (ret < 0) { + ksft_test_result_fail("fork() failed\n"); + goto close_comm_pipes; + } else if (!ret) { + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + case ANON_THP_COLLAPSE_FULLY_SHARED: + exit(child_memcmp_fn(mem, size, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + exit(child_memcmp_fn(mem, size / 2, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + exit(child_memcmp_fn(mem + size / 2, size / 2, + &comm_pipes)); + break; + default: + assert(false); + } + } + + while (read(comm_pipes.child_ready[0], &buf, 1) != 1) + ; + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* + * Revert MADV_DONTFORK such that we merge the VMAs and are + * able to actually collapse. + */ + ret = madvise(mem, size, MADV_DOFORK); + if (ret) { + ksft_test_result_fail("MADV_DOFORK failed\n"); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + /* FALLTHROUGH */ + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* Collapse before anyone modified the COW-shared page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + /* Modify the page. */ + memset(mem, 0xff, size); + write(comm_pipes.parent_ready[1], "0", 1); + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + + ksft_test_result(!ret, "No leak from parent into child\n"); +close_comm_pipes: + close_comm_pipes(&comm_pipes); +} + +static void test_anon_thp_collapse_unshared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UNSHARED); +} + +static void test_anon_thp_collapse_fully_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_FULLY_SHARED); +} + +static void test_anon_thp_collapse_lower_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_LOWER_SHARED); +} + +static void test_anon_thp_collapse_upper_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UPPER_SHARED); +} + +/* + * Test cases that are specific to anonymous THP: pages in private mappings + * that may get shared via COW during fork(). + */ +static const struct test_case anon_thp_test_cases[] = { + /* + * Basic COW test for fork() without any GUP when collapsing a THP + * before fork(). + * + * Re-mapping a PTE-mapped anon THP using a single PMD ("in-place + * collapse") might easily get COW handling wrong when not collapsing + * exclusivity information properly. + */ + { + "Basic COW after fork() when collapsing before fork()", + test_anon_thp_collapse_unshared, + }, + /* Basic COW test, but collapse after COW-sharing a full THP. */ + { + "Basic COW after fork() when collapsing after fork() (fully shared)", + test_anon_thp_collapse_fully_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the lower half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (lower shared)", + test_anon_thp_collapse_lower_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the upper half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (upper shared)", + test_anon_thp_collapse_upper_shared, + }, +}; + +static void run_anon_thp_test_cases(void) +{ + int i; + + if (!thpsize) + return; + + ksft_print_msg("[INFO] Anonymous THP tests\n"); + + for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) { + struct test_case const *test_case = &anon_thp_test_cases[i]; + + ksft_print_msg("[RUN] %s\n", test_case->desc); + do_run_with_thp(test_case->fn, THP_RUN_PMD); + } +} + +static int tests_per_anon_thp_test_case(void) +{ + return thpsize ? 1 : 0; +} + typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); static void test_cow(char *mem, const char *smem, size_t size) @@ -1518,6 +1747,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); @@ -1526,6 +1756,7 @@ int main(int argc, char **argv) ksft_exit_fail_msg("opening pagemap failed\n"); run_anon_test_cases(); + run_anon_thp_test_cases(); run_non_anon_test_cases(); err = ksft_get_fail_cnt(); diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index e43879291dac..e43879291dac 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 4adaad1b822f..4adaad1b822f 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c diff --git a/tools/testing/selftests/vm/hugepage-mmap.c b/tools/testing/selftests/mm/hugepage-mmap.c index 955ef87f382c..955ef87f382c 100644 --- a/tools/testing/selftests/vm/hugepage-mmap.c +++ b/tools/testing/selftests/mm/hugepage-mmap.c diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index e53b5eaa8fce..e53b5eaa8fce 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c diff --git a/tools/testing/selftests/vm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index e2527f32005b..e2527f32005b 100644 --- a/tools/testing/selftests/vm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 557bdbd4f87e..557bdbd4f87e 100644 --- a/tools/testing/selftests/vm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 9a127a8fe176..9a127a8fe176 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index bf2d2a684edf..bf2d2a684edf 100644 --- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 64126c8cd561..64126c8cd561 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c diff --git a/tools/testing/selftests/vm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index b11b7e5115dc..d8b5b4930412 100644 --- a/tools/testing/selftests/vm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -37,7 +37,7 @@ static bool range_maps_duplicates(char *addr, unsigned long size) /* * There is no easy way to check if there are KSM pages mapped into * this range. We only check that the range does not map the same PFN - * twice by comaring each pair of mapped pages. + * twice by comparing each pair of mapped pages. */ for (offs_a = 0; offs_a < size; offs_a += pagesize) { pfn_a = pagemap_get_pfn(pagemap_fd, addr + offs_a); diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index f9eb4d67e0dd..f9eb4d67e0dd 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 262eae6b58f2..262eae6b58f2 100644 --- a/tools/testing/selftests/vm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index eed44322d1a6..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 312889edb84a..312889edb84a 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c diff --git a/tools/testing/selftests/vm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 6b8aeaa0bf7a..6b8aeaa0bf7a 100644 --- a/tools/testing/selftests/vm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c new file mode 100644 index 000000000000..f466a099f1bf --- /dev/null +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef __aarch64__ +#include <asm/hwcap.h> +#endif + +#include <linux/mman.h> +#include <linux/prctl.h> + +#include <stdio.h> +#include <stdlib.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +#ifndef __aarch64__ +# define PROT_BTI 0 +#endif + +TEST(prctl_flags) +{ + EXPECT_LT(prctl(PR_SET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 0L, 7L), 0); + + EXPECT_LT(prctl(PR_GET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 0L, 7L), 0); +} + +FIXTURE(mdwe) +{ + void *p; + int flags; + size_t size; + pid_t pid; +}; + +FIXTURE_VARIANT(mdwe) +{ + bool enabled; + bool forked; +}; + +FIXTURE_VARIANT_ADD(mdwe, stock) +{ + .enabled = false, + .forked = false, +}; + +FIXTURE_VARIANT_ADD(mdwe, enabled) +{ + .enabled = true, + .forked = false, +}; + +FIXTURE_VARIANT_ADD(mdwe, forked) +{ + .enabled = true, + .forked = true, +}; + +FIXTURE_SETUP(mdwe) +{ + int ret, status; + + self->p = NULL; + self->flags = MAP_SHARED | MAP_ANONYMOUS; + self->size = getpagesize(); + + if (!variant->enabled) + return; + + ret = prctl(PR_SET_MDWE, PR_MDWE_REFUSE_EXEC_GAIN, 0L, 0L, 0L); + ASSERT_EQ(ret, 0) { + TH_LOG("PR_SET_MDWE failed or unsupported"); + } + + ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); + ASSERT_EQ(ret, 1); + + if (variant->forked) { + self->pid = fork(); + ASSERT_GE(self->pid, 0) { + TH_LOG("fork failed\n"); + } + + if (self->pid > 0) { + ret = waitpid(self->pid, &status, 0); + ASSERT_TRUE(WIFEXITED(status)); + exit(WEXITSTATUS(status)); + } + } +} + +FIXTURE_TEARDOWN(mdwe) +{ + if (self->p && self->p != MAP_FAILED) + munmap(self->p, self->size); +} + +TEST_F(mdwe, mmap_READ_EXEC) +{ + self->p = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0); + EXPECT_NE(self->p, MAP_FAILED); +} + +TEST_F(mdwe, mmap_WRITE_EXEC) +{ + self->p = mmap(NULL, self->size, PROT_WRITE | PROT_EXEC, self->flags, 0, 0); + if (variant->enabled) { + EXPECT_EQ(self->p, MAP_FAILED); + } else { + EXPECT_NE(self->p, MAP_FAILED); + } +} + +TEST_F(mdwe, mprotect_stay_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); + EXPECT_EQ(ret, 0); +} + +TEST_F(mdwe, mprotect_add_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); + if (variant->enabled) { + EXPECT_LT(ret, 0); + } else { + EXPECT_EQ(ret, 0); + } +} + +TEST_F(mdwe, mprotect_WRITE_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_WRITE, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_WRITE | PROT_EXEC); + if (variant->enabled) { + EXPECT_LT(ret, 0); + } else { + EXPECT_EQ(ret, 0); + } +} + +TEST_F(mdwe, mmap_FIXED) +{ + void *p, *p2; + + p2 = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0); + self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + p = mmap(self->p + self->size, self->size, PROT_READ | PROT_EXEC, + self->flags | MAP_FIXED, 0, 0); + if (variant->enabled) { + EXPECT_EQ(p, MAP_FAILED); + } else { + EXPECT_EQ(p, self->p); + } +} + +TEST_F(mdwe, arm64_BTI) +{ + int ret; + +#ifdef __aarch64__ + if (!(getauxval(AT_HWCAP2) & HWCAP2_BTI)) +#endif + SKIP(return, "HWCAP2_BTI not supported"); + + self->p = mmap(NULL, self->size, PROT_EXEC, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_EXEC | PROT_BTI); + EXPECT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c729..957b9e18c729 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c diff --git a/tools/testing/selftests/vm/migration.c b/tools/testing/selftests/mm/migration.c index 1cec8425e3ca..1cec8425e3ca 100644 --- a/tools/testing/selftests/vm/migration.c +++ b/tools/testing/selftests/mm/migration.c diff --git a/tools/testing/selftests/vm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 782ea94dee2f..782ea94dee2f 100644 --- a/tools/testing/selftests/vm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 11b2301f3aa3..11b2301f3aa3 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c diff --git a/tools/testing/selftests/vm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 2a6e76c226bc..2a6e76c226bc 100644 --- a/tools/testing/selftests/vm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 6c62966ab5db..6c62966ab5db 100644 --- a/tools/testing/selftests/vm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c diff --git a/tools/testing/selftests/vm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index f01dc4a85b0b..f01dc4a85b0b 100644 --- a/tools/testing/selftests/vm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 9496346973d4..5c3773de9f0f 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -119,47 +119,109 @@ static unsigned long long get_mmap_min_addr(void) } /* - * This test validates that merge is called when expanding a mapping. - * Mapping containing three pages is created, middle page is unmapped - * and then the mapping containing the first page is expanded so that - * it fills the created hole. The two parts should merge creating - * single mapping with three pages. + * Using /proc/self/maps, assert that the specified address range is contained + * within a single mapping. */ -static void mremap_expand_merge(unsigned long page_size) +static bool is_range_mapped(FILE *maps_fp, void *start, void *end) { - char *test_name = "mremap expand merge"; - FILE *fp; char *line = NULL; size_t len = 0; bool success = false; - char *start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - - munmap(start + page_size, page_size); - mremap(start, page_size, 2 * page_size, 0); - fp = fopen("/proc/self/maps", "r"); - if (fp == NULL) { - ksft_test_result_fail("%s\n", test_name); - return; - } + rewind(maps_fp); - while (getline(&line, &len, fp) != -1) { + while (getline(&line, &len, maps_fp) != -1) { char *first = strtok(line, "- "); void *first_val = (void *)strtol(first, NULL, 16); char *second = strtok(NULL, "- "); void *second_val = (void *) strtol(second, NULL, 16); - if (first_val == start && second_val == start + 3 * page_size) { + if (first_val <= start && second_val >= end) { success = true; break; } } + + return success; +} + +/* + * This test validates that merge is called when expanding a mapping. + * Mapping containing three pages is created, middle page is unmapped + * and then the mapping containing the first page is expanded so that + * it fills the created hole. The two parts should merge creating + * single mapping with three pages. + */ +static void mremap_expand_merge(FILE *maps_fp, unsigned long page_size) +{ + char *test_name = "mremap expand merge"; + bool success = false; + char *remap, *start; + + start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (start == MAP_FAILED) { + ksft_print_msg("mmap failed: %s\n", strerror(errno)); + goto out; + } + + munmap(start + page_size, page_size); + remap = mremap(start, page_size, 2 * page_size, 0); + if (remap == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + munmap(start, page_size); + munmap(start + 2 * page_size, page_size); + goto out; + } + + success = is_range_mapped(maps_fp, start, start + 3 * page_size); + munmap(start, 3 * page_size); + +out: + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} + +/* + * Similar to mremap_expand_merge() except instead of removing the middle page, + * we remove the last then attempt to remap offset from the second page. This + * should result in the mapping being restored to its former state. + */ +static void mremap_expand_merge_offset(FILE *maps_fp, unsigned long page_size) +{ + + char *test_name = "mremap expand merge offset"; + bool success = false; + char *remap, *start; + + start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (start == MAP_FAILED) { + ksft_print_msg("mmap failed: %s\n", strerror(errno)); + goto out; + } + + /* Unmap final page to ensure we have space to expand. */ + munmap(start + 2 * page_size, page_size); + remap = mremap(start + page_size, page_size, 2 * page_size, 0); + if (remap == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + munmap(start, 2 * page_size); + goto out; + } + + success = is_range_mapped(maps_fp, start, start + 3 * page_size); + munmap(start, 3 * page_size); + +out: if (success) ksft_test_result_pass("%s\n", test_name); else ksft_test_result_fail("%s\n", test_name); - fclose(fp); } /* @@ -380,11 +442,12 @@ int main(int argc, char **argv) int i, run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; unsigned int pattern_seed; - int num_expand_tests = 1; + int num_expand_tests = 2; struct test test_cases[MAX_TEST]; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; time_t t; + FILE *maps_fp; pattern_seed = (unsigned int) time(&t); @@ -458,7 +521,17 @@ int main(int argc, char **argv) run_mremap_test_case(test_cases[i], &failures, threshold_mb, pattern_seed); - mremap_expand_merge(page_size); + maps_fp = fopen("/proc/self/maps", "r"); + + if (maps_fp == NULL) { + ksft_print_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); + exit(KSFT_FAIL); + } + + mremap_expand_merge(maps_fp, page_size); + mremap_expand_merge_offset(maps_fp, page_size); + + fclose(maps_fp); if (run_perf_tests) { ksft_print_msg("\n%s\n", diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 634d87dfb2a4..634d87dfb2a4 100644 --- a/tools/testing/selftests/vm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index 92f3be3dd8e5..92f3be3dd8e5 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1ebb586b2fbc..1ebb586b2fbc 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 72c14cd3ddc7..72c14cd3ddc7 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 95f403a0c46d..95f403a0c46d 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..8984e0bb58c7 100755..100644 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh diff --git a/tools/testing/selftests/vm/settings b/tools/testing/selftests/mm/settings index 9abfc60e9e6f..9abfc60e9e6f 100644 --- a/tools/testing/selftests/vm/settings +++ b/tools/testing/selftests/mm/settings diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 21d8830c5f24..21d8830c5f24 100644 --- a/tools/testing/selftests/vm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 76e1c36dd9e5..76e1c36dd9e5 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/mm/test_hmm.sh index 46e19b5d648d..46e19b5d648d 100755..100644 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/mm/test_hmm.sh diff --git a/tools/testing/selftests/vm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh index d73b846736f1..d73b846736f1 100755..100644 --- a/tools/testing/selftests/vm/test_vmalloc.sh +++ b/tools/testing/selftests/mm/test_vmalloc.sh diff --git a/tools/testing/selftests/vm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 361ef7192cc6..361ef7192cc6 100644 --- a/tools/testing/selftests/vm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index e3f00adb1b82..e3f00adb1b82 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 7f22844ed704..7f22844ed704 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c diff --git a/tools/testing/selftests/vm/util.h b/tools/testing/selftests/mm/util.h index b27d26199334..b27d26199334 100644 --- a/tools/testing/selftests/vm/util.h +++ b/tools/testing/selftests/mm/util.h diff --git a/tools/testing/selftests/vm/va_128TBswitch.c b/tools/testing/selftests/mm/va_128TBswitch.c index 1d2068989883..1d2068989883 100644 --- a/tools/testing/selftests/vm/va_128TBswitch.c +++ b/tools/testing/selftests/mm/va_128TBswitch.c diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/mm/va_128TBswitch.sh index 41580751dc51..41580751dc51 100755..100644 --- a/tools/testing/selftests/vm/va_128TBswitch.sh +++ b/tools/testing/selftests/mm/va_128TBswitch.sh diff --git a/tools/testing/selftests/vm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index c0592646ed93..c0592646ed93 100644 --- a/tools/testing/selftests/vm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 40e795624ff3..40e795624ff3 100644 --- a/tools/testing/selftests/vm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 1995ee911ef2..1995ee911ef2 100644 --- a/tools/testing/selftests/vm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..70a02301f4c2 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 6a2caba19ee1..6a2caba19ee1 100644 --- a/tools/testing/selftests/vm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c diff --git a/tools/testing/selftests/mount_setattr/Makefile b/tools/testing/selftests/mount_setattr/Makefile index 2250f7dcb81e..0c0d7b1234c1 100644 --- a/tools/testing/selftests/mount_setattr/Makefile +++ b/tools/testing/selftests/mount_setattr/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for mount selftests. -CFLAGS = -g -I../../../../usr/include/ -Wall -O2 -pthread +CFLAGS = -g $(KHDR_INCLUDES) -Wall -O2 -pthread -TEST_GEN_FILES += mount_setattr_test +TEST_GEN_PROGS := mount_setattr_test include ../lib.mk diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 8c5fea68ae67..582669ca38e9 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -103,13 +103,6 @@ #else #define __NR_mount_setattr 442 #endif - -struct mount_attr { - __u64 attr_set; - __u64 attr_clr; - __u64 propagation; - __u64 userns_fd; -}; #endif #ifndef __NR_open_tree diff --git a/tools/testing/selftests/move_mount_set_group/Makefile b/tools/testing/selftests/move_mount_set_group/Makefile index 80c2d86812b0..94235846b6f9 100644 --- a/tools/testing/selftests/move_mount_set_group/Makefile +++ b/tools/testing/selftests/move_mount_set_group/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for mount selftests. -CFLAGS = -g -I../../../../usr/include/ -Wall -O2 +CFLAGS = -g $(KHDR_INCLUDES) -Wall -O2 TEST_GEN_FILES += move_mount_set_group_test diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3007e98a6d64..6cd8993454d7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -38,6 +38,7 @@ TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += srv6_hencap_red_l3vpn_test.sh TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh +TEST_PROGS += srv6_end_flavors_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS += ndisc_unsolicited_na_test.sh @@ -45,6 +46,8 @@ TEST_PROGS += arp_ndisc_untracked_subnets.sh TEST_PROGS += stress_reuseport_listen.sh TEST_PROGS += l2_tos_ttl_inherit.sh TEST_PROGS += bind_bhash.sh +TEST_PROGS += ip_local_port_range.sh +TEST_PROGS += rps_default_mask.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest @@ -75,14 +78,61 @@ TEST_GEN_PROGS += so_incoming_cpu TEST_PROGS += sctp_vrf.sh TEST_GEN_FILES += sctp_hello TEST_GEN_FILES += csum +TEST_GEN_FILES += nat6to4.o +TEST_GEN_FILES += ip_local_port_range TEST_FILES := settings include ../lib.mk -include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf + $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +EXTRA_CLEAN := $(SCRATCH_DIR) diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile deleted file mode 100644 index 4abaf16d2077..000000000000 --- a/tools/testing/selftests/net/bpf/Makefile +++ /dev/null @@ -1,51 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -CLANG ?= clang -SCRATCH_DIR := $(OUTPUT)/tools -BUILD_DIR := $(SCRATCH_DIR)/build -BPFDIR := $(abspath ../../../lib/bpf) -APIDIR := $(abspath ../../../include/uapi) - -CCINCLUDE += -I../../bpf -CCINCLUDE += -I../../../../../usr/include/ -CCINCLUDE += -I$(SCRATCH_DIR)/include - -BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a - -MAKE_DIRS := $(BUILD_DIR)/libbpf $(OUTPUT)/bpf -$(MAKE_DIRS): - mkdir -p $@ - -TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o -all: $(TEST_CUSTOM_PROGS) - -# Get Clang's default includes on this system, as opposed to those seen by -# '-target bpf'. This fixes "missing" files on some architectures/distros, -# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. -# -# Use '-idirafter': Don't interfere with include mechanics except where the -# build would have failed anyways. -define get_sys_includes -$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ -$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') -endef - -ifneq ($(CROSS_COMPILE),) -CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) -endif - -CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) - -$(TEST_CUSTOM_PROGS): $(OUTPUT)/%.o: %.c $(BPFOBJ) | $(MAKE_DIRS) - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ - -$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ - $(APIDIR)/linux/bpf.h \ - | $(BUILD_DIR)/libbpf - $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ - EXTRA_CFLAGS='-g -O0' \ - DESTDIR=$(SCRATCH_DIR) prefix= all install_headers - -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) - diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index bd89198cd817..cc9fd55ab869 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -3,6 +3,9 @@ CONFIG_NET_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y +CONFIG_RPS=y +CONFIG_SYSFS=y +CONFIG_PROC_SYSCTL=y CONFIG_NET_VRF=y CONFIG_NET_L3_MASTER_DEV=y CONFIG_IPV6=y diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5637b5dadabd..7da8ec838c63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,7 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" +TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" VERBOSE=0 PAUSE_ON_FAIL=no @@ -655,6 +655,98 @@ fib_nexthop_test() cleanup } +fib6_notify_test() +{ + setup + + echo + echo "Fib6 info length calculation in route notify test" + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP -6 address add 2001:$i::1/64 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP -6 route add 2001::/64 \ + nexthop via 2001:10::2 dev dummy_10 \ + nexthop encap ip6 dst 2002::20 via 2001:20::2 dev dummy_20 \ + nexthop encap ip6 dst 2002::30 via 2001:30::2 dev dummy_30 \ + nexthop encap ip6 dst 2002::40 via 2001:40::2 dev dummy_40 \ + nexthop encap ip6 dst 2002::50 via 2001:50::2 dev dummy_50 \ + nexthop encap ip6 dst 2002::60 via 2001:60::2 dev dummy_60 \ + nexthop encap ip6 dst 2002::70 via 2001:70::2 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv6 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + #rm errors.txt + + cleanup &> /dev/null +} + + +fib_notify_test() +{ + setup + + echo + echo "Fib4 info length calculation in route notify test" + + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP address add 20.20.$i.2/24 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP route add 10.0.0.0/24 \ + nexthop via 20.20.10.1 dev dummy_10 \ + nexthop encap ip dst 192.168.10.20 via 20.20.20.1 dev dummy_20 \ + nexthop encap ip dst 192.168.10.30 via 20.20.30.1 dev dummy_30 \ + nexthop encap ip dst 192.168.10.40 via 20.20.40.1 dev dummy_40 \ + nexthop encap ip dst 192.168.10.50 via 20.20.50.1 dev dummy_50 \ + nexthop encap ip dst 192.168.10.60 via 20.20.60.1 dev dummy_60 \ + nexthop encap ip dst 192.168.10.70 via 20.20.70.1 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv4 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + rm errors.txt + + cleanup &> /dev/null +} + fib_suppress_test() { echo @@ -2065,6 +2157,8 @@ EOF ################################################################################ # main +trap cleanup EXIT + while getopts :t:pPhv o do case $o in @@ -2109,6 +2203,8 @@ do fib_carrier_test|carrier) fib_carrier_test;; fib_rp_filter_test|rp_filter) fib_rp_filter_test;; fib_nexthop_test|nexthop) fib_nexthop_test;; + fib_notify_test|ipv4_notify) fib_notify_test;; + fib6_notify_test|ipv6_notify) fib6_notify_test;; fib_suppress_test|suppress) fib_suppress_test;; ipv6_route_test|ipv6_rt) ipv6_route_test;; ipv4_route_test|ipv4_rt) ipv4_route_test;; diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 453ae006fbcf..91201ab3c4fc 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -4,6 +4,7 @@ TEST_PROGS = bridge_igmp.sh \ bridge_locked_port.sh \ bridge_mdb.sh \ bridge_mdb_host.sh \ + bridge_mdb_max.sh \ bridge_mdb_port_down.sh \ bridge_mld.sh \ bridge_port_isolation.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 2fa5973c0c28..ae3f9462a2b6 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -742,10 +742,109 @@ cfg_test_port() cfg_test_port_l2 } +ipv4_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "239.1.1.$i" + done +} + +ipv6_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "ff0e::$(printf %x $i)" + done +} + +l2_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "01:00:00:00:00:$(printf %02x $i)" + done +} + +cfg_test_dump_common() +{ + local name=$1; shift + local fn=$1; shift + local max_bridges=2 + local max_grps=256 + local max_ports=32 + local num_entries + local batch_file + local grp + local i j + + RET=0 + + # Create net devices. + for i in $(seq 1 $max_bridges); do + ip link add name br-test${i} up type bridge vlan_filtering 1 \ + mcast_snooping 1 + for j in $(seq 1 $max_ports); do + ip link add name br-test${i}-du${j} up \ + master br-test${i} type dummy + done + done + + # Create batch file with MDB entries. + batch_file=$(mktemp) + for i in $(seq 1 $max_bridges); do + for j in $(seq 1 $max_ports); do + for grp in $($fn $max_grps); do + echo "mdb add dev br-test${i} \ + port br-test${i}-du${j} grp $grp \ + permanent vid 1" >> $batch_file + done + done + done + + # Program the batch file and check for expected number of entries. + bridge -b $batch_file + for i in $(seq 1 $max_bridges); do + num_entries=$(bridge mdb show dev br-test${i} | \ + grep "permanent" | wc -l) + [[ $num_entries -eq $((max_grps * max_ports)) ]] + check_err $? "Wrong number of entries in br-test${i}" + done + + # Cleanup. + rm $batch_file + for i in $(seq 1 $max_bridges); do + ip link del dev br-test${i} + for j in $(seq $max_ports); do + ip link del dev br-test${i}-du${j} + done + done + + log_test "$name large scale dump tests" +} + +# Check large scale dump. +cfg_test_dump() +{ + echo + log_info "# Large scale dump tests" + + cfg_test_dump_common "IPv4" ipv4_grps_get + cfg_test_dump_common "IPv6" ipv6_grps_get + cfg_test_dump_common "L2" l2_grps_get +} + cfg_test() { cfg_test_host cfg_test_port + cfg_test_dump } __fwd_test_host_ip() @@ -1018,26 +1117,6 @@ fwd_test() ip -6 address del fe80::1/64 dev br0 } -igmpv3_is_in_get() -{ - local igmpv3 - - igmpv3=$(: - )"22:"$( : Type - Membership Report - )"00:"$( : Reserved - )"2a:f8:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ef:01:01:01:"$( : Multicast Address - 239.1.1.1 - )"c0:00:02:02"$( : Source Address - 192.0.2.2 - ) - - echo $igmpv3 -} - ctrl_igmpv3_is_in_test() { RET=0 @@ -1049,7 +1128,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 check_fail $? "Permanent entry affected by IGMP packet" @@ -1062,7 +1141,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ grep -q 192.0.2.2 @@ -1074,36 +1153,7 @@ ctrl_igmpv3_is_in_test() bridge mdb del dev br0 port $swp1 grp 239.1.1.1 vid 10 - log_test "IGMPv3 MODE_IS_INCLUE tests" -} - -mldv2_is_in_get() -{ - local hbh - local icmpv6 - - hbh=$(: - )"3a:"$( : Next Header - ICMPv6 - )"00:"$( : Hdr Ext Len - )"00:00:00:00:00:00:"$( : Options and Padding - ) - - icmpv6=$(: - )"8f:"$( : Type - MLDv2 Report - )"00:"$( : Code - )"45:39:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ff:0e:00:00:00:00:00:00:"$( : Multicast address - ff0e::1 - )"00:00:00:00:00:00:00:01:"$( : - )"20:01:0d:b8:00:01:00:00:"$( : Source Address - 2001:db8:1::2 - )"00:00:00:00:00:00:00:02:"$( : - ) - - echo ${hbh}${icmpv6} + log_test "IGMPv3 MODE_IS_INCLUDE tests" } ctrl_mldv2_is_in_test() @@ -1116,8 +1166,9 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) + local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ grep -q 2001:db8:1::2 @@ -1131,7 +1182,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ grep -q 2001:db8:1::2 diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh new file mode 100755 index 000000000000..ae255b662ba3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -0,0 +1,1336 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:1::2/64 | +# | | | | | | +# | | + $h1.20 | | | + $h2.20 | +# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 | +# | \ | 2001:db8:2::1/64 | | \ | 2001:db8:2::2/64 | +# | \| | | \| | +# | + $h1 | | + $h2 | +# +----|------------------+ +----|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR0 (802.1q) + $swp2 | | +# | | vid 10 vid 10 | | +# | | vid 20 vid 20 | | +# | | | | +# | +-----------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_8021d + test_8021q + test_8021qvs +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64 + vlan_create $h1 20 v$h1 198.51.100.1/24 2001:db8:2::1/64 +} + +h1_destroy() +{ + vlan_destroy $h1 20 + vlan_destroy $h1 10 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 10 v$h2 192.0.2.2/28 + vlan_create $h2 20 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 20 + vlan_destroy $h2 10 + simple_if_fini $h2 +} + +switch_create_8021d() +{ + log_info "802.1d tests" + + ip link add name br0 type bridge vlan_filtering 0 \ + mcast_snooping 1 \ + mcast_igmp_version 3 mcast_mld_version 2 + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up +} + +switch_create_8021q() +{ + local br_flags=$1; shift + + log_info "802.1q $br_flags${br_flags:+ }tests" + + ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 1 $br_flags \ + mcast_igmp_version 3 mcast_mld_version 2 + bridge vlan add vid 10 dev br0 self + bridge vlan add vid 20 dev br0 self + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + bridge vlan add vid 10 dev $swp1 + bridge vlan add vid 20 dev $swp1 + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up + bridge vlan add vid 10 dev $swp2 + bridge vlan add vid 20 dev $swp2 +} + +switch_create_8021qvs() +{ + switch_create_8021q "mcast_vlan_snooping 1" + bridge vlan global set dev br0 vid 10 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 10 mcast_mld_version 2 + bridge vlan global set dev br0 vid 20 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 20 mcast_mld_version 2 +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link set dev br0 down + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy 2>/dev/null + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +cfg_src_list() +{ + local IPs=("$@") + local IPstr=$(echo ${IPs[@]} | tr '[:space:]' , | sed 's/,$//') + + echo ${IPstr:+source_list }${IPstr} +} + +cfg_group_op() +{ + local op=$1; shift + local locus=$1; shift + local GRP=$1; shift + local state=$1; shift + local IPs=("$@") + + local source_list=$(cfg_src_list ${IPs[@]}) + + # Everything besides `bridge mdb' uses the "dev X vid Y" syntax, + # so we use it here as well and convert. + local br_locus=$(echo "$locus" | sed 's/^dev /port /') + + bridge mdb $op dev br0 $br_locus grp $GRP $state \ + filter_mode include $source_list +} + +cfg4_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=239.1.1.${grp} + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg4_entries_add() +{ + cfg4_entries_op add "$@" +} + +cfg4_entries_del() +{ + cfg4_entries_op del "$@" +} + +cfg6_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=ff0e::${grp} + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg6_entries_add() +{ + cfg6_entries_op add "$@" +} + +cfg6_entries_del() +{ + cfg6_entries_op del "$@" +} + +locus_dev_peer() +{ + local dev_kw=$1; shift + local dev=$1; shift + local vid_kw=$1; shift + local vid=$1; shift + + echo "$h1.${vid:-10}" +} + +locus_dev() +{ + local dev_kw=$1; shift + local dev=$1; shift + + echo $dev +} + +ctl4_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl4_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +ctl6_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv2_is_in_get $SIP $GRP $IPs) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl6_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv1_done_get $SIP $GRP) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +bridge_maxgroups_errmsg_check_cfg() +{ + local msg=$1; shift + local needle=$1; shift + + echo "$msg" | grep -q mcast_max_groups + check_err $? "Adding MDB entries failed for the wrong reason: $msg" +} + +bridge_maxgroups_errmsg_check_cfg4() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_cfg6() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_ctl4() +{ + : +} + +bridge_maxgroups_errmsg_check_ctl6() +{ + : +} + +bridge_port_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_n_groups' +} + +bridge_port_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_max_groups' +} + +bridge_port_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge link set dev $(locus_dev $locus) mcast_max_groups $max +} + +bridge_port_vlan_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_n_groups' +} + +bridge_port_vlan_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_max_groups' +} + +bridge_port_vlan_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge vlan set $locus mcast_max_groups $max +} + +test_ngroups_reporting() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n0=$(bridge_${context}_ngroups_get "$locus") + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Couldn't add MDB entries" + local n1=$(bridge_${context}_ngroups_get "$locus") + + ((n1 == n0 + 5)) + check_err $? "Number of groups was $n0, now is $n1, but $((n0 + 5)) expected" + + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + local n2=$(bridge_${context}_ngroups_get "$locus") + + ((n2 == n0)) + check_err $? "Number of groups was $n0, now is $n2, but should be back to $n0" + + log_test "$CFG: $context: ngroups reporting" +} + +test_8021d_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1" +} + +test_8021q_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port_vlan "dev $swp1 vid 10" +} + +test_ngroups_cross_vlan() +{ + local CFG=$1; shift + + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + + RET=0 + + local n10=$(bridge_port_vlan_ngroups_get "$locus1") + local n20=$(bridge_port_vlan_ngroups_get "$locus2") + ${CFG}_entries_add "$locus1" temp 5 111 + check_err $? "Couldn't add MDB entries to VLAN 10" + local n11=$(bridge_port_vlan_ngroups_get "$locus1") + local n21=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n11 == n10 + 5)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n11, but 5 entries added on VLAN 10, $((n10 + 5)) expected" + + ((n21 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n21, but no change expected on VLAN 20" + + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add MDB entries to VLAN 20" + local n12=$(bridge_port_vlan_ngroups_get "$locus1") + local n22=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n12 == n11)) + check_err $? "Number of groups at VLAN 10 was $n11, now is $n12, but no change expected on VLAN 10" + + ((n22 == n21 + 5)) + check_err $? "Number of groups at VLAN 20 was $n21, now is $n22, but 5 entries added on VLAN 20, $((n21 + 5)) expected" + + ${CFG}_entries_del "$locus1" temp 5 111 + check_err $? "Couldn't delete MDB entries from VLAN 10" + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries from VLAN 20" + local n13=$(bridge_port_vlan_ngroups_get "$locus1") + local n23=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n13 == n10)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n13, but should be back to $n10" + + ((n23 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n23, but should be back to $n20" + + log_test "$CFG: port_vlan: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_ngroups_cross_vlan_cfg4() +{ + test_ngroups_cross_vlan cfg4 +} + +test_8021qvs_ngroups_cross_vlan_ctl4() +{ + test_ngroups_cross_vlan ctl4 +} + +test_8021qvs_ngroups_cross_vlan_cfg6() +{ + test_ngroups_cross_vlan cfg6 +} + +test_8021qvs_ngroups_cross_vlan_ctl6() +{ + test_ngroups_cross_vlan ctl6 +} + +test_maxgroups_zero() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + local max + + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 0)) + check_err $? "Max groups on $locus should be 0, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Couldn't set maximum to 0" + + # Test that setting 0 explicitly still serves as infinity. + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Adding 5 MDB entries failed but should have passed" + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + + log_test "$CFG: $context maxgroups: reporting and treatment of 0" +} + +test_8021d_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_zero_cross_vlan() +{ + local CFG=$1; shift + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local max + + RET=0 + + bridge_port_vlan_maxgroups_set "$locus1" 100 + check_err $? "$locus1: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 100 + check_err $? "$locus2: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_maxgroups_set "$locus0" 100 + check_err $? "$locus0: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 0 + check_err $? "$locus2: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0 but $max reported" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN maximums" +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg4() +{ + test_maxgroups_zero_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl4() +{ + test_maxgroups_zero_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg6() +{ + test_maxgroups_zero_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl6() +{ + test_maxgroups_zero_cross_vlan ctl6 +} + +test_maxgroups_too_low() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + ${CFG}_entries_add "$locus" temp 5 111 + check_err $? "$locus: Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" $((n+2)) + check_err $? "$locus: Setting maxgroups to $((n+2)) failed" + + msg=$(${CFG}_entries_add "$locus" temp 2 112 2>&1) + check_fail $? "$locus: Adding more entries passed when max<n" + bridge_maxgroups_errmsg_check_cfg "$msg" + + ${CFG}_entries_del "$locus" temp 5 111 + check_err $? "$locus: Couldn't delete MDB entries" + + ${CFG}_entries_add "$locus" temp 2 112 + check_err $? "$locus: Adding more entries failed" + + ${CFG}_entries_del "$locus" temp 2 112 + check_err $? "$locus: Deleting more entries failed" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: configure below ngroups" +} + +test_8021d_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_entries() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + # Configure a low maximum + bridge_${context}_maxgroups_set "$locus" $((n+1)) + check_err $? "$locus: Couldn't set maximum" + + # Try to add more entries than the configured maximum + msg=$(${CFG}_entries_add "$locus" temp 5 2>&1) + check_fail $? "Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # When adding entries through the control path, as many as possible + # get created. That's consistent with the mcast_hash_max behavior. + # So there, drop the entries explicitly. + if [[ ${CFG%[46]} == ctl ]]; then + ${CFG}_entries_del "$locus" temp 17 2>&1 + fi + + local n2=$(bridge_${context}_ngroups_get "$locus") + ((n2 == n)) + check_err $? "Number of groups was $n, but after a failed attempt to add MDB entries it changed to $n2" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: add too many MDB entries" +} + +test_8021d_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_cross_vlan() +{ + local CFG=$1; shift + + RET=0 + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local n1=$(bridge_port_vlan_ngroups_get "$locus1") + local n2=$(bridge_port_vlan_ngroups_get "$locus2") + local msg + + if ((n1 > n2)); then + local tmp=$n1 + n1=$n2 + n2=$tmp + + tmp="$locus1" + locus1="$locus2" + locus2="$tmp" + fi + + # Now 0 <= n1 <= n2. + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add 5 entries" + + n2=$(bridge_port_vlan_ngroups_get "$locus2") + # Now 0 <= n1 < n2-1. + + # Setting locus1'maxgroups to n2-1 should pass. The number is + # smaller than both the absolute number of MDB entries, and in + # particular than number of locus2's number of entries, but it is + # large enough to cover locus1's entries. Thus we check that + # individual VLAN's ngroups are independent. + bridge_port_vlan_maxgroups_set "$locus1" $((n2-1)) + check_err $? "Setting ${locus1}'s maxgroups to $((n2-1)) failed" + + msg=$(${CFG}_entries_add "$locus1" temp $n2 111 2>&1) + check_fail $? "$locus1: Adding $n2 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + bridge_port_maxgroups_set "$locus0" $((n1 + n2 + 2)) + check_err $? "$locus0: Couldn't set maximum" + + msg=$(${CFG}_entries_add "$locus1" temp 5 111 2>&1) + check_fail $? "$locus1: Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # IGMP/MLD packets can cause several entries to be added, before + # the maximum is hit and the rest is then bounced. Remove what was + # committed, if anything. + ${CFG}_entries_del "$locus1" temp 5 111 2>/dev/null + + ${CFG}_entries_add "$locus1" temp 2 111 + check_err $? "$locus1: Adding 2 MDB entries failed, but should have passed" + + ${CFG}_entries_del "$locus1" temp 2 111 + check_err $? "Couldn't delete MDB entries" + + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Couldn't set maximum to 0" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Couldn't set maximum to 0" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg4() +{ + test_maxgroups_too_many_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl4() +{ + test_maxgroups_too_many_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg6() +{ + test_maxgroups_too_many_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl6() +{ + test_maxgroups_too_many_cross_vlan ctl6 +} + +test_vlan_attributes() +{ + local locus=$1; shift + local expect=$1; shift + + RET=0 + + local max=$(bridge_port_vlan_maxgroups_get "$locus") + local n=$(bridge_port_vlan_ngroups_get "$locus") + + eval "[[ $max $expect ]]" + check_err $? "$locus: maxgroups attribute expected to be $expect, but was $max" + + eval "[[ $n $expect ]]" + check_err $? "$locus: ngroups attribute expected to be $expect, but was $n" + + log_test "port_vlan: presence of ngroups and maxgroups attributes" +} + +test_8021q_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "== null" +} + +test_8021qvs_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "-ge 0" +} + +test_toggle_vlan_snooping() +{ + local mode=$1; shift + + RET=0 + + local CFG=cfg4 + local context=port_vlan + local locus="dev $swp1 vid 10" + + ${CFG}_entries_add "$locus" $mode 5 + check_err $? "Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + + ip link set dev br0 type bridge mcast_vlan_snooping 0 + sleep 1 + ip link set dev br0 type bridge mcast_vlan_snooping 1 + + local n=$(bridge_${context}_ngroups_get "$locus") + local nn=$(bridge mdb show dev br0 | grep $swp1 | wc -l) + ((nn == n)) + check_err $? "mcast_n_groups expected to be $nn, but $n reported" + + local max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100 but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Failed to set max to 0" + + log_test "$CFG: $context: $mode: mcast_vlan_snooping toggle" +} + +test_toggle_vlan_snooping_temp() +{ + test_toggle_vlan_snooping temp +} + +test_toggle_vlan_snooping_permanent() +{ + test_toggle_vlan_snooping permanent +} + +# ngroup test suites + +test_8021d_ngroups_cfg4() +{ + test_8021d_ngroups_reporting_cfg4 +} + +test_8021d_ngroups_ctl4() +{ + test_8021d_ngroups_reporting_ctl4 +} + +test_8021d_ngroups_cfg6() +{ + test_8021d_ngroups_reporting_cfg6 +} + +test_8021d_ngroups_ctl6() +{ + test_8021d_ngroups_reporting_ctl6 +} + +test_8021q_ngroups_cfg4() +{ + test_8021q_ngroups_reporting_cfg4 +} + +test_8021q_ngroups_ctl4() +{ + test_8021q_ngroups_reporting_ctl4 +} + +test_8021q_ngroups_cfg6() +{ + test_8021q_ngroups_reporting_cfg6 +} + +test_8021q_ngroups_ctl6() +{ + test_8021q_ngroups_reporting_ctl6 +} + +test_8021qvs_ngroups_cfg4() +{ + test_8021qvs_ngroups_reporting_cfg4 + test_8021qvs_ngroups_cross_vlan_cfg4 +} + +test_8021qvs_ngroups_ctl4() +{ + test_8021qvs_ngroups_reporting_ctl4 + test_8021qvs_ngroups_cross_vlan_ctl4 +} + +test_8021qvs_ngroups_cfg6() +{ + test_8021qvs_ngroups_reporting_cfg6 + test_8021qvs_ngroups_cross_vlan_cfg6 +} + +test_8021qvs_ngroups_ctl6() +{ + test_8021qvs_ngroups_reporting_ctl6 + test_8021qvs_ngroups_cross_vlan_ctl6 +} + +# maxgroups test suites + +test_8021d_maxgroups_cfg4() +{ + test_8021d_maxgroups_zero_cfg4 + test_8021d_maxgroups_too_low_cfg4 + test_8021d_maxgroups_too_many_entries_cfg4 +} + +test_8021d_maxgroups_ctl4() +{ + test_8021d_maxgroups_zero_ctl4 + test_8021d_maxgroups_too_low_ctl4 + test_8021d_maxgroups_too_many_entries_ctl4 +} + +test_8021d_maxgroups_cfg6() +{ + test_8021d_maxgroups_zero_cfg6 + test_8021d_maxgroups_too_low_cfg6 + test_8021d_maxgroups_too_many_entries_cfg6 +} + +test_8021d_maxgroups_ctl6() +{ + test_8021d_maxgroups_zero_ctl6 + test_8021d_maxgroups_too_low_ctl6 + test_8021d_maxgroups_too_many_entries_ctl6 +} + +test_8021q_maxgroups_cfg4() +{ + test_8021q_maxgroups_zero_cfg4 + test_8021q_maxgroups_too_low_cfg4 + test_8021q_maxgroups_too_many_entries_cfg4 +} + +test_8021q_maxgroups_ctl4() +{ + test_8021q_maxgroups_zero_ctl4 + test_8021q_maxgroups_too_low_ctl4 + test_8021q_maxgroups_too_many_entries_ctl4 +} + +test_8021q_maxgroups_cfg6() +{ + test_8021q_maxgroups_zero_cfg6 + test_8021q_maxgroups_too_low_cfg6 + test_8021q_maxgroups_too_many_entries_cfg6 +} + +test_8021q_maxgroups_ctl6() +{ + test_8021q_maxgroups_zero_ctl6 + test_8021q_maxgroups_too_low_ctl6 + test_8021q_maxgroups_too_many_entries_ctl6 +} + +test_8021qvs_maxgroups_cfg4() +{ + test_8021qvs_maxgroups_zero_cfg4 + test_8021qvs_maxgroups_zero_cross_vlan_cfg4 + test_8021qvs_maxgroups_too_low_cfg4 + test_8021qvs_maxgroups_too_many_entries_cfg4 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg4 +} + +test_8021qvs_maxgroups_ctl4() +{ + test_8021qvs_maxgroups_zero_ctl4 + test_8021qvs_maxgroups_zero_cross_vlan_ctl4 + test_8021qvs_maxgroups_too_low_ctl4 + test_8021qvs_maxgroups_too_many_entries_ctl4 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl4 +} + +test_8021qvs_maxgroups_cfg6() +{ + test_8021qvs_maxgroups_zero_cfg6 + test_8021qvs_maxgroups_zero_cross_vlan_cfg6 + test_8021qvs_maxgroups_too_low_cfg6 + test_8021qvs_maxgroups_too_many_entries_cfg6 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg6 +} + +test_8021qvs_maxgroups_ctl6() +{ + test_8021qvs_maxgroups_zero_ctl6 + test_8021qvs_maxgroups_zero_cross_vlan_ctl6 + test_8021qvs_maxgroups_too_low_ctl6 + test_8021qvs_maxgroups_too_many_entries_ctl6 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl6 +} + +# other test suites + +test_8021qvs_toggle_vlan_snooping() +{ + test_toggle_vlan_snooping_temp + test_toggle_vlan_snooping_permanent +} + +# test groups + +test_8021d() +{ + # Tests for vlan_filtering 0 mcast_vlan_snooping 0. + + switch_create_8021d + setup_wait + + test_8021d_ngroups_cfg4 + test_8021d_ngroups_ctl4 + test_8021d_ngroups_cfg6 + test_8021d_ngroups_ctl6 + test_8021d_maxgroups_cfg4 + test_8021d_maxgroups_ctl4 + test_8021d_maxgroups_cfg6 + test_8021d_maxgroups_ctl6 + + switch_destroy +} + +test_8021q() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 0. + + switch_create_8021q + setup_wait + + test_8021q_vlan_attributes + test_8021q_ngroups_cfg4 + test_8021q_ngroups_ctl4 + test_8021q_ngroups_cfg6 + test_8021q_ngroups_ctl6 + test_8021q_maxgroups_cfg4 + test_8021q_maxgroups_ctl4 + test_8021q_maxgroups_cfg6 + test_8021q_maxgroups_ctl6 + + switch_destroy +} + +test_8021qvs() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 1. + + switch_create_8021qvs + setup_wait + + test_8021qvs_vlan_attributes + test_8021qvs_ngroups_cfg4 + test_8021qvs_ngroups_ctl4 + test_8021qvs_ngroups_cfg6 + test_8021qvs_ngroups_ctl6 + test_8021qvs_maxgroups_cfg4 + test_8021qvs_maxgroups_ctl4 + test_8021qvs_maxgroups_cfg6 + test_8021qvs_maxgroups_ctl6 + test_8021qvs_toggle_vlan_snooping + + switch_destroy +} + +trap cleanup EXIT + +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 3d8e4ebda1b6..d47499ba81c7 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -524,27 +524,6 @@ cmd_jq() [ ! -z "$output" ] } -lldpad_app_wait_set() -{ - local dev=$1; shift - - while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do - echo "$dev: waiting for lldpad to push pending APP updates" - sleep 5 - done -} - -lldpad_app_wait_del() -{ - # Give lldpad a chance to push down the changes. If the device is downed - # too soon, the updates will be left pending. However, they will have - # been struck off the lldpad's DB already, so we won't be able to tell - # they are pending. Then on next test iteration this would cause - # weirdness as newly-added APP rules conflict with the old ones, - # sometimes getting stuck in an "unknown" state. - sleep 5 -} - pre_cleanup() { if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then @@ -1692,3 +1671,219 @@ hw_stats_monitor_test() log_test "${type}_stats notifications" } + +ipv4_to_bytes() +{ + local IP=$1; shift + + printf '%02x:' ${IP//./ } | + sed 's/:$//' +} + +# Convert a given IPv6 address, `IP' such that the :: token, if present, is +# expanded, and each 16-bit group is padded with zeroes to be 4 hexadecimal +# digits. An optional `BYTESEP' parameter can be given to further separate +# individual bytes of each 16-bit group. +expand_ipv6() +{ + local IP=$1; shift + local bytesep=$1; shift + + local cvt_ip=${IP/::/_} + local colons=${cvt_ip//[^:]/} + local allcol=::::::: + # IP where :: -> the appropriate number of colons: + local allcol_ip=${cvt_ip/_/${allcol:${#colons}}} + + echo $allcol_ip | tr : '\n' | + sed s/^/0000/ | + sed 's/.*\(..\)\(..\)/\1'"$bytesep"'\2/' | + tr '\n' : | + sed 's/:$//' +} + +ipv6_to_bytes() +{ + local IP=$1; shift + + expand_ipv6 "$IP" : +} + +u16_to_bytes() +{ + local u16=$1; shift + + printf "%04x" $u16 | sed 's/^/000/;s/^.*\(..\)\(..\)$/\1:\2/' +} + +# Given a mausezahn-formatted payload (colon-separated bytes given as %02x), +# possibly with a keyword CHECKSUM stashed where a 16-bit checksum should be, +# calculate checksum as per RFC 1071, assuming the CHECKSUM field (if any) +# stands for 00:00. +payload_template_calc_checksum() +{ + local payload=$1; shift + + ( + # Set input radix. + echo "16i" + # Push zero for the initial checksum. + echo 0 + + # Pad the payload with a terminating 00: in case we get an odd + # number of bytes. + echo "${payload%:}:00:" | + sed 's/CHECKSUM/00:00/g' | + tr '[:lower:]' '[:upper:]' | + # Add the word to the checksum. + sed 's/\(..\):\(..\):/\1\2+\n/g' | + # Strip the extra odd byte we pushed if left unconverted. + sed 's/\(..\):$//' + + echo "10000 ~ +" # Calculate and add carry. + echo "FFFF r - p" # Bit-flip and print. + ) | + dc | + tr '[:upper:]' '[:lower:]' +} + +payload_template_expand_checksum() +{ + local payload=$1; shift + local checksum=$1; shift + + local ckbytes=$(u16_to_bytes $checksum) + + echo "$payload" | sed "s/CHECKSUM/$ckbytes/g" +} + +payload_template_nbytes() +{ + local payload=$1; shift + + payload_template_expand_checksum "${payload%:}" 0 | + sed 's/:/\n/g' | wc -l +} + +igmpv3_is_in_get() +{ + local GRP=$1; shift + local sources=("$@") + + local igmpv3 + local nsources=$(u16_to_bytes ${#sources[@]}) + + # IS_IN ( $sources ) + igmpv3=$(: + )"22:"$( : Type - Membership Report + )"00:"$( : Reserved + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv4_to_bytes $GRP):"$( : Multicast Address + )"$(for src in "${sources[@]}"; do + ipv4_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + local checksum=$(payload_template_calc_checksum "$igmpv3") + + payload_template_expand_checksum "$igmpv3" $checksum +} + +igmpv2_leave_get() +{ + local GRP=$1; shift + + local payload=$(: + )"17:"$( : Type - Leave Group + )"00:"$( : Max Resp Time - not meaningful + )"CHECKSUM:"$( : Checksum + )"$(ipv4_to_bytes $GRP)"$( : Group Address + ) + local checksum=$(payload_template_calc_checksum "$payload") + + payload_template_expand_checksum "$payload" $checksum +} + +mldv2_is_in_get() +{ + local SIP=$1; shift + local GRP=$1; shift + local sources=("$@") + + local hbh + local icmpv6 + local nsources=$(u16_to_bytes ${#sources[@]}) + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"8f:"$( : Type - MLDv2 Report + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + )"$(for src in "${sources[@]}"; do + ipv6_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} + +mldv1_done_get() +{ + local SIP=$1; shift + local GRP=$1; shift + + local hbh + local icmpv6 + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"84:"$( : Type - MLDv1 Done + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Max Resp Delay - not meaningful + )"00:00:"$( : Reserved + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 1e0a62f638fe..a96cff8e7219 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,8 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test mirred_egress_to_ingress_test" + gact_trap_test mirred_egress_to_ingress_test \ + mirred_egress_to_ingress_tcp_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -198,6 +199,52 @@ mirred_egress_to_ingress_test() log_test "mirred_egress_to_ingress ($tcflags)" } +mirred_egress_to_ingress_tcp_test() +{ + mirred_e2i_tf1=$(mktemp) mirred_e2i_tf2=$(mktemp) + + RET=0 + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$mirred_e2i_tf1 + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ + action ct commit nat src addr 192.0.2.2 pipe \ + action ct clear pipe \ + action ct commit nat dst addr 192.0.2.1 pipe \ + action ct clear pipe \ + action skbedit ptype host pipe \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \ + $tcflags ip_proto icmp \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \ + ip_proto icmp \ + action drop + + ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + local rpid=$! + ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + wait -n $rpid + cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 + check_err $? "server output check failed" + + $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ + -t icmp "ping,id=42,seq=5" -q + tc_check_packets "dev $h1 egress" 101 10 + check_err $? "didn't mirred redirect ICMP" + tc_check_packets "dev $h1 ingress" 102 10 + check_err $? "didn't drop mirred ICMP" + local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) + test ${overlimits} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits}" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower + tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower + + rm -f $mirred_e2i_tf1 $mirred_e2i_tf2 + log_test "mirred_egress_to_ingress_tcp ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} @@ -223,6 +270,8 @@ setup_prepare() cleanup() { + local tf + pre_cleanup switch_destroy @@ -233,6 +282,8 @@ cleanup() ip link set $swp2 address $swp2origmac ip link set $swp1 address $swp1origmac + + for tf in $mirred_e2i_tf1 $mirred_e2i_tf2; do rm -f $tf; done } mirred_egress_redirect_test() diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c new file mode 100644 index 000000000000..75e3fdacdf73 --- /dev/null +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -0,0 +1,447 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2023 Cloudflare + +/* Test IP_LOCAL_PORT_RANGE socket option: IPv4 + IPv6, TCP + UDP. + * + * Tests assume that net.ipv4.ip_local_port_range is [40000, 49999]. + * Don't run these directly but with ip_local_port_range.sh script. + */ + +#include <fcntl.h> +#include <netinet/ip.h> + +#include "../kselftest_harness.h" + +#ifndef IP_LOCAL_PORT_RANGE +#define IP_LOCAL_PORT_RANGE 51 +#endif + +static __u32 pack_port_range(__u16 lo, __u16 hi) +{ + return (hi << 16) | (lo << 0); +} + +static void unpack_port_range(__u32 range, __u16 *lo, __u16 *hi) +{ + *lo = range & 0xffff; + *hi = range >> 16; +} + +static int get_so_domain(int fd) +{ + int domain, err; + socklen_t len; + + len = sizeof(domain); + err = getsockopt(fd, SOL_SOCKET, SO_DOMAIN, &domain, &len); + if (err) + return -1; + + return domain; +} + +static int bind_to_loopback_any_port(int fd) +{ + union { + struct sockaddr sa; + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } addr; + socklen_t addr_len; + + memset(&addr, 0, sizeof(addr)); + switch (get_so_domain(fd)) { + case AF_INET: + addr.v4.sin_family = AF_INET; + addr.v4.sin_port = htons(0); + addr.v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr_len = sizeof(addr.v4); + break; + case AF_INET6: + addr.v6.sin6_family = AF_INET6; + addr.v6.sin6_port = htons(0); + addr.v6.sin6_addr = in6addr_loopback; + addr_len = sizeof(addr.v6); + break; + default: + return -1; + } + + return bind(fd, &addr.sa, addr_len); +} + +static int get_sock_port(int fd) +{ + union { + struct sockaddr sa; + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } addr; + socklen_t addr_len; + int err; + + addr_len = sizeof(addr); + memset(&addr, 0, sizeof(addr)); + err = getsockname(fd, &addr.sa, &addr_len); + if (err) + return -1; + + switch (addr.sa.sa_family) { + case AF_INET: + return ntohs(addr.v4.sin_port); + case AF_INET6: + return ntohs(addr.v6.sin6_port); + default: + errno = EAFNOSUPPORT; + return -1; + } +} + +static int get_ip_local_port_range(int fd, __u32 *range) +{ + socklen_t len; + __u32 val; + int err; + + len = sizeof(val); + err = getsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &val, &len); + if (err) + return -1; + + *range = val; + return 0; +} + +FIXTURE(ip_local_port_range) {}; + +FIXTURE_SETUP(ip_local_port_range) +{ +} + +FIXTURE_TEARDOWN(ip_local_port_range) +{ +} + +FIXTURE_VARIANT(ip_local_port_range) { + int so_domain; + int so_type; + int so_protocol; +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_tcp) { + .so_domain = AF_INET, + .so_type = SOCK_STREAM, + .so_protocol = 0, +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_udp) { + .so_domain = AF_INET, + .so_type = SOCK_DGRAM, + .so_protocol = 0, +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_stcp) { + .so_domain = AF_INET, + .so_type = SOCK_STREAM, + .so_protocol = IPPROTO_SCTP, +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_tcp) { + .so_domain = AF_INET6, + .so_type = SOCK_STREAM, + .so_protocol = 0, +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_udp) { + .so_domain = AF_INET6, + .so_type = SOCK_DGRAM, + .so_protocol = 0, +}; + +FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_stcp) { + .so_domain = AF_INET6, + .so_type = SOCK_STREAM, + .so_protocol = IPPROTO_SCTP, +}; + +TEST_F(ip_local_port_range, invalid_option_value) +{ + __u16 val16; + __u32 val32; + __u64 val64; + int fd, err; + + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + /* Too few bytes */ + val16 = 40000; + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &val16, sizeof(val16)); + EXPECT_TRUE(err) TH_LOG("expected setsockopt(IP_LOCAL_PORT_RANGE) to fail"); + EXPECT_EQ(errno, EINVAL); + + /* Empty range: low port > high port */ + val32 = pack_port_range(40222, 40111); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &val32, sizeof(val32)); + EXPECT_TRUE(err) TH_LOG("expected setsockopt(IP_LOCAL_PORT_RANGE) to fail"); + EXPECT_EQ(errno, EINVAL); + + /* Too many bytes */ + val64 = pack_port_range(40333, 40444); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &val64, sizeof(val64)); + EXPECT_TRUE(err) TH_LOG("expected setsockopt(IP_LOCAL_PORT_RANGE) to fail"); + EXPECT_EQ(errno, EINVAL); + + err = close(fd); + ASSERT_TRUE(!err) TH_LOG("close failed"); +} + +TEST_F(ip_local_port_range, port_range_out_of_netns_range) +{ + const struct test { + __u16 range_lo; + __u16 range_hi; + } tests[] = { + { 30000, 39999 }, /* socket range below netns range */ + { 50000, 59999 }, /* socket range above netns range */ + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + /* Bind a couple of sockets, not just one, to check + * that the range wasn't clamped to a single port from + * the netns range. That is [40000, 40000] or [49999, + * 49999], respectively for each test case. + */ + int fds[2], i; + + TH_LOG("lo %5hu, hi %5hu", t->range_lo, t->range_hi); + + for (i = 0; i < ARRAY_SIZE(fds); i++) { + int fd, err, port; + __u32 range; + + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("#%d: socket failed", i); + + range = pack_port_range(t->range_lo, t->range_hi); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("#%d: setsockopt(IP_LOCAL_PORT_RANGE) failed", i); + + err = bind_to_loopback_any_port(fd); + ASSERT_TRUE(!err) TH_LOG("#%d: bind failed", i); + + /* Check that socket port range outside of ephemeral range is ignored */ + port = get_sock_port(fd); + ASSERT_GE(port, 40000) TH_LOG("#%d: expected port within netns range", i); + ASSERT_LE(port, 49999) TH_LOG("#%d: expected port within netns range", i); + + fds[i] = fd; + } + + for (i = 0; i < ARRAY_SIZE(fds); i++) + ASSERT_TRUE(close(fds[i]) == 0) TH_LOG("#%d: close failed", i); + } +} + +TEST_F(ip_local_port_range, single_port_range) +{ + const struct test { + __u16 range_lo; + __u16 range_hi; + __u16 expected; + } tests[] = { + /* single port range within ephemeral range */ + { 45000, 45000, 45000 }, + /* first port in the ephemeral range (clamp from above) */ + { 0, 40000, 40000 }, + /* last port in the ephemeral range (clamp from below) */ + { 49999, 0, 49999 }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + int fd, err, port; + __u32 range; + + TH_LOG("lo %5hu, hi %5hu, expected %5hu", + t->range_lo, t->range_hi, t->expected); + + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + range = pack_port_range(t->range_lo, t->range_hi); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + err = bind_to_loopback_any_port(fd); + ASSERT_TRUE(!err) TH_LOG("bind failed"); + + port = get_sock_port(fd); + ASSERT_EQ(port, t->expected) TH_LOG("unexpected local port"); + + err = close(fd); + ASSERT_TRUE(!err) TH_LOG("close failed"); + } +} + +TEST_F(ip_local_port_range, exhaust_8_port_range) +{ + __u8 port_set = 0; + int i, fd, err; + __u32 range; + __u16 port; + int fds[8]; + + for (i = 0; i < ARRAY_SIZE(fds); i++) { + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + range = pack_port_range(40000, 40007); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + err = bind_to_loopback_any_port(fd); + ASSERT_TRUE(!err) TH_LOG("bind failed"); + + port = get_sock_port(fd); + ASSERT_GE(port, 40000) TH_LOG("expected port within sockopt range"); + ASSERT_LE(port, 40007) TH_LOG("expected port within sockopt range"); + + port_set |= 1 << (port - 40000); + fds[i] = fd; + } + + /* Check that all every port from the test range is in use */ + ASSERT_EQ(port_set, 0xff) TH_LOG("expected all ports to be busy"); + + /* Check that bind() fails because the whole range is busy */ + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + range = pack_port_range(40000, 40007); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + err = bind_to_loopback_any_port(fd); + ASSERT_TRUE(err) TH_LOG("expected bind to fail"); + ASSERT_EQ(errno, EADDRINUSE); + + err = close(fd); + ASSERT_TRUE(!err) TH_LOG("close failed"); + + for (i = 0; i < ARRAY_SIZE(fds); i++) { + err = close(fds[i]); + ASSERT_TRUE(!err) TH_LOG("close failed"); + } +} + +TEST_F(ip_local_port_range, late_bind) +{ + union { + struct sockaddr sa; + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } addr; + socklen_t addr_len; + const int one = 1; + int fd, err; + __u32 range; + __u16 port; + + if (variant->so_protocol == IPPROTO_SCTP) + SKIP(return, "SCTP doesn't support IP_BIND_ADDRESS_NO_PORT"); + + fd = socket(variant->so_domain, variant->so_type, 0); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + range = pack_port_range(40100, 40199); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + err = setsockopt(fd, SOL_IP, IP_BIND_ADDRESS_NO_PORT, &one, sizeof(one)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_BIND_ADDRESS_NO_PORT) failed"); + + err = bind_to_loopback_any_port(fd); + ASSERT_TRUE(!err) TH_LOG("bind failed"); + + port = get_sock_port(fd); + ASSERT_EQ(port, 0) TH_LOG("getsockname failed"); + + /* Invalid destination */ + memset(&addr, 0, sizeof(addr)); + switch (variant->so_domain) { + case AF_INET: + addr.v4.sin_family = AF_INET; + addr.v4.sin_port = htons(0); + addr.v4.sin_addr.s_addr = htonl(INADDR_ANY); + addr_len = sizeof(addr.v4); + break; + case AF_INET6: + addr.v6.sin6_family = AF_INET6; + addr.v6.sin6_port = htons(0); + addr.v6.sin6_addr = in6addr_any; + addr_len = sizeof(addr.v6); + break; + default: + ASSERT_TRUE(false) TH_LOG("unsupported socket domain"); + } + + /* connect() doesn't need to succeed for late bind to happen */ + connect(fd, &addr.sa, addr_len); + + port = get_sock_port(fd); + ASSERT_GE(port, 40100); + ASSERT_LE(port, 40199); + + err = close(fd); + ASSERT_TRUE(!err) TH_LOG("close failed"); +} + +TEST_F(ip_local_port_range, get_port_range) +{ + __u16 lo, hi; + __u32 range; + int fd, err; + + fd = socket(variant->so_domain, variant->so_type, variant->so_protocol); + ASSERT_GE(fd, 0) TH_LOG("socket failed"); + + /* Get range before it will be set */ + err = get_ip_local_port_range(fd, &range); + ASSERT_TRUE(!err) TH_LOG("getsockopt(IP_LOCAL_PORT_RANGE) failed"); + + unpack_port_range(range, &lo, &hi); + ASSERT_EQ(lo, 0) TH_LOG("unexpected low port"); + ASSERT_EQ(hi, 0) TH_LOG("unexpected high port"); + + range = pack_port_range(12345, 54321); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + /* Get range after it has been set */ + err = get_ip_local_port_range(fd, &range); + ASSERT_TRUE(!err) TH_LOG("getsockopt(IP_LOCAL_PORT_RANGE) failed"); + + unpack_port_range(range, &lo, &hi); + ASSERT_EQ(lo, 12345) TH_LOG("unexpected low port"); + ASSERT_EQ(hi, 54321) TH_LOG("unexpected high port"); + + /* Unset the port range */ + range = pack_port_range(0, 0); + err = setsockopt(fd, SOL_IP, IP_LOCAL_PORT_RANGE, &range, sizeof(range)); + ASSERT_TRUE(!err) TH_LOG("setsockopt(IP_LOCAL_PORT_RANGE) failed"); + + /* Get range after it has been unset */ + err = get_ip_local_port_range(fd, &range); + ASSERT_TRUE(!err) TH_LOG("getsockopt(IP_LOCAL_PORT_RANGE) failed"); + + unpack_port_range(range, &lo, &hi); + ASSERT_EQ(lo, 0) TH_LOG("unexpected low port"); + ASSERT_EQ(hi, 0) TH_LOG("unexpected high port"); + + err = close(fd); + ASSERT_TRUE(!err) TH_LOG("close failed"); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh new file mode 100755 index 000000000000..6c6ad346eaa0 --- /dev/null +++ b/tools/testing/selftests/net/ip_local_port_range.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +./in_netns.sh \ + sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range' diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 24bcd7b9bdb2..ef628b16fe9b 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -17,6 +17,11 @@ flush_pids() sleep 1.1 ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null + + for _ in $(seq 10); do + [ -z "$(ip netns pids "${ns}")" ] && break + sleep 0.1 + done } cleanup() @@ -37,15 +42,20 @@ if [ $? -ne 0 ];then exit $ksft_skip fi +get_msk_inuse() +{ + ip netns exec $ns cat /proc/net/protocols | awk '$1~/^MPTCP$/{print $3}' +} + __chk_nr() { - local condition="$1" + local command="$1" local expected=$2 local msg nr shift 2 msg=$* - nr=$(ss -inmHMN $ns | $condition) + nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then @@ -57,9 +67,17 @@ __chk_nr() test_cnt=$((test_cnt+1)) } +__chk_msk_nr() +{ + local condition=$1 + shift 1 + + __chk_nr "ss -inmHMN $ns | $condition" $* +} + chk_msk_nr() { - __chk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" $* } wait_msk_nr() @@ -97,12 +115,12 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" $* } chk_msk_remote_key_nr() { - __chk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" $* } __chk_listen() @@ -142,6 +160,26 @@ chk_msk_listen() nr=$(ss -Ml $filter | wc -l) } +chk_msk_inuse() +{ + local expected=$1 + local listen_nr + + shift 1 + + listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) + expected=$((expected + listen_nr)) + + for _ in $(seq 10); do + if [ $(get_msk_inuse) -eq $expected ];then + break + fi + sleep 0.1 + done + + __chk_nr get_msk_inuse $expected $* +} + # $1: ns, $2: port wait_local_port_listen() { @@ -195,8 +233,10 @@ wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" +chk_msk_inuse 2 "....chk 2 msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" echo "a" | \ timeout ${timeout_test} \ @@ -211,8 +251,11 @@ echo "b" | \ 127.0.0.1 >/dev/null & wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" +chk_msk_inuse 1 "....chk 1 msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" + NR_CLIENTS=100 for I in `seq 1 $NR_CLIENTS`; do echo "a" | \ @@ -232,6 +275,9 @@ for I in `seq 1 $NR_CLIENTS`; do done wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 8a8266957bc5..b25a31445ded 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -627,7 +627,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, char rbuf[8192]; ssize_t len; - if (fds.events == 0) + if (fds.events == 0 || quit) break; switch (poll(&fds, 1, poll_timeout)) { @@ -733,7 +733,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, } /* leave some time for late join/announce */ - if (cfg_remove) + if (cfg_remove && !quit) usleep(cfg_wait); return 0; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 079f8f46849d..42e3bd1a05f5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -780,24 +780,17 @@ do_transfer() addr_nr_ns2=${addr_nr_ns2:9} fi - local local_addr - if is_v6 "${connect_addr}"; then - local_addr="::" - else - local_addr="0.0.0.0" - fi - extra_srv_args="$extra_args $extra_srv_args" if [ "$test_link_fail" -gt 1 ];then timeout ${timeout_test} \ ip netns exec ${listener_ns} \ ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args ${local_addr} < "$sinfail" > "$sout" & + $extra_srv_args "::" < "$sinfail" > "$sout" & else timeout ${timeout_test} \ ip netns exec ${listener_ns} \ ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args ${local_addr} < "$sin" > "$sout" & + $extra_srv_args "::" < "$sin" > "$sout" & fi local spid=$! @@ -2460,6 +2453,47 @@ v4mapped_tests() fi } +mixed_tests() +{ + if reset "IPv4 sockets do not use IPv6 addresses"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + fi + + # Need an IPv6 mptcp socket to allow subflows of both families + if reset "simult IPv4 and IPv6 subflows"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + chk_join_nr 1 1 1 + fi + + # cross families subflows will not be created even in fullmesh mode + if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + chk_join_nr 1 1 1 + fi + + # fullmesh still tries to create all the possibly subflows with + # matching family + if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 2 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 fullmesh_1 slow + chk_join_nr 4 4 4 + fi +} + backup_tests() { # single subflow, backup @@ -3132,6 +3166,7 @@ all_tests_sorted=( a@add_tests 6@ipv6_tests 4@v4mapped_tests + M@mixed_tests b@backup_tests p@add_addr_ports_tests k@syncookies_tests diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index ab2d581f28a1..66c5be25c13d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -43,41 +43,40 @@ rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" +print_title() +{ + stdbuf -o0 -e0 printf "INFO: %s\n" "${1}" +} + kill_wait() { + [ $1 -eq 0 ] && return 0 + + kill -SIGUSR1 $1 > /dev/null 2>&1 kill $1 > /dev/null 2>&1 wait $1 2>/dev/null } cleanup() { - echo "cleanup" - - rm -rf $file $client_evts $server_evts + print_title "Cleanup" # Terminate the MPTCP connection and related processes - if [ $client4_pid -ne 0 ]; then - kill -SIGUSR1 $client4_pid > /dev/null 2>&1 - fi - if [ $server4_pid -ne 0 ]; then - kill_wait $server4_pid - fi - if [ $client6_pid -ne 0 ]; then - kill -SIGUSR1 $client6_pid > /dev/null 2>&1 - fi - if [ $server6_pid -ne 0 ]; then - kill_wait $server6_pid - fi - if [ $server_evts_pid -ne 0 ]; then - kill_wait $server_evts_pid - fi - if [ $client_evts_pid -ne 0 ]; then - kill_wait $client_evts_pid - fi + local pid + for pid in $client4_pid $server4_pid $client6_pid $server6_pid\ + $server_evts_pid $client_evts_pid + do + kill_wait $pid + done + local netns for netns in "$ns1" "$ns2" ;do ip netns del "$netns" done + + rm -rf $file $client_evts $server_evts + + stdbuf -o0 -e0 printf "Done\n" } trap cleanup EXIT @@ -108,6 +107,7 @@ ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad ip -net "$ns2" link set ns2eth1 up +print_title "Init" stdbuf -o0 -e0 printf "Created network namespaces ns1, ns2 \t\t\t[OK]\n" make_file() @@ -193,11 +193,16 @@ make_connection() server_serverside=$(grep "type:1," "$server_evts" | sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q') + stdbuf -o0 -e0 printf "Established IP%s MPTCP Connection ns2 => ns1 \t\t" $is_v6 if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && [ "$server_serverside" = 1 ] then - stdbuf -o0 -e0 printf "Established IP%s MPTCP Connection ns2 => ns1 \t\t[OK]\n" $is_v6 + stdbuf -o0 -e0 printf "[OK]\n" else + stdbuf -o0 -e0 printf "[FAIL]\n" + stdbuf -o0 -e0 printf "\tExpected tokens (c:%s - s:%s) and server (c:%d - s:%d)\n" \ + "${client_token}" "${server_token}" \ + "${client_serverside}" "${server_serverside}" exit 1 fi @@ -217,6 +222,48 @@ make_connection() fi } +# $1: var name ; $2: prev ret +check_expected_one() +{ + local var="${1}" + local exp="e_${var}" + local prev_ret="${2}" + + if [ "${!var}" = "${!exp}" ] + then + return 0 + fi + + if [ "${prev_ret}" = "0" ] + then + stdbuf -o0 -e0 printf "[FAIL]\n" + fi + + stdbuf -o0 -e0 printf "\tExpected value for '%s': '%s', got '%s'.\n" \ + "${var}" "${!var}" "${!exp}" + return 1 +} + +# $@: all var names to check +check_expected() +{ + local ret=0 + local var + + for var in "${@}" + do + check_expected_one "${var}" "${ret}" || ret=1 + done + + if [ ${ret} -eq 0 ] + then + stdbuf -o0 -e0 printf "[OK]\n" + return 0 + fi + + exit 1 +} + verify_announce_event() { local evt=$1 @@ -242,19 +289,14 @@ verify_announce_event() fi dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && - [ "$addr" = "$e_addr" ] && [ "$dport" = "$e_dport" ] && - [ "$id" = "$e_id" ] - then - stdbuf -o0 -e0 printf "[OK]\n" - return 0 - fi - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + + check_expected "type" "token" "addr" "dport" "id" } test_announce() { + print_title "Announce tests" + # Capture events on the network namespace running the server :>"$server_evts" @@ -270,7 +312,7 @@ test_announce() then stdbuf -o0 -e0 printf "[OK]\n" else - stdbuf -o0 -e0 printf "[FAIL]\n" + stdbuf -o0 -e0 printf "[FAIL]\n\ttype defined: %s\n" "${type}" exit 1 fi @@ -347,18 +389,14 @@ verify_remove_event() type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && - [ "$id" = "$e_id" ] - then - stdbuf -o0 -e0 printf "[OK]\n" - return 0 - fi - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + + check_expected "type" "token" "id" } test_remove() { + print_title "Remove tests" + # Capture events on the network namespace running the server :>"$server_evts" @@ -507,20 +545,13 @@ verify_subflow_events() daddr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") fi - if [ "$type" = "$e_type" ] && [ "$token" = "$e_token" ] && - [ "$daddr" = "$e_daddr" ] && [ "$e_dport" = "$dport" ] && - [ "$family" = "$e_family" ] && [ "$saddr" = "$e_saddr" ] && - [ "$e_locid" = "$locid" ] && [ "$e_remid" = "$remid" ] - then - stdbuf -o0 -e0 printf "[OK]\n" - return 0 - fi - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + check_expected "type" "token" "daddr" "dport" "family" "saddr" "locid" "remid" } test_subflows() { + print_title "Subflows v4 or v6 only tests" + # Capture events on the network namespace running the server :>"$server_evts" @@ -754,6 +785,8 @@ test_subflows() test_subflows_v4_v6_mix() { + print_title "Subflows v4 and v6 mix tests" + # Attempt to add a listener at 10.0.2.1:<subflow-port> ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ $app6_port > /dev/null 2>&1 & @@ -800,6 +833,8 @@ test_subflows_v4_v6_mix() test_prio() { + print_title "Prio tests" + local count # Send MP_PRIO signal from client to server machine @@ -811,7 +846,7 @@ test_prio() count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ $count != 1 ]; then - stdbuf -o0 -e0 printf "[FAIL]\n" + stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}" exit 1 else stdbuf -o0 -e0 printf "[OK]\n" @@ -822,7 +857,7 @@ test_prio() count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ $count != 1 ]; then - stdbuf -o0 -e0 printf "[FAIL]\n" + stdbuf -o0 -e0 printf "[FAIL]\n\tCount != 1: %d\n" "${count}" exit 1 else stdbuf -o0 -e0 printf "[OK]\n" @@ -863,19 +898,13 @@ verify_listener_events() sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') fi - if [ $type ] && [ $type = $e_type ] && - [ $family ] && [ $family = $e_family ] && - [ $saddr ] && [ $saddr = $e_saddr ] && - [ $sport ] && [ $sport = $e_sport ]; then - stdbuf -o0 -e0 printf "[OK]\n" - return 0 - fi - stdbuf -o0 -e0 printf "[FAIL]\n" - exit 1 + check_expected "type" "family" "saddr" "sport" } test_listener() { + print_title "Listener tests" + # Capture events on the network namespace running the client :>$client_evts @@ -902,8 +931,10 @@ test_listener() verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } +print_title "Make connections" make_connection make_connection "v6" + test_announce test_remove test_subflows diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/nat6to4.c index ac54c36b25fc..ac54c36b25fc 100644 --- a/tools/testing/selftests/net/bpf/nat6to4.c +++ b/tools/testing/selftests/net/nat6to4.c diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh new file mode 100755 index 000000000000..0fd0d2db3abc --- /dev/null +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +readonly ksft_skip=4 +readonly cpus=$(nproc) +ret=0 + +[ $cpus -gt 2 ] || exit $ksft_skip + +readonly INITIAL_RPS_DEFAULT_MASK=$(cat /proc/sys/net/core/rps_default_mask) +readonly TAG="$(mktemp -u XXXXXX)" +readonly VETH="veth${TAG}" +readonly NETNS="ns-${TAG}" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up +} + +cleanup() { + echo $INITIAL_RPS_DEFAULT_MASK > /proc/sys/net/core/rps_default_mask + ip netns del $NETNS +} + +chk_rps() { + local rps_mask expected_rps_mask=$4 + local dev_name=$3 + local netns=$2 + local cmd="cat" + local msg=$1 + + [ -n "$netns" ] && cmd="ip netns exec $netns $cmd" + + rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus) + printf "%-60s" "$msg" + if [ $rps_mask -eq $expected_rps_mask ]; then + echo "[ ok ]" + else + echo "[fail] expected $expected_rps_mask found $rps_mask" + ret=1 + fi +} + +trap cleanup EXIT + +echo 0 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "empty rps_default_mask" $NETNS lo 0 +cleanup + +echo 1 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "changing rps_default_mask dont affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK + +echo 3 > /proc/sys/net/core/rps_default_mask +chk_rps "changing rps_default_mask dont affect existing netns" $NETNS lo 0 + +ip link add name $VETH type veth peer netns $NETNS name $VETH +ip link set dev $VETH up +ip -n $NETNS link set dev $VETH up +chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3 +chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0 +ip netns del $NETNS + +setup +chk_rps "rps_default_mask is 0 by default in child netns" "$NETNS" lo 0 + +ip netns exec $NETNS sysctl -qw net.core.rps_default_mask=1 +ip link add name $VETH type veth peer netns $NETNS name $VETH +chk_rps "changing rps_default_mask in child ns don't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK +chk_rps "changing rps_default_mask in child ns affects new childns devices" $NETNS $VETH 1 +chk_rps "changing rps_default_mask in child ns don't affect existing devices" $NETNS lo 0 + +exit $ret diff --git a/tools/testing/selftests/net/srv6_end_flavors_test.sh b/tools/testing/selftests/net/srv6_end_flavors_test.sh new file mode 100755 index 000000000000..50563443a4ad --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_flavors_test.sh @@ -0,0 +1,869 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Andrea Mayer <andrea.mayer@uniroma2.it> +# author: Paolo Lungaroni <paolo.lungaroni@uniroma2.it> +# +# This script is designed to test the support for "flavors" in the SRv6 End +# behavior. +# +# Flavors defined in RFC8986 [1] represent additional operations that can modify +# or extend the existing SRv6 End, End.X and End.T behaviors. For the sake of +# convenience, we report the list of flavors described in [1] hereafter: +# - Penultimate Segment Pop (PSP); +# - Ultimate Segment Pop (USP); +# - Ultimate Segment Decapsulation (USD). +# +# The End, End.X, and End.T behaviors can support these flavors either +# individually or in combinations. +# Currently in this selftest we consider only the PSP flavor for the SRv6 End +# behavior. However, it is possible to extend the script as soon as other +# flavors will be supported in the kernel. +# +# The purpose of the PSP flavor consists in instructing the penultimate node +# listed in the SRv6 policy to remove (i.e. pop) the outermost SRH from the IPv6 +# header. +# A PSP enabled SRv6 End behavior instance processes the SRH by: +# - decrementing the Segment Left (SL) value from 1 to 0; +# - copying the last SID from the SID List into the IPv6 Destination Address +# (DA); +# - removing the SRH from the extension headers following the IPv6 header. +# +# Once the SRH is removed, the IPv6 packet is forwarded to the destination using +# the IPv6 DA updated during the PSP operation (i.e. the IPv6 DA corresponding +# to the last SID carried by the removed SRH). +# +# Although the PSP flavor can be set for any SRv6 End behavior instance on any +# SR node, it will be active only on such behaviors bound to a penultimate SID +# for a given SRv6 policy. +# SL=2 SL=1 SL=0 +# | | | +# For example, given the SRv6 policy (SID List := <X, Y, Z>): +# - a PSP enabled SRv6 End behavior bound to SID Y will apply the PSP operation +# as Segment Left (SL) is 1, corresponding to the Penultimate Segment of the +# SID List; +# - a PSP enabled SRv6 End behavior bound to SID X will *NOT* apply the PSP +# operation as the Segment Left is 2. This behavior instance will apply the +# "standard" End packet processing, ignoring the configured PSP flavor at +# all. +# +# [1] RFC8986: https://datatracker.ietf.org/doc/html/rfc8986 +# +# Network topology +# ================ +# +# The network topology used in this selftest is depicted hereafter, composed by +# two hosts (hs-1, hs-2) and four routers (rt-1, rt-2, rt-3, rt-4). +# Hosts hs-1 and hs-2 are connected to routers rt-1 and rt-2, respectively, +# allowing them to communicate with each other. +# Traffic exchanged between hs-1 and hs-2 can follow different network paths. +# The network operator, through specific SRv6 Policies can steer traffic to one +# path rather than another. In this selftest this is implemented as follows: +# +# i) The SRv6 H.Insert behavior applies SRv6 Policies on traffic received by +# connected hosts. It pushes the Segment Routing Header (SRH) after the +# IPv6 header. The SRH contains the SID List (i.e. SRv6 Policy) needed for +# steering traffic across the segments/waypoints specified in that list; +# +# ii) The SRv6 End behavior advances the active SID in the SID List carried by +# the SRH; +# +# iii) The PSP enabled SRv6 End behavior is used to remove the SRH when such +# behavior is configured on a node bound to the Penultimate Segment carried +# by the SID List. +# +# cafe::1 cafe::2 +# +--------+ +--------+ +# | | | | +# | hs-1 | | hs-2 | +# | | | | +# +---+----+ +--- +---+ +# cafe::/64 | | cafe::/64 +# | | +# +---+----+ +----+---+ +# | | fcf0:0:1:2::/64 | | +# | rt-1 +-------------------+ rt-2 | +# | | | | +# +---+----+ +----+---+ +# | . . | +# | fcf0:0:1:3::/64 . | +# | . . | +# | . . | +# fcf0:0:1:4::/64 | . | fcf0:0:2:3::/64 +# | . . | +# | . . | +# | fcf0:0:2:4::/64 . | +# | . . | +# +---+----+ +----+---+ +# | | | | +# | rt-4 +-------------------+ rt-3 | +# | | fcf0:0:3:4::/64 | | +# +---+----+ +----+---+ +# +# Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in +# the IPv6 operator network. +# +# +# Local SID table +# =============== +# +# Each SRv6 router is configured with a Local SID table in which SIDs are +# stored. Considering the given SRv6 router rt-x, at least two SIDs are +# configured in the Local SID table: +# +# Local SID table for SRv6 router rt-x +# +---------------------------------------------------------------------+ +# |fcff:x::e is associated with the SRv6 End behavior | +# |fcff:x::ef1 is associated with the SRv6 End behavior with PSP flavor | +# +---------------------------------------------------------------------+ +# +# The fcff::/16 prefix is reserved by the operator for the SIDs. Reachability of +# SIDs is ensured by proper configuration of the IPv6 operator's network and +# SRv6 routers. +# +# +# SRv6 Policies +# ============= +# +# An SRv6 ingress router applies different SRv6 Policies to the traffic received +# from connected hosts on the basis of the destination addresses. +# In case of SRv6 H.Insert behavior, the SRv6 Policy enforcement consists of +# pushing the SRH (carrying a given SID List) after the existing IPv6 header. +# Note that in the inserting mode, there is no encapsulation at all. +# +# Before applying an SRv6 Policy using the SRv6 H.Insert behavior +# +------+---------+ +# | IPv6 | Payload | +# +------+---------+ +# +# After applying an SRv6 Policy using the SRv6 H.Insert behavior +# +------+-----+---------+ +# | IPv6 | SRH | Payload | +# +------+-----+---------+ +# +# Traffic from hs-1 to hs-2 +# ------------------------- +# +# Packets generated from hs-1 and directed towards hs-2 are +# handled by rt-1 which applies the following SRv6 Policy: +# +# i.a) IPv6 traffic, SID List=fcff:3::e,fcff:4::ef1,fcff:2::ef1,cafe::2 +# +# Router rt-1 is configured to enforce the Policy (i.a) through the SRv6 +# H.Insert behavior which pushes the SRH after the existing IPv6 header. This +# Policy steers the traffic from hs-1 across rt-3, rt-4, rt-2 and finally to the +# destination hs-2. +# +# As the packet reaches the router rt-3, the SRv6 End behavior bound to SID +# fcff:3::e is triggered. The behavior updates the Segment Left (from SL=3 to +# SL=2) in the SRH, the IPv6 DA with fcff:4::ef1 and forwards the packet to the +# next router on the path, i.e. rt-4. +# +# When router rt-4 receives the packet, the PSP enabled SRv6 End behavior bound +# to SID fcff:4::ef1 is executed. Since the SL=2, the PSP operation is *NOT* +# kicked in and the behavior applies the default End processing: the Segment +# Left is decreased (from SL=2 to SL=1), the IPv6 DA is updated with the SID +# fcff:2::ef1 and the packet is forwarded to router rt-2. +# +# The PSP enabled SRv6 End behavior on rt-2 is associated with SID fcff:2::ef1 +# and is executed as the packet is received. Because SL=1, the behavior applies +# the PSP processing on the packet as follows: i) SL is decreased, i.e. from +# SL=1 to SL=0; ii) last SID (cafe::2) is copied into the IPv6 DA; iii) the +# outermost SRH is removed from the extension headers following the IPv6 header. +# Once the PSP processing is completed, the packet is forwarded to the host hs-2 +# (destination). +# +# Traffic from hs-2 to hs-1 +# ------------------------- +# +# Packets generated from hs-2 and directed to hs-1 are handled by rt-2 which +# applies the following SRv6 Policy: +# +# i.b) IPv6 traffic, SID List=fcff:1::ef1,cafe::1 +# +# Router rt-2 is configured to enforce the Policy (i.b) through the SRv6 +# H.Insert behavior which pushes the SRH after the existing IPv6 header. This +# Policy steers the traffic from hs-2 across rt-1 and finally to the +# destination hs-1 +# +# +# When the router rt-1 receives the packet, the PSP enabled SRv6 End behavior +# associated with the SID fcff:1::ef1 is triggered. Since the SL=1, +# the PSP operation takes place: i) the SL is decremented; ii) the IPv6 DA is +# set with the last SID; iii) the SRH is removed from the extension headers +# after the IPv6 header. At this point, the packet with IPv6 DA=cafe::1 is sent +# to the destination, i.e. hs-1. + +# Kselftest framework requirement - SKIP code is 4. +readonly ksft_skip=4 + +readonly RDMSUFF="$(mktemp -u XXXXXXXX)" +readonly DUMMY_DEVNAME="dum0" +readonly RT2HS_DEVNAME="veth1" +readonly LOCALSID_TABLE_ID=90 +readonly IPv6_RT_NETWORK=fcf0:0 +readonly IPv6_HS_NETWORK=cafe +readonly IPv6_TESTS_ADDR=2001:db8::1 +readonly LOCATOR_SERVICE=fcff +readonly END_FUNC=000e +readonly END_PSP_FUNC=0ef1 + +PING_TIMEOUT_SEC=4 +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +# IDs of routers and hosts are initialized during the setup of the testing +# network +ROUTERS='' +HOSTS='' + +SETUP_ERR=1 + +ret=${ksft_skip} +nsuccess=0 +nfail=0 + +log_test() +{ + local rc="$1" + local expected="$2" + local msg="$3" + + if [ "${rc}" -eq "${expected}" ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + printf "\nTests passed: %3d\n" "${nsuccess}" + printf "Tests failed: %3d\n" "${nfail}" + + # when a test fails, the value of 'ret' is set to 1 (error code). + # Conversely, when all tests are passed successfully, the 'ret' value + # is set to 0 (success code). + if [ "${ret}" -ne 1 ]; then + ret=0 + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +test_command_or_ksft_skip() +{ + local cmd="$1" + + if [ ! -x "$(command -v "${cmd}")" ]; then + echo "SKIP: Could not run test without \"${cmd}\" tool"; + exit "${ksft_skip}" + fi +} + +get_nodename() +{ + local name="$1" + + echo "${name}-${RDMSUFF}" +} + +get_rtname() +{ + local rtid="$1" + + get_nodename "rt-${rtid}" +} + +get_hsname() +{ + local hsid="$1" + + get_nodename "hs-${hsid}" +} + +__create_namespace() +{ + local name="$1" + + ip netns add "${name}" +} + +create_router() +{ + local rtid="$1" + local nsname + + nsname="$(get_rtname "${rtid}")" + + __create_namespace "${nsname}" +} + +create_host() +{ + local hsid="$1" + local nsname + + nsname="$(get_hsname "${hsid}")" + + __create_namespace "${nsname}" +} + +cleanup() +{ + local nsname + local i + + # destroy routers + for i in ${ROUTERS}; do + nsname="$(get_rtname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # destroy hosts + for i in ${HOSTS}; do + nsname="$(get_hsname "${i}")" + + ip netns del "${nsname}" &>/dev/null || true + done + + # check whether the setup phase was completed successfully or not. In + # case of an error during the setup phase of the testing environment, + # the selftest is considered as "skipped". + if [ "${SETUP_ERR}" -ne 0 ]; then + echo "SKIP: Setting up the testing environment failed" + exit "${ksft_skip}" + fi + + exit "${ret}" +} + +add_link_rt_pairs() +{ + local rt="$1" + local rt_neighs="$2" + local neigh + local nsname + local neigh_nsname + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + neigh_nsname="$(get_rtname "${neigh}")" + + ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \ + type veth peer name "veth-rt-${neigh}-${rt}" \ + netns "${neigh_nsname}" + done +} + +get_network_prefix() +{ + local rt="$1" + local neigh="$2" + local p="${rt}" + local q="${neigh}" + + if [ "${p}" -gt "${q}" ]; then + p="${q}"; q="${rt}" + fi + + echo "${IPv6_RT_NETWORK}:${p}:${q}" +} + +# Given the description of a router <id:op> as an input, the function returns +# the <id> token which represents the ID of the router. +# i.e. input: "12:psp" +# output: "12" +__get_srv6_rtcfg_id() +{ + local element="$1" + + echo "${element}" | cut -d':' -f1 +} + +# Given the description of a router <id:op> as an input, the function returns +# the <op> token which represents the operation (e.g. End behavior with or +# withouth flavors) configured for the node. + +# Note that when the operation represents an End behavior with a list of +# flavors, the output is the ordered version of that list. +# i.e. input: "5:usp,psp,usd" +# output: "psp,usd,usp" +__get_srv6_rtcfg_op() +{ + local element="$1" + + # return the lexicographically ordered flavors + echo "${element}" | cut -d':' -f2 | sed 's/,/\n/g' | sort | \ + xargs | sed 's/ /,/g' +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt="$1" + local rt_neighs="$2" + local nsname + local net_prefix + local devname + local neigh + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + ip -netns "${nsname}" addr \ + add "${net_prefix}::${rt}/64" dev "${devname}" nodad + + ip -netns "${nsname}" link set "${devname}" up + done + + ip -netns "${nsname}" link set lo up + + ip -netns "${nsname}" link add ${DUMMY_DEVNAME} type dummy + ip -netns "${nsname}" link set ${DUMMY_DEVNAME} up + + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +# Setup local SIDs for an SRv6 router +setup_rt_local_sids() +{ + local rt="$1" + local rt_neighs="$2" + local net_prefix + local devname + local nsname + local neigh + + nsname="$(get_rtname "${rt}")" + + for neigh in ${rt_neighs}; do + devname="veth-rt-${rt}-${neigh}" + + net_prefix="$(get_network_prefix "${rt}" "${neigh}")" + + # set underlay network routes for SIDs reachability + ip -netns "${nsname}" -6 route \ + add "${LOCATOR_SERVICE}:${neigh}::/32" \ + table "${LOCALSID_TABLE_ID}" \ + via "${net_prefix}::${neigh}" dev "${devname}" + done + + # Local End behavior (note that "dev" is a dummy interface chosen for + # the sake of simplicity). + ip -netns "${nsname}" -6 route \ + add "${LOCATOR_SERVICE}:${rt}::${END_FUNC}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End dev "${DUMMY_DEVNAME}" + + + # all SIDs start with a common locator. Routes and SRv6 Endpoint + # behavior instaces are grouped together in the 'localsid' table. + ip -netns "${nsname}" -6 rule \ + add to "${LOCATOR_SERVICE}::/16" \ + lookup "${LOCALSID_TABLE_ID}" prio 999 + + # set default routes to unreachable + ip -netns "${nsname}" -6 route \ + add unreachable default metric 4278198272 \ + dev "${DUMMY_DEVNAME}" +} + +# This helper function builds and installs the SID List (i.e. SRv6 Policy) +# to be applied on incoming packets at the ingress node. Moreover, it +# configures the SRv6 nodes specified in the SID List to process the traffic +# according to the operations required by the Policy itself. +# args: +# $1 - destination host (i.e. cafe::x host) +# $2 - SRv6 router configured for enforcing the SRv6 Policy +# $3 - compact way to represent a list of SRv6 routers with their operations +# (i.e. behaviors) that each of them needs to perform. Every <nodeid:op> +# element constructs a SID that is associated with the behavior <op> on +# the <nodeid> node. The list of such elements forms an SRv6 Policy. +__setup_rt_policy() +{ + local dst="$1" + local encap_rt="$2" + local policy_rts="$3" + local behavior_cfg + local in_nsname + local rt_nsname + local policy='' + local function + local fullsid + local op_type + local node + local n + + in_nsname="$(get_rtname "${encap_rt}")" + + for n in ${policy_rts}; do + node="$(__get_srv6_rtcfg_id "${n}")" + op_type="$(__get_srv6_rtcfg_op "${n}")" + rt_nsname="$(get_rtname "${node}")" + + case "${op_type}" in + "noflv") + policy="${policy}${LOCATOR_SERVICE}:${node}::${END_FUNC}," + function="${END_FUNC}" + behavior_cfg="End" + ;; + + "psp") + policy="${policy}${LOCATOR_SERVICE}:${node}::${END_PSP_FUNC}," + function="${END_PSP_FUNC}" + behavior_cfg="End flavors psp" + ;; + + *) + break + ;; + esac + + fullsid="${LOCATOR_SERVICE}:${node}::${function}" + + # add SRv6 Endpoint behavior to the selected router + if ! ip -netns "${rt_nsname}" -6 route get "${fullsid}" \ + &>/dev/null; then + ip -netns "${rt_nsname}" -6 route \ + add "${fullsid}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action ${behavior_cfg} \ + dev "${DUMMY_DEVNAME}" + fi + done + + # we need to remove the trailing comma to avoid inserting an empty + # address (::0) in the SID List. + policy="${policy%,}" + + # add SRv6 policy to incoming traffic sent by connected hosts + ip -netns "${in_nsname}" -6 route \ + add "${IPv6_HS_NETWORK}::${dst}" \ + encap seg6 mode inline segs "${policy}" \ + dev "${DUMMY_DEVNAME}" + + ip -netns "${in_nsname}" -6 neigh \ + add proxy "${IPv6_HS_NETWORK}::${dst}" \ + dev "${RT2HS_DEVNAME}" +} + +# see __setup_rt_policy +setup_rt_policy_ipv6() +{ + __setup_rt_policy "$1" "$2" "$3" +} + +setup_hs() +{ + local hs="$1" + local rt="$2" + local hsname + local rtname + + hsname="$(get_hsname "${hs}")" + rtname="$(get_rtname "${rt}")" + + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip -netns "${hsname}" link add veth0 type veth \ + peer name "${RT2HS_DEVNAME}" netns "${rtname}" + + ip -netns "${hsname}" addr \ + add "${IPv6_HS_NETWORK}::${hs}/64" dev veth0 nodad + + ip -netns "${hsname}" link set veth0 up + ip -netns "${hsname}" link set lo up + + ip -netns "${rtname}" addr \ + add "${IPv6_HS_NETWORK}::254/64" dev "${RT2HS_DEVNAME}" nodad + + ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up + + ip netns exec "${rtname}" \ + sysctl -wq net.ipv6.conf."${RT2HS_DEVNAME}".proxy_ndp=1 +} + +setup() +{ + local i + + # create routers + ROUTERS="1 2 3 4"; readonly ROUTERS + for i in ${ROUTERS}; do + create_router "${i}" + done + + # create hosts + HOSTS="1 2"; readonly HOSTS + for i in ${HOSTS}; do + create_host "${i}" + done + + # set up the links for connecting routers + add_link_rt_pairs 1 "2 3 4" + add_link_rt_pairs 2 "3 4" + add_link_rt_pairs 3 "4" + + # set up the basic connectivity of routers and routes required for + # reachability of SIDs. + setup_rt_networking 1 "2 3 4" + setup_rt_networking 2 "1 3 4" + setup_rt_networking 3 "1 2 4" + setup_rt_networking 4 "1 2 3" + + # set up the hosts connected to routers + setup_hs 1 1 + setup_hs 2 2 + + # set up default SRv6 Endpoints (i.e. SRv6 End behavior) + setup_rt_local_sids 1 "2 3 4" + setup_rt_local_sids 2 "1 3 4" + setup_rt_local_sids 3 "1 2 4" + setup_rt_local_sids 4 "1 2 3" + + # set up SRv6 policies + # create a connection between hosts hs-1 and hs-2. + # The path between hs-1 and hs-2 traverses SRv6 aware routers. + # For each direction two path are chosen: + # + # Direction hs-1 -> hs-2 (PSP flavor) + # - rt-1 (SRv6 H.Insert policy) + # - rt-3 (SRv6 End behavior) + # - rt-4 (SRv6 End flavor PSP with SL>1, acting as End behavior) + # - rt-2 (SRv6 End flavor PSP with SL=1) + # + # Direction hs-2 -> hs-1 (PSP flavor) + # - rt-2 (SRv6 H.Insert policy) + # - rt-1 (SRv6 End flavor PSP with SL=1) + setup_rt_policy_ipv6 2 1 "3:noflv 4:psp 2:psp" + setup_rt_policy_ipv6 1 2 "1:psp" + + # testing environment was set up successfully + SETUP_ERR=0 +} + +check_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + local prefix + local rtsrc_nsname + + rtsrc_nsname="$(get_rtname "${rtsrc}")" + + prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")" + + ip netns exec "${rtsrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${prefix}::${rtdst}" >/dev/null 2>&1 +} + +check_and_log_rt_connectivity() +{ + local rtsrc="$1" + local rtdst="$2" + + check_rt_connectivity "${rtsrc}" "${rtdst}" + log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}" +} + +check_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + local hssrc_nsname + + hssrc_nsname="$(get_hsname "${hssrc}")" + + ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \ + "${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1 +} + +check_and_log_hs2gw_connectivity() +{ + local hssrc="$1" + + check_hs_ipv6_connectivity "${hssrc}" 254 + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> gw" +} + +check_and_log_hs_ipv6_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_hs_ipv6_connectivity "${hssrc}" "${hsdst}" + log_test $? 0 "IPv6 Hosts connectivity: hs-${hssrc} -> hs-${hsdst}" +} + +check_and_log_hs_connectivity() +{ + local hssrc="$1" + local hsdst="$2" + + check_and_log_hs_ipv6_connectivity "${hssrc}" "${hsdst}" +} + +router_tests() +{ + local i + local j + + log_section "IPv6 routers connectivity test" + + for i in ${ROUTERS}; do + for j in ${ROUTERS}; do + if [ "${i}" -eq "${j}" ]; then + continue + fi + + check_and_log_rt_connectivity "${i}" "${j}" + done + done +} + +host2gateway_tests() +{ + local hs + + log_section "IPv6 connectivity test among hosts and gateways" + + for hs in ${HOSTS}; do + check_and_log_hs2gw_connectivity "${hs}" + done +} + +host_srv6_end_flv_psp_tests() +{ + log_section "SRv6 connectivity test hosts (h1 <-> h2, PSP flavor)" + + check_and_log_hs_connectivity 1 2 + check_and_log_hs_connectivity 2 1 +} + +test_iproute2_supp_or_ksft_skip() +{ + local flavor="$1" + + if ! ip route help 2>&1 | grep -qo "${flavor}"; then + echo "SKIP: Missing SRv6 ${flavor} flavor support in iproute2" + exit "${ksft_skip}" + fi +} + +test_kernel_supp_or_ksft_skip() +{ + local flavor="$1" + local test_netns + + test_netns="kflv-$(mktemp -u XXXXXXXX)" + + if ! ip netns add "${test_netns}"; then + echo "SKIP: Cannot set up netns to test kernel support for flavors" + exit "${ksft_skip}" + fi + + if ! ip -netns "${test_netns}" link \ + add "${DUMMY_DEVNAME}" type dummy; then + echo "SKIP: Cannot set up dummy dev to test kernel support for flavors" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + if ! ip -netns "${test_netns}" link \ + set "${DUMMY_DEVNAME}" up; then + echo "SKIP: Cannot activate dummy dev to test kernel support for flavors" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + if ! ip -netns "${test_netns}" -6 route \ + add "${IPv6_TESTS_ADDR}" encap seg6local \ + action End flavors "${flavor}" dev "${DUMMY_DEVNAME}"; then + echo "SKIP: ${flavor} flavor not supported in kernel" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + ip netns del "${test_netns}" +} + +test_dummy_dev_or_ksft_skip() +{ + local test_netns + + test_netns="dummy-$(mktemp -u XXXXXXXX)" + + if ! ip netns add "${test_netns}"; then + echo "SKIP: Cannot set up netns for testing dummy dev support" + exit "${ksft_skip}" + fi + + modprobe dummy &>/dev/null || true + if ! ip -netns "${test_netns}" link \ + add "${DUMMY_DEVNAME}" type dummy; then + echo "SKIP: dummy dev not supported" + + ip netns del "${test_netns}" + exit "${ksft_skip}" + fi + + ip netns del "${test_netns}" +} + +if [ "$(id -u)" -ne 0 ]; then + echo "SKIP: Need root privileges" + exit "${ksft_skip}" +fi + +# required programs to carry out this selftest +test_command_or_ksft_skip ip +test_command_or_ksft_skip ping +test_command_or_ksft_skip sysctl +test_command_or_ksft_skip grep +test_command_or_ksft_skip cut +test_command_or_ksft_skip sed +test_command_or_ksft_skip sort +test_command_or_ksft_skip xargs + +test_dummy_dev_or_ksft_skip +test_iproute2_supp_or_ksft_skip psp +test_kernel_supp_or_ksft_skip psp + +set -e +trap cleanup EXIT + +setup +set +e + +router_tests +host2gateway_tests +host_srv6_end_flv_psp_tests + +print_log_test_results diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 00f837c9bc6c..46a02bbd31d0 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -137,7 +137,8 @@ static void *mmap_large_buffer(size_t need, size_t *allocated) if (buffer == (void *)-1) { sz = need; buffer = mmap(NULL, sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, + -1, 0); if (buffer != (void *)-1) fprintf(stderr, "MAP_HUGETLB attempt failed, look at /sys/kernel/mm/hugepages for optimal performance\n"); } diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index c9c4b9d65839..0a6359bed0b9 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -40,8 +40,8 @@ run_one() { ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact - tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action - tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file nat6to4.o section schedcls/egress4/snat4 direct-action echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & @@ -88,8 +88,8 @@ if [ ! -f ${BPF_FILE} ]; then exit -1 fi -if [ ! -f bpf/nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" +if [ ! -f nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 4058c7451e70..f35a924d4a30 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -214,11 +214,10 @@ static void do_verify_udp(const char *data, int len) static int recv_msg(int fd, char *buf, int len, int *gso_size) { - char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + char control[CMSG_SPACE(sizeof(int))] = {0}; struct msghdr msg = {0}; struct iovec iov = {0}; struct cmsghdr *cmsg; - uint16_t *gsosizeptr; int ret; iov.iov_base = buf; @@ -237,8 +236,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) cmsg = CMSG_NXTHDR(&msg, cmsg)) { if (cmsg->cmsg_level == SOL_UDP && cmsg->cmsg_type == UDP_GRO) { - gsosizeptr = (uint16_t *) CMSG_DATA(cmsg); - *gso_size = *gsosizeptr; + *gso_size = *(int *)CMSG_DATA(cmsg); break; } } diff --git a/tools/testing/selftests/netfilter/rpath.sh b/tools/testing/selftests/netfilter/rpath.sh index f7311e66d219..5289c8447a41 100755 --- a/tools/testing/selftests/netfilter/rpath.sh +++ b/tools/testing/selftests/netfilter/rpath.sh @@ -62,10 +62,16 @@ ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad # firewall matches to test -[ -n "$iptables" ] && ip netns exec "$ns2" \ - "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter -[ -n "$ip6tables" ] && ip netns exec "$ns2" \ - "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter +[ -n "$iptables" ] && { + common='-t raw -A PREROUTING -s 192.168.0.0/16' + ip netns exec "$ns2" "$iptables" $common -m rpfilter + ip netns exec "$ns2" "$iptables" $common -m rpfilter --invert +} +[ -n "$ip6tables" ] && { + common='-t raw -A PREROUTING -s fec0::/16' + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter --invert +} [ -n "$nft" ] && ip netns exec "$ns2" $nft -f - <<EOF table inet t { chain c { @@ -89,6 +95,11 @@ ipt_zero_rule() { # (command) [ -n "$1" ] || return 0 ip netns exec "$ns2" "$1" -t raw -vS | grep -q -- "-m rpfilter -c 0 0" } +ipt_zero_reverse_rule() { # (command) + [ -n "$1" ] || return 0 + ip netns exec "$ns2" "$1" -t raw -vS | \ + grep -q -- "-m rpfilter --invert -c 0 0" +} nft_zero_rule() { # (family) [ -n "$nft" ] || return 0 ip netns exec "$ns2" "$nft" list chain inet t c | \ @@ -101,8 +112,7 @@ netns_ping() { # (netns, args...) ip netns exec "$netns" ping -q -c 1 -W 1 "$@" >/dev/null } -testrun() { - # clear counters first +clear_counters() { [ -n "$iptables" ] && ip netns exec "$ns2" "$iptables" -t raw -Z [ -n "$ip6tables" ] && ip netns exec "$ns2" "$ip6tables" -t raw -Z if [ -n "$nft" ]; then @@ -111,6 +121,10 @@ testrun() { ip netns exec "$ns2" $nft -s list table inet t; ) | ip netns exec "$ns2" $nft -f - fi +} + +testrun() { + clear_counters # test 1: martian traffic should fail rpfilter matches netns_ping "$ns1" -I v0 192.168.42.1 && \ @@ -120,9 +134,13 @@ testrun() { ipt_zero_rule "$iptables" || die "iptables matched martian" ipt_zero_rule "$ip6tables" || die "ip6tables matched martian" + ipt_zero_reverse_rule "$iptables" && die "iptables not matched martian" + ipt_zero_reverse_rule "$ip6tables" && die "ip6tables not matched martian" nft_zero_rule ip || die "nft IPv4 matched martian" nft_zero_rule ip6 || die "nft IPv6 matched martian" + clear_counters + # test 2: rpfilter match should pass for regular traffic netns_ping "$ns1" 192.168.23.1 || \ die "regular ping 192.168.23.1 failed" @@ -131,6 +149,8 @@ testrun() { ipt_zero_rule "$iptables" && die "iptables match not effective" ipt_zero_rule "$ip6tables" && die "ip6tables match not effective" + ipt_zero_reverse_rule "$iptables" || die "iptables match over-effective" + ipt_zero_reverse_rule "$ip6tables" || die "ip6tables match over-effective" nft_zero_rule ip && die "nft IPv4 match not effective" nft_zero_rule ip6 && die "nft IPv6 match not effective" diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 22f1e1d73fa8..8fe61d3e3cce 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -14,21 +14,25 @@ endif # kernel image names by architecture IMAGE_i386 = arch/x86/boot/bzImage +IMAGE_x86_64 = arch/x86/boot/bzImage IMAGE_x86 = arch/x86/boot/bzImage IMAGE_arm64 = arch/arm64/boot/Image IMAGE_arm = arch/arm/boot/zImage IMAGE_mips = vmlinuz IMAGE_riscv = arch/riscv/boot/Image +IMAGE_s390 = arch/s390/boot/bzImage IMAGE = $(IMAGE_$(ARCH)) IMAGE_NAME = $(notdir $(IMAGE)) # default kernel configurations that appear to be usable DEFCONFIG_i386 = defconfig +DEFCONFIG_x86_64 = defconfig DEFCONFIG_x86 = defconfig DEFCONFIG_arm64 = defconfig DEFCONFIG_arm = multi_v7_defconfig DEFCONFIG_mips = malta_defconfig DEFCONFIG_riscv = defconfig +DEFCONFIG_s390 = defconfig DEFCONFIG = $(DEFCONFIG_$(ARCH)) # optional tests to run (default = all) @@ -36,20 +40,24 @@ TEST = # QEMU_ARCH: arch names used by qemu QEMU_ARCH_i386 = i386 +QEMU_ARCH_x86_64 = x86_64 QEMU_ARCH_x86 = x86_64 QEMU_ARCH_arm64 = aarch64 QEMU_ARCH_arm = arm QEMU_ARCH_mips = mipsel # works with malta_defconfig QEMU_ARCH_riscv = riscv64 +QEMU_ARCH_s390 = s390x QEMU_ARCH = $(QEMU_ARCH_$(ARCH)) # QEMU_ARGS : some arch-specific args to pass to qemu QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x86_64 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) # OUTPUT is only set when run from the main makefile, otherwise @@ -62,7 +70,8 @@ else Q=@ endif -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables +CFLAGS_s390 = -m64 +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables $(CFLAGS_$(ARCH)) LDFLAGS := -s help: @@ -71,6 +80,7 @@ help: @echo " help this help" @echo " sysroot create the nolibc sysroot here (uses \$$ARCH)" @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)" + @echo " run-user runs the executable under QEMU (uses \$$ARCH, \$$TEST)" @echo " initramfs prepare the initramfs with nolibc-test" @echo " defconfig create a fresh new default config (uses \$$ARCH)" @echo " kernel (re)build the kernel with the initramfs (uses \$$ARCH)" @@ -104,6 +114,11 @@ nolibc-test: nolibc-test.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc +# qemu user-land test +run-user: nolibc-test + $(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || : + $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + initramfs: nolibc-test $(QUIET_MKDIR)mkdir -p initramfs $(call QUIET_INSTALL, initramfs/init) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index f14f5076fb6d..c4a0c915139c 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -442,6 +442,35 @@ int test_getdents64(const char *dir) return ret; } +static int test_getpagesize(void) +{ + long x = getpagesize(); + int c; + + if (x < 0) + return x; + +#if defined(__x86_64__) || defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) + /* + * x86 family is always 4K page. + */ + c = (x == 4096); +#elif defined(__aarch64__) + /* + * Linux aarch64 supports three values of page size: 4K, 16K, and 64K + * which are selected at kernel compilation time. + */ + c = (x == 4096 || x == (16 * 1024) || x == (64 * 1024)); +#else + /* + * Assuming other architectures must have at least 4K page. + */ + c = (x >= 4096); +#endif + + return !c; +} + /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. */ @@ -502,6 +531,7 @@ int run_syscall(int min, int max) CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; #endif + CASE_TEST(getpagesize); EXPECT_SYSZR(1, test_getpagesize()); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(link_root1); EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break; diff --git a/tools/testing/selftests/perf_events/Makefile b/tools/testing/selftests/perf_events/Makefile index fcafa5f0d34c..db93c4ff081a 100644 --- a/tools/testing/selftests/perf_events/Makefile +++ b/tools/testing/selftests/perf_events/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include +CFLAGS += -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) LDFLAGS += -lpthread TEST_GEN_PROGS := sigtrap_threads remove_on_exec diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index edafaca1aeb3..9286a1d22cd3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -g -I../../../../usr/include/ +CFLAGS += -g $(KHDR_INCLUDES) TEST_GEN_PROGS = regression_enomem diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 778b6cdc8aed..d731e3e76d5b 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -pthread -Wall +CFLAGS += -g $(KHDR_INCLUDES) -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test diff --git a/tools/testing/selftests/powerpc/dscr/dscr.h b/tools/testing/selftests/powerpc/dscr/dscr.h index b703714e7d98..2c54998d4715 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr.h +++ b/tools/testing/selftests/powerpc/dscr/dscr.h @@ -64,48 +64,26 @@ inline void set_dscr_usr(unsigned long val) /* Default DSCR access */ unsigned long get_default_dscr(void) { - int fd = -1, ret; - char buf[16]; + int err; unsigned long val; - if (fd == -1) { - fd = open(DSCR_DEFAULT, O_RDONLY); - if (fd == -1) { - perror("open() failed"); - exit(1); - } - } - memset(buf, 0, sizeof(buf)); - lseek(fd, 0, SEEK_SET); - ret = read(fd, buf, sizeof(buf)); - if (ret == -1) { + err = read_ulong(DSCR_DEFAULT, &val, 16); + if (err) { perror("read() failed"); exit(1); } - sscanf(buf, "%lx", &val); - close(fd); return val; } void set_default_dscr(unsigned long val) { - int fd = -1, ret; - char buf[16]; + int err; - if (fd == -1) { - fd = open(DSCR_DEFAULT, O_RDWR); - if (fd == -1) { - perror("open() failed"); - exit(1); - } - } - sprintf(buf, "%lx\n", val); - ret = write(fd, buf, strlen(buf)); - if (ret == -1) { + err = write_ulong(DSCR_DEFAULT, val, 16); + if (err) { perror("write() failed"); exit(1); } - close(fd); } double uniform_deviate(int seed) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index f20d1c166d1e..4f1fef6198fc 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -12,27 +12,16 @@ static int check_cpu_dscr_default(char *file, unsigned long val) { - char buf[10]; - int fd, rc; + unsigned long cpu_dscr; + int err; - fd = open(file, O_RDWR); - if (fd == -1) { - perror("open() failed"); - return 1; - } - - rc = read(fd, buf, sizeof(buf)); - if (rc == -1) { - perror("read() failed"); - close(fd); - return 1; - } - close(fd); + err = read_ulong(file, &cpu_dscr, 16); + if (err) + return err; - buf[rc] = '\0'; - if (strtol(buf, NULL, 16) != val) { + if (cpu_dscr != val) { printf("DSCR match failed: %ld (system) %ld (cpu)\n", - val, strtol(buf, NULL, 16)); + val, cpu_dscr); return 1; } return 0; diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index e222a5858450..eed7dd7582b2 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -33,8 +33,24 @@ void *get_auxv_entry(int type); int pick_online_cpu(void); -int read_debugfs_file(char *debugfs_file, int *result); -int write_debugfs_file(char *debugfs_file, int result); +int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base); +int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base); +int parse_int(const char *buffer, size_t count, int *result, int base); +int parse_uint(const char *buffer, size_t count, unsigned int *result, int base); +int parse_long(const char *buffer, size_t count, long *result, int base); +int parse_ulong(const char *buffer, size_t count, unsigned long *result, int base); + +int read_file(const char *path, char *buf, size_t count, size_t *len); +int write_file(const char *path, const char *buf, size_t count); +int read_file_alloc(const char *path, char **buf, size_t *len); +int read_long(const char *path, long *result, int base); +int write_long(const char *path, long result, int base); +int read_ulong(const char *path, unsigned long *result, int base); +int write_ulong(const char *path, unsigned long result, int base); +int read_debugfs_file(const char *debugfs_file, char *buf, size_t count); +int write_debugfs_file(const char *debugfs_file, const char *buf, size_t count); +int read_debugfs_int(const char *debugfs_file, int *result); +int write_debugfs_int(const char *debugfs_file, int result); int read_sysfs_file(char *debugfs_file, char *result, size_t result_size); int perf_event_open_counter(unsigned int type, unsigned long config, int group_fd); diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c index 095195a25687..4de079923ccb 100644 --- a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c +++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c @@ -143,54 +143,6 @@ int gzip_header_blank(char *buf) return i; } -/* Caller must free the allocated buffer return nonzero on error. */ -int read_alloc_input_file(char *fname, char **buf, size_t *bufsize) -{ - struct stat statbuf; - FILE *fp; - char *p; - size_t num_bytes; - - if (stat(fname, &statbuf)) { - perror(fname); - return(-1); - } - fp = fopen(fname, "r"); - if (fp == NULL) { - perror(fname); - return(-1); - } - assert(NULL != (p = (char *) malloc(statbuf.st_size))); - num_bytes = fread(p, 1, statbuf.st_size, fp); - if (ferror(fp) || (num_bytes != statbuf.st_size)) { - perror(fname); - return(-1); - } - *buf = p; - *bufsize = num_bytes; - return 0; -} - -/* Returns nonzero on error */ -int write_output_file(char *fname, char *buf, size_t bufsize) -{ - FILE *fp; - size_t num_bytes; - - fp = fopen(fname, "w"); - if (fp == NULL) { - perror(fname); - return(-1); - } - num_bytes = fwrite(buf, 1, bufsize, fp); - if (ferror(fp) || (num_bytes != bufsize)) { - perror(fname); - return(-1); - } - fclose(fp); - return 0; -} - /* * Z_SYNC_FLUSH as described in zlib.h. * Returns number of appended bytes @@ -257,7 +209,7 @@ int compress_file(int argc, char **argv, void *handle) fprintf(stderr, "usage: %s <fname>\n", argv[0]); exit(-1); } - if (read_alloc_input_file(argv[1], &inbuf, &inlen)) + if (read_file_alloc(argv[1], &inbuf, &inlen)) exit(-1); fprintf(stderr, "file %s read, %ld bytes\n", argv[1], inlen); @@ -399,7 +351,7 @@ int compress_file(int argc, char **argv, void *handle) assert(FNAME_MAX > (strlen(argv[1]) + strlen(FEXT))); strcpy(outname, argv[1]); strcat(outname, FEXT); - if (write_output_file(outname, outbuf, dsttotlen)) { + if (write_file(outname, outbuf, dsttotlen)) { fprintf(stderr, "write error: %s\n", outname); exit(-1); } diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 88690b97b7b9..719f94f10d41 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -190,38 +190,14 @@ int parse_proc_maps(void) bool require_paranoia_below(int level) { + int err; long current; - char *end, buf[16]; - FILE *f; - bool rc; - - rc = false; - - f = fopen(PARANOID_PATH, "r"); - if (!f) { - perror("fopen"); - goto out; - } - if (!fgets(buf, sizeof(buf), f)) { - printf("Couldn't read " PARANOID_PATH "?\n"); - goto out_close; - } - - current = strtol(buf, &end, 10); - - if (end == buf) { + err = read_long(PARANOID_PATH, ¤t, 10); + if (err) { printf("Couldn't parse " PARANOID_PATH "?\n"); - goto out_close; + return false; } - if (current >= level) - goto out_close; - - rc = true; -out_close: - fclose(f); -out: - return rc; + return current < level; } - diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 2f02cb54224d..cbeeaeae8837 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -33,7 +33,7 @@ TESTS_64 := $(patsubst %,$(OUTPUT)/%,$(TESTS_64)) $(TESTS_64): CFLAGS += -m64 $(TM_TESTS): CFLAGS += -I../tm -mhtm -CFLAGS += -I../../../../../usr/include -fno-pie +CFLAGS += $(KHDR_INCLUDES) -fno-pie $(OUTPUT)/ptrace-gpr: ptrace-gpr.S $(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index 4e8d0ce1ff58..f6f8596ce8e1 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -348,15 +348,11 @@ static int parent(struct shared_info *info, pid_t pid) static int write_core_pattern(const char *core_pattern) { - size_t len = strlen(core_pattern), ret; - FILE *f; + int err; - f = fopen(core_pattern_file, "w"); - SKIP_IF_MSG(!f, "Try with root privileges"); - - ret = fwrite(core_pattern, 1, len, f); - fclose(f); - if (ret != len) { + err = write_file(core_pattern_file, core_pattern, strlen(core_pattern)); + if (err) { + SKIP_IF_MSG(err == -EPERM, "Try with root privileges"); perror("Error writing to core_pattern file"); return TEST_FAIL; } @@ -366,8 +362,8 @@ static int write_core_pattern(const char *core_pattern) static int setup_core_pattern(char **core_pattern_, bool *changed_) { - FILE *f; char *core_pattern; + size_t len; int ret; core_pattern = malloc(PATH_MAX); @@ -376,22 +372,14 @@ static int setup_core_pattern(char **core_pattern_, bool *changed_) return TEST_FAIL; } - f = fopen(core_pattern_file, "r"); - if (!f) { - perror("Error opening core_pattern file"); - ret = TEST_FAIL; - goto out; - } - - ret = fread(core_pattern, 1, PATH_MAX - 1, f); - fclose(f); - if (!ret) { + ret = read_file(core_pattern_file, core_pattern, PATH_MAX - 1, &len); + if (ret) { perror("Error reading core_pattern file"); ret = TEST_FAIL; goto out; } - core_pattern[ret] = '\0'; + core_pattern[len] = '\0'; /* Check whether we can predict the name of the core file. */ if (!strcmp(core_pattern, "core") || !strcmp(core_pattern, "core.%p")) diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index 7488315fd847..e0d979ab0204 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -5,7 +5,7 @@ TEST_PROGS := mitigation-patching.sh top_srcdir = ../../../../.. -CFLAGS += -I../../../../../usr/include +CFLAGS += $(KHDR_INCLUDES) include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c index 68ce377b205e..e01c573deadd 100644 --- a/tools/testing/selftests/powerpc/security/entry_flush.c +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -34,18 +34,18 @@ int entry_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } if (rfi_flush_orig != 0) { - if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", 0) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); FAIL_IF(1); } @@ -105,7 +105,7 @@ again: if (entry_flush == entry_flush_orig) { entry_flush = !entry_flush_orig; - if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); return 1; } @@ -120,12 +120,12 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush debugfs file"); return 1; } diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index f73484a6470f..6bedc86443a6 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -34,18 +34,18 @@ int rfi_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { have_entry_flush = 0; } else { have_entry_flush = 1; if (entry_flush_orig != 0) { - if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + if (write_debugfs_int("powerpc/entry_flush", 0) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); return 1; } @@ -105,7 +105,7 @@ again: if (rfi_flush == rfi_flush_orig) { rfi_flush = !rfi_flush_orig; - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; } @@ -120,13 +120,13 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } if (have_entry_flush) { - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush " "debugfs file"); return 1; diff --git a/tools/testing/selftests/powerpc/security/uaccess_flush.c b/tools/testing/selftests/powerpc/security/uaccess_flush.c index cf80f960e38a..fcf23ea9b183 100644 --- a/tools/testing/selftests/powerpc/security/uaccess_flush.c +++ b/tools/testing/selftests/powerpc/security/uaccess_flush.c @@ -36,30 +36,30 @@ int uaccess_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/uaccess_flush", &uaccess_flush_orig) < 0) { + if (read_debugfs_int("powerpc/uaccess_flush", &uaccess_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } if (rfi_flush_orig != 0) { - if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", 0) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); FAIL_IF(1); } } if (entry_flush_orig != 0) { - if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + if (write_debugfs_int("powerpc/entry_flush", 0) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); FAIL_IF(1); } @@ -119,7 +119,7 @@ again: if (uaccess_flush == uaccess_flush_orig) { uaccess_flush = !uaccess_flush_orig; - if (write_debugfs_file("powerpc/uaccess_flush", uaccess_flush) < 0) { + if (write_debugfs_int("powerpc/uaccess_flush", uaccess_flush) < 0) { perror("error writing to powerpc/uaccess_flush debugfs file"); return 1; } @@ -134,17 +134,17 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/uaccess_flush", uaccess_flush_orig) < 0) { + if (write_debugfs_int("powerpc/uaccess_flush", uaccess_flush_orig) < 0) { perror("unable to restore original value of powerpc/uaccess_flush debugfs file"); return 1; } diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile index b63f8459c704..ee1740ddfb0c 100644 --- a/tools/testing/selftests/powerpc/syscalls/Makefile +++ b/tools/testing/selftests/powerpc/syscalls/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only TEST_GEN_PROGS := ipc_unmuxed rtas_filter -CFLAGS += -I../../../../../usr/include +CFLAGS += $(KHDR_INCLUDES) top_srcdir = ../../../../.. include ../../lib.mk -$(TEST_GEN_PROGS): ../harness.c +$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/syscalls/rtas_filter.c b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c index 03b487f18d00..9b17780f0b18 100644 --- a/tools/testing/selftests/powerpc/syscalls/rtas_filter.c +++ b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c @@ -8,6 +8,7 @@ #include <byteswap.h> #include <stdint.h> #include <inttypes.h> +#include <linux/limits.h> #include <stdio.h> #include <string.h> #include <sys/syscall.h> @@ -50,70 +51,16 @@ struct region { struct region *next; }; -int read_entire_file(int fd, char **buf, size_t *len) -{ - size_t buf_size = 0; - size_t off = 0; - int rc; - - *buf = NULL; - do { - buf_size += BLOCK_SIZE; - if (*buf == NULL) - *buf = malloc(buf_size); - else - *buf = realloc(*buf, buf_size); - - if (*buf == NULL) - return -ENOMEM; - - rc = read(fd, *buf + off, BLOCK_SIZE); - if (rc < 0) - return -EIO; - - off += rc; - } while (rc == BLOCK_SIZE); - - if (len) - *len = off; - - return 0; -} - -static int open_prop_file(const char *prop_path, const char *prop_name, int *fd) -{ - char *path; - int len; - - /* allocate enough for two string, a slash and trailing NULL */ - len = strlen(prop_path) + strlen(prop_name) + 1 + 1; - path = malloc(len); - if (path == NULL) - return -ENOMEM; - - snprintf(path, len, "%s/%s", prop_path, prop_name); - - *fd = open(path, O_RDONLY); - free(path); - if (*fd < 0) - return -errno; - - return 0; -} - static int get_property(const char *prop_path, const char *prop_name, char **prop_val, size_t *prop_len) { - int rc, fd; - - rc = open_prop_file(prop_path, prop_name, &fd); - if (rc) - return rc; + char path[PATH_MAX]; - rc = read_entire_file(fd, prop_val, prop_len); - close(fd); + int len = snprintf(path, sizeof(path), "%s/%s", prop_path, prop_name); + if (len < 0 || len >= sizeof(path)) + return -ENOMEM; - return rc; + return read_file_alloc(path, prop_val, prop_len); } int rtas_token(const char *call_name) @@ -138,22 +85,14 @@ err: static int read_kregion_bounds(struct region *kregion) { char *buf; - int fd; - int rc; + int err; - fd = open("/proc/ppc64/rtas/rmo_buffer", O_RDONLY); - if (fd < 0) { - printf("Could not open rmo_buffer file\n"); + err = read_file_alloc("/proc/ppc64/rtas/rmo_buffer", &buf, NULL); + if (err) { + perror("Could not open rmo_buffer file"); return RTAS_IO_ASSERT; } - rc = read_entire_file(fd, &buf, NULL); - close(fd); - if (rc) { - free(buf); - return rc; - } - sscanf(buf, "%" SCNx64 " %x", &kregion->addr, &kregion->size); free(buf); diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 5881e97c73c1..3876805c2f31 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -17,7 +17,7 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c CFLAGS += -mhtm $(OUTPUT)/tm-syscall: tm-syscall-asm.S -$(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include +$(OUTPUT)/tm-syscall: CFLAGS += $(KHDR_INCLUDES) $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 1f36ee1a909a..7c8cfedb012a 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -8,6 +8,8 @@ #include <elf.h> #include <errno.h> #include <fcntl.h> +#include <inttypes.h> +#include <limits.h> #include <link.h> #include <sched.h> #include <stdio.h> @@ -26,34 +28,360 @@ static char auxv[4096]; -int read_auxv(char *buf, ssize_t buf_size) +int read_file(const char *path, char *buf, size_t count, size_t *len) { - ssize_t num; - int rc, fd; + ssize_t rc; + int fd; + int err; + char eof; - fd = open("/proc/self/auxv", O_RDONLY); - if (fd == -1) { - perror("open"); + fd = open(path, O_RDONLY); + if (fd < 0) return -errno; + + rc = read(fd, buf, count); + if (rc < 0) { + err = -errno; + goto out; } - num = read(fd, buf, buf_size); - if (num < 0) { - perror("read"); - rc = -EIO; + if (len) + *len = rc; + + /* Overflow if there are still more bytes after filling the buffer */ + if (rc == count) { + rc = read(fd, &eof, 1); + if (rc != 0) { + err = -EOVERFLOW; + goto out; + } + } + + err = 0; + +out: + close(fd); + errno = -err; + return err; +} + +int read_file_alloc(const char *path, char **buf, size_t *len) +{ + size_t read_offset = 0; + size_t buffer_len = 0; + char *buffer = NULL; + int err; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + /* + * We don't use stat & preallocate st_size because some non-files + * report 0 file size. Instead just dynamically grow the buffer + * as needed. + */ + while (1) { + ssize_t rc; + + if (read_offset >= buffer_len / 2) { + char *next_buffer; + + buffer_len = buffer_len ? buffer_len * 2 : 4096; + next_buffer = realloc(buffer, buffer_len); + if (!next_buffer) { + err = -errno; + goto out; + } + buffer = next_buffer; + } + + rc = read(fd, buffer + read_offset, buffer_len - read_offset); + if (rc < 0) { + err = -errno; + goto out; + } + + if (rc == 0) + break; + + read_offset += rc; + } + + *buf = buffer; + if (len) + *len = read_offset; + + err = 0; + +out: + close(fd); + if (err) + free(buffer); + errno = -err; + return err; +} + +int write_file(const char *path, const char *buf, size_t count) +{ + int fd; + int err; + ssize_t rc; + + fd = open(path, O_WRONLY | O_CREAT | O_TRUNC, 0644); + if (fd < 0) + return -errno; + + rc = write(fd, buf, count); + if (rc < 0) { + err = -errno; goto out; } - if (num > buf_size) { - printf("overflowed auxv buffer\n"); - rc = -EOVERFLOW; + if (rc != count) { + err = -EOVERFLOW; goto out; } - rc = 0; + err = 0; + out: close(fd); - return rc; + errno = -err; + return err; +} + +int read_auxv(char *buf, ssize_t buf_size) +{ + int err; + + err = read_file("/proc/self/auxv", buf, buf_size, NULL); + if (err) { + perror("Error reading /proc/self/auxv"); + return err; + } + + return 0; +} + +int read_debugfs_file(const char *subpath, char *buf, size_t count) +{ + char path[PATH_MAX] = "/sys/kernel/debug/"; + + strncat(path, subpath, sizeof(path) - strlen(path) - 1); + + return read_file(path, buf, count, NULL); +} + +int write_debugfs_file(const char *subpath, const char *buf, size_t count) +{ + char path[PATH_MAX] = "/sys/kernel/debug/"; + + strncat(path, subpath, sizeof(path) - strlen(path) - 1); + + return write_file(path, buf, count); +} + +static int validate_int_parse(const char *buffer, size_t count, char *end) +{ + int err = 0; + + /* Require at least one digit */ + if (end == buffer) { + err = -EINVAL; + goto out; + } + + /* Require all remaining characters be whitespace-ish */ + for (; end < buffer + count; end++) { + if (*end == '\0') + break; + + if (*end != ' ' && *end != '\n') { + err = -EINVAL; + goto out; + } + } + +out: + errno = -err; + return err; +} + +static int parse_bounded_int(const char *buffer, size_t count, intmax_t *result, + int base, intmax_t min, intmax_t max) +{ + int err; + char *end; + + errno = 0; + *result = strtoimax(buffer, &end, base); + + if (errno) + return -errno; + + err = validate_int_parse(buffer, count, end); + if (err) + goto out; + + if (*result < min || *result > max) + err = -EOVERFLOW; + +out: + errno = -err; + return err; +} + +static int parse_bounded_uint(const char *buffer, size_t count, uintmax_t *result, + int base, uintmax_t max) +{ + int err = 0; + char *end; + + errno = 0; + *result = strtoumax(buffer, &end, base); + + if (errno) + return -errno; + + err = validate_int_parse(buffer, count, end); + if (err) + goto out; + + if (*result > max) + err = -EOVERFLOW; + +out: + errno = -err; + return err; +} + +int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base) +{ + return parse_bounded_int(buffer, count, result, base, INTMAX_MIN, INTMAX_MAX); +} + +int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base) +{ + return parse_bounded_uint(buffer, count, result, base, UINTMAX_MAX); +} + +int parse_int(const char *buffer, size_t count, int *result, int base) +{ + intmax_t parsed; + int err = parse_bounded_int(buffer, count, &parsed, base, INT_MIN, INT_MAX); + + *result = parsed; + return err; +} + +int parse_uint(const char *buffer, size_t count, unsigned int *result, int base) +{ + uintmax_t parsed; + int err = parse_bounded_uint(buffer, count, &parsed, base, UINT_MAX); + + *result = parsed; + return err; +} + +int parse_long(const char *buffer, size_t count, long *result, int base) +{ + intmax_t parsed; + int err = parse_bounded_int(buffer, count, &parsed, base, LONG_MIN, LONG_MAX); + + *result = parsed; + return err; +} + +int parse_ulong(const char *buffer, size_t count, unsigned long *result, int base) +{ + uintmax_t parsed; + int err = parse_bounded_uint(buffer, count, &parsed, base, ULONG_MAX); + + *result = parsed; + return err; +} + +int read_long(const char *path, long *result, int base) +{ + int err; + char buffer[32] = {0}; + + err = read_file(path, buffer, sizeof(buffer) - 1, NULL); + if (err) + return err; + + return parse_long(buffer, sizeof(buffer), result, base); +} + +int read_ulong(const char *path, unsigned long *result, int base) +{ + int err; + char buffer[32] = {0}; + + err = read_file(path, buffer, sizeof(buffer) - 1, NULL); + if (err) + return err; + + return parse_ulong(buffer, sizeof(buffer), result, base); +} + +int write_long(const char *path, long result, int base) +{ + int err; + int len; + char buffer[32]; + + /* Decimal only for now: no format specifier for signed hex values */ + if (base != 10) { + err = -EINVAL; + goto out; + } + + len = snprintf(buffer, sizeof(buffer), "%ld", result); + if (len < 0 || len >= sizeof(buffer)) { + err = -EOVERFLOW; + goto out; + } + + err = write_file(path, buffer, len); + +out: + errno = -err; + return err; +} + +int write_ulong(const char *path, unsigned long result, int base) +{ + int err; + int len; + char buffer[32]; + char *fmt; + + switch (base) { + case 10: + fmt = "%lu"; + break; + case 16: + fmt = "%lx"; + break; + default: + err = -EINVAL; + goto out; + } + + len = snprintf(buffer, sizeof(buffer), fmt, result); + if (len < 0 || len >= sizeof(buffer)) { + err = -errno; + goto out; + } + + err = write_file(path, buffer, len); + +out: + errno = -err; + return err; } void *find_auxv_entry(int type, char *auxv) @@ -142,65 +470,31 @@ bool is_ppc64le(void) int read_sysfs_file(char *fpath, char *result, size_t result_size) { char path[PATH_MAX] = "/sys/"; - int rc = -1, fd; strncat(path, fpath, PATH_MAX - strlen(path) - 1); - if ((fd = open(path, O_RDONLY)) < 0) - return rc; - - rc = read(fd, result, result_size); - - close(fd); - - if (rc < 0) - return rc; - - return 0; + return read_file(path, result, result_size, NULL); } -int read_debugfs_file(char *debugfs_file, int *result) +int read_debugfs_int(const char *debugfs_file, int *result) { - int rc = -1, fd; - char path[PATH_MAX]; - char value[16]; - - strcpy(path, "/sys/kernel/debug/"); - strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1); + int err; + char value[16] = {0}; - if ((fd = open(path, O_RDONLY)) < 0) - return rc; + err = read_debugfs_file(debugfs_file, value, sizeof(value) - 1); + if (err) + return err; - if ((rc = read(fd, value, sizeof(value))) < 0) - return rc; - - value[15] = 0; - *result = atoi(value); - close(fd); - - return 0; + return parse_int(value, sizeof(value), result, 10); } -int write_debugfs_file(char *debugfs_file, int result) +int write_debugfs_int(const char *debugfs_file, int result) { - int rc = -1, fd; - char path[PATH_MAX]; char value[16]; - strcpy(path, "/sys/kernel/debug/"); - strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1); - - if ((fd = open(path, O_WRONLY)) < 0) - return rc; - snprintf(value, 16, "%d", result); - if ((rc = write(fd, value, strlen(value))) < 0) - return rc; - - close(fd); - - return 0; + return write_debugfs_file(debugfs_file, value, strlen(value)); } static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, diff --git a/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c index 62a93cc61b7c..6d1a5ee8eb28 100644 --- a/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c +++ b/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c @@ -79,7 +79,7 @@ int main(void) { int n_tasks = 100, i; - fprintf(stderr, "[No further output means we're allright]\n"); + fprintf(stderr, "[No further output means we're all right]\n"); for (i=0; i<n_tasks; i++) if (fork() == 0) diff --git a/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c index 79950f9a26fd..d39511eb9b01 100644 --- a/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c +++ b/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c @@ -83,7 +83,7 @@ int main(void) { int n_tasks = 100, i; - fprintf(stderr, "[No further output means we're allright]\n"); + fprintf(stderr, "[No further output means we're all right]\n"); for (i=0; i<n_tasks; i++) if (fork() == 0) diff --git a/tools/testing/selftests/ptp/Makefile b/tools/testing/selftests/ptp/Makefile index ef06de0898b7..8f57f88ecadd 100644 --- a/tools/testing/selftests/ptp/Makefile +++ b/tools/testing/selftests/ptp/Makefile @@ -1,10 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../usr/include/ -TEST_PROGS := testptp +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := testptp LDLIBS += -lrt -all: $(TEST_PROGS) +TEST_PROGS = phc.sh include ../lib.mk - -clean: - rm -fr $(TEST_PROGS) diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index 2f1f532c39db..96ffa94afb91 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -std=c99 -pthread -iquote../../../../include/uapi -Wall +CFLAGS += -std=c99 -pthread -Wall $(KHDR_INCLUDES) TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 66d0414d8e4b..b52d5069563c 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -159,6 +159,9 @@ identify_boot_image () { qemu-system-aarch64) echo arch/arm64/boot/Image ;; + qemu-system-s390x) + echo arch/s390/boot/bzImage + ;; *) echo vmlinux ;; @@ -184,6 +187,9 @@ identify_qemu () { elif echo $u | grep -q aarch64 then echo qemu-system-aarch64 + elif echo $u | grep -q 'IBM S/390' + then + echo qemu-system-s390x elif uname -a | grep -q ppc64 then echo qemu-system-ppc64 diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh index 70d62fd0d31d..71f0dfbb2a6d 100755 --- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh +++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh @@ -64,7 +64,7 @@ ___EOF___ # build using nolibc on supported archs (smaller executable) and fall # back to regular glibc on other ones. if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \ - "||__ARM_EABI__||__aarch64__\nyes\n#endif" \ + "||__ARM_EABI__||__aarch64__||__s390x__\nyes\n#endif" \ | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \ | grep -q '^yes'; then # architecture supported by nolibc diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 82a52810a649..b357ba24af06 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) LDLIBS += -lpthread -ldl diff --git a/tools/testing/selftests/sched/Makefile b/tools/testing/selftests/sched/Makefile index 10c72f14fea9..099ee9213557 100644 --- a/tools/testing/selftests/sched/Makefile +++ b/tools/testing/selftests/sched/Makefile @@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -Wl,-rpath=./ \ $(CLANG_FLAGS) LDLIBS += -lpthread diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 8109b17dc764..25e0d95d3713 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -27,6 +27,7 @@ #include <sys/prctl.h> #include <unistd.h> #include <time.h> +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -151,12 +152,17 @@ static void create_threads(int num_threads, int thr_tids[]) static int child_func_process(void *arg) { struct child_args *ca = (struct child_args *)arg; + int ret; close(ca->pfd[0]); create_threads(ca->num_threads, ca->thr_tids); - write(ca->pfd[1], &ca->thr_tids, sizeof(int) * ca->num_threads); + ret = write(ca->pfd[1], &ca->thr_tids, sizeof(int) * ca->num_threads); + if (ret == -1) + printf("write failed on pfd[%d] - error (%s)\n", + ca->pfd[1], strerror(errno)); + close(ca->pfd[1]); while (1) @@ -169,7 +175,7 @@ static unsigned char child_func_process_stack[STACK_SIZE]; void create_processes(int num_processes, int num_threads, struct child_args proc[]) { pid_t cpid; - int i; + int i, ret; for (i = 0; i < num_processes; ++i) { proc[i].num_threads = num_threads; @@ -184,7 +190,10 @@ void create_processes(int num_processes, int num_threads, struct child_args proc } for (i = 0; i < num_processes; ++i) { - read(proc[i].pfd[0], &proc[i].thr_tids, sizeof(int) * proc[i].num_threads); + ret = read(proc[i].pfd[0], &proc[i].thr_tids, sizeof(int) * proc[i].num_threads); + if (ret == -1) + printf("read failed on proc[%d].pfd[0] error (%s)\n", + i, strerror(errno)); close(proc[i].pfd[0]); } } diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index f017c382c036..584fba487037 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/ +CFLAGS += -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) LDFLAGS += -lpthread LDLIBS += -lcap diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 61386e499b77..43ec36b179dc 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -128,6 +128,8 @@ struct seccomp_data { # define __NR_seccomp 277 # elif defined(__csky__) # define __NR_seccomp 277 +# elif defined(__loongarch__) +# define __NR_seccomp 277 # elif defined(__hppa__) # define __NR_seccomp 338 # elif defined(__powerpc__) @@ -1755,6 +1757,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) NT_ARM_SYSTEM_CALL, &__v)); \ } while (0) # define SYSCALL_RET(_regs) (_regs).regs[0] +#elif defined(__loongarch__) +# define ARCH_REGS struct user_pt_regs +# define SYSCALL_NUM(_regs) (_regs).regs[11] +# define SYSCALL_RET(_regs) (_regs).regs[4] #elif defined(__riscv) && __riscv_xlen == 64 # define ARCH_REGS struct user_regs_struct # define SYSCALL_NUM(_regs) (_regs).a7 diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index d0121a8a3523..df0f91bf6890 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra -CFLAGS += -I../../../../usr/include/ +CFLAGS += $(KHDR_INCLUDES) LDFLAGS += -pthread .PHONY: all clean diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json b/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json deleted file mode 100644 index bdcbaa4c5663..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json +++ /dev/null @@ -1,203 +0,0 @@ -[ - { - "id": "2141", - "name": "Add rsvp filter with tcp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 198.168.10.64", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 198.168.10.64 ipproto tcp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5267", - "name": "Add rsvp filter with udp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 1.1.1.1 ipproto udp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2819", - "name": "Add rsvp filter with src ip and src port", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 sender 2.2.2.2/5021 classid 1:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp sender 2.2.2.2/5021", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "c967", - "name": "Add rsvp filter with tunnelid and continue action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnelid 2 classid 1:1 action continue", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp tunnelid 2.*action order [0-9]+: gact action continue", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5463", - "name": "Add rsvp filter with tunnel and pipe action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2332", - "name": "Add rsvp filter with miltiple actions", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 7 rsvp ipproto udp session 1.1.1.1 classid 1:1 action skbedit mark 7 pipe action gact drop", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp.*action order [0-9]+: skbedit mark 7 pipe.*action order [0-9]+: gact action drop", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8879", - "name": "Add rsvp filter with tunnel and skp flag", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8261", - "name": "List rsvp filters", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 classid 1:1", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 2.2.2.2/1234 classid 2:1" - ], - "cmdUnderTest": "$TC filter show dev $DEV1 parent ffff:", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8989", - "name": "Delete rsvp filter", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1" - ], - "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 2:1 session 1.1.1.1/1234 ipproto udp tunnelid 9", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tcindex.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tcindex.json deleted file mode 100644 index 44901db70376..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tcindex.json +++ /dev/null @@ -1,227 +0,0 @@ -[ - { - "id": "8293", - "name": "Add tcindex filter with default action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref 1 tcindex chain 0 handle 0x0001 classid 1:1", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "7281", - "name": "Add tcindex filter with hash size and pass action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex hash 32 fall_through classid 1:1 action pass", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref.*tcindex chain [0-9]+ handle 0x0001 classid 1:1.*action order [0-9]+: gact action pass", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "b294", - "name": "Add tcindex filter with mask shift and reclassify action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex hash 32 mask 1 shift 2 fall_through classid 1:1 action reclassify", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref.*tcindex chain [0-9]+ handle 0x0001 classid 1:1.*action order [0-9]+: gact action reclassify", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "0532", - "name": "Add tcindex filter with pass_on and continue actions", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex hash 32 mask 1 shift 2 pass_on classid 1:1 action continue", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref.*tcindex chain [0-9]+ handle 0x0001 classid 1:1.*action order [0-9]+: gact action continue", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "d473", - "name": "Add tcindex filter with pipe action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex hash 32 mask 1 shift 2 fall_through classid 1:1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref.*tcindex chain [0-9]+ handle 0x0001 classid 1:1.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2940", - "name": "Add tcindex filter with miltiple actions", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 7 tcindex hash 32 mask 1 shift 2 fall_through classid 1:1 action skbedit mark 7 pipe action gact drop", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 7 protocol ip tcindex", - "matchPattern": "^filter parent ffff: protocol ip pref 7 tcindex.*handle 0x0001.*action.*skbedit.*mark 7 pipe.*action.*gact action drop", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "1893", - "name": "List tcindex filters", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1", - "$TC filter add dev $DEV1 parent ffff: handle 2 protocol ip prio 1 tcindex classid 1:1" - ], - "cmdUnderTest": "$TC filter show dev $DEV1 parent ffff:", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "handle 0x000[0-9]+ classid 1:1", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2041", - "name": "Change tcindex filter with pass action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action drop" - ], - "cmdUnderTest": "$TC filter change dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action pass", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "handle 0x0001 classid 1:1.*action order [0-9]+: gact action pass", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "9203", - "name": "Replace tcindex filter with pass action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action drop" - ], - "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action pass", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "handle 0x0001 classid 1:1.*action order [0-9]+: gact action pass", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "7957", - "name": "Delete tcindex filter with drop action", - "category": [ - "filter", - "tcindex" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action drop" - ], - "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 1 protocol ip prio 1 tcindex classid 1:1 action drop", - "expExitCode": "0", - "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip tcindex", - "matchPattern": "handle 0x0001 classid 1:1.*action order [0-9]+: gact action drop", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json deleted file mode 100644 index f5bc8670a67d..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json +++ /dev/null @@ -1,94 +0,0 @@ -[ - { - "id": "7628", - "name": "Create ATM with default setting", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "390a", - "name": "Delete ATM with valid handle", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root atm" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "32a0", - "name": "Show ATM class", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class atm 1: parent 1:", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6310", - "name": "Dump ATM stats", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json deleted file mode 100644 index 1ab21c83a122..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json +++ /dev/null @@ -1,184 +0,0 @@ -[ - { - "id": "3460", - "name": "Create CBQ with default setting", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "0592", - "name": "Create CBQ with mpu", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 mpu 1000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4684", - "name": "Create CBQ with valid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 128", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4345", - "name": "Create CBQ with invalid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 100", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4525", - "name": "Create CBQ with valid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 16", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6784", - "name": "Create CBQ with invalid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 128", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5468", - "name": "Delete CBQ with handle", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "492a", - "name": "Show CBQ class", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class cbq 1: root rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json deleted file mode 100644 index c030795f9c37..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json +++ /dev/null @@ -1,140 +0,0 @@ -[ - { - "id": "6345", - "name": "Create DSMARK with default setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "3462", - "name": "Create DSMARK with default_index setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 512", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0200", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "ca95", - "name": "Create DSMARK with set_tc_index flag", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "a950", - "name": "Create DSMARK with multiple setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4092", - "name": "Delete DSMARK with handle", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5930", - "name": "Show DSMARK class", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class dsmark 1:", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tdx/Makefile b/tools/testing/selftests/tdx/Makefile index 8dd43517cd55..306e9c4d5ef7 100644 --- a/tools/testing/selftests/tdx/Makefile +++ b/tools/testing/selftests/tdx/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -O3 -Wl,-no-as-needed -Wall -static +CFLAGS += -O3 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) -static TEST_GEN_PROGS := tdx_guest_test diff --git a/tools/testing/selftests/tdx/tdx_guest_test.c b/tools/testing/selftests/tdx/tdx_guest_test.c index 2a2afd856798..81d8cb88ea1a 100644 --- a/tools/testing/selftests/tdx/tdx_guest_test.c +++ b/tools/testing/selftests/tdx/tdx_guest_test.c @@ -12,8 +12,8 @@ #include <errno.h> #include <fcntl.h> +#include <linux/tdx-guest.h> #include "../kselftest_harness.h" -#include "../../../../include/uapi/linux/tdx-guest.h" #define TDX_GUEST_DEVNAME "/dev/tdx_guest" #define HEX_DUMP_SIZE 8 diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index c7363c6764fc..bba8cb54548e 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -344,7 +344,7 @@ def get_algorithm(name): def hex_dump(d): - d = [format(ord(x), '02x') for x in d] + d = [format(x, '02x') for x in d] d = [d[i: i + 16] for i in range(0, len(d), 16)] d = [' '.join(x) for x in d] d = os.linesep.join(d) diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile index c765d8635d9a..6b512b86aec3 100644 --- a/tools/testing/selftests/user_events/Makefile +++ b/tools/testing/selftests/user_events/Makefile @@ -1,7 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include +CFLAGS += -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) LDLIBS += -lrt -lpthread -lm +# Note: +# This test depends on <linux/user_events.h> exported in uapi +# The following commit removed user_events.h out of uapi: +# commit 5cfff569cab8bf544bab62c911c5d6efd5af5e05 +# tracing: Move user_events.h temporarily out of include/uapi +# This test will not compile until user_events.h is added +# back to uapi. + TEST_GEN_PROGS = ftrace_test dyn_test perf_test TEST_FILES := settings diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 0388c4d60af0..ca9374b56ead 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -34,7 +34,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) -CFLAGS := -O2 -g -std=gnu99 -pthread -Wall +CFLAGS := -O2 -g -std=gnu99 -pthread -Wall $(KHDR_INCLUDES) # call32_from_64 in thunks.S uses absolute addresses. ifeq ($(CAN_BUILD_WITH_NOPIE),1) diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index f8293c6910c9..43a254f0e14d 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only -all: test +all: test vsock_perf test: vsock_test vsock_diag_test vsock_test: vsock_test.o timeout.o control.o util.o vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o +vsock_perf: vsock_perf.o CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 4d5045e7d2c3..84ee217ba8ee 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -35,3 +35,37 @@ Invoke test binaries in both directions as follows: --control-port=$GUEST_IP \ --control-port=1234 \ --peer-cid=3 + +vsock_perf utility +------------------- +'vsock_perf' is a simple tool to measure vsock performance. It works in +sender/receiver modes: sender connect to peer at the specified port and +starts data transmission to the receiver. After data processing is done, +it prints several metrics(see below). + +Usage: +# run as sender +# connect to CID 2, port 1234, send 1G of data, tx buf size is 1M +./vsock_perf --sender 2 --port 1234 --bytes 1G --buf-size 1M + +Output: +tx performance: A Gbits/s + +Output explanation: +A is calculated as "number of bits to send" / "time in tx loop" + +# run as receiver +# listen port 1234, rx buf size is 1M, socket buf size is 1G, SO_RCVLOWAT is 64K +./vsock_perf --port 1234 --buf-size 1M --vsk-size 1G --rcvlowat 64K + +Output: +rx performance: A Gbits/s +total in 'read()': B sec +POLLIN wakeups: C +average in 'read()': D ns + +Output explanation: +A is calculated as "number of received bits" / "time in rx loop". +B is time, spent in 'read()' system call(excluding 'poll()') +C is number of 'poll()' wake ups with POLLIN bit set. +D is B / C, e.g. average amount of time, spent in single 'read()'. diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index 4874872fc5a3..d2deb4b15b94 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -141,6 +141,34 @@ void control_writeln(const char *str) timeout_end(); } +void control_writeulong(unsigned long value) +{ + char str[32]; + + if (snprintf(str, sizeof(str), "%lu", value) >= sizeof(str)) { + perror("snprintf"); + exit(EXIT_FAILURE); + } + + control_writeln(str); +} + +unsigned long control_readulong(void) +{ + unsigned long value; + char *str; + + str = control_readln(); + + if (!str) + exit(EXIT_FAILURE); + + value = strtoul(str, NULL, 10); + free(str); + + return value; +} + /* Return the next line from the control socket (without the trailing newline). * * The program terminates if a timeout occurs. diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h index 51814b4f9ac1..c1f77fdb2c7a 100644 --- a/tools/testing/vsock/control.h +++ b/tools/testing/vsock/control.h @@ -9,7 +9,9 @@ void control_init(const char *control_host, const char *control_port, void control_cleanup(void); void control_writeln(const char *str); char *control_readln(void); +unsigned long control_readulong(void); void control_expectln(const char *str); bool control_cmpln(char *line, const char *str, bool fail); +void control_writeulong(unsigned long value); #endif /* CONTROL_H */ diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 2acbb7703c6a..01b636d3039a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -395,3 +395,16 @@ void skip_test(struct test_case *test_cases, size_t test_cases_len, test_cases[test_id].skip = true; } + +unsigned long hash_djb2(const void *data, size_t len) +{ + unsigned long hash = 5381; + int i = 0; + + while (i < len) { + hash = ((hash << 5) + hash) + ((unsigned char *)data)[i]; + i++; + } + + return hash; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index a3375ad2fb7f..fb99208a95ea 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -49,4 +49,5 @@ void run_tests(const struct test_case *test_cases, void list_tests(const struct test_case *test_cases); void skip_test(struct test_case *test_cases, size_t test_cases_len, const char *test_id_str); +unsigned long hash_djb2(const void *data, size_t len); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c new file mode 100644 index 000000000000..a72520338f84 --- /dev/null +++ b/tools/testing/vsock/vsock_perf.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock_perf - benchmark utility for vsock. + * + * Copyright (C) 2022 SberDevices. + * + * Author: Arseniy Krasnov <AVKrasnov@sberdevices.ru> + */ +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <time.h> +#include <stdint.h> +#include <poll.h> +#include <sys/socket.h> +#include <linux/vm_sockets.h> + +#define DEFAULT_BUF_SIZE_BYTES (128 * 1024) +#define DEFAULT_TO_SEND_BYTES (64 * 1024) +#define DEFAULT_VSOCK_BUF_BYTES (256 * 1024) +#define DEFAULT_RCVLOWAT_BYTES 1 +#define DEFAULT_PORT 1234 + +#define BYTES_PER_GB (1024 * 1024 * 1024ULL) +#define NSEC_PER_SEC (1000000000ULL) + +static unsigned int port = DEFAULT_PORT; +static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES; +static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES; + +static void error(const char *s) +{ + perror(s); + exit(EXIT_FAILURE); +} + +static time_t current_nsec(void) +{ + struct timespec ts; + + if (clock_gettime(CLOCK_REALTIME, &ts)) + error("clock_gettime"); + + return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec; +} + +/* From lib/cmdline.c. */ +static unsigned long memparse(const char *ptr) +{ + char *endptr; + + unsigned long long ret = strtoull(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + case 'P': + case 'p': + ret <<= 10; + case 'T': + case 't': + ret <<= 10; + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + endptr++; + default: + break; + } + + return ret; +} + +static void vsock_increase_buf_size(int fd) +{ + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + &vsock_buf_bytes, sizeof(vsock_buf_bytes))) + error("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &vsock_buf_bytes, sizeof(vsock_buf_bytes))) + error("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); +} + +static int vsock_connect(unsigned int cid, unsigned int port) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (fd < 0) { + perror("socket"); + return -1; + } + + if (connect(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("connect"); + close(fd); + return -1; + } + + return fd; +} + +static float get_gbps(unsigned long bits, time_t ns_delta) +{ + return ((float)bits / 1000000000ULL) / + ((float)ns_delta / NSEC_PER_SEC); +} + +static void run_receiver(unsigned long rcvlowat_bytes) +{ + unsigned int read_cnt; + time_t rx_begin_ns; + time_t in_read_ns; + size_t total_recv; + int client_fd; + char *data; + int fd; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = VMADDR_CID_ANY, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + + socklen_t clientaddr_len = sizeof(clientaddr.svm); + + printf("Run as receiver\n"); + printf("Listen port %u\n", port); + printf("RX buffer %lu bytes\n", buf_size_bytes); + printf("vsock buffer %lu bytes\n", vsock_buf_bytes); + printf("SO_RCVLOWAT %lu bytes\n", rcvlowat_bytes); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (fd < 0) + error("socket"); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) + error("bind"); + + if (listen(fd, 1) < 0) + error("listen"); + + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + + if (client_fd < 0) + error("accept"); + + vsock_increase_buf_size(client_fd); + + if (setsockopt(client_fd, SOL_SOCKET, SO_RCVLOWAT, + &rcvlowat_bytes, + sizeof(rcvlowat_bytes))) + error("setsockopt(SO_RCVLOWAT)"); + + data = malloc(buf_size_bytes); + + if (!data) { + fprintf(stderr, "'malloc()' failed\n"); + exit(EXIT_FAILURE); + } + + read_cnt = 0; + in_read_ns = 0; + total_recv = 0; + rx_begin_ns = current_nsec(); + + while (1) { + struct pollfd fds = { 0 }; + + fds.fd = client_fd; + fds.events = POLLIN | POLLERR | + POLLHUP | POLLRDHUP; + + if (poll(&fds, 1, -1) < 0) + error("poll"); + + if (fds.revents & POLLERR) { + fprintf(stderr, "'poll()' error\n"); + exit(EXIT_FAILURE); + } + + if (fds.revents & POLLIN) { + ssize_t bytes_read; + time_t t; + + t = current_nsec(); + bytes_read = read(fds.fd, data, buf_size_bytes); + in_read_ns += (current_nsec() - t); + read_cnt++; + + if (!bytes_read) + break; + + if (bytes_read < 0) { + perror("read"); + exit(EXIT_FAILURE); + } + + total_recv += bytes_read; + } + + if (fds.revents & (POLLHUP | POLLRDHUP)) + break; + } + + printf("total bytes received: %zu\n", total_recv); + printf("rx performance: %f Gbits/s\n", + get_gbps(total_recv * 8, current_nsec() - rx_begin_ns)); + printf("total time in 'read()': %f sec\n", (float)in_read_ns / NSEC_PER_SEC); + printf("average time in 'read()': %f ns\n", (float)in_read_ns / read_cnt); + printf("POLLIN wakeups: %i\n", read_cnt); + + free(data); + close(client_fd); + close(fd); +} + +static void run_sender(int peer_cid, unsigned long to_send_bytes) +{ + time_t tx_begin_ns; + time_t tx_total_ns; + size_t total_send; + void *data; + int fd; + + printf("Run as sender\n"); + printf("Connect to %i:%u\n", peer_cid, port); + printf("Send %lu bytes\n", to_send_bytes); + printf("TX buffer %lu bytes\n", buf_size_bytes); + + fd = vsock_connect(peer_cid, port); + + if (fd < 0) + exit(EXIT_FAILURE); + + data = malloc(buf_size_bytes); + + if (!data) { + fprintf(stderr, "'malloc()' failed\n"); + exit(EXIT_FAILURE); + } + + memset(data, 0, buf_size_bytes); + total_send = 0; + tx_begin_ns = current_nsec(); + + while (total_send < to_send_bytes) { + ssize_t sent; + + sent = write(fd, data, buf_size_bytes); + + if (sent <= 0) + error("write"); + + total_send += sent; + } + + tx_total_ns = current_nsec() - tx_begin_ns; + + printf("total bytes sent: %zu\n", total_send); + printf("tx performance: %f Gbits/s\n", + get_gbps(total_send * 8, tx_total_ns)); + printf("total time in 'write()': %f sec\n", + (float)tx_total_ns / NSEC_PER_SEC); + + close(fd); + free(data); +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "help", + .has_arg = no_argument, + .val = 'H', + }, + { + .name = "sender", + .has_arg = required_argument, + .val = 'S', + }, + { + .name = "port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "bytes", + .has_arg = required_argument, + .val = 'M', + }, + { + .name = "buf-size", + .has_arg = required_argument, + .val = 'B', + }, + { + .name = "vsk-size", + .has_arg = required_argument, + .val = 'V', + }, + { + .name = "rcvlowat", + .has_arg = required_argument, + .val = 'R', + }, + {}, +}; + +static void usage(void) +{ + printf("Usage: ./vsock_perf [--help] [options]\n" + "\n" + "This is benchmarking utility, to test vsock performance.\n" + "It runs in two modes: sender or receiver. In sender mode, it\n" + "connects to the specified CID and starts data transmission.\n" + "\n" + "Options:\n" + " --help This message\n" + " --sender <cid> Sender mode (receiver default)\n" + " <cid> of the receiver to connect to\n" + " --port <port> Port (default %d)\n" + " --bytes <bytes>KMG Bytes to send (default %d)\n" + " --buf-size <bytes>KMG Data buffer size (default %d). In sender mode\n" + " it is the buffer size, passed to 'write()'. In\n" + " receiver mode it is the buffer size passed to 'read()'.\n" + " --vsk-size <bytes>KMG Socket buffer size (default %d)\n" + " --rcvlowat <bytes>KMG SO_RCVLOWAT value (default %d)\n" + "\n", DEFAULT_PORT, DEFAULT_TO_SEND_BYTES, + DEFAULT_BUF_SIZE_BYTES, DEFAULT_VSOCK_BUF_BYTES, + DEFAULT_RCVLOWAT_BYTES); + exit(EXIT_FAILURE); +} + +static long strtolx(const char *arg) +{ + long value; + char *end; + + value = strtol(arg, &end, 10); + + if (end != arg + strlen(arg)) + usage(); + + return value; +} + +int main(int argc, char **argv) +{ + unsigned long to_send_bytes = DEFAULT_TO_SEND_BYTES; + unsigned long rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES; + int peer_cid = -1; + bool sender = false; + + while (1) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'V': /* Peer buffer size. */ + vsock_buf_bytes = memparse(optarg); + break; + case 'R': /* SO_RCVLOWAT value. */ + rcvlowat_bytes = memparse(optarg); + break; + case 'P': /* Port to connect to. */ + port = strtolx(optarg); + break; + case 'M': /* Bytes to send. */ + to_send_bytes = memparse(optarg); + break; + case 'B': /* Size of rx/tx buffer. */ + buf_size_bytes = memparse(optarg); + break; + case 'S': /* Sender mode. CID to connect to. */ + peer_cid = strtolx(optarg); + sender = true; + break; + case 'H': /* Help. */ + usage(); + break; + default: + usage(); + } + } + + if (!sender) + run_receiver(rcvlowat_bytes); + else + run_sender(peer_cid, to_send_bytes); + + return 0; +} diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index bb6d691cb30d..67e9f9df3a8c 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -284,10 +284,14 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) close(fd); } -#define MESSAGES_CNT 7 -#define MSG_EOR_IDX (MESSAGES_CNT / 2) +#define SOCK_BUF_SIZE (2 * 1024 * 1024) +#define MAX_MSG_SIZE (32 * 1024) + static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long curr_hash; + int page_size; + int msg_count; int fd; fd = vsock_seqpacket_connect(opts->peer_cid, 1234); @@ -296,18 +300,79 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } - /* Send several messages, one with MSG_EOR flag */ - for (int i = 0; i < MESSAGES_CNT; i++) - send_byte(fd, 1, (i == MSG_EOR_IDX) ? MSG_EOR : 0); + /* Wait, until receiver sets buffer size. */ + control_expectln("SRVREADY"); + + curr_hash = 0; + page_size = getpagesize(); + msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE; + + for (int i = 0; i < msg_count; i++) { + ssize_t send_size; + size_t buf_size; + int flags; + void *buf; + + /* Use "small" buffers and "big" buffers. */ + if (i & 1) + buf_size = page_size + + (rand() % (MAX_MSG_SIZE - page_size)); + else + buf_size = 1 + (rand() % page_size); + + buf = malloc(buf_size); + + if (!buf) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + memset(buf, rand() & 0xff, buf_size); + /* Set at least one MSG_EOR + some random. */ + if (i == (msg_count / 2) || (rand() & 1)) { + flags = MSG_EOR; + curr_hash++; + } else { + flags = 0; + } + + send_size = send(fd, buf, buf_size, flags); + + if (send_size < 0) { + perror("send"); + exit(EXIT_FAILURE); + } + + if (send_size != buf_size) { + fprintf(stderr, "Invalid send size\n"); + exit(EXIT_FAILURE); + } + + /* + * Hash sum is computed at both client and server in + * the same way: + * H += hash('message data') + * Such hash "controls" both data integrity and message + * bounds. After data exchange, both sums are compared + * using control socket, and if message bounds wasn't + * broken - two values must be equal. + */ + curr_hash += hash_djb2(buf, buf_size); + free(buf); + } control_writeln("SENDDONE"); + control_writeulong(curr_hash); close(fd); } static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) { + unsigned long sock_buf_size; + unsigned long remote_hash; + unsigned long curr_hash; int fd; - char buf[16]; + char buf[MAX_MSG_SIZE]; struct msghdr msg = {0}; struct iovec iov = {0}; @@ -317,25 +382,57 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + &sock_buf_size, sizeof(sock_buf_size))) { + perror("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + exit(EXIT_FAILURE); + } + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &sock_buf_size, sizeof(sock_buf_size))) { + perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + exit(EXIT_FAILURE); + } + + /* Ready to receive data. */ + control_writeln("SRVREADY"); + /* Wait, until peer sends whole data. */ control_expectln("SENDDONE"); iov.iov_base = buf; iov.iov_len = sizeof(buf); msg.msg_iov = &iov; msg.msg_iovlen = 1; - for (int i = 0; i < MESSAGES_CNT; i++) { - if (recvmsg(fd, &msg, 0) != 1) { - perror("message bound violated"); - exit(EXIT_FAILURE); - } + curr_hash = 0; + + while (1) { + ssize_t recv_size; - if ((i == MSG_EOR_IDX) ^ !!(msg.msg_flags & MSG_EOR)) { - perror("MSG_EOR"); + recv_size = recvmsg(fd, &msg, 0); + + if (!recv_size) + break; + + if (recv_size < 0) { + perror("recvmsg"); exit(EXIT_FAILURE); } + + if (msg.msg_flags & MSG_EOR) + curr_hash++; + + curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size); } close(fd); + remote_hash = control_readulong(); + + if (curr_hash != remote_hash) { + fprintf(stderr, "Message bounds broken\n"); + exit(EXIT_FAILURE); + } } #define MESSAGE_TRUNC_SZ 32 @@ -427,7 +524,7 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts) tv.tv_usec = 0; if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) { - perror("setsockopt 'SO_RCVTIMEO'"); + perror("setsockopt(SO_RCVTIMEO)"); exit(EXIT_FAILURE); } @@ -472,6 +569,70 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts) close(fd); } +static void test_seqpacket_bigmsg_client(const struct test_opts *opts) +{ + unsigned long sock_buf_size; + ssize_t send_size; + socklen_t len; + void *data; + int fd; + + len = sizeof(sock_buf_size); + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (getsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &sock_buf_size, &len)) { + perror("getsockopt"); + exit(EXIT_FAILURE); + } + + sock_buf_size++; + + data = malloc(sock_buf_size); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + send_size = send(fd, data, sock_buf_size, 0); + if (send_size != -1) { + fprintf(stderr, "expected 'send(2)' failure, got %zi\n", + send_size); + exit(EXIT_FAILURE); + } + + if (errno != EMSGSIZE) { + fprintf(stderr, "expected EMSGSIZE in 'errno', got %i\n", + errno); + exit(EXIT_FAILURE); + } + + control_writeln("CLISENT"); + + free(data); + close(fd); +} + +static void test_seqpacket_bigmsg_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("CLISENT"); + + close(fd); +} + #define BUF_PATTERN_1 'a' #define BUF_PATTERN_2 'b' @@ -644,7 +805,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, &lowat_val, sizeof(lowat_val))) { - perror("setsockopt"); + perror("setsockopt(SO_RCVLOWAT)"); exit(EXIT_FAILURE); } @@ -754,6 +915,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_poll_rcvlowat_client, .run_server = test_stream_poll_rcvlowat_server, }, + { + .name = "SOCK_SEQPACKET big message", + .run_client = test_seqpacket_bigmsg_client, + .run_server = test_seqpacket_bigmsg_server, + }, {}, }; @@ -837,6 +1003,7 @@ int main(int argc, char **argv) .peer_cid = VMADDR_CID_ANY, }; + srand(time(NULL)); init_signals(); for (;;) { diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index 59a7f2346eab..0fd9c747d396 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -1584,7 +1584,7 @@ static void *do_printloop(void *arg) /* * Toss a coin to decide if we want to sleep before printing * out the backtrace. The reason for this is that opening - * /sys/kernel/debug/tracing/trace will cause a blackout of + * /sys/kernel/tracing/trace will cause a blackout of * hundreds of ms, where no latencies will be noted by the * latency tracer. Thus by randomly sleeping we try to avoid * missing traces systematically due to this. With this option diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 22e28b76f800..2456a399eb9a 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -119,6 +119,8 @@ install: doc_install $(STRIP) $(DESTDIR)$(BINDIR)/rtla @test ! -f $(DESTDIR)$(BINDIR)/osnoise || rm $(DESTDIR)$(BINDIR)/osnoise ln -s rtla $(DESTDIR)$(BINDIR)/osnoise + @test ! -f $(DESTDIR)$(BINDIR)/hwnoise || rm $(DESTDIR)$(BINDIR)/hwnoise + ln -s rtla $(DESTDIR)$(BINDIR)/hwnoise @test ! -f $(DESTDIR)$(BINDIR)/timerlat || rm $(DESTDIR)$(BINDIR)/timerlat ln -s rtla $(DESTDIR)$(BINDIR)/timerlat diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c index 4dee343909b1..3ca7a3853943 100644 --- a/tools/tracing/rtla/src/osnoise.c +++ b/tools/tracing/rtla/src/osnoise.c @@ -734,6 +734,113 @@ void osnoise_put_tracing_thresh(struct osnoise_context *context) context->orig_tracing_thresh = OSNOISE_OPTION_INIT_VAL; } +static int osnoise_options_get_option(char *option) +{ + char *options = tracefs_instance_file_read(NULL, "osnoise/options", NULL); + char no_option[128]; + int retval = 0; + char *opt; + + if (!options) + return OSNOISE_OPTION_INIT_VAL; + + /* + * Check first if the option is disabled. + */ + snprintf(no_option, sizeof(no_option), "NO_%s", option); + + opt = strstr(options, no_option); + if (opt) + goto out_free; + + /* + * Now that it is not disabled, if the string is there, it is + * enabled. If the string is not there, the option does not exist. + */ + opt = strstr(options, option); + if (opt) + retval = 1; + else + retval = OSNOISE_OPTION_INIT_VAL; + +out_free: + free(options); + return retval; +} + +static int osnoise_options_set_option(char *option, bool onoff) +{ + char no_option[128]; + + if (onoff) + return tracefs_instance_file_write(NULL, "osnoise/options", option); + + snprintf(no_option, sizeof(no_option), "NO_%s", option); + + return tracefs_instance_file_write(NULL, "osnoise/options", no_option); +} + +static int osnoise_get_irq_disable(struct osnoise_context *context) +{ + if (context->opt_irq_disable != OSNOISE_OPTION_INIT_VAL) + return context->opt_irq_disable; + + if (context->orig_opt_irq_disable != OSNOISE_OPTION_INIT_VAL) + return context->orig_opt_irq_disable; + + context->orig_opt_irq_disable = osnoise_options_get_option("OSNOISE_IRQ_DISABLE"); + + return context->orig_opt_irq_disable; +} + +int osnoise_set_irq_disable(struct osnoise_context *context, bool onoff) +{ + int opt_irq_disable = osnoise_get_irq_disable(context); + int retval; + + if (opt_irq_disable == OSNOISE_OPTION_INIT_VAL) + return -1; + + if (opt_irq_disable == onoff) + return 0; + + retval = osnoise_options_set_option("OSNOISE_IRQ_DISABLE", onoff); + if (retval < 0) + return -1; + + context->opt_irq_disable = onoff; + + return 0; +} + +static void osnoise_restore_irq_disable(struct osnoise_context *context) +{ + int retval; + + if (context->orig_opt_irq_disable == OSNOISE_OPTION_INIT_VAL) + return; + + if (context->orig_opt_irq_disable == context->opt_irq_disable) + goto out_done; + + retval = osnoise_options_set_option("OSNOISE_IRQ_DISABLE", context->orig_opt_irq_disable); + if (retval < 0) + err_msg("Could not restore original OSNOISE_IRQ_DISABLE option\n"); + +out_done: + context->orig_opt_irq_disable = OSNOISE_OPTION_INIT_VAL; +} + +static void osnoise_put_irq_disable(struct osnoise_context *context) +{ + osnoise_restore_irq_disable(context); + + if (context->orig_opt_irq_disable == OSNOISE_OPTION_INIT_VAL) + return; + + context->orig_opt_irq_disable = OSNOISE_OPTION_INIT_VAL; +} + /* * enable_osnoise - enable osnoise tracer in the trace_instance */ @@ -798,6 +905,9 @@ struct osnoise_context *osnoise_context_alloc(void) context->orig_tracing_thresh = OSNOISE_OPTION_INIT_VAL; context->tracing_thresh = OSNOISE_OPTION_INIT_VAL; + context->orig_opt_irq_disable = OSNOISE_OPTION_INIT_VAL; + context->opt_irq_disable = OSNOISE_OPTION_INIT_VAL; + osnoise_get_context(context); return context; @@ -824,6 +934,7 @@ void osnoise_put_context(struct osnoise_context *context) osnoise_put_timerlat_period_us(context); osnoise_put_print_stack(context); osnoise_put_tracing_thresh(context); + osnoise_put_irq_disable(context); free(context); } @@ -958,3 +1069,9 @@ usage: osnoise_usage(1); exit(1); } + +int hwnoise_main(int argc, char *argv[]) +{ + osnoise_top_main(argc, argv); + exit(0); +} diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h index 04a4384cc544..4dcf22ccd704 100644 --- a/tools/tracing/rtla/src/osnoise.h +++ b/tools/tracing/rtla/src/osnoise.h @@ -38,6 +38,10 @@ struct osnoise_context { /* -1 as init value because 0 is disabled */ long long orig_print_stack; long long print_stack; + + /* -1 as init value because 0 is off */ + int orig_opt_irq_disable; + int opt_irq_disable; }; /* @@ -79,6 +83,8 @@ void osnoise_restore_print_stack(struct osnoise_context *context); int osnoise_set_print_stack(struct osnoise_context *context, long long print_stack); +int osnoise_set_irq_disable(struct osnoise_context *context, bool onoff); + /* * osnoise_tool - osnoise based tool definition. */ @@ -97,3 +103,4 @@ struct osnoise_tool *osnoise_init_trace_tool(char *tracer); int osnoise_hist_main(int argc, char *argv[]); int osnoise_top_main(int argc, char **argv); int osnoise_main(int argc, char **argv); +int hwnoise_main(int argc, char **argv); diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 5d7ea479ac89..13e1233690bb 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -121,6 +121,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, { struct osnoise_hist_params *params = tool->params; struct osnoise_hist_data *data = tool->data; + unsigned long long total_duration; int entries = data->entries; int bucket; int *hist; @@ -131,10 +132,12 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (data->bucket_size) bucket = duration / data->bucket_size; + total_duration = duration * count; + hist = data->hist[cpu].samples; data->hist[cpu].count += count; update_min(&data->hist[cpu].min_sample, &duration); - update_sum(&data->hist[cpu].sum_sample, &duration); + update_sum(&data->hist[cpu].sum_sample, &total_duration); update_max(&data->hist[cpu].max_sample, &duration); if (bucket < entries) @@ -332,8 +335,8 @@ osnoise_print_summary(struct osnoise_hist_params *params, continue; if (data->hist[cpu].count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_sample / data->hist[cpu].count); + trace_seq_printf(trace->seq, "%9.2f ", + ((double) data->hist[cpu].sum_sample) / data->hist[cpu].count); else trace_seq_printf(trace->seq, " - "); } diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 76479bfb2922..562f2e4b18c5 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -14,6 +14,11 @@ #include "osnoise.h" #include "utils.h" +enum osnoise_mode { + MODE_OSNOISE = 0, + MODE_HWNOISE +}; + /* * osnoise top parameters */ @@ -32,6 +37,7 @@ struct osnoise_top_params { int set_sched; struct sched_attr sched_param; struct trace_events *events; + enum osnoise_mode mode; }; struct osnoise_top_cpu { @@ -143,15 +149,23 @@ osnoise_top_handler(struct trace_seq *s, struct tep_record *record, */ static void osnoise_top_header(struct osnoise_tool *top) { + struct osnoise_top_params *params = top->params; struct trace_seq *s = top->trace.seq; char duration[26]; get_duration(top->start_time, duration, sizeof(duration)); trace_seq_printf(s, "\033[2;37;40m"); - trace_seq_printf(s, " Operating System Noise"); - trace_seq_printf(s, " "); - trace_seq_printf(s, " "); + trace_seq_printf(s, " "); + + if (params->mode == MODE_OSNOISE) { + trace_seq_printf(s, "Operating System Noise"); + trace_seq_printf(s, " "); + } else if (params->mode == MODE_HWNOISE) { + trace_seq_printf(s, "Hardware-related Noise"); + } + + trace_seq_printf(s, " "); trace_seq_printf(s, "\033[0;0;0m"); trace_seq_printf(s, "\n"); @@ -162,7 +176,14 @@ static void osnoise_top_header(struct osnoise_tool *top) trace_seq_printf(s, " Noise "); trace_seq_printf(s, " %% CPU Aval "); trace_seq_printf(s, " Max Noise Max Single "); - trace_seq_printf(s, " HW NMI IRQ Softirq Thread"); + trace_seq_printf(s, " HW NMI"); + + if (params->mode == MODE_HWNOISE) + goto eol; + + trace_seq_printf(s, " IRQ Softirq Thread"); + +eol: trace_seq_printf(s, "\033[0;0;0m"); trace_seq_printf(s, "\n"); } @@ -181,6 +202,7 @@ static void clear_terminal(struct trace_seq *seq) */ static void osnoise_top_print(struct osnoise_tool *tool, int cpu) { + struct osnoise_top_params *params = tool->params; struct trace_seq *s = tool->trace.seq; struct osnoise_top_cpu *cpu_data; struct osnoise_top_data *data; @@ -205,6 +227,12 @@ static void osnoise_top_print(struct osnoise_tool *tool, int cpu) trace_seq_printf(s, "%12llu ", cpu_data->hw_count); trace_seq_printf(s, "%12llu ", cpu_data->nmi_count); + + if (params->mode == MODE_HWNOISE) { + trace_seq_printf(s, "\n"); + return; + } + trace_seq_printf(s, "%12llu ", cpu_data->irq_count); trace_seq_printf(s, "%12llu ", cpu_data->softirq_count); trace_seq_printf(s, "%12llu\n", cpu_data->thread_count); @@ -241,12 +269,12 @@ osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top) /* * osnoise_top_usage - prints osnoise top usage message */ -void osnoise_top_usage(char *usage) +static void osnoise_top_usage(struct osnoise_top_params *params, char *usage) { int i; static const char * const msg[] = { - " usage: rtla osnoise [top] [-h] [-q] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", + " [-h] [-q] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", " [-T us] [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] \\", " [-c cpu-list] [-P priority]", "", @@ -277,9 +305,22 @@ void osnoise_top_usage(char *usage) if (usage) fprintf(stderr, "%s\n", usage); - fprintf(stderr, "rtla osnoise top: a per-cpu summary of the OS noise (version %s)\n", + if (params->mode == MODE_OSNOISE) { + fprintf(stderr, + "rtla osnoise top: a per-cpu summary of the OS noise (version %s)\n", VERSION); + fprintf(stderr, " usage: rtla osnoise [top]"); + } + + if (params->mode == MODE_HWNOISE) { + fprintf(stderr, + "rtla hwnoise: a summary of hardware-related noise (version %s)\n", + VERSION); + + fprintf(stderr, " usage: rtla hwnoise"); + } + for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); exit(1); @@ -299,6 +340,9 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) if (!params) exit(1); + if (strcmp(argv[0], "hwnoise") == 0) + params->mode = MODE_HWNOISE; + while (1) { static struct option long_options[] = { {"auto", required_argument, 0, 'a'}, @@ -345,7 +389,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) - osnoise_top_usage("\nInvalid -c cpu list\n"); + osnoise_top_usage(params, "\nInvalid -c cpu list\n"); params->cpus = optarg; break; case 'D': @@ -354,7 +398,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) case 'd': params->duration = parse_seconds_duration(optarg); if (!params->duration) - osnoise_top_usage("Invalid -D duration\n"); + osnoise_top_usage(params, "Invalid -D duration\n"); break; case 'e': tevent = trace_event_alloc(optarg); @@ -370,17 +414,17 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) break; case 'h': case '?': - osnoise_top_usage(NULL); + osnoise_top_usage(params, NULL); break; case 'p': params->period = get_llong_from_str(optarg); if (params->period > 10000000) - osnoise_top_usage("Period longer than 10 s\n"); + osnoise_top_usage(params, "Period longer than 10 s\n"); break; case 'P': retval = parse_prio(optarg, ¶ms->sched_param); if (retval == -1) - osnoise_top_usage("Invalid -P priority"); + osnoise_top_usage(params, "Invalid -P priority"); params->set_sched = 1; break; case 'q': @@ -389,7 +433,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) case 'r': params->runtime = get_llong_from_str(optarg); if (params->runtime < 100) - osnoise_top_usage("Runtime shorter than 100 us\n"); + osnoise_top_usage(params, "Runtime shorter than 100 us\n"); break; case 's': params->stop_us = get_llong_from_str(optarg); @@ -415,7 +459,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) exit(EXIT_FAILURE); } } else { - osnoise_top_usage("--trigger requires a previous -e\n"); + osnoise_top_usage(params, "--trigger requires a previous -e\n"); } break; case '1': /* filter */ @@ -426,11 +470,11 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv) exit(EXIT_FAILURE); } } else { - osnoise_top_usage("--filter requires a previous -e\n"); + osnoise_top_usage(params, "--filter requires a previous -e\n"); } break; default: - osnoise_top_usage("Invalid option"); + osnoise_top_usage(params, "Invalid option"); } } @@ -495,6 +539,14 @@ osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_top_params *p } } + if (params->mode == MODE_HWNOISE) { + retval = osnoise_set_irq_disable(tool->context, 1); + if (retval) { + err_msg("Failed to set OSNOISE_IRQ_DISABLE option\n"); + goto out_err; + } + } + return 0; out_err: diff --git a/tools/tracing/rtla/src/rtla.c b/tools/tracing/rtla/src/rtla.c index 52e8f1825281..7635c70123ab 100644 --- a/tools/tracing/rtla/src/rtla.c +++ b/tools/tracing/rtla/src/rtla.c @@ -26,6 +26,7 @@ static void rtla_usage(int err) "", " commands:", " osnoise - gives information about the operating system noise (osnoise)", + " hwnoise - gives information about hardware-related noise", " timerlat - measures the timer irq and thread latency", "", NULL, @@ -47,6 +48,9 @@ int run_command(int argc, char **argv, int start_position) if (strcmp(argv[start_position], "osnoise") == 0) { osnoise_main(argc-start_position, &argv[start_position]); goto ran; + } else if (strcmp(argv[start_position], "hwnoise") == 0) { + hwnoise_main(argc-start_position, &argv[start_position]); + goto ran; } else if (strcmp(argv[start_position], "timerlat") == 0) { timerlat_main(argc-start_position, &argv[start_position]); goto ran; diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c new file mode 100644 index 000000000000..ec4e0f4b0e6c --- /dev/null +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -0,0 +1,990 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +#include <stdlib.h> +#include <errno.h> +#include "utils.h" +#include "osnoise.h" +#include "timerlat.h" + +enum timelat_state { + TIMERLAT_INIT = 0, + TIMERLAT_WAITING_IRQ, + TIMERLAT_WAITING_THREAD, +}; + +#define MAX_COMM 24 + +/* + * Per-cpu data statistics and data. + */ +struct timerlat_aa_data { + /* Current CPU state */ + int curr_state; + + /* timerlat IRQ latency */ + unsigned long long tlat_irq_seqnum; + unsigned long long tlat_irq_latency; + unsigned long long tlat_irq_timstamp; + + /* timerlat Thread latency */ + unsigned long long tlat_thread_seqnum; + unsigned long long tlat_thread_latency; + unsigned long long tlat_thread_timstamp; + + /* + * Information about the thread running when the IRQ + * arrived. + * + * This can be blocking or interference, depending on the + * priority of the thread. Assuming timerlat is the highest + * prio, it is blocking. If timerlat has a lower prio, it is + * interference. + * note: "unsigned long long" because they are fetch using tep_get_field_val(); + */ + unsigned long long run_thread_pid; + char run_thread_comm[MAX_COMM]; + unsigned long long thread_blocking_duration; + unsigned long long max_exit_idle_latency; + + /* Information about the timerlat timer irq */ + unsigned long long timer_irq_start_time; + unsigned long long timer_irq_start_delay; + unsigned long long timer_irq_duration; + unsigned long long timer_exit_from_idle; + + /* + * Information about the last IRQ before the timerlat irq + * arrived. + * + * If now - timestamp is <= latency, it might have influenced + * in the timerlat irq latency. Otherwise, ignore it. + */ + unsigned long long prev_irq_duration; + unsigned long long prev_irq_timstamp; + + /* + * Interference sum. + */ + unsigned long long thread_nmi_sum; + unsigned long long thread_irq_sum; + unsigned long long thread_softirq_sum; + unsigned long long thread_thread_sum; + + /* + * Interference task information. + */ + struct trace_seq *prev_irqs_seq; + struct trace_seq *nmi_seq; + struct trace_seq *irqs_seq; + struct trace_seq *softirqs_seq; + struct trace_seq *threads_seq; + struct trace_seq *stack_seq; + + /* + * Current thread. + */ + char current_comm[MAX_COMM]; + unsigned long long current_pid; + + /* + * Is the system running a kworker? + */ + unsigned long long kworker; + unsigned long long kworker_func; +}; + +/* + * The analysis context and system wide view + */ +struct timerlat_aa_context { + int nr_cpus; + int dump_tasks; + + /* per CPU data */ + struct timerlat_aa_data *taa_data; + + /* + * required to translate function names and register + * events. + */ + struct osnoise_tool *tool; +}; + +/* + * The data is stored as a local variable, but accessed via a helper function. + * + * It could be stored inside the trace context. But every access would + * require container_of() + a series of pointers. Do we need it? Not sure. + * + * For now keep it simple. If needed, store it in the tool, add the *context + * as a parameter in timerlat_aa_get_ctx() and do the magic there. + */ +static struct timerlat_aa_context *__timerlat_aa_ctx; + +static struct timerlat_aa_context *timerlat_aa_get_ctx(void) +{ + return __timerlat_aa_ctx; +} + +/* + * timerlat_aa_get_data - Get the per-cpu data from the timerlat context + */ +static struct timerlat_aa_data +*timerlat_aa_get_data(struct timerlat_aa_context *taa_ctx, int cpu) +{ + return &taa_ctx->taa_data[cpu]; +} + +/* + * timerlat_aa_irq_latency - Handles timerlat IRQ event + */ +static int timerlat_aa_irq_latency(struct timerlat_aa_data *taa_data, + struct trace_seq *s, struct tep_record *record, + struct tep_event *event) +{ + /* + * For interference, we start now looking for things that can delay + * the thread. + */ + taa_data->curr_state = TIMERLAT_WAITING_THREAD; + taa_data->tlat_irq_timstamp = record->ts; + + /* + * Zero values. + */ + taa_data->thread_nmi_sum = 0; + taa_data->thread_irq_sum = 0; + taa_data->thread_softirq_sum = 0; + taa_data->thread_blocking_duration = 0; + taa_data->timer_irq_start_time = 0; + taa_data->timer_irq_duration = 0; + taa_data->timer_exit_from_idle = 0; + + /* + * Zero interference tasks. + */ + trace_seq_reset(taa_data->nmi_seq); + trace_seq_reset(taa_data->irqs_seq); + trace_seq_reset(taa_data->softirqs_seq); + trace_seq_reset(taa_data->threads_seq); + + /* IRQ latency values */ + tep_get_field_val(s, event, "timer_latency", record, &taa_data->tlat_irq_latency, 1); + tep_get_field_val(s, event, "seqnum", record, &taa_data->tlat_irq_seqnum, 1); + + /* The thread that can cause blocking */ + tep_get_common_field_val(s, event, "common_pid", record, &taa_data->run_thread_pid, 1); + + /* + * Get exit from idle case. + * + * If it is not idle thread: + */ + if (taa_data->run_thread_pid) + return 0; + + /* + * if the latency is shorter than the known exit from idle: + */ + if (taa_data->tlat_irq_latency < taa_data->max_exit_idle_latency) + return 0; + + /* + * To be safe, ignore the cases in which an IRQ/NMI could have + * interfered with the timerlat IRQ. + */ + if (taa_data->tlat_irq_timstamp - taa_data->tlat_irq_latency + < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) + return 0; + + taa_data->max_exit_idle_latency = taa_data->tlat_irq_latency; + + return 0; +} + +/* + * timerlat_aa_thread_latency - Handles timerlat thread event + */ +static int timerlat_aa_thread_latency(struct timerlat_aa_data *taa_data, + struct trace_seq *s, struct tep_record *record, + struct tep_event *event) +{ + /* + * For interference, we start now looking for things that can delay + * the IRQ of the next cycle. + */ + taa_data->curr_state = TIMERLAT_WAITING_IRQ; + taa_data->tlat_thread_timstamp = record->ts; + + /* Thread latency values */ + tep_get_field_val(s, event, "timer_latency", record, &taa_data->tlat_thread_latency, 1); + tep_get_field_val(s, event, "seqnum", record, &taa_data->tlat_thread_seqnum, 1); + + return 0; +} + +/* + * timerlat_aa_handler - Handle timerlat events + * + * This function is called to handle timerlat events recording statistics. + * + * Returns 0 on success, -1 otherwise. + */ +int timerlat_aa_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long long thread; + + if (!taa_data) + return -1; + + tep_get_field_val(s, event, "context", record, &thread, 1); + if (!thread) + return timerlat_aa_irq_latency(taa_data, s, record, event); + else + return timerlat_aa_thread_latency(taa_data, s, record, event); +} + +/* + * timerlat_aa_nmi_handler - Handles NMI noise + * + * It is used to collect information about interferences from NMI. It is + * hooked to the osnoise:nmi_noise event. + */ +static int timerlat_aa_nmi_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long long duration; + unsigned long long start; + + tep_get_field_val(s, event, "duration", record, &duration, 1); + tep_get_field_val(s, event, "start", record, &start, 1); + + if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) { + taa_data->prev_irq_duration = duration; + taa_data->prev_irq_timstamp = start; + + trace_seq_reset(taa_data->prev_irqs_seq); + trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s \t\t\t%9.2f us\n", + "nmi", ns_to_usf(duration)); + return 0; + } + + taa_data->thread_nmi_sum += duration; + trace_seq_printf(taa_data->nmi_seq, " %24s \t\t\t%9.2f us\n", + "nmi", ns_to_usf(duration)); + + return 0; +} + +/* + * timerlat_aa_irq_handler - Handles IRQ noise + * + * It is used to collect information about interferences from IRQ. It is + * hooked to the osnoise:irq_noise event. + * + * It is a little bit more complex than the other because it measures: + * - The IRQs that can delay the timer IRQ before it happened. + * - The Timerlat IRQ handler + * - The IRQs that happened between the timerlat IRQ and the timerlat thread + * (IRQ interference). + */ +static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long long expected_start; + unsigned long long duration; + unsigned long long vector; + unsigned long long start; + char *desc; + int val; + + tep_get_field_val(s, event, "duration", record, &duration, 1); + tep_get_field_val(s, event, "start", record, &start, 1); + tep_get_field_val(s, event, "vector", record, &vector, 1); + desc = tep_get_field_raw(s, event, "desc", record, &val, 1); + + /* + * Before the timerlat IRQ. + */ + if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) { + taa_data->prev_irq_duration = duration; + taa_data->prev_irq_timstamp = start; + + trace_seq_reset(taa_data->prev_irqs_seq); + trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s:%-3llu \t\t%9.2f us\n", + desc, vector, ns_to_usf(duration)); + return 0; + } + + /* + * The timerlat IRQ: taa_data->timer_irq_start_time is zeroed at + * the timerlat irq handler. + */ + if (!taa_data->timer_irq_start_time) { + expected_start = taa_data->tlat_irq_timstamp - taa_data->tlat_irq_latency; + + taa_data->timer_irq_start_time = start; + taa_data->timer_irq_duration = duration; + + taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start; + + /* + * not exit from idle. + */ + if (taa_data->run_thread_pid) + return 0; + + if (expected_start > taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) + taa_data->timer_exit_from_idle = taa_data->timer_irq_start_delay; + + return 0; + } + + /* + * IRQ interference. + */ + taa_data->thread_irq_sum += duration; + trace_seq_printf(taa_data->irqs_seq, " %24s:%-3llu \t %9.2f us\n", + desc, vector, ns_to_usf(duration)); + + return 0; +} + +static char *softirq_name[] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", + "IRQ_POLL", "TASKLET", "SCHED", "HRTIMER", "RCU" }; + + +/* + * timerlat_aa_softirq_handler - Handles Softirq noise + * + * It is used to collect information about interferences from Softirq. It is + * hooked to the osnoise:softirq_noise event. + * + * It is only printed in the non-rt kernel, as softirqs become thread on RT. + */ +static int timerlat_aa_softirq_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long long duration; + unsigned long long vector; + unsigned long long start; + + if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) + return 0; + + tep_get_field_val(s, event, "duration", record, &duration, 1); + tep_get_field_val(s, event, "start", record, &start, 1); + tep_get_field_val(s, event, "vector", record, &vector, 1); + + taa_data->thread_softirq_sum += duration; + + trace_seq_printf(taa_data->softirqs_seq, "\t%24s:%-3llu \t %9.2f us\n", + softirq_name[vector], vector, ns_to_usf(duration)); + return 0; +} + +/* + * timerlat_aa_softirq_handler - Handles thread noise + * + * It is used to collect information about interferences from threads. It is + * hooked to the osnoise:thread_noise event. + * + * Note: if you see thread noise, your timerlat thread was not the highest prio one. + */ +static int timerlat_aa_thread_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long long duration; + unsigned long long start; + unsigned long long pid; + const char *comm; + int val; + + if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) + return 0; + + tep_get_field_val(s, event, "duration", record, &duration, 1); + tep_get_field_val(s, event, "start", record, &start, 1); + + tep_get_common_field_val(s, event, "common_pid", record, &pid, 1); + comm = tep_get_field_raw(s, event, "comm", record, &val, 1); + + if (pid == taa_data->run_thread_pid && !taa_data->thread_blocking_duration) { + taa_data->thread_blocking_duration = duration; + + if (comm) + strncpy(taa_data->run_thread_comm, comm, MAX_COMM); + else + sprintf(taa_data->run_thread_comm, "<...>"); + + } else { + taa_data->thread_thread_sum += duration; + + trace_seq_printf(taa_data->threads_seq, "\t%24s:%-3llu \t\t%9.2f us\n", + comm, pid, ns_to_usf(duration)); + } + + return 0; +} + +/* + * timerlat_aa_stack_handler - Handles timerlat IRQ stack trace + * + * Saves and parse the stack trace generated by the timerlat IRQ. + */ +static int timerlat_aa_stack_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + unsigned long *caller; + const char *function; + int val, i; + + trace_seq_reset(taa_data->stack_seq); + + trace_seq_printf(taa_data->stack_seq, " Blocking thread stack trace\n"); + caller = tep_get_field_raw(s, event, "caller", record, &val, 1); + if (caller) { + for (i = 0; ; i++) { + function = tep_find_function(taa_ctx->tool->trace.tep, caller[i]); + if (!function) + break; + trace_seq_printf(taa_data->stack_seq, "\t\t-> %s\n", function); + } + } + return 0; +} + +/* + * timerlat_aa_sched_switch_handler - Tracks the current thread running on the CPU + * + * Handles the sched:sched_switch event to trace the current thread running on the + * CPU. It is used to display the threads running on the other CPUs when the trace + * stops. + */ +static int timerlat_aa_sched_switch_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + const char *comm; + int val; + + tep_get_field_val(s, event, "next_pid", record, &taa_data->current_pid, 1); + comm = tep_get_field_raw(s, event, "next_comm", record, &val, 1); + + strncpy(taa_data->current_comm, comm, MAX_COMM); + + /* + * If this was a kworker, clean the last kworkers that ran. + */ + taa_data->kworker = 0; + taa_data->kworker_func = 0; + + return 0; +} + +/* + * timerlat_aa_kworker_start_handler - Tracks a kworker running on the CPU + * + * Handles workqueue:workqueue_execute_start event, keeping track of + * the job that a kworker could be doing in the CPU. + * + * We already catch problems of hardware related latencies caused by work queues + * running driver code that causes hardware stall. For example, with DRM drivers. + */ +static int timerlat_aa_kworker_start_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu); + + tep_get_field_val(s, event, "work", record, &taa_data->kworker, 1); + tep_get_field_val(s, event, "function", record, &taa_data->kworker_func, 1); + return 0; +} + +/* + * timerlat_thread_analysis - Prints the analysis of a CPU that hit a stop tracing + * + * This is the core of the analysis. + */ +static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, + int irq_thresh, int thread_thresh) +{ + unsigned long long exp_irq_ts; + int total; + int irq; + + /* + * IRQ latency or Thread latency? + */ + if (taa_data->tlat_irq_seqnum > taa_data->tlat_thread_seqnum) { + irq = 1; + total = taa_data->tlat_irq_latency; + } else { + irq = 0; + total = taa_data->tlat_thread_latency; + } + + /* + * Expected IRQ arrival time using the trace clock as the base. + */ + exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; + + if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) + printf(" Previous IRQ interference: \t up to %9.2f us", + ns_to_usf(taa_data->prev_irq_duration)); + + /* + * The delay that the IRQ suffered before starting. + */ + printf(" IRQ handler delay: %16s %9.2f us (%.2f %%)\n", + (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "", + ns_to_usf(taa_data->timer_irq_start_delay), + ns_to_per(total, taa_data->timer_irq_start_delay)); + + /* + * Timerlat IRQ. + */ + printf(" IRQ latency: \t\t\t\t %9.2f us\n", + ns_to_usf(taa_data->tlat_irq_latency)); + + if (irq) { + /* + * If the trace stopped due to IRQ, the other events will not happen + * because... the trace stopped :-). + * + * That is all folks, the stack trace was printed before the stop, + * so it will be displayed, it is the key. + */ + printf(" Blocking thread:\n"); + printf(" %24s:%-9llu\n", + taa_data->run_thread_comm, taa_data->run_thread_pid); + } else { + /* + * The duration of the IRQ handler that handled the timerlat IRQ. + */ + printf(" Timerlat IRQ duration: \t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->timer_irq_duration), + ns_to_per(total, taa_data->timer_irq_duration)); + + /* + * The amount of time that the current thread postponed the scheduler. + * + * Recalling that it is net from NMI/IRQ/Softirq interference, so there + * is no need to compute values here. + */ + printf(" Blocking thread: \t\t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->thread_blocking_duration), + ns_to_per(total, taa_data->thread_blocking_duration)); + + printf(" %24s:%-9llu %9.2f us\n", + taa_data->run_thread_comm, taa_data->run_thread_pid, + ns_to_usf(taa_data->thread_blocking_duration)); + } + + /* + * Print the stack trace! + */ + trace_seq_do_printf(taa_data->stack_seq); + + /* + * NMIs can happen during the IRQ, so they are always possible. + */ + if (taa_data->thread_nmi_sum) + printf(" NMI interference \t\t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->thread_nmi_sum), + ns_to_per(total, taa_data->thread_nmi_sum)); + + /* + * If it is an IRQ latency, the other factors can be skipped. + */ + if (irq) + goto print_total; + + /* + * Prints the interference caused by IRQs to the thread latency. + */ + if (taa_data->thread_irq_sum) { + printf(" IRQ interference \t\t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->thread_irq_sum), + ns_to_per(total, taa_data->thread_irq_sum)); + + trace_seq_do_printf(taa_data->irqs_seq); + } + + /* + * Prints the interference caused by Softirqs to the thread latency. + */ + if (taa_data->thread_softirq_sum) { + printf(" Softirq interference \t\t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->thread_softirq_sum), + ns_to_per(total, taa_data->thread_softirq_sum)); + + trace_seq_do_printf(taa_data->softirqs_seq); + } + + /* + * Prints the interference caused by other threads to the thread latency. + * + * If this happens, your timerlat is not the highest prio. OK, migration + * thread can happen. But otherwise, you are not measuring the "scheduling + * latency" only, and here is the difference from scheduling latency and + * timer handling latency. + */ + if (taa_data->thread_thread_sum) { + printf(" Thread interference \t\t\t %9.2f us (%.2f %%)\n", + ns_to_usf(taa_data->thread_thread_sum), + ns_to_per(total, taa_data->thread_thread_sum)); + + trace_seq_do_printf(taa_data->threads_seq); + } + + /* + * Done. + */ +print_total: + printf("------------------------------------------------------------------------\n"); + printf(" %s latency: \t\t\t %9.2f us (100%%)\n", irq ? "IRQ" : "Thread", + ns_to_usf(total)); +} + +/** + * timerlat_auto_analysis - Analyze the collected data + */ +void timerlat_auto_analysis(int irq_thresh, int thread_thresh) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + unsigned long long max_exit_from_idle = 0; + struct timerlat_aa_data *taa_data; + int max_exit_from_idle_cpu; + struct tep_handle *tep; + int cpu; + + /* bring stop tracing to the ns scale */ + irq_thresh = irq_thresh * 1000; + thread_thresh = thread_thresh * 1000; + + for (cpu = 0; cpu < taa_ctx->nr_cpus; cpu++) { + taa_data = timerlat_aa_get_data(taa_ctx, cpu); + + if (irq_thresh && taa_data->tlat_irq_latency >= irq_thresh) { + printf("## CPU %d hit stop tracing, analyzing it ##\n", cpu); + timerlat_thread_analysis(taa_data, cpu, irq_thresh, thread_thresh); + } else if (thread_thresh && (taa_data->tlat_thread_latency) >= thread_thresh) { + printf("## CPU %d hit stop tracing, analyzing it ##\n", cpu); + timerlat_thread_analysis(taa_data, cpu, irq_thresh, thread_thresh); + } + + if (taa_data->max_exit_idle_latency > max_exit_from_idle) { + max_exit_from_idle = taa_data->max_exit_idle_latency; + max_exit_from_idle_cpu = cpu; + } + + } + + if (max_exit_from_idle) { + printf("\n"); + printf("Max timerlat IRQ latency from idle: %.2f us in cpu %d\n", + ns_to_usf(max_exit_from_idle), max_exit_from_idle_cpu); + } + if (!taa_ctx->dump_tasks) + return; + + printf("\n"); + printf("Printing CPU tasks:\n"); + for (cpu = 0; cpu < taa_ctx->nr_cpus; cpu++) { + taa_data = timerlat_aa_get_data(taa_ctx, cpu); + tep = taa_ctx->tool->trace.tep; + + printf(" [%.3d] %24s:%llu", cpu, taa_data->current_comm, taa_data->current_pid); + + if (taa_data->kworker_func) + printf(" kworker:%s:%s", + tep_find_function(tep, taa_data->kworker) ? : "<...>", + tep_find_function(tep, taa_data->kworker_func)); + printf("\n"); + } + +} + +/* + * timerlat_aa_destroy_seqs - Destroy seq files used to store parsed data + */ +static void timerlat_aa_destroy_seqs(struct timerlat_aa_context *taa_ctx) +{ + struct timerlat_aa_data *taa_data; + int i; + + if (!taa_ctx->taa_data) + return; + + for (i = 0; i < taa_ctx->nr_cpus; i++) { + taa_data = timerlat_aa_get_data(taa_ctx, i); + + if (taa_data->prev_irqs_seq) { + trace_seq_destroy(taa_data->prev_irqs_seq); + free(taa_data->prev_irqs_seq); + } + + if (taa_data->nmi_seq) { + trace_seq_destroy(taa_data->nmi_seq); + free(taa_data->nmi_seq); + } + + if (taa_data->irqs_seq) { + trace_seq_destroy(taa_data->irqs_seq); + free(taa_data->irqs_seq); + } + + if (taa_data->softirqs_seq) { + trace_seq_destroy(taa_data->softirqs_seq); + free(taa_data->softirqs_seq); + } + + if (taa_data->threads_seq) { + trace_seq_destroy(taa_data->threads_seq); + free(taa_data->threads_seq); + } + + if (taa_data->stack_seq) { + trace_seq_destroy(taa_data->stack_seq); + free(taa_data->stack_seq); + } + } +} + +/* + * timerlat_aa_init_seqs - Init seq files used to store parsed information + * + * Instead of keeping data structures to store raw data, use seq files to + * store parsed data. + * + * Allocates and initialize seq files. + * + * Returns 0 on success, -1 otherwise. + */ +static int timerlat_aa_init_seqs(struct timerlat_aa_context *taa_ctx) +{ + struct timerlat_aa_data *taa_data; + int i; + + for (i = 0; i < taa_ctx->nr_cpus; i++) { + + taa_data = timerlat_aa_get_data(taa_ctx, i); + + taa_data->prev_irqs_seq = calloc(1, sizeof(*taa_data->prev_irqs_seq)); + if (!taa_data->prev_irqs_seq) + goto out_err; + + trace_seq_init(taa_data->prev_irqs_seq); + + taa_data->nmi_seq = calloc(1, sizeof(*taa_data->nmi_seq)); + if (!taa_data->nmi_seq) + goto out_err; + + trace_seq_init(taa_data->nmi_seq); + + taa_data->irqs_seq = calloc(1, sizeof(*taa_data->irqs_seq)); + if (!taa_data->irqs_seq) + goto out_err; + + trace_seq_init(taa_data->irqs_seq); + + taa_data->softirqs_seq = calloc(1, sizeof(*taa_data->softirqs_seq)); + if (!taa_data->softirqs_seq) + goto out_err; + + trace_seq_init(taa_data->softirqs_seq); + + taa_data->threads_seq = calloc(1, sizeof(*taa_data->threads_seq)); + if (!taa_data->threads_seq) + goto out_err; + + trace_seq_init(taa_data->threads_seq); + + taa_data->stack_seq = calloc(1, sizeof(*taa_data->stack_seq)); + if (!taa_data->stack_seq) + goto out_err; + + trace_seq_init(taa_data->stack_seq); + } + + return 0; + +out_err: + timerlat_aa_destroy_seqs(taa_ctx); + return -1; +} + +/* + * timerlat_aa_unregister_events - Unregister events used in the auto-analysis + */ +static void timerlat_aa_unregister_events(struct osnoise_tool *tool, int dump_tasks) +{ + tracefs_event_disable(tool->trace.inst, "osnoise", NULL); + + tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "nmi_noise", + timerlat_aa_nmi_handler, tool); + + tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "irq_noise", + timerlat_aa_irq_handler, tool); + + tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "softirq_noise", + timerlat_aa_softirq_handler, tool); + + tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "thread_noise", + timerlat_aa_thread_handler, tool); + + tep_unregister_event_handler(tool->trace.tep, -1, "ftrace", "kernel_stack", + timerlat_aa_stack_handler, tool); + if (!dump_tasks) + return; + + tracefs_event_disable(tool->trace.inst, "sched", "sched_switch"); + tep_unregister_event_handler(tool->trace.tep, -1, "sched", "sched_switch", + timerlat_aa_sched_switch_handler, tool); + + tracefs_event_disable(tool->trace.inst, "workqueue", "workqueue_execute_start"); + tep_unregister_event_handler(tool->trace.tep, -1, "workqueue", "workqueue_execute_start", + timerlat_aa_kworker_start_handler, tool); +} + +/* + * timerlat_aa_register_events - Register events used in the auto-analysis + * + * Returns 0 on success, -1 otherwise. + */ +static int timerlat_aa_register_events(struct osnoise_tool *tool, int dump_tasks) +{ + int retval; + + /* + * register auto-analysis handlers. + */ + retval = tracefs_event_enable(tool->trace.inst, "osnoise", NULL); + if (retval < 0 && !errno) { + err_msg("Could not find osnoise events\n"); + goto out_err; + } + + tep_register_event_handler(tool->trace.tep, -1, "osnoise", "nmi_noise", + timerlat_aa_nmi_handler, tool); + + tep_register_event_handler(tool->trace.tep, -1, "osnoise", "irq_noise", + timerlat_aa_irq_handler, tool); + + tep_register_event_handler(tool->trace.tep, -1, "osnoise", "softirq_noise", + timerlat_aa_softirq_handler, tool); + + tep_register_event_handler(tool->trace.tep, -1, "osnoise", "thread_noise", + timerlat_aa_thread_handler, tool); + + tep_register_event_handler(tool->trace.tep, -1, "ftrace", "kernel_stack", + timerlat_aa_stack_handler, tool); + + if (!dump_tasks) + return 0; + + /* + * Dump task events. + */ + retval = tracefs_event_enable(tool->trace.inst, "sched", "sched_switch"); + if (retval < 0 && !errno) { + err_msg("Could not find sched_switch\n"); + goto out_err; + } + + tep_register_event_handler(tool->trace.tep, -1, "sched", "sched_switch", + timerlat_aa_sched_switch_handler, tool); + + retval = tracefs_event_enable(tool->trace.inst, "workqueue", "workqueue_execute_start"); + if (retval < 0 && !errno) { + err_msg("Could not find workqueue_execute_start\n"); + goto out_err; + } + + tep_register_event_handler(tool->trace.tep, -1, "workqueue", "workqueue_execute_start", + timerlat_aa_kworker_start_handler, tool); + + return 0; + +out_err: + timerlat_aa_unregister_events(tool, dump_tasks); + return -1; +} + +/** + * timerlat_aa_destroy - Destroy timerlat auto-analysis + */ +void timerlat_aa_destroy(void) +{ + struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx(); + + if (!taa_ctx) + return; + + if (!taa_ctx->taa_data) + goto out_ctx; + + timerlat_aa_unregister_events(taa_ctx->tool, taa_ctx->dump_tasks); + timerlat_aa_destroy_seqs(taa_ctx); + free(taa_ctx->taa_data); +out_ctx: + free(taa_ctx); +} + +/** + * timerlat_aa_init - Initialize timerlat auto-analysis + * + * Returns 0 on success, -1 otherwise. + */ +int timerlat_aa_init(struct osnoise_tool *tool, int nr_cpus, int dump_tasks) +{ + struct timerlat_aa_context *taa_ctx; + int retval; + + taa_ctx = calloc(1, sizeof(*taa_ctx)); + if (!taa_ctx) + return -1; + + __timerlat_aa_ctx = taa_ctx; + + taa_ctx->nr_cpus = nr_cpus; + taa_ctx->tool = tool; + taa_ctx->dump_tasks = dump_tasks; + + taa_ctx->taa_data = calloc(nr_cpus, sizeof(*taa_ctx->taa_data)); + if (!taa_ctx->taa_data) + goto out_err; + + retval = timerlat_aa_init_seqs(taa_ctx); + if (retval) + goto out_err; + + retval = timerlat_aa_register_events(tool, dump_tasks); + if (retval) + goto out_err; + + return 0; + +out_err: + timerlat_aa_destroy(); + return -1; +} diff --git a/tools/tracing/rtla/src/timerlat_aa.h b/tools/tracing/rtla/src/timerlat_aa.h new file mode 100644 index 000000000000..d4f6ca7e342a --- /dev/null +++ b/tools/tracing/rtla/src/timerlat_aa.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org> + */ + +int timerlat_aa_init(struct osnoise_tool *tool, int nr_cpus, int dump_task); +void timerlat_aa_destroy(void); + +int timerlat_aa_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context); + +void timerlat_auto_analysis(int irq_thresh, int thread_thresh); diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 334271935222..eea5b3357e27 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -10,10 +10,12 @@ #include <unistd.h> #include <stdio.h> #include <time.h> +#include <errno.h> #include "utils.h" #include "osnoise.h" #include "timerlat.h" +#include "timerlat_aa.h" struct timerlat_top_params { char *cpus; @@ -30,6 +32,8 @@ struct timerlat_top_params { int quiet; int set_sched; int dma_latency; + int no_aa; + int dump_tasks; struct sched_attr sched_param; struct trace_events *events; }; @@ -130,17 +134,22 @@ timerlat_top_handler(struct trace_seq *s, struct tep_record *record, struct tep_event *event, void *context) { struct trace_instance *trace = context; + struct timerlat_top_params *params; unsigned long long latency, thread; struct osnoise_tool *top; int cpu = record->cpu; top = container_of(trace, struct osnoise_tool, trace); + params = top->params; tep_get_field_val(s, event, "context", record, &thread, 1); tep_get_field_val(s, event, "timer_latency", record, &latency, 1); timerlat_top_update(top, cpu, thread, latency); + if (!params->no_aa) + timerlat_aa_handler(s, record, event, context); + return 0; } @@ -281,11 +290,13 @@ static void timerlat_top_usage(char *usage) " -c/--cpus cpus: run the tracer only on the given cpus", " -d/--duration time[m|h|d]: duration of the session in seconds", " -D/--debug: print debug info", + " --dump-tasks: prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)", " -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", " -e/--event <sys:event>: enable the <sys:event> in the trace instance, multiple -e are allowed", " --filter <command>: enable a trace event filter to the previous -e event", " --trigger <command>: enable a trace event trigger to the previous -e event", " -n/--nano: display data in nanoseconds", + " --no-aa: disable auto-analysis, reducing rtla timerlat cpu usage", " -q/--quiet print only a summary at the end", " --dma-latency us: set /dev/cpu_dma_latency latency <us> to reduce exit from idle latency", " -P/--priority o:prio|r:prio|f:prio|d:runtime:period : set scheduling parameters", @@ -349,13 +360,15 @@ static struct timerlat_top_params {"trigger", required_argument, 0, '0'}, {"filter", required_argument, 0, '1'}, {"dma-latency", required_argument, 0, '2'}, + {"no-aa", no_argument, 0, '3'}, + {"dump-tasks", no_argument, 0, '4'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:", + c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:34", long_options, &option_index); /* detect the end of the options. */ @@ -368,13 +381,13 @@ static struct timerlat_top_params /* set thread stop to auto_thresh */ params->stop_total_us = auto_thresh; + params->stop_us = auto_thresh; /* get stack trace */ params->print_stack = auto_thresh; /* set trace */ params->trace_output = "timerlat_trace.txt"; - break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); @@ -437,6 +450,7 @@ static struct timerlat_top_params params->trace_output = &optarg[1]; else params->trace_output = "timerlat_trace.txt"; + break; case '0': /* trigger */ if (params->events) { @@ -467,6 +481,12 @@ static struct timerlat_top_params exit(EXIT_FAILURE); } break; + case '3': /* no-aa */ + params->no_aa = 1; + break; + case '4': + params->dump_tasks = 1; + break; default: timerlat_top_usage("Invalid option"); } @@ -477,6 +497,12 @@ static struct timerlat_top_params exit(EXIT_FAILURE); } + /* + * Auto analysis only happens if stop tracing, thus: + */ + if (!params->stop_us && !params->stop_total_us) + params->no_aa = 1; + return params; } @@ -547,6 +573,7 @@ static struct osnoise_tool { struct osnoise_tool *top; int nr_cpus; + int retval; nr_cpus = sysconf(_SC_NPROCESSORS_CONF); @@ -563,6 +590,16 @@ static struct osnoise_tool tep_register_event_handler(top->trace.tep, -1, "ftrace", "timerlat", timerlat_top_handler, top); + /* + * If no auto analysis, we are ready. + */ + if (params->no_aa) + return top; + + retval = timerlat_aa_init(top, nr_cpus, params->dump_tasks); + if (retval) + goto out_err; + return top; out_err: @@ -688,6 +725,10 @@ int timerlat_top_main(int argc, char *argv[]) if (trace_is_off(&top->trace, &record->trace)) { printf("rtla timerlat hit stop tracing\n"); + + if (!params->no_aa) + timerlat_auto_analysis(params->stop_us, params->stop_total_us); + if (params->trace_output) { printf(" Saving trace to %s\n", params->trace_output); save_trace_to_file(record->trace.inst, params->trace_output); @@ -701,6 +742,7 @@ out_top: params->events = NULL; out_free: timerlat_free_top(top->data); + timerlat_aa_destroy(); osnoise_destroy_tool(record); osnoise_destroy_tool(top); free(params); diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 5571afd3b549..90e4f52a030b 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -56,3 +56,6 @@ struct sched_attr { int parse_prio(char *arg, struct sched_attr *sched_param); int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr); int set_cpu_dma_latency(int32_t latency); + +#define ns_to_usf(x) (((double)x/1000)) +#define ns_to_per(total, part) ((part * 100) / (double)total) diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c index 50848d79b38b..ad28582bcf2b 100644 --- a/tools/verification/rv/src/in_kernel.c +++ b/tools/verification/rv/src/in_kernel.c @@ -519,7 +519,7 @@ static void ikm_usage_print_reactors(void) start = ++end; end = strstr(start, "\n"); - }; + } fprintf(stderr, "\n"); } diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 1b25cc7c64bb..7b7139d97d74 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -4,7 +4,7 @@ test: virtio_test vringh_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o -CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h +CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h -mfunction-return=thunk -fcf-protection=none -mindirect-branch-register CFLAGS += -pthread LDFLAGS += -pthread vpath %.c ../../drivers/virtio ../../drivers/vhost |